Bump version to 0.9.1

Reviewed-on: https://git.deuxfleurs.fr/Deuxfleurs/garage/pulls/688

.cargo/config.toml

@@ -0,0 +1,3 @@
+[target.x86_64-unknown-linux-gnu]
+linker = "clang"
+rustflags = ["-C", "link-arg=-fuse-ld=mold"]

.drone.yml

@@ -20,6 +20,7 @@ steps:
     image: nixpkgs/nix:nixos-22.05
     environment:
       GARAGE_TEST_INTEGRATION_EXE: result-bin/bin/garage
+      GARAGE_TEST_INTEGRATION_PATH: tmp-garage-integration
     commands:
       - nix-build --no-build-output --attr clippy.amd64 --argstr git_version ${DRONE_TAG:-$DRONE_COMMIT}
       - nix-build --no-build-output --attr test.amd64
@@ -31,8 +32,9 @@ steps:
       - ./result/bin/garage_util-*
       - ./result/bin/garage_web-*
       - ./result/bin/garage-*
-      - ./result/bin/integration-*
+      - ./result/bin/integration-* || (cat tmp-garage-integration/stderr.log; false)
       - rm result
+      - rm -rv tmp-garage-integration
 
   - name: integration tests
     image: nixpkgs/nix:nixos-22.05
@@ -63,11 +65,16 @@ steps:
       - nix-build --no-build-output --attr pkgs.amd64.release --argstr git_version ${DRONE_TAG:-$DRONE_COMMIT}
       - nix-shell --attr rust --run "./script/not-dynamic.sh result-bin/bin/garage"
 
-  - name: integration
+  - name: integration tests
     image: nixpkgs/nix:nixos-22.05
     commands:
       - nix-shell --attr integration --run ./script/test-smoke.sh || (cat /tmp/garage.log; false)
 
+  - name: upgrade tests
+    image: nixpkgs/nix:nixos-22.05
+    commands:
+      - nix-shell --attr integration --run "./script/test-upgrade.sh v0.8.4 x86_64-unknown-linux-musl" || (cat /tmp/garage.log; false)
+
   - name: push static binary
     image: nixpkgs/nix:nixos-22.05
     environment:
@@ -114,11 +121,16 @@ steps:
       - nix-build --no-build-output --attr pkgs.i386.release --argstr git_version ${DRONE_TAG:-$DRONE_COMMIT}
       - nix-shell --attr rust --run "./script/not-dynamic.sh result-bin/bin/garage"
 
-  - name: integration
+  - name: integration tests
     image: nixpkgs/nix:nixos-22.05
     commands:
       - nix-shell --attr integration --run ./script/test-smoke.sh || (cat /tmp/garage.log; false)
 
+  - name: upgrade tests
+    image: nixpkgs/nix:nixos-22.05
+    commands:
+      - nix-shell --attr integration --run "./script/test-upgrade.sh v0.8.4 i686-unknown-linux-musl" || (cat /tmp/garage.log; false)
+
   - name: push static binary
     image: nixpkgs/nix:nixos-22.05
     environment:
@@ -283,6 +295,6 @@ trigger:
 
 ---
 kind: signature
-hmac: ac09a5a8c82502f67271f93afa1e1e21ce66383b8e24a6deb26b285cc1c378ba
+hmac: 0c4b57eb4b27b7c6a6ff21ab87f0767fe3eb90f5d95d5cbcdccf794e9d2a5d86
 
 ...

Cargo.lock

@@ -1198,7 +1198,7 @@ dependencies = [
 
 [[package]]
 name = "garage"
-version = "0.8.5"
+version = "0.9.1"
 dependencies = [
  "assert-json-diff",
  "async-trait",
@@ -1250,7 +1250,7 @@ dependencies = [
 
 [[package]]
 name = "garage_api"
-version = "0.8.5"
+version = "0.9.1"
 dependencies = [
  "async-trait",
  "base64 0.21.3",
@@ -1296,12 +1296,13 @@ dependencies = [
 
 [[package]]
 name = "garage_block"
-version = "0.8.5"
+version = "0.9.1"
 dependencies = [
  "arc-swap",
  "async-compression",
  "async-trait",
  "bytes",
+ "bytesize",
  "futures",
  "futures-util",
  "garage_db",
@@ -1321,7 +1322,7 @@ dependencies = [
 
 [[package]]
 name = "garage_db"
-version = "0.8.5"
+version = "0.9.1"
 dependencies = [
  "clap 4.4.0",
  "err-derive",
@@ -1336,12 +1337,13 @@ dependencies = [
 
 [[package]]
 name = "garage_model"
-version = "0.8.5"
+version = "0.9.1"
 dependencies = [
  "arc-swap",
  "async-trait",
  "base64 0.21.3",
  "blake2",
+ "chrono",
  "err-derive",
  "futures",
  "futures-util",
@@ -1363,18 +1365,21 @@ dependencies = [
 
 [[package]]
 name = "garage_rpc"
-version = "0.8.5"
+version = "0.9.1"
 dependencies = [
  "arc-swap",
  "async-trait",
  "bytes",
+ "bytesize",
  "err-derive",
+ "format_table",
  "futures",
  "futures-util",
  "garage_db",
  "garage_util",
  "gethostname",
  "hex",
+ "itertools 0.10.5",
  "k8s-openapi",
  "kube",
  "kuska-sodiumoxide",
@@ -1395,7 +1400,7 @@ dependencies = [
 
 [[package]]
 name = "garage_table"
-version = "0.8.5"
+version = "0.9.1"
 dependencies = [
  "arc-swap",
  "async-trait",
@@ -1417,7 +1422,7 @@ dependencies = [
 
 [[package]]
 name = "garage_util"
-version = "0.8.5"
+version = "0.9.1"
 dependencies = [
  "arc-swap",
  "async-trait",
@@ -1451,7 +1456,7 @@ dependencies = [
 
 [[package]]
 name = "garage_web"
-version = "0.8.5"
+version = "0.9.1"
 dependencies = [
  "err-derive",
  "futures",
@@ -2284,9 +2289,9 @@ checksum = "e5ce46fe64a9d73be07dcbe690a38ce1b293be448fd8ce1e6c1b8062c9f72c6a"
 
 [[package]]
 name = "netapp"
-version = "0.5.2"
+version = "0.10.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "4ffe47ac46d3b2ce2f736a70865492df082e042eb2bfdddfca3b8dd66bd9469d"
+checksum = "0a00b76cec93e3ae68c9ed5f08e27a1507424987ee23d5ec961ebd4da820a265"
 dependencies = [
  "arc-swap",
  "async-trait",
@@ -3033,9 +3038,9 @@ dependencies = [
 
 [[package]]
 name = "rmp-serde"
-version = "0.15.5"
+version = "1.1.2"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "723ecff9ad04f4ad92fe1c8ca6c20d2196d9286e9c60727c4cb5511629260e9d"
+checksum = "bffea85eea980d8a74453e5d02a8d93028f3c34725de143085a844ebe953258a"
 dependencies = [
  "byteorder",
  "rmp",

Cargo.nix

@@ -7,13 +7,13 @@ args@{
     "garage_db/default"
     "garage_util/default"
     "garage_rpc/default"
+    "format_table/default"
     "garage_table/default"
     "garage_block/default"
     "garage_model/default"
     "garage_api/default"
     "garage_web/default"
     "garage/default"
-    "format_table/default"
     "k2v-client/default"
   ],
   rustPackages,
@@ -33,7 +33,7 @@ args@{
   ignoreLockHash,
 }:
 let
-  nixifiedLockHash = "79d4a9e02f28a0c0f31576781738e132ac96ff4944b3bc2ca7375c6dd15b83ce";
+  nixifiedLockHash = "f8da48e74313b18ee372a07d6a7d63a27c7effde24ed8599dfb91ea311df10f8";
   workspaceSrc = if args.workspaceSrc == null then ./. else args.workspaceSrc;
   currentLockHash = builtins.hashFile "sha256" (workspaceSrc + /Cargo.lock);
   lockHashIgnored = if ignoreLockHash
@@ -57,16 +57,16 @@ in
 {
   cargo2nixVersion = "0.11.0";
   workspace = {
-    garage_db = rustPackages.unknown.garage_db."0.8.5";
-    garage_util = rustPackages.unknown.garage_util."0.8.5";
-    garage_rpc = rustPackages.unknown.garage_rpc."0.8.5";
-    garage_table = rustPackages.unknown.garage_table."0.8.5";
-    garage_block = rustPackages.unknown.garage_block."0.8.5";
-    garage_model = rustPackages.unknown.garage_model."0.8.5";
-    garage_api = rustPackages.unknown.garage_api."0.8.5";
-    garage_web = rustPackages.unknown.garage_web."0.8.5";
-    garage = rustPackages.unknown.garage."0.8.5";
+    garage_db = rustPackages.unknown.garage_db."0.9.1";
+    garage_util = rustPackages.unknown.garage_util."0.9.1";
+    garage_rpc = rustPackages.unknown.garage_rpc."0.9.1";
     format_table = rustPackages.unknown.format_table."0.1.1";
+    garage_table = rustPackages.unknown.garage_table."0.9.1";
+    garage_block = rustPackages.unknown.garage_block."0.9.1";
+    garage_model = rustPackages.unknown.garage_model."0.9.1";
+    garage_api = rustPackages.unknown.garage_api."0.9.1";
+    garage_web = rustPackages.unknown.garage_web."0.9.1";
+    garage = rustPackages.unknown.garage."0.9.1";
     k2v-client = rustPackages.unknown.k2v-client."0.0.4";
   };
   "registry+https://github.com/rust-lang/crates.io-index".addr2line."0.21.0" = overridableMkRustCrate (profileName: rec {
@@ -98,12 +98,12 @@ in
       (lib.optional (rootFeatures' ? "garage/kubernetes-discovery" || rootFeatures' ? "garage_rpc/kube" || rootFeatures' ? "garage_rpc/kubernetes-discovery") "std")
     ];
     dependencies = {
-      ${ if rootFeatures' ? "garage/bundled-libs" || rootFeatures' ? "garage/default" || rootFeatures' ? "garage/kubernetes-discovery" || rootFeatures' ? "garage/sqlite" || rootFeatures' ? "garage_db/bundled-libs" || rootFeatures' ? "garage_db/rusqlite" || rootFeatures' ? "garage_db/sqlite" || rootFeatures' ? "garage_model/sqlite" || rootFeatures' ? "garage_rpc/kube" || rootFeatures' ? "garage_rpc/kubernetes-discovery" then "cfg_if" else null } = (rustPackages."registry+https://github.com/rust-lang/crates.io-index".cfg-if."1.0.0" { inherit profileName; }).out;
+      ${ if rootFeatures' ? "garage/bundled-libs" || rootFeatures' ? "garage/default" || rootFeatures' ? "garage/kubernetes-discovery" || rootFeatures' ? "garage/sqlite" || rootFeatures' ? "garage_db/bundled-libs" || rootFeatures' ? "garage_db/default" || rootFeatures' ? "garage_db/rusqlite" || rootFeatures' ? "garage_db/sqlite" || rootFeatures' ? "garage_model/default" || rootFeatures' ? "garage_model/sqlite" || rootFeatures' ? "garage_rpc/kube" || rootFeatures' ? "garage_rpc/kubernetes-discovery" then "cfg_if" else null } = (rustPackages."registry+https://github.com/rust-lang/crates.io-index".cfg-if."1.0.0" { inherit profileName; }).out;
       ${ if rootFeatures' ? "garage/kubernetes-discovery" || rootFeatures' ? "garage_rpc/kube" || rootFeatures' ? "garage_rpc/kubernetes-discovery" then "getrandom" else null } = (rustPackages."registry+https://github.com/rust-lang/crates.io-index".getrandom."0.2.10" { inherit profileName; }).out;
-      ${ if (rootFeatures' ? "garage/bundled-libs" || rootFeatures' ? "garage/default" || rootFeatures' ? "garage/kubernetes-discovery" || rootFeatures' ? "garage/sqlite" || rootFeatures' ? "garage_db/bundled-libs" || rootFeatures' ? "garage_db/rusqlite" || rootFeatures' ? "garage_db/sqlite" || rootFeatures' ? "garage_model/sqlite" || rootFeatures' ? "garage_rpc/kube" || rootFeatures' ? "garage_rpc/kubernetes-discovery") && !((hostPlatform.parsed.cpu.name == "armv6l" || hostPlatform.parsed.cpu.name == "armv7l") && hostPlatform.parsed.kernel.name == "none") then "once_cell" else null } = (rustPackages."registry+https://github.com/rust-lang/crates.io-index".once_cell."1.18.0" { inherit profileName; }).out;
+      ${ if (rootFeatures' ? "garage/bundled-libs" || rootFeatures' ? "garage/default" || rootFeatures' ? "garage/kubernetes-discovery" || rootFeatures' ? "garage/sqlite" || rootFeatures' ? "garage_db/bundled-libs" || rootFeatures' ? "garage_db/default" || rootFeatures' ? "garage_db/rusqlite" || rootFeatures' ? "garage_db/sqlite" || rootFeatures' ? "garage_model/default" || rootFeatures' ? "garage_model/sqlite" || rootFeatures' ? "garage_rpc/kube" || rootFeatures' ? "garage_rpc/kubernetes-discovery") && !((hostPlatform.parsed.cpu.name == "armv6l" || hostPlatform.parsed.cpu.name == "armv7l") && hostPlatform.parsed.kernel.name == "none") then "once_cell" else null } = (rustPackages."registry+https://github.com/rust-lang/crates.io-index".once_cell."1.18.0" { inherit profileName; }).out;
     };
     buildDependencies = {
-      ${ if rootFeatures' ? "garage/bundled-libs" || rootFeatures' ? "garage/default" || rootFeatures' ? "garage/kubernetes-discovery" || rootFeatures' ? "garage/sqlite" || rootFeatures' ? "garage_db/bundled-libs" || rootFeatures' ? "garage_db/rusqlite" || rootFeatures' ? "garage_db/sqlite" || rootFeatures' ? "garage_model/sqlite" || rootFeatures' ? "garage_rpc/kube" || rootFeatures' ? "garage_rpc/kubernetes-discovery" then "version_check" else null } = (buildRustPackages."registry+https://github.com/rust-lang/crates.io-index".version_check."0.9.4" { profileName = "__noProfile"; }).out;
+      ${ if rootFeatures' ? "garage/bundled-libs" || rootFeatures' ? "garage/default" || rootFeatures' ? "garage/kubernetes-discovery" || rootFeatures' ? "garage/sqlite" || rootFeatures' ? "garage_db/bundled-libs" || rootFeatures' ? "garage_db/default" || rootFeatures' ? "garage_db/rusqlite" || rootFeatures' ? "garage_db/sqlite" || rootFeatures' ? "garage_model/default" || rootFeatures' ? "garage_model/sqlite" || rootFeatures' ? "garage_rpc/kube" || rootFeatures' ? "garage_rpc/kubernetes-discovery" then "version_check" else null } = (buildRustPackages."registry+https://github.com/rust-lang/crates.io-index".version_check."0.9.4" { profileName = "__noProfile"; }).out;
     };
   });
   
@@ -128,7 +128,7 @@ in
     registry = "registry+https://github.com/rust-lang/crates.io-index";
     src = fetchCratesIo { inherit name version; sha256 = "0942ffc6dcaadf03badf6e6a2d0228460359d5e34b57ccdc720b7382dfbd5ec5"; };
     features = builtins.concatLists [
-      (lib.optional (rootFeatures' ? "garage/bundled-libs" || rootFeatures' ? "garage/default" || rootFeatures' ? "garage/sqlite" || rootFeatures' ? "garage_db/bundled-libs" || rootFeatures' ? "garage_db/rusqlite" || rootFeatures' ? "garage_db/sqlite" || rootFeatures' ? "garage_model/sqlite") "alloc")
+      (lib.optional (rootFeatures' ? "garage/bundled-libs" || rootFeatures' ? "garage/default" || rootFeatures' ? "garage/sqlite" || rootFeatures' ? "garage_db/bundled-libs" || rootFeatures' ? "garage_db/default" || rootFeatures' ? "garage_db/rusqlite" || rootFeatures' ? "garage_db/sqlite" || rootFeatures' ? "garage_model/default" || rootFeatures' ? "garage_model/sqlite") "alloc")
     ];
   });
   
@@ -824,7 +824,7 @@ in
     registry = "registry+https://github.com/rust-lang/crates.io-index";
     src = fetchCratesIo { inherit name version; sha256 = "b1f45e9417d87227c7a56d22e471c6206462cba514c7590c09aff4cf6d1ddcad"; };
     dependencies = {
-      ${ if rootFeatures' ? "garage/lmdb" || rootFeatures' ? "garage_db/heed" || rootFeatures' ? "garage_db/lmdb" || rootFeatures' ? "garage_model/lmdb" then "serde" else null } = (rustPackages."registry+https://github.com/rust-lang/crates.io-index".serde."1.0.188" { inherit profileName; }).out;
+      ${ if rootFeatures' ? "garage/default" || rootFeatures' ? "garage/lmdb" || rootFeatures' ? "garage_db/default" || rootFeatures' ? "garage_db/heed" || rootFeatures' ? "garage_db/lmdb" || rootFeatures' ? "garage_model/default" || rootFeatures' ? "garage_model/lmdb" then "serde" else null } = (rustPackages."registry+https://github.com/rust-lang/crates.io-index".serde."1.0.188" { inherit profileName; }).out;
     };
   });
   
@@ -888,8 +888,8 @@ in
     registry = "registry+https://github.com/rust-lang/crates.io-index";
     src = fetchCratesIo { inherit name version; sha256 = "17febce684fd15d89027105661fec94afb475cb995fbc59d2865198446ba2eea"; };
     features = builtins.concatLists [
-      (lib.optional (rootFeatures' ? "garage/lmdb" || rootFeatures' ? "garage_db/heed" || rootFeatures' ? "garage_db/lmdb" || rootFeatures' ? "garage_model/lmdb") "extern_crate_alloc")
-      (lib.optional (rootFeatures' ? "garage/lmdb" || rootFeatures' ? "garage_db/heed" || rootFeatures' ? "garage_db/lmdb" || rootFeatures' ? "garage_model/lmdb") "extern_crate_std")
+      (lib.optional (rootFeatures' ? "garage/default" || rootFeatures' ? "garage/lmdb" || rootFeatures' ? "garage_db/default" || rootFeatures' ? "garage_db/heed" || rootFeatures' ? "garage_db/lmdb" || rootFeatures' ? "garage_model/default" || rootFeatures' ? "garage_model/lmdb") "extern_crate_alloc")
+      (lib.optional (rootFeatures' ? "garage/default" || rootFeatures' ? "garage/lmdb" || rootFeatures' ? "garage_db/default" || rootFeatures' ? "garage_db/heed" || rootFeatures' ? "garage_db/lmdb" || rootFeatures' ? "garage_model/default" || rootFeatures' ? "garage_model/lmdb") "extern_crate_std")
     ];
   });
   
@@ -1182,13 +1182,13 @@ in
     registry = "registry+https://github.com/rust-lang/crates.io-index";
     src = fetchCratesIo { inherit name version; sha256 = "d1cfb3ea8a53f37c40dea2c7bedcbd88bdfae54f5e2175d6ecaff1c988353add"; };
     features = builtins.concatLists [
-      (lib.optional (rootFeatures' ? "garage/lmdb" || rootFeatures' ? "garage_db/heed" || rootFeatures' ? "garage_db/lmdb" || rootFeatures' ? "garage_model/lmdb") "alloc")
-      (lib.optional (rootFeatures' ? "garage/lmdb" || rootFeatures' ? "garage_db/heed" || rootFeatures' ? "garage_db/lmdb" || rootFeatures' ? "garage_model/lmdb") "default")
-      (lib.optional (rootFeatures' ? "garage/lmdb" || rootFeatures' ? "garage_db/heed" || rootFeatures' ? "garage_db/lmdb" || rootFeatures' ? "garage_model/lmdb") "std")
+      (lib.optional (rootFeatures' ? "garage/default" || rootFeatures' ? "garage/lmdb" || rootFeatures' ? "garage_db/default" || rootFeatures' ? "garage_db/heed" || rootFeatures' ? "garage_db/lmdb" || rootFeatures' ? "garage_model/default" || rootFeatures' ? "garage_model/lmdb") "alloc")
+      (lib.optional (rootFeatures' ? "garage/default" || rootFeatures' ? "garage/lmdb" || rootFeatures' ? "garage_db/default" || rootFeatures' ? "garage_db/heed" || rootFeatures' ? "garage_db/lmdb" || rootFeatures' ? "garage_model/default" || rootFeatures' ? "garage_model/lmdb") "default")
+      (lib.optional (rootFeatures' ? "garage/default" || rootFeatures' ? "garage/lmdb" || rootFeatures' ? "garage_db/default" || rootFeatures' ? "garage_db/heed" || rootFeatures' ? "garage_db/lmdb" || rootFeatures' ? "garage_model/default" || rootFeatures' ? "garage_model/lmdb") "std")
     ];
     dependencies = {
-      ${ if rootFeatures' ? "garage/lmdb" || rootFeatures' ? "garage_db/heed" || rootFeatures' ? "garage_db/lmdb" || rootFeatures' ? "garage_model/lmdb" then "cfg_if" else null } = (rustPackages."registry+https://github.com/rust-lang/crates.io-index".cfg-if."1.0.0" { inherit profileName; }).out;
-      ${ if rootFeatures' ? "garage/lmdb" || rootFeatures' ? "garage_db/heed" || rootFeatures' ? "garage_db/lmdb" || rootFeatures' ? "garage_model/lmdb" then "crossbeam_utils" else null } = (rustPackages."registry+https://github.com/rust-lang/crates.io-index".crossbeam-utils."0.8.16" { inherit profileName; }).out;
+      ${ if rootFeatures' ? "garage/default" || rootFeatures' ? "garage/lmdb" || rootFeatures' ? "garage_db/default" || rootFeatures' ? "garage_db/heed" || rootFeatures' ? "garage_db/lmdb" || rootFeatures' ? "garage_model/default" || rootFeatures' ? "garage_model/lmdb" then "cfg_if" else null } = (rustPackages."registry+https://github.com/rust-lang/crates.io-index".cfg-if."1.0.0" { inherit profileName; }).out;
+      ${ if rootFeatures' ? "garage/default" || rootFeatures' ? "garage/lmdb" || rootFeatures' ? "garage_db/default" || rootFeatures' ? "garage_db/heed" || rootFeatures' ? "garage_db/lmdb" || rootFeatures' ? "garage_model/default" || rootFeatures' ? "garage_model/lmdb" then "crossbeam_utils" else null } = (rustPackages."registry+https://github.com/rust-lang/crates.io-index".crossbeam-utils."0.8.16" { inherit profileName; }).out;
     };
   });
   
@@ -1459,8 +1459,8 @@ in
     registry = "registry+https://github.com/rust-lang/crates.io-index";
     src = fetchCratesIo { inherit name version; sha256 = "4443176a9f2c162692bd3d352d745ef9413eec5782a80d8fd6f8a1ac692a07f7"; };
     features = builtins.concatLists [
-      (lib.optional (rootFeatures' ? "garage/bundled-libs" || rootFeatures' ? "garage/default" || rootFeatures' ? "garage/sqlite" || rootFeatures' ? "garage_db/bundled-libs" || rootFeatures' ? "garage_db/rusqlite" || rootFeatures' ? "garage_db/sqlite" || rootFeatures' ? "garage_model/sqlite") "default")
-      (lib.optional (rootFeatures' ? "garage/bundled-libs" || rootFeatures' ? "garage/default" || rootFeatures' ? "garage/sqlite" || rootFeatures' ? "garage_db/bundled-libs" || rootFeatures' ? "garage_db/rusqlite" || rootFeatures' ? "garage_db/sqlite" || rootFeatures' ? "garage_model/sqlite") "std")
+      (lib.optional (rootFeatures' ? "garage/bundled-libs" || rootFeatures' ? "garage/default" || rootFeatures' ? "garage/sqlite" || rootFeatures' ? "garage_db/bundled-libs" || rootFeatures' ? "garage_db/default" || rootFeatures' ? "garage_db/rusqlite" || rootFeatures' ? "garage_db/sqlite" || rootFeatures' ? "garage_model/default" || rootFeatures' ? "garage_model/sqlite") "default")
+      (lib.optional (rootFeatures' ? "garage/bundled-libs" || rootFeatures' ? "garage/default" || rootFeatures' ? "garage/sqlite" || rootFeatures' ? "garage_db/bundled-libs" || rootFeatures' ? "garage_db/default" || rootFeatures' ? "garage_db/rusqlite" || rootFeatures' ? "garage_db/sqlite" || rootFeatures' ? "garage_model/default" || rootFeatures' ? "garage_model/sqlite") "std")
     ];
   });
   
@@ -1705,9 +1705,9 @@ in
     };
   });
   
-  "unknown".garage."0.8.5" = overridableMkRustCrate (profileName: rec {
+  "unknown".garage."0.9.1" = overridableMkRustCrate (profileName: rec {
     name = "garage";
-    version = "0.8.5";
+    version = "0.9.1";
     registry = "unknown";
     src = fetchCrateLocal (workspaceSrc + "/src/garage");
     features = builtins.concatLists [
@@ -1716,13 +1716,13 @@ in
       (lib.optional (rootFeatures' ? "garage/default") "default")
       (lib.optional (rootFeatures' ? "garage/default" || rootFeatures' ? "garage/k2v") "k2v")
       (lib.optional (rootFeatures' ? "garage/kubernetes-discovery") "kubernetes-discovery")
-      (lib.optional (rootFeatures' ? "garage/lmdb") "lmdb")
+      (lib.optional (rootFeatures' ? "garage/default" || rootFeatures' ? "garage/lmdb") "lmdb")
       (lib.optional (rootFeatures' ? "garage/default" || rootFeatures' ? "garage/metrics") "metrics")
       (lib.optional (rootFeatures' ? "garage/opentelemetry-otlp" || rootFeatures' ? "garage/telemetry-otlp") "opentelemetry-otlp")
       (lib.optional (rootFeatures' ? "garage/default" || rootFeatures' ? "garage/metrics" || rootFeatures' ? "garage/opentelemetry-prometheus") "opentelemetry-prometheus")
       (lib.optional (rootFeatures' ? "garage/default" || rootFeatures' ? "garage/metrics" || rootFeatures' ? "garage/prometheus") "prometheus")
       (lib.optional (rootFeatures' ? "garage/default" || rootFeatures' ? "garage/sled") "sled")
-      (lib.optional (rootFeatures' ? "garage/sqlite") "sqlite")
+      (lib.optional (rootFeatures' ? "garage/default" || rootFeatures' ? "garage/sqlite") "sqlite")
       (lib.optional (rootFeatures' ? "garage/system-libs") "system-libs")
       (lib.optional (rootFeatures' ? "garage/telemetry-otlp") "telemetry-otlp")
     ];
@@ -1734,18 +1734,18 @@ in
       format_table = (rustPackages."unknown".format_table."0.1.1" { inherit profileName; }).out;
       futures = (rustPackages."registry+https://github.com/rust-lang/crates.io-index".futures."0.3.28" { inherit profileName; }).out;
       futures_util = (rustPackages."registry+https://github.com/rust-lang/crates.io-index".futures-util."0.3.28" { inherit profileName; }).out;
-      garage_api = (rustPackages."unknown".garage_api."0.8.5" { inherit profileName; }).out;
-      garage_block = (rustPackages."unknown".garage_block."0.8.5" { inherit profileName; }).out;
-      garage_db = (rustPackages."unknown".garage_db."0.8.5" { inherit profileName; }).out;
-      garage_model = (rustPackages."unknown".garage_model."0.8.5" { inherit profileName; }).out;
-      garage_rpc = (rustPackages."unknown".garage_rpc."0.8.5" { inherit profileName; }).out;
-      garage_table = (rustPackages."unknown".garage_table."0.8.5" { inherit profileName; }).out;
-      garage_util = (rustPackages."unknown".garage_util."0.8.5" { inherit profileName; }).out;
-      garage_web = (rustPackages."unknown".garage_web."0.8.5" { inherit profileName; }).out;
+      garage_api = (rustPackages."unknown".garage_api."0.9.1" { inherit profileName; }).out;
+      garage_block = (rustPackages."unknown".garage_block."0.9.1" { inherit profileName; }).out;
+      garage_db = (rustPackages."unknown".garage_db."0.9.1" { inherit profileName; }).out;
+      garage_model = (rustPackages."unknown".garage_model."0.9.1" { inherit profileName; }).out;
+      garage_rpc = (rustPackages."unknown".garage_rpc."0.9.1" { inherit profileName; }).out;
+      garage_table = (rustPackages."unknown".garage_table."0.9.1" { inherit profileName; }).out;
+      garage_util = (rustPackages."unknown".garage_util."0.9.1" { inherit profileName; }).out;
+      garage_web = (rustPackages."unknown".garage_web."0.9.1" { inherit profileName; }).out;
       git_version = (rustPackages."registry+https://github.com/rust-lang/crates.io-index".git-version."0.3.5" { inherit profileName; }).out;
       hex = (rustPackages."registry+https://github.com/rust-lang/crates.io-index".hex."0.4.3" { inherit profileName; }).out;
       sodiumoxide = (rustPackages."registry+https://github.com/rust-lang/crates.io-index".kuska-sodiumoxide."0.2.5-0" { inherit profileName; }).out;
-      netapp = (rustPackages."registry+https://github.com/rust-lang/crates.io-index".netapp."0.5.2" { inherit profileName; }).out;
+      netapp = (rustPackages."registry+https://github.com/rust-lang/crates.io-index".netapp."0.10.0" { inherit profileName; }).out;
       opentelemetry = (rustPackages."registry+https://github.com/rust-lang/crates.io-index".opentelemetry."0.17.0" { inherit profileName; }).out;
       ${ if rootFeatures' ? "garage/opentelemetry-otlp" || rootFeatures' ? "garage/telemetry-otlp" then "opentelemetry_otlp" else null } = (rustPackages."registry+https://github.com/rust-lang/crates.io-index".opentelemetry-otlp."0.10.0" { inherit profileName; }).out;
       ${ if rootFeatures' ? "garage/default" || rootFeatures' ? "garage/metrics" || rootFeatures' ? "garage/opentelemetry-prometheus" then "opentelemetry_prometheus" else null } = (rustPackages."registry+https://github.com/rust-lang/crates.io-index".opentelemetry-prometheus."0.10.0" { inherit profileName; }).out;
@@ -1778,9 +1778,9 @@ in
     };
   });
   
-  "unknown".garage_api."0.8.5" = overridableMkRustCrate (profileName: rec {
+  "unknown".garage_api."0.9.1" = overridableMkRustCrate (profileName: rec {
     name = "garage_api";
-    version = "0.8.5";
+    version = "0.9.1";
     registry = "unknown";
     src = fetchCrateLocal (workspaceSrc + "/src/api");
     features = builtins.concatLists [
@@ -1799,11 +1799,11 @@ in
       form_urlencoded = (rustPackages."registry+https://github.com/rust-lang/crates.io-index".form_urlencoded."1.2.0" { inherit profileName; }).out;
       futures = (rustPackages."registry+https://github.com/rust-lang/crates.io-index".futures."0.3.28" { inherit profileName; }).out;
       futures_util = (rustPackages."registry+https://github.com/rust-lang/crates.io-index".futures-util."0.3.28" { inherit profileName; }).out;
-      garage_block = (rustPackages."unknown".garage_block."0.8.5" { inherit profileName; }).out;
-      garage_model = (rustPackages."unknown".garage_model."0.8.5" { inherit profileName; }).out;
-      garage_rpc = (rustPackages."unknown".garage_rpc."0.8.5" { inherit profileName; }).out;
-      garage_table = (rustPackages."unknown".garage_table."0.8.5" { inherit profileName; }).out;
-      garage_util = (rustPackages."unknown".garage_util."0.8.5" { inherit profileName; }).out;
+      garage_block = (rustPackages."unknown".garage_block."0.9.1" { inherit profileName; }).out;
+      garage_model = (rustPackages."unknown".garage_model."0.9.1" { inherit profileName; }).out;
+      garage_rpc = (rustPackages."unknown".garage_rpc."0.9.1" { inherit profileName; }).out;
+      garage_table = (rustPackages."unknown".garage_table."0.9.1" { inherit profileName; }).out;
+      garage_util = (rustPackages."unknown".garage_util."0.9.1" { inherit profileName; }).out;
       hex = (rustPackages."registry+https://github.com/rust-lang/crates.io-index".hex."0.4.3" { inherit profileName; }).out;
       hmac = (rustPackages."registry+https://github.com/rust-lang/crates.io-index".hmac."0.12.1" { inherit profileName; }).out;
       http = (rustPackages."registry+https://github.com/rust-lang/crates.io-index".http."0.2.9" { inherit profileName; }).out;
@@ -1833,9 +1833,9 @@ in
     };
   });
   
-  "unknown".garage_block."0.8.5" = overridableMkRustCrate (profileName: rec {
+  "unknown".garage_block."0.9.1" = overridableMkRustCrate (profileName: rec {
     name = "garage_block";
-    version = "0.8.5";
+    version = "0.9.1";
     registry = "unknown";
     src = fetchCrateLocal (workspaceSrc + "/src/block");
     features = builtins.concatLists [
@@ -1846,12 +1846,13 @@ in
       async_compression = (rustPackages."registry+https://github.com/rust-lang/crates.io-index".async-compression."0.4.1" { inherit profileName; }).out;
       async_trait = (buildRustPackages."registry+https://github.com/rust-lang/crates.io-index".async-trait."0.1.73" { profileName = "__noProfile"; }).out;
       bytes = (rustPackages."registry+https://github.com/rust-lang/crates.io-index".bytes."1.4.0" { inherit profileName; }).out;
+      bytesize = (rustPackages."registry+https://github.com/rust-lang/crates.io-index".bytesize."1.3.0" { inherit profileName; }).out;
       futures = (rustPackages."registry+https://github.com/rust-lang/crates.io-index".futures."0.3.28" { inherit profileName; }).out;
       futures_util = (rustPackages."registry+https://github.com/rust-lang/crates.io-index".futures-util."0.3.28" { inherit profileName; }).out;
-      garage_db = (rustPackages."unknown".garage_db."0.8.5" { inherit profileName; }).out;
-      garage_rpc = (rustPackages."unknown".garage_rpc."0.8.5" { inherit profileName; }).out;
-      garage_table = (rustPackages."unknown".garage_table."0.8.5" { inherit profileName; }).out;
-      garage_util = (rustPackages."unknown".garage_util."0.8.5" { inherit profileName; }).out;
+      garage_db = (rustPackages."unknown".garage_db."0.9.1" { inherit profileName; }).out;
+      garage_rpc = (rustPackages."unknown".garage_rpc."0.9.1" { inherit profileName; }).out;
+      garage_table = (rustPackages."unknown".garage_table."0.9.1" { inherit profileName; }).out;
+      garage_util = (rustPackages."unknown".garage_util."0.9.1" { inherit profileName; }).out;
       hex = (rustPackages."registry+https://github.com/rust-lang/crates.io-index".hex."0.4.3" { inherit profileName; }).out;
       opentelemetry = (rustPackages."registry+https://github.com/rust-lang/crates.io-index".opentelemetry."0.17.0" { inherit profileName; }).out;
       rand = (rustPackages."registry+https://github.com/rust-lang/crates.io-index".rand."0.8.5" { inherit profileName; }).out;
@@ -1864,9 +1865,9 @@ in
     };
   });
   
-  "unknown".garage_db."0.8.5" = overridableMkRustCrate (profileName: rec {
+  "unknown".garage_db."0.9.1" = overridableMkRustCrate (profileName: rec {
     name = "garage_db";
-    version = "0.8.5";
+    version = "0.9.1";
     registry = "unknown";
     src = fetchCrateLocal (workspaceSrc + "/src/db");
     features = builtins.concatLists [
@@ -1874,20 +1875,20 @@ in
       (lib.optional (rootFeatures' ? "garage_db/clap" || rootFeatures' ? "garage_db/cli") "clap")
       (lib.optional (rootFeatures' ? "garage_db/cli") "cli")
       (lib.optional (rootFeatures' ? "garage_db/default") "default")
-      (lib.optional (rootFeatures' ? "garage/lmdb" || rootFeatures' ? "garage_db/heed" || rootFeatures' ? "garage_db/lmdb" || rootFeatures' ? "garage_model/lmdb") "heed")
-      (lib.optional (rootFeatures' ? "garage/lmdb" || rootFeatures' ? "garage_db/lmdb" || rootFeatures' ? "garage_model/lmdb") "lmdb")
+      (lib.optional (rootFeatures' ? "garage/default" || rootFeatures' ? "garage/lmdb" || rootFeatures' ? "garage_db/default" || rootFeatures' ? "garage_db/heed" || rootFeatures' ? "garage_db/lmdb" || rootFeatures' ? "garage_model/default" || rootFeatures' ? "garage_model/lmdb") "heed")
+      (lib.optional (rootFeatures' ? "garage/default" || rootFeatures' ? "garage/lmdb" || rootFeatures' ? "garage_db/default" || rootFeatures' ? "garage_db/lmdb" || rootFeatures' ? "garage_model/default" || rootFeatures' ? "garage_model/lmdb") "lmdb")
       (lib.optional (rootFeatures' ? "garage_db/cli" || rootFeatures' ? "garage_db/pretty_env_logger") "pretty_env_logger")
-      (lib.optional (rootFeatures' ? "garage/sqlite" || rootFeatures' ? "garage_db/rusqlite" || rootFeatures' ? "garage_db/sqlite" || rootFeatures' ? "garage_model/sqlite") "rusqlite")
+      (lib.optional (rootFeatures' ? "garage/default" || rootFeatures' ? "garage/sqlite" || rootFeatures' ? "garage_db/default" || rootFeatures' ? "garage_db/rusqlite" || rootFeatures' ? "garage_db/sqlite" || rootFeatures' ? "garage_model/default" || rootFeatures' ? "garage_model/sqlite") "rusqlite")
       (lib.optional (rootFeatures' ? "garage/default" || rootFeatures' ? "garage/sled" || rootFeatures' ? "garage_db/default" || rootFeatures' ? "garage_db/sled" || rootFeatures' ? "garage_model/default" || rootFeatures' ? "garage_model/sled") "sled")
-      (lib.optional (rootFeatures' ? "garage/sqlite" || rootFeatures' ? "garage_db/sqlite" || rootFeatures' ? "garage_model/sqlite") "sqlite")
+      (lib.optional (rootFeatures' ? "garage/default" || rootFeatures' ? "garage/sqlite" || rootFeatures' ? "garage_db/default" || rootFeatures' ? "garage_db/sqlite" || rootFeatures' ? "garage_model/default" || rootFeatures' ? "garage_model/sqlite") "sqlite")
     ];
     dependencies = {
       ${ if rootFeatures' ? "garage_db/clap" || rootFeatures' ? "garage_db/cli" then "clap" else null } = (rustPackages."registry+https://github.com/rust-lang/crates.io-index".clap."4.4.0" { inherit profileName; }).out;
       err_derive = (buildRustPackages."registry+https://github.com/rust-lang/crates.io-index".err-derive."0.3.1" { profileName = "__noProfile"; }).out;
-      ${ if rootFeatures' ? "garage/lmdb" || rootFeatures' ? "garage_db/heed" || rootFeatures' ? "garage_db/lmdb" || rootFeatures' ? "garage_model/lmdb" then "heed" else null } = (rustPackages."registry+https://github.com/rust-lang/crates.io-index".heed."0.11.0" { inherit profileName; }).out;
+      ${ if rootFeatures' ? "garage/default" || rootFeatures' ? "garage/lmdb" || rootFeatures' ? "garage_db/default" || rootFeatures' ? "garage_db/heed" || rootFeatures' ? "garage_db/lmdb" || rootFeatures' ? "garage_model/default" || rootFeatures' ? "garage_model/lmdb" then "heed" else null } = (rustPackages."registry+https://github.com/rust-lang/crates.io-index".heed."0.11.0" { inherit profileName; }).out;
       hexdump = (rustPackages."registry+https://github.com/rust-lang/crates.io-index".hexdump."0.1.1" { inherit profileName; }).out;
       ${ if rootFeatures' ? "garage_db/cli" || rootFeatures' ? "garage_db/pretty_env_logger" then "pretty_env_logger" else null } = (rustPackages."registry+https://github.com/rust-lang/crates.io-index".pretty_env_logger."0.5.0" { inherit profileName; }).out;
-      ${ if rootFeatures' ? "garage/bundled-libs" || rootFeatures' ? "garage/default" || rootFeatures' ? "garage/sqlite" || rootFeatures' ? "garage_db/bundled-libs" || rootFeatures' ? "garage_db/rusqlite" || rootFeatures' ? "garage_db/sqlite" || rootFeatures' ? "garage_model/sqlite" then "rusqlite" else null } = (rustPackages."registry+https://github.com/rust-lang/crates.io-index".rusqlite."0.29.0" { inherit profileName; }).out;
+      ${ if rootFeatures' ? "garage/bundled-libs" || rootFeatures' ? "garage/default" || rootFeatures' ? "garage/sqlite" || rootFeatures' ? "garage_db/bundled-libs" || rootFeatures' ? "garage_db/default" || rootFeatures' ? "garage_db/rusqlite" || rootFeatures' ? "garage_db/sqlite" || rootFeatures' ? "garage_model/default" || rootFeatures' ? "garage_model/sqlite" then "rusqlite" else null } = (rustPackages."registry+https://github.com/rust-lang/crates.io-index".rusqlite."0.29.0" { inherit profileName; }).out;
       ${ if rootFeatures' ? "garage/default" || rootFeatures' ? "garage/sled" || rootFeatures' ? "garage_db/default" || rootFeatures' ? "garage_db/sled" || rootFeatures' ? "garage_model/default" || rootFeatures' ? "garage_model/sled" then "sled" else null } = (rustPackages."registry+https://github.com/rust-lang/crates.io-index".sled."0.34.7" { inherit profileName; }).out;
       tracing = (rustPackages."registry+https://github.com/rust-lang/crates.io-index".tracing."0.1.37" { inherit profileName; }).out;
     };
@@ -1896,33 +1897,34 @@ in
     };
   });
   
-  "unknown".garage_model."0.8.5" = overridableMkRustCrate (profileName: rec {
+  "unknown".garage_model."0.9.1" = overridableMkRustCrate (profileName: rec {
     name = "garage_model";
-    version = "0.8.5";
+    version = "0.9.1";
     registry = "unknown";
     src = fetchCrateLocal (workspaceSrc + "/src/model");
     features = builtins.concatLists [
       (lib.optional (rootFeatures' ? "garage_model/default") "default")
       (lib.optional (rootFeatures' ? "garage/default" || rootFeatures' ? "garage/k2v" || rootFeatures' ? "garage_api/k2v" || rootFeatures' ? "garage_model/k2v") "k2v")
-      (lib.optional (rootFeatures' ? "garage/lmdb" || rootFeatures' ? "garage_model/lmdb") "lmdb")
+      (lib.optional (rootFeatures' ? "garage/default" || rootFeatures' ? "garage/lmdb" || rootFeatures' ? "garage_model/default" || rootFeatures' ? "garage_model/lmdb") "lmdb")
       (lib.optional (rootFeatures' ? "garage/default" || rootFeatures' ? "garage/sled" || rootFeatures' ? "garage_model/default" || rootFeatures' ? "garage_model/sled") "sled")
-      (lib.optional (rootFeatures' ? "garage/sqlite" || rootFeatures' ? "garage_model/sqlite") "sqlite")
+      (lib.optional (rootFeatures' ? "garage/default" || rootFeatures' ? "garage/sqlite" || rootFeatures' ? "garage_model/default" || rootFeatures' ? "garage_model/sqlite") "sqlite")
     ];
     dependencies = {
       arc_swap = (rustPackages."registry+https://github.com/rust-lang/crates.io-index".arc-swap."1.6.0" { inherit profileName; }).out;
       async_trait = (buildRustPackages."registry+https://github.com/rust-lang/crates.io-index".async-trait."0.1.73" { profileName = "__noProfile"; }).out;
       base64 = (rustPackages."registry+https://github.com/rust-lang/crates.io-index".base64."0.21.3" { inherit profileName; }).out;
       blake2 = (rustPackages."registry+https://github.com/rust-lang/crates.io-index".blake2."0.10.6" { inherit profileName; }).out;
+      chrono = (rustPackages."registry+https://github.com/rust-lang/crates.io-index".chrono."0.4.26" { inherit profileName; }).out;
       err_derive = (buildRustPackages."registry+https://github.com/rust-lang/crates.io-index".err-derive."0.3.1" { profileName = "__noProfile"; }).out;
       futures = (rustPackages."registry+https://github.com/rust-lang/crates.io-index".futures."0.3.28" { inherit profileName; }).out;
       futures_util = (rustPackages."registry+https://github.com/rust-lang/crates.io-index".futures-util."0.3.28" { inherit profileName; }).out;
-      garage_block = (rustPackages."unknown".garage_block."0.8.5" { inherit profileName; }).out;
-      garage_db = (rustPackages."unknown".garage_db."0.8.5" { inherit profileName; }).out;
-      garage_rpc = (rustPackages."unknown".garage_rpc."0.8.5" { inherit profileName; }).out;
-      garage_table = (rustPackages."unknown".garage_table."0.8.5" { inherit profileName; }).out;
-      garage_util = (rustPackages."unknown".garage_util."0.8.5" { inherit profileName; }).out;
+      garage_block = (rustPackages."unknown".garage_block."0.9.1" { inherit profileName; }).out;
+      garage_db = (rustPackages."unknown".garage_db."0.9.1" { inherit profileName; }).out;
+      garage_rpc = (rustPackages."unknown".garage_rpc."0.9.1" { inherit profileName; }).out;
+      garage_table = (rustPackages."unknown".garage_table."0.9.1" { inherit profileName; }).out;
+      garage_util = (rustPackages."unknown".garage_util."0.9.1" { inherit profileName; }).out;
       hex = (rustPackages."registry+https://github.com/rust-lang/crates.io-index".hex."0.4.3" { inherit profileName; }).out;
-      netapp = (rustPackages."registry+https://github.com/rust-lang/crates.io-index".netapp."0.5.2" { inherit profileName; }).out;
+      netapp = (rustPackages."registry+https://github.com/rust-lang/crates.io-index".netapp."0.10.0" { inherit profileName; }).out;
       opentelemetry = (rustPackages."registry+https://github.com/rust-lang/crates.io-index".opentelemetry."0.17.0" { inherit profileName; }).out;
       rand = (rustPackages."registry+https://github.com/rust-lang/crates.io-index".rand."0.8.5" { inherit profileName; }).out;
       serde = (rustPackages."registry+https://github.com/rust-lang/crates.io-index".serde."1.0.188" { inherit profileName; }).out;
@@ -1933,9 +1935,9 @@ in
     };
   });
   
-  "unknown".garage_rpc."0.8.5" = overridableMkRustCrate (profileName: rec {
+  "unknown".garage_rpc."0.9.1" = overridableMkRustCrate (profileName: rec {
     name = "garage_rpc";
-    version = "0.8.5";
+    version = "0.9.1";
     registry = "unknown";
     src = fetchCrateLocal (workspaceSrc + "/src/rpc");
     features = builtins.concatLists [
@@ -1952,17 +1954,20 @@ in
       arc_swap = (rustPackages."registry+https://github.com/rust-lang/crates.io-index".arc-swap."1.6.0" { inherit profileName; }).out;
       async_trait = (buildRustPackages."registry+https://github.com/rust-lang/crates.io-index".async-trait."0.1.73" { profileName = "__noProfile"; }).out;
       bytes = (rustPackages."registry+https://github.com/rust-lang/crates.io-index".bytes."1.4.0" { inherit profileName; }).out;
+      bytesize = (rustPackages."registry+https://github.com/rust-lang/crates.io-index".bytesize."1.3.0" { inherit profileName; }).out;
       ${ if rootFeatures' ? "garage/consul-discovery" || rootFeatures' ? "garage_rpc/consul-discovery" || rootFeatures' ? "garage_rpc/err-derive" then "err_derive" else null } = (buildRustPackages."registry+https://github.com/rust-lang/crates.io-index".err-derive."0.3.1" { profileName = "__noProfile"; }).out;
+      format_table = (rustPackages."unknown".format_table."0.1.1" { inherit profileName; }).out;
       futures = (rustPackages."registry+https://github.com/rust-lang/crates.io-index".futures."0.3.28" { inherit profileName; }).out;
       futures_util = (rustPackages."registry+https://github.com/rust-lang/crates.io-index".futures-util."0.3.28" { inherit profileName; }).out;
-      garage_db = (rustPackages."unknown".garage_db."0.8.5" { inherit profileName; }).out;
-      garage_util = (rustPackages."unknown".garage_util."0.8.5" { inherit profileName; }).out;
+      garage_db = (rustPackages."unknown".garage_db."0.9.1" { inherit profileName; }).out;
+      garage_util = (rustPackages."unknown".garage_util."0.9.1" { inherit profileName; }).out;
       gethostname = (rustPackages."registry+https://github.com/rust-lang/crates.io-index".gethostname."0.4.3" { inherit profileName; }).out;
       hex = (rustPackages."registry+https://github.com/rust-lang/crates.io-index".hex."0.4.3" { inherit profileName; }).out;
+      itertools = (rustPackages."registry+https://github.com/rust-lang/crates.io-index".itertools."0.10.5" { inherit profileName; }).out;
       ${ if rootFeatures' ? "garage/kubernetes-discovery" || rootFeatures' ? "garage_rpc/k8s-openapi" || rootFeatures' ? "garage_rpc/kubernetes-discovery" then "k8s_openapi" else null } = (rustPackages."registry+https://github.com/rust-lang/crates.io-index".k8s-openapi."0.16.0" { inherit profileName; }).out;
       ${ if rootFeatures' ? "garage/kubernetes-discovery" || rootFeatures' ? "garage_rpc/kube" || rootFeatures' ? "garage_rpc/kubernetes-discovery" then "kube" else null } = (rustPackages."registry+https://github.com/rust-lang/crates.io-index".kube."0.75.0" { inherit profileName; }).out;
       sodiumoxide = (rustPackages."registry+https://github.com/rust-lang/crates.io-index".kuska-sodiumoxide."0.2.5-0" { inherit profileName; }).out;
-      netapp = (rustPackages."registry+https://github.com/rust-lang/crates.io-index".netapp."0.5.2" { inherit profileName; }).out;
+      netapp = (rustPackages."registry+https://github.com/rust-lang/crates.io-index".netapp."0.10.0" { inherit profileName; }).out;
       nix = (rustPackages."registry+https://github.com/rust-lang/crates.io-index".nix."0.27.1" { inherit profileName; }).out;
       opentelemetry = (rustPackages."registry+https://github.com/rust-lang/crates.io-index".opentelemetry."0.17.0" { inherit profileName; }).out;
       pnet_datalink = (rustPackages."registry+https://github.com/rust-lang/crates.io-index".pnet_datalink."0.33.0" { inherit profileName; }).out;
@@ -1978,9 +1983,9 @@ in
     };
   });
   
-  "unknown".garage_table."0.8.5" = overridableMkRustCrate (profileName: rec {
+  "unknown".garage_table."0.9.1" = overridableMkRustCrate (profileName: rec {
     name = "garage_table";
-    version = "0.8.5";
+    version = "0.9.1";
     registry = "unknown";
     src = fetchCrateLocal (workspaceSrc + "/src/table");
     dependencies = {
@@ -1989,9 +1994,9 @@ in
       bytes = (rustPackages."registry+https://github.com/rust-lang/crates.io-index".bytes."1.4.0" { inherit profileName; }).out;
       futures = (rustPackages."registry+https://github.com/rust-lang/crates.io-index".futures."0.3.28" { inherit profileName; }).out;
       futures_util = (rustPackages."registry+https://github.com/rust-lang/crates.io-index".futures-util."0.3.28" { inherit profileName; }).out;
-      garage_db = (rustPackages."unknown".garage_db."0.8.5" { inherit profileName; }).out;
-      garage_rpc = (rustPackages."unknown".garage_rpc."0.8.5" { inherit profileName; }).out;
-      garage_util = (rustPackages."unknown".garage_util."0.8.5" { inherit profileName; }).out;
+      garage_db = (rustPackages."unknown".garage_db."0.9.1" { inherit profileName; }).out;
+      garage_rpc = (rustPackages."unknown".garage_rpc."0.9.1" { inherit profileName; }).out;
+      garage_util = (rustPackages."unknown".garage_util."0.9.1" { inherit profileName; }).out;
       hex = (rustPackages."registry+https://github.com/rust-lang/crates.io-index".hex."0.4.3" { inherit profileName; }).out;
       hexdump = (rustPackages."registry+https://github.com/rust-lang/crates.io-index".hexdump."0.1.1" { inherit profileName; }).out;
       opentelemetry = (rustPackages."registry+https://github.com/rust-lang/crates.io-index".opentelemetry."0.17.0" { inherit profileName; }).out;
@@ -2003,9 +2008,9 @@ in
     };
   });
   
-  "unknown".garage_util."0.8.5" = overridableMkRustCrate (profileName: rec {
+  "unknown".garage_util."0.9.1" = overridableMkRustCrate (profileName: rec {
     name = "garage_util";
-    version = "0.8.5";
+    version = "0.9.1";
     registry = "unknown";
     src = fetchCrateLocal (workspaceSrc + "/src/util");
     features = builtins.concatLists [
@@ -2021,16 +2026,16 @@ in
       digest = (rustPackages."registry+https://github.com/rust-lang/crates.io-index".digest."0.10.7" { inherit profileName; }).out;
       err_derive = (buildRustPackages."registry+https://github.com/rust-lang/crates.io-index".err-derive."0.3.1" { profileName = "__noProfile"; }).out;
       futures = (rustPackages."registry+https://github.com/rust-lang/crates.io-index".futures."0.3.28" { inherit profileName; }).out;
-      garage_db = (rustPackages."unknown".garage_db."0.8.5" { inherit profileName; }).out;
+      garage_db = (rustPackages."unknown".garage_db."0.9.1" { inherit profileName; }).out;
       hex = (rustPackages."registry+https://github.com/rust-lang/crates.io-index".hex."0.4.3" { inherit profileName; }).out;
       hexdump = (rustPackages."registry+https://github.com/rust-lang/crates.io-index".hexdump."0.1.1" { inherit profileName; }).out;
       http = (rustPackages."registry+https://github.com/rust-lang/crates.io-index".http."0.2.9" { inherit profileName; }).out;
       hyper = (rustPackages."registry+https://github.com/rust-lang/crates.io-index".hyper."0.14.27" { inherit profileName; }).out;
       lazy_static = (rustPackages."registry+https://github.com/rust-lang/crates.io-index".lazy_static."1.4.0" { inherit profileName; }).out;
-      netapp = (rustPackages."registry+https://github.com/rust-lang/crates.io-index".netapp."0.5.2" { inherit profileName; }).out;
+      netapp = (rustPackages."registry+https://github.com/rust-lang/crates.io-index".netapp."0.10.0" { inherit profileName; }).out;
       opentelemetry = (rustPackages."registry+https://github.com/rust-lang/crates.io-index".opentelemetry."0.17.0" { inherit profileName; }).out;
       rand = (rustPackages."registry+https://github.com/rust-lang/crates.io-index".rand."0.8.5" { inherit profileName; }).out;
-      rmp_serde = (rustPackages."registry+https://github.com/rust-lang/crates.io-index".rmp-serde."0.15.5" { inherit profileName; }).out;
+      rmp_serde = (rustPackages."registry+https://github.com/rust-lang/crates.io-index".rmp-serde."1.1.2" { inherit profileName; }).out;
       serde = (rustPackages."registry+https://github.com/rust-lang/crates.io-index".serde."1.0.188" { inherit profileName; }).out;
       serde_json = (rustPackages."registry+https://github.com/rust-lang/crates.io-index".serde_json."1.0.105" { inherit profileName; }).out;
       sha2 = (rustPackages."registry+https://github.com/rust-lang/crates.io-index".sha2."0.10.7" { inherit profileName; }).out;
@@ -2047,18 +2052,18 @@ in
     };
   });
   
-  "unknown".garage_web."0.8.5" = overridableMkRustCrate (profileName: rec {
+  "unknown".garage_web."0.9.1" = overridableMkRustCrate (profileName: rec {
     name = "garage_web";
-    version = "0.8.5";
+    version = "0.9.1";
     registry = "unknown";
     src = fetchCrateLocal (workspaceSrc + "/src/web");
     dependencies = {
       err_derive = (buildRustPackages."registry+https://github.com/rust-lang/crates.io-index".err-derive."0.3.1" { profileName = "__noProfile"; }).out;
       futures = (rustPackages."registry+https://github.com/rust-lang/crates.io-index".futures."0.3.28" { inherit profileName; }).out;
-      garage_api = (rustPackages."unknown".garage_api."0.8.5" { inherit profileName; }).out;
-      garage_model = (rustPackages."unknown".garage_model."0.8.5" { inherit profileName; }).out;
-      garage_table = (rustPackages."unknown".garage_table."0.8.5" { inherit profileName; }).out;
-      garage_util = (rustPackages."unknown".garage_util."0.8.5" { inherit profileName; }).out;
+      garage_api = (rustPackages."unknown".garage_api."0.9.1" { inherit profileName; }).out;
+      garage_model = (rustPackages."unknown".garage_model."0.9.1" { inherit profileName; }).out;
+      garage_table = (rustPackages."unknown".garage_table."0.9.1" { inherit profileName; }).out;
+      garage_util = (rustPackages."unknown".garage_util."0.9.1" { inherit profileName; }).out;
       http = (rustPackages."registry+https://github.com/rust-lang/crates.io-index".http."0.2.9" { inherit profileName; }).out;
       hyper = (rustPackages."registry+https://github.com/rust-lang/crates.io-index".hyper."0.14.27" { inherit profileName; }).out;
       hyperlocal = (rustPackages."registry+https://github.com/rust-lang/crates.io-index".hyperlocal."0.8.0" { inherit profileName; }).out;
@@ -2182,15 +2187,15 @@ in
     registry = "registry+https://github.com/rust-lang/crates.io-index";
     src = fetchCratesIo { inherit name version; sha256 = "2c6201b9ff9fd90a5a3bac2e56a830d0caa509576f0e503818ee82c181b3437a"; };
     features = builtins.concatLists [
-      (lib.optional (rootFeatures' ? "garage/bundled-libs" || rootFeatures' ? "garage/default" || rootFeatures' ? "garage/sqlite" || rootFeatures' ? "garage_db/bundled-libs" || rootFeatures' ? "garage_db/rusqlite" || rootFeatures' ? "garage_db/sqlite" || rootFeatures' ? "garage_model/sqlite") "ahash")
-      (lib.optional (rootFeatures' ? "garage/bundled-libs" || rootFeatures' ? "garage/default" || rootFeatures' ? "garage/sqlite" || rootFeatures' ? "garage_db/bundled-libs" || rootFeatures' ? "garage_db/rusqlite" || rootFeatures' ? "garage_db/sqlite" || rootFeatures' ? "garage_model/sqlite") "allocator-api2")
-      (lib.optional (rootFeatures' ? "garage/bundled-libs" || rootFeatures' ? "garage/default" || rootFeatures' ? "garage/sqlite" || rootFeatures' ? "garage_db/bundled-libs" || rootFeatures' ? "garage_db/rusqlite" || rootFeatures' ? "garage_db/sqlite" || rootFeatures' ? "garage_model/sqlite") "default")
-      (lib.optional (rootFeatures' ? "garage/bundled-libs" || rootFeatures' ? "garage/default" || rootFeatures' ? "garage/sqlite" || rootFeatures' ? "garage_db/bundled-libs" || rootFeatures' ? "garage_db/rusqlite" || rootFeatures' ? "garage_db/sqlite" || rootFeatures' ? "garage_model/sqlite") "inline-more")
+      (lib.optional (rootFeatures' ? "garage/bundled-libs" || rootFeatures' ? "garage/default" || rootFeatures' ? "garage/sqlite" || rootFeatures' ? "garage_db/bundled-libs" || rootFeatures' ? "garage_db/default" || rootFeatures' ? "garage_db/rusqlite" || rootFeatures' ? "garage_db/sqlite" || rootFeatures' ? "garage_model/default" || rootFeatures' ? "garage_model/sqlite") "ahash")
+      (lib.optional (rootFeatures' ? "garage/bundled-libs" || rootFeatures' ? "garage/default" || rootFeatures' ? "garage/sqlite" || rootFeatures' ? "garage_db/bundled-libs" || rootFeatures' ? "garage_db/default" || rootFeatures' ? "garage_db/rusqlite" || rootFeatures' ? "garage_db/sqlite" || rootFeatures' ? "garage_model/default" || rootFeatures' ? "garage_model/sqlite") "allocator-api2")
+      (lib.optional (rootFeatures' ? "garage/bundled-libs" || rootFeatures' ? "garage/default" || rootFeatures' ? "garage/sqlite" || rootFeatures' ? "garage_db/bundled-libs" || rootFeatures' ? "garage_db/default" || rootFeatures' ? "garage_db/rusqlite" || rootFeatures' ? "garage_db/sqlite" || rootFeatures' ? "garage_model/default" || rootFeatures' ? "garage_model/sqlite") "default")
+      (lib.optional (rootFeatures' ? "garage/bundled-libs" || rootFeatures' ? "garage/default" || rootFeatures' ? "garage/sqlite" || rootFeatures' ? "garage_db/bundled-libs" || rootFeatures' ? "garage_db/default" || rootFeatures' ? "garage_db/rusqlite" || rootFeatures' ? "garage_db/sqlite" || rootFeatures' ? "garage_model/default" || rootFeatures' ? "garage_model/sqlite") "inline-more")
       (lib.optional (rootFeatures' ? "garage/kubernetes-discovery" || rootFeatures' ? "garage/opentelemetry-otlp" || rootFeatures' ? "garage/telemetry-otlp" || rootFeatures' ? "garage_rpc/kube" || rootFeatures' ? "garage_rpc/kubernetes-discovery") "raw")
     ];
     dependencies = {
-      ${ if rootFeatures' ? "garage/bundled-libs" || rootFeatures' ? "garage/default" || rootFeatures' ? "garage/sqlite" || rootFeatures' ? "garage_db/bundled-libs" || rootFeatures' ? "garage_db/rusqlite" || rootFeatures' ? "garage_db/sqlite" || rootFeatures' ? "garage_model/sqlite" then "ahash" else null } = (rustPackages."registry+https://github.com/rust-lang/crates.io-index".ahash."0.8.3" { inherit profileName; }).out;
-      ${ if rootFeatures' ? "garage/bundled-libs" || rootFeatures' ? "garage/default" || rootFeatures' ? "garage/sqlite" || rootFeatures' ? "garage_db/bundled-libs" || rootFeatures' ? "garage_db/rusqlite" || rootFeatures' ? "garage_db/sqlite" || rootFeatures' ? "garage_model/sqlite" then "allocator_api2" else null } = (rustPackages."registry+https://github.com/rust-lang/crates.io-index".allocator-api2."0.2.16" { inherit profileName; }).out;
+      ${ if rootFeatures' ? "garage/bundled-libs" || rootFeatures' ? "garage/default" || rootFeatures' ? "garage/sqlite" || rootFeatures' ? "garage_db/bundled-libs" || rootFeatures' ? "garage_db/default" || rootFeatures' ? "garage_db/rusqlite" || rootFeatures' ? "garage_db/sqlite" || rootFeatures' ? "garage_model/default" || rootFeatures' ? "garage_model/sqlite" then "ahash" else null } = (rustPackages."registry+https://github.com/rust-lang/crates.io-index".ahash."0.8.3" { inherit profileName; }).out;
+      ${ if rootFeatures' ? "garage/bundled-libs" || rootFeatures' ? "garage/default" || rootFeatures' ? "garage/sqlite" || rootFeatures' ? "garage_db/bundled-libs" || rootFeatures' ? "garage_db/default" || rootFeatures' ? "garage_db/rusqlite" || rootFeatures' ? "garage_db/sqlite" || rootFeatures' ? "garage_model/default" || rootFeatures' ? "garage_model/sqlite" then "allocator_api2" else null } = (rustPackages."registry+https://github.com/rust-lang/crates.io-index".allocator-api2."0.2.16" { inherit profileName; }).out;
     };
   });
   
@@ -2200,7 +2205,7 @@ in
     registry = "registry+https://github.com/rust-lang/crates.io-index";
     src = fetchCratesIo { inherit name version; sha256 = "312f66718a2d7789ffef4f4b7b213138ed9f1eb3aa1d0d82fc99f88fb3ffd26f"; };
     dependencies = {
-      ${ if rootFeatures' ? "garage/bundled-libs" || rootFeatures' ? "garage/default" || rootFeatures' ? "garage/sqlite" || rootFeatures' ? "garage_db/bundled-libs" || rootFeatures' ? "garage_db/rusqlite" || rootFeatures' ? "garage_db/sqlite" || rootFeatures' ? "garage_model/sqlite" then "hashbrown" else null } = (rustPackages."registry+https://github.com/rust-lang/crates.io-index".hashbrown."0.14.0" { inherit profileName; }).out;
+      ${ if rootFeatures' ? "garage/bundled-libs" || rootFeatures' ? "garage/default" || rootFeatures' ? "garage/sqlite" || rootFeatures' ? "garage_db/bundled-libs" || rootFeatures' ? "garage_db/default" || rootFeatures' ? "garage_db/rusqlite" || rootFeatures' ? "garage_db/sqlite" || rootFeatures' ? "garage_model/default" || rootFeatures' ? "garage_model/sqlite" then "hashbrown" else null } = (rustPackages."registry+https://github.com/rust-lang/crates.io-index".hashbrown."0.14.0" { inherit profileName; }).out;
     };
   });
   
@@ -2230,20 +2235,20 @@ in
     registry = "registry+https://github.com/rust-lang/crates.io-index";
     src = fetchCratesIo { inherit name version; sha256 = "269c7486ed6def5d7b59a427cec3e87b4d4dd4381d01e21c8c9f2d3985688392"; };
     features = builtins.concatLists [
-      (lib.optional (rootFeatures' ? "garage/lmdb" || rootFeatures' ? "garage_db/heed" || rootFeatures' ? "garage_db/lmdb" || rootFeatures' ? "garage_model/lmdb") "lmdb")
-      (lib.optional (rootFeatures' ? "garage/lmdb" || rootFeatures' ? "garage_db/heed" || rootFeatures' ? "garage_db/lmdb" || rootFeatures' ? "garage_model/lmdb") "lmdb-rkv-sys")
+      (lib.optional (rootFeatures' ? "garage/default" || rootFeatures' ? "garage/lmdb" || rootFeatures' ? "garage_db/default" || rootFeatures' ? "garage_db/heed" || rootFeatures' ? "garage_db/lmdb" || rootFeatures' ? "garage_model/default" || rootFeatures' ? "garage_model/lmdb") "lmdb")
+      (lib.optional (rootFeatures' ? "garage/default" || rootFeatures' ? "garage/lmdb" || rootFeatures' ? "garage_db/default" || rootFeatures' ? "garage_db/heed" || rootFeatures' ? "garage_db/lmdb" || rootFeatures' ? "garage_model/default" || rootFeatures' ? "garage_model/lmdb") "lmdb-rkv-sys")
     ];
     dependencies = {
-      ${ if rootFeatures' ? "garage/lmdb" || rootFeatures' ? "garage_db/heed" || rootFeatures' ? "garage_db/lmdb" || rootFeatures' ? "garage_model/lmdb" then "bytemuck" else null } = (rustPackages."registry+https://github.com/rust-lang/crates.io-index".bytemuck."1.13.1" { inherit profileName; }).out;
-      ${ if rootFeatures' ? "garage/lmdb" || rootFeatures' ? "garage_db/heed" || rootFeatures' ? "garage_db/lmdb" || rootFeatures' ? "garage_model/lmdb" then "byteorder" else null } = (rustPackages."registry+https://github.com/rust-lang/crates.io-index".byteorder."1.4.3" { inherit profileName; }).out;
-      ${ if rootFeatures' ? "garage/lmdb" || rootFeatures' ? "garage_db/heed" || rootFeatures' ? "garage_db/lmdb" || rootFeatures' ? "garage_model/lmdb" then "heed_traits" else null } = (rustPackages."registry+https://github.com/rust-lang/crates.io-index".heed-traits."0.8.0" { inherit profileName; }).out;
-      ${ if rootFeatures' ? "garage/lmdb" || rootFeatures' ? "garage_db/heed" || rootFeatures' ? "garage_db/lmdb" || rootFeatures' ? "garage_model/lmdb" then "heed_types" else null } = (rustPackages."registry+https://github.com/rust-lang/crates.io-index".heed-types."0.8.0" { inherit profileName; }).out;
-      ${ if rootFeatures' ? "garage/lmdb" || rootFeatures' ? "garage_db/heed" || rootFeatures' ? "garage_db/lmdb" || rootFeatures' ? "garage_model/lmdb" then "libc" else null } = (rustPackages."registry+https://github.com/rust-lang/crates.io-index".libc."0.2.147" { inherit profileName; }).out;
-      ${ if rootFeatures' ? "garage/lmdb" || rootFeatures' ? "garage_db/heed" || rootFeatures' ? "garage_db/lmdb" || rootFeatures' ? "garage_model/lmdb" then "lmdb_sys" else null } = (rustPackages."registry+https://github.com/rust-lang/crates.io-index".lmdb-rkv-sys."0.11.2" { inherit profileName; }).out;
-      ${ if rootFeatures' ? "garage/lmdb" || rootFeatures' ? "garage_db/heed" || rootFeatures' ? "garage_db/lmdb" || rootFeatures' ? "garage_model/lmdb" then "once_cell" else null } = (rustPackages."registry+https://github.com/rust-lang/crates.io-index".once_cell."1.18.0" { inherit profileName; }).out;
-      ${ if rootFeatures' ? "garage/lmdb" || rootFeatures' ? "garage_db/heed" || rootFeatures' ? "garage_db/lmdb" || rootFeatures' ? "garage_model/lmdb" then "page_size" else null } = (rustPackages."registry+https://github.com/rust-lang/crates.io-index".page_size."0.4.2" { inherit profileName; }).out;
-      ${ if rootFeatures' ? "garage/lmdb" || rootFeatures' ? "garage_db/heed" || rootFeatures' ? "garage_db/lmdb" || rootFeatures' ? "garage_model/lmdb" then "synchronoise" else null } = (rustPackages."registry+https://github.com/rust-lang/crates.io-index".synchronoise."1.0.1" { inherit profileName; }).out;
-      ${ if (rootFeatures' ? "garage/lmdb" || rootFeatures' ? "garage_db/heed" || rootFeatures' ? "garage_db/lmdb" || rootFeatures' ? "garage_model/lmdb") && hostPlatform.isWindows then "url" else null } = (rustPackages."registry+https://github.com/rust-lang/crates.io-index".url."2.4.0" { inherit profileName; }).out;
+      ${ if rootFeatures' ? "garage/default" || rootFeatures' ? "garage/lmdb" || rootFeatures' ? "garage_db/default" || rootFeatures' ? "garage_db/heed" || rootFeatures' ? "garage_db/lmdb" || rootFeatures' ? "garage_model/default" || rootFeatures' ? "garage_model/lmdb" then "bytemuck" else null } = (rustPackages."registry+https://github.com/rust-lang/crates.io-index".bytemuck."1.13.1" { inherit profileName; }).out;
+      ${ if rootFeatures' ? "garage/default" || rootFeatures' ? "garage/lmdb" || rootFeatures' ? "garage_db/default" || rootFeatures' ? "garage_db/heed" || rootFeatures' ? "garage_db/lmdb" || rootFeatures' ? "garage_model/default" || rootFeatures' ? "garage_model/lmdb" then "byteorder" else null } = (rustPackages."registry+https://github.com/rust-lang/crates.io-index".byteorder."1.4.3" { inherit profileName; }).out;
+      ${ if rootFeatures' ? "garage/default" || rootFeatures' ? "garage/lmdb" || rootFeatures' ? "garage_db/default" || rootFeatures' ? "garage_db/heed" || rootFeatures' ? "garage_db/lmdb" || rootFeatures' ? "garage_model/default" || rootFeatures' ? "garage_model/lmdb" then "heed_traits" else null } = (rustPackages."registry+https://github.com/rust-lang/crates.io-index".heed-traits."0.8.0" { inherit profileName; }).out;
+      ${ if rootFeatures' ? "garage/default" || rootFeatures' ? "garage/lmdb" || rootFeatures' ? "garage_db/default" || rootFeatures' ? "garage_db/heed" || rootFeatures' ? "garage_db/lmdb" || rootFeatures' ? "garage_model/default" || rootFeatures' ? "garage_model/lmdb" then "heed_types" else null } = (rustPackages."registry+https://github.com/rust-lang/crates.io-index".heed-types."0.8.0" { inherit profileName; }).out;
+      ${ if rootFeatures' ? "garage/default" || rootFeatures' ? "garage/lmdb" || rootFeatures' ? "garage_db/default" || rootFeatures' ? "garage_db/heed" || rootFeatures' ? "garage_db/lmdb" || rootFeatures' ? "garage_model/default" || rootFeatures' ? "garage_model/lmdb" then "libc" else null } = (rustPackages."registry+https://github.com/rust-lang/crates.io-index".libc."0.2.147" { inherit profileName; }).out;
+      ${ if rootFeatures' ? "garage/default" || rootFeatures' ? "garage/lmdb" || rootFeatures' ? "garage_db/default" || rootFeatures' ? "garage_db/heed" || rootFeatures' ? "garage_db/lmdb" || rootFeatures' ? "garage_model/default" || rootFeatures' ? "garage_model/lmdb" then "lmdb_sys" else null } = (rustPackages."registry+https://github.com/rust-lang/crates.io-index".lmdb-rkv-sys."0.11.2" { inherit profileName; }).out;
+      ${ if rootFeatures' ? "garage/default" || rootFeatures' ? "garage/lmdb" || rootFeatures' ? "garage_db/default" || rootFeatures' ? "garage_db/heed" || rootFeatures' ? "garage_db/lmdb" || rootFeatures' ? "garage_model/default" || rootFeatures' ? "garage_model/lmdb" then "once_cell" else null } = (rustPackages."registry+https://github.com/rust-lang/crates.io-index".once_cell."1.18.0" { inherit profileName; }).out;
+      ${ if rootFeatures' ? "garage/default" || rootFeatures' ? "garage/lmdb" || rootFeatures' ? "garage_db/default" || rootFeatures' ? "garage_db/heed" || rootFeatures' ? "garage_db/lmdb" || rootFeatures' ? "garage_model/default" || rootFeatures' ? "garage_model/lmdb" then "page_size" else null } = (rustPackages."registry+https://github.com/rust-lang/crates.io-index".page_size."0.4.2" { inherit profileName; }).out;
+      ${ if rootFeatures' ? "garage/default" || rootFeatures' ? "garage/lmdb" || rootFeatures' ? "garage_db/default" || rootFeatures' ? "garage_db/heed" || rootFeatures' ? "garage_db/lmdb" || rootFeatures' ? "garage_model/default" || rootFeatures' ? "garage_model/lmdb" then "synchronoise" else null } = (rustPackages."registry+https://github.com/rust-lang/crates.io-index".synchronoise."1.0.1" { inherit profileName; }).out;
+      ${ if (rootFeatures' ? "garage/default" || rootFeatures' ? "garage/lmdb" || rootFeatures' ? "garage_db/default" || rootFeatures' ? "garage_db/heed" || rootFeatures' ? "garage_db/lmdb" || rootFeatures' ? "garage_model/default" || rootFeatures' ? "garage_model/lmdb") && hostPlatform.isWindows then "url" else null } = (rustPackages."registry+https://github.com/rust-lang/crates.io-index".url."2.4.0" { inherit profileName; }).out;
     };
   });
   
@@ -2260,20 +2265,20 @@ in
     registry = "registry+https://github.com/rust-lang/crates.io-index";
     src = fetchCratesIo { inherit name version; sha256 = "9a6cf0a6952fcedc992602d5cddd1e3fff091fbe87d38636e3ec23a31f32acbd"; };
     features = builtins.concatLists [
-      (lib.optional (rootFeatures' ? "garage/lmdb" || rootFeatures' ? "garage_db/heed" || rootFeatures' ? "garage_db/lmdb" || rootFeatures' ? "garage_model/lmdb") "bincode")
-      (lib.optional (rootFeatures' ? "garage/lmdb" || rootFeatures' ? "garage_db/heed" || rootFeatures' ? "garage_db/lmdb" || rootFeatures' ? "garage_model/lmdb") "default")
-      (lib.optional (rootFeatures' ? "garage/lmdb" || rootFeatures' ? "garage_db/heed" || rootFeatures' ? "garage_db/lmdb" || rootFeatures' ? "garage_model/lmdb") "serde")
-      (lib.optional (rootFeatures' ? "garage/lmdb" || rootFeatures' ? "garage_db/heed" || rootFeatures' ? "garage_db/lmdb" || rootFeatures' ? "garage_model/lmdb") "serde-bincode")
-      (lib.optional (rootFeatures' ? "garage/lmdb" || rootFeatures' ? "garage_db/heed" || rootFeatures' ? "garage_db/lmdb" || rootFeatures' ? "garage_model/lmdb") "serde-json")
-      (lib.optional (rootFeatures' ? "garage/lmdb" || rootFeatures' ? "garage_db/heed" || rootFeatures' ? "garage_db/lmdb" || rootFeatures' ? "garage_model/lmdb") "serde_json")
+      (lib.optional (rootFeatures' ? "garage/default" || rootFeatures' ? "garage/lmdb" || rootFeatures' ? "garage_db/default" || rootFeatures' ? "garage_db/heed" || rootFeatures' ? "garage_db/lmdb" || rootFeatures' ? "garage_model/default" || rootFeatures' ? "garage_model/lmdb") "bincode")
+      (lib.optional (rootFeatures' ? "garage/default" || rootFeatures' ? "garage/lmdb" || rootFeatures' ? "garage_db/default" || rootFeatures' ? "garage_db/heed" || rootFeatures' ? "garage_db/lmdb" || rootFeatures' ? "garage_model/default" || rootFeatures' ? "garage_model/lmdb") "default")
+      (lib.optional (rootFeatures' ? "garage/default" || rootFeatures' ? "garage/lmdb" || rootFeatures' ? "garage_db/default" || rootFeatures' ? "garage_db/heed" || rootFeatures' ? "garage_db/lmdb" || rootFeatures' ? "garage_model/default" || rootFeatures' ? "garage_model/lmdb") "serde")
+      (lib.optional (rootFeatures' ? "garage/default" || rootFeatures' ? "garage/lmdb" || rootFeatures' ? "garage_db/default" || rootFeatures' ? "garage_db/heed" || rootFeatures' ? "garage_db/lmdb" || rootFeatures' ? "garage_model/default" || rootFeatures' ? "garage_model/lmdb") "serde-bincode")
+      (lib.optional (rootFeatures' ? "garage/default" || rootFeatures' ? "garage/lmdb" || rootFeatures' ? "garage_db/default" || rootFeatures' ? "garage_db/heed" || rootFeatures' ? "garage_db/lmdb" || rootFeatures' ? "garage_model/default" || rootFeatures' ? "garage_model/lmdb") "serde-json")
+      (lib.optional (rootFeatures' ? "garage/default" || rootFeatures' ? "garage/lmdb" || rootFeatures' ? "garage_db/default" || rootFeatures' ? "garage_db/heed" || rootFeatures' ? "garage_db/lmdb" || rootFeatures' ? "garage_model/default" || rootFeatures' ? "garage_model/lmdb") "serde_json")
     ];
     dependencies = {
-      ${ if rootFeatures' ? "garage/lmdb" || rootFeatures' ? "garage_db/heed" || rootFeatures' ? "garage_db/lmdb" || rootFeatures' ? "garage_model/lmdb" then "bincode" else null } = (rustPackages."registry+https://github.com/rust-lang/crates.io-index".bincode."1.3.3" { inherit profileName; }).out;
-      ${ if rootFeatures' ? "garage/lmdb" || rootFeatures' ? "garage_db/heed" || rootFeatures' ? "garage_db/lmdb" || rootFeatures' ? "garage_model/lmdb" then "bytemuck" else null } = (rustPackages."registry+https://github.com/rust-lang/crates.io-index".bytemuck."1.13.1" { inherit profileName; }).out;
-      ${ if rootFeatures' ? "garage/lmdb" || rootFeatures' ? "garage_db/heed" || rootFeatures' ? "garage_db/lmdb" || rootFeatures' ? "garage_model/lmdb" then "byteorder" else null } = (rustPackages."registry+https://github.com/rust-lang/crates.io-index".byteorder."1.4.3" { inherit profileName; }).out;
-      ${ if rootFeatures' ? "garage/lmdb" || rootFeatures' ? "garage_db/heed" || rootFeatures' ? "garage_db/lmdb" || rootFeatures' ? "garage_model/lmdb" then "heed_traits" else null } = (rustPackages."registry+https://github.com/rust-lang/crates.io-index".heed-traits."0.8.0" { inherit profileName; }).out;
-      ${ if rootFeatures' ? "garage/lmdb" || rootFeatures' ? "garage_db/heed" || rootFeatures' ? "garage_db/lmdb" || rootFeatures' ? "garage_model/lmdb" then "serde" else null } = (rustPackages."registry+https://github.com/rust-lang/crates.io-index".serde."1.0.188" { inherit profileName; }).out;
-      ${ if rootFeatures' ? "garage/lmdb" || rootFeatures' ? "garage_db/heed" || rootFeatures' ? "garage_db/lmdb" || rootFeatures' ? "garage_model/lmdb" then "serde_json" else null } = (rustPackages."registry+https://github.com/rust-lang/crates.io-index".serde_json."1.0.105" { inherit profileName; }).out;
+      ${ if rootFeatures' ? "garage/default" || rootFeatures' ? "garage/lmdb" || rootFeatures' ? "garage_db/default" || rootFeatures' ? "garage_db/heed" || rootFeatures' ? "garage_db/lmdb" || rootFeatures' ? "garage_model/default" || rootFeatures' ? "garage_model/lmdb" then "bincode" else null } = (rustPackages."registry+https://github.com/rust-lang/crates.io-index".bincode."1.3.3" { inherit profileName; }).out;
+      ${ if rootFeatures' ? "garage/default" || rootFeatures' ? "garage/lmdb" || rootFeatures' ? "garage_db/default" || rootFeatures' ? "garage_db/heed" || rootFeatures' ? "garage_db/lmdb" || rootFeatures' ? "garage_model/default" || rootFeatures' ? "garage_model/lmdb" then "bytemuck" else null } = (rustPackages."registry+https://github.com/rust-lang/crates.io-index".bytemuck."1.13.1" { inherit profileName; }).out;
+      ${ if rootFeatures' ? "garage/default" || rootFeatures' ? "garage/lmdb" || rootFeatures' ? "garage_db/default" || rootFeatures' ? "garage_db/heed" || rootFeatures' ? "garage_db/lmdb" || rootFeatures' ? "garage_model/default" || rootFeatures' ? "garage_model/lmdb" then "byteorder" else null } = (rustPackages."registry+https://github.com/rust-lang/crates.io-index".byteorder."1.4.3" { inherit profileName; }).out;
+      ${ if rootFeatures' ? "garage/default" || rootFeatures' ? "garage/lmdb" || rootFeatures' ? "garage_db/default" || rootFeatures' ? "garage_db/heed" || rootFeatures' ? "garage_db/lmdb" || rootFeatures' ? "garage_model/default" || rootFeatures' ? "garage_model/lmdb" then "heed_traits" else null } = (rustPackages."registry+https://github.com/rust-lang/crates.io-index".heed-traits."0.8.0" { inherit profileName; }).out;
+      ${ if rootFeatures' ? "garage/default" || rootFeatures' ? "garage/lmdb" || rootFeatures' ? "garage_db/default" || rootFeatures' ? "garage_db/heed" || rootFeatures' ? "garage_db/lmdb" || rootFeatures' ? "garage_model/default" || rootFeatures' ? "garage_model/lmdb" then "serde" else null } = (rustPackages."registry+https://github.com/rust-lang/crates.io-index".serde."1.0.188" { inherit profileName; }).out;
+      ${ if rootFeatures' ? "garage/default" || rootFeatures' ? "garage/lmdb" || rootFeatures' ? "garage_db/default" || rootFeatures' ? "garage_db/heed" || rootFeatures' ? "garage_db/lmdb" || rootFeatures' ? "garage_model/default" || rootFeatures' ? "garage_model/lmdb" then "serde_json" else null } = (rustPackages."registry+https://github.com/rust-lang/crates.io-index".serde_json."1.0.105" { inherit profileName; }).out;
     };
   });
   
@@ -2649,12 +2654,12 @@ in
     registry = "registry+https://github.com/rust-lang/crates.io-index";
     src = fetchCratesIo { inherit name version; sha256 = "b0fd2260e829bddf4cb6ea802289de2f86d6a7a690192fbe91b3f46e0f2c8473"; };
     features = builtins.concatLists [
-      (lib.optional (rootFeatures' ? "garage/opentelemetry-otlp" || rootFeatures' ? "garage/telemetry-otlp") "default")
-      (lib.optional (rootFeatures' ? "garage/opentelemetry-otlp" || rootFeatures' ? "garage/telemetry-otlp") "use_alloc")
-      (lib.optional (rootFeatures' ? "garage/opentelemetry-otlp" || rootFeatures' ? "garage/telemetry-otlp") "use_std")
+      [ "default" ]
+      [ "use_alloc" ]
+      [ "use_std" ]
     ];
     dependencies = {
-      ${ if rootFeatures' ? "garage/opentelemetry-otlp" || rootFeatures' ? "garage/telemetry-otlp" then "either" else null } = (rustPackages."registry+https://github.com/rust-lang/crates.io-index".either."1.9.0" { inherit profileName; }).out;
+      either = (rustPackages."registry+https://github.com/rust-lang/crates.io-index".either."1.9.0" { inherit profileName; }).out;
     };
   });
   
@@ -3010,15 +3015,15 @@ in
       (lib.optional (rootFeatures' ? "garage/bundled-libs" || rootFeatures' ? "garage/default" || rootFeatures' ? "garage_db/bundled-libs") "bundled")
       (lib.optional (rootFeatures' ? "garage/bundled-libs" || rootFeatures' ? "garage/default" || rootFeatures' ? "garage_db/bundled-libs") "bundled_bindings")
       (lib.optional (rootFeatures' ? "garage/bundled-libs" || rootFeatures' ? "garage/default" || rootFeatures' ? "garage_db/bundled-libs") "cc")
-      (lib.optional (rootFeatures' ? "garage/bundled-libs" || rootFeatures' ? "garage/default" || rootFeatures' ? "garage/sqlite" || rootFeatures' ? "garage_db/bundled-libs" || rootFeatures' ? "garage_db/rusqlite" || rootFeatures' ? "garage_db/sqlite" || rootFeatures' ? "garage_model/sqlite") "default")
-      (lib.optional (rootFeatures' ? "garage/bundled-libs" || rootFeatures' ? "garage/default" || rootFeatures' ? "garage/sqlite" || rootFeatures' ? "garage_db/bundled-libs" || rootFeatures' ? "garage_db/rusqlite" || rootFeatures' ? "garage_db/sqlite" || rootFeatures' ? "garage_model/sqlite") "min_sqlite_version_3_14_0")
-      (lib.optional (rootFeatures' ? "garage/bundled-libs" || rootFeatures' ? "garage/default" || rootFeatures' ? "garage/sqlite" || rootFeatures' ? "garage_db/bundled-libs" || rootFeatures' ? "garage_db/rusqlite" || rootFeatures' ? "garage_db/sqlite" || rootFeatures' ? "garage_model/sqlite") "pkg-config")
-      (lib.optional (rootFeatures' ? "garage/bundled-libs" || rootFeatures' ? "garage/default" || rootFeatures' ? "garage/sqlite" || rootFeatures' ? "garage_db/bundled-libs" || rootFeatures' ? "garage_db/rusqlite" || rootFeatures' ? "garage_db/sqlite" || rootFeatures' ? "garage_model/sqlite") "vcpkg")
+      (lib.optional (rootFeatures' ? "garage/bundled-libs" || rootFeatures' ? "garage/default" || rootFeatures' ? "garage/sqlite" || rootFeatures' ? "garage_db/bundled-libs" || rootFeatures' ? "garage_db/default" || rootFeatures' ? "garage_db/rusqlite" || rootFeatures' ? "garage_db/sqlite" || rootFeatures' ? "garage_model/default" || rootFeatures' ? "garage_model/sqlite") "default")
+      (lib.optional (rootFeatures' ? "garage/bundled-libs" || rootFeatures' ? "garage/default" || rootFeatures' ? "garage/sqlite" || rootFeatures' ? "garage_db/bundled-libs" || rootFeatures' ? "garage_db/default" || rootFeatures' ? "garage_db/rusqlite" || rootFeatures' ? "garage_db/sqlite" || rootFeatures' ? "garage_model/default" || rootFeatures' ? "garage_model/sqlite") "min_sqlite_version_3_14_0")
+      (lib.optional (rootFeatures' ? "garage/bundled-libs" || rootFeatures' ? "garage/default" || rootFeatures' ? "garage/sqlite" || rootFeatures' ? "garage_db/bundled-libs" || rootFeatures' ? "garage_db/default" || rootFeatures' ? "garage_db/rusqlite" || rootFeatures' ? "garage_db/sqlite" || rootFeatures' ? "garage_model/default" || rootFeatures' ? "garage_model/sqlite") "pkg-config")
+      (lib.optional (rootFeatures' ? "garage/bundled-libs" || rootFeatures' ? "garage/default" || rootFeatures' ? "garage/sqlite" || rootFeatures' ? "garage_db/bundled-libs" || rootFeatures' ? "garage_db/default" || rootFeatures' ? "garage_db/rusqlite" || rootFeatures' ? "garage_db/sqlite" || rootFeatures' ? "garage_model/default" || rootFeatures' ? "garage_model/sqlite") "vcpkg")
     ];
     buildDependencies = {
       ${ if rootFeatures' ? "garage/bundled-libs" || rootFeatures' ? "garage/default" || rootFeatures' ? "garage_db/bundled-libs" then "cc" else null } = (buildRustPackages."registry+https://github.com/rust-lang/crates.io-index".cc."1.0.83" { profileName = "__noProfile"; }).out;
-      ${ if rootFeatures' ? "garage/bundled-libs" || rootFeatures' ? "garage/default" || rootFeatures' ? "garage/sqlite" || rootFeatures' ? "garage_db/bundled-libs" || rootFeatures' ? "garage_db/rusqlite" || rootFeatures' ? "garage_db/sqlite" || rootFeatures' ? "garage_model/sqlite" then "pkg_config" else null } = (buildRustPackages."registry+https://github.com/rust-lang/crates.io-index".pkg-config."0.3.27" { profileName = "__noProfile"; }).out;
-      ${ if rootFeatures' ? "garage/bundled-libs" || rootFeatures' ? "garage/default" || rootFeatures' ? "garage/sqlite" || rootFeatures' ? "garage_db/bundled-libs" || rootFeatures' ? "garage_db/rusqlite" || rootFeatures' ? "garage_db/sqlite" || rootFeatures' ? "garage_model/sqlite" then "vcpkg" else null } = (buildRustPackages."registry+https://github.com/rust-lang/crates.io-index".vcpkg."0.2.15" { profileName = "__noProfile"; }).out;
+      ${ if rootFeatures' ? "garage/bundled-libs" || rootFeatures' ? "garage/default" || rootFeatures' ? "garage/sqlite" || rootFeatures' ? "garage_db/bundled-libs" || rootFeatures' ? "garage_db/default" || rootFeatures' ? "garage_db/rusqlite" || rootFeatures' ? "garage_db/sqlite" || rootFeatures' ? "garage_model/default" || rootFeatures' ? "garage_model/sqlite" then "pkg_config" else null } = (buildRustPackages."registry+https://github.com/rust-lang/crates.io-index".pkg-config."0.3.27" { profileName = "__noProfile"; }).out;
+      ${ if rootFeatures' ? "garage/bundled-libs" || rootFeatures' ? "garage/default" || rootFeatures' ? "garage/sqlite" || rootFeatures' ? "garage_db/bundled-libs" || rootFeatures' ? "garage_db/default" || rootFeatures' ? "garage_db/rusqlite" || rootFeatures' ? "garage_db/sqlite" || rootFeatures' ? "garage_model/default" || rootFeatures' ? "garage_model/sqlite" then "vcpkg" else null } = (buildRustPackages."registry+https://github.com/rust-lang/crates.io-index".vcpkg."0.2.15" { profileName = "__noProfile"; }).out;
     };
   });
   
@@ -3048,14 +3053,14 @@ in
     registry = "registry+https://github.com/rust-lang/crates.io-index";
     src = fetchCratesIo { inherit name version; sha256 = "61b9ce6b3be08acefa3003c57b7565377432a89ec24476bbe72e11d101f852fe"; };
     features = builtins.concatLists [
-      (lib.optional (rootFeatures' ? "garage/lmdb" || rootFeatures' ? "garage_db/heed" || rootFeatures' ? "garage_db/lmdb" || rootFeatures' ? "garage_model/lmdb") "default")
+      (lib.optional (rootFeatures' ? "garage/default" || rootFeatures' ? "garage/lmdb" || rootFeatures' ? "garage_db/default" || rootFeatures' ? "garage_db/heed" || rootFeatures' ? "garage_db/lmdb" || rootFeatures' ? "garage_model/default" || rootFeatures' ? "garage_model/lmdb") "default")
     ];
     dependencies = {
-      ${ if rootFeatures' ? "garage/lmdb" || rootFeatures' ? "garage_db/heed" || rootFeatures' ? "garage_db/lmdb" || rootFeatures' ? "garage_model/lmdb" then "libc" else null } = (rustPackages."registry+https://github.com/rust-lang/crates.io-index".libc."0.2.147" { inherit profileName; }).out;
+      ${ if rootFeatures' ? "garage/default" || rootFeatures' ? "garage/lmdb" || rootFeatures' ? "garage_db/default" || rootFeatures' ? "garage_db/heed" || rootFeatures' ? "garage_db/lmdb" || rootFeatures' ? "garage_model/default" || rootFeatures' ? "garage_model/lmdb" then "libc" else null } = (rustPackages."registry+https://github.com/rust-lang/crates.io-index".libc."0.2.147" { inherit profileName; }).out;
     };
     buildDependencies = {
-      ${ if rootFeatures' ? "garage/lmdb" || rootFeatures' ? "garage_db/heed" || rootFeatures' ? "garage_db/lmdb" || rootFeatures' ? "garage_model/lmdb" then "cc" else null } = (buildRustPackages."registry+https://github.com/rust-lang/crates.io-index".cc."1.0.83" { profileName = "__noProfile"; }).out;
-      ${ if rootFeatures' ? "garage/lmdb" || rootFeatures' ? "garage_db/heed" || rootFeatures' ? "garage_db/lmdb" || rootFeatures' ? "garage_model/lmdb" then "pkg_config" else null } = (buildRustPackages."registry+https://github.com/rust-lang/crates.io-index".pkg-config."0.3.27" { profileName = "__noProfile"; }).out;
+      ${ if rootFeatures' ? "garage/default" || rootFeatures' ? "garage/lmdb" || rootFeatures' ? "garage_db/default" || rootFeatures' ? "garage_db/heed" || rootFeatures' ? "garage_db/lmdb" || rootFeatures' ? "garage_model/default" || rootFeatures' ? "garage_model/lmdb" then "cc" else null } = (buildRustPackages."registry+https://github.com/rust-lang/crates.io-index".cc."1.0.83" { profileName = "__noProfile"; }).out;
+      ${ if rootFeatures' ? "garage/default" || rootFeatures' ? "garage/lmdb" || rootFeatures' ? "garage_db/default" || rootFeatures' ? "garage_db/heed" || rootFeatures' ? "garage_db/lmdb" || rootFeatures' ? "garage_model/default" || rootFeatures' ? "garage_model/lmdb" then "pkg_config" else null } = (buildRustPackages."registry+https://github.com/rust-lang/crates.io-index".pkg-config."0.3.27" { profileName = "__noProfile"; }).out;
     };
   });
   
@@ -3219,11 +3224,11 @@ in
     src = fetchCratesIo { inherit name version; sha256 = "e5ce46fe64a9d73be07dcbe690a38ce1b293be448fd8ce1e6c1b8062c9f72c6a"; };
   });
   
-  "registry+https://github.com/rust-lang/crates.io-index".netapp."0.5.2" = overridableMkRustCrate (profileName: rec {
+  "registry+https://github.com/rust-lang/crates.io-index".netapp."0.10.0" = overridableMkRustCrate (profileName: rec {
     name = "netapp";
-    version = "0.5.2";
+    version = "0.10.0";
     registry = "registry+https://github.com/rust-lang/crates.io-index";
-    src = fetchCratesIo { inherit name version; sha256 = "4ffe47ac46d3b2ce2f736a70865492df082e042eb2bfdddfca3b8dd66bd9469d"; };
+    src = fetchCratesIo { inherit name version; sha256 = "0a00b76cec93e3ae68c9ed5f08e27a1507424987ee23d5ec961ebd4da820a265"; };
     features = builtins.concatLists [
       [ "default" ]
       [ "opentelemetry" ]
@@ -3245,7 +3250,7 @@ in
       opentelemetry_contrib = (rustPackages."registry+https://github.com/rust-lang/crates.io-index".opentelemetry-contrib."0.9.0" { inherit profileName; }).out;
       pin_project = (rustPackages."registry+https://github.com/rust-lang/crates.io-index".pin-project."1.1.3" { inherit profileName; }).out;
       rand = (rustPackages."registry+https://github.com/rust-lang/crates.io-index".rand."0.8.5" { inherit profileName; }).out;
-      rmp_serde = (rustPackages."registry+https://github.com/rust-lang/crates.io-index".rmp-serde."0.15.5" { inherit profileName; }).out;
+      rmp_serde = (rustPackages."registry+https://github.com/rust-lang/crates.io-index".rmp-serde."1.1.2" { inherit profileName; }).out;
       serde = (rustPackages."registry+https://github.com/rust-lang/crates.io-index".serde."1.0.188" { inherit profileName; }).out;
       tokio = (rustPackages."registry+https://github.com/rust-lang/crates.io-index".tokio."1.32.0" { inherit profileName; }).out;
       tokio_stream = (rustPackages."registry+https://github.com/rust-lang/crates.io-index".tokio-stream."0.1.14" { inherit profileName; }).out;
@@ -3480,7 +3485,7 @@ in
       [ "default" ]
       [ "race" ]
       [ "std" ]
-      (lib.optional (rootFeatures' ? "garage/bundled-libs" || rootFeatures' ? "garage/default" || rootFeatures' ? "garage/kubernetes-discovery" || rootFeatures' ? "garage/sqlite" || rootFeatures' ? "garage_db/bundled-libs" || rootFeatures' ? "garage_db/rusqlite" || rootFeatures' ? "garage_db/sqlite" || rootFeatures' ? "garage_model/sqlite" || rootFeatures' ? "garage_rpc/kube" || rootFeatures' ? "garage_rpc/kubernetes-discovery") "unstable")
+      (lib.optional (rootFeatures' ? "garage/bundled-libs" || rootFeatures' ? "garage/default" || rootFeatures' ? "garage/kubernetes-discovery" || rootFeatures' ? "garage/sqlite" || rootFeatures' ? "garage_db/bundled-libs" || rootFeatures' ? "garage_db/default" || rootFeatures' ? "garage_db/rusqlite" || rootFeatures' ? "garage_db/sqlite" || rootFeatures' ? "garage_model/default" || rootFeatures' ? "garage_model/sqlite" || rootFeatures' ? "garage_rpc/kube" || rootFeatures' ? "garage_rpc/kubernetes-discovery") "unstable")
     ];
   });
   
@@ -3618,8 +3623,8 @@ in
     registry = "registry+https://github.com/rust-lang/crates.io-index";
     src = fetchCratesIo { inherit name version; sha256 = "eebde548fbbf1ea81a99b128872779c437752fb99f217c45245e1a61dcd9edcd"; };
     dependencies = {
-      ${ if (rootFeatures' ? "garage/lmdb" || rootFeatures' ? "garage_db/heed" || rootFeatures' ? "garage_db/lmdb" || rootFeatures' ? "garage_model/lmdb") && hostPlatform.isUnix then "libc" else null } = (rustPackages."registry+https://github.com/rust-lang/crates.io-index".libc."0.2.147" { inherit profileName; }).out;
-      ${ if (rootFeatures' ? "garage/lmdb" || rootFeatures' ? "garage_db/heed" || rootFeatures' ? "garage_db/lmdb" || rootFeatures' ? "garage_model/lmdb") && hostPlatform.isWindows then "winapi" else null } = (rustPackages."registry+https://github.com/rust-lang/crates.io-index".winapi."0.3.9" { inherit profileName; }).out;
+      ${ if (rootFeatures' ? "garage/default" || rootFeatures' ? "garage/lmdb" || rootFeatures' ? "garage_db/default" || rootFeatures' ? "garage_db/heed" || rootFeatures' ? "garage_db/lmdb" || rootFeatures' ? "garage_model/default" || rootFeatures' ? "garage_model/lmdb") && hostPlatform.isUnix then "libc" else null } = (rustPackages."registry+https://github.com/rust-lang/crates.io-index".libc."0.2.147" { inherit profileName; }).out;
+      ${ if (rootFeatures' ? "garage/default" || rootFeatures' ? "garage/lmdb" || rootFeatures' ? "garage_db/default" || rootFeatures' ? "garage_db/heed" || rootFeatures' ? "garage_db/lmdb" || rootFeatures' ? "garage_model/default" || rootFeatures' ? "garage_model/lmdb") && hostPlatform.isWindows then "winapi" else null } = (rustPackages."registry+https://github.com/rust-lang/crates.io-index".winapi."0.3.9" { inherit profileName; }).out;
     };
   });
   
@@ -4310,11 +4315,11 @@ in
     };
   });
   
-  "registry+https://github.com/rust-lang/crates.io-index".rmp-serde."0.15.5" = overridableMkRustCrate (profileName: rec {
+  "registry+https://github.com/rust-lang/crates.io-index".rmp-serde."1.1.2" = overridableMkRustCrate (profileName: rec {
     name = "rmp-serde";
-    version = "0.15.5";
+    version = "1.1.2";
     registry = "registry+https://github.com/rust-lang/crates.io-index";
-    src = fetchCratesIo { inherit name version; sha256 = "723ecff9ad04f4ad92fe1c8ca6c20d2196d9286e9c60727c4cb5511629260e9d"; };
+    src = fetchCratesIo { inherit name version; sha256 = "bffea85eea980d8a74453e5d02a8d93028f3c34725de143085a844ebe953258a"; };
     dependencies = {
       byteorder = (rustPackages."registry+https://github.com/rust-lang/crates.io-index".byteorder."1.4.3" { inherit profileName; }).out;
       rmp = (rustPackages."registry+https://github.com/rust-lang/crates.io-index".rmp."0.8.12" { inherit profileName; }).out;
@@ -4347,12 +4352,12 @@ in
       (lib.optional (rootFeatures' ? "garage/bundled-libs" || rootFeatures' ? "garage/default" || rootFeatures' ? "garage_db/bundled-libs") "modern_sqlite")
     ];
     dependencies = {
-      ${ if rootFeatures' ? "garage/bundled-libs" || rootFeatures' ? "garage/default" || rootFeatures' ? "garage/sqlite" || rootFeatures' ? "garage_db/bundled-libs" || rootFeatures' ? "garage_db/rusqlite" || rootFeatures' ? "garage_db/sqlite" || rootFeatures' ? "garage_model/sqlite" then "bitflags" else null } = (rustPackages."registry+https://github.com/rust-lang/crates.io-index".bitflags."2.4.0" { inherit profileName; }).out;
-      ${ if rootFeatures' ? "garage/bundled-libs" || rootFeatures' ? "garage/default" || rootFeatures' ? "garage/sqlite" || rootFeatures' ? "garage_db/bundled-libs" || rootFeatures' ? "garage_db/rusqlite" || rootFeatures' ? "garage_db/sqlite" || rootFeatures' ? "garage_model/sqlite" then "fallible_iterator" else null } = (rustPackages."registry+https://github.com/rust-lang/crates.io-index".fallible-iterator."0.2.0" { inherit profileName; }).out;
-      ${ if rootFeatures' ? "garage/bundled-libs" || rootFeatures' ? "garage/default" || rootFeatures' ? "garage/sqlite" || rootFeatures' ? "garage_db/bundled-libs" || rootFeatures' ? "garage_db/rusqlite" || rootFeatures' ? "garage_db/sqlite" || rootFeatures' ? "garage_model/sqlite" then "fallible_streaming_iterator" else null } = (rustPackages."registry+https://github.com/rust-lang/crates.io-index".fallible-streaming-iterator."0.1.9" { inherit profileName; }).out;
-      ${ if rootFeatures' ? "garage/bundled-libs" || rootFeatures' ? "garage/default" || rootFeatures' ? "garage/sqlite" || rootFeatures' ? "garage_db/bundled-libs" || rootFeatures' ? "garage_db/rusqlite" || rootFeatures' ? "garage_db/sqlite" || rootFeatures' ? "garage_model/sqlite" then "hashlink" else null } = (rustPackages."registry+https://github.com/rust-lang/crates.io-index".hashlink."0.8.3" { inherit profileName; }).out;
-      ${ if rootFeatures' ? "garage/bundled-libs" || rootFeatures' ? "garage/default" || rootFeatures' ? "garage/sqlite" || rootFeatures' ? "garage_db/bundled-libs" || rootFeatures' ? "garage_db/rusqlite" || rootFeatures' ? "garage_db/sqlite" || rootFeatures' ? "garage_model/sqlite" then "libsqlite3_sys" else null } = (rustPackages."registry+https://github.com/rust-lang/crates.io-index".libsqlite3-sys."0.26.0" { inherit profileName; }).out;
-      ${ if rootFeatures' ? "garage/bundled-libs" || rootFeatures' ? "garage/default" || rootFeatures' ? "garage/sqlite" || rootFeatures' ? "garage_db/bundled-libs" || rootFeatures' ? "garage_db/rusqlite" || rootFeatures' ? "garage_db/sqlite" || rootFeatures' ? "garage_model/sqlite" then "smallvec" else null } = (rustPackages."registry+https://github.com/rust-lang/crates.io-index".smallvec."1.11.0" { inherit profileName; }).out;
+      ${ if rootFeatures' ? "garage/bundled-libs" || rootFeatures' ? "garage/default" || rootFeatures' ? "garage/sqlite" || rootFeatures' ? "garage_db/bundled-libs" || rootFeatures' ? "garage_db/default" || rootFeatures' ? "garage_db/rusqlite" || rootFeatures' ? "garage_db/sqlite" || rootFeatures' ? "garage_model/default" || rootFeatures' ? "garage_model/sqlite" then "bitflags" else null } = (rustPackages."registry+https://github.com/rust-lang/crates.io-index".bitflags."2.4.0" { inherit profileName; }).out;
+      ${ if rootFeatures' ? "garage/bundled-libs" || rootFeatures' ? "garage/default" || rootFeatures' ? "garage/sqlite" || rootFeatures' ? "garage_db/bundled-libs" || rootFeatures' ? "garage_db/default" || rootFeatures' ? "garage_db/rusqlite" || rootFeatures' ? "garage_db/sqlite" || rootFeatures' ? "garage_model/default" || rootFeatures' ? "garage_model/sqlite" then "fallible_iterator" else null } = (rustPackages."registry+https://github.com/rust-lang/crates.io-index".fallible-iterator."0.2.0" { inherit profileName; }).out;
+      ${ if rootFeatures' ? "garage/bundled-libs" || rootFeatures' ? "garage/default" || rootFeatures' ? "garage/sqlite" || rootFeatures' ? "garage_db/bundled-libs" || rootFeatures' ? "garage_db/default" || rootFeatures' ? "garage_db/rusqlite" || rootFeatures' ? "garage_db/sqlite" || rootFeatures' ? "garage_model/default" || rootFeatures' ? "garage_model/sqlite" then "fallible_streaming_iterator" else null } = (rustPackages."registry+https://github.com/rust-lang/crates.io-index".fallible-streaming-iterator."0.1.9" { inherit profileName; }).out;
+      ${ if rootFeatures' ? "garage/bundled-libs" || rootFeatures' ? "garage/default" || rootFeatures' ? "garage/sqlite" || rootFeatures' ? "garage_db/bundled-libs" || rootFeatures' ? "garage_db/default" || rootFeatures' ? "garage_db/rusqlite" || rootFeatures' ? "garage_db/sqlite" || rootFeatures' ? "garage_model/default" || rootFeatures' ? "garage_model/sqlite" then "hashlink" else null } = (rustPackages."registry+https://github.com/rust-lang/crates.io-index".hashlink."0.8.3" { inherit profileName; }).out;
+      ${ if rootFeatures' ? "garage/bundled-libs" || rootFeatures' ? "garage/default" || rootFeatures' ? "garage/sqlite" || rootFeatures' ? "garage_db/bundled-libs" || rootFeatures' ? "garage_db/default" || rootFeatures' ? "garage_db/rusqlite" || rootFeatures' ? "garage_db/sqlite" || rootFeatures' ? "garage_model/default" || rootFeatures' ? "garage_model/sqlite" then "libsqlite3_sys" else null } = (rustPackages."registry+https://github.com/rust-lang/crates.io-index".libsqlite3-sys."0.26.0" { inherit profileName; }).out;
+      ${ if rootFeatures' ? "garage/bundled-libs" || rootFeatures' ? "garage/default" || rootFeatures' ? "garage/sqlite" || rootFeatures' ? "garage_db/bundled-libs" || rootFeatures' ? "garage_db/default" || rootFeatures' ? "garage_db/rusqlite" || rootFeatures' ? "garage_db/sqlite" || rootFeatures' ? "garage_model/default" || rootFeatures' ? "garage_model/sqlite" then "smallvec" else null } = (rustPackages."registry+https://github.com/rust-lang/crates.io-index".smallvec."1.11.0" { inherit profileName; }).out;
     };
   });
   
@@ -5016,7 +5021,7 @@ in
     registry = "registry+https://github.com/rust-lang/crates.io-index";
     src = fetchCratesIo { inherit name version; sha256 = "3dbc01390fc626ce8d1cffe3376ded2b72a11bb70e1c75f404a210e4daa4def2"; };
     dependencies = {
-      ${ if rootFeatures' ? "garage/lmdb" || rootFeatures' ? "garage_db/heed" || rootFeatures' ? "garage_db/lmdb" || rootFeatures' ? "garage_model/lmdb" then "crossbeam_queue" else null } = (rustPackages."registry+https://github.com/rust-lang/crates.io-index".crossbeam-queue."0.3.8" { inherit profileName; }).out;
+      ${ if rootFeatures' ? "garage/default" || rootFeatures' ? "garage/lmdb" || rootFeatures' ? "garage_db/default" || rootFeatures' ? "garage_db/heed" || rootFeatures' ? "garage_db/lmdb" || rootFeatures' ? "garage_model/default" || rootFeatures' ? "garage_model/lmdb" then "crossbeam_queue" else null } = (rustPackages."registry+https://github.com/rust-lang/crates.io-index".crossbeam-queue."0.3.8" { inherit profileName; }).out;
     };
   });
   

Cargo.toml

@@ -18,14 +18,14 @@ default-members = ["src/garage"]
 
 [workspace.dependencies]
 format_table = { version = "0.1.1", path = "src/format-table" }
-garage_api = { version = "0.8.5", path = "src/api" }
-garage_block = { version = "0.8.5", path = "src/block" }
-garage_db = { version = "0.8.5", path = "src/db", default-features = false }
-garage_model = { version = "0.8.5", path = "src/model", default-features = false }
-garage_rpc = { version = "0.8.5", path = "src/rpc" }
-garage_table = { version = "0.8.5", path = "src/table" }
-garage_util = { version = "0.8.5", path = "src/util" }
-garage_web = { version = "0.8.5", path = "src/web" }
+garage_api = { version = "0.9.1", path = "src/api" }
+garage_block = { version = "0.9.1", path = "src/block" }
+garage_db = { version = "0.9.1", path = "src/db", default-features = false }
+garage_model = { version = "0.9.1", path = "src/model", default-features = false }
+garage_rpc = { version = "0.9.1", path = "src/rpc" }
+garage_table = { version = "0.9.1", path = "src/table" }
+garage_util = { version = "0.9.1", path = "src/util" }
+garage_web = { version = "0.9.1", path = "src/web" }
 k2v-client = { version = "0.0.4", path = "src/k2v-client" }
 
 [profile.dev]

doc/api/garage-admin-v1.html

@@ -0,0 +1,24 @@
+<!DOCTYPE html>
+<html>
+  <head>
+    <title>Garage Adminstration API v0</title>
+    <!-- needed for adaptive design -->
+    <meta charset="utf-8"/>
+    <meta name="viewport" content="width=device-width, initial-scale=1">
+    <link href="./css/redoc.css" rel="stylesheet">
+
+    <!--
+    Redoc doesn't change outer page styles
+    -->
+    <style>
+      body {
+        margin: 0;
+        padding: 0;
+      }
+    </style>
+  </head>
+  <body>
+    <redoc spec-url='./garage-admin-v1.yml'></redoc>
+    <script src="./redoc.standalone.js"> </script>
+  </body>
+</html>

doc/book/build/golang.md

@@ -37,30 +37,84 @@ import (
     "context"
     "fmt"
     "os"
+    "strings"
     garage "git.deuxfleurs.fr/garage-sdk/garage-admin-sdk-golang"
 )
 
 func main() {
-    // Set Host and other parameters
+    // Initialization
     configuration := garage.NewConfiguration()
     configuration.Host = "127.0.0.1:3903"
-
-
-    // We can now generate a client
     client := garage.NewAPIClient(configuration)
-
-    // Authentication is handled through the context pattern
     ctx := context.WithValue(context.Background(), garage.ContextAccessToken, "s3cr3t")
 
-    // Send a request
-    resp, r, err := client.NodesApi.GetNodes(ctx).Execute()
-    if err != nil {
-        fmt.Fprintf(os.Stderr, "Error when calling `NodesApi.GetNodes``: %v\n", err)
-        fmt.Fprintf(os.Stderr, "Full HTTP response: %v\n", r)
+    // Nodes
+    fmt.Println("--- nodes ---")
+    nodes, _, _ := client.NodesApi.GetNodes(ctx).Execute()
+    fmt.Fprintf(os.Stdout, "First hostname: %v\n", nodes.KnownNodes[0].Hostname)
+    capa := int64(1000000000)
+    change := []garage.NodeRoleChange{
+	    garage.NodeRoleChange{NodeRoleUpdate: &garage.NodeRoleUpdate {
+	        Id: *nodes.KnownNodes[0].Id,
+	        Zone: "dc1",
+	        Capacity: *garage.NewNullableInt64(&capa),
+	        Tags: []string{ "fast", "amd64" },
+	    }},
     }
+    staged, _, _ := client.LayoutApi.AddLayout(ctx).NodeRoleChange(change).Execute()
+    msg, _, _ := client.LayoutApi.ApplyLayout(ctx).LayoutVersion(*garage.NewLayoutVersion(staged.Version + 1)).Execute()
+    fmt.Printf(strings.Join(msg.Message, "\n")) // Layout configured
 
-    // Process the response
-    fmt.Fprintf(os.Stdout, "Target hostname: %v\n", resp.KnownNodes[resp.Node].Hostname)
+    health, _, _ := client.NodesApi.GetHealth(ctx).Execute()
+    fmt.Printf("Status: %s, nodes: %v/%v, storage: %v/%v, partitions: %v/%v\n", health.Status, health.ConnectedNodes, health.KnownNodes, health.StorageNodesOk, health.StorageNodes, health.PartitionsAllOk, health.Partitions)
+
+    // Key
+    fmt.Println("\n--- key ---")
+    key := "openapi-key"
+    keyInfo, _, _ := client.KeyApi.AddKey(ctx).AddKeyRequest(garage.AddKeyRequest{Name: *garage.NewNullableString(&key) }).Execute()
+    defer client.KeyApi.DeleteKey(ctx).Id(*keyInfo.AccessKeyId).Execute()
+    fmt.Printf("AWS_ACCESS_KEY_ID=%s\nAWS_SECRET_ACCESS_KEY=%s\n", *keyInfo.AccessKeyId, *keyInfo.SecretAccessKey.Get())
+
+    id := *keyInfo.AccessKeyId
+    canCreateBucket := true
+    updateKeyRequest := *garage.NewUpdateKeyRequest()
+    updateKeyRequest.SetName("openapi-key-updated")
+    updateKeyRequest.SetAllow(garage.UpdateKeyRequestAllow { CreateBucket: &canCreateBucket })
+    update, _, _ := client.KeyApi.UpdateKey(ctx).Id(id).UpdateKeyRequest(updateKeyRequest).Execute()
+    fmt.Printf("Updated %v with key name %v\n", *update.AccessKeyId, *update.Name)
+
+    keyList, _, _ := client.KeyApi.ListKeys(ctx).Execute()
+    fmt.Printf("Keys count: %v\n", len(keyList))
+
+    // Bucket
+    fmt.Println("\n--- bucket ---")
+    global_name := "global-ns-openapi-bucket"
+    local_name := "local-ns-openapi-bucket"
+    bucketInfo, _, _ := client.BucketApi.CreateBucket(ctx).CreateBucketRequest(garage.CreateBucketRequest{
+        GlobalAlias: &global_name,
+        LocalAlias: &garage.CreateBucketRequestLocalAlias {
+            AccessKeyId: keyInfo.AccessKeyId,
+	    Alias: &local_name,
+        },
+    }).Execute()
+    defer client.BucketApi.DeleteBucket(ctx).Id(*bucketInfo.Id).Execute()
+    fmt.Printf("Bucket id: %s\n", *bucketInfo.Id)
+
+    updateBucketRequest := *garage.NewUpdateBucketRequest()
+    website := garage.NewUpdateBucketRequestWebsiteAccess()
+    website.SetEnabled(true)
+    website.SetIndexDocument("index.html")
+    website.SetErrorDocument("errors/4xx.html")
+    updateBucketRequest.SetWebsiteAccess(*website)
+    quotas := garage.NewUpdateBucketRequestQuotas()
+    quotas.SetMaxSize(1000000000)
+    quotas.SetMaxObjects(999999999)
+    updateBucketRequest.SetQuotas(*quotas)
+    updatedBucket, _, _ := client.BucketApi.UpdateBucket(ctx).Id(*bucketInfo.Id).UpdateBucketRequest(updateBucketRequest).Execute()
+    fmt.Printf("Bucket %v website activation: %v\n", *updatedBucket.Id, *updatedBucket.WebsiteAccess)
+
+    bucketList, _, _ := client.BucketApi.ListBuckets(ctx).Execute()
+    fmt.Printf("Bucket count: %v\n", len(bucketList))
 }
 ```
 

doc/book/build/javascript.md

@@ -31,9 +31,9 @@ npm install --save git+https://git.deuxfleurs.fr/garage-sdk/garage-admin-sdk-js.
 A short example:
 
 ```javascript
-const garage = require('garage_administration_api_v0garage_v0_8_0');
+const garage = require('garage_administration_api_v1garage_v0_9_0');
 
-const api = new garage.ApiClient("http://127.0.0.1:3903/v0");
+const api = new garage.ApiClient("http://127.0.0.1:3903/v1");
 api.authentications['bearerAuth'].accessToken = "s3cr3t";
 
 const [node, layout, key, bucket] = [

doc/book/build/python.md

@@ -80,7 +80,7 @@ from garage_admin_sdk.apis import *
 from garage_admin_sdk.models import *
 
 configuration = garage_admin_sdk.Configuration(
-  host = "http://localhost:3903/v0",
+  host = "http://localhost:3903/v1",
   access_token = "s3cr3t"
 )
 
@@ -94,13 +94,14 @@ print(f"running garage {status.garage_version}, node_id {status.node}")
 
 # Change layout of this node
 current = layout.get_layout()
-layout.add_layout({
-  status.node: NodeClusterInfo(
+layout.add_layout([
+  NodeRoleChange(
+    id = status.node,
     zone = "dc1",
-    capacity = 1,
+    capacity = 1000000000,
     tags = [ "dev" ],
   )
-})
+])
 layout.apply_layout(LayoutVersion(
   version = current.version + 1
 ))

doc/book/connect/apps/index.md

@@ -37,7 +37,7 @@ Second, we suppose you have created a key and a bucket.
 As a reminder, you can create a key for your nextcloud instance as follow:
 
 ```bash
-garage key new --name nextcloud-key
+garage key create nextcloud-key
 ```
 
 Keep the Key ID and the Secret key in a pad, they will be needed later.  
@@ -139,14 +139,14 @@ a reasonable trade-off for some instances.
 Create a key for Peertube:
 
 ```bash
-garage key new --name peertube-key
+garage key create peertube-key
 ```
 
 Keep the Key ID and the Secret key in a pad, they will be needed later.  
 
 We need two buckets, one for normal videos (named peertube-video) and one for webtorrent videos (named peertube-playlist).
 ```bash
-garage bucket create peertube-video
+garage bucket create peertube-videos
 garage bucket create peertube-playlist
 ```
 
@@ -216,7 +216,7 @@ object_storage:
 
   # Same settings but for webtorrent videos
   videos:
-    bucket_name: 'peertube-video'
+    bucket_name: 'peertube-videos'
     prefix: ''
     # You must fill this field to make Peertube use our reverse proxy/website logic
     base_url: 'http://peertube-videos.web.garage.localhost'
@@ -253,7 +253,7 @@ As such, your Garage cluster should be configured appropriately for good perform
 This is the usual Garage setup:
 
 ```bash
-garage key new --name mastodon-key
+garage key create mastodon-key
 garage bucket create mastodon-data
 garage bucket allow mastodon-data --read --write --key mastodon-key
 ```
@@ -379,7 +379,7 @@ Supposing you have a working synapse installation, you can add the module with p
 Now create a bucket and a key for your matrix instance (note your Key ID and Secret Key somewhere, they will be needed later):
 
 ```bash
-garage key new --name matrix-key
+garage key create matrix-key
 garage bucket create matrix
 garage bucket allow matrix --read --write --key matrix-key
 ```

doc/book/connect/backup.md

@@ -54,7 +54,7 @@ how to configure this.
 Create your key and bucket:
 
 ```bash
-garage key new my-key
+garage key create my-key
 garage bucket create backup
 garage bucket allow backup --read --write --key my-key
 ```

doc/book/connect/repositories.md

@@ -23,7 +23,7 @@ You can configure a different target for each data type (check `[lfs]` and `[att
 Let's start by creating a key and a bucket (your key id and secret will be needed later, keep them somewhere):
 
 ```bash
-garage key new --name gitea-key
+garage key create gitea-key
 garage bucket create gitea
 garage bucket allow gitea --read --write --key gitea-key
 ```
@@ -118,7 +118,7 @@ through another support, like a git repository.
 As a first step, we will need to create a bucket on Garage and enabling website access on it:
 
 ```bash
-garage key new --name nix-key
+garage key create nix-key
 garage bucket create nix.example.com
 garage bucket allow nix.example.com --read --write --key nix-key
 garage bucket website nix.example.com --allow

doc/book/cookbook/exposing-websites.md

@@ -38,7 +38,7 @@ Our website serving logic is as follow:
 
 Now we need to infer the URL of your website through your bucket name.
 Let assume:
-  - we set `root_domain = ".web.example.com"` in `garage.toml` ([ref](@/documentation/reference-manual/configuration.md#root_domain))
+  - we set `root_domain = ".web.example.com"` in `garage.toml` ([ref](@/documentation/reference-manual/configuration.md#web_root_domain))
   - our bucket name is `garagehq.deuxfleurs.fr`.
 
 Our bucket will be served if the Host field matches one of these 2 values (the port is ignored):

doc/book/cookbook/real-world.md

@@ -19,9 +19,10 @@ To run a real-world deployment, make sure the following conditions are met:
 
 - You have at least three machines with sufficient storage space available.
 
-- Each machine has a public IP address which is reachable by other machines. It
-  is highly recommended that you use IPv6 for this end-to-end connectivity. If
-  IPv6 is not available, then using a mesh VPN such as
+- Each machine has an IP address which makes it directly reachable by all other machines.
+  In many cases, nodes will be behind a NAT and will not each have a public
+  IPv4 addresses. In this case, is recommended that you use IPv6 for this
+  end-to-end connectivity if it is available. Otherwise, using a mesh VPN such as
   [Nebula](https://github.com/slackhq/nebula) or
   [Yggdrasil](https://yggdrasil-network.github.io/) are approaches to consider
   in addition to building out your own VPN tunneling.
@@ -42,7 +43,7 @@ For our example, we will suppose the following infrastructure with IPv6 connecti
 | Brussels | Mars    | fc00:F::1  | 1.5 TB     |
 
 Note that Garage will **always** store the three copies of your data on nodes at different
-locations. This means that in the case of this small example, the available capacity
+locations. This means that in the case of this small example, the usable capacity
 of the cluster is in fact only 1.5 TB, because nodes in Brussels can't store more than that.
 This also means that nodes in Paris and London will be under-utilized.
 To make better use of the available hardware, you should ensure that the capacity
@@ -75,28 +76,23 @@ to store 2 TB of data in total.
 
 - For the metadata storage, Garage does not do checksumming and integrity
   verification on its own. If you are afraid of bitrot/data corruption,
-  put your metadata directory on a BTRFS partition. Otherwise, just use regular
+  put your metadata directory on a ZFS or BTRFS partition. Otherwise, just use regular
   EXT4 or XFS.
 
-- Having a single server with several storage drives is currently not very well
-  supported in Garage ([#218](https://git.deuxfleurs.fr/Deuxfleurs/garage/issues/218)).
-  For an easy setup, just put all your drives in a RAID0 or a ZFS RAIDZ array.
-  If you're adventurous, you can try to format each of your disk as
-  a separate XFS partition, and then run one `garage` daemon per disk drive,
-  or use something like [`mergerfs`](https://github.com/trapexit/mergerfs) to merge
-  all your disks in a single union filesystem that spreads load over them.
+- Servers with multiple HDDs are supported natively by Garage without resorting
+  to RAID, see [our dedicated documentation page](@/documentation/operations/multi-hdd.md).
 
 ## Get a Docker image
 
 Our docker image is currently named `dxflrs/garage` and is stored on the [Docker Hub](https://hub.docker.com/r/dxflrs/garage/tags?page=1&ordering=last_updated).
-We encourage you to use a fixed tag (eg. `v0.8.0`) and not the `latest` tag.
-For this example, we will use the latest published version at the time of the writing which is `v0.8.0` but it's up to you
+We encourage you to use a fixed tag (eg. `v0.9.1`) and not the `latest` tag.
+For this example, we will use the latest published version at the time of the writing which is `v0.9.1` but it's up to you
 to check [the most recent versions on the Docker Hub](https://hub.docker.com/r/dxflrs/garage/tags?page=1&ordering=last_updated).
 
 For example:
 
 ```
-sudo docker pull dxflrs/garage:v0.8.0
+sudo docker pull dxflrs/garage:v0.9.1
 ```
 
 ## Deploying and configuring Garage
@@ -161,12 +157,13 @@ docker run \
   -v /etc/garage.toml:/etc/garage.toml \
   -v /var/lib/garage/meta:/var/lib/garage/meta \
   -v /var/lib/garage/data:/var/lib/garage/data \
-  dxflrs/garage:v0.8.0
+  dxflrs/garage:v0.9.1
 ```
 
-It should be restarted automatically at each reboot.
-Please note that we use host networking as otherwise Docker containers
-can not communicate with IPv6.
+With this command line, Garage should be started automatically at each boot.
+Please note that we use host networking as otherwise the network indirection
+added by Docker would prevent Garage nodes from communicating with one another
+(especially if using IPv6).
 
 If you want to use `docker-compose`, you may use the following `docker-compose.yml` file as a reference:
 
@@ -174,7 +171,7 @@ If you want to use `docker-compose`, you may use the following `docker-compose.y
 version: "3"
 services:
   garage:
-    image: dxflrs/garage:v0.8.0
+    image: dxflrs/garage:v0.9.1
     network_mode: "host"
     restart: unless-stopped
     volumes:
@@ -183,10 +180,12 @@ services:
       - /var/lib/garage/data:/var/lib/garage/data
 ```
 
-Upgrading between Garage versions should be supported transparently,
-but please check the relase notes before doing so!
-To upgrade, simply stop and remove this container and
-start again the command with a new version of Garage.
+If you wish to upgrade your cluster, make sure to read the corresponding
+[documentation page](@/documentation/operations/upgrading.md) first, as well as
+the documentation relevant to your version of Garage in the case of major
+upgrades.  With the containerized setup proposed here, the upgrade process
+will require stopping and removing the existing container, and re-creating it
+with the upgraded version.
 
 ## Controling the daemon
 
@@ -270,12 +269,12 @@ of a role that is assigned to each active cluster node.
 For our example, we will suppose we have the following infrastructure
 (Capacity, Identifier and Zone are specific values to Garage described in the following):
 
-| Location | Name    | Disk Space | `Capacity` | `Identifier` | `Zone` |
-|----------|---------|------------|------------|--------------|--------------|
-| Paris    | Mercury | 1 TB       | `10`       | `563e`     | `par1`       |
-| Paris    | Venus   | 2 TB       | `20`       | `86f0`     | `par1`       |
-| London   | Earth   | 2 TB       | `20`       | `6814`     | `lon1`       |
-| Brussels | Mars    | 1.5 TB     | `15`       | `212f`     | `bru1`       |
+| Location | Name    | Disk Space | Identifier | Zone (`-z`) | Capacity (`-c`) |
+|----------|---------|------------|------------|-------------|-----------------|
+| Paris    | Mercury | 1 TB       | `563e`     | `par1`      | `1T`            |
+| Paris    | Venus   | 2 TB       | `86f0`     | `par1`      | `2T`            |
+| London   | Earth   | 2 TB       | `6814`     | `lon1`      | `2T`            |
+| Brussels | Mars    | 1.5 TB     | `212f`     | `bru1`      | `1.5T`          |
 
 #### Node identifiers
 
@@ -297,6 +296,8 @@ garage status
 It will display the IP address associated with each node;
 from the IP address you will be able to recognize the node.
 
+We will now use the `garage layout assign` command to configure the correct parameters for each node.
+
 #### Zones
 
 Zones are simply a user-chosen identifier that identify a group of server that are grouped together logically.
@@ -306,29 +307,29 @@ In most cases, a zone will correspond to a geographical location (i.e. a datacen
 Behind the scene, Garage will use zone definition to try to store the same data on different zones,
 in order to provide high availability despite failure of a zone.
 
+Zones are passed to Garage using the `-z` flag of `garage layout assign` (see below).
+
 #### Capacity
 
-Garage reasons on an abstract metric about disk storage that is named the *capacity* of a node.
-The capacity configured in Garage must be proportional to the disk space dedicated to the node.
+Garage needs to know the storage capacity (disk space) it can/should use on
+each node, to be able to correctly balance data.
 
-Capacity values must be **integers** but can be given any signification.
-Here we chose that 1 unit of capacity = 100 GB.
+Capacity values are expressed in bytes and are passed to Garage using the `-c` flag of `garage layout assign` (see below).
 
-Note that the amount of data stored by Garage on each server may not be strictly proportional to
-its capacity value, as Garage will priorize having 3 copies of data in different zones,
-even if this means that capacities will not be strictly respected. For example in our above examples,
-nodes Earth and Mars will always store a copy of everything each, and the third copy will
-have 66% chance of being stored by Venus and 33% chance of being stored by Mercury.
+#### Tags
+
+You can add additional tags to nodes using the `-t` flag of `garage layout assign` (see below).
+Tags have no specific meaning for Garage and can be used at your convenience.
 
 #### Injecting the topology
 
 Given the information above, we will configure our cluster as follow:
 
 ```bash
-garage layout assign 563e -z par1 -c 10 -t mercury
-garage layout assign 86f0 -z par1 -c 20 -t venus
-garage layout assign 6814 -z lon1 -c 20 -t earth 
-garage layout assign 212f -z bru1 -c 15 -t mars 
+garage layout assign 563e -z par1 -c 1T -t mercury
+garage layout assign 86f0 -z par1 -c 2T -t venus
+garage layout assign 6814 -z lon1 -c 2T -t earth 
+garage layout assign 212f -z bru1 -c 1.5T -t mars 
 ```
 
 At this point, the changes in the cluster layout have not yet been applied.
@@ -338,6 +339,7 @@ To show the new layout that will be applied, call:
 garage layout show
 ```
 
+Make sure to read carefully the output of `garage layout show`.
 Once you are satisfied with your new layout, apply it with:
 
 ```bash

doc/book/operations/durability-repairs.md

@@ -91,6 +91,16 @@ is definitely lost, then there is no other choice than to declare your S3 object
 as unrecoverable, and to delete them properly from the data store. This can be done
 using the `garage block purge` command.
 
+## Rebalancing data directories
+
+In [multi-HDD setups](@/documentation/operations/multi-hdd.md), to ensure that
+data blocks are well balanced between storage locations, you may run a
+rebalance operation using `garage repair rebalance`. This is usefull when
+adding storage locations or when capacities of the storage locations have been
+changed.  Once this is finished, Garage will know for each block of a single
+possible location where it can be, which can increase access speed.  This
+operation will also move out all data from locations marked as read-only.
+
 
 # Metadata operations
 
@@ -114,4 +124,3 @@ in your cluster, you can run one of the following repair procedures:
 
 - `garage repair versions`: checks that all versions belong to a non-deleted object, and purges any orphan version
 - `garage repair block_refs`: checks that all block references belong to a non-deleted object version, and purges any orphan block reference (this will then allow the blocks to be garbage-collected)
-

doc/book/operations/layout.md

@@ -9,18 +9,30 @@ a certain capacity, or a gateway node that does not store data and is only
 used as an API entry point for faster cluster access.
 An introduction to building cluster layouts can be found in the [production deployment](@/documentation/cookbook/real-world.md) page.
 
+In Garage, all of the data that can be stored in a given cluster is divided
+into slices which we call *partitions*. Each partition is stored by
+one or several nodes in the cluster
+(see [`replication_mode`](@/documentation/reference-manual/configuration.md#replication_mode)).
+The layout determines the correspondence between these partition,
+which exist on a logical level, and actual storage nodes.
+
 ## How cluster layouts work in Garage
 
-In Garage, a cluster layout is composed of the following components:
+A cluster layout is composed of the following components:
 
-- a table of roles assigned to nodes
+- a table of roles assigned to nodes, defined by the user
+- an optimal assignation of partitions to nodes, computed by an algorithm that is ran once when calling `garage layout apply` or the ApplyClusterLayout API endpoint
 - a version number
 
 Garage nodes will always use the cluster layout with the highest version number.
 
 Garage nodes also maintain and synchronize between them a set of proposed role
 changes that haven't yet been applied. These changes will be applied (or
-canceled) in the next version of the layout
+canceled) in the next version of the layout.
+
+All operations on the layout can be realized using the `garage` CLI or using the
+[administration API endpoint](@/documentation/reference-manual/admin-api.md).
+We give here a description of CLI commands, the admin API semantics are very similar.
 
 The following commands insert modifications to the set of proposed role changes
 for the next layout version (but they do not create the new layout immediately):
@@ -51,7 +63,7 @@ commands will fail otherwise.
 
 ## Warnings about Garage cluster layout management
 
-**Warning: never make several calls to `garage layout apply` or `garage layout
+**⚠️ Never make several calls to `garage layout apply` or `garage layout
 revert` with the same value of the `--version` flag. Doing so can lead to the
 creation of several different layouts with the same version number, in which
 case your Garage cluster will become inconsistent until fixed.** If a call to
@@ -65,13 +77,198 @@ shell, you shouldn't have much issues as long as you run commands one after
 the other and take care of checking the output of `garage layout show`
 before applying any changes.
 
-If you are using the `garage` CLI to script layout changes, follow the following recommendations:
+If you are using the `garage` CLI or the admin API to script layout changes,
+follow the following recommendations:
 
-- Make all of your `garage` CLI calls to the same RPC host. Do not use the
-  `garage` CLI to connect to individual nodes to send them each a piece of the
-  layout changes you are making, as the changes propagate asynchronously
-  between nodes and might not all be taken into account at the time when the
-  new layout is applied.
+- If using the CLI, make all of your `garage` CLI calls to the same RPC host.
+  If using the admin API, make all of your API calls to the same Garage node. Do
+  not connect to individual nodes to send them each a piece of the layout changes
+  you are making, as the changes propagate asynchronously between nodes and might
+  not all be taken into account at the time when the new layout is applied.
 
-- **Only call `garage layout apply` once**, and call it **strictly after** all
-  of the `layout assign` and `layout remove` commands have returned.
+- **Only call `garage layout apply`/ApplyClusterLayout once**, and call it
+  **strictly after** all of the `layout assign` and `layout remove`
+  commands/UpdateClusterLayout API calls have returned.
+
+
+## Understanding unexpected layout calculations
+
+When adding, removing or modifying nodes in a cluster layout, sometimes
+unexpected assigntations of partitions to node can occur. These assignations
+are in fact normal and logical, given the objectives of the algorihtm.  Indeed,
+**the layout algorithm prioritizes moving less data between nodes over the fact
+of achieving equal distribution of load. It also tries to use all links between
+pairs of nodes in equal proportions when moving data.**  This section presents
+two examples and illustrates how one can control Garage's behavior to obtain
+the desired results.
+
+### Example 1
+
+In this example, a cluster is originally composed of 3 nodes in 3 different
+zones (data centers).  The three nodes are of equal capacity, therefore they
+are all fully exploited and all store a copy of all of the data in the cluster.
+
+Then, a fourth node of the same size is added in the datacenter `dc1`.
+As illustrated by the following, **Garage will by default not store any data on the new node**:
+
+```
+$ garage layout show
+==== CURRENT CLUSTER LAYOUT ====
+ID                Tags   Zone  Capacity   Usable capacity
+b10c110e4e854e5a  node1  dc1   1000.0 MB  1000.0 MB (100.0%)
+a235ac7695e0c54d  node2  dc2   1000.0 MB  1000.0 MB (100.0%)
+62b218d848e86a64  node3  dc3   1000.0 MB  1000.0 MB (100.0%)
+
+Zone redundancy: maximum
+
+Current cluster layout version: 6
+
+==== STAGED ROLE CHANGES ====
+ID                Tags   Zone  Capacity
+a11c7cf18af29737  node4  dc1   1000.0 MB
+
+
+==== NEW CLUSTER LAYOUT AFTER APPLYING CHANGES ====
+ID                Tags   Zone  Capacity   Usable capacity
+b10c110e4e854e5a  node1  dc1   1000.0 MB  1000.0 MB (100.0%)
+a11c7cf18af29737  node4  dc1   1000.0 MB  0 B (0.0%)
+a235ac7695e0c54d  node2  dc2   1000.0 MB  1000.0 MB (100.0%)
+62b218d848e86a64  node3  dc3   1000.0 MB  1000.0 MB (100.0%)
+
+Zone redundancy: maximum
+
+==== COMPUTATION OF A NEW PARTITION ASSIGNATION ====
+
+Partitions are replicated 3 times on at least 3 distinct zones.
+
+Optimal partition size:                     3.9 MB (3.9 MB in previous layout)
+Usable capacity / total cluster capacity:   3.0 GB / 4.0 GB (75.0 %)
+Effective capacity (replication factor 3):  1000.0 MB
+
+A total of 0 new copies of partitions need to be transferred.
+
+dc1                 Tags   Partitions        Capacity   Usable capacity
+  b10c110e4e854e5a  node1  256 (0 new)       1000.0 MB  1000.0 MB (100.0%)
+  a11c7cf18af29737  node4  0 (0 new)         1000.0 MB  0 B (0.0%)
+  TOTAL                    256 (256 unique)  2.0 GB     1000.0 MB (50.0%)
+
+dc2                 Tags   Partitions        Capacity   Usable capacity
+  a235ac7695e0c54d  node2  256 (0 new)       1000.0 MB  1000.0 MB (100.0%)
+  TOTAL                    256 (256 unique)  1000.0 MB  1000.0 MB (100.0%)
+
+dc3                 Tags   Partitions        Capacity   Usable capacity
+  62b218d848e86a64  node3  256 (0 new)       1000.0 MB  1000.0 MB (100.0%)
+  TOTAL                    256 (256 unique)  1000.0 MB  1000.0 MB (100.0%)
+```
+
+While unexpected, this is logical because of the following facts:
+
+- storing some data on the new node does not help increase the total quantity
+  of data that can be stored on the cluster, as the two other zones (`dc2` and
+  `dc3`) still need to store a full copy of everything, and their capacity is
+  still the same;
+
+- there is therefore no need to move any data on the new node as this would be pointless;
+
+- moving data to the new node has a cost which the algorithm decides to not pay if not necessary.
+
+This distribution of data can however not be what the administrator wanted: if
+they added a new node to `dc1`, it might be because the existing node is too
+slow, and they wish to divide its load by half. In that case, what they need to
+do to force Garage to distribute the data between the two nodes is to attribute
+only half of the capacity to each node in `dc1` (in our example, 500M instead of 1G).
+In that case, Garage would determine that to be able to store 1G in total, it
+would need to store 500M on the old node and 500M on the added one.
+
+
+### Example 2
+
+The following example is a slightly different scenario, where `dc1` had two
+nodes that were used at 50%, and `dc2` and `dc3` each have one node that is
+100% used. All node capacities are the same.
+
+Then, a node from `dc1` is moved into `dc3`. One could expect that the roles of
+`dc1` and `dc3` would simply be swapped: the remaining node in `dc1` would be
+used at 100%, and the two nodes now in `dc3` would be used at 50%. Instead,
+this happens:
+
+```
+==== CURRENT CLUSTER LAYOUT ====
+ID                Tags   Zone  Capacity   Usable capacity
+b10c110e4e854e5a  node1  dc1   1000.0 MB  500.0 MB (50.0%)
+a11c7cf18af29737  node4  dc1   1000.0 MB  500.0 MB (50.0%)
+a235ac7695e0c54d  node2  dc2   1000.0 MB  1000.0 MB (100.0%)
+62b218d848e86a64  node3  dc3   1000.0 MB  1000.0 MB (100.0%)
+
+Zone redundancy: maximum
+
+Current cluster layout version: 8
+
+==== STAGED ROLE CHANGES ====
+ID                Tags   Zone  Capacity
+a11c7cf18af29737  node4  dc3   1000.0 MB
+
+
+==== NEW CLUSTER LAYOUT AFTER APPLYING CHANGES ====
+ID                Tags   Zone  Capacity   Usable capacity
+b10c110e4e854e5a  node1  dc1   1000.0 MB  1000.0 MB (100.0%)
+a235ac7695e0c54d  node2  dc2   1000.0 MB  1000.0 MB (100.0%)
+62b218d848e86a64  node3  dc3   1000.0 MB  753.9 MB (75.4%)
+a11c7cf18af29737  node4  dc3   1000.0 MB  246.1 MB (24.6%)
+
+Zone redundancy: maximum
+
+==== COMPUTATION OF A NEW PARTITION ASSIGNATION ====
+
+Partitions are replicated 3 times on at least 3 distinct zones.
+
+Optimal partition size:                     3.9 MB (3.9 MB in previous layout)
+Usable capacity / total cluster capacity:   3.0 GB / 4.0 GB (75.0 %)
+Effective capacity (replication factor 3):  1000.0 MB
+
+A total of 128 new copies of partitions need to be transferred.
+
+dc1                 Tags   Partitions        Capacity   Usable capacity
+  b10c110e4e854e5a  node1  256 (128 new)     1000.0 MB  1000.0 MB (100.0%)
+  TOTAL                    256 (256 unique)  1000.0 MB  1000.0 MB (100.0%)
+
+dc2                 Tags   Partitions        Capacity   Usable capacity
+  a235ac7695e0c54d  node2  256 (0 new)       1000.0 MB  1000.0 MB (100.0%)
+  TOTAL                    256 (256 unique)  1000.0 MB  1000.0 MB (100.0%)
+
+dc3                 Tags   Partitions        Capacity   Usable capacity
+  62b218d848e86a64  node3  193 (0 new)       1000.0 MB  753.9 MB (75.4%)
+  a11c7cf18af29737  node4  63 (0 new)        1000.0 MB  246.1 MB (24.6%)
+  TOTAL                    256 (256 unique)  2.0 GB     1000.0 MB (50.0%)
+```
+
+As we can see, the node that was moved to `dc3` (node4) is only used at 25% (approximatively),
+whereas the node that was already in `dc3` (node3) is used at 75%.
+
+This can be explained by the following:
+
+- node1 will now be the only node remaining in `dc1`, thus it has to store all
+  of the data in the cluster. Since it was storing only half of it before, it has
+  to retrieve the other half from other nodes in the cluster.
+
+- The data which it does not have is entirely stored by the other node that was
+  in `dc1` and that is now in `dc3` (node4). There is also a copy of it on node2
+  and node3 since both these nodes have a copy of everything.
+
+- node3 and node4 are the two nodes that will now be in a datacenter that is
+ under-utilized (`dc3`), this means that those are the two candidates from which
+ data can be removed to be moved to node1.
+
+- Garage will move data in equal proportions from all possible sources, in this
+  case it means that it will tranfer 25% of the entire data set from node3 to
+  node1 and another 25% from node4 to node1.
+
+This explains why node3 ends with 75% utilization (100% from before minus 25%
+that is moved to node1), and node4 ends with 25% (50% from before minus 25%
+that is moved to node1).
+
+This illustrates the second principle of the layout computation: **if there is
+a choice in moving data out of some nodes, then all links between pairs of
+nodes are used in equal proportions** (this is approximately true, there is
+randomness in the algorihtm to achieve this so there might be some small
+fluctuations, as we see above).

doc/book/operations/multi-hdd.md

@@ -0,0 +1,101 @@
++++
+title = "Multi-HDD support"
+weight = 15
++++
+
+
+Since v0.9, Garage natively supports nodes that have several storage drives
+for storing data blocks (not for metadata storage).
+
+## Initial setup
+
+To set up a new Garage storage node with multiple HDDs,
+format and mount all your drives in different directories,
+and use a Garage configuration as follows:
+
+```toml
+data_dir = [
+    { path = "/path/to/hdd1", capacity = "2T" },
+    { path = "/path/to/hdd2", capacity = "4T" },
+]
+```
+
+Garage will automatically balance all blocks stored by the node
+among the different specified directories, proportionnally to the
+specified capacities.
+
+## Updating the list of storage locations
+
+If you add new storage locations to your `data_dir`,
+Garage will not rebalance existing data between storage locations.
+Newly written blocks will be balanced proportionnally to the specified capacities,
+and existing data may be moved between drives to improve balancing,
+but only opportunistically when a data block is re-written (e.g. an object
+is re-uploaded, or an object with a duplicate block is uploaded).
+
+To understand precisely what is happening, we need to dive in to how Garage
+splits data among the different storage locations.
+
+First of all, Garage divides the set of all possible block hashes
+in a fixed number of slices (currently 1024), and assigns
+to each slice a primary storage location among the specified data directories.
+The number of slices having their primary location in each data directory
+is proportionnal to the capacity specified in the config file.
+
+When Garage receives a block to write, it will always write it in the primary
+directory of the slice that contains its hash.
+
+Now, to be able to not lose existing data blocks when storage locations
+are added, Garage also keeps a list of secondary data directories
+for all of the hash slices. Secondary data directories for a slice indicates
+storage locations that once were primary directories for that slice, i.e. where
+Garage knows that data blocks of that slice might be stored.
+When Garage is requested to read a certain data block,
+it will first look in the primary storage directory of its slice,
+and if it doesn't find it there it goes through all of the secondary storage
+locations until it finds it. This allows Garage to continue operating
+normally when storage locations are added, without having to shuffle
+files between drives to place them in the correct location.
+
+This relatively simple strategy works well but does not ensure that data
+is correctly balanced among drives according to their capacity.
+To rebalance data, two strategies can be used:
+
+- Lazy rebalancing: when a block is re-written (e.g. the object is re-uploaded),
+  Garage checks whether the existing copy is in the primary directory of the slice
+  or in a secondary directory. If the current copy is in a secondary directory,
+  Garage re-writes a copy in the primary directory and deletes the one from the
+  secondary directory. This might never end up rebalancing everything if there
+  are data blocks that are only read and never written.
+
+- Active rebalancing: an operator of a Garage node can explicitly launch a repair
+  procedure that rebalances the data directories, moving all blocks to their
+  primary location. Once done, all secondary locations for all hash slices are
+  removed so that they won't be checked anymore when looking for a data block.
+
+## Read-only storage locations
+
+If you would like to move all data blocks from an existing data directory to one
+or several new data directories, mark the old directory as read-only:
+
+```toml
+data_dir = [
+    { path = "/path/to/old_data", read_only = true },
+    { path = "/path/to/new_hdd1", capacity = "2T" },
+    { path = "/path/to/new_hdd2", capacity = "4T" },
+]
+```
+
+Garage will be able to read requested blocks from the read-only directory.
+Garage will also move data out of the read-only directory either progressively
+(lazy rebalancing) or if requested explicitly (active rebalancing).
+
+Once an active rebalancing has finished, your read-only directory should be empty:
+it might still contain subdirectories, but no data files. You can check that
+it contains no files using:
+
+```bash
+find -type f /path/to/old_data      # should not print anything
+```
+
+at which point it can be removed from the `data_dir` list in your config file.

doc/book/operations/upgrading.md

@@ -80,6 +80,6 @@ The entire procedure would look something like this:
 5. If any specific migration procedure is required, it is usually in one of the two cases:
 
   - It can be run on online nodes after the new version has started, during regular cluster operation.
-  - it has to be run offline
+  - it has to be run offline, in which case you will have to again take all nodes offline one after the other to run the repair
 
    For this last step, please refer to the specific documentation pertaining to the version upgrade you are doing.

doc/book/quick-start/_index.md

@@ -84,9 +84,8 @@ admin_token = "$(openssl rand -base64 32)"
 EOF
 ```
 
-Now that your configuration file has been created, you can put
-it in the right place. By default, garage looks at **`/etc/garage.toml`.**
-
+Now that your configuration file has been created, you may save it to the directory of your choice.
+By default, Garage looks for **`/etc/garage.toml`.**
 You can also store it somewhere else, but you will have to specify `-c path/to/garage.toml`
 at each invocation of the `garage` binary (for example: `garage -c ./garage.toml server`, `garage -c ./garage.toml status`).
 
@@ -103,12 +102,14 @@ your data to be persisted properly.
 
 ### Launching the Garage server
 
-Use the following command to launch the Garage server with our configuration file:
+Use the following command to launch the Garage server:
 
 ```
-garage server
+garage -c path/to/garage.toml server
 ```
 
+If you have placed the `garage.toml` file in `/etc` (its default location), you can simply run `garage server`.
+
 You can tune Garage's verbosity as follows (from less verbose to more verbose):
 
 ```
@@ -126,7 +127,7 @@ Log level `debug` can help you check why your S3 API calls are not working.
 The `garage` utility is also used as a CLI tool to configure your Garage deployment.
 It uses values from the TOML configuration file to find the Garage daemon running on the
 local node, therefore if your configuration file is not at `/etc/garage.toml` you will
-again have to specify `-c path/to/garage.toml`.
+again have to specify `-c path/to/garage.toml` at each invocation.
 
 If the `garage` CLI is able to correctly detect the parameters of your local Garage node,
 the following command should be enough to show the status of your cluster:
@@ -140,7 +141,7 @@ This should show something like this:
 ```
 ==== HEALTHY NODES ====
 ID                 Hostname  Address         Tag                   Zone  Capacity
-563e1ac825ee3323…  linuxbox  127.0.0.1:3901  NO ROLE ASSIGNED
+563e1ac825ee3323   linuxbox  127.0.0.1:3901  NO ROLE ASSIGNED
 ```
 
 ## Creating a cluster layout
@@ -153,12 +154,12 @@ For our test deployment, we are using only one node. The way in which we configu
 it does not matter, you can simply write:
 
 ```bash
-garage layout assign -z dc1 -c 1 <node_id>
+garage layout assign -z dc1 -c 1G <node_id>
 ```
 
 where `<node_id>` corresponds to the identifier of the node shown by `garage status` (first column).
 You can enter simply a prefix of that identifier.
-For instance here you could write just `garage layout assign -z dc1 -c 1 563e`.
+For instance here you could write just `garage layout assign -z dc1 -c 1G 563e`.
 
 The layout then has to be applied to the cluster, using:
 
@@ -209,7 +210,7 @@ one key can access multiple buckets, multiple keys can access one bucket.
 Create an API key using the following command:
 
 ```
-garage key new --name nextcloud-app-key
+garage key create nextcloud-app-key
 ```
 
 The output should look as follows:

doc/book/reference-manual/admin-api.md

@@ -13,8 +13,11 @@ We will bump the version numbers prefixed to each API endpoint at each time the
 or semantics change, meaning that code that relies on these endpoint will break
 when changes are introduced.
 
-The Garage administration API was introduced in version 0.7.2, this document
-does not apply to older versions of Garage.
+Versions:
+ - Before Garage 0.7.2 - no admin API
+ - Garage 0.7.2 - admin APIv0
+ - Garage 0.9.0 - admin APIv1, deprecate admin APIv0
+
 
 
 ## Access control
@@ -131,7 +134,9 @@ $ curl -so /dev/null -w "%{http_code}" http://localhost:3903/check?domain=exampl
 
 ### Cluster operations
 
-These endpoints are defined on a dedicated [Redocly page](https://garagehq.deuxfleurs.fr/api/garage-admin-v0.html). You can also download its [OpenAPI specification](https://garagehq.deuxfleurs.fr/api/garage-admin-v0.yml).
+These endpoints have a dedicated OpenAPI spec.
+ - APIv1 - [HTML spec](https://garagehq.deuxfleurs.fr/api/garage-admin-v1.html) - [OpenAPI YAML](https://garagehq.deuxfleurs.fr/api/garage-admin-v1.yml)
+ - APIv0 (deprecated) - [HTML spec](https://garagehq.deuxfleurs.fr/api/garage-admin-v0.html) - [OpenAPI YAML](https://garagehq.deuxfleurs.fr/api/garage-admin-v0.yml)
 
 Requesting the API from the command line can be as simple as running:
 

doc/book/reference-manual/configuration.md

@@ -8,8 +8,12 @@ weight = 20
 Here is an example `garage.toml` configuration file that illustrates all of the possible options:
 
 ```toml
+replication_mode = "3"
+
 metadata_dir = "/var/lib/garage/meta"
 data_dir = "/var/lib/garage/data"
+metadata_fsync = true
+data_fsync = false
 
 db_engine = "lmdb"
 
@@ -19,8 +23,6 @@ sled_cache_capacity = "128MiB"
 sled_flush_every_ms = 2000
 lmdb_map_size = "1T"
 
-replication_mode = "3"
-
 compression_level = 1
 
 rpc_secret = "4425f5c26c5e11581d3223904324dcb5b5d5dfb14e5e7f35e38c595424f5f1e6"
@@ -75,101 +77,64 @@ The following gives details about each available configuration option.
 
 ## Available configuration options
 
-### `metadata_dir`
+### Index
 
-The directory in which Garage will store its metadata. This contains the node identifier,
-the network configuration and the peer list, the list of buckets and keys as well
-as the index of all objects, object version and object blocks.
+Top-level configuration options:
+[`block_size`](#block_size),
+[`bootstrap_peers`](#bootstrap_peers),
+[`compression_level`](#compression_level),
+[`data_dir`](#metadata_dir),
+[`data_fsync`](#data_fsync),
+[`db_engine`](#db_engine),
+[`lmdb_map_size`](#lmdb_map_size),
+[`metadata_dir`](#metadata_dir),
+[`metadata_fsync`](#metadata_fsync),
+[`replication_mode`](#replication_mode),
+[`rpc_bind_addr`](#rpc_bind_addr),
+[`rpc_public_addr`](#rpc_public_addr),
+[`rpc_secret`](#rpc_secret),
+[`rpc_secret_file`](#rpc_secret),
+[`sled_cache_capacity`](#sled_cache_capacity),
+[`sled_flush_every_ms`](#sled_flush_every_ms).
 
-Store this folder on a fast SSD drive if possible to maximize Garage's performance.
+The `[consul_discovery]` section:
+[`api`](#consul_api),
+[`ca_cert`](#consul_ca_cert),
+[`client_cert`](#consul_client_cert),
+[`client_key`](#consul_client_cert),
+[`consul_http_addr`](#consul_http_addr),
+[`meta`](#consul_tags),
+[`service_name`](#consul_service_name),
+[`tags`](#consul_tags),
+[`tls_skip_verify`](#consul_tls_skip_verify),
+[`token`](#consul_token).
 
-### `data_dir`
+The `[kubernetes_discovery]` section:
+[`namespace`](#kube_namespace),
+[`service_name`](#kube_service_name),
+[`skip_crd`](#kube_skip_crd).
 
-The directory in which Garage will store the data blocks of objects.
-This folder can be placed on an HDD. The space available for `data_dir`
-should be counted to determine a node's capacity
-when [adding it to the cluster layout](@/documentation/cookbook/real-world.md).
+The `[s3_api]` section:
+[`api_bind_addr`](#s3_api_bind_addr),
+[`root_domain`](#s3_root_domain),
+[`s3_region`](#s3_region).
 
-### `db_engine` (since `v0.8.0`)
+The `[s3_web]` section:
+[`bind_addr`](#web_bind_addr),
+[`root_domain`](#web_root_domain).
 
-By default, Garage uses the Sled embedded database library
-to store its metadata on-disk. Since `v0.8.0`, Garage can use alternative storage backends as follows:
+The `[admin]` section:
+[`api_bind_addr`](#admin_api_bind_addr),
+[`metrics_token`](#admin_metrics_token),
+[`metrics_token_file`](#admin_metrics_token),
+[`admin_token`](#admin_token),
+[`admin_token_file`](#admin_token),
+[`trace_sink`](#admin_trace_sink),
 
-| DB engine | `db_engine` value | Database path |
-| --------- | ----------------- | ------------- |
-| [Sled](https://sled.rs) | `"sled"` | `<metadata_dir>/db/` |
-| [LMDB](https://www.lmdb.tech) | `"lmdb"` | `<metadata_dir>/db.lmdb/` |
-| [Sqlite](https://sqlite.org) | `"sqlite"` | `<metadata_dir>/db.sqlite` |
 
-Performance characteristics of the different DB engines are as follows:
+### Top-level configuration options
 
-- Sled: the default database engine, which tends to produce
-  large data files and also has performance issues, especially when the metadata folder
-  is on a traditional HDD and not on SSD.
-- LMDB: the recommended alternative on 64-bit systems,
-  much more space-efficiant and slightly faster. Note that the data format of LMDB is not portable
-  between architectures, so for instance the Garage database of an x86-64
-  node cannot be moved to an ARM64 node. Also note that, while LMDB can technically be used on 32-bit systems,
-  this will limit your node to very small database sizes due to how LMDB works; it is therefore not recommended.
-- Sqlite: Garage supports Sqlite as a storage backend for metadata,
-  however it may have issues and is also very slow in its current implementation,
-  so it is not recommended to be used for now.
-
-It is possible to convert Garage's metadata directory from one format to another with a small utility named `convert_db`,
-which can be downloaded at the following locations:
-[for amd64](https://garagehq.deuxfleurs.fr/_releases/convert_db/amd64/convert_db),
-[for i386](https://garagehq.deuxfleurs.fr/_releases/convert_db/i386/convert_db),
-[for arm64](https://garagehq.deuxfleurs.fr/_releases/convert_db/arm64/convert_db),
-[for arm](https://garagehq.deuxfleurs.fr/_releases/convert_db/arm/convert_db).
-The `convert_db` utility is used as folows:
-
-```
-convert-db -a <input db engine> -i <input db path> \
-  		   -b <output db engine> -o <output db path>
-```
-
-Make sure to specify the full database path as presented in the table above,
-and not just the path to the metadata directory.
-
-### `block_size`
-
-Garage splits stored objects in consecutive chunks of size `block_size`
-(except the last one which might be smaller). The default size is 1MiB and
-should work in most cases. We recommend increasing it to e.g. 10MiB if
-you are using Garage to store large files and have fast network connections
-between all nodes (e.g. 1gbps).
-
-If you are interested in tuning this, feel free to do so (and remember to
-report your findings to us!). When this value is changed for a running Garage
-installation, only files newly uploaded will be affected. Previously uploaded
-files will remain available. This however means that chunks from existing files
-will not be deduplicated with chunks from newly uploaded files, meaning you
-might use more storage space that is optimally possible.
-
-### `sled_cache_capacity`
-
-This parameter can be used to tune the capacity of the cache used by
-[sled](https://sled.rs), the database Garage uses internally to store metadata.
-Tune this to fit the RAM you wish to make available to your Garage instance.
-This value has a conservative default (128MB) so that Garage doesn't use too much
-RAM by default, but feel free to increase this for higher performance.
-
-### `sled_flush_every_ms`
-
-This parameters can be used to tune the flushing interval of sled.
-Increase this if sled is thrashing your SSD, at the risk of losing more data in case
-of a power outage (though this should not matter much as data is replicated on other
-nodes). The default value, 2000ms, should be appropriate for most use cases.
-
-### `lmdb_map_size`
-
-This parameters can be used to set the map size used by LMDB,
-which is the size of the virtual memory region used for mapping the database file.
-The value of this parameter is the maximum size the metadata database can take.
-This value is not bound by the physical RAM size of the machine running Garage.
-If not specified, it defaults to 1GiB on 32-bit machines and 1TiB on 64-bit machines.
-
-### `replication_mode`
+#### `replication_mode` {#replication_mode}
 
 Garage supports the following replication modes:
 
@@ -252,7 +217,160 @@ to the cluster while rebalancing is in progress.  In theory, no data should be
 lost as rebalancing is a routine operation for Garage, although we cannot
 guarantee you that everything will go right in such an extreme scenario.
 
-### `compression_level`
+#### `metadata_dir` {#metadata_dir}
+
+The directory in which Garage will store its metadata. This contains the node identifier,
+the network configuration and the peer list, the list of buckets and keys as well
+as the index of all objects, object version and object blocks.
+
+Store this folder on a fast SSD drive if possible to maximize Garage's performance.
+
+#### `data_dir` {#data_dir}
+
+The directory in which Garage will store the data blocks of objects.
+This folder can be placed on an HDD. The space available for `data_dir`
+should be counted to determine a node's capacity
+when [adding it to the cluster layout](@/documentation/cookbook/real-world.md).
+
+Since `v0.9.0`, Garage supports multiple data directories with the following syntax:
+
+```toml
+data_dir = [
+    { path = "/path/to/old_data", read_only = true },
+    { path = "/path/to/new_hdd1", capacity = "2T" },
+    { path = "/path/to/new_hdd2", capacity = "4T" },
+]
+```
+
+See [the dedicated documentation page](@/documentation/operations/multi-hdd.md)
+on how to operate Garage in such a setup.
+
+#### `db_engine` (since `v0.8.0`) {#db_engine}
+
+Since `v0.8.0`, Garage can use alternative storage backends as follows:
+
+| DB engine | `db_engine` value | Database path |
+| --------- | ----------------- | ------------- |
+| [LMDB](https://www.lmdb.tech) (default since `v0.9.0`) | `"lmdb"` | `<metadata_dir>/db.lmdb/` |
+| [Sled](https://sled.rs) (default up to `v0.8.0`) | `"sled"` | `<metadata_dir>/db/` |
+| [Sqlite](https://sqlite.org) | `"sqlite"` | `<metadata_dir>/db.sqlite` |
+
+Sled was the only database engine up to Garage v0.7.0. Performance issues and
+API limitations of Sled prompted the addition of alternative engines in v0.8.0.
+Since v0.9.0, LMDB is the default engine instead of Sled, and Sled is
+deprecated. We plan to remove Sled in Garage v1.0.
+
+Performance characteristics of the different DB engines are as follows:
+
+- Sled: tends to produce large data files and also has performance issues,
+  especially when the metadata folder is on a traditional HDD and not on SSD.
+
+- LMDB: the recommended database engine on 64-bit systems, much more
+  space-efficient and slightly faster. Note that the data format of LMDB is not
+  portable between architectures, so for instance the Garage database of an
+  x86-64 node cannot be moved to an ARM64 node. Also note that, while LMDB can
+  technically be used on 32-bit systems, this will limit your node to very
+  small database sizes due to how LMDB works; it is therefore not recommended.
+
+- Sqlite: Garage supports Sqlite as an alternative storage backend for
+  metadata, and although it has not been tested as much, it is expected to work
+  satisfactorily.  Since Garage v0.9.0, performance issues have largely been
+  fixed by allowing for a no-fsync mode (see `metadata_fsync`). Sqlite does not
+  have the database size limitation of LMDB on 32-bit systems.
+
+It is possible to convert Garage's metadata directory from one format to another
+using the `garage convert-db` command, which should be used as follows:
+
+```
+garage convert-db -a <input db engine> -i <input db path> \
+                  -b <output db engine> -o <output db path>
+```
+
+Make sure to specify the full database path as presented in the table above
+(third colummn), and not just the path to the metadata directory.
+
+#### `metadata_fsync` {#metadata_fsync}
+
+Whether to enable synchronous mode for the database engine or not.
+This is disabled (`false`) by default.
+
+This reduces the risk of metadata corruption in case of power failures,
+at the cost of a significant drop in write performance,
+as Garage will have to pause to sync data to disk much more often
+(several times for API calls such as PutObject).
+
+Using this option reduces the risk of simultaneous metadata corruption on several
+cluster nodes, which could lead to data loss.
+
+If multi-site replication is used, this option is most likely not necessary, as
+it is extremely unlikely that two nodes in different locations will have a 
+power failure at the exact same time.
+
+(Metadata corruption on a single node is not an issue, the corrupted data file
+can always be deleted and reconstructed from the other nodes in the cluster.)
+
+Here is how this option impacts the different database engines:
+
+| Database | `metadata_fsync = false` (default) | `metadata_fsync = true`       |
+|----------|------------------------------------|-------------------------------|
+| Sled     | default options                    | *unsupported*                 |
+| Sqlite   | `PRAGMA synchronous = OFF`         | `PRAGMA synchronous = NORMAL` |
+| LMDB     | `MDB_NOMETASYNC` + `MDB_NOSYNC`    | `MDB_NOMETASYNC`              |
+
+Note that the Sqlite database is always ran in `WAL` mode (`PRAGMA journal_mode = WAL`).
+
+#### `data_fsync` {#data_fsync}
+
+Whether to `fsync` data blocks and their containing directory after they are
+saved to disk.
+This is disabled (`false`) by default.
+
+This might reduce the risk that a data block is lost in rare
+situations such as simultaneous node losing power,
+at the cost of a moderate drop in write performance.
+
+Similarly to `metatada_fsync`, this is likely not necessary
+if geographical replication is used.
+
+#### `block_size` {#block_size}
+
+Garage splits stored objects in consecutive chunks of size `block_size`
+(except the last one which might be smaller). The default size is 1MiB and
+should work in most cases. We recommend increasing it to e.g. 10MiB if
+you are using Garage to store large files and have fast network connections
+between all nodes (e.g. 1gbps).
+
+If you are interested in tuning this, feel free to do so (and remember to
+report your findings to us!). When this value is changed for a running Garage
+installation, only files newly uploaded will be affected. Previously uploaded
+files will remain available. This however means that chunks from existing files
+will not be deduplicated with chunks from newly uploaded files, meaning you
+might use more storage space that is optimally possible.
+
+#### `sled_cache_capacity` {#sled_cache_capacity}
+
+This parameter can be used to tune the capacity of the cache used by
+[sled](https://sled.rs), the database Garage uses internally to store metadata.
+Tune this to fit the RAM you wish to make available to your Garage instance.
+This value has a conservative default (128MB) so that Garage doesn't use too much
+RAM by default, but feel free to increase this for higher performance.
+
+#### `sled_flush_every_ms` {#sled_flush_every_ms}
+
+This parameters can be used to tune the flushing interval of sled.
+Increase this if sled is thrashing your SSD, at the risk of losing more data in case
+of a power outage (though this should not matter much as data is replicated on other
+nodes). The default value, 2000ms, should be appropriate for most use cases.
+
+#### `lmdb_map_size` {#lmdb_map_size}
+
+This parameters can be used to set the map size used by LMDB,
+which is the size of the virtual memory region used for mapping the database file.
+The value of this parameter is the maximum size the metadata database can take.
+This value is not bound by the physical RAM size of the machine running Garage.
+If not specified, it defaults to 1GiB on 32-bit machines and 1TiB on 64-bit machines.
+
+#### `compression_level` {#compression_level}
 
 Zstd compression level to use for storing blocks.
 
@@ -276,7 +394,7 @@ Compression is done synchronously, setting a value too high will add latency to
 This value can be different between nodes, compression is done by the node which receive the
 API call.
 
-### `rpc_secret`, `rpc_secret_file` or `GARAGE_RPC_SECRET`, `GARAGE_RPC_SECRET_FILE` (env)
+#### `rpc_secret`, `rpc_secret_file` or `GARAGE_RPC_SECRET`, `GARAGE_RPC_SECRET_FILE` (env) {#rpc_secret}
 
 Garage uses a secret key, called an RPC secret, that is shared between all
 nodes of the cluster in order to identify these nodes and allow them to
@@ -288,10 +406,10 @@ Since Garage `v0.8.2`, the RPC secret can also be stored in a file whose path is
 given in the configuration variable `rpc_secret_file`, or specified as an
 environment variable `GARAGE_RPC_SECRET`.
 
-Since Garage `v0.9.0`, you can also specify the path of a file storing the secret
-as the `GARAGE_RPC_SECRET_FILE` environment variable.
+Since Garage `v0.8.5` and `v0.9.1`, you can also specify the path of a file
+storing the secret as the `GARAGE_RPC_SECRET_FILE` environment variable.
 
-### `rpc_bind_addr`
+#### `rpc_bind_addr` {#rpc_bind_addr}
 
 The address and port on which to bind for inter-cluster communcations
 (reffered to as RPC for remote procedure calls).
@@ -300,14 +418,14 @@ the node, even in the case of a NAT: the NAT should be configured to forward the
 port number to the same internal port nubmer. This means that if you have several nodes running
 behind a NAT, they should each use a different RPC port number.
 
-### `rpc_public_addr`
+#### `rpc_public_addr` {#rpc_public_addr}
 
 The address and port that other nodes need to use to contact this node for
 RPC calls.  **This parameter is optional but recommended.** In case you have
 a NAT that binds the RPC port to a port that is different on your public IP,
 this field might help making it work.
 
-### `bootstrap_peers`
+#### `bootstrap_peers` {#bootstrap_peers}
 
 A list of peer identifiers on which to contact other Garage peers of this cluster.
 These peer identifiers have the following syntax:
@@ -335,42 +453,42 @@ permission verification.
 Alternatively, you can set the `GARAGE_ALLOW_WORLD_READABLE_SECRETS`
 environment variable to `true` to bypass the permissions check.
 
-## The `[consul_discovery]` section
+### The `[consul_discovery]` section
 
 Garage supports discovering other nodes of the cluster using Consul.  For this
 to work correctly, nodes need to know their IP address by which they can be
 reached by other nodes of the cluster, which should be set in `rpc_public_addr`.
 
-### `consul_http_addr` and `service_name`
+#### `consul_http_addr` {#consul_http_addr}
 
 The `consul_http_addr` parameter should be set to the full HTTP(S) address of the Consul server.
 
-### `api`
+#### `api` {#consul_api}
 
 Two APIs for service registration are supported: `catalog`  and `agent`. `catalog`, the default, will register a service using
 the `/v1/catalog` endpoints, enabling mTLS if `client_cert` and `client_key` are provided. The `agent` API uses the
 `v1/agent` endpoints instead, where an optional `token` may be provided.
 
-### `service_name`
+#### `service_name` {#consul_service_name}
 
 `service_name` should be set to the service name under which Garage's
 RPC ports are announced.
 
-### `client_cert`, `client_key`
+#### `client_cert`, `client_key` {#consul_client_cert}
 
 TLS client certificate and client key to use when communicating with Consul over TLS. Both are mandatory when doing so.
 Only available when `api = "catalog"`.
 
-### `ca_cert`
+#### `ca_cert` {#consul_ca_cert}
 
 TLS CA certificate to use when communicating with Consul over TLS.
 
-### `tls_skip_verify`
+#### `tls_skip_verify` {#consul_tls_skip_verify}
 
 Skip server hostname verification in TLS handshake.
 `ca_cert` is ignored when this is set.
 
-### `token`
+#### `token` {#consul_token}
 
 Uses the provided token for communication with Consul. Only available when `api = "agent"`.
 The policy assigned to this token should at least have these rules:
@@ -390,49 +508,49 @@ node_prefix "" {
 }
 ```
 
-### `tags` and `meta`
+#### `tags` and `meta` {#consul_tags}
 
 Additional list of tags and map of service meta to add during service registration.
 
-## The `[kubernetes_discovery]` section
+### The `[kubernetes_discovery]` section
 
 Garage supports discovering other nodes of the cluster using kubernetes custom
 resources. For this to work, a `[kubernetes_discovery]` section must be present
 with at least the `namespace` and `service_name` parameters.
 
-### `namespace`
+#### `namespace` {#kube_namespace}
 
 `namespace` sets the namespace in which the custom resources are
 configured.
 
-### `service_name`
+#### `service_name` {#kube_service_name}
 
 `service_name` is added as a label to the advertised resources to
 filter them, to allow for multiple deployments in a single namespace.
 
-### `skip_crd`
+#### `skip_crd` {#kube_skip_crd}
 
 `skip_crd` can be set to true to disable the automatic creation and
 patching of the `garagenodes.deuxfleurs.fr` CRD. You will need to create the CRD
 manually.
 
 
-## The `[s3_api]` section
+### The `[s3_api]` section
 
-### `api_bind_addr`
+#### `api_bind_addr` {#s3_api_bind_addr}
 
 The IP and port on which to bind for accepting S3 API calls.
 This endpoint does not suport TLS: a reverse proxy should be used to provide it.
 
 Alternatively, since `v0.8.5`, a path can be used to create a unix socket with 0222 mode.
 
-### `s3_region`
+#### `s3_region` {#s3_region}
 
 Garage will accept S3 API calls that are targetted to the S3 region defined here.
 API calls targetted to other regions will fail with a AuthorizationHeaderMalformed error
 message that redirects the client to the correct region.
 
-### `root_domain` {#root_domain}
+#### `root_domain` {#s3_root_domain}
 
 The optional suffix to access bucket using vhost-style in addition to path-style request.
 Note path-style requests are always enabled, whether or not vhost-style is configured.
@@ -444,12 +562,12 @@ using the hostname `my-bucket.s3.garage.eu`.
 
 
 
-## The `[s3_web]` section
+### The `[s3_web]` section
 
 Garage allows to publish content of buckets as websites. This section configures the
 behaviour of this module.
 
-### `bind_addr`
+#### `bind_addr` {#web_bind_addr}
 
 The IP and port on which to bind for accepting HTTP requests to buckets configured
 for website access.
@@ -457,7 +575,7 @@ This endpoint does not suport TLS: a reverse proxy should be used to provide it.
 
 Alternatively, since `v0.8.5`, a path can be used to create a unix socket with 0222 mode.
 
-### `root_domain`
+#### `root_domain` {#web_root_domain}
 
 The optional suffix appended to bucket names for the corresponding HTTP Host.
 
@@ -466,11 +584,11 @@ will be accessible either with hostname `deuxfleurs.fr.web.garage.eu`
 or with hostname `deuxfleurs.fr`.
 
 
-## The `[admin]` section
+### The `[admin]` section
 
 Garage has a few administration capabilities, in particular to allow remote monitoring. These features are detailed below.
 
-### `api_bind_addr`
+#### `api_bind_addr` {#admin_api_bind_addr}
 
 If specified, Garage will bind an HTTP server to this port and address, on
 which it will listen to requests for administration features.
@@ -479,7 +597,7 @@ See [administration API reference](@/documentation/reference-manual/admin-api.md
 Alternatively, since `v0.8.5`, a path can be used to create a unix socket. Note that for security reasons,
 the socket will have 0220 mode. Make sure to set user and group permissions accordingly.
 
-### `metrics_token`, `metrics_token_file` or `GARAGE_METRICS_TOKEN`, `GARAGE_METRICS_TOKEN_FILE` (env)
+#### `metrics_token`, `metrics_token_file` or `GARAGE_METRICS_TOKEN`, `GARAGE_METRICS_TOKEN_FILE` (env) {#admin_metrics_token}
 
 The token for accessing the Metrics endpoint. If this token is not set, the
 Metrics endpoint can be accessed without access control.
@@ -489,9 +607,9 @@ You can use any random string for this value. We recommend generating a random t
 `metrics_token` was introduced in Garage `v0.7.2`.
 `metrics_token_file` and the `GARAGE_METRICS_TOKEN` environment variable are supported since Garage `v0.8.2`.
 
-`GARAGE_METRICS_TOKEN_FILE` is supported since `v0.9.0`.
+`GARAGE_METRICS_TOKEN_FILE` is supported since `v0.8.5` / `v0.9.1`.
 
-### `admin_token`, `admin_token_file` or `GARAGE_ADMIN_TOKEN`, `GARAGE_ADMIN_TOKEN_FILE` (env)
+#### `admin_token`, `admin_token_file` or `GARAGE_ADMIN_TOKEN`, `GARAGE_ADMIN_TOKEN_FILE` (env) {#admin_token}
 
 The token for accessing all of the other administration endpoints.  If this
 token is not set, access to these endpoints is disabled entirely.
@@ -501,9 +619,9 @@ You can use any random string for this value. We recommend generating a random t
 `admin_token` was introduced in Garage `v0.7.2`.
 `admin_token_file` and the `GARAGE_ADMIN_TOKEN` environment variable are supported since Garage `v0.8.2`.
 
-`GARAGE_ADMIN_TOKEN_FILE` is supported since `v0.9.0`.
+`GARAGE_ADMIN_TOKEN_FILE` is supported since `v0.8.5` / `v0.9.1`.
 
-### `trace_sink`
+#### `trace_sink` {#admin_trace_sink}
 
 Optionally, the address of an OpenTelemetry collector.  If specified,
 Garage will send traces in the OpenTelemetry format to this endpoint. These

doc/book/reference-manual/features.md

@@ -52,7 +52,7 @@ This is particularly usefull when nodes are far from one another and talk to one
 
 Garage supports a variety of replication modes, with 1 copy, 2 copies or 3 copies of your data,
 and with various levels of consistency, in order to adapt to a variety of usage scenarios.
-Read our reference page on [supported replication modes](@/documentation/reference-manual/configuration.md#replication-mode)
+Read our reference page on [supported replication modes](@/documentation/reference-manual/configuration.md#replication_mode)
 to select the replication mode best suited to your use case (hint: in most cases, `replication_mode = "3"` is what you want).
 
 ### Web server for static websites

doc/book/reference-manual/s3-compatibility.md

@@ -75,16 +75,13 @@ but these endpoints are documented in [Red Hat Ceph Storage - Chapter 2. Ceph Ob
 
 | Endpoint                     | Garage                           | [Openstack Swift](https://docs.openstack.org/swift/latest/s3_compat.html) | [Ceph Object Gateway](https://docs.ceph.com/en/latest/radosgw/s3/) | [Riak CS](https://docs.riak.com/riak/cs/2.1.1/references/apis/storage/s3/index.html) | [OpenIO](https://docs.openio.io/latest/source/arch-design/s3_compliancy.html) |
 |------------------------------|----------------------------------|-----------------|---------------|---------|-----|
-| [AbortMultipartUpload](https://docs.aws.amazon.com/AmazonS3/latest/API/API_AbortMultipartUpload.html)         | ✅ Implemented                      |  ✅ | ✅ | ✅ | ✅ |
-| [CompleteMultipartUpload](https://docs.aws.amazon.com/AmazonS3/latest/API/API_CompleteMultipartUpload.html)   | ✅ Implemented (see details below)                      | ✅ | ✅ | ✅ | ✅ |
-| [CreateMultipartUpload](https://docs.aws.amazon.com/AmazonS3/latest/API/API_CreateMultipartUpload.html)        | ✅ Implemented                      | ✅| ✅ | ✅ | ✅ |
-| [ListMultipartUpload](https://docs.aws.amazon.com/AmazonS3/latest/API/API_ListMultipartUpload.html)          | ✅ Implemented                      | ✅ | ✅ | ✅ | ✅ |
-| [ListParts](https://docs.aws.amazon.com/AmazonS3/latest/API/API_ListParts.html)                    | ✅ Implemented                      | ✅ | ✅ | ✅ | ✅ |
-| [UploadPart](https://docs.aws.amazon.com/AmazonS3/latest/API/API_UploadPart.html)                  | ✅ Implemented (see details below)                      | ✅ | ✅| ✅ | ✅ |
-| [UploadPartCopy](https://docs.aws.amazon.com/AmazonS3/latest/API/API_UploadPartCopy.html)               | ✅ Implemented                      | ✅ | ✅ | ✅ | ✅ |
-
-Our implementation of Multipart Upload is currently a bit more restrictive than Amazon's one in some edge cases.
-For more information, please refer to our [issue tracker](https://git.deuxfleurs.fr/Deuxfleurs/garage/issues/204).
+| [AbortMultipartUpload](https://docs.aws.amazon.com/AmazonS3/latest/API/API_AbortMultipartUpload.html)         | ✅ Implemented  |  ✅ | ✅ | ✅ | ✅ |
+| [CompleteMultipartUpload](https://docs.aws.amazon.com/AmazonS3/latest/API/API_CompleteMultipartUpload.html)   | ✅ Implemented  | ✅ | ✅ | ✅ | ✅ |
+| [CreateMultipartUpload](https://docs.aws.amazon.com/AmazonS3/latest/API/API_CreateMultipartUpload.html)        | ✅ Implemented | ✅| ✅ | ✅ | ✅ |
+| [ListMultipartUpload](https://docs.aws.amazon.com/AmazonS3/latest/API/API_ListMultipartUpload.html)          | ✅ Implemented   | ✅ | ✅ | ✅ | ✅ |
+| [ListParts](https://docs.aws.amazon.com/AmazonS3/latest/API/API_ListParts.html)                    | ✅ Implemented             | ✅ | ✅ | ✅ | ✅ |
+| [UploadPart](https://docs.aws.amazon.com/AmazonS3/latest/API/API_UploadPart.html)                  | ✅ Implemented             | ✅ | ✅| ✅ | ✅ |
+| [UploadPartCopy](https://docs.aws.amazon.com/AmazonS3/latest/API/API_UploadPartCopy.html)               | ✅ Implemented        | ✅ | ✅ | ✅ | ✅ |
 
 ### Website endpoints
 
@@ -127,15 +124,22 @@ If you need this feature, please [share your use case in our dedicated issue](ht
 
 | Endpoint                     | Garage                           | [Openstack Swift](https://docs.openstack.org/swift/latest/s3_compat.html) | [Ceph Object Gateway](https://docs.ceph.com/en/latest/radosgw/s3/) | [Riak CS](https://docs.riak.com/riak/cs/2.1.1/references/apis/storage/s3/index.html) | [OpenIO](https://docs.openio.io/latest/source/arch-design/s3_compliancy.html) |
 |------------------------------|----------------------------------|-----------------|---------------|---------|-----|
-| [DeleteBucketLifecycle](https://docs.aws.amazon.com/AmazonS3/latest/API/API_DeleteBucketLifecycle.html) | ❌ Missing | ❌| ✅| ❌| ✅|
-| [GetBucketLifecycleConfiguration](https://docs.aws.amazon.com/AmazonS3/latest/API/API_GetBucketLifecycleConfiguration.html) | ❌ Missing | ❌| ✅ | ❌| ✅|
-| [PutBucketLifecycleConfiguration](https://docs.aws.amazon.com/AmazonS3/latest/API/API_PutBucketLifecycleConfiguration.html) | ❌ Missing | ❌| ✅ | ❌| ✅|
+| [DeleteBucketLifecycle](https://docs.aws.amazon.com/AmazonS3/latest/API/API_DeleteBucketLifecycle.html) | ✅ Implemented | ❌| ✅| ❌| ✅|
+| [GetBucketLifecycleConfiguration](https://docs.aws.amazon.com/AmazonS3/latest/API/API_GetBucketLifecycleConfiguration.html) | ✅ Implemented | ❌| ✅ | ❌| ✅|
+| [PutBucketLifecycleConfiguration](https://docs.aws.amazon.com/AmazonS3/latest/API/API_PutBucketLifecycleConfiguration.html) | ⚠ Partially implemented (see below) | ❌| ✅ | ❌| ✅|
 | [GetBucketVersioning](https://docs.aws.amazon.com/AmazonS3/latest/API/API_GetBucketVersioning.html)          | ❌ Stub (see below)       | ✅| ✅ | ❌| ✅|
 | [ListObjectVersions](https://docs.aws.amazon.com/AmazonS3/latest/API/API_ListObjectVersions.html) | ❌ Missing | ❌| ✅ | ❌| ✅|
 | [PutBucketVersioning](https://docs.aws.amazon.com/AmazonS3/latest/API/API_PutBucketVersioning.html) | ❌ Missing | ❌| ✅| ❌| ✅|
 
+**PutBucketLifecycleConfiguration:** The only actions supported are
+`AbortIncompleteMultipartUpload` and `Expiration` (without the
+`ExpiredObjectDeleteMarker` field).  All other operations are dependent on
+either bucket versionning or storage classes which Garage currently does not
+implement. The deprecated `Prefix` member directly in the the `Rule`
+structure/XML tag is not supported, specified prefixes must be inside the
+`Filter` structure/XML tag.
 
-**GetBucketVersioning:** Stub implementation (Garage does not yet support versionning so this always returns "versionning not enabled").
+**GetBucketVersioning:** Stub implementation which always returns "versionning not enabled", since Garage does not yet support bucket versionning.
 
 ### Replication endpoints
 

doc/book/working-documents/migration-09.md

@@ -0,0 +1,72 @@
++++
+title = "Migrating from 0.8 to 0.9"
+weight = 12
++++
+
+**This guide explains how to migrate to 0.9 if you have an existing 0.8 cluster.
+We don't recommend trying to migrate to 0.9 directly from 0.7 or older.**
+
+This migration procedure has been tested on several clusters without issues.
+However, it is still a *critical procedure* that might cause issues.
+**Make sure to back up all your data before attempting it!**
+
+You might also want to read our [general documentation on upgrading Garage](@/documentation/operations/upgrading.md).
+
+The following are **breaking changes** in Garage v0.9 that require your attention when migrating:
+
+- LMDB is now the default metadata db engine and Sled is deprecated. If you were using Sled, make sure to specify `db_engine = "sled"` in your configuration file, or take the time to [convert your database](https://garagehq.deuxfleurs.fr/documentation/reference-manual/configuration/#db-engine-since-v0-8-0).
+
+- Capacity values are now in actual byte units. The translation from the old layout will assign 1 capacity = 1Gb by default, which might be wrong for your cluster. This does not cause any data to be moved around, but you might want to re-assign correct capacity values post-migration.
+
+- Multipart uploads that were started in Garage v0.8 will not be visible in Garage v0.9 and will have to be restarted from scratch.
+
+- Changes to the admin API: some `v0/` endpoints have been replaced by `v1/` counterparts with updated/uniformized syntax. All other endpoints have also moved to `v1/` by default, without syntax changes, but are still available under `v0/` for compatibility.
+
+
+## Simple migration procedure (takes cluster offline for a while)
+
+The migration steps are as follows:
+
+1. Disable API and web access. You may do this by stopping your reverse proxy or by commenting out
+   the `api_bind_addr` values in your `config.toml` file and restarting Garage.
+2. Do `garage repair --all-nodes --yes tables` and `garage repair --all-nodes --yes blocks`,
+   check the logs and check that all data seems to be synced correctly between
+   nodes. If you have time, do additional checks (`versions`, `block_refs`, etc.)
+3. Check that the block resync queue and Merkle queue are empty:
+   run `garage stats -a` to query them or inspect metrics in the Grafana dashboard.
+4. Turn off Garage v0.8
+5. **Backup the metadata folder of all your nodes!** For instance, use the following command
+	if your metadata directory is `/var/lib/garage/meta`: `cd /var/lib/garage ; tar -acf meta-v0.8.tar.zst meta/`
+6. Install Garage v0.9
+7. Update your configuration file if necessary.
+8. Turn on Garage v0.9
+9. Do `garage repair --all-nodes --yes tables` and `garage repair --all-nodes --yes blocks`.
+   Wait for a full table sync to run.
+10. Your upgraded cluster should be in a working state. Re-enable API and Web
+    access and check that everything went well.
+11. Monitor your cluster in the next hours to see if it works well under your production load, report any issue.
+12. You might want to assign correct capacity values to all your nodes. Doing so might cause data to be moved
+    in your cluster, which should also be monitored carefully.
+
+## Minimal downtime migration procedure
+
+The migration to Garage v0.9 can be done with almost no downtime,
+by restarting all nodes at once in the new version.
+
+The migration steps are as follows:
+
+1. Do `garage repair --all-nodes --yes tables` and `garage repair --all-nodes --yes blocks`,
+   check the logs and check that all data seems to be synced correctly between
+   nodes. If you have time, do additional checks (`versions`, `block_refs`, etc.)
+
+2. Turn off each node individually; back up its metadata folder (see above); turn it back on again.
+   This will allow you to take a backup of all nodes without impacting global cluster availability.
+   You can do all nodes of a single zone at once as this does not impact the availability of Garage.
+
+3. Prepare your binaries and configuration files for Garage v0.9
+
+4. Shut down all v0.8 nodes simultaneously, and restart them all simultaneously in v0.9.
+   Use your favorite deployment tool (Ansible, Kubernetes, Nomad) to achieve this as fast as possible.
+   Garage v0.9 should be in a working state as soon as it starts.
+
+5. Proceed with repair and monitoring as described in steps 9-12 above.

doc/drafts/admin-api.md

@@ -52,11 +52,11 @@ Returns an HTTP status 200 if the node is ready to answer user's requests,
 and an HTTP status 503 (Service Unavailable) if there are some partitions
 for which a quorum of nodes is not available.
 A simple textual message is also returned in a body with content-type `text/plain`.
-See `/v0/health` for an API that also returns JSON output.
+See `/v1/health` for an API that also returns JSON output.
 
 ### Cluster operations
 
-#### GetClusterStatus `GET /v0/status`
+#### GetClusterStatus `GET /v1/status`
 
 Returns the cluster's current status in JSON, including:
 
@@ -70,86 +70,112 @@ Example response body:
 ```json
 {
   "node": "ec79480e0ce52ae26fd00c9da684e4fa56658d9c64cdcecb094e936de0bfe71f",
-  "garage_version": "git:v0.8.0",
-  "knownNodes": {
-    "ec79480e0ce52ae26fd00c9da684e4fa56658d9c64cdcecb094e936de0bfe71f": {
+  "garageVersion": "git:v0.9.0-dev",
+  "garageFeatures": [
+    "k2v",
+    "sled",
+    "lmdb",
+    "sqlite",
+    "metrics",
+    "bundled-libs"
+  ],
+  "rustVersion": "1.68.0",
+  "dbEngine": "LMDB (using Heed crate)",
+  "knownNodes": [
+    {
+      "id": "ec79480e0ce52ae26fd00c9da684e4fa56658d9c64cdcecb094e936de0bfe71f",
       "addr": "10.0.0.11:3901",
-      "is_up": true,
-      "last_seen_secs_ago": 9,
+      "isUp": true,
+      "lastSeenSecsAgo": 9,
       "hostname": "node1"
     },
-    "4a6ae5a1d0d33bf895f5bb4f0a418b7dc94c47c0dd2eb108d1158f3c8f60b0ff": {
+    {
+      "id": "4a6ae5a1d0d33bf895f5bb4f0a418b7dc94c47c0dd2eb108d1158f3c8f60b0ff",
       "addr": "10.0.0.12:3901",
-      "is_up": true,
-      "last_seen_secs_ago": 1,
+      "isUp": true,
+      "lastSeenSecsAgo": 1,
       "hostname": "node2"
     },
-    "23ffd0cdd375ebff573b20cc5cef38996b51c1a7d6dbcf2c6e619876e507cf27": {
+    {
+      "id": "23ffd0cdd375ebff573b20cc5cef38996b51c1a7d6dbcf2c6e619876e507cf27",
       "addr": "10.0.0.21:3901",
-      "is_up": true,
-      "last_seen_secs_ago": 7,
+      "isUp": true,
+      "lastSeenSecsAgo": 7,
       "hostname": "node3"
     },
-    "e2ee7984ee65b260682086ec70026165903c86e601a4a5a501c1900afe28d84b": {
+    {
+      "id": "e2ee7984ee65b260682086ec70026165903c86e601a4a5a501c1900afe28d84b",
       "addr": "10.0.0.22:3901",
-      "is_up": true,
-      "last_seen_secs_ago": 1,
+      "isUp": true,
+      "lastSeenSecsAgo": 1,
       "hostname": "node4"
     }
-  },
+  ],
   "layout": {
     "version": 12,
-    "roles": {
-      "ec79480e0ce52ae26fd00c9da684e4fa56658d9c64cdcecb094e936de0bfe71f": {
+    "roles": [
+      {
+        "id": "ec79480e0ce52ae26fd00c9da684e4fa56658d9c64cdcecb094e936de0bfe71f",
         "zone": "dc1",
-        "capacity": 4,
+        "capacity": 10737418240,
         "tags": [
           "node1"
         ]
       },
-      "4a6ae5a1d0d33bf895f5bb4f0a418b7dc94c47c0dd2eb108d1158f3c8f60b0ff": {
+      {
+        "id": "4a6ae5a1d0d33bf895f5bb4f0a418b7dc94c47c0dd2eb108d1158f3c8f60b0ff",
         "zone": "dc1",
-        "capacity": 6,
+        "capacity": 10737418240,
         "tags": [
           "node2"
         ]
       },
-      "23ffd0cdd375ebff573b20cc5cef38996b51c1a7d6dbcf2c6e619876e507cf27": {
+      {
+        "id": "23ffd0cdd375ebff573b20cc5cef38996b51c1a7d6dbcf2c6e619876e507cf27",
         "zone": "dc2",
-        "capacity": 10,
+        "capacity": 10737418240,
         "tags": [
           "node3"
         ]
       }
-    },
-    "stagedRoleChanges": {
-      "e2ee7984ee65b260682086ec70026165903c86e601a4a5a501c1900afe28d84b": {
+    ],
+    "stagedRoleChanges": [
+      {
+        "id": "e2ee7984ee65b260682086ec70026165903c86e601a4a5a501c1900afe28d84b",
+        "remove": false,
         "zone": "dc2",
-        "capacity": 5,
+        "capacity": 10737418240,
         "tags": [
           "node4"
         ]
       }
-    }
+      {
+        "id": "23ffd0cdd375ebff573b20cc5cef38996b51c1a7d6dbcf2c6e619876e507cf27",
+        "remove": true,
+        "zone": null,
+        "capacity": null,
+        "tags": null,
+      }
+    ]
   }
 }
 ```
 
-#### GetClusterHealth `GET /v0/health`
+#### GetClusterHealth `GET /v1/health`
 
 Returns the cluster's current health in JSON format, with the following variables:
 
-- `status`: one of `Healthy`, `Degraded` or `Unavailable`:
-  - Healthy: Garage node is connected to all storage nodes
-  - Degraded: Garage node is not connected to all storage nodes, but a quorum of write nodes is available for all partitions
-  - Unavailable: a quorum of write nodes is not available for some partitions
-- `known_nodes`: the number of nodes this Garage node has had a TCP connection to since the daemon started
-- `connected_nodes`: the nubmer of nodes this Garage node currently has an open connection to
-- `storage_nodes`: the number of storage nodes currently registered in the cluster layout
-- `storage_nodes_ok`: the number of storage nodes to which a connection is currently open
+- `status`: one of `healthy`, `degraded` or `unavailable`:
+  - healthy: Garage node is connected to all storage nodes
+  - degraded: Garage node is not connected to all storage nodes, but a quorum of write nodes is available for all partitions
+  - unavailable: a quorum of write nodes is not available for some partitions
+- `knownNodes`: the number of nodes this Garage node has had a TCP connection to since the daemon started
+- `connectedNodes`: the nubmer of nodes this Garage node currently has an open connection to
+- `storageNodes`: the number of storage nodes currently registered in the cluster layout
+- `storageNodesOk`: the number of storage nodes to which a connection is currently open
 - `partitions`: the total number of partitions of the data (currently always 256)
-- `partitions_quorum`: the number of partitions for which a quorum of write nodes is available
-- `partitions_all_ok`: the number of partitions for which we are connected to all storage nodes responsible of storing it
+- `partitionsQuorum`: the number of partitions for which a quorum of write nodes is available
+- `partitionsAllOk`: the number of partitions for which we are connected to all storage nodes responsible of storing it
 
 Contrarily to `GET /health`, this endpoint always returns a 200 OK HTTP response code.
 
@@ -157,18 +183,18 @@ Example response body:
 
 ```json
 {
-    "status": "Degraded",
-    "known_nodes": 3,
-    "connected_nodes": 2,
-    "storage_nodes": 3,
-    "storage_nodes_ok": 2,
-    "partitions": 256,
-    "partitions_quorum": 256,
-    "partitions_all_ok": 0
+  "status": "degraded",
+  "knownNodes": 3,
+  "connectedNodes": 3,
+  "storageNodes": 4,
+  "storageNodesOk": 3,
+  "partitions": 256,
+  "partitionsQuorum": 256,
+  "partitionsAllOk": 64
 }
 ```
 
-#### ConnectClusterNodes `POST /v0/connect`
+#### ConnectClusterNodes `POST /v1/connect`
 
 Instructs this Garage node to connect to other Garage nodes at specified addresses.
 
@@ -198,7 +224,7 @@ Example response:
 ]
 ```
 
-#### GetClusterLayout `GET /v0/layout`
+#### GetClusterLayout `GET /v1/layout`
 
 Returns the cluster's current layout in JSON, including:
 
@@ -212,42 +238,54 @@ Example response body:
 ```json
 {
   "version": 12,
-  "roles": {
-    "ec79480e0ce52ae26fd00c9da684e4fa56658d9c64cdcecb094e936de0bfe71f": {
+  "roles": [
+    {
+      "id": "ec79480e0ce52ae26fd00c9da684e4fa56658d9c64cdcecb094e936de0bfe71f",
       "zone": "dc1",
-      "capacity": 4,
+      "capacity": 10737418240,
       "tags": [
         "node1"
       ]
     },
-    "4a6ae5a1d0d33bf895f5bb4f0a418b7dc94c47c0dd2eb108d1158f3c8f60b0ff": {
+    {
+      "id": "4a6ae5a1d0d33bf895f5bb4f0a418b7dc94c47c0dd2eb108d1158f3c8f60b0ff",
       "zone": "dc1",
-      "capacity": 6,
+      "capacity": 10737418240,
       "tags": [
         "node2"
       ]
     },
-    "23ffd0cdd375ebff573b20cc5cef38996b51c1a7d6dbcf2c6e619876e507cf27": {
+    {
+      "id": "23ffd0cdd375ebff573b20cc5cef38996b51c1a7d6dbcf2c6e619876e507cf27",
       "zone": "dc2",
-      "capacity": 10,
+      "capacity": 10737418240,
       "tags": [
         "node3"
       ]
     }
-  },
-  "stagedRoleChanges": {
-    "e2ee7984ee65b260682086ec70026165903c86e601a4a5a501c1900afe28d84b": {
+  ],
+  "stagedRoleChanges": [
+    {
+      "id": "e2ee7984ee65b260682086ec70026165903c86e601a4a5a501c1900afe28d84b",
+      "remove": false,
       "zone": "dc2",
-      "capacity": 5,
+      "capacity": 10737418240,
       "tags": [
         "node4"
       ]
     }
-  }
+    {
+      "id": "23ffd0cdd375ebff573b20cc5cef38996b51c1a7d6dbcf2c6e619876e507cf27",
+      "remove": true,
+      "zone": null,
+      "capacity": null,
+      "tags": null,
+    }
+  ]
 }
 ```
 
-#### UpdateClusterLayout `POST /v0/layout`
+#### UpdateClusterLayout `POST /v1/layout`
 
 Send modifications to the cluster layout. These modifications will
 be included in the staged role changes, visible in subsequent calls
@@ -259,8 +297,9 @@ the layout.
 Request body format:
 
 ```json
-{
-  <node_id>: {
+[
+  {
+    "id": <node_id>,
     "capacity": <new_capacity>,
     "zone": <new_zone>,
     "tags": [
@@ -268,17 +307,22 @@ Request body format:
       ...
     ]
   },
-  <node_id_to_remove>: null,
-  ...
-}
+  {
+    "id": <node_id_to_remove>,
+    "remove": true
+  }
+]
 ```
 
 Contrary to the CLI that may update only a subset of the fields
 `capacity`, `zone` and `tags`, when calling this API all of these
 values must be specified.
 
+This returns the new cluster layout with the proposed staged changes,
+as returned by GetClusterLayout.
 
-#### ApplyClusterLayout `POST /v0/layout/apply`
+
+#### ApplyClusterLayout `POST /v1/layout/apply`
 
 Applies to the cluster the layout changes currently registered as
 staged layout changes.
@@ -295,7 +339,10 @@ Similarly to the CLI, the body must include the version of the new layout
 that will be created, which MUST be 1 + the value of the currently
 existing layout in the cluster.
 
-#### RevertClusterLayout `POST /v0/layout/revert`
+This returns the message describing all the calculations done to compute the new
+layout, as well as the description of the layout as returned by GetClusterLayout.
+
+#### RevertClusterLayout `POST /v1/layout/revert`
 
 Clears all of the staged layout changes.
 
@@ -313,10 +360,13 @@ Similarly to the CLI, the body must include the incremented
 version number, which MUST be 1 + the value of the currently
 existing layout in the cluster.
 
+This returns the new cluster layout with all changes reverted,
+as returned by GetClusterLayout.
+
 
 ### Access key operations
 
-#### ListKeys `GET /v0/key`
+#### ListKeys `GET /v1/key`
 
 Returns all API access keys in the cluster.
 
@@ -335,34 +385,8 @@ Example response:
 ]
 ```
 
-#### CreateKey `POST /v0/key`
-
-Creates a new API access key.
-
-Request body format:
-
-```json
-{
-    "name": "NameOfMyKey"
-}
-```
-
-#### ImportKey `POST /v0/key/import`
-
-Imports an existing API key.
-
-Request body format:
-
-```json
-{
-    "accessKeyId": "GK31c2f218a2e44f485b94239e",
-    "secretAccessKey": "b892c0665f0ada8a4755dae98baa3b133590e11dae3bcc1f9d769d67f16c3835",
-    "name": "NameOfMyKey"
-}
-```
-
-#### GetKeyInfo `GET /v0/key?id=<acces key id>`
-#### GetKeyInfo `GET /v0/key?search=<pattern>`
+#### GetKeyInfo `GET /v1/key?id=<acces key id>`
+#### GetKeyInfo `GET /v1/key?search=<pattern>`
 
 Returns information about the requested API access key.
 
@@ -370,6 +394,9 @@ If `id` is set, the key is looked up using its exact identifier (faster).
 If `search` is set, the key is looked up using its name or prefix
 of identifier (slower, all keys are enumerated to do this).
 
+Optionnally, the query parameter `showSecretKey=true` can be set to reveal the
+associated secret access key.
+
 Example response:
 
 ```json
@@ -433,11 +460,40 @@ Example response:
 }
 ```
 
-#### DeleteKey `DELETE /v0/key?id=<acces key id>`
+#### CreateKey `POST /v1/key`
 
-Deletes an API access key.
+Creates a new API access key.
 
-#### UpdateKey `POST /v0/key?id=<acces key id>`
+Request body format:
+
+```json
+{
+    "name": "NameOfMyKey"
+}
+```
+
+This returns the key info, including the created secret key,
+in the same format as the result of GetKeyInfo.
+
+#### ImportKey `POST /v1/key/import`
+
+Imports an existing API key.
+This will check that the imported key is in the valid format, i.e.
+is a key that could have been generated by Garage.
+
+Request body format:
+
+```json
+{
+    "accessKeyId": "GK31c2f218a2e44f485b94239e",
+    "secretAccessKey": "b892c0665f0ada8a4755dae98baa3b133590e11dae3bcc1f9d769d67f16c3835",
+    "name": "NameOfMyKey"
+}
+```
+
+This returns the key info in the same format as the result of GetKeyInfo.
+
+#### UpdateKey `POST /v1/key?id=<acces key id>`
 
 Updates information about the specified API access key.
 
@@ -457,10 +513,16 @@ All fields (`name`, `allow` and `deny`) are optional.
 If they are present, the corresponding modifications are applied to the key, otherwise nothing is changed.
 The possible flags in `allow` and `deny` are: `createBucket`.
 
+This returns the key info in the same format as the result of GetKeyInfo.
+
+#### DeleteKey `DELETE /v1/key?id=<acces key id>`
+
+Deletes an API access key.
+
 
 ### Bucket operations
 
-#### ListBuckets `GET /v0/bucket`
+#### ListBuckets `GET /v1/bucket`
 
 Returns all storage buckets in the cluster.
 
@@ -502,8 +564,8 @@ Example response:
 ]
 ```
 
-#### GetBucketInfo `GET /v0/bucket?id=<bucket id>`
-#### GetBucketInfo `GET /v0/bucket?globalAlias=<alias>`
+#### GetBucketInfo `GET /v1/bucket?id=<bucket id>`
+#### GetBucketInfo `GET /v1/bucket?globalAlias=<alias>`
 
 Returns information about the requested storage bucket.
 
@@ -535,7 +597,10 @@ Example response:
         ],
         "objects": 14827,
         "bytes": 13189855625,
-        "unfinshedUploads": 0,
+        "unfinishedUploads": 1,
+        "unfinishedMultipartUploads": 1,
+        "unfinishedMultipartUploadParts": 11,
+        "unfinishedMultipartUploadBytes": 41943040,
         "quotas": {
             "maxSize": null,
             "maxObjects": null
@@ -543,7 +608,7 @@ Example response:
 }
 ```
 
-#### CreateBucket `POST /v0/bucket`
+#### CreateBucket `POST /v1/bucket`
 
 Creates a new storage bucket.
 
@@ -583,13 +648,7 @@ or no alias at all.
 Technically, you can also specify both `globalAlias` and `localAlias` and that would create
 two aliases, but I don't see why you would want to do that.
 
-#### DeleteBucket `DELETE /v0/bucket?id=<bucket id>`
-
-Deletes a storage bucket. A bucket cannot be deleted if it is not empty.
-
-Warning: this will delete all aliases associated with the bucket!
-
-#### UpdateBucket `PUT /v0/bucket?id=<bucket id>`
+#### UpdateBucket `PUT /v1/bucket?id=<bucket id>`
 
 Updates configuration of the given bucket.
 
@@ -621,9 +680,16 @@ In `quotas`: new values of `maxSize` and `maxObjects` must both be specified, or
 to remove the quotas. An absent value will be considered the same as a `null`. It is not possible
 to change only one of the two quotas.
 
+#### DeleteBucket `DELETE /v1/bucket?id=<bucket id>`
+
+Deletes a storage bucket. A bucket cannot be deleted if it is not empty.
+
+Warning: this will delete all aliases associated with the bucket!
+
+
 ### Operations on permissions for keys on buckets
 
-#### BucketAllowKey `POST /v0/bucket/allow`
+#### BucketAllowKey `POST /v1/bucket/allow`
 
 Allows a key to do read/write/owner operations on a bucket.
 
@@ -644,7 +710,7 @@ Request body format:
 Flags in `permissions` which have the value `true` will be activated.
 Other flags will remain unchanged.
 
-#### BucketDenyKey `POST /v0/bucket/deny`
+#### BucketDenyKey `POST /v1/bucket/deny`
 
 Denies a key from doing read/write/owner operations on a bucket.
 
@@ -668,19 +734,19 @@ Other flags will remain unchanged.
 
 ### Operations on bucket aliases
 
-#### GlobalAliasBucket `PUT /v0/bucket/alias/global?id=<bucket id>&alias=<global alias>`
+#### GlobalAliasBucket `PUT /v1/bucket/alias/global?id=<bucket id>&alias=<global alias>`
 
 Empty body. Creates a global alias for a bucket.
 
-#### GlobalUnaliasBucket `DELETE /v0/bucket/alias/global?id=<bucket id>&alias=<global alias>`
+#### GlobalUnaliasBucket `DELETE /v1/bucket/alias/global?id=<bucket id>&alias=<global alias>`
 
 Removes a global alias for a bucket.
 
-#### LocalAliasBucket `PUT /v0/bucket/alias/local?id=<bucket id>&accessKeyId=<access key ID>&alias=<local alias>`
+#### LocalAliasBucket `PUT /v1/bucket/alias/local?id=<bucket id>&accessKeyId=<access key ID>&alias=<local alias>`
 
 Empty body. Creates a local alias for a bucket in the namespace of a specific access key.
 
-#### LocalUnaliasBucket `DELETE /v0/bucket/alias/local?id=<bucket id>&accessKeyId<access key ID>&alias=<local alias>`
+#### LocalUnaliasBucket `DELETE /v1/bucket/alias/local?id=<bucket id>&accessKeyId<access key ID>&alias=<local alias>`
 
 Removes a local alias for a bucket in the namespace of a specific access key.
 

doc/optimal_layout_report/.gitignore

@@ -0,0 +1,13 @@
+optimal_layout.aux
+optimal_layout.log
+optimal_layout.synctex.gz
+optimal_layout.bbl
+optimal_layout.blg
+
+geodistrib.aux
+geodistrib.bbl
+geodistrib.blg
+geodistrib.log
+geodistrib.out
+geodistrib.synctex.gz
+

doc/optimal_layout_report/geodistrib.tex

@@ -0,0 +1,317 @@
+\documentclass[]{article}
+
+\usepackage{amsmath,amssymb}
+\usepackage{amsthm}
+
+\usepackage{stmaryrd}
+
+\usepackage{graphicx,xcolor}
+\usepackage{hyperref}
+
+\usepackage{algorithm,algpseudocode,float} 
+
+\renewcommand\thesubsubsection{\Alph{subsubsection})}
+
+\newtheorem{proposition}{Proposition}
+
+%opening
+\title{An algorithm for geo-distributed and redundant storage in Garage}
+\author{Mendes Oulamara \\ \emph{mendes@deuxfleurs.fr}}
+\date{}
+
+\begin{document}
+
+\maketitle
+
+\begin{abstract}
+	Garage
+\end{abstract}
+
+\section{Introduction}
+
+Garage\footnote{\url{https://garagehq.deuxfleurs.fr/}} is an open-source distributed object storage service tailored for self-hosting. It was designed by the Deuxfleurs association\footnote{\url{https://deuxfleurs.fr/}} to enable small structures (associations, collectives, small companies) to share storage resources to reliably self-host their data, possibly with old and non-reliable machines.
+
+To achieve these reliability and availability goals, the data is broken into \emph{partitions} and every partition is replicated over 3 different machines (that we call \emph{nodes}). When the data is queried, a consensus algorithm allows to fetch it from one of the nodes. A \emph{replication factor} of 3 ensures the best guarantees in the consensus algorithm \cite{ADD RREF}, but this parameter can be different.
+
+Moreover, if the nodes are spread over different \emph{zones} (different houses, offices, cities\dots), we can ask the data to be replicated over nodes belonging to different zones, to improve the storage robustness against zone failure (such as power outage). To do so, we set a \emph{redundancy parameter}, that is no more than the replication factor, and we ask that any partition is replicated over this number of zones at least.
+
+In this work, we propose a repartition algorithm that, given the nodes specifications and the replication and redundancy parameters, computes an optimal assignation of partitions to nodes. We say that the assignation is optimal in the sense that it maximizes the size of the partitions, and hence the effective storage capacity of the system.
+
+Moreover, when a former assignation exists, which is not optimal anymore due to nodes or zones updates, our algorithm computes a new optimal assignation that minimizes the amount of data to be transferred during the assignation update (the \emph{transfer load}).
+
+We call the set of nodes cooperating to store the data a \emph{cluster}, and a description of the nodes, zones and the assignation of partitions to nodes a \emph{cluster layout}
+
+\subsection{Notations}
+
+Let $k$ be some fixed parameter value, typically 8, that we call the ``partition bits''.
+Every object to be stored in the system is split into data blocks of fixed size. We compute a hash $h(\mathbf{b})$ of every such block $\mathbf{b}$, and we define the $k$ last bits of this hash to be the partition number $p(\mathbf{b})$ of the block. This label can take $P=2^k$ different values, and hence there are $P$ different partitions. We denote $\mathbf{P}$ the set of partition labels (i.e. $\mathbf{P}=\llbracket1,P\rrbracket$).
+
+We are given a set $\mathbf{N}$ of $N$ nodes  and a set  $\mathbf{Z}$ of $Z$ zones. Every node $n$ has a non-negative storage capacity $c_n\ge 0$ and belongs to a zone $z_n\in \mathbf{Z}$. We are also given a replication parameter $\rho_\mathbf{N}$ and a redundancy parameter $\rho_\mathbf{Z}$ such that  $1\le \rho_\mathbf{Z} \le \rho_\mathbf{N}$ (typical values would be $\rho_N=3$ and $\rho_Z=2$).
+
+Our goal is to compute an assignment $\alpha = (\alpha_p^1, \ldots, \alpha_p^{\rho_\mathbf{N}})_{p\in \mathbf{P}}$ such that every partition $p$ is associated to $\rho_\mathbf{N}$ distinct nodes $\alpha_p^1, \ldots, \alpha_p^{\rho_\mathbf{N}} \in \mathbf{N}$ and these nodes belong to at least $\rho_\mathbf{Z}$ distinct zones. Among the possible assignations, we choose one that \emph{maximizes} the effective storage capacity of the cluster. If the layout contained a previous assignment $\alpha'$, we \emph{minimize} the amount of data to transfer during the layout update by making $\alpha$ as close as possible to $\alpha'$. These maximization and minimization are described more formally in the following section.
+
+\subsection{Optimization parameters}
+
+To link the effective storage capacity of the cluster to partition assignment, we make the following assumption:
+\begin{equation}
+	\tag{H1}
+	\text{\emph{All partitions have the same size $s$.}}
+\end{equation}
+This assumption is justified by the dispersion of the hashing function, when the number of partitions is small relative to the number of stored blocks.
+
+Every node $n$ wille store some number $p_n$ of partitions (it is the number of partitions $p$ such that $n$ appears in the $\alpha_p$). Hence the partitions stored by $n$ (and hence all partitions by our assumption) have there size bounded by $c_n/p_n$. This remark leads us to define the optimal size that we will want to maximize:
+
+\begin{equation}
+	\label{eq:optimal}
+	\tag{OPT}
+s^* = \min_{n \in N} \frac{c_n}{p_n}.
+\end{equation}
+
+When the capacities of the nodes are updated (this includes adding or removing a node), we want to update the assignment as well. However, transferring the data between nodes has a cost and we would like to limit the number of changes in the assignment. We make the following assumption:
+\begin{equation}
+	\tag{H2}
+	\text{\emph{Nodes updates happen rarely relatively to block operations.}}
+\end{equation}
+This assumption justifies that when we compute the new assignment $\alpha$, it is worth to optimize the partition size \eqref{eq:optimal} first, and then, among the possible optimal solution, to try to minimize the number of partition transfers. More formally, we minimize the distance between two assignments defined by
+\begin{equation}
+	d(\alpha, \alpha') := \#\{ (n,p) \in \mathbf{N}\times\mathbf{P} ~|~ n\in \alpha_p \triangle \alpha'_p \}
+\end{equation}
+where the symmetric difference $\alpha_p \triangle \alpha'_p$ denotes the nodes appearing in one of the assignations but not in both.
+
+\section{Computation of an optimal assignment}
+
+The algorithm that we propose takes as inputs the cluster layout parameters $\mathbf{N}$, $\mathbf{Z}$, $\mathbf{P}$, $(c_n)_{n\in \mathbf{N}}$, $\rho_\mathbf{N}$, $\rho_\mathbf{Z}$, that we defined in the introduction, together with the former assignation $\alpha'$ (if any). The computation of the new optimal assignation $\alpha^*$ is done in three successive steps that will be detailed in the following sections. The first step computes the largest partition size $s^*$ that an assignation can achieve. The second step computes an optimal candidate assignment $\alpha$ that achieves $s^*$ and a heuristic is used in the computation to make it hopefully close to $\alpha'$. The third steps modifies $\alpha$ iteratively to reduces $d(\alpha, \alpha')$ and yields an assignation $\alpha^*$ achieving $s^*$, and minimizing $d(\cdot, \alpha')$ among such assignations.
+
+We will explain in the next section how to represent an assignment $\alpha$ by a flow $f$ on a weighted graph $G$ to enable the use of flow and graph algorithms. The main function of the algorithm can be written as follows.
+
+\subsubsection*{Algorithm}
+
+\begin{algorithmic}[1]
+	\Function{Compute Layout}{$\mathbf{N}$, $\mathbf{Z}$, $\mathbf{P}$, $(c_n)_{n\in \mathbf{N}}$, $\rho_\mathbf{N}$, $\rho_\mathbf{Z}$, $\alpha'$}
+	\State $s^* \leftarrow$ \Call{Compute Partition Size}{$\mathbf{N}$, $\mathbf{Z}$, $\mathbf{P}$, $(c_n)_{n\in \mathbf{N}}$, $\rho_\mathbf{N}$, $\rho_\mathbf{Z}$}
+	\State $G \leftarrow G(s^*)$
+	\State $f \leftarrow$ 	\Call{Compute Candidate Assignment}{$G$, $\alpha'$}
+	\State $f^* \leftarrow$ 	\Call{Minimize transfer load}{$G$, $f$, $\alpha'$}
+	\State Build $\alpha^*$ from $f^*$
+	\State \Return $\alpha^*$
+	\EndFunction
+\end{algorithmic}
+
+\subsubsection*{Complexity}
+As we will see in the next sections, the worst case complexity of this algorithm is $O(P^2 N^2)$. The minimization of transfer load is the most expensive step, and it can run with a timeout since it is only an optimization step. Without this step (or with a smart timeout), the worst cas complexity can be $O((PN)^{3/2}\log C)$ where $C$ is the total storage capacity of the cluster. 
+
+\subsection{Determination of the partition size $s^*$}
+
+We will represent an assignment $\alpha$ as a flow in a specific graph $G$. We will not compute the optimal partition size $s^*$ a priori, but we will determine it by dichotomy, as the largest size $s$ such that the maximal flow achievable on $G=G(s)$ has value $\rho_\mathbf{N}P$. We will assume that the capacities are given in a small enough unit (say, Megabytes), and we will determine $s^*$ at the precision of the given unit.
+
+Given some candidate size value $s$, we describe the oriented weighted graph $G=(V,E)$ with vertex set $V$ arc set $E$ (see Figure \ref{fig:flowgraph}).
+
+The set of vertices $V$ contains the source $\mathbf{s}$, the sink $\mathbf{t}$, vertices 
+$\mathbf{p^+, p^-}$ for every partition $p$, vertices $\mathbf{x}_{p,z}$ for every partition $p$ and zone $z$, and vertices $\mathbf{n}$ for every node $n$. 
+
+The set of arcs $E$ contains:
+\begin{itemize}
+	\item ($\mathbf{s}$,$\mathbf{p}^+$, $\rho_\mathbf{Z}$) for every partition $p$;
+	\item ($\mathbf{s}$,$\mathbf{p}^-$, $\rho_\mathbf{N}-\rho_\mathbf{Z}$) for every partition $p$;
+	\item ($\mathbf{p}^+$,$\mathbf{x}_{p,z}$, 1) for every partition $p$ and zone $z$;
+	\item ($\mathbf{p}^-$,$\mathbf{x}_{p,z}$, $\rho_\mathbf{N}-\rho_\mathbf{Z}$) for every partition $p$ and zone $z$;
+	\item ($\mathbf{x}_{p,z}$,$\mathbf{n}$, 1) for every partition $p$, zone $z$ and node $n\in z$;
+	\item ($\mathbf{n}$, $\mathbf{t}$, $\lfloor c_n/s \rfloor$) for every node $n$.
+\end{itemize}
+
+\begin{figure}
+	\centering
+	\includegraphics[width=\linewidth]{figures/flow_graph_param}
+	\caption{An example of graph $G(s)$. Arcs are oriented from left to right, and unlabeled arcs have capacity 1. In this example, nodes $n_1,n_2,n_3$ belong to zone $z_1$, and nodes $n_4,n_5$ belong to zone $z_2$.}
+	\label{fig:flowgraph}
+\end{figure}
+
+In the following complexity calculations, we will use the number of vertices and edges of $G$. Remark from now that $\# V = O(PZ)$ and $\# E = O(PN)$.
+
+\begin{proposition}
+	An assignment $\alpha$ is realizable with partition size $s$ and the redundancy constraints $(\rho_\mathbf{N},\rho_\mathbf{Z})$ if and only if there exists a maximal flow function $f$ in $G$ with total flow $\rho_\mathbf{N}P$, such that the arcs ($\mathbf{x}_{p,z}$,$\mathbf{n}$, 1) used are exactly those for which $p$ is associated to $n$ in $\alpha$.
+\end{proposition}
+\begin{proof}
+	Given such flow $f$, we can reconstruct a candidate $\alpha$. In $f$, the flow passing through $\mathbf{p^+}$ and $\mathbf{p^-}$ is $\rho_\mathbf{N}$, and since the outgoing capacity of every $\mathbf{x}_{p,z}$ is 1, every partition is associated to $\rho_\mathbf{N}$ distinct nodes. The fraction $\rho_\mathbf{Z}$ of the flow passing through every $\mathbf{p^+}$ must be spread over as many distinct zones as every arc outgoing from $\mathbf{p^+}$ has capacity 1. So the reconstructed $\alpha$ verifies the redundancy constraints. For every node $n$, the flow between $\mathbf{n}$ and $\mathbf{t}$ corresponds to the number of partitions associated to $n$. By construction of $f$, this does not exceed $\lfloor c_n/s \rfloor$. We assumed that the partition size is $s$, hence this association does not exceed the storage capacity of the nodes.
+	
+	In the other direction, given an assignment $\alpha$, one can similarly check that the facts that $\alpha$ respects the redundancy constraints, and the storage capacities of the nodes, are necessary condition to construct a maximal flow function $f$.
+\end{proof}
+
+\textbf{Implementation remark:} In the flow algorithm, while exploring the graph, we explore the neighbours of every vertex in a random order to heuristically spread the associations between nodes and partitions.
+
+\subsubsection*{Algorithm}
+With this result mind, we can describe the first step of our algorithm. All divisions are supposed to be integer divisions.
+\begin{algorithmic}[1]
+	\Function{Compute Partition Size}{$\mathbf{N}$, $\mathbf{Z}$, $\mathbf{P}$, $(c_n)_{n\in \mathbf{N}}$, $\rho_\mathbf{N}$, $\rho_\mathbf{Z}$}
+	
+	\State Build the graph $G=G(s=1)$
+	\State $ f \leftarrow$ \Call{Maximal flow}{$G$}
+	\If{$f.\mathrm{total flow} < \rho_\mathbf{N}P$}
+	
+	\State \Return Error: capacities too small or constraints too strong.
+	\EndIf
+	
+	\State $s^- \leftarrow 1$
+	\State $s^+ \leftarrow 1+\frac{1}{\rho_\mathbf{N}}\sum_{n \in \mathbf{N}} c_n$
+	
+	\While{$s^-+1 < s^+$}
+	\State Build the graph $G=G(s=(s^-+s^+)/2)$
+	\State $ f \leftarrow$ \Call{Maximal flow}{$G$}
+	\If{$f.\mathrm{total flow} < \rho_\mathbf{N}P$}
+	\State $s^+ \leftarrow (s^- + s^+)/2$
+	\Else
+	\State $s^- \leftarrow (s^- + s^+)/2$
+	\EndIf
+	\EndWhile
+	
+	\State \Return $s^-$
+	\EndFunction
+\end{algorithmic}
+
+\subsubsection*{Complexity}
+
+To compute the maximal flow, we use Dinic's algorithm. Its complexity on general graphs is $O(\#V^2 \#E)$, but on graphs with edge capacity bounded by a constant, it turns out to be $O(\#E^{3/2})$. The graph $G$ does not fall in this case since the capacities of the arcs incoming to $\mathbf{t}$ are far from bounded. However, the proof of this complexity function works readily for graphs where we only ask the edges \emph{not} incoming to the sink $\mathbf{t}$ to have their capacities bounded by a constant. One can find the proof of this claim in \cite[Section 2]{even1975network}.
+The dichotomy adds a logarithmic factor $\log (C)$ where $C=\sum_{n \in \mathbf{N}} c_n$ is the total capacity of the cluster. The total complexity of this first function is hence 
+$O(\#E^{3/2}\log C ) = O\big((PN)^{3/2} \log C\big)$.
+
+\subsubsection*{Metrics}
+We can display the discrepancy between the computed $s^*$ and the best size we could have hoped for the given total capacity, that is $C/\rho_\mathbf{N}$.
+
+\subsection{Computation of a candidate assignment}
+
+Now that we have the optimal partition size $s^*$, to compute a candidate assignment it would be enough to compute a maximal flow function $f$ on $G(s^*)$. This is what we do if there is no former assignation $\alpha'$.
+
+If there is some $\alpha'$, we add a step that will heuristically help to obtain a candidate $\alpha$ closer to $\alpha'$. We fist compute a flow function $\tilde{f}$ that uses only the partition-to-node associations appearing in $\alpha'$. Most likely, $\tilde{f}$ will not be a maximal flow of $G(s^*)$. In Dinic's algorithm, we can start from a non maximal flow function and then discover improving paths. This is what we do by starting from $\tilde{f}$. The hope\footnote{This is only a hope, because one can find examples where the construction of $f$ from $\tilde{f}$ produces an assignment $\alpha$ that is not as close as possible to $\alpha'$.} is that the final flow function $f$ will tend to keep the associations appearing in $\tilde{f}$.
+
+More formally, we construct the graph $G_{|\alpha'}$ from $G$ by removing all the arcs $(\mathbf{x}_{p,z},\mathbf{n}, 1)$ where $p$ is not associated to $n$ in $\alpha'$. We compute a maximal flow function $\tilde{f}$ in $G_{|\alpha'}$. The flow $\tilde{f}$ is also a valid (most likely non maximal) flow function on $G$. We compute a maximal flow function $f$ on $G$ by starting Dinic's algorithm on $\tilde{f}$.
+
+\subsubsection*{Algorithm}
+\begin{algorithmic}[1]
+	\Function{Compute Candidate Assignment}{$G$, $\alpha'$}
+	\State Build the graph $G_{|\alpha'}$
+	\State $ \tilde{f} \leftarrow$ \Call{Maximal flow}{$G_{|\alpha'}$}
+	\State $ f \leftarrow$ \Call{Maximal flow from flow}{$G$, $\tilde{f}$}
+	\State \Return $f$
+	\EndFunction
+\end{algorithmic}
+
+~ 
+
+\textbf{Remark:} The function ``Maximal flow'' can be just seen as the function ``Maximal flow from flow'' called with the zero flow function as starting flow.
+
+\subsubsection*{Complexity}
+With the considerations of the last section, we have the complexity of the Dinic's algorithm $O(\#E^{3/2}) = O((PN)^{3/2})$.
+
+\subsubsection*{Metrics}
+
+We can display the flow value of $\tilde{f}$, which is an upper bound of the distance between $\alpha$ and $\alpha'$. It might be more a Debug level display than Info.
+
+\subsection{Minimization of the transfer load}
+
+Now that we have a candidate flow function $f$, we want to modify it to make its corresponding assignation $\alpha$ as close as possible to $\alpha'$. Denote by $f'$ the maximal flow corresponding to $\alpha'$, and let $d(f, \alpha')=d(f, f'):=d(\alpha,\alpha')$\footnote{It is the number of arcs of type $(\mathbf{x}_{p,z},\mathbf{n})$ saturated in one flow and not in the other.}. 
+We want to build a sequence $f=f_0, f_1, f_2 \dots$ of maximal flows such that $d(f_i, \alpha')$ decreases as $i$ increases. The distance being a non-negative integer, this sequence of flow functions must be finite. We now explain how to find some improving $f_{i+1}$ from $f_i$.
+
+For any maximal flow $f$ in $G$, we define the oriented weighted graph $G_f=(V, E_f)$ as follows. The vertices of $G_f$ are the same as the vertices of $G$. $E_f$ contains the arc $(v_1,v_2, w)$ between vertices $v_1,v_2\in V$ with weight $w$ if and only if the arc $(v_1,v_2)$ is not saturated in $f$ (i.e. $c(v_1,v_2)-f(v_1,v_2) \ge 1$, we also consider reversed arcs). The weight $w$ is: 
+\begin{itemize}
+	\item  $-1$  if $(v_1,v_2)$ is of type $(\mathbf{x}_{p,z},\mathbf{n})$ or $(\mathbf{x}_{p,z},\mathbf{n})$ and is saturated in only one of the two flows $f,f'$;
+	\item $+1$  if $(v_1,v_2)$ is of type $(\mathbf{x}_{p,z},\mathbf{n})$ or $(\mathbf{x}_{p,z},\mathbf{n})$ and is saturated in either both or none of the two flows $f,f'$;
+	\item $0$ otherwise.
+\end{itemize}
+
+If $\gamma$ is a simple cycle of arcs in $G_f$, we define its weight $w(\gamma)$ as the sum of the weights of its arcs. We can add $+1$ to the value of $f$ on the arcs of $\gamma$, and by construction of $G_f$ and the fact that $\gamma$ is a cycle, the function that we get is still a valid flow function on $G$, it is maximal as it has the same flow value as $f$. We denote this new function $f+\gamma$.
+
+\begin{proposition}
+	Given a maximal flow $f$ and a simple cycle $\gamma$ in $G_f$, we have $d(f+\gamma, f') - d(f,f') = w(\gamma)$.
+\end{proposition}
+\begin{proof}
+	Let $X$ be the set of arcs of type $(\mathbf{x}_{p,z},\mathbf{n})$. Then we can express $d(f,f')$ as
+	\begin{align*}
+		d(f,f') & = \#\{e\in X ~|~ f(e)\neq f'(e)\}
+		= \sum_{e\in X} 1_{f(e)\neq f'(e)} \\
+		& = \frac{1}{2}\big( \#X + \sum_{e\in X} 1_{f(e)\neq f'(e)} - 1_{f(e)= f'(e)} \big).
+	\end{align*}
+	We can express the cycle weight as
+	\begin{align*}
+		w(\gamma) &  = \sum_{e\in X, e\in \gamma} - 1_{f(e)\neq f'(e)} + 1_{f(e)= f'(e)}.
+	\end{align*}
+	Remark that since we passed on unit of flow in $\gamma$ to construct $f+\gamma$, we have for any $e\in X$, $f(e)=f'(e)$ if and only if $(f+\gamma)(e) \neq f'(e)$.
+	Hence
+	\begin{align*}
+		w(\gamma) &  = \frac{1}{2}(w(\gamma) + w(\gamma)) \\
+		&= \frac{1}{2} \Big( 
+		\sum_{e\in X, e\in \gamma} - 1_{f(e)\neq f'(e)} +  1_{f(e)= f'(e)} \\
+		& \qquad +
+		\sum_{e\in X, e\in \gamma} 1_{(f+\gamma)(e)\neq f'(e)} +  1_{(f+\gamma)(e)= f'(e)}
+		\Big).
+	\end{align*}
+	Plugging this in the previous equation, we find that 
+	$$d(f,f')+w(\gamma) = d(f+\gamma, f').$$
+\end{proof}
+
+This result suggests that given some flow $f_i$, we just need to find a negative cycle $\gamma$ in $G_{f_i}$ to construct $f_{i+1}$ as $f_i+\gamma$. The following proposition ensures that this greedy strategy reaches an optimal flow. 
+
+\begin{proposition}
+	For any maximal flow $f$, $G_f$ contains a negative cycle if and only if there exists a maximal flow $f^*$ in $G$ such that $d(f^*, f') < d(f, f')$.
+\end{proposition}
+\begin{proof}
+	Suppose that there is such flow $f^*$. Define the oriented multigraph $M_{f,f^*}=(V,E_M)$ with the same vertex set $V$ as in $G$, and for every $v_1,v_2 \in V$, $E_M$ contains $(f^*(v_1,v_2) - f(v_1,v_2))_+$  copies of the arc $(v_1,v_2)$. For every vertex $v$, its total degree (meaning its outer degree minus its inner degree) is equal to 
+	\begin{align*}
+		\deg v & = \sum_{u\in V} (f^*(v,u) - f(v,u))_+ - \sum_{u\in V} (f^*(u,v) - f(u,v))_+  \\
+		& = \sum_{u\in V} f^*(v,u) - f(v,u) = \sum_{u\in V} f^*(v,u) - \sum_{u\in V}  f(v,u).
+	\end{align*}
+	The last two sums are zero for any inner vertex since $f,f^*$ are flows, and they are equal on the source and sink since the two flows are both maximal and have hence the same value. Thus, $\deg v = 0$ for every vertex $v$.
+	
+	This implies that the multigraph $M_{f,f^*}$ is the union of disjoint simple cycles. $f$ can be transformed into $f^*$ by pushing a mass 1 along all these cycles in any order. Since $d(f^*, f')<d(f,f')$, there must exists one of these simple cycles $\gamma$ with $d(f+\gamma, f') < d(f, f')$. Finally, since we can push a mass in $f$ along $\gamma$, it must appear in $G_f$. Hence $\gamma$ is a cycle of $G_f$ with negative weight.
+\end{proof}
+
+In the next section we describe the corresponding algorithm. Instead of discovering only one cycle, we are allowed to discover a set $\Gamma$ of disjoint negative cycles. 
+
+\subsubsection*{Algorithm}
+\begin{algorithmic}[1]
+	\Function{Minimize transfer load}{$G$, $f$, $\alpha'$}
+	\State Build the graph $G_f$
+	\State $\Gamma \leftarrow$ \Call{Detect Negative Cycles}{$G_f$}
+	\While{$\Gamma \neq \emptyset$}
+	\ForAll{$\gamma \in \Gamma$}
+	\State $f \leftarrow f+\gamma$
+	\EndFor
+	\State Update $G_f$
+	\State $\Gamma \leftarrow$ \Call{Detect Negative Cycles}{$G_f$}
+	\EndWhile
+	\State \Return $f$
+	\EndFunction
+\end{algorithmic}
+
+\subsubsection*{Complexity}
+The distance $d(f,f')$ is bounded by the maximal number of differences in the associated assignment. If these assignment are totally disjoint, this distance is $2\rho_N P$. At every iteration of the While loop, the distance decreases, so there is at most $O(\rho_N P) = O(P)$ iterations.
+
+The detection of negative cycle is done with the Bellman-Ford algorithm, whose complexity should normally be $O(\#E\#V)$. In our case, it amounts to $O(P^2ZN)$. Multiplied by the complexity of the outer loop, it amounts to $O(P^3ZN)$ which is a lot when the number of partitions and nodes starts to be large. To avoid that, we adapt the Bellman-Ford algorithm.
+
+The Bellman-Ford algorithm runs $\#V$ iterations of an outer loop, and an inner loop over $E$. The idea is to compute the shortest paths from a source vertex $v$ to all other vertices. After $k$ iterations of the outer loop, the algorithm has computed all shortest path of length at most $k$. All simple paths have length at most $\#V-1$, so if there is an update in the last iteration of the loop, it means that there is a negative cycle in the graph. The observation that will enable us to improve the complexity is the following:
+
+\begin{proposition}
+	In the graph $G_f$ (and $G$), all simple paths have a length at most $4N$.
+\end{proposition}
+\begin{proof}
+	Since $f$ is a maximal flow, there is no outgoing edge from $\mathbf{s}$ in $G_f$. One can thus check than any simple path of length 4 must contain at least two node of type $\mathbf{n}$. Hence on a path, at most 4 arcs separate two successive nodes of type $\mathbf{n}$. 
+\end{proof}
+
+Thus, in the absence of negative cycles, shortest paths in $G_f$ have length at most $4N$. So we can do only $4N+1$ iterations of the outer loop in the Bellman-Ford algorithm. This makes the complexity of the detection of one set of cycle to be $O(N\#E) = O(N^2 P)$.
+
+With this improvement, the complexity of the whole algorithm is, in the worst case, $O(N^2P^2)$. However, since we detect several cycles at once and we start with a flow that might be close to the previous one, the number of iterations of the outer loop might be smaller in practice.
+
+
+
+\subsubsection*{Metrics}
+We can display the node and zone utilization ratio, by dividing the flow passing through them divided by their outgoing capacity. In particular, we can pinpoint saturated nodes and zones (i.e. used at their full potential).
+
+We can display the distance to the previous assignment, and the number of partition transfers.
+
+
+\bibliography{optimal_layout} 
+\bibliographystyle{ieeetr}
+
+\end{document}
+
+
+

doc/optimal_layout_report/optimal_layout.bib

@@ -0,0 +1,11 @@
+
+@article{even1975network,
+	title={Network flow and testing graph connectivity},
+	author={Even, Shimon and Tarjan, R Endre},
+	journal={SIAM journal on computing},
+	volume={4},
+	number={4},
+	pages={507--518},
+	year={1975},
+	publisher={SIAM}
+}

doc/optimal_layout_report/optimal_layout.tex

@@ -0,0 +1,709 @@
+\documentclass[]{article}
+
+\usepackage{amsmath,amssymb}
+\usepackage{amsthm}
+
+\usepackage{graphicx,xcolor}
+
+\usepackage{algorithm,algpseudocode,float} 
+
+\renewcommand\thesubsubsection{\Alph{subsubsection})}
+
+\newtheorem{proposition}{Proposition}
+
+%opening
+\title{Optimal partition assignment in Garage}
+\author{Mendes}
+
+\begin{document}
+
+\maketitle
+
+\section{Introduction}
+
+\subsection{Context}
+
+Garage is an open-source distributed storage service blablabla$\dots$
+
+Every object to be stored in the system falls in a partition given by the last $k$ bits of its hash. There are $P=2^k$ partitions. Every partition will be stored on distinct nodes of the system. The goal of the assignment of partitions to nodes is to ensure (nodes and zone) redundancy and to be as efficient as possible.
+
+\subsection{Formal description of the problem}
+
+We are given a set of nodes $\mathbf{N}$ and a set of zones $\mathbf{Z}$. Every node $n$ has a non-negative storage capacity $c_n\ge 0$ and belongs to a zone $z\in \mathbf{Z}$. We are also given a number of partition $P>0$ (typically $P=256$).
+
+We would like to compute an assignment of nodes to partitions. We will impose some redundancy constraints to this assignment, and under these constraints, we want our system to have the largest storage capacity possible. To link storage capacity to partition assignment, we make the following assumption:
+\begin{equation}
+	\tag{H1}
+	\text{\emph{All partitions have the same size $s$.}}
+\end{equation}
+This assumption is justified by the dispersion of the hashing function, when the number of partitions is small relative to the number of stored large objects.
+
+Every node $n$ wille store some number $k_n$ of partitions. Hence the partitions stored by $n$ (and hence all partitions by our assumption) have there size bounded by $c_n/k_n$. This remark leads us to define the optimal size that we will want to maximize:
+
+\begin{equation}
+	\label{eq:optimal}
+	\tag{OPT}
+s^* = \min_{n \in N} \frac{c_n}{k_n}.
+\end{equation}
+
+When the capacities of the nodes are updated (this includes adding or removing a node), we want to update the assignment as well. However, transferring the data between nodes has a cost and we would like to limit the number of changes in the assignment. We make the following assumption:
+\begin{equation}
+	\tag{H2}
+	\text{\emph{Updates of capacity happens rarely relatively to object storing.}}
+\end{equation}
+This assumption justifies that when we compute the new assignment, it is worth to optimize the partition size \eqref{eq:optimal} first, and then, among the possible optimal solution, to try to minimize the number of partition transfers.
+
+For now, in the following, we ask the following redundancy constraint:
+
+\textbf{Parametric node and zone redundancy:} Given two integer parameters $1\le \rho_\mathbf{Z} \le \rho_\mathbf{N}$, we ask every partition to be stored on $\rho_\mathbf{N}$ distinct nodes, and these nodes must belong to at least $\rho_\mathbf{Z}$ distinct zones.
+
+
+\textbf{Mode 3-strict:}  every partition needs to be assignated to three nodes belonging to three different zones.
+
+\textbf{Mode 3:} every partition needs to be assignated to three nodes. We try to spread the three nodes over different zones as much as possible.
+
+\textbf{Warning:} This is a working document written incrementaly. The last version of the algorithm is the \textbf{parametric assignment} described in the next section.
+
+
+\section{Computation of a parametric assignment}
+\textbf{Attention : }We change notations in this section.
+
+Notations : let $P$ be the number of partitions, $N$ the number of nodes, $Z$ the number of zones. Let $\mathbf{P,N,Z}$ be the label sets of, respectively, partitions, nodes and zones.
+Let $s^*$ be the largest partition size achievable with the redundancy constraints. Let $(c_n)_{n\in \mathbf{N}}$ be the storage capacity of every node. 
+
+In this section, we propose a third specification of the problem. The user inputs two redundancy parameters $1\le \rho_\mathbf{Z} \le \rho_\mathbf{N}$. We compute an assignment $\alpha = (\alpha_p^1, \ldots, \alpha_p^{\rho_\mathbf{N}})_{p\in \mathbf{P}}$ such that every partition $p$ is associated to $\rho_\mathbf{N}$ distinct nodes $\alpha_p^1, \ldots, \alpha_p^{\rho_\mathbf{N}}$ and these nodes belong to at least $\rho_\mathbf{Z}$ distinct zones.
+
+If the layout contained a previous assignment $\alpha'$, we try to minimize the amount of data to transfer during the layout update by making $\alpha$ as close as possible to $\alpha'$.
+
+In the following subsections, we describe the successive steps of the algorithm we propose to compute $\alpha$.
+
+\subsubsection*{Algorithm}
+
+\begin{algorithmic}[1]
+	\Function{Compute Layout}{$\mathbf{N}$, $\mathbf{Z}$, $\mathbf{P}$, $(c_n)_{n\in \mathbf{N}}$, $\rho_\mathbf{N}$, $\rho_\mathbf{Z}$, $\alpha'$}
+	\State $s^* \leftarrow$ \Call{Compute Partition Size}{$\mathbf{N}$, $\mathbf{Z}$, $\mathbf{P}$, $(c_n)_{n\in \mathbf{N}}$, $\rho_\mathbf{N}$, $\rho_\mathbf{Z}$}
+	\State $G \leftarrow G(s^*)$
+	\State $f \leftarrow$ 	\Call{Compute Candidate Assignment}{$G$, $\alpha'$}
+	\State $f^* \leftarrow$ 	\Call{Minimize transfer load}{$G$, $f$, $\alpha'$}
+	\State Build $\alpha^*$ from $f^*$
+	\State \Return $\alpha^*$
+	\EndFunction
+\end{algorithmic}
+
+\subsubsection*{Complexity}
+As we will see in the next sections, the worst case complexity of this algorithm is $O(P^2 N^2)$. The minimization of transfer load is the most expensive step, and it can run with a timeout since it is only an optimization step. Without this step (or with a smart timeout), the worst cas complexity can be $O((PN)^{3/2}\log C)$ where $C$ is the total storage capacity of the cluster. 
+
+\subsection{Determination of the partition size $s^*$}
+
+Again, we will represent an assignment $\alpha$ as a flow in a specific graph $G$. We will not compute the optimal partition size $s^*$ a priori, but we will determine it by dichotomy, as the largest size $s$ such that the maximal flow achievable on $G=G(s)$ has value $\rho_\mathbf{N}P$. We will assume that the capacities are given in a small enough unit (say, Megabytes), and we will determine $s^*$ at the precision of the given unit.
+
+Given some candidate size value $s$, we describe the oriented weighted graph $G=(V,E)$ with vertex set $V$ arc set $E$.
+
+The set of vertices $V$ contains the source $\mathbf{s}$, the sink $\mathbf{t}$, vertices 
+$\mathbf{p^+, p^-}$ for every partition $p$, vertices $\mathbf{x}_{p,z}$ for every partition $p$ and zone $z$, and vertices $\mathbf{n}$ for every node $n$. 
+
+The set of arcs $E$ contains:
+\begin{itemize}
+	\item ($\mathbf{s}$,$\mathbf{p}^+$, $\rho_\mathbf{Z}$) for every partition $p$;
+	\item ($\mathbf{s}$,$\mathbf{p}^-$, $\rho_\mathbf{N}-\rho_\mathbf{Z}$) for every partition $p$;
+	\item ($\mathbf{p}^+$,$\mathbf{x}_{p,z}$, 1) for every partition $p$ and zone $z$;
+	\item ($\mathbf{p}^-$,$\mathbf{x}_{p,z}$, $\rho_\mathbf{N}-\rho_\mathbf{Z}$) for every partition $p$ and zone $z$;
+	\item ($\mathbf{x}_{p,z}$,$\mathbf{n}$, 1) for every partition $p$, zone $z$ and node $n\in z$;
+	\item ($\mathbf{n}$, $\mathbf{t}$, $\lfloor c_n/s \rfloor$) for every node $n$.
+\end{itemize}
+
+In the following complexity calculations, we will use the number of vertices and edges of $G$. Remark from now that $\# V = O(PZ)$ and $\# E = O(PN)$.
+
+\begin{proposition}
+	An assignment $\alpha$ is realizable with partition size $s$ and the redundancy constraints $(\rho_\mathbf{N},\rho_\mathbf{Z})$ if and only if there exists a maximal flow function $f$ in $G$ with total flow $\rho_\mathbf{N}P$, such that the arcs ($\mathbf{x}_{p,z}$,$\mathbf{n}$, 1) used are exactly those for which $p$ is associated to $n$ in $\alpha$.
+\end{proposition}
+\begin{proof}
+	Given such flow $f$, we can reconstruct a candidate $\alpha$. In $f$, the flow passing through $\mathbf{p^+}$ and $\mathbf{p^-}$ is $\rho_\mathbf{N}$, and since the outgoing capacity of every $\mathbf{x}_{p,z}$ is 1, every partition is associated to $\rho_\mathbf{N}$ distinct nodes. The fraction $\rho_\mathbf{Z}$ of the flow passing through every $\mathbf{p^+}$ must be spread over as many distinct zones as every arc outgoing from $\mathbf{p^+}$ has capacity 1. So the reconstructed $\alpha$ verifies the redundancy constraints. For every node $n$, the flow between $\mathbf{n}$ and $\mathbf{t}$ corresponds to the number of partitions associated to $n$. By construction of $f$, this does not exceed $\lfloor c_n/s \rfloor$. We assumed that the partition size is $s$, hence this association does not exceed the storage capacity of the nodes.
+	
+	In the other direction, given an assignment $\alpha$, one can similarly check that the facts that $\alpha$ respects the redundancy constraints, and the storage capacities of the nodes, are necessary condition to construct a maximal flow function $f$.
+\end{proof}
+
+\textbf{Implementation remark:} In the flow algorithm, while exploring the graph, we explore the neighbours of every vertex in a random order to heuristically spread the association between nodes and partitions.
+
+\subsubsection*{Algorithm}
+With this result mind, we can describe the first step of our algorithm. All divisions are supposed to be integer division.
+\begin{algorithmic}[1]
+	\Function{Compute Partition Size}{$\mathbf{N}$, $\mathbf{Z}$, $\mathbf{P}$, $(c_n)_{n\in \mathbf{N}}$, $\rho_\mathbf{N}$, $\rho_\mathbf{Z}$}
+	
+	\State Build the graph $G=G(s=1)$
+	\State $ f \leftarrow$ \Call{Maximal flow}{$G$}
+	\If{$f.\mathrm{total flow} < \rho_\mathbf{N}P$}
+	
+	\State \Return Error: capacities too small or constraints too strong.
+	\EndIf
+	
+	\State $s^- \leftarrow 1$
+	\State $s^+ \leftarrow 1+\frac{1}{\rho_\mathbf{N}}\sum_{n \in \mathbf{N}} c_n$
+	
+	\While{$s^-+1 < s^+$}
+	\State Build the graph $G=G(s=(s^-+s^+)/2)$
+	\State $ f \leftarrow$ \Call{Maximal flow}{$G$}
+	\If{$f.\mathrm{total flow} < \rho_\mathbf{N}P$}
+	\State $s^+ \leftarrow (s^- + s^+)/2$
+	\Else
+	\State $s^- \leftarrow (s^- + s^+)/2$
+	\EndIf
+	\EndWhile
+	
+	\State \Return $s^-$
+	\EndFunction
+\end{algorithmic}
+
+\subsubsection*{Complexity}
+
+To compute the maximal flow, we use Dinic's algorithm. Its complexity on general graphs is $O(\#V^2 \#E)$, but on graphs with edge capacity bounded by a constant, it turns out to be $O(\#E^{3/2})$. The graph $G$ does not fall in this case since the capacities of the arcs incoming to $\mathbf{t}$ are far from bounded. However, the proof of this complexity works readily for graph where we only ask the edges \emph{not} incoming to the sink $\mathbf{t}$ to have their capacities bounded by a constant. One can find the proof of this claim in \cite[Section 2]{even1975network}.
+The dichotomy adds a logarithmic factor $\log (C)$ where $C=\sum_{n \in \mathbf{N}} c_n$ is the total capacity of the cluster. The total complexity of this first function is hence 
+$O(\#E^{3/2}\log C ) = O\big((PN)^{3/2} \log C\big)$.
+
+\subsubsection*{Metrics}
+We can display the discrepancy between the computed $s^*$ and the best size we could hope for a given total capacity, that is $C/\rho_\mathbf{N}$.
+
+\subsection{Computation of a candidate assignment}
+
+Now that we have the optimal partition size $s^*$, to compute a candidate assignment, it would be enough to compute a maximal flow function $f$ on $G(s^*)$. This is what we do if there was no previous assignment $\alpha'$.
+
+If there was some $\alpha'$, we add a step that will heuristically help to obtain a candidate $\alpha$ closer to $\alpha'$. to do so, we fist compute a flow function $\tilde{f}$ that uses only the partition-to-node association appearing in $\alpha'$. Most likely, $\tilde{f}$ will not be a maximal flow of $G(s^*)$. In Dinic's algorithm, we can start from a non maximal flow function and then discover improving paths. This is what we do in starting from $\tilde{f}$. The hope\footnote{This is only a hope, because one can find examples where the construction of $f$ from $\tilde{f}$ produces an assignment $\alpha$ that is not as close as possible to $\alpha'$.} is that the final flow function $f$ will tend to keep the associations appearing in $\tilde{f}$.
+
+More formally, we construct the graph $G_{|\alpha'}$ from $G$ by removing all the arcs $(\mathbf{x}_{p,z},\mathbf{n}, 1)$ where $p$ is not associated to $n$ in $\alpha'$. We compute a maximal flow function $\tilde{f}$ in $G_{|\alpha'}$. $\tilde{f}$ is also a valid (most likely non maximal) flow function in $G$. We compute a maximal flow function $f$ on $G$ by starting Dinic's algorithm on $\tilde{f}$.
+
+\subsubsection*{Algorithm}
+\begin{algorithmic}[1]
+	\Function{Compute Candidate Assignment}{$G$, $\alpha'$}
+	\State Build the graph $G_{|\alpha'}$
+	\State $ \tilde{f} \leftarrow$ \Call{Maximal flow}{$G_{|\alpha'}$}
+	\State $ f \leftarrow$ \Call{Maximal flow from flow}{$G$, $\tilde{f}$}
+	\State \Return $f$
+	\EndFunction
+\end{algorithmic}
+
+\textbf{Remark:} The function ``Maximal flow'' can be just seen as the function ``Maximal flow from flow'' called with the zero flow function as starting flow.
+
+\subsubsection*{Complexity}
+From the consideration of the last section, we have the complexity of the Dinic's algorithm $O(\#E^{3/2}) = O((PN)^{3/2})$.
+
+\subsubsection*{Metrics}
+
+We can display the flow value of $\tilde{f}$, which is an upper bound of the distance between $\alpha$ and $\alpha'$. It might be more a Debug level display than Info.
+
+\subsection{Minimization of the transfer load}
+
+Now that we have a candidate flow function $f$, we want to modify it to make its associated assignment as close as possible to $\alpha'$. Denote by $f'$ the maximal flow associated to $\alpha'$, and let $d(f, f')$ be distance between the associated assignments\footnote{It is the number of arcs of type $(\mathbf{x}_{p,z},\mathbf{n})$ saturated in one flow and not in the other.}. 
+We want to build a sequence $f=f_0, f_1, f_2 \dots$ of maximal flows such that $d(f_i, \alpha')$ decreases as $i$ increases. The distance being a non-negative integer, this sequence of flow functions must be finite. We now explain how to find some improving $f_{i+1}$ from $f_i$.
+
+For any maximal flow $f$ in $G$, we define the oriented weighted graph $G_f=(V, E_f)$ as follows. The vertices of $G_f$ are the same as the vertices of $G$. $E_f$ contains the arc $(v_1,v_2, w)$ between vertices $v_1,v_2\in V$ with weight $w$ if and only if the arc $(v_1,v_2)$ is not saturated in $f$ (i.e. $c(v_1,v_2)-f(v_1,v_2) \ge 1$, we also consider reversed arcs). The weight $w$ is: 
+\begin{itemize}
+	\item  $-1$  if $(v_1,v_2)$ is of type $(\mathbf{x}_{p,z},\mathbf{n})$ or $(\mathbf{x}_{p,z},\mathbf{n})$ and is saturated in only one of the two flows $f,f'$;
+	\item $+1$  if $(v_1,v_2)$ is of type $(\mathbf{x}_{p,z},\mathbf{n})$ or $(\mathbf{x}_{p,z},\mathbf{n})$ and is saturated in either both or none of the two flows $f,f'$;
+	\item $0$ otherwise.
+\end{itemize}
+
+If $\gamma$ is a simple cycle of arcs in $G_f$, we define its weight $w(\gamma)$ as the sum of the weights of its arcs. We can add $+1$ to the value of $f$ on the arcs of $\gamma$, and by construction of $G_f$ and the fact that $\gamma$ is a cycle, the function that we get is still a valid flow function on $G$, it is maximal as it has the same flow value as $f$. We denote this new function $f+\gamma$.
+
+\begin{proposition}
+	Given a maximal flow $f$ and a simple cycle $\gamma$ in $G_f$, we have $d(f+\gamma, f') - d(f,f') = w(\gamma)$.
+\end{proposition}
+\begin{proof}
+	Let $X$ be the set of arcs of type $(\mathbf{x}_{p,z},\mathbf{n})$. Then we can express $d(f,f')$ as
+	\begin{align*}
+		d(f,f') & = \#\{e\in X ~|~ f(e)\neq f'(e)\}
+		= \sum_{e\in X} 1_{f(e)\neq f'(e)} \\
+		& = \frac{1}{2}\big( \#X + \sum_{e\in X} 1_{f(e)\neq f'(e)} - 1_{f(e)= f'(e)} \big).
+	\end{align*}
+	We can express the cycle weight as
+	\begin{align*}
+		w(\gamma) &  = \sum_{e\in X, e\in \gamma} - 1_{f(e)\neq f'(e)} + 1_{f(e)= f'(e)}.
+	\end{align*}
+	Remark that since we passed on unit of flow in $\gamma$ to construct $f+\gamma$, we have for any $e\in X$, $f(e)=f'(e)$ if and only if $(f+\gamma)(e) \neq f'(e)$.
+	Hence
+	\begin{align*}
+		w(\gamma) &  = \frac{1}{2}(w(\gamma) + w(\gamma)) \\
+		&= \frac{1}{2} \Big( 
+		\sum_{e\in X, e\in \gamma} - 1_{f(e)\neq f'(e)} +  1_{f(e)= f'(e)} \\
+		& \qquad +
+		\sum_{e\in X, e\in \gamma} 1_{(f+\gamma)(e)\neq f'(e)} +  1_{(f+\gamma)(e)= f'(e)}
+		\Big).
+	\end{align*}
+	Plugging this in the previous equation, we find that 
+	$$d(f,f')+w(\gamma) = d(f+\gamma, f').$$
+\end{proof}
+
+This result suggests that given some flow $f_i$, we just need to find a negative cycle $\gamma$ in $G_{f_i}$ to construct $f_{i+1}$ as $f_i+\gamma$. The following proposition ensures that this greedy strategy reaches an optimal flow. 
+
+\begin{proposition}
+	For any maximal flow $f$, $G_f$ contains a negative cycle if and only if there exists a maximal flow $f^*$ in $G$ such that $d(f^*, f') < d(f, f')$.
+\end{proposition}
+\begin{proof}
+	Suppose that there is such flow $f^*$. Define the oriented multigraph $M_{f,f^*}=(V,E_M)$ with the same vertex set $V$ as in $G$, and for every $v_1,v_2 \in V$, $E_M$ contains $(f^*(v_1,v_2) - f(v_1,v_2))_+$  copies of the arc $(v_1,v_2)$. For every vertex $v$, its total degree (meaning its outer degree minus its inner degree) is equal to 
+	\begin{align*}
+		\deg v & = \sum_{u\in V} (f^*(v,u) - f(v,u))_+ - \sum_{u\in V} (f^*(u,v) - f(u,v))_+  \\
+		& = \sum_{u\in V} f^*(v,u) - f(v,u) = \sum_{u\in V} f^*(v,u) - \sum_{u\in V}  f(v,u).
+	\end{align*}
+	The last two sums are zero for any inner vertex since $f,f^*$ are flows, and they are equal on the source and sink since the two flows are both maximal and have hence the same value. Thus, $\deg v = 0$ for every vertex $v$.
+	
+	This implies that the multigraph $M_{f,f^*}$ is the union of disjoint simple cycles. $f$ can be transformed into $f^*$ by pushing a mass 1 along all these cycles in any order. Since $d(f^*, f')<d(f,f')$, there must exists one of these simple cycles $\gamma$ with $d(f+\gamma, f') < d(f, f')$. Finally, since we can push a mass in $f$ along $\gamma$, it must appear in $G_f$. Hence $\gamma$ is a cycle of $G_f$ with negative weight.
+\end{proof}
+
+In the next section we describe the corresponding algorithm. Instead of discovering only one cycle, we are allowed to discover a set $\Gamma$ of disjoint negative cycles. 
+
+\subsubsection*{Algorithm}
+\begin{algorithmic}[1]
+	\Function{Minimize transfer load}{$G$, $f$, $\alpha'$}
+	\State Build the graph $G_f$
+	\State $\Gamma \leftarrow$ \Call{Detect Negative Cycles}{$G_f$}
+	\While{$\Gamma \neq \emptyset$}
+	\ForAll{$\gamma \in \Gamma$}
+	\State $f \leftarrow f+\gamma$
+	\EndFor
+	\State Update $G_f$
+	\State $\Gamma \leftarrow$ \Call{Detect Negative Cycles}{$G_f$}
+	\EndWhile
+	\State \Return $f$
+	\EndFunction
+\end{algorithmic}
+
+\subsubsection*{Complexity}
+The distance $d(f,f')$ is bounded by the maximal number of differences in the associated assignment. If these assignment are totally disjoint, this distance is $2\rho_N P$. At every iteration of the While loop, the distance decreases, so there is at most $O(\rho_N P) = O(P)$ iterations.
+
+The detection of negative cycle is done with the Bellman-Ford algorithm, whose complexity should normally be $O(\#E\#V)$. In our case, it amounts to $O(P^2ZN)$. Multiplied by the complexity of the outer loop, it amounts to $O(P^3ZN)$ which is a lot when the number of partitions and nodes starts to be large. To avoid that, we adapt the Bellman-Ford algorithm.
+
+The Bellman-Ford algorithm runs $\#V$ iterations of an outer loop, and an inner loop over $E$. The idea is to compute the shortest paths from a source vertex $v$ to all other vertices. After $k$ iterations of the outer loop, the algorithm has computed all shortest path of length at most $k$. All simple paths have length at most $\#V-1$, so if there is an update in the last iteration of the loop, it means that there is a negative cycle in the graph. The observation that will enable us to improve the complexity is the following:
+
+\begin{proposition}
+	In the graph $G_f$ (and $G$), all simple paths have a length at most $4N$.
+\end{proposition}
+\begin{proof}
+	Since $f$ is a maximal flow, there is no outgoing edge from $\mathbf{s}$ in $G_f$. One can thus check than any simple path of length 4 must contain at least two node of type $\mathbf{n}$. Hence on a path, at most 4 arcs separate two successive nodes of type $\mathbf{n}$. 
+\end{proof}
+
+Thus, in the absence of negative cycles, shortest paths in $G_f$ have length at most $4N$. So we can do only $4N+1$ iterations of the outer loop in Bellman-Ford algorithm. This makes the complexity of the detection of one set of cycle to be $O(N\#E) = O(N^2 P)$.
+
+With this improvement, the complexity of the whole algorithm is, in the worst case, $O(N^2P^2)$. However, since we detect several cycles at once and we start with a flow that might be close to the previous one, the number of iterations of the outer loop might be smaller in practice.
+
+
+
+\subsubsection*{Metrics}
+We can display the node and zone utilization ratio, by dividing the flow passing through them divided by their outgoing capacity. In particular, we can pinpoint saturated nodes and zones (i.e. used at their full potential).
+
+We can display the distance to the previous assignment, and the number of partition transfers.
+
+
+
+
+
+\section{Properties of an optimal 3-strict assignment}
+
+\subsection{Optimal assignment}
+\label{sec:opt_assign}
+
+For every zone $z\in Z$, define the zone capacity $c_z = \sum_{v, z_v=z} c_v$ and define $C = \sum_v c_v = \sum_z c_z$.
+
+One can check that the best we could be doing to maximize $s^*$ would be to use the nodes proportionally to their capacity. This would yield $s^*=C/(3N)$. This is not possible because of (i) redundancy constraints and (ii) integer rounding but it gives and upper bound. 
+
+\subsubsection*{Optimal utilization}
+
+We call an \emph{utilization} a collection of non-negative integers $(n_v)_{v\in V}$ such that $\sum_v n_v = 3N$ and for every zone $z$, $\sum_{v\in z} n_v \le N$. We call such utilization \emph{optimal} if it maximizes $s^*$.
+
+We start by computing a node sub-utilization $(\hat{n}_v)_{v\in V}$ such that for every zone $z$, $\sum_{v\in z} \hat{n}_v \le N$ and we show that there is an optimal utilization respecting the constraints and such that $\hat{n}_v \le n_v$ for every node.
+
+Assume that there is a zone $z_0$ such that $c_{z_0}/C \ge 1/3$. Then for any $v\in z_0$, we define 
+$$\hat{n}_v = \left\lfloor\frac{c_v}{c_{z_0}}N\right\rfloor.$$ 
+This choice ensures for any such $v$ that
+$$
+\frac{c_v}{\hat{n}_v} \ge \frac{c_{z_0}}{N} \ge \frac{C}{3N}
+$$
+which is the universal upper bound on $s^*$. Hence any optimal utilization $(n_v)$ can be modified to another optimal utilization such that $n_v\ge \hat{n}_v$
+
+Because $z_0$ cannot store more than $N$ partition occurences, in any assignment, at least $2N$ partitions must be assignated to the zones $Z\setminus\{z_0\}$. Let $C_0 = C-c_{z_0}$. Suppose that there exists a zone $z_1\neq z_0$ such that $c_{z_1}/C_0 \ge 1/2$. Then, with the same argument as for $z_0$, we can define 
+$$\hat{n}_v = \left\lfloor\frac{c_v}{c_{z_1}}N\right\rfloor$$
+for every $v\in z_1$.
+
+Now we can assign the remaining partitions. Let $(\hat{N}, \hat{C})$ to be
+\begin{itemize}
+	\item $(3N,C)$ if we did not find any $z_0$;
+	\item $(2N,C-c_{z_0})$ if there was a $z_0$ but no $z_1$;
+	\item $(N,C-c_{z_0}-c_{z_1})$ if there was a $z_0$ and a $z_1$.
+\end{itemize}
+Then at least $\hat{N}$ partitions must be spread among the remaining zones. Hence $s^*$ is upper bounded by $\hat{C}/\hat{N}$ and without loss of generality, we can define, for every node that is not in $z_0$ nor $z_1$, 
+$$\hat{n}_v = \left\lfloor\frac{c_v}{\hat{C}}\hat{N}\right\rfloor.$$ 
+
+We constructed a sub-utilization $\hat{n}_v$. Now notice that $3N-\sum_v \hat{n}_v \le \# V$ where $\# V$ denotes the number of nodes. We can iteratively pick a node $v^*$ such that 
+\begin{itemize}
+	\item $\sum_{v\in z_{v^*}} \hat{n}_v < N$ where $z_{v^*}$ is the zone of $v^*$;
+	\item $v^*$ maximizes the quantity $c_v/(\hat{n}_v+1)$ among the vertices satisfying the first condition (i.e. not in a saturated zone).
+\end{itemize}
+We iterate these instructions until $\sum_v \hat{n}_v= 3N$, and at this stage we define $(n_v) = (\hat{n}_v)$. It is easy to prove by induction that at every step, there is an optimal utilization that is pointwise larger than $\hat{n}_v$, and in particular, that $(n_v)$ is optimal.
+
+\subsubsection*{Existence of an optimal assignment}
+
+As for now, the \emph{optimal utilization} that we obtained is just a vector of numbers and it is not clear that it can be realized as the utilization of some concrete assignment. Here is a way to get a concrete assignment.
+
+Define $3N$ tokens $t_1,\ldots, t_{3N}\in V$ as follows:
+\begin{itemize}
+	\item Enumerate the zones $z$ of $Z$ in any order;
+	\item enumerate the nodes $v$ of $z$ in any order;
+	\item repeat $n_v$ times the token $v$.
+\end{itemize} 
+Then for $1\le i \le N$, define the triplet $T_i$ to be 
+$(t_i, t_{i+N}, t_{i+2N})$. Since the same nodes of a zone appear contiguously, the three nodes of a triplet must belong to three distinct zones.
+
+However simple, this solution to go from an utilization to an assignment has the drawback of not spreading the triplets: a node will tend to be associated to the same two other nodes for many partitions. Hence, during data transfer, it will tend to use only two link, instead of spreading the bandwith use over many other links to other nodes. To achieve this goal, we will reframe the search of an assignment as a flow problem. and in the flow algorithm, we will introduce randomness in the order of exploration. This will be sufficient to obtain a good dispersion of the triplets.
+
+\begin{figure}
+	\centering
+	\includegraphics[width=0.9\linewidth]{figures/naive}
+	\caption{On the left, the creation of a concrete assignment with the naive approach of repeating tokens. On the right, the zones containing the nodes.}
+\end{figure}
+
+\subsubsection*{Assignment as a maximum flow problem}
+
+We describe the flow problem via its graph $(X,E)$ where $X$ is a set of vertices, and $E$ are directed weighted edges between the vertices. For every zone $z$, define $n_z=\sum_{v\in z} n_v$.
+
+The set of vertices $X$ contains the source $\mathbf{s}$ and the sink $\mathbf{t}$; a vertex $\mathbf{x}_z$ for every zone $z\in Z$, and a vertex $\mathbf{y}_i$ for every partition index $1\le i\le N$. 
+
+The set of edges $E$ contains
+\begin{itemize}
+	\item the edge $(\mathbf{s}, \mathbf{x}_z, n_z)$ for every zone $z\in Z$;
+	\item the edge $(\mathbf{x}_z, \mathbf{y}_i, 1)$ for every zone $z\in Z$ and partition $1\le i\le N$;
+	\item the edge $(\mathbf{y}_i, \mathbf{t}, 3)$ for every partition $1\le i\le N$.
+\end{itemize}
+
+\begin{figure}[b]
+	\centering
+	\includegraphics[width=0.6\linewidth]{figures/flow}
+	\caption{Flow problem to compute and optimal assignment.}
+\end{figure}
+
+We first show the equivalence between this problem and and the construction of an assignment. Given some optimal assignment $(n_v)$, define the flow $f:E\to \mathbb{N}$ that saturates every edge from $\mathbf{s}$ or to $\mathbf{t}$, takes value $1$ on the edge between $\mathbf{x}_z$ and $\mathbf{y}_i$ if partition $i$ is stored in some node of the zone $z$, and $0$ otherwise. One can easily check that $f$ thus defined is indeed a flow and is maximum.
+
+Reciprocally, by the existence of maximum flows constructed from optimal assignments, any maximum flow must saturate the edges linked to the source or the sink. It can only take value 0 or 1 on the other edge, and every partition vertex is associated to exactly three distinct zone vertices. Every zone is associated to exactly $n_z$ partitions.
+
+A maximum flow can be constructed using, for instance, Dinic's algorithm. This algorithm works by discovering augmenting path to iteratively increase the flow. During the exploration of the graph to find augmenting path, we can shuffle the order of enumeration of the neighbours to spread the associations between zones and partitions.
+
+Once we have such association, we can randomly distribute the $n_z$ edges picked for every zone $z$ to its nodes $v\in z$ such that every such $v$ gets $n_z$ edges. This defines an optimal assignment of partitions to nodes.
+
+
+\subsection{Minimal transfer}
+
+Assume that there was a previous assignment $(T'_i)_{1\le i\le N}$ corresponding to utilizations $(n'_v)_{v\in V}$. We would like the new computed assignment $(T_i)_{1\le i\le N}$ from some $(n_v)_{v\in V}$ to minimize the number of partitions that need to be transferred. We can imagine two different objectives corresponding to different hypotheses: 
+\begin{equation}
+	\tag{H3A}
+	\label{hyp:A}
+	\text{\emph{Transfers between different zones cost much more than inside a zone.}}
+\end{equation}
+\begin{equation}
+	\tag{H3B}
+	\label{hyp:B}
+	\text{\emph{Changing zone is not the largest cost when transferring a partition.}}
+\end{equation}
+
+In case $A$, our goal will be to minimize the number of changes of zone in the assignment of partitions to zone. More formally, we will maximize the quantity
+$$
+Q_Z := 
+\sum_{1\le i\le N} 
+\#\{z\in Z ~|~ z\cap T_i \neq \emptyset, z\cap T'_i \neq \emptyset \}
+.$$
+
+In case $B$, our goal will be to minimize the number of changes of nodes in the assignment of partitions to nodes. We will maximize the quantity
+$$
+Q_V :=
+\sum_{1\le i\le N} \#(T_i \cap T'_i).
+$$
+
+It is tempting to hope that there is a way to maximize both quantity, that having the least discrepancy in terms of nodes will lead to the least discrepancy in terms of zones. But this is actually wrong! We propose the following counter-example to convince the reader:
+
+We consider eight nodes $a, a', b, c, d, d', e, e'$ belonging to five different zones $\{a,a'\}, \{b\}, \{c\}, \{d,d'\}, \{e, e'\}$. We take three partitions ($N=3$), that are originally assigned with some utilization $(n'_v)_{v\in V}$ as follows:
+$$
+T'_1=(a,b,c) \qquad
+T'_2=(a',b,d) \qquad 
+T'_3=(b,c,e).
+$$
+This assignment, with updated utilizations $(n_v)_{v\in V}$ minimizes the number of zone changes:
+$$
+T_1=(d,b,c) \qquad
+T_2=(a,b,d) \qquad 
+T_3=(b,c,e').
+$$
+This one, with the same utilization, minimizes the number of node changes:
+$$
+T_1=(a,b,c) \qquad
+T_2=(e',b,d) \qquad 
+T_3=(b,c,d').
+$$
+One can check that in this case, it is impossible to minimize both the number of zone and node changes.
+
+Because of the redundancy constraint, we cannot use a greedy algorithm to just replace nodes in the triplets to try to get the new utilization rate: this could lead to blocking situation where there is still a hole to fill in a triplet but no available node satisfies the zone separation constraint. To circumvent this issue, we propose an algorithm based on finding cycles in a graph encoding of the assignment. As in section \ref{sec:opt_assign}, we can explore the neigbours in a random order in the graph algorithms, to spread the triplets distribution.
+
+
+\subsubsection{Minimizing the zone discrepancy}
+
+
+First, notice that, given an assignment of partitions to \emph{zones}, it is easy to deduce an assignment to \emph{nodes} that minimizes the number of transfers for this zone assignment: For every zone $z$ and every node $v\in z$, pick in any way a set $P_v$ of partitions that where assigned to $v$ in $T'$, to $z_v$ in $T$, with the cardinality of $P_v$ smaller than $n_v$. Once all these sets are chosen, complement the assignment to reach the right utilization for every node. If $\#P_v > n_v$, it means that all the partitions that could stay in $v$ (i.e. that were already in $v$ and are still assigned to its zone) do stay in $v$. If $\#P_v = n_v$, then $n_v$ partitions stay in $v$, which is the number of partitions that need to be in $v$ in the end. In both cases, we could not hope for better given the partition to zone assignment.
+
+Our goal now is to find a assignment of partitions to zones that minimizes the number of zone transfers. To do so we are going to represent an assignment as a graph.
+
+Let $G_T=(X,E_T)$ be the directed weighted graph with vertices $(\mathbf{x}_i)_{1\le i\le N}$ and $(\mathbf{y}_z)_{z\in Z}$. For any $1\le i\le N$ and $z\in Z$, $E_T$ contains  the arc:
+\begin{itemize}
+	\item $(\mathbf{x}_i, \mathbf{y}_z, +1)$, if $z$ appears in $T_i'$ and $T_i$;
+	\item $(\mathbf{x}_i, \mathbf{y}_z, -1)$, if $z$ appears in $T_i$ but not in $T'_i$;
+	\item $(\mathbf{y}_z, \mathbf{x}_i, -1)$, if $z$ appears in $T'_i$ but not in $T_i$;
+	\item $(\mathbf{y}_z, \mathbf{x}_i, +1)$, if $z$ does not appear in $T'_i$ nor in $T_i$.
+\end{itemize}
+In other words, the orientation of the arc encodes whether partition $i$ is stored in zone $z$ in the assignment $T$ and the weight $\pm 1$ encodes whether this corresponds to what happens in the assignment $T'$.
+
+\begin{figure}[t]
+	\centering
+	\begin{minipage}{.40\linewidth}
+		\centering
+		\includegraphics[width=.8\linewidth]{figures/mini_zone}
+	\end{minipage}
+	\begin{minipage}{.55\linewidth}
+		\centering
+		\includegraphics[width=.8\linewidth]{figures/mini_node}
+	\end{minipage}
+	\caption{On the left: the graph $G_T$ encoding an assignment to minimize the zone discrepancy. On the right: the graph $G_T$ encoding an assignment to minimize the node discrepancy.}
+\end{figure}
+
+
+Notice that at every partition, there are three outgoing arcs, and at every zone, there are $n_z$ incoming arcs. Moreover, if $w(e)$ is the weight of an arc $e$, define the weight of $G_T$ by
+\begin{align*}
+w(G_T) := \sum_{e\in E} w(e) &= \#Z \times N - 4 \sum_{1\le i\le N} \#\{z\in Z ~|~ z\cap T_i = \emptyset, z\cap T'_i \neq \emptyset\}	\\
+&=\#Z \times N - 4 \sum_{1\le i\le N} 3- \#\{z\in Z ~|~ z\cap T_i \neq \emptyset, z\cap T'_i \neq \emptyset\} \\
+&= (\#Z-12)N + 4 Q_Z.
+\end{align*}
+Hence maximizing $Q_Z$ is equivalent to maximizing $w(G_T)$.
+
+Assume that their exist some assignment $T^*$ with the same utilization $(n_v)_{v\in V}$. Define $G_{T^*}$ similarly and consider the set $E_\mathrm{Diff} = E_T \setminus E_{T^*}$ of arcs that appear only in $G_T$. Since all vertices have the same number of incoming arcs in $G_T$ and $G_{T^*}$, the vertices of the graph $(X, E_\mathrm{Diff})$ must all have the same number number of incoming and outgoing arrows. So $E_\mathrm{Diff}$ can be expressed as a union of disjoint cycles. Moreover, the edges of $E_\mathrm{Diff}$ must appear in $E_{T^*}$ with reversed orientation and opposite weight. Hence, we have
+$$
+ w(G_T) - w(G_{T^*}) = 2 \sum_{e\in E_\mathrm{Diff}} w(e). 
+$$
+Hence, if $T$ is not optimal, there exists some $T^*$ with $w(G_T) < w(G_{T^*})$, and by the considerations above, there must exist a cycle in $E_\mathrm{Diff}$, and hence in $G_T$, with negative weight. If we reverse the edges and weights along this cycle, we obtain some graph. Since we did not change the incoming degree of any vertex, this is the graph encoding of some valid assignment $T^+$ such that $w(G_{T^+}) > w(G_T)$. We can iterate this operation until there is no other assignment $T^*$ with larger weight, that is until we obtain an optimal assignment.
+
+
+
+\subsubsection{Minimizing the node discrepancy}
+
+We will follow an approach similar to the one where we minimize the zone discrepancy. Here we will directly obtain a node assignment from a graph encoding.
+
+Let $G_T=(X,E_T)$ be the directed weighted graph with vertices $(\mathbf{x}_i)_{1\le i\le N}$, $(\mathbf{y}_{z,i})_{z\in Z, 1\le i\le N}$ and $(\mathbf{u}_v)_{v\in V}$. For any $1\le i\le N$ and $z\in Z$, $E_T$ contains  the arc:
+\begin{itemize}
+	\item $(\mathbf{x}_i, \mathbf{y}_{z,i}, 0)$, if $z$ appears in $T_i$;
+	\item $(\mathbf{y}_{z,i}, \mathbf{x}_i, 0)$, if $z$ does not appear in $T_i$.
+\end{itemize}
+For any $1\le i\le N$ and $v\in V$, $E_T$ contains  the arc:
+\begin{itemize}
+	\item $(\mathbf{y}_{z_v,i}, \mathbf{u}_v, +1)$, if $v$ appears in $T_i'$ and $T_i$;
+	\item $(\mathbf{y}_{z_v,i}, \mathbf{u}_v, -1)$, if $v$ appears in $T_i$ but not in $T'_i$;
+	\item $(\mathbf{u}_v, \mathbf{y}_{z_v,i}, -1)$, if $v$ appears in $T'_i$ but not in $T_i$;
+	\item $(\mathbf{u}_v, \mathbf{y}_{z_v,i}, +1)$, if $v$ does not appear in $T'_i$ nor in $T_i$.
+\end{itemize}
+Every vertex $\mathbb{x}_i$ has outgoing degree 3, every vertex $\mathbf{y}_{z,v}$ has outgoing degree 1, and every vertex $\mathbf{u}_v$ has incoming degree $n_v$. 
+Remark that any graph respecting these degree constraints is the encoding of a valid assignment with utilizations $(n_v)_{v\in V}$, in particular no partition is stored in two nodes of the same zone.
+
+We define $w(G_T)$ similarly:
+\begin{align*}
+	w(G_T) := \sum_{e\in E_T} w(e) &= \#V \times N - 4\sum_{1\le i\le N} 3-\#(T_i\cap T'_i) \\
+	&= (\#V-12)N + 4Q_V.
+\end{align*}
+
+Exactly like in the previous section, the existence of an assignment with larger weight implies the existence of a negatively weighted cycle in $G_T$. Reversing this cycle gives us the encoding of a valid assignment with a larger weight. Iterating this operation yields an optimal assignment.
+
+
+\subsubsection{Linear combination of both criteria}
+
+In the graph $G_T$ defined in the previous section, instead of having weights $0$ and $\pm 1$, we could be having weights $\pm\alpha$ between $\mathbf{x}$ and  $\mathbf{y}$ vertices, and weights $\pm\beta$ between $\mathbf{y}$ and  $\mathbf{u}$ vertices, for some $\alpha,\beta>0$ (we have positive weight if the assignment corresponds to $T'$ and negative otherwise). Then
+\begin{align*}
+	w(G_T) &= \sum_{e\in E_T} w(e) = 
+	\alpha \big( (\#Z-12)N + 4 Q_Z\big) + 
+	\beta \big( (\#V-12)N + 4 Q_V\big) \\
+	&= \mathrm{const}+ 4(\alpha Q_Z + \beta Q_V).
+\end{align*}
+So maximizing the weight of such graph encoding would be equivalent to maximizing a linear combination of $Q_Z$ and $Q_V$.
+
+
+\subsection{Algorithm}
+We give a high level description of the algorithm to compute an optimal 3-strict assignment. The operations appearing at lines 1,2,4 are respectively described by Algorithms \ref{alg:util},\ref{alg:opt} and \ref{alg:mini}.
+
+
+
+\begin{algorithm}[H]
+	\caption{Optimal 3-strict assignment}
+	\label{alg:total}
+	\begin{algorithmic}[1]
+	\Function{Optimal 3-strict assignment}{$N$, $(c_v)_{v\in V}$, $T'$}
+		\State $(n_v)_{v\in V} \leftarrow$ \Call{Compute optimal utilization}{$N$, $(c_v)_{v\in V}$}
+		\State $(T_i)_{1\le i\le N} \leftarrow$ \Call{Compute candidate assignment}{$N$, $(n_v)_{v\in V}$}
+		\If {there was a previous assignment $T'$}
+			\State $T \leftarrow$ \Call{Minimization of transfers}{$(T_i)_{1\le i\le N}$, $(T'_i)_{1\le i\le N}$}
+		\EndIf
+		\State \Return $T$.
+	\EndFunction
+	\end{algorithmic}
+\end{algorithm}
+
+We give some considerations of worst case complexity for these algorithms. In the following, we assume $N>\#V>\#Z$. The complexity of Algorithm \ref{alg:total} is $O(N^3\# Z)$ if we assume \eqref{hyp:A} and $O(N^3 \#Z \#V)$ if we assume \eqref{hyp:B}.
+
+Algorithm \ref{alg:util} can be implemented with complexity $O(\#V^2)$. The complexity of the function call at line \ref{lin:subutil} is $O(\#V)$. The difference between the sum of the subutilizations and $3N$ is at most the sum of the rounding errors when computing the $\hat{n}_v$. Hence it is bounded by $\#V$ and the loop at line \ref{lin:loopsub} is iterated at most $\#V$ times. Finding the minimizing $v$ at line \ref{lin:findmin} takes $O(\#V)$ operations (naively, we could also use a heap).
+
+Algorithm \ref{alg:opt} can be implemented with complexity $O(N^3\times \#Z)$. The flow graph has $O(N+\#Z)$ vertices and $O(N\times \#Z)$ edges. Dinic's algorithm has complexity $O(\#\mathrm{Vertices}^2\#\mathrm{Edges})$ hence in our case it is $O(N^3\times \#Z)$.
+ 
+Algorithm \ref{alg:mini} can be implented with complexity $O(N^3\# Z)$ under \eqref{hyp:A} and $O(N^3 \#Z \#V)$ under \eqref{hyp:B}.
+The graph $G_T$ has $O(N)$ vertices and $O(N\times \#Z)$ edges under assumption \eqref{hyp:A} and respectively $O(N\times \#Z)$ vertices and $O(N\times \#V)$ edges under assumption \eqref{hyp:B}. The loop at line \ref{lin:repeat} is iterated at most $N$ times since the distance between $T$ and $T'$ decreases at every iteration. Bellman-Ford algorithm has complexity $O(\#\mathrm{Vertices}\#\mathrm{Edges})$, which in our case amounts to $O(N^2\# Z)$ under \eqref{hyp:A} and $O(N^2 \#Z \#V)$ under \eqref{hyp:B}.
+ 
+\begin{algorithm}
+	\caption{Computation of the optimal utilization}
+	\label{alg:util}
+	\begin{algorithmic}[1]
+\Function{Compute optimal utilization}{$N$, $(c_v)_{v\in V}$}
+	\State $(\hat{n}_v)_{v\in V} \leftarrow $ \Call{Compute subutilization}{$N$, $(c_v)_{v\in V}$} \label{lin:subutil}
+	\While{$\sum_{v\in V} \hat{n}_v < 3N$} \label{lin:loopsub}
+	\State Pick $v\in V$ minimizing $\frac{c_v}{\hat{n}_v+1}$ and such that
+		$\sum_{v'\in z_v} \hat{n}_{v'} < N$ \label{lin:findmin}
+		\State $\hat{n}_v \leftarrow \hat{n}_v+1$
+	\EndWhile
+	\State \Return $(\hat{n}_v)_{v\in V}$
+\EndFunction
+\State
+
+\Function{Compute subutilization}{$N$, $(c_v)_{v\in V}$}
+		\State $R \leftarrow 3$
+\For{$v\in V$}
+\State $\hat{n}_v \leftarrow \mathrm{unset}$
+\EndFor
+\For{$z\in Z$}
+\State $c_z \leftarrow \sum_{v\in z} c_v$
+\EndFor
+\State $C \leftarrow \sum_{z\in Z} c_z$
+\While{$\exists z \in Z$ such that $R\times c_{z} > C$}
+\For{$v\in z$}
+\State $\hat{n}_v \leftarrow \left\lfloor \frac{c_v}{c_z} N \right\rfloor$
+\EndFor
+\State $C \leftarrow C-c_z$
+\State $R\leftarrow R-1$
+\EndWhile
+\For{$v\in V$}
+\If{$\hat{n}_v = \mathrm{unset}$}
+\State $\hat{n}_v \leftarrow \left\lfloor \frac{Rc_v}{C} N \right\rfloor$
+\EndIf
+\EndFor
+\State \Return $(\hat{n}_v)_{v\in V}$
+\EndFunction
+	\end{algorithmic}
+\end{algorithm}
+
+\begin{algorithm}
+	\caption{Computation of a candidate assignment}
+	\label{alg:opt}
+	\begin{algorithmic}[1]
+		\Function{Compute candidate assignment}{$N$, $(n_v)_{v\in V}$}
+		\State Compute the flow graph $G$
+		\State Compute the maximal flow $f$ using Dinic's algorithm with randomized neighbours enumeration
+		\State Construct the assignment $(T_i)_{1\le i\le N}$ from $f$
+		\State \Return $(T_i)_{1\le i\le N}$
+		\EndFunction
+	\end{algorithmic}
+\end{algorithm}
+
+
+\begin{algorithm}
+	\caption{Minimization of the number of transfers}
+	\label{alg:mini}
+	\begin{algorithmic}[1]
+		\Function{Minimization of transfers}{$(T_i)_{1\le i\le N}$, $(T'_i)_{1\le i\le N}$}
+		\State Construct the graph encoding $G_T$
+		\Repeat \label{lin:repeat}
+		\State Find a negative cycle $\gamma$ using Bellman-Ford algorithm on $G_T$
+		\State Reverse the orientations and weights of edges in $\gamma$
+		\Until{no negative cycle is found}
+		\State Update $(T_i)_{1\le i\le N}$ from $G_T$
+		\State \Return $(T_i)_{1\le i\le N}$
+		\EndFunction
+	\end{algorithmic}
+\end{algorithm}
+
+\newpage
+
+\section{Computation of a 3-non-strict assignment}
+
+\subsection{Choices of optimality}
+
+In this mode, we primarily want to store every partition on three nodes, and only secondarily try to spread the nodes among different zone. So we make the choice of not taking the zone repartition in the criterion of optimality.
+
+We try to maximize $s^*$ defined in \eqref{eq:optimal}. So we can compute the optimal utilizations $(n_v)_{v\in V}$ with the only constraint that $n_v \le N$ for every node $v$. As in the previous section, we start with a sub-utilization proportional to $c_v$ (and capped at $N$), and we iteratively increase the $\hat{n}_v$ that is less than $N$ and maximizes the quantity $c_v/(\hat{n}_v+1)$, until the total sum is $3N$.
+
+\subsection{Computation of a candidate assignment}
+
+To compute a candidate assignment (that does not optimize zone spreading nor distance to a previous assignment yet), we can use the folowing flow problem.
+
+Define the oriented weighted graph $(X,E)$. The set of vertices $X$ contains the source $\mathbf{s}$, the sink $\mathbf{t}$, vertices 
+$\mathbf{x}_p, \mathbf{u}^+_p, \mathbf{u}^-_p$ for every partition $p$, vertices $\mathbf{y}_{p,z}$ for every partition $p$ and zone $z$, and vertices $\mathbf{z}_v$ for every node $v$. 
+
+The set of edges is composed of the following arcs:
+\begin{itemize}
+	\item ($\mathbf{s}$,$\mathbf{x}_p$, 3) for every partition $p$;
+	\item ($\mathbf{x}_p$,$\mathbf{u}^+_p$, 3) for every partition $p$;
+	\item ($\mathbf{x}_p$,$\mathbf{u}^-_p$, 2) for every partition $p$;
+	\item ($\mathbf{u}^+_p$,$\mathbf{y}_{p,z}$, 1) for every partition $p$ and zone $z$;
+	\item ($\mathbf{u}^-_p$,$\mathbf{y}_{p,z}$, 2) for every partition $p$ and zone $z$;
+	\item ($\mathbf{y}_{p,z}$,$\mathbf{z}_v$, 1) for every partition $p$, zone $z$ and node $v\in z$;
+	\item ($\mathbf{z}_v$, $\mathbf{t}$, $n_v$) for every node $v$;
+\end{itemize}
+
+One can check that any maximal flow in this graph corresponds to an assignment of partitions to nodes. In such a flow, all the arcs from $\mathbf{s}$ and to $\mathbf{t}$ are saturated. The arc from $\mathbf{y}_{p,z}$ to $\mathbf{z}_v$ is saturated if and only if $p$ is associated to~$v$. 
+Finally the flow from $\mathbf{x}_p$ to $\mathbf{y}_{p,z}$ can go either through $\mathbf{u}^+_p$ or $\mathbf{u}^-_p$.
+
+
+
+\subsection{Maximal spread and minimal transfers}
+Notice that if the arc $\mathbf{u}_p^+\mathbf{y}_{p,z}$ is not saturated but there is some flow in $\mathbf{u}_p^-\mathbf{y}_{p,z}$, then it is possible to transfer a unit of flow from the path  $\mathbf{x}_p\mathbf{u}_p^-\mathbf{y}_{p,z}$ to the path $\mathbf{x}_p\mathbf{u}_p^+\mathbf{y}_{p,z}$. So we can always find an equivalent maximal flow $f^*$ that uses the path through $\mathbf{u}_p^-$ only if the path through $\mathbf{u}_p^+$ is saturated.
+
+We will use this fact to consider the amount of flow going through the vertices $\mathbf{u}^+$ as a measure of how well the partitions are spread over nodes belonging to different zones. If the partition $p$ is associated to 3 different zones, then a flow of 3 will cross $\mathbf{u}_p^+$ in $f^*$ (i.e. a flow of 0 will cross $\mathbf{u}_p^+$). If $p$ is associated to two zones, a flow of $2$ will cross $\mathbf{u}_p^+$. If $p$ is associated to a single zone, a flow of $1$ will cross $\mathbf{u}_p^+$.
+
+Let $N_1, N_2, N_3$ be the number of partitions associated to respectively 1,2 and 3 distinct zones. We will optimize a linear combination of these variables using the discovery of positively weighted circuits in a graph.
+
+At the same step, we will also optimize the distance to a previous assignment $T'$. Let $\alpha> \beta> \gamma \ge 0$ be three parameters.
+
+Given the flow $f$, let $G_f=(X',E_f)$ be the multi-graph where $X' = X\setminus\{\mathbf{s},\mathbf{t}\}$. The set $E_f$ is composed of the arcs:
+\begin{itemize}
+\item As many arcs from $(\mathbf{x}_p, \mathbf{u}^+_p,\alpha), (\mathbf{x}_p, \mathbf{u}^+_p,\beta), (\mathbf{x}_p, \mathbf{u}^+_p,\gamma)$ (selected in this order) as there is flow crossing $\mathbf{u}^+_p$ in $f$;
+\item As many arcs from $(\mathbf{u}^+_p, \mathbf{x}_p,-\gamma), (\mathbf{u}^+_p, \mathbf{x}_p,-\beta), (\mathbf{u}^+_p, \mathbf{x}_p,-\alpha)$ (selected in this order) as there is flow crossing $\mathbf{u}^-_p$ in $f$;
+\item  As many copies of $(\mathbf{x}_p, \mathbf{u}^-_p,0)$ as there is flow through $\mathbf{u}^-_p$;
+\item  As many copies of $(\mathbf{u}^-_p,\mathbf{x}_p,0)$ so that the number of arcs between these two vertices is 2;
+\item $(\mathbf{u}^+_p,\mathbf{y}_{p,z}, 0)$ if the flow between these vertices is 1, and the opposite arc otherwise;
+\item as many copies of $(\mathbf{u}^-_p,\mathbf{y}_{p,z}, 0)$ as the flow between these vertices, and as many copies of the opposite arc as 2~$-$~the flow;
+\item $(\mathbf{y}_{p,z},\mathbf{z}_v, \pm1)$ if it is saturated in $f$, with $+1$ if $v\in T'_p$ and $-1$ otherwise;
+\item $(\mathbf{z}_v,\mathbf{y}_{p,z}, \pm1)$ if it is not saturated in $f$, with $+1$ if $v\notin T'_p$ and $-1$ otherwise.
+\end{itemize}
+To summarize, arcs are oriented left to right if they correspond to a presence of flow in $f$, and right to left if they correspond to an absence of flow. They are positively weighted if we want them to stay at their current state, and negatively if we want them to switch. Let us compute the weight of such graph.
+
+\begin{multline*}
+	w(G_f)  = \sum_{e\in E_f} w(e_f)  \\
+	= 
+	(\alpha - \beta -\gamma) N_1 + (\alpha +\beta - \gamma) N_2 + (\alpha+\beta+\gamma) N_3 
+	\\ + 
+	\#V\times N - 4 \sum_p 3-\#(T_p\cap T'_p) \\ 
+	=(\#V-12+\alpha-\beta-\gamma)\times N + 4Q_V + 2\beta N_2 + 2(\beta+\gamma) N_3 \\
+\end{multline*}
+
+As for the mode 3-strict, one can check that the difference of two such graphs corresponding to the same $(n_v)$ is always eulerian. Hence we can navigate in this class with the same greedy algorithm that discovers positive cycles and flips them.
+
+The function that we optimize is 
+$$
+2Q_V +  \beta N_2 + (\beta+\gamma) N_3.
+$$
+The choice of parameters $\beta$ and $\gamma$ should be lead by the following question: For $\beta$, where to put the tradeoff between zone dispersion and distance to the previous configuration? For $\gamma$, do we prefer to have more partitions spread between 2 zones, or have less between at least 2 zones but more between 3 zones.
+
+The quantity $Q_V$ varies between $0$ and $3N$, it should be of order $N$. The quantity $N_2+N_3$ should also be of order $N$ (it is exactly $N$ in the strict mode). So the two terms of the function are comparable. 
+
+
+\bibliography{optimal_layout} 
+\bibliographystyle{ieeetr}
+
+\end{document}
+
+
+

flake.nix

@@ -48,6 +48,10 @@
           pkgsSrc = nixpkgs;
           cargo2nixOverlay = cargo2nix.overlays.default;
           release = false;
-        }).workspaceShell { packages = [ pkgs.rustfmt ]; };
+        }).workspaceShell { packages = with pkgs; [
+          rustfmt
+          clang
+          mold
+        ]; };
       });
 }

nix/compile.nix

@@ -189,7 +189,7 @@ let
   rootFeatures = if features != null then
     features
   else
-    ([ "garage/bundled-libs" "garage/sled" "garage/k2v" ] ++ (if release then [
+    ([ "garage/bundled-libs" "garage/sled" "garage/lmdb" "garage/k2v" ] ++ (if release then [
       "garage/consul-discovery"
       "garage/kubernetes-discovery"
       "garage/metrics"

script/dev-bucket.sh

@@ -9,11 +9,22 @@ GARAGE_RELEASE="${REPO_FOLDER}/target/release/"
 NIX_RELEASE="${REPO_FOLDER}/result/bin/"
 PATH="${GARAGE_DEBUG}:${GARAGE_RELEASE}:${NIX_RELEASE}:$PATH"
 
-garage -c /tmp/config.1.toml bucket create eprouvette
-KEY_INFO=$(garage -c /tmp/config.1.toml key new --name opérateur)
+if [ -z "$GARAGE_BIN" ]; then
+	GARAGE_BIN=$(which garage || exit 1)
+	echo -en "Found garage at: ${GARAGE_BIN}\n"
+else
+	echo -en "Using garage binary at: ${GARAGE_BIN}\n"
+fi
+
+$GARAGE_BIN -c /tmp/config.1.toml bucket create eprouvette
+if [ "$GARAGE_08" = "1" ]; then
+	KEY_INFO=$($GARAGE_BIN -c /tmp/config.1.toml key new --name opérateur)
+else
+	KEY_INFO=$($GARAGE_BIN -c /tmp/config.1.toml key create opérateur)
+fi
 ACCESS_KEY=`echo $KEY_INFO|grep -Po 'GK[a-f0-9]+'`
 SECRET_KEY=`echo $KEY_INFO|grep -Po 'Secret key: [a-f0-9]+'|grep -Po '[a-f0-9]+$'`
-garage -c /tmp/config.1.toml bucket allow eprouvette --read --write --owner --key $ACCESS_KEY
+$GARAGE_BIN -c /tmp/config.1.toml bucket allow eprouvette --read --write --owner --key $ACCESS_KEY
 echo "$ACCESS_KEY $SECRET_KEY" > /tmp/garage.s3
 
 echo "Bucket s3://eprouvette created. Credentials stored in /tmp/garage.s3."

script/dev-cluster.sh

@@ -11,11 +11,16 @@ PATH="${GARAGE_DEBUG}:${GARAGE_RELEASE}:${NIX_RELEASE}:$PATH"
 FANCYCOLORS=("41m" "42m" "44m" "45m" "100m" "104m")
 
 export RUST_BACKTRACE=1 
-export RUST_LOG=garage=info,garage_api=debug,netapp=trace
+export RUST_LOG=garage=info,garage_api=debug
 MAIN_LABEL="\e[${FANCYCOLORS[0]}[main]\e[49m"
 
-WHICH_GARAGE=$(which garage || exit 1)
-echo -en "${MAIN_LABEL} Found garage at: ${WHICH_GARAGE}\n"
+if [ -z "$GARAGE_BIN" ]; then
+	GARAGE_BIN=$(which garage || exit 1)
+	echo -en "${MAIN_LABEL} Found garage at: ${GARAGE_BIN}\n"
+else
+	echo -en "${MAIN_LABEL} Using garage binary at: ${GARAGE_BIN}\n"
+fi
+$GARAGE_BIN --version
 
 NETWORK_SECRET="$(openssl rand -hex 32)"
 
@@ -28,6 +33,7 @@ LABEL="\e[${FANCYCOLORS[$count]}[$count]\e[49m"
 cat > $CONF_PATH <<EOF
 block_size = 1048576			# objects are split in blocks of maximum this number of bytes
 metadata_dir = "/tmp/garage-meta-$count"
+db_engine = "lmdb"
 data_dir = "/tmp/garage-data-$count"
 rpc_bind_addr = "0.0.0.0:$((3900+$count))"		# the port other Garage nodes will use to talk to this node
 rpc_public_addr = "127.0.0.1:$((3900+$count))"
@@ -51,7 +57,7 @@ EOF
 
 echo -en "$LABEL configuration written to $CONF_PATH\n"
 
-(garage -c /tmp/config.$count.toml server 2>&1|while read r; do echo -en "$LABEL $r\n"; done) &
+($GARAGE_BIN -c /tmp/config.$count.toml server 2>&1|while read r; do echo -en "$LABEL $r\n"; done) &
 done
 # >>>>>>>>>>>>>>>> END FOR LOOP ON NODES
 
@@ -73,14 +79,14 @@ fi
 sleep 3
 # Establish connections between nodes
 for count in $(seq 1 3); do
-	NODE=$(garage -c /tmp/config.$count.toml node id -q)
+	NODE=$($GARAGE_BIN -c /tmp/config.$count.toml node id -q)
 	for count2 in $(seq 1 3); do
-		garage -c /tmp/config.$count2.toml node connect $NODE
+		$GARAGE_BIN -c /tmp/config.$count2.toml node connect $NODE
 	done
 done
 
 RETRY=120
-until garage -c /tmp/config.1.toml status 2>&1|grep -q HEALTHY ; do 
+until $GARAGE_BIN -c /tmp/config.1.toml status 2>&1|grep -q HEALTHY ; do 
   (( RETRY-- ))
   if (( RETRY <= 0 )); then 
     echo -en "${MAIN_LABEL} Garage did not start"

script/dev-configure.sh

@@ -9,9 +9,17 @@ GARAGE_RELEASE="${REPO_FOLDER}/target/release/"
 NIX_RELEASE="${REPO_FOLDER}/result/bin/"
 PATH="${GARAGE_DEBUG}:${GARAGE_RELEASE}:${NIX_RELEASE}:$PATH"
 
+if [ -z "$GARAGE_BIN" ]; then
+	GARAGE_BIN=$(which garage || exit 1)
+	echo -en "Found garage at: ${GARAGE_BIN}\n"
+else
+	echo -en "Using garage binary at: ${GARAGE_BIN}\n"
+fi
+$GARAGE_BIN --version
+
 sleep 5
 RETRY=120
-until garage -c /tmp/config.1.toml status 2>&1|grep -q HEALTHY ; do 
+until $GARAGE_BIN -c /tmp/config.1.toml status 2>&1|grep -q HEALTHY ; do
   (( RETRY-- ))
   if (( RETRY <= 0 )); then
     echo "garage did not start in time, failing."
@@ -21,11 +29,20 @@ until garage -c /tmp/config.1.toml status 2>&1|grep -q HEALTHY ; do
 	sleep 1
 done
 
-garage -c /tmp/config.1.toml status \
-	| grep 'NO ROLE' \
-	| grep -Po '^[0-9a-f]+' \
-	| while read id; do 
-	  garage -c /tmp/config.1.toml layout assign $id -z dc1 -c 1
-	done
+if [ "$GARAGE_08" = "1" ]; then
+	$GARAGE_BIN -c /tmp/config.1.toml status \
+		| grep 'NO ROLE' \
+		| grep -Po '^[0-9a-f]+' \
+		| while read id; do
+		  $GARAGE_BIN -c /tmp/config.1.toml layout assign $id -z dc1 -c 1
+		done
+else
+	$GARAGE_BIN -c /tmp/config.1.toml status \
+		| grep 'NO ROLE' \
+		| grep -Po '^[0-9a-f]+' \
+		| while read id; do
+		  $GARAGE_BIN -c /tmp/config.1.toml layout assign $id -z dc1 -c 1G
+		done
+fi
 
-garage -c /tmp/config.1.toml layout apply --version 1
+$GARAGE_BIN -c /tmp/config.1.toml layout apply --version 1

script/helm/garage/Chart.yaml

@@ -21,4 +21,4 @@ version: 0.4.1
 # incremented each time you make changes to the application. Versions are not expected to
 # follow Semantic Versioning. They should reflect the version the application is using.
 # It is recommended to use it with quotes.
-appVersion: "v0.8.5"
+appVersion: "v0.9.1"

script/jepsen.garage/.envrc

@@ -0,0 +1 @@
+use nix

script/jepsen.garage/.gitignore

@@ -0,0 +1,17 @@
+/target
+/classes
+/checkouts
+profiles.clj
+pom.xml
+pom.xml.asc
+*.jar
+*.class
+/.lein-*
+/.nrepl-port
+/.prepl-port
+.hgignore
+.hg/
+.direnv
+/store
+/store.*
+.vagrant

script/jepsen.garage/README.md

@@ -0,0 +1,166 @@
+# jepsen.garage
+
+Jepsen checking of Garage consistency properties.
+
+## Usage
+
+Requirements:
+
+- vagrant
+- VirtualBox, configured so that nodes can take an IP in a private network `192.168.56.0/24` (it's the default)
+- a user that can create VirtualBox VMs
+- leiningen
+- gnuplot
+
+Set up VMs before running tests:
+
+```
+vagrant up
+```
+
+Run tests: see commands below.
+
+
+## Results
+
+### Register linear, without timestamp patch
+
+Command: `lein run test --nodes-file nodes.vagrant --time-limit 60 --rate 100  --concurrency 20 --workload reg1 --ops-per-key 100`
+
+Results without timestamp patch:
+
+- Fails with a simple clock-scramble nemesis (`--scenario c`).
+  Explanation: without the timestamp patch, nodes will create objects using their
+  local clock only as a timestamp, so the ordering will be all over the place if
+  clocks are scrambled.
+
+Results with timestamp patch (`--patch tsfix2`):
+
+- No failure with clock-scramble nemesis
+
+- Fails with clock-scramble nemesis + partition nemesis (`--scenario cp`).
+
+**This test is expected to fail.**
+Indeed, S3 objects are not meant to behave like linearizable registers.
+TODO explain using a counter-example
+
+
+### Read-after-write CRDT register model
+
+Command: `lein run test --nodes-file nodes.vagrant --time-limit 60 --rate 100  --concurrency 100 --workload reg2 --ops-per-key 100`
+
+Results without timestamp patch:
+
+- Fails with a simple clock-scramble nemesis (`--scenario c`).
+  Explanation: old values are not overwritten correctly when their timestamps are in the future.
+
+Results with timestamp patch (`--patch tsfix2`):
+
+- No failures with clock-scramble nemesis + partition nemesis (`--scenario cp`).
+  This proves that `tsfix2` (PR#543) does improve consistency.
+
+- **Fails with layout reconfiguration nemesis** (`--scenario r`).
+  Example of a failed run: `garage reg2/20231024T120806.899+0200`.
+  This is the failure mode we are looking for and trying to fix for NLnet task 3.
+
+Results with NLnet task 3 code (commit 707442f5de, `--patch task3a`):
+
+- No failures with `--scenario r` (0 of 10 runs), `--scenario pr` (0 of 10 runs),
+  `--scenario cpr` (0 of 10 runs) and `--scenario dpr` (0 of 10 runs).
+
+- Same with `--patch task3c` (commit `0041b013`, the final version).
+
+
+### Set, basic test (write some items, then read)
+
+Command: `lein run test --nodes-file nodes.vagrant --time-limit 60 --rate 200  --concurrency 200 --workload set1 --ops-per-key 100`
+
+Results without NLnet task3 code (`--patch tsfix2`):
+
+- For now, no failures with clock-scramble nemesis + partition nemesis -> TODO long test run
+
+- Does not seem to fail with only the layout reconfiguation nemesis (<10 runs), although theoretically it could
+
+- **Fails with the partition + layout reconfiguration nemesis** (`--scenario pr`).
+  Example of a failed run: `garage set1/20231024T172214.488+0200` (1 failure in 4 runs).
+  This is the failure mode we are looking for and trying to fix for NLnet task 3.
+
+Results with NLnet task 3 code (commit 707442f5de, `--patch task3a`):
+
+- The tests are buggy and often result in an "unknown" validity status, which
+  is caused by some requests not returning results during network partitions or
+  other nemesis-induced broken cluster states.  However, when the tests were
+  able to finish, there were no failures with scenarios `r`, `pr`, `cpr`,
+  `dpr`.
+
+
+### Set, continuous test (interspersed reads and writes)
+
+Command: `lein run test --nodes-file nodes.vagrant --time-limit 60 --rate 100  --concurrency 100 --workload set2 --ops-per-key 100`
+
+Results without NLnet task3 code (`--patch tsfix2`):
+
+- No failures with clock-scramble nemesis + db nemesis + partition nemesis (`--scenario cdp`) (0 failures in 10 runs).
+
+- **Fails with just layout reconfiguration nemesis** (`--scenario r`).
+  Example of a failed run: `garage set2/20231025T141940.198+0200` (10 failures in 10 runs).
+  This is the failure mode we are looking for and trying to fix for NLnet task 3.
+
+Results with NLnet task3 code (commit 707442f5de, `--patch task3a`):
+
+- No failures with `--scenario r` (0 of 10 runs), `--scenario pr` (0 of 10 runs),
+  `--scenario cpr` (0 of 10 runs) and `--scenario dpr` (0 of 10 runs).
+
+- Same with `--patch task3c` (commit `0041b013`, the final version).
+
+
+## NLnet task 3 final results
+
+- With code from task3 (`--patch task3c`): [reg2 and set2](results/Results-2023-12-13-task3c.png), [set1](results/Results-2023-12-14-task3-set1.png).
+- Without (`--patch tsfix2`): [reg2 and set2](results/Results-2023-12-13-tsfix2.png), set1 TBD.
+
+## Investigating (and fixing) errors
+
+### Segfaults
+
+They are due to the download being interrupted in the middle (^C during first launch on clean VMs), the `garage` binary is truncated.
+Add `:force?` to the `cached-wget!` call in `daemon.clj` to re-download the binary,
+or restar the VMs to clear temporary files.
+
+### In `jepsen.garage`: prefix wierdness
+
+In `store/garage set1/20231019T163358.615+0200`:
+
+```
+INFO [2023-10-19 16:35:20,977] clojure-agent-send-off-pool-207 - jepsen.garage.set list results for prefix set20/ : (set13/0 set13/1 set13/10 set13/11 set13/12 set13/13 set13/14 set13/15 set13/16 set13/17 set13/18 set13/19 set13/2 set13/20 set13/21 set13/22 set13/23 set13/24 set13/25 set13/26 set13/27 set13/28 set13/29 set13/3 set13/30 set13/31 set13/32 set13/33 set13/34 set13/35 set13/36 set13/37 set13/38 set13/39 set13/4 set13/40 set13/41 set13/42 set13/43 set13/44 set13/45 set13/46 set13/47 set13/48 set13/49 set13/5 set13/50 set13/51 set13/52 set13/53 set13/54 set13/55 set13/56 set13/57 set13/58 set13/59 set13/6 set13/60 set13/61 set13/62 set13/63 set13/64 set13/65 set13/66 set13/67 set13/68 set13/69 set13/7 set13/70 set13/71 set13/72 set13/73 set13/74 set13/75 set13/76 set13/77 set13/78 set13/79 set13/8 set13/80 set13/81 set13/82 set13/83 set13/84 set13/85 set13/86 set13/87 set13/88 set13/89 set13/9 set13/90 set13/91 set13/92 set13/93 set13/94 set13/95 set13/96 set13/97 set13/98 set13/99)  (node: http://192.168.56.25:3900 )
+```
+
+After inspecting, the actual S3 call made was with prefix "set13/", so at least this is not an error in Garage itself but in the jepsen code.
+
+Finally found out that this was due to closures not correctly capturing their context in the list function in s3api.clj (wtf clojure?)
+Not sure exactly where it came from but it seems to have been fixed by making list-inner a separate function and not a sub-function,
+and passing all values that were previously in the context (creds and prefix) as additional arguments.
+
+### `reg2` test inconsistency, even with timestamp fix
+
+The reg2 test is our custom checker for CRDT read-after-write on individual object keys, acting as registers which can be updated.
+The test fails without the timestamp fix, which is expected as the clock scrambler will prevent nodes from having a correct ordering of objects.
+
+With the timestamp fix (`--patch tsfix1`), the happenned-before relationship should at least be respected, meaning that when a PutObject call starts
+after another PutObject call has ended, the second call should overwrite the value of the first call, and that value should not be
+readable by future GetObject calls.
+However, we observed inconsistencies even with the timestamp fix.
+
+The inconsistencies seemed to always happenned after writing a nil value, which translates to a DeleteObject call
+instead of a PutObject. By removing the possibility of writing nil values, therefore only doing
+PutObject calls, the issue disappears. There is therefore an issue to fix in DeleteObject.
+
+The issue in DeleteObject seems to have been fixed by commit `c82d91c6bccf307186332b6c5c6fc0b128b1b2b1`, which can be used using `--patch tsfix2`.
+
+
+## License
+
+Copyright © 2023 Alex Auvolat
+
+This program and the accompanying materials are made available under the
+terms of the GNU Affero General Public License v3.0.

script/jepsen.garage/Vagrantfile

@@ -0,0 +1,40 @@
+# -*- mode: ruby -*-
+# vi: set ft=ruby :
+#
+
+def vm(config, hostname, ip)
+  config.vm.hostname = hostname
+  config.vm.network "private_network", ip: ip
+end
+
+Vagrant.configure("2") do |config|
+  config.vm.box = "generic/debian10"
+
+  config.vm.provider "virtualbox" do |vb|
+    vb.gui = false
+    vb.memory = "512"
+    vb.customize ["modifyvm", :id, "--vram=12"]
+  end
+
+  config.vm.provision "shell", inline: <<-SHELL
+    echo "root:root" | chpasswd
+    mkdir -p /root/.ssh
+    echo "ssh-ed25519 AAAAC3NzaC1lZDI1NTE5AAAAIJpaBZdYxHqMxhv2RExAOa7nkKhPBOHupMP3mYaZ73w9 lx@lindy" >> /root/.ssh/authorized_keys
+  SHELL
+
+  config.vm.define "n1" do |config| vm(config, "n1", "192.168.56.21") end
+  config.vm.define "n2" do |config| vm(config, "n2", "192.168.56.22") end
+  config.vm.define "n3" do |config| vm(config, "n3", "192.168.56.23") end
+  config.vm.define "n4" do |config| vm(config, "n4", "192.168.56.24") end
+  config.vm.define "n5" do |config| vm(config, "n5", "192.168.56.25") end
+  config.vm.define "n6" do |config| vm(config, "n6", "192.168.56.26") end
+  config.vm.define "n7" do |config| vm(config, "n7", "192.168.56.27") end
+
+  config.vm.define "n8" do |config| vm(config, "n8", "192.168.56.28") end
+  config.vm.define "n9" do |config| vm(config, "n9", "192.168.56.29") end
+  config.vm.define "n10" do |config| vm(config, "n10", "192.168.56.30") end
+  config.vm.define "n11" do |config| vm(config, "n11", "192.168.56.31") end
+  config.vm.define "n12" do |config| vm(config, "n12", "192.168.56.32") end
+  config.vm.define "n13" do |config| vm(config, "n13", "192.168.56.33") end
+  config.vm.define "n14" do |config| vm(config, "n14", "192.168.56.34") end
+end

script/jepsen.garage/all_tests_1.sh

@@ -0,0 +1,18 @@
+#!/usr/bin/env bash
+
+set -x
+
+#for ppatch in task3c task3a tsfix2; do
+for ppatch in tsfix2; do
+	#for psc in c cp cdp r pr cpr dpr; do
+	for psc in cdp r pr cpr dpr; do
+		#for ptsk in reg2 set1 set2; do
+		for ptsk in set1; do
+			for irun in $(seq 10); do
+				lein run test --nodes-file nodes.vagrant \
+					--time-limit 60 --rate 100  --concurrency 100 --ops-per-key 100 \
+					--workload $ptsk --patch $ppatch --scenario $psc
+			done
+		done
+	done
+done

script/jepsen.garage/all_tests_2.sh

@@ -0,0 +1,16 @@
+#!/usr/bin/env bash
+
+set -x
+
+#for ppatch in task3c tsfix2; do
+for ppatch in tsfix2; do
+	for psc in cdp r pr cpr dpr; do
+		for ptsk in set1; do
+			for irun in $(seq 10); do
+				lein run test --nodes-file nodes2.vagrant \
+					--time-limit 60 --rate 100  --concurrency 100 --ops-per-key 100 \
+					--workload $ptsk --patch $ppatch --scenario $psc
+			done
+		done
+	done
+done

script/jepsen.garage/jaeger.sh

@@ -0,0 +1,13 @@
+docker stop jaeger
+docker rm jaeger
+
+# UI is on localhost:16686
+# otel-grpc collector is on localhost:4317
+# otel-http collector is on localhost:4318
+
+docker run -d --name jaeger \
+  -e COLLECTOR_OTLP_ENABLED=true \
+  -p 4317:4317 \
+  -p 4318:4318 \
+  -p 16686:16686 \
+  jaegertracing/all-in-one:1.50

script/jepsen.garage/nodes.vagrant

@@ -0,0 +1,7 @@
+192.168.56.21
+192.168.56.22
+192.168.56.23
+192.168.56.24
+192.168.56.25
+192.168.56.26
+192.168.56.27

script/jepsen.garage/nodes2.vagrant

@@ -0,0 +1,7 @@
+192.168.56.28
+192.168.56.29
+192.168.56.30
+192.168.56.31
+192.168.56.32
+192.168.56.33
+192.168.56.34

script/jepsen.garage/project.clj

@@ -0,0 +1,10 @@
+(defproject jepsen.garage "0.1.0-SNAPSHOT"
+  :description "Jepsen testing for Garage"
+  :url "https://git.deuxfleurs.fr/Deuxfleurs/garage"
+  :license {:name "AGPLv3"
+            :url "https://www.gnu.org/licenses/agpl-3.0.en.html"}
+  :main jepsen.garage
+  :dependencies [[org.clojure/clojure "1.11.1"]
+                 [jepsen "0.3.3-SNAPSHOT"]
+                 [amazonica "0.3.163"]]
+  :repl-options {:init-ns jepsen.garage})

script/jepsen.garage/shell.nix

@@ -0,0 +1,18 @@
+{ pkgs ? import <nixpkgs> {
+  overlays = [
+    (self: super: {
+      jdk = super.jdk11;
+      jre = super.jre11;
+    })
+  ];
+} }:
+pkgs.mkShell {
+  nativeBuildInputs = with pkgs; [
+    leiningen
+    jdk
+    jna
+    vagrant
+    gnuplot
+    graphviz
+  ];
+}

script/jepsen.garage/src/jepsen/garage.clj

@@ -0,0 +1,105 @@
+(ns jepsen.garage
+  (:require
+    [clojure.string :as str]
+    [jepsen
+     [checker :as checker]
+     [cli :as cli]
+     [generator :as gen]
+     [nemesis :as nemesis]
+     [tests :as tests]]
+    [jepsen.os.debian :as debian]
+    [jepsen.garage
+     [daemon :as grg]
+     [nemesis :as grgNemesis]
+     [reg :as reg]
+     [set :as set]]))
+
+(def workloads
+  "A map of workload names to functions that construct workloads, given opts."
+  {"reg1" reg/workload1
+   "reg2" reg/workload2
+   "set1" set/workload1
+   "set2" set/workload2})
+
+(def scenari
+  "A map of scenari to the associated nemesis"
+  {"c" grgNemesis/scenario-c
+   "cp" grgNemesis/scenario-cp
+   "r"  grgNemesis/scenario-r
+   "pr"  grgNemesis/scenario-pr
+   "cpr"  grgNemesis/scenario-cpr
+   "cdp"  grgNemesis/scenario-cdp
+   "dpr"  grgNemesis/scenario-dpr})
+
+(def patches
+  "A map of patch names to Garage builds"
+  {"default" "v0.9.0"
+   "tsfix1" "d146cdd5b66ca1d3ed65ce93ca42c6db22defc09"
+   "tsfix2" "c82d91c6bccf307186332b6c5c6fc0b128b1b2b1"
+   "task3a" "707442f5de416fdbed4681a33b739f0a787b7834"
+   "task3b" "431b28e0cfdc9cac6c649193cf602108a8b02997"
+   "task3c" "0041b013a473e3ae72f50209d8f79db75a72848b"})
+
+(def cli-opts
+  "Additional command line options."
+  [["-p" "--patch NAME" "Garage patch to use"
+    :default "default"
+    :validate [patches (cli/one-of patches)]]
+   ["-s" "--scenario NAME" "Nemesis scenario to run"
+    :default "cp"
+    :validate [scenari (cli/one-of scenari)]]
+   ["-r" "--rate HZ" "Approximate number of requests per second, per thread."
+    :default  10
+    :parse-fn read-string
+    :validate [#(and (number? %) (pos? %)) "Must be a positive number"]]
+   [nil "--ops-per-key NUM" "Maximum number of operations on any given key."
+    :default  100
+    :parse-fn parse-long
+    :validate [pos? "Must be a positive integer."]]
+   ["-w" "--workload NAME" "Workload of test to run"
+    :default "reg1"
+    :validate [workloads (cli/one-of workloads)]]])
+
+(defn garage-test
+  "Given an options map from the command line runner (e.g. :nodes, :ssh,
+  :concurrency, ...), constructs a test map."
+  [opts]
+  (let [garage-version (get patches (:patch opts))
+        db (grg/db garage-version)
+        workload ((get workloads (:workload opts)) opts)
+        scenario ((get scenari (:scenario opts)) (assoc opts :db db))]
+    (merge tests/noop-test
+           opts
+           {:pure-generators  true
+            :name             (str "garage-" (name (:patch opts)) " " (name (:workload opts)) " " (name (:scenario opts)))
+            :os               debian/os
+            :db               db
+            :client           (:client workload)
+            :generator        (gen/phases
+                                (->>
+                                  (:generator workload)
+                                  (gen/stagger (/ (:rate opts)))
+                                  (gen/nemesis (:generator scenario))
+                                  (gen/time-limit (:time-limit opts)))
+                                (gen/log "Healing cluster")
+                                (gen/nemesis (:final-generator scenario))
+                                (gen/log "Waiting for recovery")
+                                (gen/sleep 10)
+                                (gen/log "Running final generator")
+                                (gen/clients (:final-generator workload))
+                                (gen/log "Generators all done"))
+            :nemesis          (:nemesis scenario)
+            :checker          (checker/compose
+                                {:perf (checker/perf (:perf scenario))
+                                 :workload (:checker workload)})
+            })))
+
+
+(defn -main
+  "Handles command line arguments. Can either run a test, or a web server for
+  browsing results."
+  [& args]
+  (cli/run! (merge (cli/single-test-cmd {:test-fn garage-test
+                                         :opt-spec cli-opts})
+                   (cli/serve-cmd))
+            args))

script/jepsen.garage/src/jepsen/garage/daemon.clj

@@ -0,0 +1,152 @@
+(ns jepsen.garage.daemon
+  (:require [clojure.tools.logging :refer :all]
+            [jepsen [control :as c]
+             [core :as jepsen]
+             [db :as db]]
+            [jepsen.control.util :as cu]))
+
+; CONSTANTS -- HOW GARAGE IS SET UP
+
+(def base-dir "/opt/garage")
+(def data-dir (str base-dir "/data"))
+(def meta-dir (str base-dir "/meta"))
+(def binary (str base-dir "/garage"))
+(def logfile (str base-dir "/garage.log"))
+(def pidfile (str base-dir "/garage.pid"))
+
+(def admin-token "icanhazadmin")
+(def access-key-id "GK8bfb6a51286071c6c9cd8bc3")
+(def secret-access-key "b0be95f71c1c6f16858a9edf395078b75c12ecb6b1c03385c4ae92076e4994a3")
+(def bucket-name "jepsen")
+
+; THE GARAGE DB
+
+(defn install!
+  "Download and install Garage"
+  [node version]
+  (c/su
+    (c/trace
+      (info node "installing garage" version)
+      (c/exec :mkdir :-p base-dir)
+      (let [url (str "https://garagehq.deuxfleurs.fr/_releases/" version "/x86_64-unknown-linux-musl/garage")
+            cache (cu/cached-wget! url)]
+        (c/exec :cp cache binary))
+      (c/exec :chmod :+x binary))))
+
+(defn configure!
+  "Configure Garage"
+  [node]
+  (c/su
+    (c/trace
+      (cu/write-file!
+        (str "rpc_secret = \"0fffabe52542c2b89a56b2efb7dfd477e9dafb285c9025cbdf1de7ca21a6b372\"\n"
+             "rpc_bind_addr = \"0.0.0.0:3901\"\n"
+             "rpc_public_addr = \"" node ":3901\"\n"
+             "db_engine = \"lmdb\"\n"
+             "replication_mode = \"2\"\n"
+             "data_dir = \"" data-dir "\"\n"
+             "metadata_dir = \"" meta-dir "\"\n"
+             "[s3_api]\n"
+             "s3_region = \"us-east-1\"\n"
+             "api_bind_addr = \"0.0.0.0:3900\"\n"
+             "[k2v_api]\n"
+             "api_bind_addr = \"0.0.0.0:3902\"\n"
+             "[admin]\n"
+             "api_bind_addr = \"0.0.0.0:3903\"\n"
+             "admin_token = \"" admin-token "\"\n"
+             "trace_sink = \"http://192.168.56.1:4317\"\n")
+        "/etc/garage.toml"))))
+
+(defn connect-node!
+  "Connect a Garage node to the rest of the cluster"
+  [test node]
+  (c/trace
+    (let [node-id (c/exec binary :node :id :-q)]
+      (info node "node id:" node-id)
+      (c/on-many (:nodes test)
+                 (c/exec binary :node :connect node-id)))))
+
+(defn configure-node!
+  "Configure a Garage node to be part of a cluster layout"
+  [test node]
+  (c/trace
+    (let [node-id (c/exec binary :node :id :-q)]
+      (c/on (jepsen/primary test)
+          (c/exec binary :layout :assign (subs node-id 0 16) :-c :1G :-z :dc1 :-t node)))))
+
+(defn finalize-config!
+  "Apply the layout and create a key/bucket pair in the cluster"
+  [node]
+  (c/trace
+    (c/exec binary :layout :apply :--version 1)
+    (info node "garage status:" (c/exec binary :status))
+    (c/exec binary :key :import access-key-id secret-access-key :--yes)
+    (c/exec binary :bucket :create bucket-name)
+    (c/exec binary :bucket :allow :--read :--write bucket-name :--key access-key-id)
+    (info node "key info: " (c/exec binary :key :info access-key-id))))
+
+(defn db
+  "Garage DB for a particular version"
+  [version]
+  (reify db/DB
+    (setup! [_ test node]
+      (install! node version)
+      (configure! node)
+      (cu/start-daemon!
+        {:logfile logfile
+         :pidfile pidfile
+         :chdir base-dir
+         :env {:RUST_LOG "garage=debug,garage_api=trace"}}
+        binary
+        :server)
+      (c/exec :sleep 3)
+
+      (jepsen/synchronize test)
+      (connect-node! test node)
+
+      (jepsen/synchronize test)
+      (configure-node! test node)
+
+      (jepsen/synchronize test)
+      (when (= node (jepsen/primary test))
+        (finalize-config! node)))
+
+    (teardown! [_ test node]
+      (info node "tearing down garage" version)
+      (c/su
+        (cu/stop-daemon! binary pidfile)
+        (c/exec :rm :-rf logfile)
+        (c/exec :rm :-rf data-dir)
+        (c/exec :rm :-rf meta-dir)))
+
+    db/Pause
+    (pause! [_ test node]
+      (cu/grepkill! :stop binary))
+    (resume! [_ test node]
+      (cu/grepkill! :cont binary))
+
+    db/Kill
+    (kill! [_ test node]
+      (cu/stop-daemon! binary pidfile))
+    (start! [_ test node]
+      (cu/start-daemon!
+        {:logfile logfile
+         :pidfile pidfile
+         :chdir base-dir
+         :env {:RUST_LOG "garage=debug,garage_api=trace"}}
+        binary
+        :server))
+
+    db/LogFiles
+    (log-files [_ test node]
+      [logfile])))
+
+(defn creds
+  "Obtain Garage credentials for node"
+  [node]
+  {:access-key access-key-id
+   :secret-key secret-access-key
+   :endpoint (str "http://" node ":3900")
+   :bucket bucket-name
+   :client-config {:path-style-access-enabled true}})
+

script/jepsen.garage/src/jepsen/garage/nemesis.clj

@@ -0,0 +1,142 @@
+(ns jepsen.garage.nemesis
+  (:require [clojure.tools.logging :refer :all]
+            [jepsen [control :as c]
+             [core :as jepsen]
+             [generator :as gen]
+             [nemesis :as nemesis]]
+            [jepsen.nemesis.combined :as combined]
+            [jepsen.garage.daemon :as grg]
+            [jepsen.control.util :as cu]))
+
+; ---- reconfiguration nemesis ----
+
+(defn configure-present!
+  "Configure node to be active in new cluster layout"
+  [test nodes]
+  (info "configure-present!" nodes)
+  (let [node-ids (c/on-many nodes (c/exec grg/binary :node :id :-q))
+        node-id-strs (map (fn [[_ v]] (subs v  0 16)) node-ids)]
+    (c/on
+      (jepsen/primary test)
+      (apply c/exec (concat [grg/binary :layout :assign :-c :1G] node-id-strs)))))
+
+(defn configure-absent!
+  "Configure nodes to be active in new cluster layout"
+  [test nodes]
+  (info "configure-absent!" nodes)
+  (let [node-ids (c/on-many nodes (c/exec grg/binary :node :id :-q))
+        node-id-strs (map (fn [[_ v]] (subs v  0 16)) node-ids)]
+    (c/on
+      (jepsen/primary test)
+      (apply c/exec (concat [grg/binary :layout :assign :-g] node-id-strs)))))
+
+(defn finalize-config!
+  "Apply the proposed cluster layout"
+  [test]
+  (let [layout-show (c/on (jepsen/primary test) (c/exec grg/binary :layout :show))
+        [_ layout-next-version] (re-find #"apply --version (\d+)\n" layout-show)]
+    (if layout-next-version
+      (do
+        (info "layout show: " layout-show "; next-version: " layout-next-version)
+        (c/on (jepsen/primary test)
+              (c/exec grg/binary :layout :apply :--version layout-next-version)))
+      (info "no layout changes to apply"))))
+
+(defn reconfigure-subset
+  "Reconfigure cluster with only a subset of nodes"
+  [cnt]
+  (reify nemesis/Nemesis
+    (setup! [this test] this)
+
+    (invoke! [this test op] op
+      (case (:f op)
+        :start
+          (let [[keep-nodes remove-nodes]
+                (->> (:nodes test)
+                     shuffle
+                     (split-at cnt))]
+            (info "layout split: keep " keep-nodes ", remove " remove-nodes)
+            (configure-present! test keep-nodes)
+            (configure-absent! test remove-nodes)
+            (finalize-config! test)
+            (assoc op :value keep-nodes))
+        :stop
+          (do
+            (info "layout un-split: all nodes=" (:nodes test))
+            (configure-present! test (:nodes test))
+            (finalize-config! test)
+            (assoc op :value (:nodes test)))))
+
+    (teardown! [this test] this)))
+
+; ---- nemesis scenari ----
+
+(defn nemesis-op
+  "A generator for a single nemesis operation"
+  [op]
+  (fn [_ _] {:type :info, :f op}))
+
+(defn reconfiguration-package
+  "Cluster reconfiguration nemesis package"
+  [opts]
+  {:generator        (->>
+                       (gen/mix [(nemesis-op :reconfigure-start)
+                                 (nemesis-op :reconfigure-stop)])
+                       (gen/stagger (:interval opts 5)))
+   :final-generator  {:type :info, :f :reconfigure-stop}
+   :nemesis          (nemesis/compose
+                       {{:reconfigure-start :start
+                         :reconfigure-stop :stop} (reconfigure-subset 3)})
+   :perf              #{{:name  "reconfigure"
+                         :start #{:reconfigure-start}
+                         :stop  #{:reconfigur-stop}
+                         :color "#A197E9"}}})
+
+(defn scenario-c
+  "Clock modifying scenario"
+  [opts]
+  (combined/clock-package {:db (:db opts), :interval 1, :faults #{:clock}}))
+
+(defn scenario-cp
+  "Clock modifying + partition scenario"
+  [opts]
+  (combined/compose-packages
+    [(combined/clock-package {:db (:db opts), :interval 1, :faults #{:clock}})
+     (combined/partition-package {:db (:db opts), :interval 1, :faults #{:partition}})]))
+
+(defn scenario-r
+  "Cluster reconfiguration scenario"
+  [opts]
+  (reconfiguration-package {:interval 1}))
+
+(defn scenario-pr
+  "Partition + cluster reconfiguration scenario"
+  [opts]
+  (combined/compose-packages
+    [(combined/partition-package {:db (:db opts), :interval 1, :faults #{:partition}})
+     (reconfiguration-package {:interval 1})]))
+
+(defn scenario-cpr
+  "Clock scramble + partition + cluster reconfiguration scenario"
+  [opts]
+  (combined/compose-packages
+    [(combined/clock-package {:db (:db opts), :interval 1, :faults #{:clock}})
+     (combined/partition-package {:db (:db opts), :interval 1, :faults #{:partition}})
+     (reconfiguration-package {:interval 1})]))
+
+(defn scenario-cdp
+  "Clock modifying + db + partition scenario"
+  [opts]
+  (combined/compose-packages
+    [(combined/clock-package {:db (:db opts), :interval 1, :faults #{:clock}})
+     (combined/db-package {:db (:db opts), :interval 1, :faults #{:db :pause :kill}})
+     (combined/partition-package {:db (:db opts), :interval 1, :faults #{:partition}})]))
+
+(defn scenario-dpr
+  "Db + partition + cluster reconfiguration scenario"
+  [opts]
+  (combined/compose-packages
+    [(combined/db-package {:db (:db opts), :interval 1, :faults #{:db :pause :kill}})
+     (combined/partition-package {:db (:db opts), :interval 1, :faults #{:partition}})
+     (reconfiguration-package {:interval 1})]))
+

script/jepsen.garage/src/jepsen/garage/reg.clj

@@ -0,0 +1,143 @@
+(ns jepsen.garage.reg
+  (:require [clojure.tools.logging :refer :all]
+            [clojure.string :as str]
+            [clojure.set :as set]
+            [jepsen [checker :as checker]
+             [cli :as cli]
+             [client :as client]
+             [control :as c]
+             [db :as db]
+             [generator :as gen]
+             [independent :as independent]
+             [nemesis :as nemesis]
+             [util :as util]
+             [tests :as tests]]
+            [jepsen.checker.timeline :as timeline]
+            [jepsen.control.util :as cu]
+            [jepsen.os.debian :as debian]
+            [jepsen.garage.daemon :as grg]
+            [jepsen.garage.s3api :as s3]
+            [knossos.model :as model]
+            [slingshot.slingshot :refer [try+]]))
+
+(defn op-get [_ _] {:type :invoke, :f :read, :value nil})
+(defn op-put [_ _] {:type :invoke, :f :write, :value (str (rand-int 99))})
+(defn op-del [_ _] {:type :invoke, :f :write, :value nil})
+
+(defrecord RegClient [creds]
+  client/Client
+  (open! [this test node]
+    (assoc this :creds (grg/creds node)))
+  (setup! [this test])
+  (invoke! [this test op]
+    (try+
+      (let [[k v] (:value op)]
+        (case (:f op)
+          :read
+            (util/timeout
+              10000
+              (assoc op :type :fail, :error ::timeout)
+              (let [value (s3/get (:creds this) k)]
+                (assoc op :type :ok, :value (independent/tuple k value))))
+          :write
+            (util/timeout
+              10000
+              (assoc op :type :info, :error ::timeout)
+              (do
+                (s3/put (:creds this) k v)
+                (assoc op :type :ok)))))
+      (catch (re-find #"Unavailable" (.getMessage %)) ex
+        (assoc op :type :info, :error ::unavailable))
+      (catch (re-find #"Broken pipe" (.getMessage %)) ex
+        (assoc op :type :info, :error ::broken-pipe))
+      (catch (re-find #"Connection refused" (.getMessage %)) ex
+        (assoc op :type :info, :error ::connection-refused))))
+  (teardown! [this test])
+  (close! [this test]))
+
+(defn reg-read-after-write
+  "Read-after-Write checker for register operations"
+  []
+  (reify checker/Checker
+    (check [this test history opts]
+      (let [init {:put-values {-1 nil}
+                  :put-done #{-1}
+                  :put-in-progress {}
+                  :read-can-contain {}
+                  :bad-reads #{}}
+            final (reduce
+                    (fn [state op]
+                      (let [current-values (set/union
+                                             (set (map (fn [idx] (get (:put-values state) idx)) (:put-done state)))
+                                             (set (map (fn [[_ [idx _]]] (get (:put-values state) idx)) (:put-in-progress state))))
+                            read-can-contain (reduce
+                                               (fn [rcc [idx v]] (assoc rcc idx (set/union current-values v)))
+                                               {} (:read-can-contain state))]
+                      (info "--------")
+                      (info "state: " state)
+                      (info "current-values: " current-values)
+                      (info "read-can-contain: " read-can-contain)
+                      (info "op: " op)
+                      (case [(:type op) (:f op)]
+                        ([:invoke :write])
+                          (assoc state
+                                 :read-can-contain read-can-contain
+                                 :put-values (assoc (:put-values state) (:index op) (:value op))
+                                 :put-in-progress (assoc (:put-in-progress state) (:process op) [(:index op) (:put-done state)]))
+                        ([:ok :write])
+                          (let [[index overwrites] (get (:put-in-progress state) (:process op))]
+                            (assoc state
+                                   :read-can-contain read-can-contain
+                                   :put-in-progress (dissoc (:put-in-progress state) (:process op))
+                                   :put-done
+                                     (conj
+                                       (set/difference (:put-done state) overwrites)
+                                       index)))
+                        ([:invoke :read])
+                         (assoc state
+                                :read-can-contain (assoc read-can-contain (:process op) current-values))
+                        ([:ok :read])
+                         (let [this-read-can-contain (get read-can-contain (:process op))
+                               bad-reads (if (contains? this-read-can-contain (:value op))
+                                           (:bad-reads state)
+                                           (conj (:bad-reads state) [(:process op) (:index op) (:value op) this-read-can-contain]))]
+                           (info "this-read-can-contain: " this-read-can-contain)
+                           (assoc state
+                                  :read-can-contain (dissoc read-can-contain (:process op))
+                                  :bad-reads bad-reads))
+                        state)))
+                    init history)
+            valid? (empty? (:bad-reads final))]
+        (assoc final :valid? valid?)))))
+
+(defn workload-common
+  "Common parts of workload"
+  [opts]
+  {:client           (RegClient. nil)
+   :generator        (independent/concurrent-generator
+                       10
+                       (range)
+                       (fn [k]
+                         (->>
+                           (gen/mix [op-get op-put op-del])
+                           (gen/limit (:ops-per-key opts)))))})
+
+(defn workload1
+  "Tests linearizable reads and writes"
+  [opts]
+  (assoc (workload-common opts)
+         :checker (independent/checker
+                    (checker/compose
+                      {:linear (checker/linearizable
+                                 {:model     (model/register)
+                                  :algorithm :linear})
+                       :timeline (timeline/html)}))))
+
+(defn workload2
+  "Tests CRDT reads and writes"
+  [opts]
+  (assoc (workload-common opts)
+         :checker (independent/checker
+                    (checker/compose
+                      {:reg-read-after-write (reg-read-after-write)
+                       :timeline (timeline/html)}))))

script/jepsen.garage/src/jepsen/garage/s3api.clj

@@ -0,0 +1,48 @@
+(ns jepsen.garage.s3api
+  (:require [clojure.tools.logging :refer :all]
+            [jepsen [control :as c]]
+            [amazonica.aws.s3 :as s3]
+            [slingshot.slingshot :refer [try+]]))
+
+; GARAGE S3 HELPER FUNCTIONS
+
+(defn get
+  "Helper for GetObject"
+  [creds k]
+  (try+
+    (-> (s3/get-object creds (:bucket creds) k)
+        :input-stream
+        slurp)
+    (catch (re-find #"Key not found" (.getMessage %)) ex
+      nil)))
+
+(defn put
+  "Helper for PutObject or DeleteObject (is a delete if value is nil)"
+  [creds k v]
+  (if (= v nil)
+    (s3/delete-object creds
+                      :bucket-name (:bucket creds)
+                      :key k)
+    (let [some-bytes (.getBytes v "UTF-8")
+          bytes-stream (java.io.ByteArrayInputStream. some-bytes)]
+      (s3/put-object creds
+                     :bucket-name (:bucket creds)
+                     :key k
+                     :input-stream bytes-stream
+                     :metadata {:content-length (count some-bytes)}))))
+
+(defn list-inner [creds prefix ct accum]
+  (let [list-result (s3/list-objects-v2 creds
+                                        {:bucket-name (:bucket creds)
+                                         :prefix prefix
+                                         :continuation-token ct})
+        new-object-summaries (:object-summaries list-result)
+        new-objects (map (fn [d] (:key d)) new-object-summaries)
+        objects (concat new-objects accum)]
+    (if (:truncated? list-result)
+      (list-inner creds prefix (:next-continuation-token list-result) objects)
+      objects)))
+(defn list
+  "Helper for ListObjects -- just lists everything in the bucket"
+  [creds prefix]
+  (list-inner creds prefix nil []))

script/jepsen.garage/src/jepsen/garage/set.clj

@@ -0,0 +1,135 @@
+(ns jepsen.garage.set
+  (:require [clojure.tools.logging :refer :all]
+            [clojure.string :as str]
+            [clojure.set :as set]
+            [jepsen [checker :as checker]
+             [cli :as cli]
+             [client :as client]
+             [control :as c]
+             [checker :as checker]
+             [db :as db]
+             [generator :as gen]
+             [independent :as independent]
+             [nemesis :as nemesis]
+             [util :as util]
+             [tests :as tests]]
+            [jepsen.checker.timeline :as timeline]
+            [jepsen.control.util :as cu]
+            [jepsen.os.debian :as debian]
+            [jepsen.garage.daemon :as grg]
+            [jepsen.garage.s3api :as s3]
+            [knossos.model :as model]
+            [slingshot.slingshot :refer [try+]]))
+
+(defn op-add-rand100 [_ _] {:type :invoke, :f :add, :value (rand-int 100)})
+(defn op-read [_ _] {:type :invoke, :f :read, :value nil})
+
+(defrecord SetClient [creds]
+  client/Client
+  (open! [this test node]
+    (assoc this :creds (grg/creds node)))
+  (setup! [this test])
+  (invoke! [this test op]
+    (try+
+      (let [[k v] (:value op)
+            prefix (str "set" k "/")]
+        (case (:f op)
+          :add
+            (util/timeout
+              10000
+              (assoc op :type :info, :error ::timeout)
+              (do
+                (s3/put (:creds this) (str prefix v) "present")
+                (assoc op :type :ok)))
+          :read
+            (util/timeout
+              10000
+              (assoc op :type :fail, :error ::timeout)
+              (do
+                (let [items (s3/list (:creds this) prefix)]
+                  (let [items-stripped (map (fn [o]
+                                            (assert (str/starts-with? o prefix))
+                                            (str/replace-first o prefix "")) items)
+                        items-set (set (map parse-long items-stripped))]
+                    (assoc op :type :ok, :value (independent/tuple k items-set))))))))
+      (catch (re-find #"Unavailable" (.getMessage %)) ex
+        (assoc op :type :info, :error ::unavailable))
+      (catch (re-find #"Broken pipe" (.getMessage %)) ex
+        (assoc op :type :info, :error ::broken-pipe))
+      (catch (re-find #"Connection refused" (.getMessage %)) ex
+        (assoc op :type :info, :error ::connection-refused))))
+  (teardown! [this test])
+  (close! [this test]))
+
+(defn set-read-after-write
+  "Read-after-Write checker for set operations"
+  []
+  (reify checker/Checker
+    (check [this test history opts]
+      (let [init {:add-started #{}
+                  :add-done #{}
+                  :read-must-contain {}
+                  :missed #{}
+                  :unexpected #{}}
+            final (reduce
+                    (fn [state op]
+                      (case [(:type op) (:f op)]
+                        ([:invoke :add])
+                          (assoc state :add-started (conj (:add-started state) (:value op)))
+                        ([:ok :add])
+                          (assoc state :add-done (conj (:add-done state) (:value op)))
+                        ([:invoke :read])
+                          (assoc-in state [:read-must-contain (:process op)] (:add-done state))
+                        ([:ok :read])
+                          (let [read-must-contain (get (:read-must-contain state) (:process op))
+                                new-missed (set/difference read-must-contain (:value op))
+                                new-unexpected (set/difference (:value op) (:add-started state))]
+                            (assoc state
+                                   :read-must-contain (dissoc (:read-must-contain state) (:process op))
+                                   :missed (set/union (:missed state) new-missed),
+                                   :unexpected (set/union (:unexpected state) new-unexpected)))
+                         state))
+                    init history)
+            valid? (and (empty? (:missed final)) (empty? (:unexpected final)))]
+        (assoc final :valid? valid?)))))
+
+(defn workload1
+  "Tests insertions and deletions"
+  [opts]
+  {:client            (SetClient. nil)
+   :checker           (independent/checker
+                        (checker/compose
+                          {:set (checker/set)
+                           :timeline (timeline/html)}))
+   :generator         (independent/concurrent-generator
+                        10
+                        (range 100)
+                        (fn [k]
+                          (->> (range)
+                           (map (fn [x] {:type :invoke, :f :add, :value x}))
+                           (gen/limit (:ops-per-key opts)))))
+   :final-generator   (independent/concurrent-generator
+                        10
+                        (range 100)
+                        (fn [k]
+                          (gen/phases
+                            (gen/once op-read)
+                            (gen/sleep 5))))})
+
+(defn workload2
+  "Tests insertions and deletions"
+  [opts]
+  {:client            (SetClient. nil)
+   :checker           (independent/checker
+                        (checker/compose
+                          {:set-read-after-write (set-read-after-write)
+                           ; :set-full (checker/set-full {:linearizable? false})
+                           :timeline (timeline/html)}))
+   :generator         (independent/concurrent-generator
+                        10
+                        (range)
+                        (fn [k]
+                          (->> (gen/mix [op-add-rand100 op-read])
+                               (gen/limit (:ops-per-key opts)))))})
+
+

script/jepsen.garage/test/jepsen/garage_test.clj

@@ -0,0 +1,7 @@
+(ns jepsen.garage-test
+  (:require [clojure.test :refer :all]
+            [jepsen.garage :refer :all]))
+
+(deftest a-test
+  (testing "FIXME, I fail."
+    (is (= 0 1))))

script/test-renumbering.sh

@@ -0,0 +1,138 @@
+#!/usr/bin/env bash
+
+: '
+	This script tests part renumbering on an S3 remote (here configured for Minio).
+
+	On Minio:
+
+	The results confirm that if I upload parts with number 1, 4, 5 and 6,
+	they are renumbered to 1, 2, 3 and 4 after CompleteMultipartUpload.
+	Thus, specifying partNumber=4 on a GetObject/HeadObject should return
+	information on the part I originally uploaded with part number
+
+	On S3: not tested
+
+	Sample output (on Minio):
+
+		f07e1404cc527d494242824ded3a616b  part1
+		78974cd4d0f622eb3426ea7cd22f5a1c  part4
+		f9cc379f8baa61645558d9ba7e6351fa  part5
+		1bd2383eebbac1f8e7143575ba5b1f4a  part6
+		Upload ID: 6838b813-d0ca-400b-9d28-ec8b2b5cd004
+		PART 1 ETag: "f07e1404cc527d494242824ded3a616b"
+		PART 4 ETag: "78974cd4d0f622eb3426ea7cd22f5a1c"
+		PART 5 ETag: "f9cc379f8baa61645558d9ba7e6351fa"
+		PART 6 ETag: "1bd2383eebbac1f8e7143575ba5b1f4a"
+		======================================== LIST ====
+		{
+		  "Parts": [
+			{
+			  "PartNumber": 1,
+			  "LastModified": "2023-04-25T10:21:54.350000+00:00",
+			  "ETag": "\"f07e1404cc527d494242824ded3a616b\"",
+			  "Size": 20971520
+			},
+			{
+			  "PartNumber": 4,
+			  "LastModified": "2023-04-25T10:21:54.350000+00:00",
+			  "ETag": "\"78974cd4d0f622eb3426ea7cd22f5a1c\"",
+			  "Size": 20971520
+			},
+			{
+			  "PartNumber": 5,
+			  "LastModified": "2023-04-25T10:21:54.350000+00:00",
+			  "ETag": "\"f9cc379f8baa61645558d9ba7e6351fa\"",
+			  "Size": 20971520
+			},
+			{
+			  "PartNumber": 6,
+			  "LastModified": "2023-04-25T10:21:54.350000+00:00",
+			  "ETag": "\"1bd2383eebbac1f8e7143575ba5b1f4a\"",
+			  "Size": 20971520
+			}
+		  ],
+		  "ChecksumAlgorithm": "",
+		  "Initiator": {
+			"ID": "02d6176db174dc93cb1b899f7c6078f08654445fe8cf1b6ce98d8855f66bdbf4",
+			"DisplayName": "02d6176db174dc93cb1b899f7c6078f08654445fe8cf1b6ce98d8855f66bdbf4"
+		  },
+		  "Owner": {
+			"DisplayName": "02d6176db174dc93cb1b899f7c6078f08654445fe8cf1b6ce98d8855f66bdbf4",
+			"ID": "02d6176db174dc93cb1b899f7c6078f08654445fe8cf1b6ce98d8855f66bdbf4"
+		  },
+		  "StorageClass": "STANDARD"
+		}
+		======================================== COMPLETE ====
+		{
+			"Location": "http://localhost:9000/test/upload",
+			"Bucket": "test",
+			"Key": "upload",
+			"ETag": "\"8e817c8ccd442f9a79c77b58fe808c43-4\""
+		}
+		======================================== LIST ====
+
+		An error occurred (NoSuchUpload) when calling the ListParts operation: The specified multipart upload does not exist. The upload ID may be invalid, or the upload may have been aborted or completed.
+		======================================== GET PART 4 ====
+		{
+			"AcceptRanges": "bytes",
+			"LastModified": "2023-04-25T10:21:59+00:00",
+			"ContentLength": 20971520,
+			"ETag": "\"8e817c8ccd442f9a79c77b58fe808c43-4\"",
+			"ContentRange": "bytes 62914560-83886079/83886080",
+			"ContentType": "binary/octet-stream",
+			"Metadata": {},
+			"PartsCount": 4
+		}
+		1bd2383eebbac1f8e7143575ba5b1f4a  get-part4
+
+	
+	Conclusions:
+
+	- Parts are indeed renumbered with consecutive numbers
+	- ListParts only applies to multipart uploads in progress,
+	  it cannot be used once the multipart upload has been completed
+'
+
+export AWS_ACCESS_KEY_ID=1D8Pk2k4oQSoh1BU
+export AWS_SECRET_ACCESS_KEY=4B46SR8U7FUgY0raB8Zuxg1NLyLTvbNV
+
+function aws { command aws --endpoint-url http://localhost:9000 $@ ; }
+
+aws --version
+
+aws s3 mb s3://test
+
+for NUM in 1 4 5 6; do
+	dd if=/dev/urandom of=part$NUM bs=1M count=10
+done
+md5sum part*
+
+UPLOAD=$(aws s3api create-multipart-upload --bucket test --key 'upload' | jq -r ".UploadId")
+echo "Upload ID: $UPLOAD"
+
+PARTS=""
+
+for NUM in 1 4 5 6; do
+	ETAG=$(aws s3api upload-part --bucket test --key 'upload' --part-number $NUM \
+		--body "part$NUM" --upload-id "$UPLOAD" | jq -r ".ETag")
+	echo "PART $NUM ETag: $ETAG"
+	if [ -n "$PARTS" ]; then
+		PARTS="$PARTS,"
+	fi
+	PARTS="$PARTS {\"ETag\":$ETAG,\"PartNumber\":$NUM}"
+done
+
+echo "======================================== LIST ===="
+aws s3api list-parts --bucket test --key upload --upload-id "$UPLOAD" | jq
+
+echo "======================================== COMPLETE ===="
+echo "{\"Parts\":[$PARTS]}" > mpu
+aws s3api complete-multipart-upload --multipart-upload file://mpu \
+		--bucket test --key 'upload' --upload-id "$UPLOAD"
+
+echo "======================================== LIST ===="
+aws s3api list-parts --bucket test --key upload --upload-id "$UPLOAD" | jq
+
+echo "======================================== GET PART 4 ===="
+aws s3api get-object --bucket test --key upload --part-number 4 get-part4
+md5sum get-part4

script/test-skip-part.sh

@@ -0,0 +1,103 @@
+#!/usr/bin/env bash
+
+: '
+	This script tests whether uploaded parts can be skipped in a
+	CompleteMultipartUpoad
+
+	On Minio: yes, parts can be skipped
+
+	On S3: not tested
+
+	Sample output (on Minio):
+
+		f23911bcd1230f5ebe8887cbf5bc396e  part1
+		a2657143167eaf647c40473e78a091dc  part4
+		72f72c02c5163bc81024b28ac818c5e0  part5
+		e29cf500d20498218904b8df8806caa2  part6
+		Upload ID: e8fe7b83-9800-46fb-ae90-9d7ccd42fe76
+		PART 1 ETag: "f23911bcd1230f5ebe8887cbf5bc396e"
+		PART 4 ETag: "a2657143167eaf647c40473e78a091dc"
+		PART 5 ETag: "72f72c02c5163bc81024b28ac818c5e0"
+		PART 6 ETag: "e29cf500d20498218904b8df8806caa2"
+		======================================== COMPLETE ====
+		{
+			"Location": "http://localhost:9000/test/upload",
+			"Bucket": "test",
+			"Key": "upload",
+			"ETag": "\"48246e44d4b38bdc2f3c10ee25b1af17-3\""
+		}
+		======================================== GET FULL ====
+		{
+			"AcceptRanges": "bytes",
+			"LastModified": "2023-04-25T10:54:35+00:00",
+			"ContentLength": 31457280,
+			"ETag": "\"48246e44d4b38bdc2f3c10ee25b1af17-3\"",
+			"ContentType": "binary/octet-stream",
+			"Metadata": {}
+		}
+		97fb904da7ad310699a6afab0eb6e061  get-full
+		97fb904da7ad310699a6afab0eb6e061  -
+		======================================== GET PART 3 ====
+		{
+			"AcceptRanges": "bytes",
+			"LastModified": "2023-04-25T10:54:35+00:00",
+			"ContentLength": 10485760,
+			"ETag": "\"48246e44d4b38bdc2f3c10ee25b1af17-3\"",
+			"ContentRange": "bytes 20971520-31457279/31457280",
+			"ContentType": "binary/octet-stream",
+			"Metadata": {},
+			"PartsCount": 3
+		}
+		e29cf500d20498218904b8df8806caa2  get-part3
+
+	Conclusions:
+
+	- Skipping a part in a CompleteMultipartUpoad call is OK
+	- The part is simply not included in the stored object
+	- Sequential part renumbering counts only non-skipped parts
+'
+
+export AWS_ACCESS_KEY_ID=1D8Pk2k4oQSoh1BU
+export AWS_SECRET_ACCESS_KEY=4B46SR8U7FUgY0raB8Zuxg1NLyLTvbNV
+
+function aws { command aws --endpoint-url http://localhost:9000 $@ ; }
+
+aws --version
+
+aws s3 mb s3://test
+
+for NUM in 1 4 5 6; do
+	dd if=/dev/urandom of=part$NUM bs=1M count=10
+done
+md5sum part*
+
+UPLOAD=$(aws s3api create-multipart-upload --bucket test --key 'upload' | jq -r ".UploadId")
+echo "Upload ID: $UPLOAD"
+
+PARTS=""
+
+for NUM in 1 4 5 6; do
+	ETAG=$(aws s3api upload-part --bucket test --key 'upload' --part-number $NUM \
+		--body "part$NUM" --upload-id "$UPLOAD" | jq -r ".ETag")
+	echo "PART $NUM ETag: $ETAG"
+	if [ "$NUM" != "5" ]; then
+		if [ -n "$PARTS" ]; then
+			PARTS="$PARTS,"
+		fi
+		PARTS="$PARTS {\"ETag\":$ETAG,\"PartNumber\":$NUM}"
+	fi
+done
+
+echo "======================================== COMPLETE ===="
+echo "{\"Parts\":[$PARTS]}" > mpu
+aws s3api complete-multipart-upload --multipart-upload file://mpu \
+		--bucket test --key 'upload' --upload-id "$UPLOAD"
+
+echo "======================================== GET FULL ===="
+aws s3api get-object --bucket test --key upload get-full
+md5sum get-full
+cat part1 part4 part6 | md5sum
+
+echo "======================================== GET PART 3 ===="
+aws s3api get-object --bucket test --key upload --part-number 3 get-part3
+md5sum get-part3

script/test-smoke.sh

@@ -31,6 +31,11 @@ dd if=/dev/urandom of=/tmp/garage.1.rnd bs=1k count=2 # No multipart, inline sto
 dd if=/dev/urandom of=/tmp/garage.2.rnd bs=1M count=5 # No multipart but file will be chunked
 dd if=/dev/urandom of=/tmp/garage.3.rnd bs=1M count=10 # by default, AWS starts using multipart at 8MB
 
+dd if=/dev/urandom of=/tmp/garage.part1.rnd bs=1M count=5
+dd if=/dev/urandom of=/tmp/garage.part2.rnd bs=1M count=5
+dd if=/dev/urandom of=/tmp/garage.part3.rnd bs=1M count=5
+dd if=/dev/urandom of=/tmp/garage.part4.rnd bs=1M count=5
+
 # data of lower entropy, to test compression
 dd if=/dev/urandom bs=1k count=2  | base64 -w0 > /tmp/garage.1.b64
 dd if=/dev/urandom bs=1M count=5  | base64 -w0 > /tmp/garage.2.b64
@@ -40,7 +45,7 @@ echo "🧪 S3 API testing..."
 
 # AWS
 if [ -z "$SKIP_AWS" ]; then
-  echo "🛠️ Testing with awscli"
+  echo "🛠️ Testing with awscli (aws s3)"
   source ${SCRIPT_FOLDER}/dev-env-aws.sh
   aws s3 ls
   for idx in {1..3}.{rnd,b64}; do
@@ -51,8 +56,36 @@ if [ -z "$SKIP_AWS" ]; then
     rm /tmp/garage.$idx.dl
     aws s3 rm "s3://eprouvette/&+-é\"/garage.$idx.aws"
   done
+
+  echo "🛠️ Testing multipart uploads with awscli (aws s3api)"
+  UPLOAD=$(aws s3api create-multipart-upload --bucket eprouvette --key 'upload' | jq -r ".UploadId")
+  echo "Upload ID: $UPLOAD"
+  ETAG3=$(aws s3api upload-part --bucket eprouvette --key 'upload' \
+      --part-number 3 --body "/tmp/garage.part1.rnd" --upload-id "$UPLOAD" \
+      | jq -r ".ETag")
+  ETAG2=$(aws s3api upload-part --bucket eprouvette --key 'upload' \
+      --part-number 2 --body "/tmp/garage.part2.rnd" --upload-id "$UPLOAD" \
+      | jq -r ".ETag")
+  ETAG3=$(aws s3api upload-part --bucket eprouvette --key 'upload' \
+      --part-number 3 --body "/tmp/garage.part3.rnd" --upload-id "$UPLOAD" \
+      | jq -r ".ETag")
+  ETAG6=$(aws s3api upload-part --bucket eprouvette --key 'upload' \
+      --part-number 6 --body "/tmp/garage.part4.rnd" --upload-id "$UPLOAD" \
+      | jq -r ".ETag")
+  MPU="{\"Parts\":[{\"PartNumber\":2,\"ETag\":$ETAG2}, {\"PartNumber\":3,\"ETag\":$ETAG3}, {\"PartNumber\":6,\"ETag\":$ETAG6}]}"
+  echo $MPU > /tmp/garage.mpu.json
+  aws s3api complete-multipart-upload --multipart-upload file:///tmp/garage.mpu.json \
+      --bucket eprouvette --key 'upload' --upload-id "$UPLOAD"
+  aws s3api get-object --bucket eprouvette --key upload /tmp/garage.mpu.get
+  if [ "$(md5sum /tmp/garage.mpu.get | cut -d ' ' -f 1)" != "$(cat /tmp/garage.part{2,3,4}.rnd | md5sum | cut -d ' ' -f 1)" ]; then
+    echo "Invalid multipart upload"
+    exit 1
+  fi
 fi
 
+echo "OK!!"
+exit 0
+
 # S3CMD
 if [ -z "$SKIP_S3CMD" ]; then
   echo "🛠️ Testing with s3cmd"
@@ -141,6 +174,7 @@ rm eprouvette/winscp
 EOF
 fi
 
+rm /tmp/garage.part{1..4}.rnd
 rm /tmp/garage.{1..3}.{rnd,b64}
 
 echo "🏁 Teardown"

script/test-upgrade.sh

@@ -0,0 +1,75 @@
+#!/usr/bin/env bash
+
+set -ex
+
+export LC_ALL=C.UTF-8
+export LANG=C.UTF-8
+SCRIPT_FOLDER="`dirname \"$0\"`"
+REPO_FOLDER="${SCRIPT_FOLDER}/../"
+GARAGE_DEBUG="${REPO_FOLDER}/target/debug/"
+GARAGE_RELEASE="${REPO_FOLDER}/target/release/"
+NIX_RELEASE="${REPO_FOLDER}/result/bin/:${REPO_FOLDER}/result-bin/bin/"
+PATH="${GARAGE_DEBUG}:${GARAGE_RELEASE}:${NIX_RELEASE}:$PATH"
+
+OLD_VERSION="$1"
+ARCH="$2"
+
+
+echo "Downloading old garage binary..."
+curl https://garagehq.deuxfleurs.fr/_releases/$OLD_VERSION/$ARCH/garage > /tmp/old_garage
+chmod +x /tmp/old_garage
+
+echo "============= insert data into old version cluster ================="
+
+export GARAGE_BIN=/tmp/old_garage
+if echo $OLD_VERSION | grep 'v0\.8\.'; then
+	echo "Detected Garage v0.8.x"
+	export GARAGE_08=1
+fi
+
+echo "⏳ Setup cluster using old version"
+$GARAGE_BIN --version
+${SCRIPT_FOLDER}/dev-clean.sh
+${SCRIPT_FOLDER}/dev-cluster.sh > /tmp/garage.log 2>&1 &
+sleep 6
+${SCRIPT_FOLDER}/dev-configure.sh
+${SCRIPT_FOLDER}/dev-bucket.sh
+
+echo "🛠️ Inserting data in old cluster"
+source ${SCRIPT_FOLDER}/dev-env-rclone.sh
+rclone copy "${SCRIPT_FOLDER}/../.git/" garage:eprouvette/test_dotgit --stats=1s --stats-log-level=NOTICE --stats-one-line
+
+echo "🏁 Stopping old cluster"
+killall -INT old_garage
+sleep 2
+killall -9 old_garage || true
+
+echo "🏁 Removing old garage version"
+rm -rv $GARAGE_BIN
+export -n GARAGE_BIN
+export -n GARAGE_08
+
+echo "================ read data from new cluster ==================="
+
+echo "⏳ Setup cluster using new version"
+pwd
+ls
+export GARAGE_BIN=$(which garage)
+$GARAGE_BIN --version
+${SCRIPT_FOLDER}/dev-cluster.sh >> /tmp/garage.log 2>&1 &
+sleep 3
+
+echo "🛠️ Retrieving data from old cluster"
+rclone copy garage:eprouvette/test_dotgit /tmp/test_dotgit --stats=1s --stats-log-level=NOTICE --stats-one-line --fast-list
+
+if ! diff <(find "${SCRIPT_FOLDER}/../.git" -type f | xargs md5sum | cut -d ' ' -f 1 | sort) <(find /tmp/test_dotgit -type f | xargs md5sum | cut -d ' ' -f 1 | sort); then
+	echo "TEST FAILURE: directories are different"
+	exit 1
+fi
+rm -r /tmp/test_dotgit
+
+echo "🏁 Teardown"
+rm -rf /tmp/garage-{data,meta}-*
+rm -rf /tmp/config.*.toml
+
+echo "✅ Success"

shell.nix

@@ -15,16 +15,18 @@ in {
   # --- Rust Shell ---
   # Use it to compile Garage
   rust = pkgs.mkShell {
-    nativeBuildInputs = [
-      #pkgs.rustPlatform.rust.rustc
-      pkgs.rustPlatform.rust.cargo
-      #pkgs.clippy
-      pkgs.rustfmt
-      #pkgs.perl
-      #pkgs.protobuf
-      #pkgs.pkg-config
-      #pkgs.openssl
-      pkgs.file
+    nativeBuildInputs = with pkgs; [
+      #rustPlatform.rust.rustc
+      rustPlatform.rust.cargo
+      clang
+      mold
+      #clippy
+      rustfmt
+      #perl
+      #protobuf
+      #pkg-config
+      #openssl
+      file
       #cargo2nix.packages.x86_64-linux.cargo2nix
     ];
   };

src/api/Cargo.toml

@@ -1,6 +1,6 @@
 [package]
 name = "garage_api"
-version = "0.8.5"
+version = "0.9.1"
 authors = ["Alex Auvolat <alex@adnab.me>"]
 edition = "2018"
 license = "AGPL-3.0"

src/api/admin/api_server.rs

@@ -25,7 +25,8 @@ use crate::admin::bucket::*;
 use crate::admin::cluster::*;
 use crate::admin::error::*;
 use crate::admin::key::*;
-use crate::admin::router::{Authorization, Endpoint};
+use crate::admin::router_v0;
+use crate::admin::router_v1::{Authorization, Endpoint};
 use crate::helpers::host_to_bucket;
 
 pub struct AdminApiServer {
@@ -181,7 +182,7 @@ impl AdminApiServer {
 			),
 		};
 		let status_str = format!(
-			"{}\nConsult the full health check API endpoint at /v0/health for more details\n",
+			"{}\nConsult the full health check API endpoint at /v1/health for more details\n",
 			status_str
 		);
 
@@ -229,7 +230,12 @@ impl ApiHandler for AdminApiServer {
 	type Error = Error;
 
 	fn parse_endpoint(&self, req: &Request<Body>) -> Result<Endpoint, Error> {
-		Endpoint::from_request(req)
+		if req.uri().path().starts_with("/v0/") {
+			let endpoint_v0 = router_v0::Endpoint::from_request(req)?;
+			Endpoint::from_v0(endpoint_v0)
+		} else {
+			Endpoint::from_request(req)
+		}
 	}
 
 	async fn handle(
@@ -276,8 +282,13 @@ impl ApiHandler for AdminApiServer {
 			Endpoint::RevertClusterLayout => handle_revert_cluster_layout(&self.garage, req).await,
 			// Keys
 			Endpoint::ListKeys => handle_list_keys(&self.garage).await,
-			Endpoint::GetKeyInfo { id, search } => {
-				handle_get_key_info(&self.garage, id, search).await
+			Endpoint::GetKeyInfo {
+				id,
+				search,
+				show_secret_key,
+			} => {
+				let show_secret_key = show_secret_key.map(|x| x == "true").unwrap_or(false);
+				handle_get_key_info(&self.garage, id, search, show_secret_key).await
 			}
 			Endpoint::CreateKey => handle_create_key(&self.garage, req).await,
 			Endpoint::ImportKey => handle_import_key(&self.garage, req).await,

src/api/admin/bucket.rs

@@ -14,6 +14,7 @@ use garage_model::bucket_alias_table::*;
 use garage_model::bucket_table::*;
 use garage_model::garage::Garage;
 use garage_model::permission::*;
+use garage_model::s3::mpu_table;
 use garage_model::s3::object_table::*;
 
 use crate::admin::error::*;
@@ -124,6 +125,14 @@ async fn bucket_info_results(
 		.map(|x| x.filtered_values(&garage.system.ring.borrow()))
 		.unwrap_or_default();
 
+	let mpu_counters = garage
+		.mpu_counter_table
+		.table
+		.get(&bucket_id, &EmptyKey)
+		.await?
+		.map(|x| x.filtered_values(&garage.system.ring.borrow()))
+		.unwrap_or_default();
+
 	let mut relevant_keys = HashMap::new();
 	for (k, _) in bucket
 		.state
@@ -208,12 +217,12 @@ async fn bucket_info_results(
 					}
 				})
 				.collect::<Vec<_>>(),
-			objects: counters.get(OBJECTS).cloned().unwrap_or_default(),
-			bytes: counters.get(BYTES).cloned().unwrap_or_default(),
-			unfinished_uploads: counters
-				.get(UNFINISHED_UPLOADS)
-				.cloned()
-				.unwrap_or_default(),
+			objects: *counters.get(OBJECTS).unwrap_or(&0),
+			bytes: *counters.get(BYTES).unwrap_or(&0),
+			unfinished_uploads: *counters.get(UNFINISHED_UPLOADS).unwrap_or(&0),
+			unfinished_multipart_uploads: *mpu_counters.get(mpu_table::UPLOADS).unwrap_or(&0),
+			unfinished_multipart_upload_parts: *mpu_counters.get(mpu_table::PARTS).unwrap_or(&0),
+			unfinished_multipart_upload_bytes: *mpu_counters.get(mpu_table::BYTES).unwrap_or(&0),
 			quotas: ApiBucketQuotas {
 				max_size: quotas.max_size,
 				max_objects: quotas.max_objects,
@@ -235,6 +244,9 @@ struct GetBucketInfoResult {
 	objects: i64,
 	bytes: i64,
 	unfinished_uploads: i64,
+	unfinished_multipart_uploads: i64,
+	unfinished_multipart_upload_parts: i64,
+	unfinished_multipart_upload_bytes: i64,
 	quotas: ApiBucketQuotas,
 }
 

src/api/admin/cluster.rs

@@ -1,14 +1,13 @@
-use std::collections::HashMap;
 use std::net::SocketAddr;
 use std::sync::Arc;
 
-use hyper::{Body, Request, Response, StatusCode};
+use hyper::{Body, Request, Response};
 use serde::{Deserialize, Serialize};
 
 use garage_util::crdt::*;
 use garage_util::data::*;
 
-use garage_rpc::layout::*;
+use garage_rpc::layout;
 
 use garage_model::garage::Garage;
 
@@ -26,26 +25,37 @@ pub async fn handle_get_cluster_status(garage: &Arc<Garage>) -> Result<Response<
 			.system
 			.get_known_nodes()
 			.into_iter()
-			.map(|i| {
-				(
-					hex::encode(i.id),
-					KnownNodeResp {
-						addr: i.addr,
-						is_up: i.is_up,
-						last_seen_secs_ago: i.last_seen_secs_ago,
-						hostname: i.status.hostname,
-					},
-				)
+			.map(|i| KnownNodeResp {
+				id: hex::encode(i.id),
+				addr: i.addr,
+				is_up: i.is_up,
+				last_seen_secs_ago: i.last_seen_secs_ago,
+				hostname: i.status.hostname,
 			})
 			.collect(),
-		layout: get_cluster_layout(garage),
+		layout: format_cluster_layout(&garage.system.get_cluster_layout()),
 	};
 
 	Ok(json_ok_response(&res)?)
 }
 
 pub async fn handle_get_cluster_health(garage: &Arc<Garage>) -> Result<Response<Body>, Error> {
+	use garage_rpc::system::ClusterHealthStatus;
 	let health = garage.system.health();
+	let health = ClusterHealth {
+		status: match health.status {
+			ClusterHealthStatus::Healthy => "healthy",
+			ClusterHealthStatus::Degraded => "degraded",
+			ClusterHealthStatus::Unavailable => "unavailable",
+		},
+		known_nodes: health.known_nodes,
+		connected_nodes: health.connected_nodes,
+		storage_nodes: health.storage_nodes,
+		storage_nodes_ok: health.storage_nodes_ok,
+		partitions: health.partitions,
+		partitions_quorum: health.partitions_quorum,
+		partitions_all_ok: health.partitions_all_ok,
+	};
 	Ok(json_ok_response(&health)?)
 }
 
@@ -74,33 +84,68 @@ pub async fn handle_connect_cluster_nodes(
 }
 
 pub async fn handle_get_cluster_layout(garage: &Arc<Garage>) -> Result<Response<Body>, Error> {
-	let res = get_cluster_layout(garage);
+	let res = format_cluster_layout(&garage.system.get_cluster_layout());
 
 	Ok(json_ok_response(&res)?)
 }
 
-fn get_cluster_layout(garage: &Arc<Garage>) -> GetClusterLayoutResponse {
-	let layout = garage.system.get_cluster_layout();
+fn format_cluster_layout(layout: &layout::ClusterLayout) -> GetClusterLayoutResponse {
+	let roles = layout
+		.roles
+		.items()
+		.iter()
+		.filter_map(|(k, _, v)| v.0.clone().map(|x| (k, x)))
+		.map(|(k, v)| NodeRoleResp {
+			id: hex::encode(k),
+			zone: v.zone.clone(),
+			capacity: v.capacity,
+			tags: v.tags.clone(),
+		})
+		.collect::<Vec<_>>();
+
+	let staged_role_changes = layout
+		.staging_roles
+		.items()
+		.iter()
+		.filter(|(k, _, v)| layout.roles.get(k) != Some(v))
+		.map(|(k, _, v)| match &v.0 {
+			None => NodeRoleChange {
+				id: hex::encode(k),
+				action: NodeRoleChangeEnum::Remove { remove: true },
+			},
+			Some(r) => NodeRoleChange {
+				id: hex::encode(k),
+				action: NodeRoleChangeEnum::Update {
+					zone: r.zone.clone(),
+					capacity: r.capacity,
+					tags: r.tags.clone(),
+				},
+			},
+		})
+		.collect::<Vec<_>>();
 
 	GetClusterLayoutResponse {
 		version: layout.version,
-		roles: layout
-			.roles
-			.items()
-			.iter()
-			.filter(|(_, _, v)| v.0.is_some())
-			.map(|(k, _, v)| (hex::encode(k), v.0.clone()))
-			.collect(),
-		staged_role_changes: layout
-			.staging
-			.items()
-			.iter()
-			.filter(|(k, _, v)| layout.roles.get(k) != Some(v))
-			.map(|(k, _, v)| (hex::encode(k), v.0.clone()))
-			.collect(),
+		roles,
+		staged_role_changes,
 	}
 }
 
+// ----
+
+#[derive(Debug, Clone, Copy, Serialize)]
+#[serde(rename_all = "camelCase")]
+pub struct ClusterHealth {
+	status: &'static str,
+	known_nodes: usize,
+	connected_nodes: usize,
+	storage_nodes: usize,
+	storage_nodes_ok: usize,
+	partitions: usize,
+	partitions_quorum: usize,
+	partitions_all_ok: usize,
+}
+
 #[derive(Serialize)]
 #[serde(rename_all = "camelCase")]
 struct GetClusterStatusResponse {
@@ -109,11 +154,19 @@ struct GetClusterStatusResponse {
 	garage_features: Option<&'static [&'static str]>,
 	rust_version: &'static str,
 	db_engine: String,
-	known_nodes: HashMap<String, KnownNodeResp>,
+	known_nodes: Vec<KnownNodeResp>,
 	layout: GetClusterLayoutResponse,
 }
 
 #[derive(Serialize)]
+#[serde(rename_all = "camelCase")]
+struct ApplyClusterLayoutResponse {
+	message: Vec<String>,
+	layout: GetClusterLayoutResponse,
+}
+
+#[derive(Serialize)]
+#[serde(rename_all = "camelCase")]
 struct ConnectClusterNodesResponse {
 	success: bool,
 	error: Option<String>,
@@ -123,18 +176,31 @@ struct ConnectClusterNodesResponse {
 #[serde(rename_all = "camelCase")]
 struct GetClusterLayoutResponse {
 	version: u64,
-	roles: HashMap<String, Option<NodeRole>>,
-	staged_role_changes: HashMap<String, Option<NodeRole>>,
+	roles: Vec<NodeRoleResp>,
+	staged_role_changes: Vec<NodeRoleChange>,
 }
 
 #[derive(Serialize)]
+#[serde(rename_all = "camelCase")]
+struct NodeRoleResp {
+	id: String,
+	zone: String,
+	capacity: Option<u64>,
+	tags: Vec<String>,
+}
+
+#[derive(Serialize)]
+#[serde(rename_all = "camelCase")]
 struct KnownNodeResp {
+	id: String,
 	addr: SocketAddr,
 	is_up: bool,
 	last_seen_secs_ago: Option<u64>,
 	hostname: String,
 }
 
+// ---- update functions ----
+
 pub async fn handle_update_cluster_layout(
 	garage: &Arc<Garage>,
 	req: Request<Body>,
@@ -144,22 +210,35 @@ pub async fn handle_update_cluster_layout(
 	let mut layout = garage.system.get_cluster_layout();
 
 	let mut roles = layout.roles.clone();
-	roles.merge(&layout.staging);
+	roles.merge(&layout.staging_roles);
 
-	for (node, role) in updates {
-		let node = hex::decode(node).ok_or_bad_request("Invalid node identifier")?;
+	for change in updates {
+		let node = hex::decode(&change.id).ok_or_bad_request("Invalid node identifier")?;
 		let node = Uuid::try_from(&node).ok_or_bad_request("Invalid node identifier")?;
 
+		let new_role = match change.action {
+			NodeRoleChangeEnum::Remove { remove: true } => None,
+			NodeRoleChangeEnum::Update {
+				zone,
+				capacity,
+				tags,
+			} => Some(layout::NodeRole {
+				zone,
+				capacity,
+				tags,
+			}),
+			_ => return Err(Error::bad_request("Invalid layout change")),
+		};
+
 		layout
-			.staging
-			.merge(&roles.update_mutator(node, NodeRoleV(role)));
+			.staging_roles
+			.merge(&roles.update_mutator(node, layout::NodeRoleV(new_role)));
 	}
 
 	garage.system.update_cluster_layout(&layout).await?;
 
-	Ok(Response::builder()
-		.status(StatusCode::NO_CONTENT)
-		.body(Body::empty())?)
+	let res = format_cluster_layout(&layout);
+	Ok(json_ok_response(&res)?)
 }
 
 pub async fn handle_apply_cluster_layout(
@@ -169,12 +248,15 @@ pub async fn handle_apply_cluster_layout(
 	let param = parse_json_body::<ApplyRevertLayoutRequest>(req).await?;
 
 	let layout = garage.system.get_cluster_layout();
-	let layout = layout.apply_staged_changes(Some(param.version))?;
+	let (layout, msg) = layout.apply_staged_changes(Some(param.version))?;
+
 	garage.system.update_cluster_layout(&layout).await?;
 
-	Ok(Response::builder()
-		.status(StatusCode::NO_CONTENT)
-		.body(Body::empty())?)
+	let res = ApplyClusterLayoutResponse {
+		message: msg,
+		layout: format_cluster_layout(&layout),
+	};
+	Ok(json_ok_response(&res)?)
 }
 
 pub async fn handle_revert_cluster_layout(
@@ -187,14 +269,39 @@ pub async fn handle_revert_cluster_layout(
 	let layout = layout.revert_staged_changes(Some(param.version))?;
 	garage.system.update_cluster_layout(&layout).await?;
 
-	Ok(Response::builder()
-		.status(StatusCode::NO_CONTENT)
-		.body(Body::empty())?)
+	let res = format_cluster_layout(&layout);
+	Ok(json_ok_response(&res)?)
 }
 
-type UpdateClusterLayoutRequest = HashMap<String, Option<NodeRole>>;
+// ----
+
+type UpdateClusterLayoutRequest = Vec<NodeRoleChange>;
 
 #[derive(Deserialize)]
+#[serde(rename_all = "camelCase")]
 struct ApplyRevertLayoutRequest {
 	version: u64,
 }
+
+// ----
+
+#[derive(Serialize, Deserialize)]
+#[serde(rename_all = "camelCase")]
+struct NodeRoleChange {
+	id: String,
+	#[serde(flatten)]
+	action: NodeRoleChangeEnum,
+}
+
+#[derive(Serialize, Deserialize)]
+#[serde(untagged)]
+enum NodeRoleChangeEnum {
+	#[serde(rename_all = "camelCase")]
+	Remove { remove: bool },
+	#[serde(rename_all = "camelCase")]
+	Update {
+		zone: String,
+		capacity: Option<u64>,
+		tags: Vec<String>,
+	},
+}

src/api/admin/key.rs

@@ -10,7 +10,7 @@ use garage_model::garage::Garage;
 use garage_model::key_table::*;
 
 use crate::admin::error::*;
-use crate::helpers::{json_ok_response, parse_json_body};
+use crate::helpers::{is_default, json_ok_response, parse_json_body};
 
 pub async fn handle_list_keys(garage: &Arc<Garage>) -> Result<Response<Body>, Error> {
 	let res = garage
@@ -34,6 +34,7 @@ pub async fn handle_list_keys(garage: &Arc<Garage>) -> Result<Response<Body>, Er
 }
 
 #[derive(Serialize)]
+#[serde(rename_all = "camelCase")]
 struct ListKeyResultItem {
 	id: String,
 	name: String,
@@ -43,6 +44,7 @@ pub async fn handle_get_key_info(
 	garage: &Arc<Garage>,
 	id: Option<String>,
 	search: Option<String>,
+	show_secret_key: bool,
 ) -> Result<Response<Body>, Error> {
 	let key = if let Some(id) = id {
 		garage.key_helper().get_existing_key(&id).await?
@@ -55,7 +57,7 @@ pub async fn handle_get_key_info(
 		unreachable!();
 	};
 
-	key_info_results(garage, key).await
+	key_info_results(garage, key, show_secret_key).await
 }
 
 pub async fn handle_create_key(
@@ -64,15 +66,16 @@ pub async fn handle_create_key(
 ) -> Result<Response<Body>, Error> {
 	let req = parse_json_body::<CreateKeyRequest>(req).await?;
 
-	let key = Key::new(&req.name);
+	let key = Key::new(req.name.as_deref().unwrap_or("Unnamed key"));
 	garage.key_table.insert(&key).await?;
 
-	key_info_results(garage, key).await
+	key_info_results(garage, key, true).await
 }
 
 #[derive(Deserialize)]
+#[serde(rename_all = "camelCase")]
 struct CreateKeyRequest {
-	name: String,
+	name: Option<String>,
 }
 
 pub async fn handle_import_key(
@@ -86,10 +89,15 @@ pub async fn handle_import_key(
 		return Err(Error::KeyAlreadyExists(req.access_key_id.to_string()));
 	}
 
-	let imported_key = Key::import(&req.access_key_id, &req.secret_access_key, &req.name);
+	let imported_key = Key::import(
+		&req.access_key_id,
+		&req.secret_access_key,
+		req.name.as_deref().unwrap_or("Imported key"),
+	)
+	.ok_or_bad_request("Invalid key format")?;
 	garage.key_table.insert(&imported_key).await?;
 
-	key_info_results(garage, imported_key).await
+	key_info_results(garage, imported_key, false).await
 }
 
 #[derive(Deserialize)]
@@ -97,7 +105,7 @@ pub async fn handle_import_key(
 struct ImportKeyRequest {
 	access_key_id: String,
 	secret_access_key: String,
-	name: String,
+	name: Option<String>,
 }
 
 pub async fn handle_update_key(
@@ -127,10 +135,11 @@ pub async fn handle_update_key(
 
 	garage.key_table.insert(&key).await?;
 
-	key_info_results(garage, key).await
+	key_info_results(garage, key, false).await
 }
 
 #[derive(Deserialize)]
+#[serde(rename_all = "camelCase")]
 struct UpdateKeyRequest {
 	name: Option<String>,
 	allow: Option<KeyPerm>,
@@ -149,7 +158,11 @@ pub async fn handle_delete_key(garage: &Arc<Garage>, id: String) -> Result<Respo
 		.body(Body::empty())?)
 }
 
-async fn key_info_results(garage: &Arc<Garage>, key: Key) -> Result<Response<Body>, Error> {
+async fn key_info_results(
+	garage: &Arc<Garage>,
+	key: Key,
+	show_secret: bool,
+) -> Result<Response<Body>, Error> {
 	let mut relevant_buckets = HashMap::new();
 
 	let key_state = key.state.as_option().unwrap();
@@ -178,7 +191,11 @@ async fn key_info_results(garage: &Arc<Garage>, key: Key) -> Result<Response<Bod
 	let res = GetKeyInfoResult {
 		name: key_state.name.get().clone(),
 		access_key_id: key.key_id.clone(),
-		secret_access_key: key_state.secret_key.clone(),
+		secret_access_key: if show_secret {
+			Some(key_state.secret_key.clone())
+		} else {
+			None
+		},
 		permissions: KeyPerm {
 			create_bucket: *key_state.allow_create_bucket.get(),
 		},
@@ -224,7 +241,8 @@ async fn key_info_results(garage: &Arc<Garage>, key: Key) -> Result<Response<Bod
 struct GetKeyInfoResult {
 	name: String,
 	access_key_id: String,
-	secret_access_key: String,
+	#[serde(skip_serializing_if = "is_default")]
+	secret_access_key: Option<String>,
 	permissions: KeyPerm,
 	buckets: Vec<KeyInfoBucketResult>,
 }
@@ -246,6 +264,7 @@ struct KeyInfoBucketResult {
 }
 
 #[derive(Serialize, Deserialize, Default)]
+#[serde(rename_all = "camelCase")]
 pub(crate) struct ApiBucketKeyPerm {
 	#[serde(default)]
 	pub(crate) read: bool,

src/api/admin/mod.rs

@@ -1,6 +1,7 @@
 pub mod api_server;
 mod error;
-mod router;
+mod router_v0;
+mod router_v1;
 
 mod bucket;
 mod cluster;

src/api/admin/router_v0.rs

@@ -5,12 +5,6 @@ use hyper::{Method, Request};
 use crate::admin::error::*;
 use crate::router_macros::*;
 
-pub enum Authorization {
-	None,
-	MetricsToken,
-	AdminToken,
-}
-
 router_match! {@func
 
 /// List of all Admin API endpoints.
@@ -134,15 +128,6 @@ impl Endpoint {
 
 		Ok(res)
 	}
-	/// Get the kind of authorization which is required to perform the operation.
-	pub fn authorization_type(&self) -> Authorization {
-		match self {
-			Self::Health => Authorization::None,
-			Self::CheckDomain => Authorization::None,
-			Self::Metrics => Authorization::MetricsToken,
-			_ => Authorization::AdminToken,
-		}
-	}
 }
 
 generateQueryParameters! {

src/api/admin/router_v1.rs

@@ -0,0 +1,235 @@
+use std::borrow::Cow;
+
+use hyper::{Method, Request};
+
+use crate::admin::error::*;
+use crate::admin::router_v0;
+use crate::router_macros::*;
+
+pub enum Authorization {
+	None,
+	MetricsToken,
+	AdminToken,
+}
+
+router_match! {@func
+
+/// List of all Admin API endpoints.
+#[derive(Debug, Clone, PartialEq, Eq)]
+pub enum Endpoint {
+	Options,
+	CheckDomain,
+	Health,
+	Metrics,
+	GetClusterStatus,
+	GetClusterHealth,
+	ConnectClusterNodes,
+	// Layout
+	GetClusterLayout,
+	UpdateClusterLayout,
+	ApplyClusterLayout,
+	RevertClusterLayout,
+	// Keys
+	ListKeys,
+	CreateKey,
+	ImportKey,
+	GetKeyInfo {
+		id: Option<String>,
+		search: Option<String>,
+		show_secret_key: Option<String>,
+	},
+	DeleteKey {
+		id: String,
+	},
+	UpdateKey {
+		id: String,
+	},
+	// Buckets
+	ListBuckets,
+	CreateBucket,
+	GetBucketInfo {
+		id: Option<String>,
+		global_alias: Option<String>,
+	},
+	DeleteBucket {
+		id: String,
+	},
+	UpdateBucket {
+		id: String,
+	},
+	// Bucket-Key Permissions
+	BucketAllowKey,
+	BucketDenyKey,
+	// Bucket aliases
+	GlobalAliasBucket {
+		id: String,
+		alias: String,
+	},
+	GlobalUnaliasBucket {
+		id: String,
+		alias: String,
+	},
+	LocalAliasBucket {
+		id: String,
+		access_key_id: String,
+		alias: String,
+	},
+	LocalUnaliasBucket {
+		id: String,
+		access_key_id: String,
+		alias: String,
+	},
+}}
+
+impl Endpoint {
+	/// Determine which S3 endpoint a request is for using the request, and a bucket which was
+	/// possibly extracted from the Host header.
+	/// Returns Self plus bucket name, if endpoint is not Endpoint::ListBuckets
+	pub fn from_request<T>(req: &Request<T>) -> Result<Self, Error> {
+		let uri = req.uri();
+		let path = uri.path();
+		let query = uri.query();
+
+		let mut query = QueryParameters::from_query(query.unwrap_or_default())?;
+
+		let res = router_match!(@gen_path_parser (req.method(), path, query) [
+			OPTIONS _ => Options,
+			GET "/check" => CheckDomain,
+			GET "/health" => Health,
+			GET "/metrics" => Metrics,
+			GET "/v1/status" => GetClusterStatus,
+			GET "/v1/health" => GetClusterHealth,
+			POST "/v1/connect" => ConnectClusterNodes,
+			// Layout endpoints
+			GET "/v1/layout" => GetClusterLayout,
+			POST "/v1/layout" => UpdateClusterLayout,
+			POST "/v1/layout/apply" => ApplyClusterLayout,
+			POST "/v1/layout/revert" => RevertClusterLayout,
+			// API key endpoints
+			GET "/v1/key" if id => GetKeyInfo (query_opt::id, query_opt::search, query_opt::show_secret_key),
+			GET "/v1/key" if search => GetKeyInfo (query_opt::id, query_opt::search, query_opt::show_secret_key),
+			POST "/v1/key" if id => UpdateKey (query::id),
+			POST "/v1/key" => CreateKey,
+			POST "/v1/key/import" => ImportKey,
+			DELETE "/v1/key" if id => DeleteKey (query::id),
+			GET "/v1/key" => ListKeys,
+			// Bucket endpoints
+			GET "/v1/bucket" if id => GetBucketInfo (query_opt::id, query_opt::global_alias),
+			GET "/v1/bucket" if global_alias => GetBucketInfo (query_opt::id, query_opt::global_alias),
+			GET "/v1/bucket" => ListBuckets,
+			POST "/v1/bucket" => CreateBucket,
+			DELETE "/v1/bucket" if id => DeleteBucket (query::id),
+			PUT "/v1/bucket" if id => UpdateBucket (query::id),
+			// Bucket-key permissions
+			POST "/v1/bucket/allow" => BucketAllowKey,
+			POST "/v1/bucket/deny" => BucketDenyKey,
+			// Bucket aliases
+			PUT "/v1/bucket/alias/global" => GlobalAliasBucket (query::id, query::alias),
+			DELETE "/v1/bucket/alias/global" => GlobalUnaliasBucket (query::id, query::alias),
+			PUT "/v1/bucket/alias/local" => LocalAliasBucket (query::id, query::access_key_id, query::alias),
+			DELETE "/v1/bucket/alias/local" => LocalUnaliasBucket (query::id, query::access_key_id, query::alias),
+		]);
+
+		if let Some(message) = query.nonempty_message() {
+			debug!("Unused query parameter: {}", message)
+		}
+
+		Ok(res)
+	}
+	/// Some endpoints work exactly the same in their v1/ version as they did in their v0/ version.
+	/// For these endpoints, we can convert a v0/ call to its equivalent as if it was made using
+	/// its v1/ URL.
+	pub fn from_v0(v0_endpoint: router_v0::Endpoint) -> Result<Self, Error> {
+		match v0_endpoint {
+			// Cluster endpoints
+			router_v0::Endpoint::ConnectClusterNodes => Ok(Self::ConnectClusterNodes),
+			// - GetClusterStatus: response format changed
+			// - GetClusterHealth: response format changed
+
+			// Layout endpoints
+			router_v0::Endpoint::RevertClusterLayout => Ok(Self::RevertClusterLayout),
+			// - GetClusterLayout: response format changed
+			// - UpdateClusterLayout: query format changed
+			// - ApplyCusterLayout: response format changed
+
+			// Key endpoints
+			router_v0::Endpoint::ListKeys => Ok(Self::ListKeys),
+			router_v0::Endpoint::CreateKey => Ok(Self::CreateKey),
+			router_v0::Endpoint::GetKeyInfo { id, search } => Ok(Self::GetKeyInfo {
+				id,
+				search,
+				show_secret_key: Some("true".into()),
+			}),
+			router_v0::Endpoint::DeleteKey { id } => Ok(Self::DeleteKey { id }),
+			// - UpdateKey: response format changed (secret key no longer returned)
+
+			// Bucket endpoints
+			router_v0::Endpoint::GetBucketInfo { id, global_alias } => {
+				Ok(Self::GetBucketInfo { id, global_alias })
+			}
+			router_v0::Endpoint::ListBuckets => Ok(Self::ListBuckets),
+			router_v0::Endpoint::CreateBucket => Ok(Self::CreateBucket),
+			router_v0::Endpoint::DeleteBucket { id } => Ok(Self::DeleteBucket { id }),
+			router_v0::Endpoint::UpdateBucket { id } => Ok(Self::UpdateBucket { id }),
+
+			// Bucket-key permissions
+			router_v0::Endpoint::BucketAllowKey => Ok(Self::BucketAllowKey),
+			router_v0::Endpoint::BucketDenyKey => Ok(Self::BucketDenyKey),
+
+			// Bucket alias endpoints
+			router_v0::Endpoint::GlobalAliasBucket { id, alias } => {
+				Ok(Self::GlobalAliasBucket { id, alias })
+			}
+			router_v0::Endpoint::GlobalUnaliasBucket { id, alias } => {
+				Ok(Self::GlobalUnaliasBucket { id, alias })
+			}
+			router_v0::Endpoint::LocalAliasBucket {
+				id,
+				access_key_id,
+				alias,
+			} => Ok(Self::LocalAliasBucket {
+				id,
+				access_key_id,
+				alias,
+			}),
+			router_v0::Endpoint::LocalUnaliasBucket {
+				id,
+				access_key_id,
+				alias,
+			} => Ok(Self::LocalUnaliasBucket {
+				id,
+				access_key_id,
+				alias,
+			}),
+
+			// For endpoints that have different body content syntax, issue
+			// deprecation warning
+			_ => Err(Error::bad_request(format!(
+				"v0/ endpoint is no longer supported: {}",
+				v0_endpoint.name()
+			))),
+		}
+	}
+	/// Get the kind of authorization which is required to perform the operation.
+	pub fn authorization_type(&self) -> Authorization {
+		match self {
+			Self::Health => Authorization::None,
+			Self::CheckDomain => Authorization::None,
+			Self::Metrics => Authorization::MetricsToken,
+			_ => Authorization::AdminToken,
+		}
+	}
+}
+
+generateQueryParameters! {
+	keywords: [],
+	fields: [
+		"format" => format,
+		"id" => id,
+		"search" => search,
+		"globalAlias" => global_alias,
+		"alias" => alias,
+		"accessKeyId" => access_key_id,
+		"showSecretKey" => show_secret_key
+	]
+}

src/api/helpers.rs

@@ -152,6 +152,10 @@ pub fn json_ok_response<T: Serialize>(res: &T) -> Result<Response<Body>, Error>
 		.body(Body::from(resp_json))?)
 }
 
+pub fn is_default<T: Default + PartialEq>(v: &T) -> bool {
+	*v == T::default()
+}
+
 #[cfg(test)]
 mod tests {
 	use super::*;

src/api/router_macros.rs

@@ -26,6 +26,7 @@ macro_rules! router_match {
      $($meth:ident $path:pat $(if $required:ident)? => $api:ident $(($($conv:ident :: $param:ident),*))?,)*
      ]) => {{
         {
+            #[allow(unused_parens)]
             match ($method, $reqpath) {
                 $(
                     (&Method::$meth, $path) if true $(&& $query.$required.is_some())? => Endpoint::$api {
@@ -128,12 +129,6 @@ macro_rules! router_match {
             }
         }
     };
-    (@if ($($cond:tt)+) then ($($then:tt)*) else ($($else:tt)*)) => {
-        $($then)*
-    };
-    (@if () then ($($then:tt)*) else ($($else:tt)*)) => {
-        $($else)*
-    };
 }
 
 /// This macro is used to generate part of the code in this module. It must be called only one, and

src/api/s3/api_server.rs

@@ -26,7 +26,9 @@ use crate::s3::copy::*;
 use crate::s3::cors::*;
 use crate::s3::delete::*;
 use crate::s3::get::*;
+use crate::s3::lifecycle::*;
 use crate::s3::list::*;
+use crate::s3::multipart::*;
 use crate::s3::post_object::handle_post_object;
 use crate::s3::put::*;
 use crate::s3::router::Endpoint;
@@ -256,7 +258,7 @@ impl ApiHandler for S3ApiServer {
 							bucket_name,
 							bucket_id,
 							delimiter: delimiter.map(|d| d.to_string()),
-							page_size: max_keys.map(|p| p.clamp(1, 1000)).unwrap_or(1000),
+							page_size: max_keys.unwrap_or(1000).clamp(1, 1000),
 							prefix: prefix.unwrap_or_default(),
 							urlencode_resp: encoding_type.map(|e| e == "url").unwrap_or(false),
 						},
@@ -286,7 +288,7 @@ impl ApiHandler for S3ApiServer {
 								bucket_name,
 								bucket_id,
 								delimiter: delimiter.map(|d| d.to_string()),
-								page_size: max_keys.map(|p| p.clamp(1, 1000)).unwrap_or(1000),
+								page_size: max_keys.unwrap_or(1000).clamp(1, 1000),
 								urlencode_resp: encoding_type.map(|e| e == "url").unwrap_or(false),
 								prefix: prefix.unwrap_or_default(),
 							},
@@ -319,7 +321,7 @@ impl ApiHandler for S3ApiServer {
 							bucket_name,
 							bucket_id,
 							delimiter: delimiter.map(|d| d.to_string()),
-							page_size: max_uploads.map(|p| p.clamp(1, 1000)).unwrap_or(1000),
+							page_size: max_uploads.unwrap_or(1000).clamp(1, 1000),
 							prefix: prefix.unwrap_or_default(),
 							urlencode_resp: encoding_type.map(|e| e == "url").unwrap_or(false),
 						},
@@ -342,8 +344,8 @@ impl ApiHandler for S3ApiServer {
 						bucket_id,
 						key,
 						upload_id,
-						part_number_marker: part_number_marker.map(|p| p.clamp(1, 10000)),
-						max_parts: max_parts.map(|p| p.clamp(1, 1000)).unwrap_or(1000),
+						part_number_marker: part_number_marker.map(|p| p.min(10000)),
+						max_parts: max_parts.unwrap_or(1000).clamp(1, 1000),
 					},
 				)
 				.await
@@ -353,14 +355,21 @@ impl ApiHandler for S3ApiServer {
 			}
 			Endpoint::GetBucketWebsite {} => handle_get_website(&bucket).await,
 			Endpoint::PutBucketWebsite {} => {
-				handle_put_website(garage, bucket_id, req, content_sha256).await
+				handle_put_website(garage, bucket.clone(), req, content_sha256).await
 			}
-			Endpoint::DeleteBucketWebsite {} => handle_delete_website(garage, bucket_id).await,
+			Endpoint::DeleteBucketWebsite {} => handle_delete_website(garage, bucket.clone()).await,
 			Endpoint::GetBucketCors {} => handle_get_cors(&bucket).await,
 			Endpoint::PutBucketCors {} => {
-				handle_put_cors(garage, bucket_id, req, content_sha256).await
+				handle_put_cors(garage, bucket.clone(), req, content_sha256).await
+			}
+			Endpoint::DeleteBucketCors {} => handle_delete_cors(garage, bucket.clone()).await,
+			Endpoint::GetBucketLifecycleConfiguration {} => handle_get_lifecycle(&bucket).await,
+			Endpoint::PutBucketLifecycleConfiguration {} => {
+				handle_put_lifecycle(garage, bucket.clone(), req, content_sha256).await
+			}
+			Endpoint::DeleteBucketLifecycle {} => {
+				handle_delete_lifecycle(garage, bucket.clone()).await
 			}
-			Endpoint::DeleteBucketCors {} => handle_delete_cors(garage, bucket_id).await,
 			endpoint => Err(Error::NotImplemented(endpoint.name().to_owned())),
 		};
 

src/api/s3/copy.rs

@@ -2,7 +2,7 @@ use std::pin::Pin;
 use std::sync::Arc;
 use std::time::{Duration, SystemTime, UNIX_EPOCH};
 
-use futures::{stream, stream::Stream, StreamExt, TryFutureExt};
+use futures::{stream, stream::Stream, StreamExt};
 use md5::{Digest as Md5Digest, Md5};
 
 use bytes::Bytes;
@@ -18,12 +18,14 @@ use garage_util::time::*;
 use garage_model::garage::Garage;
 use garage_model::key_table::Key;
 use garage_model::s3::block_ref_table::*;
+use garage_model::s3::mpu_table::*;
 use garage_model::s3::object_table::*;
 use garage_model::s3::version_table::*;
 
 use crate::helpers::parse_bucket_key;
 use crate::s3::error::*;
-use crate::s3::put::{decode_upload_id, get_headers};
+use crate::s3::multipart;
+use crate::s3::put::get_headers;
 use crate::s3::xml::{self as s3_xml, xmlns_tag};
 
 pub async fn handle_copy(
@@ -92,7 +94,10 @@ pub async fn handle_copy(
 			let tmp_dest_object_version = ObjectVersion {
 				uuid: new_uuid,
 				timestamp: new_timestamp,
-				state: ObjectVersionState::Uploading(new_meta.headers.clone()),
+				state: ObjectVersionState::Uploading {
+					headers: new_meta.headers.clone(),
+					multipart: false,
+				},
 			};
 			let tmp_dest_object = Object::new(
 				dest_bucket_id,
@@ -105,8 +110,14 @@ pub async fn handle_copy(
 			// this means that the BlockRef entries linked to this version cannot be
 			// marked as deleted (they are marked as deleted only if the Version
 			// doesn't exist or is marked as deleted).
-			let mut dest_version =
-				Version::new(new_uuid, dest_bucket_id, dest_key.to_string(), false);
+			let mut dest_version = Version::new(
+				new_uuid,
+				VersionBacklink::Object {
+					bucket_id: dest_bucket_id,
+					key: dest_key.to_string(),
+				},
+				false,
+			);
 			garage.version_table.insert(&dest_version).await?;
 
 			// Fill in block list for version and insert block refs
@@ -179,17 +190,13 @@ pub async fn handle_upload_part_copy(
 ) -> Result<Response<Body>, Error> {
 	let copy_precondition = CopyPreconditionHeaders::parse(req)?;
 
-	let dest_version_uuid = decode_upload_id(upload_id)?;
+	let dest_upload_id = multipart::decode_upload_id(upload_id)?;
 
 	let dest_key = dest_key.to_string();
-	let (source_object, dest_object) = futures::try_join!(
+	let (source_object, (_, _, mut dest_mpu)) = futures::try_join!(
 		get_copy_source(&garage, api_key, req),
-		garage
-			.object_table
-			.get(&dest_bucket_id, &dest_key)
-			.map_err(Error::from),
+		multipart::get_upload(&garage, &dest_bucket_id, &dest_key, &dest_upload_id)
 	)?;
-	let dest_object = dest_object.ok_or(Error::NoSuchKey)?;
 
 	let (source_object_version, source_version_data, source_version_meta) =
 		extract_source_info(&source_object)?;
@@ -217,15 +224,6 @@ pub async fn handle_upload_part_copy(
 		},
 	};
 
-	// Check destination version is indeed in uploading state
-	if !dest_object
-		.versions()
-		.iter()
-		.any(|v| v.uuid == dest_version_uuid && v.is_uploading())
-	{
-		return Err(Error::NoSuchUpload);
-	}
-
 	// Check source version is not inlined
 	match source_version_data {
 		ObjectVersionData::DeleteMarker => unreachable!(),
@@ -242,23 +240,11 @@ pub async fn handle_upload_part_copy(
 
 	// Fetch source versin with its block list,
 	// and destination version to check part hasn't yet been uploaded
-	let (source_version, dest_version) = futures::try_join!(
-		garage
-			.version_table
-			.get(&source_object_version.uuid, &EmptyKey),
-		garage.version_table.get(&dest_version_uuid, &EmptyKey),
-	)?;
-	let source_version = source_version.ok_or(Error::NoSuchKey)?;
-
-	// Check this part number hasn't yet been uploaded
-	if let Some(dv) = dest_version {
-		if dv.has_part_number(part_number) {
-			return Err(Error::bad_request(format!(
-				"Part number {} has already been uploaded",
-				part_number
-			)));
-		}
-	}
+	let source_version = garage
+		.version_table
+		.get(&source_object_version.uuid, &EmptyKey)
+		.await?
+		.ok_or(Error::NoSuchKey)?;
 
 	// We want to reuse blocks from the source version as much as possible.
 	// However, we still need to get the data from these blocks
@@ -299,6 +285,33 @@ pub async fn handle_upload_part_copy(
 		current_offset = block_end;
 	}
 
+	// Calculate the identity of destination part: timestamp, version id
+	let dest_version_id = gen_uuid();
+	let dest_mpu_part_key = MpuPartKey {
+		part_number,
+		timestamp: dest_mpu.next_timestamp(part_number),
+	};
+
+	// Create the uploaded part
+	dest_mpu.parts.clear();
+	dest_mpu.parts.put(
+		dest_mpu_part_key,
+		MpuPart {
+			version: dest_version_id,
+			etag: None,
+			size: None,
+		},
+	);
+	garage.mpu_table.insert(&dest_mpu).await?;
+
+	let mut dest_version = Version::new(
+		dest_version_id,
+		VersionBacklink::MultipartUpload {
+			upload_id: dest_upload_id,
+		},
+		false,
+	);
+
 	// Now, actually copy the blocks
 	let mut md5hasher = Md5::new();
 
@@ -348,8 +361,8 @@ pub async fn handle_upload_part_copy(
 		let must_upload = existing_block_hash.is_none();
 		let final_hash = existing_block_hash.unwrap_or_else(|| blake2sum(&data[..]));
 
-		let mut version = Version::new(dest_version_uuid, dest_bucket_id, dest_key.clone(), false);
-		version.blocks.put(
+		dest_version.blocks.clear();
+		dest_version.blocks.put(
 			VersionBlockKey {
 				part_number,
 				offset: current_offset,
@@ -363,7 +376,7 @@ pub async fn handle_upload_part_copy(
 
 		let block_ref = BlockRef {
 			block: final_hash,
-			version: dest_version_uuid,
+			version: dest_version_id,
 			deleted: false.into(),
 		};
 
@@ -378,23 +391,33 @@ pub async fn handle_upload_part_copy(
 					Ok(())
 				}
 			},
-			// Thing 2: we need to insert the block in the version
-			garage.version_table.insert(&version),
-			// Thing 3: we need to add a block reference
-			garage.block_ref_table.insert(&block_ref),
+			async {
+				// Thing 2: we need to insert the block in the version
+				garage.version_table.insert(&dest_version).await?;
+				// Thing 3: we need to add a block reference
+				garage.block_ref_table.insert(&block_ref).await
+			},
 			// Thing 4: we need to prefetch the next block
 			defragmenter.next(),
 		)?;
-		next_block = res.3;
+		next_block = res.2;
 	}
 
+	assert_eq!(current_offset, source_range.length);
+
 	let data_md5sum = md5hasher.finalize();
 	let etag = hex::encode(data_md5sum);
 
 	// Put the part's ETag in the Versiontable
-	let mut version = Version::new(dest_version_uuid, dest_bucket_id, dest_key.clone(), false);
-	version.parts_etags.put(part_number, etag.clone());
-	garage.version_table.insert(&version).await?;
+	dest_mpu.parts.put(
+		dest_mpu_part_key,
+		MpuPart {
+			version: dest_version_id,
+			etag: Some(etag.clone()),
+			size: Some(current_offset),
+		},
+	);
+	garage.mpu_table.insert(&dest_mpu).await?;
 
 	// LGTM
 	let resp_xml = s3_xml::to_xml_with_header(&CopyPartResult {

src/api/s3/cors.rs

@@ -44,14 +44,11 @@ pub async fn handle_get_cors(bucket: &Bucket) -> Result<Response<Body>, Error> {
 
 pub async fn handle_delete_cors(
 	garage: Arc<Garage>,
-	bucket_id: Uuid,
+	mut bucket: Bucket,
 ) -> Result<Response<Body>, Error> {
-	let mut bucket = garage
-		.bucket_helper()
-		.get_existing_bucket(bucket_id)
-		.await?;
-
-	let param = bucket.params_mut().unwrap();
+	let param = bucket
+		.params_mut()
+		.ok_or_internal_error("Bucket should not be deleted at this point")?;
 
 	param.cors_config.update(None);
 	garage.bucket_table.insert(&bucket).await?;
@@ -63,7 +60,7 @@ pub async fn handle_delete_cors(
 
 pub async fn handle_put_cors(
 	garage: Arc<Garage>,
-	bucket_id: Uuid,
+	mut bucket: Bucket,
 	req: Request<Body>,
 	content_sha256: Option<Hash>,
 ) -> Result<Response<Body>, Error> {
@@ -73,12 +70,9 @@ pub async fn handle_put_cors(
 		verify_signed_content(content_sha256, &body[..])?;
 	}
 
-	let mut bucket = garage
-		.bucket_helper()
-		.get_existing_bucket(bucket_id)
-		.await?;
-
-	let param = bucket.params_mut().unwrap();
+	let param = bucket
+		.params_mut()
+		.ok_or_internal_error("Bucket should not be deleted at this point")?;
 
 	let conf: CorsConfiguration = from_reader(&body as &[u8])?;
 	conf.validate()?;

src/api/s3/delete.rs

@@ -3,12 +3,12 @@ use std::sync::Arc;
 use hyper::{Body, Request, Response, StatusCode};
 
 use garage_util::data::*;
-use garage_util::time::*;
 
 use garage_model::garage::Garage;
 use garage_model::s3::object_table::*;
 
 use crate::s3::error::*;
+use crate::s3::put::next_timestamp;
 use crate::s3::xml as s3_xml;
 use crate::signature::verify_signed_content;
 
@@ -23,40 +23,36 @@ async fn handle_delete_internal(
 		.await?
 		.ok_or(Error::NoSuchKey)?; // No need to delete
 
-	let interesting_versions = object.versions().iter().filter(|v| {
-		!matches!(
-			v.state,
-			ObjectVersionState::Aborted
-				| ObjectVersionState::Complete(ObjectVersionData::DeleteMarker)
-		)
-	});
+	let del_timestamp = next_timestamp(Some(&object));
+	let del_uuid = gen_uuid();
 
-	let mut version_to_delete = None;
-	let mut timestamp = now_msec();
-	for v in interesting_versions {
-		if v.timestamp + 1 > timestamp || version_to_delete.is_none() {
-			version_to_delete = Some(v.uuid);
+	let deleted_version = object
+		.versions()
+		.iter()
+		.rev()
+		.find(|v| !matches!(&v.state, ObjectVersionState::Aborted))
+		.or_else(|| object.versions().iter().rev().next());
+	let deleted_version = match deleted_version {
+		Some(dv) => dv.uuid,
+		None => {
+			warn!("Object has no versions: {:?}", object);
+			Uuid::from([0u8; 32])
 		}
-		timestamp = std::cmp::max(timestamp, v.timestamp + 1);
-	}
-
-	let deleted_version = version_to_delete.ok_or(Error::NoSuchKey)?;
-
-	let version_uuid = gen_uuid();
+	};
 
 	let object = Object::new(
 		bucket_id,
 		key.into(),
 		vec![ObjectVersion {
-			uuid: version_uuid,
-			timestamp,
+			uuid: del_uuid,
+			timestamp: del_timestamp,
 			state: ObjectVersionState::Complete(ObjectVersionData::DeleteMarker),
 		}],
 	);
 
 	garage.object_table.insert(&object).await?;
 
-	Ok((deleted_version, version_uuid))
+	Ok((deleted_version, del_uuid))
 }
 
 pub async fn handle_delete(

src/api/s3/get.rs

@@ -149,7 +149,6 @@ pub async fn handle_head(
 
 				let (part_offset, part_end) =
 					calculate_part_bounds(&version, pn).ok_or(Error::InvalidPart)?;
-				let n_parts = version.parts_etags.items().len();
 
 				Ok(object_headers(object_version, version_meta)
 					.header(CONTENT_LENGTH, format!("{}", part_end - part_offset))
@@ -162,7 +161,7 @@ pub async fn handle_head(
 							version_meta.size
 						),
 					)
-					.header(X_AMZ_MP_PARTS_COUNT, format!("{}", n_parts))
+					.header(X_AMZ_MP_PARTS_COUNT, format!("{}", version.n_parts()?))
 					.status(StatusCode::PARTIAL_CONTENT)
 					.body(Body::empty())?)
 			}
@@ -376,7 +375,6 @@ async fn handle_get_part(
 
 			let (begin, end) =
 				calculate_part_bounds(&version, part_number).ok_or(Error::InvalidPart)?;
-			let n_parts = version.parts_etags.items().len();
 
 			let body = body_from_blocks_range(garage, version.blocks.items(), begin, end);
 
@@ -386,7 +384,7 @@ async fn handle_get_part(
 					CONTENT_RANGE,
 					format!("bytes {}-{}/{}", begin, end - 1, version_meta.size),
 				)
-				.header(X_AMZ_MP_PARTS_COUNT, format!("{}", n_parts))
+				.header(X_AMZ_MP_PARTS_COUNT, format!("{}", version.n_parts()?))
 				.body(body)?)
 		}
 		_ => unreachable!(),

src/api/s3/lifecycle.rs

@@ -0,0 +1,401 @@
+use quick_xml::de::from_reader;
+use std::sync::Arc;
+
+use hyper::{Body, Request, Response, StatusCode};
+
+use serde::{Deserialize, Serialize};
+
+use crate::s3::error::*;
+use crate::s3::xml::{to_xml_with_header, xmlns_tag, IntValue, Value};
+use crate::signature::verify_signed_content;
+
+use garage_model::bucket_table::{
+	parse_lifecycle_date, Bucket, LifecycleExpiration as GarageLifecycleExpiration,
+	LifecycleFilter as GarageLifecycleFilter, LifecycleRule as GarageLifecycleRule,
+};
+use garage_model::garage::Garage;
+use garage_util::data::*;
+
+pub async fn handle_get_lifecycle(bucket: &Bucket) -> Result<Response<Body>, Error> {
+	let param = bucket
+		.params()
+		.ok_or_internal_error("Bucket should not be deleted at this point")?;
+
+	if let Some(lifecycle) = param.lifecycle_config.get() {
+		let wc = LifecycleConfiguration::from_garage_lifecycle_config(lifecycle);
+		let xml = to_xml_with_header(&wc)?;
+		Ok(Response::builder()
+			.status(StatusCode::OK)
+			.header(http::header::CONTENT_TYPE, "application/xml")
+			.body(Body::from(xml))?)
+	} else {
+		Ok(Response::builder()
+			.status(StatusCode::NO_CONTENT)
+			.body(Body::empty())?)
+	}
+}
+
+pub async fn handle_delete_lifecycle(
+	garage: Arc<Garage>,
+	mut bucket: Bucket,
+) -> Result<Response<Body>, Error> {
+	let param = bucket
+		.params_mut()
+		.ok_or_internal_error("Bucket should not be deleted at this point")?;
+
+	param.lifecycle_config.update(None);
+	garage.bucket_table.insert(&bucket).await?;
+
+	Ok(Response::builder()
+		.status(StatusCode::NO_CONTENT)
+		.body(Body::empty())?)
+}
+
+pub async fn handle_put_lifecycle(
+	garage: Arc<Garage>,
+	mut bucket: Bucket,
+	req: Request<Body>,
+	content_sha256: Option<Hash>,
+) -> Result<Response<Body>, Error> {
+	let body = hyper::body::to_bytes(req.into_body()).await?;
+
+	if let Some(content_sha256) = content_sha256 {
+		verify_signed_content(content_sha256, &body[..])?;
+	}
+
+	let param = bucket
+		.params_mut()
+		.ok_or_internal_error("Bucket should not be deleted at this point")?;
+
+	let conf: LifecycleConfiguration = from_reader(&body as &[u8])?;
+	let config = conf
+		.validate_into_garage_lifecycle_config()
+		.ok_or_bad_request("Invalid lifecycle configuration")?;
+
+	param.lifecycle_config.update(Some(config));
+	garage.bucket_table.insert(&bucket).await?;
+
+	Ok(Response::builder()
+		.status(StatusCode::OK)
+		.body(Body::empty())?)
+}
+
+// ---- SERIALIZATION AND DESERIALIZATION TO/FROM S3 XML ----
+
+#[derive(Debug, Serialize, Deserialize, PartialEq, Eq, PartialOrd, Ord)]
+pub struct LifecycleConfiguration {
+	#[serde(serialize_with = "xmlns_tag", skip_deserializing)]
+	pub xmlns: (),
+	#[serde(rename = "Rule")]
+	pub lifecycle_rules: Vec<LifecycleRule>,
+}
+
+#[derive(Debug, Serialize, Deserialize, PartialEq, Eq, PartialOrd, Ord)]
+pub struct LifecycleRule {
+	#[serde(rename = "ID")]
+	pub id: Option<Value>,
+	#[serde(rename = "Status")]
+	pub status: Value,
+	#[serde(rename = "Filter", default)]
+	pub filter: Option<Filter>,
+	#[serde(rename = "Expiration", default)]
+	pub expiration: Option<Expiration>,
+	#[serde(rename = "AbortIncompleteMultipartUpload", default)]
+	pub abort_incomplete_mpu: Option<AbortIncompleteMpu>,
+}
+
+#[derive(Debug, Serialize, Deserialize, PartialEq, Eq, PartialOrd, Ord, Default)]
+pub struct Filter {
+	#[serde(rename = "And")]
+	pub and: Option<Box<Filter>>,
+	#[serde(rename = "Prefix")]
+	pub prefix: Option<Value>,
+	#[serde(rename = "ObjectSizeGreaterThan")]
+	pub size_gt: Option<IntValue>,
+	#[serde(rename = "ObjectSizeLessThan")]
+	pub size_lt: Option<IntValue>,
+}
+
+#[derive(Debug, Serialize, Deserialize, PartialEq, Eq, PartialOrd, Ord)]
+pub struct Expiration {
+	#[serde(rename = "Days")]
+	pub days: Option<IntValue>,
+	#[serde(rename = "Date")]
+	pub at_date: Option<Value>,
+}
+
+#[derive(Debug, Serialize, Deserialize, PartialEq, Eq, PartialOrd, Ord)]
+pub struct AbortIncompleteMpu {
+	#[serde(rename = "DaysAfterInitiation")]
+	pub days: IntValue,
+}
+
+impl LifecycleConfiguration {
+	pub fn validate_into_garage_lifecycle_config(
+		self,
+	) -> Result<Vec<GarageLifecycleRule>, &'static str> {
+		let mut ret = vec![];
+		for rule in self.lifecycle_rules {
+			ret.push(rule.validate_into_garage_lifecycle_rule()?);
+		}
+		Ok(ret)
+	}
+
+	pub fn from_garage_lifecycle_config(config: &[GarageLifecycleRule]) -> Self {
+		Self {
+			xmlns: (),
+			lifecycle_rules: config
+				.iter()
+				.map(LifecycleRule::from_garage_lifecycle_rule)
+				.collect(),
+		}
+	}
+}
+
+impl LifecycleRule {
+	pub fn validate_into_garage_lifecycle_rule(self) -> Result<GarageLifecycleRule, &'static str> {
+		let enabled = match self.status.0.as_str() {
+			"Enabled" => true,
+			"Disabled" => false,
+			_ => return Err("invalid value for <Status>"),
+		};
+
+		let filter = self
+			.filter
+			.map(Filter::validate_into_garage_lifecycle_filter)
+			.transpose()?
+			.unwrap_or_default();
+
+		let abort_incomplete_mpu_days = self.abort_incomplete_mpu.map(|x| x.days.0 as usize);
+
+		let expiration = self
+			.expiration
+			.map(Expiration::validate_into_garage_lifecycle_expiration)
+			.transpose()?;
+
+		Ok(GarageLifecycleRule {
+			id: self.id.map(|x| x.0),
+			enabled,
+			filter,
+			abort_incomplete_mpu_days,
+			expiration,
+		})
+	}
+
+	pub fn from_garage_lifecycle_rule(rule: &GarageLifecycleRule) -> Self {
+		Self {
+			id: rule.id.as_deref().map(Value::from),
+			status: if rule.enabled {
+				Value::from("Enabled")
+			} else {
+				Value::from("Disabled")
+			},
+			filter: Filter::from_garage_lifecycle_filter(&rule.filter),
+			abort_incomplete_mpu: rule
+				.abort_incomplete_mpu_days
+				.map(|days| AbortIncompleteMpu {
+					days: IntValue(days as i64),
+				}),
+			expiration: rule
+				.expiration
+				.as_ref()
+				.map(Expiration::from_garage_lifecycle_expiration),
+		}
+	}
+}
+
+impl Filter {
+	pub fn count(&self) -> i32 {
+		fn count<T>(x: &Option<T>) -> i32 {
+			x.as_ref().map(|_| 1).unwrap_or(0)
+		}
+		count(&self.prefix) + count(&self.size_gt) + count(&self.size_lt)
+	}
+
+	pub fn validate_into_garage_lifecycle_filter(
+		self,
+	) -> Result<GarageLifecycleFilter, &'static str> {
+		if self.count() > 0 && self.and.is_some() {
+			Err("Filter tag cannot contain both <And> and another condition")
+		} else if let Some(and) = self.and {
+			if and.and.is_some() {
+				return Err("Nested <And> tags");
+			}
+			Ok(and.internal_into_garage_lifecycle_filter())
+		} else if self.count() > 1 {
+			Err("Multiple Filter conditions must be wrapped in an <And> tag")
+		} else {
+			Ok(self.internal_into_garage_lifecycle_filter())
+		}
+	}
+
+	fn internal_into_garage_lifecycle_filter(self) -> GarageLifecycleFilter {
+		GarageLifecycleFilter {
+			prefix: self.prefix.map(|x| x.0),
+			size_gt: self.size_gt.map(|x| x.0 as u64),
+			size_lt: self.size_lt.map(|x| x.0 as u64),
+		}
+	}
+
+	pub fn from_garage_lifecycle_filter(rule: &GarageLifecycleFilter) -> Option<Self> {
+		let filter = Filter {
+			and: None,
+			prefix: rule.prefix.as_deref().map(Value::from),
+			size_gt: rule.size_gt.map(|x| IntValue(x as i64)),
+			size_lt: rule.size_lt.map(|x| IntValue(x as i64)),
+		};
+		match filter.count() {
+			0 => None,
+			1 => Some(filter),
+			_ => Some(Filter {
+				and: Some(Box::new(filter)),
+				..Default::default()
+			}),
+		}
+	}
+}
+
+impl Expiration {
+	pub fn validate_into_garage_lifecycle_expiration(
+		self,
+	) -> Result<GarageLifecycleExpiration, &'static str> {
+		match (self.days, self.at_date) {
+			(Some(_), Some(_)) => Err("cannot have both <Days> and <Date> in <Expiration>"),
+			(None, None) => Err("<Expiration> must contain either <Days> or <Date>"),
+			(Some(days), None) => Ok(GarageLifecycleExpiration::AfterDays(days.0 as usize)),
+			(None, Some(date)) => {
+				parse_lifecycle_date(&date.0)?;
+				Ok(GarageLifecycleExpiration::AtDate(date.0))
+			}
+		}
+	}
+
+	pub fn from_garage_lifecycle_expiration(exp: &GarageLifecycleExpiration) -> Self {
+		match exp {
+			GarageLifecycleExpiration::AfterDays(days) => Expiration {
+				days: Some(IntValue(*days as i64)),
+				at_date: None,
+			},
+			GarageLifecycleExpiration::AtDate(date) => Expiration {
+				days: None,
+				at_date: Some(Value(date.to_string())),
+			},
+		}
+	}
+}
+
+#[cfg(test)]
+mod tests {
+	use super::*;
+
+	use quick_xml::de::from_str;
+
+	#[test]
+	fn test_deserialize_lifecycle_config() -> Result<(), Error> {
+		let message = r#"<?xml version="1.0" encoding="UTF-8"?>
+<LifecycleConfiguration xmlns="http://s3.amazonaws.com/doc/2006-03-01/">
+  <Rule>
+    <ID>id1</ID>
+    <Status>Enabled</Status>
+    <Filter>
+       <Prefix>documents/</Prefix>
+    </Filter>
+    <AbortIncompleteMultipartUpload>
+       <DaysAfterInitiation>7</DaysAfterInitiation>
+    </AbortIncompleteMultipartUpload>
+  </Rule>
+  <Rule>
+    <ID>id2</ID>
+    <Status>Enabled</Status>
+    <Filter>
+       <And>
+          <Prefix>logs/</Prefix>
+          <ObjectSizeGreaterThan>1000000</ObjectSizeGreaterThan>
+       </And>
+    </Filter>
+    <Expiration>
+      <Days>365</Days>
+    </Expiration>
+  </Rule>
+</LifecycleConfiguration>"#;
+		let conf: LifecycleConfiguration = from_str(message).unwrap();
+		let ref_value = LifecycleConfiguration {
+			xmlns: (),
+			lifecycle_rules: vec![
+				LifecycleRule {
+					id: Some("id1".into()),
+					status: "Enabled".into(),
+					filter: Some(Filter {
+						prefix: Some("documents/".into()),
+						..Default::default()
+					}),
+					expiration: None,
+					abort_incomplete_mpu: Some(AbortIncompleteMpu { days: IntValue(7) }),
+				},
+				LifecycleRule {
+					id: Some("id2".into()),
+					status: "Enabled".into(),
+					filter: Some(Filter {
+						and: Some(Box::new(Filter {
+							prefix: Some("logs/".into()),
+							size_gt: Some(IntValue(1000000)),
+							..Default::default()
+						})),
+						..Default::default()
+					}),
+					expiration: Some(Expiration {
+						days: Some(IntValue(365)),
+						at_date: None,
+					}),
+					abort_incomplete_mpu: None,
+				},
+			],
+		};
+		assert_eq! {
+			ref_value,
+			conf
+		};
+
+		let message2 = to_xml_with_header(&ref_value)?;
+
+		let cleanup = |c: &str| c.replace(char::is_whitespace, "");
+		assert_eq!(cleanup(message), cleanup(&message2));
+
+		// Check validation
+		let validated = ref_value
+			.validate_into_garage_lifecycle_config()
+			.ok_or_bad_request("invalid xml config")?;
+
+		let ref_config = vec![
+			GarageLifecycleRule {
+				id: Some("id1".into()),
+				enabled: true,
+				filter: GarageLifecycleFilter {
+					prefix: Some("documents/".into()),
+					..Default::default()
+				},
+				expiration: None,
+				abort_incomplete_mpu_days: Some(7),
+			},
+			GarageLifecycleRule {
+				id: Some("id2".into()),
+				enabled: true,
+				filter: GarageLifecycleFilter {
+					prefix: Some("logs/".into()),
+					size_gt: Some(1000000),
+					..Default::default()
+				},
+				expiration: Some(GarageLifecycleExpiration::AfterDays(365)),
+				abort_incomplete_mpu_days: None,
+			},
+		];
+		assert_eq!(validated, ref_config);
+
+		let message3 = to_xml_with_header(&LifecycleConfiguration::from_garage_lifecycle_config(
+			&validated,
+		))?;
+		assert_eq!(cleanup(message), cleanup(&message3));
+
+		Ok(())
+	}
+}

src/api/s3/list.rs

@@ -1,4 +1,3 @@
-use std::cmp::Ordering;
 use std::collections::{BTreeMap, BTreeSet};
 use std::iter::{Iterator, Peekable};
 use std::sync::Arc;
@@ -11,15 +10,15 @@ use garage_util::error::Error as GarageError;
 use garage_util::time::*;
 
 use garage_model::garage::Garage;
+use garage_model::s3::mpu_table::*;
 use garage_model::s3::object_table::*;
-use garage_model::s3::version_table::Version;
 
-use garage_table::{EmptyKey, EnumerationOrder};
+use garage_table::EnumerationOrder;
 
 use crate::encoding::*;
 use crate::helpers::key_after_prefix;
 use crate::s3::error::*;
-use crate::s3::put as s3_put;
+use crate::s3::multipart as s3_multipart;
 use crate::s3::xml as s3_xml;
 
 const DUMMY_NAME: &str = "Dummy Key";
@@ -176,7 +175,9 @@ pub async fn handle_list_multipart_upload(
 			t.get_range(
 				&bucket,
 				key,
-				Some(ObjectFilter::IsUploading),
+				Some(ObjectFilter::IsUploading {
+					check_multipart: Some(true),
+				}),
 				count,
 				EnumerationOrder::Forward,
 			)
@@ -272,24 +273,26 @@ pub async fn handle_list_parts(
 ) -> Result<Response<Body>, Error> {
 	debug!("ListParts {:?}", query);
 
-	let upload_id = s3_put::decode_upload_id(&query.upload_id)?;
+	let upload_id = s3_multipart::decode_upload_id(&query.upload_id)?;
 
-	let (object, version) = futures::try_join!(
-		garage.object_table.get(&query.bucket_id, &query.key),
-		garage.version_table.get(&upload_id, &EmptyKey),
-	)?;
+	let (_, _, mpu) =
+		s3_multipart::get_upload(&garage, &query.bucket_id, &query.key, &upload_id).await?;
 
-	let (info, next) = fetch_part_info(query, object, version, upload_id)?;
+	let (info, next) = fetch_part_info(query, &mpu)?;
 
 	let result = s3_xml::ListPartsResult {
 		xmlns: (),
+
+		// Query parameters
 		bucket: s3_xml::Value(query.bucket_name.to_string()),
 		key: s3_xml::Value(query.key.to_string()),
 		upload_id: s3_xml::Value(query.upload_id.to_string()),
 		part_number_marker: query.part_number_marker.map(|e| s3_xml::IntValue(e as i64)),
-		next_part_number_marker: next.map(|e| s3_xml::IntValue(e as i64)),
 		max_parts: s3_xml::IntValue(query.max_parts as i64),
-		is_truncated: s3_xml::Value(next.map(|_| "true").unwrap_or("false").to_string()),
+
+		// Result values
+		next_part_number_marker: next.map(|e| s3_xml::IntValue(e as i64)),
+		is_truncated: s3_xml::Value(format!("{}", next.is_some())),
 		parts: info
 			.iter()
 			.map(|part| s3_xml::PartItem {
@@ -299,6 +302,8 @@ pub async fn handle_list_parts(
 				size: s3_xml::IntValue(part.size as i64),
 			})
 			.collect(),
+
+		// Dummy result values (unsupported features)
 		initiator: s3_xml::Initiator {
 			display_name: s3_xml::Value(DUMMY_NAME.to_string()),
 			id: s3_xml::Value(DUMMY_KEY.to_string()),
@@ -335,8 +340,8 @@ struct UploadInfo {
 }
 
 #[derive(Debug, PartialEq)]
-struct PartInfo {
-	etag: String,
+struct PartInfo<'a> {
+	etag: &'a str,
 	timestamp: u64,
 	part_number: u64,
 	size: u64,
@@ -421,8 +426,10 @@ where
 		// Drop the first key if needed
 		// Only AfterKey requires it according to the S3 spec and our implem.
 		match (&cursor, iter.peek()) {
-			(RangeBegin::AfterKey { key }, Some(object)) if &object.key == key => iter.next(),
-			(_, _) => None,
+			(RangeBegin::AfterKey { key }, Some(object)) if &object.key == key => {
+				iter.next();
+			}
+			_ => (),
 		};
 
 		while let Some(object) = iter.peek() {
@@ -431,16 +438,22 @@ where
 				return Ok(None);
 			}
 
-			cursor = match acc.extract(query, &cursor, &mut iter) {
-				ExtractionResult::Extracted { key } => RangeBegin::AfterKey { key },
+			match acc.extract(query, &cursor, &mut iter) {
+				ExtractionResult::Extracted { key } => {
+					cursor = RangeBegin::AfterKey { key };
+				}
 				ExtractionResult::SkipTo { key, fallback_key } => {
-					RangeBegin::IncludingKey { key, fallback_key }
+					cursor = RangeBegin::IncludingKey { key, fallback_key };
 				}
 				ExtractionResult::FilledAtUpload { key, upload } => {
-					return Ok(Some(RangeBegin::AfterUpload { key, upload }))
+					return Ok(Some(RangeBegin::AfterUpload { key, upload }));
+				}
+				ExtractionResult::Filled => {
+					return Ok(Some(cursor));
+				}
+				ExtractionResult::NoMore => {
+					return Ok(None);
 				}
-				ExtractionResult::Filled => return Ok(Some(cursor)),
-				ExtractionResult::NoMore => return Ok(None),
 			};
 		}
 
@@ -456,107 +469,51 @@ where
 	}
 }
 
-fn fetch_part_info(
+fn fetch_part_info<'a>(
 	query: &ListPartsQuery,
-	object: Option<Object>,
-	version: Option<Version>,
-	upload_id: Uuid,
-) -> Result<(Vec<PartInfo>, Option<u64>), Error> {
-	// Check results
-	let object = object.ok_or(Error::NoSuchKey)?;
+	mpu: &'a MultipartUpload,
+) -> Result<(Vec<PartInfo<'a>>, Option<u64>), Error> {
+	assert!((1..=1000).contains(&query.max_parts)); // see s3/api_server.rs
 
-	let obj_version = object
-		.versions()
-		.iter()
-		.find(|v| v.uuid == upload_id && v.is_uploading())
-		.ok_or(Error::NoSuchUpload)?;
-
-	let version = version.ok_or(Error::NoSuchKey)?;
-
-	// Cut the beginning of our 2 vectors if required
-	let (etags, blocks) = match &query.part_number_marker {
-		Some(marker) => {
-			let next = marker + 1;
-
-			let part_idx = into_ok_or_err(
-				version
-					.parts_etags
-					.items()
-					.binary_search_by(|(part_num, _)| part_num.cmp(&next)),
-			);
-			let parts = &version.parts_etags.items()[part_idx..];
-
-			let block_idx = into_ok_or_err(
-				version
-					.blocks
-					.items()
-					.binary_search_by(|(vkey, _)| vkey.part_number.cmp(&next)),
-			);
-			let blocks = &version.blocks.items()[block_idx..];
-
-			(parts, blocks)
-		}
-		None => (version.parts_etags.items(), version.blocks.items()),
-	};
-
-	// Use the block vector to compute a (part_number, size) vector
-	let mut size = Vec::<(u64, u64)>::new();
-	blocks.iter().for_each(|(key, val)| {
-		let mut new_size = val.size;
-		match size.pop() {
-			Some((part_number, size)) if part_number == key.part_number => new_size += size,
-			Some(v) => size.push(v),
-			None => (),
-		}
-		size.push((key.part_number, new_size))
-	});
-
-	// Merge the etag vector and size vector to build a PartInfo vector
-	let max_parts = query.max_parts as usize;
-	let (mut etag_iter, mut size_iter) = (etags.iter().peekable(), size.iter().peekable());
-
-	let mut info = Vec::<PartInfo>::with_capacity(max_parts);
-
-	while info.len() < max_parts {
-		match (etag_iter.peek(), size_iter.peek()) {
-			(Some((ep, etag)), Some((sp, size))) => match ep.cmp(sp) {
-				Ordering::Less => {
-					debug!("ETag information ignored due to missing corresponding block information. Query: {:?}", query);
-					etag_iter.next();
+	// Parse multipart upload part list, removing parts not yet finished
+	// and failed part uploads that were overwritten
+	let mut parts: Vec<PartInfo<'a>> = Vec::with_capacity(mpu.parts.items().len());
+	for (pk, p) in mpu.parts.items().iter() {
+		if let (Some(etag), Some(size)) = (&p.etag, p.size) {
+			let part_info = PartInfo {
+				part_number: pk.part_number,
+				timestamp: pk.timestamp,
+				etag,
+				size,
+			};
+			match parts.last_mut() {
+				Some(lastpart) if lastpart.part_number == pk.part_number => {
+					*lastpart = part_info;
 				}
-				Ordering::Equal => {
-					info.push(PartInfo {
-						etag: etag.to_string(),
-						timestamp: obj_version.timestamp,
-						part_number: *ep,
-						size: *size,
-					});
-					etag_iter.next();
-					size_iter.next();
+				_ => {
+					parts.push(part_info);
 				}
-				Ordering::Greater => {
-					debug!("Block information ignored due to missing corresponding ETag information. Query: {:?}", query);
-					size_iter.next();
-				}
-			},
-			(None, None) => return Ok((info, None)),
-			_ => {
-				debug!(
-					"Additional block or ETag information ignored. Query: {:?}",
-					query
-				);
-				return Ok((info, None));
 			}
 		}
 	}
 
-	match info.last() {
-		Some(part_info) => {
-			let pagination = Some(part_info.part_number);
-			Ok((info, pagination))
-		}
-		None => Ok((info, None)),
+	// Cut the beginning if we have a marker
+	if let Some(marker) = &query.part_number_marker {
+		let next = marker + 1;
+		let part_idx = parts
+			.binary_search_by(|part| part.part_number.cmp(&next))
+			.unwrap_or_else(|x| x);
+		parts = parts.split_off(part_idx);
 	}
+
+	// Cut the end if we have too many parts
+	if parts.len() > query.max_parts as usize {
+		parts.truncate(query.max_parts as usize);
+		let pagination = Some(parts.last().unwrap().part_number);
+		return Ok((parts, pagination));
+	}
+
+	Ok((parts, None))
 }
 
 /*
@@ -570,8 +527,8 @@ fn fetch_part_info(
 /// This key can be the prefix in the base case, or intermediate
 /// points in the dataset if we are continuing a previous listing.
 impl ListObjectsQuery {
-	fn build_accumulator(&self) -> Accumulator<String, ObjectInfo> {
-		Accumulator::<String, ObjectInfo>::new(self.common.page_size)
+	fn build_accumulator(&self) -> ObjectAccumulator {
+		ObjectAccumulator::new(self.common.page_size)
 	}
 
 	fn begin(&self) -> Result<RangeBegin, Error> {
@@ -580,9 +537,10 @@ impl ListObjectsQuery {
 				// In V2 mode, the continuation token is defined as an opaque
 				// string in the spec, so we can do whatever we want with it.
 				// In our case, it is defined as either [ or ] (for include
+				// or exclude), followed by a base64-encoded string
 				// representing the key to start with.
-				(Some(token), _) => match &token[..1] {
-					"[" => Ok(RangeBegin::IncludingKey {
+				(Some(token), _) => match &token.get(..1) {
+					Some("[") => Ok(RangeBegin::IncludingKey {
 						key: String::from_utf8(
 							BASE64_STANDARD
 								.decode(token[1..].as_bytes())
@@ -590,7 +548,7 @@ impl ListObjectsQuery {
 						)?,
 						fallback_key: None,
 					}),
-					"]" => Ok(RangeBegin::AfterKey {
+					Some("]") => Ok(RangeBegin::AfterKey {
 						key: String::from_utf8(
 							BASE64_STANDARD
 								.decode(token[1..].as_bytes())
@@ -631,8 +589,8 @@ impl ListObjectsQuery {
 }
 
 impl ListMultipartUploadsQuery {
-	fn build_accumulator(&self) -> Accumulator<Uuid, UploadInfo> {
-		Accumulator::<Uuid, UploadInfo>::new(self.common.page_size)
+	fn build_accumulator(&self) -> UploadAccumulator {
+		UploadAccumulator::new(self.common.page_size)
 	}
 
 	fn begin(&self) -> Result<RangeBegin, Error> {
@@ -651,7 +609,7 @@ impl ListMultipartUploadsQuery {
 				}),
 				uuid => Ok(RangeBegin::AfterUpload {
 					key: key_marker.to_string(),
-					upload: s3_put::decode_upload_id(uuid)?,
+					upload: s3_multipart::decode_upload_id(uuid)?,
 				}),
 			},
 
@@ -716,6 +674,7 @@ impl<K: std::cmp::Ord, V> Accumulator<K, V> {
 			Some(p) => p,
 			None => return None,
 		};
+		assert!(pfx.starts_with(&query.prefix));
 
 		// Try to register this prefix
 		// If not possible, we can return early
@@ -726,8 +685,11 @@ impl<K: std::cmp::Ord, V> Accumulator<K, V> {
 		// We consume the whole common prefix from the iterator
 		let mut last_pfx_key = &object.key;
 		loop {
-			last_pfx_key = match objects.peek() {
-				Some(o) if o.key.starts_with(pfx) => &o.key,
+			match objects.peek() {
+				Some(o) if o.key.starts_with(pfx) => {
+					last_pfx_key = &o.key;
+					objects.next();
+				}
 				Some(_) => {
 					return Some(ExtractionResult::Extracted {
 						key: last_pfx_key.to_owned(),
@@ -743,8 +705,6 @@ impl<K: std::cmp::Ord, V> Accumulator<K, V> {
 					}
 				}
 			};
-
-			objects.next();
 		}
 	}
 
@@ -759,12 +719,11 @@ impl<K: std::cmp::Ord, V> Accumulator<K, V> {
 		}
 
 		// Otherwise, we need to check if we can add it
-		match self.is_full() {
-			true => false,
-			false => {
-				self.common_prefixes.insert(key);
-				true
-			}
+		if self.is_full() {
+			false
+		} else {
+			self.common_prefixes.insert(key);
+			true
 		}
 	}
 
@@ -772,12 +731,11 @@ impl<K: std::cmp::Ord, V> Accumulator<K, V> {
 		// It is impossible to add twice a key, this is an error
 		assert!(!self.keys.contains_key(&key));
 
-		match self.is_full() {
-			true => false,
-			false => {
-				self.keys.insert(key, value);
-				true
-			}
+		if self.is_full() {
+			false
+		} else {
+			self.keys.insert(key, value);
+			true
 		}
 	}
 }
@@ -794,6 +752,7 @@ impl ExtractAccumulator for ObjectAccumulator {
 		}
 
 		let object = objects.next().expect("This iterator can not be empty as it is checked earlier in the code. This is a logic bug, please report it.");
+		assert!(object.key.starts_with(&query.prefix));
 
 		let version = match object.versions().iter().find(|x| x.is_data()) {
 			Some(v) => v,
@@ -843,7 +802,7 @@ impl ExtractAccumulator for UploadAccumulator {
 		let mut uploads_for_key = object
 			.versions()
 			.iter()
-			.filter(|x| x.is_uploading())
+			.filter(|x| x.is_uploading(Some(true)))
 			.collect::<Vec<&ObjectVersion>>();
 
 		// S3 logic requires lexicographically sorted upload ids.
@@ -918,14 +877,6 @@ impl ExtractAccumulator for UploadAccumulator {
  * Utility functions
  */
 
-/// This is a stub for Result::into_ok_or_err that is not yet in Rust stable
-fn into_ok_or_err<T>(r: Result<T, T>) -> T {
-	match r {
-		Ok(r) => r,
-		Err(r) => r,
-	}
-}
-
 /// Returns the common prefix of the object given the query prefix and delimiter
 fn common_prefix<'a>(object: &'a Object, query: &ListQueryCommon) -> Option<&'a str> {
 	match &query.delimiter {
@@ -951,7 +902,6 @@ fn uriencode_maybe(s: &str, yes: bool) -> s3_xml::Value {
 #[cfg(test)]
 mod tests {
 	use super::*;
-	use garage_model::s3::version_table::*;
 	use garage_util::*;
 	use std::iter::FromIterator;
 
@@ -991,10 +941,13 @@ mod tests {
 		ObjectVersion {
 			uuid: Uuid::from(uuid),
 			timestamp: TS,
-			state: ObjectVersionState::Uploading(ObjectVersionHeaders {
-				content_type: "text/plain".to_string(),
-				other: BTreeMap::<String, String>::new(),
-			}),
+			state: ObjectVersionState::Uploading {
+				multipart: true,
+				headers: ObjectVersionHeaders {
+					content_type: "text/plain".to_string(),
+					other: BTreeMap::<String, String>::new(),
+				},
+			},
 		}
 	}
 
@@ -1169,83 +1122,77 @@ mod tests {
 		Ok(())
 	}
 
-	fn version() -> Version {
+	fn mpu() -> MultipartUpload {
 		let uuid = Uuid::from([0x08; 32]);
 
-		let blocks = vec![
+		let parts = vec![
 			(
-				VersionBlockKey {
+				MpuPartKey {
 					part_number: 1,
-					offset: 1,
+					timestamp: TS,
 				},
-				VersionBlock {
-					hash: uuid,
-					size: 3,
+				MpuPart {
+					version: uuid,
+					size: Some(3),
+					etag: Some("etag1".into()),
 				},
 			),
 			(
-				VersionBlockKey {
-					part_number: 1,
-					offset: 2,
-				},
-				VersionBlock {
-					hash: uuid,
-					size: 2,
-				},
-			),
-			(
-				VersionBlockKey {
+				MpuPartKey {
 					part_number: 2,
-					offset: 1,
+					timestamp: TS,
 				},
-				VersionBlock {
-					hash: uuid,
-					size: 8,
+				MpuPart {
+					version: uuid,
+					size: None,
+					etag: None,
 				},
 			),
 			(
-				VersionBlockKey {
+				MpuPartKey {
+					part_number: 3,
+					timestamp: TS,
+				},
+				MpuPart {
+					version: uuid,
+					size: Some(10),
+					etag: Some("etag2".into()),
+				},
+			),
+			(
+				MpuPartKey {
 					part_number: 5,
-					offset: 1,
+					timestamp: TS,
 				},
-				VersionBlock {
-					hash: uuid,
-					size: 7,
+				MpuPart {
+					version: uuid,
+					size: Some(7),
+					etag: Some("etag3".into()),
 				},
 			),
 			(
-				VersionBlockKey {
+				MpuPartKey {
 					part_number: 8,
-					offset: 1,
+					timestamp: TS,
 				},
-				VersionBlock {
-					hash: uuid,
-					size: 5,
+				MpuPart {
+					version: uuid,
+					size: Some(5),
+					etag: Some("etag4".into()),
 				},
 			),
 		];
-		let etags = vec![
-			(1, "etag1".to_string()),
-			(3, "etag2".to_string()),
-			(5, "etag3".to_string()),
-			(8, "etag4".to_string()),
-			(9, "etag5".to_string()),
-		];
 
-		Version {
-			bucket_id: uuid,
-			key: "a".to_string(),
-			uuid,
+		MultipartUpload {
+			upload_id: uuid,
+			timestamp: TS,
 			deleted: false.into(),
-			blocks: crdt::Map::<VersionBlockKey, VersionBlock>::from_iter(blocks),
-			parts_etags: crdt::Map::<u64, String>::from_iter(etags),
+			parts: crdt::Map::<MpuPartKey, MpuPart>::from_iter(parts),
+			bucket_id: uuid,
+			key: "a".into(),
 		}
 	}
 
-	fn obj() -> Object {
-		Object::new(bucket(), "d".to_string(), vec![objup_version([0x08; 32])])
-	}
-
 	#[test]
 	fn test_fetch_part_info() -> Result<(), Error> {
 		let uuid = Uuid::from([0x08; 32]);
@@ -1258,82 +1205,85 @@ mod tests {
 			max_parts: 2,
 		};
 
-		assert!(
-			fetch_part_info(&query, None, None, uuid).is_err(),
-			"No object and version should fail"
-		);
-		assert!(
-			fetch_part_info(&query, Some(obj()), None, uuid).is_err(),
-			"No version should faild"
-		);
-		assert!(
-			fetch_part_info(&query, None, Some(version()), uuid).is_err(),
-			"No object should fail"
-		);
+		let mpu = mpu();
 
 		// Start from the beginning but with limited size to trigger pagination
-		let (info, pagination) = fetch_part_info(&query, Some(obj()), Some(version()), uuid)?;
-		assert_eq!(pagination.unwrap(), 5);
+		let (info, pagination) = fetch_part_info(&query, &mpu)?;
+		assert_eq!(pagination.unwrap(), 3);
 		assert_eq!(
 			info,
 			vec![
 				PartInfo {
-					etag: "etag1".to_string(),
+					etag: "etag1",
 					timestamp: TS,
 					part_number: 1,
-					size: 5
+					size: 3
 				},
 				PartInfo {
-					etag: "etag3".to_string(),
+					etag: "etag2",
 					timestamp: TS,
-					part_number: 5,
-					size: 7
+					part_number: 3,
+					size: 10
 				},
 			]
 		);
 
 		// Use previous pagination to make a new request
 		query.part_number_marker = Some(pagination.unwrap());
-		let (info, pagination) = fetch_part_info(&query, Some(obj()), Some(version()), uuid)?;
+		let (info, pagination) = fetch_part_info(&query, &mpu)?;
 		assert!(pagination.is_none());
 		assert_eq!(
 			info,
-			vec![PartInfo {
-				etag: "etag4".to_string(),
-				timestamp: TS,
-				part_number: 8,
-				size: 5
-			},]
+			vec![
+				PartInfo {
+					etag: "etag3",
+					timestamp: TS,
+					part_number: 5,
+					size: 7
+				},
+				PartInfo {
+					etag: "etag4",
+					timestamp: TS,
+					part_number: 8,
+					size: 5
+				},
+			]
 		);
 
 		// Trying to access a part that is way larger than registered ones
 		query.part_number_marker = Some(9999);
-		let (info, pagination) = fetch_part_info(&query, Some(obj()), Some(version()), uuid)?;
+		let (info, pagination) = fetch_part_info(&query, &mpu)?;
 		assert!(pagination.is_none());
 		assert_eq!(info, vec![]);
 
 		// Try without any limitation
 		query.max_parts = 1000;
 		query.part_number_marker = None;
-		let (info, pagination) = fetch_part_info(&query, Some(obj()), Some(version()), uuid)?;
+		let (info, pagination) = fetch_part_info(&query, &mpu)?;
 		assert!(pagination.is_none());
 		assert_eq!(
 			info,
 			vec![
 				PartInfo {
-					etag: "etag1".to_string(),
+					etag: "etag1",
 					timestamp: TS,
 					part_number: 1,
-					size: 5
+					size: 3
 				},
 				PartInfo {
-					etag: "etag3".to_string(),
+					etag: "etag2",
+					timestamp: TS,
+					part_number: 3,
+					size: 10
+				},
+				PartInfo {
+					etag: "etag3",
 					timestamp: TS,
 					part_number: 5,
 					size: 7
 				},
 				PartInfo {
-					etag: "etag4".to_string(),
+					etag: "etag4",
 					timestamp: TS,
 					part_number: 8,
 					size: 5

src/api/s3/mod.rs

@@ -6,7 +6,9 @@ mod copy;
 pub mod cors;
 mod delete;
 pub mod get;
+mod lifecycle;
 mod list;
+mod multipart;
 mod post_object;
 mod put;
 mod website;

src/api/s3/multipart.rs

@@ -0,0 +1,468 @@
+use std::collections::HashMap;
+use std::sync::Arc;
+
+use futures::prelude::*;
+use hyper::body::Body;
+use hyper::{Request, Response};
+use md5::{Digest as Md5Digest, Md5};
+
+use garage_table::*;
+use garage_util::async_hash::*;
+use garage_util::data::*;
+
+use garage_model::bucket_table::Bucket;
+use garage_model::garage::Garage;
+use garage_model::s3::block_ref_table::*;
+use garage_model::s3::mpu_table::*;
+use garage_model::s3::object_table::*;
+use garage_model::s3::version_table::*;
+
+use crate::s3::error::*;
+use crate::s3::put::*;
+use crate::s3::xml as s3_xml;
+use crate::signature::verify_signed_content;
+
+// ----
+
+pub async fn handle_create_multipart_upload(
+	garage: Arc<Garage>,
+	req: &Request<Body>,
+	bucket_name: &str,
+	bucket_id: Uuid,
+	key: &String,
+) -> Result<Response<Body>, Error> {
+	let existing_object = garage.object_table.get(&bucket_id, &key).await?;
+
+	let upload_id = gen_uuid();
+	let timestamp = next_timestamp(existing_object.as_ref());
+
+	let headers = get_headers(req.headers())?;
+
+	// Create object in object table
+	let object_version = ObjectVersion {
+		uuid: upload_id,
+		timestamp,
+		state: ObjectVersionState::Uploading {
+			multipart: true,
+			headers,
+		},
+	};
+	let object = Object::new(bucket_id, key.to_string(), vec![object_version]);
+	garage.object_table.insert(&object).await?;
+
+	// Create multipart upload in mpu table
+	// This multipart upload will hold references to uploaded parts
+	// (which are entries in the Version table)
+	let mpu = MultipartUpload::new(upload_id, timestamp, bucket_id, key.into(), false);
+	garage.mpu_table.insert(&mpu).await?;
+
+	// Send success response
+	let result = s3_xml::InitiateMultipartUploadResult {
+		xmlns: (),
+		bucket: s3_xml::Value(bucket_name.to_string()),
+		key: s3_xml::Value(key.to_string()),
+		upload_id: s3_xml::Value(hex::encode(upload_id)),
+	};
+	let xml = s3_xml::to_xml_with_header(&result)?;
+
+	Ok(Response::new(Body::from(xml.into_bytes())))
+}
+
+pub async fn handle_put_part(
+	garage: Arc<Garage>,
+	req: Request<Body>,
+	bucket_id: Uuid,
+	key: &str,
+	part_number: u64,
+	upload_id: &str,
+	content_sha256: Option<Hash>,
+) -> Result<Response<Body>, Error> {
+	let upload_id = decode_upload_id(upload_id)?;
+
+	let content_md5 = match req.headers().get("content-md5") {
+		Some(x) => Some(x.to_str()?.to_string()),
+		None => None,
+	};
+
+	// Read first chuck, and at the same time try to get object to see if it exists
+	let key = key.to_string();
+
+	let body = req.into_body().map_err(Error::from);
+	let mut chunker = StreamChunker::new(body, garage.config.block_size);
+
+	let ((_, _, mut mpu), first_block) = futures::try_join!(
+		get_upload(&garage, &bucket_id, &key, &upload_id),
+		chunker.next(),
+	)?;
+
+	// Check object is valid and part can be accepted
+	let first_block = first_block.ok_or_bad_request("Empty body")?;
+
+	// Calculate part identity: timestamp, version id
+	let version_uuid = gen_uuid();
+	let mpu_part_key = MpuPartKey {
+		part_number,
+		timestamp: mpu.next_timestamp(part_number),
+	};
+
+	// The following consists in many steps that can each fail.
+	// Keep track that some cleanup will be needed if things fail
+	// before everything is finished (cleanup is done using the Drop trait).
+	let mut interrupted_cleanup = InterruptedCleanup(Some(InterruptedCleanupInner {
+		garage: garage.clone(),
+		upload_id,
+		version_uuid,
+	}));
+
+	// Create version and link version from MPU
+	mpu.parts.clear();
+	mpu.parts.put(
+		mpu_part_key,
+		MpuPart {
+			version: version_uuid,
+			etag: None,
+			size: None,
+		},
+	);
+	garage.mpu_table.insert(&mpu).await?;
+
+	let version = Version::new(
+		version_uuid,
+		VersionBacklink::MultipartUpload { upload_id },
+		false,
+	);
+	garage.version_table.insert(&version).await?;
+
+	// Copy data to version
+	let first_block_hash = async_blake2sum(first_block.clone()).await;
+
+	let (total_size, data_md5sum, data_sha256sum) = read_and_put_blocks(
+		&garage,
+		&version,
+		part_number,
+		first_block,
+		first_block_hash,
+		&mut chunker,
+	)
+	.await?;
+
+	// Verify that checksums map
+	ensure_checksum_matches(
+		data_md5sum.as_slice(),
+		data_sha256sum,
+		content_md5.as_deref(),
+		content_sha256,
+	)?;
+
+	// Store part etag in version
+	let data_md5sum_hex = hex::encode(data_md5sum);
+	mpu.parts.put(
+		mpu_part_key,
+		MpuPart {
+			version: version_uuid,
+			etag: Some(data_md5sum_hex.clone()),
+			size: Some(total_size),
+		},
+	);
+	garage.mpu_table.insert(&mpu).await?;
+
+	// We were not interrupted, everything went fine.
+	// We won't have to clean up on drop.
+	interrupted_cleanup.cancel();
+
+	let response = Response::builder()
+		.header("ETag", format!("\"{}\"", data_md5sum_hex))
+		.body(Body::empty())
+		.unwrap();
+	Ok(response)
+}
+
+struct InterruptedCleanup(Option<InterruptedCleanupInner>);
+struct InterruptedCleanupInner {
+	garage: Arc<Garage>,
+	upload_id: Uuid,
+	version_uuid: Uuid,
+}
+
+impl InterruptedCleanup {
+	fn cancel(&mut self) {
+		drop(self.0.take());
+	}
+}
+impl Drop for InterruptedCleanup {
+	fn drop(&mut self) {
+		if let Some(info) = self.0.take() {
+			tokio::spawn(async move {
+				let version = Version::new(
+					info.version_uuid,
+					VersionBacklink::MultipartUpload {
+						upload_id: info.upload_id,
+					},
+					true,
+				);
+				if let Err(e) = info.garage.version_table.insert(&version).await {
+					warn!("Cannot cleanup after aborted UploadPart: {}", e);
+				}
+			});
+		}
+	}
+}
+
+pub async fn handle_complete_multipart_upload(
+	garage: Arc<Garage>,
+	req: Request<Body>,
+	bucket_name: &str,
+	bucket: &Bucket,
+	key: &str,
+	upload_id: &str,
+	content_sha256: Option<Hash>,
+) -> Result<Response<Body>, Error> {
+	let body = hyper::body::to_bytes(req.into_body()).await?;
+
+	if let Some(content_sha256) = content_sha256 {
+		verify_signed_content(content_sha256, &body[..])?;
+	}
+
+	let body_xml = roxmltree::Document::parse(std::str::from_utf8(&body)?)?;
+	let body_list_of_parts = parse_complete_multipart_upload_body(&body_xml)
+		.ok_or_bad_request("Invalid CompleteMultipartUpload XML")?;
+	debug!(
+		"CompleteMultipartUpload list of parts: {:?}",
+		body_list_of_parts
+	);
+
+	let upload_id = decode_upload_id(upload_id)?;
+
+	// Get object and multipart upload
+	let key = key.to_string();
+	let (object, mut object_version, mpu) =
+		get_upload(&garage, &bucket.id, &key, &upload_id).await?;
+
+	if mpu.parts.is_empty() {
+		return Err(Error::bad_request("No data was uploaded"));
+	}
+
+	let headers = match object_version.state {
+		ObjectVersionState::Uploading { headers, .. } => headers,
+		_ => unreachable!(),
+	};
+
+	// Check that part numbers are an increasing sequence.
+	// (it doesn't need to start at 1 nor to be a continuous sequence,
+	// see discussion in #192)
+	if body_list_of_parts.is_empty() {
+		return Err(Error::EntityTooSmall);
+	}
+	if !body_list_of_parts
+		.iter()
+		.zip(body_list_of_parts.iter().skip(1))
+		.all(|(p1, p2)| p1.part_number < p2.part_number)
+	{
+		return Err(Error::InvalidPartOrder);
+	}
+
+	// Check that the list of parts they gave us corresponds to parts we have here
+	debug!("Parts stored in multipart upload: {:?}", mpu.parts.items());
+	let mut have_parts = HashMap::new();
+	for (pk, pv) in mpu.parts.items().iter() {
+		have_parts.insert(pk.part_number, pv);
+	}
+	let mut parts = vec![];
+	for req_part in body_list_of_parts.iter() {
+		match have_parts.get(&req_part.part_number) {
+			Some(part) if part.etag.as_ref() == Some(&req_part.etag) && part.size.is_some() => {
+				parts.push(*part)
+			}
+			_ => return Err(Error::InvalidPart),
+		}
+	}
+
+	let grg = &garage;
+	let parts_versions = futures::future::try_join_all(parts.iter().map(|p| async move {
+		grg.version_table
+			.get(&p.version, &EmptyKey)
+			.await?
+			.ok_or_internal_error("Part version missing from version table")
+	}))
+	.await?;
+
+	// Create final version and block refs
+	let mut final_version = Version::new(
+		upload_id,
+		VersionBacklink::Object {
+			bucket_id: bucket.id,
+			key: key.to_string(),
+		},
+		false,
+	);
+	for (part_number, part_version) in parts_versions.iter().enumerate() {
+		if part_version.deleted.get() {
+			return Err(Error::InvalidPart);
+		}
+		for (vbk, vb) in part_version.blocks.items().iter() {
+			final_version.blocks.put(
+				VersionBlockKey {
+					part_number: (part_number + 1) as u64,
+					offset: vbk.offset,
+				},
+				*vb,
+			);
+		}
+	}
+	garage.version_table.insert(&final_version).await?;
+
+	let block_refs = final_version.blocks.items().iter().map(|(_, b)| BlockRef {
+		block: b.hash,
+		version: upload_id,
+		deleted: false.into(),
+	});
+	garage.block_ref_table.insert_many(block_refs).await?;
+
+	// Calculate etag of final object
+	// To understand how etags are calculated, read more here:
+	// https://teppen.io/2018/06/23/aws_s3_etags/
+	let mut etag_md5_hasher = Md5::new();
+	for part in parts.iter() {
+		etag_md5_hasher.update(part.etag.as_ref().unwrap().as_bytes());
+	}
+	let etag = format!(
+		"{}-{}",
+		hex::encode(etag_md5_hasher.finalize()),
+		parts.len()
+	);
+
+	// Calculate total size of final object
+	let total_size = parts.iter().map(|x| x.size.unwrap()).sum();
+
+	if let Err(e) = check_quotas(&garage, bucket, total_size, Some(&object)).await {
+		object_version.state = ObjectVersionState::Aborted;
+		let final_object = Object::new(bucket.id, key.clone(), vec![object_version]);
+		garage.object_table.insert(&final_object).await?;
+
+		return Err(e);
+	}
+
+	// Write final object version
+	object_version.state = ObjectVersionState::Complete(ObjectVersionData::FirstBlock(
+		ObjectVersionMeta {
+			headers,
+			size: total_size,
+			etag: etag.clone(),
+		},
+		final_version.blocks.items()[0].1.hash,
+	));
+
+	let final_object = Object::new(bucket.id, key.clone(), vec![object_version]);
+	garage.object_table.insert(&final_object).await?;
+
+	// Send response saying ok we're done
+	let result = s3_xml::CompleteMultipartUploadResult {
+		xmlns: (),
+		location: None,
+		bucket: s3_xml::Value(bucket_name.to_string()),
+		key: s3_xml::Value(key),
+		etag: s3_xml::Value(format!("\"{}\"", etag)),
+	};
+	let xml = s3_xml::to_xml_with_header(&result)?;
+
+	Ok(Response::new(Body::from(xml.into_bytes())))
+}
+
+pub async fn handle_abort_multipart_upload(
+	garage: Arc<Garage>,
+	bucket_id: Uuid,
+	key: &str,
+	upload_id: &str,
+) -> Result<Response<Body>, Error> {
+	let upload_id = decode_upload_id(upload_id)?;
+
+	let (_, mut object_version, _) =
+		get_upload(&garage, &bucket_id, &key.to_string(), &upload_id).await?;
+
+	object_version.state = ObjectVersionState::Aborted;
+	let final_object = Object::new(bucket_id, key.to_string(), vec![object_version]);
+	garage.object_table.insert(&final_object).await?;
+
+	Ok(Response::new(Body::from(vec![])))
+}
+
+// ======== helpers ============
+
+#[allow(clippy::ptr_arg)]
+pub(crate) async fn get_upload(
+	garage: &Garage,
+	bucket_id: &Uuid,
+	key: &String,
+	upload_id: &Uuid,
+) -> Result<(Object, ObjectVersion, MultipartUpload), Error> {
+	let (object, mpu) = futures::try_join!(
+		garage.object_table.get(bucket_id, key).map_err(Error::from),
+		garage
+			.mpu_table
+			.get(upload_id, &EmptyKey)
+			.map_err(Error::from),
+	)?;
+
+	let object = object.ok_or(Error::NoSuchUpload)?;
+	let mpu = mpu.ok_or(Error::NoSuchUpload)?;
+
+	let object_version = object
+		.versions()
+		.iter()
+		.find(|v| v.uuid == *upload_id && v.is_uploading(Some(true)))
+		.ok_or(Error::NoSuchUpload)?
+		.clone();
+
+	Ok((object, object_version, mpu))
+}
+
+pub fn decode_upload_id(id: &str) -> Result<Uuid, Error> {
+	let id_bin = hex::decode(id).map_err(|_| Error::NoSuchUpload)?;
+	if id_bin.len() != 32 {
+		return Err(Error::NoSuchUpload);
+	}
+	let mut uuid = [0u8; 32];
+	uuid.copy_from_slice(&id_bin[..]);
+	Ok(Uuid::from(uuid))
+}
+
+#[derive(Debug)]
+struct CompleteMultipartUploadPart {
+	etag: String,
+	part_number: u64,
+}
+
+fn parse_complete_multipart_upload_body(
+	xml: &roxmltree::Document,
+) -> Option<Vec<CompleteMultipartUploadPart>> {
+	let mut parts = vec![];
+
+	let root = xml.root();
+	let cmu = root.first_child()?;
+	if !cmu.has_tag_name("CompleteMultipartUpload") {
+		return None;
+	}
+
+	for item in cmu.children() {
+		// Only parse <Part> nodes
+		if !item.is_element() {
+			continue;
+		}
+
+		if item.has_tag_name("Part") {
+			let etag = item.children().find(|e| e.has_tag_name("ETag"))?.text()?;
+			let part_number = item
+				.children()
+				.find(|e| e.has_tag_name("PartNumber"))?
+				.text()?;
+			parts.push(CompleteMultipartUploadPart {
+				etag: etag.trim_matches('"').to_string(),
+				part_number: part_number.parse().ok()?,
+			});
+		} else {
+			return None;
+		}
+	}
+
+	Some(parts)
+}

src/api/s3/put.rs

@@ -1,8 +1,9 @@
-use std::collections::{BTreeMap, BTreeSet, HashMap};
+use std::collections::{BTreeMap, HashMap};
 use std::sync::Arc;
 
 use base64::prelude::*;
 use futures::prelude::*;
+use futures::try_join;
 use hyper::body::{Body, Bytes};
 use hyper::header::{HeaderMap, HeaderValue};
 use hyper::{Request, Response};
@@ -30,14 +31,12 @@ use garage_model::s3::object_table::*;
 use garage_model::s3::version_table::*;
 
 use crate::s3::error::*;
-use crate::s3::xml as s3_xml;
-use crate::signature::verify_signed_content;
 
 pub async fn handle_put(
 	garage: Arc<Garage>,
 	req: Request<Body>,
 	bucket: &Bucket,
-	key: &str,
+	key: &String,
 	content_sha256: Option<Hash>,
 ) -> Result<Response<Body>, Error> {
 	// Retrieve interesting headers from request
@@ -70,16 +69,24 @@ pub(crate) async fn save_stream<S: Stream<Item = Result<Bytes, Error>> + Unpin>(
 	headers: ObjectVersionHeaders,
 	body: S,
 	bucket: &Bucket,
-	key: &str,
+	key: &String,
 	content_md5: Option<String>,
 	content_sha256: Option<FixedBytes32>,
 ) -> Result<(Uuid, String), Error> {
+	let mut chunker = StreamChunker::new(body, garage.config.block_size);
+	let (first_block_opt, existing_object) = try_join!(
+		chunker.next(),
+		garage
+			.object_table
+			.get(&bucket.id, key)
+			.map_err(Error::from),
+	)?;
+
+	let first_block = first_block_opt.unwrap_or_default();
+
 	// Generate identity of new version
 	let version_uuid = gen_uuid();
-	let version_timestamp = now_msec();
-
-	let mut chunker = StreamChunker::new(body, garage.config.block_size);
-	let first_block = chunker.next().await?.unwrap_or_default();
+	let version_timestamp = next_timestamp(existing_object.as_ref());
 
 	// If body is small enough, store it directly in the object table
 	// as "inline data". We can then return immediately.
@@ -99,7 +106,7 @@ pub(crate) async fn save_stream<S: Stream<Item = Result<Bytes, Error>> + Unpin>(
 			content_sha256,
 		)?;
 
-		check_quotas(&garage, bucket, key, size).await?;
+		check_quotas(&garage, bucket, size, existing_object.as_ref()).await?;
 
 		let object_version = ObjectVersion {
 			uuid: version_uuid,
@@ -123,20 +130,23 @@ pub(crate) async fn save_stream<S: Stream<Item = Result<Bytes, Error>> + Unpin>(
 	// The following consists in many steps that can each fail.
 	// Keep track that some cleanup will be needed if things fail
 	// before everything is finished (cleanup is done using the Drop trait).
-	let mut interrupted_cleanup = InterruptedCleanup(Some((
-		garage.clone(),
-		bucket.id,
-		key.into(),
+	let mut interrupted_cleanup = InterruptedCleanup(Some(InterruptedCleanupInner {
+		garage: garage.clone(),
+		bucket_id: bucket.id,
+		key: key.into(),
 		version_uuid,
 		version_timestamp,
-	)));
+	}));
 
 	// Write version identifier in object table so that we have a trace
 	// that we are uploading something
 	let mut object_version = ObjectVersion {
 		uuid: version_uuid,
 		timestamp: version_timestamp,
-		state: ObjectVersionState::Uploading(headers.clone()),
+		state: ObjectVersionState::Uploading {
+			headers: headers.clone(),
+			multipart: false,
+		},
 	};
 	let object = Object::new(bucket.id, key.into(), vec![object_version.clone()]);
 	garage.object_table.insert(&object).await?;
@@ -145,7 +155,14 @@ pub(crate) async fn save_stream<S: Stream<Item = Result<Bytes, Error>> + Unpin>(
 	// Write this entry now, even with empty block list,
 	// to prevent block_ref entries from being deleted (they can be deleted
 	// if the reference a version that isn't found in the version table)
-	let version = Version::new(version_uuid, bucket.id, key.into(), false);
+	let version = Version::new(
+		version_uuid,
+		VersionBacklink::Object {
+			bucket_id: bucket.id,
+			key: key.into(),
+		},
+		false,
+	);
 	garage.version_table.insert(&version).await?;
 
 	// Transfer data and verify checksum
@@ -168,7 +185,7 @@ pub(crate) async fn save_stream<S: Stream<Item = Result<Bytes, Error>> + Unpin>(
 		content_sha256,
 	)?;
 
-	check_quotas(&garage, bucket, key, total_size).await?;
+	check_quotas(&garage, bucket, total_size, existing_object.as_ref()).await?;
 
 	// Save final object state, marked as Complete
 	let md5sum_hex = hex::encode(data_md5sum);
@@ -192,7 +209,7 @@ pub(crate) async fn save_stream<S: Stream<Item = Result<Bytes, Error>> + Unpin>(
 
 /// Validate MD5 sum against content-md5 header
 /// and sha256sum against signed content-sha256
-fn ensure_checksum_matches(
+pub(crate) fn ensure_checksum_matches(
 	data_md5sum: &[u8],
 	data_sha256sum: garage_util::data::FixedBytes32,
 	content_md5: Option<&str>,
@@ -218,22 +235,22 @@ fn ensure_checksum_matches(
 }
 
 /// Check that inserting this object with this size doesn't exceed bucket quotas
-async fn check_quotas(
+pub(crate) async fn check_quotas(
 	garage: &Arc<Garage>,
 	bucket: &Bucket,
-	key: &str,
 	size: u64,
+	prev_object: Option<&Object>,
 ) -> Result<(), Error> {
 	let quotas = bucket.state.as_option().unwrap().quotas.get();
 	if quotas.max_objects.is_none() && quotas.max_size.is_none() {
 		return Ok(());
 	};
 
-	let key = key.to_string();
-	let (prev_object, counters) = futures::try_join!(
-		garage.object_table.get(&bucket.id, &key),
-		garage.object_counter_table.table.get(&bucket.id, &EmptyKey),
-	)?;
+	let counters = garage
+		.object_counter_table
+		.table
+		.get(&bucket.id, &EmptyKey)
+		.await?;
 
 	let counters = counters
 		.map(|x| x.filtered_values(&garage.system.ring.borrow()))
@@ -267,7 +284,7 @@ async fn check_quotas(
 		if cnt_size_diff > 0 && current_size + cnt_size_diff > ms as i64 {
 			return Err(Error::forbidden(format!(
 				"Bucket size quota is reached, maximum total size of objects for this bucket: {}. The bucket is already {} bytes, and this object would add {} bytes.",
-				ms, current_size, size
+				ms, current_size, cnt_size_diff
 			)));
 		}
 	}
@@ -275,7 +292,7 @@ async fn check_quotas(
 	Ok(())
 }
 
-async fn read_and_put_blocks<S: Stream<Item = Result<Bytes, Error>> + Unpin>(
+pub(crate) async fn read_and_put_blocks<S: Stream<Item = Result<Bytes, Error>> + Unpin>(
 	garage: &Garage,
 	version: &Version,
 	part_number: u64,
@@ -381,7 +398,7 @@ async fn put_block_meta(
 	Ok(())
 }
 
-struct StreamChunker<S: Stream<Item = Result<Bytes, Error>>> {
+pub(crate) struct StreamChunker<S: Stream<Item = Result<Bytes, Error>>> {
 	stream: S,
 	read_all: bool,
 	block_size: usize,
@@ -389,7 +406,7 @@ struct StreamChunker<S: Stream<Item = Result<Bytes, Error>>> {
 }
 
 impl<S: Stream<Item = Result<Bytes, Error>> + Unpin> StreamChunker<S> {
-	fn new(stream: S, block_size: usize) -> Self {
+	pub(crate) fn new(stream: S, block_size: usize) -> Self {
 		Self {
 			stream,
 			read_all: false,
@@ -398,7 +415,7 @@ impl<S: Stream<Item = Result<Bytes, Error>> + Unpin> StreamChunker<S> {
 		}
 	}
 
-	async fn next(&mut self) -> Result<Option<Bytes>, Error> {
+	pub(crate) async fn next(&mut self) -> Result<Option<Bytes>, Error> {
 		while !self.read_all && self.buf.len() < self.block_size {
 			if let Some(block) = self.stream.next().await {
 				let bytes = block?;
@@ -425,7 +442,14 @@ pub fn put_response(version_uuid: Uuid, md5sum_hex: String) -> Response<Body> {
 		.unwrap()
 }
 
-struct InterruptedCleanup(Option<(Arc<Garage>, Uuid, String, Uuid, u64)>);
+struct InterruptedCleanup(Option<InterruptedCleanupInner>);
+struct InterruptedCleanupInner {
+	garage: Arc<Garage>,
+	bucket_id: Uuid,
+	key: String,
+	version_uuid: Uuid,
+	version_timestamp: u64,
+}
 
 impl InterruptedCleanup {
 	fn cancel(&mut self) {
@@ -434,15 +458,15 @@ impl InterruptedCleanup {
 }
 impl Drop for InterruptedCleanup {
 	fn drop(&mut self) {
-		if let Some((garage, bucket_id, key, version_uuid, version_ts)) = self.0.take() {
+		if let Some(info) = self.0.take() {
 			tokio::spawn(async move {
 				let object_version = ObjectVersion {
-					uuid: version_uuid,
-					timestamp: version_ts,
+					uuid: info.version_uuid,
+					timestamp: info.version_timestamp,
 					state: ObjectVersionState::Aborted,
 				};
-				let object = Object::new(bucket_id, key, vec![object_version]);
-				if let Err(e) = garage.object_table.insert(&object).await {
+				let object = Object::new(info.bucket_id, info.key, vec![object_version]);
+				if let Err(e) = info.garage.object_table.insert(&object).await {
 					warn!("Cannot cleanup after aborted PutObject: {}", e);
 				}
 			});
@@ -450,326 +474,9 @@ impl Drop for InterruptedCleanup {
 	}
 }
 
-// ----
+// ============ helpers ============
 
-pub async fn handle_create_multipart_upload(
-	garage: Arc<Garage>,
-	req: &Request<Body>,
-	bucket_name: &str,
-	bucket_id: Uuid,
-	key: &str,
-) -> Result<Response<Body>, Error> {
-	let version_uuid = gen_uuid();
-	let headers = get_headers(req.headers())?;
-
-	// Create object in object table
-	let object_version = ObjectVersion {
-		uuid: version_uuid,
-		timestamp: now_msec(),
-		state: ObjectVersionState::Uploading(headers),
-	};
-	let object = Object::new(bucket_id, key.to_string(), vec![object_version]);
-	garage.object_table.insert(&object).await?;
-
-	// Insert empty version so that block_ref entries refer to something
-	// (they are inserted concurrently with blocks in the version table, so
-	// there is the possibility that they are inserted before the version table
-	// is created, in which case it is allowed to delete them, e.g. in repair_*)
-	let version = Version::new(version_uuid, bucket_id, key.into(), false);
-	garage.version_table.insert(&version).await?;
-
-	// Send success response
-	let result = s3_xml::InitiateMultipartUploadResult {
-		xmlns: (),
-		bucket: s3_xml::Value(bucket_name.to_string()),
-		key: s3_xml::Value(key.to_string()),
-		upload_id: s3_xml::Value(hex::encode(version_uuid)),
-	};
-	let xml = s3_xml::to_xml_with_header(&result)?;
-
-	Ok(Response::new(Body::from(xml.into_bytes())))
-}
-
-pub async fn handle_put_part(
-	garage: Arc<Garage>,
-	req: Request<Body>,
-	bucket_id: Uuid,
-	key: &str,
-	part_number: u64,
-	upload_id: &str,
-	content_sha256: Option<Hash>,
-) -> Result<Response<Body>, Error> {
-	let version_uuid = decode_upload_id(upload_id)?;
-
-	let content_md5 = match req.headers().get("content-md5") {
-		Some(x) => Some(x.to_str()?.to_string()),
-		None => None,
-	};
-
-	// Read first chuck, and at the same time try to get object to see if it exists
-	let key = key.to_string();
-
-	let body = req.into_body().map_err(Error::from);
-	let mut chunker = StreamChunker::new(body, garage.config.block_size);
-
-	let (object, version, first_block) = futures::try_join!(
-		garage
-			.object_table
-			.get(&bucket_id, &key)
-			.map_err(Error::from),
-		garage
-			.version_table
-			.get(&version_uuid, &EmptyKey)
-			.map_err(Error::from),
-		chunker.next(),
-	)?;
-
-	// Check object is valid and multipart block can be accepted
-	let first_block = first_block.ok_or_bad_request("Empty body")?;
-	let object = object.ok_or_bad_request("Object not found")?;
-
-	if !object
-		.versions()
-		.iter()
-		.any(|v| v.uuid == version_uuid && v.is_uploading())
-	{
-		return Err(Error::NoSuchUpload);
-	}
-
-	// Check part hasn't already been uploaded
-	if let Some(v) = version {
-		if v.has_part_number(part_number) {
-			return Err(Error::bad_request(format!(
-				"Part number {} has already been uploaded",
-				part_number
-			)));
-		}
-	}
-
-	// Copy block to store
-	let version = Version::new(version_uuid, bucket_id, key, false);
-
-	let first_block_hash = async_blake2sum(first_block.clone()).await;
-
-	let (_, data_md5sum, data_sha256sum) = read_and_put_blocks(
-		&garage,
-		&version,
-		part_number,
-		first_block,
-		first_block_hash,
-		&mut chunker,
-	)
-	.await?;
-
-	// Verify that checksums map
-	ensure_checksum_matches(
-		data_md5sum.as_slice(),
-		data_sha256sum,
-		content_md5.as_deref(),
-		content_sha256,
-	)?;
-
-	// Store part etag in version
-	let data_md5sum_hex = hex::encode(data_md5sum);
-	let mut version = version;
-	version
-		.parts_etags
-		.put(part_number, data_md5sum_hex.clone());
-	garage.version_table.insert(&version).await?;
-
-	let response = Response::builder()
-		.header("ETag", format!("\"{}\"", data_md5sum_hex))
-		.body(Body::empty())
-		.unwrap();
-	Ok(response)
-}
-
-pub async fn handle_complete_multipart_upload(
-	garage: Arc<Garage>,
-	req: Request<Body>,
-	bucket_name: &str,
-	bucket: &Bucket,
-	key: &str,
-	upload_id: &str,
-	content_sha256: Option<Hash>,
-) -> Result<Response<Body>, Error> {
-	let body = hyper::body::to_bytes(req.into_body()).await?;
-
-	if let Some(content_sha256) = content_sha256 {
-		verify_signed_content(content_sha256, &body[..])?;
-	}
-
-	let body_xml = roxmltree::Document::parse(std::str::from_utf8(&body)?)?;
-	let body_list_of_parts = parse_complete_multipart_upload_body(&body_xml)
-		.ok_or_bad_request("Invalid CompleteMultipartUpload XML")?;
-	debug!(
-		"CompleteMultipartUpload list of parts: {:?}",
-		body_list_of_parts
-	);
-
-	let version_uuid = decode_upload_id(upload_id)?;
-
-	// Get object and version
-	let key = key.to_string();
-	let (object, version) = futures::try_join!(
-		garage.object_table.get(&bucket.id, &key),
-		garage.version_table.get(&version_uuid, &EmptyKey),
-	)?;
-
-	let object = object.ok_or(Error::NoSuchKey)?;
-	let mut object_version = object
-		.versions()
-		.iter()
-		.find(|v| v.uuid == version_uuid && v.is_uploading())
-		.cloned()
-		.ok_or(Error::NoSuchUpload)?;
-
-	let version = version.ok_or(Error::NoSuchKey)?;
-	if version.blocks.is_empty() {
-		return Err(Error::bad_request("No data was uploaded"));
-	}
-
-	let headers = match object_version.state {
-		ObjectVersionState::Uploading(headers) => headers,
-		_ => unreachable!(),
-	};
-
-	// Check that part numbers are an increasing sequence.
-	// (it doesn't need to start at 1 nor to be a continuous sequence,
-	// see discussion in #192)
-	if body_list_of_parts.is_empty() {
-		return Err(Error::EntityTooSmall);
-	}
-	if !body_list_of_parts
-		.iter()
-		.zip(body_list_of_parts.iter().skip(1))
-		.all(|(p1, p2)| p1.part_number < p2.part_number)
-	{
-		return Err(Error::InvalidPartOrder);
-	}
-
-	// Garage-specific restriction, see #204: part numbers must be
-	// consecutive starting at 1
-	if body_list_of_parts[0].part_number != 1
-		|| !body_list_of_parts
-			.iter()
-			.zip(body_list_of_parts.iter().skip(1))
-			.all(|(p1, p2)| p1.part_number + 1 == p2.part_number)
-	{
-		return Err(Error::NotImplemented("Garage does not support completing a Multipart upload with non-consecutive part numbers. This is a restriction of Garage's data model, which might be fixed in a future release. See issue #204 for more information on this topic.".into()));
-	}
-
-	// Check that the list of parts they gave us corresponds to the parts we have here
-	debug!("Expected parts from request: {:?}", body_list_of_parts);
-	debug!("Parts stored in version: {:?}", version.parts_etags.items());
-	let parts = version
-		.parts_etags
-		.items()
-		.iter()
-		.map(|pair| (&pair.0, &pair.1));
-	let same_parts = body_list_of_parts
-		.iter()
-		.map(|x| (&x.part_number, &x.etag))
-		.eq(parts);
-	if !same_parts {
-		return Err(Error::InvalidPart);
-	}
-
-	// Check that all blocks belong to one of the parts
-	let block_parts = version
-		.blocks
-		.items()
-		.iter()
-		.map(|(bk, _)| bk.part_number)
-		.collect::<BTreeSet<_>>();
-	let same_parts = body_list_of_parts
-		.iter()
-		.map(|x| x.part_number)
-		.eq(block_parts.into_iter());
-	if !same_parts {
-		return Err(Error::bad_request(
-			"Part numbers in block list and part list do not match. This can happen if a part was partially uploaded. Please abort the multipart upload and try again."
-		));
-	}
-
-	// Calculate etag of final object
-	// To understand how etags are calculated, read more here:
-	// https://teppen.io/2018/06/23/aws_s3_etags/
-	let num_parts = body_list_of_parts.len();
-	let mut etag_md5_hasher = Md5::new();
-	for (_, etag) in version.parts_etags.items().iter() {
-		etag_md5_hasher.update(etag.as_bytes());
-	}
-	let etag = format!("{}-{}", hex::encode(etag_md5_hasher.finalize()), num_parts);
-
-	// Calculate total size of final object
-	let total_size = version.blocks.items().iter().map(|x| x.1.size).sum();
-
-	if let Err(e) = check_quotas(&garage, bucket, &key, total_size).await {
-		object_version.state = ObjectVersionState::Aborted;
-		let final_object = Object::new(bucket.id, key.clone(), vec![object_version]);
-		garage.object_table.insert(&final_object).await?;
-
-		return Err(e);
-	}
-
-	// Write final object version
-	object_version.state = ObjectVersionState::Complete(ObjectVersionData::FirstBlock(
-		ObjectVersionMeta {
-			headers,
-			size: total_size,
-			etag: etag.clone(),
-		},
-		version.blocks.items()[0].1.hash,
-	));
-
-	let final_object = Object::new(bucket.id, key.clone(), vec![object_version]);
-	garage.object_table.insert(&final_object).await?;
-
-	// Send response saying ok we're done
-	let result = s3_xml::CompleteMultipartUploadResult {
-		xmlns: (),
-		location: None,
-		bucket: s3_xml::Value(bucket_name.to_string()),
-		key: s3_xml::Value(key),
-		etag: s3_xml::Value(format!("\"{}\"", etag)),
-	};
-	let xml = s3_xml::to_xml_with_header(&result)?;
-
-	Ok(Response::new(Body::from(xml.into_bytes())))
-}
-
-pub async fn handle_abort_multipart_upload(
-	garage: Arc<Garage>,
-	bucket_id: Uuid,
-	key: &str,
-	upload_id: &str,
-) -> Result<Response<Body>, Error> {
-	let version_uuid = decode_upload_id(upload_id)?;
-
-	let object = garage
-		.object_table
-		.get(&bucket_id, &key.to_string())
-		.await?;
-	let object = object.ok_or(Error::NoSuchKey)?;
-
-	let object_version = object
-		.versions()
-		.iter()
-		.find(|v| v.uuid == version_uuid && v.is_uploading());
-	let mut object_version = match object_version {
-		None => return Err(Error::NoSuchUpload),
-		Some(x) => x.clone(),
-	};
-
-	object_version.state = ObjectVersionState::Aborted;
-	let final_object = Object::new(bucket_id, key.to_string(), vec![object_version]);
-	garage.object_table.insert(&final_object).await?;
-
-	Ok(Response::new(Body::from(vec![])))
-}
-
-fn get_mime_type(headers: &HeaderMap<HeaderValue>) -> Result<String, Error> {
+pub(crate) fn get_mime_type(headers: &HeaderMap<HeaderValue>) -> Result<String, Error> {
 	Ok(headers
 		.get(hyper::header::CONTENT_TYPE)
 		.map(|x| x.to_str())
@@ -822,53 +529,10 @@ pub(crate) fn get_headers(headers: &HeaderMap<HeaderValue>) -> Result<ObjectVers
 	})
 }
 
-pub fn decode_upload_id(id: &str) -> Result<Uuid, Error> {
-	let id_bin = hex::decode(id).map_err(|_| Error::NoSuchUpload)?;
-	if id_bin.len() != 32 {
-		return Err(Error::NoSuchUpload);
-	}
-	let mut uuid = [0u8; 32];
-	uuid.copy_from_slice(&id_bin[..]);
-	Ok(Uuid::from(uuid))
-}
-
-#[derive(Debug)]
-struct CompleteMultipartUploadPart {
-	etag: String,
-	part_number: u64,
-}
-
-fn parse_complete_multipart_upload_body(
-	xml: &roxmltree::Document,
-) -> Option<Vec<CompleteMultipartUploadPart>> {
-	let mut parts = vec![];
-
-	let root = xml.root();
-	let cmu = root.first_child()?;
-	if !cmu.has_tag_name("CompleteMultipartUpload") {
-		return None;
-	}
-
-	for item in cmu.children() {
-		// Only parse <Part> nodes
-		if !item.is_element() {
-			continue;
-		}
-
-		if item.has_tag_name("Part") {
-			let etag = item.children().find(|e| e.has_tag_name("ETag"))?.text()?;
-			let part_number = item
-				.children()
-				.find(|e| e.has_tag_name("PartNumber"))?
-				.text()?;
-			parts.push(CompleteMultipartUploadPart {
-				etag: etag.trim_matches('"').to_string(),
-				part_number: part_number.parse().ok()?,
-			});
-		} else {
-			return None;
-		}
-	}
-
-	Some(parts)
+pub(crate) fn next_timestamp(existing_object: Option<&Object>) -> u64 {
+	existing_object
+		.as_ref()
+		.and_then(|obj| obj.versions().iter().map(|v| v.timestamp).max())
+		.map(|t| std::cmp::max(t + 1, now_msec()))
+		.unwrap_or_else(now_msec)
 }

src/api/s3/website.rs

@@ -43,14 +43,11 @@ pub async fn handle_get_website(bucket: &Bucket) -> Result<Response<Body>, Error
 
 pub async fn handle_delete_website(
 	garage: Arc<Garage>,
-	bucket_id: Uuid,
+	mut bucket: Bucket,
 ) -> Result<Response<Body>, Error> {
-	let mut bucket = garage
-		.bucket_helper()
-		.get_existing_bucket(bucket_id)
-		.await?;
-
-	let param = bucket.params_mut().unwrap();
+	let param = bucket
+		.params_mut()
+		.ok_or_internal_error("Bucket should not be deleted at this point")?;
 
 	param.website_config.update(None);
 	garage.bucket_table.insert(&bucket).await?;
@@ -62,7 +59,7 @@ pub async fn handle_delete_website(
 
 pub async fn handle_put_website(
 	garage: Arc<Garage>,
-	bucket_id: Uuid,
+	mut bucket: Bucket,
 	req: Request<Body>,
 	content_sha256: Option<Hash>,
 ) -> Result<Response<Body>, Error> {
@@ -72,12 +69,9 @@ pub async fn handle_put_website(
 		verify_signed_content(content_sha256, &body[..])?;
 	}
 
-	let mut bucket = garage
-		.bucket_helper()
-		.get_existing_bucket(bucket_id)
-		.await?;
-
-	let param = bucket.params_mut().unwrap();
+	let param = bucket
+		.params_mut()
+		.ok_or_internal_error("Bucket should not be deleted at this point")?;
 
 	let conf: WebsiteConfiguration = from_reader(&body as &[u8])?;
 	conf.validate()?;

src/block/Cargo.toml

@@ -1,6 +1,6 @@
 [package]
 name = "garage_block"
-version = "0.8.5"
+version = "0.9.1"
 authors = ["Alex Auvolat <alex@adnab.me>"]
 edition = "2018"
 license = "AGPL-3.0"
@@ -24,6 +24,7 @@ opentelemetry = "0.17"
 arc-swap = "1.5"
 async-trait = "0.1.7"
 bytes = "1.0"
+bytesize = "1.2"
 hex = "0.4"
 tracing = "0.1"
 rand = "0.8"

src/block/block.rs

@@ -1,3 +1,5 @@
+use std::path::PathBuf;
+
 use bytes::Bytes;
 use serde::{Deserialize, Serialize};
 use zstd::stream::{decode_all as zstd_decode, Encoder};
@@ -19,6 +21,14 @@ pub enum DataBlock {
 	Compressed(Bytes),
 }
 
+#[derive(Debug)]
+pub enum DataBlockPath {
+	/// Uncompressed data fail
+	Plain(PathBuf),
+	/// Compressed data fail
+	Compressed(PathBuf),
+}
+
 impl DataBlock {
 	/// Query whether this block is compressed
 	pub fn is_compressed(&self) -> bool {

src/block/layout.rs

@@ -0,0 +1,337 @@
+use std::path::PathBuf;
+
+use serde::{Deserialize, Serialize};
+
+use garage_util::config::DataDirEnum;
+use garage_util::data::Hash;
+use garage_util::error::{Error, OkOrMessage};
+use garage_util::migrate::*;
+
+type Idx = u16;
+
+const DRIVE_NPART: usize = 1024;
+
+const HASH_DRIVE_BYTES: (usize, usize) = (2, 3);
+
+#[derive(Serialize, Deserialize, Debug, Clone)]
+pub(crate) struct DataLayout {
+	pub(crate) data_dirs: Vec<DataDir>,
+
+	/// Primary storage location (index in data_dirs) for each partition
+	/// = the location where the data is supposed to be, blocks are always
+	/// written there (copies in other dirs may be deleted if they exist)
+	pub(crate) part_prim: Vec<Idx>,
+	/// Secondary storage locations for each partition = locations
+	/// where data blocks might be, we check from these dirs when reading
+	pub(crate) part_sec: Vec<Vec<Idx>>,
+}
+
+#[derive(Serialize, Deserialize, Debug, Clone, Eq, PartialEq)]
+pub(crate) struct DataDir {
+	pub(crate) path: PathBuf,
+	pub(crate) state: DataDirState,
+}
+
+#[derive(Serialize, Deserialize, Debug, Clone, Copy, Eq, PartialEq)]
+pub(crate) enum DataDirState {
+	Active { capacity: u64 },
+	ReadOnly,
+}
+
+impl DataLayout {
+	pub(crate) fn initialize(dirs: &DataDirEnum) -> Result<Self, Error> {
+		let data_dirs = make_data_dirs(dirs)?;
+
+		// Split partitions proportionnally to capacity for all drives
+		// to affect primary storage location
+		let total_cap = data_dirs.iter().filter_map(|x| x.capacity()).sum::<u64>();
+		assert!(total_cap > 0);
+
+		let mut part_prim = Vec::with_capacity(DRIVE_NPART);
+		let mut cum_cap = 0;
+		for (i, dd) in data_dirs.iter().enumerate() {
+			if let DataDirState::Active { capacity } = dd.state {
+				cum_cap += capacity;
+				let n_total = (cum_cap * DRIVE_NPART as u64) / total_cap;
+				part_prim.resize(n_total as usize, i as Idx);
+			}
+		}
+		assert_eq!(cum_cap, total_cap);
+		assert_eq!(part_prim.len(), DRIVE_NPART);
+
+		// If any of the storage locations is non-empty, it probably existed before
+		// this algorithm was added, so add it as a secondary storage location for all partitions
+		// to make sure existing files are not lost
+		let mut part_sec = vec![vec![]; DRIVE_NPART];
+		for (i, dd) in data_dirs.iter().enumerate() {
+			if dir_not_empty(&dd.path)? {
+				for (sec, prim) in part_sec.iter_mut().zip(part_prim.iter()) {
+					if *prim != i as Idx {
+						sec.push(i as Idx);
+					}
+				}
+			}
+		}
+
+		Ok(Self {
+			data_dirs,
+			part_prim,
+			part_sec,
+		})
+	}
+
+	pub(crate) fn update(&mut self, dirs: &DataDirEnum) -> Result<(), Error> {
+		// Make list of new data directories, exit if nothing changed
+		let data_dirs = make_data_dirs(dirs)?;
+		if data_dirs == self.data_dirs {
+			return Ok(());
+		}
+
+		let total_cap = data_dirs.iter().filter_map(|x| x.capacity()).sum::<u64>();
+		assert!(total_cap > 0);
+
+		// Compute mapping of old indices to new indices
+		let old2new = self
+			.data_dirs
+			.iter()
+			.map(|x| {
+				data_dirs
+					.iter()
+					.position(|y| y.path == x.path)
+					.map(|x| x as Idx)
+			})
+			.collect::<Vec<_>>();
+
+		// Compute secondary location list for partitions based on existing
+		// folders, translating indices from old to new
+		let mut part_sec = self
+			.part_sec
+			.iter()
+			.map(|dl| {
+				dl.iter()
+					.filter_map(|old| old2new.get(*old as usize).copied().flatten())
+					.collect::<Vec<_>>()
+			})
+			.collect::<Vec<_>>();
+
+		// Compute a vector that, for each data dir,
+		// contains the list of partitions primarily stored on that drive
+		let mut dir_prim = vec![vec![]; data_dirs.len()];
+		for (ipart, prim) in self.part_prim.iter().enumerate() {
+			if let Some(new) = old2new.get(*prim as usize).copied().flatten() {
+				dir_prim[new as usize].push(ipart);
+			}
+		}
+
+		// Compute the target number of partitions per data directory
+		let mut cum_cap = 0;
+		let mut npart_per_dir = vec![0; data_dirs.len()];
+		for (idir, dd) in data_dirs.iter().enumerate() {
+			if let DataDirState::Active { capacity } = dd.state {
+				let begin = (cum_cap * DRIVE_NPART as u64) / total_cap;
+				cum_cap += capacity;
+				let end = (cum_cap * DRIVE_NPART as u64) / total_cap;
+				npart_per_dir[idir] = (end - begin) as usize;
+			}
+		}
+		assert_eq!(cum_cap, total_cap);
+		assert_eq!(npart_per_dir.iter().sum::<usize>(), DRIVE_NPART);
+
+		// For all directories that have too many primary partitions,
+		// move that partition to secondary
+		for (idir, (parts, tgt_npart)) in dir_prim.iter_mut().zip(npart_per_dir.iter()).enumerate()
+		{
+			while parts.len() > *tgt_npart {
+				let part = parts.pop().unwrap();
+				if !part_sec[part].contains(&(idir as Idx)) {
+					part_sec[part].push(idir as Idx);
+				}
+			}
+		}
+
+		// Calculate the vector of primary partition dir index
+		let mut part_prim = vec![None; DRIVE_NPART];
+		for (idir, parts) in dir_prim.iter().enumerate() {
+			for part in parts.iter() {
+				assert!(part_prim[*part].is_none());
+				part_prim[*part] = Some(idir as Idx)
+			}
+		}
+
+		// Calculate a vector of unassigned partitions
+		let mut unassigned = part_prim
+			.iter()
+			.enumerate()
+			.filter(|(_, dir)| dir.is_none())
+			.map(|(ipart, _)| ipart)
+			.collect::<Vec<_>>();
+
+		// For all directories that don't have enough primary partitions,
+		// add partitions from unassigned
+		for (idir, (parts, tgt_npart)) in dir_prim.iter_mut().zip(npart_per_dir.iter()).enumerate()
+		{
+			if parts.len() < *tgt_npart {
+				let required = *tgt_npart - parts.len();
+				assert!(unassigned.len() >= required);
+				for _ in 0..required {
+					let new_part = unassigned.pop().unwrap();
+					part_prim[new_part] = Some(idir as Idx);
+					part_sec[new_part].retain(|x| *x != idir as Idx);
+				}
+			}
+		}
+
+		// Sanity checks
+		assert!(part_prim.iter().all(|x| x.is_some()));
+		assert!(unassigned.is_empty());
+
+		// Transform part_prim from vec of Option<Idx> to vec of Idx
+		let part_prim = part_prim
+			.into_iter()
+			.map(|x| x.unwrap())
+			.collect::<Vec<_>>();
+		assert!(part_prim.iter().all(|p| data_dirs
+			.get(*p as usize)
+			.and_then(|x| x.capacity())
+			.unwrap_or(0)
+			> 0));
+
+		// If any of the newly added storage locations is non-empty,
+		// it might have been removed and added again and might contain data,
+		// so add it as a secondary storage location for all partitions
+		// to make sure existing files are not lost
+		for (i, dd) in data_dirs.iter().enumerate() {
+			if self.data_dirs.iter().any(|ed| ed.path == dd.path) {
+				continue;
+			}
+			if dir_not_empty(&dd.path)? {
+				for (sec, prim) in part_sec.iter_mut().zip(part_prim.iter()) {
+					if *prim != i as Idx && !sec.contains(&(i as Idx)) {
+						sec.push(i as Idx);
+					}
+				}
+			}
+		}
+
+		// Apply newly generated config
+		*self = Self {
+			data_dirs,
+			part_prim,
+			part_sec,
+		};
+		Ok(())
+	}
+
+	pub(crate) fn primary_block_dir(&self, hash: &Hash) -> PathBuf {
+		let ipart = self.partition_from(hash);
+		let idir = self.part_prim[ipart] as usize;
+		self.block_dir_from(hash, &self.data_dirs[idir].path)
+	}
+
+	pub(crate) fn secondary_block_dirs<'a>(
+		&'a self,
+		hash: &'a Hash,
+	) -> impl Iterator<Item = PathBuf> + 'a {
+		let ipart = self.partition_from(hash);
+		self.part_sec[ipart]
+			.iter()
+			.map(move |idir| self.block_dir_from(hash, &self.data_dirs[*idir as usize].path))
+	}
+
+	fn partition_from(&self, hash: &Hash) -> usize {
+		u16::from_be_bytes([
+			hash.as_slice()[HASH_DRIVE_BYTES.0],
+			hash.as_slice()[HASH_DRIVE_BYTES.1],
+		]) as usize % DRIVE_NPART
+	}
+
+	fn block_dir_from(&self, hash: &Hash, dir: &PathBuf) -> PathBuf {
+		let mut path = dir.clone();
+		path.push(hex::encode(&hash.as_slice()[0..1]));
+		path.push(hex::encode(&hash.as_slice()[1..2]));
+		path
+	}
+
+	pub(crate) fn without_secondary_locations(&self) -> Self {
+		Self {
+			data_dirs: self.data_dirs.clone(),
+			part_prim: self.part_prim.clone(),
+			part_sec: self.part_sec.iter().map(|_| vec![]).collect::<Vec<_>>(),
+		}
+	}
+}
+
+impl InitialFormat for DataLayout {
+	const VERSION_MARKER: &'static [u8] = b"G09bmdl";
+}
+
+impl DataDir {
+	pub fn capacity(&self) -> Option<u64> {
+		match self.state {
+			DataDirState::Active { capacity } => Some(capacity),
+			_ => None,
+		}
+	}
+}
+
+fn make_data_dirs(dirs: &DataDirEnum) -> Result<Vec<DataDir>, Error> {
+	let mut data_dirs = vec![];
+	match dirs {
+		DataDirEnum::Single(path) => data_dirs.push(DataDir {
+			path: path.clone(),
+			state: DataDirState::Active {
+				capacity: 1_000_000_000, // whatever, doesn't matter
+			},
+		}),
+		DataDirEnum::Multiple(dirs) => {
+			let mut ok = false;
+			for dir in dirs.iter() {
+				let state = match &dir.capacity {
+					Some(cap) if dir.read_only == false => {
+						let capacity = cap.parse::<bytesize::ByteSize>()
+							.ok_or_message("invalid capacity value")?.as_u64();
+						if capacity == 0 {
+							return Err(Error::Message(format!("data directory {} should have non-zero capacity", dir.path.to_string_lossy())));
+						}
+						ok = true;
+						DataDirState::Active {
+							capacity,
+						}
+					}
+					None if dir.read_only == true => {
+						DataDirState::ReadOnly
+					}
+					_ => return Err(Error::Message(format!("data directories in data_dir should have a capacity value or be marked read_only, not the case for {}", dir.path.to_string_lossy()))),
+				};
+				data_dirs.push(DataDir {
+					path: dir.path.clone(),
+					state,
+				});
+			}
+			if !ok {
+				return Err(Error::Message(
+					"incorrect data_dir configuration, no primary writable directory specified"
+						.into(),
+				));
+			}
+		}
+	}
+	Ok(data_dirs)
+}
+
+fn dir_not_empty(path: &PathBuf) -> Result<bool, Error> {
+	for entry in std::fs::read_dir(&path)? {
+		let dir = entry?;
+		if dir.file_type()?.is_dir()
+			&& dir
+				.file_name()
+				.into_string()
+				.ok()
+				.and_then(|hex| hex::decode(&hex).ok())
+				.is_some()
+		{
+			return Ok(true);
+		}
+	}
+	Ok(false)
+}

src/block/lib.rs

@@ -6,5 +6,6 @@ pub mod repair;
 pub mod resync;
 
 mod block;
+mod layout;
 mod metrics;
 mod rc;