Enable k2v feature flag in CI

- [x] Refactoring of internal counting API
- [x] Repair procedure for counters (it's an offline procedure!!!)
- [x] New counter for objects in buckets
- [x] Add quotas to buckets struct
- [x] Add CLI to manage bucket quotas
- [x] Add admin API to manage bucket quotas
- [x] Apply quotas by adding checks on put operations
- [x] Proof-read

Co-authored-by: Alex Auvolat <alex@adnab.me>
Reviewed-on: https://git.deuxfleurs.fr/Deuxfleurs/garage/pulls/326
Co-authored-by: Alex <alex@adnab.me>
Co-committed-by: Alex <alex@adnab.me>

Cargo.lock

@@ -2,6 +2,17 @@
 # It is not intended for manual editing.
 version = 3
 
+[[package]]
+name = "ahash"
+version = "0.7.6"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "fcb51a0695d8f838b1ee009b3fbf66bda078cd64590202a864a8f3e8c4315c47"
+dependencies = [
+ "getrandom",
+ "once_cell",
+ "version_check",
+]
+
 [[package]]
 name = "aho-corasick"
 version = "0.7.18"
@@ -301,6 +312,15 @@ version = "0.13.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "904dfeac50f3cdaba28fc6f57fdcddb75f49ed61346676a78c4ffe55877802fd"
 
+[[package]]
+name = "bincode"
+version = "1.3.3"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "b1f45e9417d87227c7a56d22e471c6206462cba514c7590c09aff4cf6d1ddcad"
+dependencies = [
+ "serde",
+]
+
 [[package]]
 name = "bitflags"
 version = "1.3.2"
@@ -333,6 +353,12 @@ version = "3.9.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "a4a45a46ab1f2412e53d3a0ade76ffad2025804294569aae387231a0cd6e0899"
 
+[[package]]
+name = "bytemuck"
+version = "1.9.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "cdead85bdec19c194affaeeb670c0e41fe23de31459efd1c174d049269cf02cc"
+
 [[package]]
 name = "byteorder"
 version = "1.4.3"
@@ -361,6 +387,12 @@ dependencies = [
  "either",
 ]
 
+[[package]]
+name = "bytesize"
+version = "1.1.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "6c58ec36aac5066d5ca17df51b3e70279f5670a72102f5752cb7e7c856adfc70"
+
 [[package]]
 name = "cc"
 version = "1.0.73"
@@ -370,6 +402,12 @@ dependencies = [
  "jobserver",
 ]
 
+[[package]]
+name = "cfg-if"
+version = "0.1.10"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "4785bdd1c96b2a846b2bd7cc02e86b6b3dbf14e7e53446c4f54c92a361040822"
+
 [[package]]
 name = "cfg-if"
 version = "1.0.0"
@@ -486,7 +524,7 @@ version = "1.3.2"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "b540bd8bc810d3885c6ea91e2018302f68baba2129ab3e88f32389ee9370880d"
 dependencies = [
- "cfg-if",
+ "cfg-if 1.0.0",
 ]
 
 [[package]]
@@ -495,8 +533,8 @@ version = "0.5.4"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "5aaa7bd5fb665c6864b5f963dd9097905c54125909c7aa94c9e18507cdbe6c53"
 dependencies = [
- "cfg-if",
+ "cfg-if 1.0.0",
- "crossbeam-utils",
+ "crossbeam-utils 0.8.8",
 ]
 
 [[package]]
@@ -506,20 +544,39 @@ source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "1145cf131a2c6ba0615079ab6a638f7e1973ac9c2634fcbeaaad6114246efe8c"
 dependencies = [
  "autocfg",
- "cfg-if",
+ "cfg-if 1.0.0",
- "crossbeam-utils",
+ "crossbeam-utils 0.8.8",
  "lazy_static",
  "memoffset",
  "scopeguard",
 ]
 
+[[package]]
+name = "crossbeam-queue"
+version = "0.1.2"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "7c979cd6cfe72335896575c6b5688da489e420d36a27a0b9eb0c73db574b4a4b"
+dependencies = [
+ "crossbeam-utils 0.6.6",
+]
+
+[[package]]
+name = "crossbeam-utils"
+version = "0.6.6"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "04973fa96e96579258a5091af6003abde64af786b860f18622b82e026cca60e6"
+dependencies = [
+ "cfg-if 0.1.10",
+ "lazy_static",
+]
+
 [[package]]
 name = "crossbeam-utils"
 version = "0.8.8"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "0bf124c720b7686e3c2663cf54062ab0f68a88af2fb6a030e87e30bf721fcb38"
 dependencies = [
- "cfg-if",
+ "cfg-if 1.0.0",
  "lazy_static",
 ]
 
@@ -603,7 +660,7 @@ version = "4.0.2"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "e77a43b28d0668df09411cb0bc9a8c2adc40f9a048afe863e05fd43251e8e39c"
 dependencies = [
- "cfg-if",
+ "cfg-if 1.0.0",
  "num_cpus",
 ]
 
@@ -633,7 +690,7 @@ version = "2.0.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "b98cf8ebf19c3d1b223e151f99a4f9f0690dca41414773390fc824184ac833e1"
 dependencies = [
- "cfg-if",
+ "cfg-if 1.0.0",
  "dirs-sys-next",
 ]
 
@@ -672,7 +729,7 @@ version = "0.8.30"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "7896dc8abb250ffdda33912550faa54c88ec8b998dec0b2c55ab224921ce11df"
 dependencies = [
- "cfg-if",
+ "cfg-if 1.0.0",
 ]
 
 [[package]]
@@ -716,6 +773,18 @@ dependencies = [
  "synstructure",
 ]
 
+[[package]]
+name = "fallible-iterator"
+version = "0.2.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "4443176a9f2c162692bd3d352d745ef9413eec5782a80d8fd6f8a1ac692a07f7"
+
+[[package]]
+name = "fallible-streaming-iterator"
+version = "0.1.9"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "7360491ce676a36bf9bb3c56c1aa791658183a54d2744120f27285738d90465a"
+
 [[package]]
 name = "fastrand"
 version = "1.7.0"
@@ -885,10 +954,12 @@ dependencies = [
  "aws-sdk-s3",
  "base64",
  "bytes 1.1.0",
+ "bytesize",
  "chrono",
  "futures",
  "futures-util",
  "garage_api",
+ "garage_db",
  "garage_model 0.7.0",
  "garage_rpc 0.7.0",
  "garage_table 0.7.0",
@@ -911,7 +982,6 @@ dependencies = [
  "serde_bytes",
  "serde_json",
  "sha2",
- "sled",
  "static_init",
  "structopt",
  "tokio",
@@ -972,6 +1042,7 @@ dependencies = [
  "bytes 1.1.0",
  "futures",
  "futures-util",
+ "garage_db",
  "garage_rpc 0.7.0",
  "garage_table 0.7.0",
  "garage_util 0.7.0",
@@ -981,12 +1052,26 @@ dependencies = [
  "rmp-serde 0.15.5",
  "serde",
  "serde_bytes",
- "sled",
  "tokio",
  "tracing",
  "zstd",
 ]
 
+[[package]]
+name = "garage_db"
+version = "0.8.0"
+dependencies = [
+ "clap 3.1.18",
+ "err-derive 0.3.1",
+ "heed",
+ "hexdump",
+ "log",
+ "mktemp",
+ "pretty_env_logger",
+ "rusqlite",
+ "sled",
+]
+
 [[package]]
 name = "garage_model"
 version = "0.5.1"
@@ -1024,6 +1109,7 @@ dependencies = [
  "futures",
  "futures-util",
  "garage_block",
+ "garage_db",
  "garage_model 0.5.1",
  "garage_rpc 0.7.0",
  "garage_table 0.7.0",
@@ -1035,7 +1121,6 @@ dependencies = [
  "rmp-serde 0.15.5",
  "serde",
  "serde_bytes",
- "sled",
  "tokio",
  "tracing",
  "zstd",
@@ -1130,6 +1215,7 @@ dependencies = [
  "bytes 1.1.0",
  "futures",
  "futures-util",
+ "garage_db",
  "garage_rpc 0.7.0",
  "garage_util 0.7.0",
  "hexdump",
@@ -1138,7 +1224,6 @@ dependencies = [
  "rmp-serde 0.15.5",
  "serde",
  "serde_bytes",
- "sled",
  "tokio",
  "tracing",
 ]
@@ -1177,6 +1262,7 @@ dependencies = [
  "chrono",
  "err-derive 0.3.1",
  "futures",
+ "garage_db",
  "hex",
  "http",
  "hyper",
@@ -1187,7 +1273,6 @@ dependencies = [
  "serde",
  "serde_json",
  "sha2",
- "sled",
  "tokio",
  "toml",
  "tracing",
@@ -1237,7 +1322,7 @@ version = "0.2.5"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "d39cd93900197114fa1fcb7ae84ca742095eed9442088988ae74fa744e930e77"
 dependencies = [
- "cfg-if",
+ "cfg-if 1.0.0",
  "libc",
  "wasi 0.10.0+wasi-snapshot-preview1",
 ]
@@ -1288,6 +1373,18 @@ name = "hashbrown"
 version = "0.11.2"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "ab5ef0d4909ef3724cc8cce6ccc8572c5c817592e9285f5464f8e86f8bd3726e"
+dependencies = [
+ "ahash",
+]
+
+[[package]]
+name = "hashlink"
+version = "0.7.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "7249a3129cbc1ffccd74857f81464a323a152173cdb134e0fd81bc803b29facf"
+dependencies = [
+ "hashbrown",
+]
 
 [[package]]
 name = "heck"
@@ -1304,6 +1401,45 @@ version = "0.4.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "2540771e65fc8cb83cd6e8a237f70c319bd5c29f78ed1084ba5d50eeac86f7f9"
 
+[[package]]
+name = "heed"
+version = "0.11.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "269c7486ed6def5d7b59a427cec3e87b4d4dd4381d01e21c8c9f2d3985688392"
+dependencies = [
+ "bytemuck",
+ "byteorder",
+ "heed-traits",
+ "heed-types",
+ "libc",
+ "lmdb-rkv-sys",
+ "once_cell",
+ "page_size",
+ "serde",
+ "synchronoise",
+ "url",
+]
+
+[[package]]
+name = "heed-traits"
+version = "0.8.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "a53a94e5b2fd60417e83ffdfe136c39afacff0d4ac1d8d01cd66928ac610e1a2"
+
+[[package]]
+name = "heed-types"
+version = "0.8.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "9a6cf0a6952fcedc992602d5cddd1e3fff091fbe87d38636e3ec23a31f32acbd"
+dependencies = [
+ "bincode",
+ "bytemuck",
+ "byteorder",
+ "heed-traits",
+ "serde",
+ "serde_json",
+]
+
 [[package]]
 name = "hermit-abi"
 version = "0.1.19"
@@ -1503,7 +1639,7 @@ version = "0.1.12"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "7a5bbe824c507c5da5956355e86a746d82e0e1464f65d862cc5e71da70e94b2c"
 dependencies = [
- "cfg-if",
+ "cfg-if 1.0.0",
 ]
 
 [[package]]
@@ -1758,12 +1894,34 @@ dependencies = [
  "walkdir",
 ]
 
+[[package]]
+name = "libsqlite3-sys"
+version = "0.24.2"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "898745e570c7d0453cc1fbc4a701eb6c662ed54e8fec8b7d14be137ebeeb9d14"
+dependencies = [
+ "cc",
+ "pkg-config",
+ "vcpkg",
+]
+
 [[package]]
 name = "linked-hash-map"
 version = "0.5.4"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "7fb9b38af92608140b86b693604b9ffcc5824240a484d1ecd4795bacb2fe88f3"
 
+[[package]]
+name = "lmdb-rkv-sys"
+version = "0.11.2"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "61b9ce6b3be08acefa3003c57b7565377432a89ec24476bbe72e11d101f852fe"
+dependencies = [
+ "cc",
+ "libc",
+ "pkg-config",
+]
+
 [[package]]
 name = "lock_api"
 version = "0.4.6"
@@ -1779,7 +1937,7 @@ version = "0.4.16"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "6389c490849ff5bc16be905ae24bc913a9c8892e19b2341dbc175e14c341c2b8"
 dependencies = [
- "cfg-if",
+ "cfg-if 1.0.0",
 ]
 
 [[package]]
@@ -1855,6 +2013,15 @@ dependencies = [
  "winapi",
 ]
 
+[[package]]
+name = "mktemp"
+version = "0.4.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "975de676448231fcde04b9149d2543077e166b78fc29eae5aa219e7928410da2"
+dependencies = [
+ "uuid",
+]
+
 [[package]]
 name = "multer"
 version = "2.0.2"
@@ -1928,7 +2095,7 @@ dependencies = [
  "arc-swap",
  "async-trait",
  "bytes 0.6.0",
- "cfg-if",
+ "cfg-if 1.0.0",
  "err-derive 0.2.4",
  "futures",
  "hex",
@@ -2021,7 +2188,7 @@ source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "0c7ae222234c30df141154f159066c5093ff73b63204dcda7121eb082fc56a95"
 dependencies = [
  "bitflags",
- "cfg-if",
+ "cfg-if 1.0.0",
  "foreign-types",
  "libc",
  "once_cell",
@@ -2134,6 +2301,16 @@ version = "6.0.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "029d8d0b2f198229de29dca79676f2738ff952edf3fde542eb8bf94d8c21b435"
 
+[[package]]
+name = "page_size"
+version = "0.4.2"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "eebde548fbbf1ea81a99b128872779c437752fb99f217c45245e1a61dcd9edcd"
+dependencies = [
+ "libc",
+ "winapi",
+]
+
 [[package]]
 name = "parking_lot"
 version = "0.11.2"
@@ -2161,7 +2338,7 @@ version = "0.8.5"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "d76e8e1493bcac0d2766c42737f34458f1c8c50c0d23bcb24ea953affb273216"
 dependencies = [
- "cfg-if",
+ "cfg-if 1.0.0",
  "instant",
  "libc",
  "redox_syscall",
@@ -2175,7 +2352,7 @@ version = "0.9.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "28141e0cc4143da2443301914478dc976a61ffdb3f043058310c70df2fed8954"
 dependencies = [
- "cfg-if",
+ "cfg-if 1.0.0",
  "libc",
  "redox_syscall",
  "smallvec",
@@ -2357,7 +2534,7 @@ version = "0.13.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "b7f64969ffd5dd8f39bd57a68ac53c163a095ed9d0fb707146da1b27025a3504"
 dependencies = [
- "cfg-if",
+ "cfg-if 1.0.0",
  "fnv",
  "lazy_static",
  "memchr",
@@ -2679,6 +2856,21 @@ dependencies = [
  "tokio",
 ]
 
+[[package]]
+name = "rusqlite"
+version = "0.27.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "85127183a999f7db96d1a976a309eebbfb6ea3b0b400ddd8340190129de6eb7a"
+dependencies = [
+ "bitflags",
+ "fallible-iterator",
+ "fallible-streaming-iterator",
+ "hashlink",
+ "libsqlite3-sys",
+ "memchr",
+ "smallvec",
+]
+
 [[package]]
 name = "rustc_version"
 version = "0.4.0"
@@ -2894,7 +3086,7 @@ source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "4d58a1e1bf39749807d89cf2d98ac2dfa0ff1cb3faa38fbb64dd88ac8013d800"
 dependencies = [
  "block-buffer",
- "cfg-if",
+ "cfg-if 1.0.0",
  "cpufeatures",
  "digest",
  "opaque-debug",
@@ -2929,7 +3121,7 @@ checksum = "7f96b4737c2ce5987354855aed3797279def4ebf734436c6aa4552cf8e169935"
 dependencies = [
  "crc32fast",
  "crossbeam-epoch",
- "crossbeam-utils",
+ "crossbeam-utils 0.8.8",
  "fs2",
  "fxhash",
  "libc",
@@ -3063,6 +3255,15 @@ dependencies = [
  "unicode-xid",
 ]
 
+[[package]]
+name = "synchronoise"
+version = "1.0.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "d717ed0efc9d39ab3b642a096bc369a3e02a38a51c41845d7fe31bdad1d6eaeb"
+dependencies = [
+ "crossbeam-queue",
+]
+
 [[package]]
 name = "synstructure"
 version = "0.12.6"
@@ -3081,7 +3282,7 @@ version = "3.3.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "5cdb1ef4eaeeaddc8fbd371e5017057064af0911902ef36b39801f67cc6d79e4"
 dependencies = [
- "cfg-if",
+ "cfg-if 1.0.0",
  "fastrand",
  "libc",
  "redox_syscall",
@@ -3380,7 +3581,7 @@ version = "0.1.32"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "4a1bdf54a7c28a2bbf701e1d2233f6c77f473486b94bee4f9678da5a148dca7f"
 dependencies = [
- "cfg-if",
+ "cfg-if 1.0.0",
  "log",
  "pin-project-lite",
  "tracing-attributes",
@@ -3489,6 +3690,15 @@ dependencies = [
  "percent-encoding",
 ]
 
+[[package]]
+name = "uuid"
+version = "0.8.2"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "bc5cf98d8186244414c848017f0e2676b3fcb46807f6668a97dfe67359a3c4b7"
+dependencies = [
+ "getrandom",
+]
+
 [[package]]
 name = "vcpkg"
 version = "0.2.15"
@@ -3540,7 +3750,7 @@ version = "0.2.79"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "25f1af7423d8588a3d840681122e72e6a24ddbcb3f0ec385cac0d12d24256c06"
 dependencies = [
- "cfg-if",
+ "cfg-if 1.0.0",
  "wasm-bindgen-macro",
 ]
 

Cargo.toml

@@ -1,5 +1,6 @@
 [workspace]
 members = [
+	"src/db",
 	"src/util",
 	"src/rpc",
 	"src/table",

default.nix

@@ -86,13 +86,14 @@ in let
      It speeds up the compilation (when the feature is not required) and released crates have less dependency by default (less attack surface, disk space, etc.).
      But we want to ship these additional features when we release Garage.
      In the end, we chose to exclude all features from debug builds while putting (all of) them in the release builds.
-     Currently, the only feature of Garage is kubernetes-discovery from the garage_rpc crate.
+     Currently, the only such feature of Garage is kubernetes-discovery from the garage_rpc crate.
+     The experimental feature k2v is also enabled here in all builds.
     */
     (pkgs.rustBuilder.rustLib.makeOverride {
       name = "garage_rpc";
       overrideArgs = old:
         {
-          features = if release then [ "kubernetes-discovery" ] else [];
+          features = if release then [ "kubernetes-discovery" "k2v" ] else [ "k2v" ];
         };
     })
   ];

doc/book/connect/websites.md

@@ -3,7 +3,7 @@ title = "Websites (Hugo, Jekyll, Publii...)"
 weight = 10
 +++
 
-Garage is also suitable to host static websites.
+Garage is also suitable [to host static websites](@/documentation/cookbook/exposing-websites.md).
 While they can be deployed with traditional CLI tools, some static website generators have integrated options to ease your workflow.
 
 | Name | Status | Note |

doc/book/cookbook/reverse-proxy.md

@@ -100,7 +100,7 @@ server {
 }
 ```
 
-## Exposing the web endpoint
+### Exposing the web endpoint
 
 To better understand the logic involved, you can refer to the [Exposing buckets as websites](/cookbook/exposing_websites.html) section.
 Otherwise, the configuration is very similar to the S3 endpoint.
@@ -140,6 +140,143 @@ server {
 
 @TODO
 
-## Traefik
+## Traefik v2
 
-@TODO
+We will see in this part how to set up a reverse proxy with [Traefik](https://docs.traefik.io/).
+
+Here is [a basic configuration file](https://doc.traefik.io/traefik/https/acme/#configuration-examples):
+
+```toml
+[entryPoints]
+  [entryPoints.web]
+    address = ":80"
+
+  [entryPoints.websecure]
+    address = ":443"
+
+[certificatesResolvers.myresolver.acme]
+  email = "your-email@example.com"
+  storage = "acme.json"
+  [certificatesResolvers.myresolver.acme.httpChallenge]
+    # used during the challenge
+    entryPoint = "web"
+```
+
+### Add Garage service
+
+To add Garage on Traefik you should declare a new service using its IP address (or hostname) and port:
+
+```toml
+[http.services]
+  [http.services.my_garage_service.loadBalancer]
+    [[http.services.my_garage_service.loadBalancer.servers]]
+      url = "http://xxx.xxx.xxx.xxx"
+      port = 3900
+```
+
+It's possible to declare multiple Garage servers as back-ends:
+
+```toml
+[http.services]
+    [[http.services.my_garage_service.loadBalancer.servers]]
+      url = "http://xxx.xxx.xxx.xxx"
+      port = 3900
+    [[http.services.my_garage_service.loadBalancer.servers]]
+      url = "http://yyy.yyy.yyy.yyy"
+      port = 3900
+    [[http.services.my_garage_service.loadBalancer.servers]]
+      url = "http://zzz.zzz.zzz.zzz"
+      port = 3900
+```
+
+Traefik can remove unhealthy servers automatically with [a health check configuration](https://doc.traefik.io/traefik/routing/services/#health-check):
+
+```
+[http.services]
+  [http.services.my_garage_service.loadBalancer]
+    [http.services.my_garage_service.loadBalancer.healthCheck]
+      path = "/"
+      interval = "60s"
+      timeout = "5s"
+```
+
+### Adding a website
+
+To add a new website, add the following declaration to your Traefik configuration file:
+
+```toml
+[http.routers]
+  [http.routers.my_website]
+    rule = "Host(`yoururl.example.org`)"
+    service = "my_garage_service"
+    entryPoints = ["web"]
+```
+
+Enable HTTPS access to your website with the following configuration section ([documentation](https://doc.traefik.io/traefik/https/overview/)):
+
+```toml
+...
+    entryPoints = ["websecure"]
+    [http.routers.my_website.tls]
+      certResolver = "myresolver"
+...
+```
+
+### Adding gzip compression
+
+Add the following configuration section [to compress response](https://doc.traefik.io/traefik/middlewares/http/compress/) using [gzip](https://developer.mozilla.org/en-US/docs/Glossary/GZip_compression) before sending them to the client:
+
+```toml
+[http.routers]
+  [http.routers.my_website]
+    ...
+    middlewares = ["gzip_compress"]
+    ...
+[http.middlewares]
+  [http.middlewares.gzip_compress.compress]
+```
+
+### Add caching response
+
+Traefik's caching middleware is only available on [entreprise version](https://doc.traefik.io/traefik-enterprise/middlewares/http-cache/), however the freely-available [Souin plugin](https://github.com/darkweak/souin#tr%C3%A6fik-container) can also do the job. (section to be completed)
+
+### Complete example
+
+```toml
+[entryPoints]
+  [entryPoints.web]
+    address = ":80"
+
+  [entryPoints.websecure]
+    address = ":443"
+
+[certificatesResolvers.myresolver.acme]
+  email = "your-email@example.com"
+  storage = "acme.json"
+  [certificatesResolvers.myresolver.acme.httpChallenge]
+    # used during the challenge
+    entryPoint = "web"
+
+[http.routers]
+  [http.routers.my_website]
+    rule = "Host(`yoururl.example.org`)"
+    service = "my_garage_service"
+    middlewares = ["gzip_compress"]
+    entryPoints = ["websecure"]
+
+[http.services]
+  [http.services.my_garage_service.loadBalancer]
+    [http.services.my_garage_service.loadBalancer.healthCheck]
+      path = "/"
+      interval = "60s"
+      timeout = "5s"
+    [[http.services.my_garage_service.loadBalancer.servers]]
+      url = "http://xxx.xxx.xxx.xxx"
+    [[http.services.my_garage_service.loadBalancer.servers]]
+      url = "http://yyy.yyy.yyy.yyy"
+    [[http.services.my_garage_service.loadBalancer.servers]]
+      url = "http://zzz.zzz.zzz.zzz"
+
+[http.middlewares]
+  [http.middlewares.gzip_compress.compress]
+```

doc/book/quick-start/_index.md

@@ -249,16 +249,6 @@ mc alias set \
   --api S3v4
 ```
 
-You must also add an environment variable to your configuration to
-inform MinIO of our region (`garage` by default, corresponding to the `s3_region` parameter
-in the configuration file).
-The best way is to add the following snippet to your `$HOME/.bash_profile`
-or `$HOME/.bashrc` file:
-
-```bash
-export MC_REGION=garage
-```
-
 ### Use `mc`
 
 You can not list buckets from `mc` currently.

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

@@ -134,8 +134,8 @@ Example request body:
 
 ```json
 [
-	"ec79480e0ce52ae26fd00c9da684e4fa56658d9c64cdcecb094e936de0bfe71f@10.0.0.11:3901",
+    "ec79480e0ce52ae26fd00c9da684e4fa56658d9c64cdcecb094e936de0bfe71f@10.0.0.11:3901",
-	"4a6ae5a1d0d33bf895f5bb4f0a418b7dc94c47c0dd2eb108d1158f3c8f60b0ff@10.0.0.12:3901"
+    "4a6ae5a1d0d33bf895f5bb4f0a418b7dc94c47c0dd2eb108d1158f3c8f60b0ff@10.0.0.12:3901"
 ]
 ```
 
@@ -145,14 +145,14 @@ Example response:
 
 ```json
 [
-	{
+    {
-		"success": true,
+        "success": true,
-		"error": null
+        "error": null
-	},
+    },
-	{
+    {
-		"success": false,
+        "success": false,
-		"error": "Handshake error"
+        "error": "Handshake error"
-	}
+    }
 ]
 ```
 
@@ -301,7 +301,7 @@ Request body format:
 
 ```json
 {
-	"name": "NameOfMyKey"
+    "name": "NameOfMyKey"
 }
 ```
 
@@ -313,9 +313,9 @@ Request body format:
 
 ```json
 {
-	"accessKeyId": "GK31c2f218a2e44f485b94239e",
+    "accessKeyId": "GK31c2f218a2e44f485b94239e",
-	"secretAccessKey": "b892c0665f0ada8a4755dae98baa3b133590e11dae3bcc1f9d769d67f16c3835",
+    "secretAccessKey": "b892c0665f0ada8a4755dae98baa3b133590e11dae3bcc1f9d769d67f16c3835",
-	"name": "NameOfMyKey"
+    "name": "NameOfMyKey"
 }
 ```
 
@@ -403,11 +403,11 @@ Request body format:
 
 ```json
 {
-	"name": "NameOfMyKey",
+    "name": "NameOfMyKey",
-	"allow": {
+    "allow": {
-		"createBucket": true,
+        "createBucket": true,
-	},
+    },
-	"deny": {}
+    "deny": {}
 }
 ```
 
@@ -473,24 +473,31 @@ Example response:
 
 ```json
 {
-  "id": "e6a14cd6a27f48684579ec6b381c078ab11697e6bc8513b72b2f5307e25fff9b",
+    "id": "afa8f0a22b40b1247ccd0affb869b0af5cff980924a20e4b5e0720a44deb8d39",
-  "globalAliases": [
+        "globalAliases": [],
-    "alex"
+        "websiteAccess": false,
-  ],
+        "websiteConfig": null,
-  "keys": [
+        "keys": [
-    {
+        {
-      "accessKeyId": "GK31c2f218a2e44f485b94239e",
+            "accessKeyId": "GK31c2f218a2e44f485b94239e",
-      "name": "alex",
+            "name": "Imported key",
-      "permissions": {
+            "permissions": {
-        "read": true,
+                "read": true,
-        "write": true,
+                "write": true,
-        "owner": true
+                "owner": true
-      },
+            },
-      "bucketLocalAliases": [
+            "bucketLocalAliases": [
-        "test"
+                "debug"
-      ]
+            ]
-    }
+        }
-  ]
+        ],
+        "objects": 14827,
+        "bytes": 13189855625,
+        "unfinshedUploads": 0,
+        "quotas": {
+            "maxSize": null,
+            "maxObjects": null
+        }
 }
 ```
 
@@ -502,7 +509,7 @@ Request body format:
 
 ```json
 {
-	"globalAlias": "NameOfMyBucket"
+    "globalAlias": "NameOfMyBucket"
 }
 ```
 
@@ -510,15 +517,15 @@ OR
 
 ```json
 {
-	"localAlias": {
+    "localAlias": {
-		"accessKeyId": "GK31c2f218a2e44f485b94239e",
+        "accessKeyId": "GK31c2f218a2e44f485b94239e",
-		"alias": "NameOfMyBucket",
+        "alias": "NameOfMyBucket",
-		"allow": {
+        "allow": {
-			"read": true,
+            "read": true,
-			"write": true,
+            "write": true,
-			"owner": false
+            "owner": false
-		}
+        }
-	}
+    }
 }
 ```
 
@@ -540,26 +547,37 @@ Deletes a storage bucket. A bucket cannot be deleted if it is not empty.
 
 Warning: this will delete all aliases associated with the bucket!
 
-#### PutBucketWebsite `PUT /v0/bucket/website?id=<bucket id>`
+#### UpdateBucket `PUT /v0/bucket?id=<bucket id>`
 
-Sets the website configuration for a bucket (this also enables website access for this bucket).
+Updates configuration of the given bucket.
 
 Request body format:
 
 ```json
 {
-	"indexDocument": "index.html",
+    "websiteAccess": {
-	"errorDocument": "404.html"
+        "enabled": true,
+        "indexDocument": "index.html",
+        "errorDocument": "404.html"
+    },
+    "quotas": {
+        "maxSize": 19029801,
+        "maxObjects": null,
+    }
 }
 ```
 
-The field `errorDocument` is optional, if no error document is set a generic error message is displayed when errors happen.
+All fields (`websiteAccess` and `quotas`) are optionnal.
+If they are present, the corresponding modifications are applied to the bucket, otherwise nothing is changed.
 
+In `websiteAccess`: if `enabled` is `true`, `indexDocument` must be specified.
+The field `errorDocument` is optional, if no error document is set a generic
+error message is displayed when errors happen. Conversely, if `enabled` is
+`false`, neither `indexDocument` nor `errorDocument` must be specified.
 
-#### DeleteBucketWebsite `DELETE /v0/bucket/website?id=<bucket id>`
+In `quotas`: new values of `maxSize` and `maxObjects` must both be specified, or set to `null`
-
+to remove the quotas. An absent value will be considered the same as a `null`. It is not possible
-Deletes the website configuration for a bucket (disables website access for this bucket).
+to change only one of the two quotas.
-
 
 ### Operations on permissions for keys on buckets
 
@@ -571,13 +589,13 @@ Request body format:
 
 ```json
 {
-	"bucketId": "e6a14cd6a27f48684579ec6b381c078ab11697e6bc8513b72b2f5307e25fff9b",
+    "bucketId": "e6a14cd6a27f48684579ec6b381c078ab11697e6bc8513b72b2f5307e25fff9b",
-	"accessKeyId": "GK31c2f218a2e44f485b94239e",
+    "accessKeyId": "GK31c2f218a2e44f485b94239e",
-	"permissions": {
+    "permissions": {
-		"read": true,
+        "read": true,
-		"write": true,
+        "write": true,
-		"owner": true
+        "owner": true
-	},
+    },
 }
 ```
 
@@ -592,13 +610,13 @@ Request body format:
 
 ```json
 {
-	"bucketId": "e6a14cd6a27f48684579ec6b381c078ab11697e6bc8513b72b2f5307e25fff9b",
+    "bucketId": "e6a14cd6a27f48684579ec6b381c078ab11697e6bc8513b72b2f5307e25fff9b",
-	"accessKeyId": "GK31c2f218a2e44f485b94239e",
+    "accessKeyId": "GK31c2f218a2e44f485b94239e",
-	"permissions": {
+    "permissions": {
-		"read": false,
+        "read": false,
-		"write": false,
+        "write": false,
-		"owner": true
+        "owner": true
-	},
+    },
 }
 ```
 

src/api/admin/api_server.rs

@@ -156,12 +156,7 @@ impl ApiHandler for AdminApiServer {
 			}
 			Endpoint::CreateBucket => handle_create_bucket(&self.garage, req).await,
 			Endpoint::DeleteBucket { id } => handle_delete_bucket(&self.garage, id).await,
-			Endpoint::PutBucketWebsite { id } => {
+			Endpoint::UpdateBucket { id } => handle_update_bucket(&self.garage, id, req).await,
-				handle_put_bucket_website(&self.garage, id, req).await
-			}
-			Endpoint::DeleteBucketWebsite { id } => {
-				handle_delete_bucket_website(&self.garage, id).await
-			}
 			// Bucket-key permissions
 			Endpoint::BucketAllowKey => {
 				handle_bucket_change_key_perm(&self.garage, req, true).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::object_table::*;
 
 use crate::admin::error::*;
 use crate::admin::key::ApiBucketKeyPerm;
@@ -77,6 +78,13 @@ struct BucketLocalAlias {
 	alias: String,
 }
 
+#[derive(Serialize, Deserialize)]
+#[serde(rename_all = "camelCase")]
+struct ApiBucketQuotas {
+	max_size: Option<u64>,
+	max_objects: Option<u64>,
+}
+
 pub async fn handle_get_bucket_info(
 	garage: &Arc<Garage>,
 	id: Option<String>,
@@ -108,6 +116,14 @@ async fn bucket_info_results(
 		.get_existing_bucket(bucket_id)
 		.await?;
 
+	let counters = garage
+		.object_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
@@ -148,6 +164,7 @@ async fn bucket_info_results(
 
 	let state = bucket.state.as_option().unwrap();
 
+	let quotas = state.quotas.get();
 	let res =
 		GetBucketInfoResult {
 			id: hex::encode(&bucket.id),
@@ -191,6 +208,16 @@ async fn bucket_info_results(
 					}
 				})
 				.collect::<Vec<_>>(),
+			objects: counters.get(OBJECTS).cloned().unwrap_or_default(),
+			bytes: counters.get(BYTES).cloned().unwrap_or_default(),
+			unfinshed_uploads: counters
+				.get(UNFINISHED_UPLOADS)
+				.cloned()
+				.unwrap_or_default(),
+			quotas: ApiBucketQuotas {
+				max_size: quotas.max_size,
+				max_objects: quotas.max_objects,
+			},
 		};
 
 	Ok(json_ok_response(&res)?)
@@ -205,6 +232,10 @@ struct GetBucketInfoResult {
 	#[serde(default)]
 	website_config: Option<GetBucketInfoWebsiteResult>,
 	keys: Vec<GetBucketInfoKey>,
+	objects: i64,
+	bytes: i64,
+	unfinshed_uploads: i64,
+	quotas: ApiBucketQuotas,
 }
 
 #[derive(Serialize)]
@@ -363,14 +394,12 @@ pub async fn handle_delete_bucket(
 		.body(Body::empty())?)
 }
 
-// ---- BUCKET WEBSITE CONFIGURATION ----
+pub async fn handle_update_bucket(
-
-pub async fn handle_put_bucket_website(
 	garage: &Arc<Garage>,
 	id: String,
 	req: Request<Body>,
 ) -> Result<Response<Body>, Error> {
-	let req = parse_json_body::<PutBucketWebsiteRequest>(req).await?;
+	let req = parse_json_body::<UpdateBucketRequest>(req).await?;
 	let bucket_id = parse_bucket_id(&id)?;
 
 	let mut bucket = garage
@@ -379,10 +408,31 @@ pub async fn handle_put_bucket_website(
 		.await?;
 
 	let state = bucket.state.as_option_mut().unwrap();
-	state.website_config.update(Some(WebsiteConfig {
+
-		index_document: req.index_document,
+	if let Some(wa) = req.website_access {
-		error_document: req.error_document,
+		if wa.enabled {
-	}));
+			state.website_config.update(Some(WebsiteConfig {
+				index_document: wa.index_document.ok_or_bad_request(
+					"Please specify indexDocument when enabling website access.",
+				)?,
+				error_document: wa.error_document,
+			}));
+		} else {
+			if wa.index_document.is_some() || wa.error_document.is_some() {
+				return Err(Error::bad_request(
+					"Cannot specify indexDocument or errorDocument when disabling website access.",
+				));
+			}
+			state.website_config.update(None);
+		}
+	}
+
+	if let Some(q) = req.quotas {
+		state.quotas.update(BucketQuotas {
+			max_size: q.max_size,
+			max_objects: q.max_objects,
+		});
+	}
 
 	garage.bucket_table.insert(&bucket).await?;
 
@@ -391,29 +441,17 @@ pub async fn handle_put_bucket_website(
 
 #[derive(Deserialize)]
 #[serde(rename_all = "camelCase")]
-struct PutBucketWebsiteRequest {
+struct UpdateBucketRequest {
-	index_document: String,
+	website_access: Option<UpdateBucketWebsiteAccess>,
-	#[serde(default)]
+	quotas: Option<ApiBucketQuotas>,
-	error_document: Option<String>,
 }
 
-pub async fn handle_delete_bucket_website(
+#[derive(Deserialize)]
-	garage: &Arc<Garage>,
+#[serde(rename_all = "camelCase")]
-	id: String,
+struct UpdateBucketWebsiteAccess {
-) -> Result<Response<Body>, Error> {
+	enabled: bool,
-	let bucket_id = parse_bucket_id(&id)?;
+	index_document: Option<String>,
-
+	error_document: Option<String>,
-	let mut bucket = garage
-		.bucket_helper()
-		.get_existing_bucket(bucket_id)
-		.await?;
-
-	let state = bucket.state.as_option_mut().unwrap();
-	state.website_config.update(None);
-
-	garage.bucket_table.insert(&bucket).await?;
-
-	bucket_info_results(garage, bucket_id).await
 }
 
 // ---- BUCKET/KEY PERMISSIONS ----

src/api/admin/cluster.rs

@@ -19,6 +19,7 @@ pub async fn handle_get_cluster_status(garage: &Arc<Garage>) -> Result<Response<
 	let res = GetClusterStatusResponse {
 		node: hex::encode(garage.system.id),
 		garage_version: garage.system.garage_version(),
+		db_engine: garage.db.engine(),
 		known_nodes: garage
 			.system
 			.get_known_nodes()
@@ -98,6 +99,7 @@ fn get_cluster_layout(garage: &Arc<Garage>) -> GetClusterLayoutResponse {
 struct GetClusterStatusResponse {
 	node: String,
 	garage_version: &'static str,
+	db_engine: String,
 	known_nodes: HashMap<String, KnownNodeResp>,
 	layout: GetClusterLayoutResponse,
 }

src/api/admin/router.rs

@@ -48,10 +48,7 @@ pub enum Endpoint {
 	DeleteBucket {
 		id: String,
 	},
-	PutBucketWebsite {
+	UpdateBucket {
-		id: String,
-	},
-	DeleteBucketWebsite {
 		id: String,
 	},
 	// Bucket-Key Permissions
@@ -113,8 +110,7 @@ impl Endpoint {
 			GET "/v0/bucket" => ListBuckets,
 			POST "/v0/bucket" => CreateBucket,
 			DELETE "/v0/bucket" if id => DeleteBucket (query::id),
-			PUT "/v0/bucket/website" if id => PutBucketWebsite (query::id),
+			PUT "/v0/bucket" if id => UpdateBucket (query::id),
-			DELETE "/v0/bucket/website" if id => DeleteBucketWebsite (query::id),
 			// Bucket-key permissions
 			POST "/v0/bucket/allow" => BucketAllowKey,
 			POST "/v0/bucket/deny" => BucketDenyKey,

src/api/k2v/index.rs

@@ -10,7 +10,7 @@ use garage_rpc::ring::Ring;
 use garage_table::util::*;
 
 use garage_model::garage::Garage;
-use garage_model::k2v::counter_table::{BYTES, CONFLICTS, ENTRIES, VALUES};
+use garage_model::k2v::item_table::{BYTES, CONFLICTS, ENTRIES, VALUES};
 
 use crate::k2v::error::*;
 use crate::k2v::range::read_range;

src/api/s3/api_server.rs

@@ -4,7 +4,7 @@ use async_trait::async_trait;
 
 use futures::future::Future;
 use hyper::header;
-use hyper::{Body, Method, Request, Response};
+use hyper::{Body, Request, Response};
 
 use opentelemetry::{trace::SpanRef, KeyValue};
 
@@ -167,14 +167,7 @@ impl ApiHandler for S3ApiServer {
 			return Err(Error::forbidden("Operation is not allowed for this key."));
 		}
 
-		// Look up what CORS rule might apply to response.
+		let matching_cors_rule = find_matching_cors_rule(&bucket, &req)?;
-		// Requests for methods different than GET, HEAD or POST
-		// are always preflighted, i.e. the browser should make
-		// an OPTIONS call before to check it is allowed
-		let matching_cors_rule = match *req.method() {
-			Method::GET | Method::HEAD | Method::POST => find_matching_cors_rule(&bucket, &req)?,
-			_ => None,
-		};
 
 		let resp = match endpoint {
 			Endpoint::HeadObject {
@@ -219,7 +212,7 @@ impl ApiHandler for S3ApiServer {
 				.await
 			}
 			Endpoint::PutObject { key } => {
-				handle_put(garage, req, bucket_id, &key, content_sha256).await
+				handle_put(garage, req, &bucket, &key, content_sha256).await
 			}
 			Endpoint::AbortMultipartUpload { key, upload_id } => {
 				handle_abort_multipart_upload(garage, bucket_id, &key, &upload_id).await
@@ -233,7 +226,7 @@ impl ApiHandler for S3ApiServer {
 					garage,
 					req,
 					&bucket_name,
-					bucket_id,
+					&bucket,
 					&key,
 					&upload_id,
 					content_sha256,

src/api/s3/post_object.rs

@@ -22,7 +22,7 @@ use crate::signature::payload::{parse_date, verify_v4};
 pub async fn handle_post_object(
 	garage: Arc<Garage>,
 	req: Request<Body>,
-	bucket: String,
+	bucket_name: String,
 ) -> Result<Response<Body>, Error> {
 	let boundary = req
 		.headers()
@@ -126,13 +126,18 @@ pub async fn handle_post_object(
 
 	let bucket_id = garage
 		.bucket_helper()
-		.resolve_bucket(&bucket, &api_key)
+		.resolve_bucket(&bucket_name, &api_key)
 		.await?;
 
 	if !api_key.allow_write(&bucket_id) {
 		return Err(Error::forbidden("Operation is not allowed for this key."));
 	}
 
+	let bucket = garage
+		.bucket_helper()
+		.get_existing_bucket(bucket_id)
+		.await?;
+
 	let decoded_policy = base64::decode(&policy).ok_or_bad_request("Invalid policy")?;
 	let decoded_policy: Policy =
 		serde_json::from_slice(&decoded_policy).ok_or_bad_request("Invalid policy")?;
@@ -227,7 +232,7 @@ pub async fn handle_post_object(
 		garage,
 		headers,
 		StreamLimiter::new(stream, conditions.content_length),
-		bucket_id,
+		&bucket,
 		&key,
 		None,
 		None,
@@ -244,7 +249,7 @@ pub async fn handle_post_object(
 	{
 		target
 			.query_pairs_mut()
-			.append_pair("bucket", &bucket)
+			.append_pair("bucket", &bucket_name)
 			.append_pair("key", &key)
 			.append_pair("etag", &etag);
 		let target = target.to_string();
@@ -289,7 +294,7 @@ pub async fn handle_post_object(
 				let xml = s3_xml::PostObject {
 					xmlns: (),
 					location: s3_xml::Value(location),
-					bucket: s3_xml::Value(bucket),
+					bucket: s3_xml::Value(bucket_name),
 					key: s3_xml::Value(key),
 					etag: s3_xml::Value(etag),
 				};

src/api/s3/put.rs

@@ -1,4 +1,4 @@
-use std::collections::{BTreeMap, BTreeSet, VecDeque};
+use std::collections::{BTreeMap, BTreeSet, HashMap, VecDeque};
 use std::sync::Arc;
 
 use futures::prelude::*;
@@ -14,7 +14,9 @@ use garage_util::error::Error as GarageError;
 use garage_util::time::*;
 
 use garage_block::manager::INLINE_THRESHOLD;
+use garage_model::bucket_table::Bucket;
 use garage_model::garage::Garage;
+use garage_model::index_counter::CountedItem;
 use garage_model::s3::block_ref_table::*;
 use garage_model::s3::object_table::*;
 use garage_model::s3::version_table::*;
@@ -26,7 +28,7 @@ use crate::signature::verify_signed_content;
 pub async fn handle_put(
 	garage: Arc<Garage>,
 	req: Request<Body>,
-	bucket_id: Uuid,
+	bucket: &Bucket,
 	key: &str,
 	content_sha256: Option<Hash>,
 ) -> Result<Response<Body>, Error> {
@@ -46,7 +48,7 @@ pub async fn handle_put(
 		garage,
 		headers,
 		body,
-		bucket_id,
+		bucket,
 		key,
 		content_md5,
 		content_sha256,
@@ -59,7 +61,7 @@ pub(crate) async fn save_stream<S: Stream<Item = Result<Bytes, Error>> + Unpin>(
 	garage: Arc<Garage>,
 	headers: ObjectVersionHeaders,
 	body: S,
-	bucket_id: Uuid,
+	bucket: &Bucket,
 	key: &str,
 	content_md5: Option<String>,
 	content_sha256: Option<FixedBytes32>,
@@ -80,6 +82,7 @@ pub(crate) async fn save_stream<S: Stream<Item = Result<Bytes, Error>> + Unpin>(
 		let data_md5sum_hex = hex::encode(data_md5sum);
 
 		let data_sha256sum = sha256sum(&first_block[..]);
+		let size = first_block.len() as u64;
 
 		ensure_checksum_matches(
 			data_md5sum.as_slice(),
@@ -88,20 +91,22 @@ pub(crate) async fn save_stream<S: Stream<Item = Result<Bytes, Error>> + Unpin>(
 			content_sha256,
 		)?;
 
+		check_quotas(&garage, bucket, key, size).await?;
+
 		let object_version = ObjectVersion {
 			uuid: version_uuid,
 			timestamp: version_timestamp,
 			state: ObjectVersionState::Complete(ObjectVersionData::Inline(
 				ObjectVersionMeta {
 					headers,
-					size: first_block.len() as u64,
+					size,
 					etag: data_md5sum_hex.clone(),
 				},
 				first_block,
 			)),
 		};
 
-		let object = Object::new(bucket_id, key.into(), vec![object_version]);
+		let object = Object::new(bucket.id, key.into(), vec![object_version]);
 		garage.object_table.insert(&object).await?;
 
 		return Ok((version_uuid, data_md5sum_hex));
@@ -114,36 +119,42 @@ pub(crate) async fn save_stream<S: Stream<Item = Result<Bytes, Error>> + Unpin>(
 		timestamp: version_timestamp,
 		state: ObjectVersionState::Uploading(headers.clone()),
 	};
-	let object = Object::new(bucket_id, key.into(), vec![object_version.clone()]);
+	let object = Object::new(bucket.id, key.into(), vec![object_version.clone()]);
 	garage.object_table.insert(&object).await?;
 
 	// Initialize corresponding entry in version table
 	// 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, bucket.id, key.into(), false);
 	garage.version_table.insert(&version).await?;
 
 	// Transfer data and verify checksum
 	let first_block_hash = blake2sum(&first_block[..]);
-	let tx_result = read_and_put_blocks(
+
-		&garage,
+	let tx_result = (|| async {
-		&version,
+		let (total_size, data_md5sum, data_sha256sum) = read_and_put_blocks(
-		1,
+			&garage,
-		first_block,
+			&version,
-		first_block_hash,
+			1,
-		&mut chunker,
+			first_block,
-	)
+			first_block_hash,
-	.await
+			&mut chunker,
-	.and_then(|(total_size, data_md5sum, data_sha256sum)| {
+		)
+		.await?;
+
 		ensure_checksum_matches(
 			data_md5sum.as_slice(),
 			data_sha256sum,
 			content_md5.as_deref(),
 			content_sha256,
-		)
+		)?;
-		.map(|()| (total_size, data_md5sum))
+
-	});
+		check_quotas(&garage, bucket, key, total_size).await?;
+
+		Ok((total_size, data_md5sum))
+	})()
+	.await;
 
 	// If something went wrong, clean up
 	let (total_size, md5sum_arr) = match tx_result {
@@ -151,7 +162,7 @@ pub(crate) async fn save_stream<S: Stream<Item = Result<Bytes, Error>> + Unpin>(
 		Err(e) => {
 			// Mark object as aborted, this will free the blocks further down
 			object_version.state = ObjectVersionState::Aborted;
-			let object = Object::new(bucket_id, key.into(), vec![object_version.clone()]);
+			let object = Object::new(bucket.id, key.into(), vec![object_version.clone()]);
 			garage.object_table.insert(&object).await?;
 			return Err(e);
 		}
@@ -167,7 +178,7 @@ pub(crate) async fn save_stream<S: Stream<Item = Result<Bytes, Error>> + Unpin>(
 		},
 		first_block_hash,
 	));
-	let object = Object::new(bucket_id, key.into(), vec![object_version]);
+	let object = Object::new(bucket.id, key.into(), vec![object_version]);
 	garage.object_table.insert(&object).await?;
 
 	Ok((version_uuid, md5sum_hex))
@@ -200,6 +211,64 @@ fn ensure_checksum_matches(
 	Ok(())
 }
 
+/// Check that inserting this object with this size doesn't exceed bucket quotas
+async fn check_quotas(
+	garage: &Arc<Garage>,
+	bucket: &Bucket,
+	key: &str,
+	size: u64,
+) -> 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 = counters
+		.map(|x| x.filtered_values(&garage.system.ring.borrow()))
+		.unwrap_or_default();
+
+	let (prev_cnt_obj, prev_cnt_size) = match prev_object {
+		Some(o) => {
+			let prev_cnt = o.counts().into_iter().collect::<HashMap<_, _>>();
+			(
+				prev_cnt.get(OBJECTS).cloned().unwrap_or_default(),
+				prev_cnt.get(BYTES).cloned().unwrap_or_default(),
+			)
+		}
+		None => (0, 0),
+	};
+	let cnt_obj_diff = 1 - prev_cnt_obj;
+	let cnt_size_diff = size as i64 - prev_cnt_size;
+
+	if let Some(mo) = quotas.max_objects {
+		let current_objects = counters.get(OBJECTS).cloned().unwrap_or_default();
+		if cnt_obj_diff > 0 && current_objects + cnt_obj_diff > mo as i64 {
+			return Err(Error::forbidden(format!(
+				"Object quota is reached, maximum objects for this bucket: {}",
+				mo
+			)));
+		}
+	}
+
+	if let Some(ms) = quotas.max_size {
+		let current_size = counters.get(BYTES).cloned().unwrap_or_default();
+		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
+			)));
+		}
+	}
+
+	Ok(())
+}
+
 async fn read_and_put_blocks<S: Stream<Item = Result<Bytes, Error>> + Unpin>(
 	garage: &Garage,
 	version: &Version,
@@ -473,7 +542,7 @@ pub async fn handle_complete_multipart_upload(
 	garage: Arc<Garage>,
 	req: Request<Body>,
 	bucket_name: &str,
-	bucket_id: Uuid,
+	bucket: &Bucket,
 	key: &str,
 	upload_id: &str,
 	content_sha256: Option<Hash>,
@@ -497,7 +566,7 @@ pub async fn handle_complete_multipart_upload(
 	// Get object and version
 	let key = key.to_string();
 	let (object, version) = futures::try_join!(
-		garage.object_table.get(&bucket_id, &key),
+		garage.object_table.get(&bucket.id, &key),
 		garage.version_table.get(&version_uuid, &EmptyKey),
 	)?;
 
@@ -590,6 +659,14 @@ pub async fn handle_complete_multipart_upload(
 	// 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 {
@@ -600,7 +677,7 @@ pub async fn handle_complete_multipart_upload(
 		version.blocks.items()[0].1.hash,
 	));
 
-	let final_object = Object::new(bucket_id, key.clone(), vec![object_version]);
+	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

src/block/Cargo.toml

@@ -14,6 +14,7 @@ path = "lib.rs"
 # See more keys and their definitions at https://doc.rust-lang.org/cargo/reference/manifest.html
 
 [dependencies]
+garage_db = { version = "0.8.0", path = "../db" }
 garage_rpc = { version = "0.7.0", path = "../rpc" }
 garage_util = { version = "0.7.0", path = "../util" }
 garage_table = { version = "0.7.0", path = "../table" }
@@ -27,8 +28,6 @@ tracing = "0.1.30"
 rand = "0.8"
 zstd = { version = "0.9", default-features = false }
 
-sled = "0.34"
-
 rmp-serde = "0.15"
 serde = { version = "1.0", default-features = false, features = ["derive", "rc"] }
 serde_bytes = "0.11"

src/block/manager.rs

@@ -1,3 +1,5 @@
+use core::ops::Bound;
+
 use std::convert::TryInto;
 use std::path::{Path, PathBuf};
 use std::sync::Arc;
@@ -17,10 +19,12 @@ use opentelemetry::{
 	Context, KeyValue,
 };
 
+use garage_db as db;
+use garage_db::counted_tree_hack::CountedTree;
+
 use garage_util::data::*;
 use garage_util::error::*;
 use garage_util::metrics::RecordDuration;
-use garage_util::sled_counter::SledCountedTree;
 use garage_util::time::*;
 use garage_util::tranquilizer::Tranquilizer;
 
@@ -91,9 +95,9 @@ pub struct BlockManager {
 
 	rc: BlockRc,
 
-	resync_queue: SledCountedTree,
+	resync_queue: CountedTree,
 	resync_notify: Notify,
-	resync_errors: SledCountedTree,
+	resync_errors: CountedTree,
 
 	system: Arc<System>,
 	endpoint: Arc<Endpoint<BlockRpc, Self>>,
@@ -108,7 +112,7 @@ struct BlockManagerLocked();
 
 impl BlockManager {
 	pub fn new(
-		db: &sled::Db,
+		db: &db::Db,
 		data_dir: PathBuf,
 		compression_level: Option<i32>,
 		background_tranquility: u32,
@@ -123,12 +127,14 @@ impl BlockManager {
 		let resync_queue = db
 			.open_tree("block_local_resync_queue")
 			.expect("Unable to open block_local_resync_queue tree");
-		let resync_queue = SledCountedTree::new(resync_queue);
+		let resync_queue =
+			CountedTree::new(resync_queue).expect("Could not count block_local_resync_queue");
 
 		let resync_errors = db
 			.open_tree("block_local_resync_errors")
 			.expect("Unable to open block_local_resync_errors tree");
-		let resync_errors = SledCountedTree::new(resync_errors);
+		let resync_errors =
+			CountedTree::new(resync_errors).expect("Could not count block_local_resync_errors");
 
 		let endpoint = system
 			.netapp
@@ -219,11 +225,44 @@ impl BlockManager {
 	/// to fix any mismatch between the two.
 	pub async fn repair_data_store(&self, must_exit: &watch::Receiver<bool>) -> Result<(), Error> {
 		// 1. Repair blocks from RC table.
-		for (i, entry) in self.rc.rc.iter().enumerate() {
+		let mut next_start: Option<Hash> = None;
-			let (hash, _) = entry?;
+		loop {
-			let hash = Hash::try_from(&hash[..]).unwrap();
+			// We have to do this complicated two-step process where we first read a bunch
-			self.put_to_resync(&hash, Duration::from_secs(0))?;
+			// of hashes from the RC table, and then insert them in the to-resync queue,
-			if i & 0xFF == 0 && *must_exit.borrow() {
+			// because of SQLite. Basically, as long as we have an iterator on a DB table,
+			// we can't do anything else on the DB. The naive approach (which we had previously)
+			// of just iterating on the RC table and inserting items one to one in the resync
+			// queue can't work here, it would just provoke a deadlock in the SQLite adapter code.
+			// This is mostly because the Rust bindings for SQLite assume a worst-case scenario
+			// where SQLite is not compiled in thread-safe mode, so we have to wrap everything
+			// in a mutex (see db/sqlite_adapter.rs and discussion in PR #322).
+			let mut batch_of_hashes = vec![];
+			let start_bound = match next_start.as_ref() {
+				None => Bound::Unbounded,
+				Some(x) => Bound::Excluded(x.as_slice()),
+			};
+			for entry in self
+				.rc
+				.rc
+				.range::<&[u8], _>((start_bound, Bound::Unbounded))?
+			{
+				let (hash, _) = entry?;
+				let hash = Hash::try_from(&hash[..]).unwrap();
+				batch_of_hashes.push(hash);
+				if batch_of_hashes.len() >= 1000 {
+					break;
+				}
+			}
+			if batch_of_hashes.is_empty() {
+				break;
+			}
+
+			for hash in batch_of_hashes.into_iter() {
+				self.put_to_resync(&hash, Duration::from_secs(0))?;
+				next_start = Some(hash)
+			}
+
+			if *must_exit.borrow() {
 				return Ok(());
 			}
 		}
@@ -264,46 +303,69 @@ impl BlockManager {
 	}
 
 	/// Get lenght of resync queue
-	pub fn resync_queue_len(&self) -> usize {
+	pub fn resync_queue_len(&self) -> Result<usize, Error> {
-		self.resync_queue.len()
+		// This currently can't return an error because the CountedTree hack
+		// doesn't error on .len(), but this will change when we remove the hack
+		// (hopefully someday!)
+		Ok(self.resync_queue.len())
 	}
 
 	/// Get number of blocks that have an error
-	pub fn resync_errors_len(&self) -> usize {
+	pub fn resync_errors_len(&self) -> Result<usize, Error> {
-		self.resync_errors.len()
+		// (see resync_queue_len comment)
+		Ok(self.resync_errors.len())
 	}
 
 	/// Get number of items in the refcount table
-	pub fn rc_len(&self) -> usize {
+	pub fn rc_len(&self) -> Result<usize, Error> {
-		self.rc.rc.len()
+		Ok(self.rc.rc.len()?)
 	}
 
 	//// ----- Managing the reference counter ----
 
 	/// Increment the number of time a block is used, putting it to resynchronization if it is
 	/// required, but not known
-	pub fn block_incref(&self, hash: &Hash) -> Result<(), Error> {
+	pub fn block_incref(
-		if self.rc.block_incref(hash)? {
+		self: &Arc<Self>,
+		tx: &mut db::Transaction,
+		hash: Hash,
+	) -> db::TxOpResult<()> {
+		if self.rc.block_incref(tx, &hash)? {
 			// When the reference counter is incremented, there is
 			// normally a node that is responsible for sending us the
 			// data of the block. However that operation may fail,
 			// so in all cases we add the block here to the todo list
 			// to check later that it arrived correctly, and if not
 			// we will fecth it from someone.
-			self.put_to_resync(hash, 2 * BLOCK_RW_TIMEOUT)?;
+			let this = self.clone();
+			tokio::spawn(async move {
+				if let Err(e) = this.put_to_resync(&hash, 2 * BLOCK_RW_TIMEOUT) {
+					error!("Block {:?} could not be put in resync queue: {}.", hash, e);
+				}
+			});
 		}
 		Ok(())
 	}
 
 	/// Decrement the number of time a block is used
-	pub fn block_decref(&self, hash: &Hash) -> Result<(), Error> {
+	pub fn block_decref(
-		if self.rc.block_decref(hash)? {
+		self: &Arc<Self>,
+		tx: &mut db::Transaction,
+		hash: Hash,
+	) -> db::TxOpResult<()> {
+		if self.rc.block_decref(tx, &hash)? {
 			// When the RC is decremented, it might drop to zero,
 			// indicating that we don't need the block.
 			// There is a delay before we garbage collect it;
 			// make sure that it is handled in the resync loop
 			// after that delay has passed.
-			self.put_to_resync(hash, BLOCK_GC_DELAY + Duration::from_secs(10))?;
+			let this = self.clone();
+			tokio::spawn(async move {
+				if let Err(e) = this.put_to_resync(&hash, BLOCK_GC_DELAY + Duration::from_secs(10))
+				{
+					error!("Block {:?} could not be put in resync queue: {}.", hash, e);
+				}
+			});
 		}
 		Ok(())
 	}
@@ -503,12 +565,12 @@ impl BlockManager {
 		});
 	}
 
-	fn put_to_resync(&self, hash: &Hash, delay: Duration) -> Result<(), sled::Error> {
+	fn put_to_resync(&self, hash: &Hash, delay: Duration) -> db::Result<()> {
 		let when = now_msec() + delay.as_millis() as u64;
 		self.put_to_resync_at(hash, when)
 	}
 
-	fn put_to_resync_at(&self, hash: &Hash, when: u64) -> Result<(), sled::Error> {
+	fn put_to_resync_at(&self, hash: &Hash, when: u64) -> db::Result<()> {
 		trace!("Put resync_queue: {} {:?}", when, hash);
 		let mut key = u64::to_be_bytes(when).to_vec();
 		key.extend(hash.as_ref());
@@ -547,13 +609,8 @@ impl BlockManager {
 	// - Ok(true) -> a block was processed (successfully or not)
 	// - Ok(false) -> no block was processed, but we are ready for the next iteration
 	// - Err(_) -> a Sled error occurred when reading/writing from resync_queue/resync_errors
-	async fn resync_iter(
+	async fn resync_iter(&self, must_exit: &mut watch::Receiver<bool>) -> Result<bool, db::Error> {
-		&self,
+		if let Some((time_bytes, hash_bytes)) = self.resync_queue.first()? {
-		must_exit: &mut watch::Receiver<bool>,
-	) -> Result<bool, sled::Error> {
-		if let Some(first_pair_res) = self.resync_queue.iter().next() {
-			let (time_bytes, hash_bytes) = first_pair_res?;
-
 			let time_msec = u64::from_be_bytes(time_bytes[0..8].try_into().unwrap());
 			let now = now_msec();
 
@@ -561,7 +618,7 @@ impl BlockManager {
 				let hash = Hash::try_from(&hash_bytes[..]).unwrap();
 
 				if let Some(ec) = self.resync_errors.get(hash.as_slice())? {
-					let ec = ErrorCounter::decode(ec);
+					let ec = ErrorCounter::decode(&ec);
 					if now < ec.next_try() {
 						// if next retry after an error is not yet,
 						// don't do resync and return early, but still
@@ -602,7 +659,7 @@ impl BlockManager {
 					warn!("Error when resyncing {:?}: {}", hash, e);
 
 					let err_counter = match self.resync_errors.get(hash.as_slice())? {
-						Some(ec) => ErrorCounter::decode(ec).add1(now + 1),
+						Some(ec) => ErrorCounter::decode(&ec).add1(now + 1),
 						None => ErrorCounter::new(now + 1),
 					};
 
@@ -966,7 +1023,7 @@ impl ErrorCounter {
 		}
 	}
 
-	fn decode(data: sled::IVec) -> Self {
+	fn decode(data: &[u8]) -> Self {
 		Self {
 			errors: u64::from_be_bytes(data[0..8].try_into().unwrap()),
 			last_try: u64::from_be_bytes(data[8..16].try_into().unwrap()),

src/block/metrics.rs

@@ -1,6 +1,6 @@
 use opentelemetry::{global, metrics::*};
 
-use garage_util::sled_counter::SledCountedTree;
+use garage_db::counted_tree_hack::CountedTree;
 
 /// TableMetrics reference all counter used for metrics
 pub struct BlockManagerMetrics {
@@ -23,7 +23,7 @@ pub struct BlockManagerMetrics {
 }
 
 impl BlockManagerMetrics {
-	pub fn new(resync_queue: SledCountedTree, resync_errors: SledCountedTree) -> Self {
+	pub fn new(resync_queue: CountedTree, resync_errors: CountedTree) -> Self {
 		let meter = global::meter("garage_model/block");
 		Self {
 			_resync_queue_len: meter

src/block/rc.rs

@@ -1,5 +1,7 @@
 use std::convert::TryInto;
 
+use garage_db as db;
+
 use garage_util::data::*;
 use garage_util::error::*;
 use garage_util::time::*;
@@ -7,31 +9,41 @@ use garage_util::time::*;
 use crate::manager::BLOCK_GC_DELAY;
 
 pub struct BlockRc {
-	pub(crate) rc: sled::Tree,
+	pub(crate) rc: db::Tree,
 }
 
 impl BlockRc {
-	pub(crate) fn new(rc: sled::Tree) -> Self {
+	pub(crate) fn new(rc: db::Tree) -> Self {
 		Self { rc }
 	}
 
 	/// Increment the reference counter associated to a hash.
 	/// Returns true if the RC goes from zero to nonzero.
-	pub(crate) fn block_incref(&self, hash: &Hash) -> Result<bool, Error> {
+	pub(crate) fn block_incref(
-		let old_rc = self
+		&self,
-			.rc
+		tx: &mut db::Transaction,
-			.fetch_and_update(&hash, |old| RcEntry::parse_opt(old).increment().serialize())?;
+		hash: &Hash,
-		let old_rc = RcEntry::parse_opt(old_rc);
+	) -> db::TxOpResult<bool> {
+		let old_rc = RcEntry::parse_opt(tx.get(&self.rc, &hash)?);
+		match old_rc.increment().serialize() {
+			Some(x) => tx.insert(&self.rc, &hash, x)?,
+			None => unreachable!(),
+		};
 		Ok(old_rc.is_zero())
 	}
 
 	/// Decrement the reference counter associated to a hash.
 	/// Returns true if the RC is now zero.
-	pub(crate) fn block_decref(&self, hash: &Hash) -> Result<bool, Error> {
+	pub(crate) fn block_decref(
-		let new_rc = self
+		&self,
-			.rc
+		tx: &mut db::Transaction,
-			.update_and_fetch(&hash, |old| RcEntry::parse_opt(old).decrement().serialize())?;
+		hash: &Hash,
-		let new_rc = RcEntry::parse_opt(new_rc);
+	) -> db::TxOpResult<bool> {
+		let new_rc = RcEntry::parse_opt(tx.get(&self.rc, &hash)?).decrement();
+		match new_rc.serialize() {
+			Some(x) => tx.insert(&self.rc, &hash, x)?,
+			None => tx.remove(&self.rc, &hash)?,
+		};
 		Ok(matches!(new_rc, RcEntry::Deletable { .. }))
 	}
 
@@ -44,12 +56,15 @@ impl BlockRc {
 	/// deletion time has passed
 	pub(crate) fn clear_deleted_block_rc(&self, hash: &Hash) -> Result<(), Error> {
 		let now = now_msec();
-		self.rc.update_and_fetch(&hash, |rcval| {
+		self.rc.db().transaction(|mut tx| {
-			let updated = match RcEntry::parse_opt(rcval) {
+			let rcval = RcEntry::parse_opt(tx.get(&self.rc, &hash)?);
-				RcEntry::Deletable { at_time } if now > at_time => RcEntry::Absent,
+			match rcval {
-				v => v,
+				RcEntry::Deletable { at_time } if now > at_time => {
+					tx.remove(&self.rc, &hash)?;
+				}
+				_ => (),
 			};
-			updated.serialize()
+			tx.commit(())
 		})?;
 		Ok(())
 	}

src/db/Cargo.toml

@@ -0,0 +1,36 @@
+[package]
+name = "garage_db"
+version = "0.8.0"
+authors = ["Alex Auvolat <alex@adnab.me>"]
+edition = "2018"
+license = "AGPL-3.0"
+description = "Abstraction over multiple key/value storage engines that supports transactions"
+repository = "https://git.deuxfleurs.fr/Deuxfleurs/garage"
+readme = "../../README.md"
+
+[lib]
+path = "lib.rs"
+
+[[bin]]
+name = "convert"
+path = "bin/convert.rs"
+required-features = ["cli"]
+
+[dependencies]
+err-derive = "0.3"
+hexdump = "0.1"
+log = "0.4"
+
+heed = "0.11"
+rusqlite = { version = "0.27", features = ["bundled"] }
+sled = "0.34"
+
+# cli deps
+clap = { version = "3.1.18", optional = true, features = ["derive", "env"] }
+pretty_env_logger = { version = "0.4", optional = true }
+
+[dev-dependencies]
+mktemp = "0.4"
+
+[features]
+cli = ["clap", "pretty_env_logger"]

src/db/bin/convert.rs

@@ -0,0 +1,69 @@
+use std::path::PathBuf;
+
+use garage_db::*;
+
+use clap::Parser;
+
+/// K2V command line interface
+#[derive(Parser, Debug)]
+#[clap(author, version, about, long_about = None)]
+struct Args {
+	/// Input DB path
+	#[clap(short = 'i')]
+	input_path: PathBuf,
+	/// Input DB engine
+	#[clap(short = 'a')]
+	input_engine: String,
+
+	/// Output DB path
+	#[clap(short = 'o')]
+	output_path: PathBuf,
+	/// Output DB engine
+	#[clap(short = 'b')]
+	output_engine: String,
+}
+
+fn main() {
+	let args = Args::parse();
+	pretty_env_logger::init();
+
+	match do_conversion(args) {
+		Ok(()) => println!("Success!"),
+		Err(e) => eprintln!("Error: {}", e),
+	}
+}
+
+fn do_conversion(args: Args) -> Result<()> {
+	let input = open_db(args.input_path, args.input_engine)?;
+	let output = open_db(args.output_path, args.output_engine)?;
+	output.import(&input)?;
+	Ok(())
+}
+
+fn open_db(path: PathBuf, engine: String) -> Result<Db> {
+	match engine.as_str() {
+		"sled" => {
+			let db = sled_adapter::sled::Config::default().path(&path).open()?;
+			Ok(sled_adapter::SledDb::init(db))
+		}
+		"sqlite" | "sqlite3" | "rusqlite" => {
+			let db = sqlite_adapter::rusqlite::Connection::open(&path)?;
+			Ok(sqlite_adapter::SqliteDb::init(db))
+		}
+		"lmdb" | "heed" => {
+			std::fs::create_dir_all(&path).map_err(|e| {
+				Error(format!("Unable to create LMDB data directory: {}", e).into())
+			})?;
+
+			let map_size = lmdb_adapter::recommended_map_size();
+
+			let db = lmdb_adapter::heed::EnvOpenOptions::new()
+				.max_dbs(100)
+				.map_size(map_size)
+				.open(&path)
+				.unwrap();
+			Ok(lmdb_adapter::LmdbDb::init(db))
+		}
+		e => Err(Error(format!("Invalid DB engine: {}", e).into())),
+	}
+}

src/db/counted_tree_hack.rs

@@ -0,0 +1,127 @@
+//! This hack allows a db tree to keep in RAM a counter of the number of entries
+//! it contains, which is used to call .len() on it.  This is usefull only for
+//! the sled backend where .len() otherwise would have to traverse the whole
+//! tree to count items.  For sqlite and lmdb, this is mostly useless (but
+//! hopefully not harmfull!). Note that a CountedTree cannot be part of a
+//! transaction.
+
+use std::sync::{
+	atomic::{AtomicUsize, Ordering},
+	Arc,
+};
+
+use crate::{Result, Tree, TxError, Value, ValueIter};
+
+#[derive(Clone)]
+pub struct CountedTree(Arc<CountedTreeInternal>);
+
+struct CountedTreeInternal {
+	tree: Tree,
+	len: AtomicUsize,
+}
+
+impl CountedTree {
+	pub fn new(tree: Tree) -> Result<Self> {
+		let len = tree.len()?;
+		Ok(Self(Arc::new(CountedTreeInternal {
+			tree,
+			len: AtomicUsize::new(len),
+		})))
+	}
+
+	pub fn len(&self) -> usize {
+		self.0.len.load(Ordering::SeqCst)
+	}
+
+	pub fn is_empty(&self) -> bool {
+		self.len() == 0
+	}
+
+	pub fn get<K: AsRef<[u8]>>(&self, key: K) -> Result<Option<Value>> {
+		self.0.tree.get(key)
+	}
+
+	pub fn first(&self) -> Result<Option<(Value, Value)>> {
+		self.0.tree.first()
+	}
+
+	pub fn iter(&self) -> Result<ValueIter<'_>> {
+		self.0.tree.iter()
+	}
+
+	// ---- writing functions ----
+
+	pub fn insert<K, V>(&self, key: K, value: V) -> Result<Option<Value>>
+	where
+		K: AsRef<[u8]>,
+		V: AsRef<[u8]>,
+	{
+		let old_val = self.0.tree.insert(key, value)?;
+		if old_val.is_none() {
+			self.0.len.fetch_add(1, Ordering::SeqCst);
+		}
+		Ok(old_val)
+	}
+
+	pub fn remove<K: AsRef<[u8]>>(&self, key: K) -> Result<Option<Value>> {
+		let old_val = self.0.tree.remove(key)?;
+		if old_val.is_some() {
+			self.0.len.fetch_sub(1, Ordering::SeqCst);
+		}
+		Ok(old_val)
+	}
+
+	pub fn compare_and_swap<K, OV, NV>(
+		&self,
+		key: K,
+		expected_old: Option<OV>,
+		new: Option<NV>,
+	) -> Result<bool>
+	where
+		K: AsRef<[u8]>,
+		OV: AsRef<[u8]>,
+		NV: AsRef<[u8]>,
+	{
+		let old_some = expected_old.is_some();
+		let new_some = new.is_some();
+
+		let tx_res = self.0.tree.db().transaction(|mut tx| {
+			let old_val = tx.get(&self.0.tree, &key)?;
+			let is_same = match (&old_val, &expected_old) {
+				(None, None) => true,
+				(Some(x), Some(y)) if x == y.as_ref() => true,
+				_ => false,
+			};
+			if is_same {
+				match &new {
+					Some(v) => {
+						tx.insert(&self.0.tree, &key, v)?;
+					}
+					None => {
+						tx.remove(&self.0.tree, &key)?;
+					}
+				}
+				tx.commit(())
+			} else {
+				tx.abort(())
+			}
+		});
+
+		match tx_res {
+			Ok(()) => {
+				match (old_some, new_some) {
+					(false, true) => {
+						self.0.len.fetch_add(1, Ordering::SeqCst);
+					}
+					(true, false) => {
+						self.0.len.fetch_sub(1, Ordering::SeqCst);
+					}
+					_ => (),
+				}
+				Ok(true)
+			}
+			Err(TxError::Abort(())) => Ok(false),
+			Err(TxError::Db(e)) => Err(e),
+		}
+	}
+}

src/db/lib.rs

@@ -0,0 +1,406 @@
+pub mod lmdb_adapter;
+pub mod sled_adapter;
+pub mod sqlite_adapter;
+
+pub mod counted_tree_hack;
+
+#[cfg(test)]
+pub mod test;
+
+use core::ops::{Bound, RangeBounds};
+
+use std::borrow::Cow;
+use std::cell::Cell;
+use std::sync::Arc;
+
+use err_derive::Error;
+
+#[derive(Clone)]
+pub struct Db(pub(crate) Arc<dyn IDb>);
+
+pub struct Transaction<'a>(&'a mut dyn ITx);
+
+#[derive(Clone)]
+pub struct Tree(Arc<dyn IDb>, usize);
+
+pub type Value = Vec<u8>;
+pub type ValueIter<'a> = Box<dyn std::iter::Iterator<Item = Result<(Value, Value)>> + 'a>;
+pub type TxValueIter<'a> = Box<dyn std::iter::Iterator<Item = TxOpResult<(Value, Value)>> + 'a>;
+
+// ----
+
+#[derive(Debug, Error)]
+#[error(display = "{}", _0)]
+pub struct Error(pub Cow<'static, str>);
+
+pub type Result<T> = std::result::Result<T, Error>;
+
+#[derive(Debug, Error)]
+#[error(display = "{}", _0)]
+pub struct TxOpError(pub(crate) Error);
+pub type TxOpResult<T> = std::result::Result<T, TxOpError>;
+
+pub enum TxError<E> {
+	Abort(E),
+	Db(Error),
+}
+pub type TxResult<R, E> = std::result::Result<R, TxError<E>>;
+
+impl<E> From<TxOpError> for TxError<E> {
+	fn from(e: TxOpError) -> TxError<E> {
+		TxError::Db(e.0)
+	}
+}
+
+pub fn unabort<R, E>(res: TxResult<R, E>) -> TxOpResult<std::result::Result<R, E>> {
+	match res {
+		Ok(v) => Ok(Ok(v)),
+		Err(TxError::Abort(e)) => Ok(Err(e)),
+		Err(TxError::Db(e)) => Err(TxOpError(e)),
+	}
+}
+
+// ----
+
+impl Db {
+	pub fn engine(&self) -> String {
+		self.0.engine()
+	}
+
+	pub fn open_tree<S: AsRef<str>>(&self, name: S) -> Result<Tree> {
+		let tree_id = self.0.open_tree(name.as_ref())?;
+		Ok(Tree(self.0.clone(), tree_id))
+	}
+
+	pub fn list_trees(&self) -> Result<Vec<String>> {
+		self.0.list_trees()
+	}
+
+	pub fn transaction<R, E, F>(&self, fun: F) -> TxResult<R, E>
+	where
+		F: Fn(Transaction<'_>) -> TxResult<R, E>,
+	{
+		let f = TxFn {
+			function: fun,
+			result: Cell::new(None),
+		};
+		let tx_res = self.0.transaction(&f);
+		let ret = f
+			.result
+			.into_inner()
+			.expect("Transaction did not store result");
+
+		match tx_res {
+			Ok(()) => {
+				assert!(matches!(ret, Ok(_)));
+				ret
+			}
+			Err(TxError::Abort(())) => {
+				assert!(matches!(ret, Err(TxError::Abort(_))));
+				ret
+			}
+			Err(TxError::Db(e2)) => match ret {
+				// Ok was stored -> the error occured when finalizing
+				// transaction
+				Ok(_) => Err(TxError::Db(e2)),
+				// An error was already stored: that's the one we want to
+				// return
+				Err(TxError::Db(e)) => Err(TxError::Db(e)),
+				_ => unreachable!(),
+			},
+		}
+	}
+
+	pub fn import(&self, other: &Db) -> Result<()> {
+		let existing_trees = self.list_trees()?;
+		if !existing_trees.is_empty() {
+			return Err(Error(
+				format!(
+					"destination database already contains data: {:?}",
+					existing_trees
+				)
+				.into(),
+			));
+		}
+
+		let tree_names = other.list_trees()?;
+		for name in tree_names {
+			let tree = self.open_tree(&name)?;
+			if tree.len()? > 0 {
+				return Err(Error(format!("tree {} already contains data", name).into()));
+			}
+
+			let ex_tree = other.open_tree(&name)?;
+
+			let tx_res = self.transaction(|mut tx| {
+				let mut i = 0;
+				for item in ex_tree.iter().map_err(TxError::Abort)? {
+					let (k, v) = item.map_err(TxError::Abort)?;
+					tx.insert(&tree, k, v)?;
+					i += 1;
+					if i % 1000 == 0 {
+						println!("{}: imported {}", name, i);
+					}
+				}
+				tx.commit(i)
+			});
+			let total = match tx_res {
+				Err(TxError::Db(e)) => return Err(e),
+				Err(TxError::Abort(e)) => return Err(e),
+				Ok(x) => x,
+			};
+
+			println!("{}: finished importing, {} items", name, total);
+		}
+		Ok(())
+	}
+}
+
+#[allow(clippy::len_without_is_empty)]
+impl Tree {
+	#[inline]
+	pub fn db(&self) -> Db {
+		Db(self.0.clone())
+	}
+
+	#[inline]
+	pub fn get<T: AsRef<[u8]>>(&self, key: T) -> Result<Option<Value>> {
+		self.0.get(self.1, key.as_ref())
+	}
+	#[inline]
+	pub fn len(&self) -> Result<usize> {
+		self.0.len(self.1)
+	}
+
+	#[inline]
+	pub fn first(&self) -> Result<Option<(Value, Value)>> {
+		self.iter()?.next().transpose()
+	}
+	#[inline]
+	pub fn get_gt<T: AsRef<[u8]>>(&self, from: T) -> Result<Option<(Value, Value)>> {
+		self.range((Bound::Excluded(from), Bound::Unbounded))?
+			.next()
+			.transpose()
+	}
+
+	/// Returns the old value if there was one
+	#[inline]
+	pub fn insert<T: AsRef<[u8]>, U: AsRef<[u8]>>(
+		&self,
+		key: T,
+		value: U,
+	) -> Result<Option<Value>> {
+		self.0.insert(self.1, key.as_ref(), value.as_ref())
+	}
+	/// Returns the old value if there was one
+	#[inline]
+	pub fn remove<T: AsRef<[u8]>>(&self, key: T) -> Result<Option<Value>> {
+		self.0.remove(self.1, key.as_ref())
+	}
+	/// Clears all values from the tree
+	#[inline]
+	pub fn clear(&self) -> Result<()> {
+		self.0.clear(self.1)
+	}
+
+	#[inline]
+	pub fn iter(&self) -> Result<ValueIter<'_>> {
+		self.0.iter(self.1)
+	}
+	#[inline]
+	pub fn iter_rev(&self) -> Result<ValueIter<'_>> {
+		self.0.iter_rev(self.1)
+	}
+
+	#[inline]
+	pub fn range<K, R>(&self, range: R) -> Result<ValueIter<'_>>
+	where
+		K: AsRef<[u8]>,
+		R: RangeBounds<K>,
+	{
+		let sb = range.start_bound();
+		let eb = range.end_bound();
+		self.0.range(self.1, get_bound(sb), get_bound(eb))
+	}
+	#[inline]
+	pub fn range_rev<K, R>(&self, range: R) -> Result<ValueIter<'_>>
+	where
+		K: AsRef<[u8]>,
+		R: RangeBounds<K>,
+	{
+		let sb = range.start_bound();
+		let eb = range.end_bound();
+		self.0.range_rev(self.1, get_bound(sb), get_bound(eb))
+	}
+}
+
+#[allow(clippy::len_without_is_empty)]
+impl<'a> Transaction<'a> {
+	#[inline]
+	pub fn get<T: AsRef<[u8]>>(&self, tree: &Tree, key: T) -> TxOpResult<Option<Value>> {
+		self.0.get(tree.1, key.as_ref())
+	}
+	#[inline]
+	pub fn len(&self, tree: &Tree) -> TxOpResult<usize> {
+		self.0.len(tree.1)
+	}
+
+	/// Returns the old value if there was one
+	#[inline]
+	pub fn insert<T: AsRef<[u8]>, U: AsRef<[u8]>>(
+		&mut self,
+		tree: &Tree,
+		key: T,
+		value: U,
+	) -> TxOpResult<Option<Value>> {
+		self.0.insert(tree.1, key.as_ref(), value.as_ref())
+	}
+	/// Returns the old value if there was one
+	#[inline]
+	pub fn remove<T: AsRef<[u8]>>(&mut self, tree: &Tree, key: T) -> TxOpResult<Option<Value>> {
+		self.0.remove(tree.1, key.as_ref())
+	}
+
+	#[inline]
+	pub fn iter(&self, tree: &Tree) -> TxOpResult<TxValueIter<'_>> {
+		self.0.iter(tree.1)
+	}
+	#[inline]
+	pub fn iter_rev(&self, tree: &Tree) -> TxOpResult<TxValueIter<'_>> {
+		self.0.iter_rev(tree.1)
+	}
+
+	#[inline]
+	pub fn range<K, R>(&self, tree: &Tree, range: R) -> TxOpResult<TxValueIter<'_>>
+	where
+		K: AsRef<[u8]>,
+		R: RangeBounds<K>,
+	{
+		let sb = range.start_bound();
+		let eb = range.end_bound();
+		self.0.range(tree.1, get_bound(sb), get_bound(eb))
+	}
+	#[inline]
+	pub fn range_rev<K, R>(&self, tree: &Tree, range: R) -> TxOpResult<TxValueIter<'_>>
+	where
+		K: AsRef<[u8]>,
+		R: RangeBounds<K>,
+	{
+		let sb = range.start_bound();
+		let eb = range.end_bound();
+		self.0.range_rev(tree.1, get_bound(sb), get_bound(eb))
+	}
+
+	// ----
+
+	#[inline]
+	pub fn abort<R, E>(self, e: E) -> TxResult<R, E> {
+		Err(TxError::Abort(e))
+	}
+
+	#[inline]
+	pub fn commit<R, E>(self, r: R) -> TxResult<R, E> {
+		Ok(r)
+	}
+}
+
+// ---- Internal interfaces
+
+pub(crate) trait IDb: Send + Sync {
+	fn engine(&self) -> String;
+	fn open_tree(&self, name: &str) -> Result<usize>;
+	fn list_trees(&self) -> Result<Vec<String>>;
+
+	fn get(&self, tree: usize, key: &[u8]) -> Result<Option<Value>>;
+	fn len(&self, tree: usize) -> Result<usize>;
+
+	fn insert(&self, tree: usize, key: &[u8], value: &[u8]) -> Result<Option<Value>>;
+	fn remove(&self, tree: usize, key: &[u8]) -> Result<Option<Value>>;
+	fn clear(&self, tree: usize) -> Result<()>;
+
+	fn iter(&self, tree: usize) -> Result<ValueIter<'_>>;
+	fn iter_rev(&self, tree: usize) -> Result<ValueIter<'_>>;
+
+	fn range<'r>(
+		&self,
+		tree: usize,
+		low: Bound<&'r [u8]>,
+		high: Bound<&'r [u8]>,
+	) -> Result<ValueIter<'_>>;
+	fn range_rev<'r>(
+		&self,
+		tree: usize,
+		low: Bound<&'r [u8]>,
+		high: Bound<&'r [u8]>,
+	) -> Result<ValueIter<'_>>;
+
+	fn transaction(&self, f: &dyn ITxFn) -> TxResult<(), ()>;
+}
+
+pub(crate) trait ITx {
+	fn get(&self, tree: usize, key: &[u8]) -> TxOpResult<Option<Value>>;
+	fn len(&self, tree: usize) -> TxOpResult<usize>;
+
+	fn insert(&mut self, tree: usize, key: &[u8], value: &[u8]) -> TxOpResult<Option<Value>>;
+	fn remove(&mut self, tree: usize, key: &[u8]) -> TxOpResult<Option<Value>>;
+
+	fn iter(&self, tree: usize) -> TxOpResult<TxValueIter<'_>>;
+	fn iter_rev(&self, tree: usize) -> TxOpResult<TxValueIter<'_>>;
+
+	fn range<'r>(
+		&self,
+		tree: usize,
+		low: Bound<&'r [u8]>,
+		high: Bound<&'r [u8]>,
+	) -> TxOpResult<TxValueIter<'_>>;
+	fn range_rev<'r>(
+		&self,
+		tree: usize,
+		low: Bound<&'r [u8]>,
+		high: Bound<&'r [u8]>,
+	) -> TxOpResult<TxValueIter<'_>>;
+}
+
+pub(crate) trait ITxFn {
+	fn try_on(&self, tx: &mut dyn ITx) -> TxFnResult;
+}
+
+pub(crate) enum TxFnResult {
+	Ok,
+	Abort,
+	DbErr,
+}
+
+struct TxFn<F, R, E>
+where
+	F: Fn(Transaction<'_>) -> TxResult<R, E>,
+{
+	function: F,
+	result: Cell<Option<TxResult<R, E>>>,
+}
+
+impl<F, R, E> ITxFn for TxFn<F, R, E>
+where
+	F: Fn(Transaction<'_>) -> TxResult<R, E>,
+{
+	fn try_on(&self, tx: &mut dyn ITx) -> TxFnResult {
+		let res = (self.function)(Transaction(tx));
+		let res2 = match &res {
+			Ok(_) => TxFnResult::Ok,
+			Err(TxError::Abort(_)) => TxFnResult::Abort,
+			Err(TxError::Db(_)) => TxFnResult::DbErr,
+		};
+		self.result.set(Some(res));
+		res2
+	}
+}
+
+// ----
+
+fn get_bound<K: AsRef<[u8]>>(b: Bound<&K>) -> Bound<&[u8]> {
+	match b {
+		Bound::Included(v) => Bound::Included(v.as_ref()),
+		Bound::Excluded(v) => Bound::Excluded(v.as_ref()),
+		Bound::Unbounded => Bound::Unbounded,
+	}
+}

src/db/lmdb_adapter.rs

@@ -0,0 +1,351 @@
+use core::ops::Bound;
+use core::ptr::NonNull;
+
+use std::collections::HashMap;
+use std::convert::TryInto;
+use std::sync::{Arc, RwLock};
+
+use heed::types::ByteSlice;
+use heed::{BytesDecode, Env, RoTxn, RwTxn, UntypedDatabase as Database};
+
+use crate::{
+	Db, Error, IDb, ITx, ITxFn, Result, TxError, TxFnResult, TxOpError, TxOpResult, TxResult,
+	TxValueIter, Value, ValueIter,
+};
+
+pub use heed;
+
+// -- err
+
+impl From<heed::Error> for Error {
+	fn from(e: heed::Error) -> Error {
+		Error(format!("LMDB: {}", e).into())
+	}
+}
+
+impl From<heed::Error> for TxOpError {
+	fn from(e: heed::Error) -> TxOpError {
+		TxOpError(e.into())
+	}
+}
+
+// -- db
+
+pub struct LmdbDb {
+	db: heed::Env,
+	trees: RwLock<(Vec<Database>, HashMap<String, usize>)>,
+}
+
+impl LmdbDb {
+	pub fn init(db: Env) -> Db {
+		let s = Self {
+			db,
+			trees: RwLock::new((Vec::new(), HashMap::new())),
+		};
+		Db(Arc::new(s))
+	}
+
+	fn get_tree(&self, i: usize) -> Result<Database> {
+		self.trees
+			.read()
+			.unwrap()
+			.0
+			.get(i)
+			.cloned()
+			.ok_or_else(|| Error("invalid tree id".into()))
+	}
+}
+
+impl IDb for LmdbDb {
+	fn engine(&self) -> String {
+		"LMDB (using Heed crate)".into()
+	}
+
+	fn open_tree(&self, name: &str) -> Result<usize> {
+		let mut trees = self.trees.write().unwrap();
+		if let Some(i) = trees.1.get(name) {
+			Ok(*i)
+		} else {
+			let tree = self.db.create_database(Some(name))?;
+			let i = trees.0.len();
+			trees.0.push(tree);
+			trees.1.insert(name.to_string(), i);
+			Ok(i)
+		}
+	}
+
+	fn list_trees(&self) -> Result<Vec<String>> {
+		let tree0 = match self.db.open_database::<heed::types::Str, ByteSlice>(None)? {
+			Some(x) => x,
+			None => return Ok(vec![]),
+		};
+
+		let mut ret = vec![];
+		let tx = self.db.read_txn()?;
+		for item in tree0.iter(&tx)? {
+			let (tree_name, _) = item?;
+			ret.push(tree_name.to_string());
+		}
+		drop(tx);
+
+		let mut ret2 = vec![];
+		for tree_name in ret {
+			if self
+				.db
+				.open_database::<ByteSlice, ByteSlice>(Some(&tree_name))?
+				.is_some()
+			{
+				ret2.push(tree_name);
+			}
+		}
+
+		Ok(ret2)
+	}
+
+	// ----
+
+	fn get(&self, tree: usize, key: &[u8]) -> Result<Option<Value>> {
+		let tree = self.get_tree(tree)?;
+
+		let tx = self.db.read_txn()?;
+		let val = tree.get(&tx, key)?;
+		match val {
+			None => Ok(None),
+			Some(v) => Ok(Some(v.to_vec())),
+		}
+	}
+
+	fn len(&self, tree: usize) -> Result<usize> {
+		let tree = self.get_tree(tree)?;
+		let tx = self.db.read_txn()?;
+		Ok(tree.len(&tx)?.try_into().unwrap())
+	}
+
+	fn insert(&self, tree: usize, key: &[u8], value: &[u8]) -> Result<Option<Value>> {
+		let tree = self.get_tree(tree)?;
+		let mut tx = self.db.write_txn()?;
+		let old_val = tree.get(&tx, key)?.map(Vec::from);
+		tree.put(&mut tx, key, value)?;
+		tx.commit()?;
+		Ok(old_val)
+	}
+
+	fn remove(&self, tree: usize, key: &[u8]) -> Result<Option<Value>> {
+		let tree = self.get_tree(tree)?;
+		let mut tx = self.db.write_txn()?;
+		let old_val = tree.get(&tx, key)?.map(Vec::from);
+		tree.delete(&mut tx, key)?;
+		tx.commit()?;
+		Ok(old_val)
+	}
+
+	fn clear(&self, tree: usize) -> Result<()> {
+		let tree = self.get_tree(tree)?;
+		let mut tx = self.db.write_txn()?;
+		tree.clear(&mut tx)?;
+		tx.commit()?;
+		Ok(())
+	}
+
+	fn iter(&self, tree: usize) -> Result<ValueIter<'_>> {
+		let tree = self.get_tree(tree)?;
+		let tx = self.db.read_txn()?;
+		TxAndIterator::make(tx, |tx| Ok(tree.iter(tx)?))
+	}
+
+	fn iter_rev(&self, tree: usize) -> Result<ValueIter<'_>> {
+		let tree = self.get_tree(tree)?;
+		let tx = self.db.read_txn()?;
+		TxAndIterator::make(tx, |tx| Ok(tree.rev_iter(tx)?))
+	}
+
+	fn range<'r>(
+		&self,
+		tree: usize,
+		low: Bound<&'r [u8]>,
+		high: Bound<&'r [u8]>,
+	) -> Result<ValueIter<'_>> {
+		let tree = self.get_tree(tree)?;
+		let tx = self.db.read_txn()?;
+		TxAndIterator::make(tx, |tx| Ok(tree.range(tx, &(low, high))?))
+	}
+	fn range_rev<'r>(
+		&self,
+		tree: usize,
+		low: Bound<&'r [u8]>,
+		high: Bound<&'r [u8]>,
+	) -> Result<ValueIter<'_>> {
+		let tree = self.get_tree(tree)?;
+		let tx = self.db.read_txn()?;
+		TxAndIterator::make(tx, |tx| Ok(tree.rev_range(tx, &(low, high))?))
+	}
+
+	// ----
+
+	fn transaction(&self, f: &dyn ITxFn) -> TxResult<(), ()> {
+		let trees = self.trees.read().unwrap();
+		let mut tx = LmdbTx {
+			trees: &trees.0[..],
+			tx: self
+				.db
+				.write_txn()
+				.map_err(Error::from)
+				.map_err(TxError::Db)?,
+		};
+
+		let res = f.try_on(&mut tx);
+		match res {
+			TxFnResult::Ok => {
+				tx.tx.commit().map_err(Error::from).map_err(TxError::Db)?;
+				Ok(())
+			}
+			TxFnResult::Abort => {
+				tx.tx.abort().map_err(Error::from).map_err(TxError::Db)?;
+				Err(TxError::Abort(()))
+			}
+			TxFnResult::DbErr => {
+				tx.tx.abort().map_err(Error::from).map_err(TxError::Db)?;
+				Err(TxError::Db(Error(
+					"(this message will be discarded)".into(),
+				)))
+			}
+		}
+	}
+}
+
+// ----
+
+struct LmdbTx<'a> {
+	trees: &'a [Database],
+	tx: RwTxn<'a, 'a>,
+}
+
+impl<'a> LmdbTx<'a> {
+	fn get_tree(&self, i: usize) -> TxOpResult<&Database> {
+		self.trees.get(i).ok_or_else(|| {
+			TxOpError(Error(
+				"invalid tree id (it might have been openned after the transaction started)".into(),
+			))
+		})
+	}
+}
+
+impl<'a> ITx for LmdbTx<'a> {
+	fn get(&self, tree: usize, key: &[u8]) -> TxOpResult<Option<Value>> {
+		let tree = self.get_tree(tree)?;
+		match tree.get(&self.tx, key)? {
+			Some(v) => Ok(Some(v.to_vec())),
+			None => Ok(None),
+		}
+	}
+	fn len(&self, _tree: usize) -> TxOpResult<usize> {
+		unimplemented!(".len() in transaction not supported with LMDB backend")
+	}
+
+	fn insert(&mut self, tree: usize, key: &[u8], value: &[u8]) -> TxOpResult<Option<Value>> {
+		let tree = *self.get_tree(tree)?;
+		let old_val = tree.get(&self.tx, key)?.map(Vec::from);
+		tree.put(&mut self.tx, key, value)?;
+		Ok(old_val)
+	}
+	fn remove(&mut self, tree: usize, key: &[u8]) -> TxOpResult<Option<Value>> {
+		let tree = *self.get_tree(tree)?;
+		let old_val = tree.get(&self.tx, key)?.map(Vec::from);
+		tree.delete(&mut self.tx, key)?;
+		Ok(old_val)
+	}
+
+	fn iter(&self, _tree: usize) -> TxOpResult<TxValueIter<'_>> {
+		unimplemented!("Iterators in transactions not supported with LMDB backend");
+	}
+	fn iter_rev(&self, _tree: usize) -> TxOpResult<TxValueIter<'_>> {
+		unimplemented!("Iterators in transactions not supported with LMDB backend");
+	}
+
+	fn range<'r>(
+		&self,
+		_tree: usize,
+		_low: Bound<&'r [u8]>,
+		_high: Bound<&'r [u8]>,
+	) -> TxOpResult<TxValueIter<'_>> {
+		unimplemented!("Iterators in transactions not supported with LMDB backend");
+	}
+	fn range_rev<'r>(
+		&self,
+		_tree: usize,
+		_low: Bound<&'r [u8]>,
+		_high: Bound<&'r [u8]>,
+	) -> TxOpResult<TxValueIter<'_>> {
+		unimplemented!("Iterators in transactions not supported with LMDB backend");
+	}
+}
+
+// ----
+
+type IteratorItem<'a> = heed::Result<(
+	<ByteSlice as BytesDecode<'a>>::DItem,
+	<ByteSlice as BytesDecode<'a>>::DItem,
+)>;
+
+struct TxAndIterator<'a, I>
+where
+	I: Iterator<Item = IteratorItem<'a>> + 'a,
+{
+	tx: RoTxn<'a>,
+	iter: Option<I>,
+}
+
+impl<'a, I> TxAndIterator<'a, I>
+where
+	I: Iterator<Item = IteratorItem<'a>> + 'a,
+{
+	fn make<F>(tx: RoTxn<'a>, iterfun: F) -> Result<ValueIter<'a>>
+	where
+		F: FnOnce(&'a RoTxn<'a>) -> Result<I>,
+	{
+		let mut res = TxAndIterator { tx, iter: None };
+
+		let tx = unsafe { NonNull::from(&res.tx).as_ref() };
+		res.iter = Some(iterfun(tx)?);
+
+		Ok(Box::new(res))
+	}
+}
+
+impl<'a, I> Drop for TxAndIterator<'a, I>
+where
+	I: Iterator<Item = IteratorItem<'a>> + 'a,
+{
+	fn drop(&mut self) {
+		drop(self.iter.take());
+	}
+}
+
+impl<'a, I> Iterator for TxAndIterator<'a, I>
+where
+	I: Iterator<Item = IteratorItem<'a>> + 'a,
+{
+	type Item = Result<(Value, Value)>;
+
+	fn next(&mut self) -> Option<Self::Item> {
+		match self.iter.as_mut().unwrap().next() {
+			None => None,
+			Some(Err(e)) => Some(Err(e.into())),
+			Some(Ok((k, v))) => Some(Ok((k.to_vec(), v.to_vec()))),
+		}
+	}
+}
+
+// ----
+
+#[cfg(target_pointer_width = "64")]
+pub fn recommended_map_size() -> usize {
+	1usize << 40
+}
+
+#[cfg(target_pointer_width = "32")]
+pub fn recommended_map_size() -> usize {
+	use log::warn;
+	warn!("LMDB is not recommended on 32-bit systems, database size will be limited");
+	1usize << 30
+}

src/db/sled_adapter.rs

@@ -0,0 +1,266 @@
+use core::ops::Bound;
+
+use std::cell::Cell;
+use std::collections::HashMap;
+use std::sync::{Arc, RwLock};
+
+use sled::transaction::{
+	ConflictableTransactionError, TransactionError, Transactional, TransactionalTree,
+	UnabortableTransactionError,
+};
+
+use crate::{
+	Db, Error, IDb, ITx, ITxFn, Result, TxError, TxFnResult, TxOpError, TxOpResult, TxResult,
+	TxValueIter, Value, ValueIter,
+};
+
+pub use sled;
+
+// -- err
+
+impl From<sled::Error> for Error {
+	fn from(e: sled::Error) -> Error {
+		Error(format!("Sled: {}", e).into())
+	}
+}
+
+impl From<sled::Error> for TxOpError {
+	fn from(e: sled::Error) -> TxOpError {
+		TxOpError(e.into())
+	}
+}
+
+// -- db
+
+pub struct SledDb {
+	db: sled::Db,
+	trees: RwLock<(Vec<sled::Tree>, HashMap<String, usize>)>,
+}
+
+impl SledDb {
+	pub fn init(db: sled::Db) -> Db {
+		let s = Self {
+			db,
+			trees: RwLock::new((Vec::new(), HashMap::new())),
+		};
+		Db(Arc::new(s))
+	}
+
+	fn get_tree(&self, i: usize) -> Result<sled::Tree> {
+		self.trees
+			.read()
+			.unwrap()
+			.0
+			.get(i)
+			.cloned()
+			.ok_or_else(|| Error("invalid tree id".into()))
+	}
+}
+
+impl IDb for SledDb {
+	fn engine(&self) -> String {
+		"Sled".into()
+	}
+
+	fn open_tree(&self, name: &str) -> Result<usize> {
+		let mut trees = self.trees.write().unwrap();
+		if let Some(i) = trees.1.get(name) {
+			Ok(*i)
+		} else {
+			let tree = self.db.open_tree(name)?;
+			let i = trees.0.len();
+			trees.0.push(tree);
+			trees.1.insert(name.to_string(), i);
+			Ok(i)
+		}
+	}
+
+	fn list_trees(&self) -> Result<Vec<String>> {
+		let mut trees = vec![];
+		for name in self.db.tree_names() {
+			let name = std::str::from_utf8(&name)
+				.map_err(|e| Error(format!("{}", e).into()))?
+				.to_string();
+			if name != "__sled__default" {
+				trees.push(name);
+			}
+		}
+		Ok(trees)
+	}
+
+	// ----
+
+	fn get(&self, tree: usize, key: &[u8]) -> Result<Option<Value>> {
+		let tree = self.get_tree(tree)?;
+		let val = tree.get(key)?;
+		Ok(val.map(|x| x.to_vec()))
+	}
+
+	fn len(&self, tree: usize) -> Result<usize> {
+		let tree = self.get_tree(tree)?;
+		Ok(tree.len())
+	}
+
+	fn insert(&self, tree: usize, key: &[u8], value: &[u8]) -> Result<Option<Value>> {
+		let tree = self.get_tree(tree)?;
+		let old_val = tree.insert(key, value)?;
+		Ok(old_val.map(|x| x.to_vec()))
+	}
+
+	fn remove(&self, tree: usize, key: &[u8]) -> Result<Option<Value>> {
+		let tree = self.get_tree(tree)?;
+		let old_val = tree.remove(key)?;
+		Ok(old_val.map(|x| x.to_vec()))
+	}
+
+	fn clear(&self, tree: usize) -> Result<()> {
+		let tree = self.get_tree(tree)?;
+		tree.clear()?;
+		Ok(())
+	}
+
+	fn iter(&self, tree: usize) -> Result<ValueIter<'_>> {
+		let tree = self.get_tree(tree)?;
+		Ok(Box::new(tree.iter().map(|v| {
+			v.map(|(x, y)| (x.to_vec(), y.to_vec())).map_err(Into::into)
+		})))
+	}
+
+	fn iter_rev(&self, tree: usize) -> Result<ValueIter<'_>> {
+		let tree = self.get_tree(tree)?;
+		Ok(Box::new(tree.iter().rev().map(|v| {
+			v.map(|(x, y)| (x.to_vec(), y.to_vec())).map_err(Into::into)
+		})))
+	}
+
+	fn range<'r>(
+		&self,
+		tree: usize,
+		low: Bound<&'r [u8]>,
+		high: Bound<&'r [u8]>,
+	) -> Result<ValueIter<'_>> {
+		let tree = self.get_tree(tree)?;
+		Ok(Box::new(tree.range::<&'r [u8], _>((low, high)).map(|v| {
+			v.map(|(x, y)| (x.to_vec(), y.to_vec())).map_err(Into::into)
+		})))
+	}
+	fn range_rev<'r>(
+		&self,
+		tree: usize,
+		low: Bound<&'r [u8]>,
+		high: Bound<&'r [u8]>,
+	) -> Result<ValueIter<'_>> {
+		let tree = self.get_tree(tree)?;
+		Ok(Box::new(tree.range::<&'r [u8], _>((low, high)).rev().map(
+			|v| v.map(|(x, y)| (x.to_vec(), y.to_vec())).map_err(Into::into),
+		)))
+	}
+
+	// ----
+
+	fn transaction(&self, f: &dyn ITxFn) -> TxResult<(), ()> {
+		let trees = self.trees.read().unwrap();
+		let res = trees.0.transaction(|txtrees| {
+			let mut tx = SledTx {
+				trees: txtrees,
+				err: Cell::new(None),
+			};
+			match f.try_on(&mut tx) {
+				TxFnResult::Ok => {
+					assert!(tx.err.into_inner().is_none());
+					Ok(())
+				}
+				TxFnResult::Abort => {
+					assert!(tx.err.into_inner().is_none());
+					Err(ConflictableTransactionError::Abort(()))
+				}
+				TxFnResult::DbErr => {
+					let e = tx.err.into_inner().expect("No DB error");
+					Err(e.into())
+				}
+			}
+		});
+		match res {
+			Ok(()) => Ok(()),
+			Err(TransactionError::Abort(())) => Err(TxError::Abort(())),
+			Err(TransactionError::Storage(s)) => Err(TxError::Db(s.into())),
+		}
+	}
+}
+
+// ----
+
+struct SledTx<'a> {
+	trees: &'a [TransactionalTree],
+	err: Cell<Option<UnabortableTransactionError>>,
+}
+
+impl<'a> SledTx<'a> {
+	fn get_tree(&self, i: usize) -> TxOpResult<&TransactionalTree> {
+		self.trees.get(i).ok_or_else(|| {
+			TxOpError(Error(
+				"invalid tree id (it might have been openned after the transaction started)".into(),
+			))
+		})
+	}
+
+	fn save_error<R>(
+		&self,
+		v: std::result::Result<R, UnabortableTransactionError>,
+	) -> TxOpResult<R> {
+		match v {
+			Ok(x) => Ok(x),
+			Err(e) => {
+				let txt = format!("{}", e);
+				self.err.set(Some(e));
+				Err(TxOpError(Error(txt.into())))
+			}
+		}
+	}
+}
+
+impl<'a> ITx for SledTx<'a> {
+	fn get(&self, tree: usize, key: &[u8]) -> TxOpResult<Option<Value>> {
+		let tree = self.get_tree(tree)?;
+		let tmp = self.save_error(tree.get(key))?;
+		Ok(tmp.map(|x| x.to_vec()))
+	}
+	fn len(&self, _tree: usize) -> TxOpResult<usize> {
+		unimplemented!(".len() in transaction not supported with Sled backend")
+	}
+
+	fn insert(&mut self, tree: usize, key: &[u8], value: &[u8]) -> TxOpResult<Option<Value>> {
+		let tree = self.get_tree(tree)?;
+		let old_val = self.save_error(tree.insert(key, value))?;
+		Ok(old_val.map(|x| x.to_vec()))
+	}
+	fn remove(&mut self, tree: usize, key: &[u8]) -> TxOpResult<Option<Value>> {
+		let tree = self.get_tree(tree)?;
+		let old_val = self.save_error(tree.remove(key))?;
+		Ok(old_val.map(|x| x.to_vec()))
+	}
+
+	fn iter(&self, _tree: usize) -> TxOpResult<TxValueIter<'_>> {
+		unimplemented!("Iterators in transactions not supported with Sled backend");
+	}
+	fn iter_rev(&self, _tree: usize) -> TxOpResult<TxValueIter<'_>> {
+		unimplemented!("Iterators in transactions not supported with Sled backend");
+	}
+
+	fn range<'r>(
+		&self,
+		_tree: usize,
+		_low: Bound<&'r [u8]>,
+		_high: Bound<&'r [u8]>,
+	) -> TxOpResult<TxValueIter<'_>> {
+		unimplemented!("Iterators in transactions not supported with Sled backend");
+	}
+	fn range_rev<'r>(
+		&self,
+		_tree: usize,
+		_low: Bound<&'r [u8]>,
+		_high: Bound<&'r [u8]>,
+	) -> TxOpResult<TxValueIter<'_>> {
+		unimplemented!("Iterators in transactions not supported with Sled backend");
+	}
+}

src/db/sqlite_adapter.rs

@@ -0,0 +1,510 @@
+use core::ops::Bound;
+
+use std::borrow::BorrowMut;
+use std::marker::PhantomPinned;
+use std::pin::Pin;
+use std::ptr::NonNull;
+use std::sync::{Arc, Mutex, MutexGuard};
+
+use log::trace;
+
+use rusqlite::{params, Connection, Rows, Statement, Transaction};
+
+use crate::{
+	Db, Error, IDb, ITx, ITxFn, Result, TxError, TxFnResult, TxOpError, TxOpResult, TxResult,
+	TxValueIter, Value, ValueIter,
+};
+
+pub use rusqlite;
+
+// --- err
+
+impl From<rusqlite::Error> for Error {
+	fn from(e: rusqlite::Error) -> Error {
+		Error(format!("Sqlite: {}", e).into())
+	}
+}
+
+impl From<rusqlite::Error> for TxOpError {
+	fn from(e: rusqlite::Error) -> TxOpError {
+		TxOpError(e.into())
+	}
+}
+
+// -- db
+
+pub struct SqliteDb(Mutex<SqliteDbInner>);
+
+struct SqliteDbInner {
+	db: Connection,
+	trees: Vec<String>,
+}
+
+impl SqliteDb {
+	pub fn init(db: rusqlite::Connection) -> Db {
+		let s = Self(Mutex::new(SqliteDbInner {
+			db,
+			trees: Vec::new(),
+		}));
+		Db(Arc::new(s))
+	}
+}
+
+impl SqliteDbInner {
+	fn get_tree(&self, i: usize) -> Result<&'_ str> {
+		self.trees
+			.get(i)
+			.map(String::as_str)
+			.ok_or_else(|| Error("invalid tree id".into()))
+	}
+
+	fn internal_get(&self, tree: &str, key: &[u8]) -> Result<Option<Value>> {
+		let mut stmt = self
+			.db
+			.prepare(&format!("SELECT v FROM {} WHERE k = ?1", tree))?;
+		let mut res_iter = stmt.query([key])?;
+		match res_iter.next()? {
+			None => Ok(None),
+			Some(v) => Ok(Some(v.get::<_, Vec<u8>>(0)?)),
+		}
+	}
+}
+
+impl IDb for SqliteDb {
+	fn engine(&self) -> String {
+		format!("sqlite3 v{} (using rusqlite crate)", rusqlite::version())
+	}
+
+	fn open_tree(&self, name: &str) -> Result<usize> {
+		let name = format!("tree_{}", name.replace(':', "_COLON_"));
+		let mut this = self.0.lock().unwrap();
+
+		if let Some(i) = this.trees.iter().position(|x| x == &name) {
+			Ok(i)
+		} else {
+			trace!("create table {}", name);
+			this.db.execute(
+				&format!(
+					"CREATE TABLE IF NOT EXISTS {} (
+						k BLOB PRIMARY KEY,
+						v BLOB
+					)",
+					name
+				),
+				[],
+			)?;
+			trace!("table created: {}, unlocking", name);
+
+			let i = this.trees.len();
+			this.trees.push(name.to_string());
+			Ok(i)
+		}
+	}
+
+	fn list_trees(&self) -> Result<Vec<String>> {
+		let mut trees = vec![];
+
+		trace!("list_trees: lock db");
+		let this = self.0.lock().unwrap();
+		trace!("list_trees: lock acquired");
+
+		let mut stmt = this.db.prepare(
+			"SELECT name FROM sqlite_schema WHERE type = 'table' AND name LIKE 'tree_%'",
+		)?;
+		let mut rows = stmt.query([])?;
+		while let Some(row) = rows.next()? {
+			let name = row.get::<_, String>(0)?;
+			let name = name.replace("_COLON_", ":");
+			let name = name.strip_prefix("tree_").unwrap().to_string();
+			trees.push(name);
+		}
+		Ok(trees)
+	}
+
+	// ----
+
+	fn get(&self, tree: usize, key: &[u8]) -> Result<Option<Value>> {
+		trace!("get {}: lock db", tree);
+		let this = self.0.lock().unwrap();
+		trace!("get {}: lock acquired", tree);
+
+		let tree = this.get_tree(tree)?;
+		this.internal_get(tree, key)
+	}
+
+	fn len(&self, tree: usize) -> Result<usize> {
+		trace!("len {}: lock db", tree);
+		let this = self.0.lock().unwrap();
+		trace!("len {}: lock acquired", tree);
+
+		let tree = this.get_tree(tree)?;
+		let mut stmt = this.db.prepare(&format!("SELECT COUNT(*) FROM {}", tree))?;
+		let mut res_iter = stmt.query([])?;
+		match res_iter.next()? {
+			None => Ok(0),
+			Some(v) => Ok(v.get::<_, usize>(0)?),
+		}
+	}
+
+	fn insert(&self, tree: usize, key: &[u8], value: &[u8]) -> Result<Option<Value>> {
+		trace!("insert {}: lock db", tree);
+		let this = self.0.lock().unwrap();
+		trace!("insert {}: lock acquired", tree);
+
+		let tree = this.get_tree(tree)?;
+		let old_val = this.internal_get(tree, key)?;
+
+		let sql = match &old_val {
+			Some(_) => format!("UPDATE {} SET v = ?2 WHERE k = ?1", tree),
+			None => format!("INSERT INTO {} (k, v) VALUES (?1, ?2)", tree),
+		};
+		let n = this.db.execute(&sql, params![key, value])?;
+		assert_eq!(n, 1);
+
+		Ok(old_val)
+	}
+
+	fn remove(&self, tree: usize, key: &[u8]) -> Result<Option<Value>> {
+		trace!("remove {}: lock db", tree);
+		let this = self.0.lock().unwrap();
+		trace!("remove {}: lock acquired", tree);
+
+		let tree = this.get_tree(tree)?;
+		let old_val = this.internal_get(tree, key)?;
+
+		if old_val.is_some() {
+			let n = this
+				.db
+				.execute(&format!("DELETE FROM {} WHERE k = ?1", tree), params![key])?;
+			assert_eq!(n, 1);
+		}
+
+		Ok(old_val)
+	}
+
+	fn clear(&self, tree: usize) -> Result<()> {
+		trace!("clear {}: lock db", tree);
+		let this = self.0.lock().unwrap();
+		trace!("clear {}: lock acquired", tree);
+
+		let tree = this.get_tree(tree)?;
+		this.db.execute(&format!("DELETE FROM {}", tree), [])?;
+		Ok(())
+	}
+
+	fn iter(&self, tree: usize) -> Result<ValueIter<'_>> {
+		trace!("iter {}: lock db", tree);
+		let this = self.0.lock().unwrap();
+		trace!("iter {}: lock acquired", tree);
+
+		let tree = this.get_tree(tree)?;
+		let sql = format!("SELECT k, v FROM {} ORDER BY k ASC", tree);
+		DbValueIterator::make(this, &sql, [])
+	}
+
+	fn iter_rev(&self, tree: usize) -> Result<ValueIter<'_>> {
+		trace!("iter_rev {}: lock db", tree);
+		let this = self.0.lock().unwrap();
+		trace!("iter_rev {}: lock acquired", tree);
+
+		let tree = this.get_tree(tree)?;
+		let sql = format!("SELECT k, v FROM {} ORDER BY k DESC", tree);
+		DbValueIterator::make(this, &sql, [])
+	}
+
+	fn range<'r>(
+		&self,
+		tree: usize,
+		low: Bound<&'r [u8]>,
+		high: Bound<&'r [u8]>,
+	) -> Result<ValueIter<'_>> {
+		trace!("range {}: lock db", tree);
+		let this = self.0.lock().unwrap();
+		trace!("range {}: lock acquired", tree);
+
+		let tree = this.get_tree(tree)?;
+
+		let (bounds_sql, params) = bounds_sql(low, high);
+		let sql = format!("SELECT k, v FROM {} {} ORDER BY k ASC", tree, bounds_sql);
+
+		let params = params
+			.iter()
+			.map(|x| x as &dyn rusqlite::ToSql)
+			.collect::<Vec<_>>();
+
+		DbValueIterator::make::<&[&dyn rusqlite::ToSql]>(this, &sql, params.as_ref())
+	}
+	fn range_rev<'r>(
+		&self,
+		tree: usize,
+		low: Bound<&'r [u8]>,
+		high: Bound<&'r [u8]>,
+	) -> Result<ValueIter<'_>> {
+		trace!("range_rev {}: lock db", tree);
+		let this = self.0.lock().unwrap();
+		trace!("range_rev {}: lock acquired", tree);
+
+		let tree = this.get_tree(tree)?;
+
+		let (bounds_sql, params) = bounds_sql(low, high);
+		let sql = format!("SELECT k, v FROM {} {} ORDER BY k DESC", tree, bounds_sql);
+
+		let params = params
+			.iter()
+			.map(|x| x as &dyn rusqlite::ToSql)
+			.collect::<Vec<_>>();
+
+		DbValueIterator::make::<&[&dyn rusqlite::ToSql]>(this, &sql, params.as_ref())
+	}
+
+	// ----
+
+	fn transaction(&self, f: &dyn ITxFn) -> TxResult<(), ()> {
+		trace!("transaction: lock db");
+		let mut this = self.0.lock().unwrap();
+		trace!("transaction: lock acquired");
+
+		let this_mut_ref: &mut SqliteDbInner = this.borrow_mut();
+
+		let mut tx = SqliteTx {
+			tx: this_mut_ref
+				.db
+				.transaction()
+				.map_err(Error::from)
+				.map_err(TxError::Db)?,
+			trees: &this_mut_ref.trees,
+		};
+		let res = match f.try_on(&mut tx) {
+			TxFnResult::Ok => {
+				tx.tx.commit().map_err(Error::from).map_err(TxError::Db)?;
+				Ok(())
+			}
+			TxFnResult::Abort => {
+				tx.tx.rollback().map_err(Error::from).map_err(TxError::Db)?;
+				Err(TxError::Abort(()))
+			}
+			TxFnResult::DbErr => {
+				tx.tx.rollback().map_err(Error::from).map_err(TxError::Db)?;
+				Err(TxError::Db(Error(
+					"(this message will be discarded)".into(),
+				)))
+			}
+		};
+
+		trace!("transaction done");
+		res
+	}
+}
+
+// ----
+
+struct SqliteTx<'a> {
+	tx: Transaction<'a>,
+	trees: &'a [String],
+}
+
+impl<'a> SqliteTx<'a> {
+	fn get_tree(&self, i: usize) -> TxOpResult<&'_ str> {
+		self.trees.get(i).map(String::as_ref).ok_or_else(|| {
+			TxOpError(Error(
+				"invalid tree id (it might have been openned after the transaction started)".into(),
+			))
+		})
+	}
+
+	fn internal_get(&self, tree: &str, key: &[u8]) -> TxOpResult<Option<Value>> {
+		let mut stmt = self
+			.tx
+			.prepare(&format!("SELECT v FROM {} WHERE k = ?1", tree))?;
+		let mut res_iter = stmt.query([key])?;
+		match res_iter.next()? {
+			None => Ok(None),
+			Some(v) => Ok(Some(v.get::<_, Vec<u8>>(0)?)),
+		}
+	}
+}
+
+impl<'a> ITx for SqliteTx<'a> {
+	fn get(&self, tree: usize, key: &[u8]) -> TxOpResult<Option<Value>> {
+		let tree = self.get_tree(tree)?;
+		self.internal_get(tree, key)
+	}
+	fn len(&self, tree: usize) -> TxOpResult<usize> {
+		let tree = self.get_tree(tree)?;
+		let mut stmt = self.tx.prepare(&format!("SELECT COUNT(*) FROM {}", tree))?;
+		let mut res_iter = stmt.query([])?;
+		match res_iter.next()? {
+			None => Ok(0),
+			Some(v) => Ok(v.get::<_, usize>(0)?),
+		}
+	}
+
+	fn insert(&mut self, tree: usize, key: &[u8], value: &[u8]) -> TxOpResult<Option<Value>> {
+		let tree = self.get_tree(tree)?;
+		let old_val = self.internal_get(tree, key)?;
+
+		let sql = match &old_val {
+			Some(_) => format!("UPDATE {} SET v = ?2 WHERE k = ?1", tree),
+			None => format!("INSERT INTO {} (k, v) VALUES (?1, ?2)", tree),
+		};
+		let n = self.tx.execute(&sql, params![key, value])?;
+		assert_eq!(n, 1);
+
+		Ok(old_val)
+	}
+	fn remove(&mut self, tree: usize, key: &[u8]) -> TxOpResult<Option<Value>> {
+		let tree = self.get_tree(tree)?;
+		let old_val = self.internal_get(tree, key)?;
+
+		if old_val.is_some() {
+			let n = self
+				.tx
+				.execute(&format!("DELETE FROM {} WHERE k = ?1", tree), params![key])?;
+			assert_eq!(n, 1);
+		}
+
+		Ok(old_val)
+	}
+
+	fn iter(&self, _tree: usize) -> TxOpResult<TxValueIter<'_>> {
+		unimplemented!();
+	}
+	fn iter_rev(&self, _tree: usize) -> TxOpResult<TxValueIter<'_>> {
+		unimplemented!();
+	}
+
+	fn range<'r>(
+		&self,
+		_tree: usize,
+		_low: Bound<&'r [u8]>,
+		_high: Bound<&'r [u8]>,
+	) -> TxOpResult<TxValueIter<'_>> {
+		unimplemented!();
+	}
+	fn range_rev<'r>(
+		&self,
+		_tree: usize,
+		_low: Bound<&'r [u8]>,
+		_high: Bound<&'r [u8]>,
+	) -> TxOpResult<TxValueIter<'_>> {
+		unimplemented!();
+	}
+}
+
+// ----
+
+struct DbValueIterator<'a> {
+	db: MutexGuard<'a, SqliteDbInner>,
+	stmt: Option<Statement<'a>>,
+	iter: Option<Rows<'a>>,
+	_pin: PhantomPinned,
+}
+
+impl<'a> DbValueIterator<'a> {
+	fn make<P: rusqlite::Params>(
+		db: MutexGuard<'a, SqliteDbInner>,
+		sql: &str,
+		args: P,
+	) -> Result<ValueIter<'a>> {
+		let res = DbValueIterator {
+			db,
+			stmt: None,
+			iter: None,
+			_pin: PhantomPinned,
+		};
+		let mut boxed = Box::pin(res);
+		trace!("make iterator with sql: {}", sql);
+
+		unsafe {
+			let db = NonNull::from(&boxed.db);
+			let stmt = db.as_ref().db.prepare(sql)?;
+
+			let mut_ref: Pin<&mut DbValueIterator<'a>> = Pin::as_mut(&mut boxed);
+			Pin::get_unchecked_mut(mut_ref).stmt = Some(stmt);
+
+			let mut stmt = NonNull::from(&boxed.stmt);
+			let iter = stmt.as_mut().as_mut().unwrap().query(args)?;
+
+			let mut_ref: Pin<&mut DbValueIterator<'a>> = Pin::as_mut(&mut boxed);
+			Pin::get_unchecked_mut(mut_ref).iter = Some(iter);
+		}
+
+		Ok(Box::new(DbValueIteratorPin(boxed)))
+	}
+}
+
+impl<'a> Drop for DbValueIterator<'a> {
+	fn drop(&mut self) {
+		trace!("drop iter");
+		drop(self.iter.take());
+		drop(self.stmt.take());
+	}
+}
+
+struct DbValueIteratorPin<'a>(Pin<Box<DbValueIterator<'a>>>);
+
+impl<'a> Iterator for DbValueIteratorPin<'a> {
+	type Item = Result<(Value, Value)>;
+
+	fn next(&mut self) -> Option<Self::Item> {
+		let next = unsafe {
+			let mut_ref: Pin<&mut DbValueIterator<'a>> = Pin::as_mut(&mut self.0);
+			Pin::get_unchecked_mut(mut_ref).iter.as_mut()?.next()
+		};
+		let row = match next {
+			Err(e) => return Some(Err(e.into())),
+			Ok(None) => return None,
+			Ok(Some(r)) => r,
+		};
+		let k = match row.get::<_, Vec<u8>>(0) {
+			Err(e) => return Some(Err(e.into())),
+			Ok(x) => x,
+		};
+		let v = match row.get::<_, Vec<u8>>(1) {
+			Err(e) => return Some(Err(e.into())),
+			Ok(y) => y,
+		};
+		Some(Ok((k, v)))
+	}
+}
+
+// ----
+
+fn bounds_sql<'r>(low: Bound<&'r [u8]>, high: Bound<&'r [u8]>) -> (String, Vec<Vec<u8>>) {
+	let mut sql = String::new();
+	let mut params: Vec<Vec<u8>> = vec![];
+
+	match low {
+		Bound::Included(b) => {
+			sql.push_str(" WHERE k >= ?1");
+			params.push(b.to_vec());
+		}
+		Bound::Excluded(b) => {
+			sql.push_str(" WHERE k > ?1");
+			params.push(b.to_vec());
+		}
+		Bound::Unbounded => (),
+	};
+
+	match high {
+		Bound::Included(b) => {
+			if !params.is_empty() {
+				sql.push_str(" AND k <= ?2");
+			} else {
+				sql.push_str(" WHERE k <= ?1");
+			}
+			params.push(b.to_vec());
+		}
+		Bound::Excluded(b) => {
+			if !params.is_empty() {
+				sql.push_str(" AND k < ?2");
+			} else {
+				sql.push_str(" WHERE k < ?1");
+			}
+			params.push(b.to_vec());
+		}
+		Bound::Unbounded => (),
+	}
+
+	(sql, params)
+}

src/db/test.rs

@@ -0,0 +1,106 @@
+use crate::*;
+
+use crate::lmdb_adapter::LmdbDb;
+use crate::sled_adapter::SledDb;
+use crate::sqlite_adapter::SqliteDb;
+
+fn test_suite(db: Db) {
+	let tree = db.open_tree("tree").unwrap();
+
+	let ka: &[u8] = &b"test"[..];
+	let kb: &[u8] = &b"zwello"[..];
+	let kint: &[u8] = &b"tz"[..];
+	let va: &[u8] = &b"plop"[..];
+	let vb: &[u8] = &b"plip"[..];
+	let vc: &[u8] = &b"plup"[..];
+
+	assert!(tree.insert(ka, va).unwrap().is_none());
+	assert_eq!(tree.get(ka).unwrap().unwrap(), va);
+
+	let res = db.transaction::<_, (), _>(|mut tx| {
+		assert_eq!(tx.get(&tree, ka).unwrap().unwrap(), va);
+
+		assert_eq!(tx.insert(&tree, ka, vb).unwrap().unwrap(), va);
+
+		assert_eq!(tx.get(&tree, ka).unwrap().unwrap(), vb);
+
+		tx.commit(12)
+	});
+	assert!(matches!(res, Ok(12)));
+	assert_eq!(tree.get(ka).unwrap().unwrap(), vb);
+
+	let res = db.transaction::<(), _, _>(|mut tx| {
+		assert_eq!(tx.get(&tree, ka).unwrap().unwrap(), vb);
+
+		assert_eq!(tx.insert(&tree, ka, vc).unwrap().unwrap(), vb);
+
+		assert_eq!(tx.get(&tree, ka).unwrap().unwrap(), vc);
+
+		tx.abort(42)
+	});
+	assert!(matches!(res, Err(TxError::Abort(42))));
+	assert_eq!(tree.get(ka).unwrap().unwrap(), vb);
+
+	let mut iter = tree.iter().unwrap();
+	let next = iter.next().unwrap().unwrap();
+	assert_eq!((next.0.as_ref(), next.1.as_ref()), (ka, vb));
+	assert!(iter.next().is_none());
+	drop(iter);
+
+	assert!(tree.insert(kb, vc).unwrap().is_none());
+	assert_eq!(tree.get(kb).unwrap().unwrap(), vc);
+
+	let mut iter = tree.iter().unwrap();
+	let next = iter.next().unwrap().unwrap();
+	assert_eq!((next.0.as_ref(), next.1.as_ref()), (ka, vb));
+	let next = iter.next().unwrap().unwrap();
+	assert_eq!((next.0.as_ref(), next.1.as_ref()), (kb, vc));
+	assert!(iter.next().is_none());
+	drop(iter);
+
+	let mut iter = tree.range(kint..).unwrap();
+	let next = iter.next().unwrap().unwrap();
+	assert_eq!((next.0.as_ref(), next.1.as_ref()), (kb, vc));
+	assert!(iter.next().is_none());
+	drop(iter);
+
+	let mut iter = tree.range_rev(..kint).unwrap();
+	let next = iter.next().unwrap().unwrap();
+	assert_eq!((next.0.as_ref(), next.1.as_ref()), (ka, vb));
+	assert!(iter.next().is_none());
+	drop(iter);
+
+	let mut iter = tree.iter_rev().unwrap();
+	let next = iter.next().unwrap().unwrap();
+	assert_eq!((next.0.as_ref(), next.1.as_ref()), (kb, vc));
+	let next = iter.next().unwrap().unwrap();
+	assert_eq!((next.0.as_ref(), next.1.as_ref()), (ka, vb));
+	assert!(iter.next().is_none());
+	drop(iter);
+}
+
+#[test]
+fn test_lmdb_db() {
+	let path = mktemp::Temp::new_dir().unwrap();
+	let db = heed::EnvOpenOptions::new()
+		.max_dbs(100)
+		.open(&path)
+		.unwrap();
+	let db = LmdbDb::init(db);
+	test_suite(db);
+	drop(path);
+}
+
+#[test]
+fn test_sled_db() {
+	let path = mktemp::Temp::new_dir().unwrap();
+	let db = SledDb::init(sled::open(path.to_path_buf()).unwrap());
+	test_suite(db);
+	drop(path);
+}
+
+#[test]
+fn test_sqlite_db() {
+	let db = SqliteDb::init(rusqlite::Connection::open_in_memory().unwrap());
+	test_suite(db);
+}

src/garage/Cargo.toml

@@ -21,6 +21,7 @@ path = "tests/lib.rs"
 # See more keys and their definitions at https://doc.rust-lang.org/cargo/reference/manifest.html
 
 [dependencies]
+garage_db = { version = "0.8.0", path = "../db" }
 garage_api = { version = "0.7.0", path = "../api" }
 garage_model = { version = "0.7.0", path = "../model" }
 garage_rpc = { version = "0.7.0", path = "../rpc" }
@@ -29,6 +30,7 @@ garage_util = { version = "0.7.0", path = "../util" }
 garage_web = { version = "0.7.0", path = "../web" }
 
 bytes = "1.0"
+bytesize = "1.1"
 hex = "0.4"
 tracing = { version = "0.1.30", features = ["log-always"] }
 pretty_env_logger = "0.4"
@@ -36,8 +38,6 @@ rand = "0.8"
 async-trait = "0.1.7"
 sodiumoxide = { version = "0.2.5-0", package = "kuska-sodiumoxide" }
 
-sled = "0.34"
-
 rmp-serde = "0.15"
 serde = { version = "1.0", default-features = false, features = ["derive", "rc"] }
 serde_bytes = "0.11"

src/garage/admin.rs

@@ -24,11 +24,12 @@ use garage_model::migrate::Migrate;
 use garage_model::permission::*;
 
 use crate::cli::*;
-use crate::repair::Repair;
+use crate::repair::online::OnlineRepair;
 
 pub const ADMIN_RPC_PATH: &str = "garage/admin_rpc.rs/Rpc";
 
 #[derive(Debug, Serialize, Deserialize)]
+#[allow(clippy::large_enum_variant)]
 pub enum AdminRpc {
 	BucketOperation(BucketOperation),
 	KeyOperation(KeyOperation),
@@ -39,7 +40,11 @@ pub enum AdminRpc {
 	// Replies
 	Ok(String),
 	BucketList(Vec<Bucket>),
-	BucketInfo(Bucket, HashMap<String, Key>),
+	BucketInfo {
+		bucket: Bucket,
+		relevant_keys: HashMap<String, Key>,
+		counters: HashMap<String, i64>,
+	},
 	KeyList(Vec<(String, String)>),
 	KeyInfo(Key, HashMap<Uuid, Bucket>),
 }
@@ -72,6 +77,7 @@ impl AdminRpcHandler {
 			BucketOperation::Allow(query) => self.handle_bucket_allow(query).await,
 			BucketOperation::Deny(query) => self.handle_bucket_deny(query).await,
 			BucketOperation::Website(query) => self.handle_bucket_website(query).await,
+			BucketOperation::SetQuotas(query) => self.handle_bucket_set_quotas(query).await,
 		}
 	}
 
@@ -87,6 +93,7 @@ impl AdminRpcHandler {
 				EnumerationOrder::Forward,
 			)
 			.await?;
+
 		Ok(AdminRpc::BucketList(buckets))
 	}
 
@@ -104,6 +111,15 @@ impl AdminRpcHandler {
 			.get_existing_bucket(bucket_id)
 			.await?;
 
+		let counters = self
+			.garage
+			.object_counter_table
+			.table
+			.get(&bucket_id, &EmptyKey)
+			.await?
+			.map(|x| x.filtered_values(&self.garage.system.ring.borrow()))
+			.unwrap_or_default();
+
 		let mut relevant_keys = HashMap::new();
 		for (k, _) in bucket
 			.state
@@ -139,7 +155,11 @@ impl AdminRpcHandler {
 			}
 		}
 
-		Ok(AdminRpc::BucketInfo(bucket, relevant_keys))
+		Ok(AdminRpc::BucketInfo {
+			bucket,
+			relevant_keys,
+			counters,
+		})
 	}
 
 	#[allow(clippy::ptr_arg)]
@@ -431,6 +451,60 @@ impl AdminRpcHandler {
 		Ok(AdminRpc::Ok(msg))
 	}
 
+	async fn handle_bucket_set_quotas(&self, query: &SetQuotasOpt) -> Result<AdminRpc, Error> {
+		let bucket_id = self
+			.garage
+			.bucket_helper()
+			.resolve_global_bucket_name(&query.bucket)
+			.await?
+			.ok_or_bad_request("Bucket not found")?;
+
+		let mut bucket = self
+			.garage
+			.bucket_helper()
+			.get_existing_bucket(bucket_id)
+			.await?;
+		let bucket_state = bucket.state.as_option_mut().unwrap();
+
+		if query.max_size.is_none() && query.max_objects.is_none() {
+			return Err(Error::BadRequest(
+				"You must specify either --max-size or --max-objects (or both) for this command to do something.".to_string(),
+			));
+		}
+
+		let mut quotas = bucket_state.quotas.get().clone();
+
+		match query.max_size.as_ref().map(String::as_ref) {
+			Some("none") => quotas.max_size = None,
+			Some(v) => {
+				let bs = v
+					.parse::<bytesize::ByteSize>()
+					.ok_or_bad_request(format!("Invalid size specified: {}", v))?;
+				quotas.max_size = Some(bs.as_u64());
+			}
+			_ => (),
+		}
+
+		match query.max_objects.as_ref().map(String::as_ref) {
+			Some("none") => quotas.max_objects = None,
+			Some(v) => {
+				let mo = v
+					.parse::<u64>()
+					.ok_or_bad_request(format!("Invalid number specified: {}", v))?;
+				quotas.max_objects = Some(mo);
+			}
+			_ => (),
+		}
+
+		bucket_state.quotas.update(quotas);
+		self.garage.bucket_table.insert(&bucket).await?;
+
+		Ok(AdminRpc::Ok(format!(
+			"Quotas updated for {}",
+			&query.bucket
+		)))
+	}
+
 	async fn handle_key_cmd(&self, cmd: &KeyOperation) -> Result<AdminRpc, Error> {
 		match cmd {
 			KeyOperation::List => self.handle_list_keys().await,
@@ -619,7 +693,7 @@ impl AdminRpcHandler {
 				)))
 			}
 		} else {
-			let repair = Repair {
+			let repair = OnlineRepair {
 				garage: self.garage.clone(),
 			};
 			self.garage
@@ -660,11 +734,11 @@ impl AdminRpcHandler {
 			}
 			Ok(AdminRpc::Ok(ret))
 		} else {
-			Ok(AdminRpc::Ok(self.gather_stats_local(opt)))
+			Ok(AdminRpc::Ok(self.gather_stats_local(opt)?))
 		}
 	}
 
-	fn gather_stats_local(&self, opt: StatsOpt) -> String {
+	fn gather_stats_local(&self, opt: StatsOpt) -> Result<String, Error> {
 		let mut ret = String::new();
 		writeln!(
 			&mut ret,
@@ -672,6 +746,7 @@ impl AdminRpcHandler {
 			self.garage.system.garage_version(),
 		)
 		.unwrap();
+		writeln!(&mut ret, "\nDatabase engine: {}", self.garage.db.engine()).unwrap();
 
 		// Gather ring statistics
 		let ring = self.garage.system.ring.borrow().clone();
@@ -689,59 +764,71 @@ impl AdminRpcHandler {
 			writeln!(&mut ret, "  {:?} {}", n, c).unwrap();
 		}
 
-		self.gather_table_stats(&mut ret, &self.garage.bucket_table, &opt);
+		self.gather_table_stats(&mut ret, &self.garage.bucket_table, &opt)?;
-		self.gather_table_stats(&mut ret, &self.garage.key_table, &opt);
+		self.gather_table_stats(&mut ret, &self.garage.key_table, &opt)?;
-		self.gather_table_stats(&mut ret, &self.garage.object_table, &opt);
+		self.gather_table_stats(&mut ret, &self.garage.object_table, &opt)?;
-		self.gather_table_stats(&mut ret, &self.garage.version_table, &opt);
+		self.gather_table_stats(&mut ret, &self.garage.version_table, &opt)?;
-		self.gather_table_stats(&mut ret, &self.garage.block_ref_table, &opt);
+		self.gather_table_stats(&mut ret, &self.garage.block_ref_table, &opt)?;
 
 		writeln!(&mut ret, "\nBlock manager stats:").unwrap();
 		if opt.detailed {
 			writeln!(
 				&mut ret,
 				"  number of RC entries (~= number of blocks): {}",
-				self.garage.block_manager.rc_len()
+				self.garage.block_manager.rc_len()?
 			)
 			.unwrap();
 		}
 		writeln!(
 			&mut ret,
 			"  resync queue length: {}",
-			self.garage.block_manager.resync_queue_len()
+			self.garage.block_manager.resync_queue_len()?
 		)
 		.unwrap();
 		writeln!(
 			&mut ret,
 			"  blocks with resync errors: {}",
-			self.garage.block_manager.resync_errors_len()
+			self.garage.block_manager.resync_errors_len()?
 		)
 		.unwrap();
 
-		ret
+		Ok(ret)
 	}
 
-	fn gather_table_stats<F, R>(&self, to: &mut String, t: &Arc<Table<F, R>>, opt: &StatsOpt)
+	fn gather_table_stats<F, R>(
+		&self,
+		to: &mut String,
+		t: &Arc<Table<F, R>>,
+		opt: &StatsOpt,
+	) -> Result<(), Error>
 	where
 		F: TableSchema + 'static,
 		R: TableReplication + 'static,
 	{
 		writeln!(to, "\nTable stats for {}", F::TABLE_NAME).unwrap();
 		if opt.detailed {
-			writeln!(to, "  number of items: {}", t.data.store.len()).unwrap();
+			writeln!(
+				to,
+				"  number of items: {}",
+				t.data.store.len().map_err(GarageError::from)?
+			)
+			.unwrap();
 			writeln!(
 				to,
 				"  Merkle tree size: {}",
-				t.merkle_updater.merkle_tree_len()
+				t.merkle_updater.merkle_tree_len()?
 			)
 			.unwrap();
 		}
 		writeln!(
 			to,
 			"  Merkle updater todo queue length: {}",
-			t.merkle_updater.todo_len()
+			t.merkle_updater.todo_len()?
 		)
 		.unwrap();
-		writeln!(to, "  GC todo queue length: {}", t.data.gc_todo_len()).unwrap();
+		writeln!(to, "  GC todo queue length: {}", t.data.gc_todo_len()?).unwrap();
+
+		Ok(())
 	}
 }
 

src/garage/cli/cmd.rs

@@ -169,8 +169,12 @@ pub async fn cmd_admin(
 		AdminRpc::BucketList(bl) => {
 			print_bucket_list(bl);
 		}
-		AdminRpc::BucketInfo(bucket, rk) => {
+		AdminRpc::BucketInfo {
-			print_bucket_info(&bucket, &rk);
+			bucket,
+			relevant_keys,
+			counters,
+		} => {
+			print_bucket_info(&bucket, &relevant_keys, &counters);
 		}
 		AdminRpc::KeyList(kl) => {
 			print_key_list(kl);

src/garage/cli/structs.rs

@@ -33,10 +33,15 @@ pub enum Command {
 	#[structopt(name = "migrate")]
 	Migrate(MigrateOpt),
 
-	/// Start repair of node data
+	/// Start repair of node data on remote node
 	#[structopt(name = "repair")]
 	Repair(RepairOpt),
 
+	/// Offline reparation of node data (these repairs must be run offline
+	/// directly on the server node)
+	#[structopt(name = "offline-repair")]
+	OfflineRepair(OfflineRepairOpt),
+
 	/// Gather node statistics
 	#[structopt(name = "stats")]
 	Stats(StatsOpt),
@@ -175,6 +180,10 @@ pub enum BucketOperation {
 	/// Expose as website or not
 	#[structopt(name = "website")]
 	Website(WebsiteOpt),
+
+	/// Set the quotas for this bucket
+	#[structopt(name = "set-quotas")]
+	SetQuotas(SetQuotasOpt),
 }
 
 #[derive(Serialize, Deserialize, StructOpt, Debug)]
@@ -261,6 +270,21 @@ pub struct PermBucketOpt {
 	pub bucket: String,
 }
 
+#[derive(Serialize, Deserialize, StructOpt, Debug)]
+pub struct SetQuotasOpt {
+	/// Bucket name
+	pub bucket: String,
+
+	/// Set a maximum size for the bucket (specify a size e.g. in MiB or GiB,
+	/// or `none` for no size restriction)
+	#[structopt(long = "max-size")]
+	pub max_size: Option<String>,
+
+	/// Set a maximum number of objects for the bucket (or `none` for no restriction)
+	#[structopt(long = "max-objects")]
+	pub max_objects: Option<String>,
+}
+
 #[derive(Serialize, Deserialize, StructOpt, Debug)]
 pub enum KeyOperation {
 	/// List keys
@@ -405,6 +429,27 @@ pub enum RepairWhat {
 	},
 }
 
+#[derive(Serialize, Deserialize, StructOpt, Debug, Clone)]
+pub struct OfflineRepairOpt {
+	/// Confirm the launch of the repair operation
+	#[structopt(long = "yes")]
+	pub yes: bool,
+
+	#[structopt(subcommand)]
+	pub what: OfflineRepairWhat,
+}
+
+#[derive(Serialize, Deserialize, StructOpt, Debug, Eq, PartialEq, Clone)]
+pub enum OfflineRepairWhat {
+	/// Repair K2V item counters
+	#[cfg(feature = "k2v")]
+	#[structopt(name = "k2v_item_counters")]
+	K2VItemCounters,
+	/// Repair object counters
+	#[structopt(name = "object_counters")]
+	ObjectCounters,
+}
+
 #[derive(Serialize, Deserialize, StructOpt, Debug, Clone)]
 pub struct StatsOpt {
 	/// Gather statistics from all nodes

src/garage/cli/util.rs

@@ -7,6 +7,7 @@ use garage_util::formater::format_table;
 
 use garage_model::bucket_table::*;
 use garage_model::key_table::*;
+use garage_model::s3::object_table::{BYTES, OBJECTS, UNFINISHED_UPLOADS};
 
 pub fn print_bucket_list(bl: Vec<Bucket>) {
 	println!("List of buckets:");
@@ -29,11 +30,12 @@ pub fn print_bucket_list(bl: Vec<Bucket>) {
 			[((k, n), _, _)] => format!("{}:{}", k, n),
 			s => format!("[{} local aliases]", s.len()),
 		};
+
 		table.push(format!(
 			"\t{}\t{}\t{}",
 			aliases.join(","),
 			local_aliases_n,
-			hex::encode(bucket.id)
+			hex::encode(bucket.id),
 		));
 	}
 	format_table(table);
@@ -121,7 +123,11 @@ pub fn print_key_info(key: &Key, relevant_buckets: &HashMap<Uuid, Bucket>) {
 	}
 }
 
-pub fn print_bucket_info(bucket: &Bucket, relevant_keys: &HashMap<String, Key>) {
+pub fn print_bucket_info(
+	bucket: &Bucket,
+	relevant_keys: &HashMap<String, Key>,
+	counters: &HashMap<String, i64>,
+) {
 	let key_name = |k| {
 		relevant_keys
 			.get(k)
@@ -133,7 +139,42 @@ pub fn print_bucket_info(bucket: &Bucket, relevant_keys: &HashMap<String, Key>)
 	match &bucket.state {
 		Deletable::Deleted => println!("Bucket is deleted."),
 		Deletable::Present(p) => {
-			println!("Website access: {}", p.website_config.get().is_some());
+			let size =
+				bytesize::ByteSize::b(counters.get(BYTES).cloned().unwrap_or_default() as u64);
+			println!(
+				"\nSize: {} ({})",
+				size.to_string_as(true),
+				size.to_string_as(false)
+			);
+			println!(
+				"Objects: {}",
+				counters.get(OBJECTS).cloned().unwrap_or_default()
+			);
+			println!(
+				"Unfinished multipart uploads: {}",
+				counters
+					.get(UNFINISHED_UPLOADS)
+					.cloned()
+					.unwrap_or_default()
+			);
+
+			println!("\nWebsite access: {}", p.website_config.get().is_some());
+
+			let quotas = p.quotas.get();
+			if quotas.max_size.is_some() || quotas.max_objects.is_some() {
+				println!("\nQuotas:");
+				if let Some(ms) = quotas.max_size {
+					let ms = bytesize::ByteSize::b(ms);
+					println!(
+						" maximum size: {} ({})",
+						ms.to_string_as(true),
+						ms.to_string_as(false)
+					);
+				}
+				if let Some(mo) = quotas.max_objects {
+					println!(" maximum number of objects: {}", mo);
+				}
+			}
 
 			println!("\nGlobal aliases:");
 			for (alias, _, active) in p.aliases.items().iter() {

src/garage/main.rs

@@ -61,17 +61,17 @@ async fn main() {
 	pretty_env_logger::init();
 	sodiumoxide::init().expect("Unable to init sodiumoxide");
 
+	// Abort on panic (same behavior as in Go)
+	std::panic::set_hook(Box::new(|panic_info| {
+		error!("{}", panic_info.to_string());
+		std::process::abort();
+	}));
+
 	let opt = Opt::from_args();
-
 	let res = match opt.cmd {
-		Command::Server => {
+		Command::Server => server::run_server(opt.config_file).await,
-			// Abort on panic (same behavior as in Go)
+		Command::OfflineRepair(repair_opt) => {
-			std::panic::set_hook(Box::new(|panic_info| {
+			repair::offline::offline_repair(opt.config_file, repair_opt).await
-				error!("{}", panic_info.to_string());
-				std::process::abort();
-			}));
-
-			server::run_server(opt.config_file).await
 		}
 		Command::Node(NodeOperation::NodeId(node_id_opt)) => {
 			node_id_command(opt.config_file, node_id_opt.quiet)

src/garage/repair/mod.rs

@@ -0,0 +1,2 @@
+pub mod offline;
+pub mod online;

src/garage/repair/offline.rs

@@ -0,0 +1,55 @@
+use std::path::PathBuf;
+
+use tokio::sync::watch;
+
+use garage_util::background::*;
+use garage_util::config::*;
+use garage_util::error::*;
+
+use garage_model::garage::Garage;
+
+use crate::cli::structs::*;
+
+pub async fn offline_repair(config_file: PathBuf, opt: OfflineRepairOpt) -> Result<(), Error> {
+	if !opt.yes {
+		return Err(Error::Message(
+			"Please add the --yes flag to launch repair operation".into(),
+		));
+	}
+
+	info!("Loading configuration...");
+	let config = read_config(config_file)?;
+
+	info!("Initializing background runner...");
+	let (done_tx, done_rx) = watch::channel(false);
+	let (background, await_background_done) = BackgroundRunner::new(16, done_rx);
+
+	info!("Initializing Garage main data store...");
+	let garage = Garage::new(config.clone(), background)?;
+
+	info!("Launching repair operation...");
+	match opt.what {
+		#[cfg(feature = "k2v")]
+		OfflineRepairWhat::K2VItemCounters => {
+			garage
+				.k2v
+				.counter_table
+				.offline_recount_all(&garage.k2v.item_table)?;
+		}
+		OfflineRepairWhat::ObjectCounters => {
+			garage
+				.object_counter_table
+				.offline_recount_all(&garage.object_table)?;
+		}
+	}
+
+	info!("Repair operation finished, shutting down Garage internals...");
+	done_tx.send(true).unwrap();
+	drop(garage);
+
+	await_background_done.await?;
+
+	info!("Cleaning up...");
+
+	Ok(())
+}

src/garage/repair/online.rs

@@ -11,11 +11,11 @@ use garage_util::error::Error;
 
 use crate::*;
 
-pub struct Repair {
+pub struct OnlineRepair {
 	pub garage: Arc<Garage>,
 }
 
-impl Repair {
+impl OnlineRepair {
 	pub async fn repair_worker(&self, opt: RepairOpt, must_exit: watch::Receiver<bool>) {
 		if let Err(e) = self.repair_worker_aux(opt, must_exit).await {
 			warn!("Repair worker failed with error: {}", e);
@@ -64,13 +64,23 @@ impl Repair {
 
 	async fn repair_versions(&self, must_exit: &watch::Receiver<bool>) -> Result<(), Error> {
 		let mut pos = vec![];
+		let mut i = 0;
 
-		while let Some((item_key, item_bytes)) =
+		while !*must_exit.borrow() {
-			self.garage.version_table.data.store.get_gt(&pos)?
+			let item_bytes = match self.garage.version_table.data.store.get_gt(pos)? {
-		{
+				Some((k, v)) => {
-			pos = item_key.to_vec();
+					pos = k;
+					v
+				}
+				None => break,
+			};
 
-			let version = rmp_serde::decode::from_read_ref::<_, Version>(item_bytes.as_ref())?;
+			i += 1;
+			if i % 1000 == 0 {
+				info!("repair_versions: {}", i);
+			}
+
+			let version = rmp_serde::decode::from_read_ref::<_, Version>(&item_bytes)?;
 			if version.deleted.get() {
 				continue;
 			}
@@ -98,23 +108,30 @@ impl Repair {
 					))
 					.await?;
 			}
-
-			if *must_exit.borrow() {
-				break;
-			}
 		}
+		info!("repair_versions: finished, done {}", i);
 		Ok(())
 	}
 
 	async fn repair_block_ref(&self, must_exit: &watch::Receiver<bool>) -> Result<(), Error> {
 		let mut pos = vec![];
+		let mut i = 0;
 
-		while let Some((item_key, item_bytes)) =
+		while !*must_exit.borrow() {
-			self.garage.block_ref_table.data.store.get_gt(&pos)?
+			let item_bytes = match self.garage.block_ref_table.data.store.get_gt(pos)? {
-		{
+				Some((k, v)) => {
-			pos = item_key.to_vec();
+					pos = k;
+					v
+				}
+				None => break,
+			};
 
-			let block_ref = rmp_serde::decode::from_read_ref::<_, BlockRef>(item_bytes.as_ref())?;
+			i += 1;
+			if i % 1000 == 0 {
+				info!("repair_block_ref: {}", i);
+			}
+
+			let block_ref = rmp_serde::decode::from_read_ref::<_, BlockRef>(&item_bytes)?;
 			if block_ref.deleted.get() {
 				continue;
 			}
@@ -139,11 +156,8 @@ impl Repair {
 					})
 					.await?;
 			}
-
-			if *must_exit.borrow() {
-				break;
-			}
 		}
+		info!("repair_block_ref: finished, done {}", i);
 		Ok(())
 	}
 }

src/garage/server.rs

@@ -27,24 +27,14 @@ async fn wait_from(mut chan: watch::Receiver<bool>) {
 
 pub async fn run_server(config_file: PathBuf) -> Result<(), Error> {
 	info!("Loading configuration...");
-	let config = read_config(config_file).expect("Unable to read config file");
+	let config = read_config(config_file)?;
-
-	info!("Opening database...");
-	let mut db_path = config.metadata_dir.clone();
-	db_path.push("db");
-	let db = sled::Config::default()
-		.path(&db_path)
-		.cache_capacity(config.sled_cache_capacity)
-		.flush_every_ms(Some(config.sled_flush_every_ms))
-		.open()
-		.expect("Unable to open sled DB");
 
 	info!("Initializing background runner...");
 	let watch_cancel = netapp::util::watch_ctrl_c();
 	let (background, await_background_done) = BackgroundRunner::new(16, watch_cancel.clone());
 
 	info!("Initializing Garage main data store...");
-	let garage = Garage::new(config.clone(), db, background);
+	let garage = Garage::new(config.clone(), background)?;
 
 	info!("Initialize tracing...");
 	if let Some(export_to) = config.admin.trace_sink {
@@ -54,6 +44,7 @@ pub async fn run_server(config_file: PathBuf) -> Result<(), Error> {
 	info!("Initialize Admin API server and metrics collector...");
 	let admin_server = AdminApiServer::new(garage.clone());
 
+	info!("Launching internal Garage cluster communications...");
 	let run_system = tokio::spawn(garage.system.clone().run(watch_cancel.clone()));
 
 	info!("Create admin RPC handler...");

src/garage/tests/bucket.rs

@@ -29,8 +29,7 @@ async fn test_bucket_all() {
 			.unwrap()
 			.iter()
 			.filter(|x| x.name.as_ref().is_some())
-			.find(|x| x.name.as_ref().unwrap() == "hello")
+			.any(|x| x.name.as_ref().unwrap() == "hello"));
-			.is_some());
 	}
 	{
 		// Get its location
@@ -75,13 +74,12 @@ async fn test_bucket_all() {
 	{
 		// Check bucket is deleted with List buckets
 		let r = ctx.client.list_buckets().send().await.unwrap();
-		assert!(r
+		assert!(!r
 			.buckets
 			.as_ref()
 			.unwrap()
 			.iter()
 			.filter(|x| x.name.as_ref().is_some())
-			.find(|x| x.name.as_ref().unwrap() == "hello")
+			.any(|x| x.name.as_ref().unwrap() == "hello"));
-			.is_none());
 	}
 }

src/model/Cargo.toml

@@ -14,6 +14,7 @@ path = "lib.rs"
 # See more keys and their definitions at https://doc.rust-lang.org/cargo/reference/manifest.html
 
 [dependencies]
+garage_db = { version = "0.8.0", path = "../db" }
 garage_rpc = { version = "0.7.0", path = "../rpc" }
 garage_table = { version = "0.7.0", path = "../table" }
 garage_block = { version = "0.7.0", path = "../block" }
@@ -30,8 +31,6 @@ tracing = "0.1.30"
 rand = "0.8"
 zstd = { version = "0.9", default-features = false }
 
-sled = "0.34"
-
 rmp-serde = "0.15"
 serde = { version = "1.0", default-features = false, features = ["derive", "rc"] }
 serde_bytes = "0.11"

src/model/bucket_table.rs

@@ -1,6 +1,6 @@
 use serde::{Deserialize, Serialize};
 
-use garage_table::crdt::Crdt;
+use garage_table::crdt::*;
 use garage_table::*;
 use garage_util::data::*;
 use garage_util::time::*;
@@ -44,6 +44,9 @@ pub struct BucketParams {
 	pub website_config: crdt::Lww<Option<WebsiteConfig>>,
 	/// CORS rules
 	pub cors_config: crdt::Lww<Option<Vec<CorsRule>>>,
+	/// Bucket quotas
+	#[serde(default)]
+	pub quotas: crdt::Lww<BucketQuotas>,
 }
 
 #[derive(PartialEq, Eq, Clone, Debug, Serialize, Deserialize)]
@@ -62,6 +65,18 @@ pub struct CorsRule {
 	pub expose_headers: Vec<String>,
 }
 
+#[derive(Default, PartialEq, Eq, PartialOrd, Ord, Clone, Debug, Serialize, Deserialize)]
+pub struct BucketQuotas {
+	/// Maximum size in bytes (bucket size = sum of sizes of objects in the bucket)
+	pub max_size: Option<u64>,
+	/// Maximum number of non-deleted objects in the bucket
+	pub max_objects: Option<u64>,
+}
+
+impl AutoCrdt for BucketQuotas {
+	const WARN_IF_DIFFERENT: bool = true;
+}
+
 impl BucketParams {
 	/// Create an empty BucketParams with no authorized keys and no website accesss
 	pub fn new() -> Self {
@@ -72,6 +87,7 @@ impl BucketParams {
 			local_aliases: crdt::LwwMap::new(),
 			website_config: crdt::Lww::new(None),
 			cors_config: crdt::Lww::new(None),
+			quotas: crdt::Lww::new(BucketQuotas::default()),
 		}
 	}
 }
@@ -86,6 +102,7 @@ impl Crdt for BucketParams {
 
 		self.website_config.merge(&o.website_config);
 		self.cors_config.merge(&o.cors_config);
+		self.quotas.merge(&o.quotas);
 	}
 }
 

src/model/garage.rs

@@ -2,8 +2,11 @@ use std::sync::Arc;
 
 use netapp::NetworkKey;
 
+use garage_db as db;
+
 use garage_util::background::*;
 use garage_util::config::*;
+use garage_util::error::Error;
 
 use garage_rpc::system::System;
 
@@ -20,12 +23,11 @@ use crate::s3::version_table::*;
 use crate::bucket_alias_table::*;
 use crate::bucket_table::*;
 use crate::helper;
+use crate::index_counter::*;
 use crate::key_table::*;
 
 #[cfg(feature = "k2v")]
-use crate::index_counter::*;
+use crate::k2v::{item_table::*, poll::*, rpc::*};
-#[cfg(feature = "k2v")]
-use crate::k2v::{counter_table::*, item_table::*, poll::*, rpc::*};
 
 /// An entire Garage full of data
 pub struct Garage {
@@ -33,7 +35,7 @@ pub struct Garage {
 	pub config: Config,
 
 	/// The local database
-	pub db: sled::Db,
+	pub db: db::Db,
 	/// A background job runner
 	pub background: Arc<BackgroundRunner>,
 	/// The membership manager
@@ -50,6 +52,8 @@ pub struct Garage {
 
 	/// Table containing S3 objects
 	pub object_table: Arc<Table<ObjectTable, TableShardedReplication>>,
+	/// Counting table containing object counters
+	pub object_counter_table: Arc<IndexCounter<Object>>,
 	/// Table containing S3 object versions
 	pub version_table: Arc<Table<VersionTable, TableShardedReplication>>,
 	/// Table containing S3 block references (not blocks themselves)
@@ -64,14 +68,57 @@ pub struct GarageK2V {
 	/// Table containing K2V items
 	pub item_table: Arc<Table<K2VItemTable, TableShardedReplication>>,
 	/// Indexing table containing K2V item counters
-	pub counter_table: Arc<IndexCounter<K2VCounterTable>>,
+	pub counter_table: Arc<IndexCounter<K2VItem>>,
 	/// K2V RPC handler
 	pub rpc: Arc<K2VRpcHandler>,
 }
 
 impl Garage {
 	/// Create and run garage
-	pub fn new(config: Config, db: sled::Db, background: Arc<BackgroundRunner>) -> Arc<Self> {
+	pub fn new(config: Config, background: Arc<BackgroundRunner>) -> Result<Arc<Self>, Error> {
+		info!("Opening database...");
+		let mut db_path = config.metadata_dir.clone();
+		std::fs::create_dir_all(&db_path).expect("Unable to create Garage meta data directory");
+		let db = match config.db_engine.as_str() {
+			"sled" => {
+				db_path.push("db");
+				info!("Opening Sled database at: {}", db_path.display());
+				let db = db::sled_adapter::sled::Config::default()
+					.path(&db_path)
+					.cache_capacity(config.sled_cache_capacity)
+					.flush_every_ms(Some(config.sled_flush_every_ms))
+					.open()
+					.expect("Unable to open sled DB");
+				db::sled_adapter::SledDb::init(db)
+			}
+			"sqlite" | "sqlite3" | "rusqlite" => {
+				db_path.push("db.sqlite");
+				info!("Opening Sqlite database at: {}", db_path.display());
+				let db = db::sqlite_adapter::rusqlite::Connection::open(db_path)
+					.expect("Unable to open sqlite DB");
+				db::sqlite_adapter::SqliteDb::init(db)
+			}
+			"lmdb" | "heed" => {
+				db_path.push("db.lmdb");
+				info!("Opening LMDB database at: {}", db_path.display());
+				std::fs::create_dir_all(&db_path).expect("Unable to create LMDB data directory");
+				let map_size = garage_db::lmdb_adapter::recommended_map_size();
+
+				let db = db::lmdb_adapter::heed::EnvOpenOptions::new()
+					.max_dbs(100)
+					.map_size(map_size)
+					.open(&db_path)
+					.expect("Unable to open LMDB DB");
+				db::lmdb_adapter::LmdbDb::init(db)
+			}
+			e => {
+				return Err(Error::Message(format!(
+					"Unsupported DB engine: {} (options: sled, sqlite, lmdb)",
+					e
+				)));
+			}
+		};
+
 		let network_key = NetworkKey::from_slice(
 			&hex::decode(&config.rpc_secret).expect("Invalid RPC secret key")[..],
 		)
@@ -153,12 +200,16 @@ impl Garage {
 			&db,
 		);
 
+		info!("Initialize object counter table...");
+		let object_counter_table = IndexCounter::new(system.clone(), meta_rep_param.clone(), &db);
+
 		info!("Initialize object_table...");
 		#[allow(clippy::redundant_clone)]
 		let object_table = Table::new(
 			ObjectTable {
 				background: background.clone(),
 				version_table: version_table.clone(),
+				object_counter_table: object_counter_table.clone(),
 			},
 			meta_rep_param.clone(),
 			system.clone(),
@@ -169,9 +220,8 @@ impl Garage {
 		#[cfg(feature = "k2v")]
 		let k2v = GarageK2V::new(system.clone(), &db, meta_rep_param);
 
-		info!("Initialize Garage...");
+		// -- done --
-
+		Ok(Arc::new(Self {
-		Arc::new(Self {
 			config,
 			db,
 			background,
@@ -181,11 +231,12 @@ impl Garage {
 			bucket_alias_table,
 			key_table,
 			object_table,
+			object_counter_table,
 			version_table,
 			block_ref_table,
 			#[cfg(feature = "k2v")]
 			k2v,
-		})
+		}))
 	}
 
 	pub fn bucket_helper(&self) -> helper::bucket::BucketHelper {
@@ -199,7 +250,7 @@ impl Garage {
 
 #[cfg(feature = "k2v")]
 impl GarageK2V {
-	fn new(system: Arc<System>, db: &sled::Db, meta_rep_param: TableShardedReplication) -> Self {
+	fn new(system: Arc<System>, db: &db::Db, meta_rep_param: TableShardedReplication) -> Self {
 		info!("Initialize K2V counter table...");
 		let counter_table = IndexCounter::new(system.clone(), meta_rep_param.clone(), db);
 		info!("Initialize K2V subscription manager...");

src/model/index_counter.rs

@@ -1,3 +1,4 @@
+use core::ops::Bound;
 use std::collections::{hash_map, BTreeMap, HashMap};
 use std::marker::PhantomData;
 use std::sync::Arc;
@@ -6,34 +7,42 @@ use std::time::Duration;
 use serde::{Deserialize, Serialize};
 use tokio::sync::{mpsc, watch};
 
+use garage_db as db;
+
 use garage_rpc::ring::Ring;
 use garage_rpc::system::System;
 use garage_util::data::*;
 use garage_util::error::*;
+use garage_util::time::*;
 
 use garage_table::crdt::*;
-use garage_table::replication::TableShardedReplication;
+use garage_table::replication::*;
 use garage_table::*;
 
-pub trait CounterSchema: Clone + PartialEq + Send + Sync + 'static {
+pub trait CountedItem: Clone + PartialEq + Send + Sync + 'static {
-	const NAME: &'static str;
+	const COUNTER_TABLE_NAME: &'static str;
-	type P: PartitionKey + Clone + PartialEq + Serialize + for<'de> Deserialize<'de> + Send + Sync;
+
-	type S: SortKey + Clone + PartialEq + Serialize + for<'de> Deserialize<'de> + Send + Sync;
+	type CP: PartitionKey + Clone + PartialEq + Serialize + for<'de> Deserialize<'de> + Send + Sync;
+	type CS: SortKey + Clone + PartialEq + Serialize + for<'de> Deserialize<'de> + Send + Sync;
+
+	fn counter_partition_key(&self) -> &Self::CP;
+	fn counter_sort_key(&self) -> &Self::CS;
+	fn counts(&self) -> Vec<(&'static str, i64)>;
 }
 
 /// A counter entry in the global table
-#[derive(PartialEq, Clone, Debug, Serialize, Deserialize)]
+#[derive(Clone, PartialEq, Debug, Serialize, Deserialize)]
-pub struct CounterEntry<T: CounterSchema> {
+pub struct CounterEntry<T: CountedItem> {
-	pub pk: T::P,
+	pub pk: T::CP,
-	pub sk: T::S,
+	pub sk: T::CS,
 	pub values: BTreeMap<String, CounterValue>,
 }
 
-impl<T: CounterSchema> Entry<T::P, T::S> for CounterEntry<T> {
+impl<T: CountedItem> Entry<T::CP, T::CS> for CounterEntry<T> {
-	fn partition_key(&self) -> &T::P {
+	fn partition_key(&self) -> &T::CP {
 		&self.pk
 	}
-	fn sort_key(&self) -> &T::S {
+	fn sort_key(&self) -> &T::CS {
 		&self.sk
 	}
 	fn is_tombstone(&self) -> bool {
@@ -43,7 +52,7 @@ impl<T: CounterSchema> Entry<T::P, T::S> for CounterEntry<T> {
 	}
 }
 
-impl<T: CounterSchema> CounterEntry<T> {
+impl<T: CountedItem> CounterEntry<T> {
 	pub fn filtered_values(&self, ring: &Ring) -> HashMap<String, i64> {
 		let nodes = &ring.layout.node_id_vec[..];
 		self.filtered_values_with_nodes(nodes)
@@ -76,7 +85,7 @@ pub struct CounterValue {
 	pub node_values: BTreeMap<Uuid, (u64, i64)>,
 }
 
-impl<T: CounterSchema> Crdt for CounterEntry<T> {
+impl<T: CountedItem> Crdt for CounterEntry<T> {
 	fn merge(&mut self, other: &Self) {
 		for (name, e2) in other.values.iter() {
 			if let Some(e) = self.values.get_mut(name) {
@@ -102,22 +111,18 @@ impl Crdt for CounterValue {
 	}
 }
 
-pub struct CounterTable<T: CounterSchema> {
+pub struct CounterTable<T: CountedItem> {
 	_phantom_t: PhantomData<T>,
 }
 
-impl<T: CounterSchema> TableSchema for CounterTable<T> {
+impl<T: CountedItem> TableSchema for CounterTable<T> {
-	const TABLE_NAME: &'static str = T::NAME;
+	const TABLE_NAME: &'static str = T::COUNTER_TABLE_NAME;
 
-	type P = T::P;
+	type P = T::CP;
-	type S = T::S;
+	type S = T::CS;
 	type E = CounterEntry<T>;
 	type Filter = (DeletedFilter, Vec<Uuid>);
 
-	fn updated(&self, _old: Option<&Self::E>, _new: Option<&Self::E>) {
-		// nothing for now
-	}
-
 	fn matches_filter(entry: &Self::E, filter: &Self::Filter) -> bool {
 		if filter.0 == DeletedFilter::Any {
 			return true;
@@ -133,18 +138,18 @@ impl<T: CounterSchema> TableSchema for CounterTable<T> {
 
 // ----
 
-pub struct IndexCounter<T: CounterSchema> {
+pub struct IndexCounter<T: CountedItem> {
 	this_node: Uuid,
-	local_counter: sled::Tree,
+	local_counter: db::Tree,
-	propagate_tx: mpsc::UnboundedSender<(T::P, T::S, LocalCounterEntry)>,
+	propagate_tx: mpsc::UnboundedSender<(T::CP, T::CS, LocalCounterEntry<T>)>,
 	pub table: Arc<Table<CounterTable<T>, TableShardedReplication>>,
 }
 
-impl<T: CounterSchema> IndexCounter<T> {
+impl<T: CountedItem> IndexCounter<T> {
 	pub fn new(
 		system: Arc<System>,
 		replication: TableShardedReplication,
-		db: &sled::Db,
+		db: &db::Db,
 	) -> Arc<Self> {
 		let background = system.background.clone();
 
@@ -153,7 +158,7 @@ impl<T: CounterSchema> IndexCounter<T> {
 		let this = Arc::new(Self {
 			this_node: system.id,
 			local_counter: db
-				.open_tree(format!("local_counter:{}", T::NAME))
+				.open_tree(format!("local_counter_v2:{}", T::COUNTER_TABLE_NAME))
 				.expect("Unable to open local counter tree"),
 			propagate_tx,
 			table: Table::new(
@@ -168,42 +173,63 @@ impl<T: CounterSchema> IndexCounter<T> {
 
 		let this2 = this.clone();
 		background.spawn_worker(
-			format!("{} index counter propagator", T::NAME),
+			format!("{} index counter propagator", T::COUNTER_TABLE_NAME),
 			move |must_exit| this2.clone().propagate_loop(propagate_rx, must_exit),
 		);
 		this
 	}
 
-	pub fn count(&self, pk: &T::P, sk: &T::S, counts: &[(&str, i64)]) -> Result<(), Error> {
+	pub fn count(
+		&self,
+		tx: &mut db::Transaction,
+		old: Option<&T>,
+		new: Option<&T>,
+	) -> db::TxResult<(), Error> {
+		let pk = old
+			.map(|e| e.counter_partition_key())
+			.unwrap_or_else(|| new.unwrap().counter_partition_key());
+		let sk = old
+			.map(|e| e.counter_sort_key())
+			.unwrap_or_else(|| new.unwrap().counter_sort_key());
+
+		// calculate counter differences
+		let mut counts = HashMap::new();
+		for (k, v) in old.map(|x| x.counts()).unwrap_or_default() {
+			*counts.entry(k).or_insert(0) -= v;
+		}
+		for (k, v) in new.map(|x| x.counts()).unwrap_or_default() {
+			*counts.entry(k).or_insert(0) += v;
+		}
+
+		// update local counter table
 		let tree_key = self.table.data.tree_key(pk, sk);
 
-		let new_entry = self.local_counter.transaction(|tx| {
+		let mut entry = match tx.get(&self.local_counter, &tree_key[..])? {
-			let mut entry = match tx.get(&tree_key[..])? {
+			Some(old_bytes) => {
-				Some(old_bytes) => {
+				rmp_serde::decode::from_read_ref::<_, LocalCounterEntry<T>>(&old_bytes)
-					rmp_serde::decode::from_read_ref::<_, LocalCounterEntry>(&old_bytes)
+					.map_err(Error::RmpDecode)
-						.map_err(Error::RmpDecode)
+					.map_err(db::TxError::Abort)?
-						.map_err(sled::transaction::ConflictableTransactionError::Abort)?
-				}
-				None => LocalCounterEntry {
-					values: BTreeMap::new(),
-				},
-			};
-
-			for (s, inc) in counts.iter() {
-				let mut ent = entry.values.entry(s.to_string()).or_insert((0, 0));
-				ent.0 += 1;
-				ent.1 += *inc;
 			}
+			None => LocalCounterEntry {
+				pk: pk.clone(),
+				sk: sk.clone(),
+				values: BTreeMap::new(),
+			},
+		};
 
-			let new_entry_bytes = rmp_to_vec_all_named(&entry)
+		let now = now_msec();
-				.map_err(Error::RmpEncode)
+		for (s, inc) in counts.iter() {
-				.map_err(sled::transaction::ConflictableTransactionError::Abort)?;
+			let mut ent = entry.values.entry(s.to_string()).or_insert((0, 0));
-			tx.insert(&tree_key[..], new_entry_bytes)?;
+			ent.0 = std::cmp::max(ent.0 + 1, now);
+			ent.1 += *inc;
+		}
 
-			Ok(entry)
+		let new_entry_bytes = rmp_to_vec_all_named(&entry)
-		})?;
+			.map_err(Error::RmpEncode)
+			.map_err(db::TxError::Abort)?;
+		tx.insert(&self.local_counter, &tree_key[..], new_entry_bytes)?;
 
-		if let Err(e) = self.propagate_tx.send((pk.clone(), sk.clone(), new_entry)) {
+		if let Err(e) = self.propagate_tx.send((pk.clone(), sk.clone(), entry)) {
 			error!(
 				"Could not propagate updated counter values, failed to send to channel: {}",
 				e
@@ -215,7 +241,7 @@ impl<T: CounterSchema> IndexCounter<T> {
 
 	async fn propagate_loop(
 		self: Arc<Self>,
-		mut propagate_rx: mpsc::UnboundedReceiver<(T::P, T::S, LocalCounterEntry)>,
+		mut propagate_rx: mpsc::UnboundedReceiver<(T::CP, T::CS, LocalCounterEntry<T>)>,
 		must_exit: watch::Receiver<bool>,
 	) {
 		// This loop batches updates to counters to be sent all at once.
@@ -238,7 +264,7 @@ impl<T: CounterSchema> IndexCounter<T> {
 
 			if let Some((pk, sk, counters)) = ent {
 				let tree_key = self.table.data.tree_key(&pk, &sk);
-				let dist_entry = counters.into_counter_entry::<T>(self.this_node, pk, sk);
+				let dist_entry = counters.into_counter_entry(self.this_node);
 				match buf.entry(tree_key) {
 					hash_map::Entry::Vacant(e) => {
 						e.insert(dist_entry);
@@ -257,10 +283,10 @@ impl<T: CounterSchema> IndexCounter<T> {
 				if let Err(e) = self.table.insert_many(entries).await {
 					errors += 1;
 					if errors >= 2 && *must_exit.borrow() {
-						error!("({}) Could not propagate {} counter values: {}, these counters will not be updated correctly.", T::NAME, buf.len(), e);
+						error!("({}) Could not propagate {} counter values: {}, these counters will not be updated correctly.", T::COUNTER_TABLE_NAME, buf.len(), e);
 						break;
 					}
-					warn!("({}) Could not propagate {} counter values: {}, retrying in 5 seconds (retry #{})", T::NAME, buf.len(), e, errors);
+					warn!("({}) Could not propagate {} counter values: {}, retrying in 5 seconds (retry #{})", T::COUNTER_TABLE_NAME, buf.len(), e, errors);
 					tokio::time::sleep(Duration::from_secs(5)).await;
 					continue;
 				}
@@ -274,23 +300,155 @@ impl<T: CounterSchema> IndexCounter<T> {
 			}
 		}
 	}
+
+	pub fn offline_recount_all<TS, TR>(
+		&self,
+		counted_table: &Arc<Table<TS, TR>>,
+	) -> Result<(), Error>
+	where
+		TS: TableSchema<E = T>,
+		TR: TableReplication,
+	{
+		let save_counter_entry = |entry: CounterEntry<T>| -> Result<(), Error> {
+			let entry_k = self
+				.table
+				.data
+				.tree_key(entry.partition_key(), entry.sort_key());
+			self.table
+				.data
+				.update_entry_with(&entry_k, |ent| match ent {
+					Some(mut ent) => {
+						ent.merge(&entry);
+						ent
+					}
+					None => entry.clone(),
+				})?;
+			Ok(())
+		};
+
+		// 1. Set all old local counters to zero
+		let now = now_msec();
+		let mut next_start: Option<Vec<u8>> = None;
+		loop {
+			let low_bound = match next_start.take() {
+				Some(v) => Bound::Excluded(v),
+				None => Bound::Unbounded,
+			};
+			let mut batch = vec![];
+			for item in self.local_counter.range((low_bound, Bound::Unbounded))? {
+				batch.push(item?);
+				if batch.len() > 1000 {
+					break;
+				}
+			}
+
+			if batch.is_empty() {
+				break;
+			}
+
+			info!("zeroing old counters... ({})", hex::encode(&batch[0].0));
+			for (local_counter_k, local_counter) in batch {
+				let mut local_counter =
+					rmp_serde::decode::from_read_ref::<_, LocalCounterEntry<T>>(&local_counter)?;
+
+				for (_, tv) in local_counter.values.iter_mut() {
+					tv.0 = std::cmp::max(tv.0 + 1, now);
+					tv.1 = 0;
+				}
+
+				let local_counter_bytes = rmp_to_vec_all_named(&local_counter)?;
+				self.local_counter
+					.insert(&local_counter_k, &local_counter_bytes)?;
+
+				let counter_entry = local_counter.into_counter_entry(self.this_node);
+				save_counter_entry(counter_entry)?;
+
+				next_start = Some(local_counter_k);
+			}
+		}
+
+		// 2. Recount all table entries
+		let now = now_msec();
+		let mut next_start: Option<Vec<u8>> = None;
+		loop {
+			let low_bound = match next_start.take() {
+				Some(v) => Bound::Excluded(v),
+				None => Bound::Unbounded,
+			};
+			let mut batch = vec![];
+			for item in counted_table
+				.data
+				.store
+				.range((low_bound, Bound::Unbounded))?
+			{
+				batch.push(item?);
+				if batch.len() > 1000 {
+					break;
+				}
+			}
+
+			if batch.is_empty() {
+				break;
+			}
+
+			info!("counting entries... ({})", hex::encode(&batch[0].0));
+			for (counted_entry_k, counted_entry) in batch {
+				let counted_entry = counted_table.data.decode_entry(&counted_entry)?;
+
+				let pk = counted_entry.counter_partition_key();
+				let sk = counted_entry.counter_sort_key();
+				let counts = counted_entry.counts();
+
+				let local_counter_key = self.table.data.tree_key(pk, sk);
+				let mut local_counter = match self.local_counter.get(&local_counter_key)? {
+					Some(old_bytes) => {
+						let ent = rmp_serde::decode::from_read_ref::<_, LocalCounterEntry<T>>(
+							&old_bytes,
+						)?;
+						assert!(ent.pk == *pk);
+						assert!(ent.sk == *sk);
+						ent
+					}
+					None => LocalCounterEntry {
+						pk: pk.clone(),
+						sk: sk.clone(),
+						values: BTreeMap::new(),
+					},
+				};
+				for (s, v) in counts.iter() {
+					let mut tv = local_counter.values.entry(s.to_string()).or_insert((0, 0));
+					tv.0 = std::cmp::max(tv.0 + 1, now);
+					tv.1 += v;
+				}
+
+				let local_counter_bytes = rmp_to_vec_all_named(&local_counter)?;
+				self.local_counter
+					.insert(&local_counter_key, local_counter_bytes)?;
+
+				let counter_entry = local_counter.into_counter_entry(self.this_node);
+				save_counter_entry(counter_entry)?;
+
+				next_start = Some(counted_entry_k);
+			}
+		}
+
+		// Done
+		Ok(())
+	}
 }
 
 #[derive(PartialEq, Clone, Debug, Serialize, Deserialize)]
-struct LocalCounterEntry {
+struct LocalCounterEntry<T: CountedItem> {
+	pk: T::CP,
+	sk: T::CS,
 	values: BTreeMap<String, (u64, i64)>,
 }
 
-impl LocalCounterEntry {
+impl<T: CountedItem> LocalCounterEntry<T> {
-	fn into_counter_entry<T: CounterSchema>(
+	fn into_counter_entry(self, this_node: Uuid) -> CounterEntry<T> {
-		self,
-		this_node: Uuid,
-		pk: T::P,
-		sk: T::S,
-	) -> CounterEntry<T> {
 		CounterEntry {
-			pk,
+			pk: self.pk,
-			sk,
+			sk: self.sk,
 			values: self
 				.values
 				.into_iter()

src/model/k2v/counter_table.rs

@@ -1,20 +0,0 @@
-use garage_util::data::*;
-
-use crate::index_counter::*;
-
-pub const ENTRIES: &str = "entries";
-pub const CONFLICTS: &str = "conflicts";
-pub const VALUES: &str = "values";
-pub const BYTES: &str = "bytes";
-
-#[derive(PartialEq, Clone)]
-pub struct K2VCounterTable;
-
-impl CounterSchema for K2VCounterTable {
-	const NAME: &'static str = "k2v_index_counter";
-
-	// Partition key = bucket id
-	type P = Uuid;
-	// Sort key = K2V item's partition key
-	type S = String;
-}

src/model/k2v/item_table.rs

@@ -2,6 +2,7 @@ use serde::{Deserialize, Serialize};
 use std::collections::BTreeMap;
 use std::sync::Arc;
 
+use garage_db as db;
 use garage_util::data::*;
 
 use garage_table::crdt::*;
@@ -9,9 +10,13 @@ use garage_table::*;
 
 use crate::index_counter::*;
 use crate::k2v::causality::*;
-use crate::k2v::counter_table::*;
 use crate::k2v::poll::*;
 
+pub const ENTRIES: &str = "entries";
+pub const CONFLICTS: &str = "conflicts";
+pub const VALUES: &str = "values";
+pub const BYTES: &str = "bytes";
+
 #[derive(PartialEq, Clone, Debug, Serialize, Deserialize)]
 pub struct K2VItem {
 	pub partition: K2VItemPartition,
@@ -111,27 +116,6 @@ impl K2VItem {
 			ent.discard();
 		}
 	}
-
-	// returns counters: (non-deleted entries, conflict entries, non-tombstone values, bytes used)
-	fn stats(&self) -> (i64, i64, i64, i64) {
-		let values = self.values();
-
-		let n_entries = if self.is_tombstone() { 0 } else { 1 };
-		let n_conflicts = if values.len() > 1 { 1 } else { 0 };
-		let n_values = values
-			.iter()
-			.filter(|v| matches!(v, DvvsValue::Value(_)))
-			.count() as i64;
-		let n_bytes = values
-			.iter()
-			.map(|v| match v {
-				DvvsValue::Deleted => 0,
-				DvvsValue::Value(v) => v.len() as i64,
-			})
-			.sum();
-
-		(n_entries, n_conflicts, n_values, n_bytes)
-	}
 }
 
 impl DvvsEntry {
@@ -203,7 +187,7 @@ impl Entry<K2VItemPartition, String> for K2VItem {
 }
 
 pub struct K2VItemTable {
-	pub(crate) counter_table: Arc<IndexCounter<K2VCounterTable>>,
+	pub(crate) counter_table: Arc<IndexCounter<K2VItem>>,
 	pub(crate) subscriptions: Arc<SubscriptionManager>,
 }
 
@@ -221,41 +205,30 @@ impl TableSchema for K2VItemTable {
 	type E = K2VItem;
 	type Filter = ItemFilter;
 
-	fn updated(&self, old: Option<&Self::E>, new: Option<&Self::E>) {
+	fn updated(
+		&self,
+		tx: &mut db::Transaction,
+		old: Option<&Self::E>,
+		new: Option<&Self::E>,
+	) -> db::TxOpResult<()> {
 		// 1. Count
-		let (old_entries, old_conflicts, old_values, old_bytes) = match old {
+		let counter_res = self.counter_table.count(tx, old, new);
-			None => (0, 0, 0, 0),
+		if let Err(e) = db::unabort(counter_res)? {
-			Some(e) => e.stats(),
+			// This result can be returned by `counter_table.count()` for instance
-		};
+			// if messagepack serialization or deserialization fails at some step.
-		let (new_entries, new_conflicts, new_values, new_bytes) = match new {
+			// Warn admin but ignore this error for now, that's all we can do.
-			None => (0, 0, 0, 0),
+			error!(
-			Some(e) => e.stats(),
+				"Unable to update K2V item counter: {}. Index values will be wrong!",
-		};
+				e
-
+			);
-		let count_pk = old
-			.map(|e| e.partition.bucket_id)
-			.unwrap_or_else(|| new.unwrap().partition.bucket_id);
-		let count_sk = old
-			.map(|e| &e.partition.partition_key)
-			.unwrap_or_else(|| &new.unwrap().partition.partition_key);
-
-		if let Err(e) = self.counter_table.count(
-			&count_pk,
-			count_sk,
-			&[
-				(ENTRIES, new_entries - old_entries),
-				(CONFLICTS, new_conflicts - old_conflicts),
-				(VALUES, new_values - old_values),
-				(BYTES, new_bytes - old_bytes),
-			],
-		) {
-			error!("Could not update K2V counter for bucket {:?} partition {}; counts will now be inconsistent. {}", count_pk, count_sk, e);
 		}
 
 		// 2. Notify
 		if let Some(new_ent) = new {
 			self.subscriptions.notify(new_ent);
 		}
+
+		Ok(())
 	}
 
 	#[allow(clippy::nonminimal_bool)]
@@ -266,6 +239,47 @@ impl TableSchema for K2VItemTable {
 	}
 }
 
+impl CountedItem for K2VItem {
+	const COUNTER_TABLE_NAME: &'static str = "k2v_index_counter_v2";
+
+	// Partition key = bucket id
+	type CP = Uuid;
+	// Sort key = K2V item's partition key
+	type CS = String;
+
+	fn counter_partition_key(&self) -> &Uuid {
+		&self.partition.bucket_id
+	}
+	fn counter_sort_key(&self) -> &String {
+		&self.partition.partition_key
+	}
+
+	fn counts(&self) -> Vec<(&'static str, i64)> {
+		let values = self.values();
+
+		let n_entries = if self.is_tombstone() { 0 } else { 1 };
+		let n_conflicts = if values.len() > 1 { 1 } else { 0 };
+		let n_values = values
+			.iter()
+			.filter(|v| matches!(v, DvvsValue::Value(_)))
+			.count() as i64;
+		let n_bytes = values
+			.iter()
+			.map(|v| match v {
+				DvvsValue::Deleted => 0,
+				DvvsValue::Value(v) => v.len() as i64,
+			})
+			.sum();
+
+		vec![
+			(ENTRIES, n_entries),
+			(CONFLICTS, n_conflicts),
+			(VALUES, n_values),
+			(BYTES, n_bytes),
+		]
+	}
+}
+
 #[cfg(test)]
 mod tests {
 	use super::*;

src/model/k2v/mod.rs

@@ -1,6 +1,5 @@
 pub mod causality;
 
-pub mod counter_table;
 pub mod item_table;
 
 pub mod poll;

src/model/migrate.rs

@@ -25,11 +25,15 @@ impl Migrate {
 			.open_tree("bucket:table")
 			.map_err(GarageError::from)?;
 
-		for res in tree.iter() {
+		let mut old_buckets = vec![];
+		for res in tree.iter().map_err(GarageError::from)? {
 			let (_k, v) = res.map_err(GarageError::from)?;
 			let bucket = rmp_serde::decode::from_read_ref::<_, old_bucket::Bucket>(&v[..])
 				.map_err(GarageError::from)?;
+			old_buckets.push(bucket);
+		}
 
+		for bucket in old_buckets {
 			if let old_bucket::BucketState::Present(p) = bucket.state.get() {
 				self.migrate_buckets050_do_bucket(&bucket, p).await?;
 			}
@@ -73,6 +77,7 @@ impl Migrate {
 					local_aliases: LwwMap::new(),
 					website_config: Lww::new(website),
 					cors_config: Lww::new(None),
+					quotas: Lww::new(Default::default()),
 				}),
 			})
 			.await?;

src/model/s3/block_ref_table.rs

@@ -1,6 +1,8 @@
 use serde::{Deserialize, Serialize};
 use std::sync::Arc;
 
+use garage_db as db;
+
 use garage_util::data::*;
 
 use garage_table::crdt::Crdt;
@@ -51,21 +53,22 @@ impl TableSchema for BlockRefTable {
 	type E = BlockRef;
 	type Filter = DeletedFilter;
 
-	fn updated(&self, old: Option<&Self::E>, new: Option<&Self::E>) {
+	fn updated(
-		#[allow(clippy::or_fun_call)]
+		&self,
-		let block = &old.or(new).unwrap().block;
+		tx: &mut db::Transaction,
+		old: Option<&Self::E>,
+		new: Option<&Self::E>,
+	) -> db::TxOpResult<()> {
+		let block = old.or(new).unwrap().block;
 		let was_before = old.map(|x| !x.deleted.get()).unwrap_or(false);
 		let is_after = new.map(|x| !x.deleted.get()).unwrap_or(false);
 		if is_after && !was_before {
-			if let Err(e) = self.block_manager.block_incref(block) {
+			self.block_manager.block_incref(tx, block)?;
-				warn!("block_incref failed for block {:?}: {}", block, e);
-			}
 		}
 		if was_before && !is_after {
-			if let Err(e) = self.block_manager.block_decref(block) {
+			self.block_manager.block_decref(tx, block)?;
-				warn!("block_decref failed for block {:?}: {}", block, e);
-			}
 		}
+		Ok(())
 	}
 
 	fn matches_filter(entry: &Self::E, filter: &Self::Filter) -> bool {

src/model/s3/object_table.rs

@@ -2,6 +2,8 @@ use serde::{Deserialize, Serialize};
 use std::collections::BTreeMap;
 use std::sync::Arc;
 
+use garage_db as db;
+
 use garage_util::background::BackgroundRunner;
 use garage_util::data::*;
 
@@ -9,10 +11,15 @@ use garage_table::crdt::*;
 use garage_table::replication::TableShardedReplication;
 use garage_table::*;
 
+use crate::index_counter::*;
 use crate::s3::version_table::*;
 
 use garage_model_050::object_table as old;
 
+pub const OBJECTS: &str = "objects";
+pub const UNFINISHED_UPLOADS: &str = "unfinished_uploads";
+pub const BYTES: &str = "bytes";
+
 /// An object
 #[derive(PartialEq, Clone, Debug, Serialize, Deserialize)]
 pub struct Object {
@@ -216,6 +223,7 @@ impl Crdt for Object {
 pub struct ObjectTable {
 	pub background: Arc<BackgroundRunner>,
 	pub version_table: Arc<Table<VersionTable, TableShardedReplication>>,
+	pub object_counter_table: Arc<IndexCounter<Object>>,
 }
 
 #[derive(Clone, Copy, Debug, Serialize, Deserialize)]
@@ -232,7 +240,22 @@ impl TableSchema for ObjectTable {
 	type E = Object;
 	type Filter = ObjectFilter;
 
-	fn updated(&self, old: Option<&Self::E>, new: Option<&Self::E>) {
+	fn updated(
+		&self,
+		tx: &mut db::Transaction,
+		old: Option<&Self::E>,
+		new: Option<&Self::E>,
+	) -> db::TxOpResult<()> {
+		// 1. Count
+		let counter_res = self.object_counter_table.count(tx, old, new);
+		if let Err(e) = db::unabort(counter_res)? {
+			error!(
+				"Unable to update object counter: {}. Index values will be wrong!",
+				e
+			);
+		}
+
+		// 2. Spawn threads that propagates deletions to version table
 		let version_table = self.version_table.clone();
 		let old = old.cloned();
 		let new = new.cloned();
@@ -259,7 +282,8 @@ impl TableSchema for ObjectTable {
 				}
 			}
 			Ok(())
-		})
+		});
+		Ok(())
 	}
 
 	fn matches_filter(entry: &Self::E, filter: &Self::Filter) -> bool {
@@ -275,6 +299,49 @@ impl TableSchema for ObjectTable {
 	}
 }
 
+impl CountedItem for Object {
+	const COUNTER_TABLE_NAME: &'static str = "bucket_object_counter";
+
+	// Partition key = bucket id
+	type CP = Uuid;
+	// Sort key = nothing
+	type CS = EmptyKey;
+
+	fn counter_partition_key(&self) -> &Uuid {
+		&self.bucket_id
+	}
+	fn counter_sort_key(&self) -> &EmptyKey {
+		&EmptyKey
+	}
+
+	fn counts(&self) -> Vec<(&'static str, i64)> {
+		let versions = self.versions();
+		let n_objects = if versions.iter().any(|v| v.is_data()) {
+			1
+		} else {
+			0
+		};
+		let n_unfinished_uploads = versions
+			.iter()
+			.filter(|v| matches!(v.state, ObjectVersionState::Uploading(_)))
+			.count();
+		let n_bytes = versions
+			.iter()
+			.map(|v| match &v.state {
+				ObjectVersionState::Complete(ObjectVersionData::Inline(meta, _))
+				| ObjectVersionState::Complete(ObjectVersionData::FirstBlock(meta, _)) => meta.size,
+				_ => 0,
+			})
+			.sum::<u64>();
+
+		vec![
+			(OBJECTS, n_objects),
+			(UNFINISHED_UPLOADS, n_unfinished_uploads as i64),
+			(BYTES, n_bytes as i64),
+		]
+	}
+}
+
 // vvvvvvvv migration code, stupid stuff vvvvvvvvvvvv
 // (we just want to change bucket into bucket_id by hashing it)
 

src/model/s3/version_table.rs

@@ -1,6 +1,8 @@
 use serde::{Deserialize, Serialize};
 use std::sync::Arc;
 
+use garage_db as db;
+
 use garage_util::background::BackgroundRunner;
 use garage_util::data::*;
 
@@ -137,7 +139,12 @@ impl TableSchema for VersionTable {
 	type E = Version;
 	type Filter = DeletedFilter;
 
-	fn updated(&self, old: Option<&Self::E>, new: Option<&Self::E>) {
+	fn updated(
+		&self,
+		_tx: &mut db::Transaction,
+		old: Option<&Self::E>,
+		new: Option<&Self::E>,
+	) -> db::TxOpResult<()> {
 		let block_ref_table = self.block_ref_table.clone();
 		let old = old.cloned();
 		let new = new.cloned();
@@ -160,7 +167,9 @@ impl TableSchema for VersionTable {
 				}
 			}
 			Ok(())
-		})
+		});
+
+		Ok(())
 	}
 
 	fn matches_filter(entry: &Self::E, filter: &Self::Filter) -> bool {

src/table/Cargo.toml

@@ -14,6 +14,7 @@ path = "lib.rs"
 # See more keys and their definitions at https://doc.rust-lang.org/cargo/reference/manifest.html
 
 [dependencies]
+garage_db = { version = "0.8.0", path = "../db" }
 garage_rpc = { version = "0.7.0", path = "../rpc" }
 garage_util = { version = "0.7.0", path = "../util" }
 
@@ -25,8 +26,6 @@ hexdump = "0.1"
 tracing = "0.1.30"
 rand = "0.8"
 
-sled = "0.34"
-
 rmp-serde = "0.15"
 serde = { version = "1.0", default-features = false, features = ["derive", "rc"] }
 serde_bytes = "0.11"

src/table/data.rs

@@ -3,12 +3,13 @@ use std::convert::TryInto;
 use std::sync::Arc;
 
 use serde_bytes::ByteBuf;
-use sled::{IVec, Transactional};
 use tokio::sync::Notify;
 
+use garage_db as db;
+use garage_db::counted_tree_hack::CountedTree;
+
 use garage_util::data::*;
 use garage_util::error::*;
-use garage_util::sled_counter::SledCountedTree;
 
 use garage_rpc::system::System;
 
@@ -25,12 +26,12 @@ pub struct TableData<F: TableSchema, R: TableReplication> {
 	pub instance: F,
 	pub replication: R,
 
-	pub store: sled::Tree,
+	pub store: db::Tree,
 
-	pub(crate) merkle_tree: sled::Tree,
+	pub(crate) merkle_tree: db::Tree,
-	pub(crate) merkle_todo: sled::Tree,
+	pub(crate) merkle_todo: db::Tree,
 	pub(crate) merkle_todo_notify: Notify,
-	pub(crate) gc_todo: SledCountedTree,
+	pub(crate) gc_todo: CountedTree,
 
 	pub(crate) metrics: TableMetrics,
 }
@@ -40,7 +41,7 @@ where
 	F: TableSchema,
 	R: TableReplication,
 {
-	pub fn new(system: Arc<System>, instance: F, replication: R, db: &sled::Db) -> Arc<Self> {
+	pub fn new(system: Arc<System>, instance: F, replication: R, db: &db::Db) -> Arc<Self> {
 		let store = db
 			.open_tree(&format!("{}:table", F::TABLE_NAME))
 			.expect("Unable to open DB tree");
@@ -55,7 +56,7 @@ where
 		let gc_todo = db
 			.open_tree(&format!("{}:gc_todo_v2", F::TABLE_NAME))
 			.expect("Unable to open DB tree");
-		let gc_todo = SledCountedTree::new(gc_todo);
+		let gc_todo = CountedTree::new(gc_todo).expect("Cannot count gc_todo_v2");
 
 		let metrics = TableMetrics::new(F::TABLE_NAME, merkle_todo.clone(), gc_todo.clone());
 
@@ -98,30 +99,30 @@ where
 					None => partition_hash.to_vec(),
 					Some(sk) => self.tree_key(partition_key, sk),
 				};
-				let range = self.store.range(first_key..);
+				let range = self.store.range(first_key..)?;
 				self.read_range_aux(partition_hash, range, filter, limit)
 			}
 			EnumerationOrder::Reverse => match start {
 				Some(sk) => {
 					let last_key = self.tree_key(partition_key, sk);
-					let range = self.store.range(..=last_key).rev();
+					let range = self.store.range_rev(..=last_key)?;
 					self.read_range_aux(partition_hash, range, filter, limit)
 				}
 				None => {
 					let mut last_key = partition_hash.to_vec();
 					let lower = u128::from_be_bytes(last_key[16..32].try_into().unwrap());
 					last_key[16..32].copy_from_slice(&u128::to_be_bytes(lower + 1));
-					let range = self.store.range(..last_key).rev();
+					let range = self.store.range_rev(..last_key)?;
 					self.read_range_aux(partition_hash, range, filter, limit)
 				}
 			},
 		}
 	}
 
-	fn read_range_aux(
+	fn read_range_aux<'a>(
 		&self,
 		partition_hash: Hash,
-		range: impl Iterator<Item = sled::Result<(IVec, IVec)>>,
+		range: db::ValueIter<'a>,
 		filter: &Option<F::Filter>,
 		limit: usize,
 	) -> Result<Vec<Arc<ByteBuf>>, Error> {
@@ -139,7 +140,7 @@ where
 				}
 			};
 			if keep {
-				ret.push(Arc::new(ByteBuf::from(value.as_ref())));
+				ret.push(Arc::new(ByteBuf::from(value)));
 			}
 			if ret.len() >= limit {
 				break;
@@ -183,12 +184,10 @@ where
 		tree_key: &[u8],
 		f: impl Fn(Option<F::E>) -> F::E,
 	) -> Result<Option<F::E>, Error> {
-		let changed = (&self.store, &self.merkle_todo).transaction(|(store, mkl_todo)| {
+		let changed = self.store.db().transaction(|mut tx| {
-			let (old_entry, old_bytes, new_entry) = match store.get(tree_key)? {
+			let (old_entry, old_bytes, new_entry) = match tx.get(&self.store, tree_key)? {
 				Some(old_bytes) => {
-					let old_entry = self
+					let old_entry = self.decode_entry(&old_bytes).map_err(db::TxError::Abort)?;
-						.decode_entry(&old_bytes)
-						.map_err(sled::transaction::ConflictableTransactionError::Abort)?;
 					let new_entry = f(Some(old_entry.clone()));
 					(Some(old_entry), Some(old_bytes), new_entry)
 				}
@@ -204,24 +203,28 @@ where
 			// the associated Merkle tree entry.
 			let new_bytes = rmp_to_vec_all_named(&new_entry)
 				.map_err(Error::RmpEncode)
-				.map_err(sled::transaction::ConflictableTransactionError::Abort)?;
+				.map_err(db::TxError::Abort)?;
 			let encoding_changed = Some(&new_bytes[..]) != old_bytes.as_ref().map(|x| &x[..]);
+			drop(old_bytes);
 
 			if value_changed || encoding_changed {
 				let new_bytes_hash = blake2sum(&new_bytes[..]);
-				mkl_todo.insert(tree_key.to_vec(), new_bytes_hash.as_slice())?;
+				tx.insert(&self.merkle_todo, tree_key, new_bytes_hash.as_slice())?;
-				store.insert(tree_key.to_vec(), new_bytes)?;
+				tx.insert(&self.store, tree_key, new_bytes)?;
-				Ok(Some((old_entry, new_entry, new_bytes_hash)))
+
+				self.instance
+					.updated(&mut tx, old_entry.as_ref(), Some(&new_entry))?;
+
+				Ok(Some((new_entry, new_bytes_hash)))
 			} else {
 				Ok(None)
 			}
 		})?;
 
-		if let Some((old_entry, new_entry, new_bytes_hash)) = changed {
+		if let Some((new_entry, new_bytes_hash)) = changed {
 			self.metrics.internal_update_counter.add(1);
 
 			let is_tombstone = new_entry.is_tombstone();
-			self.instance.updated(old_entry.as_ref(), Some(&new_entry));
 			self.merkle_todo_notify.notify_one();
 			if is_tombstone {
 				// We are only responsible for GC'ing this item if we are the
@@ -244,22 +247,23 @@ where
 	}
 
 	pub(crate) fn delete_if_equal(self: &Arc<Self>, k: &[u8], v: &[u8]) -> Result<bool, Error> {
-		let removed = (&self.store, &self.merkle_todo).transaction(|(store, mkl_todo)| {
+		let removed = self
-			if let Some(cur_v) = store.get(k)? {
+			.store
-				if cur_v == v {
+			.db()
-					store.remove(k)?;
+			.transaction(|mut tx| match tx.get(&self.store, k)? {
-					mkl_todo.insert(k, vec![])?;
+				Some(cur_v) if cur_v == v => {
-					return Ok(true);
+					tx.remove(&self.store, k)?;
+					tx.insert(&self.merkle_todo, k, vec![])?;
+
+					let old_entry = self.decode_entry(v).map_err(db::TxError::Abort)?;
+					self.instance.updated(&mut tx, Some(&old_entry), None)?;
+					Ok(true)
 				}
-			}
+				_ => Ok(false),
-			Ok(false)
+			})?;
-		})?;
 
 		if removed {
 			self.metrics.internal_delete_counter.add(1);
-
-			let old_entry = self.decode_entry(v)?;
-			self.instance.updated(Some(&old_entry), None);
 			self.merkle_todo_notify.notify_one();
 		}
 		Ok(removed)
@@ -270,25 +274,26 @@ where
 		k: &[u8],
 		vhash: Hash,
 	) -> Result<bool, Error> {
-		let removed = (&self.store, &self.merkle_todo).transaction(|(store, mkl_todo)| {
+		let removed = self
-			if let Some(cur_v) = store.get(k)? {
+			.store
-				if blake2sum(&cur_v[..]) == vhash {
+			.db()
-					store.remove(k)?;
+			.transaction(|mut tx| match tx.get(&self.store, k)? {
-					mkl_todo.insert(k, vec![])?;
+				Some(cur_v) if blake2sum(&cur_v[..]) == vhash => {
-					return Ok(Some(cur_v));
+					tx.remove(&self.store, k)?;
-				}
+					tx.insert(&self.merkle_todo, k, vec![])?;
-			}
-			Ok(None)
-		})?;
 
-		if let Some(old_v) = removed {
+					let old_entry = self.decode_entry(&cur_v[..]).map_err(db::TxError::Abort)?;
-			let old_entry = self.decode_entry(&old_v[..])?;
+					self.instance.updated(&mut tx, Some(&old_entry), None)?;
-			self.instance.updated(Some(&old_entry), None);
+					Ok(true)
+				}
+				_ => Ok(false),
+			})?;
+
+		if removed {
+			self.metrics.internal_delete_counter.add(1);
 			self.merkle_todo_notify.notify_one();
-			Ok(true)
-		} else {
-			Ok(false)
 		}
+		Ok(removed)
 	}
 
 	// ---- Utility functions ----
@@ -315,7 +320,7 @@ where
 		}
 	}
 
-	pub fn gc_todo_len(&self) -> usize {
+	pub fn gc_todo_len(&self) -> Result<usize, Error> {
-		self.gc_todo.len()
+		Ok(self.gc_todo.len())
 	}
 }

src/table/gc.rs

@@ -12,9 +12,10 @@ use futures::select;
 use futures_util::future::*;
 use tokio::sync::watch;
 
+use garage_db::counted_tree_hack::CountedTree;
+
 use garage_util::data::*;
 use garage_util::error::*;
-use garage_util::sled_counter::SledCountedTree;
 use garage_util::time::*;
 
 use garage_rpc::system::System;
@@ -100,18 +101,16 @@ where
 	async fn gc_loop_iter(&self) -> Result<Option<Duration>, Error> {
 		let now = now_msec();
 
-		let mut entries = vec![];
-		let mut excluded = vec![];
-
 		// List entries in the GC todo list
 		// These entries are put there when a tombstone is inserted in the table
 		// (see update_entry in data.rs)
-		for entry_kv in self.data.gc_todo.iter() {
+		let mut candidates = vec![];
+		for entry_kv in self.data.gc_todo.iter()? {
 			let (k, vhash) = entry_kv?;
-			let mut todo_entry = GcTodoEntry::parse(&k, &vhash);
+			let todo_entry = GcTodoEntry::parse(&k, &vhash);
 
 			if todo_entry.deletion_time() > now {
-				if entries.is_empty() && excluded.is_empty() {
+				if candidates.is_empty() {
 					// If the earliest entry in the todo list shouldn't yet be processed,
 					// return a duration to wait in the loop
 					return Ok(Some(Duration::from_millis(
@@ -123,15 +122,23 @@ where
 				}
 			}
 
-			let vhash = Hash::try_from(&vhash[..]).unwrap();
+			candidates.push(todo_entry);
+			if candidates.len() >= 2 * TABLE_GC_BATCH_SIZE {
+				break;
+			}
+		}
 
+		let mut entries = vec![];
+		let mut excluded = vec![];
+		for mut todo_entry in candidates {
 			// Check if the tombstone is still the current value of the entry.
 			// If not, we don't actually want to GC it, and we will remove it
 			// from the gc_todo table later (below).
+			let vhash = todo_entry.value_hash;
 			todo_entry.value = self
 				.data
 				.store
-				.get(&k[..])?
+				.get(&todo_entry.key[..])?
 				.filter(|v| blake2sum(&v[..]) == vhash)
 				.map(|v| v.to_vec());
 
@@ -353,17 +360,17 @@ impl GcTodoEntry {
 	}
 
 	/// Parses a GcTodoEntry from a (k, v) pair stored in the gc_todo tree
-	pub(crate) fn parse(sled_k: &[u8], sled_v: &[u8]) -> Self {
+	pub(crate) fn parse(db_k: &[u8], db_v: &[u8]) -> Self {
 		Self {
-			tombstone_timestamp: u64::from_be_bytes(sled_k[0..8].try_into().unwrap()),
+			tombstone_timestamp: u64::from_be_bytes(db_k[0..8].try_into().unwrap()),
-			key: sled_k[8..].to_vec(),
+			key: db_k[8..].to_vec(),
-			value_hash: Hash::try_from(sled_v).unwrap(),
+			value_hash: Hash::try_from(db_v).unwrap(),
 			value: None,
 		}
 	}
 
 	/// Saves the GcTodoEntry in the gc_todo tree
-	pub(crate) fn save(&self, gc_todo_tree: &SledCountedTree) -> Result<(), Error> {
+	pub(crate) fn save(&self, gc_todo_tree: &CountedTree) -> Result<(), Error> {
 		gc_todo_tree.insert(self.todo_table_key(), self.value_hash.as_slice())?;
 		Ok(())
 	}
@@ -373,9 +380,9 @@ impl GcTodoEntry {
 	/// This is usefull to remove a todo entry only under the condition
 	/// that it has not changed since the time it was read, i.e.
 	/// what we have to do is still the same
-	pub(crate) fn remove_if_equal(&self, gc_todo_tree: &SledCountedTree) -> Result<(), Error> {
+	pub(crate) fn remove_if_equal(&self, gc_todo_tree: &CountedTree) -> Result<(), Error> {
-		let _ = gc_todo_tree.compare_and_swap::<_, _, Vec<u8>>(
+		gc_todo_tree.compare_and_swap::<_, _, &[u8]>(
-			&self.todo_table_key()[..],
+			&self.todo_table_key(),
 			Some(self.value_hash),
 			None,
 		)?;

src/table/merkle.rs

@@ -4,11 +4,10 @@ use std::time::Duration;
 use futures::select;
 use futures_util::future::*;
 use serde::{Deserialize, Serialize};
-use sled::transaction::{
-	ConflictableTransactionError, ConflictableTransactionResult, TransactionalTree,
-};
 use tokio::sync::watch;
 
+use garage_db as db;
+
 use garage_util::background::BackgroundRunner;
 use garage_util::data::*;
 use garage_util::error::Error;
@@ -90,35 +89,35 @@ where
 
 	async fn updater_loop(self: Arc<Self>, mut must_exit: watch::Receiver<bool>) {
 		while !*must_exit.borrow() {
-			if let Some(x) = self.data.merkle_todo.iter().next() {
+			match self.updater_loop_iter() {
-				match x {
+				Ok(true) => (),
-					Ok((key, valhash)) => {
+				Ok(false) => {
-						if let Err(e) = self.update_item(&key[..], &valhash[..]) {
+					select! {
-							warn!(
+						_ = self.data.merkle_todo_notify.notified().fuse() => {},
-								"({}) Error while updating Merkle tree item: {}",
+						_ = must_exit.changed().fuse() => {},
-								F::TABLE_NAME,
-								e
-							);
-						}
-					}
-					Err(e) => {
-						warn!(
-							"({}) Error while iterating on Merkle todo tree: {}",
-							F::TABLE_NAME,
-							e
-						);
-						tokio::time::sleep(Duration::from_secs(10)).await;
 					}
 				}
-			} else {
+				Err(e) => {
-				select! {
+					warn!(
-					_ = self.data.merkle_todo_notify.notified().fuse() => {},
+						"({}) Error while updating Merkle tree item: {}",
-					_ = must_exit.changed().fuse() => {},
+						F::TABLE_NAME,
+						e
+					);
+					tokio::time::sleep(Duration::from_secs(10)).await;
 				}
 			}
 		}
 	}
 
+	fn updater_loop_iter(&self) -> Result<bool, Error> {
+		if let Some((key, valhash)) = self.data.merkle_todo.first()? {
+			self.update_item(&key, &valhash)?;
+			Ok(true)
+		} else {
+			Ok(false)
+		}
+	}
+
 	fn update_item(&self, k: &[u8], vhash_by: &[u8]) -> Result<(), Error> {
 		let khash = blake2sum(k);
 
@@ -137,13 +136,16 @@ where
 		};
 		self.data
 			.merkle_tree
-			.transaction(|tx| self.update_item_rec(tx, k, &khash, &key, new_vhash))?;
+			.db()
+			.transaction(|mut tx| self.update_item_rec(&mut tx, k, &khash, &key, new_vhash))?;
 
-		let deleted = self
+		let deleted = self.data.merkle_todo.db().transaction(|mut tx| {
-			.data
+			let remove = matches!(tx.get(&self.data.merkle_todo, k)?, Some(ov) if ov == vhash_by);
-			.merkle_todo
+			if remove {
-			.compare_and_swap::<_, _, Vec<u8>>(k, Some(vhash_by), None)?
+				tx.remove(&self.data.merkle_todo, k)?;
-			.is_ok();
+			}
+			Ok(remove)
+		})?;
 
 		if !deleted {
 			debug!(
@@ -157,12 +159,12 @@ where
 
 	fn update_item_rec(
 		&self,
-		tx: &TransactionalTree,
+		tx: &mut db::Transaction<'_>,
 		k: &[u8],
 		khash: &Hash,
 		key: &MerkleNodeKey,
 		new_vhash: Option<Hash>,
-	) -> ConflictableTransactionResult<Option<Hash>, Error> {
+	) -> db::TxResult<Option<Hash>, Error> {
 		let i = key.prefix.len();
 
 		// Read node at current position (defined by the prefix stored in key)
@@ -203,7 +205,7 @@ where
 							}
 							MerkleNode::Intermediate(_) => Some(MerkleNode::Intermediate(children)),
 							x @ MerkleNode::Leaf(_, _) => {
-								tx.remove(key_sub.encode())?;
+								tx.remove(&self.data.merkle_tree, key_sub.encode())?;
 								Some(x)
 							}
 						}
@@ -283,28 +285,27 @@ where
 
 	fn read_node_txn(
 		&self,
-		tx: &TransactionalTree,
+		tx: &mut db::Transaction<'_>,
 		k: &MerkleNodeKey,
-	) -> ConflictableTransactionResult<MerkleNode, Error> {
+	) -> db::TxResult<MerkleNode, Error> {
-		let ent = tx.get(k.encode())?;
+		let ent = tx.get(&self.data.merkle_tree, k.encode())?;
-		MerkleNode::decode_opt(ent).map_err(ConflictableTransactionError::Abort)
+		MerkleNode::decode_opt(&ent).map_err(db::TxError::Abort)
 	}
 
 	fn put_node_txn(
 		&self,
-		tx: &TransactionalTree,
+		tx: &mut db::Transaction<'_>,
 		k: &MerkleNodeKey,
 		v: &MerkleNode,
-	) -> ConflictableTransactionResult<Hash, Error> {
+	) -> db::TxResult<Hash, Error> {
 		trace!("Put Merkle node: {:?} => {:?}", k, v);
 		if *v == MerkleNode::Empty {
-			tx.remove(k.encode())?;
+			tx.remove(&self.data.merkle_tree, k.encode())?;
 			Ok(self.empty_node_hash)
 		} else {
-			let vby = rmp_to_vec_all_named(v)
+			let vby = rmp_to_vec_all_named(v).map_err(|e| db::TxError::Abort(e.into()))?;
-				.map_err(|e| ConflictableTransactionError::Abort(e.into()))?;
 			let rethash = blake2sum(&vby[..]);
-			tx.insert(k.encode(), vby)?;
+			tx.insert(&self.data.merkle_tree, k.encode(), vby)?;
 			Ok(rethash)
 		}
 	}
@@ -312,15 +313,15 @@ where
 	// Access a node in the Merkle tree, used by the sync protocol
 	pub(crate) fn read_node(&self, k: &MerkleNodeKey) -> Result<MerkleNode, Error> {
 		let ent = self.data.merkle_tree.get(k.encode())?;
-		MerkleNode::decode_opt(ent)
+		MerkleNode::decode_opt(&ent)
 	}
 
-	pub fn merkle_tree_len(&self) -> usize {
+	pub fn merkle_tree_len(&self) -> Result<usize, Error> {
-		self.data.merkle_tree.len()
+		Ok(self.data.merkle_tree.len()?)
 	}
 
-	pub fn todo_len(&self) -> usize {
+	pub fn todo_len(&self) -> Result<usize, Error> {
-		self.data.merkle_todo.len()
+		Ok(self.data.merkle_todo.len()?)
 	}
 }
 
@@ -347,7 +348,7 @@ impl MerkleNodeKey {
 }
 
 impl MerkleNode {
-	fn decode_opt(ent: Option<sled::IVec>) -> Result<Self, Error> {
+	fn decode_opt(ent: &Option<db::Value>) -> Result<Self, Error> {
 		match ent {
 			None => Ok(MerkleNode::Empty),
 			Some(v) => Ok(rmp_serde::decode::from_read_ref::<_, MerkleNode>(&v[..])?),

src/table/metrics.rs

@@ -1,6 +1,7 @@
 use opentelemetry::{global, metrics::*, KeyValue};
 
-use garage_util::sled_counter::SledCountedTree;
+use garage_db as db;
+use garage_db::counted_tree_hack::CountedTree;
 
 /// TableMetrics reference all counter used for metrics
 pub struct TableMetrics {
@@ -19,21 +20,19 @@ pub struct TableMetrics {
 	pub(crate) sync_items_received: Counter<u64>,
 }
 impl TableMetrics {
-	pub fn new(
+	pub fn new(table_name: &'static str, merkle_todo: db::Tree, gc_todo: CountedTree) -> Self {
-		table_name: &'static str,
-		merkle_todo: sled::Tree,
-		gc_todo: SledCountedTree,
-	) -> Self {
 		let meter = global::meter(table_name);
 		TableMetrics {
 			_merkle_todo_len: meter
 				.u64_value_observer(
 					"table.merkle_updater_todo_queue_length",
 					move |observer| {
-						observer.observe(
+						if let Ok(v) = merkle_todo.len() {
-							merkle_todo.len() as u64,
+							observer.observe(
-							&[KeyValue::new("table_name", table_name)],
+								v as u64,
-						)
+								&[KeyValue::new("table_name", table_name)],
+							);
+						}
 					},
 				)
 				.with_description("Merkle tree updater TODO queue length")
@@ -45,7 +44,7 @@ impl TableMetrics {
 						observer.observe(
 							gc_todo.len() as u64,
 							&[KeyValue::new("table_name", table_name)],
-						)
+						);
 					},
 				)
 				.with_description("Table garbage collector TODO queue length")

src/table/schema.rs

@@ -1,5 +1,6 @@
 use serde::{Deserialize, Serialize};
 
+use garage_db as db;
 use garage_util::data::*;
 
 use crate::crdt::Crdt;
@@ -82,11 +83,19 @@ pub trait TableSchema: Send + Sync {
 		None
 	}
 
-	// Updated triggers some stuff downstream, but it is not supposed to block or fail,
+	/// Actions triggered by data changing in a table. If such actions
-	// as the update itself is an unchangeable fact that will never go back
+	/// include updates to the local database that should be applied
-	// due to CRDT logic. Typically errors in propagation of info should be logged
+	/// atomically with the item update itself, a db transaction is
-	// to stderr.
+	/// provided on which these changes should be done.
-	fn updated(&self, _old: Option<&Self::E>, _new: Option<&Self::E>) {}
+	/// This function can return a DB error but that's all.
+	fn updated(
+		&self,
+		_tx: &mut db::Transaction,
+		_old: Option<&Self::E>,
+		_new: Option<&Self::E>,
+	) -> db::TxOpResult<()> {
+		Ok(())
+	}
 
 	fn matches_filter(entry: &Self::E, filter: &Self::Filter) -> bool;
 }

src/table/sync.rs

@@ -258,9 +258,9 @@ where
 		while !*must_exit.borrow() {
 			let mut items = Vec::new();
 
-			for item in self.data.store.range(begin.to_vec()..end.to_vec()) {
+			for item in self.data.store.range(begin.to_vec()..end.to_vec())? {
 				let (key, value) = item?;
-				items.push((key.to_vec(), Arc::new(ByteBuf::from(value.as_ref()))));
+				items.push((key.to_vec(), Arc::new(ByteBuf::from(value))));
 
 				if items.len() >= 1024 {
 					break;
@@ -603,8 +603,16 @@ impl SyncTodo {
 			let retain = nodes.contains(&my_id);
 			if !retain {
 				// Check if we have some data to send, otherwise skip
-				if data.store.range(begin..end).next().is_none() {
+				match data.store.range(begin..end) {
-					continue;
+					Ok(mut iter) => {
+						if iter.next().is_none() {
+							continue;
+						}
+					}
+					Err(e) => {
+						warn!("DB error in add_full_sync: {}", e);
+						continue;
+					}
 				}
 			}
 

src/table/table.rs

@@ -13,6 +13,8 @@ use opentelemetry::{
 	Context,
 };
 
+use garage_db as db;
+
 use garage_util::data::*;
 use garage_util::error::Error;
 use garage_util::metrics::RecordDuration;
@@ -69,7 +71,7 @@ where
 {
 	// =============== PUBLIC INTERFACE FUNCTIONS (new, insert, get, etc) ===============
 
-	pub fn new(instance: F, replication: R, system: Arc<System>, db: &sled::Db) -> Arc<Self> {
+	pub fn new(instance: F, replication: R, system: Arc<System>, db: &db::Db) -> Arc<Self> {
 		let endpoint = system
 			.netapp
 			.endpoint(format!("garage_table/table.rs/Rpc:{}", F::TABLE_NAME));

src/util/Cargo.toml

@@ -14,6 +14,8 @@ path = "lib.rs"
 # See more keys and their definitions at https://doc.rust-lang.org/cargo/reference/manifest.html
 
 [dependencies]
+garage_db = { version = "0.8.0", path = "../db" }
+
 blake2 = "0.9"
 err-derive = "0.3"
 xxhash-rust = { version = "0.8", default-features = false, features = ["xxh3"] }
@@ -22,8 +24,6 @@ tracing = "0.1.30"
 rand = "0.8"
 sha2 = "0.9"
 
-sled = "0.34"
-
 chrono = "0.4"
 rmp-serde = "0.15"
 serde = { version = "1.0", default-features = false, features = ["derive", "rc"] }

src/util/config.rs

@@ -64,14 +64,19 @@ pub struct Config {
 	#[serde(default)]
 	pub kubernetes_skip_crd: bool,
 
+	// -- DB
+	/// Database engine to use for metadata (options: sled, sqlite, lmdb)
+	#[serde(default = "default_db_engine")]
+	pub db_engine: String,
+
 	/// Sled cache size, in bytes
 	#[serde(default = "default_sled_cache_capacity")]
 	pub sled_cache_capacity: u64,
-
 	/// Sled flush interval in milliseconds
 	#[serde(default = "default_sled_flush_every_ms")]
 	pub sled_flush_every_ms: u64,
 
+	// -- APIs
 	/// Configuration for S3 api
 	pub s3_api: S3ApiConfig,
 
@@ -129,6 +134,10 @@ pub struct AdminConfig {
 	pub trace_sink: Option<String>,
 }
 
+fn default_db_engine() -> String {
+	"sled".into()
+}
+
 fn default_sled_cache_capacity() -> u64 {
 	128 * 1024 * 1024
 }

src/util/error.rs

@@ -26,8 +26,8 @@ pub enum Error {
 	#[error(display = "Netapp error: {}", _0)]
 	Netapp(#[error(source)] netapp::error::Error),
 
-	#[error(display = "Sled error: {}", _0)]
+	#[error(display = "DB error: {}", _0)]
-	Sled(#[error(source)] sled::Error),
+	Db(#[error(source)] garage_db::Error),
 
 	#[error(display = "Messagepack encode error: {}", _0)]
 	RmpEncode(#[error(source)] rmp_serde::encode::Error),
@@ -78,11 +78,11 @@ impl Error {
 	}
 }
 
-impl From<sled::transaction::TransactionError<Error>> for Error {
+impl From<garage_db::TxError<Error>> for Error {
-	fn from(e: sled::transaction::TransactionError<Error>) -> Error {
+	fn from(e: garage_db::TxError<Error>) -> Error {
 		match e {
-			sled::transaction::TransactionError::Abort(x) => x,
+			garage_db::TxError::Abort(x) => x,
-			sled::transaction::TransactionError::Storage(x) => Error::Sled(x),
+			garage_db::TxError::Db(x) => Error::Db(x),
 		}
 	}
 }

src/util/lib.rs

@@ -11,7 +11,7 @@ pub mod error;
 pub mod formater;
 pub mod metrics;
 pub mod persister;
-pub mod sled_counter;
+//pub mod sled_counter;
 pub mod time;
 pub mod token_bucket;
 pub mod tranquilizer;

src/util/sled_counter.rs

@@ -1,100 +0,0 @@
-use std::sync::{
-	atomic::{AtomicUsize, Ordering},
-	Arc,
-};
-
-use sled::{CompareAndSwapError, IVec, Iter, Result, Tree};
-
-#[derive(Clone)]
-pub struct SledCountedTree(Arc<SledCountedTreeInternal>);
-
-struct SledCountedTreeInternal {
-	tree: Tree,
-	len: AtomicUsize,
-}
-
-impl SledCountedTree {
-	pub fn new(tree: Tree) -> Self {
-		let len = tree.len();
-		Self(Arc::new(SledCountedTreeInternal {
-			tree,
-			len: AtomicUsize::new(len),
-		}))
-	}
-
-	pub fn len(&self) -> usize {
-		self.0.len.load(Ordering::Relaxed)
-	}
-
-	pub fn is_empty(&self) -> bool {
-		self.0.tree.is_empty()
-	}
-
-	pub fn get<K: AsRef<[u8]>>(&self, key: K) -> Result<Option<IVec>> {
-		self.0.tree.get(key)
-	}
-
-	pub fn iter(&self) -> Iter {
-		self.0.tree.iter()
-	}
-
-	// ---- writing functions ----
-
-	pub fn insert<K, V>(&self, key: K, value: V) -> Result<Option<IVec>>
-	where
-		K: AsRef<[u8]>,
-		V: Into<IVec>,
-	{
-		let res = self.0.tree.insert(key, value);
-		if res == Ok(None) {
-			self.0.len.fetch_add(1, Ordering::Relaxed);
-		}
-		res
-	}
-
-	pub fn remove<K: AsRef<[u8]>>(&self, key: K) -> Result<Option<IVec>> {
-		let res = self.0.tree.remove(key);
-		if matches!(res, Ok(Some(_))) {
-			self.0.len.fetch_sub(1, Ordering::Relaxed);
-		}
-		res
-	}
-
-	pub fn pop_min(&self) -> Result<Option<(IVec, IVec)>> {
-		let res = self.0.tree.pop_min();
-		if let Ok(Some(_)) = &res {
-			self.0.len.fetch_sub(1, Ordering::Relaxed);
-		};
-		res
-	}
-
-	pub fn compare_and_swap<K, OV, NV>(
-		&self,
-		key: K,
-		old: Option<OV>,
-		new: Option<NV>,
-	) -> Result<std::result::Result<(), CompareAndSwapError>>
-	where
-		K: AsRef<[u8]>,
-		OV: AsRef<[u8]>,
-		NV: Into<IVec>,
-	{
-		let old_some = old.is_some();
-		let new_some = new.is_some();
-
-		let res = self.0.tree.compare_and_swap(key, old, new);
-
-		if res == Ok(Ok(())) {
-			match (old_some, new_some) {
-				(false, true) => {
-					self.0.len.fetch_add(1, Ordering::Relaxed);
-				}
-				(true, false) => {
-					self.0.len.fetch_sub(1, Ordering::Relaxed);
-				}
-				_ => (),
-			}
-		}
-		res
-	}
-}