add internals for supporting transactional updates

chore: update cmd parameter name in shell.nix
should fix the warning : WARN[0000] Flag --customPlatform is deprecated. Use: --custom-platform
2026-08-13 15:46:53 +00:00 · 2026-02-07 13:26:56 +01:00 · 2026-01-29 22:14:34 +00:00 · 2026-01-29 20:50:05 +01:00 · 2026-01-29 20:50:05 +01:00 · 2026-01-29 20:50:05 +01:00
521 changed files with 76571 additions and 22440 deletions
@@ -1,290 +0,0 @@
---
-kind: pipeline
-name: default
-
-node:
-  nix-daemon: 1
-
-steps:
-  - name: check formatting
-    image: nixpkgs/nix:nixos-22.05
-    commands:
-      - nix-shell --attr rust --run "cargo fmt -- --check"
-
-  - name: build
-    image: nixpkgs/nix:nixos-22.05
-    commands:
-      - nix-build --no-build-output --attr clippy.amd64 --argstr git_version ${DRONE_TAG:-$DRONE_COMMIT}
-
-  - name: unit + func tests
-    image: nixpkgs/nix:nixos-22.05
-    environment:
-      GARAGE_TEST_INTEGRATION_EXE: result-bin/bin/garage
-      GARAGE_TEST_INTEGRATION_PATH: tmp-garage-integration
-    commands:
-      - nix-build --no-build-output --attr clippy.amd64 --argstr git_version ${DRONE_TAG:-$DRONE_COMMIT}
-      - nix-build --no-build-output --attr test.amd64
-      - ./result/bin/garage_db-*
-      - ./result/bin/garage_api-*
-      - ./result/bin/garage_model-*
-      - ./result/bin/garage_rpc-*
-      - ./result/bin/garage_table-*
-      - ./result/bin/garage_util-*
-      - ./result/bin/garage_web-*
-      - ./result/bin/garage-*
-      - ./result/bin/integration-* || (cat tmp-garage-integration/stderr.log; false)
-      - rm result
-      - rm -rv tmp-garage-integration
-
-  - name: integration tests
-    image: nixpkgs/nix:nixos-22.05
-    commands:
-      - nix-build --no-build-output --attr clippy.amd64 --argstr git_version ${DRONE_TAG:-$DRONE_COMMIT}
-      - nix-shell --attr integration --run ./script/test-smoke.sh || (cat /tmp/garage.log; false)
-
-trigger:
-  event:
-  - custom
-  - push
-  - pull_request
-  - tag
-  - cron
-
---
-kind: pipeline
-type: docker
-name: release-linux-amd64
-
-node:
-  nix-daemon: 1
-
-steps:
-  - name: build
-    image: nixpkgs/nix:nixos-22.05
-    commands:
-      - nix-build --no-build-output --attr pkgs.amd64.release --argstr git_version ${DRONE_TAG:-$DRONE_COMMIT}
-      - nix-shell --attr rust --run "./script/not-dynamic.sh result-bin/bin/garage"
-
-  - name: integration
-    image: nixpkgs/nix:nixos-22.05
-    commands:
-      - nix-shell --attr integration --run ./script/test-smoke.sh || (cat /tmp/garage.log; false)
-
-  - name: push static binary
-    image: nixpkgs/nix:nixos-22.05
-    environment:
-      AWS_ACCESS_KEY_ID:
-        from_secret: garagehq_aws_access_key_id
-      AWS_SECRET_ACCESS_KEY:
-        from_secret: garagehq_aws_secret_access_key
-      TARGET: "x86_64-unknown-linux-musl"
-    commands:
-      - nix-shell --attr release --run "to_s3"
-
-  - name: docker build and publish
-    image: nixpkgs/nix:nixos-22.05
-    environment:
-      DOCKER_AUTH:
-        from_secret: docker_auth
-      DOCKER_PLATFORM: "linux/amd64"
-      CONTAINER_NAME: "dxflrs/amd64_garage"
-      HOME: "/kaniko"
-    commands:
-      - mkdir -p /kaniko/.docker
-      - echo $DOCKER_AUTH > /kaniko/.docker/config.json
-      - export CONTAINER_TAG=${DRONE_TAG:-$DRONE_COMMIT}
-      - nix-shell --attr release --run "to_docker"
-
-
-trigger:
-  event:
-  - promote
-  - cron
-
---
-kind: pipeline
-type: docker
-name: release-linux-i386
-
-node:
-  nix-daemon: 1
-
-steps:
-  - name: build
-    image: nixpkgs/nix:nixos-22.05
-    commands:
-      - nix-build --no-build-output --attr pkgs.i386.release --argstr git_version ${DRONE_TAG:-$DRONE_COMMIT}
-      - nix-shell --attr rust --run "./script/not-dynamic.sh result-bin/bin/garage"
-
-  - name: integration
-    image: nixpkgs/nix:nixos-22.05
-    commands:
-      - nix-shell --attr integration --run ./script/test-smoke.sh || (cat /tmp/garage.log; false)
-
-  - name: push static binary
-    image: nixpkgs/nix:nixos-22.05
-    environment:
-      AWS_ACCESS_KEY_ID:
-        from_secret: garagehq_aws_access_key_id
-      AWS_SECRET_ACCESS_KEY:
-        from_secret: garagehq_aws_secret_access_key
-      TARGET: "i686-unknown-linux-musl"
-    commands:
-      - nix-shell --attr release --run "to_s3"
-
-  - name: docker build and publish
-    image: nixpkgs/nix:nixos-22.05
-    environment:
-      DOCKER_AUTH:
-        from_secret: docker_auth
-      DOCKER_PLATFORM: "linux/386"
-      CONTAINER_NAME: "dxflrs/386_garage"
-      HOME: "/kaniko"
-    commands:
-      - mkdir -p /kaniko/.docker
-      - echo $DOCKER_AUTH > /kaniko/.docker/config.json
-      - export CONTAINER_TAG=${DRONE_TAG:-$DRONE_COMMIT}
-      - nix-shell --attr release --run "to_docker"
-
-trigger:
-  event:
-  - promote
-  - cron
-
---
-kind: pipeline
-type: docker
-name: release-linux-arm64
-
-node:
-  nix-daemon: 1
-
-steps:
-  - name: build
-    image: nixpkgs/nix:nixos-22.05
-    commands:
-      - nix-build --no-build-output --attr pkgs.arm64.release --argstr git_version ${DRONE_TAG:-$DRONE_COMMIT}
-      - nix-shell --attr rust --run "./script/not-dynamic.sh result-bin/bin/garage"
-
-  - name: push static binary
-    image: nixpkgs/nix:nixos-22.05
-    environment:
-      AWS_ACCESS_KEY_ID:
-        from_secret: garagehq_aws_access_key_id
-      AWS_SECRET_ACCESS_KEY:
-        from_secret: garagehq_aws_secret_access_key
-      TARGET: "aarch64-unknown-linux-musl"
-    commands:
-      - nix-shell --attr release --run "to_s3"
-
-  - name: docker build and publish
-    image: nixpkgs/nix:nixos-22.05
-    environment:
-      DOCKER_AUTH:
-        from_secret: docker_auth
-      DOCKER_PLATFORM: "linux/arm64"
-      CONTAINER_NAME: "dxflrs/arm64_garage"
-      HOME: "/kaniko"
-    commands:
-      - mkdir -p /kaniko/.docker
-      - echo $DOCKER_AUTH > /kaniko/.docker/config.json
-      - export CONTAINER_TAG=${DRONE_TAG:-$DRONE_COMMIT}
-      - nix-shell --attr release --run "to_docker"
-
-trigger:
-  event:
-  - promote
-  - cron
-
---
-kind: pipeline
-type: docker
-name: release-linux-arm
-
-node:
-  nix-daemon: 1
-
-steps:
-  - name: build
-    image: nixpkgs/nix:nixos-22.05
-    commands:
-      - nix-build --no-build-output --attr pkgs.arm.release --argstr git_version ${DRONE_TAG:-$DRONE_COMMIT}
-      - nix-shell --attr rust --run "./script/not-dynamic.sh result-bin/bin/garage"
-
-  - name: push static binary
-    image: nixpkgs/nix:nixos-22.05
-    environment:
-      AWS_ACCESS_KEY_ID:
-        from_secret: garagehq_aws_access_key_id
-      AWS_SECRET_ACCESS_KEY:
-        from_secret: garagehq_aws_secret_access_key
-      TARGET: "armv6l-unknown-linux-musleabihf"
-    commands:
-      - nix-shell --attr release --run "to_s3"
-
-  - name: docker build and publish
-    image: nixpkgs/nix:nixos-22.05
-    environment:
-      DOCKER_AUTH:
-        from_secret: docker_auth
-      DOCKER_PLATFORM: "linux/arm"
-      CONTAINER_NAME: "dxflrs/arm_garage"
-      HOME: "/kaniko"
-    commands:
-      - mkdir -p /kaniko/.docker
-      - echo $DOCKER_AUTH > /kaniko/.docker/config.json
-      - export CONTAINER_TAG=${DRONE_TAG:-$DRONE_COMMIT}
-      - nix-shell --attr release --run "to_docker"
-
-trigger:
-  event:
-  - promote
-  - cron
-
---
-kind: pipeline
-type: docker
-name: refresh-release-page
-
-node:
-  nix-daemon: 1
-
-steps:
-  - name: multiarch-docker
-    image: nixpkgs/nix:nixos-22.05
-    environment:
-      DOCKER_AUTH:
-        from_secret: docker_auth
-      HOME: "/root"
-    commands:
-      - mkdir -p /root/.docker
-      - echo $DOCKER_AUTH > /root/.docker/config.json
-      - export CONTAINER_TAG=${DRONE_TAG:-$DRONE_COMMIT}
-      - nix-shell --attr release --run "multiarch_docker"
-  - name: refresh-index
-    image: nixpkgs/nix:nixos-22.05
-    environment:
-      AWS_ACCESS_KEY_ID:
-        from_secret: garagehq_aws_access_key_id
-      AWS_SECRET_ACCESS_KEY:
-        from_secret: garagehq_aws_secret_access_key
-    commands:
-      - mkdir -p /etc/nix && cp nix/nix.conf /etc/nix/nix.conf
-      - nix-shell --attr release --run "refresh_index"
-
-depends_on:
-  - release-linux-amd64
-  - release-linux-i386
-  - release-linux-arm64
-  - release-linux-arm
-
-trigger:
-  event:
-  - promote
-  - cron
-
---
-kind: signature
-hmac: 24aebbcdba84fd0cdf963061d7bb72ae5b915bfdd0f50c7b019001126fb7fa56
-
-...
@@ -0,0 +1,54 @@
+labels:
+  nix: "enabled"
+
+when:
+  event:
+  - push
+  - tag
+  - pull_request
+  - deployment
+  - cron
+  - manual
+
+steps:
+  - name: check formatting
+    image: nixpkgs/nix:nixos-24.05
+    commands:
+      - nix-build -j4 --attr flakePackages.fmt
+
+  - name: check typos
+    image: nixpkgs/nix:nixos-24.05
+    commands:
+      - nix-shell --attr ci --run typos
+
+  - name: check lints with clippy
+    image: nixpkgs/nix:nixos-24.05
+    commands:
+      - nix-build -j4 --attr flakePackages.clippy
+
+  - name: build
+    image: nixpkgs/nix:nixos-24.05
+    commands:
+      - nix-build -j4 --attr flakePackages.dev
+
+  - name: unit + func tests (lmdb)
+    image: nixpkgs/nix:nixos-24.05
+    commands:
+      - nix-build -j4 --attr flakePackages.tests-lmdb
+
+  - name: unit + func tests (sqlite)
+    image: nixpkgs/nix:nixos-24.05
+    commands:
+      - nix-build -j4 --attr flakePackages.tests-sqlite
+
+  - name: unit + func tests (fjall)
+    image: nixpkgs/nix:nixos-24.05
+    commands:
+      - nix-build -j4 --attr flakePackages.tests-fjall
+
+  - name: integration tests
+    image: nixpkgs/nix:nixos-24.05
+    commands:
+      - nix-build -j4 --attr flakePackages.dev
+      - nix-shell --attr ci --run ./script/test-smoke.sh || (cat /tmp/garage.log; false)
+    depends_on: [ build ]
@@ -0,0 +1,33 @@
+labels:
+  nix: "enabled"
+
+when:
+  event:
+  - deployment
+  - cron
+
+depends_on:
+  - release
+
+steps:
+  - name: refresh-index
+    image: nixpkgs/nix:nixos-24.05
+    environment:
+      AWS_ACCESS_KEY_ID:
+        from_secret: garagehq_aws_access_key_id
+      AWS_SECRET_ACCESS_KEY:
+        from_secret: garagehq_aws_secret_access_key
+    commands:
+      - mkdir -p /etc/nix && cp nix/nix.conf /etc/nix/nix.conf
+      - nix-shell --attr ci --run "refresh_index"
+
+  - name: multiarch-docker
+    image: nixpkgs/nix:nixos-24.05
+    environment:
+      DOCKER_AUTH:
+        from_secret: docker_auth
+    commands:
+      - mkdir -p /root/.docker
+      - echo $DOCKER_AUTH > /root/.docker/config.json
+      - export CONTAINER_TAG=${CI_COMMIT_TAG:-$CI_COMMIT_SHA}
+      - nix-shell --attr ci --run "multiarch_docker"
@@ -0,0 +1,79 @@
+labels:
+  nix: "enabled"
+
+when:
+  event:
+  - deployment
+  - cron
+
+matrix:
+  include:
+    - ARCH: amd64
+      TARGET: x86_64-unknown-linux-musl
+    - ARCH: i386
+      TARGET: i686-unknown-linux-musl
+    - ARCH: arm64
+      TARGET: aarch64-unknown-linux-musl
+    - ARCH: arm
+      TARGET: armv6l-unknown-linux-musleabihf
+
+steps:
+  - name: build
+    image: nixpkgs/nix:nixos-24.05
+    commands:
+      - nix-build --attr releasePackages.${ARCH} --argstr git_version ${CI_COMMIT_TAG:-$CI_COMMIT_SHA}
+
+  - name: check is static binary
+    image: nixpkgs/nix:nixos-24.05
+    commands:
+      - nix-shell --attr ci --run "./script/not-dynamic.sh result/bin/garage"
+
+  - name: integration tests
+    image: nixpkgs/nix:nixos-24.05
+    commands:
+      - nix-shell --attr ci --run ./script/test-smoke.sh || (cat /tmp/garage.log; false)
+    when:
+      - matrix:
+          ARCH: amd64
+      - matrix:
+          ARCH: i386
+
+  - name: upgrade tests from v1.0.0
+    image: nixpkgs/nix:nixos-24.05
+    commands:
+      - nix-shell --attr ci --run "./script/test-upgrade.sh v1.0.0 x86_64-unknown-linux-musl" || (cat /tmp/garage.log; false)
+    when:
+      - matrix:
+          ARCH: amd64
+
+  - name: upgrade tests from v0.8.4
+    image: nixpkgs/nix:nixos-24.05
+    commands:
+      - nix-shell --attr ci --run "./script/test-upgrade.sh v0.8.4 x86_64-unknown-linux-musl" || (cat /tmp/garage.log; false)
+    when:
+      - matrix:
+          ARCH: amd64
+
+  - name: push static binary
+    image: nixpkgs/nix:nixos-24.05
+    environment:
+      TARGET: "${TARGET}"
+      AWS_ACCESS_KEY_ID:
+        from_secret: garagehq_aws_access_key_id
+      AWS_SECRET_ACCESS_KEY:
+        from_secret: garagehq_aws_secret_access_key
+    commands:
+      - nix-shell --attr ci --run "to_s3"
+
+  - name: docker build and publish
+    image: nixpkgs/nix:nixos-24.05
+    environment:
+      DOCKER_PLATFORM: "linux/${ARCH}"
+      CONTAINER_NAME: "dxflrs/${ARCH}_garage"
+      DOCKER_AUTH:
+        from_secret: docker_auth
+    commands:
+      - mkdir -p /root/.docker
+      - echo $DOCKER_AUTH > /root/.docker/config.json
+      - export CONTAINER_TAG=${CI_COMMIT_TAG:-$CI_COMMIT_SHA}
+      - nix-shell --attr ci --run "to_docker"
@@ -3,11 +3,15 @@ resolver = "2"
 members = [
 	"src/db",
 	"src/util",
+	"src/net",
 	"src/rpc",
 	"src/table",
 	"src/block",
 	"src/model",
-	"src/api",
+	"src/api/common",
+	"src/api/s3",
+	"src/api/k2v",
+	"src/api/admin",
 	"src/web",
 	"src/garage",
 	"src/k2v-client",
@@ -17,19 +21,138 @@ members = [
 default-members = ["src/garage"]

 [workspace.dependencies]
+
+# Internal Garage crates
 format_table = { version = "0.1.1", path = "src/format-table" }
-garage_api = { version = "0.8.4", path = "src/api" }
-garage_block = { version = "0.8.4", path = "src/block" }
-garage_db = { version = "0.8.4", path = "src/db", default-features = false }
-garage_model = { version = "0.8.4", path = "src/model", default-features = false }
-garage_rpc = { version = "0.8.4", path = "src/rpc" }
-garage_table = { version = "0.8.4", path = "src/table" }
-garage_util = { version = "0.8.4", path = "src/util" }
-garage_web = { version = "0.8.4", path = "src/web" }
+garage_api_common = { version = "2.2.0", path = "src/api/common" }
+garage_api_admin = { version = "2.2.0", path = "src/api/admin" }
+garage_api_s3 = { version = "2.2.0", path = "src/api/s3" }
+garage_api_k2v = { version = "2.2.0", path = "src/api/k2v" }
+garage_block = { version = "2.2.0", path = "src/block" }
+garage_db = { version = "2.2.0", path = "src/db", default-features = false }
+garage_model = { version = "2.2.0", path = "src/model", default-features = false }
+garage_net = { version = "2.2.0", path = "src/net" }
+garage_rpc = { version = "2.2.0", path = "src/rpc" }
+garage_table = { version = "2.2.0", path = "src/table" }
+garage_util = { version = "2.2.0", path = "src/util" }
+garage_web = { version = "2.2.0", path = "src/web" }
 k2v-client = { version = "0.0.4", path = "src/k2v-client" }

+# External crates from crates.io
+arc-swap = "1.1"
+argon2 = "0.5"
+async-trait = "0.1.7"
+backtrace = "0.3"
+base64 = "0.21"
+blake2 = "0.10"
+bytes = "1.0"
+bytesize = "1.1"
+cfg-if = "1.0"
+chrono = { version = "0.4", features = ["serde"] }
+crc-fast = "1.6"
+crypto-common = "0.1"
+gethostname = "0.4"
+git-version = "0.3.4"
+hex = "0.4"
+hexdump = "0.1"
+hmac = "0.12"
+itertools = "0.12"
+ipnet = "2.9.0"
+lazy_static = "1.4"
+md-5 = "0.10"
+mktemp = "0.5"
+nix = { version = "0.29", default-features = false, features = ["fs"] }
+nom = "7.1"
+parking_lot = "0.12"
+parse_duration = "2.1"
+paste = "1.0"
+pin-project = "1.0.12"
+pnet_datalink = "0.34"
+rand = "0.8"
+sha1 = "0.10"
+sha2 = "0.10"
+timeago = { version = "0.4", default-features = false }
+xxhash-rust = { version = "0.8", default-features = false, features = ["xxh3"] }
+
+aes-gcm = { version = "0.10", features = ["aes", "stream"] }
+sodiumoxide = { version = "0.2.5-0", package = "kuska-sodiumoxide" }
+kuska-handshake = { version = "0.2.0", features = ["default", "async_std"] }
+
+clap = { version = "4.1", features = ["derive", "env"] }
+pretty_env_logger = "0.5"
+structopt = { version = "0.3", default-features = false }
+syslog-tracing = "0.3"
+tracing = "0.1"
+tracing-journald = "0.3.1"
+tracing-subscriber = { version = "0.3", features = ["env-filter"] }
+
+heed = { version = "0.11", default-features = false, features = ["lmdb"] }
+rusqlite = "0.37"
+r2d2 = "0.8"
+r2d2_sqlite = "0.31"
+fjall = "2.4"
+
+async-compression = { version = "0.4", features = ["tokio", "zstd"] }
+zstd = { version = "0.13", default-features = false }
+
+quick-xml = { version = "0.26", features = ["serialize"] }
+rmp-serde = "1.1.2"
+serde = { version = "1.0", default-features = false, features = ["derive", "rc"] }
+serde_bytes = "0.11"
+serde_json = "1.0"
+toml = { version = "0.8", default-features = false, features = ["parse"] }
+utoipa = { version = "5.3.1", features = ["chrono"] }
+
+# newer version requires rust edition 2021
+k8s-openapi = { version = "0.21", features = ["v1_24"] }
+kube = { version = "0.88", default-features = false, features = ["runtime", "derive", "client", "rustls-tls"] }
+schemars = "0.8"
+reqwest = { version = "0.11", default-features = false, features = ["rustls-tls-manual-roots", "json"] }
+
+form_urlencoded = "1.0.0"
+http = "1.0"
+httpdate = "1.0"
+http-range = "0.1"
+http-body-util = "0.1"
+hyper = { version = "1.0", default-features = false }
+hyper-util = { version = "0.1", features = ["full"] }
+multer = "3.0"
+percent-encoding = "2.2"
+roxmltree = "0.19"
+url = "2.3"
+
+futures = "0.3"
+futures-util = "0.3"
+tokio = { version = "1.0", default-features = false, features = ["rt", "rt-multi-thread", "io-util", "net", "time", "macros", "sync", "signal", "fs"] }
+tokio-util = { version = "0.7", features = ["compat", "io"] }
+tokio-stream = { version = "0.1", features = ["net"] }
+
+opentelemetry = { version = "0.17", features = ["rt-tokio", "metrics", "trace"] }
+opentelemetry-prometheus = "0.10"
+opentelemetry-otlp = "0.10"
+opentelemetry-contrib = "0.9"
+prometheus = "0.13"
+
+# used by the k2v-client crate only
+aws-sigv4 = { version = "1.1", default-features = false }
+hyper-rustls = { version = "0.26", default-features = false, features = ["http1", "http2", "ring", "rustls-native-certs"] }
+log = "0.4"
+thiserror = "2.0"
+
+# ---- used only as build / dev dependencies ----
+assert-json-diff = "2.0"
+rustc_version = "0.4.0"
+static_init = "1.0"
+aws-smithy-runtime = { version = "1.8", default-features = false, features = ["tls-rustls"] }
+aws-sdk-config = { version = "1.62", default-features = false }
+aws-sdk-s3 = { version = "1.79", default-features = false, features = ["rt-tokio"] }
+
 [profile.dev]
+#lto = "thin"	# disabled for now, adds 2-4 min to each CI build
 lto = "off"

 [profile.release]
-debug = true
+lto = true
+codegen-units = 1
+opt-level = 3
+strip = true
@@ -3,5 +3,5 @@ FROM scratch
 ENV RUST_BACKTRACE=1
 ENV RUST_LOG=garage=info

-COPY result-bin/bin/garage /
+COPY result/bin/garage /
 CMD [ "/garage", "server"]
@@ -1,13 +1,8 @@
-.PHONY: doc all release shell run1 run2 run3
+.PHONY: doc all run1 run2 run3

 all:
-	clear; cargo build
-
-release:
-	nix-build --attr pkgs.amd64.release --no-build-output
-
-shell:
-	nix-shell
+	clear
+	cargo build

 # ----

@@ -1,4 +1,4 @@
-Garage [![Build Status](https://drone.deuxfleurs.fr/api/badges/Deuxfleurs/garage/status.svg?ref=refs/heads/main)](https://drone.deuxfleurs.fr/Deuxfleurs/garage)
+Garage [![status-badge](https://woodpecker.deuxfleurs.fr/api/badges/1/status.svg)](https://woodpecker.deuxfleurs.fr/repos/1)
 ===

 <p align="center" style="text-align:center;">
@@ -3,54 +3,22 @@
 with import ./nix/common.nix;

 let
-  pkgs = import pkgsSrc { };
+  pkgs = import nixpkgs { };
  compile = import ./nix/compile.nix;

-  build_debug_and_release = (target: {
-    debug = (compile {
-      inherit system target git_version pkgsSrc cargo2nixOverlay;
-      release = false;
-    }).workspace.garage { compileMode = "build"; };
-
-    release = (compile {
-      inherit system target git_version pkgsSrc cargo2nixOverlay;
-      release = true;
-    }).workspace.garage { compileMode = "build"; };
-  });
-
-  test = (rustPkgs:
-    pkgs.symlinkJoin {
-      name = "garage-tests";
-      paths =
-        builtins.map (key: rustPkgs.workspace.${key} { compileMode = "test"; })
-        (builtins.attrNames rustPkgs.workspace);
-    });
+  build_release = target: (compile {
+    inherit target system git_version nixpkgs;
+    crane = flake.inputs.crane;
+    rust-overlay = flake.inputs.rust-overlay;
+    release = true;
+  }).garage;

 in {
-  pkgs = {
-    amd64 = build_debug_and_release "x86_64-unknown-linux-musl";
-    i386 = build_debug_and_release "i686-unknown-linux-musl";
-    arm64 = build_debug_and_release "aarch64-unknown-linux-musl";
-    arm = build_debug_and_release "armv6l-unknown-linux-musleabihf";
-  };
-  test = {
-    amd64 = test (compile {
-      inherit system git_version pkgsSrc cargo2nixOverlay;
-      target = "x86_64-unknown-linux-musl";
-      features = [
-        "garage/bundled-libs"
-        "garage/k2v"
-        "garage/sled"
-        "garage/lmdb"
-        "garage/sqlite"
-      ];
-    });
-  };
-  clippy = {
-    amd64 = (compile {
-      inherit system git_version pkgsSrc cargo2nixOverlay;
-      target = "x86_64-unknown-linux-musl";
-      compiler = "clippy";
-    }).workspace.garage { compileMode = "build"; };
+  releasePackages = {
+    amd64 = build_release "x86_64-unknown-linux-musl";
+    i386 = build_release "i686-unknown-linux-musl";
+    arm64 = build_release "aarch64-unknown-linux-musl";
+    arm = build_release "armv6l-unknown-linux-musleabihf";
  };
+  flakePackages = flake.packages.${system};
 }
@@ -1,7 +1,7 @@
 <!DOCTYPE html>
 <html>
  <head>
-    <title>Garage Adminstration API v0</title>
+    <title>Garage administration API v0</title>
    <!-- needed for adaptive design -->
    <meta charset="utf-8"/>
    <meta name="viewport" content="width=device-width, initial-scale=1">
@@ -3,10 +3,10 @@ info:
  version: v0.8.0
  title: Garage Administration API v0+garage-v0.8.0
  description: |
-    Administrate your Garage cluster programatically, including status, layout, keys, buckets, and maintainance tasks.
-    
-    *Disclaimer: The API is not stable yet, hence its v0 tag. The API can change at any time, and changes can include breaking backward compatibility. Read the changelog and upgrade your scripts before upgrading. Additionnaly, this specification is very early stage and can contain bugs, especially on error return codes/types that are not tested yet. Do not expect a well finished and polished product!*
-paths: 
+    Administrate your Garage cluster programmatically, including status, layout, keys, buckets, and maintenance tasks.
+
+    *Disclaimer: The API is not stable yet, hence its v0 tag. The API can change at any time, and changes can include breaking backward compatibility. Read the changelog and upgrade your scripts before upgrading. Additionally, this specification is very early stage and can contain bugs, especially on error return codes/types that are not tested yet. Do not expect a well finished and polished product!*
+paths:
  /status:
    get:
      tags: 
@@ -0,0 +1,24 @@
+<!DOCTYPE html>
+<html>
+  <head>
+    <title>Garage administration API v1</title>
+    <!-- needed for adaptive design -->
+    <meta charset="utf-8"/>
+    <meta name="viewport" content="width=device-width, initial-scale=1">
+    <link href="./css/redoc.css" rel="stylesheet">
+
+    <!--
+    Redoc doesn't change outer page styles
+    -->
+    <style>
+      body {
+        margin: 0;
+        padding: 0;
+      }
+    </style>
+  </head>
+  <body>
+    <redoc spec-url='./garage-admin-v1.yml'></redoc>
+    <script src="./redoc.standalone.js"> </script>
+  </body>
+</html>
@@ -0,0 +1,24 @@
+<!DOCTYPE html>
+<html>
+  <head>
+    <title>Garage administration API v2</title>
+    <!-- needed for adaptive design -->
+    <meta charset="utf-8"/>
+    <meta name="viewport" content="width=device-width, initial-scale=1">
+    <link href="./css/redoc.css" rel="stylesheet">
+
+    <!--
+    Redoc doesn't change outer page styles
+    -->
+    <style>
+      body {
+        margin: 0;
+        padding: 0;
+      }
+    </style>
+  </head>
+  <body>
+    <redoc spec-url='./garage-admin-v2.json'></redoc>
+    <script src="./redoc.standalone.js"> </script>
+  </body>
+</html>
@@ -51,4 +51,4 @@ We are currently building this SDK for [Python](@/documentation/build/python.md#

 More information:
  - [In the reference manual](@/documentation/reference-manual/admin-api.md)
-  - [Full specifiction](https://garagehq.deuxfleurs.fr/api/garage-admin-v0.html)
+  - [Full specification](https://garagehq.deuxfleurs.fr/api/garage-admin-v0.html)
@@ -37,30 +37,84 @@ import (
    "context"
    "fmt"
    "os"
+    "strings"
    garage "git.deuxfleurs.fr/garage-sdk/garage-admin-sdk-golang"
 )

 func main() {
-    // Set Host and other parameters
+    // Initialization
    configuration := garage.NewConfiguration()
    configuration.Host = "127.0.0.1:3903"
-
-
-    // We can now generate a client
    client := garage.NewAPIClient(configuration)
-
-    // Authentication is handled through the context pattern
    ctx := context.WithValue(context.Background(), garage.ContextAccessToken, "s3cr3t")

-    // Send a request
-    resp, r, err := client.NodesApi.GetNodes(ctx).Execute()
-    if err != nil {
-        fmt.Fprintf(os.Stderr, "Error when calling `NodesApi.GetNodes``: %v\n", err)
-        fmt.Fprintf(os.Stderr, "Full HTTP response: %v\n", r)
+    // Nodes
+    fmt.Println("--- nodes ---")
+    nodes, _, _ := client.NodesApi.GetNodes(ctx).Execute()
+    fmt.Fprintf(os.Stdout, "First hostname: %v\n", nodes.KnownNodes[0].Hostname)
+    capa := int64(1000000000)
+    change := []garage.NodeRoleChange{
+	    garage.NodeRoleChange{NodeRoleUpdate: &garage.NodeRoleUpdate {
+	        Id: *nodes.KnownNodes[0].Id,
+	        Zone: "dc1",
+	        Capacity: *garage.NewNullableInt64(&capa),
+	        Tags: []string{ "fast", "amd64" },
+	    }},
    }
+    staged, _, _ := client.LayoutApi.AddLayout(ctx).NodeRoleChange(change).Execute()
+    msg, _, _ := client.LayoutApi.ApplyLayout(ctx).LayoutVersion(*garage.NewLayoutVersion(staged.Version + 1)).Execute()
+    fmt.Printf(strings.Join(msg.Message, "\n")) // Layout configured

-    // Process the response
-    fmt.Fprintf(os.Stdout, "Target hostname: %v\n", resp.KnownNodes[resp.Node].Hostname)
+    health, _, _ := client.NodesApi.GetHealth(ctx).Execute()
+    fmt.Printf("Status: %s, nodes: %v/%v, storage: %v/%v, partitions: %v/%v\n", health.Status, health.ConnectedNodes, health.KnownNodes, health.StorageNodesOk, health.StorageNodes, health.PartitionsAllOk, health.Partitions)
+
+    // Key
+    fmt.Println("\n--- key ---")
+    key := "openapi-key"
+    keyInfo, _, _ := client.KeyApi.AddKey(ctx).AddKeyRequest(garage.AddKeyRequest{Name: *garage.NewNullableString(&key) }).Execute()
+    defer client.KeyApi.DeleteKey(ctx).Id(*keyInfo.AccessKeyId).Execute()
+    fmt.Printf("AWS_ACCESS_KEY_ID=%s\nAWS_SECRET_ACCESS_KEY=%s\n", *keyInfo.AccessKeyId, *keyInfo.SecretAccessKey.Get())
+
+    id := *keyInfo.AccessKeyId
+    canCreateBucket := true
+    updateKeyRequest := *garage.NewUpdateKeyRequest()
+    updateKeyRequest.SetName("openapi-key-updated")
+    updateKeyRequest.SetAllow(garage.UpdateKeyRequestAllow { CreateBucket: &canCreateBucket })
+    update, _, _ := client.KeyApi.UpdateKey(ctx).Id(id).UpdateKeyRequest(updateKeyRequest).Execute()
+    fmt.Printf("Updated %v with key name %v\n", *update.AccessKeyId, *update.Name)
+
+    keyList, _, _ := client.KeyApi.ListKeys(ctx).Execute()
+    fmt.Printf("Keys count: %v\n", len(keyList))
+
+    // Bucket
+    fmt.Println("\n--- bucket ---")
+    global_name := "global-ns-openapi-bucket"
+    local_name := "local-ns-openapi-bucket"
+    bucketInfo, _, _ := client.BucketApi.CreateBucket(ctx).CreateBucketRequest(garage.CreateBucketRequest{
+        GlobalAlias: &global_name,
+        LocalAlias: &garage.CreateBucketRequestLocalAlias {
+            AccessKeyId: keyInfo.AccessKeyId,
+	    Alias: &local_name,
+        },
+    }).Execute()
+    defer client.BucketApi.DeleteBucket(ctx).Id(*bucketInfo.Id).Execute()
+    fmt.Printf("Bucket id: %s\n", *bucketInfo.Id)
+
+    updateBucketRequest := *garage.NewUpdateBucketRequest()
+    website := garage.NewUpdateBucketRequestWebsiteAccess()
+    website.SetEnabled(true)
+    website.SetIndexDocument("index.html")
+    website.SetErrorDocument("errors/4xx.html")
+    updateBucketRequest.SetWebsiteAccess(*website)
+    quotas := garage.NewUpdateBucketRequestQuotas()
+    quotas.SetMaxSize(1000000000)
+    quotas.SetMaxObjects(999999999)
+    updateBucketRequest.SetQuotas(*quotas)
+    updatedBucket, _, _ := client.BucketApi.UpdateBucket(ctx).Id(*bucketInfo.Id).UpdateBucketRequest(updateBucketRequest).Execute()
+    fmt.Printf("Bucket %v website activation: %v\n", *updatedBucket.Id, *updatedBucket.WebsiteAccess)
+
+    bucketList, _, _ := client.BucketApi.ListBuckets(ctx).Execute()
+    fmt.Printf("Bucket count: %v\n", len(bucketList))
 }
 ```

@@ -31,9 +31,9 @@ npm install --save git+https://git.deuxfleurs.fr/garage-sdk/garage-admin-sdk-js.
 A short example:

 ```javascript
-const garage = require('garage_administration_api_v0garage_v0_8_0');
+const garage = require('garage_administration_api_v1garage_v0_9_0');

-const api = new garage.ApiClient("http://127.0.0.1:3903/v0");
+const api = new garage.ApiClient("http://127.0.0.1:3903/v1");
 api.authentications['bearerAuth'].accessToken = "s3cr3t";

 const [node, layout, key, bucket] = [
@@ -5,13 +5,13 @@ weight = 99

 ## S3

-If you are developping a new application, you may want to use Garage to store your user's media.
+If you are developing a new application, you may want to use Garage to store your user's media.

 The S3 API that Garage uses is a standard REST API, so as long as you can make HTTP requests,
 you can query it. You can check the [S3 REST API Reference](https://docs.aws.amazon.com/AmazonS3/latest/API/API_Operations_Amazon_Simple_Storage_Service.html) from Amazon to learn more.

-Developping your own wrapper around the REST API is time consuming and complicated.
-Instead, there are some libraries already avalaible.
+Developing your own wrapper around the REST API is time consuming and complicated.
+Instead, there are some libraries already available.

 Some of them are maintained by Amazon, some by Minio, others by the community.

@@ -23,7 +23,7 @@ client = minio.Minio(
  "GKyourapikey",
  "abcd[...]1234",
  # Force the region, this is specific to garage
-  region="region",
+  region="garage",
 )
 ```

@@ -80,7 +80,7 @@ from garage_admin_sdk.apis import *
 from garage_admin_sdk.models import *

 configuration = garage_admin_sdk.Configuration(
-  host = "http://localhost:3903/v0",
+  host = "http://localhost:3903/v1",
  access_token = "s3cr3t"
 )

@@ -94,13 +94,14 @@ print(f"running garage {status.garage_version}, node_id {status.node}")

 # Change layout of this node
 current = layout.get_layout()
-layout.add_layout({
-  status.node: NodeClusterInfo(
+layout.add_layout([
+  NodeRoleChange(
+    id = status.node,
    zone = "dc1",
-    capacity = 1,
+    capacity = 1000000000,
    tags = [ "dev" ],
  )
-})
+])
 layout.apply_layout(LayoutVersion(
  version = current.version + 1
 ))
@@ -23,7 +23,7 @@ To configure S3-compatible software to interact with Garage,
 you will need the following parameters:

 - An **API endpoint**: this corresponds to the HTTP or HTTPS address
-  used to contact the Garage server. When runing Garage locally this will usually
+  used to contact the Garage server. When running Garage locally this will usually
  be `http://127.0.0.1:3900`. In a real-world setting, you would usually have a reverse-proxy
  that adds TLS support and makes your Garage server available under a public hostname
  such as `https://garage.example.com`.
@@ -12,8 +12,9 @@ In this section, we cover the following web applications:
 | [Mastodon](#mastodon)     | ✅       | Natively supported    |
 | [Matrix](#matrix)     | ✅       |  Tested with `synapse-s3-storage-provider`    |
 | [ejabberd](#ejabberd)     | ✅       |  `mod_s3_upload`    |
-| [Pixelfed](#pixelfed)     | ❓       |  Not yet tested    |
-| [Pleroma](#pleroma)     | ❓       |  Not yet tested    |
+| [Ente](#ente)     | ✅       |  Natively supported |
+| [Pixelfed](#pixelfed)     | ❓       |  Natively supported    |
+| [Pleroma](#pleroma)     | ✅        |  Natively supported    |
 | [Lemmy](#lemmy)     | ✅        |  Supported with pict-rs    |
 | [Funkwhale](#funkwhale)     | ❓       | Not yet tested     |
 | [Misskey](#misskey)     | ❓       | Not yet tested     |
@@ -53,7 +54,7 @@ garage bucket allow nextcloud --read --write --key nextcloud-key

 Now edit your Nextcloud configuration file to enable object storage.
 On my installation, the config. file is located at the following path: `/var/www/nextcloud/config/config.php`.  
-We will add a new root key to the `$CONFIG` dictionnary named `objectstore`:
+We will add a new root key to the `$CONFIG` dictionary named `objectstore`:

 ```php
 <?php
@@ -69,7 +70,7 @@ $CONFIG = array(
        'hostname' => '127.0.0.1', // Can also be a domain name, eg. garage.example.com
        'port' => 3900,            // Put your reverse proxy port or your S3 API port
        'use_ssl' => false,        // Set it to true if you have a TLS enabled reverse proxy
-        'region' => 'garage',      // Garage has only one region named "garage"
+        'region' => 'garage',      // Garage default region is named "garage", edit according to your cluster config
        'use_path_style' => true   // Garage supports only path style, must be set to true
    ],
 ],
@@ -80,6 +81,53 @@ To test your new configuration, just reload your Nextcloud webpage and start sen

 *External link:* [Nextcloud Documentation > Primary Storage](https://docs.nextcloud.com/server/latest/admin_manual/configuration_files/primary_storage.html)

+#### SSE-C encryption (since Garage v1.0)
+
+Since version 1.0, Garage supports server-side encryption with customer keys
+(SSE-C).  In this mode, Garage is responsible for encrypting and decrypting
+objects, but it does not store the encryption key itself. The encryption key
+should be provided by Nextcloud upon each request.  This mode of operation is
+supported by Nextcloud and it has successfully been tested together with
+Garage.
+
+To enable SSE-C encryption:
+
+1. Make sure your Garage server is accessible via SSL through a reverse proxy
+   such as Nginx, and that it is using a valid public certificate (Nextcloud
+   might be able to connect to an S3 server that is using a self-signed
+   certificate, but you will lose many hours while trying, so don't).
+   Configure values for `use_ssl` and `port` accordingly in your `config.php`
+   file.
+
+2. Generate an encryption key using the following command:
+
+    ```
+    openssl rand -base64 32
+    ```
+
+    Make sure to keep this key **secret**!
+
+3. Add the encryption key in your `config.php` file as follows:
+
+
+    ```php
+    <?php
+    $CONFIG = array(
+    'objectstore' => [
+        'class' => '\\OC\\Files\\ObjectStore\\S3',
+        'arguments' => [
+            ...
+            'sse_c_key' => 'exampleencryptionkeyLbU+5fKYQcVoqnn+RaIOXgo=',
+            ...
+        ],
+    ],
+    ```
+
+Nextcloud will now make Garage encrypt files at rest in the storage bucket.
+These files will not be readable by an S3 client that has credentials to the
+bucket but doesn't also know the secret encryption key.
+
+
 ### External Storage

 **From the GUI.** Activate the "External storage support" app from the "Applications" page (click on your account icon on the top right corner of your screen to display the menu). Go to your parameters page (also located below your account icon). Click on external storage (or the corresponding translation in your language).
@@ -88,7 +136,7 @@ To test your new configuration, just reload your Nextcloud webpage and start sen
 *Click on the picture to zoom*

 Add a new external storage. Put what you want in "folder name" (eg. "shared"). Select "Amazon S3". Keep "Access Key" for the Authentication field.
-In Configuration, put your bucket name (eg. nextcloud), the host (eg. 127.0.0.1), the port (eg. 3900 or 443), the region (garage). Tick the SSL box if you have put an HTTPS proxy in front of garage. You must tick the "Path access" box and you must leave the "Legacy authentication (v2)" box empty. Put your Key ID (eg. GK...) and your Secret Key in the last two input boxes. Finally click on the tick symbol on the right of your screen.
+In Configuration, put your bucket name (eg. nextcloud), the host (eg. 127.0.0.1), the port (eg. 3900 or 443), the region ("garage" if you use the default, or the one your configured in your `garage.toml`). Tick the SSL box if you have put an HTTPS proxy in front of garage. You must tick the "Path access" box and you must leave the "Legacy authentication (v2)" box empty. Put your Key ID (eg. GK...) and your Secret Key in the last two input boxes. Finally click on the tick symbol on the right of your screen.

 Now go to your "Files" app and a new "linked folder" has appeared with the name you chose earlier (eg. "shared").

@@ -144,10 +192,10 @@ garage key create peertube-key

 Keep the Key ID and the Secret key in a pad, they will be needed later.  

-We need two buckets, one for normal videos (named peertube-video) and one for webtorrent videos (named peertube-playlist).
+We need two buckets, one for normal videos (named peertube-videos) and one for webtorrent videos (named peertube-playlists).
 ```bash
-garage bucket create peertube-video
-garage bucket create peertube-playlist
+garage bucket create peertube-videos
+garage bucket create peertube-playlists
 ```

 Now we allow our key to read and write on these buckets:
@@ -191,7 +239,7 @@ object_storage:
  # Put localhost only if you have a garage instance running on that node
  endpoint: 'http://localhost:3900' # or "garage.example.com" if you have TLS on port 443

-  # Garage supports only one region for now, named garage
+  # Garage default region is named "garage", edit according to your config
  region: 'garage'

  credentials:
@@ -206,7 +254,7 @@ object_storage:
    proxify_private_files: false

  streaming_playlists:
-    bucket_name: 'peertube-playlist'
+    bucket_name: 'peertube-playlists'

    # Keep it empty for our example
    prefix: ''
@@ -216,7 +264,7 @@ object_storage:

  # Same settings but for webtorrent videos
  videos:
-    bucket_name: 'peertube-video'
+    bucket_name: 'peertube-videos'
    prefix: ''
    # You must fill this field to make Peertube use our reverse proxy/website logic
    base_url: 'http://peertube-videos.web.garage.localhost'
@@ -245,7 +293,7 @@ with average object size ranging from 50 KB to 150 KB.
 As such, your Garage cluster should be configured appropriately for good performance:

 - use Garage v0.8.0 or higher with the [LMDB database engine](@documentation/reference-manual/configuration.md#db-engine-since-v0-8-0).
-  With the default Sled database engine, your database could quickly end up taking tens of GB of disk space.
+  Older versions of Garage used the Sled database engine which had issues, such as databases quickly ending up taking tens of GB of disk space.
 - the Garage database should be stored on a SSD

 ### Creating your bucket
@@ -288,6 +336,7 @@ From the [official Mastodon documentation](https://docs.joinmastodon.org/admin/t

 ```bash
 $ RAILS_ENV=production bin/tootctl media remove --days 3
+$ RAILS_ENV=production bin/tootctl media remove --days 15 --prune-profiles
 $ RAILS_ENV=production bin/tootctl media remove-orphans
 $ RAILS_ENV=production bin/tootctl preview_cards remove --days 15
 ```
@@ -306,8 +355,6 @@ Imports:	1.7 KB
 Settings:	0 Bytes
 ```

-Unfortunately, [old avatars and headers cannot currently be cleaned up](https://github.com/mastodon/mastodon/issues/9567).
-
 ### Migrating your data

 Data migration should be done with an efficient S3 client.
@@ -366,7 +413,7 @@ mc mirror --newer-than "3h" ./public/system/ garage/mastodon-data

 ## Matrix

-Matrix is a chat communication protocol. Its main stable server implementation, [Synapse](https://matrix-org.github.io/synapse/latest/), provides a module to store media on a S3 backend. Additionally, a server independent media store supporting S3 has been developped by the community, it has been made possible thanks to how the matrix API has been designed and will work with implementations like Conduit, Dendrite, etc.
+Matrix is a chat communication protocol. Its main stable server implementation, [Synapse](https://matrix-org.github.io/synapse/latest/), provides a module to store media on a S3 backend. Additionally, a server independent media store supporting S3 has been developed by the community, it has been made possible thanks to how the matrix API has been designed and will work with implementations like Conduit, Dendrite, etc.

 ### synapse-s3-storage-provider (synapse only)

@@ -395,7 +442,7 @@ media_storage_providers:
  store_synchronous: True  # do we want to wait that the file has been written before returning?
  config:
    bucket: matrix       # the name of our bucket, we chose matrix earlier
-    region_name: garage  # only "garage" is supported for the region field
+    region_name: garage  # "garage" by default, edit according to your cluster config
    endpoint_url: http://localhost:3900 # the path to the S3 endpoint
    access_key_id: "GKxxx" # your Key ID
    secret_access_key: "xxxx" # your Secret Key
@@ -403,7 +450,7 @@ media_storage_providers:

 Note that uploaded media will also be stored locally and this behavior can not be deactivated, it is even required for
 some operations like resizing images.
-In fact, your local filesysem is considered as a cache but without any automated way to garbage collect it.
+In fact, your local filesystem is considered as a cache but without any automated way to garbage collect it.

 We can build our garbage collector with `s3_media_upload`, a tool provided with the module.
 If you installed the module with the command provided before, you should be able to bring it in your path:
@@ -421,7 +468,7 @@ Now we can write a simple script (eg `~/.local/bin/matrix-cache-gc`):
 ## CONFIGURATION ##
 AWS_ACCESS_KEY_ID=GKxxx
 AWS_SECRET_ACCESS_KEY=xxxx
-S3_ENDPOINT=http://localhost:3900
+AWS_ENDPOINT_URL=http://localhost:3900
 S3_BUCKET=matrix
 MEDIA_STORE=/var/lib/matrix-synapse/media
 PG_USER=matrix
@@ -442,7 +489,7 @@ EOF

 s3_media_upload update-db 1d
 s3_media_upload --no-progress check-deleted $MEDIA_STORE
-s3_media_upload --no-progress upload $MEDIA_STORE $S3_BUCKET --delete --endpoint-url $S3_ENDPOINT
+s3_media_upload --no-progress upload $MEDIA_STORE $S3_BUCKET --delete --endpoint-url $AWS_ENDPOINT_URL
 ```

 This script will list all the medias that were not accessed in the 24 hours according to your database.
@@ -521,13 +568,186 @@ The module can then be configured with:
 Other configuration options can be found in the
 [configuration YAML file](https://github.com/processone/ejabberd-contrib/blob/master/mod_s3_upload/conf/mod_s3_upload.yml).

+
+## Ente
+
+Ente is an alternative for Google Photos and Apple Photos. It [can be selfhosted](https://help.ente.io/self-hosting/) and is working fine with Garage as of May 2024.
+As a first step we need to create a bucket and a key for Ente:
+
+```bash
+garage bucket create ente
+garage key create ente-key
+# For the CORS setup to work, the key needs to be --owner as well, at least temporarily.
+garage bucket allow ente --read --write --owner --key ente-key
+```
+
+We also need to setup some CORS rules to allow the Ente frontend to access the bucket:
+
+```bash
+export CORS='{"CORSRules":[{"AllowedHeaders":["*"],"AllowedMethods":["GET", "PUT", "POST", "DELETE"],"AllowedOrigins":["*"], "ExposeHeaders":["ETag"]}]}'
+aws s3api put-bucket-cors --bucket ente --cors-configuration $CORS
+```
+
+Now we need to configure ente-server to use our bucket. This is explained [in the Ente S3 documentation](https://help.ente.io/self-hosting/guides/external-s3).
+Prepare a configuration file for ente's backend as `museum.yaml`:
+
+```yaml
+credentials-file: /credentials.yaml
+apps:
+  public-albums: https://albums.example.tld # If you want to use the share album feature
+    internal:
+hardcoded-ott:
+  local-domain-suffix: "@example.com" # Your domain
+  local-domain-value: 123456 # Custom One-Time Password since we are not sending mail by default
+key:
+  # WARNING -- You MUST CHANGE the values below
+  # Someone has made an image that can do it for you : https://github.com/EdyTheCow/ente-selfhost/blob/main/images/ente-server-tools/Dockerfile
+  # Simply build it yourself or run docker run --rm ghcr.io/edythecow/ente-server-tools go run tools/gen-random-keys/main.go
+  encryption: yvmG/RnzKrbCb9L3mgsmoxXr9H7i2Z4qlbT0mL3ln4w= # CHANGE THIS VALUE
+  hash: KXYiG07wC7GIgvCSdg+WmyWdXDAn6XKYJtp/wkEU7x573+byBRAYtpTP0wwvi8i/4l37uicX1dVTUzwH3sLZyw== # CHANGE THIS VALUE
+jwt:
+  secret: i2DecQmfGreG6q1vBj5tCokhlN41gcfS2cjOs9Po-u8= # CHANGE THIS VALUE
+```
+
+The full configuration file can be found [here](https://github.com/ente-io/ente/blob/main/server/configurations/local.yaml)
+Then prepare a credentials file as `credentials.yaml`
+
+```yaml
+db:
+    host: postgres
+    port: 5432
+    name: <ente_db_name>
+    user: <pguser>
+    password: <pgpass>
+
+s3:
+    # Override the primary and secondary hot storage. The commented out values
+    # are the defaults.
+    #
+    hot_storage:
+        primary: b2-eu-cen
+    #    secondary: wasabi-eu-central-2-v3
+
+    # If true, enable some workarounds to allow us to use a local minio instance
+    # for object storage.
+    #
+    # 1. Disable SSL.
+    # 2. Use "path" style S3 URLs (see `use_path_style_urls` below).
+    # 3. Directly download the file during replication instead of going via the
+    #    Cloudflare worker.
+    # 4. Do not specify storage classes when uploading objects (since minio does
+    #    not support them, specifically it doesn't support GLACIER).
+    are_local_buckets: true
+
+    # To use "path" style S3 URLs instead of DNS-based bucket access
+    # default to true if you set "are_local_buckets: true"
+    # use_path_style_urls: true
+
+    b2-eu-cen: # Don't change this key, it is hardcoded
+        key: <keyID> 
+        secret: <keySecret>
+        endpoint: garage:3900 # publicly accessible endpoint of your garage instance
+        region: garage
+        bucket: <yourbucketName>
+        use_path_style: true
+    # you can specify secondary locations, names are hardcoded as well
+    # wasabi-eu-central-2-v3:
+    # scw-eu-fr-v3:
+    
+    # and you can also specify a bucket to be used for embeddings, preview etc..
+    # default to the first bucket 
+    # derived-storage: wasabi-eu-central-2-derived
+```
+
+Finally you can run it with Docker : 
+
+```bash
+docker run -d --name ente-server --restart unless-stopped -v /path/to/museum.yaml:/museum.yaml -v /path/to/credentials.yaml:/credentials.yaml -p 8080:8080 ghcr.io/ente-io/ente-server
+```
+
+For more information on deployment you can check the [ente documentation](https://help.ente.io/self-hosting/)
+
 ## Pixelfed

 [Pixelfed Technical Documentation > Configuration](https://docs.pixelfed.org/technical-documentation/env.html#filesystem)

 ## Pleroma

-[Pleroma Documentation > Pleroma.Uploaders.S3](https://docs-develop.pleroma.social/backend/configuration/cheatsheet/#pleromauploaderss3)
+### Creating your bucket
+
+This is the usual Garage setup:
+
+```bash
+garage key new --name pleroma-key
+garage bucket create pleroma
+garage bucket allow pleroma --read --write --owner --key pleroma-key
+```
+
+We also need to expose these buckets publicly to serve their content to users:
+
+```bash
+garage bucket website --allow pleroma
+```
+
+Note the Key ID and Secret Key.
+
+### Configure Pleroma
+
+Update your Pleroma configuration like that in `/etc/pleroma/config.exs`.
+
+```
+config :pleroma, Pleroma.Upload,
+    uploader: Pleroma.Uploaders.S3,
+    base_url: "https://pleroma.garage.example.tld"
+
+config :ex_aws, :s3,
+    access_key_id: "GW...",
+    secret_access_key: "XXX",
+    region: "garage",
+    host: "api.garage.example.tld"
+```
+
+And restart Pleroma.
+
+You can found more information in [Pleroma Documentation > Pleroma.Uploaders.S3](https://docs-develop.pleroma.social/backend/configuration/cheatsheet/#pleromauploaderss3)
+
+### Migrating your data
+
+Pleroma have an internal migration tool that can encounter some fatal error
+
+```
+** (EXIT from #PID<0.98.0>) an exception was raised:
+    ** (File.Error) could not stream "/var/lib/pleroma/uploads/09/f8": illegal operation on a directory
+        (elixir 1.17.3) lib/file/stream.ex:100: anonymous fn/3 in Enumerable.File.Stream.reduce/3
+        (elixir 1.17.3) lib/stream.ex:1675: anonymous fn/5 in Stream.resource/3
+        (elixir 1.17.3) lib/stream.ex:1891: Enumerable.Stream.do_each/4
+        (elixir 1.17.3) lib/task/supervised.ex:370: Task.Supervised.stream_reduce/7
+        (elixir 1.17.3) lib/enum.ex:4423: Enum.map/2
+        (ex_aws_s3 2.5.8) lib/ex_aws/s3/upload.ex:141: ExAws.Operation.ExAws.S3.Upload.perform/2
+        (pleroma 2.10.0) lib/pleroma/uploaders/s3.ex:60: Pleroma.Uploaders.S3.put_file/1
+        (pleroma 2.10.0) lib/pleroma/uploaders/uploader.ex:49: Pleroma.Uploaders.Uploader.put_file/2
+```
+
+So, use [your best tool](https://garagehq.deuxfleurs.fr/documentation/connect/cli/) to sync `/var/lib/pleroma/uploads/` in your S3.
+
+Then, to avoid some non existent problem (just in case of), run this command
+
+```bash
+while true
+do
+    rm -vr $(./bin/pleroma_ctl uploads migrate_local S3 2>&1 | grep "could not stream" | awk -F '"' '{print $2}')
+    sleep 5
+done
+```
+
+If you have many files, stop this command sometime and the command bellow (interactive) to delete local
+file after upload. Then restart the loop.
+
+```bash
+./bin/pleroma_ctl uploads migrate_local S3 --delete
+```
+
+And *voilà*

 ## Lemmy

@@ -55,8 +55,8 @@ Create your key and bucket:

 ```bash
 garage key create my-key
-garage bucket create backup
-garage bucket allow backup --read --write --key my-key
+garage bucket create backups
+garage bucket allow backups --read --write --key my-key
 ```

 Then register your Key ID and Secret key in your environment:
@@ -161,3 +161,59 @@ kopia repository validate-provider

 You can then run all the standard kopia commands: `kopia snapshot create`, `kopia mount`...
 Everything should work out-of-the-box.
+
+## Plakar
+
+Create your key and bucket on Garage server:
+
+```bash
+garage key create my-plakar-key
+garage bucket create plakar-backups
+garage bucket allow plakar-backups --read --write --key my-plakar-key
+…
+```
+
+On Plakar server, add your Garage as a storage location:
+```bash
+plakar store add garageS3 s3://my-garage.tld/plakar-backups \
+region=garage # Or as you've specified in garage.toml \
+access_key=<Key ID from "garage key info my-plakar-key"> \
+secret_access_key=<Secret key from "garage key info my-plakar-key">
+```
+
+Then create the repository.
+```bash
+plakar at @garageS3 create -plaintext # Unencrypted
+# or
+plakar at @garageS3 create #encrypted
+```
+
+If you encrypt your backups (Plakar default), you will need to define a strong passphrase. Do not forget to save your password safely. It will be needed to decrypt your backups.
+
+
+After the repository has been created, check that everything works as expected (that might give an empty result as no file has been added yet, but no error message):
+```bash
+plakar at @garageS3 check
+```
+
+Now that everything is configure, you can use Garage as your backups storage. For instance sync it with a local backup storage:
+```bash
+$ plakar at ~/backups sync to @garageS3
+```
+
+Or list the S3 storage content:
+```bash
+$ plakar at @garageS3 ls
+```
+
+More information in Plakar documentation: https://www.plakar.io/docs/main/quickstart/
+
+## Synology HyperBackup
+
+HyperBackup can be configured to upload backups to garage using a custom S3 destination. However, the HyperBackup client hardcodes the `us-east-1` region that is a critical input to the v4 signature process. If garage is not set to `us-east-1`, HyperBackup will recognize available buckets, but fail during the final setup stage.
+
+In garage.toml:
+```toml
+[s3_api]
+s3_region = "us-east-1"
+```
@@ -41,7 +41,7 @@ Some commands:
 # list buckets
 mc ls garage/

-# list objets in a bucket
+# list objects in a bucket
 mc ls garage/my_files

 # copy from your filesystem to garage
@@ -70,16 +70,17 @@ Then a file named `~/.aws/config` and put:
 ```toml
 [default]
 region=garage
+endpoint_url=http://127.0.0.1:3900
 ```

 Now, supposing Garage is listening on `http://127.0.0.1:3900`, you can list your buckets with:

 ```bash
-aws --endpoint-url http://127.0.0.1:3900 s3 ls
+aws s3 ls
 ```

-Passing the `--endpoint-url` parameter to each command is annoying but AWS developers do not provide a corresponding configuration entry.
-As a workaround, you can redefine the aws command by editing the file `~/.bashrc`:
+If you're using awscli `<1.29.0` or `<2.13.0`, you need to pass `--endpoint-url` to each CLI invocation explicitly.
+As a workaround, you can redefine the aws command by editing the file `~/.bashrc` in this case:

 ```
 function aws { command aws --endpoint-url http://127.0.0.1:3900 $@ ; }
@@ -148,6 +149,15 @@ rclone help
 This will tremendously accelerate operations such as `rclone sync` or `rclone ncdu` by reducing the number
 of ListObjects calls that are made.

+**Garage behind Cloudflare proxy:** when running Garage behind Cloudflare proxy, you might see `Response: error 403 Forbidden, Forbidden: Invalid signature` error in your garage logs or `AccessDenied: Forbidden: Invalid signature` error in rclone logs. Try adding `--s3-sign-accept-encoding=false` flag to your rclone command and see if the issue is resolved.
+
+```bash
+# this throws an error
+rclone lsd garage:
+
+# this should work
+rclone lsd --s3-sign-accept-encoding=false garage:
+```

 ## `s3cmd`

@@ -208,7 +218,7 @@ Within Cyberduck, a
 available within the `Preferences -> Profiles` section. This can enabled and
 then connections to Garage may be configured.

-### Instuctions for the CLI
+### Instructions for the CLI

 To configure duck (Cyberduck's CLI tool), start by creating its folder hierarchy:

@@ -258,7 +268,7 @@ duck --delete garage:/my-files/an-object.txt

 ## WinSCP (libs3) {#winscp}

-*You can find instructions on how to use the GUI in french [in our wiki](https://wiki.deuxfleurs.fr/fr/Guide/Garage/WinSCP).*
+*You can find instructions on how to use the GUI in french [in our wiki](https://guide.deuxfleurs.fr/prise_en_main/winscp/).*

 How to use `winscp.com`, the CLI interface of WinSCP:

@@ -313,4 +323,3 @@ ls
 ```

 And through the web interface at http://[::1]:8080/web/client
-
@@ -17,7 +17,7 @@ Garage can also help you serve this content.

 ## Gitea

-You can use Garage with Gitea to store your [git LFS](https://git-lfs.github.com/) data, your users' avatar, and their attachements.
+You can use Garage with Gitea to store your [git LFS](https://git-lfs.github.com/) data, your users' avatar, and their attachments.
 You can configure a different target for each data type (check `[lfs]` and `[attachment]` sections of the Gitea documentation) and you can provide a default one through the `[storage]` section.

 Let's start by creating a key and a bucket (your key id and secret will be needed later, keep them somewhere):
@@ -201,11 +201,9 @@ on the binary cache, the client will download the result from the cache instead

 ### Channels

-Channels additionnaly serve Nix definitions, ie. a `.nix` file referencing
+Channels additionally serve Nix definitions, ie. a `.nix` file referencing
 all the derivations you want to serve.

 ## Gitlab

 *External link:* [Gitlab Documentation > Object storage](https://docs.gitlab.com/ee/administration/object_storage.html)
-
-
@@ -8,18 +8,18 @@ have published Ansible roles.  We list them and compare them below.

 ## Comparison of Ansible roles

-| Feature                            | [ansible-role-garage](#zorun-ansible-role-garage) | [garage-docker-ansible-deploy](#moan0s-garage-docker-ansible-deploy) |
-|------------------------------------|---------------------------------------------|---------------------------------------------------------------|
-| **Runtime**                        | Systemd                                     | Docker                                                        |
-| **Target OS**                      | Any Linux                                   | Any Linux                                                     |
-| **Architecture**                   | amd64, arm64, i686                          | amd64, arm64                                                  |
-| **Additional software**            | None                                        | Traefik                                                       |
-| **Automatic node connection**      | ❌                                          | ✅                                                            |
-| **Layout management**              | ❌                                          | ✅                                                            |
-| **Manage buckets & keys**          | ❌                                          | ✅ (basic)                                                    |
-| **Allow custom Garage config**     | ✅                                          | ❌                                                            |
-| **Facilitate Garage upgrades**     | ✅                                          | ❌                                                            |
-| **Multiple instances on one host** | ✅                                          | ✅                                                            |
+| Feature                            | [ansible-role-garage](#zorun-ansible-role-garage) | [garage-docker-ansible-deploy](#moan0s-garage-docker-ansible-deploy) | [eddster2309 ansible-role-garage](#eddster2309-ansible-role-garage) |
+|------------------------------------|---------------------------------------------|---------------------------------------------------------------|---------------------------------|
+| **Runtime**                        | Systemd                                     | Docker                                                        | Systemd                         |
+| **Target OS**                      | Any Linux                                   | Any Linux                                                     | Any Linux                       |
+| **Architecture**                   | amd64, arm64, i686                          | amd64, arm64                                                  | arm64, arm, 386, amd64                            |
+| **Additional software**            | None                                        | Traefik                                                       | Nginx and Keepalived (optional) |
+| **Automatic node connection**      | ❌                                          | ✅                                                            | ✅                              |
+| **Layout management**              | ❌                                          | ✅                                                            | ✅                              |
+| **Manage buckets & keys**          | ❌                                          | ✅ (basic)                                                    | ✅                              |
+| **Allow custom Garage config**     | ✅                                          | ❌                                                            | ❌                              |
+| **Facilitate Garage upgrades**     | ✅                                          | ❌                                                            | ✅                              |
+| **Multiple instances on one host** | ✅                                          | ✅                                                            | ❌                              |


 ## zorun/ansible-role-garage
@@ -49,3 +49,15 @@ structured DNS names, etc).

 As a result, this role makes it easier to start with Garage on Ansible,
 but is less flexible.
+
+## eddster2309/ansible-role-garage
+
+[Source code](https://github.com/eddster2309/ansible-role-garage), [Ansible galaxy](https://galaxy.ansible.com/ui/standalone/roles/eddster2309/garage/)
+
+This role is a opinionated but customisable role using the official Garage
+static binaries and only requires Systemd. As such it should work on any
+Linux based host. It includes all the nesscary configuration to
+automatically setup a clustered Garage deployment. Most Garage
+configuration options are exposed through Ansible variables so while you
+can't provide a custom config you can get very close. It can optionally
+installed a HA nginx deployment with Keepalived.
@@ -15,9 +15,10 @@ Alpine Linux repositories (available since v3.17):
 apk add garage
 ```

-The default configuration file is installed to `/etc/garage.toml`. You can run
-Garage using: `rc-service garage start`. If you don't specify `rpc_secret`, it
-will be automatically replaced with a random string on the first start.
+The default configuration file is installed to `/etc/garage/garage.toml`. You can run
+Garage using: `rc-service garage start`.
+
+If you don't specify `rpc_secret`, it will be automatically replaced with a random string on the first start.

 Please note that this package is built without Consul discovery, Kubernetes
 discovery, OpenTelemetry exporter, and K2V features (K2V will be enabled once
@@ -26,7 +27,11 @@ it's stable).

 ## Arch Linux

-Garage is available in the [AUR](https://aur.archlinux.org/packages/garage).
+Garage is available in the official repositories under [extra](https://archlinux.org/packages/extra/x86_64/garage).
+
+```bash
+pacman -S garage
+```

 ## FreeBSD

@@ -39,3 +44,9 @@ pkg install garage
 ```bash
 nix-shell -p garage
 ```
+
+## conda-forge
+
+```bash
+pixi global install garage
+```
@@ -33,7 +33,7 @@ by adding encryption at different levels.

 We would be very curious to know your needs and thougs about ideas such as
 encryption practices and things like key management, as we want Garage to be a
-serious base platform for the developpment of secure, encrypted applications.
+serious base platform for the development of secure, encrypted applications.
 Do not hesitate to come talk to us if you have any thoughts or questions on the
 subject.

@@ -53,20 +53,43 @@ and that's also why your nodes have super long identifiers.

 Adding TLS support built into Garage is not currently planned.

-## Garage stores data in plain text on the filesystem
+## Garage stores data in plain text on the filesystem or encrypted using customer keys (SSE-C)

-Garage does not handle data encryption at rest by itself, and instead delegates
-to the user to add encryption, either at the storage layer (LUKS, etc) or on
-the client side (or both). There are no current plans to add data encryption
-directly in Garage.
+For standard S3 API requests, Garage does not encrypt data at rest by itself.
+For the most generic at rest encryption of data, we recommend setting up your
+storage partitions on encrypted LUKS devices.

-Implementing data encryption directly in Garage might make things simpler for
-end users, but also raises many more questions, especially around key
-management: for encryption of data, where could Garage get the encryption keys
-from ? If we encrypt data but keep the keys in a plaintext file next to them,
-it's useless. We probably don't want to have to manage secrets in garage as it
-would be very hard to do in a secure way. Maybe integrate with an external
-system such as Hashicorp Vault?
+If you are developing your own client software that makes use of S3 storage,
+we recommend implementing data encryption directly on the client side and never
+transmitting plaintext data to Garage. This makes it easy to use an external
+untrusted storage provider if necessary.
+
+Garage does support [SSE-C
+encryption](https://docs.aws.amazon.com/AmazonS3/latest/userguide/ServerSideEncryptionCustomerKeys.html),
+an encryption mode of Amazon S3 where data is encrypted at rest using
+encryption keys given by the client.  The encryption keys are passed to the
+server in a header in each request, to encrypt or decrypt data at the moment of
+reading or writing. The server discards the key as soon as it has finished
+using it for the request.  This mode allows the data to be encrypted at rest by
+Garage itself, but it requires support in the client software. It is also not
+adapted to a model where the server is not trusted or assumed to be
+compromised, as the server can easily know the encryption keys.  Note however
+that when using SSE-C encryption, the only Garage node that knows the
+encryption key passed in a given request is the node to which the request is
+directed (which can be a gateway node), so it is easy to have untrusted nodes
+in the cluster as long as S3 API requests containing SSE-C encryption keys are
+not directed to them.
+
+Implementing automatic data encryption directly in Garage without client-side
+management of keys (something like
+[SSE-S3](https://docs.aws.amazon.com/AmazonS3/latest/userguide/UsingServerSideEncryption.html))
+could make things simpler for end users that don't want to setup LUKS, but also
+raises many more questions, especially around key management: for encryption of
+data, where could Garage get the encryption keys from? If we encrypt data but
+keep the keys in a plaintext file next to them, it's useless. We probably don't
+want to have to manage secrets in Garage as it would be very hard to do in a
+secure way. At the time of speaking, there are no plans to implement this in
+Garage.


 # Adding data encryption using external tools
@@ -85,14 +108,14 @@ Protects against the following threats:

 - Stolen HDD

-Crucially, does not protect againt malicious sysadmins or remote attackers that
+Crucially, does not protect against malicious sysadmins or remote attackers that
 might gain access to your servers.

 Methods include full-disk encryption with tools such as LUKS.

 ## Encrypting data on the client side

-Protects againt the following threats:
+Protects against the following threats:

 - A honest-but-curious administrator
 - A malicious administrator that tries to corrupt your data
@@ -9,7 +9,7 @@ There are three methods to expose buckets as website:

 1. using the PutBucketWebsite S3 API call, which is allowed for access keys that have the owner permission bit set

-2. from the Garage CLI, by an adminstrator of the cluster
+2. from the Garage CLI, by an administrator of the cluster

 3. using the Garage administration API

@@ -38,7 +38,7 @@ Our website serving logic is as follow:

 Now we need to infer the URL of your website through your bucket name.
 Let assume:
-  - we set `root_domain = ".web.example.com"` in `garage.toml` ([ref](@/documentation/reference-manual/configuration.md#root_domain))
+  - we set `root_domain = ".web.example.com"` in `garage.toml` ([ref](@/documentation/reference-manual/configuration.md#web_root_domain))
  - our bucket name is `garagehq.deuxfleurs.fr`.

 Our bucket will be served if the Host field matches one of these 2 values (the port is ignored):
@@ -20,12 +20,12 @@ sudo apt-get update
 sudo apt-get install build-essential
 ```

-## Building from source from the Gitea repository
+## Building from source from the Forgejo repository

 The primary location for Garage's source code is the
-[Gitea repository](https://git.deuxfleurs.fr/Deuxfleurs/garage),
+[Forgejo repository](https://git.deuxfleurs.fr/Deuxfleurs/garage),
 which contains all of the released versions as well as the code
-for the developpement of the next version.
+for the development of the next version.

 Clone the repository and enter it as follows:

@@ -41,7 +41,7 @@ git tag  				# List available tags
 git checkout v0.8.0		# Change v0.8.0 with the version you wish to build
 ```

-Otherwise you will be building a developpement build from the `main` branch
+Otherwise you will be building a development build from the `main` branch
 that includes all of the changes to be released in the next version.
 Be careful that such a build might be unstable or contain bugs,
 and could be incompatible with nodes that run stable versions of Garage.
@@ -85,11 +85,14 @@ The following feature flags are available in v0.8.0:
 | Feature flag | Enabled | Description |
 | ------------ | ------- | ----------- |
 | `bundled-libs` | *by default* | Use bundled version of sqlite3, zstd, lmdb and libsodium |
-| `system-libs` | optional | Use system version of sqlite3, zstd, lmdb and libsodium<br>if available (exclusive with `bundled-libs`, build using<br>`cargo build --no-default-features --features system-libs`) |
+| `consul-discovery` | optional | Enable automatic registration and discovery<br>of cluster nodes through the Consul API |
+| `fjall` | experimental | Enable using Fjall to store Garage's metadata |
+| `journald` | optional | Enable logging to systemd-journald with<br>`GARAGE_LOG_TO_JOURNALD=true` environment variable set |
 | `k2v` | optional | Enable the experimental K2V API (if used, all nodes on your<br>Garage cluster must have it enabled as well) |
 | `kubernetes-discovery` | optional | Enable automatic registration and discovery<br>of cluster nodes through the Kubernetes API |
+| `lmdb` | *by default* | Enable using LMDB to store Garage's metadata |
 | `metrics` | *by default* | Enable collection of metrics in Prometheus format on the admin API |
+| `sqlite` | *by default* | Enable using Sqlite3 to store Garage's metadata |
+| `syslog` | optional | Enable logging to Syslog with<br>`GARAGE_LOG_TO_SYSLOG=true` environment variable set |
+| `system-libs` | optional | Use system version of sqlite3, zstd, lmdb and libsodium<br>if available (exclusive with `bundled-libs`, build using<br>`cargo build --no-default-features --features system-libs`) |
 | `telemetry-otlp` | optional | Enable collection of execution traces using OpenTelemetry |
-| `sled` | *by default* | Enable using Sled to store Garage's metadata |
-| `lmdb` | optional | Enable using LMDB to store Garage's metadata |
-| `sqlite` | optional | Enable using Sqlite3 to store Garage's metadata |
@@ -11,7 +11,7 @@ Firstly clone the repository:

 ```bash
 git clone https://git.deuxfleurs.fr/Deuxfleurs/garage
-cd garage/scripts/helm
+cd garage/script/helm
 ```

 Deploy with default options:
@@ -26,6 +26,13 @@ Or deploy with custom values:
 helm install --create-namespace --namespace garage garage ./garage -f values.override.yaml
 ```

+If you want to manage the CustomResourceDefinition used by garage for its `kubernetes_discovery` outside of the helm chart, add `garage.kubernetesSkipCrd: true` to your custom values and use the kustomization before deploying the helm chart:
+
+```bash
+kubectl apply -k ../k8s/crd
+helm install --create-namespace --namespace garage garage ./garage -f values.override.yaml
+```
+
 After deploying, cluster layout must be configured manually as described in [Creating a cluster layout](@/documentation/quick-start/_index.md#creating-a-cluster-layout). Use the following command to access garage CLI:

 ```bash
@@ -40,12 +47,12 @@ All possible configuration values can be found with:
 helm show values ./garage
 ```

-This is an example `values.overrride.yaml` for deploying in a microk8s cluster with a https s3 api ingress route:
+This is an example `values.override.yaml` for deploying in a microk8s cluster with a https s3 api ingress route:

 ```yaml
 garage:
  # Use only 2 replicas per object
-  replicationMode: "2"
+  replicationFactor: 2

 # Start 4 instances (StatefulSets) of garage
 deployment:
@@ -86,3 +93,62 @@ helm delete --namespace garage garage
 ```

 Note that this will leave behind custom CRD `garagenodes.deuxfleurs.fr`, which must be removed manually if desired.
+
+## Increase PVC size on running Garage instances
+
+Since the Garage Helm chart creates the data and meta PVC based on `StatefulSet` templates, increasing the PVC size can be a bit tricky.
+
+### Confirm the `StorageClass` used for Garage supports volume expansion
+
+Confirm the storage class used for garage.
+
+```bash
+kubectl -n garage get pvc 
+NAME            STATUS   VOLUME                                     CAPACITY   ACCESS MODES   STORAGECLASS     VOLUMEATTRIBUTESCLASS   AGE
+data-garage-0   Bound    pvc-080360c9-8ce3-4acf-8579-1701e57b7f3f   30Gi       RWO            longhorn-local   <unset>                 77d
+data-garage-1   Bound    pvc-ab8ba697-6030-4fc7-ab3c-0d6df9e3dbc0   30Gi       RWO            longhorn-local   <unset>                 5d8h
+data-garage-2   Bound    pvc-3ab37551-0231-4604-986d-136d0fd950ec   30Gi       RWO            longhorn-local   <unset>                 5d5h
+meta-garage-0   Bound    pvc-3b457302-3023-4169-846e-c928c5f2ea65   3Gi        RWO            longhorn-local   <unset>                 77d
+meta-garage-1   Bound    pvc-49ace2b9-5c85-42df-9247-51c4cf64b460   3Gi        RWO            longhorn-local   <unset>                 5d8h
+meta-garage-2   Bound    pvc-99e2e50f-42b4-4128-ae2f-b52629259723   3Gi        RWO            longhorn-local   <unset>                 5d5h
+```
+
+In this case, the storage class is `longhorn-local`. Now, check if `ALLOWVOLUMEEXPANSION` is true for the used `StorageClass`.
+
+```bash
+kubectl get storageclasses.storage.k8s.io longhorn-local
+NAME             PROVISIONER          RECLAIMPOLICY   VOLUMEBINDINGMODE   ALLOWVOLUMEEXPANSION   AGE
+longhorn-local   driver.longhorn.io   Delete          Immediate           true                   103d
+```
+
+If your `StorageClass` does not support volume expansion, double check if you can enable it. Otherwise, your only real option is to spin up a new Garage cluster with increased size and migrate all data over.
+
+If your `StorageClass` supports expansion, you are free to continue.
+
+### Increase the size of the PVCs
+
+Increase the size of all PVCs to your desired size.
+
+```bash
+kubectl -n garage edit pvc data-garage-0
+kubectl -n garage edit pvc data-garage-1
+kubectl -n garage edit pvc data-garage-2
+kubectl -n garage edit pvc meta-garage-0
+kubectl -n garage edit pvc meta-garage-1
+kubectl -n garage edit pvc meta-garage-2
+```
+
+### Increase the size of the `StatefulSet` PVC template
+
+This is an optional step, but if not done, future instances of Garage will be created with the original size from the template.
+
+```bash
+kubectl -n garage delete sts --cascade=orphan garage 
+statefulset.apps "garage" deleted
+```
+
+This will remove the Garage `StatefulSet` but leave the pods running. It may seem destructive but needs to be done this way since edits to the size of PVC templates are prohibited.
+
+### Redeploy the `StatefulSet`
+
+Now the size of future PVCs can be increased, and the Garage Helm chart can be upgraded. The new `StatefulSet` should take ownership of the orphaned pods again.
@@ -18,7 +18,7 @@ api_bind_addr = "0.0.0.0:3903"
 ```

 This will allow anyone to scrape Prometheus metrics by fetching
-`http://localhost:3093/metrics`. If you want to restrict access
+`http://localhost:3903/metrics`. If you want to restrict access
 to the exported metrics, set the `metrics_token` configuration value
 to a bearer token to be used when fetching the metrics endpoint.

@@ -19,14 +19,15 @@ To run a real-world deployment, make sure the following conditions are met:

 - You have at least three machines with sufficient storage space available.

- Each machine has a public IP address which is reachable by other machines. It
-  is highly recommended that you use IPv6 for this end-to-end connectivity. If
-  IPv6 is not available, then using a mesh VPN such as
+- Each machine has an IP address which makes it directly reachable by all other machines.
+  In many cases, nodes will be behind a NAT and will not each have a public
+  IPv4 addresses. In this case, is recommended that you use IPv6 for this
+  end-to-end connectivity if it is available. Otherwise, using a mesh VPN such as
  [Nebula](https://github.com/slackhq/nebula) or
  [Yggdrasil](https://yggdrasil-network.github.io/) are approaches to consider
  in addition to building out your own VPN tunneling.

- This guide will assume you are using Docker containers to deploy Garage on each node. 
+- This guide will assume you are using Docker containers to deploy Garage on each node.
  Garage can also be run independently, for instance as a [Systemd service](@/documentation/cookbook/systemd.md).
  You can also use an orchestrator such as Nomad or Kubernetes to automatically manage
  Docker containers on a fleet of nodes.
@@ -42,7 +43,7 @@ For our example, we will suppose the following infrastructure with IPv6 connecti
 | Brussels | Mars    | fc00:F::1  | 1.5 TB     |

 Note that Garage will **always** store the three copies of your data on nodes at different
-locations. This means that in the case of this small example, the available capacity
+locations. This means that in the case of this small example, the usable capacity
 of the cluster is in fact only 1.5 TB, because nodes in Brussels can't store more than that.
 This also means that nodes in Paris and London will be under-utilized.
 To make better use of the available hardware, you should ensure that the capacity
@@ -52,9 +53,9 @@ to store 2 TB of data in total.

 ### Best practices

- If you have fast dedicated networking between all your nodes, and are planing to store
-  very large files, bump the `block_size` configuration parameter to 10 MB
-  (`block_size = 10485760`).
+- If you have reasonably fast networking between all your nodes, and are planing to store
+  mostly large files, bump the `block_size` configuration parameter to 10 MB
+  (`block_size = "10M"`).

 - Garage stores its files in two locations: it uses a metadata directory to store frequently-accessed
  small metadata items, and a data directory to store data blocks of uploaded objects.
@@ -67,31 +68,42 @@ to store 2 TB of data in total.
  EXT4 is not recommended as it has more strict limitations on the number of inodes,
  which might cause issues with Garage when large numbers of objects are stored.

- If you only have an HDD and no SSD, it's fine to put your metadata alongside the data
-  on the same drive. Having lots of RAM for your kernel to cache the metadata will
-  help a lot with performance.  Make sure to use the LMDB database engine,
-  instead of Sled, which suffers from quite bad performance degradation on HDDs.
-  Sled is still the default for legacy reasons, but is not recommended anymore.
-
- For the metadata storage, Garage does not do checksumming and integrity
-  verification on its own. If you are afraid of bitrot/data corruption,
-  put your metadata directory on a ZFS or BTRFS partition. Otherwise, just use regular
-  EXT4 or XFS.
-
 - Servers with multiple HDDs are supported natively by Garage without resorting
  to RAID, see [our dedicated documentation page](@/documentation/operations/multi-hdd.md).

+- For the metadata storage, Garage does not do checksumming and integrity
+  verification on its own, so it is better to use a robust filesystem such as
+  BTRFS or ZFS. Users have reported that when using the LMDB database engine
+  (the default), database files have a tendency of becoming corrupted after an
+  unclean shutdown (e.g. a power outage), so you should take regular snapshots
+  to be able to recover from such a situation.  This can be done using Garage's
+  built-in automatic snapshotting (since v0.9.4), or by using filesystem level
+  snapshots. If you cannot do so, you might want to switch to Sqlite which is
+  more robust.
+
+- LMDB is the fastest and most tested database engine, but it has the following
+  weaknesses: 1/ data files are not architecture-independent, you cannot simply
+  move a Garage metadata directory between nodes running different architectures,
+  and 2/ LMDB is not suited for 32-bit platforms. Sqlite is a viable alternative
+  if any of these are of concern.
+
+- If you only have an HDD and no SSD, it's fine to put your metadata alongside
+  the data on the same drive, but then consider your filesystem choice wisely
+  (see above). Having lots of RAM for your kernel to cache the metadata will
+  help a lot with performance.  The default LMDB database engine is the most
+  tested and has good performance.
+
 ## Get a Docker image

 Our docker image is currently named `dxflrs/garage` and is stored on the [Docker Hub](https://hub.docker.com/r/dxflrs/garage/tags?page=1&ordering=last_updated).
-We encourage you to use a fixed tag (eg. `v0.8.0`) and not the `latest` tag.
-For this example, we will use the latest published version at the time of the writing which is `v0.8.0` but it's up to you
+We encourage you to use a fixed tag (eg. `v2.2.0`) and not the `latest` tag.
+For this example, we will use the latest published version at the time of the writing which is `v2.2.0` but it's up to you
 to check [the most recent versions on the Docker Hub](https://hub.docker.com/r/dxflrs/garage/tags?page=1&ordering=last_updated).

 For example:

 ```
-sudo docker pull dxflrs/garage:v0.8.0
+sudo docker pull dxflrs/garage:v2.2.0
 ```

 ## Deploying and configuring Garage
@@ -114,8 +126,9 @@ A valid `/etc/garage.toml` for our cluster would look as follows:
 metadata_dir = "/var/lib/garage/meta"
 data_dir = "/var/lib/garage/data"
 db_engine = "lmdb"
+metadata_auto_snapshot_interval = "6h"

-replication_mode = "3"
+replication_factor = 3

 compression_level = 2

@@ -139,6 +152,8 @@ Check the following for your configuration files:
 - Make sure `rpc_public_addr` contains the public IP address of the node you are configuring.
  This parameter is optional but recommended: if your nodes have trouble communicating with
  one another, consider adding it.
+  Alternatively, you can also set `rpc_public_addr_subnet`, which can filter
+  the addresses announced to other peers to a specific subnet.

 - Make sure `rpc_secret` is the same value on all nodes. It should be a 32-bytes hex-encoded secret key.
  You can generate such a key with `openssl rand -hex 32`.
@@ -156,12 +171,13 @@ docker run \
  -v /etc/garage.toml:/etc/garage.toml \
  -v /var/lib/garage/meta:/var/lib/garage/meta \
  -v /var/lib/garage/data:/var/lib/garage/data \
-  dxflrs/garage:v0.8.0
+  dxflrs/garage:v2.2.0
 ```

-It should be restarted automatically at each reboot.
-Please note that we use host networking as otherwise Docker containers
-can not communicate with IPv6.
+With this command line, Garage should be started automatically at each boot.
+Please note that we use host networking as otherwise the network indirection
+added by Docker would prevent Garage nodes from communicating with one another
+(especially if using IPv6).

 If you want to use `docker-compose`, you may use the following `docker-compose.yml` file as a reference:

@@ -169,7 +185,7 @@ If you want to use `docker-compose`, you may use the following `docker-compose.y
 version: "3"
 services:
  garage:
-    image: dxflrs/garage:v0.8.0
+    image: dxflrs/garage:v2.2.0
    network_mode: "host"
    restart: unless-stopped
    volumes:
@@ -178,12 +194,14 @@ services:
      - /var/lib/garage/data:/var/lib/garage/data
 ```

-Upgrading between Garage versions should be supported transparently,
-but please check the relase notes before doing so!
-To upgrade, simply stop and remove this container and
-start again the command with a new version of Garage.
+If you wish to upgrade your cluster, make sure to read the corresponding
+[documentation page](@/documentation/operations/upgrading.md) first, as well as
+the documentation relevant to your version of Garage in the case of major
+upgrades.  With the containerized setup proposed here, the upgrade process
+will require stopping and removing the existing container, and re-creating it
+with the upgraded version.

-## Controling the daemon
+## Controlling the daemon

 The `garage` binary has two purposes:
  - it acts as a daemon when launched with `garage server`
@@ -241,7 +259,7 @@ You can then instruct nodes to connect to one another as follows:
 Venus$ garage node connect 563e1ac825ee3323aa441e72c26d1030d6d4414aeb3dd25287c531e7fc2bc95d@[fc00:1::1]:3901
 ```

-You don't nead to instruct all node to connect to all other nodes:
+You don't need to instruct all node to connect to all other nodes:
 nodes will discover one another transitively.

 Now if your run `garage status` on any node, you should have an output that looks as follows:
@@ -265,12 +283,12 @@ of a role that is assigned to each active cluster node.
 For our example, we will suppose we have the following infrastructure
 (Capacity, Identifier and Zone are specific values to Garage described in the following):

-| Location | Name    | Disk Space | `Capacity` | `Identifier` | `Zone` |
-|----------|---------|------------|------------|--------------|--------------|
-| Paris    | Mercury | 1 TB       | `10`       | `563e`     | `par1`       |
-| Paris    | Venus   | 2 TB       | `20`       | `86f0`     | `par1`       |
-| London   | Earth   | 2 TB       | `20`       | `6814`     | `lon1`       |
-| Brussels | Mars    | 1.5 TB     | `15`       | `212f`     | `bru1`       |
+| Location | Name    | Disk Space | Identifier | Zone (`-z`) | Capacity (`-c`) |
+|----------|---------|------------|------------|-------------|-----------------|
+| Paris    | Mercury | 1 TB       | `563e`     | `par1`      | `1T`            |
+| Paris    | Venus   | 2 TB       | `86f0`     | `par1`      | `2T`            |
+| London   | Earth   | 2 TB       | `6814`     | `lon1`      | `2T`            |
+| Brussels | Mars    | 1.5 TB     | `212f`     | `bru1`      | `1.5T`          |

 #### Node identifiers

@@ -292,6 +310,8 @@ garage status
 It will display the IP address associated with each node;
 from the IP address you will be able to recognize the node.

+We will now use the `garage layout assign` command to configure the correct parameters for each node.
+
 #### Zones

 Zones are simply a user-chosen identifier that identify a group of server that are grouped together logically.
@@ -301,29 +321,29 @@ In most cases, a zone will correspond to a geographical location (i.e. a datacen
 Behind the scene, Garage will use zone definition to try to store the same data on different zones,
 in order to provide high availability despite failure of a zone.

+Zones are passed to Garage using the `-z` flag of `garage layout assign` (see below).
+
 #### Capacity

-Garage reasons on an abstract metric about disk storage that is named the *capacity* of a node.
-The capacity configured in Garage must be proportional to the disk space dedicated to the node.
+Garage needs to know the storage capacity (disk space) it can/should use on
+each node, to be able to correctly balance data.

-Capacity values must be **integers** but can be given any signification.
-Here we chose that 1 unit of capacity = 100 GB.
+Capacity values are expressed in bytes and are passed to Garage using the `-c` flag of `garage layout assign` (see below).

-Note that the amount of data stored by Garage on each server may not be strictly proportional to
-its capacity value, as Garage will priorize having 3 copies of data in different zones,
-even if this means that capacities will not be strictly respected. For example in our above examples,
-nodes Earth and Mars will always store a copy of everything each, and the third copy will
-have 66% chance of being stored by Venus and 33% chance of being stored by Mercury.
+#### Tags
+
+You can add additional tags to nodes using the `-t` flag of `garage layout assign` (see below).
+Tags have no specific meaning for Garage and can be used at your convenience.

 #### Injecting the topology

 Given the information above, we will configure our cluster as follow:

 ```bash
-garage layout assign 563e -z par1 -c 10 -t mercury
-garage layout assign 86f0 -z par1 -c 20 -t venus
-garage layout assign 6814 -z lon1 -c 20 -t earth 
-garage layout assign 212f -z bru1 -c 15 -t mars 
+garage layout assign 563e -z par1 -c 1T -t mercury
+garage layout assign 86f0 -z par1 -c 2T -t venus
+garage layout assign 6814 -z lon1 -c 2T -t earth
+garage layout assign 212f -z bru1 -c 1.5T -t mars
 ```

 At this point, the changes in the cluster layout have not yet been applied.
@@ -333,6 +353,7 @@ To show the new layout that will be applied, call:
 garage layout show
 ```

+Make sure to read carefully the output of `garage layout show`.
 Once you are satisfied with your new layout, apply it with:

 ```bash
@@ -7,7 +7,7 @@ The main reason to add a reverse proxy in front of Garage is to provide TLS to y

 In production you will likely need your certificates signed by a certificate authority.
 The most automated way is to use a provider supporting the [ACME protocol](https://datatracker.ietf.org/doc/html/rfc8555) 
-such as [Let's Encrypt](https://letsencrypt.org/), [ZeroSSL](https://zerossl.com/) or [Buypass Go SSL](https://www.buypass.com/ssl/products/acme).
+such as [Let's Encrypt](https://letsencrypt.org/) or [ZeroSSL](https://zerossl.com/).

 If you are only testing Garage, you can generate a self-signed certificate to follow the documentation:

@@ -97,7 +97,7 @@ server {
  location / {
    proxy_pass http://s3_backend;
    proxy_set_header X-Forwarded-For $proxy_add_x_forwarded_for;
-    proxy_set_header Host $host;
+    proxy_set_header Host $http_host;
    # Disable buffering to a temporary file.
    proxy_max_temp_file_size 0;
  }
@@ -272,7 +272,7 @@ Add the following configuration section [to compress response](https://doc.traef

 ### 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)
+Traefik's caching middleware is only available on [enterprise 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

@@ -472,3 +472,32 @@ https:// {

 More information on how this endpoint is implemented in Garage is available
 in the [Admin API Reference](@/documentation/reference-manual/admin-api.md) page.
+
+### Fileserver browser
+
+Caddy's built-in
+[file_server](https://caddyserver.com/docs/caddyfile/directives/file_server)
+browser functionality can be extended with the
+[caddy-fs-s3](https://github.com/sagikazarmark/caddy-fs-s3) module.
+
+This can be configured to use Garage as a backend with the following
+configuration:
+
+```caddy
+browse.garage.tld {
+    file_server {
+        fs s3 {
+            bucket test-bucket
+            region garage
+
+            endpoint https://s3.garage.tld
+            use_path_style
+        }
+
+        browse
+    }
+}
+```
+
+Caddy must also be configured with the required `AWS_ACCESS_KEY_ID` and
+`AWS_SECRET_ACCESS_KEY` environment variables to access the bucket.
@@ -28,6 +28,7 @@ StateDirectory=garage
 DynamicUser=true
 ProtectHome=true
 NoNewPrivileges=true
+LimitNOFILE=42000

 [Install]
 WantedBy=multi-user.target
@@ -37,7 +38,7 @@ WantedBy=multi-user.target
 id is dynamically allocated by systemd (set with `DynamicUser=true`). It cannot
 access (read or write) home folders (`/home`, `/root` and `/run/user`), the
 rest of the filesystem can only be read but not written, only the path seen as
-`/var/lib/garage` is writable as seen by the service. Additionnaly, the process
+`/var/lib/garage` is writable as seen by the service. Additionally, the process
 can not gain new privileges over time.

 For this to work correctly, your `garage.toml` must be set with
@@ -10,7 +10,7 @@ perspective.  It will allow you to understand if Garage is a good fit for
 you, how to better use it, how to contribute to it, what can Garage could
 and could not do, etc.

- **[Goals and use cases](@/documentation/design/goals.md):** This page explains why Garage was concieved and what practical use cases it targets.
+- **[Goals and use cases](@/documentation/design/goals.md):** This page explains why Garage was conceived and what practical use cases it targets.

 - **[Related work](@/documentation/design/related-work.md):** This pages presents the theoretical background on which Garage is built, and describes other software storage solutions and why they didn't work for us.

@@ -31,5 +31,3 @@ We love to talk and hear about Garage, that's why we keep a log here:
  - [(en, 2021-04-28) Distributed object storage is centralised](https://git.deuxfleurs.fr/Deuxfleurs/garage/src/commit/b1f60579a13d3c5eba7f74b1775c84639ea9b51a/doc/talks/2021-04-28_spirals-team/talk.pdf)

  - [(fr, 2020-12-02) Garage : jouer dans la cour des grands quand on est un hébergeur associatif](https://git.deuxfleurs.fr/Deuxfleurs/garage/src/commit/b1f60579a13d3c5eba7f74b1775c84639ea9b51a/doc/talks/2020-12-02_wide-team/talk.pdf)
-
-
@@ -15,14 +15,14 @@ The more a user request will require intra-cluster requests to complete, the mor
 This is especially true for sequential requests: requests that must wait the result of another request to be sent.
 We designed Garage without consensus algorithms (eg. Paxos or Raft) to minimize the number of sequential and parallel requests.

-This serie of benchmarks quantifies the impact of this design choice.
+This series of benchmarks quantifies the impact of this design choice.

 ### On a simple simulated network

 We start with a controlled environment, all the instances are running on the same (powerful enough) machine.

-To control the network latency, we simulate the network with [mknet](https://git.deuxfleurs.fr/trinity-1686a/mknet) (a tool we developped, based on `tc` and the linux network stack).
-To mesure S3 endpoints latency, we use our own tool [s3lat](https://git.deuxfleurs.fr/quentin/s3lat/) to observe only the intra-cluster latency and not some contention on the nodes (CPU, RAM, disk I/O, network bandwidth, etc.).
+To control the network latency, we simulate the network with [mknet](https://git.deuxfleurs.fr/trinity-1686a/mknet) (a tool we developed, based on `tc` and the linux network stack).
+To measure S3 endpoints latency, we use our own tool [s3lat](https://git.deuxfleurs.fr/quentin/s3lat/) to observe only the intra-cluster latency and not some contention on the nodes (CPU, RAM, disk I/O, network bandwidth, etc.).
 Compared to other benchmark tools, S3Lat sends only one (small) request at the same time and measures its latency.
 We selected 5 standard endpoints that are often in the critical path: ListBuckets, ListObjects, GetObject, PutObject and RemoveObject.

@@ -32,7 +32,7 @@ In this first benchmark, we consider 5 instances that are located in a different

 Compared to garage, minio latency drastically increases on 3 endpoints: GetObject, PutObject, RemoveObject.

-We suppose that these requests on minio make transactions over Raft, involving 4 sequential requests: 1) sending the message to the leader, 2) having the leader dispatch it to the other nodes, 3) waiting for the confirmation of followers and finally 4) commiting it. With our current configuration, one Raft transaction will take around 400 ms. GetObject seems to correlate to 1 transaction while PutObject and RemoveObject seems to correlate to 2 or 3. Reviewing minio code would be required to confirm this hypothesis.
+We suppose that these requests on minio make transactions over Raft, involving 4 sequential requests: 1) sending the message to the leader, 2) having the leader dispatch it to the other nodes, 3) waiting for the confirmation of followers and finally 4) committing it. With our current configuration, one Raft transaction will take around 400 ms. GetObject seems to correlate to 1 transaction while PutObject and RemoveObject seems to correlate to 2 or 3. Reviewing minio code would be required to confirm this hypothesis.

 Conversely, garage uses an architecture similar to DynamoDB and never require global cluster coordination to answer a request.
 Instead, garage can always contact the right node in charge of the requested data, and can answer in as low as one request in the case of GetObject and PutObject. We also observed that Garage latency, while often lower to minio, is more dispersed: garage is still in beta and has not received any performance optimization yet.
@@ -50,7 +50,7 @@ We plot a similar graph as before:

 This new graph is very similar to the one before, neither minio or garage seems to benefit from this new topology, but they also do not suffer from it.

-Considering garage, this is expected: nodes in the same DC are put in the same zone, and then data are spread on different zones for data resiliency and availaibility.
+Considering garage, this is expected: nodes in the same DC are put in the same zone, and then data are spread on different zones for data resiliency and availability.
 Then, in the default mode, requesting data requires to query at least 2 zones to be sure that we have the most up to date information.
 These requests will involve at least one inter-DC communication.
 In other words, we prioritize data availability and synchronization over raw performances.
@@ -48,7 +48,24 @@ locations. They use Garage themselves for the following tasks:

 - As a backup target using `rclone` and `restic`

- In the Drone continuous integration platform to store task logs
-
 The Deuxfleurs Garage cluster is a multi-site cluster currently composed of
 9 nodes in 3 physical locations.
+
+### Triplebit
+
+[Triplebit](https://www.triplebit.org) is a non-profit hosting provider and
+ISP focused on improving access to privacy-related services. They use
+Garage themselves for the following tasks:
+
+- Hosting of their homepage, [privacyguides.org](https://www.privacyguides.org/), and various other static sites
+
+- As a PowerDNS authoritative zone backend through [Lightning Stream](https://doc.powerdns.com/lightningstream/latest/index.html) and [LMDB](https://doc.powerdns.com/authoritative/backends/lmdb.html)
+
+- As a Mastodon media storage backend for [mstdn.party](https://mstdn.party/) and [mstdn.plus](https://mstdn.plus/)
+
+- As a PeerTube storage backend for [neat.tube](https://neat.tube/)
+
+- As a [Matrix media backend](https://github.com/matrix-org/synapse-s3-storage-provider)
+
+Triplebit's Garage cluster is a multi-site cluster currently composed of
+15 storage nodes in 3 physical locations.
@@ -94,10 +94,10 @@ delete a tombstone, the following condition has to be met:

 - All nodes responsible for storing this entry are aware of the existence of
  the tombstone, i.e. they cannot hold another version of the entry that is
-  superseeded by the tombstone. This ensures that deleting the tombstone is
+  superseded by the tombstone. This ensures that deleting the tombstone is
  safe and that no deleted value will come back in the system.

-Garage makes use of Sled's atomic operations (such as compare-and-swap and
+Garage uses atomic database operations (such as compare-and-swap and
 transactions) to ensure that only tombstones that have been correctly
 propagated to other nodes are ever deleted from the local entry tree.

@@ -141,4 +141,3 @@ rebalance of data, this would have led to the disk utilization to explode
 during the rebalancing, only to shrink again after 24 hours. The 10-minute
 delay is a compromise that gives good security while not having this problem of
 disk space explosion on rebalance.
-
@@ -37,7 +37,7 @@ However, Amazon S3 source code is not open but alternatives were proposed.
 We identified Minio, Pithos, Swift and Ceph.
 Minio/Ceph enforces a total order, so properties similar to a (relaxed) filesystem.
 Swift and Pithos are probably the most similar to AWS S3 with their consistent hashing ring.
-However Pithos is not maintained anymore. More precisely the company that published Pithos version 1 has developped a second version 2 but has not open sourced it.
+However Pithos is not maintained anymore. More precisely the company that published Pithos version 1 has developed a second version 2 but has not open sourced it.
 Some tests conducted by the [ACIDES project](https://acides.org/) have shown that Openstack Swift consumes way more resources (CPU+RAM) that we can afford. Furthermore, people developing Swift have not designed their software for geo-distribution.

 There were many attempts in research too. I am only thinking to [LBFS](https://pdos.csail.mit.edu/papers/lbfs:sosp01/lbfs.pdf) that was used as a basis for Seafile. But none of them have been effectively implemented yet.
@@ -63,11 +63,11 @@ Due to its industry oriented design, Ceph is also far from being *Simple* to ope
 In a certain way, Ceph and MinIO are closer together than they are from Garage or OpenStack Swift.

 **[Pithos](https://github.com/exoscale/pithos):**
-Pithos has been abandonned and should probably not used yet, in the following we explain why we did not pick their design.
+Pithos has been abandoned and should probably not used yet, in the following we explain why we did not pick their design.
 Pithos was relying as a S3 proxy in front of Cassandra (and was working with Scylla DB too).
 From its designers' mouth, storing data in Cassandra has shown its limitations justifying the project abandonment.
 They built a closed-source version 2 that does not store blobs in the database (only metadata) but did not communicate further on it.
-We considered there v2's design but concluded that it does not fit both our *Self-contained & lightweight* and *Simple* properties. It makes the development, the deployment and the operations more complicated while reducing the flexibility.
+We considered their v2's design but concluded that it does not fit both our *Self-contained & lightweight* and *Simple* properties. It makes the development, the deployment and the operations more complicated while reducing the flexibility.

 **[Riak CS](https://docs.riak.com/riak/cs/2.1.1/index.html):**
 *Not written yet*
@@ -36,7 +36,7 @@ sudo killall nix-daemon
 Now you can enter our nix-shell, all the required packages will be downloaded but they will not pollute your environment outside of the shell:

 ```bash
-nix-shell
+nix-shell -A devShell
 ```

 You can use the traditional Rust development workflow:
@@ -65,8 +65,8 @@ nix-build -j $(nproc) --max-jobs auto
 ```

 Our build has multiple parameters you might want to set:
-  - `release` build with release optimisations instead of debug
-  - `target allows` for cross compilation
+  - `release` to build with release optimisations instead of debug
+  - `target` allows for cross compilation
  - `compileMode` can be set to test or bench to build a unit test runner
  - `git_version` to inject the hash to display when running `garage stats`

@@ -80,7 +80,7 @@ nix-build \
  --git_version $(git rev-parse HEAD)
 ```

-*The result is located in `result/bin`. You can pass arguments to cross compile: check `.drone.yml` for examples.*
+*The result is located in `result/bin`. You can pass arguments to cross compile: check `.woodpecker/release.yml` for examples.*

 If you modify a `Cargo.toml` or regenerate any `Cargo.lock`, you must run `cargo2nix`:

@@ -81,12 +81,9 @@ Our cache will be checked.
 - http://www.lpenz.org/articles/nixchannel/index.html


-## Drone
+## Woodpecker

-Do not try to set a build as trusted from the interface or the CLI tool,
-your request would be ignored. Instead, directly edit the database (table `repos`, column `repo_trusted`).
-
-Drone can do parallelism both at the step and the pipeline level. At the step level, parallelism is restricted to the same runner.
+Woodpecker can do parallelism both at the step and the pipeline level. At the step level, parallelism is restricted to the same runner.

 ## Building Docker containers

@@ -99,3 +96,4 @@ We were:
  - Unable to use the kaniko container provided by Google as we can't run arbitrary logic: we need to put our secret in .docker/config.json.

 Finally we chose to build kaniko through nix and use it in a `nix-shell`.
+We then switched to using kaniko from nixpkgs when it was packaged.
@@ -23,7 +23,7 @@ This logic is defined in `nix/build_index.nix`.
 For each commit, we first pass the code to a formatter (rustfmt) and a linter (clippy).
 Then we try to build it in debug mode and run both unit tests and our integration tests.

-Additionnaly, when releasing, our integration tests are run on the release build for amd64 and i686.
+Additionally, when releasing, our integration tests are run on the release build for amd64 and i686.

 ## Generated Artifacts

@@ -32,7 +32,7 @@ We generate the following binary artifacts for now:
  - **os**: linux
  - **format**: static binary, docker container

-Additionnaly we also build two web pages and one JSON document:
+Additionally we also build two web pages and one JSON document:
  - the documentation (this website)
  - [the release page](https://garagehq.deuxfleurs.fr/_releases.html)
  - [the release list in JSON format](https://garagehq.deuxfleurs.fr/_releases.json)
@@ -42,7 +42,7 @@ and the docker containers on Docker Hub.

 ## Automation

-We automated our release process with Nix and Drone to make it more reliable.
+We automated our release process with Nix and Woodpecker to make it more reliable.
 Here we describe how we have done in case you want to debug or improve it.

 ### Caching build steps
@@ -62,52 +62,31 @@ Sending to the cache is done through `nix copy`, for example:
 nix copy --to 's3://nix?endpoint=garage.deuxfleurs.fr&region=garage&secret-key=/etc/nix/signing-key.sec' result
 ```

-*Note that you need the signing key. In our case, it is stored as a secret in Drone.*
+*The signing key possessed by the Garage maintainers is required to update the Nix cache.*

-The previous command will only send the built packet and not its dependencies.
-To send its dependency, a tool named `nix-copy-closure` has been created but it is not compatible with the S3 protocol.
-
-Instead, you can use the following commands to list all the runtime dependencies:
+The previous command will only send the built package and not its dependencies.
+In the case of our CI pipeline, we want to cache all intermediate build steps
+as well. This can be done using this quite involved command (here as an example
+for the `pkgs.amd64.release` package):

 ```bash
-nix copy \
-  --to 's3://nix?endpoint=garage.deuxfleurs.fr&region=garage&secret-key=/etc/nix/signing-key.sec' \
-  $(nix-store -qR result/)
+nix copy -j8 \
+    --to 's3://nix?endpoint=garage.deuxfleurs.fr&region=garage&secret-key=/etc/nix/nix-signing-key.sec' \
+    $(nix path-info pkgs.amd64.release --file default.nix --derivation --recursive | sed 's/\.drv$/.drv^*/')
 ```

-*We could also write this expression with xargs but this tool is not available in our container.*
+This command will simultaneously build all of the required Nix paths (using at
+most 8 parallel Nix builder jobs) and send the resulting objects to the cache.

-But in certain cases, we want to cache compile time dependencies also.
-For example, the Nix project does not provide binaries for cross compiling to i686 and thus we need to compile gcc on our own.
-We do not want to compile gcc each time, so even if it is a compile time dependency, we want to cache it.
-
-This time, the command is a bit more involved:
-
-```bash
-nix copy --to \
-  's3://nix?endpoint=garage.deuxfleurs.fr&region=garage&secret-key=/etc/nix/signing-key.sec' \
-   $(nix-store -qR --include-outputs \
-     $(nix-instantiate))
-```
-
-This is the command we use in our CI as we expect the final binary to change, so we mainly focus on
-caching our development dependencies.
-
-*Currently there is no automatic garbage collection of the cache: we should monitor its growth.
-Hopefully, we can erase it totally without breaking any build, the next build will only be slower.*
-
-In practise, we concluded that we do not want to cache all the compilation dependencies.
-Instead, we want to cache the toolchain we use to build Garage each time we change it.
-So we removed from Drone any automatic update of the cache and instead handle them manually with:
+This can be run for all the Garage packages we build using the following command:

 ```
 source ~/.awsrc
-nix-shell --run 'refresh_toolchain'
+nix-shell --attr cache --run 'refresh_cache'
 ```

-Internally, it will run `nix-build` on  `nix/toolchain.nix` and send the output plus its depedencies to the cache.
-
-To erase the cache:
+We don't automate this step at each CI build, as *there is currently no automatic garbage collection of the cache.*
+This means we should also monitor the cache's size; if it ever becomes too big we can erase it with:

 ```
 mc rm --recursive --force 'garage/nix/'
@@ -157,9 +136,9 @@ nix-shell --run refresh_index

 If you want to compile for different architectures, you will need to repeat all these commands for each architecture.

-**In practise, and except for debugging, you will never directly run these commands. Release is handled by drone**
+**In practice, and except for debugging, you will never directly run these commands. Release is handled by Woodpecker.**

-### Drone
+### Drone (obsolete)

 Our instance is available at [https://drone.deuxfleurs.fr](https://drone.deuxfleurs.fr).  
 You need an account on [https://git.deuxfleurs.fr](https://git.deuxfleurs.fr) to use it.
@@ -195,5 +174,3 @@ drone sign --save Deuxfleurs/garage
 ```

 Looking at the file, you will see that most of the commands are `nix-shell` and `nix-build` commands with various parameters.
-
-
@@ -19,7 +19,7 @@ connecting to. To run on all nodes, add the `-a` flag as follows:

 # Data block operations

-## Data store scrub
+## Data store scrub {#scrub}

 Scrubbing the data store means examining each individual data block to check that
 their content is correct, by verifying their hash. Any block found to be corrupted
@@ -42,14 +42,14 @@ You may pause an ongoing scrub using `garage repair scrub pause`, but note that
 the scrub will resume automatically 24 hours later as Garage will not let your
 cluster run without a regular scrub. If the scrub procedure is too intensive
 for your servers and is slowing down your workload, the recommended solution
-is to increase the "scrub tranquility" using `garage repair scrub set-tranquility`.
+is to increase the "scrub tranquility" using `garage worker set scrub-tranquility`.
 A higher tranquility value will make Garage take longer pauses between two block
 verifications. Of course, scrubbing the entire data store will also take longer.

 ## Block check and resync

 In some cases, nodes hold a reference to a block but do not actually have the block
-stored on disk. Conversely, they may also have on disk blocks that are not referenced
+stored on disk. Conversely, they may also have on-disk blocks that are not referenced
 any more. To fix both cases, a block repair may be run with `garage repair blocks`.
 This will scan the entire block reference counter table to check that the blocks
 exist on disk, and will scan the entire disk store to check that stored blocks
@@ -95,7 +95,7 @@ using the `garage block purge` command.

 In [multi-HDD setups](@/documentation/operations/multi-hdd.md), to ensure that
 data blocks are well balanced between storage locations, you may run a
-rebalance operation using `garage repair rebalance`. This is usefull when
+rebalance operation using `garage repair rebalance`. This is useful when
 adding storage locations or when capacities of the storage locations have been
 changed.  Once this is finished, Garage will know for each block of a single
 possible location where it can be, which can increase access speed.  This
@@ -104,6 +104,24 @@ operation will also move out all data from locations marked as read-only.

 # Metadata operations

+## Metadata snapshotting
+
+It is good practice to setup automatic snapshotting of your metadata database
+file, to recover from situations where it becomes corrupted on disk. This can
+be done at the filesystem level if you are using ZFS or BTRFS.
+
+Since Garage v0.9.4, Garage is able to take snapshots of the metadata database
+itself. This basically amounts to copying the database file, except that it can
+be run live while Garage is running without the risk of corruption or
+inconsistencies.  This can be setup to run automatically on a schedule using
+[`metadata_auto_snapshot_interval`](@/documentation/reference-manual/configuration.md#metadata_auto_snapshot_interval).
+A snapshot can also be triggered manually using the `garage meta snapshot`
+command. Note that taking a snapshot using this method is very intensive as it
+requires making a full copy of the database file, so you might prefer using
+filesystem-level snapshots if possible. To recover a corrupted node from such a
+snapshot, read the instructions
+[here](@/documentation/operations/recovering.md#corrupted_meta).
+
 ## Metadata table resync

 Garage automatically resyncs all entries stored in the metadata tables every hour,
@@ -123,4 +141,7 @@ blocks may still be held by Garage. If you suspect that such corruption has occu
 in your cluster, you can run one of the following repair procedures:

 - `garage repair versions`: checks that all versions belong to a non-deleted object, and purges any orphan version
- `garage repair block_refs`: checks that all block references belong to a non-deleted object version, and purges any orphan block reference (this will then allow the blocks to be garbage-collected)
+
+- `garage repair block-refs`: checks that all block references belong to a non-deleted object version, and purges any orphan block reference (this will then allow the blocks to be garbage-collected)
+
+- `garage repair block-rc`: checks that the reference counters for blocks are in sync with the actual number of non-deleted entries in the block reference table
@@ -9,18 +9,30 @@ a certain capacity, or a gateway node that does not store data and is only
 used as an API entry point for faster cluster access.
 An introduction to building cluster layouts can be found in the [production deployment](@/documentation/cookbook/real-world.md) page.

+In Garage, all of the data that can be stored in a given cluster is divided
+into slices which we call *partitions*. Each partition is stored by
+one or several nodes in the cluster
+(see [`replication_factor`](@/documentation/reference-manual/configuration.md#replication_factor)).
+The layout determines the correspondence between these partitions,
+which exist on a logical level, and actual storage nodes.
+
 ## How cluster layouts work in Garage

-In Garage, a cluster layout is composed of the following components:
+A cluster layout is composed of the following components:

- a table of roles assigned to nodes
+- a table of roles assigned to nodes, defined by the user
+- an optimal assignation of partitions to nodes, computed by an algorithm that is ran once when calling `garage layout apply` or the ApplyClusterLayout API endpoint
 - a version number

 Garage nodes will always use the cluster layout with the highest version number.

 Garage nodes also maintain and synchronize between them a set of proposed role
 changes that haven't yet been applied. These changes will be applied (or
-canceled) in the next version of the layout
+canceled) in the next version of the layout.
+
+All operations on the layout can be realized using the `garage` CLI or using the
+[administration API endpoint](@/documentation/reference-manual/admin-api.md).
+We give here a description of CLI commands, the admin API semantics are very similar.

 The following commands insert modifications to the set of proposed role changes
 for the next layout version (but they do not create the new layout immediately):
@@ -51,7 +63,7 @@ commands will fail otherwise.

 ## Warnings about Garage cluster layout management

-**Warning: never make several calls to `garage layout apply` or `garage layout
+**⚠️ Never make several calls to `garage layout apply` or `garage layout
 revert` with the same value of the `--version` flag. Doing so can lead to the
 creation of several different layouts with the same version number, in which
 case your Garage cluster will become inconsistent until fixed.** If a call to
@@ -65,13 +77,198 @@ shell, you shouldn't have much issues as long as you run commands one after
 the other and take care of checking the output of `garage layout show`
 before applying any changes.

-If you are using the `garage` CLI to script layout changes, follow the following recommendations:
+If you are using the `garage` CLI or the admin API to script layout changes,
+follow the following recommendations:

- Make all of your `garage` CLI calls to the same RPC host. Do not use the
-  `garage` CLI to connect to individual nodes to send them each a piece of the
-  layout changes you are making, as the changes propagate asynchronously
-  between nodes and might not all be taken into account at the time when the
-  new layout is applied.
+- If using the CLI, make all of your `garage` CLI calls to the same RPC host.
+  If using the admin API, make all of your API calls to the same Garage node. Do
+  not connect to individual nodes to send them each a piece of the layout changes
+  you are making, as the changes propagate asynchronously between nodes and might
+  not all be taken into account at the time when the new layout is applied.

- **Only call `garage layout apply` once**, and call it **strictly after** all
-  of the `layout assign` and `layout remove` commands have returned.
+- **Only call `garage layout apply`/ApplyClusterLayout once**, and call it
+  **strictly after** all of the `layout assign` and `layout remove`
+  commands/UpdateClusterLayout API calls have returned.
+
+
+## Understanding unexpected layout calculations
+
+When adding, removing or modifying nodes in a cluster layout, sometimes
+unexpected assignations of partitions to node can occur. These assignations
+are in fact normal and logical, given the objectives of the algorithm.  Indeed,
+**the layout algorithm prioritizes moving less data between nodes over
+achieving equal distribution of load. It also tries to use all links between
+pairs of nodes in equal proportions when moving data.**  This section presents
+two examples and illustrates how one can control Garage's behavior to obtain
+the desired results.
+
+### Example 1
+
+In this example, a cluster is originally composed of 3 nodes in 3 different
+zones (data centers).  The three nodes are of equal capacity, therefore they
+are all fully exploited and all store a copy of all of the data in the cluster.
+
+Then, a fourth node of the same size is added in the datacenter `dc1`.
+As illustrated by the following, **Garage will by default not store any data on the new node**:
+
+```
+$ garage layout show
+==== CURRENT CLUSTER LAYOUT ====
+ID                Tags   Zone  Capacity   Usable capacity
+b10c110e4e854e5a  node1  dc1   1000.0 MB  1000.0 MB (100.0%)
+a235ac7695e0c54d  node2  dc2   1000.0 MB  1000.0 MB (100.0%)
+62b218d848e86a64  node3  dc3   1000.0 MB  1000.0 MB (100.0%)
+
+Zone redundancy: maximum
+
+Current cluster layout version: 6
+
+==== STAGED ROLE CHANGES ====
+ID                Tags   Zone  Capacity
+a11c7cf18af29737  node4  dc1   1000.0 MB
+
+
+==== NEW CLUSTER LAYOUT AFTER APPLYING CHANGES ====
+ID                Tags   Zone  Capacity   Usable capacity
+b10c110e4e854e5a  node1  dc1   1000.0 MB  1000.0 MB (100.0%)
+a11c7cf18af29737  node4  dc1   1000.0 MB  0 B (0.0%)
+a235ac7695e0c54d  node2  dc2   1000.0 MB  1000.0 MB (100.0%)
+62b218d848e86a64  node3  dc3   1000.0 MB  1000.0 MB (100.0%)
+
+Zone redundancy: maximum
+
+==== COMPUTATION OF A NEW PARTITION ASSIGNATION ====
+
+Partitions are replicated 3 times on at least 3 distinct zones.
+
+Optimal partition size:                     3.9 MB (3.9 MB in previous layout)
+Usable capacity / total cluster capacity:   3.0 GB / 4.0 GB (75.0 %)
+Effective capacity (replication factor 3):  1000.0 MB
+
+A total of 0 new copies of partitions need to be transferred.
+
+dc1                 Tags   Partitions        Capacity   Usable capacity
+  b10c110e4e854e5a  node1  256 (0 new)       1000.0 MB  1000.0 MB (100.0%)
+  a11c7cf18af29737  node4  0 (0 new)         1000.0 MB  0 B (0.0%)
+  TOTAL                    256 (256 unique)  2.0 GB     1000.0 MB (50.0%)
+
+dc2                 Tags   Partitions        Capacity   Usable capacity
+  a235ac7695e0c54d  node2  256 (0 new)       1000.0 MB  1000.0 MB (100.0%)
+  TOTAL                    256 (256 unique)  1000.0 MB  1000.0 MB (100.0%)
+
+dc3                 Tags   Partitions        Capacity   Usable capacity
+  62b218d848e86a64  node3  256 (0 new)       1000.0 MB  1000.0 MB (100.0%)
+  TOTAL                    256 (256 unique)  1000.0 MB  1000.0 MB (100.0%)
+```
+
+While unexpected, this is logical because of the following facts:
+
+- storing some data on the new node does not help increase the total quantity
+  of data that can be stored on the cluster, as the two other zones (`dc2` and
+  `dc3`) still need to store a full copy of everything, and their capacity is
+  still the same;
+
+- there is therefore no need to move any data on the new node as this would be pointless;
+
+- moving data to the new node has a cost which the algorithm decides to not pay if not necessary.
+
+This distribution of data can however not be what the administrator wanted: if
+they added a new node to `dc1`, it might be because the existing node is too
+slow, and they wish to divide its load by half. In that case, what they need to
+do to force Garage to distribute the data between the two nodes is to attribute
+only half of the capacity to each node in `dc1` (in our example, 500M instead of 1G).
+In that case, Garage would determine that to be able to store 1G in total, it
+would need to store 500M on the old node and 500M on the added one.
+
+
+### Example 2
+
+The following example is a slightly different scenario, where `dc1` had two
+nodes that were used at 50%, and `dc2` and `dc3` each have one node that is
+100% used. All node capacities are the same.
+
+Then, a node from `dc1` is moved into `dc3`. One could expect that the roles of
+`dc1` and `dc3` would simply be swapped: the remaining node in `dc1` would be
+used at 100%, and the two nodes now in `dc3` would be used at 50%. Instead,
+this happens:
+
+```
+==== CURRENT CLUSTER LAYOUT ====
+ID                Tags   Zone  Capacity   Usable capacity
+b10c110e4e854e5a  node1  dc1   1000.0 MB  500.0 MB (50.0%)
+a11c7cf18af29737  node4  dc1   1000.0 MB  500.0 MB (50.0%)
+a235ac7695e0c54d  node2  dc2   1000.0 MB  1000.0 MB (100.0%)
+62b218d848e86a64  node3  dc3   1000.0 MB  1000.0 MB (100.0%)
+
+Zone redundancy: maximum
+
+Current cluster layout version: 8
+
+==== STAGED ROLE CHANGES ====
+ID                Tags   Zone  Capacity
+a11c7cf18af29737  node4  dc3   1000.0 MB
+
+
+==== NEW CLUSTER LAYOUT AFTER APPLYING CHANGES ====
+ID                Tags   Zone  Capacity   Usable capacity
+b10c110e4e854e5a  node1  dc1   1000.0 MB  1000.0 MB (100.0%)
+a235ac7695e0c54d  node2  dc2   1000.0 MB  1000.0 MB (100.0%)
+62b218d848e86a64  node3  dc3   1000.0 MB  753.9 MB (75.4%)
+a11c7cf18af29737  node4  dc3   1000.0 MB  246.1 MB (24.6%)
+
+Zone redundancy: maximum
+
+==== COMPUTATION OF A NEW PARTITION ASSIGNATION ====
+
+Partitions are replicated 3 times on at least 3 distinct zones.
+
+Optimal partition size:                     3.9 MB (3.9 MB in previous layout)
+Usable capacity / total cluster capacity:   3.0 GB / 4.0 GB (75.0 %)
+Effective capacity (replication factor 3):  1000.0 MB
+
+A total of 128 new copies of partitions need to be transferred.
+
+dc1                 Tags   Partitions        Capacity   Usable capacity
+  b10c110e4e854e5a  node1  256 (128 new)     1000.0 MB  1000.0 MB (100.0%)
+  TOTAL                    256 (256 unique)  1000.0 MB  1000.0 MB (100.0%)
+
+dc2                 Tags   Partitions        Capacity   Usable capacity
+  a235ac7695e0c54d  node2  256 (0 new)       1000.0 MB  1000.0 MB (100.0%)
+  TOTAL                    256 (256 unique)  1000.0 MB  1000.0 MB (100.0%)
+
+dc3                 Tags   Partitions        Capacity   Usable capacity
+  62b218d848e86a64  node3  193 (0 new)       1000.0 MB  753.9 MB (75.4%)
+  a11c7cf18af29737  node4  63 (0 new)        1000.0 MB  246.1 MB (24.6%)
+  TOTAL                    256 (256 unique)  2.0 GB     1000.0 MB (50.0%)
+```
+
+As we can see, the node that was moved to `dc3` (node4) is only used at 25% (approximately),
+whereas the node that was already in `dc3` (node3) is used at 75%.
+
+This can be explained by the following:
+
+- node1 will now be the only node remaining in `dc1`, thus it has to store all
+  of the data in the cluster. Since it was storing only half of it before, it has
+  to retrieve the other half from other nodes in the cluster.
+
+- The data which it does not have is entirely stored by the other node that was
+  in `dc1` and that is now in `dc3` (node4). There is also a copy of it on node2
+  and node3 since both these nodes have a copy of everything.
+
+- node3 and node4 are the two nodes that will now be in a datacenter that is
+ under-utilized (`dc3`), this means that those are the two candidates from which
+ data can be removed to be moved to node1.
+
+- Garage will move data in equal proportions from all possible sources, in this
+  case it means that it will transfer 25% of the entire data set from node3 to
+  node1 and another 25% from node4 to node1.
+
+This explains why node3 ends with 75% utilization (100% from before minus 25%
+that is moved to node1), and node4 ends with 25% (50% from before minus 25%
+that is moved to node1).
+
+This illustrates the second principle of the layout computation: **if there is
+a choice in moving data out of some nodes, then all links between pairs of
+nodes are used in equal proportions** (this is approximately true, there is
+randomness in the algorithm to achieve this so there might be some small
+fluctuations, as we see above).
@@ -21,14 +21,14 @@ data_dir = [
 ```

 Garage will automatically balance all blocks stored by the node
-among the different specified directories, proportionnally to the
+among the different specified directories, proportionally to the
 specified capacities.

 ## Updating the list of storage locations

 If you add new storage locations to your `data_dir`,
 Garage will not rebalance existing data between storage locations.
-Newly written blocks will be balanced proportionnally to the specified capacities,
+Newly written blocks will be balanced proportionally to the specified capacities,
 and existing data may be moved between drives to improve balancing,
 but only opportunistically when a data block is re-written (e.g. an object
 is re-uploaded, or an object with a duplicate block is uploaded).
@@ -40,7 +40,7 @@ First of all, Garage divides the set of all possible block hashes
 in a fixed number of slices (currently 1024), and assigns
 to each slice a primary storage location among the specified data directories.
 The number of slices having their primary location in each data directory
-is proportionnal to the capacity specified in the config file.
+is proportional to the capacity specified in the config file.

 When Garage receives a block to write, it will always write it in the primary
 directory of the slice that contains its hash.
@@ -5,7 +5,7 @@ weight = 40

 Garage is meant to work on old, second-hand hardware.
 In particular, this makes it likely that some of your drives will fail, and some manual intervention will be needed.
-Fear not! For Garage is fully equipped to handle drive failures, in most common cases.
+Fear not! Garage is fully equipped to handle drive failures, in most common cases.

 ## A note on availability of Garage

@@ -61,7 +61,7 @@ garage repair -a --yes blocks

 This will re-synchronize blocks of data that are missing to the new HDD, reading them from copies located on other nodes.

-You can check on the advancement of this process by doing the following command: 
+You can check on the advancement of this process by doing the following command:

 ```bash
 garage stats -a
@@ -108,3 +108,60 @@ garage layout apply   # once satisfied, apply the changes

 Garage will then start synchronizing all required data on the new node.
 This process can be monitored using the `garage stats -a` command.
+
+## Replacement scenario 3: corrupted metadata {#corrupted_meta}
+
+In some cases, your metadata DB file might become corrupted, for instance if
+your node suffered a power outage and did not shut down properly. In this case,
+you can recover without having to change the node ID and rebuilding a cluster
+layout. This means that data blocks will not need to be shuffled around, you
+must simply find a way to repair the metadata file. The best way is generally
+to discard the corrupted file and recover it from another source.
+
+First of all, start by locating the database file in your metadata directory,
+which [depends on your `db_engine`
+choice](@/documentation/reference-manual/configuration.md#db_engine).  Then,
+your recovery options are as follows:
+
+- **Option 1: resyncing from other nodes.** In case your cluster is replicated
+  with two or three copies, you can simply delete the database file, and Garage
+  will resync from other nodes. To do so, stop Garage, delete the database file
+  or directory, and restart Garage. Then, do a full table repair by calling
+  `garage repair -a --yes tables`.  This will take a bit of time to complete as
+  the new node will need to receive copies of the metadata tables from the
+  network.
+
+- **Option 2: restoring a snapshot taken by Garage.** Since v0.9.4, Garage can
+  [automatically take regular
+  snapshots](@/documentation/reference-manual/configuration.md#metadata_auto_snapshot_interval)
+  of your metadata DB file. This file or directory should be located under
+  `<metadata_dir>/snapshots`, and is named according to the UTC time at which it
+  was taken. Stop Garage, discard the database file/directory and replace it by the
+  snapshot you want to use. For instance, in the case of LMDB:
+
+  ```bash
+  cd $METADATA_DIR
+  mv db.lmdb db.lmdb.bak
+  cp -r snapshots/2024-03-15T12:13:52Z db.lmdb
+  ```
+
+  And for Sqlite:
+
+  ```bash
+  cd $METADATA_DIR
+  mv db.sqlite db.sqlite.bak
+  cp snapshots/2024-03-15T12:13:52Z db.sqlite
+  ```
+
+  Then, restart Garage and run a full table repair by calling `garage repair -a
+  --yes tables`.  This should run relatively fast as only the changes that
+  occurred since the snapshot was taken will need to be resynchronized. Of
+  course, if your cluster is not replicated, you will lose all changes that
+  occurred since the snapshot was taken.
+
+- **Option 3: restoring a filesystem-level snapshot.** If you are using ZFS or
+  BTRFS to snapshot your metadata partition, refer to their specific
+  documentation on rolling back or copying files from an old snapshot. 
+  Note that, depending on the properties of the filesystem and of the DB engine,
+  if these snapshots were taken during a write operation to the database, they may
+  also be corrupted and thus unfit for recovery.
@@ -9,7 +9,7 @@ On a new version release, there is 2 possibilities:
  - protocols and data structures remained the same ➡️ this is a **minor upgrade**
  - protocols or data structures changed  ➡️  this is a **major upgrade**

-You can quickly now what type of update you will have to operate by looking at the version identifier:
+You can quickly know what type of update you will have to operate by looking at the version identifier:
 when we require our users to do a major upgrade, we will always bump the first nonzero component of the version identifier
 (e.g. from v0.7.2 to v0.8.0).
 Conversely, for versions that only require a minor upgrade, the first nonzero component will always stay the same (e.g. from v0.8.0 to v0.8.1).
@@ -56,7 +56,7 @@ From a high level perspective, a major upgrade looks like this:
  10. Enable API access (reverse step 1)
  11. Monitor your cluster while load comes back, check that all your applications are happy with this new version

-### Major upgarades with minimal downtime
+### Major upgrades with minimal downtime

 There is only one operation that has to be coordinated cluster-wide: the switch of one version of the internal RPC protocol to the next.
 This means that an upgrade with very limited downtime can simply be performed from one major version to the next by restarting all nodes
@@ -71,7 +71,19 @@ The entire procedure would look something like this:

 2. Take each node offline individually to back up its metadata folder, bring them back online once the backup is done.
  You can do all of the nodes in a single zone at once as that won't impact global cluster availability.
-  Do not try to make a backup of the metadata folder of a running node.
+  Do not try to manually copy the metadata folder of a running node.
+
+  **Since Garage v0.9.4,** you can use the `garage meta snapshot --all` command
+  to take a simultaneous snapshot of the metadata database files of all your
+  nodes.  This avoids the tedious process of having to take them down one by
+  one before upgrading. Be careful that if automatic snapshotting is enabled,
+  Garage only keeps the last two snapshots and deletes older ones, so you might
+  want to disable automatic snapshotting in your upgraded configuration file
+  until you have confirmed that the upgrade ran successfully.  In addition to
+  snapshotting the metadata databases of your nodes, you should back-up at
+  least the `cluster_layout` file of one of your Garage instances (this file
+  should be the same on all nodes and you can copy it safely while Garage is
+  running).

 3. Prepare your binaries and configuration files for the new Garage version

@@ -42,6 +42,13 @@ If a binary of the last version is not available for your architecture,
 or if you want a build customized for your system,
 you can [build Garage from source](@/documentation/cookbook/from-source.md).

+If none of these option work for you, you can also run Garage in a Docker
+container.  When using Docker, the commands used in this guide will not work
+anymore.  We recommend reading the tutorial on [configuring a
+multi-node cluster](@/documentation/cookbook/real-world.md) to learn about
+using Garage as a Docker container. For simplicity, a minimal command to launch
+Garage using Docker is provided in this quick start guide as well.
+

 ## Configuring and starting Garage

@@ -57,9 +64,9 @@ to generate unique and private secrets for security reasons:
 cat > garage.toml <<EOF
 metadata_dir = "/tmp/meta"
 data_dir = "/tmp/data"
-db_engine = "lmdb"
+db_engine = "sqlite"

-replication_mode = "none"
+replication_factor = 1

 rpc_bind_addr = "[::]:3901"
 rpc_public_addr = "127.0.0.1:3901"
@@ -79,14 +86,17 @@ index = "index.html"
 api_bind_addr = "[::]:3904"

 [admin]
-api_bind_addr = "0.0.0.0:3903"
+api_bind_addr = "[::]:3903"
 admin_token = "$(openssl rand -base64 32)"
+metrics_token = "$(openssl rand -base64 32)"
 EOF
 ```

-Now that your configuration file has been created, you can put
-it in the right place. By default, garage looks at **`/etc/garage.toml`.**
+See the [Configuration file format](https://garagehq.deuxfleurs.fr/documentation/reference-manual/configuration/)
+for complete options and values.

+Now that your configuration file has been created, you may save it to the directory of your choice.
+By default, Garage looks for **`/etc/garage.toml`.**
 You can also store it somewhere else, but you will have to specify `-c path/to/garage.toml`
 at each invocation of the `garage` binary (for example: `garage -c ./garage.toml server`, `garage -c ./garage.toml status`).

@@ -103,16 +113,39 @@ your data to be persisted properly.

 ### Launching the Garage server

-Use the following command to launch the Garage server with our configuration file:
+Use the following command to launch the Garage server:

 ```
-garage server
+garage -c path/to/garage.toml server
 ```

-You can tune Garage's verbosity as follows (from less verbose to more verbose):
+If you have placed the `garage.toml` file in `/etc` (its default location), you can simply run `garage server`.

+Alternatively, if you cannot or do not wish to run the Garage binary directly,
+you may use Docker to run Garage in a container using the following command:
+
+```bash
+docker run \
+  -d \
+  --name garaged \
+  -p 3900:3900 -p 3901:3901 -p 3902:3902 -p 3903:3903 \
+  -v /path/to/garage.toml:/etc/garage.toml \
+  -v /path/to/garage/meta:/var/lib/garage/meta \
+  -v /path/to/garage/data:/var/lib/garage/data \
+  dxflrs/garage:v2.2.0
 ```
-RUST_LOG=garage=info garage server
+
+Under Linux, you can substitute `--network host` for `-p 3900:3900 -p 3901:3901 -p 3902:3902 -p 3903:3903`
+
+#### Troubleshooting
+
+Ensure your configuration file, `metadata_dir` and `data_dir`  are readable by the user running the `garage` server or Docker.
+
+You can tune Garage's verbosity by setting the `RUST_LOG=` environment variable. \
+Available log levels are (from less verbose to more verbose): `error`, `warn`, `info` *(default)*, `debug` and `trace`.
+
+```bash
+RUST_LOG=garage=info garage server # default
 RUST_LOG=garage=debug garage server
 RUST_LOG=garage=trace garage server
 ```
@@ -126,7 +159,10 @@ Log level `debug` can help you check why your S3 API calls are not working.
 The `garage` utility is also used as a CLI tool to configure your Garage deployment.
 It uses values from the TOML configuration file to find the Garage daemon running on the
 local node, therefore if your configuration file is not at `/etc/garage.toml` you will
-again have to specify `-c path/to/garage.toml`.
+again have to specify `-c path/to/garage.toml` at each invocation.
+
+If you are running Garage in a Docker container, you can set `alias garage="docker exec -ti <container name> /garage"`
+to use the Garage binary inside your container.

 If the `garage` CLI is able to correctly detect the parameters of your local Garage node,
 the following command should be enough to show the status of your cluster:
@@ -140,30 +176,31 @@ This should show something like this:
 ```
 ==== HEALTHY NODES ====
 ID                 Hostname  Address         Tag                   Zone  Capacity
-563e1ac825ee3323…  linuxbox  127.0.0.1:3901  NO ROLE ASSIGNED
+563e1ac825ee3323   linuxbox  127.0.0.1:3901  NO ROLE ASSIGNED
 ```

 ## Creating a cluster layout

 Creating a cluster layout for a Garage deployment means informing Garage
-of the disk space available on each node of the cluster
-as well as the zone (e.g. datacenter) each machine is located in.
+of the disk space available on each node of the cluster, `-c`,
+as well as the name of the zone (e.g. datacenter), `-z`, each machine is located in.

-For our test deployment, we are using only one node. The way in which we configure
-it does not matter, you can simply write:
+For our test deployment, we are have only one node with zone named `dc1` and a
+capacity of `1G`, though the capacity is ignored for a single node deployment
+and can be changed later when adding new nodes.

 ```bash
-garage layout assign -z dc1 -c 1 <node_id>
+garage layout assign -z dc1 -c 1G <node_id>
 ```

 where `<node_id>` corresponds to the identifier of the node shown by `garage status` (first column).
 You can enter simply a prefix of that identifier.
-For instance here you could write just `garage layout assign -z dc1 -c 1 563e`.
+For instance here you could write just `garage layout assign -z dc1 -c 1G 563e`.

 The layout then has to be applied to the cluster, using:

 ```bash
-garage layout apply
+garage layout apply --version 1
 ```


@@ -248,7 +285,7 @@ garage bucket info nextcloud-bucket
 ```


-## Uploading and downlading from Garage
+## Uploading and downloading from Garage

 To download and upload files on garage, we can use a third-party tool named `awscli`.

@@ -269,12 +306,14 @@ named `~/.awsrc` with this content:
 export AWS_ACCESS_KEY_ID=xxxx      # put your Key ID here
 export AWS_SECRET_ACCESS_KEY=xxxx  # put your Secret key here
 export AWS_DEFAULT_REGION='garage'
-export AWS_ENDPOINT='http://localhost:3900'
+export AWS_ENDPOINT_URL='http://localhost:3900'

-function aws { command aws --endpoint-url $AWS_ENDPOINT $@ ; }
 aws --version
 ```

+Note you need to have at least `awscli` `>=1.29.0` or `>=2.13.0`, otherwise you
+need to specify `--endpoint-url` explicitly on each `awscli` invocation.
+
 Now, each time you want to use `awscli` on this target, run:

 ```bash
@@ -311,7 +350,7 @@ Check [our s3 compatibility list](@/documentation/reference-manual/s3-compatibil

 ### Other tools for interacting with Garage

-The following tools can also be used to send and recieve files from/to Garage:
+The following tools can also be used to send and receive files from/to Garage:

 - [minio-client](@/documentation/connect/cli.md#minio-client) 
 - [s3cmd](@/documentation/connect/cli.md#s3cmd) 
@@ -6,38 +6,167 @@ weight = 40
 The Garage administration API is accessible through a dedicated server whose
 listen address is specified in the `[admin]` section of the configuration
 file (see [configuration file
-reference](@/documentation/reference-manual/configuration.md))
+reference](@/documentation/reference-manual/configuration.md)).

-**WARNING.** At this point, there is no comittement to stability of the APIs described in this document.
-We will bump the version numbers prefixed to each API endpoint at each time the syntax
-or semantics change, meaning that code that relies on these endpoint will break
-when changes are introduced.
+The current version of the admin API is v2.  No breaking changes to the Garage
+administration API will be published outside of a major release.

-The Garage administration API was introduced in version 0.7.2, this document
-does not apply to older versions of Garage.
+History of previous versions:

+ - Before Garage v0.7.2 - no admin API
+ - Garage v0.7.2 - admin API v0
+ - Garage v0.9.0 - admin API v1, deprecate admin API v0
+ - Garage v2.0.0 - admin API v2, deprecate admin API v1

 ## Access control

-The admin API uses two different tokens for acces control, that are specified in the config file's `[admin]` section:
+### Using an API token

- `metrics_token`: the token for accessing the Metrics endpoint (if this token
-  is not set in the config file, the Metrics endpoint can be accessed without
-  access control);
-
- `admin_token`: the token for accessing all of the other administration
-  endpoints (if this token is not set in the config file, access to these
-  endpoints is disabled entirely).
-
-These tokens are used as simple HTTP bearer tokens. In other words, to
-authenticate access to an admin API endpoint, add the following HTTP header
-to your request:
+Administration API tokens tokens are used as simple HTTP bearer tokens. In
+other words, to authenticate access to an admin API endpoint, add the following
+HTTP header to your request:

 ```
 Authorization: Bearer <token>
 ```

-## Administration API endpoints
+### User-defined API tokens
+
+Cluster administrators may dynamically define administration tokens using the CLI commands under `garage admin-token`.
+Such tokens may be limited in scope, meaning that they may enable access to only a subset of API calls.
+They may also have an expiration date to limit their use in time.
+
+Here is an example to create an administration token that is valid for 30 days
+and gives access to only a subset of API calls, allowing it to create buckets
+and access keys and give keys permissions on buckets:
+
+```bash
+$ garage admin-token create --expires-in 30d \
+    --scope ListBuckets,GetBucketInfo,ListKeys,GetKeyInfo,CreateBucket,CreateKey,AllowBucketKey,DenyBucketKey \
+    my-token
+This is your secret bearer token, it will not be shown again by Garage:
+
+  8ed1830b10a276ff57061950.kOSIpxWK9zSGbTO9Xadpv3YndSFWma0_snXcYHaORXk
+
+==== ADMINISTRATION TOKEN INFORMATION ====
+Token ID:    8ed1830b10a276ff57061950
+Token name:  my-token
+Created:     2025-06-15 15:12:44.160 +02:00
+Validity:    valid
+Expiration:  2025-07-15 15:12:44.117 +02:00
+
+Scope:       ListBuckets
+             GetBucketInfo
+             ListKeys
+             GetKeyInfo
+             CreateBucket
+             CreateKey
+             AllowBucketKey
+             DenyBucketKey
+```
+
+When running this command, your token will be shown only once and **will never
+be shown again by Garage**, so make sure to save it directly.  The token is
+hashed internally, and is identified by its prefix (32 hex digits followed by a
+dot) which is saved in clear.
+
+When running `garage admin-token list`, you might see something like this:
+
+```
+ID                        Created     Name                                       Expiration                      Scope
+-                         -           metrics_token (from daemon configuration)  never                           Metrics
+8ed1830b10a276ff57061950  2025-06-15  my-token                                   2025-07-15 15:12:44.117 +02:00  ListBuckets, ... (8)
+```
+
+### Master API tokens
+
+The admin API can also use two different master tokens for access control,
+specified in the config file's `[admin]` section:
+
+- `metrics_token`: the token for accessing the Metrics endpoint. If this token
+  is not set in the config file, the Metrics endpoint can be accessed without
+  access control.
+
+- `admin_token`: the token for accessing all of the other administration
+  endpoints. If this token is not set in the config file, access to these
+  endpoints is only possible with a user-defined admin token.
+
+With the introduction of multiple user-defined admin tokens, the use of master
+API tokens is now discouraged.
+
+
+## Using the admin API
+
+All of the admin API endpoints are described in the OpenAPI specification:
+
+ - APIv2 - [HTML spec](https://garagehq.deuxfleurs.fr/api/garage-admin-v2.html) - [OpenAPI JSON](https://garagehq.deuxfleurs.fr/api/garage-admin-v2.json)
+ - APIv1 (deprecated) - [HTML spec](https://garagehq.deuxfleurs.fr/api/garage-admin-v1.html) - [OpenAPI YAML](https://garagehq.deuxfleurs.fr/api/garage-admin-v1.yml)
+ - APIv0 (deprecated) - [HTML spec](https://garagehq.deuxfleurs.fr/api/garage-admin-v0.html) - [OpenAPI YAML](https://garagehq.deuxfleurs.fr/api/garage-admin-v0.yml)
+
+Making a request to the API from the command line can be as simple as running:
+
+```bash
+curl -H 'Authorization: Bearer s3cr3t' http://localhost:3903/v2/GetClusterStatus | jq
+```
+
+For more advanced use cases, we recommend using an SDK.  
+[Go to the "Build your own app" section to know how to use our SDKs](@/documentation/build/_index.md)
+
+### Making API calls from the `garage` CLI
+
+Since v2.0.0, the `garage` binary provides a subcommand `garage json-api` that
+allows you to invoke the API without making an HTTP request.  This can be
+useful for scripting Garage deployments.
+
+`garage json-api` proxies API calls through Garage's internal RPC protocol,
+therefore it does not require any form of authentication: RPC connection
+parameters are discovered automatically to contact the locally-running Garage
+instance (as when running any other `garage` CLI command).
+
+For simple calls that take no parameters, usage is as follows:
+
+```
+$ garage json-api GetClusterHealth
+{
+  "connectedNodes": 3,
+  "knownNodes": 3,
+  "partitions": 256,
+  "partitionsAllOk": 256,
+  "partitionsQuorum": 256,
+  "status": "healthy",
+  "storageNodes": 3,
+  "storageNodesOk": 3
+}
+```
+
+If you need to specify a JSON body for your call, you can add it directly after
+the name of the function you are calling:
+
+```
+$ garage json-api CreateAdminToken '{"name": "test"}'
+```
+
+Or you can feed it through stdin by adding a `-` as the last command parameter:
+
+```
+$ garage json-api CreateAdminToken -
+{"name": "test"}
+<EOF>
+```
+
+For admin API calls that would have taken query parameters in their HTTP version, these parameters can be passed in the JSON body object:
+
+```
+$ garage json-api GetAdminTokenInfo '{"id":"b0e6e0ace2c0b2aca4cdb2de"}'
+```
+
+For admin API calls that take both query parameters and a JSON body, combine them in the following fashion:
+
+```
+$ garage json-api UpdateAdminToken '{"id":"b0e6e0ace2c0b2aca4cdb2de", "body":{"name":"not a test"}}'
+```
+
+## Special administration API endpoints

 ### Metrics `GET /metrics`

@@ -80,13 +209,13 @@ content-length: 102
 date: Tue, 08 Aug 2023 07:22:38 GMT

 Garage is fully operational
-Consult the full health check API endpoint at /v0/health for more details
+Consult the full health check API endpoint at /v2/GetClusterHealth for more details
 ```

 ### On-demand TLS `GET /check`

-To prevent abuses for on-demand TLS, Caddy developpers have specified an endpoint that can be queried by the reverse proxy
-to know if a given domain is allowed to get a certificate. Garage implements this endpoints to tell if a given domain is handled by Garage or is garbage.
+To prevent abuse for on-demand TLS, Caddy developers have specified an endpoint that can be queried by the reverse proxy
+to know if a given domain is allowed to get a certificate. Garage implements these endpoints to tell if a given domain is handled by Garage or is garbage.

 Garage responds with the following logic:
 - If the domain matches the pattern `<bucket-name>.<s3_api.root_domain>`, returns 200 OK
@@ -99,7 +228,7 @@ You must manually declare the domain in your reverse-proxy. Idem for K2V.*

 *Note 2: buckets in a user's namespace are not supported yet by this endpoint. This is a limitation of this endpoint currently.*

-**Example:** Suppose a Garage instance configured with `s3_api.root_domain = .s3.garage.localhost` and `s3_web.root_domain = .web.garage.localhost`.
+**Example:** Suppose a Garage instance is configured with `s3_api.root_domain = .s3.garage.localhost` and `s3_web.root_domain = .web.garage.localhost`.

 With a private `media` bucket (name in the global namespace, website is disabled), the endpoint will feature the following behavior:

@@ -123,21 +252,7 @@ $ curl -so /dev/null -w "%{http_code}" http://localhost:3903/check?domain=exampl
 200
 ```

-
 **References:**
 - [Using On-Demand TLS](https://caddyserver.com/docs/automatic-https#using-on-demand-tls)
 - [Add option for a backend check to approve use of on-demand TLS](https://github.com/caddyserver/caddy/pull/1939)
 - [Serving tens of thousands of domains over HTTPS with Caddy](https://caddy.community/t/serving-tens-of-thousands-of-domains-over-https-with-caddy/11179)
-
-### Cluster operations
-
-These endpoints are defined on a dedicated [Redocly page](https://garagehq.deuxfleurs.fr/api/garage-admin-v0.html). You can also download its [OpenAPI specification](https://garagehq.deuxfleurs.fr/api/garage-admin-v0.yml).
-
-Requesting the API from the command line can be as simple as running:
-
-```bash
-curl -H 'Authorization: Bearer s3cr3t' http://localhost:3903/v0/status | jq
-```
-
-For more advanced use cases, we recommend using a SDK.  
-[Go to the "Build your own app" section to know how to use our SDKs](@/documentation/build/_index.md)
@@ -8,48 +8,63 @@ weight = 20
 Here is an example `garage.toml` configuration file that illustrates all of the possible options:

 ```toml
+replication_factor = 3
+consistency_mode = "consistent"
+
 metadata_dir = "/var/lib/garage/meta"
 data_dir = "/var/lib/garage/data"
+metadata_snapshots_dir = "/var/lib/garage/snapshots"
 metadata_fsync = true
 data_fsync = false
+disable_scrub = false
+use_local_tz = false
+metadata_auto_snapshot_interval = "6h"

 db_engine = "lmdb"

-block_size = 1048576
-
-sled_cache_capacity = "128MiB"
-sled_flush_every_ms = 2000
+block_size = "1M"
+block_ram_buffer_max = "256MiB"
+block_max_concurrent_reads = 16
+block_max_concurrent_writes_per_request =10
 lmdb_map_size = "1T"

-replication_mode = "3"
-
 compression_level = 1

 rpc_secret = "4425f5c26c5e11581d3223904324dcb5b5d5dfb14e5e7f35e38c595424f5f1e6"
 rpc_bind_addr = "[::]:3901"
+rpc_bind_outgoing = false
 rpc_public_addr = "[fc00:1::1]:3901"
+# or set rpc_public_adr_subnet to filter down autodiscovery to a subnet:
+# rpc_public_addr_subnet = "2001:0db8:f00:b00:/64"
+
+
+allow_world_readable_secrets = false

 bootstrap_peers = [
    "563e1ac825ee3323aa441e72c26d1030d6d4414aeb3dd25287c531e7fc2bc95d@[fc00:1::1]:3901",
-    "86f0f26ae4afbd59aaf9cfb059eefac844951efd5b8caeec0d53f4ed6c85f332[fc00:1::2]:3901",
+    "86f0f26ae4afbd59aaf9cfb059eefac844951efd5b8caeec0d53f4ed6c85f332@[fc00:1::2]:3901",
    "681456ab91350f92242e80a531a3ec9392cb7c974f72640112f90a600d7921a4@[fc00:B::1]:3901",
    "212fd62eeaca72c122b45a7f4fa0f55e012aa5e24ac384a72a3016413fa724ff@[fc00:F::1]:3901",
 ]

+allow_punycode = false

 [consul_discovery]
 api = "catalog"
-consul_http_addr = "http://127.0.0.1:8500"
+consul_http_addr = "https://127.0.0.1:8500"
+tls_skip_verify = false
 service_name = "garage-daemon"
+
 ca_cert = "/etc/consul/consul-ca.crt"
 client_cert = "/etc/consul/consul-client.crt"
 client_key = "/etc/consul/consul-key.crt"
+
 # for `agent` API mode, unset client_cert and client_key, and optionally enable `token`
 # token = "abcdef-01234-56789"
-tls_skip_verify = false
+
 tags = [ "dns-enabled" ]
 meta = { dns-acl = "allow trusted" }
-
+datacenters = ["dc1", "dc2", "dc3"]

 [kubernetes_discovery]
 namespace = "garage"
@@ -65,11 +80,13 @@ root_domain = ".s3.garage"
 [s3_web]
 bind_addr = "[::]:3902"
 root_domain = ".web.garage"
+add_host_to_metrics = true

 [admin]
 api_bind_addr = "0.0.0.0:3903"
-metrics_token = "cacce0b2de4bc2d9f5b5fdff551e01ac1496055aed248202d415398987e35f81"
-admin_token = "ae8cb40ea7368bbdbb6430af11cca7da833d3458a5f52086f4e805a570fb5c2a"
+metrics_token = "BCAdFjoa9G0KJR0WXnHHm7fs1ZAbfpI8iIZ+Z/a2NgI="
+metrics_require_token = true
+admin_token = "UkLeGWEvHnXBqnueR3ISEMWpOnm40jH2tM2HnnL/0F4="
 trace_sink = "http://localhost:4317"
 ```

@@ -77,7 +94,200 @@ The following gives details about each available configuration option.

 ## Available configuration options

-### `metadata_dir`
+### Index
+
+[Environment variables](#env_variables).
+
+Top-level configuration options, in alphabetical order:
+[`allow_punycode`](#allow_punycode),
+[`allow_world_readable_secrets`](#allow_world_readable_secrets),
+[`block_max_concurrent_reads`](#block_max_concurrent_reads),
+[`block_max_concurrent_writes_per_request`](#block_max_concurrent_writes_per_request),
+[`block_ram_buffer_max`](#block_ram_buffer_max),
+[`block_size`](#block_size),
+[`bootstrap_peers`](#bootstrap_peers),
+[`compression_level`](#compression_level),
+[`consistency_mode`](#consistency_mode),
+[`data_dir`](#data_dir),
+[`data_fsync`](#data_fsync),
+[`db_engine`](#db_engine),
+[`disable_scrub`](#disable_scrub),
+[`lmdb_map_size`](#lmdb_map_size),
+[`metadata_auto_snapshot_interval`](#metadata_auto_snapshot_interval),
+[`metadata_dir`](#metadata_dir),
+[`metadata_fsync`](#metadata_fsync),
+[`metadata_snapshots_dir`](#metadata_snapshots_dir),
+[`replication_factor`](#replication_factor),
+[`rpc_bind_addr`](#rpc_bind_addr),
+[`rpc_bind_outgoing`](#rpc_bind_outgoing),
+[`rpc_public_addr`](#rpc_public_addr),
+[`rpc_public_addr_subnet`](#rpc_public_addr_subnet)
+[`rpc_secret`/`rpc_secret_file`](#rpc_secret),
+[`use_local_tz`](#use_local_tz).
+
+The `[consul_discovery]` section:
+[`api`](#consul_api),
+[`ca_cert`](#consul_ca_cert),
+[`client_cert`](#consul_client_cert_and_key),
+[`client_key`](#consul_client_cert_and_key),
+[`consul_http_addr`](#consul_http_addr),
+[`datacenters`](#consul_datacenters)
+[`meta`](#consul_tags_and_meta),
+[`service_name`](#consul_service_name),
+[`tags`](#consul_tags_and_meta),
+[`tls_skip_verify`](#consul_tls_skip_verify),
+[`token`](#consul_token).
+
+
+The `[kubernetes_discovery]` section:
+[`namespace`](#kube_namespace),
+[`service_name`](#kube_service_name),
+[`skip_crd`](#kube_skip_crd).
+
+The `[s3_api]` section:
+[`api_bind_addr`](#s3_api_bind_addr),
+[`root_domain`](#s3_root_domain),
+[`s3_region`](#s3_region).
+
+The `[s3_web]` section:
+[`add_host_to_metrics`](#web_add_host_to_metrics),
+[`bind_addr`](#web_bind_addr),
+[`root_domain`](#web_root_domain).
+
+The `[admin]` section:
+[`api_bind_addr`](#admin_api_bind_addr),
+[`metrics_require_token`](#admin_metrics_require_token),
+[`metrics_token`/`metrics_token_file`](#admin_metrics_token),
+[`admin_token`/`admin_token_file`](#admin_token),
+[`trace_sink`](#admin_trace_sink),
+
+### Environment variables {#env_variables}
+
+The following configuration parameters must be specified as environment variables,
+they do not exist in the configuration file:
+
+- `GARAGE_LOG_TO_SYSLOG` (since `v0.9.4`): set this to `1` or `true` to make the
+  Garage daemon send its logs to `syslog` (using the libc `syslog` function)
+  instead of printing to stderr.
+
+- `GARAGE_LOG_TO_JOURNALD` (since `v1.2.0`): set this to `1` or `true` to make the
+  Garage daemon send its logs to `journald` (using the native protocol of `systemd-journald`)
+  instead of printing to stderr.
+
+The following environment variables can be used to override the corresponding
+values in the configuration file:
+
+- [`GARAGE_ALLOW_WORLD_READABLE_SECRETS`](#allow_world_readable_secrets)
+- [`GARAGE_RPC_SECRET` and `GARAGE_RPC_SECRET_FILE`](#rpc_secret)
+- [`GARAGE_ADMIN_TOKEN` and `GARAGE_ADMIN_TOKEN_FILE`](#admin_token)
+- [`GARAGE_METRICS_TOKEN` and `GARAGE_METRICS_TOKEN`](#admin_metrics_token)
+
+
+### Top-level configuration options
+
+#### `replication_factor` (since `v1.0.0`) {#replication_factor}
+
+The replication factor can be any positive integer smaller or equal the node count in your cluster.
+The chosen replication factor has a big impact on the cluster's failure tolerancy and performance characteristics.
+
+- `1`: data stored on Garage is stored on a single node. There is no
+  redundancy, and data will be unavailable as soon as one node fails or its
+  network is disconnected.  Do not use this for anything else than test
+  deployments.
+
+- `2`: data stored on Garage will be stored on two different nodes, if possible
+  in different zones. Garage tolerates one node failure, or several nodes
+  failing but all in a single zone (in a deployment with at least two zones),
+  before losing data. Data remains available in read-only mode when one node is
+  down, but write operations will fail.
+
+- `3`: data stored on Garage will be stored on three different nodes, if
+  possible each in a different zones.  Garage tolerates two node failure, or
+  several node failures but in no more than two zones (in a deployment with at
+  least three zones), before losing data. As long as only a single node fails,
+  or node failures are only in a single zone, reading and writing data to
+  Garage can continue normally.
+
+- `5`, `7`, ...: When setting the replication factor above 3, it is most useful to
+  choose an uneven value, since for every two copies added, one more node can fail
+  before losing the ability to write and read to the cluster.
+
+Note that in modes `2` and `3`,
+if at least the same number of zones are available, an arbitrary number of failures in
+any given zone is tolerated as copies of data will be spread over several zones.
+
+**Make sure `replication_factor` is the same in the configuration files of all nodes.
+Never run a Garage cluster where that is not the case.**
+
+It is technically possible to change the replication factor although it's a
+dangerous operation that is not officially supported.  This requires you to
+delete the existing cluster layout and create a new layout from scratch,
+meaning that a full rebalancing of your cluster's data will be needed.  To do
+it, shut down your cluster entirely, delete the `custer_layout` files in the
+meta directories of all your nodes, update all your configuration files with
+the new `replication_factor` parameter, restart your cluster, and then create a
+new layout with all the nodes you want to keep.  Rebalancing data will take
+some time, and data might temporarily appear unavailable to your users.
+It is recommended to shut down public access to the cluster while rebalancing
+is in progress.  In theory, no data should be lost as rebalancing is a
+routine operation for Garage, although we cannot guarantee you that everything
+ will go right in such an extreme scenario.
+
+#### `consistency_mode` (since `v1.0.0`) {#consistency_mode}
+
+The consistency mode setting determines the read and write behaviour of your cluster.
+
+  - `consistent`: The default setting. This is what the paragraph above describes.
+    The read and write quorum will be determined so that read-after-write consistency
+    is guaranteed.
+  - `degraded`: Lowers the read
+    quorum to `1`, to allow you to read data from your cluster when several
+    nodes (or nodes in several zones) are unavailable.  In this mode, Garage
+    does not provide read-after-write consistency anymore.
+    The write quorum stays the same as in the `consistent` mode, ensuring that
+    data successfully written to Garage is stored on multiple nodes (depending
+    the replication factor).
+  - `dangerous`: This mode lowers both the read
+    and write quorums to `1`, to allow you to both read and write to your
+    cluster when several nodes (or nodes in several zones) are unavailable.  It
+    is the least consistent mode of operation proposed by Garage, and also one
+    that should probably never be used.
+
+Changing the `consistency_mode` between modes while leaving the `replication_factor` untouched
+(e.g. setting your node's `consistency_mode` to `degraded` when it was previously unset, or from
+`dangerous` to `consistent`), can be done easily by just changing the `consistency_mode`
+parameter in your config files and restarting all your Garage nodes.
+
+The consistency mode can be used together with various replication factors, to achieve
+a wide range of read and write characteristics. Some examples:
+
+  - Replication factor `2`, consistency mode `degraded`: While this mode
+    technically exists, its properties are the same as with consistency mode `consistent`,
+    since the read quorum with replication factor `2`, consistency mode `consistent` is already 1.
+
+  - Replication factor `2`, consistency mode `dangerous`: written objects are written to
+    the second replica asynchronously. This means that Garage will return `200
+    OK` to a PutObject request before the second copy is fully written (or even
+    before it even starts being written).  This means that data can more easily
+    be lost if the node crashes before a second copy can be completed.  This
+    also means that written objects might not be visible immediately in read
+    operations.  In other words, this configuration severely breaks the consistency and
+    durability guarantees of standard Garage cluster operation.  Benefits of
+    this configuration: you can still write to your cluster when one node is
+    unavailable.
+
+The quorums associated with each replication mode are described below:
+
+| `consistency_mode` | `replication_factor` | Write quorum | Read quorum | Read-after-write consistency? |
+| ------------------ | -------------------- | ------------ | ----------- | ----------------------------- |
+| `consistent`       | 1                    | 1            | 1           | yes                           |
+| `consistent`       | 2                    | 2            | 1           | yes                           |
+| `dangerous`        | 2                    | 1            | 1           | NO                            |
+| `consistent`       | 3                    | 2            | 2           | yes                           |
+| `degraded`         | 3                    | 2            | 1           | NO                            |
+| `dangerous`        | 3                    | 1            | 1           | NO                            |
+
+#### `metadata_dir` {#metadata_dir}

 The directory in which Garage will store its metadata. This contains the node identifier,
 the network configuration and the peer list, the list of buckets and keys as well
@@ -85,7 +295,8 @@ as the index of all objects, object version and object blocks.

 Store this folder on a fast SSD drive if possible to maximize Garage's performance.

-### `data_dir`
+
+#### `data_dir` {#data_dir}

 The directory in which Garage will store the data blocks of objects.
 This folder can be placed on an HDD. The space available for `data_dir`
@@ -105,48 +316,89 @@ data_dir = [
 See [the dedicated documentation page](@/documentation/operations/multi-hdd.md)
 on how to operate Garage in such a setup.

-### `db_engine` (since `v0.8.0`)
+#### `metadata_snapshots_dir` (since `v1.1.0`) {#metadata_snapshots_dir}

-By default, Garage uses the Sled embedded database library
-to store its metadata on-disk. Since `v0.8.0`, Garage can use alternative storage backends as follows:
+The directory in which Garage will store metadata snapshots when it
+performs a snapshot of the metadata database, either when instructed to do
+so from a RPC call or regularly through
+[`metadata_auto_snapshot_interval`](#metadata_auto_snapshot_interval).
+
+By default, Garage will store snapshots into a `snapshots/` subdirectory
+of [`metadata_dir`](#metadata_dir). This might quickly fill up your
+metadata storage space if you use snapshots, because Garage will need up
+to 4x the space of the existing metadata database: each snapshot requires
+roughly as much space as the original database, and Garage temporarily
+needs to store up to three different snapshots before it cleans up the oldest
+snapshot to go back to two stored snapshots.
+
+To prevent filling your disk, you might to change this setting to a
+directory with ample available space, e.g. on the same storage space as
+[`data_dir`](#data_dir).
+
+#### `db_engine` (since `v0.8.0`) {#db_engine}
+
+Since `v0.8.0`, Garage can use alternative storage backends as follows:

 | DB engine | `db_engine` value | Database path |
 | --------- | ----------------- | ------------- |
-| [Sled](https://sled.rs) | `"sled"` | `<metadata_dir>/db/` |
-| [LMDB](https://www.lmdb.tech) | `"lmdb"` | `<metadata_dir>/db.lmdb/` |
-| [Sqlite](https://sqlite.org) | `"sqlite"` | `<metadata_dir>/db.sqlite` |
+| [LMDB](https://www.symas.com/lmdb) (since `v0.8.0`, default since `v0.9.0`) | `"lmdb"` | `<metadata_dir>/db.lmdb/` |
+| [Sqlite](https://sqlite.org) (since `v0.8.0`) | `"sqlite"` | `<metadata_dir>/db.sqlite` |
+| [Fjall](https://github.com/fjall-rs/fjall) (**experimental support** since `v1.3.0`/`v2.1.0`) | `"fjall"` | `<metadata_dir>/db.fjall/` |
+| [Sled](https://sled.rs) (old default, removed since `v1.0`) | `"sled"` | `<metadata_dir>/db/` |
+
+Sled was supported until Garage v0.9.x, and was removed in Garage v1.0.
+You can still use an older binary of Garage (e.g. v0.9.4) to migrate
+old Sled metadata databases to another engine.

 Performance characteristics of the different DB engines are as follows:

- Sled: the default database engine, which tends to produce
-  large data files and also has performance issues, especially when the metadata folder
-  is on a traditional HDD and not on SSD.
- LMDB: the recommended alternative on 64-bit systems,
-  much more space-efficiant and slightly faster. Note that the data format of LMDB is not portable
-  between architectures, so for instance the Garage database of an x86-64
-  node cannot be moved to an ARM64 node. Also note that, while LMDB can technically be used on 32-bit systems,
-  this will limit your node to very small database sizes due to how LMDB works; it is therefore not recommended.
- Sqlite: Garage supports Sqlite as a storage backend for metadata,
-  however it may have issues and is also very slow in its current implementation,
-  so it is not recommended to be used for now.
+- **LMDB:** the recommended database engine for high-performance distributed clusters
+  with `replication_factor` ≥ 2.
+  LMDB works well, but is known to have the following limitations:

-It is possible to convert Garage's metadata directory from one format to another with a small utility named `convert_db`,
-which can be downloaded at the following locations:
-[for amd64](https://garagehq.deuxfleurs.fr/_releases/convert_db/amd64/convert_db),
-[for i386](https://garagehq.deuxfleurs.fr/_releases/convert_db/i386/convert_db),
-[for arm64](https://garagehq.deuxfleurs.fr/_releases/convert_db/arm64/convert_db),
-[for arm](https://garagehq.deuxfleurs.fr/_releases/convert_db/arm/convert_db).
-The `convert_db` utility is used as folows:
+  - LMDB is prone to database corruption after an unclean shutdown (e.g. a process kill
+    or a power outage).  It is recommended to configure
+    [`metadata_auto_snapshot_interval`](#metadata_auto_snapshot_interval) to be
+    able to easily recover from this situation. With `replication_factor` ≥ 2,
+    metadata can also be reconstructed from remote nodes upon corruption
+    (see [Recovering from failures](@/documentation/operations/recovering.md#corrupted_meta)).
+
+  - The data format of LMDB is not portable between architectures, so for
+    instance the Garage database of an x86-64 node cannot be moved to an ARM64
+    node.
+
+  - While LMDB can technically be used on 32-bit systems, this will limit your
+    node to very small database sizes due to how LMDB works; it is therefore
+    not recommended.
+
+  - Keys in LMDB are limited to 511 bytes. This limit translates to limits on
+    object keys in S3 and sort keys in K2V that are limited to 479 bytes.
+
+- **Sqlite:** Garage supports Sqlite as an alternative storage backend for
+  metadata, which does not have the issues listed above for LMDB.  Sqlite is
+  slower than LMDB, so it is not the best choice for high-performance storage
+  clusters.
+
+- **Fjall:** a storage engine based on LSM trees, which theoretically allow for
+  higher write throughput than other storage engines that are based on B-trees.
+  Using Fjall could potentially improve Garage's performance significantly in
+  write-heavy workloads. **Support for Fjall is experimental at this point**,
+  we have added it to Garage for evaluation purposes only. **Use it only with
+  test data, and report any issues to our bug tracker. Do not use it for
+  production workloads.**
+
+It is possible to convert Garage's metadata directory from one format to another
+using the `garage convert-db` command, which should be used as follows:

 ```
-convert-db -a <input db engine> -i <input db path> \
-  		   -b <output db engine> -o <output db path>
+garage convert-db -a <input db engine> -i <input db path> \
+                  -b <output db engine> -o <output db path>
 ```

-Make sure to specify the full database path as presented in the table above,
-and not just the path to the metadata directory.
+Make sure to specify the full database path as presented in the table above
+(third column), and not just the path to the metadata directory.

-### `metadata_fsync`
+#### `metadata_fsync` {#metadata_fsync}

 Whether to enable synchronous mode for the database engine or not.
 This is disabled (`false`) by default.
@@ -160,7 +412,7 @@ Using this option reduces the risk of simultaneous metadata corruption on severa
 cluster nodes, which could lead to data loss.

 If multi-site replication is used, this option is most likely not necessary, as
-it is extremely unlikely that two nodes in different locations will have a 
+it is extremely unlikely that two nodes in different locations will have a
 power failure at the exact same time.

 (Metadata corruption on a single node is not an issue, the corrupted data file
@@ -170,13 +422,13 @@ Here is how this option impacts the different database engines:

 | Database | `metadata_fsync = false` (default) | `metadata_fsync = true`       |
 |----------|------------------------------------|-------------------------------|
-| Sled     | default options                    | *unsupported*                 |
 | Sqlite   | `PRAGMA synchronous = OFF`         | `PRAGMA synchronous = NORMAL` |
 | LMDB     | `MDB_NOMETASYNC` + `MDB_NOSYNC`    | `MDB_NOMETASYNC`              |
+| Fjall    | default options                    | not supported                 |

 Note that the Sqlite database is always ran in `WAL` mode (`PRAGMA journal_mode = WAL`).

-### `data_fsync`
+#### `data_fsync` {#data_fsync}

 Whether to `fsync` data blocks and their containing directory after they are
 saved to disk.
@@ -186,10 +438,60 @@ This might reduce the risk that a data block is lost in rare
 situations such as simultaneous node losing power,
 at the cost of a moderate drop in write performance.

-Similarly to `metatada_fsync`, this is likely not necessary
+Similarly to `metadata_fsync`, this is likely not necessary
 if geographical replication is used.

-### `block_size`
+#### `metadata_auto_snapshot_interval` (since `v0.9.4`) {#metadata_auto_snapshot_interval}
+
+If this value is set, Garage will automatically take a snapshot of the metadata
+DB file at a regular interval and save it in the metadata directory,
+or in [`metadata_snapshots_dir`](#metadata_snapshots_dir) if it is set.
+This parameter can take any duration string that can be parsed by
+the [`parse_duration`](https://docs.rs/parse_duration/latest/parse_duration/#syntax) crate.
+
+Snapshots can allow to recover from situations where the metadata DB file is
+corrupted, for instance after an unclean shutdown.  See [this
+page](@/documentation/operations/recovering.md#corrupted_meta) for details.
+Garage keeps only the two most recent snapshots of the metadata DB and deletes
+older ones automatically.
+You can also create metadata snapshots manually at any point using the
+`garage meta snapshot` command.
+
+Using snapshots created by Garage is the best option to make snapshots of your
+node's metadata for potential recovery, as they are guaranteed to be clean and
+consistent, contrarily to filesystem-level snapshots that may be taken while
+some writes are in-flight and thus might be corrupted.
+
+Note that taking a metadata snapshot is a relatively intensive operation as the
+entire data file is copied. A snapshot being taken might have performance
+impacts on the Garage node while it is running. If the cluster is under heavy
+write load when a snapshot operation is running, this might also cause the
+database file to grow in size significantly as pages cannot be recycled easily.
+
+#### `disable_scrub` {#disable_scrub}
+
+By default, Garage runs a scrub of the data directory approximately once per
+month, with a random delay to avoid all nodes running at the same time.  When
+it scrubs the data directory, Garage will read all of the data files stored on
+disk to check their integrity, and will rebuild any data files that it finds
+corrupted, using the remaining valid copies stored on other nodes.
+See [this page](@/documentation/operations/durability-repairs.md#scrub) for details.
+
+Set the `disable_scrub` configuration value to `true` if you don't need Garage
+to scrub the data directory, for instance if you are already scrubbing at the
+filesystem level. Note that in this case, if you find a corrupted data file,
+you should delete it from the data directory and then call `garage repair
+blocks` on the node to ensure that it re-obtains a copy from another node on
+the network.
+
+#### `use_local_tz` (since `v1.1.0`) {#use_local_tz}
+
+By default, Garage runs the lifecycle worker every day at midnight in UTC. Set the
+`use_local_tz` configuration value to `true` if you want Garage to run the
+lifecycle worker at midnight in your local timezone. If you have multiple nodes,
+you should also ensure that each node has the same timezone configuration.
+
+#### `block_size` {#block_size}

 Garage splits stored objects in consecutive chunks of size `block_size`
 (except the last one which might be smaller). The default size is 1MiB and
@@ -204,22 +506,69 @@ files will remain available. This however means that chunks from existing files
 will not be deduplicated with chunks from newly uploaded files, meaning you
 might use more storage space that is optimally possible.

-### `sled_cache_capacity`
+#### `block_ram_buffer_max` (since `v0.9.4`) {#block_ram_buffer_max}

-This parameter can be used to tune the capacity of the cache used by
-[sled](https://sled.rs), the database Garage uses internally to store metadata.
-Tune this to fit the RAM you wish to make available to your Garage instance.
-This value has a conservative default (128MB) so that Garage doesn't use too much
-RAM by default, but feel free to increase this for higher performance.
+A limit on the total size of data blocks kept in RAM by S3 API nodes awaiting
+to be sent to storage nodes asynchronously.

-### `sled_flush_every_ms`
+Explanation: since Garage wants to tolerate node failures, it uses quorum
+writes to send data blocks to storage nodes: try to write the block to three
+nodes, and return ok as soon as two writes complete. So even if all three nodes
+are online, the third write always completes asynchronously.  In general, there
+are not many writes to a cluster, and the third asynchronous write can
+terminate early enough so as to not cause unbounded RAM growth.  However, if
+the S3 API node is continuously receiving large quantities of data and the
+third node is never able to catch up, many data blocks will be kept buffered in
+RAM as they are awaiting transfer to the third node.

-This parameters can be used to tune the flushing interval of sled.
-Increase this if sled is thrashing your SSD, at the risk of losing more data in case
-of a power outage (though this should not matter much as data is replicated on other
-nodes). The default value, 2000ms, should be appropriate for most use cases.
+The `block_ram_buffer_max` sets a limit to the size of buffers that can be kept
+in RAM in this process.  When the limit is reached, backpressure is applied
+back to the S3 client.

-### `lmdb_map_size`
+Note that this only counts buffers that have arrived to a certain stage of
+processing (received from the client + encrypted and/or compressed as
+necessary) and are ready to send to the storage nodes. Many other buffers will
+not be counted and this is not a hard limit on RAM consumption.  In particular,
+if many clients send requests simultaneously with large objects, the RAM
+consumption will always grow linearly with the number of concurrent requests,
+as each request will use a few buffers of size `block_size` for receiving and
+intermediate processing before even trying to send the data to the storage
+node.
+
+The default value is 256MiB.
+
+#### `block_max_concurrent_reads` (since `v1.3.0` / `v2.1.0`) {#block_max_concurrent_reads}
+
+The maximum number of blocks (individual files in the data directory) open
+simultaneously for reading.
+
+Reducing this number does not limit the number of data blocks that can be
+transferred through the network simultaneously. This mechanism was just added
+as a backpressure mechanism for HDD read speed: it helps avoid a situation
+where too many requests are coming in and Garage is reading too many block
+files simultaneously, thus not making timely progress on any of the reads.
+
+When a request to read a data block comes in through the network, the requests
+awaits for one of the `block_max_concurrent_reads` slots to be available
+(internally implemented using a Semaphore object). Once it acquired a read
+slot, it reads the entire block file to RAM and frees the slot as soon as the
+block file is finished reading. Only after the slot is released will the
+block's data start being transferred over the network.  If the request fails to
+acquire a reading slot within 15 seconds, it fails with a timeout error.
+Timeout events can be monitored through the `block_read_semaphore_timeouts`
+metric in Prometheus: a non-zero number of such events indicates an I/O
+bottleneck on HDD read speed.
+
+
+#### `block_max_concurrent_writes_per_request` (since `v1.3.1` / `v2.2.0`) {#block_max_concurrent_writes_per_request}
+
+This parameter is designed to adapt to the concurrent write performance of 
+different storage media. Maximum number of parallel block writes per put request.
+Higher values may improve throughput but increase memory usage.
+
+Default value: 3. Recommended values: 10-30 for NVMe, 3-10 for spinning HDD.
+
+#### `lmdb_map_size` {#lmdb_map_size}

 This parameters can be used to set the map size used by LMDB,
 which is the size of the virtual memory region used for mapping the database file.
@@ -227,90 +576,7 @@ The value of this parameter is the maximum size the metadata database can take.
 This value is not bound by the physical RAM size of the machine running Garage.
 If not specified, it defaults to 1GiB on 32-bit machines and 1TiB on 64-bit machines.

-### `replication_mode`
-
-Garage supports the following replication modes:
-
- `none` or `1`: data stored on Garage is stored on a single node. There is no
-  redundancy, and data will be unavailable as soon as one node fails or its
-  network is disconnected.  Do not use this for anything else than test
-  deployments.
-
- `2`: data stored on Garage will be stored on two different nodes, if possible
-  in different zones. Garage tolerates one node failure, or several nodes
-  failing but all in a single zone (in a deployment with at least two zones),
-  before losing data. Data remains available in read-only mode when one node is
-  down, but write operations will fail.
-
-  - `2-dangerous`: a variant of mode `2`, where written objects are written to
-    the second replica asynchronously. This means that Garage will return `200
-    OK` to a PutObject request before the second copy is fully written (or even
-    before it even starts being written).  This means that data can more easily
-    be lost if the node crashes before a second copy can be completed.  This
-    also means that written objects might not be visible immediately in read
-    operations.  In other words, this mode severely breaks the consistency and
-    durability guarantees of standard Garage cluster operation.  Benefits of
-    this mode: you can still write to your cluster when one node is
-    unavailable.
-
- `3`: data stored on Garage will be stored on three different nodes, if
-  possible each in a different zones.  Garage tolerates two node failure, or
-  several node failures but in no more than two zones (in a deployment with at
-  least three zones), before losing data. As long as only a single node fails,
-  or node failures are only in a single zone, reading and writing data to
-  Garage can continue normally.
-
-  - `3-degraded`: a variant of replication mode `3`, that lowers the read
-    quorum to `1`, to allow you to read data from your cluster when several
-    nodes (or nodes in several zones) are unavailable.  In this mode, Garage
-    does not provide read-after-write consistency anymore.  The write quorum is
-    still 2, ensuring that data successfully written to Garage is stored on at
-    least two nodes.
-
-  - `3-dangerous`: a variant of replication mode `3` that lowers both the read
-    and write quorums to `1`, to allow you to both read and write to your
-    cluster when several nodes (or nodes in several zones) are unavailable.  It
-    is the least consistent mode of operation proposed by Garage, and also one
-    that should probably never be used.
-
-Note that in modes `2` and `3`,
-if at least the same number of zones are available, an arbitrary number of failures in
-any given zone is tolerated as copies of data will be spread over several zones.
-
-**Make sure `replication_mode` is the same in the configuration files of all nodes.
-Never run a Garage cluster where that is not the case.**
-
-The quorums associated with each replication mode are described below:
-
-| `replication_mode` | Number of replicas | Write quorum | Read quorum | Read-after-write consistency? |
-| ------------------ | ------------------ | ------------ | ----------- | ----------------------------- |
-| `none` or `1`      | 1                  | 1            | 1           | yes                           |
-| `2`                | 2                  | 2            | 1           | yes                           |
-| `2-dangerous`      | 2                  | 1            | 1           | NO                            |
-| `3`                | 3                  | 2            | 2           | yes                           |
-| `3-degraded`       | 3                  | 2            | 1           | NO                            |
-| `3-dangerous`      | 3                  | 1            | 1           | NO                            |
-
-Changing the `replication_mode` between modes with the same number of replicas
-(e.g. from `3` to `3-degraded`, or from `2-dangerous` to `2`), can be done easily by
-just changing the `replication_mode` parameter in your config files and restarting all your
-Garage nodes.
-
-It is also technically possible to change the replication mode to a mode with a
-different numbers of replicas, although it's a dangerous operation that is not
-officially supported.  This requires you to delete the existing cluster layout
-and create a new layout from scratch, meaning that a full rebalancing of your
-cluster's data will be needed.  To do it, shut down your cluster entirely,
-delete the `custer_layout` files in the meta directories of all your nodes,
-update all your configuration files with the new `replication_mode` parameter,
-restart your cluster, and then create a new layout with all the nodes you want
-to keep.  Rebalancing data will take some time, and data might temporarily
-appear unavailable to your users.  It is recommended to shut down public access
-to the cluster while rebalancing is in progress.  In theory, no data should be
-lost as rebalancing is a routine operation for Garage, although we cannot
-guarantee you that everything will go right in such an extreme scenario.
-
-### `compression_level`
+#### `compression_level` {#compression_level}

 Zstd compression level to use for storing blocks.

@@ -334,7 +600,7 @@ Compression is done synchronously, setting a value too high will add latency to
 This value can be different between nodes, compression is done by the node which receive the
 API call.

-### `rpc_secret`, `rpc_secret_file` or `GARAGE_RPC_SECRET` (env)
+#### `rpc_secret`, `rpc_secret_file` or `GARAGE_RPC_SECRET`, `GARAGE_RPC_SECRET_FILE` (env) {#rpc_secret}

 Garage uses a secret key, called an RPC secret, that is shared between all
 nodes of the cluster in order to identify these nodes and allow them to
@@ -346,23 +612,45 @@ Since Garage `v0.8.2`, the RPC secret can also be stored in a file whose path is
 given in the configuration variable `rpc_secret_file`, or specified as an
 environment variable `GARAGE_RPC_SECRET`.

-### `rpc_bind_addr`
+Since Garage `v0.8.5` and `v0.9.1`, you can also specify the path of a file
+storing the secret as the `GARAGE_RPC_SECRET_FILE` environment variable.

-The address and port on which to bind for inter-cluster communcations
-(reffered to as RPC for remote procedure calls).
+#### `rpc_bind_addr` {#rpc_bind_addr}
+
+The address and port on which to bind for inter-cluster communications
+(referred to as RPC for remote procedure calls).
 The port specified here should be the same one that other nodes will used to contact
 the node, even in the case of a NAT: the NAT should be configured to forward the external
-port number to the same internal port nubmer. This means that if you have several nodes running
+port number to the same internal port number. This means that if you have several nodes running
 behind a NAT, they should each use a different RPC port number.

-### `rpc_public_addr`
+#### `rpc_bind_outgoing` (since `v0.9.2`) {#rpc_bind_outgoing}
+
+If enabled, pre-bind all sockets for outgoing connections to the same IP address
+used for listening (the IP address specified in `rpc_bind_addr`) before
+trying to connect to remote nodes.
+This can be necessary if a node has multiple IP addresses,
+but only one is allowed or able to reach the other nodes,
+for instance due to firewall rules or specific routing configuration.
+
+Disabled by default.
+
+#### `rpc_public_addr` {#rpc_public_addr}

 The address and port that other nodes need to use to contact this node for
 RPC calls.  **This parameter is optional but recommended.** In case you have
 a NAT that binds the RPC port to a port that is different on your public IP,
 this field might help making it work.

-### `bootstrap_peers`
+#### `rpc_public_addr_subnet` {#rpc_public_addr_subnet}
+In case `rpc_public_addr` is not set, but autodiscovery is used, this allows
+filtering the list of automatically discovered IPs to a specific subnet.
+
+For example, if nodes should pick *their* IP inside a specific subnet, but you
+don't want to explicitly write the IP down (as it's dynamic, or you want to
+share configs across nodes), you can use this option.
+
+#### `bootstrap_peers` {#bootstrap_peers}

 A list of peer identifiers on which to contact other Garage peers of this cluster.
 These peer identifiers have the following syntax:
@@ -378,43 +666,61 @@ be obtained by running `garage node id` and then included directly in the
 key will be returned by `garage node id` and you will have to add the IP
 yourself.

+#### `allow_world_readable_secrets` or `GARAGE_ALLOW_WORLD_READABLE_SECRETS` (env) {#allow_world_readable_secrets}

-## The `[consul_discovery]` section
+Garage checks the permissions of your secret files to make sure they're not
+world-readable. In some cases, the check might fail and consider your files as
+world-readable even if they're not, for instance when using Posix ACLs.
+
+Setting `allow_world_readable_secrets` to `true` bypass this
+permission verification.
+
+Alternatively, you can set the `GARAGE_ALLOW_WORLD_READABLE_SECRETS`
+environment variable to `true` to bypass the permissions check.
+
+#### `allow_punycode` {#allow_punycode}
+
+Allow creating buckets with names containing punycode. When used for buckets served
+as websites, this allows using almost any unicode character in the domain name.
+
+Default to `false`.
+
+### The `[consul_discovery]` section

 Garage supports discovering other nodes of the cluster using Consul.  For this
 to work correctly, nodes need to know their IP address by which they can be
 reached by other nodes of the cluster, which should be set in `rpc_public_addr`.

-### `consul_http_addr` and `service_name`
+#### `consul_http_addr` {#consul_http_addr}

 The `consul_http_addr` parameter should be set to the full HTTP(S) address of the Consul server.

-### `api`
+#### `api` {#consul_api}

 Two APIs for service registration are supported: `catalog`  and `agent`. `catalog`, the default, will register a service using
 the `/v1/catalog` endpoints, enabling mTLS if `client_cert` and `client_key` are provided. The `agent` API uses the
 `v1/agent` endpoints instead, where an optional `token` may be provided.

-### `service_name`
+#### `service_name` {#consul_service_name}

 `service_name` should be set to the service name under which Garage's
 RPC ports are announced.

-### `client_cert`, `client_key`
+#### `client_cert`, `client_key` {#consul_client_cert_and_key}

 TLS client certificate and client key to use when communicating with Consul over TLS. Both are mandatory when doing so.
 Only available when `api = "catalog"`.

-### `ca_cert`
+#### `ca_cert` {#consul_ca_cert}

 TLS CA certificate to use when communicating with Consul over TLS.

-### `tls_skip_verify`
+#### `tls_skip_verify` {#consul_tls_skip_verify}

 Skip server hostname verification in TLS handshake.
 `ca_cert` is ignored when this is set.

-### `token`
+#### `token` {#consul_token}

 Uses the provided token for communication with Consul. Only available when `api = "agent"`.
 The policy assigned to this token should at least have these rules:
@@ -434,70 +740,86 @@ node_prefix "" {
 }
 ```

-### `tags` and `meta`
+
+#### `datacenters` {#consul_datacenters}
+
+Optional list of datacenters that allow garage to do service discovery when Consul is configured in WAN federation.
+
+Example: `datacenters = ["dc1", "dc2", "dc3"]`
+
+In a WAN configuration, by default the Consul services API only responds with
+local LAN services.  When a list of datacenters is specified using this option,
+Garage will query the consul server API by datacenter directly, allowing for
+Garage to discover nodes across the Consul WAN.
+
+#### `tags` and `meta` {#consul_tags_and_meta}

 Additional list of tags and map of service meta to add during service registration.

-## The `[kubernetes_discovery]` section
+### The `[kubernetes_discovery]` section

 Garage supports discovering other nodes of the cluster using kubernetes custom
 resources. For this to work, a `[kubernetes_discovery]` section must be present
 with at least the `namespace` and `service_name` parameters.

-### `namespace`
+#### `namespace` {#kube_namespace}

 `namespace` sets the namespace in which the custom resources are
 configured.

-### `service_name`
+#### `service_name` {#kube_service_name}

 `service_name` is added as a label to the advertised resources to
 filter them, to allow for multiple deployments in a single namespace.

-### `skip_crd`
+#### `skip_crd` {#kube_skip_crd}

 `skip_crd` can be set to true to disable the automatic creation and
 patching of the `garagenodes.deuxfleurs.fr` CRD. You will need to create the CRD
 manually.


-## The `[s3_api]` section
+### The `[s3_api]` section

-### `api_bind_addr`
+#### `api_bind_addr` {#s3_api_bind_addr}

 The IP and port on which to bind for accepting S3 API calls.
-This endpoint does not suport TLS: a reverse proxy should be used to provide it.
+This endpoint does not support TLS: a reverse proxy should be used to provide it.

-### `s3_region`
+Alternatively, since `v0.8.5`, a path can be used to create a unix socket with 0222 mode.

-Garage will accept S3 API calls that are targetted to the S3 region defined here.
-API calls targetted to other regions will fail with a AuthorizationHeaderMalformed error
+#### `s3_region` {#s3_region}
+
+Garage will accept S3 API calls that are targeted to the S3 region defined here.
+API calls targeted to other regions will fail with a AuthorizationHeaderMalformed error
 message that redirects the client to the correct region.

-### `root_domain` {#root_domain}
+#### `root_domain` {#s3_root_domain}

 The optional suffix to access bucket using vhost-style in addition to path-style request.
 Note path-style requests are always enabled, whether or not vhost-style is configured.
 Configuring vhost-style S3 required a wildcard DNS entry, and possibly a wildcard TLS certificate,
-but might be required by softwares not supporting path-style requests.
+but might be required by software not supporting path-style requests.

 If `root_domain` is `s3.garage.eu`, a bucket called `my-bucket` can be interacted with
 using the hostname `my-bucket.s3.garage.eu`.



-## The `[s3_web]` section
+### The `[s3_web]` section

 Garage allows to publish content of buckets as websites. This section configures the
 behaviour of this module.

-### `bind_addr`
+#### `bind_addr` {#web_bind_addr}

 The IP and port on which to bind for accepting HTTP requests to buckets configured
 for website access.
-This endpoint does not suport TLS: a reverse proxy should be used to provide it.
+This endpoint does not support TLS: a reverse proxy should be used to provide it.

-### `root_domain`
+Alternatively, since `v0.8.5`, a path can be used to create a unix socket with 0222 mode.
+
+#### `root_domain` {#web_root_domain}

 The optional suffix appended to bucket names for the corresponding HTTP Host.

@@ -505,40 +827,71 @@ For instance, if `root_domain` is `web.garage.eu`, a bucket called `deuxfleurs.f
 will be accessible either with hostname `deuxfleurs.fr.web.garage.eu`
 or with hostname `deuxfleurs.fr`.

+#### `add_host_to_metrics` {#web_add_host_to_metrics}

-## The `[admin]` section
+Whether to include the requested domain name (HTTP `Host` header) in the
+Prometheus metrics of the web endpoint. This is disabled by default as the
+number of possible values is not bounded and can be a source of cardinality
+explosion in the exported metrics.
+
+
+### The `[admin]` section

 Garage has a few administration capabilities, in particular to allow remote monitoring. These features are detailed below.

-### `api_bind_addr`
+#### `api_bind_addr` {#admin_api_bind_addr}

 If specified, Garage will bind an HTTP server to this port and address, on
 which it will listen to requests for administration features.
 See [administration API reference](@/documentation/reference-manual/admin-api.md) to learn more about these features.

-### `metrics_token`, `metrics_token_file` or `GARAGE_METRICS_TOKEN` (env)
+Alternatively, since `v0.8.5`, a path can be used to create a unix socket. Note that for security reasons,
+the socket will have 0220 mode. Make sure to set user and group permissions accordingly.

-The token for accessing the Metrics endpoint. If this token is not set, the
-Metrics endpoint can be accessed without access control.
+#### `admin_token`, `admin_token_file` or `GARAGE_ADMIN_TOKEN`, `GARAGE_ADMIN_TOKEN_FILE` (env) {#admin_token}

-You can use any random string for this value. We recommend generating a random token with `openssl rand -hex 32`.
+The token for accessing all administration functions on the admin endpoint,
+with the exception of the metrics endpoint (see `metrics_token`).

-`metrics_token` was introduced in Garage `v0.7.2`.
-`metrics_token_file` and the `GARAGE_METRICS_TOKEN` environment variable are supported since Garage `v0.8.2`.
+You can use any random string for this value. We recommend generating a random
+token with `openssl rand -base64 32`.

+For Garage version earlier than `v2.0`, if this token is not set,
+access to these endpoints is disabled entirely.

-### `admin_token`, `admin_token_file` or `GARAGE_ADMIN_TOKEN` (env)
-
-The token for accessing all of the other administration endpoints.  If this
-token is not set, access to these endpoints is disabled entirely.
-
-You can use any random string for this value. We recommend generating a random token with `openssl rand -hex 32`.
+Since Garage `v2.0`, additional admin API tokens can be defined dynamically
+in your Garage cluster using administration commands. This new admin token system
+is more flexible since it allows admin tokens to have an expiration date,
+and to have a scope restricted to certain admin API functions. If `admin_token`
+is set, it behaves as an admin token without expiration and with full scope.
+Otherwise, only admin API tokens defined dynamically can be used.

 `admin_token` was introduced in Garage `v0.7.2`.
 `admin_token_file` and the `GARAGE_ADMIN_TOKEN` environment variable are supported since Garage `v0.8.2`.

+`GARAGE_ADMIN_TOKEN_FILE` is supported since `v0.8.5` / `v0.9.1`.

-### `trace_sink`
+#### `metrics_token`, `metrics_token_file` or `GARAGE_METRICS_TOKEN`, `GARAGE_METRICS_TOKEN_FILE` (env) {#admin_metrics_token}
+
+The token for accessing the Prometheus metrics endpoint (`/metrics`).
+If this token is not set, and unless `metrics_require_token` is set to `true`,
+the metrics endpoint can be accessed without access control.
+
+You can use any random string for this value. We recommend generating a random token with `openssl rand -base64 32`.
+
+`metrics_token` was introduced in Garage `v0.7.2`.
+`metrics_token_file` and the `GARAGE_METRICS_TOKEN` environment variable are supported since Garage `v0.8.2`.
+
+`GARAGE_METRICS_TOKEN_FILE` is supported since `v0.8.5` / `v0.9.1`.
+
+#### `metrics_require_token` (since `v2.0.0`) {#admin_metrics_require_token}
+
+If this is set to `true`, accessing the metrics endpoint will always require
+an access token. Valid tokens include the `metrics_token` if it is set,
+and admin API token defined dynamically in Garage which have
+the `Metrics` endpoint in their scope.
+
+#### `trace_sink` {#admin_trace_sink}

 Optionally, the address of an OpenTelemetry collector.  If specified,
 Garage will send traces in the OpenTelemetry format to this endpoint. These
@@ -37,6 +37,21 @@ A Garage cluster can very easily evolve over time, as storage nodes are added or
 Garage will automatically rebalance data between nodes as needed to ensure the desired number of copies.
 Read about cluster layout management [here](@/documentation/operations/layout.md).

+### Several replication modes
+
+Garage supports a variety of replication modes, with configurable replica count,
+and with various levels of consistency, in order to adapt to a variety of usage scenarios.
+Read our reference page on [supported replication modes](@/documentation/reference-manual/configuration.md#replication_factor)
+to select the replication mode best suited to your use case (hint: in most cases, `replication_factor = 3` is what you want).
+
+### Compression and deduplication
+
+All data stored in Garage is deduplicated, and optionally compressed using
+Zstd.  Objects uploaded to Garage are chunked in blocks of constant sizes (see
+[`block_size`](@/documentation/reference-manual/configuration.md#block_size)),
+and the hashes of individual blocks are used to dispatch them to storage nodes
+and to deduplicate them.
+
 ### No RAFT slowing you down

 It might seem strange to tout the absence of something as a desirable feature,
@@ -46,14 +61,7 @@ directed to a Garage cluster can be handled independently of one another instead
 of going through a central bottleneck (the leader node).
 As a consequence, requests can be handled much faster, even in cases where latency
 between cluster nodes is important (see our [benchmarks](@/documentation/design/benchmarks/index.md) for data on this).
-This is particularly usefull when nodes are far from one another and talk to one other through standard Internet connections.
-
-### Several replication modes
-
-Garage supports a variety of replication modes, with 1 copy, 2 copies or 3 copies of your data,
-and with various levels of consistency, in order to adapt to a variety of usage scenarios.
-Read our reference page on [supported replication modes](@/documentation/reference-manual/configuration.md#replication-mode)
-to select the replication mode best suited to your use case (hint: in most cases, `replication_mode = "3"` is what you want).
+This is particularly useful when nodes are far from one another and talk to one other through standard Internet connections.

 ### Web server for static websites

@@ -76,13 +84,13 @@ exposing the same content under different domain names.

 Garage also supports bucket aliases which are local to a single user:
 this allows different users to have different buckets with the same name, thus avoiding naming collisions.
-This can be helpfull for instance if you want to write an application that creates per-user buckets with always the same name.
+This can be helpful for instance if you want to write an application that creates per-user buckets with always the same name.

 This feature is totally invisible to S3 clients and does not break compatibility with AWS.

 ### Cluster administration API

-Garage provides a fully-fledged REST API to administer your cluster programatically.
+Garage provides a fully-fledged REST API to administer your cluster programmatically.
 Functionality included in the admin API include: setting up and monitoring
 cluster nodes, managing access credentials, and managing storage buckets and bucket aliases.
 A full reference of the administration API is available [here](@/documentation/reference-manual/admin-api.md).
@@ -92,7 +100,7 @@ A full reference of the administration API is available [here](@/documentation/r
 Garage makes some internal metrics available in the Prometheus data format,
 which allows you to build interactive dashboards to visualize the load and internal state of your storage cluster.

-For developpers and performance-savvy administrators,
+For developers and performance-savvy administrators,
 Garage also supports exporting traces of what it does internally in OpenTelemetry format.
 This allows to monitor the time spent at various steps of the processing of requests,
 in order to detect potential performance bottlenecks.
@@ -121,5 +129,5 @@ related to objects stored in an S3 bucket.
 In the context of our research project, [Aérogramme](https://aerogramme.deuxfleurs.fr),
 K2V is used to provide metadata and log storage for operations on encrypted e-mail storage.

-Learn more on the specification of K2V [here](https://git.deuxfleurs.fr/Deuxfleurs/garage/src/branch/k2v/doc/drafts/k2v-spec.md)
+Learn more on the specification of K2V [here](https://git.deuxfleurs.fr/Deuxfleurs/garage/src/commit/f8be15c37db857e177d543de7be863692628d567/doc/drafts/k2v-spec.md)
 and on how to enable it in Garage [here](@/documentation/reference-manual/k2v.md).
@@ -16,10 +16,10 @@ the `k2v` feature flag enabled can be obtained from our download page under
 with `-k2v` (example: `v0.7.2-k2v`).

 The specification of the K2V API can be found
-[here](https://git.deuxfleurs.fr/Deuxfleurs/garage/src/branch/main/doc/drafts/k2v-spec.md).
+[here](https://git.deuxfleurs.fr/Deuxfleurs/garage/src/commit/f8be15c37db857e177d543de7be863692628d567/doc/drafts/k2v-spec.md).
 This document also includes a high-level overview of K2V's design.

-The K2V API uses AWSv4 signatures for authentification, same as the S3 API.
+The K2V API uses AWSv4 signatures for authentication, same as the S3 API.
 The AWS region used for signature calculation is always the same as the one
 defined for the S3 API in the config file.

@@ -55,4 +55,3 @@ cargo build --features cli --bin k2v-cli
 The CLI utility is self-documented, run `k2v-cli --help` to learn how to use
 it. There is also a short README.md in the `src/k2v-client` folder with some
 instructions.
-
@@ -27,6 +27,112 @@ Exposes the Garage replication factor configured on the node
 garage_replication_factor 3
 ```

+#### `garage_local_disk_avail` and `garage_local_disk_total` (gauge)
+
+Reports the available and total disk space on each node, for data and metadata separately.
+
+```
+garage_local_disk_avail{volume="data"} 540341960704
+garage_local_disk_avail{volume="metadata"} 540341960704
+garage_local_disk_total{volume="data"} 763063566336
+garage_local_disk_total{volume="metadata"} 763063566336
+```
+
+### Cluster health status metrics
+
+#### `cluster_healthy` (gauge)
+
+Whether all storage nodes are connected (0 or 1)
+
+```
+cluster_healthy 0
+```
+
+#### `cluster_available` (gauge)
+
+Whether all requests can be served, even if some storage nodes are disconnected
+
+```
+cluster_available 1
+```
+
+#### `cluster_connected_nodes` (gauge)
+
+Number of nodes currently connected
+
+```
+cluster_connected_nodes 3
+```
+
+#### `cluster_known_nodes` (gauge)
+
+Number of nodes already seen once in the cluster
+
+```
+cluster_known_nodes 3
+```
+
+#### `cluster_layout_node_connected` (gauge)
+
+Connection status for individual nodes of the cluster layout
+
+```
+cluster_layout_node_connected{id="62b218d848e86a64",role_capacity="1000000000",role_gateway="0",role_zone="dc1"} 1
+cluster_layout_node_connected{id="a11c7cf18af29737",role_capacity="1000000000",role_gateway="0",role_zone="dc1"} 0
+cluster_layout_node_connected{id="a235ac7695e0c54d",role_capacity="1000000000",role_gateway="0",role_zone="dc1"} 1
+cluster_layout_node_connected{id="b10c110e4e854e5a",role_capacity="1000000000",role_gateway="0",role_zone="dc1"} 1
+```
+
+#### `cluster_layout_node_disconnected_time` (gauge)
+
+Time (in seconds) since last connection to individual nodes of the cluster layout
+
+```
+cluster_layout_node_disconnected_time{id="62b218d848e86a64",role_capacity="1000000000",role_gateway="0",role_zone="dc1"} 0
+cluster_layout_node_disconnected_time{id="a235ac7695e0c54d",role_capacity="1000000000",role_gateway="0",role_zone="dc1"} 0
+cluster_layout_node_disconnected_time{id="b10c110e4e854e5a",role_capacity="1000000000",role_gateway="0",role_zone="dc1"} 0
+```
+
+#### `cluster_storage_nodes` (gauge)
+
+Number of storage nodes declared in the current layout
+
+```
+cluster_storage_nodes 4
+```
+
+#### `cluster_storage_nodes_ok` (gauge)
+
+Number of storage nodes currently connected
+
+```
+cluster_storage_nodes_ok 3
+```
+
+#### `cluster_partitions` (gauge)
+
+Number of partitions in the layout (this is always 256)
+
+```
+cluster_partitions 256
+```
+
+#### `cluster_partitions_all_ok` (gauge)
+
+Number of partitions for which all storage nodes are connected
+
+```
+cluster_partitions_all_ok 64
+```
+
+#### `cluster_partitions_quorum` (gauge)
+
+Number of partitions for which we have a quorum of connected nodes and all requests can be served
+
+```
+cluster_partitions_quorum 256
+```
+
 ### Metrics of the API endpoints

 #### `api_admin_request_counter` (counter)
@@ -119,6 +225,17 @@ block_bytes_read 120586322022
 block_bytes_written 3386618077
 ```

+#### `block_ram_buffer_free_kb` (gauge)
+
+Kibibytes available for buffering blocks that have to be sent to remote nodes.
+When clients send too much data to this node and a storage node is not receiving
+data fast enough due to slower network conditions, this will decrease down to
+zero and backpressure will be applied.
+
+```
+block_ram_buffer_free_kb 219829
+```
+
 #### `block_compression_level` (counter)

 Exposes the block compression level configured for the Garage node.
@@ -275,7 +392,7 @@ table_merkle_updater_todo_queue_length{table_name="block_ref"} 0

 #### `table_sync_items_received`, `table_sync_items_sent` (counters)

-Number of data items sent to/recieved from other nodes during resync procedures
+Number of data items sent to/received from other nodes during resync procedures

 ```
 table_sync_items_received{from="<remote node>",table_name="bucket_v2"} 3
@@ -23,16 +23,17 @@ Feel free to open a PR to suggest fixes this table. Minio is missing because the
 - 2022-05-25 - Many Ceph S3 endpoints are not documented but implemented. Following a notification from the Ceph community, we added them.


-
 ## High-level features

 | Feature                      | Garage                           | [Openstack Swift](https://docs.openstack.org/swift/latest/s3_compat.html) | [Ceph Object Gateway](https://docs.ceph.com/en/latest/radosgw/s3/) | [Riak CS](https://docs.riak.com/riak/cs/2.1.1/references/apis/storage/s3/index.html) | [OpenIO](https://docs.openio.io/latest/source/arch-design/s3_compliancy.html) |
 |------------------------------|----------------------------------|-----------------|---------------|---------|-----|
-| [signature v2](https://docs.aws.amazon.com/general/latest/gr/signature-version-2.html) (deprecated) | ❌ Missing | ✅ |  ✅ | ✅ | ✅ |
+| [signature v2](https://docs.aws.amazon.com/AmazonS3/latest/API/Appendix-Sigv2.html) (deprecated) | ❌ Missing | ✅ |  ✅ | ✅ | ✅ |
 | [signature v4](https://docs.aws.amazon.com/AmazonS3/latest/API/sig-v4-authenticating-requests.html) |  ✅ Implemented |  ✅ |  ✅ | ❌ | ✅ |
 | [URL path-style](https://docs.aws.amazon.com/AmazonS3/latest/userguide/VirtualHosting.html#path-style-access) (eg. `host.tld/bucket/key`) |  ✅ Implemented | ✅ |  ✅ | ❓| ✅ |
 | [URL vhost-style](https://docs.aws.amazon.com/AmazonS3/latest/userguide/VirtualHosting.html#virtual-hosted-style-access) URL (eg. `bucket.host.tld/key`) |  ✅ Implemented | ❌| ✅| ✅ | ✅ |
 | [Presigned URLs](https://docs.aws.amazon.com/AmazonS3/latest/userguide/ShareObjectPreSignedURL.html) |  ✅ Implemented | ❌|  ✅ | ✅ |  ✅(❓) |
+| [SSE-C encryption](https://docs.aws.amazon.com/AmazonS3/latest/userguide/ServerSideEncryptionCustomerKeys.html) |  ✅ Implemented | ❓ |  ✅ | ❌ |  ✅ |
+| [Bucket versioning](https://docs.aws.amazon.com/AmazonS3/latest/userguide/Versioning.html) | ❌ Missing | ✅ |  ✅ | ❌ | ✅ |

 *Note:* OpenIO does not says if it supports presigned URLs. Because it is part
 of signature v4 and they claim they support it without additional precisions,
@@ -44,7 +45,7 @@ we suppose that OpenIO supports presigned URLs.
 All endpoints that are missing on Garage will return a 501 Not Implemented.
 Some `x-amz-` headers are not implemented.

-### Core endoints
+### Core endpoints

 | Endpoint                     | Garage                           | [Openstack Swift](https://docs.openstack.org/swift/latest/s3_compat.html) | [Ceph Object Gateway](https://docs.ceph.com/en/latest/radosgw/s3/) | [Riak CS](https://docs.riak.com/riak/cs/2.1.1/references/apis/storage/s3/index.html) | [OpenIO](https://docs.openio.io/latest/source/arch-design/s3_compliancy.html) |
 |------------------------------|----------------------------------|-----------------|---------------|---------|-----|
@@ -134,12 +135,12 @@ If you need this feature, please [share your use case in our dedicated issue](ht
 **PutBucketLifecycleConfiguration:** The only actions supported are
 `AbortIncompleteMultipartUpload` and `Expiration` (without the
 `ExpiredObjectDeleteMarker` field).  All other operations are dependent on
-either bucket versionning or storage classes which Garage currently does not
+either bucket versioning or storage classes which Garage currently does not
 implement. The deprecated `Prefix` member directly in the the `Rule`
 structure/XML tag is not supported, specified prefixes must be inside the
 `Filter` structure/XML tag.

-**GetBucketVersioning:** Stub implementation which always returns "versionning not enabled", since Garage does not yet support bucket versionning.
+**GetBucketVersioning:** Stub implementation which always returns "versioning not enabled", since Garage does not yet support bucket versioning.

 ### Replication endpoints

@@ -154,7 +155,7 @@ Please open an issue if you have a use case for replication.
 *Note: Ceph documentation briefly says that Ceph supports
 [replication through the S3 API](https://docs.ceph.com/en/latest/radosgw/multisite-sync-policy/#s3-replication-api)
 but with some limitations.
-Additionaly, replication endpoints are not documented in the S3 compatibility page so I don't know what kind of support we can expect.*
+Additionally, replication endpoints are not documented in the S3 compatibility page so I don't know what kind of support we can expect.*

 ### Locking objects

@@ -196,7 +197,7 @@ Please open an issue if you have a use case.

 ### Vendor specific endpoints

-<details><summary>Display Amazon specifc endpoints</summary>
+<details><summary>Display Amazon specific endpoints</summary>


 | Endpoint                     | Garage                           | [Openstack Swift](https://docs.openstack.org/swift/latest/s3_compat.html) | [Ceph Object Gateway](https://docs.ceph.com/en/latest/radosgw/s3/) | [Riak CS](https://docs.riak.com/riak/cs/2.1.1/references/apis/storage/s3/index.html) | [OpenIO](https://docs.openio.io/latest/source/arch-design/s3_compliancy.html) |
@@ -233,4 +234,3 @@ Please open an issue if you have a use case.
 | [SelectObjectContent](https://docs.aws.amazon.com/AmazonS3/latest/API/API_SelectObjectContent.html) | ❌ Missing | ❌| ❌| ❌| ❌|

 </details>
-
@@ -3,7 +3,7 @@ title = "S3 compatibility target"
 weight = 5
 +++

-If there is a specific S3 functionnality you have a need for, feel free to open
+If there is a specific S3 functionality you have a need for, feel free to open
 a PR to put the corresponding endpoints higher in the list.  Please explain
 your motivations for doing so in the PR message.

@@ -42,7 +42,7 @@ The general principle are similar, but details have not been updated.**
 A version is defined by the existence of at least one entry in the blocks table for a certain version UUID.
 We must keep the following invariant: if a version exists in the blocks table, it has to be referenced in the objects table.
 We explicitly manage concurrent versions of an object: the version timestamp and version UUID columns are index columns, thus we may have several concurrent versions of an object.
-Important: before deleting an older version from the objects table, we must make sure that we did a successfull delete of the blocks of that version from the blocks table.
+Important: before deleting an older version from the objects table, we must make sure that we did a successful delete of the blocks of that version from the blocks table.

 Thus, the workflow for reading an object is as follows:

@@ -68,7 +68,7 @@ Workflow for DELETE:
 1. Check write permission (LDAP)
 2. Get current version (or versions) in object table
 3. Do the deletion of those versions NOT IN A BACKGROUND JOB THIS TIME
-4. Return succes to the user if we were able to delete blocks from the blocks table and entries from the object table
+4. Return success to the user if we were able to delete blocks from the blocks table and entries from the object table

 To delete a version:

@@ -92,10 +92,10 @@ Known issue: if someone is reading from a version that we want to delete and the
 - file path = /meta/(first 3 hex digits of hash)/(rest of hash)
 - map block hash -> set of version UUIDs where it is referenced

-Usefull metadata:
+Useful metadata:

 - list of versions that reference this block in the Casandra table, so that we can do GC by checking in Cassandra that the lines still exist
- list of other nodes that we know have acknowledged a write of this block, usefull in the rebalancing algorithm
+- list of other nodes that we know have acknowledged a write of this block, useful in the rebalancing algorithm

 Write strategy: have a single thread that does all write IO so that it is serialized (or have several threads that manage independent parts of the hash space). When writing a blob, write it to a temporary file, close, then rename so that a concurrent read gets a consistent result (either not found or found with whole content).

@@ -49,12 +49,12 @@ The ring construction that selects `n_token` random positions for each nodes giv
 is not well-balanced: the space between the tokens varies a lot, and some partitions are thus bigger than others.
 This problem was demonstrated in the original Dynamo DB paper.

-To solve this, we want to apply a better second method for partitionning our dataset:
+To solve this, we want to apply a better second method for partitioning our dataset:

 1. fix an initially large number of partitions (say 1024) with evenly-spaced delimiters, 

 2. attribute each partition randomly to a node, with a probability
-   proportionnal to its capacity (which `n_tokens` represented in the first
+   proportional to its capacity (which `n_tokens` represented in the first
   method)

 For now we continue using the multi-DC ring walking described above.
@@ -66,7 +66,7 @@ I have studied two ways to do the attribution of partitions to nodes, in a way t

 MagLev provided significantly better balancing, as it guarantees that the exact
 same number of partitions is attributed to all nodes that have the same
-capacity (and that this number is proportionnal to the node's capacity, except
+capacity (and that this number is proportional to the node's capacity, except
 for large values), however in both cases:

 - the distribution is still bad, because we use the naive multi-DC ring walking
@@ -1,6 +1,6 @@
 +++
 title = "Migrating from 0.3 to 0.4"
-weight = 20
+weight = 80
 +++

 **Migrating from 0.3 to 0.4 is unsupported. This document is only intended to
@@ -68,7 +68,7 @@ The migration steps are as follows:
 5. Turn off Garage 0.3

 6. Backup metadata folders if you can (i.e. if you have space to do it
-   somewhere). Backuping data folders could also be usefull but that's much
+   somewhere). Backuping data folders could also be useful but that's much
   harder to do. If your filesystem supports snapshots, this could be a good
   time to use them.

@@ -1,6 +1,6 @@
 +++
 title = "Migrating from 0.5 to 0.6"
-weight = 15
+weight = 75
 +++

 **This guide explains how to migrate to 0.6 if you have an existing 0.5 cluster.
@@ -1,6 +1,6 @@
 +++
 title = "Migrating from 0.6 to 0.7"
-weight = 14
+weight = 74
 +++
 **This guide explains how to migrate to 0.7 if you have an existing 0.6 cluster.
 We don't recommend trying to migrate to 0.7 directly from 0.5 or older.**
@@ -19,7 +19,7 @@ The migration steps are as follows:
 2. Disable API and web access. Garage does not support disabling
   these endpoints but you can change the port number or stop your reverse
   proxy for instance.
-3. Check once again that your cluster is healty. Run again `garage repair --all-nodes --yes tables` which is quick.
+3. Check once again that your cluster is healthy. Run again `garage repair --all-nodes --yes tables` which is quick.
   Also check your queues are empty, run `garage stats` to query them.
 4. Turn off Garage v0.6
 5. Backup the metadata folder of all your nodes: `cd /var/lib/garage ; tar -acf meta-v0.6.tar.zst meta/`
@@ -1,6 +1,6 @@
 +++
 title = "Migrating from 0.7 to 0.8"
-weight = 13
+weight = 73
 +++

 **This guide explains how to migrate to 0.8 if you have an existing 0.7 cluster.
@@ -0,0 +1,72 @@
+++
+title = "Migrating from 0.8 to 0.9"
+weight = 72
+++
+
+**This guide explains how to migrate to 0.9 if you have an existing 0.8 cluster.
+We don't recommend trying to migrate to 0.9 directly from 0.7 or older.**
+
+This migration procedure has been tested on several clusters without issues.
+However, it is still a *critical procedure* that might cause issues.
+**Make sure to back up all your data before attempting it!**
+
+You might also want to read our [general documentation on upgrading Garage](@/documentation/operations/upgrading.md).
+
+The following are **breaking changes** in Garage v0.9 that require your attention when migrating:
+
+- LMDB is now the default metadata db engine and Sled is deprecated. If you were using Sled, make sure to specify `db_engine = "sled"` in your configuration file, or take the time to [convert your database](https://garagehq.deuxfleurs.fr/documentation/reference-manual/configuration/#db-engine-since-v0-8-0).
+
+- Capacity values are now in actual byte units. The translation from the old layout will assign 1 capacity = 1Gb by default, which might be wrong for your cluster. This does not cause any data to be moved around, but you might want to re-assign correct capacity values post-migration.
+
+- Multipart uploads that were started in Garage v0.8 will not be visible in Garage v0.9 and will have to be restarted from scratch.
+
+- Changes to the admin API: some `v0/` endpoints have been replaced by `v1/` counterparts with updated/uniformized syntax. All other endpoints have also moved to `v1/` by default, without syntax changes, but are still available under `v0/` for compatibility.
+
+
+## Simple migration procedure (takes cluster offline for a while)
+
+The migration steps are as follows:
+
+1. Disable API and web access. You may do this by stopping your reverse proxy or by commenting out
+   the `api_bind_addr` values in your `config.toml` file and restarting Garage.
+2. Do `garage repair --all-nodes --yes tables` and `garage repair --all-nodes --yes blocks`,
+   check the logs and check that all data seems to be synced correctly between
+   nodes. If you have time, do additional checks (`versions`, `block_refs`, etc.)
+3. Check that the block resync queue and Merkle queue are empty:
+   run `garage stats -a` to query them or inspect metrics in the Grafana dashboard.
+4. Turn off Garage v0.8
+5. **Backup the metadata folder of all your nodes!** For instance, use the following command
+	if your metadata directory is `/var/lib/garage/meta`: `cd /var/lib/garage ; tar -acf meta-v0.8.tar.zst meta/`
+6. Install Garage v0.9
+7. Update your configuration file if necessary.
+8. Turn on Garage v0.9
+9. Do `garage repair --all-nodes --yes tables` and `garage repair --all-nodes --yes blocks`.
+   Wait for a full table sync to run.
+10. Your upgraded cluster should be in a working state. Re-enable API and Web
+    access and check that everything went well.
+11. Monitor your cluster in the next hours to see if it works well under your production load, report any issue.
+12. You might want to assign correct capacity values to all your nodes. Doing so might cause data to be moved
+    in your cluster, which should also be monitored carefully.
+
+## Minimal downtime migration procedure
+
+The migration to Garage v0.9 can be done with almost no downtime,
+by restarting all nodes at once in the new version.
+
+The migration steps are as follows:
+
+1. Do `garage repair --all-nodes --yes tables` and `garage repair --all-nodes --yes blocks`,
+   check the logs and check that all data seems to be synced correctly between
+   nodes. If you have time, do additional checks (`versions`, `block_refs`, etc.)
+
+2. Turn off each node individually; back up its metadata folder (see above); turn it back on again.
+   This will allow you to take a backup of all nodes without impacting global cluster availability.
+   You can do all nodes of a single zone at once as this does not impact the availability of Garage.
+
+3. Prepare your binaries and configuration files for Garage v0.9
+
+4. Shut down all v0.8 nodes simultaneously, and restart them all simultaneously in v0.9.
+   Use your favorite deployment tool (Ansible, Kubernetes, Nomad) to achieve this as fast as possible.
+   Garage v0.9 should be in a working state as soon as it starts.
+
+5. Proceed with repair and monitoring as described in steps 9-12 above.
@@ -0,0 +1,77 @@
+++
+title = "Migrating from 0.9 to 1.0"
+weight = 71
+++
+
+**This guide explains how to migrate to 1.0 if you have an existing 0.9 cluster.
+We don't recommend trying to migrate to 1.0 directly from 0.8 or older.**
+
+This migration procedure has been tested on several clusters without issues.
+However, it is still a *critical procedure* that might cause issues.
+**Make sure to back up all your data before attempting it!**
+
+You might also want to read our [general documentation on upgrading Garage](@/documentation/operations/upgrading.md).
+
+## Changes introduced in v1.0
+
+The following are **breaking changes** in Garage v1.0 that require your attention when migrating:
+
+- The Sled metadata db engine has been **removed**. If your cluster was still
+  using Sled, you will need to **use a Garage v0.9.x binary** to convert the
+  database using the `garage convert-db` subcommand. See
+  [here](@/documentation/reference-manual/configuration.md#db_engine) for the
+  details of the procedure.
+
+The following syntax changes have been made to the configuration file:
+
+- The `replication_mode` parameter has been split into two parameters:
+  [`replication_factor`](@/documentation/reference-manual/configuration.md#replication_factor)
+  and
+  [`consistency_mode`](@/documentation/reference-manual/configuration.md#consistency_mode).
+  The old syntax using `replication_mode` is still supported for legacy
+  reasons and can still be used.
+
+- The parameters `sled_cache_capacity` and `sled_flush_every_ms` have been removed.
+
+## Migration procedure
+
+The migration to Garage v1.0 can be done with almost no downtime,
+by restarting all nodes at once in the new version.
+
+The migration steps are as follows:
+
+1. Do a `garage repair --all-nodes --yes tables`, check the logs and check that
+   all data seems to be synced correctly between nodes. If you have time, do
+   additional `garage repair` procedures (`blocks`, `versions`, `block_refs`,
+   etc.)
+
+2. Ensure you have a snapshot of your Garage installation that you can restore
+   to in case the upgrade goes wrong:
+
+   - If you are running Garage v0.9.4 or later, use the `garage meta snapshot
+     --all` to make a backup snapshot of the metadata directories of your nodes
+     for backup purposes, and save a copy of the following files in the
+     metadata directories of your nodes: `cluster_layout`, `data_layout`,
+     `node_key`, `node_key.pub`.
+
+   - If you are running a filesystem such as ZFS or BTRFS that support
+     snapshotting, you can create a filesystem-level snapshot to be used as a
+     restoration point if needed.
+
+   - In other cases, make a backup using the old procedure: turn off each node
+     individually; back up its metadata folder (for instance, use the following
+     command if your metadata directory is `/var/lib/garage/meta`: `cd
+     /var/lib/garage ; tar -acf meta-v0.9.tar.zst meta/`); turn it back on
+     again.  This will allow you to take a backup of all nodes without
+     impacting global cluster availability.  You can do all nodes of a single
+     zone at once as this does not impact the availability of Garage.
+
+3. Prepare your updated binaries and configuration files for Garage v1.0
+
+4. Shut down all v0.9 nodes simultaneously, and restart them all simultaneously
+   in v1.0.  Use your favorite deployment tool (Ansible, Kubernetes, Nomad) to
+   achieve this as fast as possible.  Garage v1.0 should be in a working state
+   as soon as enough nodes have started.
+
+5. Monitor your cluster in the following hours to see if it works well under
+   your production load.
@@ -0,0 +1,70 @@
+++
+title = "Migrating from 1.0 to 2.0"
+weight = 70
+++
+
+**This guide explains how to migrate to v2.x if you have an existing v1.x.x cluster.
+We don't recommend trying to migrate to v2.x directly from v0.9.x or older.**
+
+This migration procedure has been tested on several clusters without issues.
+However, it is still a *critical procedure* that might cause issues.
+**Make sure to back up all your data before attempting it!**
+
+You might also want to read our [general documentation on upgrading Garage](@/documentation/operations/upgrading.md).
+
+## Changes introduced in v2.0
+
+The following are **breaking changes** in Garage v2.0 that require your attention when migrating:
+
+- The administration API has been completely reworked.
+  Some calls to the `/v1/` endpoints will still work but most will not.
+  New endpoints are prefixed by `/v2/`. **You will need to update all your code that makes use of the admin API.**
+
+- `replication_mode` is no longer a supported configuration parameter,
+  please use `replication_factor` and `consistency_mode` instead.
+
+## Migration procedure
+
+The migration to Garage v2.0 can be done with almost no downtime,
+by restarting all nodes at once in the new version.
+
+The migration steps are as follows:
+
+1. Do a `garage repair --all-nodes --yes tables`, check the logs and check that
+   all data seems to be synced correctly between nodes. If you have time, do
+   additional `garage repair` procedures (`blocks`, `versions`, `block_refs`,
+   etc.)
+
+2. Ensure you have a snapshot of your Garage installation that you can restore
+   to in case the upgrade goes wrong, with one of the following options:
+
+   - You may use the `garage meta snapshot --all` command
+     to make a backup snapshot of the metadata directories of your nodes
+     for backup purposes. Once this command has completed, copy the following
+     files and directories from the `metadata_dir` of all your nodes
+     to somewhere safe: `snapshots`, `cluster_layout`, `data_layout`,
+     `node_key`, `node_key.pub`. (If you have set the `metadata_snapshots_dir`
+     to a different value in your config file, back up that directory instead.)
+
+   - If you are running a filesystem such as ZFS or BTRFS that support
+     snapshotting, you can create a filesystem-level snapshot of the `metadata_dir`
+     of all your nodes to be used as a restoration point if needed.
+
+   - You may also make a back-up manually: turn off each node
+     individually; back up its metadata folder (for instance, use the following
+     command if your metadata directory is `/var/lib/garage/meta`: `cd
+     /var/lib/garage ; tar -acf meta-v1.0.tar.zst meta/`); turn it back on
+     again.  This will allow you to take a backup of all nodes without
+     impacting global cluster availability.  You can do all nodes of a single
+     zone at once as this does not impact the availability of Garage.
+
+3. Prepare your updated binaries and configuration files for Garage v2.0.
+   **Remember to update your configuration file to remove `replication_mode` and replace it by `replication_factor`.**
+
+4. Shut down all v1.0 nodes simultaneously, and restart them all simultaneously
+   in v2.0.  Use your favorite deployment tool (Ansible, Kubernetes, Nomad) to
+   achieve this as fast as possible.  Garage v2.0 should be in a working state
+   as soon as enough nodes have started.
+
+5. Monitor your cluster in the following hours to see if it works well under
+   your production load.
@@ -1,6 +1,6 @@
 +++
 title = "Testing strategy"
-weight = 30
+weight = 100
 +++


@@ -28,16 +28,16 @@ We should try to test in least invasive ways, i.e. minimize the impact of the te
 - Not making `garage` a shared library (launch using `execve`, it's perfectly fine)

 Instead, we should focus on building a clean outer interface for the `garage` binary,
-for example loading configuration using environnement variables instead of the configuration file if that's helpfull for writing the tests.
+for example loading configuration using environment variables instead of the configuration file if that's helpful for writing the tests.

 There are two reasons for this:

- Keep the soure code clean and focused
+- Keep the source code clean and focused
 - Test something that is as close as possible as the true garage that will actually be running

 Reminder: rules of simplicity, concerning changes to Garage's source code.
 Always question what we are doing.
-Never do anything just because it looks nice or because we "think" it might be usefull at some later point but without knowing precisely why/when.
+Never do anything just because it looks nice or because we "think" it might be useful at some later point but without knowing precisely why/when.
 Only do things that make perfect sense in the context of what we currently know.

 ## References
@@ -71,5 +71,3 @@ Interesting blog posts on the blog of the Sled database:
 Misc:
  - [mutagen](https://github.com/llogiq/mutagen) - mutation testing is a way to assert our test quality by mutating the code and see if the mutation makes the tests fail
  - [fuzzing](https://rust-fuzz.github.io/book/) - cargo supports fuzzing, it could be a way to test our software reliability in presence of garbage data.
-  
-
@@ -8,18 +8,22 @@ listen address is specified in the `[admin]` section of the configuration
 file (see [configuration file
 reference](@/documentation/reference-manual/configuration.md))

-**WARNING.** At this point, there is no comittement to stability of the APIs described in this document.
-We will bump the version numbers prefixed to each API endpoint at each time the syntax
-or semantics change, meaning that code that relies on these endpoint will break
+**WARNING.** At this point, there is no commitment to the stability of the APIs described in this document.
+We will bump the version numbers prefixed to each API endpoint each time the syntax
+or semantics change, meaning that code that relies on these endpoints will break
 when changes are introduced.

-The Garage administration API was introduced in version 0.7.2, this document
-does not apply to older versions of Garage.
+The Garage administration API was introduced in version 0.7.2, and was
+changed several times.
+
+**THIS DOCUMENT IS DEPRECATED.** We now have an OpenAPI spec which is automatically generated
+from Garage's source code and is always up-to-date. See `doc/api/garage-admin-v2.html`.
+Text in this document is no longer kept in sync with the admin API's actual behavior.


 ## Access control

-The admin API uses two different tokens for acces control, that are specified in the config file's `[admin]` section:
+The admin API uses two different tokens for access control, that are specified in the config file's `[admin]` section:

 - `metrics_token`: the token for accessing the Metrics endpoint (if this token
  is not set in the config file, the Metrics endpoint can be accessed without
@@ -52,116 +56,118 @@ Returns an HTTP status 200 if the node is ready to answer user's requests,
 and an HTTP status 503 (Service Unavailable) if there are some partitions
 for which a quorum of nodes is not available.
 A simple textual message is also returned in a body with content-type `text/plain`.
-See `/v1/health` for an API that also returns JSON output.
+See `/v2/GetClusterHealth` for an API that also returns JSON output.
+
+### Other special endpoints
+
+#### CheckDomain `GET /check?domain=<domain>`
+
+Checks whether this Garage cluster serves a website for domain `<domain>`.
+Returns HTTP 200 Ok if yes, or HTTP 4xx if no website is available for this domain.

 ### Cluster operations

-#### GetClusterStatus `GET /v1/status`
+#### GetClusterStatus `GET /v2/GetClusterStatus`

 Returns the cluster's current status in JSON, including:

- ID of the node being queried and its version of the Garage daemon
 - Live nodes
 - Currently configured cluster layout
- Staged changes to the cluster layout

 Example response body:

 ```json
 {
-  "node": "ec79480e0ce52ae26fd00c9da684e4fa56658d9c64cdcecb094e936de0bfe71f",
-  "garageVersion": "git:v0.9.0-dev",
-  "garageFeatures": [
-    "k2v",
-    "sled",
-    "lmdb",
-    "sqlite",
-    "metrics",
-    "bundled-libs"
-  ],
-  "rustVersion": "1.68.0",
-  "dbEngine": "LMDB (using Heed crate)",
-  "knownNodes": [
+  "layoutVersion": 5,
+  "nodes": [
    {
-      "id": "ec79480e0ce52ae26fd00c9da684e4fa56658d9c64cdcecb094e936de0bfe71f",
-      "addr": "10.0.0.11:3901",
+      "id": "62b218d848e86a64f7fe1909735f29a4350547b54c4b204f91246a14eb0a1a8c",
+      "role": {
+        "id": "62b218d848e86a64f7fe1909735f29a4350547b54c4b204f91246a14eb0a1a8c",
+        "zone": "dc1",
+        "capacity": 100000000000,
+        "tags": []
+      },
+      "addr": "10.0.0.3:3901",
+      "hostname": "node3",
      "isUp": true,
-      "lastSeenSecsAgo": 9,
-      "hostname": "node1"
+      "lastSeenSecsAgo": 12,
+      "draining": false,
+      "dataPartition": {
+        "available": 660270088192,
+        "total": 873862266880
+      },
+      "metadataPartition": {
+        "available": 660270088192,
+        "total": 873862266880
+      }
    },
    {
-      "id": "4a6ae5a1d0d33bf895f5bb4f0a418b7dc94c47c0dd2eb108d1158f3c8f60b0ff",
-      "addr": "10.0.0.12:3901",
+      "id": "a11c7cf18af297379eff8688360155fe68d9061654449ba0ce239252f5a7487f",
+      "role": null,
+      "addr": "10.0.0.2:3901",
+      "hostname": "node2",
      "isUp": true,
-      "lastSeenSecsAgo": 1,
-      "hostname": "node2"
+      "lastSeenSecsAgo": 11,
+      "draining": true,
+      "dataPartition": {
+        "available": 660270088192,
+        "total": 873862266880
+      },
+      "metadataPartition": {
+        "available": 660270088192,
+        "total": 873862266880
+      }
    },
    {
-      "id": "23ffd0cdd375ebff573b20cc5cef38996b51c1a7d6dbcf2c6e619876e507cf27",
-      "addr": "10.0.0.21:3901",
+      "id": "a235ac7695e0c54d7b403943025f57504d500fdcc5c3e42c71c5212faca040a2",
+      "role": {
+        "id": "a235ac7695e0c54d7b403943025f57504d500fdcc5c3e42c71c5212faca040a2",
+        "zone": "dc1",
+        "capacity": 100000000000,
+        "tags": []
+      },
+      "addr": "127.0.0.1:3904",
+      "hostname": "lindy",
      "isUp": true,
-      "lastSeenSecsAgo": 7,
-      "hostname": "node3"
+      "lastSeenSecsAgo": 2,
+      "draining": false,
+      "dataPartition": {
+        "available": 660270088192,
+        "total": 873862266880
+      },
+      "metadataPartition": {
+        "available": 660270088192,
+        "total": 873862266880
+      }
    },
    {
-      "id": "e2ee7984ee65b260682086ec70026165903c86e601a4a5a501c1900afe28d84b",
-      "addr": "10.0.0.22:3901",
+      "id": "b10c110e4e854e5aa3f4637681befac755154b20059ec163254ddbfae86b09df",
+      "role": {
+        "id": "b10c110e4e854e5aa3f4637681befac755154b20059ec163254ddbfae86b09df",
+        "zone": "dc1",
+        "capacity": 100000000000,
+        "tags": []
+      },
+      "addr": "10.0.0.1:3901",
+      "hostname": "node1",
      "isUp": true,
-      "lastSeenSecsAgo": 1,
-      "hostname": "node4"
+      "lastSeenSecsAgo": 3,
+      "draining": false,
+      "dataPartition": {
+        "available": 660270088192,
+        "total": 873862266880
+      },
+      "metadataPartition": {
+        "available": 660270088192,
+        "total": 873862266880
+      }
    }
-  ],
-  "layout": {
-    "version": 12,
-    "roles": [
-      {
-        "id": "ec79480e0ce52ae26fd00c9da684e4fa56658d9c64cdcecb094e936de0bfe71f",
-        "zone": "dc1",
-        "capacity": 10737418240,
-        "tags": [
-          "node1"
-        ]
-      },
-      {
-        "id": "4a6ae5a1d0d33bf895f5bb4f0a418b7dc94c47c0dd2eb108d1158f3c8f60b0ff",
-        "zone": "dc1",
-        "capacity": 10737418240,
-        "tags": [
-          "node2"
-        ]
-      },
-      {
-        "id": "23ffd0cdd375ebff573b20cc5cef38996b51c1a7d6dbcf2c6e619876e507cf27",
-        "zone": "dc2",
-        "capacity": 10737418240,
-        "tags": [
-          "node3"
-        ]
-      }
-    ],
-    "stagedRoleChanges": [
-      {
-        "id": "e2ee7984ee65b260682086ec70026165903c86e601a4a5a501c1900afe28d84b",
-        "remove": false,
-        "zone": "dc2",
-        "capacity": 10737418240,
-        "tags": [
-          "node4"
-        ]
-      }
-      {
-        "id": "23ffd0cdd375ebff573b20cc5cef38996b51c1a7d6dbcf2c6e619876e507cf27",
-        "remove": true,
-        "zone": null,
-        "capacity": null,
-        "tags": null,
-      }
-    ]
-  }
+  ]
 }
 ```

-#### GetClusterHealth `GET /v1/health`
+#### GetClusterHealth `GET /v2/GetClusterHealth`

 Returns the cluster's current health in JSON format, with the following variables:

@@ -170,7 +176,7 @@ Returns the cluster's current health in JSON format, with the following variable
  - degraded: Garage node is not connected to all storage nodes, but a quorum of write nodes is available for all partitions
  - unavailable: a quorum of write nodes is not available for some partitions
 - `knownNodes`: the number of nodes this Garage node has had a TCP connection to since the daemon started
- `connectedNodes`: the nubmer of nodes this Garage node currently has an open connection to
+- `connectedNodes`: the number of nodes this Garage node currently has an open connection to
 - `storageNodes`: the number of storage nodes currently registered in the cluster layout
 - `storageNodesOk`: the number of storage nodes to which a connection is currently open
 - `partitions`: the total number of partitions of the data (currently always 256)
@@ -194,7 +200,7 @@ Example response body:
 }
 ```

-#### ConnectClusterNodes `POST /v1/connect`
+#### ConnectClusterNodes `POST /v2/ConnectClusterNodes`

 Instructs this Garage node to connect to other Garage nodes at specified addresses.

@@ -224,7 +230,7 @@ Example response:
 ]
 ```

-#### GetClusterLayout `GET /v1/layout`
+#### GetClusterLayout `GET /v2/GetClusterLayout`

 Returns the cluster's current layout in JSON, including:

@@ -285,7 +291,7 @@ Example response body:
 }
 ```

-#### UpdateClusterLayout `POST /v1/layout`
+#### UpdateClusterLayout `POST /v2/UpdateClusterLayout`

 Send modifications to the cluster layout. These modifications will
 be included in the staged role changes, visible in subsequent calls
@@ -322,7 +328,7 @@ This returns the new cluster layout with the proposed staged changes,
 as returned by GetClusterLayout.


-#### ApplyClusterLayout `POST /v1/layout/apply`
+#### ApplyClusterLayout `POST /v2/ApplyClusterLayout`

 Applies to the cluster the layout changes currently registered as
 staged layout changes.
@@ -342,23 +348,11 @@ existing layout in the cluster.
 This returns the message describing all the calculations done to compute the new
 layout, as well as the description of the layout as returned by GetClusterLayout.

-#### RevertClusterLayout `POST /v1/layout/revert`
+#### RevertClusterLayout `POST /v2/RevertClusterLayout`

 Clears all of the staged layout changes.

-Request body format:
-
-```json
-{
-  "version": 13
-}
-```
-
-Reverting the staged changes is done by incrementing the version number
-and clearing the contents of the staged change list.
-Similarly to the CLI, the body must include the incremented
-version number, which MUST be 1 + the value of the currently
-existing layout in the cluster.
+This requests contains an empty body.

 This returns the new cluster layout with all changes reverted,
 as returned by GetClusterLayout.
@@ -366,7 +360,7 @@ as returned by GetClusterLayout.

 ### Access key operations

-#### ListKeys `GET /v1/key`
+#### ListKeys `GET /v2/ListKeys`

 Returns all API access keys in the cluster.

@@ -385,8 +379,8 @@ Example response:
 ]
 ```

-#### GetKeyInfo `GET /v1/key?id=<acces key id>`
-#### GetKeyInfo `GET /v1/key?search=<pattern>`
+#### GetKeyInfo `GET /v2/GetKeyInfo?id=<access key id>`
+#### GetKeyInfo `GET /v2/GetKeyInfo?search=<pattern>`

 Returns information about the requested API access key.

@@ -394,7 +388,7 @@ If `id` is set, the key is looked up using its exact identifier (faster).
 If `search` is set, the key is looked up using its name or prefix
 of identifier (slower, all keys are enumerated to do this).

-Optionnally, the query parameter `showSecretKey=true` can be set to reveal the
+Optionally, the query parameter `showSecretKey=true` can be set to reveal the
 associated secret access key.

 Example response:
@@ -460,7 +454,7 @@ Example response:
 }
 ```

-#### CreateKey `POST /v1/key`
+#### CreateKey `POST /v2/CreateKey`

 Creates a new API access key.

@@ -475,7 +469,7 @@ Request body format:
 This returns the key info, including the created secret key,
 in the same format as the result of GetKeyInfo.

-#### ImportKey `POST /v1/key/import`
+#### ImportKey `POST /v2/ImportKey`

 Imports an existing API key.
 This will check that the imported key is in the valid format, i.e.
@@ -493,7 +487,7 @@ Request body format:

 This returns the key info in the same format as the result of GetKeyInfo.

-#### UpdateKey `POST /v1/key?id=<acces key id>`
+#### UpdateKey `POST /v2/UpdateKey?id=<access key id>`

 Updates information about the specified API access key.

@@ -515,14 +509,14 @@ The possible flags in `allow` and `deny` are: `createBucket`.

 This returns the key info in the same format as the result of GetKeyInfo.

-#### DeleteKey `DELETE /v1/key?id=<acces key id>`
+#### DeleteKey `POST /v2/DeleteKey?id=<access key id>`

 Deletes an API access key.


 ### Bucket operations

-#### ListBuckets `GET /v1/bucket`
+#### ListBuckets `GET /v2/ListBuckets`

 Returns all storage buckets in the cluster.

@@ -564,8 +558,8 @@ Example response:
 ]
 ```

-#### GetBucketInfo `GET /v1/bucket?id=<bucket id>`
-#### GetBucketInfo `GET /v1/bucket?globalAlias=<alias>`
+#### GetBucketInfo `GET /v2/GetBucketInfo?id=<bucket id>`
+#### GetBucketInfo `GET /v2/GetBucketInfo?globalAlias=<alias>`

 Returns information about the requested storage bucket.

@@ -608,7 +602,7 @@ Example response:
 }
 ```

-#### CreateBucket `POST /v1/bucket`
+#### CreateBucket `POST /v2/CreateBucket`

 Creates a new storage bucket.

@@ -648,7 +642,7 @@ or no alias at all.
 Technically, you can also specify both `globalAlias` and `localAlias` and that would create
 two aliases, but I don't see why you would want to do that.

-#### UpdateBucket `PUT /v1/bucket?id=<bucket id>`
+#### UpdateBucket `POST /v2/UpdateBucket?id=<bucket id>`

 Updates configuration of the given bucket.

@@ -680,16 +674,38 @@ In `quotas`: new values of `maxSize` and `maxObjects` must both be specified, or
 to remove the quotas. An absent value will be considered the same as a `null`. It is not possible
 to change only one of the two quotas.

-#### DeleteBucket `DELETE /v1/bucket?id=<bucket id>`
+#### DeleteBucket `POST /v2/DeleteBucket?id=<bucket id>`

 Deletes a storage bucket. A bucket cannot be deleted if it is not empty.

 Warning: this will delete all aliases associated with the bucket!

+#### CleanupIncompleteUploads `POST /v2/CleanupIncompleteUploads`
+
+Cleanup all incomplete uploads in a bucket that are older than a specified number
+of seconds.
+
+Request body format:
+
+```json
+{
+    "bucketId": "e6a14cd6a27f48684579ec6b381c078ab11697e6bc8513b72b2f5307e25fff9b",
+    "olderThanSecs": 3600
+}
+```
+
+Response format
+
+```json
+{
+    "uploadsDeleted": 12
+}
+```
+

 ### Operations on permissions for keys on buckets

-#### BucketAllowKey `POST /v1/bucket/allow`
+#### AllowBucketKey `POST /v2/AllowBucketKey`

 Allows a key to do read/write/owner operations on a bucket.

@@ -710,7 +726,7 @@ Request body format:
 Flags in `permissions` which have the value `true` will be activated.
 Other flags will remain unchanged.

-#### BucketDenyKey `POST /v1/bucket/deny`
+#### DenyBucketKey `POST /v2/DenyBucketKey`

 Denies a key from doing read/write/owner operations on a bucket.

@@ -734,19 +750,35 @@ Other flags will remain unchanged.

 ### Operations on bucket aliases

-#### GlobalAliasBucket `PUT /v1/bucket/alias/global?id=<bucket id>&alias=<global alias>`
+#### AddBucketAlias `POST /v2/AddBucketAlias`

-Empty body. Creates a global alias for a bucket.
+Creates an alias for a bucket in the namespace of a specific access key.
+To create a global alias, specify the `globalAlias` field.
+To create a local alias, specify the `localAlias` and `accessKeyId` fields.

-#### GlobalUnaliasBucket `DELETE /v1/bucket/alias/global?id=<bucket id>&alias=<global alias>`
+Request body format:

-Removes a global alias for a bucket.
+```json
+{
+    "bucketId": "e6a14cd6a27f48684579ec6b381c078ab11697e6bc8513b72b2f5307e25fff9b",
+    "globalAlias": "my-bucket"
+}
+```

-#### LocalAliasBucket `PUT /v1/bucket/alias/local?id=<bucket id>&accessKeyId=<access key ID>&alias=<local alias>`
+or:

-Empty body. Creates a local alias for a bucket in the namespace of a specific access key.
+```json
+{
+    "bucketId": "e6a14cd6a27f48684579ec6b381c078ab11697e6bc8513b72b2f5307e25fff9b",
+    "accessKeyId": "GK31c2f218a2e44f485b94239e",
+    "localAlias": "my-bucket"
+}
+```

-#### LocalUnaliasBucket `DELETE /v1/bucket/alias/local?id=<bucket id>&accessKeyId<access key ID>&alias=<local alias>`
+#### RemoveBucketAlias `POST /v2/RemoveBucketAlias`

-Removes a local alias for a bucket in the namespace of a specific access key.
+Removes an alias for a bucket in the namespace of a specific access key.
+To remove a global alias, specify the `globalAlias` field.
+To remove a local alias, specify the `localAlias` and `accessKeyId` fields.

+Request body format: same as AddBucketAlias.
@@ -35,7 +35,7 @@ Triples in K2V are constituted of three fields:
  partition key in which the client wants to read/delete lists of items

 - a sort key (`sk`), an utf8 string that defines the index of the triplet inside its
-  partition; triplets are uniquely idendified by their partition key + sort key
+  partition; triplets are uniquely identified by their partition key + sort key

 - a value (`v`), an opaque binary blob associated to the partition key + sort key;
  they are transmitted as binary when possible but in most case in the JSON API
@@ -74,7 +74,7 @@ are obsoleted by the new write.

 **Basic insertion.** To insert a new value `v4` with context `[(node1, t2), (node2, t3)]`, in a
 simple case where there was no insertion in-between reading the value
-mentionned above and writing `v4`, and supposing that node2 receives the
+mentioned above and writing `v4`, and supposing that node2 receives the
 InsertItem query:

 - `node2` generates a timestamp `t4` such that `t4 > t3`.
@@ -146,7 +146,7 @@ in a bucket, as the partition key becomes the sort key in the index.
 How indexing works:

 - Each node keeps a local count of how many items it stores for each partition,
-  in a local Sled tree that is updated atomically when an item is modified.
+  in a local database tree that is updated atomically when an item is modified.
 - These local counters are asynchronously stored in the index table which is
  a regular Garage table spread in the network. Counters are stored as LWW values,
  so basically the final table will have the following structure:
@@ -332,7 +332,7 @@ Inserts a single item. This request does not use JSON, the body is sent directly

 To supersede previous values, the HTTP header `X-Garage-Causality-Token` should
 be set to the causality token returned by a previous read on this key. This
-header can be ommitted for the first writes to the key.
+header can be omitted for the first writes to the key.

 Example query:

@@ -397,7 +397,7 @@ smallest partition key that exists.  It returns partition keys in increasing
 order, or decreasing order if `reverse` is set to `true`,
 and stops when either of the following conditions is met:

-1. if `end` is specfied, the partition key `end` is reached or surpassed (if it
+1. if `end` is specified, the partition key `end` is reached or surpassed (if it
   is reached exactly, it is not included in the result)

 2. if `limit` is specified, `limit` partition keys have been listed
@@ -491,7 +491,7 @@ the triplet is inserted for the first time, the causality token should be set to

 The value is expected to be a base64-encoded binary blob. The value `null` can
 also be used to delete the triplet while preserving causality information: this
-allows to know if a delete has happenned concurrently with an insert, in which
+allows to know if a delete has happened concurrently with an insert, in which
 case both are preserved and returned on reads (see below).

 Partition keys and sort keys are utf8 strings which are stored sorted by
@@ -540,7 +540,7 @@ JSON struct with the following fields:

 For each of the searches, triplets are listed and returned separately. The
 semantics of `prefix`, `start`, `end`, `limit` and `reverse` are the same as for ReadIndex. The
-additionnal parameter `singleItem` allows to get a single item, whose sort key
+additional parameter `singleItem` allows to get a single item, whose sort key
 is the one given in `start`. Parameters `conflictsOnly` and `tombstones`
 control additional filters on the items that are returned.

@@ -562,7 +562,7 @@ token>", v: ["<value1>", ...] }`, with the following fields:
 - in case of concurrent update and deletion, a `null` is added to the list of concurrent values

 - if the `tombstones` query parameter is set to `true`, tombstones are returned
-  for items that have been deleted (this can be usefull for inserting after an
+  for items that have been deleted (this can be useful for inserting after an
  item that has been deleted, so that the insert is not considered
  concurrent with the delete). Tombstones are returned as tuples in the
  same format with only `null` values
@@ -59,7 +59,7 @@ To link the effective storage capacity of the cluster to partition assignment, w
 \end{equation}
 This assumption is justified by the dispersion of the hashing function, when the number of partitions is small relative to the number of stored blocks.

-Every node $n$ wille store some number $p_n$ of partitions (it is the number of partitions $p$ such that $n$ appears in the $\alpha_p$). Hence the partitions stored by $n$ (and hence all partitions by our assumption) have there size bounded by $c_n/p_n$. This remark leads us to define the optimal size that we will want to maximize:
+Every node $n$ will store some number $p_n$ of partitions (it is the number of partitions $p$ such that $n$ appears in the $\alpha_p$). Hence the partitions stored by $n$ (and hence all partitions by our assumption) have there size bounded by $c_n/p_n$. This remark leads us to define the optimal size that we will want to maximize:

 \begin{equation}
 	\label{eq:optimal}
@@ -38,7 +38,7 @@ We would like to compute an assignment of nodes to partitions. We will impose so
 \end{equation}
 This assumption is justified by the dispersion of the hashing function, when the number of partitions is small relative to the number of stored large objects.

-Every node $n$ wille store some number $k_n$ of partitions. Hence the partitions stored by $n$ (and hence all partitions by our assumption) have there size bounded by $c_n/k_n$. This remark leads us to define the optimal size that we will want to maximize:
+Every node $n$ will store some number $k_n$ of partitions. Hence the partitions stored by $n$ (and hence all partitions by our assumption) have there size bounded by $c_n/k_n$. This remark leads us to define the optimal size that we will want to maximize:

 \begin{equation}
 	\label{eq:optimal}
@@ -62,7 +62,7 @@ For now, in the following, we ask the following redundancy constraint:

 \textbf{Mode 3:} every partition needs to be assignated to three nodes. We try to spread the three nodes over different zones as much as possible.

-\textbf{Warning:} This is a working document written incrementaly. The last version of the algorithm is the \textbf{parametric assignment} described in the next section.
+\textbf{Warning:} This is a working document written incrementally. The last version of the algorithm is the \textbf{parametric assignment} described in the next section.


 \section{Computation of a parametric assignment}
@@ -318,7 +318,7 @@ $$
 $$
 which is the universal upper bound on $s^*$. Hence any optimal utilization $(n_v)$ can be modified to another optimal utilization such that $n_v\ge \hat{n}_v$

-Because $z_0$ cannot store more than $N$ partition occurences, in any assignment, at least $2N$ partitions must be assignated to the zones $Z\setminus\{z_0\}$. Let $C_0 = C-c_{z_0}$. Suppose that there exists a zone $z_1\neq z_0$ such that $c_{z_1}/C_0 \ge 1/2$. Then, with the same argument as for $z_0$, we can define 
+Because $z_0$ cannot store more than $N$ partition occurrences, in any assignment, at least $2N$ partitions must be assignated to the zones $Z\setminus\{z_0\}$. Let $C_0 = C-c_{z_0}$. Suppose that there exists a zone $z_1\neq z_0$ such that $c_{z_1}/C_0 \ge 1/2$. Then, with the same argument as for $z_0$, we can define
 $$\hat{n}_v = \left\lfloor\frac{c_v}{c_{z_1}}N\right\rfloor$$
 for every $v\in z_1$.

@@ -351,7 +351,7 @@ Define $3N$ tokens $t_1,\ldots, t_{3N}\in V$ as follows:
 Then for $1\le i \le N$, define the triplet $T_i$ to be 
 $(t_i, t_{i+N}, t_{i+2N})$. Since the same nodes of a zone appear contiguously, the three nodes of a triplet must belong to three distinct zones.

-However simple, this solution to go from an utilization to an assignment has the drawback of not spreading the triplets: a node will tend to be associated to the same two other nodes for many partitions. Hence, during data transfer, it will tend to use only two link, instead of spreading the bandwith use over many other links to other nodes. To achieve this goal, we will reframe the search of an assignment as a flow problem. and in the flow algorithm, we will introduce randomness in the order of exploration. This will be sufficient to obtain a good dispersion of the triplets.
+However simple, this solution to go from an utilization to an assignment has the drawback of not spreading the triplets: a node will tend to be associated to the same two other nodes for many partitions. Hence, during data transfer, it will tend to use only two link, instead of spreading the bandwidth use over many other links to other nodes. To achieve this goal, we will reframe the search of an assignment as a flow problem. and in the flow algorithm, we will introduce randomness in the order of exploration. This will be sufficient to obtain a good dispersion of the triplets.

 \begin{figure}
 	\centering
@@ -436,7 +436,7 @@ T_3=(b,c,d').
 $$
 One can check that in this case, it is impossible to minimize both the number of zone and node changes.

-Because of the redundancy constraint, we cannot use a greedy algorithm to just replace nodes in the triplets to try to get the new utilization rate: this could lead to blocking situation where there is still a hole to fill in a triplet but no available node satisfies the zone separation constraint. To circumvent this issue, we propose an algorithm based on finding cycles in a graph encoding of the assignment. As in section \ref{sec:opt_assign}, we can explore the neigbours in a random order in the graph algorithms, to spread the triplets distribution.
+Because of the redundancy constraint, we cannot use a greedy algorithm to just replace nodes in the triplets to try to get the new utilization rate: this could lead to blocking situation where there is still a hole to fill in a triplet but no available node satisfies the zone separation constraint. To circumvent this issue, we propose an algorithm based on finding cycles in a graph encoding of the assignment. As in section \ref{sec:opt_assign}, we can explore the neighbours in a random order in the graph algorithms, to spread the triplets distribution.


 \subsubsection{Minimizing the zone discrepancy}
@@ -550,8 +550,8 @@ We give some considerations of worst case complexity for these algorithms. In th
 Algorithm \ref{alg:util} can be implemented with complexity $O(\#V^2)$. The complexity of the function call at line \ref{lin:subutil} is $O(\#V)$. The difference between the sum of the subutilizations and $3N$ is at most the sum of the rounding errors when computing the $\hat{n}_v$. Hence it is bounded by $\#V$ and the loop at line \ref{lin:loopsub} is iterated at most $\#V$ times. Finding the minimizing $v$ at line \ref{lin:findmin} takes $O(\#V)$ operations (naively, we could also use a heap).

 Algorithm \ref{alg:opt} can be implemented with complexity $O(N^3\times \#Z)$. The flow graph has $O(N+\#Z)$ vertices and $O(N\times \#Z)$ edges. Dinic's algorithm has complexity $O(\#\mathrm{Vertices}^2\#\mathrm{Edges})$ hence in our case it is $O(N^3\times \#Z)$.
- 
-Algorithm \ref{alg:mini} can be implented with complexity $O(N^3\# Z)$ under \eqref{hyp:A} and $O(N^3 \#Z \#V)$ under \eqref{hyp:B}.
+
+Algorithm \ref{alg:mini} can be implemented with complexity $O(N^3\# Z)$ under \eqref{hyp:A} and $O(N^3 \#Z \#V)$ under \eqref{hyp:B}.
 The graph $G_T$ has $O(N)$ vertices and $O(N\times \#Z)$ edges under assumption \eqref{hyp:A} and respectively $O(N\times \#Z)$ vertices and $O(N\times \#V)$ edges under assumption \eqref{hyp:B}. The loop at line \ref{lin:repeat} is iterated at most $N$ times since the distance between $T$ and $T'$ decreases at every iteration. Bellman-Ford algorithm has complexity $O(\#\mathrm{Vertices}\#\mathrm{Edges})$, which in our case amounts to $O(N^2\# Z)$ under \eqref{hyp:A} and $O(N^2 \#Z \#V)$ under \eqref{hyp:B}.
 
 \begin{algorithm}
@@ -637,7 +637,7 @@ We try to maximize $s^*$ defined in \eqref{eq:optimal}. So we can compute the op

 \subsection{Computation of a candidate assignment}

-To compute a candidate assignment (that does not optimize zone spreading nor distance to a previous assignment yet), we can use the folowing flow problem.
+To compute a candidate assignment (that does not optimize zone spreading nor distance to a previous assignment yet), we can use the following flow problem.

 Define the oriented weighted graph $(X,E)$. The set of vertices $X$ contains the source $\mathbf{s}$, the sink $\mathbf{t}$, vertices 
 $\mathbf{x}_p, \mathbf{u}^+_p, \mathbf{u}^-_p$ for every partition $p$, vertices $\mathbf{y}_{p,z}$ for every partition $p$ and zone $z$, and vertices $\mathbf{z}_v$ for every node $v$. 
@@ -680,14 +680,14 @@ Given the flow $f$, let $G_f=(X',E_f)$ be the multi-graph where $X' = X\setminus
 \end{itemize}
 To summarize, arcs are oriented left to right if they correspond to a presence of flow in $f$, and right to left if they correspond to an absence of flow. They are positively weighted if we want them to stay at their current state, and negatively if we want them to switch. Let us compute the weight of such graph.

-\begin{multline*}
+\begin{multiline*}
 	w(G_f)  = \sum_{e\in E_f} w(e_f)  \\
 	= 
 	(\alpha - \beta -\gamma) N_1 + (\alpha +\beta - \gamma) N_2 + (\alpha+\beta+\gamma) N_3 
 	\\ + 
 	\#V\times N - 4 \sum_p 3-\#(T_p\cap T'_p) \\ 
 	=(\#V-12+\alpha-\beta-\gamma)\times N + 4Q_V + 2\beta N_2 + 2(\beta+\gamma) N_3 \\
-\end{multline*}
+\end{multiline*}

 As for the mode 3-strict, one can check that the difference of two such graphs corresponding to the same $(n_v)$ is always eulerian. Hence we can navigate in this class with the same greedy algorithm that discovers positive cycles and flips them.

@@ -0,0 +1 @@
+.direnv/
@@ -0,0 +1,17 @@
+*
+
+!*.txt
+!*.md
+
+!assets
+
+!.gitignore
+!*.svg
+!*.png
+!*.jpg
+!*.tex
+!Makefile
+!.gitignore
+!assets/*.drawio.pdf
+
+!talk.pdf
@@ -0,0 +1,34 @@
+ASSETS=assets/consistent_hashing_1.pdf \
+	   assets/consistent_hashing_2.pdf \
+	   assets/consistent_hashing_3.pdf \
+	   assets/consistent_hashing_4.pdf \
+	   assets/garage_tables.pdf \
+	   assets/consensus.pdf_tex \
+	   assets/lattice1.pdf_tex \
+	   assets/lattice2.pdf_tex \
+	   assets/lattice3.pdf_tex \
+	   assets/lattice4.pdf_tex \
+	   assets/lattice5.pdf_tex \
+	   assets/lattice6.pdf_tex \
+	   assets/lattice7.pdf_tex \
+	   assets/lattice8.pdf_tex \
+	   assets/latticeB_1.pdf_tex \
+	   assets/latticeB_2.pdf_tex \
+	   assets/latticeB_3.pdf_tex \
+	   assets/latticeB_4.pdf_tex \
+	   assets/latticeB_5.pdf_tex \
+	   assets/latticeB_6.pdf_tex \
+	   assets/latticeB_7.pdf_tex \
+	   assets/latticeB_8.pdf_tex \
+	   assets/latticeB_9.pdf_tex \
+	   assets/latticeB_10.pdf_tex \
+	   assets/deuxfleurs.pdf
+
+talk.pdf: talk.tex $(ASSETS)
+	pdflatex talk.tex
+
+assets/%.pdf: assets/%.svg
+	inkscape -D -z --file=$^ --export-pdf=$@
+
+assets/%.pdf_tex: assets/%.svg
+	inkscape -D -z --file=$^ --export-pdf=$@ --export-latex
@@ -0,0 +1,39 @@
+### (fr) Garage, un système de stockage de données géo-distribué léger et robuste
+
+Garage est un système de stockage de données léger, géo-distribué, qui
+implémente le protocole de stockage S3 de Amazon. Garage est destiné
+principalement à l'auto-hébergement sur du matériel courant d'occasion. À ce
+titre, il doit tolérer un grand nombre de pannes: coupures de courant, coupures
+de connexion Internet, pannes de machines, ... Il doit également être facile à
+déployer et à maintenir, afin de pouvoir être facilement utilisé par des
+amateurs ou des petites organisations.
+
+Cette présentation vous proposera un aperçu de Garage et du choix technique
+principal qui rend un système comme Garage possible: le refus d'utiliser des
+algorithmes de consensus, remplacés avantageusement par des méthodes à
+cohérence faible.  Notre modèle est fortement inspiré de la base de donnée
+Dynamo (DeCandia et al, 2007), et fait usage des types de données CRDT (Shapiro
+et al, 2011).  Nous exploreront comment ces méthodes s'appliquent à la
+construction de l'abstraction "stockage objet" dans un système distribué, et
+quelles autres abstractions peuvent ou ne peuvent pas être construites dans ce
+modèle.
+
+### (en) Garage, a lightweight and robust geo-distributed data storage system
+
+Garage is a lightweight geo-distributed data store that implements the Amazon
+S3 object storage protocol.  Garage is meant primarily for self-hosting at home
+on second-hand commodity hardware, meaning it has to tolerate a wide variety of
+failure scenarios such as power cuts, Internet disconnections and machine
+crashes. It also has to be easy to deploy and maintain, so that hobbyists and
+small organizations can use it without trouble. 
+
+This talk will present Garage and the key technical choice that made Garage
+possible: refusing to use consensus algorithms and using instead weak
+consistency methods, with a model that is loosely based on that of the Dynamo
+database (DeCandia et al, 2007) and that makes heavy use of conflict-free
+replicated data types (Shapiro et al, 2011).  We will explore how these methods
+are suited to building the "object store" abstraction in a distributed system,
+and what other abstractions are possible or impossible to build in this model.
+
+
+
@@ -0,0 +1,137 @@
+<?xml version="1.0" encoding="UTF-8" standalone="no"?>
+<!-- Created with Inkscape (http://www.inkscape.org/) -->
+
+<svg
+   width="800"
+   height="300"
+   viewBox="0 0 211.66666 79.374999"
+   version="1.1"
+   id="svg5"
+   inkscape:version="1.2.2 (b0a8486541, 2022-12-01)"
+   sodipodi:docname="consensus.svg"
+   xmlns:inkscape="http://www.inkscape.org/namespaces/inkscape"
+   xmlns:sodipodi="http://sodipodi.sourceforge.net/DTD/sodipodi-0.dtd"
+   xmlns="http://www.w3.org/2000/svg"
+   xmlns:svg="http://www.w3.org/2000/svg">
+  <sodipodi:namedview
+     id="namedview7"
+     pagecolor="#ffffff"
+     bordercolor="#666666"
+     borderopacity="1.0"
+     inkscape:showpageshadow="2"
+     inkscape:pageopacity="0.0"
+     inkscape:pagecheckerboard="0"
+     inkscape:deskcolor="#d1d1d1"
+     inkscape:document-units="mm"
+     showgrid="false"
+     inkscape:zoom="1.4734708"
+     inkscape:cx="310.49139"
+     inkscape:cy="179.1688"
+     inkscape:window-width="1920"
+     inkscape:window-height="999"
+     inkscape:window-x="0"
+     inkscape:window-y="0"
+     inkscape:window-maximized="1"
+     inkscape:current-layer="layer1" />
+  <defs
+     id="defs2">
+    <marker
+       style="overflow:visible"
+       id="Arrow2"
+       refX="0"
+       refY="0"
+       orient="auto-start-reverse"
+       inkscape:stockid="Arrow2"
+       markerWidth="7.6999998"
+       markerHeight="5.5999999"
+       viewBox="0 0 7.7 5.6"
+       inkscape:isstock="true"
+       inkscape:collect="always"
+       preserveAspectRatio="xMidYMid">
+      <path
+         transform="scale(0.7)"
+         d="M -2,-4 9,0 -2,4 c 2,-2.33 2,-5.66 0,-8 z"
+         style="fill:context-stroke;fill-rule:evenodd;stroke:none"
+         id="arrow2L" />
+    </marker>
+  </defs>
+  <g
+     inkscape:label="Layer 1"
+     inkscape:groupmode="layer"
+     id="layer1">
+    <g
+       id="g1218"
+       transform="translate(-8.9161476,-12.502301)">
+      <circle
+         style="fill:#ffffff;stroke:#000000;stroke-width:1;stroke-dasharray:none;stroke-opacity:1"
+         id="path111"
+         cx="38.904896"
+         cy="37.936272"
+         r="13.474442" />
+      <text
+         xml:space="preserve"
+         style="font-size:8.46667px;line-height:1.25;font-family:sans-serif;text-align:center;text-anchor:middle;stroke-width:0.264583;fill:#000000"
+         x="38.879501"
+         y="40.908073"
+         id="text1105"><tspan
+           sodipodi:role="line"
+           id="tspan1103"
+           style="stroke-width:0.264583;fill:#000000"
+           x="38.879501"
+           y="40.908073">$\bot$</tspan></text>
+    </g>
+    <g
+       id="g1218-3"
+       transform="translate(127.41938,-12.502301)">
+      <circle
+         style="fill:#ffffff;stroke:#000000;stroke-width:1;stroke-dasharray:none;stroke-opacity:1"
+         id="path111-5"
+         cx="38.904896"
+         cy="37.936272"
+         r="13.474442" />
+      <text
+         xml:space="preserve"
+         style="font-size:8.46667px;line-height:1.25;font-family:sans-serif;text-align:center;text-anchor:middle;stroke-width:0.264583;fill:#000000"
+         x="38.879501"
+         y="40.908073"
+         id="text1105-6"><tspan
+           sodipodi:role="line"
+           id="tspan1103-2"
+           style="stroke-width:0.264583;fill:#000000"
+           x="38.879501"
+           y="40.908073">$x$</tspan></text>
+    </g>
+    <path
+       style="fill:none;stroke:#000000;stroke-width:1;stroke-linecap:butt;stroke-linejoin:miter;stroke-dasharray:none;stroke-opacity:1;marker-end:url(#Arrow2)"
+       d="M 44.289635,25.433971 H 145.90576"
+       id="path1414"
+       sodipodi:nodetypes="cc" />
+    <text
+       xml:space="preserve"
+       style="font-size:8.46667px;line-height:1.25;font-family:sans-serif;text-align:center;text-anchor:middle;stroke-width:0.264583;fill:#000000"
+       x="92.729836"
+       y="21.781803"
+       id="text2092"><tspan
+         sodipodi:role="line"
+         id="tspan2090"
+         style="stroke-width:0.264583;fill:#000000"
+         x="92.729836"
+         y="21.781803">$propose(x) / x$</tspan></text>
+    <text
+       xml:space="preserve"
+       style="font-size:8.46667px;line-height:1.25;font-family:sans-serif;text-align:center;text-anchor:middle;stroke-width:0.264583;fill:#000000"
+       x="166.29887"
+       y="69.89299"
+       id="text2092-9"><tspan
+         sodipodi:role="line"
+         id="tspan2090-1"
+         style="stroke-width:0.264583;fill:#000000"
+         x="166.29887"
+         y="69.89299">$propose(y) / x$</tspan></text>
+    <path
+       style="fill:none;stroke:#000000;stroke-width:1;stroke-linecap:butt;stroke-linejoin:miter;stroke-dasharray:none;stroke-opacity:1;marker-end:url(#Arrow2)"
+       d="m 155.82329,35.899857 c -8.35129,12.319651 0.54055,24.640898 11.72797,24.072085 8.65403,-0.440005 18.59818,-11.705963 11.8146,-20.570891"
+       id="path2150"
+       sodipodi:nodetypes="csc" />
+  </g>
+</svg>
@@ -0,0 +1,91 @@
+<?xml version="1.0" encoding="UTF-8" standalone="no"?>
+<svg
+   viewBox="0 0 70.424515 70.300102"
+   version="1.1"
+   id="svg8"
+   sodipodi:docname="logo.svg"
+   inkscape:version="1.1 (c68e22c387, 2021-05-23)"
+   inkscape:export-filename="/home/quentin/Documents/dev/deuxfleurs/site/src/img/logo.png"
+   inkscape:export-xdpi="699.30194"
+   inkscape:export-ydpi="699.30194"
+   width="70.424515"
+   height="70.300102"
+   xmlns:inkscape="http://www.inkscape.org/namespaces/inkscape"
+   xmlns:sodipodi="http://sodipodi.sourceforge.net/DTD/sodipodi-0.dtd"
+   xmlns="http://www.w3.org/2000/svg"
+   xmlns:svg="http://www.w3.org/2000/svg">
+  <defs
+     id="defs12" />
+  <sodipodi:namedview
+     id="namedview10"
+     pagecolor="#ffffff"
+     bordercolor="#666666"
+     borderopacity="1.0"
+     inkscape:pageshadow="2"
+     inkscape:pageopacity="0.0"
+     inkscape:pagecheckerboard="0"
+     showgrid="false"
+     inkscape:zoom="12.125"
+     inkscape:cx="43.092783"
+     inkscape:cy="48.082474"
+     inkscape:window-width="3072"
+     inkscape:window-height="1659"
+     inkscape:window-x="0"
+     inkscape:window-y="0"
+     inkscape:window-maximized="1"
+     inkscape:current-layer="svg8" />
+  <g
+     id="g79969"
+     transform="translate(-0.827,34.992103)">
+    <path
+       fill="#ffffff"
+       d="m 15.632,34.661 c -0.799,-0.597 -1.498,-1.484 -2.035,-2.592 l -0.228,-0.47 -0.46,0.249 c -0.975,0.528 -1.913,0.858 -2.744,0.969 L 9.963,29.061 6.327,30.029 C 6.17,29.175 6.202,28.142 6.423,27.007 L 6.526,26.482 5.994,26.416 C 4.752,26.262 3.688,25.891 2.89,25.336 L 4.411,22.419 1.423,20.896 C 1.742,19.952 2.371,19.014 3.257,18.161 L 3.634,17.798 3.255,17.438 C 2.452,16.674 1.847,15.884 1.485,15.127 L 4.995,13.774 2.95,10.615 C 3.69,10.213 4.643,9.929 5.739,9.783 L 6.258,9.715 6.167,9.201 C 5.952,7.99 5.995,6.863 6.291,5.913 l 3.308,0.523 0.524,-3.308 c 0.988,0.013 2.08,0.326 3.164,0.907 L 13.749,4.283 13.975,3.81 C 14.454,2.807 15.019,1.986 15.628,1.406 L 18,4.326 20.372,1.406 c 0.609,0.58 1.175,1.401 1.653,2.404 l 0.226,0.473 0.462,-0.247 C 23.798,3.455 24.891,3.142 25.877,3.13 L 26.4,6.438 29.71,5.913 c 0.296,0.951 0.34,2.078 0.124,3.288 l -0.092,0.515 0.518,0.069 c 1.095,0.145 2.048,0.43 2.788,0.832 l -2.046,3.156 3.511,1.355 c -0.361,0.757 -0.966,1.547 -1.77,2.311 l -0.379,0.36 0.377,0.363 c 0.888,0.854 1.516,1.793 1.835,2.736 l -2.984,1.52 1.521,2.984 c -0.812,0.574 -1.871,0.964 -3.094,1.134 l -0.518,0.072 0.096,0.514 c 0.201,1.089 0.226,2.083 0.073,2.909 l -3.634,-0.97 -0.204,3.757 c -0.83,-0.11 -1.768,-0.44 -2.742,-0.968 l -0.459,-0.249 -0.228,0.47 c -0.539,1.107 -1.237,1.994 -2.036,2.591 L 18,32.293 Z"
+       id="path2" />
+    <path
+       d="M 7.092,10.678 C 6.562,9.189 6.394,7.708 6.66,6.478 l 2.368,0.375 0.987,0.156 0.157,-0.988 0.375,-2.368 C 11.808,3.78 13.16,4.396 14.409,5.359 14.527,5.022 14.653,4.696 14.791,4.392 13.24,3.257 11.568,2.629 10.061,2.629 9.938,2.629 9.816,2.633 9.695,2.642 L 9.184,5.865 5.96,5.354 C 5.36,6.841 5.395,8.769 6.045,10.747 6.38,10.71 6.729,10.686 7.092,10.678 Z M 21.593,5.359 c 1.248,-0.962 2.6,-1.578 3.86,-1.705 l 0.376,2.368 0.156,0.988 0.987,-0.157 2.369,-0.376 c 0.266,1.23 0.098,2.71 -0.432,4.2 0.361,0.009 0.711,0.032 1.046,0.07 C 30.606,8.769 30.64,6.841 30.04,5.353 L 26.815,5.865 26.304,2.641 c -0.12,-0.008 -0.242,-0.012 -0.365,-0.012 -1.507,0 -3.179,0.628 -4.73,1.762 0.14,0.306 0.266,0.631 0.384,0.968 z M 7.368,27 h 0.035 c 0.067,0 0.157,-0.604 0.26,-0.947 -0.098,0.004 -0.197,0.046 -0.294,0.046 -1.496,0 -2.826,-0.303 -3.83,-0.89 L 4.628,23.081 5.082,22.194 4.191,21.742 2.055,20.654 C 2.563,19.503 3.57,18.404 4.873,17.511 4.586,17.292 4.312,17.07 4.063,16.842 2.376,18.059 1.217,19.597 0.828,21.152 l 2.908,1.483 -1.482,2.843 C 3.475,26.501 5.303,27 7.368,27 Z m 27.806,-5.846 c -0.39,-1.555 -1.548,-3.093 -3.234,-4.311 -0.25,0.228 -0.523,0.451 -0.81,0.669 1.304,0.893 2.31,1.992 2.817,3.145 l -2.136,1.088 -0.891,0.453 0.454,0.892 1.089,2.137 c -1.004,0.587 -2.332,0.904 -3.828,0.904 -0.099,0 -0.199,-0.01 -0.299,-0.013 0.103,0.344 0.192,0.683 0.26,1.011 l 0.039,0.002 c 2.066,0 3.892,-0.563 5.112,-1.587 l -1.482,-2.908 z m -12.653,9.182 c -0.447,1.517 -1.181,2.812 -2.119,3.651 L 18.707,32.293 18,31.586 l -0.707,0.707 -1.695,1.694 c -0.938,-0.839 -1.673,-2.136 -2.12,-3.652 -0.296,0.206 -0.593,0.397 -0.886,0.563 0.636,1.98 1.741,3.559 3.1,4.409 L 18,33 l 2.308,2.308 c 1.358,-0.851 2.464,-2.428 3.101,-4.408 -0.295,-0.168 -0.591,-0.359 -0.888,-0.564 z"
+       fill="#ea596e"
+       id="path4" />
+    <path
+       fill="#ea596e"
+       d="m 20.118,5.683 c 0.426,1.146 0.748,2.596 0.841,4.284 l 0.2,3.683 3.564,-0.946 c 1.32,-0.351 2.655,-0.536 3.86,-0.536 0.16,0 0.318,0.003 0.474,0.01 l -1.827,2.819 3.139,1.211 c -0.958,0.759 -2.237,1.514 -3.814,2.123 l -3.441,1.328 2.001,3.099 c 0.918,1.42 1.509,2.782 1.838,3.96 L 23.709,25.853 23.527,29.21 C 22.508,28.533 21.395,27.55 20.329,26.237 L 18,23.374 15.672,26.236 c -1.066,1.312 -2.179,2.295 -3.198,2.972 l -0.18,-3.354 -3.248,0.864 c 0.329,-1.178 0.921,-2.54 1.839,-3.961 L 12.889,19.658 9.447,18.33 C 7.87,17.721 6.591,16.967 5.633,16.208 L 8.768,15 6.941,12.177 c 0.155,-0.006 0.313,-0.01 0.473,-0.01 1.206,0 2.541,0.185 3.861,0.536 l 3.564,0.947 0.202,-3.683 c 0.092,-1.688 0.415,-3.138 0.84,-4.284 L 18,8.292 20.118,5.683 M 20.308,0.692 18,3.533 15.692,0.692 C 13.703,2.224 12.271,5.684 12.046,9.804 10.429,9.374 8.854,9.167 7.414,9.167 c -2.11,0 -3.929,0.445 -5.161,1.289 l 1.989,3.073 -3.415,1.316 c 0.842,2.366 3.69,4.797 7.54,6.283 -2.241,3.465 -3.116,7.106 -2.407,9.516 l 3.537,-0.941 0.196,3.654 c 2.512,-0.07 5.703,-2.027 8.307,-5.228 2.603,3.201 5.796,5.158 8.306,5.228 l 0.198,-3.655 3.535,0.943 c 0.71,-2.411 -0.165,-6.05 -2.404,-9.517 3.849,-1.485 6.696,-3.918 7.538,-6.283 l -3.415,-1.318 1.99,-3.07 c -1.233,-0.844 -3.053,-1.29 -5.164,-1.29 -1.438,0 -3.013,0.207 -4.63,0.636 C 23.729,5.684 22.297,2.224 20.308,0.692 Z"
+       id="path6" />
+  </g>
+  <g
+     id="g79964"
+     transform="translate(-1.043816,35.993714)">
+    <path
+       fill="#ffffff"
+       d="m 51.92633,-2.0247139 c -0.799,-0.597 -1.498,-1.484 -2.035,-2.592 l -0.228,-0.47 -0.46,0.249 c -0.975,0.528 -1.913,0.858 -2.744,0.969 l -0.202,-3.7560001 -3.636,0.968 c -0.157,-0.854 -0.125,-1.887 0.096,-3.022 l 0.103,-0.525 -0.532,-0.066 c -1.242,-0.154 -2.306,-0.525 -3.104,-1.08 l 1.521,-2.917 -2.988,-1.523 c 0.319,-0.944 0.948,-1.882 1.834,-2.735 l 0.377,-0.363 -0.379,-0.36 c -0.803,-0.764 -1.408,-1.554 -1.77,-2.311 l 3.51,-1.353 -2.045,-3.159 c 0.74,-0.402 1.693,-0.686 2.789,-0.832 l 0.519,-0.068 -0.091,-0.514 c -0.215,-1.211 -0.172,-2.338 0.124,-3.288 l 3.308,0.523 0.524,-3.308 c 0.988,0.013 2.08,0.326 3.164,0.907 l 0.462,0.248 0.226,-0.473 c 0.479,-1.003 1.044,-1.824 1.653,-2.404 l 2.372,2.92 2.372,-2.92 c 0.609,0.58 1.175,1.401 1.653,2.404 l 0.226,0.473 0.462,-0.247 c 1.085,-0.581 2.178,-0.894 3.164,-0.906 l 0.523,3.308 3.31,-0.525 c 0.296,0.951 0.34,2.078 0.124,3.288 l -0.092,0.515 0.518,0.069 c 1.095,0.145 2.048,0.43 2.788,0.832 l -2.046,3.156 3.511,1.355 c -0.361,0.757 -0.966,1.547 -1.77,2.311 l -0.379,0.36 0.377,0.363 c 0.888,0.854 1.516,1.793 1.835,2.736 l -2.984,1.52 1.521,2.984 c -0.812,0.574 -1.871,0.964 -3.094,1.134 l -0.518,0.072 0.096,0.514 c 0.201,1.089 0.226,2.083 0.073,2.909 l -3.634,-0.97 -0.204,3.7570001 c -0.83,-0.11 -1.768,-0.44 -2.742,-0.968 l -0.459,-0.249 -0.228,0.47 c -0.539,1.107 -1.237,1.994 -2.036,2.591 l -2.367,-2.369 z"
+       id="path2-9" />
+    <path
+       d="m 43.38633,-26.007714 c -0.53,-1.489 -0.698,-2.97 -0.432,-4.2 l 2.368,0.375 0.987,0.156 0.157,-0.988 0.375,-2.368 c 1.261,0.127 2.613,0.743 3.862,1.706 0.118,-0.337 0.244,-0.663 0.382,-0.967 -1.551,-1.135 -3.223,-1.763 -4.73,-1.763 -0.123,0 -0.245,0.004 -0.366,0.013 l -0.511,3.223 -3.224,-0.511 c -0.6,1.487 -0.565,3.415 0.085,5.393 0.335,-0.037 0.684,-0.061 1.047,-0.069 z m 14.501,-5.319 c 1.248,-0.962 2.6,-1.578 3.86,-1.705 l 0.376,2.368 0.156,0.988 0.987,-0.157 2.369,-0.376 c 0.266,1.23 0.098,2.71 -0.432,4.2 0.361,0.009 0.711,0.032 1.046,0.07 0.651,-1.978 0.685,-3.906 0.085,-5.394 l -3.225,0.512 -0.511,-3.224 c -0.12,-0.008 -0.242,-0.012 -0.365,-0.012 -1.507,0 -3.179,0.628 -4.73,1.762 0.14,0.306 0.266,0.631 0.384,0.968 z m -14.225,21.641 h 0.035 c 0.067,0 0.157,-0.604 0.26,-0.947 -0.098,0.004 -0.197,0.046 -0.294,0.046 -1.496,0 -2.826,-0.303 -3.83,-0.89 l 1.089,-2.128 0.454,-0.887 -0.891,-0.452 -2.136,-1.088 c 0.508,-1.151 1.515,-2.25 2.818,-3.143 -0.287,-0.219 -0.561,-0.441 -0.81,-0.669 -1.687,1.217 -2.846,2.755 -3.235,4.31 l 2.908,1.483 -1.482,2.843 c 1.221,1.023 3.049,1.522 5.114,1.522 z m 27.806,-5.846 c -0.39,-1.555 -1.548,-3.093 -3.234,-4.311 -0.25,0.228 -0.523,0.451 -0.81,0.669 1.304,0.893 2.31,1.992 2.817,3.145 l -2.136,1.088 -0.891,0.453 0.454,0.892 1.089,2.137 c -1.004,0.587 -2.332,0.904 -3.828,0.904 -0.099,0 -0.199,-0.01 -0.299,-0.013 0.103,0.344 0.192,0.683 0.26,1.011 l 0.039,0.002 c 2.066,0 3.892,-0.563 5.112,-1.587 l -1.482,-2.908 z m -12.653,9.182 c -0.447,1.5170001 -1.181,2.8120001 -2.119,3.6510001 l -1.695,-1.694 -0.707,-0.707 -0.707,0.707 -1.695,1.694 c -0.938,-0.839 -1.673,-2.136 -2.12,-3.6520001 -0.296,0.2060001 -0.593,0.3970001 -0.886,0.5630001 0.636,1.98 1.741,3.559 3.1,4.409 l 2.308,-2.307 2.308,2.308 c 1.358,-0.851 2.464,-2.428 3.101,-4.408 -0.295,-0.168 -0.591,-0.359 -0.888,-0.5640001 z"
+       fill="#ea596e"
+       id="path4-3" />
+    <path
+       fill="#ea596e"
+       d="m 56.41233,-31.002714 c 0.426,1.146 0.748,2.596 0.841,4.284 l 0.2,3.683 3.564,-0.946 c 1.32,-0.351 2.655,-0.536 3.86,-0.536 0.16,0 0.318,0.003 0.474,0.01 l -1.827,2.819 3.139,1.211 c -0.958,0.759 -2.237,1.514 -3.814,2.123 l -3.441,1.328 2.001,3.099 c 0.918,1.42 1.509,2.782 1.838,3.96 l -3.244,-0.865 -0.182,3.357 c -1.019,-0.677 -2.132,-1.66 -3.198,-2.973 l -2.329,-2.863 -2.328,2.862 c -1.066,1.312 -2.179,2.295 -3.198,2.972 l -0.18,-3.354 -3.248,0.864 c 0.329,-1.178 0.921,-2.54 1.839,-3.961 l 2.004,-3.099 -3.442,-1.328 c -1.577,-0.609 -2.856,-1.363 -3.814,-2.122 l 3.135,-1.208 -1.827,-2.823 c 0.155,-0.006 0.313,-0.01 0.473,-0.01 1.206,0 2.541,0.185 3.861,0.536 l 3.564,0.947 0.202,-3.683 c 0.092,-1.688 0.415,-3.138 0.84,-4.284 l 2.119,2.609 2.118,-2.609 m 0.19,-4.991 -2.308,2.841 -2.308,-2.841 c -1.989,1.532 -3.421,4.992 -3.646,9.112 -1.617,-0.43 -3.192,-0.637 -4.632,-0.637 -2.11,0 -3.929,0.445 -5.161,1.289 l 1.989,3.073 -3.415,1.316 c 0.842,2.366 3.69,4.797 7.54,6.283 -2.241,3.465 -3.116,7.106 -2.407,9.5160001 l 3.537,-0.9410001 0.196,3.6540001 c 2.512,-0.07 5.703,-2.027 8.307,-5.2280001 2.603,3.2010001 5.796,5.1580001 8.306,5.2280001 l 0.198,-3.6550001 3.535,0.9430001 c 0.71,-2.4110001 -0.165,-6.0500001 -2.404,-9.5170001 3.849,-1.485 6.696,-3.918 7.538,-6.283 l -3.415,-1.318 1.99,-3.07 c -1.233,-0.844 -3.053,-1.29 -5.164,-1.29 -1.438,0 -3.013,0.207 -4.63,0.636 -0.225,-4.119 -1.657,-7.579 -3.646,-9.111 z"
+       id="path6-6" />
+  </g>
+  <text
+     xml:space="preserve"
+     style="font-style:normal;font-weight:normal;font-size:42.6667px;line-height:1.25;font-family:sans-serif;fill:#ea596e;fill-opacity:1;stroke:none"
+     x="2.2188232"
+     y="31.430677"
+     id="text46212"><tspan
+       sodipodi:role="line"
+       id="tspan46210"
+       x="2.2188232"
+       y="31.430677"
+       style="font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;font-size:42.6667px;font-family:'TeX Gyre Termes';-inkscape-font-specification:'TeX Gyre Termes'">D</tspan></text>
+  <text
+     xml:space="preserve"
+     style="font-style:normal;font-weight:normal;font-size:42.6667px;line-height:1.25;font-family:sans-serif;fill:#ea596e;fill-opacity:1;stroke:none"
+     x="41.347008"
+     y="67.114784"
+     id="text46212-1"><tspan
+       sodipodi:role="line"
+       id="tspan46210-5"
+       x="41.347008"
+       y="67.114784"
+       style="font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;font-size:42.6667px;font-family:'TeX Gyre Termes';-inkscape-font-specification:'TeX Gyre Termes'">F</tspan></text>
+</svg>
--- a/Show More
+++ b/Show More