Merge pull request 'add extraVolumes and extraVolumeMounts to helm chart' (#896) from eugene-davis/garage:main into main

Reviewed-on: Deuxfleurs/garage#896
Reviewed-by: maximilien <me@mricher.fr>

.cargo/config.toml

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

.drone.yml

@@ -1,478 +0,0 @@
----
-kind: pipeline
-name: default
-
-workspace:
-  base: /drone/garage
-
-volumes:
-- name: nix_store
-  host:
-    path: /var/lib/drone/nix
-- name: nix_config
-  temp: {}
-
-environment:
-  HOME: /drone/garage
-
-steps:
-  - name: setup nix
-    image: nixpkgs/nix:nixos-21.05
-    volumes:
-    - name: nix_store
-      path: /nix
-    - name: nix_config
-      path: /etc/nix
-    commands:
-      - cp nix/nix.conf /etc/nix/nix.conf
-      - nix-build --no-build-output --no-out-link shell.nix --arg release false  -A inputDerivation
-
-  - name: code quality
-    image: nixpkgs/nix:nixos-21.05
-    volumes:
-    - name: nix_store
-      path: /nix
-    - name: nix_config
-      path: /etc/nix
-    commands:
-      - nix-shell --arg release false --run "cargo fmt -- --check"
-      - nix-shell --arg release false --run "cargo clippy -- --deny warnings"
-
-  - name: build
-    image: nixpkgs/nix:nixos-21.05
-    volumes:
-    - name: nix_store
-      path: /nix
-    - name: nix_config
-      path: /etc/nix
-    commands:
-      - nix-build --no-build-output --option log-lines 100 --argstr target x86_64-unknown-linux-musl --arg release false --argstr git_version $DRONE_COMMIT
-
-  - name: unit + func tests
-    image: nixpkgs/nix:nixos-21.05
-    environment:
-      GARAGE_TEST_INTEGRATION_EXE: result/bin/garage
-    volumes:
-    - name: nix_store
-      path: /nix
-    - name: nix_config
-      path: /etc/nix
-    commands:
-      - |
-        nix-build \
-          --no-build-output \
-          --option log-lines 100 \
-          --argstr target x86_64-unknown-linux-musl \
-          --argstr compileMode test
-      - ./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-*
-
-  - name: smoke-test
-    image: nixpkgs/nix:nixos-21.05
-    volumes:
-    - name: nix_store
-      path: /nix
-    - name: nix_config
-      path: /etc/nix
-    commands:
-      - nix-build --no-build-output --argstr target x86_64-unknown-linux-musl --arg release false --argstr git_version $DRONE_COMMIT
-      - nix-shell --arg release false --run ./script/test-smoke.sh || (cat /tmp/garage.log; false)
-
-trigger:
-  event:
-  - custom
-  - push
-  - pull_request
-  - tag
-  - cron
-
-node:
-  nix: 1
-
----
-kind: pipeline
-type: docker
-name: release-linux-x86_64
-
-volumes:
-- name: nix_store
-  host:
-    path: /var/lib/drone/nix
-- name: nix_config
-  temp: {}
-
-environment:
-  TARGET: x86_64-unknown-linux-musl
-
-steps:
-  - name: setup nix
-    image: nixpkgs/nix:nixos-21.05
-    volumes:
-    - name: nix_store
-      path: /nix
-    - name: nix_config
-      path: /etc/nix
-    commands:
-      - cp nix/nix.conf /etc/nix/nix.conf
-      - nix-build --no-build-output --no-out-link shell.nix -A inputDerivation
-
-  - name: build
-    image: nixpkgs/nix:nixos-21.05
-    volumes:
-    - name: nix_store
-      path: /nix
-    - name: nix_config
-      path: /etc/nix
-    commands:
-      - nix-build --no-build-output --argstr target $TARGET --arg release true --argstr git_version $DRONE_COMMIT
-
-  - name: integration
-    image: nixpkgs/nix:nixos-21.05
-    volumes:
-    - name: nix_store
-      path: /nix
-    - name: nix_config
-      path: /etc/nix
-    commands:
-      - nix-shell --run ./script/test-smoke.sh || (cat /tmp/garage.log; false)
-
-  - name: push static binary
-    image: nixpkgs/nix:nixos-21.05
-    volumes:
-    - name: nix_store
-      path: /nix
-    - name: nix_config
-      path: /etc/nix
-    environment:
-      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 --arg rust false --arg integration false --run "to_s3"
-
-  - name: docker build and publish
-    image: nixpkgs/nix:nixos-21.05
-    volumes:
-    - name: nix_store
-      path: /nix
-    - name: nix_config
-      path: /etc/nix
-    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 --arg rust false --arg integration false --run "to_docker"
-
-
-trigger:
-  event:
-  - promote
-  - cron
-
-node:
-  nix: 1
-
----
-kind: pipeline
-type: docker
-name: release-linux-i686
-
-volumes:
-- name: nix_store
-  host:
-    path: /var/lib/drone/nix
-- name: nix_config
-  temp: {}
-
-environment:
-  TARGET: i686-unknown-linux-musl
-
-steps:
-  - name: setup nix
-    image: nixpkgs/nix:nixos-21.05
-    volumes:
-    - name: nix_store
-      path: /nix
-    - name: nix_config
-      path: /etc/nix
-    commands:
-      - cp nix/nix.conf /etc/nix/nix.conf
-      - nix-build --no-build-output --no-out-link shell.nix -A inputDerivation
-
-  - name: build
-    image: nixpkgs/nix:nixos-21.05
-    volumes:
-    - name: nix_store
-      path: /nix
-    - name: nix_config
-      path: /etc/nix
-    commands:
-      - nix-build --no-build-output --argstr target $TARGET --arg release true --argstr git_version $DRONE_COMMIT
-
-  - name: integration
-    image: nixpkgs/nix:nixos-21.05
-    volumes:
-    - name: nix_store
-      path: /nix
-    - name: nix_config
-      path: /etc/nix
-    commands:
-      - nix-shell --run ./script/test-smoke.sh || (cat /tmp/garage.log; false)
-
-  - name: push static binary
-    image: nixpkgs/nix:nixos-21.05
-    volumes:
-    - name: nix_store
-      path: /nix
-    - name: nix_config
-      path: /etc/nix
-    environment:
-      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 --arg rust false --arg integration false --run "to_s3"
-
-  - name: docker build and publish
-    image: nixpkgs/nix:nixos-21.05
-    volumes:
-    - name: nix_store
-      path: /nix
-    - name: nix_config
-      path: /etc/nix
-    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 --arg rust false --arg integration false --run "to_docker"
-
-trigger:
-  event:
-  - promote
-  - cron
-
-node:
-  nix: 1
-
----
-kind: pipeline
-type: docker
-name: release-linux-aarch64
-
-volumes:
-- name: nix_store
-  host:
-    path: /var/lib/drone/nix
-- name: nix_config
-  temp: {}
-
-environment:
-  TARGET: aarch64-unknown-linux-musl
-
-steps:
-  - name: setup nix
-    image: nixpkgs/nix:nixos-21.05
-    volumes:
-    - name: nix_store
-      path: /nix
-    - name: nix_config
-      path: /etc/nix
-    commands:
-      - cp nix/nix.conf /etc/nix/nix.conf
-      - nix-build --no-build-output --no-out-link ./shell.nix --arg rust false --arg integration false -A inputDerivation
-
-  - name: build
-    image: nixpkgs/nix:nixos-21.05
-    volumes:
-    - name: nix_store
-      path: /nix
-    - name: nix_config
-      path: /etc/nix
-    commands:
-      - nix-build --no-build-output --argstr target $TARGET --arg release true --argstr git_version $DRONE_COMMIT
-
-  - name: push static binary
-    image: nixpkgs/nix:nixos-21.05
-    volumes:
-    - name: nix_store
-      path: /nix
-    - name: nix_config
-      path: /etc/nix
-    environment:
-      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 --arg rust false --arg integration false --run "to_s3"
-
-  - name: docker build and publish
-    image: nixpkgs/nix:nixos-21.05
-    volumes:
-    - name: nix_store
-      path: /nix
-    - name: nix_config
-      path: /etc/nix
-    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 --arg rust false --arg integration false --run "to_docker"
-
-trigger:
-  event:
-  - promote
-  - cron
-
-node:
-  nix: 1
-
----
-kind: pipeline
-type: docker
-name: release-linux-armv6l
-
-volumes:
-- name: nix_store
-  host:
-    path: /var/lib/drone/nix
-- name: nix_config
-  temp: {}
-
-environment:
-  TARGET: armv6l-unknown-linux-musleabihf
-
-steps:
-  - name: setup nix
-    image: nixpkgs/nix:nixos-21.05
-    volumes:
-    - name: nix_store
-      path: /nix
-    - name: nix_config
-      path: /etc/nix
-    commands:
-      - cp nix/nix.conf /etc/nix/nix.conf
-      - nix-build --no-build-output --no-out-link --arg rust false --arg integration false -A inputDerivation
-
-  - name: build
-    image: nixpkgs/nix:nixos-21.05
-    volumes:
-    - name: nix_store
-      path: /nix
-    - name: nix_config
-      path: /etc/nix
-    commands:
-      - nix-build --no-build-output --argstr target $TARGET --arg release true --argstr git_version $DRONE_COMMIT
-
-  - name: push static binary
-    image: nixpkgs/nix:nixos-21.05
-    volumes:
-    - name: nix_store
-      path: /nix
-    - name: nix_config
-      path: /etc/nix
-    environment:
-      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 --arg integration false --arg rust false --run "to_s3"
-
-  - name: docker build and publish
-    image: nixpkgs/nix:nixos-21.05
-    volumes:
-    - name: nix_store
-      path: /nix
-    - name: nix_config
-      path: /etc/nix
-    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 --arg rust false --arg integration false --run "to_docker"
-
-trigger:
-  event:
-  - promote
-  - cron
-
-node:
-  nix: 1
-
----
-kind: pipeline
-type: docker
-name: refresh-release-page
-
-volumes:
-- name: nix_store
-  host:
-    path: /var/lib/drone/nix
-
-steps:
-  - name: refresh-index
-    image: nixpkgs/nix:nixos-21.05
-    volumes:
-    - name: nix_store
-      path: /nix
-    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 --arg integration false --arg rust false --run "refresh_index"
-
-depends_on:
-  - release-linux-x86_64
-  - release-linux-i686
-  - release-linux-aarch64
-  - release-linux-armv6l
-
-trigger:
-  event:
-  - promote
-  - cron
-
-node:
-  nix: 1
-
----
-kind: signature
-hmac: 3fc19d6f9a3555519c8405e3281b2e74289bb802f644740d5481d53df3a01fa4
-
-...

.envrc

@@ -0,0 +1 @@
+use flake

.gitattributes

@@ -1 +0,0 @@
-*.pdf filter=lfs diff=lfs merge=lfs -text

.gitignore

@@ -3,3 +3,4 @@
 /pki
 **/*.rs.bk
 *.swp
+/.direnv

.woodpecker/debug.yaml

@@ -0,0 +1,47 @@
+when:
+  event:
+  - push
+  - tag
+  - pull_request
+  - deployment
+  - cron
+  - manual
+
+steps:
+  - name: check formatting
+    image: nixpkgs/nix:nixos-22.05
+    commands:
+      - nix-shell --attr devShell --run "cargo fmt -- --check"
+
+  - name: build
+    image: nixpkgs/nix:nixos-22.05
+    commands:
+      - nix-build --no-build-output --attr clippy.amd64 --argstr git_version ${CI_COMMIT_TAG:-$CI_COMMIT_SHA}
+
+  - 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 ${CI_COMMIT_TAG:-$CI_COMMIT_SHA}
+      - 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-*
+      - GARAGE_TEST_INTEGRATION_DB_ENGINE=lmdb ./result/bin/integration-* || (cat tmp-garage-integration/stderr.log; false)
+      - nix-shell --attr ci --run "killall -9 garage" || true
+      - GARAGE_TEST_INTEGRATION_DB_ENGINE=sqlite ./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 ${CI_COMMIT_TAG:-$CI_COMMIT_SHA}
+      - nix-shell --attr ci --run ./script/test-smoke.sh || (cat /tmp/garage.log; false)

.woodpecker/publish.yaml

@@ -0,0 +1,29 @@
+when:
+  event:
+  - deployment
+  - cron
+
+depends_on:
+  - release
+
+steps:
+  - name: refresh-index
+    image: nixpkgs/nix:nixos-22.05
+    secrets:
+      - source: garagehq_aws_access_key_id
+        target: AWS_ACCESS_KEY_ID
+      - source: garagehq_aws_secret_access_key
+        target: 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-22.05
+    secrets:
+      - 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"

.woodpecker/release.yaml

@@ -0,0 +1,70 @@
+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-22.05
+    commands:
+      - nix-build --no-build-output --attr pkgs.${ARCH}.release --argstr git_version ${CI_COMMIT_TAG:-$CI_COMMIT_SHA}
+
+  - name: check is static binary
+    image: nixpkgs/nix:nixos-22.05
+    commands:
+      - nix-build --no-build-output --attr pkgs.${ARCH}.release --argstr git_version ${CI_COMMIT_TAG:-$CI_COMMIT_SHA}
+      - nix-shell --attr ci --run "./script/not-dynamic.sh result-bin/bin/garage"
+
+  - name: integration tests
+    image: nixpkgs/nix:nixos-22.05
+    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
+    image: nixpkgs/nix:nixos-22.05
+    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-22.05
+    environment:
+      TARGET: "${TARGET}"
+    secrets:
+      - source: garagehq_aws_access_key_id
+        target: AWS_ACCESS_KEY_ID
+      - source: garagehq_aws_secret_access_key
+        target: AWS_SECRET_ACCESS_KEY
+    commands:
+      - nix-shell --attr ci --run "to_s3"
+
+  - name: docker build and publish
+    image: nixpkgs/nix:nixos-22.05
+    environment:
+      DOCKER_PLATFORM: "linux/${ARCH}"
+      CONTAINER_NAME: "dxflrs/${ARCH}_garage"
+    secrets:
+      - 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"

Cargo.toml

@@ -1,17 +1,152 @@
 [workspace]
+resolver = "2"
 members = [
+	"src/db",
 	"src/util",
+	"src/net",
 	"src/rpc",
 	"src/table",
+	"src/block",
 	"src/model",
-	"src/admin",
 	"src/api",
 	"src/web",
-	"src/garage"
+	"src/garage",
+	"src/k2v-client",
+	"src/format-table",
 ]
 
+default-members = ["src/garage"]
+
+[workspace.dependencies]
+
+# Internal Garage crates
+format_table = { version = "0.1.1", path = "src/format-table" }
+garage_api = { version = "1.0.1", path = "src/api" }
+garage_block = { version = "1.0.1", path = "src/block" }
+garage_db = { version = "1.0.1", path = "src/db", default-features = false }
+garage_model = { version = "1.0.1", path = "src/model", default-features = false }
+garage_net = { version = "1.0.1", path = "src/net" }
+garage_rpc = { version = "1.0.1", path = "src/rpc" }
+garage_table = { version = "1.0.1", path = "src/table" }
+garage_util = { version = "1.0.1", path = "src/util" }
+garage_web = { version = "1.0.1", path = "src/web" }
+k2v-client = { version = "0.0.4", path = "src/k2v-client" }
+
+# External crates from crates.io
+arc-swap = "1.0"
+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 = "0.4"
+crc32fast = "1.4"
+crc32c = "0.6"
+crypto-common = "0.1"
+digest = "0.10"
+err-derive = "0.3"
+gethostname = "0.4"
+git-version = "0.3.4"
+hex = "0.4"
+hexdump = "0.1"
+hmac = "0.12"
+idna = "0.5"
+itertools = "0.12"
+ipnet = "2.9.0"
+lazy_static = "1.4"
+md-5 = "0.10"
+mktemp = "0.5"
+nix = { version = "0.27", default-features = false, features = ["fs"] }
+nom = "7.1"
+parse_duration = "2.1"
+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-subscriber = { version = "0.3", features = ["env-filter"] }
+
+heed = { version = "0.11", default-features = false, features = ["lmdb"] }
+rusqlite = "0.31.0"
+r2d2 = "0.8"
+r2d2_sqlite = "0.24"
+
+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"] }
+
+# 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 = ["net", "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" }
+hyper-rustls = { version = "0.26", features = ["http2"] }
+log = "0.4"
+thiserror = "1.0"
+
+# ---- used only as build / dev dependencies ----
+assert-json-diff = "2.0"
+rustc_version = "0.4.0"
+static_init = "1.0"
+
+aws-config = "1.1.4"
+aws-sdk-config = "1.13"
+aws-sdk-s3 = "1.14"
+
 [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 = "s"
+strip = true

Dockerfile

@@ -3,5 +3,5 @@ FROM scratch
 ENV RUST_BACKTRACE=1
 ENV RUST_LOG=garage=info
 
-COPY result/bin/garage /
+COPY result-bin/bin/garage /
 CMD [ "/garage", "server"]

Makefile

@@ -1,13 +1,27 @@
-.PHONY: doc all release shell
+.PHONY: doc all release shell run1 run2 run3
 
 all:
 	clear; cargo build
 
-doc:
-	cd doc/book; mdbook build
-
 release:
-	nix-build --arg release true
+	nix-build --attr pkgs.amd64.release --no-build-output
 
 shell:
 	nix-shell
+
+# ----
+
+run1:
+	RUST_LOG=garage=debug ./target/debug/garage -c tmp/config1.toml server
+run1rel:
+	RUST_LOG=garage=debug ./target/release/garage -c tmp/config1.toml server
+
+run2:
+	RUST_LOG=garage=debug ./target/debug/garage -c tmp/config2.toml server
+run2rel:
+	RUST_LOG=garage=debug ./target/release/garage -c tmp/config2.toml server
+
+run3:
+	RUST_LOG=garage=debug ./target/debug/garage -c tmp/config3.toml server
+run3rel:
+	RUST_LOG=garage=debug ./target/release/garage -c tmp/config3.toml server

README.md

@@ -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;">
@@ -15,18 +15,24 @@ Garage [![Build Status](https://drone.deuxfleurs.fr/api/badges/Deuxfleurs/garage
 	]
 </p>
 
-Garage is a lightweight S3-compatible distributed object store, with the following goals:
+Garage is an S3-compatible distributed object storage service
+designed for self-hosting at a small-to-medium scale.
 
-- As self-contained as possible
-- Easy to set up
-- Highly resilient to network failures, network latency, disk failures, sysadmin failures
-- Relatively simple
-- Made for multi-datacenter deployments
+Garage is designed for storage clusters composed of nodes running
+at different physical locations,
+in order to easily provide a storage service that replicates data at these different
+locations and stays available even when some servers are unreachable.
+Garage also focuses on being lightweight, easy to operate, and highly resilient to
+machine failures.
 
-Non-goals include:
+Garage is built by [Deuxfleurs](https://deuxfleurs.fr),
+an experimental small-scale self hosted service provider,
+which has been using it in production since its first release in 2020.
 
-- Extremely high performance
-- Complete implementation of the S3 API
-- Erasure coding (our replication model is simply to copy the data as is on several nodes, in different datacenters if possible)
+Learn more on our dedicated documentation pages:
 
-Our main use case is to provide a distributed storage layer for small-scale self hosted services such as [Deuxfleurs](https://deuxfleurs.fr).
+- [Goals and use cases](https://garagehq.deuxfleurs.fr/documentation/design/goals/)
+- [Features](https://garagehq.deuxfleurs.fr/documentation/reference-manual/features/)
+- [Quick start](https://garagehq.deuxfleurs.fr/documentation/quick-start/)
+
+Garage is entirely free software released under the terms of the AGPLv3.

default.nix

@@ -1,125 +1,55 @@
-{
-  system ? builtins.currentSystem,
-  release ? false,
-  target ? "x86_64-unknown-linux-musl",
-  compileMode ? null,
-  git_version ? null,
-}:
+{ system ? builtins.currentSystem, git_version ? null, }:
 
 with import ./nix/common.nix;
 
 let
-  crossSystem = { config = target; };
-in let
-  log = v: builtins.trace v v;
+  pkgs = import pkgsSrc { };
+  compile = import ./nix/compile.nix;
 
-  pkgs = import pkgsSrc {
-    inherit system crossSystem;
-    overlays = [ cargo2nixOverlay ];
+  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);
+    });
+
+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";
   };
-
-
-  /*
-   Rust and Nix triples are not the same. Cargo2nix has a dedicated library
-   to convert Nix triples to Rust ones. We need this conversion as we want to
-   set later options linked to our (rust) target in a generic way. Not only
-   the triple terminology is different, but also the "roles" are named differently.
-   Nix uses a build/host/target terminology where Nix's "host" maps to Cargo's "target".
-  */
-  rustTarget = log (pkgs.rustBuilder.rustLib.rustTriple pkgs.stdenv.hostPlatform);
-
-  /*
-   Cargo2nix is built for rustOverlay which installs Rust from Mozilla releases.
-   We want our own Rust to avoid incompatibilities, like we had with musl 1.2.0.
-   rustc was built with musl < 1.2.0 and nix shipped musl >= 1.2.0 which lead to compilation breakage.
-   So we want a Rust release that is bound to our Nix repository to avoid these problems.
-   See here for more info: https://musl.libc.org/time64.html
-   Because Cargo2nix does not support the Rust environment shipped by NixOS,
-   we emulate the structure of the Rust object created by rustOverlay.
-   In practise, rustOverlay ships rustc+cargo in a single derivation while
-   NixOS ships them in separate ones. We reunite them with symlinkJoin.
-   */
-  rustChannel = pkgs.symlinkJoin {
-    name ="rust-channel";
-    paths = [ 
-      pkgs.rustPlatform.rust.rustc
-      pkgs.rustPlatform.rust.cargo
-    ];
+  test = {
+    amd64 = test (compile {
+      inherit system git_version pkgsSrc cargo2nixOverlay;
+      target = "x86_64-unknown-linux-musl";
+      features = [
+        "garage/bundled-libs"
+        "garage/k2v"
+        "garage/lmdb"
+        "garage/sqlite"
+      ];
+    });
   };
-
-  overrides = pkgs.rustBuilder.overrides.all ++ [
-    /*
-     [1] We need to alter Nix hardening to be able to statically compile: PIE,
-     Position Independent Executables seems to be supported only on amd64. Having
-     this flags set either make our executables crash or compile as dynamic on many platforms.
-     In the following section codegenOpts, we reactive it for the supported targets
-     (only amd64 curently) through the `-static-pie` flag. PIE is a feature used
-     by ASLR, which helps mitigate security issues.
-     Learn more about Nix Hardening: https://github.com/NixOS/nixpkgs/blob/master/pkgs/build-support/cc-wrapper/add-hardening.sh
-
-     [2] We want to inject the git version while keeping the build deterministic.
-     As we do not want to consider the .git folder as part of the input source,
-     we ask the user (the CI often) to pass the value to Nix.
-    */
-    (pkgs.rustBuilder.rustLib.makeOverride {
-      name = "garage";
-      overrideAttrs = drv:
-        /* [1] */ { hardeningDisable = [ "pie" ]; }
-        //
-        /* [2] */ (if git_version != null then {
-          preConfigure = ''
-            ${drv.preConfigure or ""}
-            export GIT_VERSION="${git_version}"
-          '';
-        } else {});
-    })
-  ];
-
-  packageFun = import ./Cargo.nix;
-
-  /*
-    We compile fully static binaries with musl to simplify deployment on most systems.
-    When possible, we reactivate PIE hardening (see above).
-
-    Also, if you set the RUSTFLAGS environment variable, the following parameters will
-    be ignored.
-
-    For more information on static builds, please refer to Rust's RFC 1721.
-    https://rust-lang.github.io/rfcs/1721-crt-static.html#specifying-dynamicstatic-c-runtime-linkage
-  */
-
-  codegenOpts = {
-   "armv6l-unknown-linux-musleabihf" = [ "target-feature=+crt-static" "link-arg=-static" ]; /* compile as dynamic with static-pie */
-   "aarch64-unknown-linux-musl" = [ "target-feature=+crt-static" "link-arg=-static" ]; /* segfault with static-pie */
-   "i686-unknown-linux-musl" = [ "target-feature=+crt-static" "link-arg=-static" ]; /* segfault with static-pie */
-   "x86_64-unknown-linux-musl" = [ "target-feature=+crt-static" "link-arg=-static-pie" ];
+  clippy = {
+    amd64 = (compile {
+      inherit system git_version pkgsSrc cargo2nixOverlay;
+      target = "x86_64-unknown-linux-musl";
+      compiler = "clippy";
+    }).workspace.garage { compileMode = "build"; };
   };
-
-  /*
-   The following definition is not elegant as we use a low level function of Cargo2nix
-   that enables us to pass our custom rustChannel object. We need this low level definition
-   to pass Nix's Rust toolchains instead of Mozilla's one.
-
-   target is mandatory but must be kept to null to allow cargo2nix to set it to the appropriate value
-   for each crate.
-  */ 
-  rustPkgs = pkgs.rustBuilder.makePackageSet {
-    inherit packageFun rustChannel release codegenOpts;
-    packageOverrides = overrides;
-    target = null;
-
-    buildRustPackages = pkgs.buildPackages.rustBuilder.makePackageSet {
-      inherit rustChannel packageFun codegenOpts;
-      packageOverrides = overrides;
-      target = null;
-    };
-  };
-
-
-in
-  if compileMode == "test"
-    then pkgs.symlinkJoin {
-      name ="garage-tests";
-      paths = builtins.map (key: rustPkgs.workspace.${key} { inherit compileMode; }) (builtins.attrNames rustPkgs.workspace);
-    }
-    else rustPkgs.workspace.garage { inherit compileMode; }
+}

doc/api/README.md

@@ -0,0 +1,17 @@
+# Browse doc
+
+Run in this directory:
+
+```
+python3 -m http.server 
+```
+
+And open in your browser:
+  - http://localhost:8000/garage-admin-v0.html
+
+# Validate doc
+
+```
+wget https://repo1.maven.org/maven2/org/openapitools/openapi-generator-cli/6.1.0/openapi-generator-cli-6.1.0.jar -O openapi-generator-cli.jar
+java -jar openapi-generator-cli.jar validate -i garage-admin-v0.yml
+```

doc/api/css/redoc.css

@@ -0,0 +1,59 @@
+/* montserrat-300 - latin */
+@font-face {
+  font-family: 'Montserrat';
+  font-style: normal;
+  font-weight: 300;
+  src: local(''),
+       url('../fonts/montserrat-v25-latin-300.woff2') format('woff2'), /* Chrome 26+, Opera 23+, Firefox 39+ */
+       url('../fonts/montserrat-v25-latin-300.woff') format('woff'); /* Chrome 6+, Firefox 3.6+, IE 9+, Safari 5.1+ */
+}
+
+/* montserrat-regular - latin */
+@font-face {
+  font-family: 'Montserrat';
+  font-style: normal;
+  font-weight: 400;
+  src: local(''),
+       url('../fonts/montserrat-v25-latin-regular.woff2') format('woff2'), /* Chrome 26+, Opera 23+, Firefox 39+ */
+       url('../fonts/montserrat-v25-latin-regular.woff') format('woff'); /* Chrome 6+, Firefox 3.6+, IE 9+, Safari 5.1+ */
+}
+
+/* montserrat-700 - latin */
+@font-face {
+  font-family: 'Montserrat';
+  font-style: normal;
+  font-weight: 700;
+  src: local(''),
+       url('../fonts/montserrat-v25-latin-700.woff2') format('woff2'), /* Chrome 26+, Opera 23+, Firefox 39+ */
+       url('../fonts/montserrat-v25-latin-700.woff') format('woff'); /* Chrome 6+, Firefox 3.6+, IE 9+, Safari 5.1+ */
+}
+/* roboto-300 - latin */
+@font-face {
+  font-family: 'Roboto';
+  font-style: normal;
+  font-weight: 300;
+  src: local(''),
+       url('../fonts/roboto-v30-latin-300.woff2') format('woff2'), /* Chrome 26+, Opera 23+, Firefox 39+ */
+       url('../fonts/roboto-v30-latin-300.woff') format('woff'); /* Chrome 6+, Firefox 3.6+, IE 9+, Safari 5.1+ */
+}
+
+/* roboto-regular - latin */
+@font-face {
+  font-family: 'Roboto';
+  font-style: normal;
+  font-weight: 400;
+  src: local(''),
+       url('../fonts/roboto-v30-latin-regular.woff2') format('woff2'), /* Chrome 26+, Opera 23+, Firefox 39+ */
+       url('../fonts/roboto-v30-latin-regular.woff') format('woff'); /* Chrome 6+, Firefox 3.6+, IE 9+, Safari 5.1+ */
+}
+
+/* roboto-700 - latin */
+@font-face {
+  font-family: 'Roboto';
+  font-style: normal;
+  font-weight: 700;
+  src: local(''),
+       url('../fonts/roboto-v30-latin-700.woff2') format('woff2'), /* Chrome 26+, Opera 23+, Firefox 39+ */
+       url('../fonts/roboto-v30-latin-700.woff') format('woff'); /* Chrome 6+, Firefox 3.6+, IE 9+, Safari 5.1+ */
+}
+

doc/api/garage-admin-v0.html

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

doc/api/garage-admin-v1.html

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

doc/book/build/_index.md

@@ -0,0 +1,54 @@
++++
+title = "Build your own app"
+weight = 40
+sort_by = "weight"
+template = "documentation.html"
++++
+
+Garage has many API that you can rely on to build complex applications.
+In this section, we reference the existing SDKs and give some code examples.
+
+
+## ⚠️ DISCLAIMER
+
+**K2V AND ADMIN SDK ARE TECHNICAL PREVIEWS**. The following limitations apply:
+  - The API is not complete, some actions are possible only through the `garage` binary
+  - The underlying admin API is not yet stable nor complete, it can breaks at any time
+  - The generator configuration is currently tweaked, the library might break at any time due to a generator change
+  - Because the API and the library are not stable, none of them are published in a package manager (npm, pypi, etc.)
+  - This code has not been extensively tested, some things might not work (please report!)
+
+To have the best experience possible, please consider:
+  - Make sure that the version of the library you are using is pinned (`go.sum`, `package-lock.json`, `requirements.txt`).
+  - Before upgrading your Garage cluster, make sure that you can find a version of this SDK that works with your targeted version and that you are able to update your own code to work with this new version of the library.
+  - Join our Matrix channel at `#garage:deuxfleurs.fr`, say that you are interested by this SDK, and report any friction.
+  - If stability is critical, mirror this repository on your own infrastructure, regenerate the SDKs and upgrade them at your own pace.
+
+
+## About the APIs
+
+Code can interact with Garage through 3 different APIs: S3, K2V, and Admin.
+Each of them has a specific scope.
+
+### S3
+
+De-facto standard, introduced by Amazon, designed to store blobs of data.
+
+### K2V
+
+A simple database API similar to RiakKV or DynamoDB.
+Think a key value store with some additional operations.
+Its design is inspired by Distributed Hash Tables (DHT).
+
+More information:
+  - [In the reference manual](@/documentation/reference-manual/k2v.md)
+
+
+### Administration
+
+Garage operations can also be automated through a REST API.
+We are currently building this SDK for [Python](@/documentation/build/python.md#admin-api), [Javascript](@/documentation/build/javascript.md#administration) and [Golang](@/documentation/build/golang.md#administration).
+
+More information:
+  - [In the reference manual](@/documentation/reference-manual/admin-api.md)
+  - [Full specifiction](https://garagehq.deuxfleurs.fr/api/garage-admin-v0.html)

doc/book/build/golang.md

@@ -0,0 +1,123 @@
++++
+title = "Golang"
+weight = 30
++++
+
+## S3
+
+*Coming soon*
+
+Some refs:
+  - Minio minio-go-sdk
+    - [Reference](https://docs.min.io/docs/golang-client-api-reference.html)
+
+  - Amazon aws-sdk-go-v2
+    - [Installation](https://aws.github.io/aws-sdk-go-v2/docs/getting-started/)
+    - [Reference](https://pkg.go.dev/github.com/aws/aws-sdk-go-v2/service/s3)
+    - [Example](https://aws.github.io/aws-sdk-go-v2/docs/code-examples/s3/putobject/)
+
+## K2V
+
+*Coming soon*
+
+## Administration
+
+Install the SDK with:
+
+```bash
+go get git.deuxfleurs.fr/garage-sdk/garage-admin-sdk-golang
+```
+
+A short example:
+
+```go
+package main
+
+import (
+    "context"
+    "fmt"
+    "os"
+    "strings"
+    garage "git.deuxfleurs.fr/garage-sdk/garage-admin-sdk-golang"
+)
+
+func main() {
+    // Initialization
+    configuration := garage.NewConfiguration()
+    configuration.Host = "127.0.0.1:3903"
+    client := garage.NewAPIClient(configuration)
+    ctx := context.WithValue(context.Background(), garage.ContextAccessToken, "s3cr3t")
+
+    // 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
+
+    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))
+}
+```
+
+See also:
+ - [generated doc](https://git.deuxfleurs.fr/garage-sdk/garage-admin-sdk-golang)
+ - [examples](https://git.deuxfleurs.fr/garage-sdk/garage-admin-sdk-generator/src/branch/main/example/golang)

doc/book/build/javascript.md

@@ -0,0 +1,55 @@
++++
+title = "Javascript"
+weight = 10
++++
+
+## S3
+
+*Coming soon*.
+
+Some refs:
+  - Minio SDK
+    - [Reference](https://docs.min.io/docs/javascript-client-api-reference.html)
+
+  - Amazon aws-sdk-js
+    - [Installation](https://docs.aws.amazon.com/sdk-for-javascript/v3/developer-guide/getting-started.html)
+    - [Reference](https://docs.aws.amazon.com/AWSJavaScriptSDK/latest/AWS/S3.html)
+    - [Example](https://docs.aws.amazon.com/sdk-for-javascript/v3/developer-guide/s3-example-creating-buckets.html)
+
+## K2V
+
+*Coming soon*
+
+## Administration
+
+Install the SDK with:
+
+```bash
+npm install --save git+https://git.deuxfleurs.fr/garage-sdk/garage-admin-sdk-js.git
+```
+
+A short example:
+
+```javascript
+const garage = require('garage_administration_api_v1garage_v0_9_0');
+
+const api = new garage.ApiClient("http://127.0.0.1:3903/v1");
+api.authentications['bearerAuth'].accessToken = "s3cr3t";
+
+const [node, layout, key, bucket] = [
+  new garage.NodesApi(api),
+  new garage.LayoutApi(api),
+  new garage.KeyApi(api),
+  new garage.BucketApi(api),
+];
+
+node.getNodes().then((data) => {
+  console.log(`nodes: ${Object.values(data.knownNodes).map(n => n.hostname)}`)
+}, (error) => {
+  console.error(error);
+});
+```
+
+See also:
+ - [sdk repository](https://git.deuxfleurs.fr/garage-sdk/garage-admin-sdk-js)
+ - [examples](https://git.deuxfleurs.fr/garage-sdk/garage-admin-sdk-generator/src/branch/main/example/javascript)

doc/book/build/others.md

@@ -1,8 +1,10 @@
 +++
-title = "Your code (PHP, JS, Go...)"
-weight = 30
+title = "Others"
+weight = 99
 +++
 
+## S3
+
 If you are developping 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,
@@ -13,44 +15,14 @@ Instead, there are some libraries already avalaible.
 
 Some of them are maintained by Amazon, some by Minio, others by the community.
 
-## PHP
+### PHP
 
   - Amazon aws-sdk-php
     - [Installation](https://docs.aws.amazon.com/sdk-for-php/v3/developer-guide/getting-started_installation.html)
     - [Reference](https://docs.aws.amazon.com/aws-sdk-php/v3/api/api-s3-2006-03-01.html)
     - [Example](https://docs.aws.amazon.com/sdk-for-php/v3/developer-guide/s3-examples-creating-buckets.html)
 
-## Javascript
-
-  - Minio SDK
-    - [Reference](https://docs.min.io/docs/javascript-client-api-reference.html)
-
-  - Amazon aws-sdk-js
-    - [Installation](https://docs.aws.amazon.com/sdk-for-javascript/v3/developer-guide/getting-started.html)
-    - [Reference](https://docs.aws.amazon.com/AWSJavaScriptSDK/latest/AWS/S3.html)
-    - [Example](https://docs.aws.amazon.com/sdk-for-javascript/v3/developer-guide/s3-example-creating-buckets.html)
-
-## Golang
-
-  - Minio minio-go-sdk
-    - [Reference](https://docs.min.io/docs/golang-client-api-reference.html)
-
-  - Amazon aws-sdk-go-v2
-    - [Installation](https://aws.github.io/aws-sdk-go-v2/docs/getting-started/)
-    - [Reference](https://pkg.go.dev/github.com/aws/aws-sdk-go-v2/service/s3)
-    - [Example](https://aws.github.io/aws-sdk-go-v2/docs/code-examples/s3/putobject/)
-
-## Python
-
-  - Minio SDK
-    - [Reference](https://docs.min.io/docs/python-client-api-reference.html)
-
-  - Amazon boto3
-    - [Installation](https://boto3.amazonaws.com/v1/documentation/api/latest/guide/quickstart.html)
-    - [Reference](https://boto3.amazonaws.com/v1/documentation/api/latest/reference/services/s3.html)
-    - [Example](https://boto3.amazonaws.com/v1/documentation/api/latest/guide/s3-uploading-files.html)
-
-## Java
+### Java
 
   - Minio SDK
     - [Reference](https://docs.min.io/docs/java-client-api-reference.html)
@@ -60,23 +32,18 @@ Some of them are maintained by Amazon, some by Minio, others by the community.
     - [Reference](https://sdk.amazonaws.com/java/api/latest/software/amazon/awssdk/services/s3/S3Client.html)
     - [Example](https://docs.aws.amazon.com/sdk-for-java/latest/developer-guide/examples-s3-objects.html)
 
-## Rust
-
-  - Amazon aws-rust-sdk
-    - [Github](https://github.com/awslabs/aws-sdk-rust)
-
-## .NET
+### .NET
 
   - Minio SDK
     - [Reference](https://docs.min.io/docs/dotnet-client-api-reference.html)
 
   - Amazon aws-dotnet-sdk
 
-## C++
+### C++
 
   - Amazon aws-cpp-sdk
 
-## Haskell
+### Haskell
 
   - Minio SDK
     - [Reference](https://docs.min.io/docs/haskell-client-api-reference.html)

doc/book/build/python.md

@@ -0,0 +1,139 @@
++++
+title = "Python"
+weight = 20
++++
+
+## S3
+
+### Using Minio SDK
+
+First install the SDK:
+
+```bash
+pip3 install minio
+```
+
+Then instantiate a client object using garage root domain, api key and secret:
+
+```python
+import minio
+
+client = minio.Minio(
+  "your.domain.tld",
+  "GKyourapikey",
+  "abcd[...]1234",
+  # Force the region, this is specific to garage
+  region="garage",
+)
+```
+
+Then use all the standard S3 endpoints as implemented by the Minio SDK:
+
+```
+# List buckets
+print(client.list_buckets())
+
+# Put an object containing 'content' to /path in bucket named 'bucket':
+content = b"content"
+client.put_object(
+  "bucket",
+  "path",
+  io.BytesIO(content),
+  len(content),
+)
+
+# Read the object back and check contents
+data = client.get_object("bucket", "path").read()
+assert data == content
+```
+
+For further documentation, see the Minio SDK
+[Reference](https://docs.min.io/docs/python-client-api-reference.html)
+
+### Using Amazon boto3
+
+*Coming soon*
+
+See the official documentation:
+  - [Installation](https://boto3.amazonaws.com/v1/documentation/api/latest/guide/quickstart.html)
+  - [Reference](https://boto3.amazonaws.com/v1/documentation/api/latest/reference/services/s3.html)
+  - [Example](https://boto3.amazonaws.com/v1/documentation/api/latest/guide/s3-uploading-files.html)
+
+## K2V
+
+*Coming soon*
+
+## Admin API
+
+You need at least Python 3.6, pip, and setuptools.
+Because the python package is in a subfolder, the command is a bit more complicated than usual:
+
+```bash
+pip3 install --user 'git+https://git.deuxfleurs.fr/garage-sdk/garage-admin-sdk-python'
+```
+
+Now, let imagine you have a fresh Garage instance running on localhost, with the admin API configured on port 3903 with the bearer `s3cr3t`:
+
+```python
+import garage_admin_sdk
+from garage_admin_sdk.apis import *
+from garage_admin_sdk.models import *
+
+configuration = garage_admin_sdk.Configuration(
+  host = "http://localhost:3903/v1",
+  access_token = "s3cr3t"
+)
+
+# Init APIs
+api = garage_admin_sdk.ApiClient(configuration)
+nodes, layout, keys, buckets = NodesApi(api), LayoutApi(api), KeyApi(api), BucketApi(api)
+
+# Display some info on the node
+status = nodes.get_nodes()
+print(f"running garage {status.garage_version}, node_id {status.node}")
+
+# Change layout of this node
+current = layout.get_layout()
+layout.add_layout([
+  NodeRoleChange(
+    id = status.node,
+    zone = "dc1",
+    capacity = 1000000000,
+    tags = [ "dev" ],
+  )
+])
+layout.apply_layout(LayoutVersion(
+  version = current.version + 1
+))
+
+# Create key, allow it to create buckets
+kinfo = keys.add_key(AddKeyRequest(name="openapi"))
+
+allow_create = UpdateKeyRequestAllow(create_bucket=True)
+keys.update_key(kinfo.access_key_id, UpdateKeyRequest(allow=allow_create))
+
+# Create a bucket, allow key, set quotas
+binfo = buckets.create_bucket(CreateBucketRequest(global_alias="documentation"))
+binfo = buckets.allow_bucket_key(AllowBucketKeyRequest(
+  bucket_id=binfo.id,
+  access_key_id=kinfo.access_key_id,
+  permissions=AllowBucketKeyRequestPermissions(read=True, write=True, owner=True),
+))
+binfo = buckets.update_bucket(binfo.id, UpdateBucketRequest(
+  quotas=UpdateBucketRequestQuotas(max_size=19029801,max_objects=1500)))
+
+# Display key
+print(f"""
+cluster ready
+key id is {kinfo.access_key_id}
+secret key is {kinfo.secret_access_key}
+bucket {binfo.global_aliases[0]} contains {binfo.objects}/{binfo.quotas.max_objects} objects
+""")
+```
+
+*This example is named `short.py` in the example folder. Other python examples are also available.*
+
+See also:
+ - [sdk repo](https://git.deuxfleurs.fr/garage-sdk/garage-admin-sdk-python)
+ - [examples](https://git.deuxfleurs.fr/garage-sdk/garage-admin-sdk-generator/src/branch/main/example/python)
+

doc/book/build/rust.md

@@ -0,0 +1,47 @@
++++
+title = "Rust"
+weight = 40
++++
+
+## S3
+
+*Coming soon*
+
+Some refs:
+  - Amazon aws-rust-sdk
+    - [Github](https://github.com/awslabs/aws-sdk-rust)
+
+## K2V
+
+*Coming soon*
+
+Some refs: https://git.deuxfleurs.fr/Deuxfleurs/garage/src/branch/main/src/k2v-client
+
+```bash
+# all these values can be provided on the cli instead
+export AWS_ACCESS_KEY_ID=GK123456
+export AWS_SECRET_ACCESS_KEY=0123..789
+export AWS_REGION=garage
+export K2V_ENDPOINT=http://172.30.2.1:3903
+export K2V_BUCKET=my-bucket
+
+cargo run --features=cli -- read-range my-partition-key --all
+
+cargo run --features=cli -- insert my-partition-key my-sort-key --text "my string1"
+cargo run --features=cli -- insert my-partition-key my-sort-key --text "my string2"
+cargo run --features=cli -- insert my-partition-key my-sort-key2 --text "my string"
+
+cargo run --features=cli -- read-range my-partition-key --all
+
+causality=$(cargo run --features=cli -- read my-partition-key my-sort-key2 -b | head -n1)
+cargo run --features=cli -- delete my-partition-key my-sort-key2 -c $causality
+
+causality=$(cargo run --features=cli -- read my-partition-key my-sort-key -b | head -n1)
+cargo run --features=cli -- insert my-partition-key my-sort-key --text "my string3" -c $causality
+
+cargo run --features=cli -- read-range my-partition-key --all
+```
+
+## Admin API
+
+*Coming soon*

doc/book/connect/_index.md

@@ -1,6 +1,6 @@
 +++
-title = "Integrations"
-weight = 3
+title = "Existing integrations"
+weight = 30
 sort_by = "weight"
 template = "documentation.html"
 +++
@@ -10,12 +10,12 @@ Garage implements the Amazon S3 protocol, which makes it compatible with many ex
 
 In particular, you will find here instructions to connect it with:
 
-  - [Browsing tools](@/documentation/connect/cli.md)
   - [Applications](@/documentation/connect/apps/index.md)
-  - [Website hosting](@/documentation/connect/websites.md)
-  - [Software repositories](@/documentation/connect/repositories.md)
-  - [Your own code](@/documentation/connect/code.md)
+  - [Browsing tools](@/documentation/connect/cli.md)
   - [FUSE](@/documentation/connect/fs.md)
+  - [Observability](@/documentation/connect/observability.md)
+  - [Software repositories](@/documentation/connect/repositories.md)
+  - [Website hosting](@/documentation/connect/websites.md)
 
 ### Generic instructions
 

doc/book/connect/apps/index.md

@@ -8,12 +8,13 @@ In this section, we cover the following web applications:
 | Name | Status | Note |
 |------|--------|------|
 | [Nextcloud](#nextcloud)     | ✅       |  Both Primary Storage and External Storage are supported    |
-| [Peertube](#peertube)     | ✅       | Must be configured with the website endpoint     |
-| [Mastodon](#mastodon)     | ❓       | Not yet tested     |
+| [Peertube](#peertube)     | ✅       | Supported with the website endpoint, proxifying private videos unsupported     |
+| [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    |
-| [Lemmy](#lemmy)     | ❓       |  Not yet tested    |
+| [Lemmy](#lemmy)     | ✅        |  Supported with pict-rs    |
 | [Funkwhale](#funkwhale)     | ❓       | Not yet tested     |
 | [Misskey](#misskey)     | ❓       | Not yet tested     |
 | [Prismo](#prismo)     | ❓       | Not yet tested     |
@@ -36,7 +37,7 @@ Second, we suppose you have created a key and a bucket.
 As a reminder, you can create a key for your nextcloud instance as follow:
 
 ```bash
-garage key new --name nextcloud-key
+garage key create nextcloud-key
 ```
 
 Keep the Key ID and the Secret key in a pad, they will be needed later.  
@@ -79,6 +80,53 @@ 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).
@@ -128,20 +176,24 @@ In other words, Peertube is only responsible of the "control plane" and offload
 In return, this system is a bit harder to configure.
 We show how it is still possible to configure Garage with Peertube, allowing you to spread the load and the bandwidth usage on the Garage cluster.
 
+Starting from version 5.0, Peertube also supports improving the security for private videos by not exposing them directly
+but relying on a single control point in the Peertube instance. This is based on S3 per-object and prefix ACL, which are not currently supported
+in Garage, so this feature is unsupported. While this technically impedes security for private videos, it is not a blocking issue and could be
+a reasonable trade-off for some instances.
 
 ### Create resources in Garage
 
 Create a key for Peertube:
 
 ```bash
-garage key new --name peertube-key
+garage key create peertube-key
 ```
 
 Keep the Key ID and the Secret key in a pad, they will be needed later.  
 
 We need two buckets, one for normal videos (named peertube-video) and one for webtorrent videos (named peertube-playlist).
 ```bash
-garage bucket create peertube-video
+garage bucket create peertube-videos
 garage bucket create peertube-playlist
 ```
 
@@ -195,6 +247,11 @@ object_storage:
 
   max_upload_part: 2GB
 
+  proxy:
+    # You may enable this feature, yet it will not provide any security benefit, so
+    # you should rather benefit from Garage public endpoint for all videos
+    proxify_private_files: false
+
   streaming_playlists:
     bucket_name: 'peertube-playlist'
 
@@ -206,7 +263,7 @@ 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'
@@ -224,7 +281,134 @@ You can now reload the page and see in your browser console that data are fetche
 
 ## Mastodon
 
-https://docs.joinmastodon.org/admin/config/#cdn
+Mastodon natively supports the S3 protocol to store media files, and it works out-of-the-box with Garage.
+You will need to expose your Garage bucket as a website: that way, media files will be served directly from Garage.
+
+### Performance considerations
+
+Mastodon tends to store many small objects over time: expect hundreds of thousands of objects,
+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).
+  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
+
+This is the usual Garage setup:
+
+```bash
+garage key create mastodon-key
+garage bucket create mastodon-data
+garage bucket allow mastodon-data --read --write --key mastodon-key
+```
+
+Note the Key ID and Secret Key.
+
+### Exposing your bucket as a website
+
+Create a DNS name to serve your media files, such as `my-social-media.mydomain.tld`.
+This name will be publicly exposed to the users of your Mastodon instance: they
+will load images directly from this DNS name.
+
+As [documented here](@/documentation/cookbook/exposing-websites.md),
+add this DNS name as alias to your bucket, and expose it as a website:
+
+```bash
+garage bucket alias mastodon-data my-social-media.mydomain.tld
+garage bucket website --allow mastodon-data
+```
+
+Then you will likely need to [setup a reverse proxy](@/documentation/cookbook/reverse-proxy.md)
+in front of it to serve your media files over HTTPS.
+
+### Cleaning up old media files before migration
+
+Mastodon instance quickly accumulate a lot of media files from the federation.
+Most of them are not strictly necessary because they can be fetched again from
+other servers.  As such, it is highly recommended to clean them up before
+migration, this will greatly reduce the migration time.
+
+From the [official Mastodon documentation](https://docs.joinmastodon.org/admin/tootctl/#media):
+
+```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
+```
+
+Here is a typical disk usage for a small but multi-year instance after cleanup:
+
+```bash
+$ RAILS_ENV=production bin/tootctl media usage
+Attachments:	5.67 GB (1.14 GB local)
+Custom emoji:	295 MB (0 Bytes local)
+Preview cards:	154 MB
+Avatars:	3.77 GB (127 KB local)
+Headers:	8.72 GB (242 KB local)
+Backups:	0 Bytes
+Imports:	1.7 KB
+Settings:	0 Bytes
+```
+
+### Migrating your data
+
+Data migration should be done with an efficient S3 client.
+The [minio client](@documentation/connect/cli.md#minio-client) is a good choice
+thanks to its mirror mode:
+
+```bash
+mc mirror ./public/system/ garage/mastodon-data
+```
+
+Here is a typical bucket usage after all data has been migrated:
+
+```bash
+$ garage bucket info mastodon-data
+
+Size: 20.3 GiB (21.8 GB)
+Objects: 175968
+```
+
+### Configuring Mastodon
+
+In your `.env.production` configuration file:
+
+```bash
+S3_ENABLED=true
+# Internal access to Garage
+S3_ENDPOINT=http://my-garage-instance.mydomain.tld:3900
+S3_REGION=garage
+S3_BUCKET=mastodon-data
+# Change this (Key ID and Secret Key of your Garage key)
+AWS_ACCESS_KEY_ID=GKe88df__CHANGETHIS__c5145
+AWS_SECRET_ACCESS_KEY=a2f7__CHANGETHIS__77fcfcf7a58f47a4aa4431f2e675c56da37821a1070000
+# What name gets exposed to users (HTTPS is implicit)
+S3_ALIAS_HOST=my-social-media.mydomain.tld
+```
+
+For more details, see the [reference Mastodon documentation](https://docs.joinmastodon.org/admin/config/#cdn).
+
+Restart all Mastodon services and everything should now be using Garage!
+You can check the URLs of images in the Mastodon web client, they should start
+with `https://my-social-media.mydomain.tld`.
+
+### Last migration sync
+
+After Mastodon is successfully using Garage, you can run a last sync from the local filesystem to Garage:
+
+```bash
+mc mirror --newer-than "3h" ./public/system/ garage/mastodon-data
+```
+
+### References
+
+[cybrespace's guide to migrate to S3](https://github.com/cybrespace/cybrespace-meta/blob/master/s3.md)
+(the guide is for Amazon S3, so the configuration is a bit different, but the rest is similar)
+
 
 ## Matrix
 
@@ -241,7 +425,7 @@ Supposing you have a working synapse installation, you can add the module with p
 Now create a bucket and a key for your matrix instance (note your Key ID and Secret Key somewhere, they will be needed later):
 
 ```bash
-garage key new --name matrix-key
+garage key create matrix-key
 garage bucket create matrix
 garage bucket allow matrix --read --write --key matrix-key
 ```
@@ -283,7 +467,7 @@ 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
@@ -304,7 +488,7 @@ 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.
@@ -337,6 +521,52 @@ And add a new line. For example, to run it every 10 minutes:
 
 *External link:* [matrix-media-repo Documentation > S3](https://docs.t2bot.io/matrix-media-repo/configuration/s3-datastore.html)
 
+## ejabberd
+
+ejabberd is an XMPP server implementation which, with the `mod_s3_upload`
+module in the [ejabberd-contrib](https://github.com/processone/ejabberd-contrib)
+repository, can be integrated to store chat media files in Garage.
+
+For uploads, this module leverages presigned URLs - this allows XMPP clients to
+directly send media to Garage. Receiving clients then retrieve this media
+through the [static website](@/documentation/cookbook/exposing-websites.md)
+functionality.
+
+As the data itself is publicly accessible to someone with knowledge of the
+object URL - users are recommended to use
+[E2EE](@/documentation/cookbook/encryption.md) to protect this data-at-rest
+from unauthorized access.
+
+Install the module with:
+
+```bash
+ejabberdctl module_install mod_s3_upload
+```
+
+Create the required key and bucket with:
+
+```bash
+garage key new --name ejabberd
+garage bucket create objects.xmpp-server.fr
+garage bucket allow objects.xmpp-server.fr --read --write --key ejabberd
+garage bucket website --allow objects.xmpp-server.fr
+```
+
+The module can then be configured with:
+
+```
+  mod_s3_upload:
+    #bucket_url: https://objects.xmpp-server.fr.my-garage-instance.mydomain.tld
+    bucket_url: https://my-garage-instance.mydomain.tld/objects.xmpp-server.fr
+    access_key_id: GK...
+    access_key_secret: ...
+    region: garage
+    download_url: https://objects.xmpp-server.fr
+```
+
+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).
+
 ## Pixelfed
 
 [Pixelfed Technical Documentation > Configuration](https://docs.pixelfed.org/technical-documentation/env.html#filesystem)
@@ -347,7 +577,68 @@ And add a new line. For example, to run it every 10 minutes:
 
 ## Lemmy
 
-Lemmy uses pict-rs that [supports S3 backends](https://git.asonix.dog/asonix/pict-rs/commit/f9f4fc63d670f357c93f24147c2ee3e1278e2d97)
+Lemmy uses pict-rs that [supports S3 backends](https://git.asonix.dog/asonix/pict-rs/commit/f9f4fc63d670f357c93f24147c2ee3e1278e2d97).
+This feature requires `pict-rs >= 4.0.0`.
+
+### Creating your bucket
+
+This is the usual Garage setup:
+
+```bash
+garage key new --name pictrs-key
+garage bucket create pictrs-data
+garage bucket allow pictrs-data --read --write --key pictrs-key
+```
+
+Note the Key ID and Secret Key.
+
+### Migrating your data
+
+If your pict-rs instance holds existing data, you first need to migrate to the S3 bucket.
+
+Stop pict-rs, then run the migration utility from local filesystem to the bucket:
+
+```
+pict-rs \
+  filesystem -p /path/to/existing/files \
+  object-store \
+   -e my-garage-instance.mydomain.tld:3900 \
+   -b pictrs-data \
+   -r garage \
+   -a GK... \
+   -s abcdef0123456789...
+```
+
+This is pretty slow, so hold on while migrating.
+
+### Running pict-rs with an S3 backend
+
+Pict-rs supports both a configuration file and environment variables.
+
+Either set the following section in your `pict-rs.toml`:
+
+```
+[store]
+type = 'object_storage'
+endpoint = 'http://my-garage-instance.mydomain.tld:3900'
+bucket_name = 'pictrs-data'
+region = 'garage'
+access_key = 'GK...'
+secret_key = 'abcdef0123456789...'
+```
+
+... or set these environment variables:
+
+
+```
+PICTRS__STORE__TYPE=object_storage
+PICTRS__STORE__ENDPOINT=http://my-garage-instance.mydomain.tld:3900
+PICTRS__STORE__BUCKET_NAME=pictrs-data
+PICTRS__STORE__REGION=garage
+PICTRS__STORE__ACCESS_KEY=GK...
+PICTRS__STORE__SECRET_KEY=abcdef0123456789...
+```
+
 
 ## Funkwhale
 

doc/book/connect/backup.md

@@ -13,10 +13,100 @@ Borg Backup is very popular among the backup tools but it is not yet compatible
 We recommend using any other tool listed in this guide because they are all compatible with the S3 API.
 If you still want to use Borg, you can use it with `rclone mount`.
 
+## git-annex
 
+[git-annex](https://git-annex.branchable.com/) supports synchronizing files
+with its [S3 special remote](https://git-annex.branchable.com/special_remotes/S3/).
+
+Note that `git-annex` requires to be compiled with Haskell package version
+`aws-0.24` to work with Garage.
+
+```bash
+garage key new --name my-key
+garage bucket create my-git-annex
+garage bucket allow my-git-annex --read --write --key my-key
+```
+
+Register your Key ID and Secret key in your environment:
+
+```bash
+export AWS_ACCESS_KEY_ID=GKxxx
+export AWS_SECRET_ACCESS_KEY=xxxx
+```
+
+Within a git-annex enabled repository, configure your Garage S3 endpoint with
+the following command:
+
+```bash
+git annex initremote garage type=S3 encryption=none host=my-garage-instance.mydomain.tld protocol=https bucket=my-git-annex requeststyle=path region=garage signature=v4
+```
+
+Files can now be synchronized using the usual `git-annex` `copy` or `get`
+commands.
+
+Note that for simplicity - this example does not enable encryption for the files
+sent to Garage - please refer to the
+[git-annex encryption page](https://git-annex.branchable.com/encryption/) for
+how to configure this.
 
 ## Restic
 
+Create your key and bucket:
+
+```bash
+garage key create 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:
+
+```bash
+export AWS_ACCESS_KEY_ID=GKxxx
+export AWS_SECRET_ACCESS_KEY=xxxx
+```
+
+Configure restic from environment too:
+
+```bash
+export RESTIC_REPOSITORY="s3:http://localhost:3900/backups"
+
+echo "Generated password (save it safely): $(openssl rand -base64 32)"
+export RESTIC_PASSWORD=xxx # copy paste your generated password here
+```
+
+Do not forget to save your password safely (in your password manager or print it). It will be needed to decrypt your backups.
+
+Now you can use restic:
+
+```bash
+# Initialize the bucket, must be run once
+restic init
+
+# Backup your PostgreSQL database
+# (We suppose your PostgreSQL daemon is stopped for all commands)
+restic backup /var/lib/postgresql
+
+# Show backup history
+restic snapshots
+
+# Backup again your PostgreSQL database, it will be faster as only changes will be uploaded
+restic backup /var/lib/postgresql
+
+# Show backup history (again)
+restic snapshots
+
+# Restore a backup
+# (79766175 is the ID of the snapshot you want to restore)
+mv /var/lib/postgresql /var/lib/postgresql.broken
+restic restore 79766175 --target /var/lib/postgresql
+```
+
+Restic has way more features than the ones presented here.
+You can discover all of them by accessing its documentation from the link below.
+
+Files on Android devices can also be backed up with [restic-android](https://github.com/lhns/restic-android).
+
 *External links:* [Restic Documentation > Amazon S3](https://restic.readthedocs.io/en/stable/030_preparing_a_new_repo.html#amazon-s3)
 
 ## Duplicity
@@ -25,7 +115,22 @@ If you still want to use Borg, you can use it with `rclone mount`.
 
 ## Duplicati
 
-*External links:* [Duplicati Documentation > Storage Providers](https://github.com/kees-z/DuplicatiDocs/blob/master/docs/05-storage-providers.md#user-content-s3-compatible)
+*External links:* [Duplicati Documentation > Storage Providers](https://duplicati.readthedocs.io/en/latest/05-storage-providers/#s3-compatible)
+
+The following fields need to be specified:
+```
+Storage Type: S3 Compatible
+Use SSL: [ ] # Only if you have SSL
+Server: Custom server url (s3.garage.localhost:3900)
+Bucket name: bucket-name
+Bucket create region: Custom region value (garage) # Or as you've specified in garage.toml
+AWS Access ID: Key ID from "garage key info key-name"
+AWS Access Key: Secret key from "garage key info key-name"
+Client Library to use: Minio SDK
+```
+
+Click `Test connection` and then no when asked `The bucket name should start with your username, prepend automatically?`. Then it should say `Connection worked!`.
+
 
 ## knoxite
 
@@ -35,3 +140,24 @@ If you still want to use Borg, you can use it with `rclone mount`.
 
 *External links:* [Kopia Documentation > Repositories](https://kopia.io/docs/repositories/#amazon-s3)
 
+To create the Kopia repository, you need to specify the region, the HTTP(S) endpoint, the bucket name and the access keys.
+For instance, if you have an instance of garage running on `https://garage.example.com`:
+
+```
+kopia repository create s3 --region=garage --bucket=mybackups --access-key=KEY_ID --secret-access-key=SECRET_KEY --endpoint=garage.example.com
+```
+
+Or if you have an instance running on localhost, without TLS:
+
+```
+kopia repository create s3 --region=garage --bucket=mybackups --access-key=KEY_ID --secret-access-key=SECRET_KEY --endpoint=localhost:3900 --disable-tls
+```
+
+After the repository has been created, check that everything works as expected:
+
+```
+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.

doc/book/connect/cli.md

@@ -12,8 +12,10 @@ These tools are particularly suitable for debug, backups, website deployments or
 | [AWS CLI](#aws-cli)     | ✅       | Recommended   |
 | [rclone](#rclone)     | ✅       |    |
 | [s3cmd](#s3cmd)     | ✅       |    |
+| [s5cmd](#s5cmd)     | ✅       |    |
 | [(Cyber)duck](#cyberduck)     | ✅       |    |
-| [WinSCP (libs3)](#winscp)     | ✅       | No instructions yet   |
+| [WinSCP (libs3)](#winscp)     | ✅       | CLI instructions only   |
+| [sftpgo](#sftpgo)     | ✅       |    |
 
 
 ## Minio client
@@ -68,16 +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 $@ ; }
@@ -177,59 +180,34 @@ s3cmd put /tmp/hello.txt s3://my-bucket/
 s3cmd get s3://my-bucket/hello.txt hello.txt
 ```
 
+## `s5cmd`
+
+Configure a credentials file as follows:
+
+```bash
+export AWS_ACCESS_KEY_ID=GK...
+export AWS_SECRET_ACCESS_KEY=
+export AWS_DEFAULT_REGION='garage'
+export AWS_ENDPOINT='http://localhost:3900'
+```
+
+After adding these environment variables in your shell, `s5cmd` can be used
+with:
+
+```bash
+s5cmd --endpoint-url=$AWS_ENDPOINT ls
+```
+
+See its usage output for other commands available.
+
 ## Cyberduck & duck {#cyberduck}
 
 Both Cyberduck (the GUI) and duck (the CLI) have a concept of "Connection Profiles" that contain some presets for a specific provider.
-We wrote the following connection profile for Garage:
 
-```xml
-<?xml version="1.0" encoding="UTF-8"?>
-<!DOCTYPE plist PUBLIC "-//Apple//DTD PLIST 1.0//EN" "http://www.apple.com/DTDs/PropertyList-1.0.dtd">
-<plist version="1.0">
-    <dict>
-        <key>Protocol</key>
-        <string>s3</string>
-        <key>Vendor</key>
-        <string>garage</string>
-        <key>Scheme</key>
-        <string>https</string>
-        <key>Description</key>
-        <string>GarageS3</string>
-        <key>Default Hostname</key>
-        <string>127.0.0.1</string>
-        <key>Default Port</key>
-        <string>4443</string>
-        <key>Hostname Configurable</key>
-        <false/>
-        <key>Port Configurable</key>
-        <false/>
-        <key>Username Configurable</key>
-        <true/>
-        <key>Username Placeholder</key>
-        <string>Access Key ID (GK...)</string>
-        <key>Password Placeholder</key>
-        <string>Secret Key</string>
-        <key>Properties</key>
-        <array>
-            <string>s3service.disable-dns-buckets=true</string>
-        </array>
-        <key>Region</key>
-        <string>garage</string>
-        <key>Regions</key>
-        <array>
-            <string>garage</string>
-        </array>
-    </dict>
-</plist>
-```
-
-*Note: If your garage instance is configured with vhost access style, you can remove `s3service.disable-dns-buckets=true`.*
-
-### Instructions for the GUI
-
-Copy the connection profile, and save it anywhere as `garage.cyberduckprofile`.
-Then find this file with your file explorer and double click on it: Cyberduck will open a connection wizard for this profile.
-Simply follow the wizard and you should be done!
+Within Cyberduck, a
+[Garage connection profile](https://docs.cyberduck.io/protocols/s3/garage/) is
+available within the `Preferences -> Profiles` section. This can enabled and
+then connections to Garage may be configured.
 
 ### Instuctions for the CLI
 
@@ -281,5 +259,59 @@ duck --delete garage:/my-files/an-object.txt
 
 ## WinSCP (libs3) {#winscp}
 
-*No instruction yet. You can find ones 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:
+
+```
+open s3://GKxxxxx:yyyyyyy@127.0.0.1:4443 -certificate=* -rawsettings S3DefaultRegion=garage S3UrlStyle=1
+ls
+ls my-files/
+get my-files/an-object.txt Z:\tmp\object.txt
+put Z:\tmp\object.txt my-files/another-object.txt
+rm my-files/an-object
+exit
+```
+
+Notes:
+  - It seems WinSCP supports only TLS connections for S3
+  - `-certificate=*` allows self-signed certificates, remove it if you have valid certificates
+
+
+## sftpgo {#sftpgo}
+
+sftpgo needs a database to work, by default it uses sqlite and does not require additional configuration.
+You can then directly init it:
+
+```
+sftpgo initprovider
+```
+
+Then you can directly launch the daemon that will listen by default on `:8080 (http)` and `:2022 (ssh)`:
+
+```
+sftpgo serve
+```
+
+Go to the admin web interface (http://[::1]:8080/web/admin/), create the required admin account, then create a user account.
+Choose a username (eg: `ada`) and a password.
+
+In the filesystem section, choose:
+  - Storage: AWS S3 (Compatible)
+  - Bucket: *your bucket name*
+  - Region: `garage` (or the one you defined in `config.toml`)
+  - Access key: *your access key*
+  - Access secret: *your secret key*
+  - Endpoint: *your endpoint*, eg. `https://garage.example.tld`, note that the protocol (`https` here) must be specified. Non standard ports and `http` have not been tested yet.
+  - Keep the default values for other fields
+  - Tick "Use path-style addressing". It should work without ticking it if you have correctly configured your instance to use URL vhost-style.
+
+Now you can access your bucket through SFTP:
+
+```
+sftp -P2022 ada@[::1]
+ls
+```
+
+And through the web interface at http://[::1]:8080/web/client
 

doc/book/connect/observability.md

@@ -0,0 +1,57 @@
++++
+title = "Observability"
+weight = 25
++++
+
+An object store can be used as data storage location for metrics, and logs which
+can then be leveraged for systems observability.
+
+## Metrics
+
+### Prometheus
+
+Prometheus itself has no object store capabilities, however two projects exist
+which support storing metrics in an object store:
+
+ - [Cortex](https://cortexmetrics.io/)
+ - [Thanos](https://thanos.io/)
+
+## System logs
+
+### Vector
+
+[Vector](https://vector.dev/) natively supports S3 as a
+[data sink](https://vector.dev/docs/reference/configuration/sinks/aws_s3/)
+(and [source](https://vector.dev/docs/reference/configuration/sources/aws_s3/)).
+
+This can be configured with Garage with the following:
+
+```bash
+garage key new --name vector-system-logs
+garage bucket create system-logs
+garage bucket allow system-logs --read --write --key vector-system-logs
+```
+
+The `vector.toml` can then be configured as follows:
+
+```toml
+[sources.journald]
+type = "journald"
+current_boot_only = true
+
+[sinks.out]
+encoding.codec = "json"
+type = "aws_s3"
+inputs = [ "journald" ]
+bucket = "system-logs"
+key_prefix = "%F/"
+compression = "none"
+region = "garage"
+endpoint = "https://my-garage-instance.mydomain.tld"
+auth.access_key_id = ""
+auth.secret_access_key = ""
+```
+
+This is an example configuration - please refer to the Vector documentation for
+all configuration and transformation possibilities. Also note that Garage
+performs its own compression, so this should be disabled in Vector.

doc/book/connect/repositories.md

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

doc/book/connect/websites.md

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

doc/book/cookbook/_index.md

@@ -1,12 +1,12 @@
 +++
 title="Cookbook"
 template = "documentation.html"
-weight = 2
+weight = 20
 sort_by = "weight"
 +++
 
 A cookbook, when you cook, is a collection of recipes.
-Similarly, Garage's cookbook contains a collection of recipes that are known to works well!
+Similarly, Garage's cookbook contains a collection of recipes that are known to work well!
 This chapter could also be referred as "Tutorials" or "Best practices".
 
 - **[Multi-node deployment](@/documentation/cookbook/real-world.md):** This page will walk you through all of the necessary
@@ -16,6 +16,10 @@ This chapter could also be referred as "Tutorials" or "Best practices".
   source in case a binary is not provided for your architecture, or if you want to
   hack with us!
 
+- **[Binary packages](@/documentation/cookbook/binary-packages.md):** This page
+  lists the different platforms that provide ready-built software packages for
+  Garage.
+
 - **[Integration with Systemd](@/documentation/cookbook/systemd.md):** This page explains how to run Garage
   as a Systemd service (instead of as a Docker container).
 
@@ -26,6 +30,10 @@ This chapter could also be referred as "Tutorials" or "Best practices".
 
 - **[Configuring a reverse-proxy](@/documentation/cookbook/reverse-proxy.md):** This page explains how to configure a reverse-proxy to add TLS support to your S3 api endpoint.
 
-- **[Recovering from failures](@/documentation/cookbook/recovering.md):** Garage's first selling point is resilience
-  to hardware failures. This section explains how to recover from such a failure in the
-  best possible way.
+- **[Deploying on Kubernetes](@/documentation/cookbook/kubernetes.md):** This page explains how to deploy Garage on Kubernetes using our Helm chart.
+
+- **[Deploying with Ansible](@/documentation/cookbook/ansible.md):** This page lists available Ansible roles developed by the community to deploy Garage.
+
+- **[Monitoring Garage](@/documentation/cookbook/monitoring.md)** This page
+  explains the Prometheus metrics available for monitoring the Garage
+  cluster/nodes.

doc/book/cookbook/ansible.md

@@ -0,0 +1,51 @@
++++
+title = "Deploying with Ansible"
+weight = 35
++++
+
+While Ansible is not officially supported to deploy Garage, several community members
+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** | ✅                                          | ✅                                                            |
+
+
+## zorun/ansible-role-garage
+
+[Source code](https://github.com/zorun/ansible-role-garage), [Ansible galaxy](https://galaxy.ansible.com/zorun/garage)
+
+This role is voluntarily simple: it relies on the official Garage static
+binaries and only requires Systemd.  As such, it should work on any
+Linux-based OS.
+
+To make things more flexible, the user has to provide a Garage
+configuration template.  This allows to customize Garage configuration in
+any way.
+
+Some more features might be added, such as a way to automatically connect
+nodes to each other or to define a layout.
+
+## moan0s/garage-docker-ansible-deploy
+
+[Source code](https://github.com/moan0s/garage-docker-ansible-deploy), [Blog post](https://hyteck.de/post/garage/)
+
+This role is based on the Docker image for Garage, and comes with
+"batteries included": it will additionally install Docker and Traefik. In
+addition, it is "opinionated" in the sense that it expects a particular
+deployment structure (one instance per disk, one gateway per host,
+structured DNS names, etc).
+
+As a result, this role makes it easier to start with Garage on Ansible,
+but is less flexible.

doc/book/cookbook/binary-packages.md

@@ -0,0 +1,41 @@
++++
+title = "Binary packages"
+weight = 11
++++
+
+Garage is also available in binary packages on:
+
+## Alpine Linux
+
+If you use Alpine Linux, you can simply install the
+[garage](https://pkgs.alpinelinux.org/packages?name=garage) package from the
+Alpine Linux repositories (available since v3.17):
+
+```bash
+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.
+
+Please note that this package is built without Consul discovery, Kubernetes
+discovery, OpenTelemetry exporter, and K2V features (K2V will be enabled once
+it's stable).
+
+
+## Arch Linux
+
+Garage is available in the [AUR](https://aur.archlinux.org/packages/garage).
+
+## FreeBSD
+
+```bash
+pkg install garage
+```
+
+## NixOS
+
+```bash
+nix-shell -p garage
+```

doc/book/cookbook/encryption.md

@@ -0,0 +1,139 @@
++++
+title = "Encryption"
+weight = 50
++++
+
+Encryption is a recurring subject when discussing Garage. 
+Garage does not handle data encryption by itself, but many things can
+already be done with Garage's current feature set and the existing ecosystem.
+
+This page takes a high level approach to security in general and data encryption
+in particular.
+
+
+# Examining your need for encryption
+
+- Why do you want encryption in Garage?
+
+- What is your threat model? What are you fearing?
+  - A stolen HDD?
+  - A curious administrator?
+  - A malicious administrator?
+  - A remote attacker?
+  - etc.
+
+- What services do you want to protect with encryption?
+  - An existing application? Which one? (eg. Nextcloud)
+  - An application that you are writing
+
+- Any expertise you may have on the subject
+
+This page explains what Garage provides, and how you can improve the situation by yourself
+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.
+Do not hesitate to come talk to us if you have any thoughts or questions on the
+subject.
+
+
+# Capabilities provided by Garage
+
+## Traffic is encrypted between Garage nodes
+
+RPCs between Garage nodes are encrypted. More specifically, contrary to many
+distributed software, it is impossible in Garage to have clear-text RPC.  We
+use the [kuska handshake](https://github.com/Kuska-ssb/handshake) library which
+implements a protocol that has been clearly reviewed, Secure ScuttleButt's
+Secret Handshake protocol.  This is why setting a `rpc_secret` is mandatory,
+and that's also why your nodes have super long identifiers.
+
+## HTTP API endpoints provided by Garage are in clear text
+
+Adding TLS support built into Garage is not currently planned.
+
+## Garage stores data in plain text on the filesystem or encrypted using customer keys (SSE-C)
+
+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.
+
+If you are developping 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
+
+## Encrypting traffic between a Garage node and your client
+
+You have multiple options to have encryption between your client and a node:
+
+  - Setup a reverse proxy with TLS / ACME / Let's encrypt
+  - Setup a Garage gateway locally, and only contact the garage daemon on `localhost`
+  - Only contact your Garage daemon over a secure, encrypted overlay network such as Wireguard
+
+## Encrypting data at rest
+
+Protects against the following threats:
+
+- Stolen HDD
+
+Crucially, does not protect againt 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:
+
+- A honest-but-curious administrator
+- A malicious administrator that tries to corrupt your data
+- A remote attacker that can read your server's data
+
+Implementations are very specific to the various applications. Examples:
+
+- Matrix: uses the OLM protocol for E2EE of user messages. Media files stored
+  in Matrix are probably encrypted using symmetric encryption, with a key that is
+  distributed in the end-to-end encrypted message that contains the link to the object.
+
+- XMPP: clients normally support either OMEMO / OpenPGP for the E2EE of user
+  messages. Media files are encrypted per
+  [XEP-0454](https://xmpp.org/extensions/xep-0454.html).
+
+- Aerogramme: use the user's password as a key to decrypt data in the user's bucket
+
+- Cyberduck: comes with support for
+  [Cryptomator](https://docs.cyberduck.io/cryptomator/) which allows users to
+  create client-side vaults to encrypt files in before they are uploaded to a
+  cloud storage endpoint.

doc/book/cookbook/exposing-websites.md

@@ -5,12 +5,14 @@ weight = 25
 
 ## Configuring a bucket for website access
 
-There are two methods to expose buckets as website:
+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
 
+3. using the Garage administration API
+
 The `PutBucketWebsite` API endpoint [is documented](https://docs.aws.amazon.com/AmazonS3/latest/API/API_PutBucketWebsite.html) in the official AWS docs.
 This endpoint can also be called [using `aws s3api`](https://docs.aws.amazon.com/cli/latest/reference/s3api/put-bucket-website.html) on the command line.
 The website configuration supported by Garage is only a subset of the possibilities on Amazon S3: redirections are not supported, only the index document and error document can be specified.
@@ -36,7 +38,7 @@ Our website serving logic is as follow:
 
 Now we need to infer the URL of your website through your bucket name.
 Let assume:
-  - we set `root_domain = ".web.example.com"` in `garage.toml` ([ref](@/documentation/reference-manual/configuration.md#root_domain))
+  - we set `root_domain = ".web.example.com"` in `garage.toml` ([ref](@/documentation/reference-manual/configuration.md#web_root_domain))
   - our bucket name is `garagehq.deuxfleurs.fr`.
 
 Our bucket will be served if the Host field matches one of these 2 values (the port is ignored):

doc/book/cookbook/from-source.md

@@ -20,40 +20,76 @@ sudo apt-get update
 sudo apt-get install build-essential
 ```
 
-## Using source from `crates.io`
-
-Garage's source code is published on `crates.io`, Rust's official package repository.
-This means you can simply ask `cargo` to download and build this source code for you:
-
-```bash
-cargo install garage
-```
-
-That's all, `garage` should be in `$HOME/.cargo/bin`.
-
-You can add this folder to your `$PATH` or copy the binary somewhere else on your system.
-For instance:
-
-```bash
-sudo cp $HOME/.cargo/bin/garage /usr/local/bin/garage
-```
-
-
-## Using source from the Gitea repository
+## Building from source from the Gitea repository
 
 The primary location for Garage's source code is the
-[Gitea repository](https://git.deuxfleurs.fr/Deuxfleurs/garage).
+[Gitea 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.
 
-Clone the repository and build Garage with the following commands:
+Clone the repository and enter it as follows:
 
 ```bash
 git clone https://git.deuxfleurs.fr/Deuxfleurs/garage.git
 cd garage
-cargo build
 ```
 
-Be careful, as this will make a debug build of Garage, which will be extremely slow!
-To make a release build, invoke `cargo build --release` (this takes much longer).
+If you wish to build a specific version of Garage, check out the corresponding tag. For instance:
 
-The binaries built this way are found in `target/{debug,release}/garage`.
+```bash
+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
+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.
+
+Finally, build Garage with the following command:
+
+```bash
+cargo build --release
+```
+
+The binary built this way can now be found in `target/release/garage`.
+You may simply copy this binary to somewhere in your `$PATH` in order to
+have the `garage` command available in your shell, for instance:
+
+```bash
+sudo cp target/release/garage /usr/local/bin/garage
+```
+
+If you are planning to develop Garage,
+you might be interested in producing debug builds, which compile faster but run slower:
+this can be done by removing the `--release` flag, and the resulting build can then
+be found in `target/debug/garage`.
+
+## List of available Cargo feature flags
+
+Garage supports a number of compilation options in the form of Cargo feature flags,
+which can be used to provide builds adapted to your system and your use case.
+To produce a build with a given set of features, invoke the `cargo build` command
+as follows:
+
+```bash
+# This will build the default feature set plus feature1, feature2 and feature3
+cargo build --release --features feature1,feature2,feature3
+# This will build ONLY feature1, feature2 and feature3
+cargo build --release --no-default-features \
+            --features feature1,feature2,feature3
+```
+
+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`) |
+| `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 |
+| `metrics` | *by default* | Enable collection of metrics in Prometheus format on the admin API |
+| `telemetry-otlp` | optional | Enable collection of execution traces using OpenTelemetry |
+| `syslog` | optional | Enable logging to Syslog |
+| `lmdb` | *by default* | Enable using LMDB to store Garage's metadata |
+| `sqlite` | *by default* | Enable using Sqlite3 to store Garage's metadata |

doc/book/cookbook/gateways.md

@@ -21,7 +21,7 @@ You can configure Garage as a gateway on all nodes that will consume your S3 API
 The instructions are similar to a regular node, the only option that is different is while configuring the node, you must set the `--gateway` parameter:
 
 ```bash
-garage layout assign --gateway --tag gw1 <node_id>
+garage layout assign --gateway --tag gw1 -z dc1 <node_id>
 garage layout show    # review the changes you are making
 garage layout apply   # once satisfied, apply the changes
 ```

doc/book/cookbook/kubernetes.md

@@ -0,0 +1,88 @@
++++
+title = "Deploying on Kubernetes"
+weight = 32
++++
+
+Garage can also be deployed on a kubernetes cluster via helm chart.
+
+## Deploying
+
+Firstly clone the repository:
+
+```bash
+git clone https://git.deuxfleurs.fr/Deuxfleurs/garage
+cd garage/scripts/helm
+```
+
+Deploy with default options:
+
+```bash
+helm install --create-namespace --namespace garage garage ./garage
+```
+
+Or deploy with custom values:
+
+```bash
+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
+kubectl exec --stdin --tty -n garage garage-0 -- ./garage status
+```
+
+## Overriding default values
+
+All possible configuration values can be found with:
+
+```bash
+helm show values ./garage
+```
+
+This is an example `values.overrride.yaml` for deploying in a microk8s cluster with a https s3 api ingress route:
+
+```yaml
+garage:
+  # Use only 2 replicas per object
+  replicationMode: "2"
+
+# Start 4 instances (StatefulSets) of garage
+deployment:
+  replicaCount: 4
+
+# Override default storage class and size
+persistence:
+  meta:
+    storageClass: "openebs-hostpath"
+    size: 100Mi
+  data:
+    storageClass: "openebs-hostpath"
+    size: 1Gi
+
+ingress:
+  s3:
+    api:
+      enabled: true
+      className: "public"
+      annotations:
+        cert-manager.io/cluster-issuer: "letsencrypt-prod"
+        nginx.ingress.kubernetes.io/proxy-body-size: 500m
+      hosts:
+        - host: s3-api.my-domain.com
+          paths:
+            - path: /
+              pathType: Prefix
+      tls:
+        - secretName: garage-ingress-cert
+          hosts:
+            - s3-api.my-domain.com
+```
+
+## Removing
+
+```bash
+helm delete --namespace garage garage
+```
+
+Note that this will leave behind custom CRD `garagenodes.deuxfleurs.fr`, which must be removed manually if desired.

doc/book/cookbook/monitoring.md

@@ -0,0 +1,53 @@
++++
+title = "Monitoring Garage"
+weight = 40
++++
+
+Garage exposes some internal metrics in the Prometheus data format.
+This page explains how to exploit these metrics.
+
+## Setting up monitoring
+
+### Enabling the Admin API endpoint
+
+If you have not already enabled the [administration API endpoint](@/documentation/reference-manual/admin-api.md), do so by adding the following lines to your configuration file:
+
+```toml
+[admin]
+api_bind_addr = "0.0.0.0:3903"
+```
+
+This will allow anyone to scrape Prometheus metrics by fetching
+`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.
+
+### Setting up Prometheus and Grafana
+
+Add a scrape config to your Prometheus daemon to scrape metrics from
+all of your nodes:
+
+```yaml
+scrape_configs:
+  - job_name: 'garage'
+    static_configs:
+      - targets:
+        - 'node1.mycluster:3903'
+        - 'node2.mycluster:3903'
+        - 'node3.mycluster:3903'
+```
+
+If you have set a metrics token in your Garage configuration file,
+add the following lines in your Prometheus scrape config:
+
+```yaml
+    authorization:
+      type: Bearer
+      credentials: 'your metrics token'
+```
+
+To visualize the scraped data in Grafana,
+you can either import our [Grafana dashboard for Garage](https://git.deuxfleurs.fr/Deuxfleurs/garage/raw/branch/main/script/telemetry/grafana-garage-dashboard-prometheus.json)
+or make your own.
+
+The list of exported metrics is available on our [dedicated page](@/documentation/reference-manual/monitoring.md) in the Reference manual section.

doc/book/cookbook/real-world.md

@@ -11,21 +11,23 @@ We recommend first following the [quick start guide](@/documentation/quick-start
 to get familiar with Garage's command line and usage patterns.
 
 
+## Preparing your environment
 
-## Prerequisites
+### Prerequisites
 
 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.
-  Running behind a NAT is likely to be possible but hasn't been tested for the latest version (TODO).
+- 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.
 
-- Ideally, each machine should have a SSD available in addition to the HDD you are dedicating
-  to Garage. This will allow for faster access to metadata and has the potential
-  to drastically reduce Garage's response times.
-
-- 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.
@@ -35,24 +37,73 @@ For our example, we will suppose the following infrastructure with IPv6 connecti
 
 | Location | Name    | IP Address | Disk Space |
 |----------|---------|------------|------------|
-| Paris    | Mercury | fc00:1::1  | 1 To       |
-| Paris    | Venus   | fc00:1::2  | 2 To       |
-| London   | Earth   | fc00:B::1  | 2 To       |
-| Brussels | Mars    | fc00:F::1  | 1.5 To     |
+| Paris    | Mercury | fc00:1::1  | 1 TB       |
+| Paris    | Venus   | fc00:1::2  | 2 TB       |
+| London   | Earth   | fc00:B::1  | 2 TB       |
+| 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 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
+available in the different locations of your cluster is roughly the same.
+For instance, here, the Mercury node could be moved to Brussels; this would allow the cluster
+to store 2 TB of data in total.
 
+### Best practices
+
+- 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.
+  Ideally, the metadata directory would be stored on an SSD (smaller but faster),
+  and the data directory would be stored on an HDD (larger but slower).
+
+- For the data directory, Garage already does checksumming and integrity verification,
+  so there is no need to use a filesystem such as BTRFS or ZFS that does it.
+  We recommend using XFS for the data partition, as it has the best performance.
+  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.
+
+- 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/amd64_garage` and is stored on the [Docker Hub](https://hub.docker.com/r/dxflrs/amd64_garage/tags?page=1&ordering=last_updated).
-We encourage you to use a fixed tag (eg. `v0.4.0`) and not the `latest` tag.
-For this example, we will use the latest published version at the time of the writing which is `v0.4.0` but it's up to you
-to check [the most recent versions on the Docker Hub](https://hub.docker.com/r/dxflrs/amd64_garage/tags?page=1&ordering=last_updated).
+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. `v1.0.1`) and not the `latest` tag.
+For this example, we will use the latest published version at the time of the writing which is `v1.0.1` but it's up to you
+to check [the most recent versions on the Docker Hub](https://hub.docker.com/r/dxflrs/garage/tags?page=1&ordering=last_updated).
 
 For example:
 
 ```
-sudo docker pull dxflrs/amd64_garage:v0.4.0
+sudo docker pull dxflrs/garage:v1.0.1
 ```
 
 ## Deploying and configuring Garage
@@ -69,13 +120,15 @@ especially you must consider the following folders/files:
   this folder will be your main data storage and must be on a large storage (e.g. large HDD)
 
 
-A valid `/etc/garage/garage.toml` for our cluster would look as follows:
+A valid `/etc/garage.toml` for our cluster would look as follows:
 
 ```toml
 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
 
@@ -83,8 +136,6 @@ rpc_bind_addr = "[::]:3901"
 rpc_public_addr = "<this node's public IP>:3901"
 rpc_secret = "<RPC secret>"
 
-bootstrap_peers = []
-
 [s3_api]
 s3_region = "garage"
 api_bind_addr = "[::]:3900"
@@ -101,6 +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`.
@@ -118,19 +171,37 @@ 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 \
-  lxpz/garage_amd64:v0.4.0
+  dxflrs/garage:v1.0.1
 ```
 
-It should be restarted automatically at each reboot.
-Please note that we use host networking as otherwise Docker containers
-can not communicate with IPv6.
+With this command line, Garage should be started automatically at each boot.
+Please note that we use host networking as otherwise the network indirection
+added by Docker would prevent Garage nodes from communicating with one another
+(especially if using IPv6).
 
-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 want to use `docker-compose`, you may use the following `docker-compose.yml` file as a reference:
 
-## Controling the daemon
+```yaml
+version: "3"
+services:
+  garage:
+    image: dxflrs/garage:v1.0.1
+    network_mode: "host"
+    restart: unless-stopped
+    volumes:
+      - /etc/garage.toml:/etc/garage.toml
+      - /var/lib/garage/meta:/var/lib/garage/meta
+      - /var/lib/garage/data:/var/lib/garage/data
+```
+
+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.
+
+## Controlling the daemon
 
 The `garage` binary has two purposes:
   - it acts as a daemon when launched with `garage server`
@@ -139,6 +210,12 @@ The `garage` binary has two purposes:
 Ensure an appropriate `garage` binary (the same version as your Docker image) is available in your path.
 If your configuration file is at `/etc/garage.toml`, the `garage` binary should work with no further change.
 
+You can also use an alias as follows to use the Garage binary inside your docker container:
+
+```bash
+alias garage="docker exec -ti <container name> /garage"
+```
+
 You can test your `garage` CLI utility by running a simple command such as:
 
 ```bash
@@ -182,7 +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:
@@ -206,12 +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 To       | `10`       | `563e`     | `par1`       |
-| Paris    | Venus   | 2 To       | `20`       | `86f0`     | `par1`       |
-| London   | Earth   | 2 To       | `20`       | `6814`     | `lon1`       |
-| Brussels | Mars    | 1.5 To     | `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
 
@@ -233,6 +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.
@@ -242,29 +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 -z par1 -c 10 -t mercury 563e
-garage layout assign -z par1 -c 20 -t venus 86f0
-garage layout assign -z lon1 -c 20 -t earth 6814
-garage layout assign -z bru1 -c 15 -t mars 212f
+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.
@@ -274,6 +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
@@ -281,7 +361,7 @@ garage layout apply
 ```
 
 **WARNING:** if you want to use the layout modification commands in a script,
-make sure to read [this page](@/documentation/reference-manual/layout.md) first.
+make sure to read [this page](@/documentation/operations/layout.md) first.
 
 
 ## Using your Garage cluster
@@ -291,5 +371,5 @@ and is covered in the [quick start guide](@/documentation/quick-start/_index.md)
 Remember also that the CLI is self-documented thanks to the `--help` flag and
 the `help` subcommand (e.g. `garage help`, `garage key --help`).
 
-Configuring S3-compatible applicatiosn to interact with Garage
+Configuring S3-compatible applications to interact with Garage
 is covered in the [Integrations](@/documentation/connect/_index.md) section.

doc/book/cookbook/reverse-proxy.md

@@ -70,14 +70,16 @@ A possible configuration:
 
 ```nginx
 upstream s3_backend {
-  # if you have a garage instance locally
+  # If you have a garage instance locally.
   server 127.0.0.1:3900;
-  # you can also put your other instances
+  # You can also put your other instances.
   server 192.168.1.3:3900;
-  # domain names also work
+  # Domain names also work.
   server garage1.example.com:3900;
-  # you can assign weights if you have some servers 
-  # that are more powerful than others
+  # A "backup" server is only used if all others have failed.
+  server garage-remote.example.com:3900 backup;
+  # You can assign weights if you have some servers
+  # that can serve more requests than others.
   server garage2.example.com:3900 weight=2;
 }
 
@@ -96,11 +98,13 @@ server {
     proxy_pass http://s3_backend;
     proxy_set_header X-Forwarded-For $proxy_add_x_forwarded_for;
     proxy_set_header Host $host;
+    # Disable buffering to a temporary file.
+    proxy_max_temp_file_size 0;
   }
 }
 ```
 
-## Exposing the web endpoint
+### Exposing the web endpoint
 
 To better understand the logic involved, you can refer to the [Exposing buckets as websites](/cookbook/exposing_websites.html) section.
 Otherwise, the configuration is very similar to the S3 endpoint.
@@ -140,6 +144,360 @@ server {
 
 @TODO
 
-## Traefik
+## Traefik v2
 
-@TODO
+We will see in this part how to set up a reverse proxy with [Traefik](https://docs.traefik.io/).
+
+Here is [a basic configuration file](https://doc.traefik.io/traefik/https/acme/#configuration-examples):
+
+```toml
+[entryPoints]
+  [entryPoints.web]
+    address = ":80"
+
+  [entryPoints.websecure]
+    address = ":443"
+
+[certificatesResolvers.myresolver.acme]
+  email = "your-email@example.com"
+  storage = "acme.json"
+  [certificatesResolvers.myresolver.acme.httpChallenge]
+    # used during the challenge
+    entryPoint = "web"
+```
+
+### Add Garage service
+
+To add Garage on Traefik you should declare two new services using its IP
+address (or hostname) and port, these are used for the S3, and web components
+of Garage:
+
+```toml
+[http.services]
+  [http.services.garage-s3-service.loadBalancer]
+    [[http.services.garage-s3-service.loadBalancer.servers]]
+      url = "http://xxx.xxx.xxx.xxx"
+      port = 3900
+
+  [http.services.garage-web-service.loadBalancer]
+    [[http.services.garage-web-service.loadBalancer.servers]]
+      url = "http://xxx.xxx.xxx.xxx"
+      port = 3902
+```
+
+It's possible to declare multiple Garage servers as back-ends:
+
+```toml
+[http.services]
+    [[http.services.garage-s3-service.loadBalancer.servers]]
+      url = "http://xxx.xxx.xxx.xxx"
+      port = 3900
+    [[http.services.garage-s3-service.loadBalancer.servers]]
+      url = "http://yyy.yyy.yyy.yyy"
+      port = 3900
+    [[http.services.garage-s3-service.loadBalancer.servers]]
+      url = "http://zzz.zzz.zzz.zzz"
+      port = 3900
+
+    [[http.services.garage-web-service.loadBalancer.servers]]
+      url = "http://xxx.xxx.xxx.xxx"
+      port = 3902
+    [[http.services.garage-web-service.loadBalancer.servers]]
+      url = "http://yyy.yyy.yyy.yyy"
+      port = 3902
+    [[http.services.garage-web-service.loadBalancer.servers]]
+      url = "http://zzz.zzz.zzz.zzz"
+      port = 3902
+```
+
+Traefik can remove unhealthy servers automatically with [a health check configuration](https://doc.traefik.io/traefik/routing/services/#health-check):
+
+```
+[http.services]
+  [http.services.garage-s3-service.loadBalancer]
+    [http.services.garage-s3-service.loadBalancer.healthCheck]
+      path = "/health"
+      port = "3903"
+      #interval = "15s"
+      #timeout = "2s"
+
+  [http.services.garage-web-service.loadBalancer]
+    [http.services.garage-web-service.loadBalancer.healthCheck]
+      path = "/health"
+      port = "3903"
+      #interval = "15s"
+      #timeout = "2s"
+```
+
+### Adding a website
+
+To add a new website, add the following declaration to your Traefik configuration file:
+
+```toml
+[http.routers]
+  [http.routers.garage-s3]
+    rule = "Host(`s3.example.org`)"
+    service = "garage-s3-service"
+    entryPoints = ["websecure"]
+
+  [http.routers.my_website]
+    rule = "Host(`yoururl.example.org`)"
+    service = "garage-web-service"
+    entryPoints = ["websecure"]
+```
+
+Enable HTTPS access to your website with the following configuration section ([documentation](https://doc.traefik.io/traefik/https/overview/)):
+
+```toml
+...
+    entryPoints = ["websecure"]
+    [http.routers.my_website.tls]
+      certResolver = "myresolver"
+...
+```
+
+### Adding compression
+
+Add the following configuration section [to compress response](https://doc.traefik.io/traefik/middlewares/http/compress/) using [gzip](https://developer.mozilla.org/en-US/docs/Glossary/GZip_compression) before sending them to the client:
+
+```toml
+[http.routers]
+  [http.routers.my_website]
+    ...
+    middlewares = ["compression"]
+    ...
+[http.middlewares]
+  [http.middlewares.compression.compress]
+```
+
+### Add caching response
+
+Traefik's caching middleware is only available on [entreprise version](https://doc.traefik.io/traefik-enterprise/middlewares/http-cache/), however the freely-available [Souin plugin](https://github.com/darkweak/souin#tr%C3%A6fik-container) can also do the job. (section to be completed)
+
+### Complete example
+
+```toml
+[entryPoints]
+  [entryPoints.web]
+    address = ":80"
+
+  [entryPoints.websecure]
+    address = ":443"
+
+[certificatesResolvers.myresolver.acme]
+  email = "your-email@example.com"
+  storage = "acme.json"
+  [certificatesResolvers.myresolver.acme.httpChallenge]
+    # used during the challenge
+    entryPoint = "web"
+
+[http.routers]
+  [http.routers.garage-s3]
+    rule = "Host(`s3.example.org`)"
+    service = "garage-s3-service"
+    entryPoints = ["websecure"]
+
+  [http.routers.my_website]
+    rule = "Host(`yoururl.example.org`)"
+    service = "garage-web-service"
+    middlewares = ["compression"]
+    entryPoints = ["websecure"]
+
+[http.services]
+  [http.services.garage-s3-service.loadBalancer]
+    [http.services.garage-s3-service.loadBalancer.healthCheck]
+      path = "/health"
+      port = "3903"
+      #interval = "15s"
+      #timeout = "2s"
+
+  [http.services.garage-web-service.loadBalancer]
+    [http.services.garage-web-service.loadBalancer.healthCheck]
+      path = "/health"
+      port = "3903"
+      #interval = "15s"
+      #timeout = "2s"
+
+    [[http.services.garage-s3-service.loadBalancer.servers]]
+      url = "http://xxx.xxx.xxx.xxx"
+      port = 3900
+    [[http.services.garage-s3-service.loadBalancer.servers]]
+      url = "http://yyy.yyy.yyy.yyy"
+      port = 3900
+    [[http.services.garage-s3-service.loadBalancer.servers]]
+      url = "http://zzz.zzz.zzz.zzz"
+      port = 3900
+
+    [[http.services.garage-web-service.loadBalancer.servers]]
+      url = "http://xxx.xxx.xxx.xxx"
+      port = 3902
+    [[http.services.garage-web-service.loadBalancer.servers]]
+      url = "http://yyy.yyy.yyy.yyy"
+      port = 3902
+    [[http.services.garage-web-service.loadBalancer.servers]]
+      url = "http://zzz.zzz.zzz.zzz"
+      port = 3902
+
+[http.middlewares]
+  [http.middlewares.compression.compress]
+```
+
+## Caddy
+
+Your Caddy configuration can be as simple as:
+
+```caddy
+s3.garage.tld, *.s3.garage.tld {
+	reverse_proxy localhost:3900 192.168.1.2:3900 example.tld:3900 {
+        health_uri       /health
+        health_port      3903
+        #health_interval 15s
+        #health_timeout  5s
+    }
+}
+
+*.web.garage.tld {
+	reverse_proxy localhost:3902 192.168.1.2:3902 example.tld:3902 {
+        health_uri       /health
+        health_port      3903
+        #health_interval 15s
+        #health_timeout  5s
+    }
+}
+
+admin.garage.tld {
+	reverse_proxy localhost:3903 {
+        health_uri       /health
+        health_port      3903
+        #health_interval 15s
+        #health_timeout  5s
+    }
+}
+```
+
+But at the same time, the `reverse_proxy` is very flexible.
+For a production deployment, you should [read its documentation](https://caddyserver.com/docs/caddyfile/directives/reverse_proxy) as it supports features like DNS discovery of upstreams, load balancing with checks, streaming parameters, etc.
+
+### Caching
+
+Caddy can compiled with a
+[cache plugin](https://github.com/caddyserver/cache-handler) which can be used
+to provide a hot-cache at the webserver-level for static websites hosted by
+Garage.
+
+This can be configured as follows:
+
+```caddy
+# Caddy global configuration section
+{
+	# Bare minimum configuration to enable cache.
+	order cache before rewrite
+
+	cache
+
+	#cache
+	#	allowed_http_verbs GET
+	#	default_cache_control public
+	#	ttl 8h
+	#}
+}
+
+# Site specific section
+https:// {
+	cache
+
+	#cache {
+	#	timeout {
+	#		backend 30s
+	#	}
+	#}
+
+	reverse_proxy ...
+}
+```
+
+Caching is a complicated subject, and the reader is encouraged to study the
+available options provided by the plugin.
+
+### On-demand TLS
+
+Caddy supports a technique called
+[on-demand TLS](https://caddyserver.com/docs/automatic-https#on-demand-tls), by
+which one can configure the webserver to provision TLS certificates when a
+client first connects to it.
+
+In order to prevent an attack vector whereby domains are simply pointed at your
+webserver and certificates are requested for them - Caddy can be configured to
+ask Garage if a domain is authorized for web hosting, before it then requests
+a TLS certificate.
+
+This 'check' endpoint, which is on the admin port (3903 by default), can be
+configured in Caddy's global section as follows:
+
+```caddy
+{
+	...
+	on_demand_tls {
+		ask http://localhost:3903/check
+		interval 2m
+		burst 5
+	}
+	...
+}
+```
+
+The host section can then be configured with (note that this uses the web
+endpoint instead):
+
+```caddy
+# For a specific set of subdomains
+*.web.garage.tld {
+	tls {
+		on_demand
+	}
+
+	reverse_proxy localhost:3902 192.168.1.2:3902 example.tld:3902
+}
+
+# Accept all domains on HTTPS
+# Never configure this without global section above
+https:// {
+	tls {
+		on_demand
+	}
+
+	reverse_proxy localhost:3902 192.168.1.2:3902 example.tld:3902
+}
+```
+
+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.

doc/book/cookbook/systemd.md

@@ -33,7 +33,20 @@ NoNewPrivileges=true
 WantedBy=multi-user.target
 ```
 
-*A note on hardening: garage will be run as a non privileged user, its user id is dynamically allocated by systemd. 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 (mapped to /var/lib/private/garage on your host). Additionnaly, the process can not gain new privileges over time.*
+**A note on hardening:** Garage will be run as a non privileged user, its user
+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
+can not gain new privileges over time.
+
+For this to work correctly, your `garage.toml` must be set with
+`metadata_dir=/var/lib/garage/meta` and `data_dir=/var/lib/garage/data`. This
+is mandatory to use the DynamicUser hardening feature of systemd, which
+autocreates these directories as virtual mapping. If the directory
+`/var/lib/garage` already exists before starting the server for the first time,
+the systemd service might not start correctly.  Note that in your host
+filesystem, Garage data will be held in `/var/lib/private/garage`.
 
 To start the service then automatically enable it at boot:
 

doc/book/design/_index.md

@@ -1,6 +1,6 @@
 +++
 title = "Design"
-weight = 5
+weight = 70
 sort_by = "weight"
 template = "documentation.html"
 +++
@@ -20,12 +20,16 @@ and could not do, etc.
 
 We love to talk and hear about Garage, that's why we keep a log here:
 
+  - [(en, 2023-01-18) Presentation of Garage with some details on CRDTs and data partitioning among nodes](https://git.deuxfleurs.fr/Deuxfleurs/garage/src/commit/4cff37397f626ef063dad29e5b5e97ab1206015d/doc/talks/2023-01-18-tocatta/talk.pdf)
+
+  - [(fr, 2022-11-19) De l'auto-hébergement à l'entre-hébergement : Garage, pour conserver ses données ensemble](https://git.deuxfleurs.fr/Deuxfleurs/garage/src/commit/4cff37397f626ef063dad29e5b5e97ab1206015d/doc/talks/2022-11-19-Capitole-du-Libre/pr%C3%A9sentation.pdf)
+
+  - [(en, 2022-06-23) General presentation of Garage](https://git.deuxfleurs.fr/Deuxfleurs/garage/src/commit/4cff37397f626ef063dad29e5b5e97ab1206015d/doc/talks/2022-06-23-stack/talk.pdf)
+
   - [(fr, 2021-11-13, video) Garage : Mille et une façons de stocker vos données](https://video.tedomum.net/w/moYKcv198dyMrT8hCS5jz9) and [slides (html)](https://rfid.deuxfleurs.fr/presentations/2021-11-13/garage/) - during [RFID#1](https://rfid.deuxfleurs.fr/programme/2021-11-13/) event
 
-  - [(en, 2021-04-28) Distributed object storage is centralised](https://git.deuxfleurs.fr/Deuxfleurs/garage/raw/commit/b1f60579a13d3c5eba7f74b1775c84639ea9b51a/doc/talks/2021-04-28_spirals-team/talk.pdf)
+  - [(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/raw/commit/b1f60579a13d3c5eba7f74b1775c84639ea9b51a/doc/talks/2020-12-02_wide-team/talk.pdf)
-
-*Did you write or talk about Garage? [Open a pull request](https://git.deuxfleurs.fr/Deuxfleurs/garage/) to add a link here!*
+  - [(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)
 
 

doc/book/design/benchmarks/index.md

@@ -1,6 +1,6 @@
 +++
 title = "Benchmarks"
-weight = 10
+weight = 40
 +++
 
 With Garage, we wanted to build a software defined storage service that follow the [KISS principle](https://en.wikipedia.org/wiki/KISS_principle),

doc/book/design/goals.md

@@ -1,23 +1,23 @@
 +++
 title = "Goals and use cases"
-weight = 5
+weight = 10
 +++
 
 ## Goals and non-goals
 
 Garage is a lightweight geo-distributed data store that implements the
 [Amazon S3](https://docs.aws.amazon.com/AmazonS3/latest/API/Welcome.html)
-object storage protocole. It enables applications to store large blobs such
+object storage protocol. It enables applications to store large blobs such
 as pictures, video, images, documents, etc., in a redundant multi-node
 setting. S3 is versatile enough to also be used to publish a static
 website.
 
-Garage is an opinionated object storage solutoin, we focus on the following **desirable properties**:
+Garage is an opinionated object storage solution, we focus on the following **desirable properties**:
 
+  - **Internet enabled**: made for multi-sites (eg. datacenters, offices, households, etc.) interconnected through regular Internet connections.
   - **Self-contained & lightweight**: works everywhere and integrates well in existing environments to target [hyperconverged infrastructures](https://en.wikipedia.org/wiki/Hyper-converged_infrastructure).
   - **Highly resilient**: highly resilient to network failures, network latency, disk failures, sysadmin failures.
   - **Simple**: simple to understand, simple to operate, simple to debug.
-  - **Internet enabled**: made for multi-sites (eg. datacenters, offices, households, etc.) interconnected through regular Internet connections.
 
 We also noted that the pursuit of some other goals are detrimental to our initial goals.
 The following has been identified as **non-goals** (if these points matter to you, you should not use Garage):
@@ -42,15 +42,28 @@ locations. They use Garage themselves for the following tasks:
 
 - As a [Matrix media backend](https://github.com/matrix-org/synapse-s3-storage-provider)
 
-- To store personal data and shared documents through [Bagage](https://git.deuxfleurs.fr/Deuxfleurs/bagage), a homegrown WebDav-to-S3 proxy
-
-- In the Drone continuous integration platform to store task logs
-
 - As a Nix binary cache
 
-- As a backup target using `rclone`
+- To store personal data and shared documents through [Bagage](https://git.deuxfleurs.fr/Deuxfleurs/bagage), a homegrown WebDav-to-S3 and SFTP-to-S3 proxy
+
+- As a backup target using `rclone` and `restic`
 
 The Deuxfleurs Garage cluster is a multi-site cluster currently composed of
-4 nodes in 2 physical locations. In the future it will be expanded to at
-least 3 physical locations to fully exploit Garage's potential for high
-availability.
+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 Mastodon object 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
+10 nodes in 3 physical locations.

doc/book/design/internals.md

@@ -20,6 +20,49 @@ In the meantime, you can find some information at the following links:
 - [an old design draft](@/documentation/working-documents/design-draft.md)
 
 
+## Request routing logic
+
+Data retrieval requests to Garage endpoints (S3 API and websites) are resolved 
+to an individual object in a bucket. Since objects are replicated to multiple nodes 
+Garage must ensure consistency before answering the request.
+
+### Using quorum to ensure consistency
+
+Garage ensures consistency by attempting to establish a quorum with the
+data nodes responsible for the object. When a majority of the data nodes
+have provided metadata on a object Garage can then answer the request.
+
+When a request arrives Garage will, assuming the recommended 3 replicas, perform the following actions:
+
+- Make a request to the two preferred nodes for object metadata
+- Try the third node if one of the two initial requests fail
+- Check that the metadata from at least 2 nodes match
+- Check that the object hasn't been marked deleted
+- Answer the request with inline data from metadata if object is small enough
+- Or get data blocks from the preferred nodes and answer using the assembled object
+
+Garage dynamically determines which nodes to query based on health, preference, and 
+which nodes actually host a given data. Garage has no concept of "primary" so any 
+healthy node with the data can be used as long as a quorum is reached for the metadata.
+
+### Node health
+
+Garage keeps a TCP session open to each node in the cluster and periodically pings them. If a connection
+cannot be established, or a node fails to answer a number of pings, the target node is marked as failed.
+Failed nodes are not used for quorum or other internal requests.
+
+### Node preference
+
+Garage prioritizes which nodes to query according to a few criteria:
+
+- A node always prefers itself if it can answer the request
+- Then the node prioritizes nodes in the same zone
+- Finally the nodes with the lowest latency are prioritized 
+
+
+For further reading on the cluster structure look at the [gateway](@/documentation/cookbook/gateways.md) 
+and [cluster layout management](@/documentation/operations/layout.md) pages.
+
 ## Garbage collection
 
 A faulty garbage collection procedure has been the cause of
@@ -54,7 +97,7 @@ delete a tombstone, the following condition has to be met:
   superseeded 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.
 

doc/book/design/related-work.md

@@ -1,6 +1,6 @@
 +++
 title = "Related work"
-weight = 15
+weight = 50
 +++
 
 ## Context
@@ -67,13 +67,12 @@ Pithos has been abandonned and should probably not used yet, in the following we
 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*
 
-**[IPFS](https://ipfs.io/):**
-*Not written yet*
+**[IPFS](https://ipfs.io/):** IPFS has design goals radically different from Garage, we have [a blog post](@/blog/2022-ipfs/index.md) talking about it.
 
 ## Specific research papers
 

doc/book/development/_index.md

@@ -1,6 +1,6 @@
 +++
 title = "Development"
-weight = 6
+weight = 80
 sort_by = "weight"
 template = "documentation.html"
 +++

doc/book/development/devenv.md

@@ -25,7 +25,7 @@ git clone https://git.deuxfleurs.fr/Deuxfleurs/garage
 cd garage
 ```
 
-*Optionnaly, you can use our nix.conf file to speed up compilations:*
+*Optionally, you can use our nix.conf file to speed up compilations:*
 
 ```bash
 sudo mkdir -p /etc/nix
@@ -39,7 +39,7 @@ Now you can enter our nix-shell, all the required packages will be downloaded bu
 nix-shell
 ```
 
-You can use the traditionnal Rust development workflow:
+You can use the traditional Rust development workflow:
 
 ```bash
 cargo build  # compile the project
@@ -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`:
 

doc/book/development/miscellaneous-notes.md

@@ -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.

doc/book/development/release-process.md

@@ -11,7 +11,7 @@ We define them as our release process.
 While we run some tests on every commits, we do not make a release for all of them.
 
 A release can be triggered manually by "promoting" a successful build.
-Otherwise, every weeks, a release build is triggered on the `main` branch.
+Otherwise, every night, a release build is triggered on the `main` branch.
 
 If the build is from a tag following the regex: `v[0-9]+\.[0-9]+\.[0-9]+`, it will be listed as stable.
 If it is a tag but with a different format, it will be listed as Extra.
@@ -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.relase` 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.

doc/book/operations/_index.md

@@ -0,0 +1,23 @@
++++
+title = "Operations & Maintenance"
+weight = 50
+sort_by = "weight"
+template = "documentation.html"
++++
+
+This section contains a number of important information on how to best operate a Garage cluster,
+to ensure integrity and availability of your data:
+
+- **[Upgrading Garage](@/documentation/operations/upgrading.md):** General instructions on how to
+  upgrade your cluster from one version to the next. Instructions specific for each version upgrade
+  can bef ound in the [working documents](@/documentation/working-documents/_index.md) section.
+
+- **[Layout management](@/documentation/operations/layout.md):** Best practices for using the `garage layout`
+  commands when adding or removing nodes from your cluster.
+
+- **[Durability and repairs](@/documentation/operations/durability-repairs.md):** How to check for small things
+  that might be going wrong, and how to recover from such failures.
+
+- **[Recovering from failures](@/documentation/operations/recovering.md):** Garage's first selling point is resilience
+  to hardware failures. This section explains how to recover from such a failure in the
+  best possible way.

doc/book/operations/durability-repairs.md

@@ -0,0 +1,147 @@
++++
+title = "Durability & Repairs"
+weight = 30
++++
+
+To ensure the best durability of your data and to fix any inconsistencies that may
+pop up in a distributed system, Garage provides a series of repair operations.
+This guide will explain the meaning of each of them and when they should be applied.
+
+
+# General syntax of repair operations
+
+Repair operations described below are of the form `garage repair <repair_name>`.
+These repairs will not launch without the `--yes` flag, which should
+be added as follows: `garage repair --yes <repair_name>`.
+By default these repair procedures will only run on the Garage node your CLI is
+connecting to. To run on all nodes, add the `-a` flag as follows:
+`garage repair -a --yes <repair_name>`.
+
+# Data block operations
+
+## 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
+(e.g. by bitrot or by an accidental manipulation of the datastore) will be
+restored from another node that holds a valid copy.
+
+Scrubs are automatically scheduled by Garage to run every 25-35 days (the
+actual time is randomized to spread load across nodes). The next scheduled run
+can be viewed with `garage worker get`.
+
+A scrub can also be launched manually using `garage repair scrub start`.
+
+To view the status of an ongoing scrub, first find the task ID of the scrub worker
+using `garage worker list`. Then, run `garage worker info <scrub_task_id>` to
+view detailed runtime statistics of the scrub. To gather cluster-wide information,
+this command has to be run on each individual node.
+
+A scrub is a very disk-intensive operation that might slow down your cluster.
+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`.
+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
+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
+are referenced.
+
+It is recommended to run this procedure when changing your cluster layout,
+after the metadata tables have finished synchronizing between nodes
+(usually a few hours after `garage layout apply`).
+
+## Inspecting lost blocks
+
+In extremely rare situations, data blocks may be unavailable from the entire cluster.
+This means that even using `garage repair blocks`, some nodes may be unable
+to fetch data blocks for which they hold a reference.
+
+These errors are stored on each node in a list of "block resync errors", i.e.
+blocks for which the last resync operation failed.
+This list can be inspected using `garage block list-errors`.
+These errors usually fall into one of the following categories:
+
+1. a block is still referenced but the object was deleted, this is a case
+   of metadata reference inconsistency (see below for the fix)
+2. a block is referenced by a non-deleted object, but could not be fetched due
+   to a transient error such as a network failure
+3. a block is referenced by a non-deleted object, but could not be fetched due
+   to a permanent error such as there not being any valid copy of the block on the
+   entire cluster
+
+To help make the difference between cases 1 and cases 2 and 3, you may use the
+`garage block info` command to see which objects hold a reference to each block.
+
+In the second case (transient errors), Garage will try to fetch the block again
+after a certain time, so the error should disappear naturally. You can also
+request Garage to try to fetch the block immediately using `garage block retry-now`
+if you have fixed the transient issue.
+
+If you are confident that you are in the third scenario and that your data block
+is definitely lost, then there is no other choice than to declare your S3 objects
+as unrecoverable, and to delete them properly from the data store. This can be done
+using the `garage block purge` command.
+
+## Rebalancing data directories
+
+In [multi-HDD setups](@/documentation/operations/multi-hdd.md), to ensure that
+data blocks are well balanced between storage locations, you may run a
+rebalance operation using `garage repair rebalance`. This is 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
+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,
+to ensure that all nodes have the most up-to-date version of all the information
+they should be holding.
+The resync procedure is based on a Merkle tree that allows to efficiently find
+differences between nodes.
+
+In some special cases, e.g. before an upgrade, you might want to run a table
+resync manually. This can be done using `garage repair tables`.
+
+## Metadata table reference fixes
+
+In some very rare cases where nodes are unavailable, some references between objects
+are broken. For instance, if an object is deleted, the underlying versions or data
+blocks may still be held by Garage. If you suspect that such corruption has occurred
+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-rc`: checks that the reference counters for blocks are in sync with the actual number of non-deleted entries in the block reference table

doc/book/operations/layout.md

@@ -0,0 +1,274 @@
++++
+title = "Cluster layout management"
+weight = 20
++++
+
+The cluster layout in Garage is a table that assigns to each node a role in
+the cluster. The role of a node in Garage can either be a storage node with
+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
+
+A cluster layout is composed of the following components:
+
+- 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.
+
+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):
+
+```bash
+garage layout assign [...]
+garage layout remove [...]
+```
+
+The following command can be used to inspect the layout that is currently set in the cluster
+and the changes proposed for the next layout version, if any:
+
+```bash
+garage layout show
+```
+
+The following commands create a new layout with the specified version number,
+that either takes into account the proposed changes or cancels them:
+
+```bash
+garage layout apply --version <new_version_number>
+garage layout revert --version <new_version_number>
+```
+
+The version number of the new layout to create must be 1 + the version number
+of the previous layout that existed in the cluster.  The `apply` and `revert`
+commands will fail otherwise.
+
+## Warnings about Garage cluster layout management
+
+**⚠️ 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
+`garage layout apply` or `garage layout revert` has failed and `garage layout
+show` indicates that a new layout with the given version number has not been
+set in the cluster, then it is fine to call the command again with the same
+version number.
+
+If you are using the `garage` CLI by typing individual commands in your
+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 or the admin API to script layout changes,
+follow the following recommendations:
+
+- 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`/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% (approximatively),
+whereas the node that was already in `dc3` (node3) is used at 75%.
+
+This can be explained by the following:
+
+- node1 will now be the only node remaining in `dc1`, thus it has to store all
+  of the data in the cluster. Since it was storing only half of it before, it has
+  to retrieve the other half from other nodes in the cluster.
+
+- The data which it does not have is entirely stored by the other node that was
+  in `dc1` and that is now in `dc3` (node4). There is also a copy of it on node2
+  and node3 since both these nodes have a copy of everything.
+
+- node3 and node4 are the two nodes that will now be in a datacenter that is
+ under-utilized (`dc3`), this means that those are the two candidates from which
+ data can be removed to be moved to node1.
+
+- Garage will move data in equal proportions from all possible sources, in this
+  case it means that it will tranfer 25% of the entire data set from node3 to
+  node1 and another 25% from node4 to node1.
+
+This explains why node3 ends with 75% utilization (100% from before minus 25%
+that is moved to node1), and node4 ends with 25% (50% from before minus 25%
+that is moved to node1).
+
+This illustrates the second principle of the layout computation: **if there is
+a choice in moving data out of some nodes, then all links between pairs of
+nodes are used in equal proportions** (this is approximately true, there is
+randomness in the algorithm to achieve this so there might be some small
+fluctuations, as we see above).

doc/book/operations/multi-hdd.md

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

doc/book/operations/recovering.md

@@ -1,11 +1,11 @@
 +++
 title = "Recovering from failures"
-weight = 35
+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 +108,57 @@ 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.

doc/book/operations/upgrading.md

@@ -0,0 +1,97 @@
++++
+title = "Upgrading Garage"
+weight = 10
++++
+
+Garage is a stateful clustered application, where all nodes are communicating together and share data structures.
+It makes upgrade more difficult than stateless applications so you must be more careful when upgrading.
+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 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).
+
+Major upgrades are designed to be run only between contiguous versions.
+Example: migrations from v0.7.1 to v0.8.0 and from v0.7.0 to v0.8.2 are supported but migrations from v0.6.0 to v0.8.0 are not supported.
+
+The `garage_build_info`
+[Prometheus metric](@/documentation/reference-manual/monitoring.md) provides
+an overview for which Garage versions are currently in use within a cluster.
+
+## Minor upgrades
+
+Minor upgrades do not imply cluster downtime.
+Before upgrading, you should still read [the changelog](https://git.deuxfleurs.fr/Deuxfleurs/garage/releases) and ideally test your deployment on a staging cluster before.
+
+When you are ready, start by checking the health of your cluster.
+You can force some checks with `garage repair`, we recommend at least running `garage repair --all-nodes --yes tables` which is very quick to run (less than a minute).
+You will see that the command correctly terminated in the logs of your daemon, or using `garage worker list` (the repair workers should be in the `Done` state).
+
+Finally, you can simply upgrade nodes one by one.
+For each node: stop it, install the new binary, edit the configuration if needed, restart it.
+
+## Major upgrades
+
+Major upgrades can be done with minimal downtime with a bit of preparation, but the simplest way is usually to put the cluster offline for the duration of the migration.
+Before upgrading, you must read [the changelog](https://git.deuxfleurs.fr/Deuxfleurs/garage/releases) and you must test your deployment on a staging cluster before.
+
+We write guides for each major upgrade, they are stored under the "Working Documents" section of this documentation.
+
+### Major upgrades with full downtime
+
+From a high level perspective, a major upgrade looks like this:
+
+  1. Disable API access (for instance in your reverse proxy, or by commenting the corresponding section in your Garage configuration file and restarting Garage)
+  2. Check that your cluster is idle
+  3. Make sure the health of your cluster is good (see `garage repair`)
+  4. Stop the whole cluster
+  5. Back up the metadata folder of all your nodes, so that you will be able to restore it if the upgrade fails (data blocks being immutable, they should not be impacted)
+  6. Install the new binary, update the configuration
+  7. Start the whole cluster
+  8. If needed, run the corresponding migration from `garage migrate`
+  9. Make sure the health of your cluster is good
+  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
+
+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
+simultaneously in the new version.
+The downtime will simply be the time required for all nodes to stop and start again, which should be less than a minute.
+If all nodes fail to stop and restart simultaneously, some nodes might be temporarily shut out from the cluster as nodes using different RPC protocol
+versions are prevented to talk to one another.
+
+The entire procedure would look something like this:
+
+1. Make sure the health of your cluster is good (see `garage repair`)
+
+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.
+
+  **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
+
+4. Restart all nodes simultaneously in the new version
+
+5. If any specific migration procedure is required, it is usually in one of the two cases:
+
+  - It can be run on online nodes after the new version has started, during regular cluster operation.
+  - it has to be run offline, in which case you will have to again take all nodes offline one after the other to run the repair
+
+   For this last step, please refer to the specific documentation pertaining to the version upgrade you are doing.

doc/book/quick-start/_index.md

@@ -1,6 +1,6 @@
 +++
 title = "Quick Start"
-weight = 0
+weight = 10
 sort_by = "weight"
 template = "documentation.html"
 +++
@@ -9,6 +9,15 @@ Let's start your Garage journey!
 In this chapter, we explain how to deploy Garage as a single-node server
 and how to interact with it.
 
+## What is Garage?
+
+Before jumping in, you might be interested in reading the following pages:
+
+- [Goals and use cases](@/documentation/design/goals.md)
+- [List of features](@/documentation/reference-manual/features.md)
+
+## Scope of this tutorial
+
 Our goal is to introduce you to Garage's workflows.
 Following this guide is recommended before moving on to
 [configuring a multi-node cluster](@/documentation/cookbook/real-world.md).
@@ -26,32 +35,42 @@ Place this binary somewhere in your `$PATH` so that you can invoke the `garage`
 command directly (for instance you can copy the binary in `/usr/local/bin`
 or in `~/.local/bin`).
 
+You may also check whether your distribution already includes a
+[binary package for Garage](@/documentation/cookbook/binary-packages.md).
+
 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
 
-### Writing a first configuration file
+### Generating a first configuration file
 
 This first configuration file should allow you to get started easily with the simplest
 possible Garage deployment.
-**Save it as `/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`).
 
-```toml
+We will create it with the following command line
+to generate unique and private secrets for security reasons:
+
+```bash
+cat > garage.toml <<EOF
 metadata_dir = "/tmp/meta"
 data_dir = "/tmp/data"
+db_engine = "sqlite"
 
-replication_mode = "none"
+replication_factor = 1
 
 rpc_bind_addr = "[::]:3901"
 rpc_public_addr = "127.0.0.1:3901"
-rpc_secret = "1799bccfd7411eddcf9ebd316bc1f5287ad12a68094e1c6ac6abde7e6feae1ec"
-
-bootstrap_peers = []
+rpc_secret = "$(openssl rand -hex 32)"
 
 [s3_api]
 s3_region = "garage"
@@ -62,12 +81,29 @@ root_domain = ".s3.garage.localhost"
 bind_addr = "[::]:3902"
 root_domain = ".web.garage.localhost"
 index = "index.html"
+
+[k2v_api]
+api_bind_addr = "[::]:3904"
+
+[admin]
+api_bind_addr = "[::]:3903"
+admin_token = "$(openssl rand -base64 32)"
+metrics_token = "$(openssl rand -base64 32)"
+EOF
 ```
 
-The `rpc_secret` value provided above is just an example. It will work, but in
-order to secure your cluster you will need to use another one. You can generate
-such a value with `openssl rand -hex 32`.
+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`).
+
+As you can see, the `rpc_secret` is a 32 bytes hexadecimal string.
+You can regenerate it with `openssl rand -hex 32`.
+If you target a cluster deployment with multiple nodes, make sure that
+you use the same value for all nodes.
 
 As you can see in the `metadata_dir` and `data_dir` parameters, we are saving Garage's data
 in `/tmp` which gets erased when your system reboots. This means that data stored on this
@@ -77,16 +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 /etc/garage.toml:/path/to/garage.toml \
+  -v /var/lib/garage/meta:/path/to/garage/meta \
+  -v /var/lib/garage/data:/path/to/garage/data \
+  dxflrs/garage:v0.9.4
 ```
-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
 ```
@@ -100,7 +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:
@@ -114,7 +176,7 @@ This should show something like this:
 ```
 ==== HEALTHY NODES ====
 ID                 Hostname  Address         Tag                   Zone  Capacity
-563e1ac825ee3323…  linuxbox  127.0.0.1:3901  NO ROLE ASSIGNED
+563e1ac825ee3323   linuxbox  127.0.0.1:3901  NO ROLE ASSIGNED
 ```
 
 ## Creating a cluster layout
@@ -127,12 +189,12 @@ For our test deployment, we are using only one node. The way in which we configu
 it does not matter, you can simply write:
 
 ```bash
-garage layout assign -z dc1 -c 1 <node_id>
+garage layout assign -z dc1 -c 1G <node_id>
 ```
 
 where `<node_id>` corresponds to the identifier of the node shown by `garage status` (first column).
 You can enter simply a prefix of that identifier.
-For instance here you could write just `garage layout assign -z dc1 -c 1 563e`.
+For instance here you could write just `garage layout assign -z dc1 -c 1G 563e`.
 
 The layout then has to be applied to the cluster, using:
 
@@ -183,7 +245,7 @@ one key can access multiple buckets, multiple keys can access one bucket.
 Create an API key using the following command:
 
 ```
-garage key new --name nextcloud-app-key
+garage key create nextcloud-app-key
 ```
 
 The output should look as follows:
@@ -210,6 +272,7 @@ Now that we have a bucket and a key, we need to give permissions to the key on t
 garage bucket allow \
   --read \
   --write \
+  --owner \
   nextcloud-bucket \
   --key nextcloud-app-key
 ```
@@ -221,66 +284,77 @@ garage bucket info nextcloud-bucket
 ```
 
 
-## Uploading and downlading from Garage
+## Uploading and downloading from Garage
 
-We recommend the use of MinIO Client to interact with Garage files (`mc`).
-Instructions to install it and use it are provided on the
-[MinIO website](https://docs.min.io/docs/minio-client-quickstart-guide.html).
-Before reading the following, you need a working `mc` command on your path.
+To download and upload files on garage, we can use a third-party tool named `awscli`.
 
-Note that on certain Linux distributions such as Arch Linux, the Minio client binary
-is called `mcli` instead of `mc` (to avoid name clashes with the Midnight Commander).
 
-### Configure `mc`
+### Install and configure `awscli`
 
-You need your access key and secret key created above.
-We will assume you are invoking `mc` on the same machine as the Garage server,
-your S3 API endpoint is therefore `http://127.0.0.1:3900`.
-For this whole configuration, you must set an alias name: we chose `my-garage`, that you will used for all commands.
-
-Adapt the following command accordingly and run it:
+If you have python on your system, you can install it with:
 
 ```bash
-mc alias set \
-  my-garage \
-  http://127.0.0.1:3900 \
-  <access key> \
-  <secret key> \
-  --api S3v4
+python -m pip install --user awscli
 ```
 
-You must also add an environment variable to your configuration to
-inform MinIO of our region (`garage` by default, corresponding to the `s3_region` parameter
-in the configuration file).
-The best way is to add the following snippet to your `$HOME/.bash_profile`
-or `$HOME/.bashrc` file:
+Now that `awscli` is installed, you must configure it to talk to your Garage instance,
+with your key. There are multiple ways to do that, the simplest one is to create a file
+named `~/.awsrc` with this content:
 
 ```bash
-export MC_REGION=garage
+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_URL='http://localhost:3900'
+
+aws --version
 ```
 
-### Use `mc`
+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.
 
-You can not list buckets from `mc` currently.
-
-But the following commands and many more should work:
+Now, each time you want to use `awscli` on this target, run:
 
 ```bash
-mc cp image.png my-garage/nextcloud-bucket
-mc cp my-garage/nextcloud-bucket/image.png .
-mc ls my-garage/nextcloud-bucket
-mc mirror localdir/ my-garage/another-bucket
+source ~/.awsrc
 ```
 
+*You can create multiple files with different names if you 
+have multiple Garage clusters or different keys.
+Switching from one cluster to another is as simple as
+sourcing the right file.*
+
+### Example usage of `awscli`
+
+```bash
+# list buckets
+aws s3 ls
+
+# list objects of a bucket
+aws s3 ls s3://nextcloud-bucket
+
+# copy from your filesystem to garage
+aws s3 cp /proc/cpuinfo s3://nextcloud-bucket/cpuinfo.txt
+
+# copy from garage to your filesystem
+aws s3 cp s3://nextcloud-bucket/cpuinfo.txt /tmp/cpuinfo.txt
+```
+
+Note that you can use `awscli` for more advanced operations like
+creating a bucket, pre-signing a request or managing your website.
+[Read the full documentation to know more](https://awscli.amazonaws.com/v2/documentation/api/latest/reference/s3/index.html).
+
+Some features are however not implemented like ACL or policy.
+Check [our s3 compatibility list](@/documentation/reference-manual/s3-compatibility.md).
 
 ### Other tools for interacting with Garage
 
 The following tools can also be used to send and recieve files from/to Garage:
 
-- the [AWS CLI](https://aws.amazon.com/cli/)
-- [`rclone`](https://rclone.org/)
-- [Cyberduck](https://cyberduck.io/)
-- [`s3cmd`](https://s3tools.org/s3cmd)
+- [minio-client](@/documentation/connect/cli.md#minio-client) 
+- [s3cmd](@/documentation/connect/cli.md#s3cmd) 
+- [rclone](@/documentation/connect/cli.md#rclone)
+- [Cyberduck](@/documentation/connect/cli.md#cyberduck)
+- [WinSCP](@/documentation/connect/cli.md#winscp) 
 
-Refer to the ["Integrations" section](@/documentation/connect/_index.md) to learn how to
-configure application and command line utilities to integrate with Garage.
+An exhaustive list is maintained in the ["Integrations" > "Browsing tools" section](@/documentation/connect/_index.md).

doc/book/reference-manual/_index.md

@@ -1,6 +1,6 @@
 +++
 title = "Reference Manual"
-weight = 4
+weight = 60
 sort_by = "weight"
 template = "documentation.html"
 +++

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

@@ -0,0 +1,148 @@
++++
+title = "Administration API"
+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))
+
+**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 endpoint will break
+when changes are introduced.
+
+Versions:
+ - Before Garage 0.7.2 - no admin API
+ - Garage 0.7.2 - admin APIv0
+ - Garage 0.9.0 - admin APIv1, deprecate admin APIv0
+
+
+
+## Access control
+
+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
+  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:
+
+```
+Authorization: Bearer <token>
+```
+
+## Administration API endpoints
+
+### Metrics `GET /metrics`
+
+Returns internal Garage metrics in Prometheus format.
+The metrics are directly documented when returned by the API.
+
+**Example:**
+
+```
+$ curl -i http://localhost:3903/metrics
+HTTP/1.1 200 OK
+content-type: text/plain; version=0.0.4
+content-length: 12145
+date: Tue, 08 Aug 2023 07:25:05 GMT
+
+# HELP api_admin_error_counter Number of API calls to the various Admin API endpoints that resulted in errors
+# TYPE api_admin_error_counter counter
+api_admin_error_counter{api_endpoint="CheckWebsiteEnabled",status_code="400"} 1
+api_admin_error_counter{api_endpoint="CheckWebsiteEnabled",status_code="404"} 3
+# HELP api_admin_request_counter Number of API calls to the various Admin API endpoints
+# TYPE api_admin_request_counter counter
+api_admin_request_counter{api_endpoint="CheckWebsiteEnabled"} 7
+api_admin_request_counter{api_endpoint="Health"} 3
+# HELP api_admin_request_duration Duration of API calls to the various Admin API endpoints
+...
+```
+
+### Health `GET /health`
+
+Returns `200 OK` if enough nodes are up to have a quorum (ie. serve requests),
+otherwise returns `503 Service Unavailable`.
+
+**Example:**
+
+```
+$ curl -i http://localhost:3903/health
+HTTP/1.1 200 OK
+content-type: text/plain
+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
+```
+
+### On-demand TLS `GET /check`
+
+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
+ - If the domain matches the pattern `<bucket-name>.<s3_web.root_domain>` and website is configured for `<bucket>`, returns 200 OK
+ - If the domain matches the pattern `<bucket-name>` and website is configured for `<bucket>`, returns 200 OK
+ - Otherwise, returns 404 Not Found, 400 Bad Request or 5xx requests.
+
+*Note 1: because in the path-style URL mode, there is only one domain that is not known by Garage, hence it is not supported by this API endpoint.
+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 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:
+
+```
+$ curl -so /dev/null -w "%{http_code}" http://localhost:3903/check?domain=media.s3.garage.localhost
+200
+$ curl -so /dev/null -w "%{http_code}" http://localhost:3903/check?domain=media
+400
+$ curl -so /dev/null -w "%{http_code}" http://localhost:3903/check?domain=media.web.garage.localhost
+400
+```
+
+With a public `example.com` bucket (name in the global namespace, website is activated), the endpoint will feature the following behavior:
+
+```
+$ curl -so /dev/null -w "%{http_code}" http://localhost:3903/check?domain=example.com.s3.garage.localhost
+200
+$ curl -so /dev/null -w "%{http_code}" http://localhost:3903/check?domain=example.com
+200
+$ curl -so /dev/null -w "%{http_code}" http://localhost:3903/check?domain=example.com.web.garage.localhost
+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 have a dedicated OpenAPI spec.
+ - APIv1 - [HTML spec](https://garagehq.deuxfleurs.fr/api/garage-admin-v1.html) - [OpenAPI YAML](https://garagehq.deuxfleurs.fr/api/garage-admin-v1.yml)
+ - APIv0 (deprecated) - [HTML spec](https://garagehq.deuxfleurs.fr/api/garage-admin-v0.html) - [OpenAPI YAML](https://garagehq.deuxfleurs.fr/api/garage-admin-v0.yml)
+
+Requesting the API from the command line can be as simple as running:
+
+```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)

doc/book/reference-manual/cli.md

@@ -1,6 +1,6 @@
 +++
 title = "Garage CLI"
-weight = 15
+weight = 30
 +++
 
 The Garage CLI is mostly self-documented. Make use of the `help` subcommand

doc/book/reference-manual/configuration.md

@@ -1,40 +1,69 @@
 +++
 title = "Configuration file format"
-weight = 5
+weight = 20
 +++
 
+## Full example
+
 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_fsync = true
+data_fsync = false
+disable_scrub = false
+metadata_auto_snapshot_interval = "6h"
 
-block_size = 1048576
+db_engine = "lmdb"
 
-replication_mode = "3"
+block_size = "1M"
+block_ram_buffer_max = "256MiB"
+
+lmdb_map_size = "1T"
 
 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",
 ]
 
-consul_host = "consul.service"
-consul_service_name = "garage-daemon"
 
-kubernetes_namespace = "garage"
-kubernetes_service_name = "garage-daemon"
-kubernetes_skip_crd = false
+[consul_discovery]
+api = "catalog"
+consul_http_addr = "http://127.0.0.1:8500"
+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" }
+
+
+[kubernetes_discovery]
+namespace = "garage"
+service_name = "garage-daemon"
+skip_crd = false
 
-sled_cache_capacity = 134217728
-sled_flush_every_ms = 2000
 
 [s3_api]
 api_bind_addr = "[::]:3900"
@@ -44,13 +73,199 @@ root_domain = ".s3.garage"
 [s3_web]
 bind_addr = "[::]:3902"
 root_domain = ".web.garage"
+
+[admin]
+api_bind_addr = "0.0.0.0:3903"
+metrics_token = "BCAdFjoa9G0KJR0WXnHHm7fs1ZAbfpI8iIZ+Z/a2NgI="
+admin_token = "UkLeGWEvHnXBqnueR3ISEMWpOnm40jH2tM2HnnL/0F4="
+trace_sink = "http://localhost:4317"
 ```
 
 The following gives details about each available configuration option.
 
 ## Available configuration options
 
-### `metadata_dir`
+### Index
+
+[Environment variables](#env_variables).
+
+Top-level configuration options:
+[`allow_world_readable_secrets`](#allow_world_readable_secrets),
+[`block_ram_buffer_max`](#block_ram_buffer_max),
+[`block_size`](#block_size),
+[`bootstrap_peers`](#bootstrap_peers),
+[`compression_level`](#compression_level),
+[`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),
+[`replication_factor`](#replication_factor),
+[`consistency_mode`](#consistency_mode),
+[`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).
+
+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),
+[`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:
+[`bind_addr`](#web_bind_addr),
+[`root_domain`](#web_root_domain).
+
+The `[admin]` section:
+[`api_bind_addr`](#admin_api_bind_addr),
+[`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 parameter must be specified as an environment
+variable, it does 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.
+
+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` {#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` {#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
@@ -58,18 +273,165 @@ 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`
 should be counted to determine a node's capacity
 when [adding it to the cluster layout](@/documentation/cookbook/real-world.md).
 
-### `block_size`
+Since `v0.9.0`, Garage supports multiple data directories with the following syntax:
+
+```toml
+data_dir = [
+    { path = "/path/to/old_data", read_only = true },
+    { path = "/path/to/new_hdd1", capacity = "2T" },
+    { path = "/path/to/new_hdd2", capacity = "4T" },
+]
+```
+
+See [the dedicated documentation page](@/documentation/operations/multi-hdd.md)
+on how to operate Garage in such a setup.
+
+#### `db_engine` (since `v0.8.0`) {#db_engine}
+
+Since `v0.8.0`, Garage can use alternative storage backends as follows:
+
+| DB engine | `db_engine` value | Database path |
+| --------- | ----------------- | ------------- |
+| [LMDB](https://www.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` |
+| [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:
+
+- LMDB: the recommended database engine for high-performance distributed clusters.
+LMDB works very well, but is known to have the following limitations:
+
+  - 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.
+
+  - Several users have reported corrupted LMDB database files after an unclean
+    shutdown (e.g. a power outage). This situation can generally be recovered
+    from if your cluster is geo-replicated (by rebuilding your metadata db from
+    other nodes), or if you have saved regular snapshots at the filesystem
+    level.
+
+  - 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 limted to 479 bytes.
+
+- Sqlite: Garage supports Sqlite as an alternative storage backend for
+  metadata, which does not have the issues listed above for LMDB.
+  On versions 0.8.x and earlier, Sqlite should be avoided due to abysmal
+  performance, which was fixed with the addition of `metadata_fsync`.
+  Sqlite is still probably slower than LMDB due to the way we use it,
+  so it is not the best choice for high-performance storage clusters,
+  but it should work fine in many cases.
+
+It is possible to convert Garage's metadata directory from one format to another
+using the `garage convert-db` command, which should be used as follows:
+
+```
+garage convert-db -a <input db engine> -i <input db path> \
+                  -b <output db engine> -o <output db path>
+```
+
+Make sure to specify the full database path as presented in the table above
+(third colummn), and not just the path to the metadata directory.
+
+#### `metadata_fsync` {#metadata_fsync}
+
+Whether to enable synchronous mode for the database engine or not.
+This is disabled (`false`) by default.
+
+This reduces the risk of metadata corruption in case of power failures,
+at the cost of a significant drop in write performance,
+as Garage will have to pause to sync data to disk much more often
+(several times for API calls such as PutObject).
+
+Using this option reduces the risk of simultaneous metadata corruption on several
+cluster nodes, which could lead to data loss.
+
+If multi-site replication is used, this option is most likely not necessary, as
+it is extremely unlikely that two nodes in different locations will have a
+power failure at the exact same time.
+
+(Metadata corruption on a single node is not an issue, the corrupted data file
+can always be deleted and reconstructed from the other nodes in the cluster.)
+
+Here is how this option impacts the different database engines:
+
+| Database | `metadata_fsync = false` (default) | `metadata_fsync = true`       |
+|----------|------------------------------------|-------------------------------|
+| Sqlite   | `PRAGMA synchronous = OFF`         | `PRAGMA synchronous = NORMAL` |
+| LMDB     | `MDB_NOMETASYNC` + `MDB_NOSYNC`    | `MDB_NOMETASYNC`              |
+
+Note that the Sqlite database is always ran in `WAL` mode (`PRAGMA journal_mode = WAL`).
+
+#### `data_fsync` {#data_fsync}
+
+Whether to `fsync` data blocks and their containing directory after they are
+saved to disk.
+This is disabled (`false`) by default.
+
+This might reduce the risk that a data block is lost in rare
+situations such as simultaneous node losing power,
+at the cost of a moderate drop in write performance.
+
+Similarly to `metatada_fsync`, this is likely not necessary
+if geographical replication is used.
+
+#### `metadata_auto_snapshot_interval` (since Garage 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.
+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.
+
+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.
+For this reason, it might be better to use filesystem-level snapshots instead
+if possible.
+
+#### `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.
+
+#### `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 1MB and
-should work in most cases. We recommend increasing it to e.g. 10MB if
+(except the last one which might be smaller). The default size is 1MiB and
+should work in most cases. We recommend increasing it to e.g. 10MiB if
 you are using Garage to store large files and have fast network connections
 between all nodes (e.g. 1gbps).
 
@@ -80,36 +442,46 @@ 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.
 
-### `replication_mode`
+#### `block_ram_buffer_max` (since v0.9.4) {#block_ram_buffer_max}
 
-Garage supports the following replication modes:
+A limit on the total size of data blocks kept in RAM by S3 API nodes awaiting
+to be sent to storage nodes asynchronously.
 
-- `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.
+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.
 
-- `2`: data stored on Garage will be stored on two different nodes, if possible in different
-  zones. Garage tolerates one node failure before losing data. Data should be available
-  read-only when one node is down, but write operations will fail.
-  Use this only if you really have to.
+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.
 
-- `3`: data stored on Garage will be stored on three different nodes, if possible each in
-  a different zones.
-  Garage tolerates two node failure before losing data. Data should be available
-  read-only when two nodes are down, and writes should be possible if only a single node
-  is down.
+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.
 
-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.
+The default value is 256MiB.
 
-**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.**
+#### `lmdb_map_size` {#lmdb_map_size}
 
-Changing the `replication_mode` of a cluster might work (make sure to shut down all nodes
-and changing it everywhere at the time), but is not officially supported.
+This parameters can be used to set the map size used by LMDB,
+which is the size of the virtual memory region used for mapping the database file.
+The value of this parameter is the maximum size the metadata database can take.
+This value is not bound by the physical RAM size of the machine running Garage.
+If not specified, it defaults to 1GiB on 32-bit machines and 1TiB on 64-bit machines.
 
-### `compression_level`
+#### `compression_level` {#compression_level}
 
 Zstd compression level to use for storing blocks.
 
@@ -117,7 +489,7 @@ Values between `1` (faster compression) and `19` (smaller file) are standard com
 levels for zstd. From `20` to `22`, compression levels are referred as "ultra" and must be
 used with extra care as it will use lot of memory. A value of `0` will let zstd choose a
 default value (currently `3`). Finally, zstd has also compression designed to be faster
-than default compression levels, they range from `-1` (smaller file) to `-99` (faster 
+than default compression levels, they range from `-1` (smaller file) to `-99` (faster
 compression).
 
 If you do not specify a `compression_level` entry, Garage will set it to `1` for you. With
@@ -133,15 +505,22 @@ 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`, `rpc_secret_file` or `GARAGE_RPC_SECRET`, `GARAGE_RPC_SECRET_FILE` (env) {#rpc_secret}
 
-Garage uses a secret key that is shared between all nodes of the cluster
-in order to identify these nodes and allow them to communicate together.
-This key should be specified here in the form of a 32-byte hex-encoded
-random string. Such a string can be generated with a command
-such as `openssl rand -hex 32`.
+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
+communicate together. The RPC secret is a 32-byte hex-encoded random string,
+which can be generated with a command such as `openssl rand -hex 32`.
 
-### `rpc_bind_addr`
+The RPC secret should be specified in the `rpc_secret` configuration variable.
+Since Garage `v0.8.2`, the RPC secret can also be stored in a file whose path is
+given in the configuration variable `rpc_secret_file`, or specified as an
+environment variable `GARAGE_RPC_SECRET`.
+
+Since Garage `v0.8.5` and `v0.9.1`, you can also specify the path of a file
+storing the secret as the `GARAGE_RPC_SECRET_FILE` environment variable.
+
+#### `rpc_bind_addr` {#rpc_bind_addr}
 
 The address and port on which to bind for inter-cluster communcations
 (reffered to as RPC for remote procedure calls).
@@ -150,14 +529,33 @@ the node, even in the case of a NAT: the NAT should be configured to forward the
 port number to the same internal port nubmer. This means that if you have several nodes running
 behind a NAT, they should each use a different RPC port number.
 
-### `rpc_public_addr`
+#### `rpc_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:
@@ -173,65 +571,118 @@ 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.
 
-### `consul_host` and `consul_service_name`
+### `allow_world_readable_secrets` or `GARAGE_ALLOW_WORLD_READABLE_SECRETS` (env) {#allow_world_readable_secrets}
+
+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.
+
+### 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`.
 
-The `consul_host` parameter should be set to the hostname of the Consul server,
-and `consul_service_name` should be set to the service name under which Garage's
+#### `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` {#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` {#consul_service_name}
+
+`service_name` should be set to the service name under which Garage's
 RPC ports are announced.
 
-Garage does not yet support talking to Consul over TLS.
+#### `client_cert`, `client_key` {#consul_client_cert_and_key}
 
-### `kubernetes_namespace`, `kubernetes_service_name` and `kubernetes_skip_crd`
+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` {#consul_ca_cert}
+
+TLS CA certificate to use when communicating with Consul over TLS.
+
+#### `tls_skip_verify` {#consul_tls_skip_verify}
+
+Skip server hostname verification in TLS handshake.
+`ca_cert` is ignored when this is set.
+
+#### `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:
+
+```hcl
+// the `service_name` specified above
+service "garage" {
+  policy = "write"
+}
+
+service_prefix "" {
+  policy = "read"
+}
+
+node_prefix "" {
+  policy = "read"
+}
+```
+
+#### `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
 
 Garage supports discovering other nodes of the cluster using kubernetes custom
-resources. For this to work `kubernetes_namespace` and `kubernetes_service_name`
-need to be configured.
+resources. For this to work, a `[kubernetes_discovery]` section must be present
+with at least the `namespace` and `service_name` parameters.
 
-`kubernetes_namespace` sets the namespace in which the custom resources are
-configured. `kubernetes_service_name` is added as a label to these resources to
+#### `namespace` {#kube_namespace}
+
+`namespace` sets the namespace in which the custom resources are
+configured.
+
+#### `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.
 
-`kubernetes_skip_crd` can be set to true to disable the automatic creation and
+#### `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.
 
-### `sled_cache_capacity`
 
-This parameter can be used to tune the capacity of the cache used by
-[sled](https://sled.rs), the database Garage uses internally to store metadata.
-Tune this to fit the RAM you wish to make available to your Garage instance.
-This value has a conservative default (128MB) so that Garage doesn't use too much
-RAM by default, but feel free to increase this for higher performance.
+### The `[s3_api]` section
 
-### `sled_flush_every_ms`
-
-This parameters can be used to tune the flushing interval of sled.
-Increase this if sled is thrashing your SSD, at the risk of losing more data in case
-of a power outage (though this should not matter much as data is replicated on other
-nodes). The default value, 2000ms, should be appropriate for most use cases.
-
-
-
-## 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.
 
-### `s3_region`
+Alternatively, since `v0.8.5`, a path can be used to create a unix socket with 0222 mode.
+
+#### `s3_region` {#s3_region}
 
 Garage will accept S3 API calls that are targetted to the S3 region defined here.
 API calls targetted to other regions will fail with a AuthorizationHeaderMalformed error
 message that redirects the client to the correct region.
 
-### `root_domain` {#root_domain}
+#### `root_domain` {#s3_root_domain}
 
-The optionnal suffix to access bucket using vhost-style in addition to path-style request.
+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.
@@ -241,22 +692,67 @@ 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.
 
-### `root_domain`
+Alternatively, since `v0.8.5`, a path can be used to create a unix socket with 0222 mode.
 
-The optionnal suffix appended to bucket names for the corresponding HTTP Host.
+#### `root_domain` {#web_root_domain}
+
+The optional suffix appended to bucket names for the corresponding HTTP Host.
 
 For instance, if `root_domain` is `web.garage.eu`, a bucket called `deuxfleurs.fr`
 will be accessible either with hostname `deuxfleurs.fr.web.garage.eu`
 or with hostname `deuxfleurs.fr`.
 
+
+### The `[admin]` section
+
+Garage has a few administration capabilities, in particular to allow remote monitoring. These features are detailed below.
+
+#### `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.
+
+Alternatively, since `v0.8.5`, a path can be used to create a unix socket. Note that for security reasons,
+the socket will have 0220 mode. Make sure to set user and group permissions accordingly.
+
+#### `metrics_token`, `metrics_token_file` or `GARAGE_METRICS_TOKEN`, `GARAGE_METRICS_TOKEN_FILE` (env) {#admin_metrics_token}
+
+The token for accessing the Metrics endpoint. If this token is not set, the
+Metrics endpoint can be accessed without access control.
+
+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`.
+
+#### `admin_token`, `admin_token_file` or `GARAGE_ADMIN_TOKEN`, `GARAGE_ADMIN_TOKEN_FILE` (env) {#admin_token}
+
+The token for accessing all of the other administration endpoints.  If this
+token is not set, access to these endpoints is disabled entirely.
+
+You can use any random string for this value. We recommend generating a random token with `openssl rand -base64 32`.
+
+`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` {#admin_trace_sink}
+
+Optionally, the address of an OpenTelemetry collector.  If specified,
+Garage will send traces in the OpenTelemetry format to this endpoint. These
+trace allow to inspect Garage's operation when it handles S3 API requests.

doc/book/reference-manual/features.md

@@ -0,0 +1,133 @@
++++
+title = "List of Garage features"
+weight = 10
++++
+
+
+### S3 API
+
+The main goal of Garage is to provide an object storage service that is compatible with the
+[S3 API](https://docs.aws.amazon.com/AmazonS3/latest/API/Welcome.html) from Amazon Web Services.
+We try to adhere as strictly as possible to the semantics of the API as implemented by Amazon
+and other vendors such as Minio or CEPH.
+
+Of course Garage does not implement the full span of API endpoints that AWS S3 does;
+the exact list of S3 features implemented by Garage can be found [on our S3 compatibility page](@/documentation/reference-manual/s3-compatibility.md).
+
+### Geo-distribution
+
+Garage allows you to store copies of your data in multiple geographical locations in order to maximize resilience
+to adverse events, such as network/power outages or hardware failures.
+This allows Garage to run very well even at home, using consumer-grade Internet connectivity
+(such as FTTH) and power, as long as cluster nodes can be spawned at several physical locations.
+Garage exploits knowledge of the capacity and physical location of each storage node to design
+a storage plan that best exploits the available storage capacity while satisfying the geo-distributed replication constraint.
+
+To learn more about geo-distributed Garage clusters,
+read our documentation on [setting up a real-world deployment](@/documentation/cookbook/real-world.md).
+
+### Standalone/self-contained
+
+Garage is extremely simple to deploy, and does not depend on any external service to run.
+This makes setting up and administering storage clusters, we hope, as easy as it could be.
+
+### Flexible topology
+
+A Garage cluster can very easily evolve over time, as storage nodes are added or removed.
+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 optionnally 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,
+but this is in fact a very important point! Garage does not use RAFT or another
+consensus algorithm internally to order incoming requests: this means that all requests
+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.
+
+### Web server for static websites
+
+A storage bucket can easily be configured to be served directly by Garage as a static web site.
+Domain names for multiple websites directly map to bucket names, making it easy to build
+a platform for your users to autonomously build and host their websites over Garage.
+Surprisingly, none of the other alternative S3 implementations we surveyed (such as Minio
+or CEPH) support publishing static websites from S3 buckets, a feature that is however
+directly inherited from S3 on AWS.
+Read more on our [dedicated documentation page](@/documentation/cookbook/exposing-websites.md).
+
+### Bucket names as aliases
+
+In Garage, a bucket may have several names, known as aliases.
+Aliases can easily be added and removed on demand:
+this allows to easily rename buckets if needed
+without having to copy all of their content, something that cannot be done on AWS.
+For buckets served as static websites, having multiple aliases for a bucket can allow
+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 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.
+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).
+
+### Metrics and traces
+
+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,
+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.
+
+### Kubernetes and Nomad integrations
+
+Garage can automatically discover other nodes in the cluster thanks to integration
+with orchestrators such as Kubernetes and Nomad (when used with Consul).
+This eases the configuration of your cluster as it removes one step where nodes need
+to be manually connected to one another.
+
+### Support for changing IP addresses
+
+As long as all of your nodes don't change their IP address at the same time,
+Garage should be able to tolerate nodes with changing/dynamic IP addresses,
+as nodes will regularly exchange the IP addresses of their peers and try to
+reconnect using newer addresses when existing connections are broken.
+
+### K2V API (experimental)
+
+As part of an ongoing research project, Garage can expose an experimental key/value storage API called K2V.
+K2V is made for the storage and retrieval of many small key/value pairs that need to be processed in bulk.
+This completes the S3 API with an alternative that can be used to easily store and access metadata
+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)
+and on how to enable it in Garage [here](@/documentation/reference-manual/k2v.md).

doc/book/reference-manual/k2v.md

@@ -0,0 +1,58 @@
++++
+title = "K2V"
+weight = 100
++++
+
+Starting with version 0.7.2, Garage introduces an optional feature, K2V,
+which is an alternative storage API designed to help efficiently store
+many small values in buckets (in opposition to S3 which is more designed
+to store large blobs).
+
+K2V is currently disabled at compile time in all builds, as the
+specification is still subject to changes. To build a Garage version with
+K2V, the Cargo feature flag `k2v` must be activated.  Special builds with
+the `k2v` feature flag enabled can be obtained from our download page under
+"Extra builds": such builds can be identified easily as their tag name ends
+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).
+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 AWS region used for signature calculation is always the same as the one
+defined for the S3 API in the config file.
+
+## Enabling and using K2V
+
+To enable K2V, download and run a build that has the `k2v` feature flag
+enabled, or produce one yourself. Then, add the following section to your
+configuration file:
+
+```toml
+[k2v_api]
+api_bind_addr = "<ip>:<port>"
+```
+
+Please select a port number that is not already in use by another API
+endpoint (S3 api, admin API) or by the RPC server.
+
+We provide an early-stage K2V client library for Rust which can be imported by adding the following to your `Cargo.toml` file:
+
+```toml
+k2v-client = { git = "https://git.deuxfleurs.fr/Deuxfleurs/garage.git" }
+```
+
+There is also a simple CLI utility which can be built from source in the
+following way:
+
+```sh
+git clone https://git.deuxfleurs.fr/Deuxfleurs/garage.git
+cd garage/src/k2v-client
+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.
+

doc/book/reference-manual/layout.md

@@ -1,77 +0,0 @@
-+++
-title = "Cluster layout management"
-weight = 10
-+++
-
-The cluster layout in Garage is a table that assigns to each node a role in
-the cluster. The role of a node in Garage can either be a storage node with
-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.
-
-## How cluster layouts work in Garage
-
-In Garage, a cluster layout is composed of the following components:
-
-- a table of roles assigned to nodes
-- 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
-
-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):
-
-```bash
-garage layout assign [...]
-garage layout remove [...]
-```
-
-The following command can be used to inspect the layout that is currently set in the cluster
-and the changes proposed for the next layout version, if any:
-
-```bash
-garage layout show
-```
-
-The following commands create a new layout with the specified version number,
-that either takes into account the proposed changes or cancels them:
-
-```bash
-garage layout apply --version <new_version_number>
-garage layout revert --version <new_version_number>
-```
-
-The version number of the new layout to create must be 1 + the version number
-of the previous layout that existed in the cluster.  The `apply` and `revert`
-commands will fail otherwise.
-
-## Warnings about Garage cluster layout management
-
-**Warning: 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
-`garage layout apply` or `garage layout revert` has failed and `garage layout
-show` indicates that a new layout with the given version number has not been
-set in the cluster, then it is fine to call the command again with the same
-version number.
-
-If you are using the `garage` CLI by typing individual commands in your
-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:
-
-- 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.
-
-- **Only call `garage layout apply` once**, and call it **strictly after** all
-  of the `layout assign` and `layout remove` commands have returned.

doc/book/reference-manual/monitoring.md

@@ -0,0 +1,402 @@
+
++++
+title = "Monitoring"
+weight = 60
++++
+
+
+For information on setting up monitoring, see our [dedicated page](@/documentation/cookbook/monitoring.md) in the Cookbook section.
+
+## List of exported metrics
+
+### Garage system metrics
+
+#### `garage_build_info` (counter)
+
+Exposes the Garage version number running on a node.
+
+```
+garage_build_info{version="1.0"} 1
+```
+
+#### `garage_replication_factor` (counter)
+
+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)
+
+Counts the number of requests to a given endpoint of the administration API. Example:
+
+```
+api_admin_request_counter{api_endpoint="Metrics"} 127041
+```
+
+#### `api_admin_request_duration` (histogram)
+
+Evaluates the duration of API calls to the various administration API endpoint. Example:
+
+```
+api_admin_request_duration_bucket{api_endpoint="Metrics",le="0.5"} 127041
+api_admin_request_duration_sum{api_endpoint="Metrics"} 605.250344830999
+api_admin_request_duration_count{api_endpoint="Metrics"} 127041
+```
+
+#### `api_s3_request_counter` (counter)
+
+Counts the number of requests to a given endpoint of the S3 API. Example:
+
+```
+api_s3_request_counter{api_endpoint="CreateMultipartUpload"} 1
+```
+
+#### `api_s3_error_counter` (counter)
+
+Counts the number of requests to a given endpoint of the S3 API that returned an error. Example:
+
+```
+api_s3_error_counter{api_endpoint="GetObject",status_code="404"} 39
+```
+
+#### `api_s3_request_duration` (histogram)
+
+Evaluates the duration of API calls to the various S3 API endpoints. Example:
+
+```
+api_s3_request_duration_bucket{api_endpoint="CreateMultipartUpload",le="0.5"} 1
+api_s3_request_duration_sum{api_endpoint="CreateMultipartUpload"} 0.046340762
+api_s3_request_duration_count{api_endpoint="CreateMultipartUpload"} 1
+```
+
+#### `api_k2v_request_counter` (counter), `api_k2v_error_counter` (counter), `api_k2v_error_duration` (histogram)
+
+Same as for S3, for the K2V API.
+
+
+### Metrics of the Web endpoint
+
+
+#### `web_request_counter` (counter)
+
+Number of requests to the web endpoint
+
+```
+web_request_counter{method="GET"} 80
+```
+
+#### `web_request_duration` (histogram)
+
+Duration of requests to the web endpoint
+
+```
+web_request_duration_bucket{method="GET",le="0.5"} 80
+web_request_duration_sum{method="GET"} 1.0528433229999998
+web_request_duration_count{method="GET"} 80
+```
+
+#### `web_error_counter` (counter)
+
+Number of requests to the web endpoint resulting in errors
+
+```
+web_error_counter{method="GET",status_code="404 Not Found"} 64
+```
+
+
+### Metrics of the data block manager
+
+#### `block_bytes_read`, `block_bytes_written` (counter)
+
+Number of bytes read/written to/from disk in the data storage directory.
+
+```
+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.
+
+```
+block_compression_level 3
+```
+
+#### `block_read_duration`, `block_write_duration` (histograms)
+
+Evaluates the duration of the reading/writing of individual data blocks in the data storage directory.
+
+```
+block_read_duration_bucket{le="0.5"} 169229
+block_read_duration_sum 2761.6902550310056
+block_read_duration_count 169240
+block_write_duration_bucket{le="0.5"} 3559
+block_write_duration_sum 195.59170078500006
+block_write_duration_count 3571
+```
+
+#### `block_delete_counter` (counter)
+
+Counts the number of data blocks that have been deleted from storage.
+
+```
+block_delete_counter 122
+```
+
+#### `block_resync_counter` (counter), `block_resync_duration` (histogram)
+
+Counts the number of resync operations the node has executed, and evaluates their duration.
+
+```
+block_resync_counter 308897
+block_resync_duration_bucket{le="0.5"} 308892
+block_resync_duration_sum 139.64204196100016
+block_resync_duration_count 308897
+```
+
+#### `block_resync_queue_length` (gauge)
+
+The number of block hashes currently queued for a resync.
+This is normal to be nonzero for long periods of time.
+
+```
+block_resync_queue_length 0
+```
+
+#### `block_resync_errored_blocks` (gauge)
+
+The number of block hashes that we were unable to resync last time we tried.
+**THIS SHOULD BE ZERO, OR FALL BACK TO ZERO RAPIDLY, IN A HEALTHY CLUSTER.**
+Persistent nonzero values indicate that some data is likely to be lost.
+
+```
+block_resync_errored_blocks 0
+```
+
+
+### Metrics related to RPCs (remote procedure calls) between nodes
+
+#### `rpc_netapp_request_counter` (counter)
+
+Number of RPC requests emitted
+
+```
+rpc_request_counter{from="<this node>",rpc_endpoint="garage_block/manager.rs/Rpc",to="<remote node>"} 176
+```
+
+#### `rpc_netapp_error_counter` (counter)
+
+Number of communication errors (errors in the Netapp library, generally due to disconnected nodes)
+
+```
+rpc_netapp_error_counter{from="<this node>",rpc_endpoint="garage_block/manager.rs/Rpc",to="<remote node>"} 354
+```
+
+#### `rpc_timeout_counter` (counter)
+
+Number of RPC timeouts, should be close to zero in a healthy cluster.
+
+```
+rpc_timeout_counter{from="<this node>",rpc_endpoint="garage_rpc/membership.rs/SystemRpc",to="<remote node>"} 1
+```
+
+#### `rpc_duration` (histogram)
+
+The duration of internal RPC calls between Garage nodes.
+
+```
+rpc_duration_bucket{from="<this node>",rpc_endpoint="garage_block/manager.rs/Rpc",to="<remote node>",le="0.5"} 166
+rpc_duration_sum{from="<this node>",rpc_endpoint="garage_block/manager.rs/Rpc",to="<remote node>"} 35.172253716
+rpc_duration_count{from="<this node>",rpc_endpoint="garage_block/manager.rs/Rpc",to="<remote node>"} 174
+```
+
+
+### Metrics of the metadata table manager
+
+#### `table_gc_todo_queue_length` (gauge)
+
+Table garbage collector TODO queue length
+
+```
+table_gc_todo_queue_length{table_name="block_ref"} 0
+```
+
+#### `table_get_request_counter` (counter), `table_get_request_duration` (histogram)
+
+Number of get/get_range requests internally made on each table, and their duration.
+
+```
+table_get_request_counter{table_name="bucket_alias"} 315
+table_get_request_duration_bucket{table_name="bucket_alias",le="0.5"} 315
+table_get_request_duration_sum{table_name="bucket_alias"} 0.048509778000000024
+table_get_request_duration_count{table_name="bucket_alias"} 315
+```
+
+
+#### `table_put_request_counter` (counter), `table_put_request_duration` (histogram)
+
+Number of insert/insert_many requests internally made on this table, and their duration
+
+```
+table_put_request_counter{table_name="block_ref"} 677
+table_put_request_duration_bucket{table_name="block_ref",le="0.5"} 677
+table_put_request_duration_sum{table_name="block_ref"} 61.617528636
+table_put_request_duration_count{table_name="block_ref"} 677
+```
+
+#### `table_internal_delete_counter` (counter)
+
+Number of value deletions in the tree (due to GC or repartitioning)
+
+```
+table_internal_delete_counter{table_name="block_ref"} 2296
+```
+
+#### `table_internal_update_counter` (counter)
+
+Number of value updates where the value actually changes (includes creation of new key and update of existing key)
+
+```
+table_internal_update_counter{table_name="block_ref"} 5996
+```
+
+#### `table_merkle_updater_todo_queue_length` (gauge)
+
+Merkle tree updater TODO queue length (should fall to zero rapidly)
+
+```
+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
+
+```
+table_sync_items_received{from="<remote node>",table_name="bucket_v2"} 3
+table_sync_items_sent{table_name="block_ref",to="<remote node>"} 2
+```
+
+

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

@@ -1,79 +1,103 @@
 +++
 title = "S3 Compatibility status"
-weight = 20
+weight = 70
 +++
 
-## Endpoint implementation
+## DISCLAIMER
 
-All APIs that are missing on Garage will return a 501 Not Implemented.
-Some `x-amz-` headers are not implemented.
+**The compatibility list for other platforms is given only for informational
+purposes and based on available documentation.** They are sometimes completed,
+in a best effort approach, with the source code and inputs from maintainers
+when documentation is lacking. We are not proactively monitoring new versions
+of each software: check the modification history to know when the page has been
+updated for the last time. Some entries will be inexact or outdated. For any
+serious decision, you must make your own tests.
+**The official documentation of each project can be accessed by clicking on the
+project name in the column header.**
 
-*The compatibility list for other platforms is given only for information purposes and based on available documentation. Some entries might be inexact. Feel free to open a PR to fix this table. Minio is missing because they do not provide a public S3 compatibility list.*
+Feel free to open a PR to suggest fixes this table. Minio is missing because they do not provide a public S3 compatibility list.
 
-### Features
+## Update history
+
+- 2022-02-07 - First version of this page
+- 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/general/latest/gr/signature-version-2.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 | ❓ |  ✅ | ❌ |  ✅ |
 
-*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, we suppose that OpenIO supports presigned URLs.
+*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,
+we suppose that OpenIO supports presigned URLs.
+
+
+## Endpoint implementation
+
+All endpoints that are missing on Garage will return a 501 Not Implemented.
+Some `x-amz-` headers are not implemented.
 
 ### Core endoints
 
-| 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) |  
+| 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) |
 |------------------------------|----------------------------------|-----------------|---------------|---------|-----|
 | [CreateBucket](https://docs.aws.amazon.com/AmazonS3/latest/API/API_CreateBucket.html)                 | ✅ Implemented                      | ✅ | ✅ | ✅ | ✅ |
 | [DeleteBucket](https://docs.aws.amazon.com/AmazonS3/latest/API/API_DeleteBucket.html)                 | ✅ Implemented                      | ✅ |  ✅ | ✅ | ✅ |
 | [GetBucketLocation](https://docs.aws.amazon.com/AmazonS3/latest/API/API_GetBucketLocation.html)            | ✅ Implemented                 | ✅ | ✅ | ❌ | ✅ |
 | [HeadBucket](https://docs.aws.amazon.com/AmazonS3/latest/API/API_HeadBucket.html)                   | ✅ Implemented                      | ✅ | ✅ |  ✅ | ✅ |
 | [ListBuckets](https://docs.aws.amazon.com/AmazonS3/latest/API/API_ListBuckets.html)                  | ✅ Implemented                      | ❌| ✅ | ✅ | ✅ |
-| [HeadObject](https://docs.aws.amazon.com/AmazonS3/latest/API/API_HeadObject.html)                   | ✅ Implemented                      | ✅ | ✅ | ✅ | ✅ | 
-| [CopyObject](https://docs.aws.amazon.com/AmazonS3/latest/API/API_CopyObject.html)                   | ✅ Implemented                      |  ✅ | ✅ | ✅ | ✅ | 
+| [HeadObject](https://docs.aws.amazon.com/AmazonS3/latest/API/API_HeadObject.html)                   | ✅ Implemented                      | ✅ | ✅ | ✅ | ✅ |
+| [CopyObject](https://docs.aws.amazon.com/AmazonS3/latest/API/API_CopyObject.html)                   | ✅ Implemented                      |  ✅ | ✅ | ✅ | ✅ |
 | [DeleteObject](https://docs.aws.amazon.com/AmazonS3/latest/API/API_DeleteObject.html)                 | ✅ Implemented                      | ✅ | ✅ | ✅ | ✅ |
 | [DeleteObjects](https://docs.aws.amazon.com/AmazonS3/latest/API/API_DeleteObjects.html)                | ✅ Implemented                      |  ✅  | ✅ | ✅ | ✅ |
 | [GetObject](https://docs.aws.amazon.com/AmazonS3/latest/API/API_GetObject.html)                    | ✅ Implemented                      |  ✅ | ✅ | ✅ | ✅ |
 | [ListObjects](https://docs.aws.amazon.com/AmazonS3/latest/API/API_ListObjects.html)                  | ✅ Implemented (see details below)   | ✅ | ✅ |  ✅ | ❌|
-| [ListObjectsV2](https://docs.aws.amazon.com/AmazonS3/latest/API/API_ListObjectsV2.html)                | ✅ Implemented                      | ❌| ❌| ❌| ✅ |
-| [PostObject](https://docs.aws.amazon.com/AmazonS3/latest/API/RESTObjectPOST.html) (compatibility API)                   |  ❌ Missing                      | ❌| ✅ | ❌| ❌|
+| [ListObjectsV2](https://docs.aws.amazon.com/AmazonS3/latest/API/API_ListObjectsV2.html)                | ✅ Implemented                      | ❌|  ✅  | ❌| ✅ |
+| [PostObject](https://docs.aws.amazon.com/AmazonS3/latest/API/RESTObjectPOST.html)                  | ✅ Implemented                      | ❌| ✅ | ❌| ❌|
 | [PutObject](https://docs.aws.amazon.com/AmazonS3/latest/API/API_PutObject.html)                    | ✅ Implemented                      | ✅ | ✅ | ✅ | ✅ |
 
-**ListObjects:** Implemented, but there isn't a very good specification of what `encoding-type=url` covers so there might be some encoding bugs. In our implementation the url-encoded fields are in the same in ListObjects as they are in ListObjectsV2.
+**ListObjects:** Implemented, but there isn't a very good specification of what
+`encoding-type=url` covers so there might be some encoding bugs. In our
+implementation the url-encoded fields are in the same in ListObjects as they
+are in ListObjectsV2.
 
-*Note: Ceph API documentation is incomplete and miss at least HeadBucket and UploadPartCopy, but these endpoints are documented in [Red Hat Ceph Storage - Chapter 2. Ceph Object Gateway and the S3 API](https://access.redhat.com/documentation/en-us/red_hat_ceph_storage/4/html/developer_guide/ceph-object-gateway-and-the-s3-api)*
+*Note: Ceph API documentation is incomplete and lacks at least HeadBucket and UploadPartCopy,
+but these endpoints are documented in [Red Hat Ceph Storage - Chapter 2. Ceph Object Gateway and the S3 API](https://access.redhat.com/documentation/en-us/red_hat_ceph_storage/4/html/developer_guide/ceph-object-gateway-and-the-s3-api)*
 
 ### Multipart Upload 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) |  
+| Endpoint                     | Garage                           | [Openstack Swift](https://docs.openstack.org/swift/latest/s3_compat.html) | [Ceph Object Gateway](https://docs.ceph.com/en/latest/radosgw/s3/) | [Riak CS](https://docs.riak.com/riak/cs/2.1.1/references/apis/storage/s3/index.html) | [OpenIO](https://docs.openio.io/latest/source/arch-design/s3_compliancy.html) |
 |------------------------------|----------------------------------|-----------------|---------------|---------|-----|
-| [AbortMultipartUpload](https://docs.aws.amazon.com/AmazonS3/latest/API/API_AbortMultipartUpload.html)         | ✅ Implemented                      |  ✅ | ✅ | ✅ | ✅ |
-| [CompleteMultipartUpload](https://docs.aws.amazon.com/AmazonS3/latest/API/API_CompleteMultipartUpload.html)   | ✅ Implemented (see details below)                      | ✅ | ✅ | ✅ | ✅ |
-| [CreateMultipartUpload](https://docs.aws.amazon.com/AmazonS3/latest/API/API_CreateMultipartUpload.html)        | ✅ Implemented                      | ✅| ✅ | ✅ | ✅ |
-| [ListMultipartUpload](https://docs.aws.amazon.com/AmazonS3/latest/API/API_ListMultipartUpload.html)          | ✅ Implemented                      | ✅ | ✅ | ✅ | ✅ |
-| [ListParts](https://docs.aws.amazon.com/AmazonS3/latest/API/API_ListParts.html)                    | ✅ Implemented                      | ✅ | ✅ | ✅ | ✅ |
-| [UploadPart](https://docs.aws.amazon.com/AmazonS3/latest/API/API_UploadPart.html)                  | ✅ Implemented (see details below)                      | ✅ | ✅| ✅ | ✅ |
-| [UploadPartCopy](https://docs.aws.amazon.com/AmazonS3/latest/API/API_UploadPartCopy.html)               | ✅ Implemented                      | ✅ | ✅ | ✅ | ✅ |
-
-Our implementation of Multipart Upload is currently a bit more restrictive than Amazon's one in some edge cases.
-For more information, please refer to our [issue tracker](https://git.deuxfleurs.fr/Deuxfleurs/garage/issues/204).
+| [AbortMultipartUpload](https://docs.aws.amazon.com/AmazonS3/latest/API/API_AbortMultipartUpload.html)         | ✅ Implemented  |  ✅ | ✅ | ✅ | ✅ |
+| [CompleteMultipartUpload](https://docs.aws.amazon.com/AmazonS3/latest/API/API_CompleteMultipartUpload.html)   | ✅ Implemented  | ✅ | ✅ | ✅ | ✅ |
+| [CreateMultipartUpload](https://docs.aws.amazon.com/AmazonS3/latest/API/API_CreateMultipartUpload.html)        | ✅ Implemented | ✅| ✅ | ✅ | ✅ |
+| [ListMultipartUpload](https://docs.aws.amazon.com/AmazonS3/latest/API/API_ListMultipartUpload.html)          | ✅ Implemented   | ✅ | ✅ | ✅ | ✅ |
+| [ListParts](https://docs.aws.amazon.com/AmazonS3/latest/API/API_ListParts.html)                    | ✅ Implemented             | ✅ | ✅ | ✅ | ✅ |
+| [UploadPart](https://docs.aws.amazon.com/AmazonS3/latest/API/API_UploadPart.html)                  | ✅ Implemented             | ✅ | ✅| ✅ | ✅ |
+| [UploadPartCopy](https://docs.aws.amazon.com/AmazonS3/latest/API/API_UploadPartCopy.html)               | ✅ Implemented        | ✅ | ✅ | ✅ | ✅ |
 
 ### Website endpoints
 
-| 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) |  
+| 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) |
 |------------------------------|----------------------------------|-----------------|---------------|---------|-----|
 | [DeleteBucketWebsite](https://docs.aws.amazon.com/AmazonS3/latest/API/API_DeleteBucketWebsite.html)          | ✅ Implemented                      | ❌| ❌| ❌| ❌|
 | [GetBucketWebsite](https://docs.aws.amazon.com/AmazonS3/latest/API/API_GetBucketWebsite.html)             | ✅ Implemented                      |  ❌ | ❌| ❌| ❌|
 | [PutBucketWebsite](https://docs.aws.amazon.com/AmazonS3/latest/API/API_PutBucketWebsite.html)             | ⚠ Partially implemented (see below)| ❌| ❌| ❌| ❌|
-| [DeleteBucketCors](https://docs.aws.amazon.com/AmazonS3/latest/API/API_DeleteBucketCors.html)             | ✅ Implemented                      |  ❌| ❌| ❌| ✅ |
-| [GetBucketCors](https://docs.aws.amazon.com/AmazonS3/latest/API/API_GetBucketCors.html)                | ✅ Implemented                      |  ❌ | ❌| ❌| ✅ |
-| [PutBucketCors](https://docs.aws.amazon.com/AmazonS3/latest/API/API_PutBucketCors.html)                | ✅ Implemented                      | ❌| ❌| ❌| ✅ |
+| [DeleteBucketCors](https://docs.aws.amazon.com/AmazonS3/latest/API/API_DeleteBucketCors.html)             | ✅ Implemented                      |  ❌|  ✅ | ❌| ✅ |
+| [GetBucketCors](https://docs.aws.amazon.com/AmazonS3/latest/API/API_GetBucketCors.html)                | ✅ Implemented                      |  ❌ |  ✅ | ❌| ✅ |
+| [PutBucketCors](https://docs.aws.amazon.com/AmazonS3/latest/API/API_PutBucketCors.html)                | ✅ Implemented                      | ❌|  ✅ | ❌| ✅ |
 
 **PutBucketWebsite:** Implemented, but only stores the index document suffix and the error document path. Redirects are not supported.
 
-*Note: Ceph radosgw has some support for static websites but it is different from Amazon one plus it does not implement its configuration endpoints.*
+*Note: Ceph radosgw has some support for static websites but it is different from the Amazon one. It also does not implement its configuration endpoints.*
 
 ### ACL, Policies endpoints
 
@@ -81,94 +105,102 @@ Amazon has 2 access control mechanisms in S3: ACL (legacy) and policies (new one
 Garage implements none of them, and has its own system instead, built around a per-access-key-per-bucket logic.
 See Garage CLI reference manual to learn how to use Garage's permission system.
 
-| 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) |  
+| 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) |
 |------------------------------|----------------------------------|-----------------|---------------|---------|-----|
-| [DeleteBucketPolicy](https://docs.aws.amazon.com/AmazonS3/latest/API/API_DeleteBucketPolicy.html) | ❌ Missing | ❌| ❌| ✅ | ❌|
-| [GetBucketPolicy](https://docs.aws.amazon.com/AmazonS3/latest/API/API_GetBucketPolicy.html) | ❌ Missing | ❌| ❌| ⚠ | ❌|
-| [GetBucketPolicyStatus](https://docs.aws.amazon.com/AmazonS3/latest/API/API_GetBucketPolicyStatus.html) | ❌ Missing | ❌| ❌| ❌| ❌|
-| [PutBucketPolicy](https://docs.aws.amazon.com/AmazonS3/latest/API/API_PutBucketPolicy.html) | ❌ Missing | ❌| ❌| ⚠ | ❌|
+| [DeleteBucketPolicy](https://docs.aws.amazon.com/AmazonS3/latest/API/API_DeleteBucketPolicy.html) | ❌ Missing | ❌|  ✅ | ✅ | ❌|
+| [GetBucketPolicy](https://docs.aws.amazon.com/AmazonS3/latest/API/API_GetBucketPolicy.html) | ❌ Missing | ❌|  ✅ | ⚠ | ❌|
+| [GetBucketPolicyStatus](https://docs.aws.amazon.com/AmazonS3/latest/API/API_GetBucketPolicyStatus.html) | ❌ Missing | ❌| ✅ | ❌| ❌|
+| [PutBucketPolicy](https://docs.aws.amazon.com/AmazonS3/latest/API/API_PutBucketPolicy.html) | ❌ Missing | ❌|  ✅ | ⚠ | ❌|
 | [GetBucketAcl](https://docs.aws.amazon.com/AmazonS3/latest/API/API_GetBucketAcl.html) | ❌ Missing | ✅ | ✅ | ✅ | ✅ |
 | [PutBucketAcl](https://docs.aws.amazon.com/AmazonS3/latest/API/API_PutBucketAcl.html) | ❌ Missing | ✅ | ✅ | ✅ | ✅ |
 | [GetObjectAcl](https://docs.aws.amazon.com/AmazonS3/latest/API/API_GetObjectAcl.html) | ❌ Missing | ✅ | ✅ | ✅ | ✅ |
 | [PutObjectAcl](https://docs.aws.amazon.com/AmazonS3/latest/API/API_PutObjectAcl.html) | ❌ Missing | ✅ | ✅ | ✅ | ✅ |
 
-*Notes:* Ceph claims that it supports bucket policies but does not implement any Policy endpoints. They probably refer to their own permission system. Riak CS only supports a subset of the policy configuration.
+*Notes:* Riak CS only supports a subset of the policy configuration.
 
 ### Versioning, Lifecycle endpoints
 
-Garage does not support (yet) object versioning.
+Garage does not (yet) support object versioning.
 If you need this feature, please [share your use case in our dedicated issue](https://git.deuxfleurs.fr/Deuxfleurs/garage/issues/166).
 
-| 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) |  
+| Endpoint                     | Garage                           | [Openstack Swift](https://docs.openstack.org/swift/latest/s3_compat.html) | [Ceph Object Gateway](https://docs.ceph.com/en/latest/radosgw/s3/) | [Riak CS](https://docs.riak.com/riak/cs/2.1.1/references/apis/storage/s3/index.html) | [OpenIO](https://docs.openio.io/latest/source/arch-design/s3_compliancy.html) |
 |------------------------------|----------------------------------|-----------------|---------------|---------|-----|
-| [DeleteBucketLifecycle](https://docs.aws.amazon.com/AmazonS3/latest/API/API_DeleteBucketLifecycle.html) | ❌ Missing | ❌| ✅| ❌| ✅|
-| [GetBucketLifecycleConfiguration](https://docs.aws.amazon.com/AmazonS3/latest/API/API_GetBucketLifecycleConfiguration.html) | ❌ Missing | ❌| ⚠ | ❌| ✅|
-| [PutBucketLifecycleConfiguration](https://docs.aws.amazon.com/AmazonS3/latest/API/API_PutBucketLifecycleConfiguration.html) | ❌ Missing | ❌| ⚠ | ❌| ✅|
+| [DeleteBucketLifecycle](https://docs.aws.amazon.com/AmazonS3/latest/API/API_DeleteBucketLifecycle.html) | ✅ Implemented | ❌| ✅| ❌| ✅|
+| [GetBucketLifecycleConfiguration](https://docs.aws.amazon.com/AmazonS3/latest/API/API_GetBucketLifecycleConfiguration.html) | ✅ Implemented | ❌| ✅ | ❌| ✅|
+| [PutBucketLifecycleConfiguration](https://docs.aws.amazon.com/AmazonS3/latest/API/API_PutBucketLifecycleConfiguration.html) | ⚠ Partially implemented (see below) | ❌| ✅ | ❌| ✅|
 | [GetBucketVersioning](https://docs.aws.amazon.com/AmazonS3/latest/API/API_GetBucketVersioning.html)          | ❌ Stub (see below)       | ✅| ✅ | ❌| ✅|
 | [ListObjectVersions](https://docs.aws.amazon.com/AmazonS3/latest/API/API_ListObjectVersions.html) | ❌ Missing | ❌| ✅ | ❌| ✅|
 | [PutBucketVersioning](https://docs.aws.amazon.com/AmazonS3/latest/API/API_PutBucketVersioning.html) | ❌ Missing | ❌| ✅| ❌| ✅|
 
+**PutBucketLifecycleConfiguration:** The only actions supported are
+`AbortIncompleteMultipartUpload` and `Expiration` (without the
+`ExpiredObjectDeleteMarker` field).  All other operations are dependent on
+either bucket versionning or storage classes which Garage currently does not
+implement. The deprecated `Prefix` member directly in the the `Rule`
+structure/XML tag is not supported, specified prefixes must be inside the
+`Filter` structure/XML tag.
 
-**GetBucketVersioning:** Stub implementation (Garage does not yet support versionning so this always returns "versionning not enabled").
+**GetBucketVersioning:** Stub implementation which always returns "versionning not enabled", since Garage does not yet support bucket versionning.
 
-*Note: Ceph only supports `Expiration`, `NoncurrentVersionExpiration` and `AbortIncompleteMultipartUpload` on its Lifecycle endpoints.*
- 
 ### Replication endpoints
 
 Please open an issue if you have a use case for replication.
 
-| 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) |  
+| 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) |
 |------------------------------|----------------------------------|-----------------|---------------|---------|-----|
 | [DeleteBucketReplication](https://docs.aws.amazon.com/AmazonS3/latest/API/API_DeleteBucketReplication.html) | ❌ Missing | ❌| ✅ | ❌| ❌|
 | [GetBucketReplication](https://docs.aws.amazon.com/AmazonS3/latest/API/API_GetBucketReplication.html) | ❌ Missing | ❌| ✅ | ❌| ❌|
 | [PutBucketReplication](https://docs.aws.amazon.com/AmazonS3/latest/API/API_PutBucketReplication.html) | ❌ Missing | ❌| ⚠ | ❌| ❌|
 
-*Note: Ceph documentation briefly says that Ceph supports [replication though 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.*
+*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.*
 
 ### Locking objects
 
 Amazon defines a concept of [object locking](https://docs.aws.amazon.com/AmazonS3/latest/userguide/object-lock.html) that can be achieved either through a Retention period or a Legal hold.
 
-| 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) |  
+| 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) |
 |------------------------------|----------------------------------|-----------------|---------------|---------|-----|
 | [GetObjectLegalHold](https://docs.aws.amazon.com/AmazonS3/latest/API/API_GetObjectLegalHold.html) | ❌ Missing | ❌| ✅ | ❌| ❌|
 | [PutObjectLegalHold](https://docs.aws.amazon.com/AmazonS3/latest/API/API_PutObjectLegalHold.html) | ❌ Missing | ❌| ✅ | ❌| ❌|
 | [GetObjectRetention](https://docs.aws.amazon.com/AmazonS3/latest/API/API_GetObjectRetention.html) | ❌ Missing | ❌| ✅ | ❌| ❌|
 | [PutObjectRetention](https://docs.aws.amazon.com/AmazonS3/latest/API/API_PutObjectRetention.html) | ❌ Missing | ❌| ✅ | ❌| ❌|
-| [GetObjectLockConfiguration](https://docs.aws.amazon.com/AmazonS3/latest/API/API_GetObjectLockConfiguration.html) | ❌ Missing | ❌| ❌| ❌| ❌|
-| [PutObjectLockConfiguration](https://docs.aws.amazon.com/AmazonS3/latest/API/API_PutObjectLockConfiguration.html) | ❌ Missing | ❌| ❌| ❌| ❌|
+| [GetObjectLockConfiguration](https://docs.aws.amazon.com/AmazonS3/latest/API/API_GetObjectLockConfiguration.html) | ❌ Missing | ❌| ✅ | ❌| ❌|
+| [PutObjectLockConfiguration](https://docs.aws.amazon.com/AmazonS3/latest/API/API_PutObjectLockConfiguration.html) | ❌ Missing | ❌| ✅ | ❌| ❌|
 
 ### (Server-side) encryption
 
 We think that you can either encrypt your server partition or do client-side encryption, so we did not implement server-side encryption for Garage.
 Please open an issue if you have a use case.
 
-| 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) |  
+| 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) |
 |------------------------------|----------------------------------|-----------------|---------------|---------|-----|
-| [DeleteBucketEncryption](https://docs.aws.amazon.com/AmazonS3/latest/API/API_DeleteBucketEncryption.html) | ❌ Missing | ❌| ❌| ❌| ❌|
-| [GetBucketEncryption](https://docs.aws.amazon.com/AmazonS3/latest/API/API_GetBucketEncryption.html) | ❌ Missing | ❌| ❌| ❌| ❌|
-| [PutBucketEncryption](https://docs.aws.amazon.com/AmazonS3/latest/API/API_PutBucketEncryption.html) | ❌ Missing | ❌| ❌| ❌| ❌|
+| [DeleteBucketEncryption](https://docs.aws.amazon.com/AmazonS3/latest/API/API_DeleteBucketEncryption.html) | ❌ Missing | ❌| ✅ | ❌| ❌|
+| [GetBucketEncryption](https://docs.aws.amazon.com/AmazonS3/latest/API/API_GetBucketEncryption.html) | ❌ Missing | ❌| ✅ | ❌| ❌|
+| [PutBucketEncryption](https://docs.aws.amazon.com/AmazonS3/latest/API/API_PutBucketEncryption.html) | ❌ Missing | ❌| ✅ | ❌| ❌|
 
 ### Misc 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) |  
+| 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) |
 |------------------------------|----------------------------------|-----------------|---------------|---------|-----|
 | [GetBucketNotificationConfiguration](https://docs.aws.amazon.com/AmazonS3/latest/API/API_GetBucketNotificationConfiguration.html) | ❌ Missing | ❌| ✅ | ❌| ❌|
 | [PutBucketNotificationConfiguration](https://docs.aws.amazon.com/AmazonS3/latest/API/API_PutBucketNotificationConfiguration.html) | ❌ Missing | ❌| ✅ | ❌| ❌|
-| [DeleteBucketTagging](https://docs.aws.amazon.com/AmazonS3/latest/API/API_DeleteBucketTagging.html) | ❌ Missing | ❌| ❌| ❌| ✅ |
-| [GetBucketTagging](https://docs.aws.amazon.com/AmazonS3/latest/API/API_GetBucketTagging.html) | ❌ Missing | ❌| ❌| ❌| ✅ |
-| [PutBucketTagging](https://docs.aws.amazon.com/AmazonS3/latest/API/API_PutBucketTagging.html) | ❌ Missing | ❌| ❌| ❌| ✅ |
-| [DeleteObjectTagging](https://docs.aws.amazon.com/AmazonS3/latest/API/API_DeleteObjectTagging.html) | ❌ Missing | ❌| ❌| ❌| ✅ |
-| [GetObjectTagging](https://docs.aws.amazon.com/AmazonS3/latest/API/API_GetObjectTagging.html) | ❌ Missing | ❌| ❌| ❌| ✅ |
-| [PutObjectTagging](https://docs.aws.amazon.com/AmazonS3/latest/API/API_PutObjectTagging.html) | ❌ Missing | ❌| ❌| ❌| ✅ |
-| [GetObjectTorrent](https://docs.aws.amazon.com/AmazonS3/latest/API/API_GetObjectTorrent.html) | ❌ Missing | ❌| ❌| ❌| ❌|
+| [DeleteBucketTagging](https://docs.aws.amazon.com/AmazonS3/latest/API/API_DeleteBucketTagging.html) | ❌ Missing | ❌| ✅ | ❌| ✅ |
+| [GetBucketTagging](https://docs.aws.amazon.com/AmazonS3/latest/API/API_GetBucketTagging.html) | ❌ Missing | ❌| ✅ | ❌| ✅ |
+| [PutBucketTagging](https://docs.aws.amazon.com/AmazonS3/latest/API/API_PutBucketTagging.html) | ❌ Missing | ❌| ✅ | ❌| ✅ |
+| [DeleteObjectTagging](https://docs.aws.amazon.com/AmazonS3/latest/API/API_DeleteObjectTagging.html) | ❌ Missing | ❌| ✅ | ❌| ✅ |
+| [GetObjectTagging](https://docs.aws.amazon.com/AmazonS3/latest/API/API_GetObjectTagging.html) | ❌ Missing | ❌| ✅ | ❌| ✅ |
+| [PutObjectTagging](https://docs.aws.amazon.com/AmazonS3/latest/API/API_PutObjectTagging.html) | ❌ Missing | ❌| ✅ | ❌| ✅ |
+| [GetObjectTorrent](https://docs.aws.amazon.com/AmazonS3/latest/API/API_GetObjectTorrent.html) | ❌ Missing | ❌| ✅ | ❌| ❌|
 
 ### Vendor specific endpoints
 
 <details><summary>Display Amazon specifc 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) |  
+| 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) |
 |------------------------------|----------------------------------|-----------------|---------------|---------|-----|
 | [DeleteBucketAnalyticsConfiguration](https://docs.aws.amazon.com/AmazonS3/latest/API/API_DeleteBucketAnalyticsConfiguration.html) | ❌ Missing | ❌| ❌| ❌| ❌|
 | [DeleteBucketIntelligentTieringConfiguration](https://docs.aws.amazon.com/AmazonS3/latest/API/API_DeleteBucketIntelligentTieringConfiguration.html) | ❌ Missing | ❌| ❌| ❌| ❌|

doc/book/working-documents/_index.md

@@ -1,6 +1,6 @@
 +++
 title = "Working Documents"
-weight = 7
+weight = 90
 sort_by = "weight"
 template = "documentation.html"
 +++

doc/book/working-documents/design-draft.md

@@ -1,6 +1,6 @@
 +++
-title = "Design draft"
-weight = 25
+title = "Design draft (obsolete)"
+weight = 900
 +++
 
 **WARNING: this documentation is a design draft which was written before Garage's actual implementation.

doc/book/working-documents/load-balancing.md

@@ -1,6 +1,6 @@
 +++
-title = "Load balancing data"
-weight = 10
+title = "Load balancing data (obsolete)"
+weight = 910
 +++
 
 **This is being yet improved in release 0.5. The working document has not been updated yet, it still only applies to Garage 0.2 through 0.4.**

doc/book/working-documents/migration-06.md

@@ -4,12 +4,12 @@ weight = 15
 +++
 
 **This guide explains how to migrate to 0.6 if you have an existing 0.5 cluster.
-We don't recommend trying to migrate directly from 0.4 or older to 0.6.**
+We don't recommend trying to migrate to 0.6 directly from 0.4 or older.**
 
 **We make no guarantee that this migration will work perfectly:
 back up all your data before attempting it!**
 
-Garage v0.6 (not yet released) introduces a new data model for buckets,
+Garage v0.6 introduces a new data model for buckets,
 that allows buckets to have many names (aliases).
 Buckets can also have "private" aliases (called local aliases),
 which are only visible when using a certain access key.

doc/book/working-documents/migration-07.md

@@ -0,0 +1,31 @@
++++
+title = "Migrating from 0.6 to 0.7"
+weight = 14
++++
+**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.**
+
+**We make no guarantee that this migration will work perfectly:
+back up all your data before attempting it!**
+
+Garage v0.7 introduces a cluster protocol change to support request tracing through OpenTelemetry.
+No data structure is changed, so no data migration is required.
+
+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 (`scrub`, `block_refs`, etc.)
+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.
+   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/`
+6. Install Garage v0.7, edit the configuration if you plan to use OpenTelemetry or the Kubernetes integration
+7. Turn on Garage v0.7
+8. Do `garage repair --all-nodes --yes tables` and `garage repair --all-nodes --yes blocks`
+9. Your upgraded cluster should be in a working state. Re-enable API and Web
+    access and check that everything went well.
+10. Monitor your cluster in the next hours to see if it works well under your production load, report any issue.

doc/book/working-documents/migration-08.md

@@ -0,0 +1,57 @@
++++
+title = "Migrating from 0.7 to 0.8"
+weight = 13
++++
+
+**This guide explains how to migrate to 0.8 if you have an existing 0.7 cluster.
+We don't recommend trying to migrate to 0.8 directly from 0.6 or older.**
+
+**We make no guarantee that this migration will work perfectly:
+back up all your data before attempting it!**
+
+Garage v0.8 introduces new data tables that allow the counting of objects in buckets in order to implement bucket quotas.
+A manual migration step is required to first count objects in Garage buckets and populate these tables with accurate data.
+
+## Simple migration procedure (takes cluster offline for a while)
+
+The migration steps are as follows:
+
+1. Disable API and web access. Garage v0.7 does not support disabling
+   these endpoints but you can change the port number or stop your reverse proxy for instance.
+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 queues are empty: run `garage stats` to query them or inspect metrics in the Grafana dashboard.
+4. Turn off Garage v0.7
+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-v0.7.tar.zst meta/`
+6. Install Garage v0.8
+7. **Before starting Garage v0.8**, run the offline migration step: `garage offline-repair --yes object_counters`.
+   This can take a while to run, depending on the number of objects stored in your cluster.
+8. Turn on Garage v0.8
+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.
+
+## Minimal downtime migration procedure
+
+The migration to Garage v0.8 can be done with almost no downtime,
+by restarting all nodes at once in the new version. The only limitation with this
+method is that bucket sizes and item counts will not be estimated correctly
+until all nodes have had a chance to run their offline migration procedure.
+
+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 v0.8
+
+4. Shut down all v0.7 nodes simultaneously, and restart them all simultaneously in v0.8. Use your favorite deployment tool (Ansible, Kubernetes, Nomad) to achieve this as fast as possible.
+
+5. At this point, Garage will indicate invalid values for the size and number of objects in each bucket (most likely, it will indicate zero). To fix this, take each node offline individually to do the offline migration step: `garage offline-repair --yes object_counters`. Again you can do all nodes of a single zone at once.

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

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

doc/book/working-documents/migration-1.md

@@ -0,0 +1,77 @@
++++
+title = "Migrating from 0.9 to 1.0"
+weight = 11
++++
+
+**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.

doc/book/working-documents/testing-strategy.md

@@ -0,0 +1,75 @@
++++
+title = "Testing strategy"
+weight = 30
++++
+
+
+## Testing Garage
+
+Currently, we have the following tests:
+
+- some unit tests spread around the codebase
+- integration tests written in Rust (`src/garage/test`) to check that Garage operations perform correctly
+- integration test for compatibility with external tools (`script/test-smoke.sh`)
+
+We have also tried `minio/mint` but it fails a lot and for now we haven't gotten a lot from it.
+
+In the future:
+
+1. We'd like to have a systematic way of testing with `minio/mint`,
+   it would add value to Garage by providing a compatibility score and reference that can be trusted.
+2. We'd also like to do testing with Jepsen in some way.
+
+## How to instrument Garagae
+
+We should try to test in least invasive ways, i.e. minimize the impact of the testing framework on Garage's source code. This means for example:
+
+- Not abstracting IO/nondeterminism in the source code
+- 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.
+
+There are two reasons for this:
+
+- Keep the soure 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.
+Only do things that make perfect sense in the context of what we currently know.
+
+## References
+
+Testing is a research field on its own.
+About testing distributed systems:
+
+ - [Jepsen](https://jepsen.io/) is a testing framework designed to test distributed systems. It can mock some part of the system like the time and the network.
+ - [FoundationDB Testing Approach](https://www.micahlerner.com/2021/06/12/foundationdb-a-distributed-unbundled-transactional-key-value-store.html#what-is-unique-about-foundationdbs-testing-framework). They chose to abstract "all sources of nondeterminism and communication are abstracted, including network, disk, time, and pseudo random number generator" to be able to run tests by simulating faults.
+ - [Testing Distributed Systems](https://asatarin.github.io/testing-distributed-systems/) - Curated list of resources on testing distributed systems
+ 
+About S3 compatibility:
+  - [ceph/s3-tests](https://github.com/ceph/s3-tests)
+  - (deprecated) [minio/s3verify](https://blog.min.io/s3verify-a-simple-tool-to-verify-aws-s3-api-compatibility/)
+  - [minio/mint](https://github.com/minio/mint)
+
+About benchmarking S3 (I think it is not necessarily very relevant for this iteration):
+  - [minio/warp](https://github.com/minio/warp)
+  - [wasabi-tech/s3-benchmark](https://github.com/wasabi-tech/s3-benchmark)
+  - [dvassallo/s3-benchmark](https://github.com/dvassallo/s3-benchmark)
+  - [intel-cloud/cosbench](https://github.com/intel-cloud/cosbench) - used by Ceph
+  
+Engineering blog posts:
+ - [Quincy @ Scale: A Tale of Three Large-Scale Clusters](https://ceph.io/en/news/blog/2022/three-large-scale-clusters/)
+
+Interesting blog posts on the blog of the Sled database: 
+
+- <https://sled.rs/simulation.html>
+- <https://sled.rs/perf.html>
+  
+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.
+  
+

doc/drafts/admin-api.md

@@ -0,0 +1,760 @@
++++
+title = "Administration API"
+weight = 60
++++
+
+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))
+
+**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.
+
+
+## Access control
+
+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
+  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:
+
+```
+Authorization: Bearer <token>
+```
+
+## Administration API endpoints
+
+### Metrics-related endpoints
+
+#### Metrics `GET /metrics`
+
+Returns internal Garage metrics in Prometheus format.
+
+#### Health `GET /health`
+
+Used for simple health checks in a cluster setting with an orchestrator.
+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.
+
+### Cluster operations
+
+#### GetClusterStatus `GET /v1/status`
+
+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": "b10c110e4e854e5aa3f4637681befac755154b20059ec163254ddbfae86b09df",
+  "garageVersion": "v1.0.1",
+  "garageFeatures": [
+    "k2v",
+    "lmdb",
+    "sqlite",
+    "metrics",
+    "bundled-libs"
+  ],
+  "rustVersion": "1.68.0",
+  "dbEngine": "LMDB (using Heed crate)",
+  "layoutVersion": 5,
+  "nodes": [
+    {
+      "id": "62b218d848e86a64f7fe1909735f29a4350547b54c4b204f91246a14eb0a1a8c",
+      "role": {
+        "id": "62b218d848e86a64f7fe1909735f29a4350547b54c4b204f91246a14eb0a1a8c",
+        "zone": "dc1",
+        "capacity": 100000000000,
+        "tags": []
+      },
+      "addr": "10.0.0.3:3901",
+      "hostname": "node3",
+      "isUp": true,
+      "lastSeenSecsAgo": 12,
+      "draining": false,
+      "dataPartition": {
+        "available": 660270088192,
+        "total": 873862266880
+      },
+      "metadataPartition": {
+        "available": 660270088192,
+        "total": 873862266880
+      }
+    },
+    {
+      "id": "a11c7cf18af297379eff8688360155fe68d9061654449ba0ce239252f5a7487f",
+      "role": null,
+      "addr": "10.0.0.2:3901",
+      "hostname": "node2",
+      "isUp": true,
+      "lastSeenSecsAgo": 11,
+      "draining": true,
+      "dataPartition": {
+        "available": 660270088192,
+        "total": 873862266880
+      },
+      "metadataPartition": {
+        "available": 660270088192,
+        "total": 873862266880
+      }
+    },
+    {
+      "id": "a235ac7695e0c54d7b403943025f57504d500fdcc5c3e42c71c5212faca040a2",
+      "role": {
+        "id": "a235ac7695e0c54d7b403943025f57504d500fdcc5c3e42c71c5212faca040a2",
+        "zone": "dc1",
+        "capacity": 100000000000,
+        "tags": []
+      },
+      "addr": "127.0.0.1:3904",
+      "hostname": "lindy",
+      "isUp": true,
+      "lastSeenSecsAgo": 2,
+      "draining": false,
+      "dataPartition": {
+        "available": 660270088192,
+        "total": 873862266880
+      },
+      "metadataPartition": {
+        "available": 660270088192,
+        "total": 873862266880
+      }
+    },
+    {
+      "id": "b10c110e4e854e5aa3f4637681befac755154b20059ec163254ddbfae86b09df",
+      "role": {
+        "id": "b10c110e4e854e5aa3f4637681befac755154b20059ec163254ddbfae86b09df",
+        "zone": "dc1",
+        "capacity": 100000000000,
+        "tags": []
+      },
+      "addr": "10.0.0.1:3901",
+      "hostname": "node1",
+      "isUp": true,
+      "lastSeenSecsAgo": 3,
+      "draining": false,
+      "dataPartition": {
+        "available": 660270088192,
+        "total": 873862266880
+      },
+      "metadataPartition": {
+        "available": 660270088192,
+        "total": 873862266880
+      }
+    }
+  ]
+}
+```
+
+#### GetClusterHealth `GET /v1/health`
+
+Returns the cluster's current health in JSON format, with the following variables:
+
+- `status`: one of `healthy`, `degraded` or `unavailable`:
+  - healthy: Garage node is connected to all storage nodes
+  - degraded: Garage node is not connected to all storage nodes, but a quorum of write nodes is available for all partitions
+  - unavailable: a quorum of write nodes is not available for some partitions
+- `knownNodes`: the number of nodes this Garage node has had a TCP connection to since the daemon started
+- `connectedNodes`: the nubmer of nodes this Garage node currently has an open connection to
+- `storageNodes`: the number of storage nodes currently registered in the cluster layout
+- `storageNodesOk`: the number of storage nodes to which a connection is currently open
+- `partitions`: the total number of partitions of the data (currently always 256)
+- `partitionsQuorum`: the number of partitions for which a quorum of write nodes is available
+- `partitionsAllOk`: the number of partitions for which we are connected to all storage nodes responsible of storing it
+
+Contrarily to `GET /health`, this endpoint always returns a 200 OK HTTP response code.
+
+Example response body:
+
+```json
+{
+  "status": "degraded",
+  "knownNodes": 3,
+  "connectedNodes": 3,
+  "storageNodes": 4,
+  "storageNodesOk": 3,
+  "partitions": 256,
+  "partitionsQuorum": 256,
+  "partitionsAllOk": 64
+}
+```
+
+#### ConnectClusterNodes `POST /v1/connect`
+
+Instructs this Garage node to connect to other Garage nodes at specified addresses.
+
+Example request body:
+
+```json
+[
+    "ec79480e0ce52ae26fd00c9da684e4fa56658d9c64cdcecb094e936de0bfe71f@10.0.0.11:3901",
+    "4a6ae5a1d0d33bf895f5bb4f0a418b7dc94c47c0dd2eb108d1158f3c8f60b0ff@10.0.0.12:3901"
+]
+```
+
+The format of the string for a node to connect to is: `<node ID>@<ip address>:<port>`, same as in the `garage node connect` CLI call.
+
+Example response:
+
+```json
+[
+    {
+        "success": true,
+        "error": null
+    },
+    {
+        "success": false,
+        "error": "Handshake error"
+    }
+]
+```
+
+#### GetClusterLayout `GET /v1/layout`
+
+Returns the cluster's current layout in JSON, including:
+
+- Currently configured cluster layout
+- Staged changes to the cluster layout
+
+(the info returned by this endpoint is a subset of the info returned by GetClusterStatus)
+
+Example response body:
+
+```json
+{
+  "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,
+    }
+  ]
+}
+```
+
+#### UpdateClusterLayout `POST /v1/layout`
+
+Send modifications to the cluster layout. These modifications will
+be included in the staged role changes, visible in subsequent calls
+of `GetClusterLayout`. Once the set of staged changes is satisfactory,
+the user may call `ApplyClusterLayout` to apply the changed changes,
+or `Revert ClusterLayout` to clear all of the staged changes in
+the layout.
+
+Request body format:
+
+```json
+[
+  {
+    "id": <node_id>,
+    "capacity": <new_capacity>,
+    "zone": <new_zone>,
+    "tags": [
+      <new_tag>,
+      ...
+    ]
+  },
+  {
+    "id": <node_id_to_remove>,
+    "remove": true
+  }
+]
+```
+
+Contrary to the CLI that may update only a subset of the fields
+`capacity`, `zone` and `tags`, when calling this API all of these
+values must be specified.
+
+This returns the new cluster layout with the proposed staged changes,
+as returned by GetClusterLayout.
+
+
+#### ApplyClusterLayout `POST /v1/layout/apply`
+
+Applies to the cluster the layout changes currently registered as
+staged layout changes.
+
+Request body format:
+
+```json
+{
+  "version": 13
+}
+```
+
+Similarly to the CLI, the body must include the version of the new layout
+that will be created, which MUST be 1 + the value of the currently
+existing layout in the cluster.
+
+This returns the message describing all the calculations done to compute the new
+layout, as well as the description of the layout as returned by GetClusterLayout.
+
+#### RevertClusterLayout `POST /v1/layout/revert`
+
+Clears all of the staged layout changes.
+
+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 returns the new cluster layout with all changes reverted,
+as returned by GetClusterLayout.
+
+
+### Access key operations
+
+#### ListKeys `GET /v1/key`
+
+Returns all API access keys in the cluster.
+
+Example response:
+
+```json
+[
+  {
+    "id": "GK31c2f218a2e44f485b94239e",
+    "name": "test"
+  },
+  {
+    "id": "GKe10061ac9c2921f09e4c5540",
+    "name": "test2"
+  }
+]
+```
+
+#### GetKeyInfo `GET /v1/key?id=<acces key id>`
+#### GetKeyInfo `GET /v1/key?search=<pattern>`
+
+Returns information about the requested API access key.
+
+If `id` is set, the key is looked up using its exact identifier (faster).
+If `search` is set, the key is looked up using its name or prefix
+of identifier (slower, all keys are enumerated to do this).
+
+Optionnally, the query parameter `showSecretKey=true` can be set to reveal the
+associated secret access key.
+
+Example response:
+
+```json
+{
+  "name": "test",
+  "accessKeyId": "GK31c2f218a2e44f485b94239e",
+  "secretAccessKey": "b892c0665f0ada8a4755dae98baa3b133590e11dae3bcc1f9d769d67f16c3835",
+  "permissions": {
+    "createBucket": false
+  },
+  "buckets": [
+    {
+      "id": "70dc3bed7fe83a75e46b66e7ddef7d56e65f3c02f9f80b6749fb97eccb5e1033",
+      "globalAliases": [
+        "test2"
+      ],
+      "localAliases": [],
+      "permissions": {
+        "read": true,
+        "write": true,
+        "owner": false
+      }
+    },
+    {
+      "id": "d7452a935e663fc1914f3a5515163a6d3724010ce8dfd9e4743ca8be5974f995",
+      "globalAliases": [
+        "test3"
+      ],
+      "localAliases": [],
+      "permissions": {
+        "read": true,
+        "write": true,
+        "owner": false
+      }
+    },
+    {
+      "id": "e6a14cd6a27f48684579ec6b381c078ab11697e6bc8513b72b2f5307e25fff9b",
+      "globalAliases": [],
+      "localAliases": [
+        "test"
+      ],
+      "permissions": {
+        "read": true,
+        "write": true,
+        "owner": true
+      }
+    },
+    {
+      "id": "96470e0df00ec28807138daf01915cfda2bee8eccc91dea9558c0b4855b5bf95",
+      "globalAliases": [
+        "alex"
+      ],
+      "localAliases": [],
+      "permissions": {
+        "read": true,
+        "write": true,
+        "owner": true
+      }
+    }
+  ]
+}
+```
+
+#### CreateKey `POST /v1/key`
+
+Creates a new API access key.
+
+Request body format:
+
+```json
+{
+    "name": "NameOfMyKey"
+}
+```
+
+This returns the key info, including the created secret key,
+in the same format as the result of GetKeyInfo.
+
+#### ImportKey `POST /v1/key/import`
+
+Imports an existing API key.
+This will check that the imported key is in the valid format, i.e.
+is a key that could have been generated by Garage.
+
+Request body format:
+
+```json
+{
+    "accessKeyId": "GK31c2f218a2e44f485b94239e",
+    "secretAccessKey": "b892c0665f0ada8a4755dae98baa3b133590e11dae3bcc1f9d769d67f16c3835",
+    "name": "NameOfMyKey"
+}
+```
+
+This returns the key info in the same format as the result of GetKeyInfo.
+
+#### UpdateKey `POST /v1/key?id=<acces key id>`
+
+Updates information about the specified API access key.
+
+Request body format:
+
+```json
+{
+    "name": "NameOfMyKey",
+    "allow": {
+        "createBucket": true,
+    },
+    "deny": {}
+}
+```
+
+All fields (`name`, `allow` and `deny`) are optional.
+If they are present, the corresponding modifications are applied to the key, otherwise nothing is changed.
+The possible flags in `allow` and `deny` are: `createBucket`.
+
+This returns the key info in the same format as the result of GetKeyInfo.
+
+#### DeleteKey `DELETE /v1/key?id=<acces key id>`
+
+Deletes an API access key.
+
+
+### Bucket operations
+
+#### ListBuckets `GET /v1/bucket`
+
+Returns all storage buckets in the cluster.
+
+Example response:
+
+```json
+[
+  {
+    "id": "70dc3bed7fe83a75e46b66e7ddef7d56e65f3c02f9f80b6749fb97eccb5e1033",
+    "globalAliases": [
+      "test2"
+    ],
+    "localAliases": []
+  },
+  {
+    "id": "96470e0df00ec28807138daf01915cfda2bee8eccc91dea9558c0b4855b5bf95",
+    "globalAliases": [
+      "alex"
+    ],
+    "localAliases": []
+  },
+  {
+    "id": "d7452a935e663fc1914f3a5515163a6d3724010ce8dfd9e4743ca8be5974f995",
+    "globalAliases": [
+      "test3"
+    ],
+    "localAliases": []
+  },
+  {
+    "id": "e6a14cd6a27f48684579ec6b381c078ab11697e6bc8513b72b2f5307e25fff9b",
+    "globalAliases": [],
+    "localAliases": [
+      {
+        "accessKeyId": "GK31c2f218a2e44f485b94239e",
+        "alias": "test"
+      }
+    ]
+  }
+]
+```
+
+#### GetBucketInfo `GET /v1/bucket?id=<bucket id>`
+#### GetBucketInfo `GET /v1/bucket?globalAlias=<alias>`
+
+Returns information about the requested storage bucket.
+
+If `id` is set, the bucket is looked up using its exact identifier.
+If `globalAlias` is set, the bucket is looked up using its global alias.
+(both are fast)
+
+Example response:
+
+```json
+{
+    "id": "afa8f0a22b40b1247ccd0affb869b0af5cff980924a20e4b5e0720a44deb8d39",
+        "globalAliases": [],
+        "websiteAccess": false,
+        "websiteConfig": null,
+        "keys": [
+        {
+            "accessKeyId": "GK31c2f218a2e44f485b94239e",
+            "name": "Imported key",
+            "permissions": {
+                "read": true,
+                "write": true,
+                "owner": true
+            },
+            "bucketLocalAliases": [
+                "debug"
+            ]
+        }
+        ],
+        "objects": 14827,
+        "bytes": 13189855625,
+        "unfinishedUploads": 1,
+        "unfinishedMultipartUploads": 1,
+        "unfinishedMultipartUploadParts": 11,
+        "unfinishedMultipartUploadBytes": 41943040,
+        "quotas": {
+            "maxSize": null,
+            "maxObjects": null
+        }
+}
+```
+
+#### CreateBucket `POST /v1/bucket`
+
+Creates a new storage bucket.
+
+Request body format:
+
+```json
+{
+    "globalAlias": "NameOfMyBucket"
+}
+```
+
+OR
+
+```json
+{
+    "localAlias": {
+        "accessKeyId": "GK31c2f218a2e44f485b94239e",
+        "alias": "NameOfMyBucket",
+        "allow": {
+            "read": true,
+            "write": true,
+            "owner": false
+        }
+    }
+}
+```
+
+OR
+
+```json
+{}
+```
+
+Creates a new bucket, either with a global alias, a local one,
+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>`
+
+Updates configuration of the given bucket.
+
+Request body format:
+
+```json
+{
+    "websiteAccess": {
+        "enabled": true,
+        "indexDocument": "index.html",
+        "errorDocument": "404.html"
+    },
+    "quotas": {
+        "maxSize": 19029801,
+        "maxObjects": null,
+    }
+}
+```
+
+All fields (`websiteAccess` and `quotas`) are optional.
+If they are present, the corresponding modifications are applied to the bucket, otherwise nothing is changed.
+
+In `websiteAccess`: if `enabled` is `true`, `indexDocument` must be specified.
+The field `errorDocument` is optional, if no error document is set a generic
+error message is displayed when errors happen. Conversely, if `enabled` is
+`false`, neither `indexDocument` nor `errorDocument` must be specified.
+
+In `quotas`: new values of `maxSize` and `maxObjects` must both be specified, or set to `null`
+to remove the quotas. An absent value will be considered the same as a `null`. It is not possible
+to change only one of the two quotas.
+
+#### DeleteBucket `DELETE /v1/bucket?id=<bucket id>`
+
+Deletes a storage bucket. A bucket cannot be deleted if it is not empty.
+
+Warning: this will delete all aliases associated with the bucket!
+
+
+### Operations on permissions for keys on buckets
+
+#### BucketAllowKey `POST /v1/bucket/allow`
+
+Allows a key to do read/write/owner operations on a bucket.
+
+Request body format:
+
+```json
+{
+    "bucketId": "e6a14cd6a27f48684579ec6b381c078ab11697e6bc8513b72b2f5307e25fff9b",
+    "accessKeyId": "GK31c2f218a2e44f485b94239e",
+    "permissions": {
+        "read": true,
+        "write": true,
+        "owner": true
+    },
+}
+```
+
+Flags in `permissions` which have the value `true` will be activated.
+Other flags will remain unchanged.
+
+#### BucketDenyKey `POST /v1/bucket/deny`
+
+Denies a key from doing read/write/owner operations on a bucket.
+
+Request body format:
+
+```json
+{
+    "bucketId": "e6a14cd6a27f48684579ec6b381c078ab11697e6bc8513b72b2f5307e25fff9b",
+    "accessKeyId": "GK31c2f218a2e44f485b94239e",
+    "permissions": {
+        "read": false,
+        "write": false,
+        "owner": true
+    },
+}
+```
+
+Flags in `permissions` which have the value `true` will be deactivated.
+Other flags will remain unchanged.
+
+
+### Operations on bucket aliases
+
+#### GlobalAliasBucket `PUT /v1/bucket/alias/global?id=<bucket id>&alias=<global alias>`
+
+Empty body. Creates a global alias for a bucket.
+
+#### GlobalUnaliasBucket `DELETE /v1/bucket/alias/global?id=<bucket id>&alias=<global alias>`
+
+Removes a global alias for a bucket.
+
+#### LocalAliasBucket `PUT /v1/bucket/alias/local?id=<bucket id>&accessKeyId=<access key ID>&alias=<local alias>`
+
+Empty body. Creates a local alias for a bucket in the namespace of a specific access key.
+
+#### LocalUnaliasBucket `DELETE /v1/bucket/alias/local?id=<bucket id>&accessKeyId<access key ID>&alias=<local alias>`
+
+Removes a local alias for a bucket in the namespace of a specific access key.
+

doc/drafts/k2v-spec.md

@@ -0,0 +1,784 @@
+# Specification of the Garage K2V API (K2V = Key/Key/Value)
+
+- We are storing triplets of the form `(partition key, sort key, value)` -> no
+  user-defined fields, the client is responsible of writing whatever he wants
+  in the value (typically an encrypted blob). Values are binary blobs, which
+  are always represented as their base64 encoding in the JSON API. Partition
+  keys and sort keys are utf8 strings.
+
+- Triplets are stored in buckets; each bucket stores a separate set of triplets
+
+- Bucket names and access keys are the same as for accessing the S3 API
+
+- K2V triplets exist separately from S3 objects. K2V triplets don't exist for
+  the S3 API, and S3 objects don't exist for the K2V API.
+
+- Values stored for triplets have associated causality information, that enables
+  Garage to detect concurrent writes. In case of concurrent writes, Garage
+  keeps the concurrent values until a further write supersedes the concurrent
+  values. This is the same method as Riak KV implements. The method used is
+  based on DVVS (dotted version vector sets), described in the paper "Scalable
+  and Accurate Causality Tracking for Eventually Consistent Data Stores", as
+  well as [here](https://github.com/ricardobcl/Dotted-Version-Vectors)
+
+
+## Data format
+
+### Triple format
+
+Triples in K2V are constituted of three fields:
+
+- a partition key (`pk`), an utf8 string that defines in what partition the
+  triplet is stored; triplets in different partitions cannot be listed together
+  in a ReadBatch command, or deleted together in a DeleteBatch command: a
+  separate command must be included in the ReadBatch/DeleteBatch call for each
+  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
+
+- 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
+  they will be represented as strings using base64 encoding; a value can also
+  be `null` to indicate a deleted triplet (a `null` value is called a tombstone)
+
+### Causality information
+
+K2V supports storing several concurrent values associated to a pk+sk, in the
+case where insertion or deletion operations are detected to be concurrent (i.e.
+there is not one that was aware of the other, they are not causally dependant
+one on the other).  In practice, it even looks more like the opposite: to
+overwrite a previously existing value, the client must give a "causality token"
+that "proves" (not in a cryptographic sense) that it had seen a previous value.
+Otherwise, the value written will not overwrite an existing value, it will just
+create a new concurrent value.
+
+The causality token is a binary/b64-encoded representation of a context,
+specified below.
+
+A set of concurrent values looks like this:
+
+```
+(node1, tdiscard1, (v1, t1), (v2, t2)) ; tdiscard1 < t1 < t2
+(node2, tdiscard2, (v3, t3)            ; tdiscard2 < t3
+```
+
+`tdiscard` for a node `i` means that all values inserted by node `i` with times
+`<= tdiscard` are obsoleted, i.e. have been read by a client that overwrote it
+afterwards.
+
+The associated context would be the following: `[(node1, t2), (node2, t3)]`,
+i.e. if a node reads this set of values and inserts a new values, we will now
+have `tdiscard1 = t2` and `tdiscard2 = t3`, to indicate that values v1, v2 and v3
+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
+InsertItem query:
+
+- `node2` generates a timestamp `t4` such that `t4 > t3`.
+- the new state is as follows:
+
+```
+(node1, tdiscard1', ())       ; tdiscard1' = t2
+(node2, tdiscard2', (v4, t4)) ; tdiscard2' = t3
+```
+
+**A more complex insertion example.** In the general case, other intermediate values could have
+been written before `v4` with context `[(node1, t2), (node2, t3)]` is sent to the system.
+For instance, here is a possible sequence of events:
+
+1. First we have the set of values v1, v2 and v3 described above.
+   A node reads it, it obtains values v1, v2 and v3 with context `[(node1, t2), (node2, t3)]`.
+
+2. A node writes a value `v5` with context `[(node1, t1)]`, i.e. `v5` is only a
+   successor of v1 but not of v2 or v3. Suppose node1 receives the write, it
+   will generate a new timestamp `t5` larger than all of the timestamps it
+   knows of, i.e. `t5 > t2`. We will now have:
+
+```
+(node1, tdiscard1'', (v2, t2), (v5, t5)) ; tdiscard1'' = t1 < t2 < t5
+(node2, tdiscard2, (v3, t3)              ; tdiscard2 < t3
+```
+
+3. Now `v4` is written with context `[(node1, t2), (node2, t3)]`, and node2
+   processes the query. It will generate `t4 > t3` and the state will become:
+
+```
+(node1, tdiscard1', (v5, t5))       ; tdiscard1' = t2 < t5
+(node2, tdiscard2', (v4, t4))       ; tdiscard2' = t3
+```
+
+**Generic algorithm for handling insertions:** A certain node n handles the
+InsertItem and is responsible for the correctness of this procedure.
+
+1. Lock the key (or the whole table?) at this node to prevent concurrent updates of the value that would mess things up
+2. Read current set of values
+3. Generate a new timestamp that is larger than the largest timestamp for node n
+4. Add the inserted value in the list of values of node n
+5. Update the discard times to be the times set in the context, and accordingly discard overwritten values
+6. Release lock
+7. Propagate updated value to other nodes
+8. Return to user when propagation achieved the write quorum (propagation to other nodes continues asynchronously)
+
+**Encoding of contexts:**
+
+Contexts consist in a list of (node id, timestamp) pairs.
+They are encoded in binary as follows:
+
+```
+checksum: u64, [ node: u64, timestamp: u64 ]*
+```
+
+The checksum is just the XOR of all of the node IDs and timestamps.
+
+Once encoded in binary, contexts are written and transmitted in base64.
+
+
+### Indexing
+
+K2V keeps an index, a secondary data structure that is updated asynchronously,
+that keeps tracks of the number of triplets stored for each partition key.
+This allows easy listing of all of the partition keys for which triplets exist
+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 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:
+
+```
+- pk: bucket
+- sk: partition key for which we are counting
+- v:  lwwmap (node id -> number of items)
+```
+
+The final number of items present in the partition can be estimated by taking
+the maximum of the values (i.e. the value for the node that announces having
+the most items for that partition). In most cases the values for different node
+IDs should all be the same; more precisely, three node IDs should map to the
+same non-zero value, and all other node IDs that are present are tombstones
+that map to zeroes.  Note that we need to filter out values from nodes that are
+no longer part of the cluster layout, as when nodes are removed they won't
+necessarily have had the time to set their counters to zero.
+
+## Important details
+
+**THIS SECTION CONTAINS A FEW WARNINGS ON THE K2V API WHICH ARE IMPORTANT
+TO UNDERSTAND IN ORDER TO USE IT CORRECTLY.**
+
+- **Internal server errors on updates do not mean that the update isn't stored.**
+  K2V will return an internal server error when it cannot reach a quorum of nodes on
+  which to save an updated value. However the value may still be stored on just one
+  node, which will then propagate it to other nodes asynchronously via anti-entropy.
+
+- **Batch operations are not transactions.** When calling InsertBatch or DeleteBatch,
+  items may appear partially inserted/deleted while the operation is being processed.
+  More importantly, if InsertBatch or DeleteBatch returns an internal server error,
+  some of the items to be inserted/deleted might end up inserted/deleted on the server,
+  while others may still have their old value.
+
+- **Concurrent values are deduplicated.** When inserting a value for a key,
+  Garage might internally end up
+  storing the value several times if there are network errors. These values will end up as
+  concurrent values for a key, with the same byte string (or `null` for a deletion).
+  Garage fixes this by deduplicating concurrent values when they are returned to the
+  user on read operations. Importantly, *Garage does not differentiate between duplicate
+  concurrent values due to the user making the same call twice, or Garage having to
+  do an internal retry*. This means that all duplicate concurrent values are deduplicated
+  when an item is read: if the user inserts twice concurrently the same value, they will
+  only read it once.
+
+## API Endpoints
+
+**Remark.** Example queries and responses here are given in JSON5 format
+for clarity. However the actual K2V API uses basic JSON so all examples
+and responses need to be translated.
+
+### Operations on single items
+
+**ReadItem: `GET /<bucket>/<partition key>?sort_key=<sort key>`**
+
+
+Query parameters:
+
+| name       | default value | meaning                          |
+|------------|---------------|----------------------------------|
+| `sort_key` | **mandatory** | The sort key of the item to read |
+
+Returns the item with specified partition key and sort key. Values can be
+returned in either of two ways:
+
+1. a JSON array of base64-encoded values, or `null`'s for tombstones, with
+   header `Content-Type: application/json`
+
+2. in the case where there are no concurrent values, the single present value
+   can be returned directly as the response body (or an HTTP 204 NO CONTENT for
+   a tombstone), with header `Content-Type: application/octet-stream`
+
+The choice between return formats 1 and 2 is directed by the `Accept` HTTP header:
+
+- if the `Accept` header is not present, format 1 is always used
+
+- if `Accept` contains `application/json` but not `application/octet-stream`,
+  format 1 is always used
+
+- if `Accept` contains `application/octet-stream` but not `application/json`,
+  format 2 is used when there is a single value, and an HTTP error 409 (HTTP
+  409 CONFLICT) is returned in the case of multiple concurrent values
+  (including concurrent tombstones)
+
+- if `Accept` contains both, format 2 is used when there is a single value, and
+  format 1 is used as a fallback in case of concurrent values
+
+- if `Accept` contains none, HTTP 406 NOT ACCEPTABLE is raised
+
+Example query:
+
+```
+GET /my_bucket/mailboxes?sort_key=INBOX HTTP/1.1
+```
+
+Example response:
+
+```json
+HTTP/1.1 200 OK
+X-Garage-Causality-Token: opaquetoken123
+Content-Type: application/json
+
+[
+  "b64cryptoblob123",
+  "b64cryptoblob'123"
+]
+```
+
+Example response in case the item is a tombstone:
+
+```
+HTTP/1.1 200 OK
+X-Garage-Causality-Token: opaquetoken999
+Content-Type: application/json
+
+[
+  null
+]
+```
+
+Example query 2:
+
+```
+GET /my_bucket/mailboxes?sort_key=INBOX HTTP/1.1
+Accept: application/octet-stream
+```
+
+Example response if multiple concurrent versions exist:
+
+```
+HTTP/1.1 409 CONFLICT
+X-Garage-Causality-Token: opaquetoken123
+Content-Type: application/octet-stream
+```
+
+Example response in case of single value:
+
+```
+HTTP/1.1 200 OK
+X-Garage-Causality-Token: opaquetoken123
+Content-Type: application/octet-stream
+
+cryptoblob123
+```
+
+Example response in case of a single value that is a tombstone:
+
+```
+HTTP/1.1 204 NO CONTENT
+X-Garage-Causality-Token: opaquetoken123
+Content-Type: application/octet-stream
+```
+
+
+**PollItem: `GET /<bucket>/<partition key>?sort_key=<sort key>&causality_token=<causality token>`**
+
+This endpoint will block until a new value is written to a key.
+
+The GET parameter `causality_token` should be set to the causality
+token returned with the last read of the key, so that K2V knows
+what values are concurrent or newer than the ones that the
+client previously knew.
+
+This endpoint returns the new value in the same format as ReadItem.
+If no new value is written and the timeout elapses,
+an HTTP 304 NOT MODIFIED is returned.
+
+Query parameters:
+
+| name              | default value | meaning                                                                    |
+|-------------------|---------------|----------------------------------------------------------------------------|
+| `sort_key`        | **mandatory** | The sort key of the item to read                                           |
+| `causality_token` | **mandatory** | The causality token of the last known value or set of values               |
+| `timeout`         | 300           | The timeout before 304 NOT MODIFIED is returned if the value isn't updated |
+
+The timeout can be set to any number of seconds, with a maximum of 600 seconds (10 minutes).
+
+
+**InsertItem: `PUT /<bucket>/<partition key>?sort_key=<sort_key>`**
+
+Inserts a single item. This request does not use JSON, the body is sent directly as a binary blob.
+
+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.
+
+Example query:
+
+```
+PUT /my_bucket/mailboxes?sort_key=INBOX HTTP/1.1
+X-Garage-Causality-Token: opaquetoken123
+
+myblobblahblahblah
+```
+
+Example response:
+
+```
+HTTP/1.1 204 No Content
+```
+
+**DeleteItem: `DELETE /<bucket>/<partition key>?sort_key=<sort_key>`**
+
+Deletes a single item. The HTTP header `X-Garage-Causality-Token` must be set
+to the causality token returned by a previous read on this key, to indicate
+which versions of the value should be deleted. The request will not process if
+`X-Garage-Causality-Token` is not set.
+
+Example query:
+
+```
+DELETE /my_bucket/mailboxes?sort_key=INBOX HTTP/1.1
+X-Garage-Causality-Token: opaquetoken123
+```
+
+Example response:
+
+```
+HTTP/1.1 204 NO CONTENT
+```
+
+### Operations on index
+
+**ReadIndex: `GET /<bucket>?start=<start>&end=<end>&limit=<limit>`**
+
+Lists all partition keys in the bucket for which some triplets exist, and gives
+for each the number of triplets, total number of values (which might be bigger
+than the number of triplets in case of conflicts), total number of bytes of
+these values, and number of triplets that are in a state of conflict.
+The values returned are an approximation of the true counts in the bucket,
+as these values are asynchronously updated, and thus eventually consistent.
+
+Query parameters:
+
+| name      | default value | meaning                                                        |
+|-----------|---------------|----------------------------------------------------------------|
+| `prefix`  | `null`        | Restrict listing to partition keys that start with this prefix |
+| `start`   | `null`        | First partition key to list, in lexicographical order          |
+| `end`     | `null`        | Last partition key to list (excluded)                          |
+| `limit`   | `null`        | Maximum number of partition keys to list                       |
+| `reverse` | `false`       | Iterate in reverse lexicographical order                       |
+
+The response consists in a JSON object that repeats the parameters of the query and gives the result (see below).
+
+The listing starts at partition key `start`, or if not specified at the
+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
+   is reached exactly, it is not included in the result)
+
+2. if `limit` is specified, `limit` partition keys have been listed
+
+3. no more partition keys are available to list
+
+In case 2, and if there are more partition keys to list before condition 1
+triggers, then in the result `more` is set to `true` and `nextStart` is set to
+the first partition key that couldn't be listed due to the limit. In the first
+case (if the listing stopped because of the `end` parameter), `more` is not set
+and the `nextStart` key is not specified.
+
+Note that if `reverse` is set to `true`, `start` is the highest key
+(in lexicographical order) for which values are returned.
+This means that if an `end` is specified, it must be smaller than `start`,
+otherwise no values will be returned.
+
+Example query:
+
+```
+GET /my_bucket HTTP/1.1
+```
+
+Example response:
+
+```json
+HTTP/1.1 200 OK
+
+{
+  prefix: null,
+  start: null,
+  end: null,
+  limit: null,
+  reverse: false,
+  partitionKeys: [
+    {
+      pk: "keys",
+      entries: 3043,
+      conflicts: 0,
+      values: 3043,
+      bytes: 121720,
+    },
+    {
+      pk: "mailbox:INBOX",
+      entries: 42,
+      conflicts: 1,
+      values: 43,
+      bytes: 142029,
+    },
+    {
+      pk: "mailbox:Junk",
+      entries: 2991
+      conflicts: 0,
+      values: 2991,
+      bytes: 12019322,
+    },
+    {
+      pk: "mailbox:Trash",
+      entries: 10,
+      conflicts: 0,
+      values: 10,
+      bytes: 32401,
+    },
+    {
+      pk: "mailboxes",
+      entries: 3,
+      conflicts: 0,
+      values: 3,
+      bytes: 3019,
+    },
+  ],
+  more: false,
+  nextStart: null,
+}
+```
+
+
+### Operations on batches of items
+
+**InsertBatch: `POST /<bucket>`**
+
+Simple insertion and deletion of triplets. The body is just a list of items to
+insert in the following format:
+`{ pk: "<partition key>", sk: "<sort key>", ct: "<causality token>"|null, v: "<value>"|null }`.
+
+The causality token should be the one returned in a previous read request (e.g.
+by ReadItem or ReadBatch), to indicate that this write takes into account the
+values that were returned from these reads, and supersedes them causally. If
+the triplet is inserted for the first time, the causality token should be set to
+`null`.
+
+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
+case both are preserved and returned on reads (see below).
+
+Partition keys and sort keys are utf8 strings which are stored sorted by
+lexicographical ordering of their binary representation.
+
+Example query:
+
+```json
+POST /my_bucket HTTP/1.1
+
+[
+  { pk: "mailbox:INBOX", sk: "001892831", ct: "opaquetoken321", v: "b64cryptoblob321updated" },
+  { pk: "mailbox:INBOX", sk: "001892912", ct: null, v: "b64cryptoblob444" },
+  { pk: "mailbox:INBOX", sk: "001892932", ct: "opaquetoken654", v: null },
+]
+```
+
+Example response:
+
+```
+HTTP/1.1 204 NO CONTENT
+```
+
+
+**ReadBatch: `POST /<bucket>?search`**, or alternatively<br/>
+**ReadBatch: `SEARCH /<bucket>`**
+
+Batch read of triplets in a bucket.
+
+The request body is a JSON list of searches, that each specify a range of
+items to get (to get single items, set `singleItem` to `true`). A search is a
+JSON struct with the following fields:
+
+| name            | default value | meaning                                                                                |
+|-----------------|---------------|----------------------------------------------------------------------------------------|
+| `partitionKey`  | **mandatory** | The partition key in which to search                                                   |
+| `prefix`        | `null`        | Restrict items to list to those whose sort keys start with this prefix                 |
+| `start`         | `null`        | The sort key of the first item to read                                                 |
+| `end`           | `null`        | The sort key of the last item to read (excluded)                                       |
+| `limit`         | `null`        | The maximum number of items to return                                                  |
+| `reverse`       | `false`       | Iterate in reverse lexicographical order on sort keys                                  |
+| `singleItem`    | `false`       | Whether to return only the item with sort key `start`                                  |
+| `conflictsOnly` | `false`       | Whether to return only items that have several concurrent values                       |
+| `tombstones`    | `false`       | Whether or not to return tombstone lines to indicate the presence of old deleted items |
+
+
+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
+is the one given in `start`. Parameters `conflictsOnly` and `tombstones`
+control additional filters on the items that are returned.
+
+The result is a list of length the number of searches, that consists in for
+each search a JSON object specified similarly to the result of ReadIndex, but
+that lists triplets within a partition key.
+
+The format of returned tuples is as follows: `{ sk: "<sort key>", ct: "<causality
+token>", v: ["<value1>", ...] }`, with the following fields:
+
+- `sk` (sort key): any unicode string used as a sort key
+
+- `ct` (causality token): an opaque token served by the server (generally
+  base64-encoded) to be used in subsequent writes to this key
+
+- `v` (list of values): each value is a binary blob, always base64-encoded;
+  contains multiple items when concurrent values exists
+
+- 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
+  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
+
+Example query:
+
+```json
+POST /my_bucket?search HTTP/1.1
+
+[
+  {
+    partitionKey: "mailboxes",
+  },
+  {
+    partitionKey: "mailbox:INBOX",
+    start: "001892831",
+    limit: 3,
+  },
+  {
+    partitionKey: "keys",
+    start: "0",
+    singleItem: true,
+  },
+]
+```
+
+Example associated response body:
+
+```json
+HTTP/1.1 200 OK
+
+[
+  {
+    partitionKey: "mailboxes",
+    prefix: null,
+    start: null,
+    end: null,
+    limit: null,
+    reverse: false,
+    conflictsOnly: false,
+    tombstones: false,
+    singleItem: false,
+    items: [
+      { sk: "INBOX", ct: "opaquetoken123", v: ["b64cryptoblob123", "b64cryptoblob'123"] },
+      { sk: "Trash", ct: "opaquetoken456", v: ["b64cryptoblob456"] },
+      { sk: "Junk", ct: "opaquetoken789", v: ["b64cryptoblob789"] },
+    ],
+    more: false,
+    nextStart: null,
+  },
+  {
+    partitionKey: "mailbox::INBOX",
+    prefix: null,
+    start: "001892831",
+    end: null,
+    limit: 3,
+    reverse: false,
+    conflictsOnly: false,
+    tombstones: false,
+    singleItem: false,
+    items: [
+      { sk: "001892831", ct: "opaquetoken321", v: ["b64cryptoblob321"] },
+      { sk: "001892832", ct: "opaquetoken654", v: ["b64cryptoblob654"] },
+      { sk: "001892874", ct: "opaquetoken987", v: ["b64cryptoblob987"] },
+    ],
+    more: true,
+    nextStart: "001892898",
+  },
+  {
+    partitionKey: "keys",
+    prefix: null,
+    start: "0",
+    end: null,
+    conflictsOnly: false,
+    tombstones: false,
+    limit: null,
+    reverse: false,
+    singleItem: true,
+    items: [
+      { sk: "0", ct: "opaquetoken999", v: ["b64binarystuff999"] },
+    ],
+    more: false,
+    nextStart: null,
+  },
+]
+```
+
+
+
+**DeleteBatch: `POST /<bucket>?delete`**
+
+Batch deletion of triplets. The request format is the same for `POST
+/<bucket>?search` to indicate items or range of items, except that here they
+are deleted instead of returned, but only the fields `partitionKey`, `prefix`, `start`,
+`end`, and `singleItem` are supported. Causality information is not given by
+the user: this request will internally list all triplets and write deletion
+markers that supersede all of the versions that have been read.
+
+This request returns for each series of items to be deleted, the number of
+matching items that have been found and deleted.
+
+Example query:
+
+```json
+POST /my_bucket?delete HTTP/1.1
+
+[
+  {
+    partitionKey: "mailbox:OldMailbox",
+  },
+  {
+    partitionKey: "mailbox:INBOX",
+    start: "0018928321",
+    singleItem: true,
+  },
+]
+```
+
+Example response:
+
+```json
+HTTP/1.1 200 OK
+
+[
+  {
+    partitionKey: "mailbox:OldMailbox",
+    prefix: null,
+    start: null,
+    end: null,
+    singleItem: false,
+    deletedItems: 35,
+  },
+  {
+    partitionKey: "mailbox:INBOX",
+    prefix: null,
+    start: "0018928321",
+    end: null,
+    singleItem: true,
+    deletedItems: 1,
+  },
+]
+```
+
+**PollRange: `POST /<bucket>/<partition key>?poll_range`**, or alternatively<br/>
+**PollRange: `SEARCH /<bucket>/<partition key>?poll_range`**
+
+Polls a range of items for changes.
+
+The query body is a JSON object consisting of the following fields:
+
+| name            | default value | meaning                                                                                |
+|-----------------|---------------|----------------------------------------------------------------------------------------|
+| `prefix`        | `null`        | Restrict items to poll to those whose sort keys start with this prefix                 |
+| `start`         | `null`        | The sort key of the first item to poll                                                 |
+| `end`           | `null`        | The sort key of the last item to poll (excluded)                                       |
+| `timeout`       | 300           | The timeout before 304 NOT MODIFIED is returned if no value in the range is updated    |
+| `seenMarker`    | `null`        | An opaque string returned by a previous PollRange call, that represents items already seen |
+
+The timeout can be set to any number of seconds, with a maximum of 600 seconds (10 minutes).
+
+The response is either:
+
+- A HTTP 304 NOT MODIFIED response with an empty body, if the timeout expired and no changes occurred
+
+- A HTTP 200 response, indicating that some changes have occurred since the last PollRange call, in which case a JSON object is returned in the body with the following fields:
+
+| name            | meaning                                                                                |
+|-----------------|----------------------------------------------------------------------------------------|
+| `seenMarker`    | An opaque string that represents items already seen for future PollRange calls         |
+| `items`         | The list of items that have changed since last PollRange call, in the same format as ReadBatch |
+
+If no seen marker is known by the caller, it can do a PollRange call
+without specifying `seenMarker`. In this case, the PollRange call will
+complete immediately, and return the current content of the range (which
+can be empty) and a seen marker to be used in further PollRange calls. This
+is the only case in which PollRange might return an HTTP 200 with an empty
+set of items.
+
+A seen marker returned as a response to a PollRange query can be used for further PollRange
+queries on the same range, or for PollRange queries in a subrange of the initial range.
+It may not be used for PollRange queries on ranges larger or outside of the initial range.
+
+Example query:
+
+```json
+SEARCH /my_bucket?poll_range HTTP/1.1
+
+{
+  "prefix": "0391.",
+  "start": "0391.000001973107",
+  "seenMarker": "opaquestring123",
+}
+```
+
+
+Example response:
+
+```json
+HTTP/1.1 200 OK
+Content-Type: application/json
+
+{
+  "seenMarker": "opaquestring456",
+  "items": [
+    { sk: "0391.000001973221", ct: "opaquetoken123", v: ["b64cryptoblob123", "b64cryptoblob'123"] },
+    { sk: "0391.000001974191", ct: "opaquetoken456", v: ["b64cryptoblob456", "b64cryptoblob'456"] },
+  ]
+}
+```
+
+
+## Internals: causality tokens
+
+The method used is based on DVVS (dotted version vector sets). See:
+
+- the paper "Scalable and Accurate Causality Tracking for Eventually Consistent Data Stores"
+- <https://github.com/ricardobcl/Dotted-Version-Vectors>
+
+For DVVS to work, write operations (at each node) must take a lock on the data table.

doc/optimal_layout_report/.gitignore

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