Compare commits

..

1 Commits

Author SHA1 Message Date
Alex Auvolat a46c3d2502 [rm-sled] Replace unsafe code with ouroboros in sqlite adapter 2024-03-12 11:47:14 +01:00
314 changed files with 17713 additions and 28317 deletions
+3
View File
@@ -0,0 +1,3 @@
[target.x86_64-unknown-linux-gnu]
linker = "clang"
rustflags = ["-C", "link-arg=-fuse-ld=mold"]
+24 -33
View File
@@ -1,6 +1,3 @@
labels:
nix: "enabled"
when:
event:
- push
@@ -12,43 +9,37 @@ when:
steps:
- name: check formatting
image: nixpkgs/nix:nixos-24.05
image: nixpkgs/nix:nixos-22.05
commands:
- nix-build -j4 --attr flakePackages.fmt
- name: check typos
image: nixpkgs/nix:nixos-24.05
commands:
- nix-shell --attr ci --run typos
- name: check lints with clippy
image: nixpkgs/nix:nixos-24.05
commands:
- nix-build -j4 --attr flakePackages.clippy
- nix-shell --attr devShell --run "cargo fmt -- --check"
- name: build
image: nixpkgs/nix:nixos-24.05
image: nixpkgs/nix:nixos-22.05
commands:
- nix-build -j4 --attr flakePackages.dev
- nix-build --no-build-output --attr clippy.amd64 --argstr git_version ${CI_COMMIT_TAG:-$CI_COMMIT_SHA}
- name: unit + func tests (lmdb)
image: nixpkgs/nix:nixos-24.05
- 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 -j4 --attr flakePackages.tests-lmdb
- name: unit + func tests (sqlite)
image: nixpkgs/nix:nixos-24.05
commands:
- nix-build -j4 --attr flakePackages.tests-sqlite
- name: unit + func tests (fjall)
image: nixpkgs/nix:nixos-24.05
commands:
- nix-build -j4 --attr flakePackages.tests-fjall
- 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-*
- ./result/bin/integration-* || (cat tmp-garage-integration/stderr.log; false)
- rm result
- rm -rv tmp-garage-integration
- name: integration tests
image: nixpkgs/nix:nixos-24.05
image: nixpkgs/nix:nixos-22.05
commands:
- nix-build -j4 --attr flakePackages.dev
- 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)
depends_on: [ build ]
+9 -13
View File
@@ -1,6 +1,3 @@
labels:
nix: "enabled"
when:
event:
- deployment
@@ -11,21 +8,20 @@ depends_on:
steps:
- name: refresh-index
image: nixpkgs/nix:nixos-24.05
environment:
AWS_ACCESS_KEY_ID:
from_secret: garagehq_aws_access_key_id
AWS_SECRET_ACCESS_KEY:
from_secret: garagehq_aws_secret_access_key
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-24.05
environment:
DOCKER_AUTH:
from_secret: docker_auth
image: nixpkgs/nix:nixos-22.05
secrets:
- docker_auth
commands:
- mkdir -p /root/.docker
- echo $DOCKER_AUTH > /root/.docker/config.json
+17 -26
View File
@@ -1,6 +1,3 @@
labels:
nix: "enabled"
when:
event:
- deployment
@@ -19,17 +16,18 @@ matrix:
steps:
- name: build
image: nixpkgs/nix:nixos-24.05
image: nixpkgs/nix:nixos-22.05
commands:
- nix-build --attr releasePackages.${ARCH} --argstr git_version ${CI_COMMIT_TAG:-$CI_COMMIT_SHA}
- 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-24.05
image: nixpkgs/nix:nixos-22.05
commands:
- nix-shell --attr ci --run "./script/not-dynamic.sh result/bin/garage"
- 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-24.05
image: nixpkgs/nix:nixos-22.05
commands:
- nix-shell --attr ci --run ./script/test-smoke.sh || (cat /tmp/garage.log; false)
when:
@@ -38,16 +36,8 @@ steps:
- matrix:
ARCH: i386
- name: upgrade tests from v1.0.0
image: nixpkgs/nix:nixos-24.05
commands:
- nix-shell --attr ci --run "./script/test-upgrade.sh v1.0.0 x86_64-unknown-linux-musl" || (cat /tmp/garage.log; false)
when:
- matrix:
ARCH: amd64
- name: upgrade tests from v0.8.4
image: nixpkgs/nix:nixos-24.05
- 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:
@@ -55,23 +45,24 @@ steps:
ARCH: amd64
- name: push static binary
image: nixpkgs/nix:nixos-24.05
image: nixpkgs/nix:nixos-22.05
environment:
TARGET: "${TARGET}"
AWS_ACCESS_KEY_ID:
from_secret: garagehq_aws_access_key_id
AWS_SECRET_ACCESS_KEY:
from_secret: garagehq_aws_secret_access_key
secrets:
- source: garagehq_aws_access_key_id
target: AWS_ACCESS_KEY_ID
- source: garagehq_aws_secret_access_key
target: AWS_SECRET_ACCESS_KEY
commands:
- nix-shell --attr ci --run "to_s3"
- name: docker build and publish
image: nixpkgs/nix:nixos-24.05
image: nixpkgs/nix:nixos-22.05
environment:
DOCKER_PLATFORM: "linux/${ARCH}"
CONTAINER_NAME: "dxflrs/${ARCH}_garage"
DOCKER_AUTH:
from_secret: docker_auth
secrets:
- docker_auth
commands:
- mkdir -p /root/.docker
- echo $DOCKER_AUTH > /root/.docker/config.json
Generated
+1230 -1791
View File
File diff suppressed because it is too large Load Diff
+7124
View File
File diff suppressed because it is too large Load Diff
+30 -42
View File
@@ -8,10 +8,7 @@ members = [
"src/table",
"src/block",
"src/model",
"src/api/common",
"src/api/s3",
"src/api/k2v",
"src/api/admin",
"src/api",
"src/web",
"src/garage",
"src/k2v-client",
@@ -24,22 +21,19 @@ default-members = ["src/garage"]
# Internal Garage crates
format_table = { version = "0.1.1", path = "src/format-table" }
garage_api_common = { version = "2.2.0", path = "src/api/common" }
garage_api_admin = { version = "2.2.0", path = "src/api/admin" }
garage_api_s3 = { version = "2.2.0", path = "src/api/s3" }
garage_api_k2v = { version = "2.2.0", path = "src/api/k2v" }
garage_block = { version = "2.2.0", path = "src/block" }
garage_db = { version = "2.2.0", path = "src/db", default-features = false }
garage_model = { version = "2.2.0", path = "src/model", default-features = false }
garage_net = { version = "2.2.0", path = "src/net" }
garage_rpc = { version = "2.2.0", path = "src/rpc" }
garage_table = { version = "2.2.0", path = "src/table" }
garage_util = { version = "2.2.0", path = "src/util" }
garage_web = { version = "2.2.0", path = "src/web" }
garage_api = { version = "0.10.0", path = "src/api" }
garage_block = { version = "0.10.0", path = "src/block" }
garage_db = { version = "0.10.0", path = "src/db", default-features = false }
garage_model = { version = "0.10.0", path = "src/model", default-features = false }
garage_net = { version = "0.10.0", path = "src/net" }
garage_rpc = { version = "0.10.0", path = "src/rpc" }
garage_table = { version = "0.10.0", path = "src/table" }
garage_util = { version = "0.10.0", path = "src/util" }
garage_web = { version = "0.10.0", path = "src/web" }
k2v-client = { version = "0.0.4", path = "src/k2v-client" }
# External crates from crates.io
arc-swap = "1.1"
arc-swap = "1.0"
argon2 = "0.5"
async-trait = "0.1.7"
backtrace = "0.3"
@@ -48,28 +42,27 @@ blake2 = "0.10"
bytes = "1.0"
bytesize = "1.1"
cfg-if = "1.0"
chrono = { version = "0.4", features = ["serde"] }
crc-fast = "1.6"
chrono = "0.4"
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 = "0.29", default-features = false, features = ["fs"] }
nix = { version = "0.27", default-features = false, features = ["fs"] }
nom = "7.1"
parking_lot = "0.12"
ouroboros = "0.18"
parse_duration = "2.1"
paste = "1.0"
pin-project = "1.0.12"
pnet_datalink = "0.34"
rand = "0.8"
sha1 = "0.10"
sha2 = "0.10"
timeago = { version = "0.4", default-features = false }
xxhash-rust = { version = "0.8", default-features = false, features = ["xxh3"] }
@@ -81,27 +74,21 @@ kuska-handshake = { version = "0.2.0", features = ["default", "async_std"] }
clap = { version = "4.1", features = ["derive", "env"] }
pretty_env_logger = "0.5"
structopt = { version = "0.3", default-features = false }
syslog-tracing = "0.3"
tracing = "0.1"
tracing-journald = "0.3.1"
tracing-subscriber = { version = "0.3", features = ["env-filter"] }
heed = { version = "0.11", default-features = false, features = ["lmdb"] }
rusqlite = "0.37"
r2d2 = "0.8"
r2d2_sqlite = "0.31"
fjall = "2.4"
rusqlite = "0.30.0"
async-compression = { version = "0.4", features = ["tokio", "zstd"] }
zstd = { version = "0.13", default-features = false }
quick-xml = { version = "0.26", features = ["serialize"] }
quick-xml = { version = "0.26", features = [ "serialize" ] }
rmp-serde = "1.1.2"
serde = { version = "1.0", default-features = false, features = ["derive", "rc"] }
serde_bytes = "0.11"
serde_json = "1.0"
toml = { version = "0.8", default-features = false, features = ["parse"] }
utoipa = { version = "5.3.1", features = ["chrono"] }
# newer version requires rust edition 2021
k8s-openapi = { version = "0.21", features = ["v1_24"] }
@@ -115,7 +102,7 @@ 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"] }
hyper-util = { version = "0.1", features = [ "full" ] }
multer = "3.0"
percent-encoding = "2.2"
roxmltree = "0.19"
@@ -123,29 +110,30 @@ url = "2.3"
futures = "0.3"
futures-util = "0.3"
tokio = { version = "1.0", default-features = false, features = ["rt", "rt-multi-thread", "io-util", "net", "time", "macros", "sync", "signal", "fs"] }
tokio = { 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 = { version = "0.17", features = [ "rt-tokio", "metrics", "trace" ] }
opentelemetry-prometheus = "0.10"
opentelemetry-otlp = "0.10"
opentelemetry-contrib = "0.9"
prometheus = "0.13"
# used by the k2v-client crate only
aws-sigv4 = { version = "1.1", default-features = false }
hyper-rustls = { version = "0.26", default-features = false, features = ["http1", "http2", "ring", "rustls-native-certs"] }
aws-sigv4 = { version = "1.1" }
hyper-rustls = { version = "0.26", features = ["http2"] }
log = "0.4"
thiserror = "2.0"
thiserror = "1.0"
# ---- used only as build / dev dependencies ----
assert-json-diff = "2.0"
rustc_version = "0.4.0"
static_init = "1.0"
aws-smithy-runtime = { version = "1.8", default-features = false, features = ["tls-rustls"] }
aws-sdk-config = { version = "1.62", default-features = false }
aws-sdk-s3 = { version = "1.79", default-features = false, features = ["rt-tokio"] }
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
@@ -154,5 +142,5 @@ lto = "off"
[profile.release]
lto = true
codegen-units = 1
opt-level = 3
opt-level = "s"
strip = true
+1 -1
View File
@@ -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"]
+8 -3
View File
@@ -1,8 +1,13 @@
.PHONY: doc all run1 run2 run3
.PHONY: doc all release shell run1 run2 run3
all:
clear
cargo build
clear; cargo build
release:
nix-build --attr pkgs.amd64.release --no-build-output
shell:
nix-shell
# ----
+44 -13
View File
@@ -3,22 +3,53 @@
with import ./nix/common.nix;
let
pkgs = import nixpkgs { };
pkgs = import pkgsSrc { };
compile = import ./nix/compile.nix;
build_release = target: (compile {
inherit target system git_version nixpkgs;
crane = flake.inputs.crane;
rust-overlay = flake.inputs.rust-overlay;
release = true;
}).garage;
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 {
releasePackages = {
amd64 = build_release "x86_64-unknown-linux-musl";
i386 = build_release "i686-unknown-linux-musl";
arm64 = build_release "aarch64-unknown-linux-musl";
arm = build_release "armv6l-unknown-linux-musleabihf";
pkgs = {
amd64 = build_debug_and_release "x86_64-unknown-linux-musl";
i386 = build_debug_and_release "i686-unknown-linux-musl";
arm64 = build_debug_and_release "aarch64-unknown-linux-musl";
arm = build_debug_and_release "armv6l-unknown-linux-musleabihf";
};
test = {
amd64 = test (compile {
inherit system git_version pkgsSrc cargo2nixOverlay;
target = "x86_64-unknown-linux-musl";
features = [
"garage/bundled-libs"
"garage/k2v"
"garage/lmdb"
"garage/sqlite"
];
});
};
clippy = {
amd64 = (compile {
inherit system git_version pkgsSrc cargo2nixOverlay;
target = "x86_64-unknown-linux-musl";
compiler = "clippy";
}).workspace.garage { compileMode = "build"; };
};
flakePackages = flake.packages.${system};
}
+1 -1
View File
@@ -1,7 +1,7 @@
<!DOCTYPE html>
<html>
<head>
<title>Garage administration API v0</title>
<title>Garage Adminstration API v0</title>
<!-- needed for adaptive design -->
<meta charset="utf-8"/>
<meta name="viewport" content="width=device-width, initial-scale=1">
+4 -4
View File
@@ -3,10 +3,10 @@ info:
version: v0.8.0
title: Garage Administration API v0+garage-v0.8.0
description: |
Administrate your Garage cluster programmatically, including status, layout, keys, buckets, and maintenance tasks.
*Disclaimer: The API is not stable yet, hence its v0 tag. The API can change at any time, and changes can include breaking backward compatibility. Read the changelog and upgrade your scripts before upgrading. Additionally, this specification is very early stage and can contain bugs, especially on error return codes/types that are not tested yet. Do not expect a well finished and polished product!*
paths:
Administrate your Garage cluster programatically, including status, layout, keys, buckets, and maintainance tasks.
*Disclaimer: The API is not stable yet, hence its v0 tag. The API can change at any time, and changes can include breaking backward compatibility. Read the changelog and upgrade your scripts before upgrading. Additionnaly, this specification is very early stage and can contain bugs, especially on error return codes/types that are not tested yet. Do not expect a well finished and polished product!*
paths:
/status:
get:
tags:
+1 -1
View File
@@ -1,7 +1,7 @@
<!DOCTYPE html>
<html>
<head>
<title>Garage administration API v1</title>
<title>Garage Adminstration API v0</title>
<!-- needed for adaptive design -->
<meta charset="utf-8"/>
<meta name="viewport" content="width=device-width, initial-scale=1">
+7 -7
View File
@@ -3,10 +3,10 @@ info:
version: v0.9.0
title: Garage Administration API v0+garage-v0.9.0
description: |
Administrate your Garage cluster programmatically, including status, layout, keys, buckets, and maintenance tasks.
*Disclaimer: The API is not stable yet, hence its v0 tag. The API can change at any time, and changes can include breaking backward compatibility. Read the changelog and upgrade your scripts before upgrading. Additionally, this specification is very early stage and can contain bugs, especially on error return codes/types that are not tested yet. Do not expect a well finished and polished product!*
paths:
Administrate your Garage cluster programatically, including status, layout, keys, buckets, and maintainance tasks.
*Disclaimer: The API is not stable yet, hence its v0 tag. The API can change at any time, and changes can include breaking backward compatibility. Read the changelog and upgrade your scripts before upgrading. Additionnaly, this specification is very early stage and can contain bugs, especially on error return codes/types that are not tested yet. Do not expect a well finished and polished product!*
paths:
/health:
get:
tags:
@@ -440,7 +440,7 @@ paths:
- "false"
example: "true"
required: false
description: "Whether or not the secret key should be returned in the response"
description: "Wether or not the secret key should be returned in the response"
responses:
'500':
description: "The server can not handle your request. Check your connectivity with the rest of the cluster."
@@ -687,7 +687,7 @@ paths:
operationId: "GetBucketInfo"
summary: "Get a bucket"
description: |
Given a bucket identifier (`id`) or a global alias (`globalAlias`), get its information.
Given a bucket identifier (`id`) or a global alias (`alias`), get its information.
It includes its aliases, its web configuration, keys that have some permissions
on it, some statistics (number of objects, size), number of dangling multipart uploads,
and its quotas (if any).
@@ -701,7 +701,7 @@ paths:
example: "b4018dc61b27ccb5c64ec1b24f53454bbbd180697c758c4d47a22a8921864a87"
schema:
type: string
- name: globalAlias
- name: alias
in: query
description: |
The exact global alias of one of the existing buckets.
-24
View File
@@ -1,24 +0,0 @@
<!DOCTYPE html>
<html>
<head>
<title>Garage administration API v2</title>
<!-- needed for adaptive design -->
<meta charset="utf-8"/>
<meta name="viewport" content="width=device-width, initial-scale=1">
<link href="./css/redoc.css" rel="stylesheet">
<!--
Redoc doesn't change outer page styles
-->
<style>
body {
margin: 0;
padding: 0;
}
</style>
</head>
<body>
<redoc spec-url='./garage-admin-v2.json'></redoc>
<script src="./redoc.standalone.js"> </script>
</body>
</html>
File diff suppressed because it is too large Load Diff
+1 -1
View File
@@ -51,4 +51,4 @@ We are currently building this SDK for [Python](@/documentation/build/python.md#
More information:
- [In the reference manual](@/documentation/reference-manual/admin-api.md)
- [Full specification](https://garagehq.deuxfleurs.fr/api/garage-admin-v0.html)
- [Full specifiction](https://garagehq.deuxfleurs.fr/api/garage-admin-v0.html)
+3 -3
View File
@@ -5,13 +5,13 @@ weight = 99
## S3
If you are developing a new application, you may want to use Garage to store your user's media.
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,
you can query it. You can check the [S3 REST API Reference](https://docs.aws.amazon.com/AmazonS3/latest/API/API_Operations_Amazon_Simple_Storage_Service.html) from Amazon to learn more.
Developing your own wrapper around the REST API is time consuming and complicated.
Instead, there are some libraries already available.
Developping your own wrapper around the REST API is time consuming and complicated.
Instead, there are some libraries already avalaible.
Some of them are maintained by Amazon, some by Minio, others by the community.
+1 -1
View File
@@ -23,7 +23,7 @@ client = minio.Minio(
"GKyourapikey",
"abcd[...]1234",
# Force the region, this is specific to garage
region="garage",
region="region",
)
```
+1 -1
View File
@@ -23,7 +23,7 @@ To configure S3-compatible software to interact with Garage,
you will need the following parameters:
- An **API endpoint**: this corresponds to the HTTP or HTTPS address
used to contact the Garage server. When running Garage locally this will usually
used to contact the Garage server. When runing Garage locally this will usually
be `http://127.0.0.1:3900`. In a real-world setting, you would usually have a reverse-proxy
that adds TLS support and makes your Garage server available under a public hostname
such as `https://garage.example.com`.
+15 -188
View File
@@ -12,9 +12,8 @@ In this section, we cover the following web applications:
| [Mastodon](#mastodon) | ✅ | Natively supported |
| [Matrix](#matrix) | ✅ | Tested with `synapse-s3-storage-provider` |
| [ejabberd](#ejabberd) | ✅ | `mod_s3_upload` |
| [Ente](#ente) | | Natively supported |
| [Pixelfed](#pixelfed) | ❓ | Natively supported |
| [Pleroma](#pleroma) | ✅ | Natively supported |
| [Pixelfed](#pixelfed) | | Not yet tested |
| [Pleroma](#pleroma) | ❓ | Not yet tested |
| [Lemmy](#lemmy) | ✅ | Supported with pict-rs |
| [Funkwhale](#funkwhale) | ❓ | Not yet tested |
| [Misskey](#misskey) | ❓ | Not yet tested |
@@ -54,7 +53,7 @@ garage bucket allow nextcloud --read --write --key nextcloud-key
Now edit your Nextcloud configuration file to enable object storage.
On my installation, the config. file is located at the following path: `/var/www/nextcloud/config/config.php`.
We will add a new root key to the `$CONFIG` dictionary named `objectstore`:
We will add a new root key to the `$CONFIG` dictionnary named `objectstore`:
```php
<?php
@@ -70,7 +69,7 @@ $CONFIG = array(
'hostname' => '127.0.0.1', // Can also be a domain name, eg. garage.example.com
'port' => 3900, // Put your reverse proxy port or your S3 API port
'use_ssl' => false, // Set it to true if you have a TLS enabled reverse proxy
'region' => 'garage', // Garage default region is named "garage", edit according to your cluster config
'region' => 'garage', // Garage has only one region named "garage"
'use_path_style' => true // Garage supports only path style, must be set to true
],
],
@@ -136,7 +135,7 @@ bucket but doesn't also know the secret encryption key.
*Click on the picture to zoom*
Add a new external storage. Put what you want in "folder name" (eg. "shared"). Select "Amazon S3". Keep "Access Key" for the Authentication field.
In Configuration, put your bucket name (eg. nextcloud), the host (eg. 127.0.0.1), the port (eg. 3900 or 443), the region ("garage" if you use the default, or the one your configured in your `garage.toml`). Tick the SSL box if you have put an HTTPS proxy in front of garage. You must tick the "Path access" box and you must leave the "Legacy authentication (v2)" box empty. Put your Key ID (eg. GK...) and your Secret Key in the last two input boxes. Finally click on the tick symbol on the right of your screen.
In Configuration, put your bucket name (eg. nextcloud), the host (eg. 127.0.0.1), the port (eg. 3900 or 443), the region (garage). Tick the SSL box if you have put an HTTPS proxy in front of garage. You must tick the "Path access" box and you must leave the "Legacy authentication (v2)" box empty. Put your Key ID (eg. GK...) and your Secret Key in the last two input boxes. Finally click on the tick symbol on the right of your screen.
Now go to your "Files" app and a new "linked folder" has appeared with the name you chose earlier (eg. "shared").
@@ -192,10 +191,10 @@ garage key create peertube-key
Keep the Key ID and the Secret key in a pad, they will be needed later.
We need two buckets, one for normal videos (named peertube-videos) and one for webtorrent videos (named peertube-playlists).
We need two buckets, one for normal videos (named peertube-video) and one for webtorrent videos (named peertube-playlist).
```bash
garage bucket create peertube-videos
garage bucket create peertube-playlists
garage bucket create peertube-playlist
```
Now we allow our key to read and write on these buckets:
@@ -239,7 +238,7 @@ object_storage:
# Put localhost only if you have a garage instance running on that node
endpoint: 'http://localhost:3900' # or "garage.example.com" if you have TLS on port 443
# Garage default region is named "garage", edit according to your config
# Garage supports only one region for now, named garage
region: 'garage'
credentials:
@@ -254,7 +253,7 @@ object_storage:
proxify_private_files: false
streaming_playlists:
bucket_name: 'peertube-playlists'
bucket_name: 'peertube-playlist'
# Keep it empty for our example
prefix: ''
@@ -336,7 +335,6 @@ From the [official Mastodon documentation](https://docs.joinmastodon.org/admin/t
```bash
$ RAILS_ENV=production bin/tootctl media remove --days 3
$ RAILS_ENV=production bin/tootctl media remove --days 15 --prune-profiles
$ RAILS_ENV=production bin/tootctl media remove-orphans
$ RAILS_ENV=production bin/tootctl preview_cards remove --days 15
```
@@ -355,6 +353,8 @@ Imports: 1.7 KB
Settings: 0 Bytes
```
Unfortunately, [old avatars and headers cannot currently be cleaned up](https://github.com/mastodon/mastodon/issues/9567).
### Migrating your data
Data migration should be done with an efficient S3 client.
@@ -413,7 +413,7 @@ mc mirror --newer-than "3h" ./public/system/ garage/mastodon-data
## Matrix
Matrix is a chat communication protocol. Its main stable server implementation, [Synapse](https://matrix-org.github.io/synapse/latest/), provides a module to store media on a S3 backend. Additionally, a server independent media store supporting S3 has been developed by the community, it has been made possible thanks to how the matrix API has been designed and will work with implementations like Conduit, Dendrite, etc.
Matrix is a chat communication protocol. Its main stable server implementation, [Synapse](https://matrix-org.github.io/synapse/latest/), provides a module to store media on a S3 backend. Additionally, a server independent media store supporting S3 has been developped by the community, it has been made possible thanks to how the matrix API has been designed and will work with implementations like Conduit, Dendrite, etc.
### synapse-s3-storage-provider (synapse only)
@@ -442,7 +442,7 @@ media_storage_providers:
store_synchronous: True # do we want to wait that the file has been written before returning?
config:
bucket: matrix # the name of our bucket, we chose matrix earlier
region_name: garage # "garage" by default, edit according to your cluster config
region_name: garage # only "garage" is supported for the region field
endpoint_url: http://localhost:3900 # the path to the S3 endpoint
access_key_id: "GKxxx" # your Key ID
secret_access_key: "xxxx" # your Secret Key
@@ -450,7 +450,7 @@ media_storage_providers:
Note that uploaded media will also be stored locally and this behavior can not be deactivated, it is even required for
some operations like resizing images.
In fact, your local filesystem is considered as a cache but without any automated way to garbage collect it.
In fact, your local filesysem is considered as a cache but without any automated way to garbage collect it.
We can build our garbage collector with `s3_media_upload`, a tool provided with the module.
If you installed the module with the command provided before, you should be able to bring it in your path:
@@ -568,186 +568,13 @@ The module can then be configured with:
Other configuration options can be found in the
[configuration YAML file](https://github.com/processone/ejabberd-contrib/blob/master/mod_s3_upload/conf/mod_s3_upload.yml).
## Ente
Ente is an alternative for Google Photos and Apple Photos. It [can be selfhosted](https://help.ente.io/self-hosting/) and is working fine with Garage as of May 2024.
As a first step we need to create a bucket and a key for Ente:
```bash
garage bucket create ente
garage key create ente-key
# For the CORS setup to work, the key needs to be --owner as well, at least temporarily.
garage bucket allow ente --read --write --owner --key ente-key
```
We also need to setup some CORS rules to allow the Ente frontend to access the bucket:
```bash
export CORS='{"CORSRules":[{"AllowedHeaders":["*"],"AllowedMethods":["GET", "PUT", "POST", "DELETE"],"AllowedOrigins":["*"], "ExposeHeaders":["ETag"]}]}'
aws s3api put-bucket-cors --bucket ente --cors-configuration $CORS
```
Now we need to configure ente-server to use our bucket. This is explained [in the Ente S3 documentation](https://help.ente.io/self-hosting/guides/external-s3).
Prepare a configuration file for ente's backend as `museum.yaml`:
```yaml
credentials-file: /credentials.yaml
apps:
public-albums: https://albums.example.tld # If you want to use the share album feature
internal:
hardcoded-ott:
local-domain-suffix: "@example.com" # Your domain
local-domain-value: 123456 # Custom One-Time Password since we are not sending mail by default
key:
# WARNING -- You MUST CHANGE the values below
# Someone has made an image that can do it for you : https://github.com/EdyTheCow/ente-selfhost/blob/main/images/ente-server-tools/Dockerfile
# Simply build it yourself or run docker run --rm ghcr.io/edythecow/ente-server-tools go run tools/gen-random-keys/main.go
encryption: yvmG/RnzKrbCb9L3mgsmoxXr9H7i2Z4qlbT0mL3ln4w= # CHANGE THIS VALUE
hash: KXYiG07wC7GIgvCSdg+WmyWdXDAn6XKYJtp/wkEU7x573+byBRAYtpTP0wwvi8i/4l37uicX1dVTUzwH3sLZyw== # CHANGE THIS VALUE
jwt:
secret: i2DecQmfGreG6q1vBj5tCokhlN41gcfS2cjOs9Po-u8= # CHANGE THIS VALUE
```
The full configuration file can be found [here](https://github.com/ente-io/ente/blob/main/server/configurations/local.yaml)
Then prepare a credentials file as `credentials.yaml`
```yaml
db:
host: postgres
port: 5432
name: <ente_db_name>
user: <pguser>
password: <pgpass>
s3:
# Override the primary and secondary hot storage. The commented out values
# are the defaults.
#
hot_storage:
primary: b2-eu-cen
# secondary: wasabi-eu-central-2-v3
# If true, enable some workarounds to allow us to use a local minio instance
# for object storage.
#
# 1. Disable SSL.
# 2. Use "path" style S3 URLs (see `use_path_style_urls` below).
# 3. Directly download the file during replication instead of going via the
# Cloudflare worker.
# 4. Do not specify storage classes when uploading objects (since minio does
# not support them, specifically it doesn't support GLACIER).
are_local_buckets: true
# To use "path" style S3 URLs instead of DNS-based bucket access
# default to true if you set "are_local_buckets: true"
# use_path_style_urls: true
b2-eu-cen: # Don't change this key, it is hardcoded
key: <keyID>
secret: <keySecret>
endpoint: garage:3900 # publicly accessible endpoint of your garage instance
region: garage
bucket: <yourbucketName>
use_path_style: true
# you can specify secondary locations, names are hardcoded as well
# wasabi-eu-central-2-v3:
# scw-eu-fr-v3:
# and you can also specify a bucket to be used for embeddings, preview etc..
# default to the first bucket
# derived-storage: wasabi-eu-central-2-derived
```
Finally you can run it with Docker :
```bash
docker run -d --name ente-server --restart unless-stopped -v /path/to/museum.yaml:/museum.yaml -v /path/to/credentials.yaml:/credentials.yaml -p 8080:8080 ghcr.io/ente-io/ente-server
```
For more information on deployment you can check the [ente documentation](https://help.ente.io/self-hosting/)
## Pixelfed
[Pixelfed Technical Documentation > Configuration](https://docs.pixelfed.org/technical-documentation/env.html#filesystem)
## Pleroma
### Creating your bucket
This is the usual Garage setup:
```bash
garage key new --name pleroma-key
garage bucket create pleroma
garage bucket allow pleroma --read --write --owner --key pleroma-key
```
We also need to expose these buckets publicly to serve their content to users:
```bash
garage bucket website --allow pleroma
```
Note the Key ID and Secret Key.
### Configure Pleroma
Update your Pleroma configuration like that in `/etc/pleroma/config.exs`.
```
config :pleroma, Pleroma.Upload,
uploader: Pleroma.Uploaders.S3,
base_url: "https://pleroma.garage.example.tld"
config :ex_aws, :s3,
access_key_id: "GW...",
secret_access_key: "XXX",
region: "garage",
host: "api.garage.example.tld"
```
And restart Pleroma.
You can found more information in [Pleroma Documentation > Pleroma.Uploaders.S3](https://docs-develop.pleroma.social/backend/configuration/cheatsheet/#pleromauploaderss3)
### Migrating your data
Pleroma have an internal migration tool that can encounter some fatal error
```
** (EXIT from #PID<0.98.0>) an exception was raised:
** (File.Error) could not stream "/var/lib/pleroma/uploads/09/f8": illegal operation on a directory
(elixir 1.17.3) lib/file/stream.ex:100: anonymous fn/3 in Enumerable.File.Stream.reduce/3
(elixir 1.17.3) lib/stream.ex:1675: anonymous fn/5 in Stream.resource/3
(elixir 1.17.3) lib/stream.ex:1891: Enumerable.Stream.do_each/4
(elixir 1.17.3) lib/task/supervised.ex:370: Task.Supervised.stream_reduce/7
(elixir 1.17.3) lib/enum.ex:4423: Enum.map/2
(ex_aws_s3 2.5.8) lib/ex_aws/s3/upload.ex:141: ExAws.Operation.ExAws.S3.Upload.perform/2
(pleroma 2.10.0) lib/pleroma/uploaders/s3.ex:60: Pleroma.Uploaders.S3.put_file/1
(pleroma 2.10.0) lib/pleroma/uploaders/uploader.ex:49: Pleroma.Uploaders.Uploader.put_file/2
```
So, use [your best tool](https://garagehq.deuxfleurs.fr/documentation/connect/cli/) to sync `/var/lib/pleroma/uploads/` in your S3.
Then, to avoid some non existent problem (just in case of), run this command
```bash
while true
do
rm -vr $(./bin/pleroma_ctl uploads migrate_local S3 2>&1 | grep "could not stream" | awk -F '"' '{print $2}')
sleep 5
done
```
If you have many files, stop this command sometime and the command bellow (interactive) to delete local
file after upload. Then restart the loop.
```bash
./bin/pleroma_ctl uploads migrate_local S3 --delete
```
And *voilà*
[Pleroma Documentation > Pleroma.Uploaders.S3](https://docs-develop.pleroma.social/backend/configuration/cheatsheet/#pleromauploaderss3)
## Lemmy
-56
View File
@@ -161,59 +161,3 @@ kopia repository validate-provider
You can then run all the standard kopia commands: `kopia snapshot create`, `kopia mount`...
Everything should work out-of-the-box.
## Plakar
Create your key and bucket on Garage server:
```bash
garage key create my-plakar-key
garage bucket create plakar-backups
garage bucket allow plakar-backups --read --write --key my-plakar-key
```
On Plakar server, add your Garage as a storage location:
```bash
plakar store add garageS3 s3://my-garage.tld/plakar-backups \
region=garage # Or as you've specified in garage.toml \
access_key=<Key ID from "garage key info my-plakar-key"> \
secret_access_key=<Secret key from "garage key info my-plakar-key">
```
Then create the repository.
```bash
plakar at @garageS3 create -plaintext # Unencrypted
# or
plakar at @garageS3 create #encrypted
```
If you encrypt your backups (Plakar default), you will need to define a strong passphrase. Do not forget to save your password safely. It will be needed to decrypt your backups.
After the repository has been created, check that everything works as expected (that might give an empty result as no file has been added yet, but no error message):
```bash
plakar at @garageS3 check
```
Now that everything is configure, you can use Garage as your backups storage. For instance sync it with a local backup storage:
```bash
$ plakar at ~/backups sync to @garageS3
```
Or list the S3 storage content:
```bash
$ plakar at @garageS3 ls
```
More information in Plakar documentation: https://www.plakar.io/docs/main/quickstart/
## Synology HyperBackup
HyperBackup can be configured to upload backups to garage using a custom S3 destination. However, the HyperBackup client hardcodes the `us-east-1` region that is a critical input to the v4 signature process. If garage is not set to `us-east-1`, HyperBackup will recognize available buckets, but fail during the final setup stage.
In garage.toml:
```toml
[s3_api]
s3_region = "us-east-1"
```
+4 -12
View File
@@ -41,7 +41,7 @@ Some commands:
# list buckets
mc ls garage/
# list objects in a bucket
# list objets in a bucket
mc ls garage/my_files
# copy from your filesystem to garage
@@ -149,15 +149,6 @@ rclone help
This will tremendously accelerate operations such as `rclone sync` or `rclone ncdu` by reducing the number
of ListObjects calls that are made.
**Garage behind Cloudflare proxy:** when running Garage behind Cloudflare proxy, you might see `Response: error 403 Forbidden, Forbidden: Invalid signature` error in your garage logs or `AccessDenied: Forbidden: Invalid signature` error in rclone logs. Try adding `--s3-sign-accept-encoding=false` flag to your rclone command and see if the issue is resolved.
```bash
# this throws an error
rclone lsd garage:
# this should work
rclone lsd --s3-sign-accept-encoding=false garage:
```
## `s3cmd`
@@ -218,7 +209,7 @@ Within Cyberduck, a
available within the `Preferences -> Profiles` section. This can enabled and
then connections to Garage may be configured.
### Instructions for the CLI
### Instuctions for the CLI
To configure duck (Cyberduck's CLI tool), start by creating its folder hierarchy:
@@ -268,7 +259,7 @@ duck --delete garage:/my-files/an-object.txt
## WinSCP (libs3) {#winscp}
*You can find instructions on how to use the GUI in french [in our wiki](https://guide.deuxfleurs.fr/prise_en_main/winscp/).*
*You can find instructions on how to use the GUI in french [in our wiki](https://wiki.deuxfleurs.fr/fr/Guide/Garage/WinSCP).*
How to use `winscp.com`, the CLI interface of WinSCP:
@@ -323,3 +314,4 @@ ls
```
And through the web interface at http://[::1]:8080/web/client
+4 -2
View File
@@ -17,7 +17,7 @@ Garage can also help you serve this content.
## Gitea
You can use Garage with Gitea to store your [git LFS](https://git-lfs.github.com/) data, your users' avatar, and their attachments.
You can use Garage with Gitea to store your [git LFS](https://git-lfs.github.com/) data, your users' avatar, and their attachements.
You can configure a different target for each data type (check `[lfs]` and `[attachment]` sections of the Gitea documentation) and you can provide a default one through the `[storage]` section.
Let's start by creating a key and a bucket (your key id and secret will be needed later, keep them somewhere):
@@ -201,9 +201,11 @@ on the binary cache, the client will download the result from the cache instead
### Channels
Channels additionally serve Nix definitions, ie. a `.nix` file referencing
Channels additionnaly serve Nix definitions, ie. a `.nix` file referencing
all the derivations you want to serve.
## Gitlab
*External link:* [Gitlab Documentation > Object storage](https://docs.gitlab.com/ee/administration/object_storage.html)
+12 -24
View File
@@ -8,18 +8,18 @@ have published Ansible roles. We list them and compare them below.
## Comparison of Ansible roles
| Feature | [ansible-role-garage](#zorun-ansible-role-garage) | [garage-docker-ansible-deploy](#moan0s-garage-docker-ansible-deploy) | [eddster2309 ansible-role-garage](#eddster2309-ansible-role-garage) |
|------------------------------------|---------------------------------------------|---------------------------------------------------------------|---------------------------------|
| **Runtime** | Systemd | Docker | Systemd |
| **Target OS** | Any Linux | Any Linux | Any Linux |
| **Architecture** | amd64, arm64, i686 | amd64, arm64 | arm64, arm, 386, amd64 |
| **Additional software** | None | Traefik | Nginx and Keepalived (optional) |
| **Automatic node connection** | ❌ | ✅ | ✅ |
| **Layout management** | ❌ | ✅ | ✅ |
| **Manage buckets & keys** | ❌ | ✅ (basic) | ✅ |
| **Allow custom Garage config** | ✅ | ❌ | ❌ |
| **Facilitate Garage upgrades** | ✅ | ❌ | ✅ |
| **Multiple instances on one host** | ✅ | ✅ | ❌ |
| 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
@@ -49,15 +49,3 @@ structured DNS names, etc).
As a result, this role makes it easier to start with Garage on Ansible,
but is less flexible.
## eddster2309/ansible-role-garage
[Source code](https://github.com/eddster2309/ansible-role-garage), [Ansible galaxy](https://galaxy.ansible.com/ui/standalone/roles/eddster2309/garage/)
This role is a opinionated but customisable role using the official Garage
static binaries and only requires Systemd. As such it should work on any
Linux based host. It includes all the nesscary configuration to
automatically setup a clustered Garage deployment. Most Garage
configuration options are exposed through Ansible variables so while you
can't provide a custom config you can get very close. It can optionally
installed a HA nginx deployment with Keepalived.
+4 -15
View File
@@ -15,10 +15,9 @@ Alpine Linux repositories (available since v3.17):
apk add garage
```
The default configuration file is installed to `/etc/garage/garage.toml`. You can run
Garage using: `rc-service garage start`.
If you don't specify `rpc_secret`, it will be automatically replaced with a random string on the first start.
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
@@ -27,11 +26,7 @@ it's stable).
## Arch Linux
Garage is available in the official repositories under [extra](https://archlinux.org/packages/extra/x86_64/garage).
```bash
pacman -S garage
```
Garage is available in the [AUR](https://aur.archlinux.org/packages/garage).
## FreeBSD
@@ -44,9 +39,3 @@ pkg install garage
```bash
nix-shell -p garage
```
## conda-forge
```bash
pixi global install garage
```
+15 -38
View File
@@ -33,7 +33,7 @@ by adding encryption at different levels.
We would be very curious to know your needs and thougs about ideas such as
encryption practices and things like key management, as we want Garage to be a
serious base platform for the development of secure, encrypted applications.
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.
@@ -53,43 +53,20 @@ and that's also why your nodes have super long identifiers.
Adding TLS support built into Garage is not currently planned.
## Garage stores data in plain text on the filesystem or encrypted using customer keys (SSE-C)
## Garage stores data in plain text on the filesystem
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.
Garage does not handle data encryption at rest by itself, and instead delegates
to the user to add encryption, either at the storage layer (LUKS, etc) or on
the client side (or both). There are no current plans to add data encryption
directly in Garage.
If you are developing your own client software that makes use of S3 storage,
we recommend implementing data encryption directly on the client side and never
transmitting plaintext data to Garage. This makes it easy to use an external
untrusted storage provider if necessary.
Garage does support [SSE-C
encryption](https://docs.aws.amazon.com/AmazonS3/latest/userguide/ServerSideEncryptionCustomerKeys.html),
an encryption mode of Amazon S3 where data is encrypted at rest using
encryption keys given by the client. The encryption keys are passed to the
server in a header in each request, to encrypt or decrypt data at the moment of
reading or writing. The server discards the key as soon as it has finished
using it for the request. This mode allows the data to be encrypted at rest by
Garage itself, but it requires support in the client software. It is also not
adapted to a model where the server is not trusted or assumed to be
compromised, as the server can easily know the encryption keys. Note however
that when using SSE-C encryption, the only Garage node that knows the
encryption key passed in a given request is the node to which the request is
directed (which can be a gateway node), so it is easy to have untrusted nodes
in the cluster as long as S3 API requests containing SSE-C encryption keys are
not directed to them.
Implementing automatic data encryption directly in Garage without client-side
management of keys (something like
[SSE-S3](https://docs.aws.amazon.com/AmazonS3/latest/userguide/UsingServerSideEncryption.html))
could make things simpler for end users that don't want to setup LUKS, but also
raises many more questions, especially around key management: for encryption of
data, where could Garage get the encryption keys from? If we encrypt data but
keep the keys in a plaintext file next to them, it's useless. We probably don't
want to have to manage secrets in Garage as it would be very hard to do in a
secure way. At the time of speaking, there are no plans to implement this in
Garage.
Implementing data encryption directly in Garage might make things simpler for
end users, but also raises many more questions, especially around key
management: for encryption of data, where could Garage get the encryption keys
from ? If we encrypt data but keep the keys in a plaintext file next to them,
it's useless. We probably don't want to have to manage secrets in garage as it
would be very hard to do in a secure way. Maybe integrate with an external
system such as Hashicorp Vault?
# Adding data encryption using external tools
@@ -108,14 +85,14 @@ Protects against the following threats:
- Stolen HDD
Crucially, does not protect against malicious sysadmins or remote attackers that
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 against the following threats:
Protects againt the following threats:
- A honest-but-curious administrator
- A malicious administrator that tries to corrupt your data
+1 -1
View File
@@ -9,7 +9,7 @@ There are three methods to expose buckets as website:
1. using the PutBucketWebsite S3 API call, which is allowed for access keys that have the owner permission bit set
2. from the Garage CLI, by an administrator of the cluster
2. from the Garage CLI, by an adminstrator of the cluster
3. using the Garage administration API
+7 -11
View File
@@ -20,12 +20,12 @@ sudo apt-get update
sudo apt-get install build-essential
```
## Building from source from the Forgejo repository
## Building from source from the Gitea repository
The primary location for Garage's source code is the
[Forgejo 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 development of the next version.
for the developpement of the next version.
Clone the repository and enter it as follows:
@@ -41,7 +41,7 @@ git tag # List available tags
git checkout v0.8.0 # Change v0.8.0 with the version you wish to build
```
Otherwise you will be building a development build from the `main` branch
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.
@@ -85,14 +85,10 @@ 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 |
| `consul-discovery` | optional | Enable automatic registration and discovery<br>of cluster nodes through the Consul API |
| `fjall` | experimental | Enable using Fjall to store Garage's metadata |
| `journald` | optional | Enable logging to systemd-journald with<br>`GARAGE_LOG_TO_JOURNALD=true` environment variable set |
| `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 |
| `lmdb` | *by default* | Enable using LMDB to store Garage's metadata |
| `metrics` | *by default* | Enable collection of metrics in Prometheus format on the admin API |
| `sqlite` | *by default* | Enable using Sqlite3 to store Garage's metadata |
| `syslog` | optional | Enable logging to Syslog with<br>`GARAGE_LOG_TO_SYSLOG=true` environment variable set |
| `system-libs` | optional | Use system version of sqlite3, zstd, lmdb and libsodium<br>if available (exclusive with `bundled-libs`, build using<br>`cargo build --no-default-features --features system-libs`) |
| `telemetry-otlp` | optional | Enable collection of execution traces using OpenTelemetry |
| `lmdb` | *by default* | Enable using LMDB to store Garage's metadata |
| `sqlite` | optional | Enable using Sqlite3 to store Garage's metadata |
+3 -69
View File
@@ -11,7 +11,7 @@ Firstly clone the repository:
```bash
git clone https://git.deuxfleurs.fr/Deuxfleurs/garage
cd garage/script/helm
cd garage/scripts/helm
```
Deploy with default options:
@@ -26,13 +26,6 @@ Or deploy with custom values:
helm install --create-namespace --namespace garage garage ./garage -f values.override.yaml
```
If you want to manage the CustomResourceDefinition used by garage for its `kubernetes_discovery` outside of the helm chart, add `garage.kubernetesSkipCrd: true` to your custom values and use the kustomization before deploying the helm chart:
```bash
kubectl apply -k ../k8s/crd
helm install --create-namespace --namespace garage garage ./garage -f values.override.yaml
```
After deploying, cluster layout must be configured manually as described in [Creating a cluster layout](@/documentation/quick-start/_index.md#creating-a-cluster-layout). Use the following command to access garage CLI:
```bash
@@ -47,12 +40,12 @@ All possible configuration values can be found with:
helm show values ./garage
```
This is an example `values.override.yaml` for deploying in a microk8s cluster with a https s3 api ingress route:
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
replicationFactor: 2
replicationMode: "2"
# Start 4 instances (StatefulSets) of garage
deployment:
@@ -93,62 +86,3 @@ helm delete --namespace garage garage
```
Note that this will leave behind custom CRD `garagenodes.deuxfleurs.fr`, which must be removed manually if desired.
## Increase PVC size on running Garage instances
Since the Garage Helm chart creates the data and meta PVC based on `StatefulSet` templates, increasing the PVC size can be a bit tricky.
### Confirm the `StorageClass` used for Garage supports volume expansion
Confirm the storage class used for garage.
```bash
kubectl -n garage get pvc
NAME STATUS VOLUME CAPACITY ACCESS MODES STORAGECLASS VOLUMEATTRIBUTESCLASS AGE
data-garage-0 Bound pvc-080360c9-8ce3-4acf-8579-1701e57b7f3f 30Gi RWO longhorn-local <unset> 77d
data-garage-1 Bound pvc-ab8ba697-6030-4fc7-ab3c-0d6df9e3dbc0 30Gi RWO longhorn-local <unset> 5d8h
data-garage-2 Bound pvc-3ab37551-0231-4604-986d-136d0fd950ec 30Gi RWO longhorn-local <unset> 5d5h
meta-garage-0 Bound pvc-3b457302-3023-4169-846e-c928c5f2ea65 3Gi RWO longhorn-local <unset> 77d
meta-garage-1 Bound pvc-49ace2b9-5c85-42df-9247-51c4cf64b460 3Gi RWO longhorn-local <unset> 5d8h
meta-garage-2 Bound pvc-99e2e50f-42b4-4128-ae2f-b52629259723 3Gi RWO longhorn-local <unset> 5d5h
```
In this case, the storage class is `longhorn-local`. Now, check if `ALLOWVOLUMEEXPANSION` is true for the used `StorageClass`.
```bash
kubectl get storageclasses.storage.k8s.io longhorn-local
NAME PROVISIONER RECLAIMPOLICY VOLUMEBINDINGMODE ALLOWVOLUMEEXPANSION AGE
longhorn-local driver.longhorn.io Delete Immediate true 103d
```
If your `StorageClass` does not support volume expansion, double check if you can enable it. Otherwise, your only real option is to spin up a new Garage cluster with increased size and migrate all data over.
If your `StorageClass` supports expansion, you are free to continue.
### Increase the size of the PVCs
Increase the size of all PVCs to your desired size.
```bash
kubectl -n garage edit pvc data-garage-0
kubectl -n garage edit pvc data-garage-1
kubectl -n garage edit pvc data-garage-2
kubectl -n garage edit pvc meta-garage-0
kubectl -n garage edit pvc meta-garage-1
kubectl -n garage edit pvc meta-garage-2
```
### Increase the size of the `StatefulSet` PVC template
This is an optional step, but if not done, future instances of Garage will be created with the original size from the template.
```bash
kubectl -n garage delete sts --cascade=orphan garage
statefulset.apps "garage" deleted
```
This will remove the Garage `StatefulSet` but leave the pods running. It may seem destructive but needs to be done this way since edits to the size of PVC templates are prohibited.
### Redeploy the `StatefulSet`
Now the size of future PVCs can be increased, and the Garage Helm chart can be upgraded. The new `StatefulSet` should take ownership of the orphaned pods again.
+22 -37
View File
@@ -27,7 +27,7 @@ To run a real-world deployment, make sure the following conditions are met:
[Yggdrasil](https://yggdrasil-network.github.io/) are approaches to consider
in addition to building out your own VPN tunneling.
- This guide will assume you are using Docker containers to deploy Garage on each node.
- This guide will assume you are using Docker containers to deploy Garage on each node.
Garage can also be run independently, for instance as a [Systemd service](@/documentation/cookbook/systemd.md).
You can also use an orchestrator such as Nomad or Kubernetes to automatically manage
Docker containers on a fleet of nodes.
@@ -53,9 +53,9 @@ 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"`).
- If you have fast dedicated networking between all your nodes, and are planing to store
very large files, bump the `block_size` configuration parameter to 10 MB
(`block_size = 10485760`).
- 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.
@@ -68,42 +68,30 @@ to store 2 TB of data in total.
EXT4 is not recommended as it has more strict limitations on the number of inodes,
which might cause issues with Garage when large numbers of objects are stored.
- Servers with multiple HDDs are supported natively by Garage without resorting
to RAID, see [our dedicated documentation page](@/documentation/operations/multi-hdd.md).
- If you only have an HDD and no SSD, it's fine to put your metadata alongside the data
on the same drive. Having lots of RAM for your kernel to cache the metadata will
help a lot with performance. The default LMDB database engine is the most tested
and has good performance.
- 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.
verification on its own. If you are afraid of bitrot/data corruption,
put your metadata directory on a ZFS or BTRFS partition. Otherwise, just use regular
EXT4 or XFS.
- 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.
- Servers with multiple HDDs are supported natively by Garage without resorting
to RAID, see [our dedicated documentation page](@/documentation/operations/multi-hdd.md).
## Get a Docker image
Our docker image is currently named `dxflrs/garage` and is stored on the [Docker Hub](https://hub.docker.com/r/dxflrs/garage/tags?page=1&ordering=last_updated).
We encourage you to use a fixed tag (eg. `v2.2.0`) and not the `latest` tag.
For this example, we will use the latest published version at the time of the writing which is `v2.2.0` but it's up to you
We encourage you to use a fixed tag (eg. `v0.9.3`) and not the `latest` tag.
For this example, we will use the latest published version at the time of the writing which is `v0.9.3` but it's up to you
to check [the most recent versions on the Docker Hub](https://hub.docker.com/r/dxflrs/garage/tags?page=1&ordering=last_updated).
For example:
```
sudo docker pull dxflrs/garage:v2.2.0
sudo docker pull dxflrs/garage:v0.9.3
```
## Deploying and configuring Garage
@@ -126,7 +114,6 @@ A valid `/etc/garage.toml` for our cluster would look as follows:
metadata_dir = "/var/lib/garage/meta"
data_dir = "/var/lib/garage/data"
db_engine = "lmdb"
metadata_auto_snapshot_interval = "6h"
replication_factor = 3
@@ -152,8 +139,6 @@ 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`.
@@ -171,7 +156,7 @@ docker run \
-v /etc/garage.toml:/etc/garage.toml \
-v /var/lib/garage/meta:/var/lib/garage/meta \
-v /var/lib/garage/data:/var/lib/garage/data \
dxflrs/garage:v2.2.0
dxflrs/garage:v0.9.3
```
With this command line, Garage should be started automatically at each boot.
@@ -185,7 +170,7 @@ If you want to use `docker-compose`, you may use the following `docker-compose.y
version: "3"
services:
garage:
image: dxflrs/garage:v2.2.0
image: dxflrs/garage:v0.9.3
network_mode: "host"
restart: unless-stopped
volumes:
@@ -201,7 +186,7 @@ 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
## Controling the daemon
The `garage` binary has two purposes:
- it acts as a daemon when launched with `garage server`
@@ -259,7 +244,7 @@ You can then instruct nodes to connect to one another as follows:
Venus$ garage node connect 563e1ac825ee3323aa441e72c26d1030d6d4414aeb3dd25287c531e7fc2bc95d@[fc00:1::1]:3901
```
You don't need to instruct all node to connect to all other nodes:
You don't nead 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:
@@ -342,8 +327,8 @@ Given the information above, we will configure our cluster as follow:
```bash
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
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.
+3 -3
View File
@@ -7,7 +7,7 @@ The main reason to add a reverse proxy in front of Garage is to provide TLS to y
In production you will likely need your certificates signed by a certificate authority.
The most automated way is to use a provider supporting the [ACME protocol](https://datatracker.ietf.org/doc/html/rfc8555)
such as [Let's Encrypt](https://letsencrypt.org/) or [ZeroSSL](https://zerossl.com/).
such as [Let's Encrypt](https://letsencrypt.org/), [ZeroSSL](https://zerossl.com/) or [Buypass Go SSL](https://www.buypass.com/ssl/products/acme).
If you are only testing Garage, you can generate a self-signed certificate to follow the documentation:
@@ -97,7 +97,7 @@ server {
location / {
proxy_pass http://s3_backend;
proxy_set_header X-Forwarded-For $proxy_add_x_forwarded_for;
proxy_set_header Host $http_host;
proxy_set_header Host $host;
# Disable buffering to a temporary file.
proxy_max_temp_file_size 0;
}
@@ -272,7 +272,7 @@ Add the following configuration section [to compress response](https://doc.traef
### Add caching response
Traefik's caching middleware is only available on [enterprise version](https://doc.traefik.io/traefik-enterprise/middlewares/http-cache/), however the freely-available [Souin plugin](https://github.com/darkweak/souin#tr%C3%A6fik-container) can also do the job. (section to be completed)
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
+1 -2
View File
@@ -28,7 +28,6 @@ StateDirectory=garage
DynamicUser=true
ProtectHome=true
NoNewPrivileges=true
LimitNOFILE=42000
[Install]
WantedBy=multi-user.target
@@ -38,7 +37,7 @@ WantedBy=multi-user.target
id is dynamically allocated by systemd (set with `DynamicUser=true`). It cannot
access (read or write) home folders (`/home`, `/root` and `/run/user`), the
rest of the filesystem can only be read but not written, only the path seen as
`/var/lib/garage` is writable as seen by the service. Additionally, the process
`/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
+3 -1
View File
@@ -10,7 +10,7 @@ perspective. It will allow you to understand if Garage is a good fit for
you, how to better use it, how to contribute to it, what can Garage could
and could not do, etc.
- **[Goals and use cases](@/documentation/design/goals.md):** This page explains why Garage was conceived and what practical use cases it targets.
- **[Goals and use cases](@/documentation/design/goals.md):** This page explains why Garage was concieved and what practical use cases it targets.
- **[Related work](@/documentation/design/related-work.md):** This pages presents the theoretical background on which Garage is built, and describes other software storage solutions and why they didn't work for us.
@@ -31,3 +31,5 @@ We love to talk and hear about Garage, that's why we keep a log here:
- [(en, 2021-04-28) Distributed object storage is centralised](https://git.deuxfleurs.fr/Deuxfleurs/garage/src/commit/b1f60579a13d3c5eba7f74b1775c84639ea9b51a/doc/talks/2021-04-28_spirals-team/talk.pdf)
- [(fr, 2020-12-02) Garage : jouer dans la cour des grands quand on est un hébergeur associatif](https://git.deuxfleurs.fr/Deuxfleurs/garage/src/commit/b1f60579a13d3c5eba7f74b1775c84639ea9b51a/doc/talks/2020-12-02_wide-team/talk.pdf)
+5 -5
View File
@@ -15,14 +15,14 @@ The more a user request will require intra-cluster requests to complete, the mor
This is especially true for sequential requests: requests that must wait the result of another request to be sent.
We designed Garage without consensus algorithms (eg. Paxos or Raft) to minimize the number of sequential and parallel requests.
This series of benchmarks quantifies the impact of this design choice.
This serie of benchmarks quantifies the impact of this design choice.
### On a simple simulated network
We start with a controlled environment, all the instances are running on the same (powerful enough) machine.
To control the network latency, we simulate the network with [mknet](https://git.deuxfleurs.fr/trinity-1686a/mknet) (a tool we developed, based on `tc` and the linux network stack).
To measure S3 endpoints latency, we use our own tool [s3lat](https://git.deuxfleurs.fr/quentin/s3lat/) to observe only the intra-cluster latency and not some contention on the nodes (CPU, RAM, disk I/O, network bandwidth, etc.).
To control the network latency, we simulate the network with [mknet](https://git.deuxfleurs.fr/trinity-1686a/mknet) (a tool we developped, based on `tc` and the linux network stack).
To mesure S3 endpoints latency, we use our own tool [s3lat](https://git.deuxfleurs.fr/quentin/s3lat/) to observe only the intra-cluster latency and not some contention on the nodes (CPU, RAM, disk I/O, network bandwidth, etc.).
Compared to other benchmark tools, S3Lat sends only one (small) request at the same time and measures its latency.
We selected 5 standard endpoints that are often in the critical path: ListBuckets, ListObjects, GetObject, PutObject and RemoveObject.
@@ -32,7 +32,7 @@ In this first benchmark, we consider 5 instances that are located in a different
Compared to garage, minio latency drastically increases on 3 endpoints: GetObject, PutObject, RemoveObject.
We suppose that these requests on minio make transactions over Raft, involving 4 sequential requests: 1) sending the message to the leader, 2) having the leader dispatch it to the other nodes, 3) waiting for the confirmation of followers and finally 4) committing it. With our current configuration, one Raft transaction will take around 400 ms. GetObject seems to correlate to 1 transaction while PutObject and RemoveObject seems to correlate to 2 or 3. Reviewing minio code would be required to confirm this hypothesis.
We suppose that these requests on minio make transactions over Raft, involving 4 sequential requests: 1) sending the message to the leader, 2) having the leader dispatch it to the other nodes, 3) waiting for the confirmation of followers and finally 4) commiting it. With our current configuration, one Raft transaction will take around 400 ms. GetObject seems to correlate to 1 transaction while PutObject and RemoveObject seems to correlate to 2 or 3. Reviewing minio code would be required to confirm this hypothesis.
Conversely, garage uses an architecture similar to DynamoDB and never require global cluster coordination to answer a request.
Instead, garage can always contact the right node in charge of the requested data, and can answer in as low as one request in the case of GetObject and PutObject. We also observed that Garage latency, while often lower to minio, is more dispersed: garage is still in beta and has not received any performance optimization yet.
@@ -50,7 +50,7 @@ We plot a similar graph as before:
This new graph is very similar to the one before, neither minio or garage seems to benefit from this new topology, but they also do not suffer from it.
Considering garage, this is expected: nodes in the same DC are put in the same zone, and then data are spread on different zones for data resiliency and availability.
Considering garage, this is expected: nodes in the same DC are put in the same zone, and then data are spread on different zones for data resiliency and availaibility.
Then, in the default mode, requesting data requires to query at least 2 zones to be sure that we have the most up to date information.
These requests will involve at least one inter-DC communication.
In other words, we prioritize data availability and synchronization over raw performances.
-19
View File
@@ -50,22 +50,3 @@ locations. They use Garage themselves for the following tasks:
The Deuxfleurs Garage cluster is a multi-site cluster currently composed of
9 nodes in 3 physical locations.
### Triplebit
[Triplebit](https://www.triplebit.org) is a non-profit hosting provider and
ISP focused on improving access to privacy-related services. They use
Garage themselves for the following tasks:
- Hosting of their homepage, [privacyguides.org](https://www.privacyguides.org/), and various other static sites
- As a PowerDNS authoritative zone backend through [Lightning Stream](https://doc.powerdns.com/lightningstream/latest/index.html) and [LMDB](https://doc.powerdns.com/authoritative/backends/lmdb.html)
- As a Mastodon media storage backend for [mstdn.party](https://mstdn.party/) and [mstdn.plus](https://mstdn.plus/)
- As a PeerTube storage backend for [neat.tube](https://neat.tube/)
- As a [Matrix media backend](https://github.com/matrix-org/synapse-s3-storage-provider)
Triplebit's Garage cluster is a multi-site cluster currently composed of
15 storage nodes in 3 physical locations.
+2 -1
View File
@@ -94,7 +94,7 @@ delete a tombstone, the following condition has to be met:
- All nodes responsible for storing this entry are aware of the existence of
the tombstone, i.e. they cannot hold another version of the entry that is
superseded by the tombstone. This ensures that deleting the tombstone is
superseeded by the tombstone. This ensures that deleting the tombstone is
safe and that no deleted value will come back in the system.
Garage uses atomic database operations (such as compare-and-swap and
@@ -141,3 +141,4 @@ rebalance of data, this would have led to the disk utilization to explode
during the rebalancing, only to shrink again after 24 hours. The 10-minute
delay is a compromise that gives good security while not having this problem of
disk space explosion on rebalance.
+3 -3
View File
@@ -37,7 +37,7 @@ However, Amazon S3 source code is not open but alternatives were proposed.
We identified Minio, Pithos, Swift and Ceph.
Minio/Ceph enforces a total order, so properties similar to a (relaxed) filesystem.
Swift and Pithos are probably the most similar to AWS S3 with their consistent hashing ring.
However Pithos is not maintained anymore. More precisely the company that published Pithos version 1 has developed a second version 2 but has not open sourced it.
However Pithos is not maintained anymore. More precisely the company that published Pithos version 1 has developped a second version 2 but has not open sourced it.
Some tests conducted by the [ACIDES project](https://acides.org/) have shown that Openstack Swift consumes way more resources (CPU+RAM) that we can afford. Furthermore, people developing Swift have not designed their software for geo-distribution.
There were many attempts in research too. I am only thinking to [LBFS](https://pdos.csail.mit.edu/papers/lbfs:sosp01/lbfs.pdf) that was used as a basis for Seafile. But none of them have been effectively implemented yet.
@@ -63,11 +63,11 @@ Due to its industry oriented design, Ceph is also far from being *Simple* to ope
In a certain way, Ceph and MinIO are closer together than they are from Garage or OpenStack Swift.
**[Pithos](https://github.com/exoscale/pithos):**
Pithos has been abandoned and should probably not used yet, in the following we explain why we did not pick their design.
Pithos has been abandonned and should probably not used yet, in the following we explain why we did not pick their design.
Pithos was relying as a S3 proxy in front of Cassandra (and was working with Scylla DB too).
From its designers' mouth, storing data in Cassandra has shown its limitations justifying the project abandonment.
They built a closed-source version 2 that does not store blobs in the database (only metadata) but did not communicate further on it.
We considered 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.
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.
**[Riak CS](https://docs.riak.com/riak/cs/2.1.1/index.html):**
*Not written yet*
+3 -3
View File
@@ -36,7 +36,7 @@ sudo killall nix-daemon
Now you can enter our nix-shell, all the required packages will be downloaded but they will not pollute your environment outside of the shell:
```bash
nix-shell -A devShell
nix-shell
```
You can use the traditional Rust development workflow:
@@ -65,8 +65,8 @@ nix-build -j $(nproc) --max-jobs auto
```
Our build has multiple parameters you might want to set:
- `release` to build with release optimisations instead of debug
- `target` allows for cross compilation
- `release` build with release optimisations instead of debug
- `target allows` for cross compilation
- `compileMode` can be set to test or bench to build a unit test runner
- `git_version` to inject the hash to display when running `garage stats`
+5 -3
View File
@@ -23,7 +23,7 @@ This logic is defined in `nix/build_index.nix`.
For each commit, we first pass the code to a formatter (rustfmt) and a linter (clippy).
Then we try to build it in debug mode and run both unit tests and our integration tests.
Additionally, when releasing, our integration tests are run on the release build for amd64 and i686.
Additionnaly, when releasing, our integration tests are run on the release build for amd64 and i686.
## Generated Artifacts
@@ -32,7 +32,7 @@ We generate the following binary artifacts for now:
- **os**: linux
- **format**: static binary, docker container
Additionally we also build two web pages and one JSON document:
Additionnaly we also build two web pages and one JSON document:
- the documentation (this website)
- [the release page](https://garagehq.deuxfleurs.fr/_releases.html)
- [the release list in JSON format](https://garagehq.deuxfleurs.fr/_releases.json)
@@ -67,7 +67,7 @@ nix copy --to 's3://nix?endpoint=garage.deuxfleurs.fr&region=garage&secret-key=/
The previous command will only send the built package and not its dependencies.
In the case of our CI pipeline, we want to cache all intermediate build steps
as well. This can be done using this quite involved command (here as an example
for the `pkgs.amd64.release` package):
for the `pkgs.amd64.relase` package):
```bash
nix copy -j8 \
@@ -174,3 +174,5 @@ drone sign --save Deuxfleurs/garage
```
Looking at the file, you will see that most of the commands are `nix-shell` and `nix-build` commands with various parameters.
+3 -24
View File
@@ -19,7 +19,7 @@ connecting to. To run on all nodes, add the `-a` flag as follows:
# Data block operations
## Data store scrub {#scrub}
## Data store scrub
Scrubbing the data store means examining each individual data block to check that
their content is correct, by verifying their hash. Any block found to be corrupted
@@ -42,7 +42,7 @@ 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 worker set scrub-tranquility`.
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.
@@ -104,24 +104,6 @@ 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,
@@ -141,7 +123,4 @@ blocks may still be held by Garage. If you suspect that such corruption has occu
in your cluster, you can run one of the following repair procedures:
- `garage repair versions`: checks that all versions belong to a non-deleted object, and purges any orphan version
- `garage repair block-refs`: checks that all block references belong to a non-deleted object version, and purges any orphan block reference (this will then allow the blocks to be garbage-collected)
- `garage repair block-rc`: checks that the reference counters for blocks are in sync with the actual number of non-deleted entries in the block reference table
- `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)
+2 -2
View File
@@ -242,7 +242,7 @@ dc3 Tags Partitions Capacity Usable capacity
TOTAL 256 (256 unique) 2.0 GB 1000.0 MB (50.0%)
```
As we can see, the node that was moved to `dc3` (node4) is only used at 25% (approximately),
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:
@@ -260,7 +260,7 @@ This can be explained by the following:
data can be removed to be moved to node1.
- Garage will move data in equal proportions from all possible sources, in this
case it means that it will transfer 25% of the entire data set from node3 to
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%
+3 -3
View File
@@ -21,14 +21,14 @@ data_dir = [
```
Garage will automatically balance all blocks stored by the node
among the different specified directories, proportionally to the
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 proportionally to the specified capacities,
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).
@@ -40,7 +40,7 @@ First of all, Garage divides the set of all possible block hashes
in a fixed number of slices (currently 1024), and assigns
to each slice a primary storage location among the specified data directories.
The number of slices having their primary location in each data directory
is proportional to the capacity specified in the config file.
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.
+2 -59
View File
@@ -5,7 +5,7 @@ weight = 40
Garage is meant to work on old, second-hand hardware.
In particular, this makes it likely that some of your drives will fail, and some manual intervention will be needed.
Fear not! Garage is fully equipped to handle drive failures, in most common cases.
Fear not! For 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
@@ -108,60 +108,3 @@ garage layout apply # once satisfied, apply the changes
Garage will then start synchronizing all required data on the new node.
This process can be monitored using the `garage stats -a` command.
## Replacement scenario 3: corrupted metadata {#corrupted_meta}
In some cases, your metadata DB file might become corrupted, for instance if
your node suffered a power outage and did not shut down properly. In this case,
you can recover without having to change the node ID and rebuilding a cluster
layout. This means that data blocks will not need to be shuffled around, you
must simply find a way to repair the metadata file. The best way is generally
to discard the corrupted file and recover it from another source.
First of all, start by locating the database file in your metadata directory,
which [depends on your `db_engine`
choice](@/documentation/reference-manual/configuration.md#db_engine). Then,
your recovery options are as follows:
- **Option 1: resyncing from other nodes.** In case your cluster is replicated
with two or three copies, you can simply delete the database file, and Garage
will resync from other nodes. To do so, stop Garage, delete the database file
or directory, and restart Garage. Then, do a full table repair by calling
`garage repair -a --yes tables`. This will take a bit of time to complete as
the new node will need to receive copies of the metadata tables from the
network.
- **Option 2: restoring a snapshot taken by Garage.** Since v0.9.4, Garage can
[automatically take regular
snapshots](@/documentation/reference-manual/configuration.md#metadata_auto_snapshot_interval)
of your metadata DB file. This file or directory should be located under
`<metadata_dir>/snapshots`, and is named according to the UTC time at which it
was taken. Stop Garage, discard the database file/directory and replace it by the
snapshot you want to use. For instance, in the case of LMDB:
```bash
cd $METADATA_DIR
mv db.lmdb db.lmdb.bak
cp -r snapshots/2024-03-15T12:13:52Z db.lmdb
```
And for Sqlite:
```bash
cd $METADATA_DIR
mv db.sqlite db.sqlite.bak
cp snapshots/2024-03-15T12:13:52Z db.sqlite
```
Then, restart Garage and run a full table repair by calling `garage repair -a
--yes tables`. This should run relatively fast as only the changes that
occurred since the snapshot was taken will need to be resynchronized. Of
course, if your cluster is not replicated, you will lose all changes that
occurred since the snapshot was taken.
- **Option 3: restoring a filesystem-level snapshot.** If you are using ZFS or
BTRFS to snapshot your metadata partition, refer to their specific
documentation on rolling back or copying files from an old snapshot.
Note that, depending on the properties of the filesystem and of the DB engine,
if these snapshots were taken during a write operation to the database, they may
also be corrupted and thus unfit for recovery.
+2 -14
View File
@@ -56,7 +56,7 @@ From a high level perspective, a major upgrade looks like this:
10. Enable API access (reverse step 1)
11. Monitor your cluster while load comes back, check that all your applications are happy with this new version
### Major upgrades with minimal downtime
### 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
@@ -71,19 +71,7 @@ The entire procedure would look something like this:
2. Take each node offline individually to back up its metadata folder, bring them back online once the backup is done.
You can do all of the nodes in a single zone at once as that won't impact global cluster availability.
Do not try to manually copy the metadata folder of a running node.
**Since Garage v0.9.4,** you can use the `garage meta snapshot --all` command
to take a simultaneous snapshot of the metadata database files of all your
nodes. This avoids the tedious process of having to take them down one by
one before upgrading. Be careful that if automatic snapshotting is enabled,
Garage only keeps the last two snapshots and deletes older ones, so you might
want to disable automatic snapshotting in your upgraded configuration file
until you have confirmed that the upgrade ran successfully. In addition to
snapshotting the metadata databases of your nodes, you should back-up at
least the `cluster_layout` file of one of your Garage instances (this file
should be the same on all nodes and you can copy it safely while Garage is
running).
Do not try to make a backup of the metadata folder of a running node.
3. Prepare your binaries and configuration files for the new Garage version
+7 -41
View File
@@ -42,13 +42,6 @@ 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
@@ -64,7 +57,7 @@ to generate unique and private secrets for security reasons:
cat > garage.toml <<EOF
metadata_dir = "/tmp/meta"
data_dir = "/tmp/data"
db_engine = "sqlite"
db_engine = "lmdb"
replication_factor = 1
@@ -92,9 +85,6 @@ metrics_token = "$(openssl rand -base64 32)"
EOF
```
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`
@@ -121,26 +111,6 @@ garage -c path/to/garage.toml server
If you have placed the `garage.toml` file in `/etc` (its default location), you can simply run `garage server`.
Alternatively, if you cannot or do not wish to run the Garage binary directly,
you may use Docker to run Garage in a container using the following command:
```bash
docker run \
-d \
--name garaged \
-p 3900:3900 -p 3901:3901 -p 3902:3902 -p 3903:3903 \
-v /path/to/garage.toml:/etc/garage.toml \
-v /path/to/garage/meta:/var/lib/garage/meta \
-v /path/to/garage/data:/var/lib/garage/data \
dxflrs/garage:v2.2.0
```
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`.
@@ -161,9 +131,6 @@ It uses values from the TOML configuration file to find the Garage daemon runnin
local node, therefore if your configuration file is not at `/etc/garage.toml` you will
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:
@@ -182,12 +149,11 @@ ID Hostname Address Tag Zone Capacit
## Creating a cluster layout
Creating a cluster layout for a Garage deployment means informing Garage
of the disk space available on each node of the cluster, `-c`,
as well as the name of the zone (e.g. datacenter), `-z`, each machine is located in.
of the disk space available on each node of the cluster
as well as the zone (e.g. datacenter) each machine is located in.
For our test deployment, we are have only one node with zone named `dc1` and a
capacity of `1G`, though the capacity is ignored for a single node deployment
and can be changed later when adding new nodes.
For our test deployment, we are using only one node. The way in which we configure
it does not matter, you can simply write:
```bash
garage layout assign -z dc1 -c 1G <node_id>
@@ -200,7 +166,7 @@ For instance here you could write just `garage layout assign -z dc1 -c 1G 563e`.
The layout then has to be applied to the cluster, using:
```bash
garage layout apply --version 1
garage layout apply
```
@@ -350,7 +316,7 @@ Check [our s3 compatibility list](@/documentation/reference-manual/s3-compatibil
### Other tools for interacting with Garage
The following tools can also be used to send and receive files from/to Garage:
The following tools can also be used to send and recieve files from/to Garage:
- [minio-client](@/documentation/connect/cli.md#minio-client)
- [s3cmd](@/documentation/connect/cli.md#s3cmd)
+40 -150
View File
@@ -6,167 +6,41 @@ weight = 40
The Garage administration API is accessible through a dedicated server whose
listen address is specified in the `[admin]` section of the configuration
file (see [configuration file
reference](@/documentation/reference-manual/configuration.md)).
reference](@/documentation/reference-manual/configuration.md))
The current version of the admin API is v2. No breaking changes to the Garage
administration API will be published outside of a major release.
**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
History of previous versions:
- Before Garage v0.7.2 - no admin API
- Garage v0.7.2 - admin API v0
- Garage v0.9.0 - admin API v1, deprecate admin API v0
- Garage v2.0.0 - admin API v2, deprecate admin API v1
## Access control
### Using an API token
The admin API uses two different tokens for access control, that are specified in the config file's `[admin]` section:
Administration API tokens tokens are used as simple HTTP bearer tokens. In
other words, to authenticate access to an admin API endpoint, add the following
HTTP header to your request:
- `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>
```
### User-defined API tokens
Cluster administrators may dynamically define administration tokens using the CLI commands under `garage admin-token`.
Such tokens may be limited in scope, meaning that they may enable access to only a subset of API calls.
They may also have an expiration date to limit their use in time.
Here is an example to create an administration token that is valid for 30 days
and gives access to only a subset of API calls, allowing it to create buckets
and access keys and give keys permissions on buckets:
```bash
$ garage admin-token create --expires-in 30d \
--scope ListBuckets,GetBucketInfo,ListKeys,GetKeyInfo,CreateBucket,CreateKey,AllowBucketKey,DenyBucketKey \
my-token
This is your secret bearer token, it will not be shown again by Garage:
8ed1830b10a276ff57061950.kOSIpxWK9zSGbTO9Xadpv3YndSFWma0_snXcYHaORXk
==== ADMINISTRATION TOKEN INFORMATION ====
Token ID: 8ed1830b10a276ff57061950
Token name: my-token
Created: 2025-06-15 15:12:44.160 +02:00
Validity: valid
Expiration: 2025-07-15 15:12:44.117 +02:00
Scope: ListBuckets
GetBucketInfo
ListKeys
GetKeyInfo
CreateBucket
CreateKey
AllowBucketKey
DenyBucketKey
```
When running this command, your token will be shown only once and **will never
be shown again by Garage**, so make sure to save it directly. The token is
hashed internally, and is identified by its prefix (32 hex digits followed by a
dot) which is saved in clear.
When running `garage admin-token list`, you might see something like this:
```
ID Created Name Expiration Scope
- - metrics_token (from daemon configuration) never Metrics
8ed1830b10a276ff57061950 2025-06-15 my-token 2025-07-15 15:12:44.117 +02:00 ListBuckets, ... (8)
```
### Master API tokens
The admin API can also use two different master tokens for access control,
specified in the config file's `[admin]` section:
- `metrics_token`: the token for accessing the Metrics endpoint. If this token
is not set in the config file, the Metrics endpoint can be accessed without
access control.
- `admin_token`: the token for accessing all of the other administration
endpoints. If this token is not set in the config file, access to these
endpoints is only possible with a user-defined admin token.
With the introduction of multiple user-defined admin tokens, the use of master
API tokens is now discouraged.
## Using the admin API
All of the admin API endpoints are described in the OpenAPI specification:
- APIv2 - [HTML spec](https://garagehq.deuxfleurs.fr/api/garage-admin-v2.html) - [OpenAPI JSON](https://garagehq.deuxfleurs.fr/api/garage-admin-v2.json)
- APIv1 (deprecated) - [HTML spec](https://garagehq.deuxfleurs.fr/api/garage-admin-v1.html) - [OpenAPI YAML](https://garagehq.deuxfleurs.fr/api/garage-admin-v1.yml)
- APIv0 (deprecated) - [HTML spec](https://garagehq.deuxfleurs.fr/api/garage-admin-v0.html) - [OpenAPI YAML](https://garagehq.deuxfleurs.fr/api/garage-admin-v0.yml)
Making a request to the API from the command line can be as simple as running:
```bash
curl -H 'Authorization: Bearer s3cr3t' http://localhost:3903/v2/GetClusterStatus | jq
```
For more advanced use cases, we recommend using an SDK.
[Go to the "Build your own app" section to know how to use our SDKs](@/documentation/build/_index.md)
### Making API calls from the `garage` CLI
Since v2.0.0, the `garage` binary provides a subcommand `garage json-api` that
allows you to invoke the API without making an HTTP request. This can be
useful for scripting Garage deployments.
`garage json-api` proxies API calls through Garage's internal RPC protocol,
therefore it does not require any form of authentication: RPC connection
parameters are discovered automatically to contact the locally-running Garage
instance (as when running any other `garage` CLI command).
For simple calls that take no parameters, usage is as follows:
```
$ garage json-api GetClusterHealth
{
"connectedNodes": 3,
"knownNodes": 3,
"partitions": 256,
"partitionsAllOk": 256,
"partitionsQuorum": 256,
"status": "healthy",
"storageNodes": 3,
"storageNodesOk": 3
}
```
If you need to specify a JSON body for your call, you can add it directly after
the name of the function you are calling:
```
$ garage json-api CreateAdminToken '{"name": "test"}'
```
Or you can feed it through stdin by adding a `-` as the last command parameter:
```
$ garage json-api CreateAdminToken -
{"name": "test"}
<EOF>
```
For admin API calls that would have taken query parameters in their HTTP version, these parameters can be passed in the JSON body object:
```
$ garage json-api GetAdminTokenInfo '{"id":"b0e6e0ace2c0b2aca4cdb2de"}'
```
For admin API calls that take both query parameters and a JSON body, combine them in the following fashion:
```
$ garage json-api UpdateAdminToken '{"id":"b0e6e0ace2c0b2aca4cdb2de", "body":{"name":"not a test"}}'
```
## Special administration API endpoints
## Administration API endpoints
### Metrics `GET /metrics`
@@ -209,7 +83,7 @@ content-length: 102
date: Tue, 08 Aug 2023 07:22:38 GMT
Garage is fully operational
Consult the full health check API endpoint at /v2/GetClusterHealth for more details
Consult the full health check API endpoint at /v0/health for more details
```
### On-demand TLS `GET /check`
@@ -252,7 +126,23 @@ $ curl -so /dev/null -w "%{http_code}" http://localhost:3903/check?domain=exampl
200
```
**References:**
- [Using On-Demand TLS](https://caddyserver.com/docs/automatic-https#using-on-demand-tls)
- [Add option for a backend check to approve use of on-demand TLS](https://github.com/caddyserver/caddy/pull/1939)
- [Serving tens of thousands of domains over HTTPS with Caddy](https://caddy.community/t/serving-tens-of-thousands-of-domains-over-https-with-caddy/11179)
### Cluster operations
These endpoints 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)
+47 -310
View File
@@ -13,19 +13,13 @@ consistency_mode = "consistent"
metadata_dir = "/var/lib/garage/meta"
data_dir = "/var/lib/garage/data"
metadata_snapshots_dir = "/var/lib/garage/snapshots"
metadata_fsync = true
data_fsync = false
disable_scrub = false
use_local_tz = false
metadata_auto_snapshot_interval = "6h"
db_engine = "lmdb"
block_size = "1M"
block_ram_buffer_max = "256MiB"
block_max_concurrent_reads = 16
block_max_concurrent_writes_per_request =10
lmdb_map_size = "1T"
compression_level = 1
@@ -34,11 +28,6 @@ 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",
@@ -47,24 +36,20 @@ bootstrap_peers = [
"212fd62eeaca72c122b45a7f4fa0f55e012aa5e24ac384a72a3016413fa724ff@[fc00:F::1]:3901",
]
allow_punycode = false
[consul_discovery]
api = "catalog"
consul_http_addr = "https://127.0.0.1:8500"
tls_skip_verify = false
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" }
datacenters = ["dc1", "dc2", "dc3"]
[kubernetes_discovery]
namespace = "garage"
@@ -80,12 +65,10 @@ root_domain = ".s3.garage"
[s3_web]
bind_addr = "[::]:3902"
root_domain = ".web.garage"
add_host_to_metrics = true
[admin]
api_bind_addr = "0.0.0.0:3903"
metrics_token = "BCAdFjoa9G0KJR0WXnHHm7fs1ZAbfpI8iIZ+Z/a2NgI="
metrics_require_token = true
admin_token = "UkLeGWEvHnXBqnueR3ISEMWpOnm40jH2tM2HnnL/0F4="
trace_sink = "http://localhost:4317"
```
@@ -96,34 +79,22 @@ The following gives details about each available configuration option.
### Index
[Environment variables](#env_variables).
Top-level configuration options, in alphabetical order:
[`allow_punycode`](#allow_punycode),
[`allow_world_readable_secrets`](#allow_world_readable_secrets),
[`block_max_concurrent_reads`](#block_max_concurrent_reads),
[`block_max_concurrent_writes_per_request`](#block_max_concurrent_writes_per_request),
[`block_ram_buffer_max`](#block_ram_buffer_max),
Top-level configuration options:
[`block_size`](#block_size),
[`bootstrap_peers`](#bootstrap_peers),
[`compression_level`](#compression_level),
[`consistency_mode`](#consistency_mode),
[`data_dir`](#data_dir),
[`data_fsync`](#data_fsync),
[`db_engine`](#db_engine),
[`disable_scrub`](#disable_scrub),
[`lmdb_map_size`](#lmdb_map_size),
[`metadata_auto_snapshot_interval`](#metadata_auto_snapshot_interval),
[`metadata_dir`](#metadata_dir),
[`metadata_fsync`](#metadata_fsync),
[`metadata_snapshots_dir`](#metadata_snapshots_dir),
[`replication_factor`](#replication_factor),
[`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),
[`use_local_tz`](#use_local_tz).
[`rpc_secret`/`rpc_secret_file`](#rpc_secret).
The `[consul_discovery]` section:
[`api`](#consul_api),
@@ -131,14 +102,12 @@ The `[consul_discovery]` section:
[`client_cert`](#consul_client_cert_and_key),
[`client_key`](#consul_client_cert_and_key),
[`consul_http_addr`](#consul_http_addr),
[`datacenters`](#consul_datacenters)
[`meta`](#consul_tags_and_meta),
[`service_name`](#consul_service_name),
[`tags`](#consul_tags_and_meta),
[`tls_skip_verify`](#consul_tls_skip_verify),
[`token`](#consul_token).
The `[kubernetes_discovery]` section:
[`namespace`](#kube_namespace),
[`service_name`](#kube_service_name),
@@ -150,42 +119,19 @@ The `[s3_api]` section:
[`s3_region`](#s3_region).
The `[s3_web]` section:
[`add_host_to_metrics`](#web_add_host_to_metrics),
[`bind_addr`](#web_bind_addr),
[`root_domain`](#web_root_domain).
The `[admin]` section:
[`api_bind_addr`](#admin_api_bind_addr),
[`metrics_require_token`](#admin_metrics_require_token),
[`metrics_token`/`metrics_token_file`](#admin_metrics_token),
[`admin_token`/`admin_token_file`](#admin_token),
[`trace_sink`](#admin_trace_sink),
### Environment variables {#env_variables}
The following configuration parameters must be specified as environment variables,
they do not exist in the configuration file:
- `GARAGE_LOG_TO_SYSLOG` (since `v0.9.4`): set this to `1` or `true` to make the
Garage daemon send its logs to `syslog` (using the libc `syslog` function)
instead of printing to stderr.
- `GARAGE_LOG_TO_JOURNALD` (since `v1.2.0`): set this to `1` or `true` to make the
Garage daemon send its logs to `journald` (using the native protocol of `systemd-journald`)
instead of printing to stderr.
The following environment variables can be used to override the corresponding
values in the configuration file:
- [`GARAGE_ALLOW_WORLD_READABLE_SECRETS`](#allow_world_readable_secrets)
- [`GARAGE_RPC_SECRET` and `GARAGE_RPC_SECRET_FILE`](#rpc_secret)
- [`GARAGE_ADMIN_TOKEN` and `GARAGE_ADMIN_TOKEN_FILE`](#admin_token)
- [`GARAGE_METRICS_TOKEN` and `GARAGE_METRICS_TOKEN`](#admin_metrics_token)
### Top-level configuration options
#### `replication_factor` (since `v1.0.0`) {#replication_factor}
#### `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.
@@ -233,7 +179,7 @@ is in progress. In theory, no data should be lost as rebalancing is a
routine operation for Garage, although we cannot guarantee you that everything
will go right in such an extreme scenario.
#### `consistency_mode` (since `v1.0.0`) {#consistency_mode}
#### `consistency_mode` {#consistency_mode}
The consistency mode setting determines the read and write behaviour of your cluster.
@@ -295,7 +241,6 @@ as the index of all objects, object version and object blocks.
Store this folder on a fast SSD drive if possible to maximize Garage's performance.
#### `data_dir` {#data_dir}
The directory in which Garage will store the data blocks of objects.
@@ -316,76 +261,34 @@ data_dir = [
See [the dedicated documentation page](@/documentation/operations/multi-hdd.md)
on how to operate Garage in such a setup.
#### `metadata_snapshots_dir` (since `v1.1.0`) {#metadata_snapshots_dir}
The directory in which Garage will store metadata snapshots when it
performs a snapshot of the metadata database, either when instructed to do
so from a RPC call or regularly through
[`metadata_auto_snapshot_interval`](#metadata_auto_snapshot_interval).
By default, Garage will store snapshots into a `snapshots/` subdirectory
of [`metadata_dir`](#metadata_dir). This might quickly fill up your
metadata storage space if you use snapshots, because Garage will need up
to 4x the space of the existing metadata database: each snapshot requires
roughly as much space as the original database, and Garage temporarily
needs to store up to three different snapshots before it cleans up the oldest
snapshot to go back to two stored snapshots.
To prevent filling your disk, you might to change this setting to a
directory with ample available space, e.g. on the same storage space as
[`data_dir`](#data_dir).
#### `db_engine` (since `v0.8.0`) {#db_engine}
Since `v0.8.0`, Garage can use alternative storage backends as follows:
| DB engine | `db_engine` value | Database path |
| --------- | ----------------- | ------------- |
| [LMDB](https://www.symas.com/lmdb) (since `v0.8.0`, default since `v0.9.0`) | `"lmdb"` | `<metadata_dir>/db.lmdb/` |
| [LMDB](https://www.lmdb.tech) (since `v0.8.0`, default since `v0.9.0`) | `"lmdb"` | `<metadata_dir>/db.lmdb/` |
| [Sqlite](https://sqlite.org) (since `v0.8.0`) | `"sqlite"` | `<metadata_dir>/db.sqlite` |
| [Fjall](https://github.com/fjall-rs/fjall) (**experimental support** since `v1.3.0`/`v2.1.0`) | `"fjall"` | `<metadata_dir>/db.fjall/` |
| [Sled](https://sled.rs) (old default, removed since `v1.0`) | `"sled"` | `<metadata_dir>/db/` |
Sled was supported until Garage v0.9.x, and was removed in Garage v1.0.
You can still use an older binary of Garage (e.g. v0.9.4) to migrate
You can still use an older binary of Garage (e.g. v0.9.3) 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
with `replication_factor` ≥ 2.
LMDB works well, but is known to have the following limitations:
- LMDB: the recommended database engine on 64-bit systems, much more
space-efficient and slightly faster. Note that the data format of LMDB is not
portable between architectures, so for instance the Garage database of an
x86-64 node cannot be moved to an ARM64 node. Also note that, while LMDB can
technically be used on 32-bit systems, this will limit your node to very
small database sizes due to how LMDB works; it is therefore not recommended.
- LMDB is prone to database corruption after an unclean shutdown (e.g. a process kill
or a power outage). It is recommended to configure
[`metadata_auto_snapshot_interval`](#metadata_auto_snapshot_interval) to be
able to easily recover from this situation. With `replication_factor` ≥ 2,
metadata can also be reconstructed from remote nodes upon corruption
(see [Recovering from failures](@/documentation/operations/recovering.md#corrupted_meta)).
- The data format of LMDB is not portable between architectures, so for
instance the Garage database of an x86-64 node cannot be moved to an ARM64
node.
- While LMDB can technically be used on 32-bit systems, this will limit your
node to very small database sizes due to how LMDB works; it is therefore
not recommended.
- Keys in LMDB are limited to 511 bytes. This limit translates to limits on
object keys in S3 and sort keys in K2V that are limited to 479 bytes.
- **Sqlite:** Garage supports Sqlite as an alternative storage backend for
metadata, which does not have the issues listed above for LMDB. Sqlite is
slower than LMDB, so it is not the best choice for high-performance storage
clusters.
- **Fjall:** a storage engine based on LSM trees, which theoretically allow for
higher write throughput than other storage engines that are based on B-trees.
Using Fjall could potentially improve Garage's performance significantly in
write-heavy workloads. **Support for Fjall is experimental at this point**,
we have added it to Garage for evaluation purposes only. **Use it only with
test data, and report any issues to our bug tracker. Do not use it for
production workloads.**
- Sqlite: Garage supports Sqlite as an alternative storage backend for
metadata, and although it has not been tested as much, it is expected to work
satisfactorily. Since Garage v0.9.0, performance issues have largely been
fixed by allowing for a no-fsync mode (see `metadata_fsync`). Sqlite does not
have the database size limitation of LMDB on 32-bit systems.
It is possible to convert Garage's metadata directory from one format to another
using the `garage convert-db` command, which should be used as follows:
@@ -396,7 +299,7 @@ garage convert-db -a <input db engine> -i <input db path> \
```
Make sure to specify the full database path as presented in the table above
(third column), and not just the path to the metadata directory.
(third colummn), and not just the path to the metadata directory.
#### `metadata_fsync` {#metadata_fsync}
@@ -412,7 +315,7 @@ Using this option reduces the risk of simultaneous metadata corruption on severa
cluster nodes, which could lead to data loss.
If multi-site replication is used, this option is most likely not necessary, as
it is extremely unlikely that two nodes in different locations will have a
it is extremely unlikely that two nodes in different locations will have a
power failure at the exact same time.
(Metadata corruption on a single node is not an issue, the corrupted data file
@@ -424,7 +327,6 @@ Here is how this option impacts the different database engines:
|----------|------------------------------------|-------------------------------|
| Sqlite | `PRAGMA synchronous = OFF` | `PRAGMA synchronous = NORMAL` |
| LMDB | `MDB_NOMETASYNC` + `MDB_NOSYNC` | `MDB_NOMETASYNC` |
| Fjall | default options | not supported |
Note that the Sqlite database is always ran in `WAL` mode (`PRAGMA journal_mode = WAL`).
@@ -438,59 +340,9 @@ 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 `metadata_fsync`, this is likely not necessary
Similarly to `metatada_fsync`, this is likely not necessary
if geographical replication is used.
#### `metadata_auto_snapshot_interval` (since `v0.9.4`) {#metadata_auto_snapshot_interval}
If this value is set, Garage will automatically take a snapshot of the metadata
DB file at a regular interval and save it in the metadata directory,
or in [`metadata_snapshots_dir`](#metadata_snapshots_dir) if it is set.
This parameter can take any duration string that can be parsed by
the [`parse_duration`](https://docs.rs/parse_duration/latest/parse_duration/#syntax) crate.
Snapshots can allow to recover from situations where the metadata DB file is
corrupted, for instance after an unclean shutdown. See [this
page](@/documentation/operations/recovering.md#corrupted_meta) for details.
Garage keeps only the two most recent snapshots of the metadata DB and deletes
older ones automatically.
You can also create metadata snapshots manually at any point using the
`garage meta snapshot` command.
Using snapshots created by Garage is the best option to make snapshots of your
node's metadata for potential recovery, as they are guaranteed to be clean and
consistent, contrarily to filesystem-level snapshots that may be taken while
some writes are in-flight and thus might be corrupted.
Note that taking a metadata snapshot is a relatively intensive operation as the
entire data file is copied. A snapshot being taken might have performance
impacts on the Garage node while it is running. If the cluster is under heavy
write load when a snapshot operation is running, this might also cause the
database file to grow in size significantly as pages cannot be recycled easily.
#### `disable_scrub` {#disable_scrub}
By default, Garage runs a scrub of the data directory approximately once per
month, with a random delay to avoid all nodes running at the same time. When
it scrubs the data directory, Garage will read all of the data files stored on
disk to check their integrity, and will rebuild any data files that it finds
corrupted, using the remaining valid copies stored on other nodes.
See [this page](@/documentation/operations/durability-repairs.md#scrub) for details.
Set the `disable_scrub` configuration value to `true` if you don't need Garage
to scrub the data directory, for instance if you are already scrubbing at the
filesystem level. Note that in this case, if you find a corrupted data file,
you should delete it from the data directory and then call `garage repair
blocks` on the node to ensure that it re-obtains a copy from another node on
the network.
#### `use_local_tz` (since `v1.1.0`) {#use_local_tz}
By default, Garage runs the lifecycle worker every day at midnight in UTC. Set the
`use_local_tz` configuration value to `true` if you want Garage to run the
lifecycle worker at midnight in your local timezone. If you have multiple nodes,
you should also ensure that each node has the same timezone configuration.
#### `block_size` {#block_size}
Garage splits stored objects in consecutive chunks of size `block_size`
@@ -506,68 +358,6 @@ 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.
#### `block_ram_buffer_max` (since `v0.9.4`) {#block_ram_buffer_max}
A limit on the total size of data blocks kept in RAM by S3 API nodes awaiting
to be sent to storage nodes asynchronously.
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.
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.
Note that this only counts buffers that have arrived to a certain stage of
processing (received from the client + encrypted and/or compressed as
necessary) and are ready to send to the storage nodes. Many other buffers will
not be counted and this is not a hard limit on RAM consumption. In particular,
if many clients send requests simultaneously with large objects, the RAM
consumption will always grow linearly with the number of concurrent requests,
as each request will use a few buffers of size `block_size` for receiving and
intermediate processing before even trying to send the data to the storage
node.
The default value is 256MiB.
#### `block_max_concurrent_reads` (since `v1.3.0` / `v2.1.0`) {#block_max_concurrent_reads}
The maximum number of blocks (individual files in the data directory) open
simultaneously for reading.
Reducing this number does not limit the number of data blocks that can be
transferred through the network simultaneously. This mechanism was just added
as a backpressure mechanism for HDD read speed: it helps avoid a situation
where too many requests are coming in and Garage is reading too many block
files simultaneously, thus not making timely progress on any of the reads.
When a request to read a data block comes in through the network, the requests
awaits for one of the `block_max_concurrent_reads` slots to be available
(internally implemented using a Semaphore object). Once it acquired a read
slot, it reads the entire block file to RAM and frees the slot as soon as the
block file is finished reading. Only after the slot is released will the
block's data start being transferred over the network. If the request fails to
acquire a reading slot within 15 seconds, it fails with a timeout error.
Timeout events can be monitored through the `block_read_semaphore_timeouts`
metric in Prometheus: a non-zero number of such events indicates an I/O
bottleneck on HDD read speed.
#### `block_max_concurrent_writes_per_request` (since `v1.3.1` / `v2.2.0`) {#block_max_concurrent_writes_per_request}
This parameter is designed to adapt to the concurrent write performance of
different storage media. Maximum number of parallel block writes per put request.
Higher values may improve throughput but increase memory usage.
Default value: 3. Recommended values: 10-30 for NVMe, 3-10 for spinning HDD.
#### `lmdb_map_size` {#lmdb_map_size}
This parameters can be used to set the map size used by LMDB,
@@ -617,14 +407,14 @@ 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 communications
(referred to as RPC for remote procedure calls).
The address and port on which to bind for inter-cluster communcations
(reffered to as RPC for remote procedure calls).
The port specified here should be the same one that other nodes will used to contact
the node, even in the case of a NAT: the NAT should be configured to forward the external
port number to the same internal port number. This means that if you have several nodes running
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_bind_outgoing` (since `v0.9.2`) {#rpc_bind_outgoing}
#### `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
@@ -642,14 +432,6 @@ 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.
#### `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.
@@ -666,7 +448,7 @@ be obtained by running `garage node id` and then included directly in the
key will be returned by `garage node id` and you will have to add the IP
yourself.
#### `allow_world_readable_secrets` or `GARAGE_ALLOW_WORLD_READABLE_SECRETS` (env) {#allow_world_readable_secrets}
### `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
@@ -678,13 +460,6 @@ permission verification.
Alternatively, you can set the `GARAGE_ALLOW_WORLD_READABLE_SECRETS`
environment variable to `true` to bypass the permissions check.
#### `allow_punycode` {#allow_punycode}
Allow creating buckets with names containing punycode. When used for buckets served
as websites, this allows using almost any unicode character in the domain name.
Default to `false`.
### The `[consul_discovery]` section
Garage supports discovering other nodes of the cluster using Consul. For this
@@ -740,18 +515,6 @@ node_prefix "" {
}
```
#### `datacenters` {#consul_datacenters}
Optional list of datacenters that allow garage to do service discovery when Consul is configured in WAN federation.
Example: `datacenters = ["dc1", "dc2", "dc3"]`
In a WAN configuration, by default the Consul services API only responds with
local LAN services. When a list of datacenters is specified using this option,
Garage will query the consul server API by datacenter directly, allowing for
Garage to discover nodes across the Consul WAN.
#### `tags` and `meta` {#consul_tags_and_meta}
Additional list of tags and map of service meta to add during service registration.
@@ -784,14 +547,14 @@ manually.
#### `api_bind_addr` {#s3_api_bind_addr}
The IP and port on which to bind for accepting S3 API calls.
This endpoint does not support TLS: a reverse proxy should be used to provide it.
This endpoint does not suport TLS: a reverse proxy should be used to provide it.
Alternatively, since `v0.8.5`, a path can be used to create a unix socket with 0222 mode.
#### `s3_region` {#s3_region}
Garage will accept S3 API calls that are targeted to the S3 region defined here.
API calls targeted to other regions will fail with a AuthorizationHeaderMalformed error
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` {#s3_root_domain}
@@ -799,7 +562,7 @@ message that redirects the client to the correct region.
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 software not supporting path-style requests.
but might be required by softwares not supporting path-style requests.
If `root_domain` is `s3.garage.eu`, a bucket called `my-bucket` can be interacted with
using the hostname `my-bucket.s3.garage.eu`.
@@ -815,7 +578,7 @@ behaviour of this module.
The IP and port on which to bind for accepting HTTP requests to buckets configured
for website access.
This endpoint does not support TLS: a reverse proxy should be used to provide it.
This endpoint does not suport TLS: a reverse proxy should be used to provide it.
Alternatively, since `v0.8.5`, a path can be used to create a unix socket with 0222 mode.
@@ -827,13 +590,6 @@ For instance, if `root_domain` is `web.garage.eu`, a bucket called `deuxfleurs.f
will be accessible either with hostname `deuxfleurs.fr.web.garage.eu`
or with hostname `deuxfleurs.fr`.
#### `add_host_to_metrics` {#web_add_host_to_metrics}
Whether to include the requested domain name (HTTP `Host` header) in the
Prometheus metrics of the web endpoint. This is disabled by default as the
number of possible values is not bounded and can be a source of cardinality
explosion in the exported metrics.
### The `[admin]` section
@@ -848,34 +604,10 @@ See [administration API reference](@/documentation/reference-manual/admin-api.md
Alternatively, since `v0.8.5`, a path can be used to create a unix socket. Note that for security reasons,
the socket will have 0220 mode. Make sure to set user and group permissions accordingly.
#### `admin_token`, `admin_token_file` or `GARAGE_ADMIN_TOKEN`, `GARAGE_ADMIN_TOKEN_FILE` (env) {#admin_token}
The token for accessing all administration functions on the admin endpoint,
with the exception of the metrics endpoint (see `metrics_token`).
You can use any random string for this value. We recommend generating a random
token with `openssl rand -base64 32`.
For Garage version earlier than `v2.0`, if this token is not set,
access to these endpoints is disabled entirely.
Since Garage `v2.0`, additional admin API tokens can be defined dynamically
in your Garage cluster using administration commands. This new admin token system
is more flexible since it allows admin tokens to have an expiration date,
and to have a scope restricted to certain admin API functions. If `admin_token`
is set, it behaves as an admin token without expiration and with full scope.
Otherwise, only admin API tokens defined dynamically can be used.
`admin_token` was introduced in Garage `v0.7.2`.
`admin_token_file` and the `GARAGE_ADMIN_TOKEN` environment variable are supported since Garage `v0.8.2`.
`GARAGE_ADMIN_TOKEN_FILE` is supported since `v0.8.5` / `v0.9.1`.
#### `metrics_token`, `metrics_token_file` or `GARAGE_METRICS_TOKEN`, `GARAGE_METRICS_TOKEN_FILE` (env) {#admin_metrics_token}
The token for accessing the Prometheus metrics endpoint (`/metrics`).
If this token is not set, and unless `metrics_require_token` is set to `true`,
the metrics endpoint can be accessed without access control.
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`.
@@ -884,12 +616,17 @@ You can use any random string for this value. We recommend generating a random t
`GARAGE_METRICS_TOKEN_FILE` is supported since `v0.8.5` / `v0.9.1`.
#### `metrics_require_token` (since `v2.0.0`) {#admin_metrics_require_token}
#### `admin_token`, `admin_token_file` or `GARAGE_ADMIN_TOKEN`, `GARAGE_ADMIN_TOKEN_FILE` (env) {#admin_token}
If this is set to `true`, accessing the metrics endpoint will always require
an access token. Valid tokens include the `metrics_token` if it is set,
and admin API token defined dynamically in Garage which have
the `Metrics` endpoint in their scope.
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}
+6 -6
View File
@@ -46,7 +46,7 @@ to select the replication mode best suited to your use case (hint: in most cases
### Compression and deduplication
All data stored in Garage is deduplicated, and optionally compressed using
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
@@ -61,7 +61,7 @@ directed to a Garage cluster can be handled independently of one another instead
of going through a central bottleneck (the leader node).
As a consequence, requests can be handled much faster, even in cases where latency
between cluster nodes is important (see our [benchmarks](@/documentation/design/benchmarks/index.md) for data on this).
This is particularly useful when nodes are far from one another and talk to one other through standard Internet connections.
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
@@ -84,13 +84,13 @@ exposing the same content under different domain names.
Garage also supports bucket aliases which are local to a single user:
this allows different users to have different buckets with the same name, thus avoiding naming collisions.
This can be helpful for instance if you want to write an application that creates per-user buckets with always the same name.
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 programmatically.
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).
@@ -100,7 +100,7 @@ A full reference of the administration API is available [here](@/documentation/r
Garage makes some internal metrics available in the Prometheus data format,
which allows you to build interactive dashboards to visualize the load and internal state of your storage cluster.
For developers and performance-savvy administrators,
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.
@@ -129,5 +129,5 @@ related to objects stored in an S3 bucket.
In the context of our research project, [Aérogramme](https://aerogramme.deuxfleurs.fr),
K2V is used to provide metadata and log storage for operations on encrypted e-mail storage.
Learn more on the specification of K2V [here](https://git.deuxfleurs.fr/Deuxfleurs/garage/src/commit/f8be15c37db857e177d543de7be863692628d567/doc/drafts/k2v-spec.md)
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).
+3 -2
View File
@@ -16,10 +16,10 @@ the `k2v` feature flag enabled can be obtained from our download page under
with `-k2v` (example: `v0.7.2-k2v`).
The specification of the K2V API can be found
[here](https://git.deuxfleurs.fr/Deuxfleurs/garage/src/commit/f8be15c37db857e177d543de7be863692628d567/doc/drafts/k2v-spec.md).
[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 authentication, same as the S3 API.
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.
@@ -55,3 +55,4 @@ 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.
+1 -12
View File
@@ -225,17 +225,6 @@ 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.
@@ -392,7 +381,7 @@ table_merkle_updater_todo_queue_length{table_name="block_ref"} 0
#### `table_sync_items_received`, `table_sync_items_sent` (counters)
Number of data items sent to/received from other nodes during resync procedures
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
@@ -23,17 +23,17 @@ Feel free to open a PR to suggest fixes this table. Minio is missing because the
- 2022-05-25 - Many Ceph S3 endpoints are not documented but implemented. Following a notification from the Ceph community, we added them.
## High-level features
| Feature | Garage | [Openstack Swift](https://docs.openstack.org/swift/latest/s3_compat.html) | [Ceph Object Gateway](https://docs.ceph.com/en/latest/radosgw/s3/) | [Riak CS](https://docs.riak.com/riak/cs/2.1.1/references/apis/storage/s3/index.html) | [OpenIO](https://docs.openio.io/latest/source/arch-design/s3_compliancy.html) |
|------------------------------|----------------------------------|-----------------|---------------|---------|-----|
| [signature v2](https://docs.aws.amazon.com/AmazonS3/latest/API/Appendix-Sigv2.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 | ❓ | ✅ | ❌ | ✅ |
| [Bucket versioning](https://docs.aws.amazon.com/AmazonS3/latest/userguide/Versioning.html) | ❌ Missing | ✅ | ✅ | ❌ | ✅ |
*Note:* OpenIO does not says if it supports presigned URLs. Because it is part
of signature v4 and they claim they support it without additional precisions,
@@ -45,7 +45,7 @@ we suppose that OpenIO supports presigned URLs.
All endpoints that are missing on Garage will return a 501 Not Implemented.
Some `x-amz-` headers are not implemented.
### Core endpoints
### 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) |
|------------------------------|----------------------------------|-----------------|---------------|---------|-----|
@@ -135,12 +135,12 @@ If you need this feature, please [share your use case in our dedicated issue](ht
**PutBucketLifecycleConfiguration:** The only actions supported are
`AbortIncompleteMultipartUpload` and `Expiration` (without the
`ExpiredObjectDeleteMarker` field). All other operations are dependent on
either bucket versioning or storage classes which Garage currently does not
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 which always returns "versioning not enabled", since Garage does not yet support bucket versioning.
**GetBucketVersioning:** Stub implementation which always returns "versionning not enabled", since Garage does not yet support bucket versionning.
### Replication endpoints
@@ -155,7 +155,7 @@ Please open an issue if you have a use case for replication.
*Note: Ceph documentation briefly says that Ceph supports
[replication through the S3 API](https://docs.ceph.com/en/latest/radosgw/multisite-sync-policy/#s3-replication-api)
but with some limitations.
Additionally, replication endpoints are not documented in the S3 compatibility page so I don't know what kind of support we can expect.*
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
@@ -197,7 +197,7 @@ Please open an issue if you have a use case.
### Vendor specific endpoints
<details><summary>Display Amazon specific endpoints</summary>
<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) |
@@ -234,3 +234,4 @@ Please open an issue if you have a use case.
| [SelectObjectContent](https://docs.aws.amazon.com/AmazonS3/latest/API/API_SelectObjectContent.html) | ❌ Missing | ❌| ❌| ❌| ❌|
</details>
@@ -3,7 +3,7 @@ title = "S3 compatibility target"
weight = 5
+++
If there is a specific S3 functionality you have a need for, feel free to open
If there is a specific S3 functionnality you have a need for, feel free to open
a PR to put the corresponding endpoints higher in the list. Please explain
your motivations for doing so in the PR message.
+4 -4
View File
@@ -42,7 +42,7 @@ The general principle are similar, but details have not been updated.**
A version is defined by the existence of at least one entry in the blocks table for a certain version UUID.
We must keep the following invariant: if a version exists in the blocks table, it has to be referenced in the objects table.
We explicitly manage concurrent versions of an object: the version timestamp and version UUID columns are index columns, thus we may have several concurrent versions of an object.
Important: before deleting an older version from the objects table, we must make sure that we did a successful delete of the blocks of that version from the blocks table.
Important: before deleting an older version from the objects table, we must make sure that we did a successfull delete of the blocks of that version from the blocks table.
Thus, the workflow for reading an object is as follows:
@@ -68,7 +68,7 @@ Workflow for DELETE:
1. Check write permission (LDAP)
2. Get current version (or versions) in object table
3. Do the deletion of those versions NOT IN A BACKGROUND JOB THIS TIME
4. Return success to the user if we were able to delete blocks from the blocks table and entries from the object table
4. Return succes to the user if we were able to delete blocks from the blocks table and entries from the object table
To delete a version:
@@ -92,10 +92,10 @@ Known issue: if someone is reading from a version that we want to delete and the
- file path = /meta/(first 3 hex digits of hash)/(rest of hash)
- map block hash -> set of version UUIDs where it is referenced
Useful metadata:
Usefull metadata:
- list of versions that reference this block in the Casandra table, so that we can do GC by checking in Cassandra that the lines still exist
- list of other nodes that we know have acknowledged a write of this block, useful in the rebalancing algorithm
- list of other nodes that we know have acknowledged a write of this block, usefull in the rebalancing algorithm
Write strategy: have a single thread that does all write IO so that it is serialized (or have several threads that manage independent parts of the hash space). When writing a blob, write it to a temporary file, close, then rename so that a concurrent read gets a consistent result (either not found or found with whole content).
+3 -3
View File
@@ -49,12 +49,12 @@ The ring construction that selects `n_token` random positions for each nodes giv
is not well-balanced: the space between the tokens varies a lot, and some partitions are thus bigger than others.
This problem was demonstrated in the original Dynamo DB paper.
To solve this, we want to apply a better second method for partitioning our dataset:
To solve this, we want to apply a better second method for partitionning our dataset:
1. fix an initially large number of partitions (say 1024) with evenly-spaced delimiters,
2. attribute each partition randomly to a node, with a probability
proportional to its capacity (which `n_tokens` represented in the first
proportionnal to its capacity (which `n_tokens` represented in the first
method)
For now we continue using the multi-DC ring walking described above.
@@ -66,7 +66,7 @@ I have studied two ways to do the attribution of partitions to nodes, in a way t
MagLev provided significantly better balancing, as it guarantees that the exact
same number of partitions is attributed to all nodes that have the same
capacity (and that this number is proportional to the node's capacity, except
capacity (and that this number is proportionnal to the node's capacity, except
for large values), however in both cases:
- the distribution is still bad, because we use the naive multi-DC ring walking
+2 -2
View File
@@ -1,6 +1,6 @@
+++
title = "Migrating from 0.3 to 0.4"
weight = 80
weight = 20
+++
**Migrating from 0.3 to 0.4 is unsupported. This document is only intended to
@@ -68,7 +68,7 @@ The migration steps are as follows:
5. Turn off Garage 0.3
6. Backup metadata folders if you can (i.e. if you have space to do it
somewhere). Backuping data folders could also be useful but that's much
somewhere). Backuping data folders could also be usefull but that's much
harder to do. If your filesystem supports snapshots, this could be a good
time to use them.
+1 -1
View File
@@ -1,6 +1,6 @@
+++
title = "Migrating from 0.5 to 0.6"
weight = 75
weight = 15
+++
**This guide explains how to migrate to 0.6 if you have an existing 0.5 cluster.
+2 -2
View File
@@ -1,6 +1,6 @@
+++
title = "Migrating from 0.6 to 0.7"
weight = 74
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.**
@@ -19,7 +19,7 @@ The migration steps are as follows:
2. Disable API and web access. Garage does not support disabling
these endpoints but you can change the port number or stop your reverse
proxy for instance.
3. Check once again that your cluster is healthy. Run again `garage repair --all-nodes --yes tables` which is quick.
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/`
+1 -1
View File
@@ -1,6 +1,6 @@
+++
title = "Migrating from 0.7 to 0.8"
weight = 73
weight = 13
+++
**This guide explains how to migrate to 0.8 if you have an existing 0.7 cluster.
+1 -1
View File
@@ -1,6 +1,6 @@
+++
title = "Migrating from 0.8 to 0.9"
weight = 72
weight = 12
+++
**This guide explains how to migrate to 0.9 if you have an existing 0.8 cluster.
-77
View File
@@ -1,77 +0,0 @@
+++
title = "Migrating from 0.9 to 1.0"
weight = 71
+++
**This guide explains how to migrate to 1.0 if you have an existing 0.9 cluster.
We don't recommend trying to migrate to 1.0 directly from 0.8 or older.**
This migration procedure has been tested on several clusters without issues.
However, it is still a *critical procedure* that might cause issues.
**Make sure to back up all your data before attempting it!**
You might also want to read our [general documentation on upgrading Garage](@/documentation/operations/upgrading.md).
## Changes introduced in v1.0
The following are **breaking changes** in Garage v1.0 that require your attention when migrating:
- The Sled metadata db engine has been **removed**. If your cluster was still
using Sled, you will need to **use a Garage v0.9.x binary** to convert the
database using the `garage convert-db` subcommand. See
[here](@/documentation/reference-manual/configuration.md#db_engine) for the
details of the procedure.
The following syntax changes have been made to the configuration file:
- The `replication_mode` parameter has been split into two parameters:
[`replication_factor`](@/documentation/reference-manual/configuration.md#replication_factor)
and
[`consistency_mode`](@/documentation/reference-manual/configuration.md#consistency_mode).
The old syntax using `replication_mode` is still supported for legacy
reasons and can still be used.
- The parameters `sled_cache_capacity` and `sled_flush_every_ms` have been removed.
## Migration procedure
The migration to Garage v1.0 can be done with almost no downtime,
by restarting all nodes at once in the new version.
The migration steps are as follows:
1. Do a `garage repair --all-nodes --yes tables`, check the logs and check that
all data seems to be synced correctly between nodes. If you have time, do
additional `garage repair` procedures (`blocks`, `versions`, `block_refs`,
etc.)
2. Ensure you have a snapshot of your Garage installation that you can restore
to in case the upgrade goes wrong:
- If you are running Garage v0.9.4 or later, use the `garage meta snapshot
--all` to make a backup snapshot of the metadata directories of your nodes
for backup purposes, and save a copy of the following files in the
metadata directories of your nodes: `cluster_layout`, `data_layout`,
`node_key`, `node_key.pub`.
- If you are running a filesystem such as ZFS or BTRFS that support
snapshotting, you can create a filesystem-level snapshot to be used as a
restoration point if needed.
- In other cases, make a backup using the old procedure: turn off each node
individually; back up its metadata folder (for instance, use the following
command if your metadata directory is `/var/lib/garage/meta`: `cd
/var/lib/garage ; tar -acf meta-v0.9.tar.zst meta/`); turn it back on
again. This will allow you to take a backup of all nodes without
impacting global cluster availability. You can do all nodes of a single
zone at once as this does not impact the availability of Garage.
3. Prepare your updated binaries and configuration files for Garage v1.0
4. Shut down all v0.9 nodes simultaneously, and restart them all simultaneously
in v1.0. Use your favorite deployment tool (Ansible, Kubernetes, Nomad) to
achieve this as fast as possible. Garage v1.0 should be in a working state
as soon as enough nodes have started.
5. Monitor your cluster in the following hours to see if it works well under
your production load.
-70
View File
@@ -1,70 +0,0 @@
+++
title = "Migrating from 1.0 to 2.0"
weight = 70
+++
**This guide explains how to migrate to v2.x if you have an existing v1.x.x cluster.
We don't recommend trying to migrate to v2.x directly from v0.9.x or older.**
This migration procedure has been tested on several clusters without issues.
However, it is still a *critical procedure* that might cause issues.
**Make sure to back up all your data before attempting it!**
You might also want to read our [general documentation on upgrading Garage](@/documentation/operations/upgrading.md).
## Changes introduced in v2.0
The following are **breaking changes** in Garage v2.0 that require your attention when migrating:
- The administration API has been completely reworked.
Some calls to the `/v1/` endpoints will still work but most will not.
New endpoints are prefixed by `/v2/`. **You will need to update all your code that makes use of the admin API.**
- `replication_mode` is no longer a supported configuration parameter,
please use `replication_factor` and `consistency_mode` instead.
## Migration procedure
The migration to Garage v2.0 can be done with almost no downtime,
by restarting all nodes at once in the new version.
The migration steps are as follows:
1. Do a `garage repair --all-nodes --yes tables`, check the logs and check that
all data seems to be synced correctly between nodes. If you have time, do
additional `garage repair` procedures (`blocks`, `versions`, `block_refs`,
etc.)
2. Ensure you have a snapshot of your Garage installation that you can restore
to in case the upgrade goes wrong, with one of the following options:
- You may use the `garage meta snapshot --all` command
to make a backup snapshot of the metadata directories of your nodes
for backup purposes. Once this command has completed, copy the following
files and directories from the `metadata_dir` of all your nodes
to somewhere safe: `snapshots`, `cluster_layout`, `data_layout`,
`node_key`, `node_key.pub`. (If you have set the `metadata_snapshots_dir`
to a different value in your config file, back up that directory instead.)
- If you are running a filesystem such as ZFS or BTRFS that support
snapshotting, you can create a filesystem-level snapshot of the `metadata_dir`
of all your nodes to be used as a restoration point if needed.
- You may also make a back-up manually: turn off each node
individually; back up its metadata folder (for instance, use the following
command if your metadata directory is `/var/lib/garage/meta`: `cd
/var/lib/garage ; tar -acf meta-v1.0.tar.zst meta/`); turn it back on
again. This will allow you to take a backup of all nodes without
impacting global cluster availability. You can do all nodes of a single
zone at once as this does not impact the availability of Garage.
3. Prepare your updated binaries and configuration files for Garage v2.0.
**Remember to update your configuration file to remove `replication_mode` and replace it by `replication_factor`.**
4. Shut down all v1.0 nodes simultaneously, and restart them all simultaneously
in v2.0. Use your favorite deployment tool (Ansible, Kubernetes, Nomad) to
achieve this as fast as possible. Garage v2.0 should be in a working state
as soon as enough nodes have started.
5. Monitor your cluster in the following hours to see if it works well under
your production load.
@@ -1,6 +1,6 @@
+++
title = "Testing strategy"
weight = 100
weight = 30
+++
@@ -28,16 +28,16 @@ We should try to test in least invasive ways, i.e. minimize the impact of the te
- Not making `garage` a shared library (launch using `execve`, it's perfectly fine)
Instead, we should focus on building a clean outer interface for the `garage` binary,
for example loading configuration using environment variables instead of the configuration file if that's helpful for writing the tests.
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 source code clean and focused
- 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 useful at some later point but without knowing precisely why/when.
Never do anything just because it looks nice or because we "think" it might be 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
@@ -71,3 +71,5 @@ Interesting blog posts on the blog of the Sled database:
Misc:
- [mutagen](https://github.com/llogiq/mutagen) - mutation testing is a way to assert our test quality by mutating the code and see if the mutation makes the tests fail
- [fuzzing](https://rust-fuzz.github.io/book/) - cargo supports fuzzing, it could be a way to test our software reliability in presence of garbage data.
+61 -85
View File
@@ -13,12 +13,8 @@ We will bump the version numbers prefixed to each API endpoint each time the syn
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, and was
changed several times.
**THIS DOCUMENT IS DEPRECATED.** We now have an OpenAPI spec which is automatically generated
from Garage's source code and is always up-to-date. See `doc/api/garage-admin-v2.html`.
Text in this document is no longer kept in sync with the admin API's actual behavior.
The Garage administration API was introduced in version 0.7.2, this document
does not apply to older versions of Garage.
## Access control
@@ -56,28 +52,34 @@ 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 `/v2/GetClusterHealth` for an API that also returns JSON output.
### Other special endpoints
#### CheckDomain `GET /check?domain=<domain>`
Checks whether this Garage cluster serves a website for domain `<domain>`.
Returns HTTP 200 Ok if yes, or HTTP 4xx if no website is available for this domain.
See `/v1/health` for an API that also returns JSON output.
### Cluster operations
#### GetClusterStatus `GET /v2/GetClusterStatus`
#### 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": "v0.10.0",
"garageFeatures": [
"k2v",
"lmdb",
"sqlite",
"metrics",
"bundled-libs"
],
"rustVersion": "1.68.0",
"dbEngine": "LMDB (using Heed crate)",
"layoutVersion": 5,
"nodes": [
{
@@ -167,7 +169,7 @@ Example response body:
}
```
#### GetClusterHealth `GET /v2/GetClusterHealth`
#### GetClusterHealth `GET /v1/health`
Returns the cluster's current health in JSON format, with the following variables:
@@ -176,7 +178,7 @@ Returns the cluster's current health in JSON format, with the following variable
- degraded: Garage node is not connected to all storage nodes, but a quorum of write nodes is available for all partitions
- unavailable: a quorum of write nodes is not available for some partitions
- `knownNodes`: the number of nodes this Garage node has had a TCP connection to since the daemon started
- `connectedNodes`: the number of nodes this Garage node currently has an open connection to
- `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)
@@ -200,7 +202,7 @@ Example response body:
}
```
#### ConnectClusterNodes `POST /v2/ConnectClusterNodes`
#### ConnectClusterNodes `POST /v1/connect`
Instructs this Garage node to connect to other Garage nodes at specified addresses.
@@ -230,7 +232,7 @@ Example response:
]
```
#### GetClusterLayout `GET /v2/GetClusterLayout`
#### GetClusterLayout `GET /v1/layout`
Returns the cluster's current layout in JSON, including:
@@ -291,7 +293,7 @@ Example response body:
}
```
#### UpdateClusterLayout `POST /v2/UpdateClusterLayout`
#### UpdateClusterLayout `POST /v1/layout`
Send modifications to the cluster layout. These modifications will
be included in the staged role changes, visible in subsequent calls
@@ -328,7 +330,7 @@ This returns the new cluster layout with the proposed staged changes,
as returned by GetClusterLayout.
#### ApplyClusterLayout `POST /v2/ApplyClusterLayout`
#### ApplyClusterLayout `POST /v1/layout/apply`
Applies to the cluster the layout changes currently registered as
staged layout changes.
@@ -348,11 +350,23 @@ 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 /v2/RevertClusterLayout`
#### RevertClusterLayout `POST /v1/layout/revert`
Clears all of the staged layout changes.
This requests contains an empty body.
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.
@@ -360,7 +374,7 @@ as returned by GetClusterLayout.
### Access key operations
#### ListKeys `GET /v2/ListKeys`
#### ListKeys `GET /v1/key`
Returns all API access keys in the cluster.
@@ -379,8 +393,8 @@ Example response:
]
```
#### GetKeyInfo `GET /v2/GetKeyInfo?id=<access key id>`
#### GetKeyInfo `GET /v2/GetKeyInfo?search=<pattern>`
#### GetKeyInfo `GET /v1/key?id=<acces key id>`
#### GetKeyInfo `GET /v1/key?search=<pattern>`
Returns information about the requested API access key.
@@ -388,7 +402,7 @@ If `id` is set, the key is looked up using its exact identifier (faster).
If `search` is set, the key is looked up using its name or prefix
of identifier (slower, all keys are enumerated to do this).
Optionally, the query parameter `showSecretKey=true` can be set to reveal the
Optionnally, the query parameter `showSecretKey=true` can be set to reveal the
associated secret access key.
Example response:
@@ -454,7 +468,7 @@ Example response:
}
```
#### CreateKey `POST /v2/CreateKey`
#### CreateKey `POST /v1/key`
Creates a new API access key.
@@ -469,7 +483,7 @@ Request body format:
This returns the key info, including the created secret key,
in the same format as the result of GetKeyInfo.
#### ImportKey `POST /v2/ImportKey`
#### ImportKey `POST /v1/key/import`
Imports an existing API key.
This will check that the imported key is in the valid format, i.e.
@@ -487,7 +501,7 @@ Request body format:
This returns the key info in the same format as the result of GetKeyInfo.
#### UpdateKey `POST /v2/UpdateKey?id=<access key id>`
#### UpdateKey `POST /v1/key?id=<acces key id>`
Updates information about the specified API access key.
@@ -509,14 +523,14 @@ The possible flags in `allow` and `deny` are: `createBucket`.
This returns the key info in the same format as the result of GetKeyInfo.
#### DeleteKey `POST /v2/DeleteKey?id=<access key id>`
#### DeleteKey `DELETE /v1/key?id=<acces key id>`
Deletes an API access key.
### Bucket operations
#### ListBuckets `GET /v2/ListBuckets`
#### ListBuckets `GET /v1/bucket`
Returns all storage buckets in the cluster.
@@ -558,8 +572,8 @@ Example response:
]
```
#### GetBucketInfo `GET /v2/GetBucketInfo?id=<bucket id>`
#### GetBucketInfo `GET /v2/GetBucketInfo?globalAlias=<alias>`
#### GetBucketInfo `GET /v1/bucket?id=<bucket id>`
#### GetBucketInfo `GET /v1/bucket?globalAlias=<alias>`
Returns information about the requested storage bucket.
@@ -602,7 +616,7 @@ Example response:
}
```
#### CreateBucket `POST /v2/CreateBucket`
#### CreateBucket `POST /v1/bucket`
Creates a new storage bucket.
@@ -642,7 +656,7 @@ or no alias at all.
Technically, you can also specify both `globalAlias` and `localAlias` and that would create
two aliases, but I don't see why you would want to do that.
#### UpdateBucket `POST /v2/UpdateBucket?id=<bucket id>`
#### UpdateBucket `PUT /v1/bucket?id=<bucket id>`
Updates configuration of the given bucket.
@@ -674,38 +688,16 @@ In `quotas`: new values of `maxSize` and `maxObjects` must both be specified, or
to remove the quotas. An absent value will be considered the same as a `null`. It is not possible
to change only one of the two quotas.
#### DeleteBucket `POST /v2/DeleteBucket?id=<bucket id>`
#### 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!
#### CleanupIncompleteUploads `POST /v2/CleanupIncompleteUploads`
Cleanup all incomplete uploads in a bucket that are older than a specified number
of seconds.
Request body format:
```json
{
"bucketId": "e6a14cd6a27f48684579ec6b381c078ab11697e6bc8513b72b2f5307e25fff9b",
"olderThanSecs": 3600
}
```
Response format
```json
{
"uploadsDeleted": 12
}
```
### Operations on permissions for keys on buckets
#### AllowBucketKey `POST /v2/AllowBucketKey`
#### BucketAllowKey `POST /v1/bucket/allow`
Allows a key to do read/write/owner operations on a bucket.
@@ -726,7 +718,7 @@ Request body format:
Flags in `permissions` which have the value `true` will be activated.
Other flags will remain unchanged.
#### DenyBucketKey `POST /v2/DenyBucketKey`
#### BucketDenyKey `POST /v1/bucket/deny`
Denies a key from doing read/write/owner operations on a bucket.
@@ -750,35 +742,19 @@ Other flags will remain unchanged.
### Operations on bucket aliases
#### AddBucketAlias `POST /v2/AddBucketAlias`
#### GlobalAliasBucket `PUT /v1/bucket/alias/global?id=<bucket id>&alias=<global alias>`
Creates an alias for a bucket in the namespace of a specific access key.
To create a global alias, specify the `globalAlias` field.
To create a local alias, specify the `localAlias` and `accessKeyId` fields.
Empty body. Creates a global alias for a bucket.
Request body format:
#### GlobalUnaliasBucket `DELETE /v1/bucket/alias/global?id=<bucket id>&alias=<global alias>`
```json
{
"bucketId": "e6a14cd6a27f48684579ec6b381c078ab11697e6bc8513b72b2f5307e25fff9b",
"globalAlias": "my-bucket"
}
```
Removes a global alias for a bucket.
or:
#### LocalAliasBucket `PUT /v1/bucket/alias/local?id=<bucket id>&accessKeyId=<access key ID>&alias=<local alias>`
```json
{
"bucketId": "e6a14cd6a27f48684579ec6b381c078ab11697e6bc8513b72b2f5307e25fff9b",
"accessKeyId": "GK31c2f218a2e44f485b94239e",
"localAlias": "my-bucket"
}
```
Empty body. Creates a local alias for a bucket in the namespace of a specific access key.
#### RemoveBucketAlias `POST /v2/RemoveBucketAlias`
#### LocalUnaliasBucket `DELETE /v1/bucket/alias/local?id=<bucket id>&accessKeyId<access key ID>&alias=<local alias>`
Removes an alias for a bucket in the namespace of a specific access key.
To remove a global alias, specify the `globalAlias` field.
To remove a local alias, specify the `localAlias` and `accessKeyId` fields.
Removes a local alias for a bucket in the namespace of a specific access key.
Request body format: same as AddBucketAlias.
+7 -7
View File
@@ -35,7 +35,7 @@ Triples in K2V are constituted of three fields:
partition key in which the client wants to read/delete lists of items
- a sort key (`sk`), an utf8 string that defines the index of the triplet inside its
partition; triplets are uniquely identified by their partition key + sort key
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
@@ -74,7 +74,7 @@ are obsoleted by the new write.
**Basic insertion.** To insert a new value `v4` with context `[(node1, t2), (node2, t3)]`, in a
simple case where there was no insertion in-between reading the value
mentioned above and writing `v4`, and supposing that node2 receives the
mentionned above and writing `v4`, and supposing that node2 receives the
InsertItem query:
- `node2` generates a timestamp `t4` such that `t4 > t3`.
@@ -332,7 +332,7 @@ Inserts a single item. This request does not use JSON, the body is sent directly
To supersede previous values, the HTTP header `X-Garage-Causality-Token` should
be set to the causality token returned by a previous read on this key. This
header can be omitted for the first writes to the key.
header can be ommitted for the first writes to the key.
Example query:
@@ -397,7 +397,7 @@ smallest partition key that exists. It returns partition keys in increasing
order, or decreasing order if `reverse` is set to `true`,
and stops when either of the following conditions is met:
1. if `end` is specified, the partition key `end` is reached or surpassed (if it
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
@@ -491,7 +491,7 @@ the triplet is inserted for the first time, the causality token should be set to
The value is expected to be a base64-encoded binary blob. The value `null` can
also be used to delete the triplet while preserving causality information: this
allows to know if a delete has happened concurrently with an insert, in which
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
@@ -540,7 +540,7 @@ JSON struct with the following fields:
For each of the searches, triplets are listed and returned separately. The
semantics of `prefix`, `start`, `end`, `limit` and `reverse` are the same as for ReadIndex. The
additional parameter `singleItem` allows to get a single item, whose sort key
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.
@@ -562,7 +562,7 @@ token>", v: ["<value1>", ...] }`, with the following fields:
- in case of concurrent update and deletion, a `null` is added to the list of concurrent values
- if the `tombstones` query parameter is set to `true`, tombstones are returned
for items that have been deleted (this can be useful for inserting after an
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
+1 -1
View File
@@ -59,7 +59,7 @@ To link the effective storage capacity of the cluster to partition assignment, w
\end{equation}
This assumption is justified by the dispersion of the hashing function, when the number of partitions is small relative to the number of stored blocks.
Every node $n$ will store some number $p_n$ of partitions (it is the number of partitions $p$ such that $n$ appears in the $\alpha_p$). Hence the partitions stored by $n$ (and hence all partitions by our assumption) have there size bounded by $c_n/p_n$. This remark leads us to define the optimal size that we will want to maximize:
Every node $n$ wille store some number $p_n$ of partitions (it is the number of partitions $p$ such that $n$ appears in the $\alpha_p$). Hence the partitions stored by $n$ (and hence all partitions by our assumption) have there size bounded by $c_n/p_n$. This remark leads us to define the optimal size that we will want to maximize:
\begin{equation}
\label{eq:optimal}
+10 -10
View File
@@ -38,7 +38,7 @@ We would like to compute an assignment of nodes to partitions. We will impose so
\end{equation}
This assumption is justified by the dispersion of the hashing function, when the number of partitions is small relative to the number of stored large objects.
Every node $n$ will store some number $k_n$ of partitions. Hence the partitions stored by $n$ (and hence all partitions by our assumption) have there size bounded by $c_n/k_n$. This remark leads us to define the optimal size that we will want to maximize:
Every node $n$ wille store some number $k_n$ of partitions. Hence the partitions stored by $n$ (and hence all partitions by our assumption) have there size bounded by $c_n/k_n$. This remark leads us to define the optimal size that we will want to maximize:
\begin{equation}
\label{eq:optimal}
@@ -62,7 +62,7 @@ For now, in the following, we ask the following redundancy constraint:
\textbf{Mode 3:} every partition needs to be assignated to three nodes. We try to spread the three nodes over different zones as much as possible.
\textbf{Warning:} This is a working document written incrementally. The last version of the algorithm is the \textbf{parametric assignment} described in the next section.
\textbf{Warning:} This is a working document written incrementaly. The last version of the algorithm is the \textbf{parametric assignment} described in the next section.
\section{Computation of a parametric assignment}
@@ -318,7 +318,7 @@ $$
$$
which is the universal upper bound on $s^*$. Hence any optimal utilization $(n_v)$ can be modified to another optimal utilization such that $n_v\ge \hat{n}_v$
Because $z_0$ cannot store more than $N$ partition occurrences, in any assignment, at least $2N$ partitions must be assignated to the zones $Z\setminus\{z_0\}$. Let $C_0 = C-c_{z_0}$. Suppose that there exists a zone $z_1\neq z_0$ such that $c_{z_1}/C_0 \ge 1/2$. Then, with the same argument as for $z_0$, we can define
Because $z_0$ cannot store more than $N$ partition occurences, in any assignment, at least $2N$ partitions must be assignated to the zones $Z\setminus\{z_0\}$. Let $C_0 = C-c_{z_0}$. Suppose that there exists a zone $z_1\neq z_0$ such that $c_{z_1}/C_0 \ge 1/2$. Then, with the same argument as for $z_0$, we can define
$$\hat{n}_v = \left\lfloor\frac{c_v}{c_{z_1}}N\right\rfloor$$
for every $v\in z_1$.
@@ -351,7 +351,7 @@ Define $3N$ tokens $t_1,\ldots, t_{3N}\in V$ as follows:
Then for $1\le i \le N$, define the triplet $T_i$ to be
$(t_i, t_{i+N}, t_{i+2N})$. Since the same nodes of a zone appear contiguously, the three nodes of a triplet must belong to three distinct zones.
However simple, this solution to go from an utilization to an assignment has the drawback of not spreading the triplets: a node will tend to be associated to the same two other nodes for many partitions. Hence, during data transfer, it will tend to use only two link, instead of spreading the bandwidth use over many other links to other nodes. To achieve this goal, we will reframe the search of an assignment as a flow problem. and in the flow algorithm, we will introduce randomness in the order of exploration. This will be sufficient to obtain a good dispersion of the triplets.
However simple, this solution to go from an utilization to an assignment has the drawback of not spreading the triplets: a node will tend to be associated to the same two other nodes for many partitions. Hence, during data transfer, it will tend to use only two link, instead of spreading the bandwith use over many other links to other nodes. To achieve this goal, we will reframe the search of an assignment as a flow problem. and in the flow algorithm, we will introduce randomness in the order of exploration. This will be sufficient to obtain a good dispersion of the triplets.
\begin{figure}
\centering
@@ -436,7 +436,7 @@ T_3=(b,c,d').
$$
One can check that in this case, it is impossible to minimize both the number of zone and node changes.
Because of the redundancy constraint, we cannot use a greedy algorithm to just replace nodes in the triplets to try to get the new utilization rate: this could lead to blocking situation where there is still a hole to fill in a triplet but no available node satisfies the zone separation constraint. To circumvent this issue, we propose an algorithm based on finding cycles in a graph encoding of the assignment. As in section \ref{sec:opt_assign}, we can explore the neighbours in a random order in the graph algorithms, to spread the triplets distribution.
Because of the redundancy constraint, we cannot use a greedy algorithm to just replace nodes in the triplets to try to get the new utilization rate: this could lead to blocking situation where there is still a hole to fill in a triplet but no available node satisfies the zone separation constraint. To circumvent this issue, we propose an algorithm based on finding cycles in a graph encoding of the assignment. As in section \ref{sec:opt_assign}, we can explore the neigbours in a random order in the graph algorithms, to spread the triplets distribution.
\subsubsection{Minimizing the zone discrepancy}
@@ -550,8 +550,8 @@ We give some considerations of worst case complexity for these algorithms. In th
Algorithm \ref{alg:util} can be implemented with complexity $O(\#V^2)$. The complexity of the function call at line \ref{lin:subutil} is $O(\#V)$. The difference between the sum of the subutilizations and $3N$ is at most the sum of the rounding errors when computing the $\hat{n}_v$. Hence it is bounded by $\#V$ and the loop at line \ref{lin:loopsub} is iterated at most $\#V$ times. Finding the minimizing $v$ at line \ref{lin:findmin} takes $O(\#V)$ operations (naively, we could also use a heap).
Algorithm \ref{alg:opt} can be implemented with complexity $O(N^3\times \#Z)$. The flow graph has $O(N+\#Z)$ vertices and $O(N\times \#Z)$ edges. Dinic's algorithm has complexity $O(\#\mathrm{Vertices}^2\#\mathrm{Edges})$ hence in our case it is $O(N^3\times \#Z)$.
Algorithm \ref{alg:mini} can be implemented with complexity $O(N^3\# Z)$ under \eqref{hyp:A} and $O(N^3 \#Z \#V)$ under \eqref{hyp:B}.
Algorithm \ref{alg:mini} can be implented with complexity $O(N^3\# Z)$ under \eqref{hyp:A} and $O(N^3 \#Z \#V)$ under \eqref{hyp:B}.
The graph $G_T$ has $O(N)$ vertices and $O(N\times \#Z)$ edges under assumption \eqref{hyp:A} and respectively $O(N\times \#Z)$ vertices and $O(N\times \#V)$ edges under assumption \eqref{hyp:B}. The loop at line \ref{lin:repeat} is iterated at most $N$ times since the distance between $T$ and $T'$ decreases at every iteration. Bellman-Ford algorithm has complexity $O(\#\mathrm{Vertices}\#\mathrm{Edges})$, which in our case amounts to $O(N^2\# Z)$ under \eqref{hyp:A} and $O(N^2 \#Z \#V)$ under \eqref{hyp:B}.
\begin{algorithm}
@@ -637,7 +637,7 @@ We try to maximize $s^*$ defined in \eqref{eq:optimal}. So we can compute the op
\subsection{Computation of a candidate assignment}
To compute a candidate assignment (that does not optimize zone spreading nor distance to a previous assignment yet), we can use the following flow problem.
To compute a candidate assignment (that does not optimize zone spreading nor distance to a previous assignment yet), we can use the folowing flow problem.
Define the oriented weighted graph $(X,E)$. The set of vertices $X$ contains the source $\mathbf{s}$, the sink $\mathbf{t}$, vertices
$\mathbf{x}_p, \mathbf{u}^+_p, \mathbf{u}^-_p$ for every partition $p$, vertices $\mathbf{y}_{p,z}$ for every partition $p$ and zone $z$, and vertices $\mathbf{z}_v$ for every node $v$.
@@ -680,14 +680,14 @@ Given the flow $f$, let $G_f=(X',E_f)$ be the multi-graph where $X' = X\setminus
\end{itemize}
To summarize, arcs are oriented left to right if they correspond to a presence of flow in $f$, and right to left if they correspond to an absence of flow. They are positively weighted if we want them to stay at their current state, and negatively if we want them to switch. Let us compute the weight of such graph.
\begin{multiline*}
\begin{multline*}
w(G_f) = \sum_{e\in E_f} w(e_f) \\
=
(\alpha - \beta -\gamma) N_1 + (\alpha +\beta - \gamma) N_2 + (\alpha+\beta+\gamma) N_3
\\ +
\#V\times N - 4 \sum_p 3-\#(T_p\cap T'_p) \\
=(\#V-12+\alpha-\beta-\gamma)\times N + 4Q_V + 2\beta N_2 + 2(\beta+\gamma) N_3 \\
\end{multiline*}
\end{multline*}
As for the mode 3-strict, one can check that the difference of two such graphs corresponding to the same $(n_v)$ is always eulerian. Hence we can navigate in this class with the same greedy algorithm that discovers positive cycles and flips them.
-17
View File
@@ -1,17 +0,0 @@
*
!*.txt
!*.md
!assets
!.gitignore
!*.svg
!*.png
!*.jpg
!*.tex
!Makefile
!.gitignore
!assets/*.drawio.pdf
!talk.pdf
-19
View File
@@ -1,19 +0,0 @@
ASSETS=../assets/lattice/lattice1.pdf_tex \
../assets/lattice/lattice2.pdf_tex \
../assets/lattice/lattice3.pdf_tex \
../assets/lattice/lattice4.pdf_tex \
../assets/lattice/lattice5.pdf_tex \
../assets/lattice/lattice6.pdf_tex \
../assets/lattice/lattice7.pdf_tex \
../assets/lattice/lattice8.pdf_tex \
../assets/logos/deuxfleurs.pdf \
../assets/timeline-22-24.pdf
talk.pdf: talk.tex $(ASSETS)
pdflatex talk.tex
%.pdf: %.svg
inkscape -D -z --file=$^ --export-pdf=$@
%.pdf_tex: %.svg
inkscape -D -z --file=$^ --export-pdf=$@ --export-latex
Binary file not shown.
-702
View File
@@ -1,702 +0,0 @@
\nonstopmode
\documentclass[aspectratio=169,xcolor={svgnames}]{beamer}
\usepackage[utf8]{inputenc}
% \usepackage[frenchb]{babel}
\usepackage{amsmath}
\usepackage{mathtools}
\usepackage{breqn}
\usepackage{multirow}
\usetheme{boxes}
\usepackage{graphicx}
\usepackage{import}
\usepackage{adjustbox}
\usepackage[absolute,overlay]{textpos}
%\useoutertheme[footline=authortitle,subsection=false]{miniframes}
%\useoutertheme[footline=authorinstitute,subsection=false]{miniframes}
\useoutertheme{infolines}
\setbeamertemplate{headline}{}
\beamertemplatenavigationsymbolsempty
\definecolor{TitleOrange}{RGB}{255,137,0}
\setbeamercolor{title}{fg=TitleOrange}
\setbeamercolor{frametitle}{fg=TitleOrange}
\definecolor{ListOrange}{RGB}{255,145,5}
\setbeamertemplate{itemize item}{\color{ListOrange}$\blacktriangleright$}
\definecolor{verygrey}{RGB}{70,70,70}
\setbeamercolor{normal text}{fg=verygrey}
\usepackage{tabu}
\usepackage{multicol}
\usepackage{vwcol}
\usepackage{stmaryrd}
\usepackage{graphicx}
\usepackage[normalem]{ulem}
\AtBeginSection[]{
\begin{frame}
\vfill
\centering
\begin{beamercolorbox}[sep=8pt,center,shadow=true,rounded=true]{title}
\usebeamerfont{title}\insertsectionhead\par%
\end{beamercolorbox}
\vfill
\end{frame}
}
\title{Garage, an S3 backend as reliable as possible}
\author{Garage Authors}
\date{JoSy S3, 2025-10-08}
\begin{document}
\begin{frame}
\centering
\includegraphics[width=.3\linewidth]{../../sticker/Garage.png}
\vspace{1em}
{\large\bf Garage, an S3 backend as reliable as possible}
\vspace{1em}
\url{https://garagehq.deuxfleurs.fr/}\\
\url{mailto:garagehq@deuxfleurs.fr}\\
\texttt{\#garage:deuxfleurs.fr} on Matrix
\end{frame}
\section{Meet Garage}
\begin{frame}
\frametitle{A non-profit initiative}
\begin{columns}[t]
\begin{column}{.2\textwidth}
\centering
\adjincludegraphics[width=.5\linewidth, valign=t]{../assets/logos/deuxfleurs.pdf}
\end{column}
\begin{column}{.8\textwidth}
\textbf{Part of a degrowth initiative}\\
Garage has been created at Deuxfleurs where we experiment running Internet services without datacenter on commodity and refurbished hardware.
\end{column}
\end{columns}
\vspace{2em}
\begin{columns}[t]
\begin{column}{.2\textwidth}
\centering
\adjincludegraphics[width=.5\linewidth, valign=t]{../assets/community.png}
\end{column}
\begin{column}{.8\textwidth}
\textbf{Developed by a community}\\
{\small Some recent contributors: Arthur C, Charles H, dongdigua, Etienne L, Jonah A, Julien K, Lapineige, MagicRR, Milas B, Niklas M, RockWolf, Schwitzd, trinity-1686a, Xavier S, babykart, Baptiste J, eddster2309, James O'C, Joker9944, Maximilien R, Renjaya RZ, Yureka...}
\end{column}
\end{columns}
\vspace{2em}
\begin{columns}[t]
\begin{column}{.2\textwidth}
\centering
\adjincludegraphics[width=.5\linewidth, valign=t]{../assets/logos/AGPLv3_Logo.png}
\end{column}
\begin{column}{.8\textwidth}
\textbf{Owned by nobody, open-core is impossible, zero VC money}\\
AGPL + no Contributor License Agreement = Garage ownership spreads among hundredth of contributors.
\end{column}
\end{columns}
\end{frame}
\begin{frame}
\frametitle{Getting support for Garage}
\begin{columns}[t]
\begin{column}{.2\textwidth}
\centering
\adjincludegraphics[width=.4\linewidth, valign=t]{../assets/alex.jpg}
\end{column}
\begin{column}{.4\textwidth}
\textbf{Alex Auvolat}\\
PhD; co-founder of Deuxfleurs\\
Garage maintainer, Freelance
\end{column}
\begin{column}{.3\textwidth}
\centering
\adjincludegraphics[width=.4\linewidth, valign=t]{../assets/support.png}
\end{column}
\begin{column}{.1\textwidth}
~
\end{column}
\end{columns}
\vspace{2em}
\begin{columns}[t]
\begin{column}{.2\textwidth}
\centering
\adjincludegraphics[width=.4\linewidth, valign=t]{../assets/quentin.jpg}
\end{column}
\begin{column}{.4\textwidth}
\textbf{Quentin Dufour}\\
PhD; co-founder of Deuxfleurs\\
Garage contributor, Freelance
\end{column}
\begin{column}{.4\textwidth}
For support requests, write at: \\
\url{garagehq@deuxfleurs.fr}
\end{column}
\end{columns}
\vspace{2em}
\begin{columns}[t]
\begin{column}{.2\textwidth}
\centering
\adjincludegraphics[width=.4\linewidth, valign=t]{../assets/armael.jpg}
\end{column}
\begin{column}{.4\textwidth}
\textbf{Armaël Guéneau}\\
PhD; member of Deuxfleurs\\
Garage contributor, Freelance
\end{column}
\begin{column}{.4\textwidth}
Eligible: email support, architecture design, specific feature development, etc.
\end{column}
\end{columns}
\end{frame}
\begin{frame}
\frametitle{Our initial goal}
\centering
\Large
Being a self-sovereign community to be free of our degrowth choice
$\big\downarrow$
As web citizens, datacenters are big black boxes. \\
We want to leave them to autonoumously manage our servers.
$\big\downarrow$
We want reliable services without relying on dedicated hardware or places.
\end{frame}
\begin{frame}
\frametitle{Building a resilient system with cheap stuff}
\only<1,4-7>{
\begin{itemize}
\item \textcolor<5->{gray}{Commodity hardware (e.g. old desktop PCs)\\
\vspace{.5em}
\visible<4->{{\footnotesize (can die at any time)}}}
\vspace{1.5em}
\item<5-> \textcolor<7->{gray}{Regular Internet (e.g. FTTB, FTTH) and power grid connections\\
\vspace{.5em}
\visible<6->{{\footnotesize (can be unavailable randomly)}}}
\vspace{1.5em}
\item<7-> \textbf{Geographical redundancy} (multi-site replication)
\end{itemize}
}
\only<2>{
\begin{center}
\includegraphics[width=.8\linewidth]{../assets/neptune.jpg}
\end{center}
}
\only<3>{
\begin{center}
\includegraphics[width=.8\linewidth]{../assets/atuin.jpg}
\end{center}
}
\only<8>{
\begin{center}
\includegraphics[width=.8\linewidth]{../assets/inframap_jdll2023.pdf}
\end{center}
}
\end{frame}
\begin{frame}
\frametitle{Object storage: a crucial component}
\begin{center}
\includegraphics[height=6em]{../assets/logos/Amazon-S3.jpg}
\hspace{3em}
\visible<2->{\includegraphics[height=5em]{../assets/logos/minio.png}}
\hspace{3em}
\visible<3>{\includegraphics[height=6em]{../../logo/garage_hires_crop.png}}
\end{center}
\vspace{1em}
S3: a de-facto standard, many compatible applications
\vspace{1em}
\visible<2->{MinIO is self-hostable but not suited for geo-distributed deployments}
\vspace{1em}
\visible<3->{\textbf{Garage is a self-hosted drop-in replacement for the Amazon S3 object store}}
\end{frame}
\begin{frame}
\frametitle{CRDTs / weak consistency instead of consensus}
\underline{Internally, Garage uses only CRDTs} (conflict-free replicated data types)
\vspace{2em}
Why not Raft, Paxos, ...? Issues of consensus algorithms:
\vspace{1em}
\begin{itemize}
\item<2-> \textbf{Software complexity}
\vspace{1em}
\item<3-> \textbf{Performance issues:}
\vspace{.5em}
\begin{itemize}
\item<4-> The leader is a \textbf{bottleneck} for all requests\\
\vspace{.5em}
\item<5-> \textbf{Sensitive to higher latency} between nodes
\vspace{.5em}
\item<6-> \textbf{Takes time to reconverge} when disrupted (e.g. node going down)
\end{itemize}
\end{itemize}
\end{frame}
\begin{frame}
\frametitle{The data model of object storage}
Object storage is basically a \textbf{key-value store}:
\vspace{.5em}
{\scriptsize
\begin{center}
\begin{tabular}{|l|p{7cm}|}
\hline
\textbf{Key: file path + name} & \textbf{Value: file data + metadata} \\
\hline
\hline
\texttt{index.html} &
\texttt{Content-Type: text/html; charset=utf-8} \newline
\texttt{Content-Length: 24929} \newline
\texttt{<binary blob>} \\
\hline
\texttt{img/logo.svg} &
\texttt{Content-Type: text/svg+xml} \newline
\texttt{Content-Length: 13429} \newline
\texttt{<binary blob>} \\
\hline
\texttt{download/index.html} &
\texttt{Content-Type: text/html; charset=utf-8} \newline
\texttt{Content-Length: 26563} \newline
\texttt{<binary blob>} \\
\hline
\end{tabular}
\end{center}
}
\vspace{1em}
\begin{itemize}
\item<2> Maps well to CRDT data types
\end{itemize}
\end{frame}
\begin{frame}
\frametitle{Performance gains in practice}
\begin{center}
\includegraphics[width=.8\linewidth]{../assets/perf/endpoint_latency_0.7_0.8_minio.png}
\end{center}
\end{frame}
% ======================================== OPERATING
% ======================================== OPERATING
% ======================================== OPERATING
\section{Production clusters}
\begin{frame}
\frametitle{Deployment kinds}
\includegraphics[width=.9\linewidth]{../assets/cluster_kind.png}
\vspace{1em}
\end{frame}
\begin{frame}
\frametitle{How big they are?}
\includegraphics[width=.9\linewidth]{../assets/cluster_size.png}
\vspace{1em}
\textit{"Petabyte storage setup for a video site. Nginx as CDN in-front using garage-s3-website feature. Each storage node has ~64TB storage with raid10, no replication within garage. 25gbit nic. haproxy to loadbalance across 5 nodes. mostly reads with very few writes."}
\vspace{1em}
\textit{"We currently manage 7 Garage nodes, 28TB total storage, 6M blocks for 3M objects and 4TB of object data. We have been running Garage in production for 2.5 years."}
\end{frame}
\begin{frame}
\frametitle{Operating Garage}
\begin{center}
\only<1-2>{
\includegraphics[width=.9\linewidth]{../assets/screenshots/garage_status_0.10.png}
\\\vspace{1em}
\visible<2>{\includegraphics[width=.9\linewidth]{../assets/screenshots/garage_status_unhealthy_0.10.png}}
}
\end{center}
\end{frame}
\begin{frame}
\frametitle{Garage's architecture}
\begin{center}
\only<1>{\includegraphics[width=.45\linewidth]{../assets/garage.drawio.pdf}}%
\only<2>{\includegraphics[width=.6\linewidth]{../assets/garage_sync.drawio.pdf}}%
\end{center}
\end{frame}
\begin{frame}
\frametitle{Digging deeper}
\begin{center}
\only<1>{\includegraphics[width=.9\linewidth]{../assets/screenshots/garage_stats_0.10.png}}
\only<2>{\includegraphics[width=.5\linewidth]{../assets/screenshots/garage_worker_list_0.10.png}}
\only<3>{\includegraphics[width=.6\linewidth]{../assets/screenshots/garage_worker_param_0.10.png}}
\end{center}
\end{frame}
\begin{frame}
\frametitle{Potential limitations and bottlenecks}
\begin{itemize}
\item Global:
\begin{itemize}
\item Max. $\sim$100 nodes per cluster (excluding gateways)
\end{itemize}
\vspace{1em}
\item Metadata:
\begin{itemize}
\item One big bucket = bottleneck, object list on 3 nodes only
\end{itemize}
\vspace{1em}
\item Block manager:
\begin{itemize}
\item Lots of small files on disk
\item Processing the resync queue can be slow
\end{itemize}
\end{itemize}
\end{frame}
\begin{frame}
\frametitle{Deployment advice for very large clusters}
\begin{itemize}
\item Metadata storage:
\begin{itemize}
\item ZFS mirror (x2) on fast NVMe
\item Use LMDB storage engine
\end{itemize}
\vspace{.5em}
\item Data block storage:
\begin{itemize}
\item Use Garage's native multi-HDD support
\item XFS on individual drives
\item Increase block size (1MB $\to$ 10MB, requires more RAM and good networking)
\item Tune \texttt{resync-tranquility} and \texttt{resync-worker-count} dynamically
\end{itemize}
\vspace{.5em}
\item Other :
\begin{itemize}
\item Split data over several buckets
\item Use less than 100 storage nodes
\item Use gateway nodes
\end{itemize}
\vspace{.5em}
\end{itemize}
\end{frame}
\begin{frame}
\frametitle{Focus on Deuxfleurs}
Host institutional websites, partnership with a web agency.
Matrix media backend.
Plan to use it as an email backend for an internally developed email server.
\end{frame}
% ======================================== TIMELINE
% ======================================== TIMELINE
% ======================================== TIMELINE
\section{Recent developments}
% ====================== v0.7.0 ===============================
\begin{frame}
\begin{center}
\includegraphics[width=.8\linewidth]{../assets/tl.drawio.png}
\end{center}
\end{frame}
\begin{frame}
\frametitle{April 2022 - Garage v0.7.0}
Focus on \underline{observability and ecosystem integration}
\vspace{2em}
\begin{itemize}
\item \textbf{Monitoring:} metrics and traces, using OpenTelemetry
\vspace{1em}
\item Replication modes with 1 or 2 copies / weaker consistency
\vspace{1em}
\item Kubernetes integration for node discovery
\vspace{1em}
\item Admin API (v0.7.2)
\end{itemize}
\end{frame}
\begin{frame}
\frametitle{Metrics (Prometheus + Grafana)}
\begin{center}
\includegraphics[width=.9\linewidth]{../assets/screenshots/grafana_dashboard.png}
\end{center}
\end{frame}
\begin{frame}
\frametitle{Traces (Jaeger)}
\begin{center}
\includegraphics[width=.8\linewidth]{../assets/screenshots/jaeger_listobjects.png}
\end{center}
\end{frame}
% ====================== v0.8.0 ===============================
\begin{frame}
\begin{center}
\includegraphics[width=.8\linewidth]{../assets/tl.drawio.png}
\end{center}
\end{frame}
\begin{frame}
\frametitle{November 2022 - Garage v0.8.0}
Focus on \underline{performance}
\vspace{2em}
\begin{itemize}
\item \textbf{Alternative metadata DB engines} (LMDB, Sqlite)
\vspace{1em}
\item \textbf{Performance improvements:} block streaming, various optimizations...
\vspace{1em}
\item Bucket quotas (max size, max \#objects)
\vspace{1em}
\item Quality of life improvements, observability, etc.
\end{itemize}
\end{frame}
\begin{frame}
\frametitle{About metadata DB engines}
\textbf{Issues with Sled:}
\vspace{1em}
\begin{itemize}
\item Huge files on disk
\vspace{.5em}
\item Unpredictable performance, especially on HDD
\vspace{.5em}
\item API limitations
\vspace{.5em}
\item Not actively maintained
\end{itemize}
\vspace{2em}
\textbf{LMDB:} very stable, good performance, file size is reasonable\\
\textbf{Sqlite} also available as a second choice
\vspace{1em}
Sled will be removed in Garage v1.0
\end{frame}
\begin{frame}
\frametitle{DB engine performance comparison}
\begin{center}
\includegraphics[width=.6\linewidth]{../assets/perf/db_engine.png}
\end{center}
NB: Sqlite was slow due to synchronous mode, now configurable
\end{frame}
\begin{frame}
\frametitle{Block streaming}
\begin{center}
\only<1>{\includegraphics[width=.8\linewidth]{../assets/schema-streaming-1.png}}
\only<2>{\includegraphics[width=.8\linewidth]{../assets/schema-streaming-2.png}}
\end{center}
\end{frame}
\begin{frame}
\frametitle{TTFB benchmark}
\begin{center}
\includegraphics[width=.8\linewidth]{../assets/perf/ttfb.png}
\end{center}
\end{frame}
\begin{frame}
\frametitle{Throughput benchmark}
\begin{center}
\includegraphics[width=.7\linewidth]{../assets/perf/io-0.7-0.8-minio.png}
\end{center}
\end{frame}
% ====================== v0.9.0 ===============================
\begin{frame}
\begin{center}
\includegraphics[width=.8\linewidth]{../assets/tl.drawio.png}
\end{center}
\end{frame}
\begin{frame}
\frametitle{October 2023 - Garage v0.9.0}
Focus on \underline{streamlining \& usability}
\vspace{2em}
\begin{itemize}
\item Support multiple HDDs per node
\vspace{1em}
\item S3 compatibility:
\vspace{1em}
\begin{itemize}
\item support basic lifecycle configurations
\vspace{.5em}
\item allow for multipart upload part retries
\end{itemize}
\vspace{1em}
\item LMDB by default, deprecation of Sled
\vspace{1em}
\item New layout computation algorithm
\end{itemize}
\end{frame}
\begin{frame}
\frametitle{Layout computation}
\begin{overprint}
\onslide<1>
\begin{center}
\includegraphics[width=\linewidth, trim=0 0 0 -4cm]{../assets/screenshots/garage_status_0.9_prod_zonehl.png}
\end{center}
\onslide<2>
\begin{center}
\includegraphics[width=.7\linewidth]{../assets/map.png}
\end{center}
\end{overprint}
\vspace{1em}
Garage stores replicas on different zones when possible
\end{frame}
\begin{frame}
\frametitle{What a "layout" is}
\textbf{A layout is a precomputed index table:}
\vspace{1em}
{\footnotesize
\begin{center}
\begin{tabular}{|l|l|l|l|}
\hline
\textbf{Partition} & \textbf{Node 1} & \textbf{Node 2} & \textbf{Node 3} \\
\hline
\hline
Partition 0 & df-ymk (bespin) & Abricot (scorpio) & Courgette (neptune) \\
\hline
Partition 1 & Ananas (scorpio) & Courgette (neptune) & df-ykl (bespin) \\
\hline
Partition 2 & df-ymf (bespin) & Celeri (neptune) & Abricot (scorpio) \\
\hline
\hspace{1em}$\vdots$ & \hspace{1em}$\vdots$ & \hspace{1em}$\vdots$ & \hspace{1em}$\vdots$ \\
\hline
Partition 255 & Concombre (neptune) & df-ykl (bespin) & Abricot (scorpio) \\
\hline
\end{tabular}
\end{center}
}
\vspace{2em}
\visible<2->{
The index table is built centrally using an optimal algorithm,\\
then propagated to all nodes
}
\vspace{1em}
\visible<3->{
\footnotesize
Oulamara, M., \& Auvolat, A. (2023). \emph{An algorithm for geo-distributed and redundant storage in Garage}.\\ arXiv preprint arXiv:2302.13798.
}
\end{frame}
% ====================== v1.0.0 ===============================
\begin{frame}
\begin{center}
\includegraphics[width=.8\linewidth]{../assets/tl.drawio.png}
\end{center}
\end{frame}
\begin{frame}
\frametitle{April 2024 - Garage v1.0.0}
Focus on \underline{consistency, security \& stability}
\vspace{2em}
\begin{itemize}
\item Fix consistency issues when reshuffling data (Jepsen testing)
\vspace{1em}
\item \textbf{Security audit} by Radically Open Security
\vspace{1em}
\item Misc. S3 features (SSE-C, checksums, ...) and compatibility fixes
\end{itemize}
\end{frame}
% ====================== v2.0.0 ===============================
\begin{frame}
\begin{center}
\includegraphics[width=.8\linewidth]{../assets/tl.drawio.png}
\end{center}
\end{frame}
\begin{frame}
\frametitle{Garage v2.0.0}
Focus on \underline{}
\vspace{2em}
\begin{itemize}
\item TODO
\end{itemize}
\end{frame}
\begin{frame}
\frametitle{Currently funding...}
\textit{...}
\end{frame}
\begin{frame}
\frametitle{We run community surveys}
\begin{center}
\includegraphics[width=.6\linewidth]{../assets/survey_requested_features.png}
\end{center}
\end{frame}
% ======================================== END
% ======================================== END
% ======================================== END
\begin{frame}
\frametitle{Where to find us}
\begin{center}
\includegraphics[width=.25\linewidth]{../../logo/garage_hires.png}\\
\vspace{-1em}
\url{https://garagehq.deuxfleurs.fr/}\\
\url{mailto:garagehq@deuxfleurs.fr}\\
\texttt{\#garage:deuxfleurs.fr} on Matrix
\vspace{1.5em}
\includegraphics[width=.06\linewidth]{../assets/logos/rust_logo.png}
\includegraphics[width=.13\linewidth]{../assets/logos/AGPLv3_Logo.png}
\end{center}
\end{frame}
\end{document}
%% vim: set ts=4 sw=4 tw=0 noet spelllang=en :
Binary file not shown.

Before

Width:  |  Height:  |  Size: 30 KiB

Binary file not shown.

Before

Width:  |  Height:  |  Size: 50 KiB

Binary file not shown.

Before

Width:  |  Height:  |  Size: 24 KiB

Binary file not shown.

Before

Width:  |  Height:  |  Size: 6.1 KiB

Binary file not shown.

Before

Width:  |  Height:  |  Size: 123 KiB

Binary file not shown.

Before

Width:  |  Height:  |  Size: 7.9 KiB

Binary file not shown.

Before

Width:  |  Height:  |  Size: 183 KiB

Generated
+89 -30
View File
@@ -1,28 +1,38 @@
{
"nodes": {
"crane": {
"cargo2nix": {
"inputs": {
"flake-compat": [
"flake-compat"
],
"flake-utils": "flake-utils",
"nixpkgs": [
"nixpkgs"
],
"rust-overlay": "rust-overlay"
},
"locked": {
"lastModified": 1737689766,
"narHash": "sha256-ivVXYaYlShxYoKfSo5+y5930qMKKJ8CLcAoIBPQfJ6s=",
"owner": "ipetkov",
"repo": "crane",
"rev": "6fe74265bbb6d016d663b1091f015e2976c4a527",
"lastModified": 1666087781,
"narHash": "sha256-trKVdjMZ8mNkGfLcY5LsJJGtdV3xJDZnMVrkFjErlcs=",
"owner": "Alexis211",
"repo": "cargo2nix",
"rev": "a7a61179b66054904ef6a195d8da736eaaa06c36",
"type": "github"
},
"original": {
"owner": "ipetkov",
"repo": "crane",
"rev": "6fe74265bbb6d016d663b1091f015e2976c4a527",
"owner": "Alexis211",
"repo": "cargo2nix",
"rev": "a7a61179b66054904ef6a195d8da736eaaa06c36",
"type": "github"
}
},
"flake-compat": {
"locked": {
"lastModified": 1761640442,
"narHash": "sha256-AtrEP6Jmdvrqiv4x2xa5mrtaIp3OEe8uBYCDZDS+hu8=",
"lastModified": 1688025799,
"narHash": "sha256-ktpB4dRtnksm9F5WawoIkEneh1nrEvuxb5lJFt1iOyw=",
"owner": "nix-community",
"repo": "flake-compat",
"rev": "4a56054d8ffc173222d09dad23adf4ba946c8884",
"rev": "8bf105319d44f6b9f0d764efa4fdef9f1cc9ba1c",
"type": "github"
},
"original": {
@@ -36,11 +46,29 @@
"systems": "systems"
},
"locked": {
"lastModified": 1731533236,
"narHash": "sha256-l0KFg5HjrsfsO/JpG+r7fRrqm12kzFHyUHqHCVpMMbI=",
"lastModified": 1681202837,
"narHash": "sha256-H+Rh19JDwRtpVPAWp64F+rlEtxUWBAQW28eAi3SRSzg=",
"owner": "numtide",
"repo": "flake-utils",
"rev": "11707dc2f618dd54ca8739b309ec4fc024de578b",
"rev": "cfacdce06f30d2b68473a46042957675eebb3401",
"type": "github"
},
"original": {
"owner": "numtide",
"repo": "flake-utils",
"type": "github"
}
},
"flake-utils_2": {
"inputs": {
"systems": "systems_2"
},
"locked": {
"lastModified": 1681202837,
"narHash": "sha256-H+Rh19JDwRtpVPAWp64F+rlEtxUWBAQW28eAi3SRSzg=",
"owner": "numtide",
"repo": "flake-utils",
"rev": "cfacdce06f30d2b68473a46042957675eebb3401",
"type": "github"
},
"original": {
@@ -51,47 +79,63 @@
},
"nixpkgs": {
"locked": {
"lastModified": 1763977559,
"narHash": "sha256-g4MKqsIRy5yJwEsI+fYODqLUnAqIY4kZai0nldAP6EM=",
"lastModified": 1682109806,
"narHash": "sha256-d9g7RKNShMLboTWwukM+RObDWWpHKaqTYXB48clBWXI=",
"owner": "NixOS",
"repo": "nixpkgs",
"rev": "cfe2c7d5b5d3032862254e68c37a6576b633d632",
"rev": "2362848adf8def2866fabbffc50462e929d7fffb",
"type": "github"
},
"original": {
"owner": "NixOS",
"ref": "nixpkgs-unstable",
"repo": "nixpkgs",
"type": "github"
}
},
"nixpkgs_2": {
"locked": {
"lastModified": 1707091808,
"narHash": "sha256-LahKBAfGbY836gtpVNnWwBTIzN7yf/uYM/S0g393r0Y=",
"owner": "NixOS",
"repo": "nixpkgs",
"rev": "9f2ee8c91ac42da3ae6c6a1d21555f283458247e",
"type": "github"
},
"original": {
"owner": "NixOS",
"repo": "nixpkgs",
"rev": "cfe2c7d5b5d3032862254e68c37a6576b633d632",
"rev": "9f2ee8c91ac42da3ae6c6a1d21555f283458247e",
"type": "github"
}
},
"root": {
"inputs": {
"crane": "crane",
"cargo2nix": "cargo2nix",
"flake-compat": "flake-compat",
"flake-utils": "flake-utils",
"nixpkgs": "nixpkgs",
"rust-overlay": "rust-overlay"
"flake-utils": [
"cargo2nix",
"flake-utils"
],
"nixpkgs": "nixpkgs_2"
}
},
"rust-overlay": {
"inputs": {
"nixpkgs": [
"nixpkgs"
]
"flake-utils": "flake-utils_2",
"nixpkgs": "nixpkgs"
},
"locked": {
"lastModified": 1763952169,
"narHash": "sha256-+PeDBD8P+NKauH+w7eO/QWCIp8Cx4mCfWnh9sJmy9CM=",
"lastModified": 1707271822,
"narHash": "sha256-/DZsoPH5GBzOpVEGz5PgJ7vh8Q6TcrJq5u8FcBjqAfI=",
"owner": "oxalica",
"repo": "rust-overlay",
"rev": "ab726555a9a72e6dc80649809147823a813fa95b",
"rev": "7a94fe7690d2bdfe1aab475382a505e14dc114a6",
"type": "github"
},
"original": {
"owner": "oxalica",
"repo": "rust-overlay",
"rev": "ab726555a9a72e6dc80649809147823a813fa95b",
"type": "github"
}
},
@@ -109,6 +153,21 @@
"repo": "default",
"type": "github"
}
},
"systems_2": {
"locked": {
"lastModified": 1681028828,
"narHash": "sha256-Vy1rq5AaRuLzOxct8nz4T6wlgyUR7zLU309k9mBC768=",
"owner": "nix-systems",
"repo": "default",
"rev": "da67096a3b9bf56a91d16901293e51ba5b49a27e",
"type": "github"
},
"original": {
"owner": "nix-systems",
"repo": "default",
"type": "github"
}
}
},
"root": "root",
+64 -75
View File
@@ -2,99 +2,88 @@
description =
"Garage, an S3-compatible distributed object store for self-hosted deployments";
# Nixpkgs 25.05 as of 2025-11-24
# Nixpkgs 23.11 as of 2024-02-07, has rustc v1.73
inputs.nixpkgs.url =
"github:NixOS/nixpkgs/cfe2c7d5b5d3032862254e68c37a6576b633d632";
# Rust overlay as of 2025-11-24
inputs.rust-overlay.url =
"github:oxalica/rust-overlay/ab726555a9a72e6dc80649809147823a813fa95b";
inputs.rust-overlay.inputs.nixpkgs.follows = "nixpkgs";
# Crane as of 2025-01-24
inputs.crane.url = "github:ipetkov/crane/6fe74265bbb6d016d663b1091f015e2976c4a527";
"github:NixOS/nixpkgs/9f2ee8c91ac42da3ae6c6a1d21555f283458247e";
inputs.flake-compat.url = "github:nix-community/flake-compat";
inputs.flake-utils.url = "github:numtide/flake-utils";
outputs = { self, nixpkgs, flake-utils, crane, rust-overlay, ... }:
inputs.cargo2nix = {
# As of 2022-10-18: two small patches over unstable branch, one for clippy and one to fix feature detection
url = "github:Alexis211/cargo2nix/a7a61179b66054904ef6a195d8da736eaaa06c36";
# As of 2023-04-25:
# - my two patches were merged into unstable (one for clippy and one to "fix" feature detection)
# - rustc v1.66
# url = "github:cargo2nix/cargo2nix/8fb57a670f7993bfc24099c33eb9c5abb51f29a2";
# Rust overlay as of 2024-02-07
inputs.rust-overlay.url =
"github:oxalica/rust-overlay/7a94fe7690d2bdfe1aab475382a505e14dc114a6";
inputs.nixpkgs.follows = "nixpkgs";
inputs.flake-compat.follows = "flake-compat";
};
inputs.flake-utils.follows = "cargo2nix/flake-utils";
outputs = { self, nixpkgs, cargo2nix, flake-utils, ... }:
let
git_version = self.lastModifiedDate;
compile = import ./nix/compile.nix;
in
flake-utils.lib.eachDefaultSystem (system:
let
pkgs = nixpkgs.legacyPackages.${system};
packageFor = target: release: (compile {
inherit system target nixpkgs crane rust-overlay release;
}).garage;
testWith = extraTestEnv: (compile {
inherit system nixpkgs crane rust-overlay extraTestEnv;
release = false;
}).garage-test;
lints = (compile {
inherit system nixpkgs crane rust-overlay;
release = false;
});
in
{
packages = {
# default = native release build
default = packageFor null true;
# <arch> = cross-compiled, statically-linked release builds
amd64 = packageFor "x86_64-unknown-linux-musl" true;
i386 = packageFor "i686-unknown-linux-musl" true;
arm64 = packageFor "aarch64-unknown-linux-musl" true;
arm = packageFor "armv6l-unknown-linux-musl" true;
# dev = native dev build
dev = packageFor null false;
# test = cargo test
tests = testWith {};
tests-lmdb = testWith {
GARAGE_TEST_INTEGRATION_DB_ENGINE = "lmdb";
};
tests-sqlite = testWith {
GARAGE_TEST_INTEGRATION_DB_ENGINE = "sqlite";
};
tests-fjall = testWith {
GARAGE_TEST_INTEGRATION_DB_ENGINE = "fjall";
};
# lints (fmt, clippy)
fmt = lints.garage-cargo-fmt;
clippy = lints.garage-cargo-clippy;
};
# ---- development shell, for making native builds only ----
devShells =
packages =
let
targets = compile {
inherit system nixpkgs crane rust-overlay;
};
packageFor = target: (compile {
inherit system git_version target;
pkgsSrc = nixpkgs;
cargo2nixOverlay = cargo2nix.overlays.default;
release = true;
}).workspace.garage { compileMode = "build"; };
in
{
default = targets.devShell;
# default = native release build
default = packageFor null;
# other = cross-compiled, statically-linked builds
amd64 = packageFor "x86_64-unknown-linux-musl";
i386 = packageFor "i686-unknown-linux-musl";
arm64 = packageFor "aarch64-unknown-linux-musl";
arm = packageFor "armv6l-unknown-linux-musl";
};
# import the full shell using `nix develop .#full`
full = pkgs.mkShell {
buildInputs = with pkgs; [
targets.toolchain
protobuf
# ---- developpment shell, for making native builds only ----
devShells =
let
shellWithPackages = (packages: (compile {
inherit system git_version;
pkgsSrc = nixpkgs;
cargo2nixOverlay = cargo2nix.overlays.default;
}).workspaceShell { inherit packages; });
in
{
default = shellWithPackages
(with pkgs; [
rustfmt
clang
mold
# ---- extra packages for dev tasks ----
rust-analyzer
cargo-audit
cargo-outdated
cargo-machete
nixpkgs-fmt
openssl
socat
killall
];
};
]);
# import the full shell using `nix develop .#full`
full = shellWithPackages (with pkgs; [
rustfmt
clang
mold
# ---- extra packages for dev tasks ----
cargo-audit
cargo-outdated
cargo-machete
nixpkgs-fmt
]);
};
});
}
Executable
+158
View File
@@ -0,0 +1,158 @@
#!/usr/bin/env python
import os
import requests
from datetime import datetime
# let's talk to our AWS Elasticsearch cluster
#from requests_aws4auth import AWS4Auth
#auth = AWS4Auth('GK31c2f218a2e44f485b94239e',
# 'b892c0665f0ada8a4755dae98baa3b133590e11dae3bcc1f9d769d67f16c3835',
# 'us-east-1',
# 's3')
from aws_requests_auth.aws_auth import AWSRequestsAuth
auth = AWSRequestsAuth(aws_access_key='GK31c2f218a2e44f485b94239e',
aws_secret_access_key='b892c0665f0ada8a4755dae98baa3b133590e11dae3bcc1f9d769d67f16c3835',
aws_host='localhost:3812',
aws_region='us-east-1',
aws_service='k2v')
print("-- ReadIndex")
response = requests.get('http://localhost:3812/alex',
auth=auth)
print(response.headers)
print(response.text)
sort_keys = ["a", "b", "c", "d"]
for sk in sort_keys:
print("-- (%s) Put initial (no CT)"%sk)
response = requests.put('http://localhost:3812/alex/root?sort_key=%s'%sk,
auth=auth,
data='{}: Hello, world!'.format(datetime.timestamp(datetime.now())))
print(response.headers)
print(response.text)
print("-- Get")
response = requests.get('http://localhost:3812/alex/root?sort_key=%s'%sk,
auth=auth)
print(response.headers)
print(response.text)
ct = response.headers["x-garage-causality-token"]
print("-- ReadIndex")
response = requests.get('http://localhost:3812/alex',
auth=auth)
print(response.headers)
print(response.text)
print("-- Put with CT")
response = requests.put('http://localhost:3812/alex/root?sort_key=%s'%sk,
auth=auth,
headers={'x-garage-causality-token': ct},
data='{}: Good bye, world!'.format(datetime.timestamp(datetime.now())))
print(response.headers)
print(response.text)
print("-- Get")
response = requests.get('http://localhost:3812/alex/root?sort_key=%s'%sk,
auth=auth)
print(response.headers)
print(response.text)
print("-- Put again with same CT (concurrent)")
response = requests.put('http://localhost:3812/alex/root?sort_key=%s'%sk,
auth=auth,
headers={'x-garage-causality-token': ct},
data='{}: Concurrent value, oops'.format(datetime.timestamp(datetime.now())))
print(response.headers)
print(response.text)
for sk in sort_keys:
print("-- (%s) Get"%sk)
response = requests.get('http://localhost:3812/alex/root?sort_key=%s'%sk,
auth=auth)
print(response.headers)
print(response.text)
ct = response.headers["x-garage-causality-token"]
print("-- Delete")
response = requests.delete('http://localhost:3812/alex/root?sort_key=%s'%sk,
headers={'x-garage-causality-token': ct},
auth=auth)
print(response.headers)
print(response.text)
print("-- ReadIndex")
response = requests.get('http://localhost:3812/alex',
auth=auth)
print(response.headers)
print(response.text)
print("-- InsertBatch")
response = requests.post('http://localhost:3812/alex',
auth=auth,
data='''
[
{"pk": "root", "sk": "a", "ct": null, "v": "aW5pdGlhbCB0ZXN0Cg=="},
{"pk": "root", "sk": "b", "ct": null, "v": "aW5pdGlhbCB0ZXN1Cg=="},
{"pk": "root", "sk": "c", "ct": null, "v": "aW5pdGlhbCB0ZXN2Cg=="}
]
''')
print(response.headers)
print(response.text)
print("-- ReadIndex")
response = requests.get('http://localhost:3812/alex',
auth=auth)
print(response.headers)
print(response.text)
for sk in sort_keys:
print("-- (%s) Get"%sk)
response = requests.get('http://localhost:3812/alex/root?sort_key=%s'%sk,
auth=auth)
print(response.headers)
print(response.text)
ct = response.headers["x-garage-causality-token"]
print("-- ReadBatch")
response = requests.post('http://localhost:3812/alex?search',
auth=auth,
data='''
[
{"partitionKey": "root"},
{"partitionKey": "root", "tombstones": true},
{"partitionKey": "root", "tombstones": true, "limit": 2},
{"partitionKey": "root", "start": "c", "singleItem": true},
{"partitionKey": "root", "start": "b", "end": "d", "tombstones": true}
]
''')
print(response.headers)
print(response.text)
print("-- DeleteBatch")
response = requests.post('http://localhost:3812/alex?delete',
auth=auth,
data='''
[
{"partitionKey": "root", "start": "b", "end": "c"}
]
''')
print(response.headers)
print(response.text)
print("-- ReadBatch")
response = requests.post('http://localhost:3812/alex?search',
auth=auth,
data='''
[
{"partitionKey": "root"}
]
''')
print(response.headers)
print(response.text)
+2 -2
View File
@@ -2,7 +2,7 @@
with import ./common.nix;
let
pkgs = import nixpkgs { };
pkgs = import pkgsSrc { };
lib = pkgs.lib;
/* Converts a key list and a value list to a set
@@ -167,7 +167,7 @@ let
</ul></p>
<p> Sources:
<ul>
<li><a href="https://git.deuxfleurs.fr/Deuxfleurs/garage/src/${r.type}/${x.version}">Forgejo</a></li>
<li><a href="https://git.deuxfleurs.fr/Deuxfleurs/garage/src/${r.type}/${x.version}">gitea</a></li>
<li><a href="https://git.deuxfleurs.fr/Deuxfleurs/garage/archive/${x.version}.zip">.zip</a></li>
<li><a href="https://git.deuxfleurs.fr/Deuxfleurs/garage/archive/${x.version}.tar.gz">.tar.gz</a></li>
</ul></p>
+5 -5
View File
@@ -10,9 +10,9 @@ let
flake = (import flake-compat { system = builtins.currentSystem; src = ../.; });
in
{
flake = flake.defaultNix;
nixpkgs = flake.defaultNix.inputs.nixpkgs;
devShells = flake.defaultNix.devShells.${builtins.currentSystem};
rec {
pkgsSrc = flake.defaultNix.inputs.nixpkgs;
cargo2nix = flake.defaultNix.inputs.cargo2nix;
cargo2nixOverlay = cargo2nix.overlays.default;
devShells = builtins.getAttr builtins.currentSystem flake.defaultNix.devShells;
}
+173 -158
View File
@@ -1,64 +1,164 @@
{
/* build inputs */
nixpkgs,
crane,
rust-overlay,
/* parameters */
system,
git_version ? null,
target ? null,
release ? false,
features ? null,
extraTestEnv ? {}
}:
{ system, target ? null, pkgsSrc, cargo2nixOverlay, compiler ? "rustc"
, release ? false, git_version ? null, features ? null, }:
let
log = v: builtins.trace v v;
# NixOS and Rust/Cargo triples do not match for ARM, fix it here.
rustTarget = if target == "armv6l-unknown-linux-musleabihf" then
"arm-unknown-linux-musleabihf"
else
target;
rustTargetEnvMap = {
"x86_64-unknown-linux-musl" = "X86_64_UNKNOWN_LINUX_MUSL";
"aarch64-unknown-linux-musl" = "AARCH64_UNKNOWN_LINUX_MUSL";
"i686-unknown-linux-musl" = "I686_UNKNOWN_LINUX_MUSL";
"arm-unknown-linux-musleabihf" = "ARM_UNKNOWN_LINUX_MUSLEABIHF";
};
pkgsNative = import nixpkgs {
inherit system;
overlays = [ (import rust-overlay) ];
};
pkgs = if target != null then
import nixpkgs {
import pkgsSrc {
inherit system;
crossSystem = {
config = target;
isStatic = true;
};
overlays = [ (import rust-overlay) ];
overlays = [ cargo2nixOverlay ];
}
else
pkgsNative;
import pkgsSrc {
inherit system;
overlays = [ cargo2nixOverlay ];
};
inherit (pkgs) lib stdenv;
toolchainOptions = {
rustVersion = "1.73.0";
extraRustComponents = [ "clippy" ];
};
toolchainFn = (p: p.rust-bin.stable."1.91.0".default.override {
targets = lib.optionals (target != null) [ rustTarget ];
extensions = [
"rust-src"
"rustfmt"
buildEnv = (drv:
{
rustc = drv.setBuildEnv;
clippy = ''
${drv.setBuildEnv or ""}
echo
echo --- BUILDING WITH CLIPPY ---
echo
export NIX_RUST_BUILD_FLAGS="''${NIX_RUST_BUILD_FLAGS} --deny warnings"
export RUSTC="''${CLIPPY_DRIVER}"
'';
}.${compiler});
/* Cargo2nix provides many overrides by default, you can take inspiration from them:
https://github.com/cargo2nix/cargo2nix/blob/master/overlay/overrides.nix
You can have a complete list of the available options by looking at the overriden object, mkcrate:
https://github.com/cargo2nix/cargo2nix/blob/master/overlay/mkcrate.nix
*/
packageOverrides = pkgs:
pkgs.rustBuilder.overrides.all ++ [
/* [1] We add some logic to compile our crates with clippy, it provides us many additional lints
[2] We need to alter Nix hardening to make static binaries: PIE,
Position Independent Executables seems to be supported only on amd64. Having
this flag set either 1. make our executables crash or 2. compile as dynamic on some platforms.
Here, we deactivate it. Later (find `codegenOpts`), we reactivate it for 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 at: https://github.com/NixOS/nixpkgs/blob/master/pkgs/build-support/cc-wrapper/add-hardening.sh
[3] 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.
[4] We don't want libsodium-sys and zstd-sys to try to use pkgconfig to build against a system library.
However the features to do so get activated for some reason (due to a bug in cargo2nix?),
so disable them manually here.
*/
(pkgs.rustBuilder.rustLib.makeOverride {
name = "garage";
overrideAttrs = drv:
(if git_version != null then {
# [3]
preConfigure = ''
${drv.preConfigure or ""}
export GIT_VERSION="${git_version}"
'';
} else
{ }) // {
# [1]
setBuildEnv = (buildEnv drv);
# [2]
hardeningDisable = [ "pie" ];
};
})
(pkgs.rustBuilder.rustLib.makeOverride {
name = "garage_rpc";
overrideAttrs = drv: { # [1]
setBuildEnv = (buildEnv drv);
};
})
(pkgs.rustBuilder.rustLib.makeOverride {
name = "garage_db";
overrideAttrs = drv: { # [1]
setBuildEnv = (buildEnv drv);
};
})
(pkgs.rustBuilder.rustLib.makeOverride {
name = "garage_util";
overrideAttrs = drv: { # [1]
setBuildEnv = (buildEnv drv);
};
})
(pkgs.rustBuilder.rustLib.makeOverride {
name = "garage_table";
overrideAttrs = drv: { # [1]
setBuildEnv = (buildEnv drv);
};
})
(pkgs.rustBuilder.rustLib.makeOverride {
name = "garage_block";
overrideAttrs = drv: { # [1]
setBuildEnv = (buildEnv drv);
};
})
(pkgs.rustBuilder.rustLib.makeOverride {
name = "garage_model";
overrideAttrs = drv: { # [1]
setBuildEnv = (buildEnv drv);
};
})
(pkgs.rustBuilder.rustLib.makeOverride {
name = "garage_api";
overrideAttrs = drv: { # [1]
setBuildEnv = (buildEnv drv);
};
})
(pkgs.rustBuilder.rustLib.makeOverride {
name = "garage_web";
overrideAttrs = drv: { # [1]
setBuildEnv = (buildEnv drv);
};
})
(pkgs.rustBuilder.rustLib.makeOverride {
name = "k2v-client";
overrideAttrs = drv: { # [1]
setBuildEnv = (buildEnv drv);
};
})
(pkgs.rustBuilder.rustLib.makeOverride {
name = "libsodium-sys";
overrideArgs = old: {
features = [ ]; # [4]
};
})
(pkgs.rustBuilder.rustLib.makeOverride {
name = "zstd-sys";
overrideArgs = old: {
features = [ ]; # [4]
};
})
];
});
craneLib = (crane.mkLib pkgs).overrideToolchain toolchainFn;
src = craneLib.cleanCargoSource ../.;
/* We ship some parts of the code disabled by default by putting them behind a flag.
It speeds up the compilation (when the feature is not required) and released crates have less dependency by default (less attack surface, disk space, etc.).
@@ -68,16 +168,17 @@ let
rootFeatures = if features != null then
features
else
([ "bundled-libs" "lmdb" "sqlite" "fjall" "k2v" ] ++ (lib.optionals release [
"consul-discovery"
"kubernetes-discovery"
"metrics"
"telemetry-otlp"
"syslog"
"journald"
]));
([ "garage/bundled-libs" "garage/lmdb" "garage/k2v" ] ++ (if release then [
"garage/consul-discovery"
"garage/kubernetes-discovery"
"garage/metrics"
"garage/telemetry-otlp"
"garage/lmdb"
"garage/sqlite"
] else
[ ]));
featuresStr = lib.concatStringsSep "," rootFeatures;
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).
@@ -88,9 +189,12 @@ let
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
*/
codegenOptsMap = {
"x86_64-unknown-linux-musl" =
[ "target-feature=+crt-static" "link-arg=-static-pie" ];
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"
@@ -99,106 +203,17 @@ let
"target-feature=+crt-static"
"link-arg=-static"
]; # segfault with static-pie
"armv6l-unknown-linux-musleabihf" = [
"target-feature=+crt-static"
"link-arg=-static"
]; # compile as dynamic with static-pie
"x86_64-unknown-linux-musl" =
[ "target-feature=+crt-static" "link-arg=-static-pie" ];
};
codegenOpts = if target != null then codegenOptsMap.${target} else [
"link-arg=-fuse-ld=mold"
];
# NixOS and Rust/Cargo triples do not match for ARM, fix it here.
rustTarget = if target == "armv6l-unknown-linux-musleabihf" then
"arm-unknown-linux-musleabihf"
else
target;
commonArgs =
{
inherit src;
pname = "garage";
version = "dev";
strictDeps = true;
cargoExtraArgs = "--locked --features ${featuresStr}";
cargoTestExtraArgs = "--workspace";
nativeBuildInputs = [
pkgsNative.protobuf
pkgs.stdenv.cc
] ++ lib.optionals (target == null) [
pkgs.clang
pkgs.mold
];
CARGO_PROFILE = if release then "release" else "dev";
CARGO_BUILD_RUSTFLAGS =
lib.concatStringsSep
" "
(builtins.map (flag: "-C ${flag}") codegenOpts);
}
//
(if rustTarget != null then {
CARGO_BUILD_TARGET = rustTarget;
"CARGO_TARGET_${rustTargetEnvMap.${rustTarget}}_LINKER" = "${stdenv.cc.targetPrefix}cc";
HOST_CC = "${stdenv.cc.nativePrefix}cc";
TARGET_CC = "${stdenv.cc.targetPrefix}cc";
} else {
CARGO_TARGET_X86_64_UNKNOWN_LINUX_GNU_LINKER = "clang";
});
in rec {
toolchain = toolchainFn pkgs;
devShell = pkgs.mkShell {
buildInputs = [
toolchain
] ++ (with pkgs; [
protobuf
clang
mold
]);
};
# ---- building garage ----
garage-deps = craneLib.buildDepsOnly commonArgs;
garage = craneLib.buildPackage (commonArgs // {
cargoArtifacts = garage-deps;
doCheck = false;
} //
(if git_version != null then {
version = git_version;
GIT_VERSION = git_version;
} else {}));
# ---- testing garage ----
garage-test-bin = craneLib.cargoBuild (commonArgs // {
cargoArtifacts = garage-deps;
pname = "garage-tests";
CARGO_PROFILE = "test";
cargoExtraArgs = "${commonArgs.cargoExtraArgs} --tests --workspace";
doCheck = false;
});
garage-test = craneLib.cargoTest (commonArgs // {
cargoArtifacts = garage-test-bin;
nativeBuildInputs = commonArgs.nativeBuildInputs ++ [
pkgs.cacert
];
} // extraTestEnv);
# ---- source code linting ----
garage-cargo-fmt = craneLib.cargoFmt (commonArgs // {
cargoExtraArgs = "";
});
garage-cargo-clippy = craneLib.cargoClippy (commonArgs // {
cargoArtifacts = garage-deps;
cargoClippyExtraArgs = "--all-targets -- -D warnings";
});
}
in pkgs.rustBuilder.makePackageSet ({
inherit release packageFun packageOverrides codegenOpts rootFeatures;
target = rustTarget;
} // toolchainOptions)
+4 -10
View File
@@ -17,19 +17,13 @@ else
fi
$GARAGE_BIN -c /tmp/config.1.toml bucket create eprouvette
if [ "$GARAGE_OLDVER" = "v08" ]; then
if [ "$GARAGE_08" = "1" ]; then
KEY_INFO=$($GARAGE_BIN -c /tmp/config.1.toml key new --name opérateur)
ACCESS_KEY=`echo $KEY_INFO|grep -Po 'GK[a-f0-9]+'`
SECRET_KEY=`echo $KEY_INFO|grep -Po 'Secret key: [a-f0-9]+'|grep -Po '[a-f0-9]+$'`
elif [ "$GARAGE_OLDVER" = "v1" ]; then
KEY_INFO=$($GARAGE_BIN -c /tmp/config.1.toml key create opérateur)
ACCESS_KEY=`echo $KEY_INFO|grep -Po 'GK[a-f0-9]+'`
SECRET_KEY=`echo $KEY_INFO|grep -Po 'Secret key: [a-f0-9]+'|grep -Po '[a-f0-9]+$'`
else
KEY_INFO=$($GARAGE_BIN -c /tmp/config.1.toml json-api CreateKey '{"name":"opérateur"}')
ACCESS_KEY=`echo $KEY_INFO|jq -r .accessKeyId`
SECRET_KEY=`echo $KEY_INFO|jq -r .secretAccessKey`
KEY_INFO=$($GARAGE_BIN -c /tmp/config.1.toml key create opérateur)
fi
ACCESS_KEY=`echo $KEY_INFO|grep -Po 'GK[a-f0-9]+'`
SECRET_KEY=`echo $KEY_INFO|grep -Po 'Secret key: [a-f0-9]+'|grep -Po '[a-f0-9]+$'`
$GARAGE_BIN -c /tmp/config.1.toml bucket allow eprouvette --read --write --owner --key $ACCESS_KEY
echo "$ACCESS_KEY $SECRET_KEY" > /tmp/garage.s3
+2 -8
View File
@@ -11,7 +11,7 @@ PATH="${GARAGE_DEBUG}:${GARAGE_RELEASE}:${NIX_RELEASE}:$PATH"
FANCYCOLORS=("41m" "42m" "44m" "45m" "100m" "104m")
export RUST_BACKTRACE=1
export RUST_LOG=garage=info,garage_api_common=debug,garage_api_s3=debug
export RUST_LOG=garage=info,garage_api=debug
MAIN_LABEL="\e[${FANCYCOLORS[0]}[main]\e[49m"
if [ -z "$GARAGE_BIN" ]; then
@@ -30,12 +30,6 @@ for count in $(seq 1 3); do
CONF_PATH="/tmp/config.$count.toml"
LABEL="\e[${FANCYCOLORS[$count]}[$count]\e[49m"
if [ "$GARAGE_OLDVER" == "v08" ]; then
REPLICATION_MODE="replication_mode = \"3\""
else
REPLICATION_MODE="replication_factor = 3"
fi
cat > $CONF_PATH <<EOF
block_size = 1048576 # objects are split in blocks of maximum this number of bytes
metadata_dir = "/tmp/garage-meta-$count"
@@ -44,7 +38,7 @@ data_dir = "/tmp/garage-data-$count"
rpc_bind_addr = "0.0.0.0:$((3900+$count))" # the port other Garage nodes will use to talk to this node
rpc_public_addr = "127.0.0.1:$((3900+$count))"
bootstrap_peers = []
$REPLICATION_MODE
replication_mode = "3"
rpc_secret = "$NETWORK_SECRET"
[s3_api]
+1 -1
View File
@@ -29,7 +29,7 @@ until $GARAGE_BIN -c /tmp/config.1.toml status 2>&1|grep -q HEALTHY ; do
sleep 1
done
if [ "$GARAGE_OLDVER" = "v08" ]; then
if [ "$GARAGE_08" = "1" ]; then
$GARAGE_BIN -c /tmp/config.1.toml status \
| grep 'NO ROLE' \
| grep -Po '^[0-9a-f]+' \
+1 -1
View File
@@ -1,3 +1,3 @@
# Garage helm3 chart
Documentation is located [here](https://garagehq.deuxfleurs.fr/documentation/cookbook/kubernetes/).
Documentation is located [here](/doc/book/cookbook/kubernetes.md).
+18 -12
View File
@@ -1,18 +1,24 @@
apiVersion: v2
name: garage
description: S3-compatible object store for small self-hosted geo-distributed deployments
# A chart can be either an 'application' or a 'library' chart.
#
# Application charts are a collection of templates that can be packaged into versioned archives
# to be deployed.
#
# Library charts provide useful utilities or functions for the chart developer. They're included as
# a dependency of application charts to inject those utilities and functions into the rendering
# pipeline. Library charts do not define any templates and therefore cannot be deployed.
type: application
version: 0.9.2
appVersion: "v2.2.0"
home: https://garagehq.deuxfleurs.fr/
icon: https://garagehq.deuxfleurs.fr/images/garage-logo.svg
keywords:
- geo-distributed
- read-after-write-consistency
- s3-compatible
# This is the chart version. This version number should be incremented each time you make changes
# to the chart and its templates, including the app version.
# Versions are expected to follow Semantic Versioning (https://semver.org/)
version: 0.4.1
sources:
- https://git.deuxfleurs.fr/Deuxfleurs/garage.git
maintainers: []
# This is the version number of the application being deployed. This version number should be
# incremented each time you make changes to the application. Versions are not expected to
# follow Semantic Versioning. They should reflect the version the application is using.
# It is recommended to use it with quotes.
appVersion: "v0.9.3"
-97
View File
@@ -1,97 +0,0 @@
# garage
![Version: 0.9.2](https://img.shields.io/badge/Version-0.9.2-informational?style=flat-square) ![Type: application](https://img.shields.io/badge/Type-application-informational?style=flat-square) ![AppVersion: v2.2.0](https://img.shields.io/badge/AppVersion-v2.2.0-informational?style=flat-square)
S3-compatible object store for small self-hosted geo-distributed deployments
**Homepage:** <https://garagehq.deuxfleurs.fr/>
## Source Code
* <https://git.deuxfleurs.fr/Deuxfleurs/garage.git>
## Values
| Key | Type | Default | Description |
|-----|------|---------|-------------|
| affinity | object | `{}` | |
| commonLabels | object | `{}` | Extra labels for all resources |
| deployment.kind | string | `"StatefulSet"` | Switchable to DaemonSet |
| deployment.podManagementPolicy | string | `"OrderedReady"` | If using statefulset, allow Parallel or OrderedReady (default) |
| deployment.replicaCount | int | `3` | Number of StatefulSet replicas/garage nodes to start |
| environment | object | `{}` | |
| extraVolumeMounts | object | `{}` | |
| extraVolumes | object | `{}` | |
| fullnameOverride | string | `""` | |
| garage.blockSize | string | `"1048576"` | Defaults is 1MB An increase can result in better performance in certain scenarios https://garagehq.deuxfleurs.fr/documentation/reference-manual/configuration/#block_size |
| garage.bootstrapPeers | list | `[]` | This is not required if you use the integrated kubernetes discovery |
| garage.compressionLevel | string | `"1"` | zstd compression level of stored blocks https://garagehq.deuxfleurs.fr/documentation/reference-manual/configuration/#compression_level |
| garage.dbEngine | string | `"lmdb"` | Can be changed for better performance on certain systems https://garagehq.deuxfleurs.fr/documentation/reference-manual/configuration/#db_engine |
| garage.existingConfigMap | string | `""` | if not empty string, allow using an existing ConfigMap for the garage.toml, if set, ignores garage.toml |
| garage.garageTomlString | string | `""` | String Template for the garage configuration if set, ignores above values. Values can be templated, see https://garagehq.deuxfleurs.fr/documentation/reference-manual/configuration/ |
| garage.kubernetesSkipCrd | bool | `false` | Set to true if you want to use k8s discovery but install the CRDs manually outside of the helm chart, for example if you operate at namespace level without cluster resources |
| garage.replicationFactor | string | `"3"` | Default to 3 replicas, see the replication_factor section at https://garagehq.deuxfleurs.fr/documentation/reference-manual/configuration/#replication_factor |
| garage.consistencyMode | string | `"consistent"` | Default to read-after-write consistency, see the consistency_mode section at https://garagehq.deuxfleurs.fr/documentation/reference-manual/configuration/#consistency_mode |
| garage.metadataAutoSnapshotInterval | string | `""` | 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. https://garagehq.deuxfleurs.fr/documentation/reference-manual/configuration/#metadata_auto_snapshot_interval |
| garage.rpcBindAddr | string | `"[::]:3901"` | |
| garage.rpcSecret | string | `""` | If not given, a random secret will be generated and stored in a Secret object |
| garage.s3.api.region | string | `"garage"` | |
| garage.s3.api.rootDomain | string | `".s3.garage.tld"` | |
| garage.s3.web.index | string | `"index.html"` | |
| garage.s3.web.rootDomain | string | `".web.garage.tld"` | |
| image.pullPolicy | string | `"IfNotPresent"` | |
| image.repository | string | `"dxflrs/amd64_garage"` | default to amd64 docker image |
| image.tag | string | `""` | set the image tag, please prefer using the chart version and not this to avoid compatibility issues |
| imagePullSecrets | list | `[]` | set if you need credentials to pull your custom image |
| ingress.s3.api.annotations | object | `{}` | Rely _either_ on the className or the annotation below but not both! If you want to use the className, set className: "nginx" and replace "nginx" by an Ingress controller name, examples [here](https://kubernetes.io/docs/concepts/services-networking/ingress-controllers). |
| ingress.s3.api.enabled | bool | `false` | |
| ingress.s3.api.hosts[0] | object | `{"host":"s3.garage.tld","paths":[{"path":"/","pathType":"Prefix"}]}` | garage S3 API endpoint, to be used with awscli for example |
| ingress.s3.api.hosts[1] | object | `{"host":"*.s3.garage.tld","paths":[{"path":"/","pathType":"Prefix"}]}` | garage S3 API endpoint, DNS style bucket access |
| ingress.s3.api.labels | object | `{}` | |
| ingress.s3.api.tls | list | `[]` | |
| ingress.s3.web.annotations | object | `{}` | Rely _either_ on the className or the annotation below but not both! If you want to use the className, set className: "nginx" and replace "nginx" by an Ingress controller name, examples [here](https://kubernetes.io/docs/concepts/services-networking/ingress-controllers). |
| ingress.s3.web.enabled | bool | `false` | |
| ingress.s3.web.hosts[0] | object | `{"host":"*.web.garage.tld","paths":[{"path":"/","pathType":"Prefix"}]}` | wildcard website access with bucket name prefix |
| ingress.s3.web.hosts[1] | object | `{"host":"mywebpage.example.com","paths":[{"path":"/","pathType":"Prefix"}]}` | specific bucket access with FQDN bucket |
| ingress.s3.web.labels | object | `{}` | |
| ingress.s3.web.tls | list | `[]` | |
| initImage.pullPolicy | string | `"IfNotPresent"` | |
| initImage.repository | string | `"busybox"` | |
| initImage.tag | string | `"stable"` | |
| livenessProbe | object | `{}` | Specifies a livenessProbe |
| monitoring.metrics.enabled | bool | `false` | If true, a service for monitoring is created with a prometheus.io/scrape annotation |
| monitoring.metrics.serviceMonitor.enabled | bool | `false` | If true, a ServiceMonitor CRD is created for a prometheus operator https://github.com/coreos/prometheus-operator |
| monitoring.metrics.serviceMonitor.interval | string | `"15s"` | |
| monitoring.metrics.serviceMonitor.labels | object | `{}` | |
| monitoring.metrics.serviceMonitor.path | string | `"/metrics"` | |
| monitoring.metrics.serviceMonitor.relabelings | list | `[]` | |
| monitoring.metrics.serviceMonitor.scheme | string | `"http"` | |
| monitoring.metrics.serviceMonitor.scrapeTimeout | string | `"10s"` | |
| monitoring.metrics.serviceMonitor.tlsConfig | object | `{}` | |
| monitoring.tracing.sink | string | `""` | specify a sink endpoint for OpenTelemetry Traces, eg. `http://localhost:4317` |
| nameOverride | string | `""` | |
| nodeSelector | object | `{}` | |
| persistence.data.hostPath | string | `"/var/lib/garage/data"` | |
| persistence.data.size | string | `"100Mi"` | |
| persistence.enabled | bool | `true` | |
| persistence.meta.hostPath | string | `"/var/lib/garage/meta"` | |
| persistence.meta.size | string | `"100Mi"` | |
| podAnnotations | object | `{}` | additional pod annotations |
| podSecurityContext.fsGroup | int | `1000` | |
| podSecurityContext.runAsGroup | int | `1000` | |
| podSecurityContext.runAsNonRoot | bool | `true` | |
| podSecurityContext.runAsUser | int | `1000` | |
| readinessProbe | object | `{}` | Specifies a readinessProbe |
| resources | object | `{}` | |
| securityContext.capabilities | object | `{"drop":["ALL"]}` | The default security context is heavily restricted, feel free to tune it to your requirements |
| securityContext.readOnlyRootFilesystem | bool | `true` | |
| service.s3.api.port | int | `3900` | |
| service.s3.web.port | int | `3902` | |
| service.type | string | `"ClusterIP"` | You can rely on any service to expose your cluster - ClusterIP (+ Ingress) - NodePort (+ Ingress) - LoadBalancer |
| serviceAccount.annotations | object | `{}` | Annotations to add to the service account |
| serviceAccount.create | bool | `true` | Specifies whether a service account should be created |
| serviceAccount.name | string | `""` | The name of the service account to use. If not set and create is true, a name is generated using the fullname template |
| tolerations | list | `[]` | |
----------------------------------------------
Autogenerated from chart metadata using [helm-docs v1.14.2](https://github.com/norwoodj/helm-docs/releases/v1.14.2)
+1 -4
View File
@@ -27,7 +27,7 @@ If release name contains chart name it will be used as a full name.
Create the name of the rpc secret
*/}}
{{- define "garage.rpcSecretName" -}}
{{- .Values.garage.existingRpcSecret | default (printf "%s-rpc-secret" (include "garage.fullname" .)) -}}
{{- printf "%s-rpc-secret" (include "garage.fullname" .) -}}
{{- end }}
{{/*
@@ -47,9 +47,6 @@ helm.sh/chart: {{ include "garage.chart" . }}
app.kubernetes.io/version: {{ .Chart.AppVersion | quote }}
{{- end }}
app.kubernetes.io/managed-by: {{ .Release.Service }}
{{- with .Values.commonLabels }}
{{- toYaml . | nindent 0 }}
{{- end }}
{{- end }}
{{/*
+1 -56
View File
@@ -1,62 +1,7 @@
{{- if not .Values.garage.existingConfigMap }}
apiVersion: v1
kind: ConfigMap
metadata:
name: {{ include "garage.fullname" . }}-config
data:
garage.toml: |-
{{- if .Values.garage.garageTomlString }}
{{- tpl (index (index .Values.garage) "garageTomlString") $ | nindent 4 }}
{{- else }}
metadata_dir = "/mnt/meta"
data_dir = "/mnt/data"
db_engine = "{{ .Values.garage.dbEngine }}"
block_size = "{{ .Values.garage.blockSize }}"
replication_factor = {{ .Values.garage.replicationFactor }}
consistency_mode = "{{ .Values.garage.consistencyMode }}"
compression_level = {{ .Values.garage.compressionLevel }}
{{- if .Values.garage.metadataAutoSnapshotInterval }}
metadata_auto_snapshot_interval = {{ .Values.garage.metadataAutoSnapshotInterval | quote }}
{{- end }}
rpc_bind_addr = "{{ .Values.garage.rpcBindAddr }}"
# rpc_secret will be populated by the init container from a k8s secret object
rpc_secret = "__RPC_SECRET_REPLACE__"
bootstrap_peers = [
{{- range $index, $peer := .Values.garage.bootstrapPeers }}
{{- if $index}}, {{ end }}{{ $peer | quote }}
{{ end }}
]
{{- if .Values.garage.additionalTopLevelConfig }}
{{ .Values.garage.additionalTopLevelConfig | nindent 4 }}
{{- end }}
[kubernetes_discovery]
namespace = "{{ .Release.Namespace }}"
service_name = "{{ include "garage.fullname" . }}"
skip_crd = {{ .Values.garage.kubernetesSkipCrd }}
[s3_api]
s3_region = "{{ .Values.garage.s3.api.region }}"
api_bind_addr = "[::]:3900"
root_domain = "{{ .Values.garage.s3.api.rootDomain }}"
[s3_web]
bind_addr = "[::]:3902"
root_domain = "{{ .Values.garage.s3.web.rootDomain }}"
index = "{{ .Values.garage.s3.web.index }}"
[admin]
api_bind_addr = "[::]:3903"
{{- if .Values.monitoring.tracing.sink }}
trace_sink = "{{ .Values.monitoring.tracing.sink }}"
{{- end }}
{{- end }}
{{- end }}
{{- tpl (index (index .Values.garage) "garage.toml") $ | nindent 4 }}
-2
View File
@@ -1,4 +1,3 @@
{{- if not .Values.garage.existingRpcSecret }}
apiVersion: v1
kind: Secret
metadata:
@@ -13,4 +12,3 @@ data:
{{- $prevRpcSecret := $prevSecretData.rpcSecret | default "" | b64dec }}
{{/* Priority is: 1. from values, 2. previous value, 3. generate random */}}
rpcSecret: {{ .Values.garage.rpcSecret | default $prevRpcSecret | default (include "jupyterhub.randHex" 64) | b64enc | quote }}
{{- end }}
@@ -1,22 +0,0 @@
{{- if eq .Values.deployment.kind "StatefulSet" -}}
apiVersion: v1
kind: Service
metadata:
name: {{ include "garage.fullname" . }}-headless
labels:
{{- include "garage.labels" . | nindent 4 }}
spec:
type: ClusterIP
clusterIP: None
ports:
- port: {{ .Values.service.s3.api.port }}
targetPort: 3900
protocol: TCP
name: s3-api
- port: {{ .Values.service.s3.web.port }}
targetPort: 3902
protocol: TCP
name: s3-web
selector:
{{- include "garage.selectorLabels" . | nindent 4 }}
{{- end }}
+1 -5
View File
@@ -4,10 +4,6 @@ metadata:
name: {{ include "garage.fullname" . }}
labels:
{{- include "garage.labels" . | nindent 4 }}
{{- with .Values.service.annotations }}
annotations:
{{- toYaml . | nindent 4 }}
{{- end }}
spec:
type: {{ .Values.service.type }}
ports:
@@ -41,4 +37,4 @@ spec:
name: metrics
selector:
{{- include "garage.selectorLabels" . | nindent 4 }}
{{- end }}
{{- end }}
+12 -21
View File
@@ -10,18 +10,18 @@ spec:
{{- include "garage.selectorLabels" . | nindent 6 }}
{{- if eq .Values.deployment.kind "StatefulSet" }}
replicas: {{ .Values.deployment.replicaCount }}
serviceName: {{ include "garage.fullname" . }}-headless
podManagementPolicy: {{ .Values.deployment.podManagementPolicy }}
serviceName: {{ include "garage.fullname" . }}
{{- end }}
template:
metadata:
annotations:
checksum/config: {{ include (print $.Template.BasePath "/configmap.yaml") . | sha256sum }}
{{- with .Values.podAnnotations }}
{{- toYaml . | nindent 8 }}
{{- end }}
labels:
{{- include "garage.labels" . | nindent 8 }}
{{- include "garage.selectorLabels" . | nindent 8 }}
spec:
{{- with .Values.imagePullSecrets }}
imagePullSecrets:
@@ -63,10 +63,6 @@ spec:
name: web-api
- containerPort: 3903
name: admin
{{- with .Values.environment }}
env:
{{- toYaml . | nindent 12 }}
{{- end }}
volumeMounts:
- name: meta
mountPath: /mnt/meta
@@ -75,17 +71,15 @@ spec:
- name: etc
mountPath: /etc/garage.toml
subPath: garage.toml
{{- with .Values.extraVolumeMounts }}
{{- toYaml . | nindent 12 }}
{{- end }}
{{- with .Values.livenessProbe }}
livenessProbe:
{{- toYaml . | nindent 12 }}
{{- end }}
{{- with .Values.readinessProbe }}
readinessProbe:
{{- toYaml . | nindent 12 }}
{{- end }}
# TODO
# livenessProbe:
# httpGet:
# path: /
# port: 3900
# readinessProbe:
# httpGet:
# path: /
# port: 3900
resources:
{{- toYaml .Values.resources | nindent 12 }}
volumes:
@@ -111,9 +105,6 @@ spec:
- name: data
emptyDir: {}
{{- end }}
{{- with .Values.extraVolumes }}
{{- toYaml . | nindent 8 }}
{{- end }}
{{- with .Values.nodeSelector }}
nodeSelector:
{{- toYaml . | nindent 8 }}
+70 -101
View File
@@ -2,49 +2,30 @@
# This is a YAML-formatted file.
# Declare variables to be passed into your templates.
# -- Additional labels to add to all resources created by this chart
commonLabels: {}
# app.kubernetes.io/part-of: storage
# team: platform
# Garage configuration. These values go to garage.toml
garage:
# -- Can be changed for better performance on certain systems
# https://garagehq.deuxfleurs.fr/documentation/reference-manual/configuration/#db_engine
# Can be changed for better performance on certain systems
# https://garagehq.deuxfleurs.fr/documentation/reference-manual/configuration/#db-engine-since-v0-8-0
dbEngine: "lmdb"
# -- Defaults is 1MB
# Defaults is 1MB
# An increase can result in better performance in certain scenarios
# https://garagehq.deuxfleurs.fr/documentation/reference-manual/configuration/#block_size
# https://garagehq.deuxfleurs.fr/documentation/reference-manual/configuration/#block-size
blockSize: "1048576"
# -- Default to 3 replicas, see the replication_factor section at
# https://garagehq.deuxfleurs.fr/documentation/reference-manual/configuration/#replication_factor
replicationFactor: "3"
# Default to 3 replicas, see the replication_mode section at
# https://garagehq.deuxfleurs.fr/documentation/reference-manual/configuration/#replication-mode
replicationMode: "3"
# -- By default, enable read-after-write consistency guarantees, see the consistency_mode section at
# https://garagehq.deuxfleurs.fr/documentation/reference-manual/configuration/#consistency_mode
consistencyMode: "consistent"
# -- zstd compression level of stored blocks
# https://garagehq.deuxfleurs.fr/documentation/reference-manual/configuration/#compression_level
# zstd compression level of stored blocks
# https://garagehq.deuxfleurs.fr/documentation/reference-manual/configuration/#compression-level
compressionLevel: "1"
# -- 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.
# https://garagehq.deuxfleurs.fr/documentation/reference-manual/configuration/#metadata_auto_snapshot_interval
metadataAutoSnapshotInterval: ""
rpcBindAddr: "[::]:3901"
# -- If not given, a random secret will be generated and stored in a Secret object
# If not given, a random secret will be generated and stored in a Secret object
rpcSecret: ""
# -- If you want to provide an rpcSecret within an existing k8s secret,
# specify the secret name here, and store the value under the secret key `rpcSecret`
# the default secret will not be created
existingRpcSecret: ""
# -- This is not required if you use the integrated kubernetes discovery
# This is not required if you use the integrated kubernetes discovery
bootstrapPeers: []
# -- Set to true if you want to use k8s discovery but install the CRDs manually outside
# of the helm chart, for example if you operate at namespace level without cluster resources
kubernetesSkipCrd: false
s3:
api:
@@ -53,22 +34,47 @@ garage:
web:
rootDomain: ".web.garage.tld"
index: "index.html"
# Template for the garage configuration
# Values can be templated
# ref: https://garagehq.deuxfleurs.fr/documentation/reference-manual/configuration/
garage.toml: |-
metadata_dir = "/mnt/meta"
data_dir = "/mnt/data"
# -- Additional configuration to append to garage.toml. Use a multi-line string for custom config.
# Example:
# additionalTopLevelConfig: |-
# data_fsync = true
additionalTopLevelConfig: ""
db_engine = "{{ .Values.garage.dbEngine }}"
# -- if not empty string, allow using an existing ConfigMap for the garage.toml,
# if set, ignores garage.toml
existingConfigMap: ""
block_size = {{ .Values.garage.blockSize }}
# -- String Template for the garage configuration
# if set, ignores above values.
# Values can be templated,
# see https://garagehq.deuxfleurs.fr/documentation/reference-manual/configuration/
garageTomlString: ""
replication_mode = "{{ .Values.garage.replicationMode }}"
compression_level = {{ .Values.garage.compressionLevel }}
rpc_bind_addr = "{{ .Values.garage.rpcBindAddr }}"
# rpc_secret will be populated by the init container from a k8s secret object
rpc_secret = "__RPC_SECRET_REPLACE__"
bootstrap_peers = {{ .Values.garage.bootstrapPeers }}
[kubernetes_discovery]
namespace = "{{ .Release.Namespace }}"
service_name = "{{ include "garage.fullname" . }}"
skip_crd = {{ .Values.garage.kubernetesSkipCrd }}
[s3_api]
s3_region = "{{ .Values.garage.s3.api.region }}"
api_bind_addr = "[::]:3900"
root_domain = "{{ .Values.garage.s3.api.rootDomain }}"
[s3_web]
bind_addr = "[::]:3902"
root_domain = "{{ .Values.garage.s3.web.rootDomain }}"
index = "{{ .Values.garage.s3.web.index }}"
[admin]
api_bind_addr = "[::]:3903"
{{- if .Values.monitoring.tracing.sink }}
trace_sink = "{{ .Values.monitoring.tracing.sink }}"
{{- end }}
# Data persistence
persistence:
@@ -86,18 +92,14 @@ persistence:
# Deployment configuration
deployment:
# -- Switchable to DaemonSet
# Switchable to DaemonSet
kind: StatefulSet
# -- Number of StatefulSet replicas/garage nodes to start
# Number of StatefulSet replicas/garage nodes to start
replicaCount: 3
# -- If using statefulset, allow Parallel or OrderedReady (default)
podManagementPolicy: OrderedReady
image:
# -- default to amd64 docker image
repository: dxflrs/amd64_garage
# -- set the image tag, please prefer using the chart version and not this
# to avoid compatibility issues
# please prefer using the chart version and not this tag
tag: ""
pullPolicy: IfNotPresent
@@ -106,32 +108,29 @@ initImage:
tag: stable
pullPolicy: IfNotPresent
# -- set if you need credentials to pull your custom image
imagePullSecrets: []
nameOverride: ""
fullnameOverride: ""
serviceAccount:
# -- Specifies whether a service account should be created
# Specifies whether a service account should be created
create: true
# -- Annotations to add to the service account
# Annotations to add to the service account
annotations: {}
# -- The name of the service account to use.
# The name of the service account to use.
# If not set and create is true, a name is generated using the fullname template
name: ""
# -- additional pod annotations
podAnnotations: {}
podSecurityContext:
runAsUser: 1000
runAsGroup: 1000
fsGroup: 1000
fsGroupChangePolicy: "OnRootMismatch"
runAsNonRoot: true
securityContext:
# -- The default security context is heavily restricted,
# The default security context is heavily restricted
# feel free to tune it to your requirements
capabilities:
drop:
@@ -139,13 +138,11 @@ securityContext:
readOnlyRootFilesystem: true
service:
# -- You can rely on any service to expose your cluster
# You can rely on any service to expose your cluster
# - ClusterIP (+ Ingress)
# - NodePort (+ Ingress)
# - LoadBalancer
type: ClusterIP
# -- Annotations to add to the service
annotations: {}
s3:
api:
port: 3900
@@ -157,23 +154,20 @@ ingress:
s3:
api:
enabled: false
# -- Rely _either_ on the className or the annotation below but not both!
# If you want to use the className, set
# Rely either on the className or the annotation below but not both
# replace "nginx" by an Ingress controller
# you can find examples here https://kubernetes.io/docs/concepts/services-networking/ingress-controllers
# className: "nginx"
# and replace "nginx" by an Ingress controller name,
# examples [here](https://kubernetes.io/docs/concepts/services-networking/ingress-controllers).
annotations: {}
# kubernetes.io/ingress.class: "nginx"
# kubernetes.io/tls-acme: "true"
labels: {}
hosts:
# -- garage S3 API endpoint, to be used with awscli for example
- host: "s3.garage.tld"
- host: "s3.garage.tld" # garage S3 API endpoint
paths:
- path: /
pathType: Prefix
# -- garage S3 API endpoint, DNS style bucket access
- host: "*.s3.garage.tld"
- host: "*.s3.garage.tld" # garage S3 API endpoint, DNS style bucket access
paths:
- path: /
pathType: Prefix
@@ -183,23 +177,20 @@ ingress:
# - kubernetes.docker.internal
web:
enabled: false
# -- Rely _either_ on the className or the annotation below but not both!
# If you want to use the className, set
# Rely either on the className or the annotation below but not both
# replace "nginx" by an Ingress controller
# you can find examples here https://kubernetes.io/docs/concepts/services-networking/ingress-controllers
# className: "nginx"
# and replace "nginx" by an Ingress controller name,
# examples [here](https://kubernetes.io/docs/concepts/services-networking/ingress-controllers).
annotations: {}
# kubernetes.io/ingress.class: nginx
# kubernetes.io/tls-acme: "true"
labels: {}
hosts:
# -- wildcard website access with bucket name prefix
- host: "*.web.garage.tld"
- host: "*.web.garage.tld" # wildcard website access with bucket name prefix
paths:
- path: /
pathType: Prefix
# -- specific bucket access with FQDN bucket
- host: "mywebpage.example.com"
- host: "mywebpage.example.com" # specific bucket access with FQDN bucket
paths:
- path: /
pathType: Prefix
@@ -209,7 +200,7 @@ ingress:
# - kubernetes.docker.internal
resources: {}
# The following are indicative for a small-size deployment, for anything serious double them.
# The following are indicative for a small-size deployement, for anything serious double them.
# limits:
# cpu: 100m
# memory: 1024Mi
@@ -217,39 +208,18 @@ resources: {}
# cpu: 100m
# memory: 512Mi
# -- Specifies a livenessProbe
livenessProbe: {}
#httpGet:
# path: /health
# port: 3903
#initialDelaySeconds: 5
#periodSeconds: 30
# -- Specifies a readinessProbe
readinessProbe: {}
#httpGet:
# path: /health
# port: 3903
#initialDelaySeconds: 5
#periodSeconds: 30
nodeSelector: {}
tolerations: []
affinity: {}
environment: {}
extraVolumes: {}
extraVolumeMounts: {}
monitoring:
metrics:
# -- If true, a service for monitoring is created with a prometheus.io/scrape annotation
# If true, a service for monitoring is created with a prometheus.io/scrape annotation
enabled: false
serviceMonitor:
# -- If true, a ServiceMonitor CRD is created for a prometheus operator
# If true, a ServiceMonitor CRD is created for a prometheus operator
# https://github.com/coreos/prometheus-operator
enabled: false
path: /metrics
@@ -261,5 +231,4 @@ monitoring:
scrapeTimeout: 10s
relabelings: []
tracing:
# -- specify a sink endpoint for OpenTelemetry Traces, eg. `http://localhost:4317`
sink: ""
+3 -3
View File
@@ -127,7 +127,7 @@ They are due to the download being interrupted in the middle (^C during first la
Add `:force?` to the `cached-wget!` call in `daemon.clj` to re-download the binary,
or restar the VMs to clear temporary files.
### In `jepsen.garage`: prefix weirdness
### In `jepsen.garage`: prefix wierdness
In `store/garage set1/20231019T163358.615+0200`:
@@ -146,12 +146,12 @@ and passing all values that were previously in the context (creds and prefix) as
The reg2 test is our custom checker for CRDT read-after-write on individual object keys, acting as registers which can be updated.
The test fails without the timestamp fix, which is expected as the clock scrambler will prevent nodes from having a correct ordering of objects.
With the timestamp fix (`--patch tsfix1`), the happened-before relationship should at least be respected, meaning that when a PutObject call starts
With the timestamp fix (`--patch tsfix1`), the happenned-before relationship should at least be respected, meaning that when a PutObject call starts
after another PutObject call has ended, the second call should overwrite the value of the first call, and that value should not be
readable by future GetObject calls.
However, we observed inconsistencies even with the timestamp fix.
The inconsistencies seemed to always happened after writing a nil value, which translates to a DeleteObject call
The inconsistencies seemed to always happenned after writing a nil value, which translates to a DeleteObject call
instead of a PutObject. By removing the possibility of writing nil values, therefore only doing
PutObject calls, the issue disappears. There is therefore an issue to fix in DeleteObject.
+7 -7
View File
@@ -30,11 +30,11 @@ Vagrant.configure("2") do |config|
config.vm.define "n6" do |config| vm(config, "n6", "192.168.56.26") end
config.vm.define "n7" do |config| vm(config, "n7", "192.168.56.27") end
#config.vm.define "n8" do |config| vm(config, "n8", "192.168.56.28") end
#config.vm.define "n9" do |config| vm(config, "n9", "192.168.56.29") end
#config.vm.define "n10" do |config| vm(config, "n10", "192.168.56.30") end
#config.vm.define "n11" do |config| vm(config, "n11", "192.168.56.31") end
#config.vm.define "n12" do |config| vm(config, "n12", "192.168.56.32") end
#config.vm.define "n13" do |config| vm(config, "n13", "192.168.56.33") end
#config.vm.define "n14" do |config| vm(config, "n14", "192.168.56.34") end
config.vm.define "n8" do |config| vm(config, "n8", "192.168.56.28") end
config.vm.define "n9" do |config| vm(config, "n9", "192.168.56.29") end
config.vm.define "n10" do |config| vm(config, "n10", "192.168.56.30") end
config.vm.define "n11" do |config| vm(config, "n11", "192.168.56.31") end
config.vm.define "n12" do |config| vm(config, "n12", "192.168.56.32") end
config.vm.define "n13" do |config| vm(config, "n13", "192.168.56.33") end
config.vm.define "n14" do |config| vm(config, "n14", "192.168.56.34") end
end
+4 -3
View File
@@ -3,10 +3,11 @@
set -x
#for ppatch in task3c task3a tsfix2; do
for ppatch in v093 v1rc1; do
for ppatch in tsfix2; do
#for psc in c cp cdp r pr cpr dpr; do
for ptsk in reg2 set2; do
for psc in c cp cdp r pr cpr dpr; do
for psc in cdp r pr cpr dpr; do
#for ptsk in reg2 set1 set2; do
for ptsk in set1; do
for irun in $(seq 10); do
lein run test --nodes-file nodes.vagrant \
--time-limit 60 --rate 100 --concurrency 100 --ops-per-key 100 \

Some files were not shown because too many files have changed in this diff Show More