Compare commits

..

No commits in common. "main" and "cargo-bumps-230801" have entirely different histories.

435 changed files with 11808 additions and 82184 deletions

View file

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

288
.drone.yml Normal file
View file

@ -0,0 +1,288 @@
---
kind: pipeline
name: default
node:
nix-daemon: 1
steps:
- name: check formatting
image: nixpkgs/nix:nixos-22.05
commands:
- nix-shell --attr rust --run "cargo fmt -- --check"
- name: build
image: nixpkgs/nix:nixos-22.05
commands:
- nix-build --no-build-output --attr clippy.amd64 --argstr git_version ${DRONE_TAG:-$DRONE_COMMIT}
- name: unit + func tests
image: nixpkgs/nix:nixos-22.05
environment:
GARAGE_TEST_INTEGRATION_EXE: result-bin/bin/garage
commands:
- nix-build --no-build-output --attr clippy.amd64 --argstr git_version ${DRONE_TAG:-$DRONE_COMMIT}
- nix-build --no-build-output --attr test.amd64
- ./result/bin/garage_db-*
- ./result/bin/garage_api-*
- ./result/bin/garage_model-*
- ./result/bin/garage_rpc-*
- ./result/bin/garage_table-*
- ./result/bin/garage_util-*
- ./result/bin/garage_web-*
- ./result/bin/garage-*
- ./result/bin/integration-*
- rm result
- name: integration tests
image: nixpkgs/nix:nixos-22.05
commands:
- nix-build --no-build-output --attr clippy.amd64 --argstr git_version ${DRONE_TAG:-$DRONE_COMMIT}
- nix-shell --attr integration --run ./script/test-smoke.sh || (cat /tmp/garage.log; false)
trigger:
event:
- custom
- push
- pull_request
- tag
- cron
---
kind: pipeline
type: docker
name: release-linux-amd64
node:
nix-daemon: 1
steps:
- name: build
image: nixpkgs/nix:nixos-22.05
commands:
- nix-build --no-build-output --attr pkgs.amd64.release --argstr git_version ${DRONE_TAG:-$DRONE_COMMIT}
- nix-shell --attr rust --run "./script/not-dynamic.sh result-bin/bin/garage"
- name: integration
image: nixpkgs/nix:nixos-22.05
commands:
- nix-shell --attr integration --run ./script/test-smoke.sh || (cat /tmp/garage.log; false)
- name: push static binary
image: nixpkgs/nix:nixos-22.05
environment:
AWS_ACCESS_KEY_ID:
from_secret: garagehq_aws_access_key_id
AWS_SECRET_ACCESS_KEY:
from_secret: garagehq_aws_secret_access_key
TARGET: "x86_64-unknown-linux-musl"
commands:
- nix-shell --attr release --run "to_s3"
- name: docker build and publish
image: nixpkgs/nix:nixos-22.05
environment:
DOCKER_AUTH:
from_secret: docker_auth
DOCKER_PLATFORM: "linux/amd64"
CONTAINER_NAME: "dxflrs/amd64_garage"
HOME: "/kaniko"
commands:
- mkdir -p /kaniko/.docker
- echo $DOCKER_AUTH > /kaniko/.docker/config.json
- export CONTAINER_TAG=${DRONE_TAG:-$DRONE_COMMIT}
- nix-shell --attr release --run "to_docker"
trigger:
event:
- promote
- cron
---
kind: pipeline
type: docker
name: release-linux-i386
node:
nix-daemon: 1
steps:
- name: build
image: nixpkgs/nix:nixos-22.05
commands:
- nix-build --no-build-output --attr pkgs.i386.release --argstr git_version ${DRONE_TAG:-$DRONE_COMMIT}
- nix-shell --attr rust --run "./script/not-dynamic.sh result-bin/bin/garage"
- name: integration
image: nixpkgs/nix:nixos-22.05
commands:
- nix-shell --attr integration --run ./script/test-smoke.sh || (cat /tmp/garage.log; false)
- name: push static binary
image: nixpkgs/nix:nixos-22.05
environment:
AWS_ACCESS_KEY_ID:
from_secret: garagehq_aws_access_key_id
AWS_SECRET_ACCESS_KEY:
from_secret: garagehq_aws_secret_access_key
TARGET: "i686-unknown-linux-musl"
commands:
- nix-shell --attr release --run "to_s3"
- name: docker build and publish
image: nixpkgs/nix:nixos-22.05
environment:
DOCKER_AUTH:
from_secret: docker_auth
DOCKER_PLATFORM: "linux/386"
CONTAINER_NAME: "dxflrs/386_garage"
HOME: "/kaniko"
commands:
- mkdir -p /kaniko/.docker
- echo $DOCKER_AUTH > /kaniko/.docker/config.json
- export CONTAINER_TAG=${DRONE_TAG:-$DRONE_COMMIT}
- nix-shell --attr release --run "to_docker"
trigger:
event:
- promote
- cron
---
kind: pipeline
type: docker
name: release-linux-arm64
node:
nix-daemon: 1
steps:
- name: build
image: nixpkgs/nix:nixos-22.05
commands:
- nix-build --no-build-output --attr pkgs.arm64.release --argstr git_version ${DRONE_TAG:-$DRONE_COMMIT}
- nix-shell --attr rust --run "./script/not-dynamic.sh result-bin/bin/garage"
- name: push static binary
image: nixpkgs/nix:nixos-22.05
environment:
AWS_ACCESS_KEY_ID:
from_secret: garagehq_aws_access_key_id
AWS_SECRET_ACCESS_KEY:
from_secret: garagehq_aws_secret_access_key
TARGET: "aarch64-unknown-linux-musl"
commands:
- nix-shell --attr release --run "to_s3"
- name: docker build and publish
image: nixpkgs/nix:nixos-22.05
environment:
DOCKER_AUTH:
from_secret: docker_auth
DOCKER_PLATFORM: "linux/arm64"
CONTAINER_NAME: "dxflrs/arm64_garage"
HOME: "/kaniko"
commands:
- mkdir -p /kaniko/.docker
- echo $DOCKER_AUTH > /kaniko/.docker/config.json
- export CONTAINER_TAG=${DRONE_TAG:-$DRONE_COMMIT}
- nix-shell --attr release --run "to_docker"
trigger:
event:
- promote
- cron
---
kind: pipeline
type: docker
name: release-linux-arm
node:
nix-daemon: 1
steps:
- name: build
image: nixpkgs/nix:nixos-22.05
commands:
- nix-build --no-build-output --attr pkgs.arm.release --argstr git_version ${DRONE_TAG:-$DRONE_COMMIT}
- nix-shell --attr rust --run "./script/not-dynamic.sh result-bin/bin/garage"
- name: push static binary
image: nixpkgs/nix:nixos-22.05
environment:
AWS_ACCESS_KEY_ID:
from_secret: garagehq_aws_access_key_id
AWS_SECRET_ACCESS_KEY:
from_secret: garagehq_aws_secret_access_key
TARGET: "armv6l-unknown-linux-musleabihf"
commands:
- nix-shell --attr release --run "to_s3"
- name: docker build and publish
image: nixpkgs/nix:nixos-22.05
environment:
DOCKER_AUTH:
from_secret: docker_auth
DOCKER_PLATFORM: "linux/arm"
CONTAINER_NAME: "dxflrs/arm_garage"
HOME: "/kaniko"
commands:
- mkdir -p /kaniko/.docker
- echo $DOCKER_AUTH > /kaniko/.docker/config.json
- export CONTAINER_TAG=${DRONE_TAG:-$DRONE_COMMIT}
- nix-shell --attr release --run "to_docker"
trigger:
event:
- promote
- cron
---
kind: pipeline
type: docker
name: refresh-release-page
node:
nix-daemon: 1
steps:
- name: multiarch-docker
image: nixpkgs/nix:nixos-22.05
environment:
DOCKER_AUTH:
from_secret: docker_auth
HOME: "/root"
commands:
- mkdir -p /root/.docker
- echo $DOCKER_AUTH > /root/.docker/config.json
- export CONTAINER_TAG=${DRONE_TAG:-$DRONE_COMMIT}
- nix-shell --attr release --run "multiarch_docker"
- name: refresh-index
image: nixpkgs/nix:nixos-22.05
environment:
AWS_ACCESS_KEY_ID:
from_secret: garagehq_aws_access_key_id
AWS_SECRET_ACCESS_KEY:
from_secret: garagehq_aws_secret_access_key
commands:
- mkdir -p /etc/nix && cp nix/nix.conf /etc/nix/nix.conf
- nix-shell --attr release --run "refresh_index"
depends_on:
- release-linux-amd64
- release-linux-i386
- release-linux-arm64
- release-linux-arm
trigger:
event:
- promote
- cron
---
kind: signature
hmac: ac09a5a8c82502f67271f93afa1e1e21ce66383b8e24a6deb26b285cc1c378ba
...

View file

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

View file

@ -1,29 +0,0 @@
when:
event:
- deployment
- cron
depends_on:
- release
steps:
- name: refresh-index
image: nixpkgs/nix:nixos-22.05
secrets:
- source: garagehq_aws_access_key_id
target: AWS_ACCESS_KEY_ID
- source: garagehq_aws_secret_access_key
target: AWS_SECRET_ACCESS_KEY
commands:
- mkdir -p /etc/nix && cp nix/nix.conf /etc/nix/nix.conf
- nix-shell --attr ci --run "refresh_index"
- name: multiarch-docker
image: nixpkgs/nix:nixos-22.05
secrets:
- docker_auth
commands:
- mkdir -p /root/.docker
- echo $DOCKER_AUTH > /root/.docker/config.json
- export CONTAINER_TAG=${CI_COMMIT_TAG:-$CI_COMMIT_SHA}
- nix-shell --attr ci --run "multiarch_docker"

View file

@ -1,70 +0,0 @@
when:
event:
- deployment
- cron
matrix:
include:
- ARCH: amd64
TARGET: x86_64-unknown-linux-musl
- ARCH: i386
TARGET: i686-unknown-linux-musl
- ARCH: arm64
TARGET: aarch64-unknown-linux-musl
- ARCH: arm
TARGET: armv6l-unknown-linux-musleabihf
steps:
- name: build
image: nixpkgs/nix:nixos-22.05
commands:
- nix-build --no-build-output --attr pkgs.${ARCH}.release --argstr git_version ${CI_COMMIT_TAG:-$CI_COMMIT_SHA}
- name: check is static binary
image: nixpkgs/nix:nixos-22.05
commands:
- nix-build --no-build-output --attr pkgs.${ARCH}.release --argstr git_version ${CI_COMMIT_TAG:-$CI_COMMIT_SHA}
- nix-shell --attr ci --run "./script/not-dynamic.sh result-bin/bin/garage"
- name: integration tests
image: nixpkgs/nix:nixos-22.05
commands:
- nix-shell --attr ci --run ./script/test-smoke.sh || (cat /tmp/garage.log; false)
when:
- matrix:
ARCH: amd64
- matrix:
ARCH: i386
- name: upgrade tests
image: nixpkgs/nix:nixos-22.05
commands:
- nix-shell --attr ci --run "./script/test-upgrade.sh v0.8.4 x86_64-unknown-linux-musl" || (cat /tmp/garage.log; false)
when:
- matrix:
ARCH: amd64
- name: push static binary
image: nixpkgs/nix:nixos-22.05
environment:
TARGET: "${TARGET}"
secrets:
- source: garagehq_aws_access_key_id
target: AWS_ACCESS_KEY_ID
- source: garagehq_aws_secret_access_key
target: AWS_SECRET_ACCESS_KEY
commands:
- nix-shell --attr ci --run "to_s3"
- name: docker build and publish
image: nixpkgs/nix:nixos-22.05
environment:
DOCKER_PLATFORM: "linux/${ARCH}"
CONTAINER_NAME: "dxflrs/${ARCH}_garage"
secrets:
- docker_auth
commands:
- mkdir -p /root/.docker
- echo $DOCKER_AUTH > /root/.docker/config.json
- export CONTAINER_TAG=${CI_COMMIT_TAG:-$CI_COMMIT_SHA}
- nix-shell --attr ci --run "to_docker"

2388
Cargo.lock generated

File diff suppressed because it is too large Load diff

4990
Cargo.nix

File diff suppressed because it is too large Load diff

View file

@ -3,7 +3,6 @@ resolver = "2"
members = [
"src/db",
"src/util",
"src/net",
"src/rpc",
"src/table",
"src/block",
@ -18,135 +17,19 @@ members = [
default-members = ["src/garage"]
[workspace.dependencies]
# Internal Garage crates
format_table = { version = "0.1.1", path = "src/format-table" }
garage_api = { version = "1.0.1", path = "src/api" }
garage_block = { version = "1.0.1", path = "src/block" }
garage_db = { version = "1.0.1", path = "src/db", default-features = false }
garage_model = { version = "1.0.1", path = "src/model", default-features = false }
garage_net = { version = "1.0.1", path = "src/net" }
garage_rpc = { version = "1.0.1", path = "src/rpc" }
garage_table = { version = "1.0.1", path = "src/table" }
garage_util = { version = "1.0.1", path = "src/util" }
garage_web = { version = "1.0.1", path = "src/web" }
garage_api = { version = "0.8.2", path = "src/api" }
garage_block = { version = "0.8.2", path = "src/block" }
garage_db = { version = "0.8.2", path = "src/db", default-features = false }
garage_model = { version = "0.8.2", path = "src/model", default-features = false }
garage_rpc = { version = "0.8.2", path = "src/rpc" }
garage_table = { version = "0.8.2", path = "src/table" }
garage_util = { version = "0.8.2", path = "src/util" }
garage_web = { version = "0.8.2", path = "src/web" }
k2v-client = { version = "0.0.4", path = "src/k2v-client" }
# External crates from crates.io
arc-swap = "1.0"
argon2 = "0.5"
async-trait = "0.1.7"
backtrace = "0.3"
base64 = "0.21"
blake2 = "0.10"
bytes = "1.0"
bytesize = "1.1"
cfg-if = "1.0"
chrono = "0.4"
crc32fast = "1.4"
crc32c = "0.6"
crypto-common = "0.1"
digest = "0.10"
err-derive = "0.3"
gethostname = "0.4"
git-version = "0.3.4"
hex = "0.4"
hexdump = "0.1"
hmac = "0.12"
idna = "0.5"
itertools = "0.12"
ipnet = "2.9.0"
lazy_static = "1.4"
md-5 = "0.10"
mktemp = "0.5"
nix = { version = "0.27", default-features = false, features = ["fs"] }
nom = "7.1"
parse_duration = "2.1"
pin-project = "1.0.12"
pnet_datalink = "0.34"
rand = "0.8"
sha1 = "0.10"
sha2 = "0.10"
timeago = { version = "0.4", default-features = false }
xxhash-rust = { version = "0.8", default-features = false, features = ["xxh3"] }
aes-gcm = { version = "0.10", features = ["aes", "stream"] }
sodiumoxide = { version = "0.2.5-0", package = "kuska-sodiumoxide" }
kuska-handshake = { version = "0.2.0", features = ["default", "async_std"] }
clap = { version = "4.1", features = ["derive", "env"] }
pretty_env_logger = "0.5"
structopt = { version = "0.3", default-features = false }
syslog-tracing = "0.3"
tracing = "0.1"
tracing-subscriber = { version = "0.3", features = ["env-filter"] }
heed = { version = "0.11", default-features = false, features = ["lmdb"] }
rusqlite = "0.31.0"
r2d2 = "0.8"
r2d2_sqlite = "0.24"
async-compression = { version = "0.4", features = ["tokio", "zstd"] }
zstd = { version = "0.13", default-features = false }
quick-xml = { version = "0.26", features = [ "serialize" ] }
rmp-serde = "1.1.2"
serde = { version = "1.0", default-features = false, features = ["derive", "rc"] }
serde_bytes = "0.11"
serde_json = "1.0"
toml = { version = "0.8", default-features = false, features = ["parse"] }
# newer version requires rust edition 2021
k8s-openapi = { version = "0.21", features = ["v1_24"] }
kube = { version = "0.88", default-features = false, features = ["runtime", "derive", "client", "rustls-tls"] }
schemars = "0.8"
reqwest = { version = "0.11", default-features = false, features = ["rustls-tls-manual-roots", "json"] }
form_urlencoded = "1.0.0"
http = "1.0"
httpdate = "1.0"
http-range = "0.1"
http-body-util = "0.1"
hyper = { version = "1.0", default-features = false }
hyper-util = { version = "0.1", features = [ "full" ] }
multer = "3.0"
percent-encoding = "2.2"
roxmltree = "0.19"
url = "2.3"
futures = "0.3"
futures-util = "0.3"
tokio = { version = "1.0", default-features = false, features = ["net", "rt", "rt-multi-thread", "io-util", "net", "time", "macros", "sync", "signal", "fs"] }
tokio-util = { version = "0.7", features = ["compat", "io"] }
tokio-stream = { version = "0.1", features = ["net"] }
opentelemetry = { version = "0.17", features = [ "rt-tokio", "metrics", "trace" ] }
opentelemetry-prometheus = "0.10"
opentelemetry-otlp = "0.10"
opentelemetry-contrib = "0.9"
prometheus = "0.13"
# used by the k2v-client crate only
aws-sigv4 = { version = "1.1" }
hyper-rustls = { version = "0.26", features = ["http2"] }
log = "0.4"
thiserror = "1.0"
# ---- used only as build / dev dependencies ----
assert-json-diff = "2.0"
rustc_version = "0.4.0"
static_init = "1.0"
aws-config = "1.1.4"
aws-sdk-config = "1.13"
aws-sdk-s3 = "1.14"
[profile.dev]
#lto = "thin" # disabled for now, adds 2-4 min to each CI build
lto = "off"
[profile.release]
lto = true
codegen-units = 1
opt-level = "s"
strip = true
debug = true

View file

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

View file

@ -40,6 +40,7 @@ in {
features = [
"garage/bundled-libs"
"garage/k2v"
"garage/sled"
"garage/lmdb"
"garage/sqlite"
];

View file

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

File diff suppressed because it is too large Load diff

View file

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

View file

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

View file

@ -23,7 +23,7 @@ client = minio.Minio(
"GKyourapikey",
"abcd[...]1234",
# Force the region, this is specific to garage
region="garage",
region="region",
)
```
@ -80,7 +80,7 @@ from garage_admin_sdk.apis import *
from garage_admin_sdk.models import *
configuration = garage_admin_sdk.Configuration(
host = "http://localhost:3903/v1",
host = "http://localhost:3903/v0",
access_token = "s3cr3t"
)
@ -94,14 +94,13 @@ print(f"running garage {status.garage_version}, node_id {status.node}")
# Change layout of this node
current = layout.get_layout()
layout.add_layout([
NodeRoleChange(
id = status.node,
layout.add_layout({
status.node: NodeClusterInfo(
zone = "dc1",
capacity = 1000000000,
capacity = 1,
tags = [ "dev" ],
)
])
})
layout.apply_layout(LayoutVersion(
version = current.version + 1
))

View file

@ -37,7 +37,7 @@ Second, we suppose you have created a key and a bucket.
As a reminder, you can create a key for your nextcloud instance as follow:
```bash
garage key create nextcloud-key
garage key new --name nextcloud-key
```
Keep the Key ID and the Secret key in a pad, they will be needed later.
@ -80,53 +80,6 @@ To test your new configuration, just reload your Nextcloud webpage and start sen
*External link:* [Nextcloud Documentation > Primary Storage](https://docs.nextcloud.com/server/latest/admin_manual/configuration_files/primary_storage.html)
#### SSE-C encryption (since Garage v1.0)
Since version 1.0, Garage supports server-side encryption with customer keys
(SSE-C). In this mode, Garage is responsible for encrypting and decrypting
objects, but it does not store the encryption key itself. The encryption key
should be provided by Nextcloud upon each request. This mode of operation is
supported by Nextcloud and it has successfully been tested together with
Garage.
To enable SSE-C encryption:
1. Make sure your Garage server is accessible via SSL through a reverse proxy
such as Nginx, and that it is using a valid public certificate (Nextcloud
might be able to connect to an S3 server that is using a self-signed
certificate, but you will lose many hours while trying, so don't).
Configure values for `use_ssl` and `port` accordingly in your `config.php`
file.
2. Generate an encryption key using the following command:
```
openssl rand -base64 32
```
Make sure to keep this key **secret**!
3. Add the encryption key in your `config.php` file as follows:
```php
<?php
$CONFIG = array(
'objectstore' => [
'class' => '\\OC\\Files\\ObjectStore\\S3',
'arguments' => [
...
'sse_c_key' => 'exampleencryptionkeyLbU+5fKYQcVoqnn+RaIOXgo=',
...
],
],
```
Nextcloud will now make Garage encrypt files at rest in the storage bucket.
These files will not be readable by an S3 client that has credentials to the
bucket but doesn't also know the secret encryption key.
### External Storage
**From the GUI.** Activate the "External storage support" app from the "Applications" page (click on your account icon on the top right corner of your screen to display the menu). Go to your parameters page (also located below your account icon). Click on external storage (or the corresponding translation in your language).
@ -186,14 +139,14 @@ a reasonable trade-off for some instances.
Create a key for Peertube:
```bash
garage key create peertube-key
garage key new --name peertube-key
```
Keep the Key ID and the Secret key in a pad, they will be needed later.
We need two buckets, one for normal videos (named peertube-video) and one for webtorrent videos (named peertube-playlist).
```bash
garage bucket create peertube-videos
garage bucket create peertube-video
garage bucket create peertube-playlist
```
@ -263,7 +216,7 @@ object_storage:
# Same settings but for webtorrent videos
videos:
bucket_name: 'peertube-videos'
bucket_name: 'peertube-video'
prefix: ''
# You must fill this field to make Peertube use our reverse proxy/website logic
base_url: 'http://peertube-videos.web.garage.localhost'
@ -292,7 +245,7 @@ with average object size ranging from 50 KB to 150 KB.
As such, your Garage cluster should be configured appropriately for good performance:
- use Garage v0.8.0 or higher with the [LMDB database engine](@documentation/reference-manual/configuration.md#db-engine-since-v0-8-0).
Older versions of Garage used the Sled database engine which had issues, such as databases quickly ending up taking tens of GB of disk space.
With the default Sled database engine, your database could quickly end up taking tens of GB of disk space.
- the Garage database should be stored on a SSD
### Creating your bucket
@ -300,7 +253,7 @@ As such, your Garage cluster should be configured appropriately for good perform
This is the usual Garage setup:
```bash
garage key create mastodon-key
garage key new --name mastodon-key
garage bucket create mastodon-data
garage bucket allow mastodon-data --read --write --key mastodon-key
```
@ -335,7 +288,6 @@ 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
```
@ -354,6 +306,8 @@ 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.
@ -425,7 +379,7 @@ Supposing you have a working synapse installation, you can add the module with p
Now create a bucket and a key for your matrix instance (note your Key ID and Secret Key somewhere, they will be needed later):
```bash
garage key create matrix-key
garage key new --name matrix-key
garage bucket create matrix
garage bucket allow matrix --read --write --key matrix-key
```
@ -467,7 +421,7 @@ Now we can write a simple script (eg `~/.local/bin/matrix-cache-gc`):
## CONFIGURATION ##
AWS_ACCESS_KEY_ID=GKxxx
AWS_SECRET_ACCESS_KEY=xxxx
AWS_ENDPOINT_URL=http://localhost:3900
S3_ENDPOINT=http://localhost:3900
S3_BUCKET=matrix
MEDIA_STORE=/var/lib/matrix-synapse/media
PG_USER=matrix
@ -488,7 +442,7 @@ EOF
s3_media_upload update-db 1d
s3_media_upload --no-progress check-deleted $MEDIA_STORE
s3_media_upload --no-progress upload $MEDIA_STORE $S3_BUCKET --delete --endpoint-url $AWS_ENDPOINT_URL
s3_media_upload --no-progress upload $MEDIA_STORE $S3_BUCKET --delete --endpoint-url $S3_ENDPOINT
```
This script will list all the medias that were not accessed in the 24 hours according to your database.

View file

@ -54,9 +54,9 @@ how to configure this.
Create your key and bucket:
```bash
garage key create my-key
garage bucket create backups
garage bucket allow backups --read --write --key my-key
garage key new my-key
garage bucket create backup
garage bucket allow backup --read --write --key my-key
```
Then register your Key ID and Secret key in your environment:

View file

@ -70,17 +70,16 @@ Then a file named `~/.aws/config` and put:
```toml
[default]
region=garage
endpoint_url=http://127.0.0.1:3900
```
Now, supposing Garage is listening on `http://127.0.0.1:3900`, you can list your buckets with:
```bash
aws s3 ls
aws --endpoint-url http://127.0.0.1:3900 s3 ls
```
If you're using awscli `<1.29.0` or `<2.13.0`, you need to pass `--endpoint-url` to each CLI invocation explicitly.
As a workaround, you can redefine the aws command by editing the file `~/.bashrc` in this case:
Passing the `--endpoint-url` parameter to each command is annoying but AWS developers do not provide a corresponding configuration entry.
As a workaround, you can redefine the aws command by editing the file `~/.bashrc`:
```
function aws { command aws --endpoint-url http://127.0.0.1:3900 $@ ; }
@ -259,7 +258,7 @@ 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:

View file

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

View file

@ -7,23 +7,10 @@ Garage is also available in binary packages on:
## Alpine Linux
If you use Alpine Linux, you can simply install the
[garage](https://pkgs.alpinelinux.org/packages?name=garage) package from the
Alpine Linux repositories (available since v3.17):
```bash
apk add garage
apk install garage
```
The default configuration file is installed to `/etc/garage.toml`. You can run
Garage using: `rc-service garage start`. If you don't specify `rpc_secret`, it
will be automatically replaced with a random string on the first start.
Please note that this package is built without Consul discovery, Kubernetes
discovery, OpenTelemetry exporter, and K2V features (K2V will be enabled once
it's stable).
## Arch Linux
Garage is available in the [AUR](https://aur.archlinux.org/packages/garage).

View file

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

View file

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

View file

@ -90,6 +90,6 @@ The following feature flags are available in v0.8.0:
| `kubernetes-discovery` | optional | Enable automatic registration and discovery<br>of cluster nodes through the Kubernetes API |
| `metrics` | *by default* | Enable collection of metrics in Prometheus format on the admin API |
| `telemetry-otlp` | optional | Enable collection of execution traces using OpenTelemetry |
| `syslog` | optional | Enable logging to Syslog |
| `lmdb` | *by default* | Enable using LMDB to store Garage's metadata |
| `sqlite` | *by default* | Enable using Sqlite3 to store Garage's metadata |
| `sled` | *by default* | Enable using Sled to store Garage's metadata |
| `lmdb` | optional | Enable using LMDB to store Garage's metadata |
| `sqlite` | optional | Enable using Sqlite3 to store Garage's metadata |

View file

@ -18,7 +18,7 @@ api_bind_addr = "0.0.0.0:3903"
```
This will allow anyone to scrape Prometheus metrics by fetching
`http://localhost:3903/metrics`. If you want to restrict access
`http://localhost:3093/metrics`. If you want to restrict access
to the exported metrics, set the `metrics_token` configuration value
to a bearer token to be used when fetching the metrics endpoint.

View file

@ -19,10 +19,9 @@ To run a real-world deployment, make sure the following conditions are met:
- You have at least three machines with sufficient storage space available.
- Each machine has an IP address which makes it directly reachable by all other machines.
In many cases, nodes will be behind a NAT and will not each have a public
IPv4 addresses. In this case, is recommended that you use IPv6 for this
end-to-end connectivity if it is available. Otherwise, using a mesh VPN such as
- Each machine has a public IP address which is reachable by other machines. It
is highly recommended that you use IPv6 for this end-to-end connectivity. If
IPv6 is not available, then using a mesh VPN such as
[Nebula](https://github.com/slackhq/nebula) or
[Yggdrasil](https://yggdrasil-network.github.io/) are approaches to consider
in addition to building out your own VPN tunneling.
@ -43,7 +42,7 @@ For our example, we will suppose the following infrastructure with IPv6 connecti
| Brussels | Mars | fc00:F::1 | 1.5 TB |
Note that Garage will **always** store the three copies of your data on nodes at different
locations. This means that in the case of this small example, the usable capacity
locations. This means that in the case of this small example, the available capacity
of the cluster is in fact only 1.5 TB, because nodes in Brussels can't store more than that.
This also means that nodes in Paris and London will be under-utilized.
To make better use of the available hardware, you should ensure that the capacity
@ -53,9 +52,9 @@ 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 +67,36 @@ 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. Make sure to use the LMDB database engine,
instead of Sled, which suffers from quite bad performance degradation on HDDs.
Sled is still the default for legacy reasons, but is not recommended anymore.
- For the metadata storage, Garage does not do checksumming and integrity
verification on its own, 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 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.
- Having a single server with several storage drives is currently not very well
supported in Garage ([#218](https://git.deuxfleurs.fr/Deuxfleurs/garage/issues/218)).
For an easy setup, just put all your drives in a RAID0 or a ZFS RAIDZ array.
If you're adventurous, you can try to format each of your disk as
a separate XFS partition, and then run one `garage` daemon per disk drive,
or use something like [`mergerfs`](https://github.com/trapexit/mergerfs) to merge
all your disks in a single union filesystem that spreads load over them.
## 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. `v1.0.1`) and not the `latest` tag.
For this example, we will use the latest published version at the time of the writing which is `v1.0.1` but it's up to you
We encourage you to use a fixed tag (eg. `v0.8.0`) and not the `latest` tag.
For this example, we will use the latest published version at the time of the writing which is `v0.8.0` but it's up to you
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:v1.0.1
sudo docker pull dxflrs/garage:v0.8.0
```
## Deploying and configuring Garage
@ -126,9 +119,8 @@ 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
replication_mode = "3"
compression_level = 2
@ -152,8 +144,6 @@ 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`.
@ -171,13 +161,12 @@ 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:v1.0.1
dxflrs/garage:v0.8.0
```
With this command line, Garage should be started automatically at each boot.
Please note that we use host networking as otherwise the network indirection
added by Docker would prevent Garage nodes from communicating with one another
(especially if using IPv6).
It should be restarted automatically at each reboot.
Please note that we use host networking as otherwise Docker containers
can not communicate with IPv6.
If you want to use `docker-compose`, you may use the following `docker-compose.yml` file as a reference:
@ -185,7 +174,7 @@ If you want to use `docker-compose`, you may use the following `docker-compose.y
version: "3"
services:
garage:
image: dxflrs/garage:v1.0.1
image: dxflrs/garage:v0.8.0
network_mode: "host"
restart: unless-stopped
volumes:
@ -194,14 +183,12 @@ services:
- /var/lib/garage/data:/var/lib/garage/data
```
If you wish to upgrade your cluster, make sure to read the corresponding
[documentation page](@/documentation/operations/upgrading.md) first, as well as
the documentation relevant to your version of Garage in the case of major
upgrades. With the containerized setup proposed here, the upgrade process
will require stopping and removing the existing container, and re-creating it
with the upgraded version.
Upgrading between Garage versions should be supported transparently,
but please check the relase notes before doing so!
To upgrade, simply stop and remove this container and
start again the command with a new version of Garage.
## Controlling the daemon
## Controling the daemon
The `garage` binary has two purposes:
- it acts as a daemon when launched with `garage server`
@ -259,7 +246,7 @@ 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:
@ -283,12 +270,12 @@ of a role that is assigned to each active cluster node.
For our example, we will suppose we have the following infrastructure
(Capacity, Identifier and Zone are specific values to Garage described in the following):
| Location | Name | Disk Space | Identifier | Zone (`-z`) | Capacity (`-c`) |
|----------|---------|------------|------------|-------------|-----------------|
| Paris | Mercury | 1 TB | `563e` | `par1` | `1T` |
| Paris | Venus | 2 TB | `86f0` | `par1` | `2T` |
| London | Earth | 2 TB | `6814` | `lon1` | `2T` |
| Brussels | Mars | 1.5 TB | `212f` | `bru1` | `1.5T` |
| Location | Name | Disk Space | `Capacity` | `Identifier` | `Zone` |
|----------|---------|------------|------------|--------------|--------------|
| Paris | Mercury | 1 TB | `10` | `563e` | `par1` |
| Paris | Venus | 2 TB | `20` | `86f0` | `par1` |
| London | Earth | 2 TB | `20` | `6814` | `lon1` |
| Brussels | Mars | 1.5 TB | `15` | `212f` | `bru1` |
#### Node identifiers
@ -310,8 +297,6 @@ garage status
It will display the IP address associated with each node;
from the IP address you will be able to recognize the node.
We will now use the `garage layout assign` command to configure the correct parameters for each node.
#### Zones
Zones are simply a user-chosen identifier that identify a group of server that are grouped together logically.
@ -321,29 +306,29 @@ In most cases, a zone will correspond to a geographical location (i.e. a datacen
Behind the scene, Garage will use zone definition to try to store the same data on different zones,
in order to provide high availability despite failure of a zone.
Zones are passed to Garage using the `-z` flag of `garage layout assign` (see below).
#### Capacity
Garage needs to know the storage capacity (disk space) it can/should use on
each node, to be able to correctly balance data.
Garage reasons on an abstract metric about disk storage that is named the *capacity* of a node.
The capacity configured in Garage must be proportional to the disk space dedicated to the node.
Capacity values are expressed in bytes and are passed to Garage using the `-c` flag of `garage layout assign` (see below).
Capacity values must be **integers** but can be given any signification.
Here we chose that 1 unit of capacity = 100 GB.
#### Tags
You can add additional tags to nodes using the `-t` flag of `garage layout assign` (see below).
Tags have no specific meaning for Garage and can be used at your convenience.
Note that the amount of data stored by Garage on each server may not be strictly proportional to
its capacity value, as Garage will priorize having 3 copies of data in different zones,
even if this means that capacities will not be strictly respected. For example in our above examples,
nodes Earth and Mars will always store a copy of everything each, and the third copy will
have 66% chance of being stored by Venus and 33% chance of being stored by Mercury.
#### Injecting the topology
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 563e -z par1 -c 10 -t mercury
garage layout assign 86f0 -z par1 -c 20 -t venus
garage layout assign 6814 -z lon1 -c 20 -t earth
garage layout assign 212f -z bru1 -c 15 -t mars
```
At this point, the changes in the cluster layout have not yet been applied.
@ -353,7 +338,6 @@ To show the new layout that will be applied, call:
garage layout show
```
Make sure to read carefully the output of `garage layout show`.
Once you are satisfied with your new layout, apply it with:
```bash

View file

@ -472,32 +472,3 @@ https:// {
More information on how this endpoint is implemented in Garage is available
in the [Admin API Reference](@/documentation/reference-manual/admin-api.md) page.
### Fileserver browser
Caddy's built-in
[file_server](https://caddyserver.com/docs/caddyfile/directives/file_server)
browser functionality can be extended with the
[caddy-fs-s3](https://github.com/sagikazarmark/caddy-fs-s3) module.
This can be configured to use Garage as a backend with the following
configuration:
```caddy
browse.garage.tld {
file_server {
fs s3 {
bucket test-bucket
region garage
endpoint https://s3.garage.tld
use_path_style
}
browse
}
}
```
Caddy must also be configured with the required `AWS_ACCESS_KEY_ID` and
`AWS_SECRET_ACCESS_KEY` environment variables to access the bucket.

View file

@ -48,22 +48,7 @@ locations. They use Garage themselves for the following tasks:
- As a backup target using `rclone` and `restic`
- In the Drone continuous integration platform to store task logs
The Deuxfleurs Garage cluster is a multi-site cluster currently composed of
9 nodes in 3 physical locations.
### Triplebit
[Triplebit](https://www.triplebit.org) is a non-profit hosting provider and
ISP focused on improving access to privacy-related services. They use
Garage themselves for the following tasks:
- Hosting of their homepage, [privacyguides.org](https://www.privacyguides.org/), and various other static sites
- As a Mastodon object storage backend for [mstdn.party](https://mstdn.party/) and [mstdn.plus](https://mstdn.plus/)
- As a PeerTube storage backend for [neat.tube](https://neat.tube/)
- As a [Matrix media backend](https://github.com/matrix-org/synapse-s3-storage-provider)
Triplebit's Garage cluster is a multi-site cluster currently composed of
10 nodes in 3 physical locations.

View file

@ -97,7 +97,7 @@ delete a tombstone, the following condition has to be met:
superseeded by the tombstone. This ensures that deleting the tombstone is
safe and that no deleted value will come back in the system.
Garage uses atomic database operations (such as compare-and-swap and
Garage makes use of Sled's atomic operations (such as compare-and-swap and
transactions) to ensure that only tombstones that have been correctly
propagated to other nodes are ever deleted from the local entry tree.

View file

@ -67,7 +67,7 @@ Pithos has been abandonned and should probably not used yet, in the following we
Pithos was relying as a S3 proxy in front of Cassandra (and was working with Scylla DB too).
From its designers' mouth, storing data in Cassandra has shown its limitations justifying the project abandonment.
They built a closed-source version 2 that does not store blobs in the database (only metadata) but did not communicate further on it.
We considered 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*

View file

@ -80,7 +80,7 @@ nix-build \
--git_version $(git rev-parse HEAD)
```
*The result is located in `result/bin`. You can pass arguments to cross compile: check `.woodpecker/release.yml` for examples.*
*The result is located in `result/bin`. You can pass arguments to cross compile: check `.drone.yml` for examples.*
If you modify a `Cargo.toml` or regenerate any `Cargo.lock`, you must run `cargo2nix`:

View file

@ -81,9 +81,12 @@ Our cache will be checked.
- http://www.lpenz.org/articles/nixchannel/index.html
## Woodpecker
## Drone
Woodpecker can do parallelism both at the step and the pipeline level. At the step level, parallelism is restricted to the same runner.
Do not try to set a build as trusted from the interface or the CLI tool,
your request would be ignored. Instead, directly edit the database (table `repos`, column `repo_trusted`).
Drone can do parallelism both at the step and the pipeline level. At the step level, parallelism is restricted to the same runner.
## Building Docker containers
@ -96,4 +99,3 @@ We were:
- Unable to use the kaniko container provided by Google as we can't run arbitrary logic: we need to put our secret in .docker/config.json.
Finally we chose to build kaniko through nix and use it in a `nix-shell`.
We then switched to using kaniko from nixpkgs when it was packaged.

View file

@ -42,7 +42,7 @@ and the docker containers on Docker Hub.
## Automation
We automated our release process with Nix and Woodpecker to make it more reliable.
We automated our release process with Nix and Drone to make it more reliable.
Here we describe how we have done in case you want to debug or improve it.
### Caching build steps
@ -62,31 +62,52 @@ Sending to the cache is done through `nix copy`, for example:
nix copy --to 's3://nix?endpoint=garage.deuxfleurs.fr&region=garage&secret-key=/etc/nix/signing-key.sec' result
```
*The signing key possessed by the Garage maintainers is required to update the Nix cache.*
*Note that you need the signing key. In our case, it is stored as a secret in Drone.*
The previous command will only send the built package and not its dependencies.
In the case of our CI pipeline, we want to cache all intermediate build steps
as well. This can be done using this quite involved command (here as an example
for the `pkgs.amd64.relase` package):
The previous command will only send the built packet and not its dependencies.
To send its dependency, a tool named `nix-copy-closure` has been created but it is not compatible with the S3 protocol.
Instead, you can use the following commands to list all the runtime dependencies:
```bash
nix copy -j8 \
--to 's3://nix?endpoint=garage.deuxfleurs.fr&region=garage&secret-key=/etc/nix/nix-signing-key.sec' \
$(nix path-info pkgs.amd64.release --file default.nix --derivation --recursive | sed 's/\.drv$/.drv^*/')
nix copy \
--to 's3://nix?endpoint=garage.deuxfleurs.fr&region=garage&secret-key=/etc/nix/signing-key.sec' \
$(nix-store -qR result/)
```
This command will simultaneously build all of the required Nix paths (using at
most 8 parallel Nix builder jobs) and send the resulting objects to the cache.
*We could also write this expression with xargs but this tool is not available in our container.*
This can be run for all the Garage packages we build using the following command:
But in certain cases, we want to cache compile time dependencies also.
For example, the Nix project does not provide binaries for cross compiling to i686 and thus we need to compile gcc on our own.
We do not want to compile gcc each time, so even if it is a compile time dependency, we want to cache it.
This time, the command is a bit more involved:
```bash
nix copy --to \
's3://nix?endpoint=garage.deuxfleurs.fr&region=garage&secret-key=/etc/nix/signing-key.sec' \
$(nix-store -qR --include-outputs \
$(nix-instantiate))
```
This is the command we use in our CI as we expect the final binary to change, so we mainly focus on
caching our development dependencies.
*Currently there is no automatic garbage collection of the cache: we should monitor its growth.
Hopefully, we can erase it totally without breaking any build, the next build will only be slower.*
In practise, we concluded that we do not want to cache all the compilation dependencies.
Instead, we want to cache the toolchain we use to build Garage each time we change it.
So we removed from Drone any automatic update of the cache and instead handle them manually with:
```
source ~/.awsrc
nix-shell --attr cache --run 'refresh_cache'
nix-shell --run 'refresh_toolchain'
```
We don't automate this step at each CI build, as *there is currently no automatic garbage collection of the cache.*
This means we should also monitor the cache's size; if it ever becomes too big we can erase it with:
Internally, it will run `nix-build` on `nix/toolchain.nix` and send the output plus its depedencies to the cache.
To erase the cache:
```
mc rm --recursive --force 'garage/nix/'
@ -136,9 +157,9 @@ nix-shell --run refresh_index
If you want to compile for different architectures, you will need to repeat all these commands for each architecture.
**In practice, and except for debugging, you will never directly run these commands. Release is handled by Woodpecker.**
**In practise, and except for debugging, you will never directly run these commands. Release is handled by drone**
### Drone (obsolete)
### Drone
Our instance is available at [https://drone.deuxfleurs.fr](https://drone.deuxfleurs.fr).
You need an account on [https://git.deuxfleurs.fr](https://git.deuxfleurs.fr) to use it.

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
@ -49,7 +49,7 @@ verifications. Of course, scrubbing the entire data store will also take longer.
## Block check and resync
In some cases, nodes hold a reference to a block but do not actually have the block
stored on disk. Conversely, they may also have on-disk blocks that are not referenced
stored on disk. Conversely, they may also have on disk blocks that are not referenced
any more. To fix both cases, a block repair may be run with `garage repair blocks`.
This will scan the entire block reference counter table to check that the blocks
exist on disk, and will scan the entire disk store to check that stored blocks
@ -91,37 +91,9 @@ is definitely lost, then there is no other choice than to declare your S3 object
as unrecoverable, and to delete them properly from the data store. This can be done
using the `garage block purge` command.
## Rebalancing data directories
In [multi-HDD setups](@/documentation/operations/multi-hdd.md), to ensure that
data blocks are well balanced between storage locations, you may run a
rebalance operation using `garage repair rebalance`. This is useful when
adding storage locations or when capacities of the storage locations have been
changed. Once this is finished, Garage will know for each block of a single
possible location where it can be, which can increase access speed. This
operation will also move out all data from locations marked as read-only.
# Metadata operations
## Metadata snapshotting
It is good practice to setup automatic snapshotting of your metadata database
file, to recover from situations where it becomes corrupted on disk. This can
be done at the filesystem level if you are using ZFS or BTRFS.
Since Garage v0.9.4, Garage is able to take snapshots of the metadata database
itself. This basically amounts to copying the database file, except that it can
be run live while Garage is running without the risk of corruption or
inconsistencies. This can be setup to run automatically on a schedule using
[`metadata_auto_snapshot_interval`](@/documentation/reference-manual/configuration.md#metadata_auto_snapshot_interval).
A snapshot can also be triggered manually using the `garage meta snapshot`
command. Note that taking a snapshot using this method is very intensive as it
requires making a full copy of the database file, so you might prefer using
filesystem-level snapshots if possible. To recover a corrupted node from such a
snapshot, read the instructions
[here](@/documentation/operations/recovering.md#corrupted_meta).
## Metadata table resync
Garage automatically resyncs all entries stored in the metadata tables every hour,
@ -141,7 +113,5 @@ blocks may still be held by Garage. If you suspect that such corruption has occu
in your cluster, you can run one of the following repair procedures:
- `garage repair versions`: checks that all versions belong to a non-deleted object, and purges any orphan version
- `garage repair block_refs`: checks that all block references belong to a non-deleted object version, and purges any orphan block reference (this will then allow the blocks to be garbage-collected)
- `garage repair block-refs`: checks that all block references belong to a non-deleted object version, and purges any orphan block reference (this will then allow the blocks to be garbage-collected)
- `garage repair block-rc`: checks that the reference counters for blocks are in sync with the actual number of non-deleted entries in the block reference table

View file

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

View file

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

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
@ -108,57 +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.

View file

@ -9,7 +9,7 @@ On a new version release, there is 2 possibilities:
- protocols and data structures remained the same ➡️ this is a **minor upgrade**
- protocols or data structures changed ➡️ this is a **major upgrade**
You can quickly know what type of update you will have to operate by looking at the version identifier:
You can quickly now what type of update you will have to operate by looking at the version identifier:
when we require our users to do a major upgrade, we will always bump the first nonzero component of the version identifier
(e.g. from v0.7.2 to v0.8.0).
Conversely, for versions that only require a minor upgrade, the first nonzero component will always stay the same (e.g. from v0.8.0 to v0.8.1).
@ -73,18 +73,6 @@ The entire procedure would look something like this:
You can do all of the nodes in a single zone at once as that won't impact global cluster availability.
Do not try to make a backup of the metadata folder of a running node.
**Since Garage v0.9.4,** you can use the `garage meta snapshot --all` command
to take a simultaneous snapshot of the metadata database files of all your
nodes. This avoids the tedious process of having to take them down one by
one before upgrading. Be careful that if automatic snapshotting is enabled,
Garage only keeps the last two snapshots and deletes older ones, so you might
want to disable automatic snapshotting in your upgraded configuration file
until you have confirmed that the upgrade ran successfully. In addition to
snapshotting the metadata databases of your nodes, you should back-up at
least the `cluster_layout` file of one of your Garage instances (this file
should be the same on all nodes and you can copy it safely while Garage is
running).
3. Prepare your binaries and configuration files for the new Garage version
4. Restart all nodes simultaneously in the new version
@ -92,6 +80,6 @@ The entire procedure would look something like this:
5. If any specific migration procedure is required, it is usually in one of the two cases:
- It can be run on online nodes after the new version has started, during regular cluster operation.
- it has to be run offline, in which case you will have to again take all nodes offline one after the other to run the repair
- it has to be run offline
For this last step, please refer to the specific documentation pertaining to the version upgrade you are doing.

View file

@ -35,20 +35,10 @@ Place this binary somewhere in your `$PATH` so that you can invoke the `garage`
command directly (for instance you can copy the binary in `/usr/local/bin`
or in `~/.local/bin`).
You may also check whether your distribution already includes a
[binary package for Garage](@/documentation/cookbook/binary-packages.md).
If a binary of the last version is not available for your architecture,
or if you want a build customized for your system,
you can [build Garage from source](@/documentation/cookbook/from-source.md).
If none of these option work for you, you can also run Garage in a Docker
container. When using Docker, the commands used in this guide will not work
anymore. We recommend reading the tutorial on [configuring a
multi-node cluster](@/documentation/cookbook/real-world.md) to learn about
using Garage as a Docker container. For simplicity, a minimal command to launch
Garage using Docker is provided in this quick start guide as well.
## Configuring and starting Garage
@ -64,9 +54,9 @@ to generate unique and private secrets for security reasons:
cat > garage.toml <<EOF
metadata_dir = "/tmp/meta"
data_dir = "/tmp/data"
db_engine = "sqlite"
db_engine = "lmdb"
replication_factor = 1
replication_mode = "none"
rpc_bind_addr = "[::]:3901"
rpc_public_addr = "127.0.0.1:3901"
@ -86,17 +76,14 @@ index = "index.html"
api_bind_addr = "[::]:3904"
[admin]
api_bind_addr = "[::]:3903"
api_bind_addr = "0.0.0.0:3903"
admin_token = "$(openssl rand -base64 32)"
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 can put
it in the right place. By default, garage looks at **`/etc/garage.toml`.**
Now that your configuration file has been created, you may save it to the directory of your choice.
By default, Garage looks for **`/etc/garage.toml`.**
You can also store it somewhere else, but you will have to specify `-c path/to/garage.toml`
at each invocation of the `garage` binary (for example: `garage -c ./garage.toml server`, `garage -c ./garage.toml status`).
@ -113,39 +100,16 @@ your data to be persisted properly.
### Launching the Garage server
Use the following command to launch the Garage server:
Use the following command to launch the Garage server with our configuration file:
```
garage -c path/to/garage.toml server
garage server
```
If you have placed the `garage.toml` file in `/etc` (its default location), you can simply run `garage server`.
You can tune Garage's verbosity as follows (from less verbose to more verbose):
Alternatively, if you cannot or do not wish to run the Garage binary directly,
you may use Docker to run Garage in a container using the following command:
```bash
docker run \
-d \
--name garaged \
-p 3900:3900 -p 3901:3901 -p 3902:3902 -p 3903:3903 \
-v /etc/garage.toml:/path/to/garage.toml \
-v /var/lib/garage/meta:/path/to/garage/meta \
-v /var/lib/garage/data:/path/to/garage/data \
dxflrs/garage:v0.9.4
```
Under Linux, you can substitute `--network host` for `-p 3900:3900 -p 3901:3901 -p 3902:3902 -p 3903:3903`
#### Troubleshooting
Ensure your configuration file, `metadata_dir` and `data_dir` are readable by the user running the `garage` server or Docker.
You can tune Garage's verbosity by setting the `RUST_LOG=` environment variable. \
Available log levels are (from less verbose to more verbose): `error`, `warn`, `info` *(default)*, `debug` and `trace`.
```bash
RUST_LOG=garage=info garage server # default
RUST_LOG=garage=info garage server
RUST_LOG=garage=debug garage server
RUST_LOG=garage=trace garage server
```
@ -159,10 +123,7 @@ Log level `debug` can help you check why your S3 API calls are not working.
The `garage` utility is also used as a CLI tool to configure your Garage deployment.
It uses values from the TOML configuration file to find the Garage daemon running on the
local node, therefore if your configuration file is not at `/etc/garage.toml` you will
again have to specify `-c path/to/garage.toml` 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.
again have to specify `-c path/to/garage.toml`.
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:
@ -176,7 +137,7 @@ This should show something like this:
```
==== HEALTHY NODES ====
ID Hostname Address Tag Zone Capacity
563e1ac825ee3323 linuxbox 127.0.0.1:3901 NO ROLE ASSIGNED
563e1ac825ee3323 linuxbox 127.0.0.1:3901 NO ROLE ASSIGNED
```
## Creating a cluster layout
@ -189,12 +150,12 @@ For our test deployment, we are using only one node. The way in which we configu
it does not matter, you can simply write:
```bash
garage layout assign -z dc1 -c 1G <node_id>
garage layout assign -z dc1 -c 1 <node_id>
```
where `<node_id>` corresponds to the identifier of the node shown by `garage status` (first column).
You can enter simply a prefix of that identifier.
For instance here you could write just `garage layout assign -z dc1 -c 1G 563e`.
For instance here you could write just `garage layout assign -z dc1 -c 1 563e`.
The layout then has to be applied to the cluster, using:
@ -245,7 +206,7 @@ one key can access multiple buckets, multiple keys can access one bucket.
Create an API key using the following command:
```
garage key create nextcloud-app-key
garage key new --name nextcloud-app-key
```
The output should look as follows:
@ -284,7 +245,7 @@ garage bucket info nextcloud-bucket
```
## Uploading and downloading from Garage
## Uploading and downlading from Garage
To download and upload files on garage, we can use a third-party tool named `awscli`.
@ -305,14 +266,12 @@ named `~/.awsrc` with this content:
export AWS_ACCESS_KEY_ID=xxxx # put your Key ID here
export AWS_SECRET_ACCESS_KEY=xxxx # put your Secret key here
export AWS_DEFAULT_REGION='garage'
export AWS_ENDPOINT_URL='http://localhost:3900'
export AWS_ENDPOINT='http://localhost:3900'
function aws { command aws --endpoint-url $AWS_ENDPOINT $@ ; }
aws --version
```
Note you need to have at least `awscli` `>=1.29.0` or `>=2.13.0`, otherwise you
need to specify `--endpoint-url` explicitly on each `awscli` invocation.
Now, each time you want to use `awscli` on this target, run:
```bash

View file

@ -8,21 +8,18 @@ listen address is specified in the `[admin]` section of the configuration
file (see [configuration file
reference](@/documentation/reference-manual/configuration.md))
**WARNING.** At this point, there is no commitment to the stability of the APIs described in this document.
We will bump the version numbers prefixed to each API endpoint each time the syntax
**WARNING.** At this point, there is no comittement to stability of the APIs described in this document.
We will bump the version numbers prefixed to each API endpoint at each time the syntax
or semantics change, meaning that code that relies on these endpoint will break
when changes are introduced.
Versions:
- Before Garage 0.7.2 - no admin API
- Garage 0.7.2 - admin APIv0
- Garage 0.9.0 - admin APIv1, deprecate admin APIv0
The Garage administration API was introduced in version 0.7.2, this document
does not apply to older versions of Garage.
## Access control
The admin API uses two different tokens for access control, that are specified in the config file's `[admin]` section:
The admin API uses two different tokens for acces control, that are specified in the config file's `[admin]` section:
- `metrics_token`: the token for accessing the Metrics endpoint (if this token
is not set in the config file, the Metrics endpoint can be accessed without
@ -88,8 +85,8 @@ Consult the full health check API endpoint at /v0/health for more details
### On-demand TLS `GET /check`
To prevent abuse for on-demand TLS, Caddy developers have specified an endpoint that can be queried by the reverse proxy
to know if a given domain is allowed to get a certificate. Garage implements these endpoints to tell if a given domain is handled by Garage or is garbage.
To prevent abuses for on-demand TLS, Caddy developpers have specified an endpoint that can be queried by the reverse proxy
to know if a given domain is allowed to get a certificate. Garage implements this endpoints to tell if a given domain is handled by Garage or is garbage.
Garage responds with the following logic:
- If the domain matches the pattern `<bucket-name>.<s3_api.root_domain>`, returns 200 OK
@ -102,7 +99,7 @@ You must manually declare the domain in your reverse-proxy. Idem for K2V.*
*Note 2: buckets in a user's namespace are not supported yet by this endpoint. This is a limitation of this endpoint currently.*
**Example:** Suppose a Garage instance is configured with `s3_api.root_domain = .s3.garage.localhost` and `s3_web.root_domain = .web.garage.localhost`.
**Example:** Suppose a Garage instance configured with `s3_api.root_domain = .s3.garage.localhost` and `s3_web.root_domain = .web.garage.localhost`.
With a private `media` bucket (name in the global namespace, website is disabled), the endpoint will feature the following behavior:
@ -134,9 +131,7 @@ $ curl -so /dev/null -w "%{http_code}" http://localhost:3903/check?domain=exampl
### 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)
These endpoints are defined on a dedicated [Redocly page](https://garagehq.deuxfleurs.fr/api/garage-admin-v0.html). You can also download its [OpenAPI specification](https://garagehq.deuxfleurs.fr/api/garage-admin-v0.yml).
Requesting the API from the command line can be as simple as running:

View file

@ -8,39 +8,27 @@ weight = 20
Here is an example `garage.toml` configuration file that illustrates all of the possible options:
```toml
replication_factor = 3
consistency_mode = "consistent"
metadata_dir = "/var/lib/garage/meta"
data_dir = "/var/lib/garage/data"
metadata_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_size = 1048576
lmdb_map_size = "1T"
sled_cache_capacity = 134217728
sled_flush_every_ms = 2000
replication_mode = "3"
compression_level = 1
rpc_secret = "4425f5c26c5e11581d3223904324dcb5b5d5dfb14e5e7f35e38c595424f5f1e6"
rpc_bind_addr = "[::]:3901"
rpc_bind_outgoing = false
rpc_public_addr = "[fc00:1::1]:3901"
# or set rpc_public_adr_subnet to filter down autodiscovery to a subnet:
# rpc_public_addr_subnet = "2001:0db8:f00:b00:/64"
allow_world_readable_secrets = false
bootstrap_peers = [
"563e1ac825ee3323aa441e72c26d1030d6d4414aeb3dd25287c531e7fc2bc95d@[fc00:1::1]:3901",
"86f0f26ae4afbd59aaf9cfb059eefac844951efd5b8caeec0d53f4ed6c85f332@[fc00:1::2]:3901",
"86f0f26ae4afbd59aaf9cfb059eefac844951efd5b8caeec0d53f4ed6c85f332[fc00:1::2]:3901",
"681456ab91350f92242e80a531a3ec9392cb7c974f72640112f90a600d7921a4@[fc00:B::1]:3901",
"212fd62eeaca72c122b45a7f4fa0f55e012aa5e24ac384a72a3016413fa724ff@[fc00:F::1]:3901",
]
@ -77,8 +65,8 @@ root_domain = ".web.garage"
[admin]
api_bind_addr = "0.0.0.0:3903"
metrics_token = "BCAdFjoa9G0KJR0WXnHHm7fs1ZAbfpI8iIZ+Z/a2NgI="
admin_token = "UkLeGWEvHnXBqnueR3ISEMWpOnm40jH2tM2HnnL/0F4="
metrics_token = "cacce0b2de4bc2d9f5b5fdff551e01ac1496055aed248202d415398987e35f81"
admin_token = "ae8cb40ea7368bbdbb6430af11cca7da833d3458a5f52086f4e805a570fb5c2a"
trace_sink = "http://localhost:4317"
```
@ -86,188 +74,7 @@ The following gives details about each available configuration option.
## Available configuration options
### Index
[Environment variables](#env_variables).
Top-level configuration options:
[`allow_world_readable_secrets`](#allow_world_readable_secrets),
[`block_ram_buffer_max`](#block_ram_buffer_max),
[`block_size`](#block_size),
[`bootstrap_peers`](#bootstrap_peers),
[`compression_level`](#compression_level),
[`data_dir`](#data_dir),
[`data_fsync`](#data_fsync),
[`db_engine`](#db_engine),
[`disable_scrub`](#disable_scrub),
[`use_local_tz`](#use_local_tz),
[`lmdb_map_size`](#lmdb_map_size),
[`metadata_auto_snapshot_interval`](#metadata_auto_snapshot_interval),
[`metadata_dir`](#metadata_dir),
[`metadata_fsync`](#metadata_fsync),
[`replication_factor`](#replication_factor),
[`consistency_mode`](#consistency_mode),
[`rpc_bind_addr`](#rpc_bind_addr),
[`rpc_bind_outgoing`](#rpc_bind_outgoing),
[`rpc_public_addr`](#rpc_public_addr),
[`rpc_public_addr_subnet`](#rpc_public_addr_subnet)
[`rpc_secret`/`rpc_secret_file`](#rpc_secret).
The `[consul_discovery]` section:
[`api`](#consul_api),
[`ca_cert`](#consul_ca_cert),
[`client_cert`](#consul_client_cert_and_key),
[`client_key`](#consul_client_cert_and_key),
[`consul_http_addr`](#consul_http_addr),
[`meta`](#consul_tags_and_meta),
[`service_name`](#consul_service_name),
[`tags`](#consul_tags_and_meta),
[`tls_skip_verify`](#consul_tls_skip_verify),
[`token`](#consul_token).
The `[kubernetes_discovery]` section:
[`namespace`](#kube_namespace),
[`service_name`](#kube_service_name),
[`skip_crd`](#kube_skip_crd).
The `[s3_api]` section:
[`api_bind_addr`](#s3_api_bind_addr),
[`root_domain`](#s3_root_domain),
[`s3_region`](#s3_region).
The `[s3_web]` section:
[`bind_addr`](#web_bind_addr),
[`root_domain`](#web_root_domain).
The `[admin]` section:
[`api_bind_addr`](#admin_api_bind_addr),
[`metrics_token`/`metrics_token_file`](#admin_metrics_token),
[`admin_token`/`admin_token_file`](#admin_token),
[`trace_sink`](#admin_trace_sink),
### Environment variables {#env_variables}
The following configuration parameter must be specified as an environment
variable, it does not exist in the configuration file:
- `GARAGE_LOG_TO_SYSLOG` (since v0.9.4): set this to `1` or `true` to make the
Garage daemon send its logs to `syslog` (using the libc `syslog` function)
instead of printing to stderr.
The following environment variables can be used to override the corresponding
values in the configuration file:
- [`GARAGE_ALLOW_WORLD_READABLE_SECRETS`](#allow_world_readable_secrets)
- [`GARAGE_RPC_SECRET` and `GARAGE_RPC_SECRET_FILE`](#rpc_secret)
- [`GARAGE_ADMIN_TOKEN` and `GARAGE_ADMIN_TOKEN_FILE`](#admin_token)
- [`GARAGE_METRICS_TOKEN` and `GARAGE_METRICS_TOKEN`](#admin_metrics_token)
### Top-level configuration options
#### `replication_factor` {#replication_factor}
The replication factor can be any positive integer smaller or equal the node count in your cluster.
The chosen replication factor has a big impact on the cluster's failure tolerancy and performance characteristics.
- `1`: data stored on Garage is stored on a single node. There is no
redundancy, and data will be unavailable as soon as one node fails or its
network is disconnected. Do not use this for anything else than test
deployments.
- `2`: data stored on Garage will be stored on two different nodes, if possible
in different zones. Garage tolerates one node failure, or several nodes
failing but all in a single zone (in a deployment with at least two zones),
before losing data. Data remains available in read-only mode when one node is
down, but write operations will fail.
- `3`: data stored on Garage will be stored on three different nodes, if
possible each in a different zones. Garage tolerates two node failure, or
several node failures but in no more than two zones (in a deployment with at
least three zones), before losing data. As long as only a single node fails,
or node failures are only in a single zone, reading and writing data to
Garage can continue normally.
- `5`, `7`, ...: When setting the replication factor above 3, it is most useful to
choose an uneven value, since for every two copies added, one more node can fail
before losing the ability to write and read to the cluster.
Note that in modes `2` and `3`,
if at least the same number of zones are available, an arbitrary number of failures in
any given zone is tolerated as copies of data will be spread over several zones.
**Make sure `replication_factor` is the same in the configuration files of all nodes.
Never run a Garage cluster where that is not the case.**
It is technically possible to change the replication factor although it's a
dangerous operation that is not officially supported. This requires you to
delete the existing cluster layout and create a new layout from scratch,
meaning that a full rebalancing of your cluster's data will be needed. To do
it, shut down your cluster entirely, delete the `custer_layout` files in the
meta directories of all your nodes, update all your configuration files with
the new `replication_factor` parameter, restart your cluster, and then create a
new layout with all the nodes you want to keep. Rebalancing data will take
some time, and data might temporarily appear unavailable to your users.
It is recommended to shut down public access to the cluster while rebalancing
is in progress. In theory, no data should be lost as rebalancing is a
routine operation for Garage, although we cannot guarantee you that everything
will go right in such an extreme scenario.
#### `consistency_mode` {#consistency_mode}
The consistency mode setting determines the read and write behaviour of your cluster.
- `consistent`: The default setting. This is what the paragraph above describes.
The read and write quorum will be determined so that read-after-write consistency
is guaranteed.
- `degraded`: Lowers the read
quorum to `1`, to allow you to read data from your cluster when several
nodes (or nodes in several zones) are unavailable. In this mode, Garage
does not provide read-after-write consistency anymore.
The write quorum stays the same as in the `consistent` mode, ensuring that
data successfully written to Garage is stored on multiple nodes (depending
the replication factor).
- `dangerous`: This mode lowers both the read
and write quorums to `1`, to allow you to both read and write to your
cluster when several nodes (or nodes in several zones) are unavailable. It
is the least consistent mode of operation proposed by Garage, and also one
that should probably never be used.
Changing the `consistency_mode` between modes while leaving the `replication_factor` untouched
(e.g. setting your node's `consistency_mode` to `degraded` when it was previously unset, or from
`dangerous` to `consistent`), can be done easily by just changing the `consistency_mode`
parameter in your config files and restarting all your Garage nodes.
The consistency mode can be used together with various replication factors, to achieve
a wide range of read and write characteristics. Some examples:
- Replication factor `2`, consistency mode `degraded`: While this mode
technically exists, its properties are the same as with consistency mode `consistent`,
since the read quorum with replication factor `2`, consistency mode `consistent` is already 1.
- Replication factor `2`, consistency mode `dangerous`: written objects are written to
the second replica asynchronously. This means that Garage will return `200
OK` to a PutObject request before the second copy is fully written (or even
before it even starts being written). This means that data can more easily
be lost if the node crashes before a second copy can be completed. This
also means that written objects might not be visible immediately in read
operations. In other words, this configuration severely breaks the consistency and
durability guarantees of standard Garage cluster operation. Benefits of
this configuration: you can still write to your cluster when one node is
unavailable.
The quorums associated with each replication mode are described below:
| `consistency_mode` | `replication_factor` | Write quorum | Read quorum | Read-after-write consistency? |
| ------------------ | -------------------- | ------------ | ----------- | ----------------------------- |
| `consistent` | 1 | 1 | 1 | yes |
| `consistent` | 2 | 2 | 1 | yes |
| `dangerous` | 2 | 1 | 1 | NO |
| `consistent` | 3 | 2 | 2 | yes |
| `degraded` | 3 | 2 | 1 | NO |
| `dangerous` | 3 | 1 | 1 | NO |
#### `metadata_dir` {#metadata_dir}
### `metadata_dir`
The directory in which Garage will store its metadata. This contains the node identifier,
the network configuration and the peer list, the list of buckets and keys as well
@ -275,172 +82,59 @@ as the index of all objects, object version and object blocks.
Store this folder on a fast SSD drive if possible to maximize Garage's performance.
#### `data_dir` {#data_dir}
### `data_dir`
The directory in which Garage will store the data blocks of objects.
This folder can be placed on an HDD. The space available for `data_dir`
should be counted to determine a node's capacity
when [adding it to the cluster layout](@/documentation/cookbook/real-world.md).
Since `v0.9.0`, Garage supports multiple data directories with the following syntax:
### `db_engine` (since `v0.8.0`)
```toml
data_dir = [
{ path = "/path/to/old_data", read_only = true },
{ path = "/path/to/new_hdd1", capacity = "2T" },
{ path = "/path/to/new_hdd2", capacity = "4T" },
]
```
See [the dedicated documentation page](@/documentation/operations/multi-hdd.md)
on how to operate Garage in such a setup.
#### `db_engine` (since `v0.8.0`) {#db_engine}
Since `v0.8.0`, Garage can use alternative storage backends as follows:
By default, Garage uses the Sled embedded database library
to store its metadata on-disk. Since `v0.8.0`, Garage can use alternative storage backends as follows:
| DB engine | `db_engine` value | Database path |
| --------- | ----------------- | ------------- |
| [LMDB](https://www.symas.com/lmdb) (since `v0.8.0`, default since `v0.9.0`) | `"lmdb"` | `<metadata_dir>/db.lmdb/` |
| [Sqlite](https://sqlite.org) (since `v0.8.0`) | `"sqlite"` | `<metadata_dir>/db.sqlite` |
| [Sled](https://sled.rs) (old default, removed since `v1.0`) | `"sled"` | `<metadata_dir>/db/` |
Sled was supported until Garage v0.9.x, and was removed in Garage v1.0.
You can still use an older binary of Garage (e.g. v0.9.4) to migrate
old Sled metadata databases to another engine.
| [Sled](https://sled.rs) | `"sled"` | `<metadata_dir>/db/` |
| [LMDB](https://www.lmdb.tech) | `"lmdb"` | `<metadata_dir>/db.lmdb/` |
| [Sqlite](https://sqlite.org) | `"sqlite"` | `<metadata_dir>/db.sqlite` |
Performance characteristics of the different DB engines are as follows:
- LMDB: the recommended database engine for high-performance distributed clusters.
LMDB works very well, but is known to have the following limitations:
- Sled: the default database engine, which tends to produce
large data files and also has performance issues, especially when the metadata folder
is on a traditional HDD and not on SSD.
- LMDB: the recommended alternative on 64-bit systems,
much more space-efficiant and slightly faster. Note that the data format of LMDB is not portable
between architectures, so for instance the Garage database of an x86-64
node cannot be moved to an ARM64 node. Also note that, while LMDB can technically be used on 32-bit systems,
this will limit your node to very small database sizes due to how LMDB works; it is therefore not recommended.
- Sqlite: Garage supports Sqlite as a storage backend for metadata,
however it may have issues and is also very slow in its current implementation,
so it is not recommended to be used for now.
- The data format of LMDB is not portable between architectures, so for
instance the Garage database of an x86-64 node cannot be moved to an ARM64
node.
- While LMDB can technically be used on 32-bit systems, this will limit your
node to very small database sizes due to how LMDB works; it is therefore
not recommended.
- Several users have reported corrupted LMDB database files after an unclean
shutdown (e.g. a power outage). This situation can generally be recovered
from if your cluster is geo-replicated (by rebuilding your metadata db from
other nodes), or if you have saved regular snapshots at the filesystem
level.
- Keys in LMDB are limited to 511 bytes. This limit translates to limits on
object keys in S3 and sort keys in K2V that are limted to 479 bytes.
- Sqlite: Garage supports Sqlite as an alternative storage backend for
metadata, which does not have the issues listed above for LMDB.
On versions 0.8.x and earlier, Sqlite should be avoided due to abysmal
performance, which was fixed with the addition of `metadata_fsync`.
Sqlite is still probably slower than LMDB due to the way we use it,
so it is not the best choice for high-performance storage clusters,
but it should work fine in many cases.
It is possible to convert Garage's metadata directory from one format to another
using the `garage convert-db` command, which should be used as follows:
It is possible to convert Garage's metadata directory from one format to another with a small utility named `convert_db`,
which can be downloaded at the following locations:
[for amd64](https://garagehq.deuxfleurs.fr/_releases/convert_db/amd64/convert_db),
[for i386](https://garagehq.deuxfleurs.fr/_releases/convert_db/i386/convert_db),
[for arm64](https://garagehq.deuxfleurs.fr/_releases/convert_db/arm64/convert_db),
[for arm](https://garagehq.deuxfleurs.fr/_releases/convert_db/arm/convert_db).
The `convert_db` utility is used as folows:
```
garage convert-db -a <input db engine> -i <input db path> \
convert-db -a <input db engine> -i <input db path> \
-b <output db engine> -o <output db path>
```
Make sure to specify the full database path as presented in the table above
(third colummn), and not just the path to the metadata directory.
Make sure to specify the full database path as presented in the table above,
and not just the path to the metadata directory.
#### `metadata_fsync` {#metadata_fsync}
Whether to enable synchronous mode for the database engine or not.
This is disabled (`false`) by default.
This reduces the risk of metadata corruption in case of power failures,
at the cost of a significant drop in write performance,
as Garage will have to pause to sync data to disk much more often
(several times for API calls such as PutObject).
Using this option reduces the risk of simultaneous metadata corruption on several
cluster nodes, which could lead to data loss.
If multi-site replication is used, this option is most likely not necessary, as
it is extremely unlikely that two nodes in different locations will have a
power failure at the exact same time.
(Metadata corruption on a single node is not an issue, the corrupted data file
can always be deleted and reconstructed from the other nodes in the cluster.)
Here is how this option impacts the different database engines:
| Database | `metadata_fsync = false` (default) | `metadata_fsync = true` |
|----------|------------------------------------|-------------------------------|
| Sqlite | `PRAGMA synchronous = OFF` | `PRAGMA synchronous = NORMAL` |
| LMDB | `MDB_NOMETASYNC` + `MDB_NOSYNC` | `MDB_NOMETASYNC` |
Note that the Sqlite database is always ran in `WAL` mode (`PRAGMA journal_mode = WAL`).
#### `data_fsync` {#data_fsync}
Whether to `fsync` data blocks and their containing directory after they are
saved to disk.
This is disabled (`false`) by default.
This might reduce the risk that a data block is lost in rare
situations such as simultaneous node losing power,
at the cost of a moderate drop in write performance.
Similarly to `metatada_fsync`, this is likely not necessary
if geographical replication is used.
#### `metadata_auto_snapshot_interval` (since Garage v0.9.4) {#metadata_auto_snapshot_interval}
If this value is set, Garage will automatically take a snapshot of the metadata
DB file at a regular interval and save it in the metadata directory.
This parameter can take any duration string that can be parsed by
the [`parse_duration`](https://docs.rs/parse_duration/latest/parse_duration/#syntax) crate.
Snapshots can allow to recover from situations where the metadata DB file is
corrupted, for instance after an unclean shutdown. See [this
page](@/documentation/operations/recovering.md#corrupted_meta) for details.
Garage keeps only the two most recent snapshots of the metadata DB and deletes
older ones automatically.
Note that taking a metadata snapshot is a relatively intensive operation as the
entire data file is copied. A snapshot being taken might have performance
impacts on the Garage node while it is running. If the cluster is under heavy
write load when a snapshot operation is running, this might also cause the
database file to grow in size significantly as pages cannot be recycled easily.
For this reason, it might be better to use filesystem-level snapshots instead
if possible.
#### `disable_scrub` {#disable_scrub}
By default, Garage runs a scrub of the data directory approximately once per
month, with a random delay to avoid all nodes running at the same time. When
it scrubs the data directory, Garage will read all of the data files stored on
disk to check their integrity, and will rebuild any data files that it finds
corrupted, using the remaining valid copies stored on other nodes.
See [this page](@/documentation/operations/durability-repairs.md#scrub) for details.
Set the `disable_scrub` configuration value to `true` if you don't need Garage
to scrub the data directory, for instance if you are already scrubbing at the
filesystem level. Note that in this case, if you find a corrupted data file,
you should delete it from the data directory and then call `garage repair
blocks` on the node to ensure that it re-obtains a copy from another node on
the network.
#### `use_local_tz` {#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}
### `block_size`
Garage splits stored objects in consecutive chunks of size `block_size`
(except the last one which might be smaller). The default size is 1MiB and
should work in most cases. We recommend increasing it to e.g. 10MiB if
(except the last one which might be smaller). The default size is 1MB and
should work in most cases. We recommend increasing it to e.g. 10MB if
you are using Garage to store large files and have fast network connections
between all nodes (e.g. 1gbps).
@ -451,46 +145,105 @@ 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}
### `sled_cache_capacity`
A limit on the total size of data blocks kept in RAM by S3 API nodes awaiting
to be sent to storage nodes asynchronously.
This parameter can be used to tune the capacity of the cache used by
[sled](https://sled.rs), the database Garage uses internally to store metadata.
Tune this to fit the RAM you wish to make available to your Garage instance.
This value has a conservative default (128MB) so that Garage doesn't use too much
RAM by default, but feel free to increase this for higher performance.
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.
### `sled_flush_every_ms`
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.
This parameters can be used to tune the flushing interval of sled.
Increase this if sled is thrashing your SSD, at the risk of losing more data in case
of a power outage (though this should not matter much as data is replicated on other
nodes). The default value, 2000ms, should be appropriate for most use cases.
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.
### `replication_mode`
The default value is 256MiB.
Garage supports the following replication modes:
#### `lmdb_map_size` {#lmdb_map_size}
- `none` or `1`: data stored on Garage is stored on a single node. There is no
redundancy, and data will be unavailable as soon as one node fails or its
network is disconnected. Do not use this for anything else than test
deployments.
This parameters can be used to set the map size used by LMDB,
which is the size of the virtual memory region used for mapping the database file.
The value of this parameter is the maximum size the metadata database can take.
This value is not bound by the physical RAM size of the machine running Garage.
If not specified, it defaults to 1GiB on 32-bit machines and 1TiB on 64-bit machines.
- `2`: data stored on Garage will be stored on two different nodes, if possible
in different zones. Garage tolerates one node failure, or several nodes
failing but all in a single zone (in a deployment with at least two zones),
before losing data. Data remains available in read-only mode when one node is
down, but write operations will fail.
#### `compression_level` {#compression_level}
- `2-dangerous`: a variant of mode `2`, where written objects are written to
the second replica asynchronously. This means that Garage will return `200
OK` to a PutObject request before the second copy is fully written (or even
before it even starts being written). This means that data can more easily
be lost if the node crashes before a second copy can be completed. This
also means that written objects might not be visible immediately in read
operations. In other words, this mode severely breaks the consistency and
durability guarantees of standard Garage cluster operation. Benefits of
this mode: you can still write to your cluster when one node is
unavailable.
- `3`: data stored on Garage will be stored on three different nodes, if
possible each in a different zones. Garage tolerates two node failure, or
several node failures but in no more than two zones (in a deployment with at
least three zones), before losing data. As long as only a single node fails,
or node failures are only in a single zone, reading and writing data to
Garage can continue normally.
- `3-degraded`: a variant of replication mode `3`, that lowers the read
quorum to `1`, to allow you to read data from your cluster when several
nodes (or nodes in several zones) are unavailable. In this mode, Garage
does not provide read-after-write consistency anymore. The write quorum is
still 2, ensuring that data successfully written to Garage is stored on at
least two nodes.
- `3-dangerous`: a variant of replication mode `3` that lowers both the read
and write quorums to `1`, to allow you to both read and write to your
cluster when several nodes (or nodes in several zones) are unavailable. It
is the least consistent mode of operation proposed by Garage, and also one
that should probably never be used.
Note that in modes `2` and `3`,
if at least the same number of zones are available, an arbitrary number of failures in
any given zone is tolerated as copies of data will be spread over several zones.
**Make sure `replication_mode` is the same in the configuration files of all nodes.
Never run a Garage cluster where that is not the case.**
The quorums associated with each replication mode are described below:
| `replication_mode` | Number of replicas | Write quorum | Read quorum | Read-after-write consistency? |
| ------------------ | ------------------ | ------------ | ----------- | ----------------------------- |
| `none` or `1` | 1 | 1 | 1 | yes |
| `2` | 2 | 2 | 1 | yes |
| `2-dangerous` | 2 | 1 | 1 | NO |
| `3` | 3 | 2 | 2 | yes |
| `3-degraded` | 3 | 2 | 1 | NO |
| `3-dangerous` | 3 | 1 | 1 | NO |
Changing the `replication_mode` between modes with the same number of replicas
(e.g. from `3` to `3-degraded`, or from `2-dangerous` to `2`), can be done easily by
just changing the `replication_mode` parameter in your config files and restarting all your
Garage nodes.
It is also technically possible to change the replication mode to a mode with a
different numbers of replicas, although it's a dangerous operation that is not
officially supported. This requires you to delete the existing cluster layout
and create a new layout from scratch, meaning that a full rebalancing of your
cluster's data will be needed. To do it, shut down your cluster entirely,
delete the `custer_layout` files in the meta directories of all your nodes,
update all your configuration files with the new `replication_mode` parameter,
restart your cluster, and then create a new layout with all the nodes you want
to keep. Rebalancing data will take some time, and data might temporarily
appear unavailable to your users. It is recommended to shut down public access
to the cluster while rebalancing is in progress. In theory, no data should be
lost as rebalancing is a routine operation for Garage, although we cannot
guarantee you that everything will go right in such an extreme scenario.
### `compression_level`
Zstd compression level to use for storing blocks.
@ -514,7 +267,7 @@ Compression is done synchronously, setting a value too high will add latency to
This value can be different between nodes, compression is done by the node which receive the
API call.
#### `rpc_secret`, `rpc_secret_file` or `GARAGE_RPC_SECRET`, `GARAGE_RPC_SECRET_FILE` (env) {#rpc_secret}
### `rpc_secret`, `rpc_secret_file` or `GARAGE_RPC_SECRET` (env)
Garage uses a secret key, called an RPC secret, that is shared between all
nodes of the cluster in order to identify these nodes and allow them to
@ -526,10 +279,7 @@ Since Garage `v0.8.2`, the RPC secret can also be stored in a file whose path is
given in the configuration variable `rpc_secret_file`, or specified as an
environment variable `GARAGE_RPC_SECRET`.
Since Garage `v0.8.5` and `v0.9.1`, you can also specify the path of a file
storing the secret as the `GARAGE_RPC_SECRET_FILE` environment variable.
#### `rpc_bind_addr` {#rpc_bind_addr}
### `rpc_bind_addr`
The address and port on which to bind for inter-cluster communcations
(reffered to as RPC for remote procedure calls).
@ -538,33 +288,14 @@ the node, even in the case of a NAT: the NAT should be configured to forward the
port number to the same internal port nubmer. This means that if you have several nodes running
behind a NAT, they should each use a different RPC port number.
#### `rpc_bind_outgoing`(since v0.9.2) {#rpc_bind_outgoing}
If enabled, pre-bind all sockets for outgoing connections to the same IP address
used for listening (the IP address specified in `rpc_bind_addr`) before
trying to connect to remote nodes.
This can be necessary if a node has multiple IP addresses,
but only one is allowed or able to reach the other nodes,
for instance due to firewall rules or specific routing configuration.
Disabled by default.
#### `rpc_public_addr` {#rpc_public_addr}
### `rpc_public_addr`
The address and port that other nodes need to use to contact this node for
RPC calls. **This parameter is optional but recommended.** In case you have
a NAT that binds the RPC port to a port that is different on your public IP,
this field might help making it work.
#### `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}
### `bootstrap_peers`
A list of peer identifiers on which to contact other Garage peers of this cluster.
These peer identifiers have the following syntax:
@ -580,54 +311,43 @@ 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}
Garage checks the permissions of your secret files to make sure they're not
world-readable. In some cases, the check might fail and consider your files as
world-readable even if they're not, for instance when using Posix ACLs.
Setting `allow_world_readable_secrets` to `true` bypass this
permission verification.
Alternatively, you can set the `GARAGE_ALLOW_WORLD_READABLE_SECRETS`
environment variable to `true` to bypass the permissions check.
### The `[consul_discovery]` section
## The `[consul_discovery]` section
Garage supports discovering other nodes of the cluster using Consul. For this
to work correctly, nodes need to know their IP address by which they can be
reached by other nodes of the cluster, which should be set in `rpc_public_addr`.
#### `consul_http_addr` {#consul_http_addr}
### `consul_http_addr` and `service_name`
The `consul_http_addr` parameter should be set to the full HTTP(S) address of the Consul server.
#### `api` {#consul_api}
### `api`
Two APIs for service registration are supported: `catalog` and `agent`. `catalog`, the default, will register a service using
the `/v1/catalog` endpoints, enabling mTLS if `client_cert` and `client_key` are provided. The `agent` API uses the
`v1/agent` endpoints instead, where an optional `token` may be provided.
#### `service_name` {#consul_service_name}
### `service_name`
`service_name` should be set to the service name under which Garage's
RPC ports are announced.
#### `client_cert`, `client_key` {#consul_client_cert_and_key}
### `client_cert`, `client_key`
TLS client certificate and client key to use when communicating with Consul over TLS. Both are mandatory when doing so.
Only available when `api = "catalog"`.
#### `ca_cert` {#consul_ca_cert}
### `ca_cert`
TLS CA certificate to use when communicating with Consul over TLS.
#### `tls_skip_verify` {#consul_tls_skip_verify}
### `tls_skip_verify`
Skip server hostname verification in TLS handshake.
`ca_cert` is ignored when this is set.
#### `token` {#consul_token}
### `token`
Uses the provided token for communication with Consul. Only available when `api = "agent"`.
The policy assigned to this token should at least have these rules:
@ -647,49 +367,47 @@ node_prefix "" {
}
```
#### `tags` and `meta` {#consul_tags_and_meta}
### `tags` and `meta`
Additional list of tags and map of service meta to add during service registration.
### The `[kubernetes_discovery]` section
## The `[kubernetes_discovery]` section
Garage supports discovering other nodes of the cluster using kubernetes custom
resources. For this to work, a `[kubernetes_discovery]` section must be present
with at least the `namespace` and `service_name` parameters.
#### `namespace` {#kube_namespace}
### `namespace`
`namespace` sets the namespace in which the custom resources are
configured.
#### `service_name` {#kube_service_name}
### `service_name`
`service_name` is added as a label to the advertised resources to
filter them, to allow for multiple deployments in a single namespace.
#### `skip_crd` {#kube_skip_crd}
### `skip_crd`
`skip_crd` can be set to true to disable the automatic creation and
patching of the `garagenodes.deuxfleurs.fr` CRD. You will need to create the CRD
manually.
### The `[s3_api]` section
## The `[s3_api]` section
#### `api_bind_addr` {#s3_api_bind_addr}
### `api_bind_addr`
The IP and port on which to bind for accepting S3 API calls.
This endpoint does not suport TLS: a reverse proxy should be used to provide it.
Alternatively, since `v0.8.5`, a path can be used to create a unix socket with 0222 mode.
#### `s3_region` {#s3_region}
### `s3_region`
Garage will accept S3 API calls that are targetted to the S3 region defined here.
API calls targetted to other regions will fail with a AuthorizationHeaderMalformed error
message that redirects the client to the correct region.
#### `root_domain` {#s3_root_domain}
### `root_domain` {#root_domain}
The optional suffix to access bucket using vhost-style in addition to path-style request.
Note path-style requests are always enabled, whether or not vhost-style is configured.
@ -701,20 +419,18 @@ using the hostname `my-bucket.s3.garage.eu`.
### The `[s3_web]` section
## The `[s3_web]` section
Garage allows to publish content of buckets as websites. This section configures the
behaviour of this module.
#### `bind_addr` {#web_bind_addr}
### `bind_addr`
The IP and port on which to bind for accepting HTTP requests to buckets configured
for website access.
This endpoint does not suport TLS: a reverse proxy should be used to provide it.
Alternatively, since `v0.8.5`, a path can be used to create a unix socket with 0222 mode.
#### `root_domain` {#web_root_domain}
### `root_domain`
The optional suffix appended to bucket names for the corresponding HTTP Host.
@ -723,44 +439,39 @@ will be accessible either with hostname `deuxfleurs.fr.web.garage.eu`
or with hostname `deuxfleurs.fr`.
### The `[admin]` section
## The `[admin]` section
Garage has a few administration capabilities, in particular to allow remote monitoring. These features are detailed below.
#### `api_bind_addr` {#admin_api_bind_addr}
### `api_bind_addr`
If specified, Garage will bind an HTTP server to this port and address, on
which it will listen to requests for administration features.
See [administration API reference](@/documentation/reference-manual/admin-api.md) to learn more about these features.
Alternatively, since `v0.8.5`, a path can be used to create a unix socket. Note that for security reasons,
the socket will have 0220 mode. Make sure to set user and group permissions accordingly.
#### `metrics_token`, `metrics_token_file` or `GARAGE_METRICS_TOKEN`, `GARAGE_METRICS_TOKEN_FILE` (env) {#admin_metrics_token}
### `metrics_token`, `metrics_token_file` or `GARAGE_METRICS_TOKEN` (env)
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`.
You can use any random string for this value. We recommend generating a random token with `openssl rand -hex 32`.
`metrics_token` was introduced in Garage `v0.7.2`.
`metrics_token_file` and the `GARAGE_METRICS_TOKEN` environment variable are supported since Garage `v0.8.2`.
`GARAGE_METRICS_TOKEN_FILE` is supported since `v0.8.5` / `v0.9.1`.
#### `admin_token`, `admin_token_file` or `GARAGE_ADMIN_TOKEN`, `GARAGE_ADMIN_TOKEN_FILE` (env) {#admin_token}
### `admin_token`, `admin_token_file` or `GARAGE_ADMIN_TOKEN` (env)
The token for accessing all of the other administration endpoints. If this
token is not set, access to these endpoints is disabled entirely.
You can use any random string for this value. We recommend generating a random token with `openssl rand -base64 32`.
You can use any random string for this value. We recommend generating a random token with `openssl rand -hex 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}
### `trace_sink`
Optionally, the address of an OpenTelemetry collector. If specified,
Garage will send traces in the OpenTelemetry format to this endpoint. These

View file

@ -37,21 +37,6 @@ A Garage cluster can very easily evolve over time, as storage nodes are added or
Garage will automatically rebalance data between nodes as needed to ensure the desired number of copies.
Read about cluster layout management [here](@/documentation/operations/layout.md).
### Several replication modes
Garage supports a variety of replication modes, with configurable replica count,
and with various levels of consistency, in order to adapt to a variety of usage scenarios.
Read our reference page on [supported replication modes](@/documentation/reference-manual/configuration.md#replication_factor)
to select the replication mode best suited to your use case (hint: in most cases, `replication_factor = 3` is what you want).
### Compression and deduplication
All data stored in Garage is deduplicated, and optionnally compressed using
Zstd. Objects uploaded to Garage are chunked in blocks of constant sizes (see
[`block_size`](@/documentation/reference-manual/configuration.md#block_size)),
and the hashes of individual blocks are used to dispatch them to storage nodes
and to deduplicate them.
### No RAFT slowing you down
It might seem strange to tout the absence of something as a desirable feature,
@ -63,6 +48,13 @@ As a consequence, requests can be handled much faster, even in cases where laten
between cluster nodes is important (see our [benchmarks](@/documentation/design/benchmarks/index.md) for data on this).
This is particularly usefull when nodes are far from one another and talk to one other through standard Internet connections.
### Several replication modes
Garage supports a variety of replication modes, with 1 copy, 2 copies or 3 copies of your data,
and with various levels of consistency, in order to adapt to a variety of usage scenarios.
Read our reference page on [supported replication modes](@/documentation/reference-manual/configuration.md#replication-mode)
to select the replication mode best suited to your use case (hint: in most cases, `replication_mode = "3"` is what you want).
### Web server for static websites
A storage bucket can easily be configured to be served directly by Garage as a static web site.

View file

@ -27,112 +27,6 @@ Exposes the Garage replication factor configured on the node
garage_replication_factor 3
```
#### `garage_local_disk_avail` and `garage_local_disk_total` (gauge)
Reports the available and total disk space on each node, for data and metadata separately.
```
garage_local_disk_avail{volume="data"} 540341960704
garage_local_disk_avail{volume="metadata"} 540341960704
garage_local_disk_total{volume="data"} 763063566336
garage_local_disk_total{volume="metadata"} 763063566336
```
### Cluster health status metrics
#### `cluster_healthy` (gauge)
Whether all storage nodes are connected (0 or 1)
```
cluster_healthy 0
```
#### `cluster_available` (gauge)
Whether all requests can be served, even if some storage nodes are disconnected
```
cluster_available 1
```
#### `cluster_connected_nodes` (gauge)
Number of nodes currently connected
```
cluster_connected_nodes 3
```
#### `cluster_known_nodes` (gauge)
Number of nodes already seen once in the cluster
```
cluster_known_nodes 3
```
#### `cluster_layout_node_connected` (gauge)
Connection status for individual nodes of the cluster layout
```
cluster_layout_node_connected{id="62b218d848e86a64",role_capacity="1000000000",role_gateway="0",role_zone="dc1"} 1
cluster_layout_node_connected{id="a11c7cf18af29737",role_capacity="1000000000",role_gateway="0",role_zone="dc1"} 0
cluster_layout_node_connected{id="a235ac7695e0c54d",role_capacity="1000000000",role_gateway="0",role_zone="dc1"} 1
cluster_layout_node_connected{id="b10c110e4e854e5a",role_capacity="1000000000",role_gateway="0",role_zone="dc1"} 1
```
#### `cluster_layout_node_disconnected_time` (gauge)
Time (in seconds) since last connection to individual nodes of the cluster layout
```
cluster_layout_node_disconnected_time{id="62b218d848e86a64",role_capacity="1000000000",role_gateway="0",role_zone="dc1"} 0
cluster_layout_node_disconnected_time{id="a235ac7695e0c54d",role_capacity="1000000000",role_gateway="0",role_zone="dc1"} 0
cluster_layout_node_disconnected_time{id="b10c110e4e854e5a",role_capacity="1000000000",role_gateway="0",role_zone="dc1"} 0
```
#### `cluster_storage_nodes` (gauge)
Number of storage nodes declared in the current layout
```
cluster_storage_nodes 4
```
#### `cluster_storage_nodes_ok` (gauge)
Number of storage nodes currently connected
```
cluster_storage_nodes_ok 3
```
#### `cluster_partitions` (gauge)
Number of partitions in the layout (this is always 256)
```
cluster_partitions 256
```
#### `cluster_partitions_all_ok` (gauge)
Number of partitions for which all storage nodes are connected
```
cluster_partitions_all_ok 64
```
#### `cluster_partitions_quorum` (gauge)
Number of partitions for which we have a quorum of connected nodes and all requests can be served
```
cluster_partitions_quorum 256
```
### Metrics of the API endpoints
#### `api_admin_request_counter` (counter)
@ -225,17 +119,6 @@ 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.

View file

@ -33,7 +33,6 @@ Feel free to open a PR to suggest fixes this table. Minio is missing because the
| [URL path-style](https://docs.aws.amazon.com/AmazonS3/latest/userguide/VirtualHosting.html#path-style-access) (eg. `host.tld/bucket/key`) | ✅ Implemented | ✅ | ✅ | ❓| ✅ |
| [URL vhost-style](https://docs.aws.amazon.com/AmazonS3/latest/userguide/VirtualHosting.html#virtual-hosted-style-access) URL (eg. `bucket.host.tld/key`) | ✅ Implemented | ❌| ✅| ✅ | ✅ |
| [Presigned URLs](https://docs.aws.amazon.com/AmazonS3/latest/userguide/ShareObjectPreSignedURL.html) | ✅ Implemented | ❌| ✅ | ✅ | ✅(❓) |
| [SSE-C encryption](https://docs.aws.amazon.com/AmazonS3/latest/userguide/ServerSideEncryptionCustomerKeys.html) | ✅ Implemented | ❓ | ✅ | ❌ | ✅ |
*Note:* OpenIO does not says if it supports presigned URLs. Because it is part
of signature v4 and they claim they support it without additional precisions,
@ -77,13 +76,16 @@ but these endpoints are documented in [Red Hat Ceph Storage - Chapter 2. Ceph Ob
| Endpoint | Garage | [Openstack Swift](https://docs.openstack.org/swift/latest/s3_compat.html) | [Ceph Object Gateway](https://docs.ceph.com/en/latest/radosgw/s3/) | [Riak CS](https://docs.riak.com/riak/cs/2.1.1/references/apis/storage/s3/index.html) | [OpenIO](https://docs.openio.io/latest/source/arch-design/s3_compliancy.html) |
|------------------------------|----------------------------------|-----------------|---------------|---------|-----|
| [AbortMultipartUpload](https://docs.aws.amazon.com/AmazonS3/latest/API/API_AbortMultipartUpload.html) | ✅ Implemented | ✅ | ✅ | ✅ | ✅ |
| [CompleteMultipartUpload](https://docs.aws.amazon.com/AmazonS3/latest/API/API_CompleteMultipartUpload.html) | ✅ Implemented | ✅ | ✅ | ✅ | ✅ |
| [CompleteMultipartUpload](https://docs.aws.amazon.com/AmazonS3/latest/API/API_CompleteMultipartUpload.html) | ✅ Implemented (see details below) | ✅ | ✅ | ✅ | ✅ |
| [CreateMultipartUpload](https://docs.aws.amazon.com/AmazonS3/latest/API/API_CreateMultipartUpload.html) | ✅ Implemented | ✅| ✅ | ✅ | ✅ |
| [ListMultipartUpload](https://docs.aws.amazon.com/AmazonS3/latest/API/API_ListMultipartUpload.html) | ✅ Implemented | ✅ | ✅ | ✅ | ✅ |
| [ListParts](https://docs.aws.amazon.com/AmazonS3/latest/API/API_ListParts.html) | ✅ Implemented | ✅ | ✅ | ✅ | ✅ |
| [UploadPart](https://docs.aws.amazon.com/AmazonS3/latest/API/API_UploadPart.html) | ✅ Implemented | ✅ | ✅| ✅ | ✅ |
| [UploadPart](https://docs.aws.amazon.com/AmazonS3/latest/API/API_UploadPart.html) | ✅ Implemented (see details below) | ✅ | ✅| ✅ | ✅ |
| [UploadPartCopy](https://docs.aws.amazon.com/AmazonS3/latest/API/API_UploadPartCopy.html) | ✅ Implemented | ✅ | ✅ | ✅ | ✅ |
Our implementation of Multipart Upload is currently a bit more restrictive than Amazon's one in some edge cases.
For more information, please refer to our [issue tracker](https://git.deuxfleurs.fr/Deuxfleurs/garage/issues/204).
### Website endpoints
| Endpoint | Garage | [Openstack Swift](https://docs.openstack.org/swift/latest/s3_compat.html) | [Ceph Object Gateway](https://docs.ceph.com/en/latest/radosgw/s3/) | [Riak CS](https://docs.riak.com/riak/cs/2.1.1/references/apis/storage/s3/index.html) | [OpenIO](https://docs.openio.io/latest/source/arch-design/s3_compliancy.html) |
@ -125,22 +127,15 @@ If you need this feature, please [share your use case in our dedicated issue](ht
| Endpoint | Garage | [Openstack Swift](https://docs.openstack.org/swift/latest/s3_compat.html) | [Ceph Object Gateway](https://docs.ceph.com/en/latest/radosgw/s3/) | [Riak CS](https://docs.riak.com/riak/cs/2.1.1/references/apis/storage/s3/index.html) | [OpenIO](https://docs.openio.io/latest/source/arch-design/s3_compliancy.html) |
|------------------------------|----------------------------------|-----------------|---------------|---------|-----|
| [DeleteBucketLifecycle](https://docs.aws.amazon.com/AmazonS3/latest/API/API_DeleteBucketLifecycle.html) | ✅ Implemented | ❌| ✅| ❌| ✅|
| [GetBucketLifecycleConfiguration](https://docs.aws.amazon.com/AmazonS3/latest/API/API_GetBucketLifecycleConfiguration.html) | ✅ Implemented | ❌| ✅ | ❌| ✅|
| [PutBucketLifecycleConfiguration](https://docs.aws.amazon.com/AmazonS3/latest/API/API_PutBucketLifecycleConfiguration.html) | ⚠ Partially implemented (see below) | ❌| ✅ | ❌| ✅|
| [DeleteBucketLifecycle](https://docs.aws.amazon.com/AmazonS3/latest/API/API_DeleteBucketLifecycle.html) | ❌ Missing | ❌| ✅| ❌| ✅|
| [GetBucketLifecycleConfiguration](https://docs.aws.amazon.com/AmazonS3/latest/API/API_GetBucketLifecycleConfiguration.html) | ❌ Missing | ❌| ✅ | ❌| ✅|
| [PutBucketLifecycleConfiguration](https://docs.aws.amazon.com/AmazonS3/latest/API/API_PutBucketLifecycleConfiguration.html) | ❌ Missing | ❌| ✅ | ❌| ✅|
| [GetBucketVersioning](https://docs.aws.amazon.com/AmazonS3/latest/API/API_GetBucketVersioning.html) | ❌ Stub (see below) | ✅| ✅ | ❌| ✅|
| [ListObjectVersions](https://docs.aws.amazon.com/AmazonS3/latest/API/API_ListObjectVersions.html) | ❌ Missing | ❌| ✅ | ❌| ✅|
| [PutBucketVersioning](https://docs.aws.amazon.com/AmazonS3/latest/API/API_PutBucketVersioning.html) | ❌ Missing | ❌| ✅| ❌| ✅|
**PutBucketLifecycleConfiguration:** The only actions supported are
`AbortIncompleteMultipartUpload` and `Expiration` (without the
`ExpiredObjectDeleteMarker` field). All other operations are dependent on
either bucket versionning or storage classes which Garage currently does not
implement. The deprecated `Prefix` member directly in the the `Rule`
structure/XML tag is not supported, specified prefixes must be inside the
`Filter` structure/XML tag.
**GetBucketVersioning:** Stub implementation which always returns "versionning not enabled", since Garage does not yet support bucket versionning.
**GetBucketVersioning:** Stub implementation (Garage does not yet support versionning so this always returns "versionning not enabled").
### Replication endpoints

View file

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

View file

@ -1,77 +0,0 @@
+++
title = "Migrating from 0.9 to 1.0"
weight = 11
+++
**This guide explains how to migrate to 1.0 if you have an existing 0.9 cluster.
We don't recommend trying to migrate to 1.0 directly from 0.8 or older.**
This migration procedure has been tested on several clusters without issues.
However, it is still a *critical procedure* that might cause issues.
**Make sure to back up all your data before attempting it!**
You might also want to read our [general documentation on upgrading Garage](@/documentation/operations/upgrading.md).
## Changes introduced in v1.0
The following are **breaking changes** in Garage v1.0 that require your attention when migrating:
- The Sled metadata db engine has been **removed**. If your cluster was still
using Sled, you will need to **use a Garage v0.9.x binary** to convert the
database using the `garage convert-db` subcommand. See
[here](@/documentation/reference-manual/configuration.md#db_engine) for the
details of the procedure.
The following syntax changes have been made to the configuration file:
- The `replication_mode` parameter has been split into two parameters:
[`replication_factor`](@/documentation/reference-manual/configuration.md#replication_factor)
and
[`consistency_mode`](@/documentation/reference-manual/configuration.md#consistency_mode).
The old syntax using `replication_mode` is still supported for legacy
reasons and can still be used.
- The parameters `sled_cache_capacity` and `sled_flush_every_ms` have been removed.
## Migration procedure
The migration to Garage v1.0 can be done with almost no downtime,
by restarting all nodes at once in the new version.
The migration steps are as follows:
1. Do a `garage repair --all-nodes --yes tables`, check the logs and check that
all data seems to be synced correctly between nodes. If you have time, do
additional `garage repair` procedures (`blocks`, `versions`, `block_refs`,
etc.)
2. Ensure you have a snapshot of your Garage installation that you can restore
to in case the upgrade goes wrong:
- If you are running Garage v0.9.4 or later, use the `garage meta snapshot
--all` to make a backup snapshot of the metadata directories of your nodes
for backup purposes, and save a copy of the following files in the
metadata directories of your nodes: `cluster_layout`, `data_layout`,
`node_key`, `node_key.pub`.
- If you are running a filesystem such as ZFS or BTRFS that support
snapshotting, you can create a filesystem-level snapshot to be used as a
restoration point if needed.
- In other cases, make a backup using the old procedure: turn off each node
individually; back up its metadata folder (for instance, use the following
command if your metadata directory is `/var/lib/garage/meta`: `cd
/var/lib/garage ; tar -acf meta-v0.9.tar.zst meta/`); turn it back on
again. This will allow you to take a backup of all nodes without
impacting global cluster availability. You can do all nodes of a single
zone at once as this does not impact the availability of Garage.
3. Prepare your updated binaries and configuration files for Garage v1.0
4. Shut down all v0.9 nodes simultaneously, and restart them all simultaneously
in v1.0. Use your favorite deployment tool (Ansible, Kubernetes, Nomad) to
achieve this as fast as possible. Garage v1.0 should be in a working state
as soon as enough nodes have started.
5. Monitor your cluster in the following hours to see if it works well under
your production load.

View file

@ -8,9 +8,9 @@ listen address is specified in the `[admin]` section of the configuration
file (see [configuration file
reference](@/documentation/reference-manual/configuration.md))
**WARNING.** At this point, there is no commitment to the stability of the APIs described in this document.
We will bump the version numbers prefixed to each API endpoint each time the syntax
or semantics change, meaning that code that relies on these endpoints will break
**WARNING.** At this point, there is no comittement to stability of the APIs described in this document.
We will bump the version numbers prefixed to each API endpoint at each time the syntax
or semantics change, meaning that code that relies on these endpoint will break
when changes are introduced.
The Garage administration API was introduced in version 0.7.2, this document
@ -19,7 +19,7 @@ does not apply to older versions of Garage.
## Access control
The admin API uses two different tokens for access control, that are specified in the config file's `[admin]` section:
The admin API uses two different tokens for acces control, that are specified in the config file's `[admin]` section:
- `metrics_token`: the token for accessing the Metrics endpoint (if this token
is not set in the config file, the Metrics endpoint can be accessed without
@ -52,11 +52,11 @@ Returns an HTTP status 200 if the node is ready to answer user's requests,
and an HTTP status 503 (Service Unavailable) if there are some partitions
for which a quorum of nodes is not available.
A simple textual message is also returned in a body with content-type `text/plain`.
See `/v1/health` for an API that also returns JSON output.
See `/v0/health` for an API that also returns JSON output.
### Cluster operations
#### GetClusterStatus `GET /v1/status`
#### GetClusterStatus `GET /v0/status`
Returns the cluster's current status in JSON, including:
@ -69,121 +69,87 @@ Example response body:
```json
{
"node": "b10c110e4e854e5aa3f4637681befac755154b20059ec163254ddbfae86b09df",
"garageVersion": "v1.0.1",
"garageFeatures": [
"k2v",
"lmdb",
"sqlite",
"metrics",
"bundled-libs"
],
"rustVersion": "1.68.0",
"dbEngine": "LMDB (using Heed crate)",
"layoutVersion": 5,
"nodes": [
{
"id": "62b218d848e86a64f7fe1909735f29a4350547b54c4b204f91246a14eb0a1a8c",
"role": {
"id": "62b218d848e86a64f7fe1909735f29a4350547b54c4b204f91246a14eb0a1a8c",
"node": "ec79480e0ce52ae26fd00c9da684e4fa56658d9c64cdcecb094e936de0bfe71f",
"garage_version": "git:v0.8.0",
"knownNodes": {
"ec79480e0ce52ae26fd00c9da684e4fa56658d9c64cdcecb094e936de0bfe71f": {
"addr": "10.0.0.11:3901",
"is_up": true,
"last_seen_secs_ago": 9,
"hostname": "node1"
},
"4a6ae5a1d0d33bf895f5bb4f0a418b7dc94c47c0dd2eb108d1158f3c8f60b0ff": {
"addr": "10.0.0.12:3901",
"is_up": true,
"last_seen_secs_ago": 1,
"hostname": "node2"
},
"23ffd0cdd375ebff573b20cc5cef38996b51c1a7d6dbcf2c6e619876e507cf27": {
"addr": "10.0.0.21:3901",
"is_up": true,
"last_seen_secs_ago": 7,
"hostname": "node3"
},
"e2ee7984ee65b260682086ec70026165903c86e601a4a5a501c1900afe28d84b": {
"addr": "10.0.0.22:3901",
"is_up": true,
"last_seen_secs_ago": 1,
"hostname": "node4"
}
},
"layout": {
"version": 12,
"roles": {
"ec79480e0ce52ae26fd00c9da684e4fa56658d9c64cdcecb094e936de0bfe71f": {
"zone": "dc1",
"capacity": 100000000000,
"tags": []
},
"addr": "10.0.0.3:3901",
"hostname": "node3",
"isUp": true,
"lastSeenSecsAgo": 12,
"draining": false,
"dataPartition": {
"available": 660270088192,
"total": 873862266880
},
"metadataPartition": {
"available": 660270088192,
"total": 873862266880
}
},
{
"id": "a11c7cf18af297379eff8688360155fe68d9061654449ba0ce239252f5a7487f",
"role": null,
"addr": "10.0.0.2:3901",
"hostname": "node2",
"isUp": true,
"lastSeenSecsAgo": 11,
"draining": true,
"dataPartition": {
"available": 660270088192,
"total": 873862266880
},
"metadataPartition": {
"available": 660270088192,
"total": 873862266880
}
},
{
"id": "a235ac7695e0c54d7b403943025f57504d500fdcc5c3e42c71c5212faca040a2",
"role": {
"id": "a235ac7695e0c54d7b403943025f57504d500fdcc5c3e42c71c5212faca040a2",
"zone": "dc1",
"capacity": 100000000000,
"tags": []
},
"addr": "127.0.0.1:3904",
"hostname": "lindy",
"isUp": true,
"lastSeenSecsAgo": 2,
"draining": false,
"dataPartition": {
"available": 660270088192,
"total": 873862266880
},
"metadataPartition": {
"available": 660270088192,
"total": 873862266880
}
},
{
"id": "b10c110e4e854e5aa3f4637681befac755154b20059ec163254ddbfae86b09df",
"role": {
"id": "b10c110e4e854e5aa3f4637681befac755154b20059ec163254ddbfae86b09df",
"zone": "dc1",
"capacity": 100000000000,
"tags": []
},
"addr": "10.0.0.1:3901",
"hostname": "node1",
"isUp": true,
"lastSeenSecsAgo": 3,
"draining": false,
"dataPartition": {
"available": 660270088192,
"total": 873862266880
},
"metadataPartition": {
"available": 660270088192,
"total": 873862266880
}
}
"capacity": 4,
"tags": [
"node1"
]
},
"4a6ae5a1d0d33bf895f5bb4f0a418b7dc94c47c0dd2eb108d1158f3c8f60b0ff": {
"zone": "dc1",
"capacity": 6,
"tags": [
"node2"
]
},
"23ffd0cdd375ebff573b20cc5cef38996b51c1a7d6dbcf2c6e619876e507cf27": {
"zone": "dc2",
"capacity": 10,
"tags": [
"node3"
]
}
},
"stagedRoleChanges": {
"e2ee7984ee65b260682086ec70026165903c86e601a4a5a501c1900afe28d84b": {
"zone": "dc2",
"capacity": 5,
"tags": [
"node4"
]
}
}
}
}
```
#### GetClusterHealth `GET /v1/health`
#### GetClusterHealth `GET /v0/health`
Returns the cluster's current health in JSON format, with the following variables:
- `status`: one of `healthy`, `degraded` or `unavailable`:
- healthy: Garage node is connected to all storage nodes
- degraded: Garage node is not connected to all storage nodes, but a quorum of write nodes is available for all partitions
- unavailable: a quorum of write nodes is not available for some partitions
- `knownNodes`: the number of nodes this Garage node has had a TCP connection to since the daemon started
- `connectedNodes`: the nubmer of nodes this Garage node currently has an open connection to
- `storageNodes`: the number of storage nodes currently registered in the cluster layout
- `storageNodesOk`: the number of storage nodes to which a connection is currently open
- `status`: one of `Healthy`, `Degraded` or `Unavailable`:
- Healthy: Garage node is connected to all storage nodes
- Degraded: Garage node is not connected to all storage nodes, but a quorum of write nodes is available for all partitions
- Unavailable: a quorum of write nodes is not available for some partitions
- `known_nodes`: the number of nodes this Garage node has had a TCP connection to since the daemon started
- `connected_nodes`: the nubmer of nodes this Garage node currently has an open connection to
- `storage_nodes`: the number of storage nodes currently registered in the cluster layout
- `storage_nodes_ok`: the number of storage nodes to which a connection is currently open
- `partitions`: the total number of partitions of the data (currently always 256)
- `partitionsQuorum`: the number of partitions for which a quorum of write nodes is available
- `partitionsAllOk`: the number of partitions for which we are connected to all storage nodes responsible of storing it
- `partitions_quorum`: the number of partitions for which a quorum of write nodes is available
- `partitions_all_ok`: the number of partitions for which we are connected to all storage nodes responsible of storing it
Contrarily to `GET /health`, this endpoint always returns a 200 OK HTTP response code.
@ -191,18 +157,18 @@ Example response body:
```json
{
"status": "degraded",
"knownNodes": 3,
"connectedNodes": 3,
"storageNodes": 4,
"storageNodesOk": 3,
"status": "Degraded",
"known_nodes": 3,
"connected_nodes": 2,
"storage_nodes": 3,
"storage_nodes_ok": 2,
"partitions": 256,
"partitionsQuorum": 256,
"partitionsAllOk": 64
"partitions_quorum": 256,
"partitions_all_ok": 0
}
```
#### ConnectClusterNodes `POST /v1/connect`
#### ConnectClusterNodes `POST /v0/connect`
Instructs this Garage node to connect to other Garage nodes at specified addresses.
@ -232,7 +198,7 @@ Example response:
]
```
#### GetClusterLayout `GET /v1/layout`
#### GetClusterLayout `GET /v0/layout`
Returns the cluster's current layout in JSON, including:
@ -246,54 +212,42 @@ Example response body:
```json
{
"version": 12,
"roles": [
{
"id": "ec79480e0ce52ae26fd00c9da684e4fa56658d9c64cdcecb094e936de0bfe71f",
"roles": {
"ec79480e0ce52ae26fd00c9da684e4fa56658d9c64cdcecb094e936de0bfe71f": {
"zone": "dc1",
"capacity": 10737418240,
"capacity": 4,
"tags": [
"node1"
]
},
{
"id": "4a6ae5a1d0d33bf895f5bb4f0a418b7dc94c47c0dd2eb108d1158f3c8f60b0ff",
"4a6ae5a1d0d33bf895f5bb4f0a418b7dc94c47c0dd2eb108d1158f3c8f60b0ff": {
"zone": "dc1",
"capacity": 10737418240,
"capacity": 6,
"tags": [
"node2"
]
},
{
"id": "23ffd0cdd375ebff573b20cc5cef38996b51c1a7d6dbcf2c6e619876e507cf27",
"23ffd0cdd375ebff573b20cc5cef38996b51c1a7d6dbcf2c6e619876e507cf27": {
"zone": "dc2",
"capacity": 10737418240,
"capacity": 10,
"tags": [
"node3"
]
}
],
"stagedRoleChanges": [
{
"id": "e2ee7984ee65b260682086ec70026165903c86e601a4a5a501c1900afe28d84b",
"remove": false,
},
"stagedRoleChanges": {
"e2ee7984ee65b260682086ec70026165903c86e601a4a5a501c1900afe28d84b": {
"zone": "dc2",
"capacity": 10737418240,
"capacity": 5,
"tags": [
"node4"
]
}
{
"id": "23ffd0cdd375ebff573b20cc5cef38996b51c1a7d6dbcf2c6e619876e507cf27",
"remove": true,
"zone": null,
"capacity": null,
"tags": null,
}
]
}
```
#### UpdateClusterLayout `POST /v1/layout`
#### UpdateClusterLayout `POST /v0/layout`
Send modifications to the cluster layout. These modifications will
be included in the staged role changes, visible in subsequent calls
@ -305,9 +259,8 @@ the layout.
Request body format:
```json
[
{
"id": <node_id>,
{
<node_id>: {
"capacity": <new_capacity>,
"zone": <new_zone>,
"tags": [
@ -315,22 +268,17 @@ Request body format:
...
]
},
{
"id": <node_id_to_remove>,
"remove": true
}
]
<node_id_to_remove>: null,
...
}
```
Contrary to the CLI that may update only a subset of the fields
`capacity`, `zone` and `tags`, when calling this API all of these
values must be specified.
This returns the new cluster layout with the proposed staged changes,
as returned by GetClusterLayout.
#### ApplyClusterLayout `POST /v1/layout/apply`
#### ApplyClusterLayout `POST /v0/layout/apply`
Applies to the cluster the layout changes currently registered as
staged layout changes.
@ -347,10 +295,7 @@ Similarly to the CLI, the body must include the version of the new layout
that will be created, which MUST be 1 + the value of the currently
existing layout in the cluster.
This returns the message describing all the calculations done to compute the new
layout, as well as the description of the layout as returned by GetClusterLayout.
#### RevertClusterLayout `POST /v1/layout/revert`
#### RevertClusterLayout `POST /v0/layout/revert`
Clears all of the staged layout changes.
@ -368,13 +313,10 @@ Similarly to the CLI, the body must include the incremented
version number, which MUST be 1 + the value of the currently
existing layout in the cluster.
This returns the new cluster layout with all changes reverted,
as returned by GetClusterLayout.
### Access key operations
#### ListKeys `GET /v1/key`
#### ListKeys `GET /v0/key`
Returns all API access keys in the cluster.
@ -393,8 +335,34 @@ Example response:
]
```
#### GetKeyInfo `GET /v1/key?id=<acces key id>`
#### GetKeyInfo `GET /v1/key?search=<pattern>`
#### CreateKey `POST /v0/key`
Creates a new API access key.
Request body format:
```json
{
"name": "NameOfMyKey"
}
```
#### ImportKey `POST /v0/key/import`
Imports an existing API key.
Request body format:
```json
{
"accessKeyId": "GK31c2f218a2e44f485b94239e",
"secretAccessKey": "b892c0665f0ada8a4755dae98baa3b133590e11dae3bcc1f9d769d67f16c3835",
"name": "NameOfMyKey"
}
```
#### GetKeyInfo `GET /v0/key?id=<acces key id>`
#### GetKeyInfo `GET /v0/key?search=<pattern>`
Returns information about the requested API access key.
@ -402,9 +370,6 @@ If `id` is set, the key is looked up using its exact identifier (faster).
If `search` is set, the key is looked up using its name or prefix
of identifier (slower, all keys are enumerated to do this).
Optionnally, the query parameter `showSecretKey=true` can be set to reveal the
associated secret access key.
Example response:
```json
@ -468,40 +433,11 @@ Example response:
}
```
#### CreateKey `POST /v1/key`
#### DeleteKey `DELETE /v0/key?id=<acces key id>`
Creates a new API access key.
Deletes an API access key.
Request body format:
```json
{
"name": "NameOfMyKey"
}
```
This returns the key info, including the created secret key,
in the same format as the result of GetKeyInfo.
#### ImportKey `POST /v1/key/import`
Imports an existing API key.
This will check that the imported key is in the valid format, i.e.
is a key that could have been generated by Garage.
Request body format:
```json
{
"accessKeyId": "GK31c2f218a2e44f485b94239e",
"secretAccessKey": "b892c0665f0ada8a4755dae98baa3b133590e11dae3bcc1f9d769d67f16c3835",
"name": "NameOfMyKey"
}
```
This returns the key info in the same format as the result of GetKeyInfo.
#### UpdateKey `POST /v1/key?id=<acces key id>`
#### UpdateKey `POST /v0/key?id=<acces key id>`
Updates information about the specified API access key.
@ -521,16 +457,10 @@ All fields (`name`, `allow` and `deny`) are optional.
If they are present, the corresponding modifications are applied to the key, otherwise nothing is changed.
The possible flags in `allow` and `deny` are: `createBucket`.
This returns the key info in the same format as the result of GetKeyInfo.
#### DeleteKey `DELETE /v1/key?id=<acces key id>`
Deletes an API access key.
### Bucket operations
#### ListBuckets `GET /v1/bucket`
#### ListBuckets `GET /v0/bucket`
Returns all storage buckets in the cluster.
@ -572,8 +502,8 @@ Example response:
]
```
#### GetBucketInfo `GET /v1/bucket?id=<bucket id>`
#### GetBucketInfo `GET /v1/bucket?globalAlias=<alias>`
#### GetBucketInfo `GET /v0/bucket?id=<bucket id>`
#### GetBucketInfo `GET /v0/bucket?globalAlias=<alias>`
Returns information about the requested storage bucket.
@ -605,10 +535,7 @@ Example response:
],
"objects": 14827,
"bytes": 13189855625,
"unfinishedUploads": 1,
"unfinishedMultipartUploads": 1,
"unfinishedMultipartUploadParts": 11,
"unfinishedMultipartUploadBytes": 41943040,
"unfinshedUploads": 0,
"quotas": {
"maxSize": null,
"maxObjects": null
@ -616,7 +543,7 @@ Example response:
}
```
#### CreateBucket `POST /v1/bucket`
#### CreateBucket `POST /v0/bucket`
Creates a new storage bucket.
@ -656,7 +583,13 @@ or no alias at all.
Technically, you can also specify both `globalAlias` and `localAlias` and that would create
two aliases, but I don't see why you would want to do that.
#### UpdateBucket `PUT /v1/bucket?id=<bucket id>`
#### DeleteBucket `DELETE /v0/bucket?id=<bucket id>`
Deletes a storage bucket. A bucket cannot be deleted if it is not empty.
Warning: this will delete all aliases associated with the bucket!
#### UpdateBucket `PUT /v0/bucket?id=<bucket id>`
Updates configuration of the given bucket.
@ -688,16 +621,9 @@ In `quotas`: new values of `maxSize` and `maxObjects` must both be specified, or
to remove the quotas. An absent value will be considered the same as a `null`. It is not possible
to change only one of the two quotas.
#### DeleteBucket `DELETE /v1/bucket?id=<bucket id>`
Deletes a storage bucket. A bucket cannot be deleted if it is not empty.
Warning: this will delete all aliases associated with the bucket!
### Operations on permissions for keys on buckets
#### BucketAllowKey `POST /v1/bucket/allow`
#### BucketAllowKey `POST /v0/bucket/allow`
Allows a key to do read/write/owner operations on a bucket.
@ -718,7 +644,7 @@ Request body format:
Flags in `permissions` which have the value `true` will be activated.
Other flags will remain unchanged.
#### BucketDenyKey `POST /v1/bucket/deny`
#### BucketDenyKey `POST /v0/bucket/deny`
Denies a key from doing read/write/owner operations on a bucket.
@ -742,19 +668,19 @@ Other flags will remain unchanged.
### Operations on bucket aliases
#### GlobalAliasBucket `PUT /v1/bucket/alias/global?id=<bucket id>&alias=<global alias>`
#### GlobalAliasBucket `PUT /v0/bucket/alias/global?id=<bucket id>&alias=<global alias>`
Empty body. Creates a global alias for a bucket.
#### GlobalUnaliasBucket `DELETE /v1/bucket/alias/global?id=<bucket id>&alias=<global alias>`
#### GlobalUnaliasBucket `DELETE /v0/bucket/alias/global?id=<bucket id>&alias=<global alias>`
Removes a global alias for a bucket.
#### LocalAliasBucket `PUT /v1/bucket/alias/local?id=<bucket id>&accessKeyId=<access key ID>&alias=<local alias>`
#### LocalAliasBucket `PUT /v0/bucket/alias/local?id=<bucket id>&accessKeyId=<access key ID>&alias=<local alias>`
Empty body. Creates a local alias for a bucket in the namespace of a specific access key.
#### LocalUnaliasBucket `DELETE /v1/bucket/alias/local?id=<bucket id>&accessKeyId<access key ID>&alias=<local alias>`
#### LocalUnaliasBucket `DELETE /v0/bucket/alias/local?id=<bucket id>&accessKeyId<access key ID>&alias=<local alias>`
Removes a local alias for a bucket in the namespace of a specific access key.

View file

@ -146,7 +146,7 @@ in a bucket, as the partition key becomes the sort key in the index.
How indexing works:
- Each node keeps a local count of how many items it stores for each partition,
in a local database tree that is updated atomically when an item is modified.
in a local Sled tree that is updated atomically when an item is modified.
- These local counters are asynchronously stored in the index table which is
a regular Garage table spread in the network. Counters are stored as LWW values,
so basically the final table will have the following structure:

View file

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

File diff suppressed because it is too large Load diff

Before

Width:  |  Height:  |  Size: 161 KiB

File diff suppressed because it is too large Load diff

Before

Width:  |  Height:  |  Size: 560 KiB

File diff suppressed because it is too large Load diff

Before

Width:  |  Height:  |  Size: 287 KiB

File diff suppressed because it is too large Load diff

Before

Width:  |  Height:  |  Size: 112 KiB

File diff suppressed because it is too large Load diff

Before

Width:  |  Height:  |  Size: 270 KiB

View file

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

View file

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

View file

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

Binary file not shown.

Binary file not shown.

Before

Width:  |  Height:  |  Size: 36 KiB

Binary file not shown.

View file

@ -1 +0,0 @@
.direnv/

View file

@ -1,17 +0,0 @@
*
!*.txt
!*.md
!assets
!.gitignore
!*.svg
!*.png
!*.jpg
!*.tex
!Makefile
!.gitignore
!assets/*.drawio.pdf
!talk.pdf

View file

@ -1,34 +0,0 @@
ASSETS=assets/consistent_hashing_1.pdf \
assets/consistent_hashing_2.pdf \
assets/consistent_hashing_3.pdf \
assets/consistent_hashing_4.pdf \
assets/garage_tables.pdf \
assets/consensus.pdf_tex \
assets/lattice1.pdf_tex \
assets/lattice2.pdf_tex \
assets/lattice3.pdf_tex \
assets/lattice4.pdf_tex \
assets/lattice5.pdf_tex \
assets/lattice6.pdf_tex \
assets/lattice7.pdf_tex \
assets/lattice8.pdf_tex \
assets/latticeB_1.pdf_tex \
assets/latticeB_2.pdf_tex \
assets/latticeB_3.pdf_tex \
assets/latticeB_4.pdf_tex \
assets/latticeB_5.pdf_tex \
assets/latticeB_6.pdf_tex \
assets/latticeB_7.pdf_tex \
assets/latticeB_8.pdf_tex \
assets/latticeB_9.pdf_tex \
assets/latticeB_10.pdf_tex \
assets/deuxfleurs.pdf
talk.pdf: talk.tex $(ASSETS)
pdflatex talk.tex
assets/%.pdf: assets/%.svg
inkscape -D -z --file=$^ --export-pdf=$@
assets/%.pdf_tex: assets/%.svg
inkscape -D -z --file=$^ --export-pdf=$@ --export-latex

View file

@ -1,39 +0,0 @@
### (fr) Garage, un système de stockage de données géo-distribué léger et robuste
Garage est un système de stockage de données léger, géo-distribué, qui
implémente le protocole de stockage S3 de Amazon. Garage est destiné
principalement à l'auto-hébergement sur du matériel courant d'occasion. À ce
titre, il doit tolérer un grand nombre de pannes: coupures de courant, coupures
de connexion Internet, pannes de machines, ... Il doit également être facile à
déployer et à maintenir, afin de pouvoir être facilement utilisé par des
amateurs ou des petites organisations.
Cette présentation vous proposera un aperçu de Garage et du choix technique
principal qui rend un système comme Garage possible: le refus d'utiliser des
algorithmes de consensus, remplacés avantageusement par des méthodes à
cohérence faible. Notre modèle est fortement inspiré de la base de donnée
Dynamo (DeCandia et al, 2007), et fait usage des types de données CRDT (Shapiro
et al, 2011). Nous exploreront comment ces méthodes s'appliquent à la
construction de l'abstraction "stockage objet" dans un système distribué, et
quelles autres abstractions peuvent ou ne peuvent pas être construites dans ce
modèle.
### (en) Garage, a lightweight and robust geo-distributed data storage system
Garage is a lightweight geo-distributed data store that implements the Amazon
S3 object storage protocol. Garage is meant primarily for self-hosting at home
on second-hand commodity hardware, meaning it has to tolerate a wide variety of
failure scenarios such as power cuts, Internet disconnections and machine
crashes. It also has to be easy to deploy and maintain, so that hobbyists and
small organizations can use it without trouble.
This talk will present Garage and the key technical choice that made Garage
possible: refusing to use consensus algorithms and using instead weak
consistency methods, with a model that is loosely based on that of the Dynamo
database (DeCandia et al, 2007) and that makes heavy use of conflict-free
replicated data types (Shapiro et al, 2011). We will explore how these methods
are suited to building the "object store" abstraction in a distributed system,
and what other abstractions are possible or impossible to build in this model.

Binary file not shown.

Before

Width:  |  Height:  |  Size: 32 KiB

Binary file not shown.

Before

Width:  |  Height:  |  Size: 115 KiB

File diff suppressed because one or more lines are too long

Before

Width:  |  Height:  |  Size: 184 KiB

Binary file not shown.

Before

Width:  |  Height:  |  Size: 26 KiB

Binary file not shown.

Before

Width:  |  Height:  |  Size: 27 KiB

Binary file not shown.

Before

Width:  |  Height:  |  Size: 8.9 KiB

Binary file not shown.

Before

Width:  |  Height:  |  Size: 18 KiB

Binary file not shown.

Before

Width:  |  Height:  |  Size: 4.8 KiB

Binary file not shown.

Before

Width:  |  Height:  |  Size: 263 KiB

Binary file not shown.

Before

Width:  |  Height:  |  Size: 82 KiB

View file

@ -1,137 +0,0 @@
<?xml version="1.0" encoding="UTF-8" standalone="no"?>
<!-- Created with Inkscape (http://www.inkscape.org/) -->
<svg
width="800"
height="300"
viewBox="0 0 211.66666 79.374999"
version="1.1"
id="svg5"
inkscape:version="1.2.2 (b0a8486541, 2022-12-01)"
sodipodi:docname="consensus.svg"
xmlns:inkscape="http://www.inkscape.org/namespaces/inkscape"
xmlns:sodipodi="http://sodipodi.sourceforge.net/DTD/sodipodi-0.dtd"
xmlns="http://www.w3.org/2000/svg"
xmlns:svg="http://www.w3.org/2000/svg">
<sodipodi:namedview
id="namedview7"
pagecolor="#ffffff"
bordercolor="#666666"
borderopacity="1.0"
inkscape:showpageshadow="2"
inkscape:pageopacity="0.0"
inkscape:pagecheckerboard="0"
inkscape:deskcolor="#d1d1d1"
inkscape:document-units="mm"
showgrid="false"
inkscape:zoom="1.4734708"
inkscape:cx="310.49139"
inkscape:cy="179.1688"
inkscape:window-width="1920"
inkscape:window-height="999"
inkscape:window-x="0"
inkscape:window-y="0"
inkscape:window-maximized="1"
inkscape:current-layer="layer1" />
<defs
id="defs2">
<marker
style="overflow:visible"
id="Arrow2"
refX="0"
refY="0"
orient="auto-start-reverse"
inkscape:stockid="Arrow2"
markerWidth="7.6999998"
markerHeight="5.5999999"
viewBox="0 0 7.7 5.6"
inkscape:isstock="true"
inkscape:collect="always"
preserveAspectRatio="xMidYMid">
<path
transform="scale(0.7)"
d="M -2,-4 9,0 -2,4 c 2,-2.33 2,-5.66 0,-8 z"
style="fill:context-stroke;fill-rule:evenodd;stroke:none"
id="arrow2L" />
</marker>
</defs>
<g
inkscape:label="Layer 1"
inkscape:groupmode="layer"
id="layer1">
<g
id="g1218"
transform="translate(-8.9161476,-12.502301)">
<circle
style="fill:#ffffff;stroke:#000000;stroke-width:1;stroke-dasharray:none;stroke-opacity:1"
id="path111"
cx="38.904896"
cy="37.936272"
r="13.474442" />
<text
xml:space="preserve"
style="font-size:8.46667px;line-height:1.25;font-family:sans-serif;text-align:center;text-anchor:middle;stroke-width:0.264583;fill:#000000"
x="38.879501"
y="40.908073"
id="text1105"><tspan
sodipodi:role="line"
id="tspan1103"
style="stroke-width:0.264583;fill:#000000"
x="38.879501"
y="40.908073">$\bot$</tspan></text>
</g>
<g
id="g1218-3"
transform="translate(127.41938,-12.502301)">
<circle
style="fill:#ffffff;stroke:#000000;stroke-width:1;stroke-dasharray:none;stroke-opacity:1"
id="path111-5"
cx="38.904896"
cy="37.936272"
r="13.474442" />
<text
xml:space="preserve"
style="font-size:8.46667px;line-height:1.25;font-family:sans-serif;text-align:center;text-anchor:middle;stroke-width:0.264583;fill:#000000"
x="38.879501"
y="40.908073"
id="text1105-6"><tspan
sodipodi:role="line"
id="tspan1103-2"
style="stroke-width:0.264583;fill:#000000"
x="38.879501"
y="40.908073">$x$</tspan></text>
</g>
<path
style="fill:none;stroke:#000000;stroke-width:1;stroke-linecap:butt;stroke-linejoin:miter;stroke-dasharray:none;stroke-opacity:1;marker-end:url(#Arrow2)"
d="M 44.289635,25.433971 H 145.90576"
id="path1414"
sodipodi:nodetypes="cc" />
<text
xml:space="preserve"
style="font-size:8.46667px;line-height:1.25;font-family:sans-serif;text-align:center;text-anchor:middle;stroke-width:0.264583;fill:#000000"
x="92.729836"
y="21.781803"
id="text2092"><tspan
sodipodi:role="line"
id="tspan2090"
style="stroke-width:0.264583;fill:#000000"
x="92.729836"
y="21.781803">$propose(x) / x$</tspan></text>
<text
xml:space="preserve"
style="font-size:8.46667px;line-height:1.25;font-family:sans-serif;text-align:center;text-anchor:middle;stroke-width:0.264583;fill:#000000"
x="166.29887"
y="69.89299"
id="text2092-9"><tspan
sodipodi:role="line"
id="tspan2090-1"
style="stroke-width:0.264583;fill:#000000"
x="166.29887"
y="69.89299">$propose(y) / x$</tspan></text>
<path
style="fill:none;stroke:#000000;stroke-width:1;stroke-linecap:butt;stroke-linejoin:miter;stroke-dasharray:none;stroke-opacity:1;marker-end:url(#Arrow2)"
d="m 155.82329,35.899857 c -8.35129,12.319651 0.54055,24.640898 11.72797,24.072085 8.65403,-0.440005 18.59818,-11.705963 11.8146,-20.570891"
id="path2150"
sodipodi:nodetypes="csc" />
</g>
</svg>

Before

Width:  |  Height:  |  Size: 4.7 KiB

File diff suppressed because one or more lines are too long

Before

Width:  |  Height:  |  Size: 53 KiB

File diff suppressed because one or more lines are too long

Before

Width:  |  Height:  |  Size: 54 KiB

File diff suppressed because one or more lines are too long

Before

Width:  |  Height:  |  Size: 56 KiB

File diff suppressed because one or more lines are too long

Before

Width:  |  Height:  |  Size: 57 KiB

View file

@ -1,91 +0,0 @@
<?xml version="1.0" encoding="UTF-8" standalone="no"?>
<svg
viewBox="0 0 70.424515 70.300102"
version="1.1"
id="svg8"
sodipodi:docname="logo.svg"
inkscape:version="1.1 (c68e22c387, 2021-05-23)"
inkscape:export-filename="/home/quentin/Documents/dev/deuxfleurs/site/src/img/logo.png"
inkscape:export-xdpi="699.30194"
inkscape:export-ydpi="699.30194"
width="70.424515"
height="70.300102"
xmlns:inkscape="http://www.inkscape.org/namespaces/inkscape"
xmlns:sodipodi="http://sodipodi.sourceforge.net/DTD/sodipodi-0.dtd"
xmlns="http://www.w3.org/2000/svg"
xmlns:svg="http://www.w3.org/2000/svg">
<defs
id="defs12" />
<sodipodi:namedview
id="namedview10"
pagecolor="#ffffff"
bordercolor="#666666"
borderopacity="1.0"
inkscape:pageshadow="2"
inkscape:pageopacity="0.0"
inkscape:pagecheckerboard="0"
showgrid="false"
inkscape:zoom="12.125"
inkscape:cx="43.092783"
inkscape:cy="48.082474"
inkscape:window-width="3072"
inkscape:window-height="1659"
inkscape:window-x="0"
inkscape:window-y="0"
inkscape:window-maximized="1"
inkscape:current-layer="svg8" />
<g
id="g79969"
transform="translate(-0.827,34.992103)">
<path
fill="#ffffff"
d="m 15.632,34.661 c -0.799,-0.597 -1.498,-1.484 -2.035,-2.592 l -0.228,-0.47 -0.46,0.249 c -0.975,0.528 -1.913,0.858 -2.744,0.969 L 9.963,29.061 6.327,30.029 C 6.17,29.175 6.202,28.142 6.423,27.007 L 6.526,26.482 5.994,26.416 C 4.752,26.262 3.688,25.891 2.89,25.336 L 4.411,22.419 1.423,20.896 C 1.742,19.952 2.371,19.014 3.257,18.161 L 3.634,17.798 3.255,17.438 C 2.452,16.674 1.847,15.884 1.485,15.127 L 4.995,13.774 2.95,10.615 C 3.69,10.213 4.643,9.929 5.739,9.783 L 6.258,9.715 6.167,9.201 C 5.952,7.99 5.995,6.863 6.291,5.913 l 3.308,0.523 0.524,-3.308 c 0.988,0.013 2.08,0.326 3.164,0.907 L 13.749,4.283 13.975,3.81 C 14.454,2.807 15.019,1.986 15.628,1.406 L 18,4.326 20.372,1.406 c 0.609,0.58 1.175,1.401 1.653,2.404 l 0.226,0.473 0.462,-0.247 C 23.798,3.455 24.891,3.142 25.877,3.13 L 26.4,6.438 29.71,5.913 c 0.296,0.951 0.34,2.078 0.124,3.288 l -0.092,0.515 0.518,0.069 c 1.095,0.145 2.048,0.43 2.788,0.832 l -2.046,3.156 3.511,1.355 c -0.361,0.757 -0.966,1.547 -1.77,2.311 l -0.379,0.36 0.377,0.363 c 0.888,0.854 1.516,1.793 1.835,2.736 l -2.984,1.52 1.521,2.984 c -0.812,0.574 -1.871,0.964 -3.094,1.134 l -0.518,0.072 0.096,0.514 c 0.201,1.089 0.226,2.083 0.073,2.909 l -3.634,-0.97 -0.204,3.757 c -0.83,-0.11 -1.768,-0.44 -2.742,-0.968 l -0.459,-0.249 -0.228,0.47 c -0.539,1.107 -1.237,1.994 -2.036,2.591 L 18,32.293 Z"
id="path2" />
<path
d="M 7.092,10.678 C 6.562,9.189 6.394,7.708 6.66,6.478 l 2.368,0.375 0.987,0.156 0.157,-0.988 0.375,-2.368 C 11.808,3.78 13.16,4.396 14.409,5.359 14.527,5.022 14.653,4.696 14.791,4.392 13.24,3.257 11.568,2.629 10.061,2.629 9.938,2.629 9.816,2.633 9.695,2.642 L 9.184,5.865 5.96,5.354 C 5.36,6.841 5.395,8.769 6.045,10.747 6.38,10.71 6.729,10.686 7.092,10.678 Z M 21.593,5.359 c 1.248,-0.962 2.6,-1.578 3.86,-1.705 l 0.376,2.368 0.156,0.988 0.987,-0.157 2.369,-0.376 c 0.266,1.23 0.098,2.71 -0.432,4.2 0.361,0.009 0.711,0.032 1.046,0.07 C 30.606,8.769 30.64,6.841 30.04,5.353 L 26.815,5.865 26.304,2.641 c -0.12,-0.008 -0.242,-0.012 -0.365,-0.012 -1.507,0 -3.179,0.628 -4.73,1.762 0.14,0.306 0.266,0.631 0.384,0.968 z M 7.368,27 h 0.035 c 0.067,0 0.157,-0.604 0.26,-0.947 -0.098,0.004 -0.197,0.046 -0.294,0.046 -1.496,0 -2.826,-0.303 -3.83,-0.89 L 4.628,23.081 5.082,22.194 4.191,21.742 2.055,20.654 C 2.563,19.503 3.57,18.404 4.873,17.511 4.586,17.292 4.312,17.07 4.063,16.842 2.376,18.059 1.217,19.597 0.828,21.152 l 2.908,1.483 -1.482,2.843 C 3.475,26.501 5.303,27 7.368,27 Z m 27.806,-5.846 c -0.39,-1.555 -1.548,-3.093 -3.234,-4.311 -0.25,0.228 -0.523,0.451 -0.81,0.669 1.304,0.893 2.31,1.992 2.817,3.145 l -2.136,1.088 -0.891,0.453 0.454,0.892 1.089,2.137 c -1.004,0.587 -2.332,0.904 -3.828,0.904 -0.099,0 -0.199,-0.01 -0.299,-0.013 0.103,0.344 0.192,0.683 0.26,1.011 l 0.039,0.002 c 2.066,0 3.892,-0.563 5.112,-1.587 l -1.482,-2.908 z m -12.653,9.182 c -0.447,1.517 -1.181,2.812 -2.119,3.651 L 18.707,32.293 18,31.586 l -0.707,0.707 -1.695,1.694 c -0.938,-0.839 -1.673,-2.136 -2.12,-3.652 -0.296,0.206 -0.593,0.397 -0.886,0.563 0.636,1.98 1.741,3.559 3.1,4.409 L 18,33 l 2.308,2.308 c 1.358,-0.851 2.464,-2.428 3.101,-4.408 -0.295,-0.168 -0.591,-0.359 -0.888,-0.564 z"
fill="#ea596e"
id="path4" />
<path
fill="#ea596e"
d="m 20.118,5.683 c 0.426,1.146 0.748,2.596 0.841,4.284 l 0.2,3.683 3.564,-0.946 c 1.32,-0.351 2.655,-0.536 3.86,-0.536 0.16,0 0.318,0.003 0.474,0.01 l -1.827,2.819 3.139,1.211 c -0.958,0.759 -2.237,1.514 -3.814,2.123 l -3.441,1.328 2.001,3.099 c 0.918,1.42 1.509,2.782 1.838,3.96 L 23.709,25.853 23.527,29.21 C 22.508,28.533 21.395,27.55 20.329,26.237 L 18,23.374 15.672,26.236 c -1.066,1.312 -2.179,2.295 -3.198,2.972 l -0.18,-3.354 -3.248,0.864 c 0.329,-1.178 0.921,-2.54 1.839,-3.961 L 12.889,19.658 9.447,18.33 C 7.87,17.721 6.591,16.967 5.633,16.208 L 8.768,15 6.941,12.177 c 0.155,-0.006 0.313,-0.01 0.473,-0.01 1.206,0 2.541,0.185 3.861,0.536 l 3.564,0.947 0.202,-3.683 c 0.092,-1.688 0.415,-3.138 0.84,-4.284 L 18,8.292 20.118,5.683 M 20.308,0.692 18,3.533 15.692,0.692 C 13.703,2.224 12.271,5.684 12.046,9.804 10.429,9.374 8.854,9.167 7.414,9.167 c -2.11,0 -3.929,0.445 -5.161,1.289 l 1.989,3.073 -3.415,1.316 c 0.842,2.366 3.69,4.797 7.54,6.283 -2.241,3.465 -3.116,7.106 -2.407,9.516 l 3.537,-0.941 0.196,3.654 c 2.512,-0.07 5.703,-2.027 8.307,-5.228 2.603,3.201 5.796,5.158 8.306,5.228 l 0.198,-3.655 3.535,0.943 c 0.71,-2.411 -0.165,-6.05 -2.404,-9.517 3.849,-1.485 6.696,-3.918 7.538,-6.283 l -3.415,-1.318 1.99,-3.07 c -1.233,-0.844 -3.053,-1.29 -5.164,-1.29 -1.438,0 -3.013,0.207 -4.63,0.636 C 23.729,5.684 22.297,2.224 20.308,0.692 Z"
id="path6" />
</g>
<g
id="g79964"
transform="translate(-1.043816,35.993714)">
<path
fill="#ffffff"
d="m 51.92633,-2.0247139 c -0.799,-0.597 -1.498,-1.484 -2.035,-2.592 l -0.228,-0.47 -0.46,0.249 c -0.975,0.528 -1.913,0.858 -2.744,0.969 l -0.202,-3.7560001 -3.636,0.968 c -0.157,-0.854 -0.125,-1.887 0.096,-3.022 l 0.103,-0.525 -0.532,-0.066 c -1.242,-0.154 -2.306,-0.525 -3.104,-1.08 l 1.521,-2.917 -2.988,-1.523 c 0.319,-0.944 0.948,-1.882 1.834,-2.735 l 0.377,-0.363 -0.379,-0.36 c -0.803,-0.764 -1.408,-1.554 -1.77,-2.311 l 3.51,-1.353 -2.045,-3.159 c 0.74,-0.402 1.693,-0.686 2.789,-0.832 l 0.519,-0.068 -0.091,-0.514 c -0.215,-1.211 -0.172,-2.338 0.124,-3.288 l 3.308,0.523 0.524,-3.308 c 0.988,0.013 2.08,0.326 3.164,0.907 l 0.462,0.248 0.226,-0.473 c 0.479,-1.003 1.044,-1.824 1.653,-2.404 l 2.372,2.92 2.372,-2.92 c 0.609,0.58 1.175,1.401 1.653,2.404 l 0.226,0.473 0.462,-0.247 c 1.085,-0.581 2.178,-0.894 3.164,-0.906 l 0.523,3.308 3.31,-0.525 c 0.296,0.951 0.34,2.078 0.124,3.288 l -0.092,0.515 0.518,0.069 c 1.095,0.145 2.048,0.43 2.788,0.832 l -2.046,3.156 3.511,1.355 c -0.361,0.757 -0.966,1.547 -1.77,2.311 l -0.379,0.36 0.377,0.363 c 0.888,0.854 1.516,1.793 1.835,2.736 l -2.984,1.52 1.521,2.984 c -0.812,0.574 -1.871,0.964 -3.094,1.134 l -0.518,0.072 0.096,0.514 c 0.201,1.089 0.226,2.083 0.073,2.909 l -3.634,-0.97 -0.204,3.7570001 c -0.83,-0.11 -1.768,-0.44 -2.742,-0.968 l -0.459,-0.249 -0.228,0.47 c -0.539,1.107 -1.237,1.994 -2.036,2.591 l -2.367,-2.369 z"
id="path2-9" />
<path
d="m 43.38633,-26.007714 c -0.53,-1.489 -0.698,-2.97 -0.432,-4.2 l 2.368,0.375 0.987,0.156 0.157,-0.988 0.375,-2.368 c 1.261,0.127 2.613,0.743 3.862,1.706 0.118,-0.337 0.244,-0.663 0.382,-0.967 -1.551,-1.135 -3.223,-1.763 -4.73,-1.763 -0.123,0 -0.245,0.004 -0.366,0.013 l -0.511,3.223 -3.224,-0.511 c -0.6,1.487 -0.565,3.415 0.085,5.393 0.335,-0.037 0.684,-0.061 1.047,-0.069 z m 14.501,-5.319 c 1.248,-0.962 2.6,-1.578 3.86,-1.705 l 0.376,2.368 0.156,0.988 0.987,-0.157 2.369,-0.376 c 0.266,1.23 0.098,2.71 -0.432,4.2 0.361,0.009 0.711,0.032 1.046,0.07 0.651,-1.978 0.685,-3.906 0.085,-5.394 l -3.225,0.512 -0.511,-3.224 c -0.12,-0.008 -0.242,-0.012 -0.365,-0.012 -1.507,0 -3.179,0.628 -4.73,1.762 0.14,0.306 0.266,0.631 0.384,0.968 z m -14.225,21.641 h 0.035 c 0.067,0 0.157,-0.604 0.26,-0.947 -0.098,0.004 -0.197,0.046 -0.294,0.046 -1.496,0 -2.826,-0.303 -3.83,-0.89 l 1.089,-2.128 0.454,-0.887 -0.891,-0.452 -2.136,-1.088 c 0.508,-1.151 1.515,-2.25 2.818,-3.143 -0.287,-0.219 -0.561,-0.441 -0.81,-0.669 -1.687,1.217 -2.846,2.755 -3.235,4.31 l 2.908,1.483 -1.482,2.843 c 1.221,1.023 3.049,1.522 5.114,1.522 z m 27.806,-5.846 c -0.39,-1.555 -1.548,-3.093 -3.234,-4.311 -0.25,0.228 -0.523,0.451 -0.81,0.669 1.304,0.893 2.31,1.992 2.817,3.145 l -2.136,1.088 -0.891,0.453 0.454,0.892 1.089,2.137 c -1.004,0.587 -2.332,0.904 -3.828,0.904 -0.099,0 -0.199,-0.01 -0.299,-0.013 0.103,0.344 0.192,0.683 0.26,1.011 l 0.039,0.002 c 2.066,0 3.892,-0.563 5.112,-1.587 l -1.482,-2.908 z m -12.653,9.182 c -0.447,1.5170001 -1.181,2.8120001 -2.119,3.6510001 l -1.695,-1.694 -0.707,-0.707 -0.707,0.707 -1.695,1.694 c -0.938,-0.839 -1.673,-2.136 -2.12,-3.6520001 -0.296,0.2060001 -0.593,0.3970001 -0.886,0.5630001 0.636,1.98 1.741,3.559 3.1,4.409 l 2.308,-2.307 2.308,2.308 c 1.358,-0.851 2.464,-2.428 3.101,-4.408 -0.295,-0.168 -0.591,-0.359 -0.888,-0.5640001 z"
fill="#ea596e"
id="path4-3" />
<path
fill="#ea596e"
d="m 56.41233,-31.002714 c 0.426,1.146 0.748,2.596 0.841,4.284 l 0.2,3.683 3.564,-0.946 c 1.32,-0.351 2.655,-0.536 3.86,-0.536 0.16,0 0.318,0.003 0.474,0.01 l -1.827,2.819 3.139,1.211 c -0.958,0.759 -2.237,1.514 -3.814,2.123 l -3.441,1.328 2.001,3.099 c 0.918,1.42 1.509,2.782 1.838,3.96 l -3.244,-0.865 -0.182,3.357 c -1.019,-0.677 -2.132,-1.66 -3.198,-2.973 l -2.329,-2.863 -2.328,2.862 c -1.066,1.312 -2.179,2.295 -3.198,2.972 l -0.18,-3.354 -3.248,0.864 c 0.329,-1.178 0.921,-2.54 1.839,-3.961 l 2.004,-3.099 -3.442,-1.328 c -1.577,-0.609 -2.856,-1.363 -3.814,-2.122 l 3.135,-1.208 -1.827,-2.823 c 0.155,-0.006 0.313,-0.01 0.473,-0.01 1.206,0 2.541,0.185 3.861,0.536 l 3.564,0.947 0.202,-3.683 c 0.092,-1.688 0.415,-3.138 0.84,-4.284 l 2.119,2.609 2.118,-2.609 m 0.19,-4.991 -2.308,2.841 -2.308,-2.841 c -1.989,1.532 -3.421,4.992 -3.646,9.112 -1.617,-0.43 -3.192,-0.637 -4.632,-0.637 -2.11,0 -3.929,0.445 -5.161,1.289 l 1.989,3.073 -3.415,1.316 c 0.842,2.366 3.69,4.797 7.54,6.283 -2.241,3.465 -3.116,7.106 -2.407,9.5160001 l 3.537,-0.9410001 0.196,3.6540001 c 2.512,-0.07 5.703,-2.027 8.307,-5.2280001 2.603,3.2010001 5.796,5.1580001 8.306,5.2280001 l 0.198,-3.6550001 3.535,0.9430001 c 0.71,-2.4110001 -0.165,-6.0500001 -2.404,-9.5170001 3.849,-1.485 6.696,-3.918 7.538,-6.283 l -3.415,-1.318 1.99,-3.07 c -1.233,-0.844 -3.053,-1.29 -5.164,-1.29 -1.438,0 -3.013,0.207 -4.63,0.636 -0.225,-4.119 -1.657,-7.579 -3.646,-9.111 z"
id="path6-6" />
</g>
<text
xml:space="preserve"
style="font-style:normal;font-weight:normal;font-size:42.6667px;line-height:1.25;font-family:sans-serif;fill:#ea596e;fill-opacity:1;stroke:none"
x="2.2188232"
y="31.430677"
id="text46212"><tspan
sodipodi:role="line"
id="tspan46210"
x="2.2188232"
y="31.430677"
style="font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;font-size:42.6667px;font-family:'TeX Gyre Termes';-inkscape-font-specification:'TeX Gyre Termes'">D</tspan></text>
<text
xml:space="preserve"
style="font-style:normal;font-weight:normal;font-size:42.6667px;line-height:1.25;font-family:sans-serif;fill:#ea596e;fill-opacity:1;stroke:none"
x="41.347008"
y="67.114784"
id="text46212-1"><tspan
sodipodi:role="line"
id="tspan46210-5"
x="41.347008"
y="67.114784"
style="font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;font-size:42.6667px;font-family:'TeX Gyre Termes';-inkscape-font-specification:'TeX Gyre Termes'">F</tspan></text>
</svg>

Before

Width:  |  Height:  |  Size: 12 KiB

Binary file not shown.

Before

Width:  |  Height:  |  Size: 129 KiB

Binary file not shown.

Before

Width:  |  Height:  |  Size: 13 KiB

Binary file not shown.

Before

Width:  |  Height:  |  Size: 88 KiB

Binary file not shown.

Before

Width:  |  Height:  |  Size: 30 KiB

View file

@ -1,537 +0,0 @@
<?xml version="1.0" encoding="UTF-8" standalone="no"?>
<svg
width="850"
height="480"
viewBox="0 0 224.89584 127"
version="1.1"
id="svg8"
inkscape:version="1.2 (dc2aedaf03, 2022-05-15)"
sodipodi:docname="garage_tables.svg"
xmlns:inkscape="http://www.inkscape.org/namespaces/inkscape"
xmlns:sodipodi="http://sodipodi.sourceforge.net/DTD/sodipodi-0.dtd"
xmlns="http://www.w3.org/2000/svg"
xmlns:svg="http://www.w3.org/2000/svg"
xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#"
xmlns:cc="http://creativecommons.org/ns#"
xmlns:dc="http://purl.org/dc/elements/1.1/">
<defs
id="defs2">
<marker
style="overflow:visible"
id="marker1262"
refX="0"
refY="0"
orient="auto"
inkscape:stockid="Arrow1Mend"
inkscape:isstock="true">
<path
transform="matrix(-0.4,0,0,-0.4,-4,0)"
style="fill:#000000;fill-opacity:1;fill-rule:evenodd;stroke:#000000;stroke-width:1pt;stroke-opacity:1"
d="M 0,0 5,-5 -12.5,0 5,5 Z"
id="path1260" />
</marker>
<marker
style="overflow:visible"
id="Arrow1Mend"
refX="0"
refY="0"
orient="auto"
inkscape:stockid="Arrow1Mend"
inkscape:isstock="true"
inkscape:collect="always">
<path
transform="matrix(-0.4,0,0,-0.4,-4,0)"
style="fill:#000000;fill-opacity:1;fill-rule:evenodd;stroke:#000000;stroke-width:1pt;stroke-opacity:1"
d="M 0,0 5,-5 -12.5,0 5,5 Z"
id="path965" />
</marker>
<marker
style="overflow:visible"
id="Arrow1Lend"
refX="0"
refY="0"
orient="auto"
inkscape:stockid="Arrow1Lend"
inkscape:isstock="true">
<path
transform="matrix(-0.8,0,0,-0.8,-10,0)"
style="fill:#000000;fill-opacity:1;fill-rule:evenodd;stroke:#000000;stroke-width:1pt;stroke-opacity:1"
d="M 0,0 5,-5 -12.5,0 5,5 Z"
id="path959" />
</marker>
</defs>
<sodipodi:namedview
id="base"
pagecolor="#ffffff"
bordercolor="#666666"
borderopacity="1.0"
inkscape:pageopacity="0.0"
inkscape:pageshadow="2"
inkscape:zoom="0.98994949"
inkscape:cx="429.31483"
inkscape:cy="289.40871"
inkscape:document-units="mm"
inkscape:current-layer="layer1"
inkscape:document-rotation="0"
showgrid="false"
units="px"
inkscape:window-width="1678"
inkscape:window-height="993"
inkscape:window-x="0"
inkscape:window-y="0"
inkscape:window-maximized="1"
inkscape:showpageshadow="2"
inkscape:pagecheckerboard="0"
inkscape:deskcolor="#d1d1d1" />
<metadata
id="metadata5">
<rdf:RDF>
<cc:Work
rdf:about="">
<dc:format>image/svg+xml</dc:format>
<dc:type
rdf:resource="http://purl.org/dc/dcmitype/StillImage" />
<dc:title />
</cc:Work>
</rdf:RDF>
</metadata>
<g
inkscape:label="Layer 1"
inkscape:groupmode="layer"
id="layer1">
<text
xml:space="preserve"
style="font-style:normal;font-weight:normal;font-size:5.64444px;line-height:1.25;font-family:sans-serif;fill:#000000;fill-opacity:1;stroke:none;stroke-width:0.264583"
x="39.570904"
y="38.452755"
id="text2025"><tspan
sodipodi:role="line"
id="tspan2023"
x="39.570904"
y="38.452755"
style="font-size:5.64444px;stroke-width:0.264583" /></text>
<text
xml:space="preserve"
style="font-style:normal;font-weight:normal;font-size:10.5833px;line-height:1.25;font-family:sans-serif;fill:#000000;fill-opacity:1;stroke:none;stroke-width:0.264583"
x="101.95796"
y="92.835831"
id="text2139"><tspan
sodipodi:role="line"
id="tspan2137"
x="101.95796"
y="92.835831"
style="stroke-width:0.264583"> </tspan></text>
<g
id="g2316"
transform="translate(-11.455511,1.5722486)">
<g
id="g2277">
<rect
style="fill:none;stroke:#000000;stroke-width:0.8;stroke-miterlimit:4;stroke-dasharray:none;stroke-dashoffset:0;stroke-opacity:1"
id="rect833"
width="47.419891"
height="95.353409"
x="18.534418"
y="24.42766" />
<rect
style="fill:none;stroke:#000000;stroke-width:0.799999;stroke-miterlimit:4;stroke-dasharray:none;stroke-dashoffset:0;stroke-opacity:1"
id="rect833-3"
width="47.419891"
height="86.973076"
x="18.534418"
y="32.807987" />
<text
xml:space="preserve"
style="font-style:normal;font-weight:normal;font-size:5.64444px;line-height:1.25;font-family:sans-serif;fill:#000000;fill-opacity:1;stroke:none;stroke-width:0.264583"
x="32.250839"
y="29.894743"
id="text852"><tspan
sodipodi:role="line"
id="tspan850"
x="32.250839"
y="29.894743"
style="font-style:normal;font-variant:normal;font-weight:bold;font-stretch:normal;font-size:5.64444px;font-family:'Liberation Mono';-inkscape-font-specification:'Liberation Mono Bold';stroke-width:0.264583">Object</tspan></text>
</g>
<g
id="g2066"
transform="translate(-2.1807817,-3.0621439)">
<g
id="g1969"
transform="matrix(0.12763631,0,0,0.12763631,0.7215051,24.717273)"
style="fill:#ff6600;fill-opacity:1;stroke:none;stroke-opacity:1">
<path
style="fill:#ff6600;fill-opacity:1;stroke:none;stroke-width:0.264583;stroke-opacity:1"
d="m 203.71837,154.80038 c -1.11451,3.75057 -2.45288,5.84095 -5.11132,7.98327 -2.2735,1.83211 -4.66721,2.65982 -8.09339,2.79857 -2.59227,0.10498 -2.92868,0.0577 -5.02863,-0.70611 -3.99215,-1.45212 -7.1627,-4.65496 -8.48408,-8.57046 -1.28374,-3.80398 -0.61478,-8.68216 1.64793,-12.01698 0.87317,-1.28689 3.15089,-3.48326 4.18771,-4.03815 l 0.53332,-28.51234 5.78454,-5.09197 6.95158,6.16704 -3.21112,3.49026 3.17616,3.45499 -3.17616,3.40822 2.98973,3.28645 -3.24843,3.3829 4.49203,4.58395 0.0516,5.69106 c 1.06874,0.64848 3.81974,3.24046 4.69548,4.56257 0.452,0.68241 1.06834,2.0197 1.36962,2.97176 0.62932,1.98864 0.88051,5.785 0.47342,7.15497 z m -10.0406,2.32604 c -0.88184,-3.17515 -4.92402,-3.78864 -6.75297,-1.02492 -0.58328,0.8814 -0.6898,1.28852 -0.58362,2.23056 0.26492,2.35041 2.45434,3.95262 4.60856,3.37255 1.19644,-0.32217 2.39435,-1.44872 2.72875,-2.56621 0.30682,-1.02529 0.30686,-0.9045 -7.9e-4,-2.01198 z"
id="path1971"
sodipodi:nodetypes="ssscsscccccccccccssscsssscc" />
</g>
<text
xml:space="preserve"
style="font-style:normal;font-weight:normal;font-size:5.64444px;line-height:1.25;font-family:sans-serif;fill:#000000;fill-opacity:1;stroke:none;stroke-width:0.264583"
x="28.809687"
y="44.070885"
id="text852-9"><tspan
sodipodi:role="line"
id="tspan850-4"
x="28.809687"
y="44.070885"
style="font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;font-size:5.64444px;font-family:'Liberation Mono';-inkscape-font-specification:'Liberation Mono Bold';stroke-width:0.264583">bucket </tspan></text>
</g>
<g
id="g2066-7"
transform="translate(-2.1807817,6.2627616)">
<g
id="g1969-8"
transform="matrix(0.12763631,0,0,0.12763631,0.7215051,24.717273)"
style="fill:#ff6600;fill-opacity:1;stroke:none;stroke-opacity:1">
<path
style="fill:#4040ff;fill-opacity:1;stroke:none;stroke-width:0.264583;stroke-opacity:1"
d="m 203.71837,154.80038 c -1.11451,3.75057 -2.45288,5.84095 -5.11132,7.98327 -2.2735,1.83211 -4.66721,2.65982 -8.09339,2.79857 -2.59227,0.10498 -2.92868,0.0577 -5.02863,-0.70611 -3.99215,-1.45212 -7.1627,-4.65496 -8.48408,-8.57046 -1.28374,-3.80398 -0.61478,-8.68216 1.64793,-12.01698 0.87317,-1.28689 3.15089,-3.48326 4.18771,-4.03815 l 0.53332,-28.51234 5.78454,-5.09197 6.95158,6.16704 -3.21112,3.49026 3.17616,3.45499 -3.17616,3.40822 2.98973,3.28645 -3.24843,3.3829 4.49203,4.58395 0.0516,5.69106 c 1.06874,0.64848 3.81974,3.24046 4.69548,4.56257 0.452,0.68241 1.06834,2.0197 1.36962,2.97176 0.62932,1.98864 0.88051,5.785 0.47342,7.15497 z m -10.0406,2.32604 c -0.88184,-3.17515 -4.92402,-3.78864 -6.75297,-1.02492 -0.58328,0.8814 -0.6898,1.28852 -0.58362,2.23056 0.26492,2.35041 2.45434,3.95262 4.60856,3.37255 1.19644,-0.32217 2.39435,-1.44872 2.72875,-2.56621 0.30682,-1.02529 0.30686,-0.9045 -7.9e-4,-2.01198 z"
id="path1971-4"
sodipodi:nodetypes="ssscsscccccccccccssscsssscc" />
</g>
<text
xml:space="preserve"
style="font-style:normal;font-weight:normal;font-size:5.64444px;line-height:1.25;font-family:sans-serif;fill:#000000;fill-opacity:1;stroke:none;stroke-width:0.264583"
x="28.809687"
y="44.070885"
id="text852-9-5"><tspan
sodipodi:role="line"
id="tspan850-4-0"
x="28.809687"
y="44.070885"
style="font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;font-size:5.64444px;font-family:'Liberation Mono';-inkscape-font-specification:'Liberation Mono Bold';stroke-width:0.264583">file path </tspan></text>
<path
style="fill:#ff6600;fill-opacity:1;stroke:none;stroke-width:0.0337704;stroke-opacity:1"
d="m 174.20027,104.45585 c -0.14225,0.47871 -0.31308,0.74552 -0.65239,1.01896 -0.29018,0.23384 -0.5957,0.33949 -1.03301,0.3572 -0.33087,0.0134 -0.37381,0.007 -0.64184,-0.0901 -0.50954,-0.18534 -0.91422,-0.59414 -1.08287,-1.0939 -0.16385,-0.48552 -0.0785,-1.10816 0.21033,-1.5338 0.11145,-0.16426 0.40217,-0.44459 0.53451,-0.51542 l 0.0681,-3.639207 0.73832,-0.64992 0.88727,0.787138 -0.40986,0.445484 0.4054,0.440982 -0.4054,0.435013 0.3816,0.41947 -0.41461,0.43178 0.57334,0.58508 0.007,0.72639 c 0.13641,0.0828 0.48753,0.4136 0.59931,0.58235 0.0577,0.0871 0.13636,0.25778 0.17481,0.3793 0.0803,0.25382 0.11239,0.73838 0.0604,0.91323 z m -1.28154,0.29689 c -0.11256,-0.40526 -0.62849,-0.48357 -0.86193,-0.13082 -0.0745,0.1125 -0.088,0.16447 -0.0745,0.2847 0.0338,0.3 0.31326,0.5045 0.58822,0.43046 0.15271,-0.0411 0.30561,-0.1849 0.34829,-0.32754 0.0392,-0.13086 0.0392,-0.11544 -1e-4,-0.2568 z"
id="path1971-3"
sodipodi:nodetypes="ssscsscccccccccccssscsssscc" />
<text
xml:space="preserve"
style="font-style:normal;font-weight:normal;font-size:5.64444px;line-height:1.25;font-family:sans-serif;fill:#000000;fill-opacity:1;stroke:none;stroke-width:0.264583"
x="177.8474"
y="104.05132"
id="text852-9-6"><tspan
sodipodi:role="line"
id="tspan850-4-7"
x="177.8474"
y="104.05132"
style="font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;font-size:5.64444px;font-family:'Liberation Mono';-inkscape-font-specification:'Liberation Mono Bold';stroke-width:0.264583">= partition key </tspan></text>
<path
style="fill:#4040ff;fill-opacity:1;stroke:none;stroke-width:0.0337704;stroke-opacity:1"
d="m 174.20027,113.78076 c -0.14225,0.47871 -0.31308,0.74552 -0.65239,1.01895 -0.29018,0.23385 -0.5957,0.33949 -1.03301,0.3572 -0.33087,0.0134 -0.37381,0.007 -0.64184,-0.0901 -0.50954,-0.18534 -0.91422,-0.59414 -1.08287,-1.0939 -0.16385,-0.48553 -0.0785,-1.10816 0.21033,-1.53381 0.11145,-0.16425 0.40217,-0.44459 0.53451,-0.51541 l 0.0681,-3.63921 0.73832,-0.64992 0.88727,0.78714 -0.40986,0.44548 0.4054,0.44098 -0.4054,0.43502 0.3816,0.41947 -0.41461,0.43178 0.57334,0.58508 0.007,0.72638 c 0.13641,0.0828 0.48753,0.4136 0.59931,0.58235 0.0577,0.0871 0.13636,0.25779 0.17481,0.37931 0.0803,0.25382 0.11239,0.73837 0.0604,0.91323 z m -1.28154,0.29689 c -0.11256,-0.40527 -0.62849,-0.48357 -0.86193,-0.13082 -0.0745,0.1125 -0.088,0.16446 -0.0745,0.2847 0.0338,0.3 0.31326,0.5045 0.58822,0.43046 0.15271,-0.0411 0.30561,-0.18491 0.34829,-0.32754 0.0392,-0.13087 0.0392,-0.11545 -1e-4,-0.2568 z"
id="path1971-4-5"
sodipodi:nodetypes="ssscsscccccccccccssscsssscc" />
<text
xml:space="preserve"
style="font-style:normal;font-weight:normal;font-size:5.64444px;line-height:1.25;font-family:sans-serif;fill:#000000;fill-opacity:1;stroke:none;stroke-width:0.264583"
x="177.8474"
y="113.37622"
id="text852-9-5-3"><tspan
sodipodi:role="line"
id="tspan850-4-0-5"
x="177.8474"
y="113.37622"
style="font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;font-size:5.64444px;font-family:'Liberation Mono';-inkscape-font-specification:'Liberation Mono Bold';stroke-width:0.264583">= sort key </tspan></text>
</g>
<g
id="g2161"
transform="translate(-62.264403,-59.333115)">
<g
id="g2271"
transform="translate(0,67.042823)">
<rect
style="fill:none;stroke:#000000;stroke-width:0.799999;stroke-miterlimit:4;stroke-dasharray:none;stroke-dashoffset:0;stroke-opacity:1"
id="rect833-6"
width="39.008453"
height="16.775949"
x="84.896881"
y="90.266838" />
<rect
style="fill:none;stroke:#000000;stroke-width:0.799999;stroke-miterlimit:4;stroke-dasharray:none;stroke-dashoffset:0;stroke-opacity:1"
id="rect833-3-1"
width="39.008453"
height="8.673645"
x="84.896881"
y="98.369141" />
<text
xml:space="preserve"
style="font-style:normal;font-weight:normal;font-size:5.64444px;line-height:1.25;font-family:sans-serif;fill:#000000;fill-opacity:1;stroke:none;stroke-width:0.264583"
x="89.826942"
y="96.212921"
id="text852-0"><tspan
sodipodi:role="line"
id="tspan850-6"
x="89.826942"
y="96.212921"
style="font-style:normal;font-variant:normal;font-weight:bold;font-stretch:normal;font-size:5.64444px;font-family:'Liberation Mono';-inkscape-font-specification:'Liberation Mono Bold';stroke-width:0.264583">Version 1</tspan></text>
<text
xml:space="preserve"
style="font-style:normal;font-weight:normal;font-size:5.64444px;line-height:1.25;font-family:sans-serif;fill:#000000;fill-opacity:1;stroke:none;stroke-width:0.264583"
x="89.826942"
y="104.71013"
id="text852-0-3"><tspan
sodipodi:role="line"
id="tspan850-6-2"
x="89.826942"
y="104.71013"
style="font-style:italic;font-variant:normal;font-weight:normal;font-stretch:normal;font-size:5.64444px;font-family:'Liberation Mono';-inkscape-font-specification:'Liberation Mono Bold';fill:#4d4d4d;stroke-width:0.264583">deleted</tspan></text>
</g>
</g>
<g
id="g2263"
transform="translate(0,-22.791204)">
<g
id="g2161-1"
transform="translate(-62.264403,-10.910843)">
<rect
style="fill:none;stroke:#000000;stroke-width:0.799999;stroke-miterlimit:4;stroke-dasharray:none;stroke-dashoffset:0;stroke-opacity:1"
id="rect833-6-5"
width="39.008453"
height="36.749603"
x="84.896881"
y="90.266838" />
<rect
style="fill:none;stroke:#000000;stroke-width:0.799999;stroke-miterlimit:4;stroke-dasharray:none;stroke-dashoffset:0;stroke-opacity:1"
id="rect833-3-1-5"
width="39.008453"
height="28.647301"
x="84.896881"
y="98.369141" />
<text
xml:space="preserve"
style="font-style:normal;font-weight:normal;font-size:5.64444px;line-height:1.25;font-family:sans-serif;fill:#000000;fill-opacity:1;stroke:none;stroke-width:0.264583"
x="89.826942"
y="96.212921"
id="text852-0-4"><tspan
sodipodi:role="line"
id="tspan850-6-7"
x="89.826942"
y="96.212921"
style="font-style:normal;font-variant:normal;font-weight:bold;font-stretch:normal;font-size:5.64444px;font-family:'Liberation Mono';-inkscape-font-specification:'Liberation Mono Bold';stroke-width:0.264583">Version 2</tspan></text>
<text
xml:space="preserve"
style="font-style:normal;font-weight:normal;font-size:5.64444px;line-height:1.25;font-family:sans-serif;fill:#000000;fill-opacity:1;stroke:none;stroke-width:0.264583"
x="89.826942"
y="104.71013"
id="text852-0-3-6"><tspan
sodipodi:role="line"
id="tspan850-6-2-5"
x="89.826942"
y="104.71013"
style="font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;font-size:5.64444px;font-family:'Liberation Mono';-inkscape-font-specification:'Liberation Mono Bold';fill:#000000;stroke-width:0.264583">id</tspan></text>
</g>
<text
xml:space="preserve"
style="font-style:normal;font-weight:normal;font-size:5.64444px;line-height:1.25;font-family:sans-serif;fill:#000000;fill-opacity:1;stroke:none;stroke-width:0.264583"
x="27.56254"
y="100.34132"
id="text852-0-3-6-6"><tspan
sodipodi:role="line"
id="tspan850-6-2-5-9"
x="27.56254"
y="100.34132"
style="font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;font-size:5.64444px;font-family:'Liberation Mono';-inkscape-font-specification:'Liberation Mono Bold';fill:#000000;stroke-width:0.264583">size</tspan></text>
<text
xml:space="preserve"
style="font-style:normal;font-weight:normal;font-size:5.64444px;line-height:1.25;font-family:sans-serif;fill:#000000;fill-opacity:1;stroke:none;stroke-width:0.264583"
x="27.56254"
y="106.90263"
id="text852-0-3-6-6-3"><tspan
sodipodi:role="line"
id="tspan850-6-2-5-9-7"
x="27.56254"
y="106.90263"
style="font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;font-size:5.64444px;font-family:'Liberation Mono';-inkscape-font-specification:'Liberation Mono Bold';fill:#000000;stroke-width:0.264583">MIME type</tspan></text>
<text
xml:space="preserve"
style="font-style:normal;font-weight:normal;font-size:5.64444px;line-height:1.25;font-family:sans-serif;fill:#000000;fill-opacity:1;stroke:none;stroke-width:0.264583"
x="27.56254"
y="111.92816"
id="text852-0-3-6-6-3-4"><tspan
sodipodi:role="line"
id="tspan850-6-2-5-9-7-5"
x="27.56254"
y="111.92816"
style="font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;font-size:5.64444px;font-family:'Liberation Mono';-inkscape-font-specification:'Liberation Mono Bold';fill:#000000;stroke-width:0.264583">...</tspan></text>
</g>
</g>
<g
id="g898"
transform="translate(-6.2484318,29.95006)">
<rect
style="fill:none;stroke:#000000;stroke-width:0.799999;stroke-miterlimit:4;stroke-dasharray:none;stroke-dashoffset:0;stroke-opacity:1"
id="rect833-7"
width="47.419891"
height="44.007515"
x="95.443573"
y="24.42766" />
<rect
style="fill:none;stroke:#000000;stroke-width:0.799999;stroke-miterlimit:4;stroke-dasharray:none;stroke-dashoffset:0;stroke-opacity:1"
id="rect833-3-4"
width="47.419891"
height="35.627186"
x="95.443573"
y="32.807987" />
<text
xml:space="preserve"
style="font-style:normal;font-weight:normal;font-size:5.64444px;line-height:1.25;font-family:sans-serif;fill:#000000;fill-opacity:1;stroke:none;stroke-width:0.264583"
x="107.46638"
y="29.894743"
id="text852-4"><tspan
sodipodi:role="line"
id="tspan850-3"
x="107.46638"
y="29.894743"
style="font-style:normal;font-variant:normal;font-weight:bold;font-stretch:normal;font-size:5.64444px;font-family:'Liberation Mono';-inkscape-font-specification:'Liberation Mono Bold';stroke-width:0.264583">Version</tspan></text>
<path
style="fill:#ff6600;fill-opacity:1;stroke:none;stroke-width:0.0337704;stroke-opacity:1"
d="m 102.90563,41.413279 c -0.14226,0.478709 -0.31308,0.745518 -0.65239,1.018956 -0.29019,0.233843 -0.59571,0.339489 -1.03301,0.357199 -0.33087,0.0134 -0.37381,0.0074 -0.64184,-0.09013 -0.50954,-0.185343 -0.914221,-0.594142 -1.082877,-1.093901 -0.163852,-0.485526 -0.07847,-1.108159 0.210335,-1.533803 0.111448,-0.164254 0.402172,-0.444591 0.534502,-0.515415 l 0.0681,-3.63921 0.73832,-0.64992 0.88727,0.787138 -0.40985,0.445484 0.40539,0.440982 -0.40539,0.435013 0.3816,0.41947 -0.41462,0.431781 0.57335,0.585078 0.007,0.726386 c 0.13641,0.08277 0.48753,0.413601 0.59931,0.58235 0.0577,0.0871 0.13636,0.257787 0.17481,0.379304 0.0803,0.253823 0.11239,0.738377 0.0604,0.913234 z m -1.28155,0.296888 c -0.11255,-0.405265 -0.62848,-0.483569 -0.86192,-0.130817 -0.0744,0.112498 -0.088,0.164461 -0.0745,0.2847 0.0338,0.299998 0.31326,0.504498 0.58822,0.43046 0.15271,-0.04112 0.3056,-0.184909 0.34828,-0.327542 0.0392,-0.130864 0.0392,-0.115447 -1e-4,-0.256801 z"
id="path1971-0"
sodipodi:nodetypes="ssscsscccccccccccssscsssscc" />
<text
xml:space="preserve"
style="font-style:normal;font-weight:normal;font-size:5.64444px;line-height:1.25;font-family:sans-serif;fill:#000000;fill-opacity:1;stroke:none;stroke-width:0.264583"
x="104.99195"
y="41.008743"
id="text852-9-7"><tspan
sodipodi:role="line"
id="tspan850-4-8"
x="104.99195"
y="41.008743"
style="font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;font-size:5.64444px;font-family:'Liberation Mono';-inkscape-font-specification:'Liberation Mono Bold';stroke-width:0.264583">id </tspan></text>
<text
xml:space="preserve"
style="font-style:normal;font-weight:normal;font-size:5.64444px;line-height:1.25;font-family:sans-serif;fill:#000000;fill-opacity:1;stroke:none;stroke-width:0.264583"
x="104.99195"
y="49.168018"
id="text852-9-7-6"><tspan
sodipodi:role="line"
id="tspan850-4-8-8"
x="104.99195"
y="49.168018"
style="font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;font-size:5.64444px;font-family:'Liberation Mono';-inkscape-font-specification:'Liberation Mono Bold';stroke-width:0.264583">h(block 1)</tspan></text>
<text
xml:space="preserve"
style="font-style:normal;font-weight:normal;font-size:5.64444px;line-height:1.25;font-family:sans-serif;fill:#000000;fill-opacity:1;stroke:none;stroke-width:0.264583"
x="104.99195"
y="56.583336"
id="text852-9-7-6-8"><tspan
sodipodi:role="line"
id="tspan850-4-8-8-4"
x="104.99195"
y="56.583336"
style="font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;font-size:5.64444px;font-family:'Liberation Mono';-inkscape-font-specification:'Liberation Mono Bold';stroke-width:0.264583">h(block 2)</tspan></text>
<text
xml:space="preserve"
style="font-style:normal;font-weight:normal;font-size:5.64444px;line-height:1.25;font-family:sans-serif;fill:#000000;fill-opacity:1;stroke:none;stroke-width:0.264583"
x="104.99195"
y="64.265732"
id="text852-9-7-6-3"><tspan
sodipodi:role="line"
id="tspan850-4-8-8-1"
x="104.99195"
y="64.265732"
style="font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;font-size:5.64444px;font-family:'Liberation Mono';-inkscape-font-specification:'Liberation Mono Bold';stroke-width:0.264583">...</tspan></text>
</g>
<g
id="g898-3"
transform="translate(75.777779,38.888663)">
<rect
style="fill:none;stroke:#000000;stroke-width:0.799999;stroke-miterlimit:4;stroke-dasharray:none;stroke-dashoffset:0;stroke-opacity:1"
id="rect833-7-6"
width="47.419891"
height="29.989157"
x="95.443573"
y="24.42766" />
<rect
style="fill:none;stroke:#000000;stroke-width:0.799999;stroke-miterlimit:4;stroke-dasharray:none;stroke-dashoffset:0;stroke-opacity:1"
id="rect833-3-4-7"
width="47.419891"
height="21.608831"
x="95.443573"
y="32.807987" />
<text
xml:space="preserve"
style="font-style:normal;font-weight:normal;font-size:5.64444px;line-height:1.25;font-family:sans-serif;fill:#000000;fill-opacity:1;stroke:none;stroke-width:0.264583"
x="102.11134"
y="29.894743"
id="text852-4-5"><tspan
sodipodi:role="line"
id="tspan850-3-3"
x="102.11134"
y="29.894743"
style="font-style:normal;font-variant:normal;font-weight:bold;font-stretch:normal;font-size:5.64444px;font-family:'Liberation Mono';-inkscape-font-specification:'Liberation Mono Bold';stroke-width:0.264583">Data block</tspan></text>
<path
style="fill:#ff6600;fill-opacity:1;stroke:none;stroke-width:0.0337704;stroke-opacity:1"
d="m 102.90563,41.413279 c -0.14226,0.478709 -0.31308,0.745518 -0.65239,1.018956 -0.29019,0.233843 -0.59571,0.339489 -1.03301,0.357199 -0.33087,0.0134 -0.37381,0.0074 -0.64184,-0.09013 -0.50954,-0.185343 -0.914221,-0.594142 -1.082877,-1.093901 -0.163852,-0.485526 -0.07847,-1.108159 0.210335,-1.533803 0.111448,-0.164254 0.402172,-0.444591 0.534502,-0.515415 l 0.0681,-3.63921 0.73832,-0.64992 0.88727,0.787138 -0.40985,0.445484 0.40539,0.440982 -0.40539,0.435013 0.3816,0.41947 -0.41462,0.431781 0.57335,0.585078 0.007,0.726386 c 0.13641,0.08277 0.48753,0.413601 0.59931,0.58235 0.0577,0.0871 0.13636,0.257787 0.17481,0.379304 0.0803,0.253823 0.11239,0.738377 0.0604,0.913234 z m -1.28155,0.296888 c -0.11255,-0.405265 -0.62848,-0.483569 -0.86192,-0.130817 -0.0744,0.112498 -0.088,0.164461 -0.0745,0.2847 0.0338,0.299998 0.31326,0.504498 0.58822,0.43046 0.15271,-0.04112 0.3056,-0.184909 0.34828,-0.327542 0.0392,-0.130864 0.0392,-0.115447 -1e-4,-0.256801 z"
id="path1971-0-5"
sodipodi:nodetypes="ssscsscccccccccccssscsssscc" />
<text
xml:space="preserve"
style="font-style:normal;font-weight:normal;font-size:5.64444px;line-height:1.25;font-family:sans-serif;fill:#000000;fill-opacity:1;stroke:none;stroke-width:0.264583"
x="104.99195"
y="41.008743"
id="text852-9-7-62"><tspan
sodipodi:role="line"
id="tspan850-4-8-9"
x="104.99195"
y="41.008743"
style="font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;font-size:5.64444px;font-family:'Liberation Mono';-inkscape-font-specification:'Liberation Mono Bold';stroke-width:0.264583">hash </tspan></text>
<text
xml:space="preserve"
style="font-style:normal;font-weight:normal;font-size:5.64444px;line-height:1.25;font-family:sans-serif;fill:#000000;fill-opacity:1;stroke:none;stroke-width:0.264583"
x="104.99195"
y="49.168018"
id="text852-9-7-6-1"><tspan
sodipodi:role="line"
id="tspan850-4-8-8-2"
x="104.99195"
y="49.168018"
style="font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;font-size:5.64444px;font-family:'Liberation Mono';-inkscape-font-specification:'Liberation Mono Bold';stroke-width:0.264583">data</tspan></text>
</g>
<path
style="fill:none;stroke:#000000;stroke-width:1;stroke-linecap:butt;stroke-linejoin:miter;stroke-miterlimit:4;stroke-dasharray:none;stroke-opacity:1;marker-end:url(#Arrow1Mend)"
d="M 42.105292,69.455903 89.563703,69.317144"
id="path954"
sodipodi:nodetypes="cc" />
<path
style="fill:none;stroke:#000000;stroke-width:1;stroke-linecap:butt;stroke-linejoin:miter;stroke-miterlimit:4;stroke-dasharray:none;stroke-opacity:1;marker-end:url(#marker1262)"
d="m 134.32612,77.363197 38.12618,0.260865"
id="path1258"
sodipodi:nodetypes="cc" />
<text
xml:space="preserve"
style="font-style:normal;font-weight:normal;font-size:5.64444px;line-height:1.25;font-family:sans-serif;fill:#000000;fill-opacity:1;stroke:none;stroke-width:0.264583"
x="8.6727352"
y="16.687063"
id="text852-3"><tspan
sodipodi:role="line"
id="tspan850-67"
x="8.6727352"
y="16.687063"
style="font-style:normal;font-variant:normal;font-weight:bold;font-stretch:normal;font-size:5.64444px;font-family:'Liberation Mono';-inkscape-font-specification:'Liberation Mono Bold';stroke-width:0.264583">Objects table </tspan></text>
<text
xml:space="preserve"
style="font-style:normal;font-weight:normal;font-size:5.64444px;line-height:1.25;font-family:sans-serif;fill:#000000;fill-opacity:1;stroke:none;stroke-width:0.264583"
x="89.190445"
y="16.687063"
id="text852-3-5"><tspan
sodipodi:role="line"
id="tspan850-67-3"
x="89.190445"
y="16.687063"
style="font-style:normal;font-variant:normal;font-weight:bold;font-stretch:normal;font-size:5.64444px;font-family:'Liberation Mono';-inkscape-font-specification:'Liberation Mono Bold';stroke-width:0.264583">Versions table </tspan></text>
<text
xml:space="preserve"
style="font-style:normal;font-weight:normal;font-size:5.64444px;line-height:1.25;font-family:sans-serif;fill:#000000;fill-opacity:1;stroke:none;stroke-width:0.264583"
x="174.55702"
y="16.687063"
id="text852-3-56"><tspan
sodipodi:role="line"
id="tspan850-67-2"
x="174.55702"
y="16.687063"
style="font-style:normal;font-variant:normal;font-weight:bold;font-stretch:normal;font-size:5.64444px;font-family:'Liberation Mono';-inkscape-font-specification:'Liberation Mono Bold';stroke-width:0.264583">Blocks table</tspan></text>
</g>
</svg>

Before

Width:  |  Height:  |  Size: 30 KiB

View file

@ -1,433 +0,0 @@
<?xml version="1.0" encoding="UTF-8" standalone="no"?>
<!-- Created with Inkscape (http://www.inkscape.org/) -->
<svg
width="1000"
height="400"
viewBox="0 0 264.58333 105.83333"
version="1.1"
id="svg5"
inkscape:version="1.2.2 (b0a8486541, 2022-12-01)"
sodipodi:docname="lattice1.svg"
xmlns:inkscape="http://www.inkscape.org/namespaces/inkscape"
xmlns:sodipodi="http://sodipodi.sourceforge.net/DTD/sodipodi-0.dtd"
xmlns="http://www.w3.org/2000/svg"
xmlns:svg="http://www.w3.org/2000/svg">
<sodipodi:namedview
id="namedview7"
pagecolor="#ffffff"
bordercolor="#666666"
borderopacity="1.0"
inkscape:showpageshadow="2"
inkscape:pageopacity="0.0"
inkscape:pagecheckerboard="0"
inkscape:deskcolor="#d1d1d1"
inkscape:document-units="mm"
showgrid="false"
inkscape:zoom="1.0419012"
inkscape:cx="445.81962"
inkscape:cy="222.66987"
inkscape:window-width="1920"
inkscape:window-height="999"
inkscape:window-x="0"
inkscape:window-y="0"
inkscape:window-maximized="1"
inkscape:current-layer="layer2" />
<defs
id="defs2">
<marker
style="overflow:visible"
id="Arrow2"
refX="0"
refY="0"
orient="auto-start-reverse"
inkscape:stockid="Arrow2"
markerWidth="7.6999998"
markerHeight="5.5999999"
viewBox="0 0 7.7 5.6"
inkscape:isstock="true"
inkscape:collect="always"
preserveAspectRatio="xMidYMid">
<path
transform="scale(0.7)"
d="M -2,-4 9,0 -2,4 c 2,-2.33 2,-5.66 0,-8 z"
style="fill:context-stroke;fill-rule:evenodd;stroke:none"
id="arrow2L" />
</marker>
<marker
style="overflow:visible"
id="Arrow2-9"
refX="0"
refY="0"
orient="auto-start-reverse"
inkscape:stockid="Arrow2"
markerWidth="7.6999998"
markerHeight="5.5999999"
viewBox="0 0 7.7 5.6"
inkscape:isstock="true"
inkscape:collect="always"
preserveAspectRatio="xMidYMid">
<path
transform="scale(0.7)"
d="M -2,-4 9,0 -2,4 c 2,-2.33 2,-5.66 0,-8 z"
style="fill:context-stroke;fill-rule:evenodd;stroke:none"
id="arrow2L-1" />
</marker>
<marker
style="overflow:visible"
id="Arrow2-9-7"
refX="0"
refY="0"
orient="auto-start-reverse"
inkscape:stockid="Arrow2"
markerWidth="7.6999998"
markerHeight="5.5999999"
viewBox="0 0 7.7 5.6"
inkscape:isstock="true"
inkscape:collect="always"
preserveAspectRatio="xMidYMid">
<path
transform="scale(0.7)"
d="M -2,-4 9,0 -2,4 c 2,-2.33 2,-5.66 0,-8 z"
style="fill:context-stroke;fill-rule:evenodd;stroke:none"
id="arrow2L-1-0" />
</marker>
<marker
style="overflow:visible"
id="Arrow2-93"
refX="0"
refY="0"
orient="auto-start-reverse"
inkscape:stockid="Arrow2"
markerWidth="7.6999998"
markerHeight="5.5999999"
viewBox="0 0 7.7 5.6"
inkscape:isstock="true"
inkscape:collect="always"
preserveAspectRatio="xMidYMid">
<path
transform="scale(0.7)"
d="M -2,-4 9,0 -2,4 c 2,-2.33 2,-5.66 0,-8 z"
style="fill:context-stroke;fill-rule:evenodd;stroke:none"
id="arrow2L-6" />
</marker>
<marker
style="overflow:visible"
id="Arrow2-9-7-2"
refX="0"
refY="0"
orient="auto-start-reverse"
inkscape:stockid="Arrow2"
markerWidth="7.6999998"
markerHeight="5.5999999"
viewBox="0 0 7.7 5.6"
inkscape:isstock="true"
inkscape:collect="always"
preserveAspectRatio="xMidYMid">
<path
transform="scale(0.7)"
d="M -2,-4 9,0 -2,4 c 2,-2.33 2,-5.66 0,-8 z"
style="fill:context-stroke;fill-rule:evenodd;stroke:none"
id="arrow2L-1-0-6" />
</marker>
<marker
style="overflow:visible"
id="Arrow2-93-1"
refX="0"
refY="0"
orient="auto-start-reverse"
inkscape:stockid="Arrow2"
markerWidth="7.6999998"
markerHeight="5.5999999"
viewBox="0 0 7.7 5.6"
inkscape:isstock="true"
inkscape:collect="always"
preserveAspectRatio="xMidYMid">
<path
transform="scale(0.7)"
d="M -2,-4 9,0 -2,4 c 2,-2.33 2,-5.66 0,-8 z"
style="fill:context-stroke;fill-rule:evenodd;stroke:none"
id="arrow2L-6-8" />
</marker>
<marker
style="overflow:visible"
id="Arrow2-9-75"
refX="0"
refY="0"
orient="auto-start-reverse"
inkscape:stockid="Arrow2"
markerWidth="7.6999998"
markerHeight="5.5999999"
viewBox="0 0 7.7 5.6"
inkscape:isstock="true"
inkscape:collect="always"
preserveAspectRatio="xMidYMid">
<path
transform="scale(0.7)"
d="M -2,-4 9,0 -2,4 c 2,-2.33 2,-5.66 0,-8 z"
style="fill:context-stroke;fill-rule:evenodd;stroke:none"
id="arrow2L-1-9" />
</marker>
<marker
style="overflow:visible"
id="Arrow2-9-75-2"
refX="0"
refY="0"
orient="auto-start-reverse"
inkscape:stockid="Arrow2"
markerWidth="7.6999998"
markerHeight="5.5999999"
viewBox="0 0 7.7 5.6"
inkscape:isstock="true"
inkscape:collect="always"
preserveAspectRatio="xMidYMid">
<path
transform="scale(0.7)"
d="M -2,-4 9,0 -2,4 c 2,-2.33 2,-5.66 0,-8 z"
style="fill:context-stroke;fill-rule:evenodd;stroke:none"
id="arrow2L-1-9-8" />
</marker>
<marker
style="overflow:visible"
id="Arrow2-9-75-7"
refX="0"
refY="0"
orient="auto-start-reverse"
inkscape:stockid="Arrow2"
markerWidth="7.6999998"
markerHeight="5.5999999"
viewBox="0 0 7.7 5.6"
inkscape:isstock="true"
inkscape:collect="always"
preserveAspectRatio="xMidYMid">
<path
transform="scale(0.7)"
d="M -2,-4 9,0 -2,4 c 2,-2.33 2,-5.66 0,-8 z"
style="fill:context-stroke;fill-rule:evenodd;stroke:none"
id="arrow2L-1-9-3" />
</marker>
<marker
style="overflow:visible"
id="Arrow2-9-75-7-1"
refX="0"
refY="0"
orient="auto-start-reverse"
inkscape:stockid="Arrow2"
markerWidth="7.6999998"
markerHeight="5.5999999"
viewBox="0 0 7.7 5.6"
inkscape:isstock="true"
inkscape:collect="always"
preserveAspectRatio="xMidYMid">
<path
transform="scale(0.7)"
d="M -2,-4 9,0 -2,4 c 2,-2.33 2,-5.66 0,-8 z"
style="fill:context-stroke;fill-rule:evenodd;stroke:none"
id="arrow2L-1-9-3-2" />
</marker>
<marker
style="overflow:visible"
id="Arrow2-93-1-4"
refX="0"
refY="0"
orient="auto-start-reverse"
inkscape:stockid="Arrow2"
markerWidth="7.6999998"
markerHeight="5.5999999"
viewBox="0 0 7.7 5.6"
inkscape:isstock="true"
inkscape:collect="always"
preserveAspectRatio="xMidYMid">
<path
transform="scale(0.7)"
d="M -2,-4 9,0 -2,4 c 2,-2.33 2,-5.66 0,-8 z"
style="fill:context-stroke;fill-rule:evenodd;stroke:none"
id="arrow2L-6-8-7" />
</marker>
<marker
style="overflow:visible"
id="Arrow2-9-7-2-8"
refX="0"
refY="0"
orient="auto-start-reverse"
inkscape:stockid="Arrow2"
markerWidth="7.6999998"
markerHeight="5.5999999"
viewBox="0 0 7.7 5.6"
inkscape:isstock="true"
inkscape:collect="always"
preserveAspectRatio="xMidYMid">
<path
transform="scale(0.7)"
d="M -2,-4 9,0 -2,4 c 2,-2.33 2,-5.66 0,-8 z"
style="fill:context-stroke;fill-rule:evenodd;stroke:none"
id="arrow2L-1-0-6-4" />
</marker>
</defs>
<g
inkscape:label="Layer 1"
inkscape:groupmode="layer"
id="layer1"
sodipodi:insensitive="true">
<rect
style="fill:#ffffff;stroke:none;stroke-width:1;stop-color:#000000"
id="rect288"
width="209.84705"
height="104.42732"
x="0.77790999"
y="0.93738818" />
</g>
<g
inkscape:groupmode="layer"
id="layer2"
inkscape:label="Layer 2">
<text
xml:space="preserve"
style="font-size:8.46667px;line-height:1.25;font-family:sans-serif;text-align:center;text-anchor:middle;stroke-width:0.264583;fill:#000000"
x="164.56372"
y="99.307442"
id="text951"><tspan
sodipodi:role="line"
id="tspan949"
style="stroke-width:0.264583;fill:#000000"
x="164.56372"
y="99.307442">$\{\}$</tspan></text>
<text
xml:space="preserve"
style="font-size:8.46667px;line-height:1.25;font-family:sans-serif;text-align:center;text-anchor:middle;stroke-width:0.264583;fill:#000000"
x="164.56372"
y="13.151893"
id="text1005"><tspan
sodipodi:role="line"
id="tspan1003"
style="stroke-width:0.264583;fill:#000000"
x="164.56372"
y="13.151893">$\{a,b,c\}$</tspan></text>
<g
id="g1175"
transform="translate(51.996784,3.5774043)">
<text
xml:space="preserve"
style="font-size:8.46667px;line-height:1.25;font-family:sans-serif;text-align:center;text-anchor:middle;stroke-width:0.264583;fill:#000000"
x="49.27084"
y="67.008698"
id="text1009"><tspan
sodipodi:role="line"
id="tspan1007"
style="stroke-width:0.264583;fill:#000000"
x="49.27084"
y="67.008698">$\{a\}$</tspan></text>
<text
xml:space="preserve"
style="font-size:8.46667px;line-height:1.25;font-family:sans-serif;text-align:center;text-anchor:middle;stroke-width:0.264583;fill:#000000"
x="112.90984"
y="67.017166"
id="text1009-3"><tspan
sodipodi:role="line"
id="tspan1007-6"
style="stroke-width:0.264583;fill:#000000"
x="112.90984"
y="67.017166">$\{b\}$</tspan></text>
<text
xml:space="preserve"
style="font-size:8.46667px;line-height:1.25;font-family:sans-serif;text-align:center;text-anchor:middle;stroke-width:0.264583;fill:#000000"
x="176.20593"
y="67.008698"
id="text1009-7"><tspan
sodipodi:role="line"
id="tspan1007-5"
style="stroke-width:0.264583;fill:#000000"
x="176.20593"
y="67.008698">$\{c\}$</tspan></text>
</g>
<g
id="g1183"
transform="translate(51.996784,1.0317046)">
<text
xml:space="preserve"
style="font-size:8.46667px;line-height:1.25;font-family:sans-serif;text-align:center;text-anchor:middle;stroke-width:0.264583;fill:#000000"
x="112.90984"
y="40.841526"
id="text1117"><tspan
sodipodi:role="line"
id="tspan1115"
style="stroke-width:0.264583;fill:#000000"
x="112.90984"
y="40.841526">$\{a,c\}$</tspan></text>
<text
xml:space="preserve"
style="font-size:8.46667px;line-height:1.25;font-family:sans-serif;text-align:center;text-anchor:middle;stroke-width:0.264583;fill:#000000"
x="49.27084"
y="40.841526"
id="text1117-3"><tspan
sodipodi:role="line"
id="tspan1115-5"
style="stroke-width:0.264583;fill:#000000"
x="49.27084"
y="40.841526">$\{a,b\}$</tspan></text>
<text
xml:space="preserve"
style="font-size:8.46667px;line-height:1.25;font-family:sans-serif;text-align:center;text-anchor:middle;stroke-width:0.264583;fill:#000000"
x="176.20593"
y="40.841526"
id="text1117-6"><tspan
sodipodi:role="line"
id="tspan1115-2"
style="stroke-width:0.264583;fill:#000000"
x="176.20593"
y="40.841526">$\{b,c\}$</tspan></text>
</g>
<path
style="fill:none;stroke:#000000;stroke-width:0.5;stroke-linecap:butt;stroke-linejoin:miter;stroke-dasharray:none;stroke-opacity:1;marker-end:url(#Arrow2)"
d="M 153.33622,90.367682 118.34198,73.428915"
id="path1300" />
<path
style="fill:none;stroke:#000000;stroke-width:0.5;stroke-linecap:butt;stroke-linejoin:miter;stroke-dasharray:none;stroke-opacity:1;marker-end:url(#Arrow2-9)"
d="M 177.46016,90.367682 212.4544,73.428915"
id="path1300-2" />
<path
style="fill:none;stroke:#000000;stroke-width:0.5;stroke-linecap:butt;stroke-linejoin:miter;stroke-dasharray:none;stroke-opacity:1;marker-end:url(#Arrow2-93)"
d="M 153.33622,61.655656 118.34198,44.716889"
id="path1300-0" />
<path
style="fill:none;stroke:#000000;stroke-width:0.5;stroke-linecap:butt;stroke-linejoin:miter;stroke-dasharray:none;stroke-opacity:1;marker-end:url(#Arrow2-9-7)"
d="M 177.46016,61.655656 212.4544,44.716889"
id="path1300-2-6" />
<path
style="fill:none;stroke:#000000;stroke-width:0.5;stroke-linecap:butt;stroke-linejoin:miter;stroke-dasharray:none;stroke-opacity:1;marker-end:url(#Arrow2-93-1)"
d="M 118.34198,61.655656 153.33622,44.716889"
id="path1300-0-7" />
<path
style="fill:none;stroke:#000000;stroke-width:0.5;stroke-linecap:butt;stroke-linejoin:miter;stroke-dasharray:none;stroke-opacity:1;marker-end:url(#Arrow2-9-7-2)"
d="M 212.4544,61.655656 177.46016,44.716889"
id="path1300-2-6-9" />
<path
style="fill:none;stroke:#000000;stroke-width:0.5;stroke-linecap:butt;stroke-linejoin:miter;stroke-dasharray:none;stroke-opacity:1;marker-end:url(#Arrow2-93-1-4)"
d="M 118.34198,34.227412 153.33622,17.288645"
id="path1300-0-7-5" />
<path
style="fill:none;stroke:#000000;stroke-width:0.5;stroke-linecap:butt;stroke-linejoin:miter;stroke-dasharray:none;stroke-opacity:1;marker-end:url(#Arrow2-9-7-2-8)"
d="M 212.4544,34.227412 177.46016,17.288645"
id="path1300-2-6-9-0" />
<path
style="fill:none;stroke:#000000;stroke-width:0.5;stroke-linecap:butt;stroke-linejoin:miter;stroke-dasharray:none;stroke-opacity:1;marker-end:url(#Arrow2-9-75)"
d="m 228.52843,61.091809 0.33313,-12.554874 m -0.33313,12.554874 0.33313,-12.554874"
id="path1300-2-2"
sodipodi:nodetypes="cc" />
<path
style="fill:none;stroke:#000000;stroke-width:0.5;stroke-linecap:butt;stroke-linejoin:miter;stroke-dasharray:none;stroke-opacity:1;marker-end:url(#Arrow2-9-75-2)"
d="m 101.90418,61.091809 0.33313,-12.554874 m -0.33313,12.554874 0.33313,-12.554874"
id="path1300-2-2-9"
sodipodi:nodetypes="cc" />
<path
style="fill:none;stroke:#000000;stroke-width:0.5;stroke-linecap:butt;stroke-linejoin:miter;stroke-dasharray:none;stroke-opacity:1;marker-end:url(#Arrow2-9-75-7)"
d="m 165.29305,89.571762 0.33313,-12.554874 m -0.33313,12.554874 0.33313,-12.554874"
id="path1300-2-2-6"
sodipodi:nodetypes="cc" />
<path
style="fill:none;stroke:#000000;stroke-width:0.5;stroke-linecap:butt;stroke-linejoin:miter;stroke-dasharray:none;stroke-opacity:1;marker-end:url(#Arrow2-9-75-7-1)"
d="m 165.29305,32.445235 0.33313,-12.554874 m -0.33313,12.554874 0.33313,-12.554874"
id="path1300-2-2-6-9"
sodipodi:nodetypes="cc" />
</g>
</svg>

Before

Width:  |  Height:  |  Size: 15 KiB

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