rm .gitattributes

corrected a few bugs

.drone.yml

@@ -19,11 +19,9 @@ steps:
   - name: unit + func tests
     image: nixpkgs/nix:nixos-22.05
     environment:
-      GARAGE_TEST_INTEGRATION_EXE: result-bin/bin/garage
+      GARAGE_TEST_INTEGRATION_EXE: result/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-*
@@ -32,7 +30,6 @@ steps:
       - ./result/bin/garage_web-*
       - ./result/bin/garage-*
       - ./result/bin/integration-*
-      - rm result
 
   - name: integration tests
     image: nixpkgs/nix:nixos-22.05
@@ -61,7 +58,7 @@ steps:
     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"
+      - nix-shell --attr rust --run "./script/not-dynamic.sh result/bin/garage"
 
   - name: integration
     image: nixpkgs/nix:nixos-22.05
@@ -112,7 +109,7 @@ steps:
     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"
+      - nix-shell --attr rust --run "./script/not-dynamic.sh result/bin/garage"
 
   - name: integration
     image: nixpkgs/nix:nixos-22.05
@@ -162,7 +159,7 @@ steps:
     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"
+      - nix-shell --attr rust --run "./script/not-dynamic.sh result/bin/garage"
 
   - name: push static binary
     image: nixpkgs/nix:nixos-22.05
@@ -207,7 +204,7 @@ steps:
     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"
+      - nix-shell --attr rust --run "./script/not-dynamic.sh result/bin/garage"
 
   - name: push static binary
     image: nixpkgs/nix:nixos-22.05
@@ -283,6 +280,6 @@ trigger:
 
 ---
 kind: signature
-hmac: ac09a5a8c82502f67271f93afa1e1e21ce66383b8e24a6deb26b285cc1c378ba
+hmac: 103a04785c98f5376a63ce22865c2576963019bbc4d828f200d2a470a3c821ea
 
 ...

.gitattributes

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

Dockerfile

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

default.nix

@@ -8,23 +8,10 @@ with import ./nix/common.nix;
 let 
   pkgs = import pkgsSrc { };
   compile = import ./nix/compile.nix;
-
   build_debug_and_release = (target: {
-    debug = (compile {
+    debug = (compile { inherit target git_version; release = false; }).workspace.garage { compileMode = "build"; }; 
-      inherit target git_version;
+    release = (compile { inherit target git_version; release = true; }).workspace.garage { compileMode = "build"; }; 
-      release = false;
-    }).workspace.garage {
-      compileMode = "build";
-    };
-
-    release = (compile {
-      inherit target git_version;
-      release = true;
-    }).workspace.garage {
-      compileMode = "build";
-    };
   });
-
   test = (rustPkgs: pkgs.symlinkJoin {
     name ="garage-tests";
     paths = builtins.map (key: rustPkgs.workspace.${key} { compileMode = "test"; }) (builtins.attrNames rustPkgs.workspace);
@@ -38,25 +25,9 @@ in {
     arm = build_debug_and_release "armv6l-unknown-linux-musleabihf";
   };
   test = {
-    amd64 = test (compile {
+    amd64 = test (compile { inherit git_version; target = "x86_64-unknown-linux-musl"; });
-      inherit git_version;
-      target = "x86_64-unknown-linux-musl";
-      features = [
-        "garage/bundled-libs"
-        "garage/k2v"
-        "garage/sled"
-        "garage/lmdb"
-        "garage/sqlite"
-      ];
-    });
   };
   clippy = {
-    amd64 = (compile {
+    amd64 = (compile { inherit git_version; compiler = "clippy"; }).workspace.garage { compileMode = "build"; } ;
-      inherit git_version;
-      target = "x86_64-unknown-linux-musl";
-      compiler = "clippy";
-    }).workspace.garage {
-      compileMode = "build";
-    };
   };
 }

doc/api/README.md

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

doc/api/css/redoc.css

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

doc/api/garage-admin-v0.html

@@ -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-v0.yml'></redoc>
-    <script src="./redoc.standalone.js"> </script>
-  </body>
-</html>

doc/book/build/_index.md

@@ -1,54 +0,0 @@
-+++
-title = "Build your own app"
-weight = 4
-sort_by = "weight"
-template = "documentation.html"
-+++
-
-Garage has many API that you can rely on to build complex applications.
-In this section, we reference the existing SDKs and give some code examples.
-
-
-## ⚠️ DISCLAIMER
-
-**K2V AND ADMIN SDK ARE TECHNICAL PREVIEWS**. The following limitations apply:
-  - The API is not complete, some actions are possible only through the `garage` binary
-  - The underlying admin API is not yet stable nor complete, it can breaks at any time
-  - The generator configuration is currently tweaked, the library might break at any time due to a generator change
-  - Because the API and the library are not stable, none of them are published in a package manager (npm, pypi, etc.)
-  - This code has not been extensively tested, some things might not work (please report!)
-
-To have the best experience possible, please consider:
-  - Make sure that the version of the library you are using is pinned (`go.sum`, `package-lock.json`, `requirements.txt`).
-  - Before upgrading your Garage cluster, make sure that you can find a version of this SDK that works with your targeted version and that you are able to update your own code to work with this new version of the library.
-  - Join our Matrix channel at `#garage:deuxfleurs.fr`, say that you are interested by this SDK, and report any friction.
-  - If stability is critical, mirror this repository on your own infrastructure, regenerate the SDKs and upgrade them at your own pace.
-
-
-## About the APIs
-
-Code can interact with Garage through 3 different APIs: S3, K2V, and Admin.
-Each of them has a specific scope.
-
-### S3
-
-De-facto standard, introduced by Amazon, designed to store blobs of data.
-
-### K2V
-
-A simple database API similar to RiakKV or DynamoDB.
-Think a key value store with some additional operations.
-Its design is inspired by Distributed Hash Tables (DHT).
-
-More information:
-  - [In the reference manual](@/documentation/reference-manual/k2v.md)
-
-
-### Administration
-
-Garage operations can also be automated through a REST API.
-We are currently building this SDK for [Python](@/documentation/build/python.md#admin-api), [Javascript](@/documentation/build/javascript.md#administration) and [Golang](@/documentation/build/golang.md#administration).
-
-More information:
-  - [In the reference manual](@/documentation/reference-manual/admin-api.md)
-  - [Full specifiction](https://garagehq.deuxfleurs.fr/api/garage-admin-v0.html)

doc/book/build/golang.md

@@ -1,69 +0,0 @@
-+++
-title = "Golang"
-weight = 30
-+++
-
-## S3
-
-*Coming soon*
-
-Some refs:
-  - Minio minio-go-sdk
-    - [Reference](https://docs.min.io/docs/golang-client-api-reference.html)
-
-  - Amazon aws-sdk-go-v2
-    - [Installation](https://aws.github.io/aws-sdk-go-v2/docs/getting-started/)
-    - [Reference](https://pkg.go.dev/github.com/aws/aws-sdk-go-v2/service/s3)
-    - [Example](https://aws.github.io/aws-sdk-go-v2/docs/code-examples/s3/putobject/)
-
-## K2V
-
-*Coming soon*
-
-## Administration
-
-Install the SDK with:
-
-```bash
-go get git.deuxfleurs.fr/garage-sdk/garage-admin-sdk-golang
-```
-
-A short example:
-
-```go
-package main
-
-import (
-    "context"
-    "fmt"
-    "os"
-    garage "git.deuxfleurs.fr/garage-sdk/garage-admin-sdk-golang"
-)
-
-func main() {
-    // 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")
-
-    // 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)
-    }
-
-    // Process the response
-    fmt.Fprintf(os.Stdout, "Target hostname: %v\n", resp.KnownNodes[resp.Node].Hostname)
-}
-```
-
-See also:
- - [generated doc](https://git.deuxfleurs.fr/garage-sdk/garage-admin-sdk-golang)
- - [examples](https://git.deuxfleurs.fr/garage-sdk/garage-admin-sdk-generator/src/branch/main/example/golang)

doc/book/build/javascript.md

@@ -1,55 +0,0 @@
-+++
-title = "Javascript"
-weight = 10
-+++
-
-## S3
-
-*Coming soon*.
-
-Some refs:
-  - Minio SDK
-    - [Reference](https://docs.min.io/docs/javascript-client-api-reference.html)
-
-  - Amazon aws-sdk-js
-    - [Installation](https://docs.aws.amazon.com/sdk-for-javascript/v3/developer-guide/getting-started.html)
-    - [Reference](https://docs.aws.amazon.com/AWSJavaScriptSDK/latest/AWS/S3.html)
-    - [Example](https://docs.aws.amazon.com/sdk-for-javascript/v3/developer-guide/s3-example-creating-buckets.html)
-
-## K2V
-
-*Coming soon*
-
-## Administration
-
-Install the SDK with:
-
-```bash
-npm install --save git+https://git.deuxfleurs.fr/garage-sdk/garage-admin-sdk-js.git
-```
-
-A short example:
-
-```javascript
-const garage = require('garage_administration_api_v0garage_v0_8_0');
-
-const api = new garage.ApiClient("http://127.0.0.1:3903/v0");
-api.authentications['bearerAuth'].accessToken = "s3cr3t";
-
-const [node, layout, key, bucket] = [
-  new garage.NodesApi(api),
-  new garage.LayoutApi(api),
-  new garage.KeyApi(api),
-  new garage.BucketApi(api),
-];
-
-node.getNodes().then((data) => {
-  console.log(`nodes: ${Object.values(data.knownNodes).map(n => n.hostname)}`)
-}, (error) => {
-  console.error(error);
-});
-```
-
-See also:
- - [sdk repository](https://git.deuxfleurs.fr/garage-sdk/garage-admin-sdk-js)
- - [examples](https://git.deuxfleurs.fr/garage-sdk/garage-admin-sdk-generator/src/branch/main/example/javascript)

doc/book/build/python.md

@@ -1,95 +0,0 @@
-+++
-title = "Python"
-weight = 20
-+++
-
-## S3
-
-*Coming soon*
-
-Some refs:
-  - Minio SDK
-    - [Reference](https://docs.min.io/docs/python-client-api-reference.html)
-
-  - Amazon boto3
-    - [Installation](https://boto3.amazonaws.com/v1/documentation/api/latest/guide/quickstart.html)
-    - [Reference](https://boto3.amazonaws.com/v1/documentation/api/latest/reference/services/s3.html)
-    - [Example](https://boto3.amazonaws.com/v1/documentation/api/latest/guide/s3-uploading-files.html)
-
-## K2V
-
-*Coming soon*
-
-## Admin API
-
-You need at least Python 3.6, pip, and setuptools.
-Because the python package is in a subfolder, the command is a bit more complicated than usual:
-
-```bash
-pip3 install --user 'git+https://git.deuxfleurs.fr/garage-sdk/garage-admin-sdk-python'
-```
-
-Now, let imagine you have a fresh Garage instance running on localhost, with the admin API configured on port 3903 with the bearer `s3cr3t`:
-
-```python
-import garage_admin_sdk
-from garage_admin_sdk.apis import *
-from garage_admin_sdk.models import *
-
-configuration = garage_admin_sdk.Configuration(
-  host = "http://localhost:3903/v0",
-  access_token = "s3cr3t"
-)
-
-# Init APIs
-api = garage_admin_sdk.ApiClient(configuration)
-nodes, layout, keys, buckets = NodesApi(api), LayoutApi(api), KeyApi(api), BucketApi(api)
-
-# Display some info on the node
-status = nodes.get_nodes()
-print(f"running garage {status.garage_version}, node_id {status.node}")
-
-# Change layout of this node
-current = layout.get_layout()
-layout.add_layout({
-  status.node: NodeClusterInfo(
-    zone = "dc1",
-    capacity = 1,
-    tags = [ "dev" ],
-  )
-})
-layout.apply_layout(LayoutVersion(
-  version = current.version + 1
-))
-
-# Create key, allow it to create buckets
-kinfo = keys.add_key(AddKeyRequest(name="openapi"))
-
-allow_create = UpdateKeyRequestAllow(create_bucket=True)
-keys.update_key(kinfo.access_key_id, UpdateKeyRequest(allow=allow_create))
-
-# Create a bucket, allow key, set quotas
-binfo = buckets.create_bucket(CreateBucketRequest(global_alias="documentation"))
-binfo = buckets.allow_bucket_key(AllowBucketKeyRequest(
-  bucket_id=binfo.id,
-  access_key_id=kinfo.access_key_id,
-  permissions=AllowBucketKeyRequestPermissions(read=True, write=True, owner=True),
-))
-binfo = buckets.update_bucket(binfo.id, UpdateBucketRequest(
-  quotas=UpdateBucketRequestQuotas(max_size=19029801,max_objects=1500)))
-
-# Display key
-print(f"""
-cluster ready
-key id is {kinfo.access_key_id}
-secret key is {kinfo.secret_access_key}
-bucket {binfo.global_aliases[0]} contains {binfo.objects}/{binfo.quotas.max_objects} objects
-""")
-```
-
-*This example is named `short.py` in the example folder. Other python examples are also available.*
-
-See also:
- - [sdk repo](https://git.deuxfleurs.fr/garage-sdk/garage-admin-sdk-python)
- - [examples](https://git.deuxfleurs.fr/garage-sdk/garage-admin-sdk-generator/src/branch/main/example/python)
-

doc/book/build/rust.md

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

doc/book/connect/_index.md

@@ -1,5 +1,5 @@
 +++
-title = "Existing integrations"
+title = "Integrations"
 weight = 3
 sort_by = "weight"
 template = "documentation.html"
@@ -14,6 +14,7 @@ In particular, you will find here instructions to connect it with:
   - [Applications](@/documentation/connect/apps/index.md)
   - [Website hosting](@/documentation/connect/websites.md)
   - [Software repositories](@/documentation/connect/repositories.md)
+  - [Your own code](@/documentation/connect/code.md)
   - [FUSE](@/documentation/connect/fs.md)
 
 ### Generic instructions

doc/book/connect/apps/index.md

@@ -9,7 +9,7 @@ In this section, we cover the following web applications:
 |------|--------|------|
 | [Nextcloud](#nextcloud)     | ✅       |  Both Primary Storage and External Storage are supported    |
 | [Peertube](#peertube)     | ✅       | Must be configured with the website endpoint     |
-| [Mastodon](#mastodon)     | ✅       | Natively supported    |
+| [Mastodon](#mastodon)     | ❓       | Not yet tested     |
 | [Matrix](#matrix)     | ✅       |  Tested with `synapse-s3-storage-provider`    |
 | [Pixelfed](#pixelfed)     | ❓       |  Not yet tested    |
 | [Pleroma](#pleroma)     | ❓       |  Not yet tested    |
@@ -224,135 +224,7 @@ You can now reload the page and see in your browser console that data are fetche
 
 ## Mastodon
 
-Mastodon natively supports the S3 protocol to store media files, and it works out-of-the-box with Garage.
+https://docs.joinmastodon.org/admin/config/#cdn
-You will need to expose your Garage bucket as a website: that way, media files will be served directly from Garage.
-
-### Performance considerations
-
-Mastodon tends to store many small objects over time: expect hundreds of thousands of objects,
-with average object size ranging from 50 KB to 150 KB.
-
-As such, your Garage cluster should be configured appropriately for good performance:
-
-- use Garage v0.8.0 or higher with the [LMDB database engine](@documentation/reference-manual/configuration.md#db-engine-since-v0-8-0).
-  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
-
-This is the usual Garage setup:
-
-```bash
-garage key new --name mastodon-key
-garage bucket create mastodon-data
-garage bucket allow mastodon-data --read --write --key mastodon-key
-```
-
-Note the Key ID and Secret Key.
-
-### Exposing your bucket as a website
-
-Create a DNS name to serve your media files, such as `my-social-media.mydomain.tld`.
-This name will be publicly exposed to the users of your Mastodon instance: they
-will load images directly from this DNS name.
-
-As [documented here](@/documentation/cookbook/exposing-websites.md),
-add this DNS name as alias to your bucket, and expose it as a website:
-
-```bash
-garage bucket alias mastodon-data my-social-media.mydomain.tld
-garage bucket website --allow mastodon-data
-```
-
-Then you will likely need to [setup a reverse proxy](@/documentation/cookbook/reverse-proxy.md)
-in front of it to serve your media files over HTTPS.
-
-### Cleaning up old media files before migration
-
-Mastodon instance quickly accumulate a lot of media files from the federation.
-Most of them are not strictly necessary because they can be fetched again from
-other servers.  As such, it is highly recommended to clean them up before
-migration, this will greatly reduce the migration time.
-
-From the [official Mastodon documentation](https://docs.joinmastodon.org/admin/tootctl/#media):
-
-```bash
-$ RAILS_ENV=production bin/tootctl media remove --days 3
-$ RAILS_ENV=production bin/tootctl media remove-orphans
-$ RAILS_ENV=production bin/tootctl preview_cards remove --days 15
-```
-
-Here is a typical disk usage for a small but multi-year instance after cleanup:
-
-```bash
-$ RAILS_ENV=production bin/tootctl media usage
-Attachments:	5.67 GB (1.14 GB local)
-Custom emoji:	295 MB (0 Bytes local)
-Preview cards:	154 MB
-Avatars:	3.77 GB (127 KB local)
-Headers:	8.72 GB (242 KB local)
-Backups:	0 Bytes
-Imports:	1.7 KB
-Settings:	0 Bytes
-```
-
-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.
-The [minio client](@documentation/connect/cli.md#minio-client) is a good choice
-thanks to its mirror mode:
-
-```bash
-mc mirror ./public/system/ garage/mastodon-data
-```
-
-Here is a typical bucket usage after all data has been migrated:
-
-```bash
-$ garage bucket info mastodon-data
-
-Size: 20.3 GiB (21.8 GB)
-Objects: 175968
-```
-
-### Configuring Mastodon
-
-In your `.env.production` configuration file:
-
-```bash
-S3_ENABLED=true
-# Internal access to Garage
-S3_ENDPOINT=http://my-garage-instance.mydomain.tld:3900
-S3_REGION=garage
-S3_BUCKET=mastodon-data
-# Change this (Key ID and Secret Key of your Garage key)
-AWS_ACCESS_KEY_ID=GKe88df__CHANGETHIS__c5145
-AWS_SECRET_ACCESS_KEY=a2f7__CHANGETHIS__77fcfcf7a58f47a4aa4431f2e675c56da37821a1070000
-# What name gets exposed to users (HTTPS is implicit)
-S3_ALIAS_HOST=my-social-media.mydomain.tld
-```
-
-For more details, see the [reference Mastodon documentation](https://docs.joinmastodon.org/admin/config/#cdn).
-
-Restart all Mastodon services and everything should now be using Garage!
-You can check the URLs of images in the Mastodon web client, they should start
-with `https://my-social-media.mydomain.tld`.
-
-### Last migration sync
-
-After Mastodon is successfully using Garage, you can run a last sync from the local filesystem to Garage:
-
-```bash
-mc mirror --newer-than "3h" ./public/system/ garage/mastodon-data
-```
-
-### References
-
-[cybrespace's guide to migrate to S3](https://github.com/cybrespace/cybrespace-meta/blob/master/s3.md)
-(the guide is for Amazon S3, so the configuration is a bit different, but the rest is similar)
-
 
 ## Matrix
 

doc/book/connect/code.md

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

doc/book/cookbook/kubernetes.md

@@ -47,11 +47,7 @@ garage:
   # Use only 2 replicas per object
   replicationMode: "2"
 
-  # Use recommended lmdb db engine
-  dbEngine: "lmdb"
-
 # Start 4 instances (StatefulSets) of garage
-deployment:
 replicaCount: 4
 
 # Override default storage class and size

doc/book/cookbook/monitoring.md

@@ -1,306 +0,0 @@
-+++
-title = "Monitoring Garage"
-weight = 40
-+++
-
-Garage exposes some internal metrics in the Prometheus data format.
-This page explains how to exploit these metrics.
-
-## Setting up monitoring
-
-### Enabling the Admin API endpoint
-
-If you have not already enabled the [administration API endpoint](@/documentation/reference-manual/admin-api.md), do so by adding the following lines to your configuration file:
-
-```toml
-[admin]
-api_bind_addr = "0.0.0.0:3903"
-```
-
-This will allow anyone to scrape Prometheus metrics by fetching
-`http://localhost: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.
-
-### Setting up Prometheus and Grafana
-
-Add a scrape config to your Prometheus daemon to scrape metrics from
-all of your nodes:
-
-```yaml
-scrape_configs:
-  - job_name: 'garage'
-    static_configs:
-      - targets:
-        - 'node1.mycluster:3903'
-        - 'node2.mycluster:3903'
-        - 'node3.mycluster:3903'
-```
-
-If you have set a metrics token in your Garage configuration file,
-add the following lines in your Prometheus scrape config:
-
-```yaml
-    authorization:
-      type: Bearer
-      credentials: 'your metrics token'
-```
-
-To visualize the scraped data in Grafana,
-you can either import our [Grafana dashboard for Garage](https://git.deuxfleurs.fr/Deuxfleurs/garage/raw/branch/main/script/telemetry/grafana-garage-dashboard-prometheus.json)
-or make your own.
-We detail below the list of exposed metrics and their meaning.
-
-
-
-## List of exported metrics
-
-
-### Metrics of the API endpoints
-
-#### `api_admin_request_counter` (counter)
-
-Counts the number of requests to a given endpoint of the administration API. Example:
-
-```
-api_admin_request_counter{api_endpoint="Metrics"} 127041
-```
-
-#### `api_admin_request_duration` (histogram)
-
-Evaluates the duration of API calls to the various administration API endpoint. Example:
-
-```
-api_admin_request_duration_bucket{api_endpoint="Metrics",le="0.5"} 127041
-api_admin_request_duration_sum{api_endpoint="Metrics"} 605.250344830999
-api_admin_request_duration_count{api_endpoint="Metrics"} 127041
-```
-
-#### `api_s3_request_counter` (counter)
-
-Counts the number of requests to a given endpoint of the S3 API. Example:
-
-```
-api_s3_request_counter{api_endpoint="CreateMultipartUpload"} 1
-```
-
-#### `api_s3_error_counter` (counter)
-
-Counts the number of requests to a given endpoint of the S3 API that returned an error. Example:
-
-```
-api_s3_error_counter{api_endpoint="GetObject",status_code="404"} 39
-```
-
-#### `api_s3_request_duration` (histogram)
-
-Evaluates the duration of API calls to the various S3 API endpoints. Example:
-
-```
-api_s3_request_duration_bucket{api_endpoint="CreateMultipartUpload",le="0.5"} 1
-api_s3_request_duration_sum{api_endpoint="CreateMultipartUpload"} 0.046340762
-api_s3_request_duration_count{api_endpoint="CreateMultipartUpload"} 1
-```
-
-#### `api_k2v_request_counter` (counter), `api_k2v_error_counter` (counter), `api_k2v_error_duration` (histogram)
-
-Same as for S3, for the K2V API.
-
-
-### Metrics of the Web endpoint
-
-
-#### `web_request_counter` (counter)
-
-Number of requests to the web endpoint
-
-```
-web_request_counter{method="GET"} 80
-```
-
-#### `web_request_duration` (histogram)
-
-Duration of requests to the web endpoint
-
-```
-web_request_duration_bucket{method="GET",le="0.5"} 80
-web_request_duration_sum{method="GET"} 1.0528433229999998
-web_request_duration_count{method="GET"} 80
-```
-
-#### `web_error_counter` (counter)
-
-Number of requests to the web endpoint resulting in errors
-
-```
-web_error_counter{method="GET",status_code="404 Not Found"} 64
-```
-
-
-### Metrics of the data block manager
-
-#### `block_bytes_read`, `block_bytes_written` (counter)
-
-Number of bytes read/written to/from disk in the data storage directory.
-
-```
-block_bytes_read 120586322022
-block_bytes_written 3386618077
-```
-
-#### `block_read_duration`, `block_write_duration` (histograms)
-
-Evaluates the duration of the reading/writing of individual data blocks in the data storage directory.
-
-```
-block_read_duration_bucket{le="0.5"} 169229
-block_read_duration_sum 2761.6902550310056
-block_read_duration_count 169240
-block_write_duration_bucket{le="0.5"} 3559
-block_write_duration_sum 195.59170078500006
-block_write_duration_count 3571
-```
-
-#### `block_delete_counter` (counter)
-
-Counts the number of data blocks that have been deleted from storage.
-
-```
-block_delete_counter 122
-```
-
-#### `block_resync_counter` (counter), `block_resync_duration` (histogram)
-
-Counts the number of resync operations the node has executed, and evaluates their duration.
-
-```
-block_resync_counter 308897
-block_resync_duration_bucket{le="0.5"} 308892
-block_resync_duration_sum 139.64204196100016
-block_resync_duration_count 308897
-```
-
-#### `block_resync_queue_length` (gauge)
-
-The number of block hashes currently queued for a resync.
-This is normal to be nonzero for long periods of time.
-
-```
-block_resync_queue_length 0
-```
-
-#### `block_resync_errored_blocks` (gauge)
-
-The number of block hashes that we were unable to resync last time we tried.
-**THIS SHOULD BE ZERO, OR FALL BACK TO ZERO RAPIDLY, IN A HEALTHY CLUSTER.**
-Persistent nonzero values indicate that some data is likely to be lost.
-
-```
-block_resync_errored_blocks 0
-```
-
-
-### Metrics related to RPCs (remote procedure calls) between nodes
-
-#### `rpc_netapp_request_counter` (counter)
-
-Number of RPC requests emitted
-
-```
-rpc_request_counter{from="<this node>",rpc_endpoint="garage_block/manager.rs/Rpc",to="<remote node>"} 176
-```
-
-#### `rpc_netapp_error_counter` (counter)
-
-Number of communication errors (errors in the Netapp library, generally due to disconnected nodes)
-
-```
-rpc_netapp_error_counter{from="<this node>",rpc_endpoint="garage_block/manager.rs/Rpc",to="<remote node>"} 354
-```
-
-#### `rpc_timeout_counter` (counter)
-
-Number of RPC timeouts, should be close to zero in a healthy cluster.
-
-```
-rpc_timeout_counter{from="<this node>",rpc_endpoint="garage_rpc/membership.rs/SystemRpc",to="<remote node>"} 1
-```
-
-#### `rpc_duration` (histogram)
-
-The duration of internal RPC calls between Garage nodes.
-
-```
-rpc_duration_bucket{from="<this node>",rpc_endpoint="garage_block/manager.rs/Rpc",to="<remote node>",le="0.5"} 166
-rpc_duration_sum{from="<this node>",rpc_endpoint="garage_block/manager.rs/Rpc",to="<remote node>"} 35.172253716
-rpc_duration_count{from="<this node>",rpc_endpoint="garage_block/manager.rs/Rpc",to="<remote node>"} 174
-```
-
-
-### Metrics of the metadata table manager
-
-#### `table_gc_todo_queue_length` (gauge)
-
-Table garbage collector TODO queue length
-
-```
-table_gc_todo_queue_length{table_name="block_ref"} 0
-```
-
-#### `table_get_request_counter` (counter), `table_get_request_duration` (histogram)
-
-Number of get/get_range requests internally made on each table, and their duration.
-
-```
-table_get_request_counter{table_name="bucket_alias"} 315
-table_get_request_duration_bucket{table_name="bucket_alias",le="0.5"} 315
-table_get_request_duration_sum{table_name="bucket_alias"} 0.048509778000000024
-table_get_request_duration_count{table_name="bucket_alias"} 315
-```
-
-
-#### `table_put_request_counter` (counter), `table_put_request_duration` (histogram)
-
-Number of insert/insert_many requests internally made on this table, and their duration
-
-```
-table_put_request_counter{table_name="block_ref"} 677
-table_put_request_duration_bucket{table_name="block_ref",le="0.5"} 677
-table_put_request_duration_sum{table_name="block_ref"} 61.617528636
-table_put_request_duration_count{table_name="block_ref"} 677
-```
-
-#### `table_internal_delete_counter` (counter)
-
-Number of value deletions in the tree (due to GC or repartitioning)
-
-```
-table_internal_delete_counter{table_name="block_ref"} 2296
-```
-
-#### `table_internal_update_counter` (counter)
-
-Number of value updates where the value actually changes (includes creation of new key and update of existing key)
-
-```
-table_internal_update_counter{table_name="block_ref"} 5996
-```
-
-#### `table_merkle_updater_todo_queue_length` (gauge)
-
-Merkle tree updater TODO queue length (should fall to zero rapidly)
-
-```
-table_merkle_updater_todo_queue_length{table_name="block_ref"} 0
-```
-
-#### `table_sync_items_received`, `table_sync_items_sent` (counters)
-
-Number of data items sent to/recieved from other nodes during resync procedures
-
-```
-table_sync_items_received{from="<remote node>",table_name="bucket_v2"} 3
-table_sync_items_sent{table_name="block_ref",to="<remote node>"} 2
-```
-
-

doc/book/cookbook/real-world.md

@@ -11,9 +11,8 @@ We recommend first following the [quick start guide](@/documentation/quick-start
 to get familiar with Garage's command line and usage patterns.
 
 
-## Preparing your environment
 
-### Prerequisites
+## Prerequisites
 
 To run a real-world deployment, make sure the following conditions are met:
 
@@ -22,6 +21,10 @@ To run a real-world deployment, make sure the following conditions are met:
 - Each machine has a public IP address which is reachable by other machines.
   Running behind a NAT is likely to be possible but hasn't been tested for the latest version (TODO).
 
+- Ideally, each machine should have a SSD available in addition to the HDD you are dedicating
+  to Garage. This will allow for faster access to metadata and has the potential
+  to significantly reduce Garage's response times.
+
 - This guide will assume you are using Docker containers to deploy Garage on each node. 
   Garage can also be run independently, for instance as a [Systemd service](@/documentation/cookbook/systemd.md).
   You can also use an orchestrator such as Nomad or Kubernetes to automatically manage
@@ -46,42 +49,6 @@ available in the different locations of your cluster is roughly the same.
 For instance, here, the Mercury node could be moved to Brussels; this would allow the cluster
 to store 2 TB of data in total.
 
-### Best practices
-
-- If you have 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.
-  Ideally, the metadata directory would be stored on an SSD (smaller but faster),
-  and the data directory would be stored on an HDD (larger but slower).
-
-- For the data directory, Garage already does checksumming and integrity verification,
-  so there is no need to use a filesystem such as BTRFS or ZFS that does it.
-  We recommend using XFS for the data partition, as it has the best performance.
-  EXT4 is not recommended as it has more strict limitations on the number of inodes,
-  which might cause issues with Garage when large numbers of objects are stored.
-
-- If you only have an HDD and no SSD, it's fine to put your metadata alongside the data
-  on the same drive. Having lots of RAM for your kernel to cache the metadata will
-  help a lot with performance.  Make sure to use the LMDB database engine,
-  instead of Sled, which suffers from quite bad performance degradation on HDDs.
-  Sled is still the default for legacy reasons, but is not recommended anymore.
-
-- For the metadata storage, Garage does not do checksumming and integrity
-  verification on its own. If you are afraid of bitrot/data corruption,
-  put your metadata directory on a BTRFS partition. Otherwise, just use regular
-  EXT4 or XFS.
-
-- 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).
@@ -114,7 +81,6 @@ A valid `/etc/garage/garage.toml` for our cluster would look as follows:
 ```toml
 metadata_dir = "/var/lib/garage/meta"
 data_dir = "/var/lib/garage/data"
-db_engine = "lmdb"
 
 replication_mode = "3"
 
@@ -124,6 +90,8 @@ rpc_bind_addr = "[::]:3901"
 rpc_public_addr = "<this node's public IP>:3901"
 rpc_secret = "<RPC secret>"
 
+bootstrap_peers = []
+
 [s3_api]
 s3_region = "garage"
 api_bind_addr = "[::]:3900"
@@ -164,21 +132,6 @@ 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:
-
-```yaml
-version: "3"
-services:
-  garage:
-    image: dxflrs/garage:v0.8.0
-    network_mode: "host"
-    restart: unless-stopped
-    volumes:
-      - /etc/garage.toml:/etc/garage.toml
-      - /var/lib/garage/meta:/var/lib/garage/meta
-      - /var/lib/garage/data:/var/lib/garage/data
-```
-
 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

doc/book/cookbook/recovering.md

@@ -1,6 +1,6 @@
 +++
 title = "Recovering from failures"
-weight = 50
+weight = 35
 +++
 
 Garage is meant to work on old, second-hand hardware.

doc/book/cookbook/reverse-proxy.md

@@ -70,16 +70,14 @@ A possible configuration:
 
 ```nginx
 upstream s3_backend {
-  # If you have a garage instance locally.
+  # if you have a garage instance locally
   server 127.0.0.1:3900;
-  # You can also put your other instances.
+  # you can also put your other instances
   server 192.168.1.3:3900;
-  # Domain names also work.
+  # domain names also work
   server garage1.example.com:3900;
-  # A "backup" server is only used if all others have failed.
+  # you can assign weights if you have some servers 
-  server garage-remote.example.com:3900 backup;
+  # that are more powerful than others
-  # You can assign weights if you have some servers
-  # that can serve more requests than others.
   server garage2.example.com:3900 weight=2;
 }
 
@@ -98,8 +96,6 @@ server {
     proxy_pass http://s3_backend;
     proxy_set_header X-Forwarded-For $proxy_add_x_forwarded_for;
     proxy_set_header Host $host;
-    # Disable buffering to a temporary file.
-    proxy_max_temp_file_size 0;
   }
 }
 ```

doc/book/cookbook/upgrading.md

@@ -1,6 +1,6 @@
 +++
 title = "Upgrading Garage"
-weight = 60
+weight = 40
 +++
 
 Garage is a stateful clustered application, where all nodes are communicating together and share data structures.

doc/book/design/_index.md

@@ -1,6 +1,6 @@
 +++
 title = "Design"
-weight = 6
+weight = 5
 sort_by = "weight"
 template = "documentation.html"
 +++

doc/book/development/_index.md

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

doc/book/quick-start/_index.md

@@ -42,25 +42,25 @@ you can [build Garage from source](@/documentation/cookbook/from-source.md).
 
 ## Configuring and starting Garage
 
-### Generating a first configuration file
+### Writing a first configuration file
 
 This first configuration file should allow you to get started easily with the simplest
 possible Garage deployment.
+**Save it as `/etc/garage.toml`.**
+You can also store it somewhere else, but you will have to specify `-c path/to/garage.toml`
+at each invocation of the `garage` binary (for example: `garage -c ./garage.toml server`, `garage -c ./garage.toml status`).
 
-We will create it with the following command line
+```toml
-to generate unique and private secrets for security reasons:
-
-```bash
-cat > garage.toml <<EOF
 metadata_dir = "/tmp/meta"
 data_dir = "/tmp/data"
-db_engine = "lmdb"
 
 replication_mode = "none"
 
 rpc_bind_addr = "[::]:3901"
 rpc_public_addr = "127.0.0.1:3901"
-rpc_secret = "$(openssl rand -hex 32)"
+rpc_secret = "1799bccfd7411eddcf9ebd316bc1f5287ad12a68094e1c6ac6abde7e6feae1ec"
+
+bootstrap_peers = []
 
 [s3_api]
 s3_region = "garage"
@@ -71,26 +71,12 @@ root_domain = ".s3.garage.localhost"
 bind_addr = "[::]:3902"
 root_domain = ".web.garage.localhost"
 index = "index.html"
-
-[k2v_api]
-api_bind_addr = "[::]:3904"
-
-[admin]
-api_bind_addr = "0.0.0.0:3903"
-admin_token = "$(openssl rand -base64 32)"
-EOF
 ```
 
-Now that your configuration file has been created, you can put
+The `rpc_secret` value provided above is just an example. It will work, but in
-it in the right place. By default, garage looks at **`/etc/garage.toml`.**
+order to secure your cluster you will need to use another one. You can generate
+such a value with `openssl rand -hex 32`.
 
-You can also store it somewhere else, but you will have to specify `-c path/to/garage.toml`
-at each invocation of the `garage` binary (for example: `garage -c ./garage.toml server`, `garage -c ./garage.toml status`).
-
-As you can see, the `rpc_secret` is a 32 bytes hexadecimal string.
-You can regenerate it with `openssl rand -hex 32`.
-If you target a cluster deployment with multiple nodes, make sure that
-you use the same value for all nodes.
 
 As you can see in the `metadata_dir` and `data_dir` parameters, we are saving Garage's data
 in `/tmp` which gets erased when your system reboots. This means that data stored on this
@@ -233,7 +219,6 @@ Now that we have a bucket and a key, we need to give permissions to the key on t
 garage bucket allow \
   --read \
   --write \
-  --owner \
   nextcloud-bucket \
   --key nextcloud-app-key
 ```
@@ -247,73 +232,54 @@ garage bucket info nextcloud-bucket
 
 ## Uploading and downlading from Garage
 
-To download and upload files on garage, we can use a third-party tool named `awscli`.
+We recommend the use of MinIO Client to interact with Garage files (`mc`).
+Instructions to install it and use it are provided on the
+[MinIO website](https://docs.min.io/docs/minio-client-quickstart-guide.html).
+Before reading the following, you need a working `mc` command on your path.
 
+Note that on certain Linux distributions such as Arch Linux, the Minio client binary
+is called `mcli` instead of `mc` (to avoid name clashes with the Midnight Commander).
 
-### Install and configure `awscli`
+### Configure `mc`
 
-If you have python on your system, you can install it with:
+You need your access key and secret key created above.
+We will assume you are invoking `mc` on the same machine as the Garage server,
+your S3 API endpoint is therefore `http://127.0.0.1:3900`.
+For this whole configuration, you must set an alias name: we chose `my-garage`, that you will used for all commands.
+
+Adapt the following command accordingly and run it:
 
 ```bash
-python -m pip install --user awscli
+mc alias set \
+  my-garage \
+  http://127.0.0.1:3900 \
+  <access key> \
+  <secret key> \
+  --api S3v4
 ```
 
-Now that `awscli` is installed, you must configure it to talk to your Garage instance,
+### Use `mc`
-with your key. There are multiple ways to do that, the simplest one is to create a file
+
-named `~/.awsrc` with this content:
+You can not list buckets from `mc` currently.
+
+But the following commands and many more should work:
 
 ```bash
-export AWS_ACCESS_KEY_ID=xxxx      # put your Key ID here
+mc cp image.png my-garage/nextcloud-bucket
-export AWS_SECRET_ACCESS_KEY=xxxx  # put your Secret key here
+mc cp my-garage/nextcloud-bucket/image.png .
-export AWS_DEFAULT_REGION='garage'
+mc ls my-garage/nextcloud-bucket
-export AWS_ENDPOINT='http://localhost:3900'
+mc mirror localdir/ my-garage/another-bucket
-
-function aws { command aws --endpoint-url $AWS_ENDPOINT $@ ; }
-aws --version
 ```
 
-Now, each time you want to use `awscli` on this target, run:
-
-```bash
-source ~/.awsrc
-```
-
-*You can create multiple files with different names if you 
-have multiple Garage clusters or different keys.
-Switching from one cluster to another is as simple as
-sourcing the right file.*
-
-### Example usage of `awscli`
-
-```bash
-# list buckets
-aws s3 ls
-
-# list objects of a bucket
-aws s3 ls s3://my_files
-
-# copy from your filesystem to garage
-aws s3 cp /proc/cpuinfo s3://my_files/cpuinfo.txt
-
-# copy from garage to your filesystem
-aws s3 cp s3/my_files/cpuinfo.txt /tmp/cpuinfo.txt
-```
-
-Note that you can use `awscli` for more advanced operations like
-creating a bucket, pre-signing a request or managing your website.
-[Read the full documentation to know more](https://awscli.amazonaws.com/v2/documentation/api/latest/reference/s3/index.html).
-
-Some features are however not implemented like ACL or policy.
-Check [our s3 compatibility list](@/documentation/reference-manual/s3-compatibility.md).
 
 ### Other tools for interacting with Garage
 
 The following tools can also be used to send and recieve files from/to Garage:
 
-- [minio-client](@/documentation/connect/cli.md#minio-client) 
+- the [AWS CLI](https://aws.amazon.com/cli/)
-- [s3cmd](@/documentation/connect/cli.md#s3cmd) 
+- [`rclone`](https://rclone.org/)
-- [rclone](@/documentation/connect/cli.md#rclone)
+- [Cyberduck](https://cyberduck.io/)
-- [Cyberduck](@/documentation/connect/cli.md#cyberduck)
+- [`s3cmd`](https://s3tools.org/s3cmd)
-- [WinSCP](@/documentation/connect/cli.md#winscp) 
 
-An exhaustive list is maintained in the ["Integrations" > "Browsing tools" section](@/documentation/connect/_index.md).
+Refer to the ["Integrations" section](@/documentation/connect/_index.md) to learn how to
+configure application and command line utilities to integrate with Garage.

doc/book/reference-manual/_index.md

@@ -1,6 +1,6 @@
 +++
 title = "Reference Manual"
-weight = 5
+weight = 4
 sort_by = "weight"
 template = "documentation.html"
 +++

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

@@ -47,13 +47,598 @@ Returns internal Garage metrics in Prometheus format.
 
 ### Cluster operations
 
-These endpoints are defined on a dedicated [Redocly page](https://garagehq.deuxfleurs.fr/api/garage-admin-v0.html). You can also download its [OpenAPI specification](https://garagehq.deuxfleurs.fr/api/garage-admin-v0.yml).
+#### GetClusterStatus `GET /v0/status`
 
-Requesting the API from the command line can be as simple as running:
+Returns the cluster's current status in JSON, including:
 
-```bash
+- ID of the node being queried and its version of the Garage daemon
-curl -H 'Authorization: Bearer s3cr3t' http://localhost:3903/v0/status | jq
+- Live nodes
+- Currently configured cluster layout
+- Staged changes to the cluster layout
+
+Example response body:
+
+```json
+{
+  "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": 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"
+        ]
+      }
+    }
+  }
+}
 ```
 
-For more advanced use cases, we recommend using a SDK.  
+#### ConnectClusterNodes `POST /v0/connect`
-[Go to the "Build your own app" section to know how to use our SDKs](@/documentation/build/_index.md)
+
+Instructs this Garage node to connect to other Garage nodes at specified addresses.
+
+Example request body:
+
+```json
+[
+    "ec79480e0ce52ae26fd00c9da684e4fa56658d9c64cdcecb094e936de0bfe71f@10.0.0.11:3901",
+    "4a6ae5a1d0d33bf895f5bb4f0a418b7dc94c47c0dd2eb108d1158f3c8f60b0ff@10.0.0.12:3901"
+]
+```
+
+The format of the string for a node to connect to is: `<node ID>@<ip address>:<port>`, same as in the `garage node connect` CLI call.
+
+Example response:
+
+```json
+[
+    {
+        "success": true,
+        "error": null
+    },
+    {
+        "success": false,
+        "error": "Handshake error"
+    }
+]
+```
+
+#### GetClusterLayout `GET /v0/layout`
+
+Returns the cluster's current layout in JSON, including:
+
+- Currently configured cluster layout
+- Staged changes to the cluster layout
+
+(the info returned by this endpoint is a subset of the info returned by GetClusterStatus)
+
+Example response body:
+
+```json
+{
+  "version": 12,
+  "roles": {
+    "ec79480e0ce52ae26fd00c9da684e4fa56658d9c64cdcecb094e936de0bfe71f": {
+      "zone": "dc1",
+      "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"
+      ]
+    }
+  }
+}
+```
+
+#### UpdateClusterLayout `POST /v0/layout`
+
+Send modifications to the cluster layout. These modifications will
+be included in the staged role changes, visible in subsequent calls
+of `GetClusterLayout`. Once the set of staged changes is satisfactory,
+the user may call `ApplyClusterLayout` to apply the changed changes,
+or `Revert ClusterLayout` to clear all of the staged changes in
+the layout.
+
+Request body format:
+
+```json
+{
+  <node_id>: {
+    "capacity": <new_capacity>,
+    "zone": <new_zone>,
+    "tags": [
+      <new_tag>,
+      ...
+    ]
+  },
+  <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.
+
+
+#### ApplyClusterLayout `POST /v0/layout/apply`
+
+Applies to the cluster the layout changes currently registered as
+staged layout changes.
+
+Request body format:
+
+```json
+{
+  "version": 13
+}
+```
+
+Similarly to the CLI, the body must include the version of the new layout
+that will be created, which MUST be 1 + the value of the currently
+existing layout in the cluster.
+
+#### RevertClusterLayout `POST /v0/layout/revert`
+
+Clears all of the staged layout changes.
+
+Request body format:
+
+```json
+{
+  "version": 13
+}
+```
+
+Reverting the staged changes is done by incrementing the version number
+and clearing the contents of the staged change list.
+Similarly to the CLI, the body must include the incremented
+version number, which MUST be 1 + the value of the currently
+existing layout in the cluster.
+
+
+### Access key operations
+
+#### ListKeys `GET /v0/key`
+
+Returns all API access keys in the cluster.
+
+Example response:
+
+```json
+[
+  {
+    "id": "GK31c2f218a2e44f485b94239e",
+    "name": "test"
+  },
+  {
+    "id": "GKe10061ac9c2921f09e4c5540",
+    "name": "test2"
+  }
+]
+```
+
+#### 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.
+
+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).
+
+Example response:
+
+```json
+{
+  "name": "test",
+  "accessKeyId": "GK31c2f218a2e44f485b94239e",
+  "secretAccessKey": "b892c0665f0ada8a4755dae98baa3b133590e11dae3bcc1f9d769d67f16c3835",
+  "permissions": {
+    "createBucket": false
+  },
+  "buckets": [
+    {
+      "id": "70dc3bed7fe83a75e46b66e7ddef7d56e65f3c02f9f80b6749fb97eccb5e1033",
+      "globalAliases": [
+        "test2"
+      ],
+      "localAliases": [],
+      "permissions": {
+        "read": true,
+        "write": true,
+        "owner": false
+      }
+    },
+    {
+      "id": "d7452a935e663fc1914f3a5515163a6d3724010ce8dfd9e4743ca8be5974f995",
+      "globalAliases": [
+        "test3"
+      ],
+      "localAliases": [],
+      "permissions": {
+        "read": true,
+        "write": true,
+        "owner": false
+      }
+    },
+    {
+      "id": "e6a14cd6a27f48684579ec6b381c078ab11697e6bc8513b72b2f5307e25fff9b",
+      "globalAliases": [],
+      "localAliases": [
+        "test"
+      ],
+      "permissions": {
+        "read": true,
+        "write": true,
+        "owner": true
+      }
+    },
+    {
+      "id": "96470e0df00ec28807138daf01915cfda2bee8eccc91dea9558c0b4855b5bf95",
+      "globalAliases": [
+        "alex"
+      ],
+      "localAliases": [],
+      "permissions": {
+        "read": true,
+        "write": true,
+        "owner": true
+      }
+    }
+  ]
+}
+```
+
+#### DeleteKey `DELETE /v0/key?id=<acces key id>`
+
+Deletes an API access key.
+
+#### UpdateKey `POST /v0/key?id=<acces key id>`
+
+Updates information about the specified API access key.
+
+Request body format:
+
+```json
+{
+    "name": "NameOfMyKey",
+    "allow": {
+        "createBucket": true,
+    },
+    "deny": {}
+}
+```
+
+All fields (`name`, `allow` and `deny`) are optionnal.
+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`.
+
+
+### Bucket operations
+
+#### ListBuckets `GET /v0/bucket`
+
+Returns all storage buckets in the cluster.
+
+Example response:
+
+```json
+[
+  {
+    "id": "70dc3bed7fe83a75e46b66e7ddef7d56e65f3c02f9f80b6749fb97eccb5e1033",
+    "globalAliases": [
+      "test2"
+    ],
+    "localAliases": []
+  },
+  {
+    "id": "96470e0df00ec28807138daf01915cfda2bee8eccc91dea9558c0b4855b5bf95",
+    "globalAliases": [
+      "alex"
+    ],
+    "localAliases": []
+  },
+  {
+    "id": "d7452a935e663fc1914f3a5515163a6d3724010ce8dfd9e4743ca8be5974f995",
+    "globalAliases": [
+      "test3"
+    ],
+    "localAliases": []
+  },
+  {
+    "id": "e6a14cd6a27f48684579ec6b381c078ab11697e6bc8513b72b2f5307e25fff9b",
+    "globalAliases": [],
+    "localAliases": [
+      {
+        "accessKeyId": "GK31c2f218a2e44f485b94239e",
+        "alias": "test"
+      }
+    ]
+  }
+]
+```
+
+#### GetBucketInfo `GET /v0/bucket?id=<bucket id>`
+#### GetBucketInfo `GET /v0/bucket?globalAlias=<alias>`
+
+Returns information about the requested storage bucket.
+
+If `id` is set, the bucket is looked up using its exact identifier.
+If `globalAlias` is set, the bucket is looked up using its global alias.
+(both are fast)
+
+Example response:
+
+```json
+{
+    "id": "afa8f0a22b40b1247ccd0affb869b0af5cff980924a20e4b5e0720a44deb8d39",
+        "globalAliases": [],
+        "websiteAccess": false,
+        "websiteConfig": null,
+        "keys": [
+        {
+            "accessKeyId": "GK31c2f218a2e44f485b94239e",
+            "name": "Imported key",
+            "permissions": {
+                "read": true,
+                "write": true,
+                "owner": true
+            },
+            "bucketLocalAliases": [
+                "debug"
+            ]
+        }
+        ],
+        "objects": 14827,
+        "bytes": 13189855625,
+        "unfinshedUploads": 0,
+        "quotas": {
+            "maxSize": null,
+            "maxObjects": null
+        }
+}
+```
+
+#### CreateBucket `POST /v0/bucket`
+
+Creates a new storage bucket.
+
+Request body format:
+
+```json
+{
+    "globalAlias": "NameOfMyBucket"
+}
+```
+
+OR
+
+```json
+{
+    "localAlias": {
+        "accessKeyId": "GK31c2f218a2e44f485b94239e",
+        "alias": "NameOfMyBucket",
+        "allow": {
+            "read": true,
+            "write": true,
+            "owner": false
+        }
+    }
+}
+```
+
+OR
+
+```json
+{}
+```
+
+Creates a new bucket, either with a global alias, a local one,
+or no alias at all.
+
+Technically, you can also specify both `globalAlias` and `localAlias` and that would create
+two aliases, but I don't see why you would want to do that.
+
+#### 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.
+
+Request body format:
+
+```json
+{
+    "websiteAccess": {
+        "enabled": true,
+        "indexDocument": "index.html",
+        "errorDocument": "404.html"
+    },
+    "quotas": {
+        "maxSize": 19029801,
+        "maxObjects": null,
+    }
+}
+```
+
+All fields (`websiteAccess` and `quotas`) are optionnal.
+If they are present, the corresponding modifications are applied to the bucket, otherwise nothing is changed.
+
+In `websiteAccess`: if `enabled` is `true`, `indexDocument` must be specified.
+The field `errorDocument` is optional, if no error document is set a generic
+error message is displayed when errors happen. Conversely, if `enabled` is
+`false`, neither `indexDocument` nor `errorDocument` must be specified.
+
+In `quotas`: new values of `maxSize` and `maxObjects` must both be specified, or set to `null`
+to remove the quotas. An absent value will be considered the same as a `null`. It is not possible
+to change only one of the two quotas.
+
+### Operations on permissions for keys on buckets
+
+#### BucketAllowKey `POST /v0/bucket/allow`
+
+Allows a key to do read/write/owner operations on a bucket.
+
+Request body format:
+
+```json
+{
+    "bucketId": "e6a14cd6a27f48684579ec6b381c078ab11697e6bc8513b72b2f5307e25fff9b",
+    "accessKeyId": "GK31c2f218a2e44f485b94239e",
+    "permissions": {
+        "read": true,
+        "write": true,
+        "owner": true
+    },
+}
+```
+
+Flags in `permissions` which have the value `true` will be activated.
+Other flags will remain unchanged.
+
+#### BucketDenyKey `POST /v0/bucket/deny`
+
+Denies a key from doing read/write/owner operations on a bucket.
+
+Request body format:
+
+```json
+{
+    "bucketId": "e6a14cd6a27f48684579ec6b381c078ab11697e6bc8513b72b2f5307e25fff9b",
+    "accessKeyId": "GK31c2f218a2e44f485b94239e",
+    "permissions": {
+        "read": false,
+        "write": false,
+        "owner": true
+    },
+}
+```
+
+Flags in `permissions` which have the value `true` will be deactivated.
+Other flags will remain unchanged.
+
+
+### Operations on bucket aliases
+
+#### GlobalAliasBucket `PUT /v0/bucket/alias/global?id=<bucket id>&alias=<global alias>`
+
+Empty body. Creates a global alias for a bucket.
+
+#### GlobalUnaliasBucket `DELETE /v0/bucket/alias/global?id=<bucket id>&alias=<global alias>`
+
+Removes a global alias for a bucket.
+
+#### 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 /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.
+

doc/book/reference-manual/configuration.md

@@ -13,9 +13,6 @@ db_engine = "lmdb"
 
 block_size = 1048576
 
-sled_cache_capacity = 134217728
-sled_flush_every_ms = 2000
-
 replication_mode = "3"
 
 compression_level = 1
@@ -31,20 +28,15 @@ bootstrap_peers = [
     "212fd62eeaca72c122b45a7f4fa0f55e012aa5e24ac384a72a3016413fa724ff@[fc00:F::1]:3901",
 ]
 
+consul_host = "consul.service"
+consul_service_name = "garage-daemon"
 
-[consul_discovery]
+kubernetes_namespace = "garage"
-consul_http_addr = "http://127.0.0.1:8500"
+kubernetes_service_name = "garage-daemon"
-service_name = "garage-daemon"
+kubernetes_skip_crd = false
-ca_cert = "/etc/consul/consul-ca.crt"
-client_cert = "/etc/consul/consul-client.crt"
-client_key = "/etc/consul/consul-key.crt"
-tls_skip_verify = false
-
-[kubernetes_discovery]
-namespace = "garage"
-service_name = "garage-daemon"
-skip_crd = false
 
+sled_cache_capacity = 134217728
+sled_flush_every_ms = 2000
 
 [s3_api]
 api_bind_addr = "[::]:3900"
@@ -137,21 +129,6 @@ files will remain available. This however means that chunks from existing files
 will not be deduplicated with chunks from newly uploaded files, meaning you
 might use more storage space that is optimally possible.
 
-### `sled_cache_capacity`
-
-This parameter can be used to tune the capacity of the cache used by
-[sled](https://sled.rs), the database Garage uses internally to store metadata.
-Tune this to fit the RAM you wish to make available to your Garage instance.
-This value has a conservative default (128MB) so that Garage doesn't use too much
-RAM by default, but feel free to increase this for higher performance.
-
-### `sled_flush_every_ms`
-
-This parameters can be used to tune the flushing interval of sled.
-Increase this if sled is thrashing your SSD, at the risk of losing more data in case
-of a power outage (though this should not matter much as data is replicated on other
-nodes). The default value, 2000ms, should be appropriate for most use cases.
-
 ### `replication_mode`
 
 Garage supports the following replication modes:
@@ -299,58 +276,48 @@ be obtained by running `garage node id` and then included directly in the
 key will be returned by `garage node id` and you will have to add the IP
 yourself.
 
-
+### `consul_host` and `consul_service_name`
-## The `[consul_discovery]` section
 
 Garage supports discovering other nodes of the cluster using Consul.  For this
 to work correctly, nodes need to know their IP address by which they can be
 reached by other nodes of the cluster, which should be set in `rpc_public_addr`.
 
-### `consul_http_addr` and `service_name`
+The `consul_host` parameter should be set to the hostname of the Consul server,
-
+and `consul_service_name` should be set to the service name under which Garage's
-The `consul_http_addr` parameter should be set to the full HTTP(S) address of the Consul server.
-
-### `service_name`
-
-`service_name` should be set to the service name under which Garage's
 RPC ports are announced.
 
-### `client_cert`, `client_key`
+Garage does not yet support talking to Consul over TLS.
 
-TLS client certificate and client key to use when communicating with Consul over TLS. Both are mandatory when doing so.
+### `kubernetes_namespace`, `kubernetes_service_name` and `kubernetes_skip_crd`
-
-### `ca_cert`
-
-TLS CA certificate to use when communicating with Consul over TLS.
-
-### `tls_skip_verify`
-
-Skip server hostname verification in TLS handshake.
-`ca_cert` is ignored when this is set.
-
-
-## 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
+resources. For this to work `kubernetes_namespace` and `kubernetes_service_name`
-with at least the `namespace` and `service_name` parameters.
+need to be configured.
 
-### `namespace`
+`kubernetes_namespace` sets the namespace in which the custom resources are
-
+configured. `kubernetes_service_name` is added as a label to these resources to
-`namespace` sets the namespace in which the custom resources are
-configured.
-
-### `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`
+`kubernetes_skip_crd` can be set to true to disable the automatic creation and
-
-`skip_crd` can be set to true to disable the automatic creation and
 patching of the `garagenodes.deuxfleurs.fr` CRD. You will need to create the CRD
 manually.
 
+### `sled_cache_capacity`
+
+This parameter can be used to tune the capacity of the cache used by
+[sled](https://sled.rs), the database Garage uses internally to store metadata.
+Tune this to fit the RAM you wish to make available to your Garage instance.
+This value has a conservative default (128MB) so that Garage doesn't use too much
+RAM by default, but feel free to increase this for higher performance.
+
+### `sled_flush_every_ms`
+
+This parameters can be used to tune the flushing interval of sled.
+Increase this if sled is thrashing your SSD, at the risk of losing more data in case
+of a power outage (though this should not matter much as data is replicated on other
+nodes). The default value, 2000ms, should be appropriate for most use cases.
+
+
 
 ## The `[s3_api]` section
 

doc/book/reference-manual/features.md

@@ -106,7 +106,7 @@ to be manually connected to one another.
 
 ### Support for changing IP addresses
 
-As long as all of your nodes don't change their IP address at the same time,
+As long as all of your nodes don't thange their IP address at the same time,
 Garage should be able to tolerate nodes with changing/dynamic IP addresses,
 as nodes will regularly exchange the IP addresses of their peers and try to
 reconnect using newer addresses when existing connections are broken.

doc/book/working-documents/_index.md

@@ -1,6 +1,6 @@
 +++
 title = "Working Documents"
-weight = 8
+weight = 7
 sort_by = "weight"
 template = "documentation.html"
 +++

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

@@ -1,6 +1,6 @@
 +++
 title = "Design draft (obsolete)"
-weight = 900
+weight = 50
 +++
 
 **WARNING: this documentation is a design draft which was written before Garage's actual implementation.

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

@@ -1,6 +1,6 @@
 +++
 title = "Load balancing data (obsolete)"
-weight = 910
+weight = 60
 +++
 
 **This is being yet improved in release 0.5. The working document has not been updated yet, it still only applies to Garage 0.2 through 0.4.**

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

@@ -1,75 +0,0 @@
-+++
-title = "Testing strategy"
-weight = 30
-+++
-
-
-## Testing Garage
-
-Currently, we have the following tests:
-
-- some unit tests spread around the codebase
-- integration tests written in Rust (`src/garage/test`) to check that Garage operations perform correctly
-- integration test for compatibility with external tools (`script/test-smoke.sh`)
-
-We have also tried `minio/mint` but it fails a lot and for now we haven't gotten a lot from it.
-
-In the future:
-
-1. We'd like to have a systematic way of testing with `minio/mint`,
-   it would add value to Garage by providing a compatibility score and reference that can be trusted.
-2. We'd also like to do testing with Jepsen in some way.
-
-## How to instrument Garagae
-
-We should try to test in least invasive ways, i.e. minimize the impact of the testing framework on Garage's source code. This means for example:
-
-- Not abstracting IO/nondeterminism in the source code
-- Not making `garage` a shared library (launch using `execve`, it's perfectly fine)
-
-Instead, we should focus on building a clean outer interface for the `garage` binary,
-for example loading configuration using environnement variables instead of the configuration file if that's helpfull for writing the tests.
-
-There are two reasons for this:
-
-- Keep the soure code clean and focused
-- Test something that is as close as possible as the true garage that will actually be running
-
-Reminder: rules of simplicity, concerning changes to Garage's source code.
-Always question what we are doing.
-Never do anything just because it looks nice or because we "think" it might be usefull at some later point but without knowing precisely why/when.
-Only do things that make perfect sense in the context of what we currently know.
-
-## References
-
-Testing is a research field on its own.
-About testing distributed systems:
-
- - [Jepsen](https://jepsen.io/) is a testing framework designed to test distributed systems. It can mock some part of the system like the time and the network.
- - [FoundationDB Testing Approach](https://www.micahlerner.com/2021/06/12/foundationdb-a-distributed-unbundled-transactional-key-value-store.html#what-is-unique-about-foundationdbs-testing-framework). They chose to abstract "all sources of nondeterminism and communication are abstracted, including network, disk, time, and pseudo random number generator" to be able to run tests by simulating faults.
- - [Testing Distributed Systems](https://asatarin.github.io/testing-distributed-systems/) - Curated list of resources on testing distributed systems
- 
-About S3 compatibility:
-  - [ceph/s3-tests](https://github.com/ceph/s3-tests)
-  - (deprecated) [minio/s3verify](https://blog.min.io/s3verify-a-simple-tool-to-verify-aws-s3-api-compatibility/)
-  - [minio/mint](https://github.com/minio/mint)
-
-About benchmarking S3 (I think it is not necessarily very relevant for this iteration):
-  - [minio/warp](https://github.com/minio/warp)
-  - [wasabi-tech/s3-benchmark](https://github.com/wasabi-tech/s3-benchmark)
-  - [dvassallo/s3-benchmark](https://github.com/dvassallo/s3-benchmark)
-  - [intel-cloud/cosbench](https://github.com/intel-cloud/cosbench) - used by Ceph
-  
-Engineering blog posts:
- - [Quincy @ Scale: A Tale of Three Large-Scale Clusters](https://ceph.io/en/news/blog/2022/three-large-scale-clusters/)
-
-Interesting blog posts on the blog of the Sled database: 
-
-- <https://sled.rs/simulation.html>
-- <https://sled.rs/perf.html>
-  
-Misc:
-  - [mutagen](https://github.com/llogiq/mutagen) - mutation testing is a way to assert our test quality by mutating the code and see if the mutation makes the tests fail
-  - [fuzzing](https://rust-fuzz.github.io/book/) - cargo supports fuzzing, it could be a way to test our software reliability in presence of garbage data.
-  
-

doc/drafts/k2v-spec.md

@@ -207,7 +207,7 @@ and responses need to be translated.
 Query parameters:
 
 | name | default value | meaning |
-|------------|---------------|----------------------------------|
+| - | - | - |
 | `sort_key` | **mandatory** | The sort key of the item to read |
 
 Returns the item with specified partition key and sort key. Values can be
@@ -318,7 +318,7 @@ an HTTP 304 NOT MODIFIED is returned.
 Query parameters:
 
 | name | default value | meaning |
-|-------------------|---------------|----------------------------------------------------------------------------|
+| - | - | - |
 | `sort_key` | **mandatory** | The sort key of the item to read |
 | `causality_token` | **mandatory** | The causality token of the last known value or set of values |
 | `timeout` | 300 | The timeout before 304 NOT MODIFIED is returned if the value isn't updated |
@@ -346,7 +346,7 @@ myblobblahblahblah
 Example response:
 
 ```
-HTTP/1.1 204 No Content
+HTTP/1.1 200 OK
 ```
 
 **DeleteItem: `DELETE /<bucket>/<partition key>?sort_key=<sort_key>`**
@@ -383,7 +383,7 @@ as these values are asynchronously updated, and thus eventually consistent.
 Query parameters:
 
 | name | default value | meaning |
-|-----------|---------------|----------------------------------------------------------------|
+| - | - | - |
 | `prefix` | `null` | Restrict listing to partition keys that start with this prefix |
 | `start` | `null` | First partition key to list, in lexicographical order |
 | `end` | `null` | Last partition key to list (excluded) |
@@ -512,7 +512,7 @@ POST /my_bucket HTTP/1.1
 Example response:
 
 ```
-HTTP/1.1 204 NO CONTENT
+HTTP/1.1 200 OK
 ```
 
 
@@ -526,7 +526,7 @@ items to get (to get single items, set `singleItem` to `true`). A search is a
 JSON struct with the following fields:
 
 | name | default value | meaning |
-|-----------------|---------------|----------------------------------------------------------------------------------------|
+| - | - | - |
 | `partitionKey` | **mandatory** | The partition key in which to search |
 | `prefix` | `null` | Restrict items to list to those whose sort keys start with this prefix |
 | `start` | `null` | The sort key of the first item to read |
@@ -683,7 +683,7 @@ POST /my_bucket?delete HTTP/1.1
 
 Example response:
 
-```json
+```
 HTTP/1.1 200 OK
 
 [

doc/optimal_layout_report/.gitignore

@@ -0,0 +1,5 @@
+optimal_layout.aux
+optimal_layout.log
+optimal_layout.synctex.gz
+optimal_layout.bbl
+optimal_layout.blg

doc/optimal_layout_report/optimal_layout.bib

@@ -0,0 +1,11 @@
+
+@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}
+}

doc/optimal_layout_report/optimal_layout.tex

@@ -0,0 +1,709 @@
+\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}
+
+
+

nix/common.nix

@@ -3,20 +3,20 @@ rec {
    * Fixed dependencies
    */
   pkgsSrc = fetchTarball {
-    # As of 2022-10-13
+    # As of 2021-10-04
-    url = "https://github.com/NixOS/nixpkgs/archive/a3073c49bc0163fea6a121c276f526837672b555.zip";
+    url = "https://github.com/NixOS/nixpkgs/archive/b27d18a412b071f5d7991d1648cfe78ee7afe68a.tar.gz";
-    sha256 = "1bz632psfbpmicyzjb8b4265y50shylccvfm6ry6mgnv5hvz324s";
+    sha256 = "1xy9zpypqfxs5gcq5dcla4bfkhxmh5nzn9dyqkr03lqycm9wg5cr";
   };
   cargo2nixSrc = fetchGit {
-    # As of 2022-10-18: two small patches over unstable branch, one for clippy and one to fix feature detection
+    # As of 2022-08-29, stacking two patches: superboum@dedup_propagate and Alexis211@fix_fetchcrategit
     url = "https://github.com/Alexis211/cargo2nix";
-    ref = "custom_unstable";
+    ref = "fix_fetchcrategit";
-    rev = "a7a61179b66054904ef6a195d8da736eaaa06c36";
+    rev = "4b31c0cc05b6394916d46e9289f51263d81973b9";
   };
 
   /*
    * Shared objects
    */
   cargo2nix = import cargo2nixSrc;
-  cargo2nixOverlay = cargo2nix.overlays.default;
+  cargo2nixOverlay = import "${cargo2nixSrc}/overlay";
 }

nix/compile.nix

@@ -1,10 +1,9 @@
 {
   system ? builtins.currentSystem,
-  target,
+  target ? null,
   compiler ? "rustc",
   release ? false,
   git_version ? null,
-  features ? null,
 }:
 
 with import ./common.nix;
@@ -14,18 +13,23 @@ let
 
   pkgs = import pkgsSrc {
     inherit system; 
-    crossSystem = {
+    ${ if target == null then null else "crossSystem" } = { config = target; };
-      config = target;
-      isStatic = true;
-    };
     overlays = [ cargo2nixOverlay ];
   };
 
+  /*
+   Rust and Nix triples are not the same. Cargo2nix has a dedicated library
+   to convert Nix triples to Rust ones. We need this conversion as we want to
+   set later options linked to our (rust) target in a generic way. Not only
+   the triple terminology is different, but also the "roles" are named differently.
+   Nix uses a build/host/target terminology where Nix's "host" maps to Cargo's "target".
+  */
+  rustTarget = log (pkgs.rustBuilder.rustLib.rustTriple pkgs.stdenv.hostPlatform);
+
   /*
    Cargo2nix is built for rustOverlay which installs Rust from Mozilla releases.
-   This is fine for 64-bit platforms, but for 32-bit platforms, we need our own Rust
+   We want our own Rust to avoid incompatibilities, like we had with musl 1.2.0.
-   to avoid incompatibilities with time_t between different versions of musl
+   rustc was built with musl < 1.2.0 and nix shipped musl >= 1.2.0 which lead to compilation breakage.
-   (>= 1.2.0 shipped by NixOS, < 1.2.0 with which rustc was built), which lead to compilation breakage.
    So we want a Rust release that is bound to our Nix repository to avoid these problems.
    See here for more info: https://musl.libc.org/time64.html
    Because Cargo2nix does not support the Rust environment shipped by NixOS,
@@ -33,21 +37,46 @@ let
    In practise, rustOverlay ships rustc+cargo in a single derivation while
    NixOS ships them in separate ones. We reunite them with symlinkJoin.
    */
-  toolchainOptions =
+  rustChannel = {
-    if target == "x86_64-unknown-linux-musl" || target == "aarch64-unknown-linux-musl" then {
+    rustc = pkgs.symlinkJoin {
-      rustVersion = "1.63.0";
+      name = "rust-channel";
-      extraRustComponents = [ "clippy" ];
-    } else {
-      rustToolchain = pkgs.symlinkJoin {
-        name = "rust-static-toolchain-${target}";
       paths = [ 
         pkgs.rustPlatform.rust.cargo
         pkgs.rustPlatform.rust.rustc
-          # clippy not needed, it only runs on amd64
       ];
     };
+    clippy = pkgs.symlinkJoin {
+      name = "clippy-channel";
+      paths = [ 
+        pkgs.rustPlatform.rust.cargo
+        pkgs.rustPlatform.rust.rustc
+        pkgs.clippy
+      ];
     };
+  }.${compiler};
 
+  clippyBuilder = pkgs.writeScriptBin "clippy" ''
+    #!${pkgs.stdenv.shell}
+    . ${cargo2nixSrc + "/overlay/utils.sh"}
+    isBuildScript=
+    args=("$@")
+    for i in "''${!args[@]}"; do
+      if [ "xmetadata=" = "x''${args[$i]::9}" ]; then
+        args[$i]=metadata=$NIX_RUST_METADATA
+      elif [ "x--crate-name" = "x''${args[$i]}" ] && [ "xbuild_script_" = "x''${args[$i+1]::13}" ]; then
+        isBuildScript=1
+      fi
+    done
+    if [ "$isBuildScript" ]; then
+      args+=($NIX_RUST_BUILD_LINK_FLAGS)
+    else
+      args+=($NIX_RUST_LINK_FLAGS)
+    fi
+    touch invoke.log
+    echo "''${args[@]}" >>invoke.log
+
+    exec ${rustChannel}/bin/clippy-driver --deny warnings "''${args[@]}"
+  '';
 
   buildEnv = (drv: {
     rustc = drv.setBuildEnv;
@@ -57,8 +86,7 @@ let
       echo --- BUILDING WITH CLIPPY ---
       echo 
 
-      export NIX_RUST_BUILD_FLAGS="''${NIX_RUST_BUILD_FLAGS} --deny warnings"
+      export RUSTC=${clippyBuilder}/bin/clippy
-      export RUSTC="''${CLIPPY_DRIVER}"
     '';
   }.${compiler});
 
@@ -69,7 +97,7 @@ let
    You can have a complete list of the available options by looking at the overriden object, mkcrate:
    https://github.com/cargo2nix/cargo2nix/blob/master/overlay/mkcrate.nix
   */
-  packageOverrides = pkgs: pkgs.rustBuilder.overrides.all ++ [
+  overrides = pkgs.rustBuilder.overrides.all ++ [
     /*
      [1] We add some logic to compile our crates with clippy, it provides us many additional lints
 
@@ -85,7 +113,12 @@ let
      As we do not want to consider the .git folder as part of the input source,
      we ask the user (the CI often) to pass the value to Nix.
 
-     [4] We don't want libsodium-sys and zstd-sys to try to use pkgconfig to build against a system library.
+     [4] We ship some parts of the code disabled by default by putting them behind a flag.
+     It speeds up the compilation (when the feature is not required) and released crates have less dependency by default (less attack surface, disk space, etc.).
+     But we want to ship these additional features when we release Garage.
+     In the end, we chose to exclude all features from debug builds while putting (all of) them in the release builds.
+
+     [5] We don't want libsodium-sys and zstd-sys to try to use pkgconfig to build against a system library.
      However the features to do so get activated for some reason (due to a bug in cargo2nix?),
      so disable them manually here.
     */
@@ -103,6 +136,10 @@ let
         /* [1] */ setBuildEnv = (buildEnv drv);
         /* [2] */ hardeningDisable = [ "pie" ];
       };
+      overrideArgs = old: {
+        /* [4] */ features = [ "bundled-libs" "sled" "metrics" "k2v" ]
+          ++ (if release then [ "kubernetes-discovery" "telemetry-otlp" "lmdb" "sqlite" ] else []);
+      };
     })
 
     (pkgs.rustBuilder.rustLib.makeOverride {
@@ -153,39 +190,18 @@ let
     (pkgs.rustBuilder.rustLib.makeOverride {
       name = "libsodium-sys";
       overrideArgs = old: {
-        features = [ ]; /* [4] */
+        features = [ ]; /* [5] */
       };
     })
 
     (pkgs.rustBuilder.rustLib.makeOverride {
       name = "zstd-sys";
       overrideArgs = old: {
-        features = [ ]; /* [4] */
+        features = [ ]; /* [5] */
       };
     })
   ];
 
-  /*
-    We ship some parts of the code disabled by default by putting them behind a flag.
-    It speeds up the compilation (when the feature is not required) and released crates have less dependency by default (less attack surface, disk space, etc.).
-    But we want to ship these additional features when we release Garage.
-    In the end, we chose to exclude all features from debug builds while putting (all of) them in the release builds.
-  */
-  rootFeatures = if features != null then features else
-     ([
-       "garage/bundled-libs"
-       "garage/sled"
-       "garage/k2v"
-     ] ++ (if release then [
-       "garage/consul-discovery"
-       "garage/kubernetes-discovery"
-       "garage/metrics"
-       "garage/telemetry-otlp"
-       "garage/lmdb"
-       "garage/sqlite"
-     ] else []));
-
-
   packageFun = import ../Cargo.nix;
 
   /*
@@ -206,15 +222,23 @@ let
    "x86_64-unknown-linux-musl" = [ "target-feature=+crt-static" "link-arg=-static-pie" ];
   };
 
-  /*
-    NixOS and Rust/Cargo triples do not match for ARM, fix it here.
-  */
-  rustTarget = if target == "armv6l-unknown-linux-musleabihf"
-    then "arm-unknown-linux-musleabihf"
-    else target;
-
 in
-  pkgs.rustBuilder.makePackageSet ({
+  /*
-    inherit release packageFun packageOverrides codegenOpts rootFeatures;
+   The following definition is not elegant as we use a low level function of Cargo2nix
-    target = rustTarget;
+   that enables us to pass our custom rustChannel object. We need this low level definition
-  } // toolchainOptions)
+   to pass Nix's Rust toolchains instead of Mozilla's one.
+
+   target is mandatory but must be kept to null to allow cargo2nix to set it to the appropriate value
+   for each crate.
+  */ 
+  pkgs.rustBuilder.makePackageSet {
+    inherit packageFun rustChannel release codegenOpts;
+    packageOverrides = overrides;
+    target = null;
+
+    buildRustPackages = pkgs.buildPackages.rustBuilder.makePackageSet {
+      inherit rustChannel packageFun codegenOpts;
+      packageOverrides = overrides;
+      target = null;
+    };
+  }

nix/toolchain.nix

@@ -6,24 +6,19 @@ with import ./common.nix;
 
 let
   platforms = [
-    #"x86_64-unknown-linux-musl"
+    "x86_64-unknown-linux-musl"
     "i686-unknown-linux-musl"
-    #"aarch64-unknown-linux-musl"
+    "aarch64-unknown-linux-musl"
     "armv6l-unknown-linux-musleabihf"
   ];
   pkgsList = builtins.map (target: import pkgsSrc { 
     inherit system; 
-    crossSystem = {
+    crossSystem = { config = target; };
-      config = target;
-      isStatic = true;
-    };
-    overlays = [ cargo2nixOverlay ];
   }) platforms;
   pkgsHost = import pkgsSrc {};
   lib = pkgsHost.lib;
   kaniko = (import ./kaniko.nix) pkgsHost;
   winscp = (import ./winscp.nix) pkgsHost;
-  manifestTool = (import ./manifest-tool.nix) pkgsHost;
 in 
   lib.flatten (builtins.map (pkgs: [
      pkgs.rustPlatform.rust.rustc
@@ -32,6 +27,5 @@ in
   ]) pkgsList) ++ [
     kaniko
     winscp
-    manifestTool
   ]
 

script/helm/garage/Chart.yaml

@@ -15,7 +15,7 @@ type: application
 # This is the chart version. This version number should be incremented each time you make changes
 # to the chart and its templates, including the app version.
 # Versions are expected to follow Semantic Versioning (https://semver.org/)
-version: 0.1.3
+version: 0.1.0
 
 # This is the version number of the application being deployed. This version number should be
 # incremented each time you make changes to the application. Versions are not expected to

script/helm/garage/templates/configmap.yaml

@@ -7,7 +7,6 @@ data:
     metadata_dir = "{{ .Values.garage.metadataDir }}"
     data_dir = "{{ .Values.garage.dataDir }}"
 
-    db_engine = "{{ .Values.garage.dbEngine }}"
     replication_mode = "{{ .Values.garage.replicationMode }}"
 
     rpc_bind_addr = "{{ .Values.garage.rpcBindAddr }}"
@@ -16,10 +15,9 @@ data:
 
     bootstrap_peers = {{ .Values.garage.bootstrapPeers }}
 
-    [kubernetes_discovery]
+    kubernetes_namespace = "{{ .Release.Namespace }}"
-    namespace = "{{ .Release.Namespace }}"
+    kubernetes_service_name = "{{ include "garage.fullname" . }}"
-    service_name = "{{ include "garage.fullname" . }}"
+    kubernetes_skip_crd = {{ .Values.garage.kubernetesSkipCrd }}
-    skip_crd = {{ .Values.garage.kubernetesSkipCrd }}
 
     [s3_api]
     s3_region = "{{ .Values.garage.s3.api.region }}"
@@ -30,6 +28,3 @@ data:
     bind_addr = "[::]:3902"
     root_domain = "{{ .Values.garage.s3.web.rootDomain }}"
     index = "{{ .Values.garage.s3.web.index }}"
-
-    [admin]
-    api_bind_addr = "[::]:3903"

script/helm/garage/templates/service.yaml

@@ -15,9 +15,5 @@ spec:
       targetPort: 3902
       protocol: TCP
       name: s3-web
-    - port: 3903
-      targetPort: 3903
-      protocol: TCP
-      name: admin
   selector:
     {{- include "garage.selectorLabels" . | nindent 4 }}

script/helm/garage/templates/statefulset.yaml

@@ -1,17 +1,15 @@
 apiVersion: apps/v1
-kind: {{ .Values.deployment.kind }}
+kind: StatefulSet
 metadata:
   name: {{ include "garage.fullname" . }}
   labels:
     {{- include "garage.labels" . | nindent 4 }}
 spec:
+  replicas: {{ .Values.replicaCount }}
   selector:
     matchLabels:
       {{- include "garage.selectorLabels" . | nindent 6 }}
-  {{- if eq .Values.deployment.kind "StatefulSet" }}
-  replicas: {{ .Values.deployment.replicaCount }}
   serviceName: {{ include "garage.fullname" . }}
-  {{- end }}
   template:
     metadata:
       {{- with .Values.podAnnotations }}
@@ -56,8 +54,6 @@ spec:
               name: s3-api
             - containerPort: 3902
               name: web-api
-            - containerPort: 3903
-              name: admin
           volumeMounts:
             - name: meta
               mountPath: /mnt/meta
@@ -83,23 +79,6 @@ spec:
             name: {{ include "garage.fullname" . }}-config
         - name: etc
           emptyDir: {}
-        {{- if .Values.persistence.enabled }}
-        {{- if eq .Values.deployment.kind "DaemonSet" }}
-        - name: meta
-          hostPath:
-            path: {{ .Values.persistence.meta.hostPath }}
-            type: DirectoryOrCreate
-        - name: data
-          hostPath:
-            path: {{ .Values.persistence.data.hostPath }}
-            type: DirectoryOrCreate
-        {{- end }}
-        {{- else }}
-        - name: meta
-          emptyDir: {}
-        - name: data
-          emptyDir: {}
-        {{- end }}
       {{- with .Values.nodeSelector }}
       nodeSelector:
         {{- toYaml . | nindent 8 }}
@@ -112,7 +91,7 @@ spec:
       tolerations:
         {{- toYaml . | nindent 8 }}
       {{- end }}
-  {{- if and .Values.persistence.enabled (eq .Values.deployment.kind "StatefulSet") }}
+  {{- if .Values.persistence.enabled }}
   volumeClaimTemplates:
   - metadata:
       name: meta

script/helm/garage/values.yaml

@@ -29,18 +29,10 @@ persistence:
   meta:
     # storageClass: "fast-storage-class"
     size: 100Mi
-    # used only for daemon sets
-    hostPath: /var/lib/garage/meta
   data:
     # storageClass: "slow-storage-class"
     size: 100Mi
-    # used only for daemon sets
-    hostPath: /var/lib/garage/data
 
-# Deployment configuration
-deployment:
-  # Switchable to DaemonSet
-  kind: StatefulSet
 # Number of StatefulSet replicas/garage nodes to start
 replicaCount: 3
 

script/test-smoke.sh

@@ -8,7 +8,7 @@ SCRIPT_FOLDER="`dirname \"$0\"`"
 REPO_FOLDER="${SCRIPT_FOLDER}/../"
 GARAGE_DEBUG="${REPO_FOLDER}/target/debug/"
 GARAGE_RELEASE="${REPO_FOLDER}/target/release/"
-NIX_RELEASE="${REPO_FOLDER}/result/bin/:${REPO_FOLDER}/result-bin/bin/"
+NIX_RELEASE="${REPO_FOLDER}/result/bin/"
 PATH="${GARAGE_DEBUG}:${GARAGE_RELEASE}:${NIX_RELEASE}:$PATH"
 CMDOUT=/tmp/garage.cmd.tmp
 

shell.nix

@@ -15,10 +15,20 @@ let
 
 in
   {
+
     /* --- Rust Shell ---
      * Use it to compile Garage
      */
     rust = pkgs.mkShell {
+      shellHook = ''
+function refresh_toolchain {
+  nix copy \
+    --to 's3://nix?endpoint=garage.deuxfleurs.fr&region=garage&secret-key=/etc/nix/signing-key.sec' \
+    $(nix-store -qR \
+      $(nix-build --quiet --no-build-output --no-out-link nix/toolchain.nix))
+}
+      '';
+
       nativeBuildInputs = [
         #pkgs.rustPlatform.rust.rustc
         pkgs.rustPlatform.rust.cargo
@@ -57,33 +67,12 @@ in
      */
     release = pkgs.mkShell {
       shellHook = ''
-function refresh_toolchain {
-  pass show deuxfleurs/nix_priv_key > /tmp/nix-signing-key.sec
-  nix copy \
-    --to 's3://nix?endpoint=garage.deuxfleurs.fr&region=garage&secret-key=/tmp/nix-signing-key.sec' \
-    $(nix-store -qR \
-      $(nix-build --no-build-output --no-out-link nix/toolchain.nix))
-  rm /tmp/nix-signing-key.sec
-}
-
-function refresh_cache {
-  pass show deuxfleurs/nix_priv_key > /tmp/nix-signing-key.sec
-  for attr in clippy.amd64 test.amd64 pkgs.{amd64,i386,arm,arm64}.{debug,release}; do
-    echo "Updating cache for ''${attr}"
-    derivation=$(nix-instantiate --attr ''${attr})
-    nix copy \
-      --to 's3://nix?endpoint=garage.deuxfleurs.fr&region=garage&secret-key=/tmp/nix-signing-key.sec' \
-      $(nix-store -qR ''${derivation%\!bin})
-  done
-  rm /tmp/nix-signing-key.sec
-}
-
 function to_s3 {
   aws \
       --endpoint-url https://garage.deuxfleurs.fr \
       --region garage \
     s3 cp \
-      ./result-bin/bin/garage \
+      ./result/bin/garage \
       s3://garagehq.deuxfleurs.fr/_releases/''${DRONE_TAG:-$DRONE_COMMIT}/''${TARGET}/garage
 }
 

src/api/Cargo.toml

@@ -36,7 +36,7 @@ sha2 = "0.10"
 
 futures = "0.3"
 futures-util = "0.3"
-pin-project = "1.0.11"
+pin-project = "1.0"
 tokio = { version = "1.0", default-features = false, features = ["rt", "rt-multi-thread", "io-util", "net", "time", "macros", "sync", "signal", "fs"] }
 tokio-stream = "0.1"
 

src/api/admin/api_server.rs

@@ -5,7 +5,7 @@ use async_trait::async_trait;
 
 use futures::future::Future;
 use http::header::{ACCESS_CONTROL_ALLOW_METHODS, ACCESS_CONTROL_ALLOW_ORIGIN, ALLOW};
-use hyper::{Body, Request, Response, StatusCode};
+use hyper::{Body, Request, Response};
 
 use opentelemetry::trace::SpanRef;
 
@@ -69,7 +69,7 @@ impl AdminApiServer {
 
 	fn handle_options(&self, _req: &Request<Body>) -> Result<Response<Body>, Error> {
 		Ok(Response::builder()
-			.status(StatusCode::NO_CONTENT)
+			.status(204)
 			.header(ALLOW, "OPTIONS, GET, POST")
 			.header(ACCESS_CONTROL_ALLOW_METHODS, "OPTIONS, GET, POST")
 			.header(ACCESS_CONTROL_ALLOW_ORIGIN, "*")
@@ -94,7 +94,7 @@ impl AdminApiServer {
 				.ok_or_internal_error("Could not serialize metrics")?;
 
 			Ok(Response::builder()
-				.status(StatusCode::OK)
+				.status(200)
 				.header(http::header::CONTENT_TYPE, encoder.format_type())
 				.body(Body::from(buffer))?)
 		}

src/api/admin/bucket.rs

@@ -210,7 +210,7 @@ async fn bucket_info_results(
 				.collect::<Vec<_>>(),
 			objects: counters.get(OBJECTS).cloned().unwrap_or_default(),
 			bytes: counters.get(BYTES).cloned().unwrap_or_default(),
-			unfinished_uploads: counters
+			unfinshed_uploads: counters
 				.get(UNFINISHED_UPLOADS)
 				.cloned()
 				.unwrap_or_default(),
@@ -234,7 +234,7 @@ struct GetBucketInfoResult {
 	keys: Vec<GetBucketInfoKey>,
 	objects: i64,
 	bytes: i64,
-	unfinished_uploads: i64,
+	unfinshed_uploads: i64,
 	quotas: ApiBucketQuotas,
 }
 

src/api/admin/cluster.rs

@@ -151,7 +151,7 @@ pub async fn handle_update_cluster_layout(
 	garage.system.update_cluster_layout(&layout).await?;
 
 	Ok(Response::builder()
-		.status(StatusCode::NO_CONTENT)
+		.status(StatusCode::OK)
 		.body(Body::empty())?)
 }
 
@@ -162,11 +162,16 @@ pub async fn handle_apply_cluster_layout(
 	let param = parse_json_body::<ApplyRevertLayoutRequest>(req).await?;
 
 	let layout = garage.system.get_cluster_layout();
-	let layout = layout.apply_staged_changes(Some(param.version))?;
+	let (layout, msg) = layout.apply_staged_changes(Some(param.version))?;
+	//TODO : how to display msg ? Should it be in the Body Response ?
+	for s in msg.iter() {
+		println!("{}", s);
+	}
+
 	garage.system.update_cluster_layout(&layout).await?;
 
 	Ok(Response::builder()
-		.status(StatusCode::NO_CONTENT)
+		.status(StatusCode::OK)
 		.body(Body::empty())?)
 }
 
@@ -181,7 +186,7 @@ pub async fn handle_revert_cluster_layout(
 	garage.system.update_cluster_layout(&layout).await?;
 
 	Ok(Response::builder()
-		.status(StatusCode::NO_CONTENT)
+		.status(StatusCode::OK)
 		.body(Body::empty())?)
 }
 

src/api/k2v/batch.rs

@@ -42,7 +42,7 @@ pub async fn handle_insert_batch(
 	garage.k2v.rpc.insert_batch(bucket_id, items2).await?;
 
 	Ok(Response::builder()
-		.status(StatusCode::NO_CONTENT)
+		.status(StatusCode::OK)
 		.body(Body::empty())?)
 }
 

src/api/k2v/item.rs

@@ -153,7 +153,7 @@ pub async fn handle_insert_item(
 		.await?;
 
 	Ok(Response::builder()
-		.status(StatusCode::NO_CONTENT)
+		.status(StatusCode::OK)
 		.body(Body::empty())?)
 }
 

src/db/lib.rs

@@ -3,8 +3,7 @@
 extern crate tracing;
 
 #[cfg(not(any(feature = "lmdb", feature = "sled", feature = "sqlite")))]
-compile_error!("Must activate the Cargo feature for at least one DB engine: lmdb, sled or sqlite.");
+//compile_error!("Must activate the Cargo feature for at least one DB engine: lmdb, sled or sqlite.");
-
 #[cfg(feature = "lmdb")]
 pub mod lmdb_adapter;
 #[cfg(feature = "sled")]

src/db/test.rs

@@ -1,5 +1,9 @@
 use crate::*;
 
+use crate::lmdb_adapter::LmdbDb;
+use crate::sled_adapter::SledDb;
+use crate::sqlite_adapter::SqliteDb;
+
 fn test_suite(db: Db) {
 	let tree = db.open_tree("tree").unwrap();
 
@@ -76,10 +80,7 @@ fn test_suite(db: Db) {
 }
 
 #[test]
-#[cfg(feature = "lmdb")]
 fn test_lmdb_db() {
-	use crate::lmdb_adapter::LmdbDb;
-
 	let path = mktemp::Temp::new_dir().unwrap();
 	let db = heed::EnvOpenOptions::new()
 		.max_dbs(100)
@@ -91,10 +92,7 @@ fn test_lmdb_db() {
 }
 
 #[test]
-#[cfg(feature = "sled")]
 fn test_sled_db() {
-	use crate::sled_adapter::SledDb;
-
 	let path = mktemp::Temp::new_dir().unwrap();
 	let db = SledDb::init(sled::open(path.to_path_buf()).unwrap());
 	test_suite(db);
@@ -102,10 +100,7 @@ fn test_sled_db() {
 }
 
 #[test]
-#[cfg(feature = "sqlite")]
 fn test_sqlite_db() {
-	use crate::sqlite_adapter::SqliteDb;
-
 	let db = SqliteDb::init(rusqlite::Connection::open_in_memory().unwrap());
 	test_suite(db);
 }

src/garage/Cargo.toml

@@ -30,11 +30,9 @@ garage_table = { version = "0.8.0", path = "../table" }
 garage_util = { version = "0.8.0", path = "../util" }
 garage_web = { version = "0.8.0", path = "../web" }
 
-backtrace = "0.3"
 bytes = "1.0"
 bytesize = "1.1"
 timeago = "0.3"
-parse_duration = "2.1"
 hex = "0.4"
 tracing = { version = "0.1.30", features = ["log-always"] }
 tracing-subscriber = { version = "0.3", features = ["env-filter"] }
@@ -60,7 +58,7 @@ opentelemetry-otlp = { version = "0.10", optional = true }
 prometheus = { version = "0.13", optional = true }
 
 [dev-dependencies]
-aws-sdk-s3 = "0.19"
+aws-sdk-s3 = "0.8"
 chrono = "0.4"
 http = "0.2"
 hmac = "0.12"
@@ -83,8 +81,6 @@ sled = [ "garage_model/sled" ]
 lmdb = [ "garage_model/lmdb" ]
 sqlite = [ "garage_model/sqlite" ]
 
-# Automatic registration and discovery via Consul API
-consul-discovery = [ "garage_rpc/consul-discovery" ]
 # Automatic registration and discovery via Kubernetes API
 kubernetes-discovery = [ "garage_rpc/kubernetes-discovery" ]
 # Prometheus exporter (/metrics endpoint).

src/garage/admin.rs

@@ -85,9 +85,6 @@ impl AdminRpcHandler {
 			BucketOperation::Deny(query) => self.handle_bucket_deny(query).await,
 			BucketOperation::Website(query) => self.handle_bucket_website(query).await,
 			BucketOperation::SetQuotas(query) => self.handle_bucket_set_quotas(query).await,
-			BucketOperation::CleanupIncompleteUploads(query) => {
-				self.handle_bucket_cleanup_incomplete_uploads(query).await
-			}
 		}
 	}
 
@@ -515,42 +512,6 @@ impl AdminRpcHandler {
 		)))
 	}
 
-	async fn handle_bucket_cleanup_incomplete_uploads(
-		&self,
-		query: &CleanupIncompleteUploadsOpt,
-	) -> Result<AdminRpc, Error> {
-		let mut bucket_ids = vec![];
-		for b in query.buckets.iter() {
-			bucket_ids.push(
-				self.garage
-					.bucket_helper()
-					.resolve_global_bucket_name(b)
-					.await?
-					.ok_or_bad_request(format!("Bucket not found: {}", b))?,
-			);
-		}
-
-		let duration = parse_duration::parse::parse(&query.older_than)
-			.ok_or_bad_request("Invalid duration passed for --older-than parameter")?;
-
-		let mut ret = String::new();
-		for bucket in bucket_ids {
-			let count = self
-				.garage
-				.bucket_helper()
-				.cleanup_incomplete_uploads(&bucket, duration)
-				.await?;
-			writeln!(
-				&mut ret,
-				"Bucket {:?}: {} incomplete uploads aborted",
-				bucket, count
-			)
-			.unwrap();
-		}
-
-		Ok(AdminRpc::Ok(ret))
-	}
-
 	async fn handle_key_cmd(&self, cmd: &KeyOperation) -> Result<AdminRpc, Error> {
 		match cmd {
 			KeyOperation::List => self.handle_list_keys().await,

src/garage/cli/layout.rs

@@ -14,8 +14,8 @@ pub async fn cli_layout_command_dispatch(
 	rpc_host: NodeID,
 ) -> Result<(), Error> {
 	match cmd {
-		LayoutOperation::Assign(configure_opt) => {
+		LayoutOperation::Assign(assign_opt) => {
-			cmd_assign_role(system_rpc_endpoint, rpc_host, configure_opt).await
+			cmd_assign_role(system_rpc_endpoint, rpc_host, assign_opt).await
 		}
 		LayoutOperation::Remove(remove_opt) => {
 			cmd_remove_role(system_rpc_endpoint, rpc_host, remove_opt).await
@@ -27,6 +27,9 @@ pub async fn cli_layout_command_dispatch(
 		LayoutOperation::Revert(revert_opt) => {
 			cmd_revert_layout(system_rpc_endpoint, rpc_host, revert_opt).await
 		}
+		LayoutOperation::Config(config_opt) => {
+			cmd_config_layout(system_rpc_endpoint, rpc_host, config_opt).await
+		}
 	}
 }
 
@@ -166,7 +169,7 @@ pub async fn cmd_show_layout(
 	rpc_cli: &Endpoint<SystemRpc, ()>,
 	rpc_host: NodeID,
 ) -> Result<(), Error> {
-	let mut layout = fetch_layout(rpc_cli, rpc_host).await?;
+	let layout = fetch_layout(rpc_cli, rpc_host).await?;
 
 	println!("==== CURRENT CLUSTER LAYOUT ====");
 	if !print_cluster_layout(&layout) {
@@ -176,9 +179,16 @@ pub async fn cmd_show_layout(
 	println!();
 	println!("Current cluster layout version: {}", layout.version);
 
-	if print_staging_role_changes(&layout) {
+	let has_role_changes = print_staging_role_changes(&layout);
-		layout.roles.merge(&layout.staging);
+	let has_param_changes = print_staging_parameters_changes(&layout);
+	if has_role_changes || has_param_changes {
+		let v = layout.version;
+		let res_apply = layout.apply_staged_changes(Some(v + 1));
 
+		// this will print the stats of what partitions
+		// will move around when we apply
+		match res_apply {
+			Ok((layout, msg)) => {
 				println!();
 				println!("==== NEW CLUSTER LAYOUT AFTER APPLYING CHANGES ====");
 				if !print_cluster_layout(&layout) {
@@ -186,20 +196,27 @@ pub async fn cmd_show_layout(
 				}
 				println!();
 
-		// this will print the stats of what partitions
+				for line in msg.iter() {
-		// will move around when we apply
+					println!("{}", line);
-		if layout.calculate_partition_assignation() {
+				}
 				println!("To enact the staged role changes, type:");
 				println!();
-			println!("    garage layout apply --version {}", layout.version + 1);
+				println!("    garage layout apply --version {}", v + 1);
 				println!();
 				println!(
                     "You can also revert all proposed changes with: garage layout revert --version {}",
-				layout.version + 1
+                    v + 1)
-			);
+			}
-		} else {
+			Err(Error::Message(s)) => {
-			println!("Not enough nodes have an assigned role to maintain enough copies of data.");
+				println!("Error while trying to compute the assignation: {}", s);
 				println!("This new layout cannot yet be applied.");
+				println!(
+                    "You can also revert all proposed changes with: garage layout revert --version {}",
+                    v + 1)
+			}
+			_ => {
+				println!("Unknown Error");
+			}
 		}
 	}
 
@@ -213,7 +230,10 @@ pub async fn cmd_apply_layout(
 ) -> Result<(), Error> {
 	let layout = fetch_layout(rpc_cli, rpc_host).await?;
 
-	let layout = layout.apply_staged_changes(apply_opt.version)?;
+	let (layout, msg) = layout.apply_staged_changes(apply_opt.version)?;
+	for line in msg.iter() {
+		println!("{}", line);
+	}
 
 	send_layout(rpc_cli, rpc_host, layout).await?;
 
@@ -238,6 +258,37 @@ pub async fn cmd_revert_layout(
 	Ok(())
 }
 
+pub async fn cmd_config_layout(
+	rpc_cli: &Endpoint<SystemRpc, ()>,
+	rpc_host: NodeID,
+	config_opt: ConfigLayoutOpt,
+) -> Result<(), Error> {
+	let mut layout = fetch_layout(rpc_cli, rpc_host).await?;
+
+	match config_opt.redundancy {
+		None => (),
+		Some(r) => {
+			if r > layout.replication_factor {
+				println!(
+					"The zone redundancy must be smaller or equal to the \
+                replication factor ({}).",
+					layout.replication_factor
+				);
+			} else if r < 1 {
+				println!("The zone redundancy must be at least 1.");
+			} else {
+				layout
+					.staged_parameters
+					.update(LayoutParameters { zone_redundancy: r });
+				println!("The new zone redundancy has been saved ({}).", r);
+			}
+		}
+	}
+
+	send_layout(rpc_cli, rpc_host, layout).await?;
+	Ok(())
+}
+
 // --- utility ---
 
 pub async fn fetch_layout(
@@ -269,21 +320,29 @@ pub async fn send_layout(
 }
 
 pub fn print_cluster_layout(layout: &ClusterLayout) -> bool {
-	let mut table = vec!["ID\tTags\tZone\tCapacity".to_string()];
+	let mut table = vec!["ID\tTags\tZone\tCapacity\tUsable".to_string()];
 	for (id, _, role) in layout.roles.items().iter() {
 		let role = match &role.0 {
 			Some(r) => r,
 			_ => continue,
 		};
 		let tags = role.tags.join(",");
+		let usage = layout.get_node_usage(id).unwrap_or(0);
+		let capacity = layout.get_node_capacity(id).unwrap_or(1);
 		table.push(format!(
-			"{:?}\t{}\t{}\t{}",
+			"{:?}\t{}\t{}\t{}\t{} ({:.1}%)",
 			id,
 			tags,
 			role.zone,
-			role.capacity_string()
+			role.capacity_string(),
+			usage as u32 * layout.partition_size,
+			(100.0 * usage as f32 * layout.partition_size as f32) / (capacity as f32)
 		));
 	}
+	println!();
+	println!("Parameters of the layout computation:");
+	println!("Zone redundancy: {}", layout.parameters.zone_redundancy);
+	println!();
 	if table.len() == 1 {
 		false
 	} else {
@@ -292,6 +351,20 @@ pub fn print_cluster_layout(layout: &ClusterLayout) -> bool {
 	}
 }
 
+pub fn print_staging_parameters_changes(layout: &ClusterLayout) -> bool {
+	let has_changes = layout.staged_parameters.get().clone() != layout.parameters;
+	if has_changes {
+		println!();
+		println!("==== NEW LAYOUT PARAMETERS ====");
+		println!(
+			"Zone redundancy: {}",
+			layout.staged_parameters.get().zone_redundancy
+		);
+		println!();
+	}
+	has_changes
+}
+
 pub fn print_staging_role_changes(layout: &ClusterLayout) -> bool {
 	let has_changes = layout
 		.staging

src/garage/cli/structs.rs

@@ -87,6 +87,10 @@ pub enum LayoutOperation {
 	#[structopt(name = "remove", version = garage_version())]
 	Remove(RemoveRoleOpt),
 
+	/// Configure parameters value for the layout computation
+	#[structopt(name = "config", version = garage_version())]
+	Config(ConfigLayoutOpt),
+
 	/// Show roles currently assigned to nodes and changes staged for commit
 	#[structopt(name = "show", version = garage_version())]
 	Show,
@@ -110,7 +114,7 @@ pub struct AssignRoleOpt {
 	#[structopt(short = "z", long = "zone")]
 	pub(crate) zone: Option<String>,
 
-	/// Capacity (in relative terms, use 1 to represent your smallest server)
+	/// Capacity (in relative terms)
 	#[structopt(short = "c", long = "capacity")]
 	pub(crate) capacity: Option<u32>,
 
@@ -133,6 +137,13 @@ pub struct RemoveRoleOpt {
 	pub(crate) node_id: String,
 }
 
+#[derive(StructOpt, Debug)]
+pub struct ConfigLayoutOpt {
+	/// Zone redundancy parameter
+	#[structopt(short = "r", long = "redundancy")]
+	pub(crate) redundancy: Option<usize>,
+}
+
 #[derive(StructOpt, Debug)]
 pub struct ApplyLayoutOpt {
 	/// Version number of new configuration: this command will fail if
@@ -189,10 +200,6 @@ pub enum BucketOperation {
 	/// Set the quotas for this bucket
 	#[structopt(name = "set-quotas", version = garage_version())]
 	SetQuotas(SetQuotasOpt),
-
-	/// Clean up (abort) old incomplete multipart uploads
-	#[structopt(name = "cleanup-incomplete-uploads", version = garage_version())]
-	CleanupIncompleteUploads(CleanupIncompleteUploadsOpt),
 }
 
 #[derive(Serialize, Deserialize, StructOpt, Debug)]
@@ -294,17 +301,6 @@ pub struct SetQuotasOpt {
 	pub max_objects: Option<String>,
 }
 
-#[derive(Serialize, Deserialize, StructOpt, Debug)]
-pub struct CleanupIncompleteUploadsOpt {
-	/// Abort multipart uploads older than this value
-	#[structopt(long = "older-than", default_value = "1d")]
-	pub older_than: String,
-
-	/// Name of bucket(s) to clean up
-	#[structopt(required = true)]
-	pub buckets: Vec<String>,
-}
-
 #[derive(Serialize, Deserialize, StructOpt, Debug)]
 pub enum KeyOperation {
 	/// List keys

src/garage/main.rs

@@ -65,6 +65,21 @@ struct Opt {
 
 #[tokio::main]
 async fn main() {
+	if std::env::var("RUST_LOG").is_err() {
+		std::env::set_var("RUST_LOG", "netapp=info,garage=info")
+	}
+	tracing_subscriber::fmt()
+		.with_writer(std::io::stderr)
+		.with_env_filter(tracing_subscriber::filter::EnvFilter::from_default_env())
+		.init();
+	sodiumoxide::init().expect("Unable to init sodiumoxide");
+
+	// Abort on panic (same behavior as in Go)
+	std::panic::set_hook(Box::new(|panic_info| {
+		error!("{}", panic_info.to_string());
+		std::process::abort();
+	}));
+
 	// Initialize version and features info
 	let features = &[
 		#[cfg(feature = "k2v")]
@@ -75,8 +90,6 @@ async fn main() {
 		"lmdb",
 		#[cfg(feature = "sqlite")]
 		"sqlite",
-		#[cfg(feature = "consul-discovery")]
-		"consul-discovery",
 		#[cfg(feature = "kubernetes-discovery")]
 		"kubernetes-discovery",
 		#[cfg(feature = "metrics")]
@@ -93,51 +106,12 @@ async fn main() {
 	}
 	garage_util::version::init_features(features);
 
+	// Parse arguments
 	let version = format!(
 		"{} [features: {}]",
 		garage_util::version::garage_version(),
 		features.join(", ")
 	);
-
-	// Initialize panic handler that aborts on panic and shows a nice message.
-	// By default, Tokio continues runing normally when a task panics. We want
-	// to avoid this behavior in Garage as this would risk putting the process in an
-	// unknown/uncontrollable state. We prefer to exit the process and restart it
-	// from scratch, so that it boots back into a fresh, known state.
-	let panic_version_info = version.clone();
-	std::panic::set_hook(Box::new(move |panic_info| {
-		eprintln!("======== PANIC (internal Garage error) ========");
-		eprintln!("{}", panic_info);
-		eprintln!();
-		eprintln!("Panics are internal errors that Garage is unable to handle on its own.");
-		eprintln!("They can be caused by bugs in Garage's code, or by corrupted data in");
-		eprintln!("the node's storage. If you feel that this error is likely to be a bug");
-		eprintln!("in Garage, please report it on our issue tracker a the following address:");
-		eprintln!();
-		eprintln!("        https://git.deuxfleurs.fr/Deuxfleurs/garage/issues");
-		eprintln!();
-		eprintln!("Please include the last log messages and the the full backtrace below in");
-		eprintln!("your bug report, as well as any relevant information on the context in");
-		eprintln!("which Garage was running when this error occurred.");
-		eprintln!();
-		eprintln!("GARAGE VERSION: {}", panic_version_info);
-		eprintln!();
-		eprintln!("BACKTRACE:");
-		eprintln!("{:?}", backtrace::Backtrace::new());
-		std::process::abort();
-	}));
-
-	// Initialize logging as well as other libraries used in Garage
-	if std::env::var("RUST_LOG").is_err() {
-		std::env::set_var("RUST_LOG", "netapp=info,garage=info")
-	}
-	tracing_subscriber::fmt()
-		.with_writer(std::io::stderr)
-		.with_env_filter(tracing_subscriber::filter::EnvFilter::from_default_env())
-		.init();
-	sodiumoxide::init().expect("Unable to init sodiumoxide");
-
-	// Parse arguments and dispatch command line
 	let opt = Opt::from_clap(&Opt::clap().version(version.as_str()).get_matches());
 
 	let res = match opt.cmd {

src/garage/tests/k2v/batch.rs

@@ -6,7 +6,7 @@ use assert_json_diff::assert_json_eq;
 use serde_json::json;
 
 use super::json_body;
-use hyper::{Method, StatusCode};
+use hyper::Method;
 
 #[tokio::test]
 async fn test_batch() {
@@ -49,7 +49,7 @@ async fn test_batch() {
 		.send()
 		.await
 		.unwrap();
-	assert_eq!(res.status(), StatusCode::NO_CONTENT);
+	assert_eq!(res.status(), 200);
 
 	for sk in ["a", "b", "c", "d.1", "d.2", "e"] {
 		let res = ctx
@@ -62,7 +62,7 @@ async fn test_batch() {
 			.send()
 			.await
 			.unwrap();
-		assert_eq!(res.status(), StatusCode::OK);
+		assert_eq!(res.status(), 200);
 		assert_eq!(
 			res.headers().get("content-type").unwrap().to_str().unwrap(),
 			"application/octet-stream"
@@ -104,7 +104,7 @@ async fn test_batch() {
 		.send()
 		.await
 		.unwrap();
-	assert_eq!(res.status(), StatusCode::OK);
+	assert_eq!(res.status(), 200);
 	let json_res = json_body(res).await;
 	assert_json_eq!(
 		json_res,
@@ -266,7 +266,7 @@ async fn test_batch() {
 		.send()
 		.await
 		.unwrap();
-	assert_eq!(res.status(), StatusCode::NO_CONTENT);
+	assert_eq!(res.status(), 200);
 
 	for sk in ["b", "c", "d.1", "d.2"] {
 		let res = ctx
@@ -280,9 +280,9 @@ async fn test_batch() {
 			.await
 			.unwrap();
 		if sk == "b" {
-			assert_eq!(res.status(), StatusCode::NO_CONTENT);
+			assert_eq!(res.status(), 204);
 		} else {
-			assert_eq!(res.status(), StatusCode::OK);
+			assert_eq!(res.status(), 200);
 		}
 		ct.insert(
 			sk,
@@ -317,7 +317,7 @@ async fn test_batch() {
 		.send()
 		.await
 		.unwrap();
-	assert_eq!(res.status(), StatusCode::OK);
+	assert_eq!(res.status(), 200);
 	let json_res = json_body(res).await;
 	assert_json_eq!(
 		json_res,
@@ -478,7 +478,7 @@ async fn test_batch() {
 		.send()
 		.await
 		.unwrap();
-	assert_eq!(res.status(), StatusCode::OK);
+	assert_eq!(res.status(), 200);
 	let json_res = json_body(res).await;
 	assert_json_eq!(
 		json_res,
@@ -514,7 +514,7 @@ async fn test_batch() {
 			.send()
 			.await
 			.unwrap();
-		assert_eq!(res.status(), StatusCode::NO_CONTENT);
+		assert_eq!(res.status(), 204);
 		assert_eq!(
 			res.headers().get("content-type").unwrap().to_str().unwrap(),
 			"application/octet-stream"
@@ -547,7 +547,7 @@ async fn test_batch() {
 		.send()
 		.await
 		.unwrap();
-	assert_eq!(res.status(), StatusCode::OK);
+	assert_eq!(res.status(), 200);
 	let json_res = json_body(res).await;
 	assert_json_eq!(
 		json_res,

src/garage/tests/k2v/errorcodes.rs

@@ -1,13 +1,13 @@
 use crate::common;
 
-use hyper::{Method, StatusCode};
+use hyper::Method;
 
 #[tokio::test]
 async fn test_error_codes() {
 	let ctx = common::context();
 	let bucket = ctx.create_bucket("test-k2v-error-codes");
 
-	// Regular insert should work (code 204)
+	// Regular insert should work (code 200)
 	let res = ctx
 		.k2v
 		.request
@@ -19,7 +19,7 @@ async fn test_error_codes() {
 		.send()
 		.await
 		.unwrap();
-	assert_eq!(res.status(), StatusCode::NO_CONTENT);
+	assert_eq!(res.status(), 200);
 
 	// Insert with trash causality token: invalid request
 	let res = ctx
@@ -34,7 +34,7 @@ async fn test_error_codes() {
 		.send()
 		.await
 		.unwrap();
-	assert_eq!(res.status(), StatusCode::BAD_REQUEST);
+	assert_eq!(res.status(), 400);
 
 	// Search without partition key: invalid request
 	let res = ctx
@@ -52,7 +52,7 @@ async fn test_error_codes() {
 		.send()
 		.await
 		.unwrap();
-	assert_eq!(res.status(), StatusCode::BAD_REQUEST);
+	assert_eq!(res.status(), 400);
 
 	// Search with start that is not in prefix: invalid request
 	let res = ctx
@@ -70,7 +70,7 @@ async fn test_error_codes() {
 		.send()
 		.await
 		.unwrap();
-	assert_eq!(res.status(), StatusCode::BAD_REQUEST);
+	assert_eq!(res.status(), 400);
 
 	// Search with invalid json: 400
 	let res = ctx
@@ -88,7 +88,7 @@ async fn test_error_codes() {
 		.send()
 		.await
 		.unwrap();
-	assert_eq!(res.status(), StatusCode::BAD_REQUEST);
+	assert_eq!(res.status(), 400);
 
 	// Batch insert with invalid causality token: 400
 	let res = ctx
@@ -105,7 +105,7 @@ async fn test_error_codes() {
 		.send()
 		.await
 		.unwrap();
-	assert_eq!(res.status(), StatusCode::BAD_REQUEST);
+	assert_eq!(res.status(), 400);
 
 	// Batch insert with invalid data: 400
 	let res = ctx
@@ -122,7 +122,7 @@ async fn test_error_codes() {
 		.send()
 		.await
 		.unwrap();
-	assert_eq!(res.status(), StatusCode::BAD_REQUEST);
+	assert_eq!(res.status(), 400);
 
 	// Poll with invalid causality token: 400
 	let res = ctx
@@ -137,5 +137,5 @@ async fn test_error_codes() {
 		.send()
 		.await
 		.unwrap();
-	assert_eq!(res.status(), StatusCode::BAD_REQUEST);
+	assert_eq!(res.status(), 400);
 }

src/garage/tests/k2v/item.rs

@@ -6,7 +6,7 @@ use assert_json_diff::assert_json_eq;
 use serde_json::json;
 
 use super::json_body;
-use hyper::{Method, StatusCode};
+use hyper::Method;
 
 #[tokio::test]
 async fn test_items_and_indices() {
@@ -56,7 +56,7 @@ async fn test_items_and_indices() {
 			.send()
 			.await
 			.unwrap();
-		assert_eq!(res.status(), StatusCode::NO_CONTENT);
+		assert_eq!(res.status(), 200);
 
 		// Get value back
 		let res = ctx
@@ -69,7 +69,7 @@ async fn test_items_and_indices() {
 			.send()
 			.await
 			.unwrap();
-		assert_eq!(res.status(), StatusCode::OK);
+		assert_eq!(res.status(), 200);
 		assert_eq!(
 			res.headers().get("content-type").unwrap().to_str().unwrap(),
 			"application/octet-stream"
@@ -132,7 +132,7 @@ async fn test_items_and_indices() {
 			.send()
 			.await
 			.unwrap();
-		assert_eq!(res.status(), StatusCode::NO_CONTENT);
+		assert_eq!(res.status(), 200);
 
 		// Get value back
 		let res = ctx
@@ -145,7 +145,7 @@ async fn test_items_and_indices() {
 			.send()
 			.await
 			.unwrap();
-		assert_eq!(res.status(), StatusCode::OK);
+		assert_eq!(res.status(), 200);
 		assert_eq!(
 			res.headers().get("content-type").unwrap().to_str().unwrap(),
 			"application/octet-stream"
@@ -201,7 +201,7 @@ async fn test_items_and_indices() {
 			.send()
 			.await
 			.unwrap();
-		assert_eq!(res.status(), StatusCode::NO_CONTENT);
+		assert_eq!(res.status(), 200);
 
 		// Get value back
 		let res = ctx
@@ -214,7 +214,7 @@ async fn test_items_and_indices() {
 			.send()
 			.await
 			.unwrap();
-		assert_eq!(res.status(), StatusCode::OK);
+		assert_eq!(res.status(), 200);
 		assert_eq!(
 			res.headers().get("content-type").unwrap().to_str().unwrap(),
 			"application/json"
@@ -271,7 +271,7 @@ async fn test_items_and_indices() {
 			.send()
 			.await
 			.unwrap();
-		assert_eq!(res.status(), StatusCode::OK);
+		assert_eq!(res.status(), 200);
 		let ct = res
 			.headers()
 			.get("x-garage-causality-token")
@@ -292,7 +292,7 @@ async fn test_items_and_indices() {
 			.send()
 			.await
 			.unwrap();
-		assert_eq!(res.status(), StatusCode::NO_CONTENT);
+		assert_eq!(res.status(), 204);
 
 		// ReadIndex -- now there should be some stuff
 		tokio::time::sleep(Duration::from_secs(1)).await;
@@ -364,7 +364,7 @@ async fn test_item_return_format() {
 		.send()
 		.await
 		.unwrap();
-	assert_eq!(res.status(), StatusCode::NO_CONTENT);
+	assert_eq!(res.status(), 200);
 
 	// f0: either
 	let res = ctx
@@ -377,7 +377,7 @@ async fn test_item_return_format() {
 		.send()
 		.await
 		.unwrap();
-	assert_eq!(res.status(), StatusCode::OK);
+	assert_eq!(res.status(), 200);
 	assert_eq!(
 		res.headers().get("content-type").unwrap().to_str().unwrap(),
 		"application/octet-stream"
@@ -405,7 +405,7 @@ async fn test_item_return_format() {
 		.send()
 		.await
 		.unwrap();
-	assert_eq!(res.status(), StatusCode::OK);
+	assert_eq!(res.status(), 200);
 	assert_eq!(
 		res.headers().get("content-type").unwrap().to_str().unwrap(),
 		"application/json"
@@ -424,7 +424,7 @@ async fn test_item_return_format() {
 		.send()
 		.await
 		.unwrap();
-	assert_eq!(res.status(), StatusCode::OK);
+	assert_eq!(res.status(), 200);
 	assert_eq!(
 		res.headers().get("content-type").unwrap().to_str().unwrap(),
 		"application/octet-stream"
@@ -446,7 +446,7 @@ async fn test_item_return_format() {
 		.send()
 		.await
 		.unwrap();
-	assert_eq!(res.status(), StatusCode::OK);
+	assert_eq!(res.status(), 200);
 	assert_eq!(
 		res.headers().get("content-type").unwrap().to_str().unwrap(),
 		"application/json"
@@ -466,7 +466,7 @@ async fn test_item_return_format() {
 		.send()
 		.await
 		.unwrap();
-	assert_eq!(res.status(), StatusCode::NO_CONTENT);
+	assert_eq!(res.status(), 200);
 
 	// f0: either
 	let res = ctx
@@ -479,7 +479,7 @@ async fn test_item_return_format() {
 		.send()
 		.await
 		.unwrap();
-	assert_eq!(res.status(), StatusCode::OK);
+	assert_eq!(res.status(), 200);
 	assert_eq!(
 		res.headers().get("content-type").unwrap().to_str().unwrap(),
 		"application/json"
@@ -503,7 +503,7 @@ async fn test_item_return_format() {
 		.send()
 		.await
 		.unwrap();
-	assert_eq!(res.status(), StatusCode::OK);
+	assert_eq!(res.status(), 200);
 	assert_eq!(
 		res.headers().get("content-type").unwrap().to_str().unwrap(),
 		"application/json"
@@ -528,7 +528,7 @@ async fn test_item_return_format() {
 		.send()
 		.await
 		.unwrap();
-	assert_eq!(res.status(), StatusCode::CONFLICT); // CONFLICT
+	assert_eq!(res.status(), 409); // CONFLICT
 
 	// f3: json
 	let res = ctx
@@ -541,7 +541,7 @@ async fn test_item_return_format() {
 		.send()
 		.await
 		.unwrap();
-	assert_eq!(res.status(), StatusCode::OK);
+	assert_eq!(res.status(), 200);
 	assert_eq!(
 		res.headers().get("content-type").unwrap().to_str().unwrap(),
 		"application/json"
@@ -568,7 +568,7 @@ async fn test_item_return_format() {
 		.send()
 		.await
 		.unwrap();
-	assert_eq!(res.status(), StatusCode::NO_CONTENT);
+	assert_eq!(res.status(), 204);
 
 	// f0: either
 	let res = ctx
@@ -581,7 +581,7 @@ async fn test_item_return_format() {
 		.send()
 		.await
 		.unwrap();
-	assert_eq!(res.status(), StatusCode::OK);
+	assert_eq!(res.status(), 200);
 	assert_eq!(
 		res.headers().get("content-type").unwrap().to_str().unwrap(),
 		"application/json"
@@ -599,7 +599,7 @@ async fn test_item_return_format() {
 		.send()
 		.await
 		.unwrap();
-	assert_eq!(res.status(), StatusCode::OK);
+	assert_eq!(res.status(), 200);
 	assert_eq!(
 		res.headers().get("content-type").unwrap().to_str().unwrap(),
 		"application/json"
@@ -625,7 +625,7 @@ async fn test_item_return_format() {
 		.send()
 		.await
 		.unwrap();
-	assert_eq!(res.status(), StatusCode::CONFLICT); // CONFLICT
+	assert_eq!(res.status(), 409); // CONFLICT
 
 	// f3: json
 	let res = ctx
@@ -638,7 +638,7 @@ async fn test_item_return_format() {
 		.send()
 		.await
 		.unwrap();
-	assert_eq!(res.status(), StatusCode::OK);
+	assert_eq!(res.status(), 200);
 	assert_eq!(
 		res.headers().get("content-type").unwrap().to_str().unwrap(),
 		"application/json"
@@ -658,7 +658,7 @@ async fn test_item_return_format() {
 		.send()
 		.await
 		.unwrap();
-	assert_eq!(res.status(), StatusCode::NO_CONTENT);
+	assert_eq!(res.status(), 204);
 
 	// f0: either
 	let res = ctx
@@ -671,7 +671,7 @@ async fn test_item_return_format() {
 		.send()
 		.await
 		.unwrap();
-	assert_eq!(res.status(), StatusCode::NO_CONTENT); // NO CONTENT
+	assert_eq!(res.status(), 204); // NO CONTENT
 
 	// f1: not specified
 	let res = ctx
@@ -683,7 +683,7 @@ async fn test_item_return_format() {
 		.send()
 		.await
 		.unwrap();
-	assert_eq!(res.status(), StatusCode::OK);
+	assert_eq!(res.status(), 200);
 	assert_eq!(
 		res.headers().get("content-type").unwrap().to_str().unwrap(),
 		"application/json"
@@ -702,7 +702,7 @@ async fn test_item_return_format() {
 		.send()
 		.await
 		.unwrap();
-	assert_eq!(res.status(), StatusCode::NO_CONTENT); // NO CONTENT
+	assert_eq!(res.status(), 204); // NO CONTENT
 
 	// f3: json
 	let res = ctx
@@ -715,7 +715,7 @@ async fn test_item_return_format() {
 		.send()
 		.await
 		.unwrap();
-	assert_eq!(res.status(), StatusCode::OK);
+	assert_eq!(res.status(), 200);
 	assert_eq!(
 		res.headers().get("content-type").unwrap().to_str().unwrap(),
 		"application/json"

src/garage/tests/k2v/poll.rs

@@ -1,4 +1,4 @@
-use hyper::{Method, StatusCode};
+use hyper::Method;
 use std::time::Duration;
 
 use crate::common;
@@ -20,7 +20,7 @@ async fn test_poll() {
 		.send()
 		.await
 		.unwrap();
-	assert_eq!(res.status(), StatusCode::NO_CONTENT);
+	assert_eq!(res.status(), 200);
 
 	// Retrieve initial value to get its causality token
 	let res2 = ctx
@@ -33,7 +33,7 @@ async fn test_poll() {
 		.send()
 		.await
 		.unwrap();
-	assert_eq!(res2.status(), StatusCode::OK);
+	assert_eq!(res2.status(), 200);
 	let ct = res2
 		.headers()
 		.get("x-garage-causality-token")
@@ -80,7 +80,7 @@ async fn test_poll() {
 		.send()
 		.await
 		.unwrap();
-	assert_eq!(res.status(), StatusCode::NO_CONTENT);
+	assert_eq!(res.status(), 200);
 
 	// Check poll finishes with correct value
 	let poll_res = tokio::select! {
@@ -88,7 +88,7 @@ async fn test_poll() {
 		res = poll => res.unwrap().unwrap(),
 	};
 
-	assert_eq!(poll_res.status(), StatusCode::OK);
+	assert_eq!(poll_res.status(), 200);
 
 	let poll_res_body = hyper::body::to_bytes(poll_res.into_body())
 		.await

src/garage/tests/k2v/simple.rs

@@ -1,6 +1,6 @@
 use crate::common;
 
-use hyper::{Method, StatusCode};
+use hyper::Method;
 
 #[tokio::test]
 async fn test_simple() {
@@ -18,7 +18,7 @@ async fn test_simple() {
 		.send()
 		.await
 		.unwrap();
-	assert_eq!(res.status(), StatusCode::NO_CONTENT);
+	assert_eq!(res.status(), 200);
 
 	let res2 = ctx
 		.k2v
@@ -30,7 +30,7 @@ async fn test_simple() {
 		.send()
 		.await
 		.unwrap();
-	assert_eq!(res2.status(), StatusCode::OK);
+	assert_eq!(res2.status(), 200);
 
 	let res2_body = hyper::body::to_bytes(res2.into_body())
 		.await

src/garage/tests/s3/website.rs

@@ -4,7 +4,7 @@ use aws_sdk_s3::{
 	model::{CorsConfiguration, CorsRule, ErrorDocument, IndexDocument, WebsiteConfiguration},
 	types::ByteStream,
 };
-use http::{Request, StatusCode};
+use http::Request;
 use hyper::{
 	body::{to_bytes, Body},
 	Client,
@@ -43,7 +43,7 @@ async fn test_website() {
 
 	let mut resp = client.request(req()).await.unwrap();
 
-	assert_eq!(resp.status(), StatusCode::NOT_FOUND);
+	assert_eq!(resp.status(), 404);
 	assert_ne!(
 		to_bytes(resp.body_mut()).await.unwrap().as_ref(),
 		BODY.as_ref()
@@ -56,7 +56,7 @@ async fn test_website() {
 		.expect_success_status("Could not allow website on bucket");
 
 	resp = client.request(req()).await.unwrap();
-	assert_eq!(resp.status(), StatusCode::OK);
+	assert_eq!(resp.status(), 200);
 	assert_eq!(
 		to_bytes(resp.body_mut()).await.unwrap().as_ref(),
 		BODY.as_ref()
@@ -69,7 +69,7 @@ async fn test_website() {
 		.expect_success_status("Could not deny website on bucket");
 
 	resp = client.request(req()).await.unwrap();
-	assert_eq!(resp.status(), StatusCode::NOT_FOUND);
+	assert_eq!(resp.status(), 404);
 	assert_ne!(
 		to_bytes(resp.body_mut()).await.unwrap().as_ref(),
 		BODY.as_ref()
@@ -175,7 +175,7 @@ async fn test_website_s3_api() {
 
 		let mut resp = client.request(req).await.unwrap();
 
-		assert_eq!(resp.status(), StatusCode::OK);
+		assert_eq!(resp.status(), 200);
 		assert_eq!(
 			resp.headers().get("access-control-allow-origin").unwrap(),
 			"*"
@@ -200,7 +200,7 @@ async fn test_website_s3_api() {
 
 		let mut resp = client.request(req).await.unwrap();
 
-		assert_eq!(resp.status(), StatusCode::NOT_FOUND);
+		assert_eq!(resp.status(), 404);
 		assert_eq!(
 			to_bytes(resp.body_mut()).await.unwrap().as_ref(),
 			BODY_ERR.as_ref()
@@ -220,7 +220,7 @@ async fn test_website_s3_api() {
 
 		let mut resp = client.request(req).await.unwrap();
 
-		assert_eq!(resp.status(), StatusCode::OK);
+		assert_eq!(resp.status(), 200);
 		assert_eq!(
 			resp.headers().get("access-control-allow-origin").unwrap(),
 			"*"
@@ -244,7 +244,7 @@ async fn test_website_s3_api() {
 
 		let mut resp = client.request(req).await.unwrap();
 
-		assert_eq!(resp.status(), StatusCode::FORBIDDEN);
+		assert_eq!(resp.status(), 403);
 		assert_ne!(
 			to_bytes(resp.body_mut()).await.unwrap().as_ref(),
 			BODY.as_ref()
@@ -285,7 +285,7 @@ async fn test_website_s3_api() {
 
 		let mut resp = client.request(req).await.unwrap();
 
-		assert_eq!(resp.status(), StatusCode::FORBIDDEN);
+		assert_eq!(resp.status(), 403);
 		assert_ne!(
 			to_bytes(resp.body_mut()).await.unwrap().as_ref(),
 			BODY.as_ref()
@@ -311,7 +311,7 @@ async fn test_website_s3_api() {
 
 		let mut resp = client.request(req).await.unwrap();
 
-		assert_eq!(resp.status(), StatusCode::NOT_FOUND);
+		assert_eq!(resp.status(), 404);
 		assert_ne!(
 			to_bytes(resp.body_mut()).await.unwrap().as_ref(),
 			BODY_ERR.as_ref()

src/k2v-client/Cargo.toml

@@ -12,7 +12,7 @@ readme = "../../README.md"
 base64 = "0.13.0"
 http = "0.2.6"
 log = "0.4"
-rusoto_core = { version = "0.48.0", default-features = false, features = ["rustls"] }
+rusoto_core = "0.48.0"
 rusoto_credential = "0.48.0"
 rusoto_signature = "0.48.0"
 serde = "1.0.137"

src/model/helper/bucket.rs

@@ -1,5 +1,3 @@
-use std::time::Duration;
-
 use garage_util::crdt::*;
 use garage_util::data::*;
 use garage_util::error::{Error as GarageError, OkOrMessage};
@@ -14,7 +12,7 @@ use crate::helper::error::*;
 use crate::helper::key::KeyHelper;
 use crate::key_table::*;
 use crate::permission::BucketKeyPerm;
-use crate::s3::object_table::*;
+use crate::s3::object_table::ObjectFilter;
 
 pub struct BucketHelper<'a>(pub(crate) &'a Garage);
 
@@ -474,69 +472,4 @@ impl<'a> BucketHelper<'a> {
 
 		Ok(true)
 	}
-
-	// ----
-
-	/// Deletes all incomplete multipart uploads that are older than a certain time.
-	/// Returns the number of uploads aborted
-	pub async fn cleanup_incomplete_uploads(
-		&self,
-		bucket_id: &Uuid,
-		older_than: Duration,
-	) -> Result<usize, Error> {
-		let older_than = now_msec() - older_than.as_millis() as u64;
-
-		let mut ret = 0usize;
-		let mut start = None;
-
-		loop {
-			let objects = self
-				.0
-				.object_table
-				.get_range(
-					bucket_id,
-					start,
-					Some(ObjectFilter::IsUploading),
-					1000,
-					EnumerationOrder::Forward,
-				)
-				.await?;
-
-			let abortions = objects
-				.iter()
-				.filter_map(|object| {
-					let aborted_versions = object
-						.versions()
-						.iter()
-						.filter(|v| v.is_uploading() && v.timestamp < older_than)
-						.map(|v| ObjectVersion {
-							state: ObjectVersionState::Aborted,
-							uuid: v.uuid,
-							timestamp: v.timestamp,
-						})
-						.collect::<Vec<_>>();
-					if !aborted_versions.is_empty() {
-						Some(Object::new(
-							object.bucket_id,
-							object.key.clone(),
-							aborted_versions,
-						))
-					} else {
-						None
-					}
-				})
-				.collect::<Vec<_>>();
-
-			ret += abortions.len();
-			self.0.object_table.insert_many(abortions).await?;
-
-			if objects.len() < 1000 {
-				break;
-			} else {
-				start = Some(objects.last().unwrap().key.clone());
-			}
-		}
-
-		Ok(ret)
-	}
 }

src/rpc/Cargo.toml

@@ -22,6 +22,7 @@ gethostname = "0.2"
 hex = "0.4"
 tracing = "0.1.30"
 rand = "0.8"
+itertools="0.10"
 sodiumoxide = { version = "0.2.5-0", package = "kuska-sodiumoxide" }
 
 async-trait = "0.1.7"
@@ -29,13 +30,12 @@ rmp-serde = "0.15"
 serde = { version = "1.0", default-features = false, features = ["derive", "rc"] }
 serde_bytes = "0.11"
 serde_json = "1.0"
-err-derive = { version = "0.3", optional = true }
 
 # newer version requires rust edition 2021
-kube = { version = "0.75", default-features = false, features = ["runtime", "derive", "client", "rustls-tls"], optional = true }
+kube = { version = "0.62", features = ["runtime", "derive"], optional = true }
-k8s-openapi = { version = "0.16", features = ["v1_22"], optional = true }
+k8s-openapi = { version = "0.13", features = ["v1_22"], optional = true }
+openssl = { version = "0.10", features = ["vendored"], optional = true }
 schemars = { version = "0.8", optional = true }
-reqwest = { version = "0.11", optional = true, default-features = false, features = ["rustls-tls-manual-roots", "json"] }
 
 # newer version requires rust edition 2021
 pnet_datalink = "0.28"
@@ -48,7 +48,9 @@ opentelemetry = "0.17"
 
 netapp = { version = "0.5.2", features = ["telemetry"] }
 
+hyper = { version = "0.14", features = ["client", "http1", "runtime", "tcp"] }
+
+
 [features]
-kubernetes-discovery = [ "kube", "k8s-openapi", "schemars" ]
+kubernetes-discovery = [ "kube", "k8s-openapi", "openssl", "schemars" ]
-consul-discovery = [ "reqwest", "err-derive" ]
 system-libs = [ "sodiumoxide/use-pkg-config" ]

src/rpc/consul.rs

@@ -1,14 +1,16 @@
 use std::collections::HashMap;
-use std::fs::File;
-use std::io::Read;
 use std::net::{IpAddr, SocketAddr};
 
-use err_derive::Error;
+use hyper::client::Client;
+use hyper::StatusCode;
+use hyper::{Body, Method, Request};
 use serde::{Deserialize, Serialize};
 
 use netapp::NodeID;
 
-use garage_util::config::ConsulDiscoveryConfig;
+use garage_util::error::Error;
+
+// ---- READING FROM CONSUL CATALOG ----
 
 #[derive(Deserialize, Clone, Debug)]
 struct ConsulQueryEntry {
@@ -20,6 +22,53 @@ struct ConsulQueryEntry {
 	node_meta: HashMap<String, String>,
 }
 
+pub async fn get_consul_nodes(
+	consul_host: &str,
+	consul_service_name: &str,
+) -> Result<Vec<(NodeID, SocketAddr)>, Error> {
+	let url = format!(
+		"http://{}/v1/catalog/service/{}",
+		consul_host, consul_service_name
+	);
+	let req = Request::builder()
+		.uri(url)
+		.method(Method::GET)
+		.body(Body::default())?;
+
+	let client = Client::new();
+
+	let resp = client.request(req).await?;
+	if resp.status() != StatusCode::OK {
+		return Err(Error::Message(format!("HTTP error {}", resp.status())));
+	}
+
+	let body = hyper::body::to_bytes(resp.into_body()).await?;
+	let entries = serde_json::from_slice::<Vec<ConsulQueryEntry>>(body.as_ref())?;
+
+	let mut ret = vec![];
+	for ent in entries {
+		let ip = ent.address.parse::<IpAddr>().ok();
+		let pubkey = ent
+			.node_meta
+			.get("pubkey")
+			.and_then(|k| hex::decode(&k).ok())
+			.and_then(|k| NodeID::from_slice(&k[..]));
+		if let (Some(ip), Some(pubkey)) = (ip, pubkey) {
+			ret.push((pubkey, SocketAddr::new(ip, ent.service_port)));
+		} else {
+			warn!(
+				"Could not process node spec from Consul: {:?} (invalid IP or public key)",
+				ent
+			);
+		}
+	}
+	debug!("Got nodes from Consul: {:?}", ret);
+
+	Ok(ret)
+}
+
+// ---- PUBLISHING TO CONSUL CATALOG ----
+
 #[derive(Serialize, Clone, Debug)]
 struct ConsulPublishEntry {
 	#[serde(rename = "Node")]
@@ -46,100 +95,16 @@ struct ConsulPublishService {
 	port: u16,
 }
 
-// ----
-
-pub struct ConsulDiscovery {
-	config: ConsulDiscoveryConfig,
-	client: reqwest::Client,
-}
-
-impl ConsulDiscovery {
-	pub fn new(config: ConsulDiscoveryConfig) -> Result<Self, ConsulError> {
-		let client = match (&config.client_cert, &config.client_key) {
-			(Some(client_cert), Some(client_key)) => {
-				let mut client_cert_buf = vec![];
-				File::open(client_cert)?.read_to_end(&mut client_cert_buf)?;
-
-				let mut client_key_buf = vec![];
-				File::open(client_key)?.read_to_end(&mut client_key_buf)?;
-
-				let identity = reqwest::Identity::from_pem(
-					&[&client_cert_buf[..], &client_key_buf[..]].concat()[..],
-				)?;
-
-				if config.tls_skip_verify {
-					reqwest::Client::builder()
-						.use_rustls_tls()
-						.danger_accept_invalid_certs(true)
-						.identity(identity)
-						.build()?
-				} else if let Some(ca_cert) = &config.ca_cert {
-					let mut ca_cert_buf = vec![];
-					File::open(ca_cert)?.read_to_end(&mut ca_cert_buf)?;
-
-					reqwest::Client::builder()
-						.use_rustls_tls()
-						.add_root_certificate(reqwest::Certificate::from_pem(&ca_cert_buf[..])?)
-						.identity(identity)
-						.build()?
-				} else {
-					reqwest::Client::builder()
-						.use_rustls_tls()
-						.identity(identity)
-						.build()?
-				}
-			}
-			(None, None) => reqwest::Client::new(),
-			_ => return Err(ConsulError::InvalidTLSConfig),
-		};
-
-		Ok(Self { client, config })
-	}
-
-	// ---- READING FROM CONSUL CATALOG ----
-
-	pub async fn get_consul_nodes(&self) -> Result<Vec<(NodeID, SocketAddr)>, ConsulError> {
-		let url = format!(
-			"{}/v1/catalog/service/{}",
-			self.config.consul_http_addr, self.config.service_name
-		);
-
-		let http = self.client.get(&url).send().await?;
-		let entries: Vec<ConsulQueryEntry> = http.json().await?;
-
-		let mut ret = vec![];
-		for ent in entries {
-			let ip = ent.address.parse::<IpAddr>().ok();
-			let pubkey = ent
-				.node_meta
-				.get("pubkey")
-				.and_then(|k| hex::decode(&k).ok())
-				.and_then(|k| NodeID::from_slice(&k[..]));
-			if let (Some(ip), Some(pubkey)) = (ip, pubkey) {
-				ret.push((pubkey, SocketAddr::new(ip, ent.service_port)));
-			} else {
-				warn!(
-					"Could not process node spec from Consul: {:?} (invalid IP or public key)",
-					ent
-				);
-			}
-		}
-		debug!("Got nodes from Consul: {:?}", ret);
-
-		Ok(ret)
-	}
-
-	// ---- PUBLISHING TO CONSUL CATALOG ----
-
 pub async fn publish_consul_service(
-		&self,
+	consul_host: &str,
+	consul_service_name: &str,
 	node_id: NodeID,
 	hostname: &str,
 	rpc_public_addr: SocketAddr,
-	) -> Result<(), ConsulError> {
+) -> Result<(), Error> {
 	let node = format!("garage:{}", hex::encode(&node_id[..8]));
 
-		let advertisement = ConsulPublishEntry {
+	let advertisment = ConsulPublishEntry {
 		node: node.clone(),
 		address: rpc_public_addr.ip(),
 		node_meta: [
@@ -151,29 +116,36 @@ impl ConsulDiscovery {
 		.collect(),
 		service: ConsulPublishService {
 			service_id: node.clone(),
-				service_name: self.config.service_name.clone(),
+			service_name: consul_service_name.to_string(),
 			tags: vec!["advertised-by-garage".into(), hostname.into()],
 			address: rpc_public_addr.ip(),
 			port: rpc_public_addr.port(),
 		},
 	};
 
-		let url = format!("{}/v1/catalog/register", self.config.consul_http_addr);
+	let url = format!("http://{}/v1/catalog/register", consul_host);
+	let req_body = serde_json::to_string(&advertisment)?;
+	debug!("Request body for consul adv: {}", req_body);
 
-		let http = self.client.put(&url).json(&advertisement).send().await?;
+	let req = Request::builder()
-		http.error_for_status()?;
+		.uri(url)
+		.method(Method::PUT)
+		.body(Body::from(req_body))?;
+
+	let client = Client::new();
+
+	let resp = client.request(req).await?;
+	debug!("Response of advertising to Consul: {:?}", resp);
+	let resp_code = resp.status();
+	let resp_bytes = &hyper::body::to_bytes(resp.into_body()).await?;
+	debug!(
+		"{}",
+		std::str::from_utf8(resp_bytes).unwrap_or("<invalid utf8>")
+	);
+
+	if resp_code != StatusCode::OK {
+		return Err(Error::Message(format!("HTTP error {}", resp_code)));
+	}
 
 	Ok(())
 }
-}
-
-/// Regroup all Consul discovery errors
-#[derive(Debug, Error)]
-pub enum ConsulError {
-	#[error(display = "IO error: {}", _0)]
-	Io(#[error(source)] std::io::Error),
-	#[error(display = "HTTP error: {}", _0)]
-	Reqwest(#[error(source)] reqwest::Error),
-	#[error(display = "Invalid Consul TLS configuration")]
-	InvalidTLSConfig,
-}

src/rpc/graph_algo.rs

@@ -0,0 +1,420 @@
+//! This module deals with graph algorithms.
+//! It is used in layout.rs to build the partition to node assignation.
+
+use rand::prelude::SliceRandom;
+use std::cmp::{max, min};
+use std::collections::HashMap;
+use std::collections::VecDeque;
+
+///Vertex data structures used in all the graphs used in layout.rs.
+///usize parameters correspond to node/zone/partitions ids.
+///To understand the vertex roles below, please refer to the formal description
+///of the layout computation algorithm.
+#[derive(Clone, Copy, Debug, PartialEq, Eq, Hash)]
+pub enum Vertex {
+	Source,
+	Pup(usize),       //The vertex p+ of partition p
+	Pdown(usize),     //The vertex p- of partition p
+	PZ(usize, usize), //The vertex corresponding to x_(partition p, zone z)
+	N(usize),         //The vertex corresponding to node n
+	Sink,
+}
+
+///Edge data structure for the flow algorithm.
+#[derive(Clone, Copy, Debug)]
+pub struct FlowEdge {
+	cap: u32,    //flow maximal capacity of the edge
+	flow: i32,   //flow value on the edge
+	dest: usize, //destination vertex id
+	rev: usize,  //index of the reversed edge (v, self) in the edge list of vertex v
+}
+
+///Edge data structure for the detection of negative cycles.
+#[derive(Clone, Copy, Debug)]
+pub struct WeightedEdge {
+	w: i32, //weight of the edge
+	dest: usize,
+}
+
+pub trait Edge: Clone + Copy {}
+impl Edge for FlowEdge {}
+impl Edge for WeightedEdge {}
+
+///Struct for the graph structure. We do encapsulation here to be able to both
+///provide user friendly Vertex enum to address vertices, and to use internally usize
+///indices and Vec instead of HashMap in the graph algorithm to optimize execution speed.
+pub struct Graph<E: Edge> {
+	vertextoid: HashMap<Vertex, usize>,
+	idtovertex: Vec<Vertex>,
+
+	//The graph is stored as an adjacency list
+	graph: Vec<Vec<E>>,
+}
+
+pub type CostFunction = HashMap<(Vertex, Vertex), i32>;
+
+impl<E: Edge> Graph<E> {
+	pub fn new(vertices: &[Vertex]) -> Self {
+		let mut map = HashMap::<Vertex, usize>::new();
+		for (i, vert) in vertices.iter().enumerate() {
+			map.insert(*vert, i);
+		}
+		Graph::<E> {
+			vertextoid: map,
+			idtovertex: vertices.to_vec(),
+			graph: vec![Vec::<E>::new(); vertices.len()],
+		}
+	}
+}
+
+impl Graph<FlowEdge> {
+	///This function adds a directed edge to the graph with capacity c, and the
+	///corresponding reversed edge with capacity 0.
+	pub fn add_edge(&mut self, u: Vertex, v: Vertex, c: u32) -> Result<(), String> {
+		if !self.vertextoid.contains_key(&u) || !self.vertextoid.contains_key(&v) {
+			return Err("The graph does not contain the provided vertex.".to_string());
+		}
+		let idu = self.vertextoid[&u];
+		let idv = self.vertextoid[&v];
+		let rev_u = self.graph[idu].len();
+		let rev_v = self.graph[idv].len();
+		self.graph[idu].push(FlowEdge {
+			cap: c,
+			dest: idv,
+			flow: 0,
+			rev: rev_v,
+		});
+		self.graph[idv].push(FlowEdge {
+			cap: 0,
+			dest: idu,
+			flow: 0,
+			rev: rev_u,
+		});
+		Ok(())
+	}
+
+	///This function returns the list of vertices that receive a positive flow from
+	///vertex v.
+	pub fn get_positive_flow_from(&self, v: Vertex) -> Result<Vec<Vertex>, String> {
+		if !self.vertextoid.contains_key(&v) {
+			return Err("The graph does not contain the provided vertex.".to_string());
+		}
+		let idv = self.vertextoid[&v];
+		let mut result = Vec::<Vertex>::new();
+		for edge in self.graph[idv].iter() {
+			if edge.flow > 0 {
+				result.push(self.idtovertex[edge.dest]);
+			}
+		}
+		Ok(result)
+	}
+
+	///This function returns the value of the flow incoming to v.
+	pub fn get_inflow(&self, v: Vertex) -> Result<i32, String> {
+		if !self.vertextoid.contains_key(&v) {
+			return Err("The graph does not contain the provided vertex.".to_string());
+		}
+		let idv = self.vertextoid[&v];
+		let mut result = 0;
+		for edge in self.graph[idv].iter() {
+			result += max(0, self.graph[edge.dest][edge.rev].flow);
+		}
+		Ok(result)
+	}
+
+	///This function returns the value of the flow outgoing from v.
+	pub fn get_outflow(&self, v: Vertex) -> Result<i32, String> {
+		if !self.vertextoid.contains_key(&v) {
+			return Err("The graph does not contain the provided vertex.".to_string());
+		}
+		let idv = self.vertextoid[&v];
+		let mut result = 0;
+		for edge in self.graph[idv].iter() {
+			result += max(0, edge.flow);
+		}
+		Ok(result)
+	}
+
+	///This function computes the flow total value by computing the outgoing flow
+	///from the source.
+	pub fn get_flow_value(&mut self) -> Result<i32, String> {
+		self.get_outflow(Vertex::Source)
+	}
+
+	///This function shuffles the order of the edge lists. It keeps the ids of the
+	///reversed edges consistent.
+	fn shuffle_edges(&mut self) {
+		let mut rng = rand::thread_rng();
+		for i in 0..self.graph.len() {
+			self.graph[i].shuffle(&mut rng);
+			//We need to update the ids of the reverse edges.
+			for j in 0..self.graph[i].len() {
+				let target_v = self.graph[i][j].dest;
+				let target_rev = self.graph[i][j].rev;
+				self.graph[target_v][target_rev].rev = j;
+			}
+		}
+	}
+
+	///Computes an upper bound of the flow on the graph
+	pub fn flow_upper_bound(&self) -> u32 {
+		let idsource = self.vertextoid[&Vertex::Source];
+		let mut flow_upper_bound = 0;
+		for edge in self.graph[idsource].iter() {
+			flow_upper_bound += edge.cap;
+		}
+		flow_upper_bound
+	}
+
+	///This function computes the maximal flow using Dinic's algorithm. It starts with
+	///the flow values already present in the graph. So it is possible to add some edge to
+	///the graph, compute a flow, add other edges, update the flow.
+	pub fn compute_maximal_flow(&mut self) -> Result<(), String> {
+		if !self.vertextoid.contains_key(&Vertex::Source) {
+			return Err("The graph does not contain a source.".to_string());
+		}
+		if !self.vertextoid.contains_key(&Vertex::Sink) {
+			return Err("The graph does not contain a sink.".to_string());
+		}
+
+		let idsource = self.vertextoid[&Vertex::Source];
+		let idsink = self.vertextoid[&Vertex::Sink];
+
+		let nb_vertices = self.graph.len();
+
+		let flow_upper_bound = self.flow_upper_bound();
+
+		//To ensure the dispersion of the associations generated by the
+		//assignation, we shuffle the neighbours of the nodes. Hence,
+		//the vertices do not consider their neighbours in the same order.
+		self.shuffle_edges();
+
+		//We run Dinic's max flow algorithm
+		loop {
+			//We build the level array from Dinic's algorithm.
+			let mut level = vec![None; nb_vertices];
+
+			let mut fifo = VecDeque::new();
+			fifo.push_back((idsource, 0));
+			while !fifo.is_empty() {
+				if let Some((id, lvl)) = fifo.pop_front() {
+					if level[id] == None {
+						//it means id has not yet been reached
+						level[id] = Some(lvl);
+						for edge in self.graph[id].iter() {
+							if edge.cap as i32 - edge.flow > 0 {
+								fifo.push_back((edge.dest, lvl + 1));
+							}
+						}
+					}
+				}
+			}
+			if level[idsink] == None {
+				//There is no residual flow
+				break;
+			}
+			//Now we run DFS respecting the level array
+			let mut next_nbd = vec![0; nb_vertices];
+			let mut lifo = VecDeque::new();
+
+			lifo.push_back((idsource, flow_upper_bound));
+
+			while let Some((id_tmp, f_tmp)) = lifo.back() {
+				let id = *id_tmp;
+				let f = *f_tmp;
+				if id == idsink {
+					//The DFS reached the sink, we can add a
+					//residual flow.
+					lifo.pop_back();
+					while let Some((id, _)) = lifo.pop_back() {
+						let nbd = next_nbd[id];
+						self.graph[id][nbd].flow += f as i32;
+						let id_rev = self.graph[id][nbd].dest;
+						let nbd_rev = self.graph[id][nbd].rev;
+						self.graph[id_rev][nbd_rev].flow -= f as i32;
+					}
+					lifo.push_back((idsource, flow_upper_bound));
+					continue;
+				}
+				//else we did not reach the sink
+				let nbd = next_nbd[id];
+				if nbd >= self.graph[id].len() {
+					//There is nothing to explore from id anymore
+					lifo.pop_back();
+					if let Some((parent, _)) = lifo.back() {
+						next_nbd[*parent] += 1;
+					}
+					continue;
+				}
+				//else we can try to send flow from id to its nbd
+				let new_flow = min(
+					f as i32,
+					self.graph[id][nbd].cap as i32 - self.graph[id][nbd].flow,
+				) as u32;
+				if new_flow == 0 {
+					next_nbd[id] += 1;
+					continue;
+				}
+				if let (Some(lvldest), Some(lvlid)) = (level[self.graph[id][nbd].dest], level[id]) {
+					if lvldest <= lvlid {
+						//We cannot send flow to nbd.
+						next_nbd[id] += 1;
+						continue;
+					}
+				}
+				//otherwise, we send flow to nbd.
+				lifo.push_back((self.graph[id][nbd].dest, new_flow));
+			}
+		}
+		Ok(())
+	}
+
+	///This function takes a flow, and a cost function on the edges, and tries to find an
+	/// equivalent flow with a better cost, by finding improving overflow cycles. It uses
+	/// as subroutine the Bellman Ford algorithm run up to path_length.
+	/// We assume that the cost of edge (u,v) is the opposite of the cost of (v,u), and
+	/// only one needs to be present in the cost function.
+	pub fn optimize_flow_with_cost(
+		&mut self,
+		cost: &CostFunction,
+		path_length: usize,
+	) -> Result<(), String> {
+		//We build the weighted graph g where we will look for negative cycle
+		let mut gf = self.build_cost_graph(cost)?;
+		let mut cycles = gf.list_negative_cycles(path_length);
+		while !cycles.is_empty() {
+			//we enumerate negative cycles
+			for c in cycles.iter() {
+				for i in 0..c.len() {
+					//We add one flow unit to the edge (u,v) of cycle c
+					let idu = self.vertextoid[&c[i]];
+					let idv = self.vertextoid[&c[(i + 1) % c.len()]];
+					for j in 0..self.graph[idu].len() {
+						//since idu appears at most once in the cycles, we enumerate every
+						//edge at most once.
+						let edge = self.graph[idu][j];
+						if edge.dest == idv {
+							self.graph[idu][j].flow += 1;
+							self.graph[idv][edge.rev].flow -= 1;
+							break;
+						}
+					}
+				}
+			}
+
+			gf = self.build_cost_graph(cost)?;
+			cycles = gf.list_negative_cycles(path_length);
+		}
+		Ok(())
+	}
+
+	///Construct the weighted graph G_f from the flow and the cost function
+	fn build_cost_graph(&self, cost: &CostFunction) -> Result<Graph<WeightedEdge>, String> {
+		let mut g = Graph::<WeightedEdge>::new(&self.idtovertex);
+		let nb_vertices = self.idtovertex.len();
+		for i in 0..nb_vertices {
+			for edge in self.graph[i].iter() {
+				if edge.cap as i32 - edge.flow > 0 {
+					//It is possible to send overflow through this edge
+					let u = self.idtovertex[i];
+					let v = self.idtovertex[edge.dest];
+					if cost.contains_key(&(u, v)) {
+						g.add_edge(u, v, cost[&(u, v)])?;
+					} else if cost.contains_key(&(v, u)) {
+						g.add_edge(u, v, -cost[&(v, u)])?;
+					} else {
+						g.add_edge(u, v, 0)?;
+					}
+				}
+			}
+		}
+		Ok(g)
+	}
+}
+
+impl Graph<WeightedEdge> {
+	///This function adds a single directed weighted edge to the graph.
+	pub fn add_edge(&mut self, u: Vertex, v: Vertex, w: i32) -> Result<(), String> {
+		if !self.vertextoid.contains_key(&u) || !self.vertextoid.contains_key(&v) {
+			return Err("The graph does not contain the provided vertex.".to_string());
+		}
+		let idu = self.vertextoid[&u];
+		let idv = self.vertextoid[&v];
+		self.graph[idu].push(WeightedEdge { w, dest: idv });
+		Ok(())
+	}
+
+	///This function lists the negative cycles it manages to find after path_length
+	///iterations of the main loop of the Bellman-Ford algorithm. For the classical
+	///algorithm, path_length needs to be equal to the number of vertices. However,
+	///for particular graph structures like in our case, the algorithm is still correct
+	///when path_length is the length of the longest possible simple path.
+	///See the formal description of the algorithm for more details.
+	fn list_negative_cycles(&self, path_length: usize) -> Vec<Vec<Vertex>> {
+		let nb_vertices = self.graph.len();
+
+		//We start with every vertex at distance 0 of some imaginary extra -1 vertex.
+		let mut distance = vec![0; nb_vertices];
+		//The prev vector collects for every vertex from where does the shortest path come
+		let mut prev = vec![None; nb_vertices];
+
+		for _ in 0..path_length + 1 {
+			for id in 0..nb_vertices {
+				for e in self.graph[id].iter() {
+					if distance[id] + e.w < distance[e.dest] {
+						distance[e.dest] = distance[id] + e.w;
+						prev[e.dest] = Some(id);
+					}
+				}
+			}
+		}
+
+		//If self.graph contains a negative cycle, then at this point the graph described
+		//by prev (which is a directed 1-forest/functional graph)
+		//must contain a cycle. We list the cycles of prev.
+		let cycles_prev = cycles_of_1_forest(&prev);
+
+		//Remark that the cycle in prev is in the reverse order compared to the cycle
+		//in the graph. Thus the .rev().
+		return cycles_prev
+			.iter()
+			.map(|cycle| cycle.iter().rev().map(|id| self.idtovertex[*id]).collect())
+			.collect();
+	}
+}
+
+///This function returns the list of cycles of a directed 1 forest. It does not
+///check for the consistency of the input.
+fn cycles_of_1_forest(forest: &[Option<usize>]) -> Vec<Vec<usize>> {
+	let mut cycles = Vec::<Vec<usize>>::new();
+	let mut time_of_discovery = vec![None; forest.len()];
+
+	for t in 0..forest.len() {
+		let mut id = t;
+		//while we are on a valid undiscovered node
+		while time_of_discovery[id] == None {
+			time_of_discovery[id] = Some(t);
+			if let Some(i) = forest[id] {
+				id = i;
+			} else {
+				break;
+			}
+		}
+		if forest[id] != None && time_of_discovery[id] == Some(t) {
+			//We discovered an id that we explored at this iteration t.
+			//It means we are on a cycle
+			let mut cy = vec![id; 1];
+			let mut id2 = id;
+			while let Some(id_next) = forest[id2] {
+				id2 = id_next;
+				if id2 != id {
+					cy.push(id2);
+				} else {
+					break;
+				}
+			}
+			cycles.push(cy);
+		}
+	}
+	cycles
+}

src/rpc/kubernetes.rs

@@ -12,8 +12,6 @@ use serde::{Deserialize, Serialize};
 
 use netapp::NodeID;
 
-use garage_util::config::KubernetesDiscoveryConfig;
-
 static K8S_GROUP: &str = "deuxfleurs.fr";
 
 #[derive(CustomResource, Debug, Serialize, Deserialize, Clone, JsonSchema)]
@@ -43,14 +41,15 @@ pub async fn create_kubernetes_crd() -> Result<(), kube::Error> {
 }
 
 pub async fn get_kubernetes_nodes(
-	kubernetes_config: &KubernetesDiscoveryConfig,
+	kubernetes_service_name: &str,
+	kubernetes_namespace: &str,
 ) -> Result<Vec<(NodeID, SocketAddr)>, kube::Error> {
 	let client = Client::try_default().await?;
-	let nodes: Api<GarageNode> = Api::namespaced(client.clone(), &kubernetes_config.namespace);
+	let nodes: Api<GarageNode> = Api::namespaced(client.clone(), kubernetes_namespace);
 
 	let lp = ListParams::default().labels(&format!(
 		"garage.{}/service={}",
-		K8S_GROUP, kubernetes_config.service_name
+		K8S_GROUP, kubernetes_service_name
 	));
 
 	let nodes = nodes.list(&lp).await?;
@@ -74,7 +73,8 @@ pub async fn get_kubernetes_nodes(
 }
 
 pub async fn publish_kubernetes_node(
-	kubernetes_config: &KubernetesDiscoveryConfig,
+	kubernetes_service_name: &str,
+	kubernetes_namespace: &str,
 	node_id: NodeID,
 	hostname: &str,
 	rpc_public_addr: SocketAddr,
@@ -93,13 +93,13 @@ pub async fn publish_kubernetes_node(
 	let labels = node.metadata.labels.insert(BTreeMap::new());
 	labels.insert(
 		format!("garage.{}/service", K8S_GROUP),
-		kubernetes_config.service_name.to_string(),
+		kubernetes_service_name.to_string(),
 	);
 
 	debug!("Node object to be applied: {:#?}", node);
 
 	let client = Client::try_default().await?;
-	let nodes: Api<GarageNode> = Api::namespaced(client.clone(), &kubernetes_config.namespace);
+	let nodes: Api<GarageNode> = Api::namespaced(client.clone(), kubernetes_namespace);
 
 	if let Ok(old_node) = nodes.get(&node_pubkey).await {
 		node.metadata.resource_version = old_node.metadata.resource_version;

src/rpc/lib.rs

@@ -3,11 +3,11 @@
 #[macro_use]
 extern crate tracing;
 
-#[cfg(feature = "consul-discovery")]
 mod consul;
 #[cfg(feature = "kubernetes-discovery")]
 mod kubernetes;
 
+pub mod graph_algo;
 pub mod layout;
 pub mod ring;
 pub mod system;

src/rpc/ring.rs

@@ -40,6 +40,7 @@ pub struct Ring {
 // Type to store compactly the id of a node in the system
 // Change this to u16 the day we want to have more than 256 nodes in a cluster
 pub type CompactNodeType = u8;
+pub const MAX_NODE_NUMBER: usize = 256;
 
 // The maximum number of times an object might get replicated
 // This must be at least 3 because Garage supports 3-way replication