Nix configuration to build convert_db

Reviewed-on: https://git.deuxfleurs.fr/Deuxfleurs/garage/pulls/393

.drone.yml

@@ -245,6 +245,17 @@ node:
   nix-daemon: 1
 
 steps:
+  - name: multiarch-docker
+    image: nixpkgs/nix:nixos-22.05
+    environment:
+      DOCKER_AUTH:
+        from_secret: docker_auth
+      HOME: "/root"
+    commands:
+      - mkdir -p /root/.docker
+      - echo $DOCKER_AUTH > /root/.docker/config.json
+      - export CONTAINER_TAG=${DRONE_TAG:-$DRONE_COMMIT}
+      - nix-shell --attr release --run "multiarch_docker"
   - name: refresh-index
     image: nixpkgs/nix:nixos-22.05
     environment:
@@ -269,6 +280,6 @@ trigger:
 
 ---
 kind: signature
-hmac: 362639b4c9541ad9bd06ff7f72b5235b2b0216bcb16eececd25285b6fe94ba6f
+hmac: 103a04785c98f5376a63ce22865c2576963019bbc4d828f200d2a470a3c821ea
 
 ...

README.md

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

default.nix

@@ -16,6 +16,7 @@ let
     name ="garage-tests";
     paths = builtins.map (key: rustPkgs.workspace.${key} { compileMode = "test"; }) (builtins.attrNames rustPkgs.workspace);
   });
+  build_convert_db = (target: (compile { inherit target git_version; release = true; }).workspace.garage_db { compileMode = "build"; });
 
 in {
   pkgs = {
@@ -23,6 +24,12 @@ in {
     i386 = build_debug_and_release "i686-unknown-linux-musl";
     arm64 = build_debug_and_release "aarch64-unknown-linux-musl";
     arm = build_debug_and_release "armv6l-unknown-linux-musleabihf";
+    convert_db = {
+      amd64 = build_convert_db "x86_64-unknown-linux-musl";
+      i386 = build_convert_db "i686-unknown-linux-musl";
+      arm64 = build_convert_db "aarch64-unknown-linux-musl";
+      arm = build_convert_db "armv6l-unknown-linux-musleabihf";
+    };
   };
   test = {
     amd64 = test (compile { inherit git_version; target = "x86_64-unknown-linux-musl"; });

doc/book/cookbook/real-world.md

@@ -51,15 +51,15 @@ to store 2 TB of data in total.
 
 ## Get a Docker image
 
-Our docker image is currently named `dxflrs/amd64_garage` and is stored on the [Docker Hub](https://hub.docker.com/r/dxflrs/amd64_garage/tags?page=1&ordering=last_updated).
+Our docker image is currently named `dxflrs/garage` and is stored on the [Docker Hub](https://hub.docker.com/r/dxflrs/garage/tags?page=1&ordering=last_updated).
-We encourage you to use a fixed tag (eg. `v0.4.0`) and not the `latest` tag.
+We encourage you to use a fixed tag (eg. `v0.8.0`) and not the `latest` tag.
-For this example, we will use the latest published version at the time of the writing which is `v0.4.0` but it's up to you
+For this example, we will use the latest published version at the time of the writing which is `v0.8.0` but it's up to you
-to check [the most recent versions on the Docker Hub](https://hub.docker.com/r/dxflrs/amd64_garage/tags?page=1&ordering=last_updated).
+to check [the most recent versions on the Docker Hub](https://hub.docker.com/r/dxflrs/garage/tags?page=1&ordering=last_updated).
 
 For example:
 
 ```
-sudo docker pull dxflrs/amd64_garage:v0.4.0
+sudo docker pull dxflrs/garage:v0.8.0
 ```
 
 ## Deploying and configuring Garage
@@ -125,7 +125,7 @@ docker run \
   -v /etc/garage.toml:/etc/garage.toml \
   -v /var/lib/garage/meta:/var/lib/garage/meta \
   -v /var/lib/garage/data:/var/lib/garage/data \
-  lxpz/garage_amd64:v0.4.0
+  dxflrs/garage:v0.8.0
 ```
 
 It should be restarted automatically at each reboot.

doc/book/design/goals.md

@@ -14,10 +14,10 @@ website.
 
 Garage is an opinionated object storage solutoin, we focus on the following **desirable properties**:
 
+  - **Internet enabled**: made for multi-sites (eg. datacenters, offices, households, etc.) interconnected through regular Internet connections.
   - **Self-contained & lightweight**: works everywhere and integrates well in existing environments to target [hyperconverged infrastructures](https://en.wikipedia.org/wiki/Hyper-converged_infrastructure).
   - **Highly resilient**: highly resilient to network failures, network latency, disk failures, sysadmin failures.
   - **Simple**: simple to understand, simple to operate, simple to debug.
-  - **Internet enabled**: made for multi-sites (eg. datacenters, offices, households, etc.) interconnected through regular Internet connections.
 
 We also noted that the pursuit of some other goals are detrimental to our initial goals.
 The following has been identified as **non-goals** (if these points matter to you, you should not use Garage):

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

@@ -16,7 +16,7 @@ The migration steps are as follows:
 1. Do `garage repair --all-nodes --yes tables` and `garage repair --all-nodes --yes blocks`,
    check the logs and check that all data seems to be synced correctly between
    nodes. If you have time, do additional checks (`scrub`, `block_refs`, etc.)
-2. Disable api and web access. Garage does not support disabling
+2. Disable API and web access. Garage does not support disabling
    these endpoints but you can change the port number or stop your reverse
    proxy for instance.
 3. Check once again that your cluster is healty. Run again `garage repair --all-nodes --yes tables` which is quick.

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

@@ -0,0 +1,34 @@
++++
+title = "Migrating from 0.7 to 0.8"
+weight = 13
++++
+
+**This guide explains how to migrate to 0.8 if you have an existing 0.7 cluster.
+We don't recommend trying to migrate to 0.8 directly from 0.6 or older.**
+
+**We make no guarantee that this migration will work perfectly:
+back up all your data before attempting it!**
+
+Garage v0.8 introduces new data tables that allow the counting of objects in buckets in order to implement bucket quotas.
+A manual migration step is required to first count objects in Garage buckets and populate these tables with accurate data.
+
+The migration steps are as follows:
+
+1. Disable API and web access. Garage v0.7 does not support disabling
+   these endpoints but you can change the port number or stop your reverse proxy for instance.
+2. Do `garage repair --all-nodes --yes tables` and `garage repair --all-nodes --yes blocks`,
+   check the logs and check that all data seems to be synced correctly between
+   nodes. If you have time, do additional checks (`scrub`, `block_refs`, etc.)
+3. Check that queues are empty: run `garage stats` to query them or inspect metrics in the Grafana dashboard.
+4. Turn off Garage v0.7
+5. **Backup the metadata folder of all your nodes!** For instance, use the following command
+	if your metadata directory is `/var/lib/garage/meta`: `cd /var/lib/garage ; tar -acf meta-v0.7.tar.zst meta/`
+6. Install Garage v0.8
+7. **Before starting Garage v0.8**, run the offline migration step: `garage offline-repair --yes object_counters`.
+   This can take a while to run, depending on the number of objects stored in your cluster.
+8. Turn on Garage v0.8
+9. Do `garage repair --all-nodes --yes tables` and `garage repair --all-nodes --yes blocks`.
+   Wait for a full table sync to run.
+10. Your upgraded cluster should be in a working state. Re-enable API and Web
+    access and check that everything went well.
+11. Monitor your cluster in the next hours to see if it works well under your production load, report any issue.

nix/compile.nix

@@ -137,8 +137,8 @@ let
         /* [2] */ hardeningDisable = [ "pie" ];
       };
       overrideArgs = old: {
-        /* [4] */ features = [ "bundled-libs" "sled" ]
+        /* [4] */ features = [ "bundled-libs" "sled" "metrics" "k2v" ]
-          ++ (if release then [ "kubernetes-discovery" "telemetry-otlp" "metrics" "lmdb" "sqlite" ] else []);
+          ++ (if release then [ "kubernetes-discovery" "telemetry-otlp" "lmdb" "sqlite" ] else []);
       };
     })
 
@@ -149,7 +149,10 @@ let
 
     (pkgs.rustBuilder.rustLib.makeOverride {
       name = "garage_db";
-      overrideAttrs = drv: { /* [1] */ setBuildEnv = (buildEnv drv); };
+      overrideAttrs = drv: {
+        /* [1] */ setBuildEnv = (buildEnv drv);
+        /* [2] */ hardeningDisable = [ "pie" ];
+      };
     })
 
     (pkgs.rustBuilder.rustLib.makeOverride {

nix/manifest-tool.nix

@@ -0,0 +1,23 @@
+pkgs:
+pkgs.buildGoModule rec {
+  pname = "manifest-tool";
+  version = "2.0.5";
+
+  src = pkgs.fetchFromGitHub {
+    owner = "estesp";
+    repo = "manifest-tool";
+    rev = "v${version}";
+    sha256 = "hjCGKnE0yrlnF/VIzOwcDzmQX3Wft+21KCny/opqdLg=";
+  } + "/v2";
+
+  vendorSha256 = null;
+
+  checkPhase = "true";
+
+  meta = with pkgs.lib; {
+    description = "Command line tool to create and query container image manifest list/indexes";
+    homepage = "https://github.com/estesp/manifest-tool";
+    license = licenses.asl20;
+    platforms = platforms.linux;
+  };
+}

shell.nix

@@ -10,6 +10,7 @@ let
     overlays = [ cargo2nixOverlay ];
   };
   kaniko = (import ./nix/kaniko.nix) pkgs;
+  manifest-tool = (import ./nix/manifest-tool.nix) pkgs;
   winscp = (import ./nix/winscp.nix) pkgs;
 
 in
@@ -84,6 +85,34 @@ function to_docker {
     --verbosity=debug
 }
 
+function multiarch_docker {
+        manifest-tool push from-spec <(cat <<EOF
+image: dxflrs/garage:''${CONTAINER_TAG}
+manifests:
+  -
+    image: dxflrs/arm64_garage:''${CONTAINER_TAG}
+    platform:
+      architecture: arm64
+      os: linux
+  -
+    image: dxflrs/amd64_garage:''${CONTAINER_TAG}
+    platform:
+      architecture: amd64
+      os: linux
+  -
+    image: dxflrs/386_garage:''${CONTAINER_TAG}
+    platform:
+      architecture: 386
+      os: linux
+  -
+    image: dxflrs/arm_garage:''${CONTAINER_TAG}
+    platform:
+      architecture: arm
+      os: linux
+EOF
+        )
+}
+
 function refresh_index {
   aws \
       --endpoint-url https://garage.deuxfleurs.fr \
@@ -113,6 +142,7 @@ function refresh_index {
       nativeBuildInputs = [
         pkgs.awscli2
         kaniko 
+        manifest-tool
       ];
     };
   }

src/api/admin/api_server.rs

@@ -34,7 +34,10 @@ pub struct AdminApiServer {
 }
 
 impl AdminApiServer {
-	pub fn new(garage: Arc<Garage>) -> Self {
+	pub fn new(
+		garage: Arc<Garage>,
+		#[cfg(feature = "metrics")] exporter: PrometheusExporter,
+	) -> Self {
 		let cfg = &garage.config.admin;
 		let metrics_token = cfg
 			.metrics_token
@@ -47,7 +50,7 @@ impl AdminApiServer {
 		Self {
 			garage,
 			#[cfg(feature = "metrics")]
-			exporter: opentelemetry_prometheus::exporter().init(),
+			exporter,
 			metrics_token,
 			admin_token,
 		}

src/api/generic_server.rs

@@ -174,7 +174,11 @@ impl<A: ApiHandler> ApiServer<A> {
 
 		let current_context = Context::current();
 		let current_span = current_context.span();
-		current_span.update_name::<String>(format!("S3 API {}", endpoint.name()));
+		current_span.update_name::<String>(format!(
+			"{} API {}",
+			A::API_NAME_DISPLAY,
+			endpoint.name()
+		));
 		current_span.set_attribute(KeyValue::new("endpoint", endpoint.name()));
 		endpoint.add_span_attributes(current_span);
 

src/garage/server.rs

@@ -32,6 +32,9 @@ pub async fn run_server(config_file: PathBuf) -> Result<(), Error> {
 
 	// ---- Initialize Garage internals ----
 
+	#[cfg(feature = "metrics")]
+	let metrics_exporter = opentelemetry_prometheus::exporter().init();
+
 	info!("Initializing background runner...");
 	let watch_cancel = netapp::util::watch_ctrl_c();
 	let (background, await_background_done) = BackgroundRunner::new(16, watch_cancel.clone());
@@ -50,7 +53,11 @@ pub async fn run_server(config_file: PathBuf) -> Result<(), Error> {
 	}
 
 	info!("Initialize Admin API server and metrics collector...");
-	let admin_server = AdminApiServer::new(garage.clone());
+	let admin_server = AdminApiServer::new(
+		garage.clone(),
+		#[cfg(feature = "metrics")]
+		metrics_exporter,
+	);
 
 	info!("Launching internal Garage cluster communications...");
 	let run_system = tokio::spawn(garage.system.clone().run(watch_cancel.clone()));