Clean up nix setup, only toolchain.nix is still in a weird state

Reviewed-on: https://git.deuxfleurs.fr/Deuxfleurs/garage/pulls/672

.cargo/config.toml

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

.gitignore

@@ -3,4 +3,6 @@
 /pki
 **/*.rs.bk
 *.swp
-/.direnv
+/.direnv
+/.cargo
+/result

Cargo.lock

@@ -1271,7 +1271,6 @@ dependencies = [
  "http-range",
  "httpdate",
  "hyper",
- "hyperlocal",
  "idna",
  "md-5",
  "multer",
@@ -1465,7 +1464,6 @@ dependencies = [
  "garage_util",
  "http",
  "hyper",
- "hyperlocal",
  "opentelemetry",
  "percent-encoding",
  "tokio",
@@ -1778,19 +1776,6 @@ dependencies = [
  "tokio-io-timeout",
 ]
 
-[[package]]
-name = "hyperlocal"
-version = "0.8.0"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "0fafdf7b2b2de7c9784f76e02c0935e65a8117ec3b768644379983ab333ac98c"
-dependencies = [
- "futures-util",
- "hex",
- "hyper",
- "pin-project",
- "tokio",
-]
-
 [[package]]
 name = "iana-time-zone"
 version = "0.1.57"

default.nix

@@ -1,56 +1,166 @@
-{ system ? builtins.currentSystem, git_version ? null, }:
-
-with import ./nix/common.nix;
+{
+  buildSystem ? builtins.currentSystem,
+  targetSystem ? buildSystem,
+  gitVersion ? null,
+  release ? false,
+  features ? null,
+}:
 
 let
-  pkgs = import pkgsSrc { };
-  compile = import ./nix/compile.nix;
-
-  build_debug_and_release = (target: {
-    debug = (compile {
-      inherit system target git_version pkgsSrc cargo2nixOverlay;
-      release = false;
-    }).workspace.garage { compileMode = "build"; };
-
-    release = (compile {
-      inherit system target git_version pkgsSrc cargo2nixOverlay;
-      release = true;
-    }).workspace.garage { compileMode = "build"; };
-  });
-
-  test = (rustPkgs:
-    pkgs.symlinkJoin {
-      name = "garage-tests";
-      paths =
-        builtins.map (key: rustPkgs.workspace.${key} { compileMode = "test"; })
-        (builtins.attrNames rustPkgs.workspace);
-    });
-
-in {
-  pkgs = {
-    amd64 = build_debug_and_release "x86_64-unknown-linux-musl";
-    i386 = build_debug_and_release "i686-unknown-linux-musl";
-    arm64 = build_debug_and_release "aarch64-unknown-linux-musl";
-    arm = build_debug_and_release "armv6l-unknown-linux-musleabihf";
+  pkgsSrc = import ./nix/pkgs.nix;
+  newBuildTarget = {
+    nixPkgsSystem,
+    rustTarget ? nixPkgsSystem,
+    nativeBuildInputs ? pkgsCross: [],
+    rustFlags ? pkgsCross: [],
+  }: {
+    inherit nixPkgsSystem rustTarget nativeBuildInputs rustFlags;
   };
-  test = {
-    amd64 = test (compile {
-      inherit system git_version pkgsSrc cargo2nixOverlay;
-      target = "x86_64-unknown-linux-musl";
-      features = [
-        "garage/bundled-libs"
-        "garage/k2v"
-        "garage/sled"
-        "garage/lmdb"
-        "garage/sqlite"
+
+  # centralize per-target configuration in a single place.
+  buildTargets = {
+    "x86_64-linux" = newBuildTarget {
+      nixPkgsSystem = "x86_64-unknown-linux-musl";
+    };
+
+    "i686-linux" = newBuildTarget {
+      nixPkgsSystem = "i686-unknown-linux-musl";
+    };
+
+    "aarch64-linux" = newBuildTarget {
+      nixPkgsSystem = "aarch64-unknown-linux-musl";
+    };
+
+    # Old Raspberry Pi's (not currently supported due to linking errors with
+    # libsqlite3 and libsodium
+    #"armv6l-linux" = newBuildTarget {
+    #  nixPkgsSystem = "armv6l-unknown-linux-musleabihf";
+    #  rustTarget = "arm-unknown-linux-musleabihf";
+    #};
+
+    "x86_64-windows" = newBuildTarget {
+      nixPkgsSystem = "x86_64-w64-mingw32";
+      rustTarget = "x86_64-pc-windows-gnu";
+      nativeBuildInputs = pkgsCross: [ pkgsCross.windows.pthreads ];
+      rustFlags = pkgsCross: [
+        "-C" "link-arg=-L${pkgsCross.windows.pthreads}/lib"
       ];
-    });
+    };
   };
-  clippy = {
-    amd64 = (compile {
-      inherit system git_version pkgsSrc cargo2nixOverlay;
-      target = "x86_64-unknown-linux-musl";
-      compiler = "clippy";
-    }).workspace.garage { compileMode = "build"; };
+
+  buildTarget = buildTargets.${targetSystem};
+
+  pkgs = import pkgsSrc { system = buildSystem; };
+  pkgsCross = import pkgsSrc {
+    system = buildSystem;
+    crossSystem.config = buildTarget.nixPkgsSystem;
   };
+
+  rustTarget = buildTarget.rustTarget;
+
+  toolchain = let
+    fenix = import (pkgs.fetchFromGitHub {
+      owner = "nix-community";
+      repo = "fenix";
+      rev = "81ab0b4f7ae9ebb57daa0edf119c4891806e4d3a";
+      hash = "sha256-bZmI7ytPAYLpyFNgj5xirDkKuAniOkj1xHdv5aIJ5GM=";
+    }) {
+      system = buildSystem;
+    };
+
+    mkToolchain = fenixTarget: fenixTarget.toolchainOf {
+      channel = "1.68.2";
+      sha256 = "sha256-4vetmUhTUsew5FODnjlnQYInzyLNyDwocGa4IvMk3DM=";
+    };
+  in
+    fenix.combine [
+      (mkToolchain fenix).rustc
+      (mkToolchain fenix).rustfmt
+      (mkToolchain fenix).cargo
+      (mkToolchain fenix).clippy
+      (mkToolchain fenix.targets.${rustTarget}).rust-std
+    ];
+
+  naersk = let
+    naerskSrc = pkgs.fetchFromGitHub {
+      owner = "nix-community";
+      repo = "naersk";
+      rev = "d9a33d69a9c421d64c8d925428864e93be895dcc";
+      hash = "sha256-e136hTT7LqQ2QjOTZQMW+jnsevWwBpMj78u6FRUsH9I=";
+    };
+  in
+    pkgs.callPackages naerskSrc {
+      cargo = toolchain;
+      rustc = toolchain;
+    };
+
+  builtFeatures = if features != null then
+      features
+  else (
+    [ "garage/bundled-libs" "garage/sled" "garage/lmdb" "garage/k2v" ] ++ (
+      if release then [
+        "garage/consul-discovery"
+        "garage/kubernetes-discovery"
+        "garage/metrics"
+        "garage/telemetry-otlp"
+        "garage/sqlite"
+      ] else [ ]
+    )
+  );
+
+  # For some reason the pkgsCross.pkgsStatic build of libsodium doesn't contain
+  # a `.a` file when compiled to a windows target, but rather contains
+  # a `.dll.a` file which libsodium-sys doesn't pick up on. Copying the one to
+  # the be the other seems to work.
+  libsodium = pkgs.runCommand "libsodium-wrapped" {
+    libsodium = pkgsCross.pkgsStatic.libsodium;
+  } ''
+    cp -rL "$libsodium" "$out"
+    chmod -R +w "$out"
+    if [ ! -e "$out"/lib/libsodium.a ] && [ -f "$out"/lib/libsodium.dll.a ]; then
+      cp "$out"/lib/libsodium.dll.a "$out"/lib/libsodium.a
+    fi
+  '';
+
+in rec {
+  inherit pkgs pkgsCross;
+
+  # Exported separately so it can be used from shell.nix
+  buildEnv = rec {
+    nativeBuildInputs = (buildTarget.nativeBuildInputs pkgsCross) ++ [
+      toolchain
+      pkgs.protobuf
+
+      # Required for shell because of rust dependency build scripts which must
+      # run on the build system.
+      pkgs.stdenv.cc
+    ];
+
+    SODIUM_LIB_DIR = "${libsodium}/lib";
+
+    # Required because ring crate is special. This also seems to have
+    # fixed some issues with the x86_64-windows cross-compile :shrug:
+    TARGET_CC = "${pkgsCross.stdenv.cc}/bin/${pkgsCross.stdenv.cc.targetPrefix}cc";
+
+    CARGO_BUILD_TARGET = rustTarget;
+    CARGO_BUILD_RUSTFLAGS = [
+      "-C" "target-feature=+crt-static"
+      "-C" "link-arg=-static"
+
+      # https://github.com/rust-lang/cargo/issues/4133
+      "-C" "linker=${TARGET_CC}"
+    ] ++ (buildTarget.rustFlags pkgsCross);
+  };
+
+  build = naersk.buildPackage (rec {
+    inherit release;
+
+    src = ./.;
+    strictDeps = true;
+    doCheck = false;
+
+    cargoBuildOptions = prev: prev++[
+      "--features=${builtins.concatStringsSep "," builtFeatures}"
+    ];
+  } // buildEnv);
 }

doc/api/garage-admin-v1.html

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

doc/book/build/golang.md

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

doc/book/build/javascript.md

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

doc/book/build/python.md

@@ -80,7 +80,7 @@ from garage_admin_sdk.apis import *
 from garage_admin_sdk.models import *
 
 configuration = garage_admin_sdk.Configuration(
-  host = "http://localhost:3903/v0",
+  host = "http://localhost:3903/v1",
   access_token = "s3cr3t"
 )
 
@@ -94,13 +94,14 @@ 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(
+layout.add_layout([
+  NodeRoleChange(
+    id = status.node,
     zone = "dc1",
-    capacity = 1,
+    capacity = 1000000000,
     tags = [ "dev" ],
   )
-})
+])
 layout.apply_layout(LayoutVersion(
   version = current.version + 1
 ))

doc/book/cookbook/exposing-websites.md

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

doc/book/operations/layout.md

@@ -12,7 +12,7 @@ An introduction to building cluster layouts can be found in the [production depl
 In Garage, all of the data that can be stored in a given cluster is divided
 into slices which we call *partitions*. Each partition is stored by
 one or several nodes in the cluster
-(see [`replication_mode`](@/documentation/reference-manual/configuration.md#replication-mode)).
+(see [`replication_mode`](@/documentation/reference-manual/configuration.md#replication_mode)).
 The layout determines the correspondence between these partition,
 which exist on a logical level, and actual storage nodes.
 

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

@@ -13,8 +13,11 @@ We will bump the version numbers prefixed to each API endpoint at each time the
 or semantics change, meaning that code that relies on these endpoint will break
 when changes are introduced.
 
-The Garage administration API was introduced in version 0.7.2, this document
-does not apply to older versions of Garage.
+Versions:
+ - Before Garage 0.7.2 - no admin API
+ - Garage 0.7.2 - admin APIv0
+ - Garage 0.9.0 - admin APIv1, deprecate admin APIv0
+
 
 
 ## Access control
@@ -131,7 +134,9 @@ $ curl -so /dev/null -w "%{http_code}" http://localhost:3903/check?domain=exampl
 
 ### 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).
+These endpoints have a dedicated OpenAPI spec.
+ - APIv1 - [HTML spec](https://garagehq.deuxfleurs.fr/api/garage-admin-v1.html) - [OpenAPI YAML](https://garagehq.deuxfleurs.fr/api/garage-admin-v1.yml)
+ - APIv0 (deprecated) - [HTML spec](https://garagehq.deuxfleurs.fr/api/garage-admin-v0.html) - [OpenAPI YAML](https://garagehq.deuxfleurs.fr/api/garage-admin-v0.yml)
 
 Requesting the API from the command line can be as simple as running:
 

doc/book/reference-manual/configuration.md

@@ -8,6 +8,8 @@ weight = 20
 Here is an example `garage.toml` configuration file that illustrates all of the possible options:
 
 ```toml
+replication_mode = "3"
+
 metadata_dir = "/var/lib/garage/meta"
 data_dir = "/var/lib/garage/data"
 metadata_fsync = true
@@ -21,8 +23,6 @@ sled_cache_capacity = "128MiB"
 sled_flush_every_ms = 2000
 lmdb_map_size = "1T"
 
-replication_mode = "3"
-
 compression_level = 1
 
 rpc_secret = "4425f5c26c5e11581d3223904324dcb5b5d5dfb14e5e7f35e38c595424f5f1e6"
@@ -77,157 +77,64 @@ The following gives details about each available configuration option.
 
 ## Available configuration options
 
-### `metadata_dir`
+### Index
 
-The directory in which Garage will store its metadata. This contains the node identifier,
-the network configuration and the peer list, the list of buckets and keys as well
-as the index of all objects, object version and object blocks.
+Top-level configuration options:
+[`block_size`](#block_size),
+[`bootstrap_peers`](#bootstrap_peers),
+[`compression_level`](#compression_level),
+[`data_dir`](#metadata_dir),
+[`data_fsync`](#data_fsync),
+[`db_engine`](#db_engine),
+[`lmdb_map_size`](#lmdb_map_size),
+[`metadata_dir`](#metadata_dir),
+[`metadata_fsync`](#metadata_fsync),
+[`replication_mode`](#replication_mode),
+[`rpc_bind_addr`](#rpc_bind_addr),
+[`rpc_public_addr`](#rpc_public_addr),
+[`rpc_secret`](#rpc_secret),
+[`rpc_secret_file`](#rpc_secret),
+[`sled_cache_capacity`](#sled_cache_capacity),
+[`sled_flush_every_ms`](#sled_flush_every_ms).
 
-Store this folder on a fast SSD drive if possible to maximize Garage's performance.
+The `[consul_discovery]` section:
+[`api`](#consul_api),
+[`ca_cert`](#consul_ca_cert),
+[`client_cert`](#consul_client_cert),
+[`client_key`](#consul_client_cert),
+[`consul_http_addr`](#consul_http_addr),
+[`meta`](#consul_tags),
+[`service_name`](#consul_service_name),
+[`tags`](#consul_tags),
+[`tls_skip_verify`](#consul_tls_skip_verify),
+[`token`](#consul_token).
 
-### `data_dir`
+The `[kubernetes_discovery]` section:
+[`namespace`](#kube_namespace),
+[`service_name`](#kube_service_name),
+[`skip_crd`](#kube_skip_crd).
 
-The directory in which Garage will store the data blocks of objects.
-This folder can be placed on an HDD. The space available for `data_dir`
-should be counted to determine a node's capacity
-when [adding it to the cluster layout](@/documentation/cookbook/real-world.md).
+The `[s3_api]` section:
+[`api_bind_addr`](#s3_api_bind_addr),
+[`root_domain`](#s3_root_domain),
+[`s3_region`](#s3_region).
 
-Since `v0.9.0`, Garage supports multiple data directories with the following syntax:
+The `[s3_web]` section:
+[`bind_addr`](#web_bind_addr),
+[`root_domain`](#web_root_domain).
 
-```toml
-data_dir = [
-    { path = "/path/to/old_data", read_only = true },
-    { path = "/path/to/new_hdd1", capacity = "2T" },
-    { path = "/path/to/new_hdd2", capacity = "4T" },
-]
-```
+The `[admin]` section:
+[`api_bind_addr`](#admin_api_bind_addr),
+[`metrics_token`](#admin_metrics_token),
+[`metrics_token_file`](#admin_metrics_token),
+[`admin_token`](#admin_token),
+[`admin_token_file`](#admin_token),
+[`trace_sink`](#admin_trace_sink),
 
-See [the dedicated documentation page](@/documentation/operations/multi-hdd.md)
-on how to operate Garage in such a setup.
 
-### `db_engine` (since `v0.8.0`)
+### Top-level configuration options
 
-By default, Garage uses the Sled embedded database library
-to store its metadata on-disk. Since `v0.8.0`, Garage can use alternative storage backends as follows:
-
-| DB engine | `db_engine` value | Database path |
-| --------- | ----------------- | ------------- |
-| [Sled](https://sled.rs) | `"sled"` | `<metadata_dir>/db/` |
-| [LMDB](https://www.lmdb.tech) | `"lmdb"` | `<metadata_dir>/db.lmdb/` |
-| [Sqlite](https://sqlite.org) | `"sqlite"` | `<metadata_dir>/db.sqlite` |
-
-Performance characteristics of the different DB engines are as follows:
-
-- Sled: the default database engine, which tends to produce
-  large data files and also has performance issues, especially when the metadata folder
-  is on a traditional HDD and not on SSD.
-- LMDB: the recommended alternative on 64-bit systems,
-  much more space-efficiant and slightly faster. Note that the data format of LMDB is not portable
-  between architectures, so for instance the Garage database of an x86-64
-  node cannot be moved to an ARM64 node. Also note that, while LMDB can technically be used on 32-bit systems,
-  this will limit your node to very small database sizes due to how LMDB works; it is therefore not recommended.
-- Sqlite: Garage supports Sqlite as a storage backend for metadata,
-  however it may have issues and is also very slow in its current implementation,
-  so it is not recommended to be used for now.
-
-It is possible to convert Garage's metadata directory from one format to another with a small utility named `convert_db`,
-which can be downloaded at the following locations:
-[for amd64](https://garagehq.deuxfleurs.fr/_releases/convert_db/amd64/convert_db),
-[for i386](https://garagehq.deuxfleurs.fr/_releases/convert_db/i386/convert_db),
-[for arm64](https://garagehq.deuxfleurs.fr/_releases/convert_db/arm64/convert_db),
-[for arm](https://garagehq.deuxfleurs.fr/_releases/convert_db/arm/convert_db).
-The `convert_db` utility is used as folows:
-
-```
-convert-db -a <input db engine> -i <input db path> \
-  		   -b <output db engine> -o <output db path>
-```
-
-Make sure to specify the full database path as presented in the table above,
-and not just the path to the metadata directory.
-
-### `metadata_fsync`
-
-Whether to enable synchronous mode for the database engine or not.
-This is disabled (`false`) by default.
-
-This reduces the risk of metadata corruption in case of power failures,
-at the cost of a significant drop in write performance,
-as Garage will have to pause to sync data to disk much more often
-(several times for API calls such as PutObject).
-
-Using this option reduces the risk of simultaneous metadata corruption on several
-cluster nodes, which could lead to data loss.
-
-If multi-site replication is used, this option is most likely not necessary, as
-it is extremely unlikely that two nodes in different locations will have a 
-power failure at the exact same time.
-
-(Metadata corruption on a single node is not an issue, the corrupted data file
-can always be deleted and reconstructed from the other nodes in the cluster.)
-
-Here is how this option impacts the different database engines:
-
-| Database | `metadata_fsync = false` (default) | `metadata_fsync = true`       |
-|----------|------------------------------------|-------------------------------|
-| Sled     | default options                    | *unsupported*                 |
-| Sqlite   | `PRAGMA synchronous = OFF`         | `PRAGMA synchronous = NORMAL` |
-| LMDB     | `MDB_NOMETASYNC` + `MDB_NOSYNC`    | `MDB_NOMETASYNC`              |
-
-Note that the Sqlite database is always ran in `WAL` mode (`PRAGMA journal_mode = WAL`).
-
-### `data_fsync`
-
-Whether to `fsync` data blocks and their containing directory after they are
-saved to disk.
-This is disabled (`false`) by default.
-
-This might reduce the risk that a data block is lost in rare
-situations such as simultaneous node losing power,
-at the cost of a moderate drop in write performance.
-
-Similarly to `metatada_fsync`, this is likely not necessary
-if geographical replication is used.
-
-### `block_size`
-
-Garage splits stored objects in consecutive chunks of size `block_size`
-(except the last one which might be smaller). The default size is 1MiB and
-should work in most cases. We recommend increasing it to e.g. 10MiB if
-you are using Garage to store large files and have fast network connections
-between all nodes (e.g. 1gbps).
-
-If you are interested in tuning this, feel free to do so (and remember to
-report your findings to us!). When this value is changed for a running Garage
-installation, only files newly uploaded will be affected. Previously uploaded
-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.
-
-### `lmdb_map_size`
-
-This parameters can be used to set the map size used by LMDB,
-which is the size of the virtual memory region used for mapping the database file.
-The value of this parameter is the maximum size the metadata database can take.
-This value is not bound by the physical RAM size of the machine running Garage.
-If not specified, it defaults to 1GiB on 32-bit machines and 1TiB on 64-bit machines.
-
-### `replication_mode`
+#### `replication_mode` {#replication_mode}
 
 Garage supports the following replication modes:
 
@@ -310,7 +217,160 @@ to the cluster while rebalancing is in progress.  In theory, no data should be
 lost as rebalancing is a routine operation for Garage, although we cannot
 guarantee you that everything will go right in such an extreme scenario.
 
-### `compression_level`
+#### `metadata_dir` {#metadata_dir}
+
+The directory in which Garage will store its metadata. This contains the node identifier,
+the network configuration and the peer list, the list of buckets and keys as well
+as the index of all objects, object version and object blocks.
+
+Store this folder on a fast SSD drive if possible to maximize Garage's performance.
+
+#### `data_dir` {#data_dir}
+
+The directory in which Garage will store the data blocks of objects.
+This folder can be placed on an HDD. The space available for `data_dir`
+should be counted to determine a node's capacity
+when [adding it to the cluster layout](@/documentation/cookbook/real-world.md).
+
+Since `v0.9.0`, Garage supports multiple data directories with the following syntax:
+
+```toml
+data_dir = [
+    { path = "/path/to/old_data", read_only = true },
+    { path = "/path/to/new_hdd1", capacity = "2T" },
+    { path = "/path/to/new_hdd2", capacity = "4T" },
+]
+```
+
+See [the dedicated documentation page](@/documentation/operations/multi-hdd.md)
+on how to operate Garage in such a setup.
+
+#### `db_engine` (since `v0.8.0`) {#db_engine}
+
+Since `v0.8.0`, Garage can use alternative storage backends as follows:
+
+| DB engine | `db_engine` value | Database path |
+| --------- | ----------------- | ------------- |
+| [LMDB](https://www.lmdb.tech) (default since `v0.9.0`) | `"lmdb"` | `<metadata_dir>/db.lmdb/` |
+| [Sled](https://sled.rs) (default up to `v0.8.0`) | `"sled"` | `<metadata_dir>/db/` |
+| [Sqlite](https://sqlite.org) | `"sqlite"` | `<metadata_dir>/db.sqlite` |
+
+Sled was the only database engine up to Garage v0.7.0. Performance issues and
+API limitations of Sled prompted the addition of alternative engines in v0.8.0.
+Since v0.9.0, LMDB is the default engine instead of Sled, and Sled is
+deprecated. We plan to remove Sled in Garage v1.0.
+
+Performance characteristics of the different DB engines are as follows:
+
+- Sled: tends to produce large data files and also has performance issues,
+  especially when the metadata folder is on a traditional HDD and not on SSD.
+
+- LMDB: the recommended database engine on 64-bit systems, much more
+  space-efficient and slightly faster. Note that the data format of LMDB is not
+  portable between architectures, so for instance the Garage database of an
+  x86-64 node cannot be moved to an ARM64 node. Also note that, while LMDB can
+  technically be used on 32-bit systems, this will limit your node to very
+  small database sizes due to how LMDB works; it is therefore not recommended.
+
+- Sqlite: Garage supports Sqlite as an alternative storage backend for
+  metadata, and although it has not been tested as much, it is expected to work
+  satisfactorily.  Since Garage v0.9.0, performance issues have largely been
+  fixed by allowing for a no-fsync mode (see `metadata_fsync`). Sqlite does not
+  have the database size limitation of LMDB on 32-bit systems.
+
+It is possible to convert Garage's metadata directory from one format to another
+using the `garage convert-db` command, which should be used as follows:
+
+```
+garage convert-db -a <input db engine> -i <input db path> \
+                  -b <output db engine> -o <output db path>
+```
+
+Make sure to specify the full database path as presented in the table above
+(third colummn), and not just the path to the metadata directory.
+
+#### `metadata_fsync` {#metadata_fsync}
+
+Whether to enable synchronous mode for the database engine or not.
+This is disabled (`false`) by default.
+
+This reduces the risk of metadata corruption in case of power failures,
+at the cost of a significant drop in write performance,
+as Garage will have to pause to sync data to disk much more often
+(several times for API calls such as PutObject).
+
+Using this option reduces the risk of simultaneous metadata corruption on several
+cluster nodes, which could lead to data loss.
+
+If multi-site replication is used, this option is most likely not necessary, as
+it is extremely unlikely that two nodes in different locations will have a 
+power failure at the exact same time.
+
+(Metadata corruption on a single node is not an issue, the corrupted data file
+can always be deleted and reconstructed from the other nodes in the cluster.)
+
+Here is how this option impacts the different database engines:
+
+| Database | `metadata_fsync = false` (default) | `metadata_fsync = true`       |
+|----------|------------------------------------|-------------------------------|
+| Sled     | default options                    | *unsupported*                 |
+| Sqlite   | `PRAGMA synchronous = OFF`         | `PRAGMA synchronous = NORMAL` |
+| LMDB     | `MDB_NOMETASYNC` + `MDB_NOSYNC`    | `MDB_NOMETASYNC`              |
+
+Note that the Sqlite database is always ran in `WAL` mode (`PRAGMA journal_mode = WAL`).
+
+#### `data_fsync` {#data_fsync}
+
+Whether to `fsync` data blocks and their containing directory after they are
+saved to disk.
+This is disabled (`false`) by default.
+
+This might reduce the risk that a data block is lost in rare
+situations such as simultaneous node losing power,
+at the cost of a moderate drop in write performance.
+
+Similarly to `metatada_fsync`, this is likely not necessary
+if geographical replication is used.
+
+#### `block_size` {#block_size}
+
+Garage splits stored objects in consecutive chunks of size `block_size`
+(except the last one which might be smaller). The default size is 1MiB and
+should work in most cases. We recommend increasing it to e.g. 10MiB if
+you are using Garage to store large files and have fast network connections
+between all nodes (e.g. 1gbps).
+
+If you are interested in tuning this, feel free to do so (and remember to
+report your findings to us!). When this value is changed for a running Garage
+installation, only files newly uploaded will be affected. Previously uploaded
+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` {#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` {#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.
+
+#### `lmdb_map_size` {#lmdb_map_size}
+
+This parameters can be used to set the map size used by LMDB,
+which is the size of the virtual memory region used for mapping the database file.
+The value of this parameter is the maximum size the metadata database can take.
+This value is not bound by the physical RAM size of the machine running Garage.
+If not specified, it defaults to 1GiB on 32-bit machines and 1TiB on 64-bit machines.
+
+#### `compression_level` {#compression_level}
 
 Zstd compression level to use for storing blocks.
 
@@ -334,7 +394,7 @@ Compression is done synchronously, setting a value too high will add latency to
 This value can be different between nodes, compression is done by the node which receive the
 API call.
 
-### `rpc_secret`, `rpc_secret_file` or `GARAGE_RPC_SECRET` (env)
+#### `rpc_secret`, `rpc_secret_file` or `GARAGE_RPC_SECRET` (env) {#rpc_secret}
 
 Garage uses a secret key, called an RPC secret, that is shared between all
 nodes of the cluster in order to identify these nodes and allow them to
@@ -346,7 +406,7 @@ Since Garage `v0.8.2`, the RPC secret can also be stored in a file whose path is
 given in the configuration variable `rpc_secret_file`, or specified as an
 environment variable `GARAGE_RPC_SECRET`.
 
-### `rpc_bind_addr`
+#### `rpc_bind_addr` {#rpc_bind_addr}
 
 The address and port on which to bind for inter-cluster communcations
 (reffered to as RPC for remote procedure calls).
@@ -355,14 +415,14 @@ the node, even in the case of a NAT: the NAT should be configured to forward the
 port number to the same internal port nubmer. This means that if you have several nodes running
 behind a NAT, they should each use a different RPC port number.
 
-### `rpc_public_addr`
+#### `rpc_public_addr` {#rpc_public_addr}
 
 The address and port that other nodes need to use to contact this node for
 RPC calls.  **This parameter is optional but recommended.** In case you have
 a NAT that binds the RPC port to a port that is different on your public IP,
 this field might help making it work.
 
-### `bootstrap_peers`
+#### `bootstrap_peers` {#bootstrap_peers}
 
 A list of peer identifiers on which to contact other Garage peers of this cluster.
 These peer identifiers have the following syntax:
@@ -379,42 +439,42 @@ key will be returned by `garage node id` and you will have to add the IP
 yourself.
 
 
-## The `[consul_discovery]` section
+### The `[consul_discovery]` section
 
 Garage supports discovering other nodes of the cluster using Consul.  For this
 to work correctly, nodes need to know their IP address by which they can be
 reached by other nodes of the cluster, which should be set in `rpc_public_addr`.
 
-### `consul_http_addr` and `service_name`
+#### `consul_http_addr` {#consul_http_addr}
 
 The `consul_http_addr` parameter should be set to the full HTTP(S) address of the Consul server.
 
-### `api`
+#### `api` {#consul_api}
 
 Two APIs for service registration are supported: `catalog`  and `agent`. `catalog`, the default, will register a service using
 the `/v1/catalog` endpoints, enabling mTLS if `client_cert` and `client_key` are provided. The `agent` API uses the
 `v1/agent` endpoints instead, where an optional `token` may be provided.
 
-### `service_name`
+#### `service_name` {#consul_service_name}
 
 `service_name` should be set to the service name under which Garage's
 RPC ports are announced.
 
-### `client_cert`, `client_key`
+#### `client_cert`, `client_key` {#consul_client_cert}
 
 TLS client certificate and client key to use when communicating with Consul over TLS. Both are mandatory when doing so.
 Only available when `api = "catalog"`.
 
-### `ca_cert`
+#### `ca_cert` {#consul_ca_cert}
 
 TLS CA certificate to use when communicating with Consul over TLS.
 
-### `tls_skip_verify`
+#### `tls_skip_verify` {#consul_tls_skip_verify}
 
 Skip server hostname verification in TLS handshake.
 `ca_cert` is ignored when this is set.
 
-### `token`
+#### `token` {#consul_token}
 
 Uses the provided token for communication with Consul. Only available when `api = "agent"`.
 The policy assigned to this token should at least have these rules:
@@ -434,49 +494,49 @@ node_prefix "" {
 }
 ```
 
-### `tags` and `meta`
+#### `tags` and `meta` {#consul_tags}
 
 Additional list of tags and map of service meta to add during service registration.
 
-## The `[kubernetes_discovery]` section
+### The `[kubernetes_discovery]` section
 
 Garage supports discovering other nodes of the cluster using kubernetes custom
 resources. For this to work, a `[kubernetes_discovery]` section must be present
 with at least the `namespace` and `service_name` parameters.
 
-### `namespace`
+#### `namespace` {#kube_namespace}
 
 `namespace` sets the namespace in which the custom resources are
 configured.
 
-### `service_name`
+#### `service_name` {#kube_service_name}
 
 `service_name` is added as a label to the advertised resources to
 filter them, to allow for multiple deployments in a single namespace.
 
-### `skip_crd`
+#### `skip_crd` {#kube_skip_crd}
 
 `skip_crd` can be set to true to disable the automatic creation and
 patching of the `garagenodes.deuxfleurs.fr` CRD. You will need to create the CRD
 manually.
 
 
-## The `[s3_api]` section
+### The `[s3_api]` section
 
-### `api_bind_addr`
+#### `api_bind_addr` {#s3_api_bind_addr}
 
 The IP and port on which to bind for accepting S3 API calls.
 This endpoint does not suport TLS: a reverse proxy should be used to provide it.
 
 Alternatively, since `v0.8.5`, a path can be used to create a unix socket with 0222 mode.
 
-### `s3_region`
+#### `s3_region` {#s3_region}
 
 Garage will accept S3 API calls that are targetted to the S3 region defined here.
 API calls targetted to other regions will fail with a AuthorizationHeaderMalformed error
 message that redirects the client to the correct region.
 
-### `root_domain` {#root_domain}
+#### `root_domain` {#s3_root_domain}
 
 The optional suffix to access bucket using vhost-style in addition to path-style request.
 Note path-style requests are always enabled, whether or not vhost-style is configured.
@@ -488,12 +548,12 @@ using the hostname `my-bucket.s3.garage.eu`.
 
 
 
-## The `[s3_web]` section
+### The `[s3_web]` section
 
 Garage allows to publish content of buckets as websites. This section configures the
 behaviour of this module.
 
-### `bind_addr`
+#### `bind_addr` {#web_bind_addr}
 
 The IP and port on which to bind for accepting HTTP requests to buckets configured
 for website access.
@@ -501,7 +561,7 @@ This endpoint does not suport TLS: a reverse proxy should be used to provide it.
 
 Alternatively, since `v0.8.5`, a path can be used to create a unix socket with 0222 mode.
 
-### `root_domain`
+#### `root_domain` {#web_root_domain}
 
 The optional suffix appended to bucket names for the corresponding HTTP Host.
 
@@ -510,11 +570,11 @@ will be accessible either with hostname `deuxfleurs.fr.web.garage.eu`
 or with hostname `deuxfleurs.fr`.
 
 
-## The `[admin]` section
+### The `[admin]` section
 
 Garage has a few administration capabilities, in particular to allow remote monitoring. These features are detailed below.
 
-### `api_bind_addr`
+#### `api_bind_addr` {#admin_api_bind_addr}
 
 If specified, Garage will bind an HTTP server to this port and address, on
 which it will listen to requests for administration features.
@@ -523,7 +583,7 @@ See [administration API reference](@/documentation/reference-manual/admin-api.md
 Alternatively, since `v0.8.5`, a path can be used to create a unix socket. Note that for security reasons,
 the socket will have 0220 mode. Make sure to set user and group permissions accordingly.
 
-### `metrics_token`, `metrics_token_file` or `GARAGE_METRICS_TOKEN` (env)
+#### `metrics_token`, `metrics_token_file` or `GARAGE_METRICS_TOKEN` (env) {#admin_metrics_token}
 
 The token for accessing the Metrics endpoint. If this token is not set, the
 Metrics endpoint can be accessed without access control.
@@ -534,7 +594,7 @@ You can use any random string for this value. We recommend generating a random t
 `metrics_token_file` and the `GARAGE_METRICS_TOKEN` environment variable are supported since Garage `v0.8.2`.
 
 
-### `admin_token`, `admin_token_file` or `GARAGE_ADMIN_TOKEN` (env)
+#### `admin_token`, `admin_token_file` or `GARAGE_ADMIN_TOKEN` (env) {#admin_token}
 
 The token for accessing all of the other administration endpoints.  If this
 token is not set, access to these endpoints is disabled entirely.
@@ -545,7 +605,7 @@ You can use any random string for this value. We recommend generating a random t
 `admin_token_file` and the `GARAGE_ADMIN_TOKEN` environment variable are supported since Garage `v0.8.2`.
 
 
-### `trace_sink`
+#### `trace_sink` {#admin_trace_sink}
 
 Optionally, the address of an OpenTelemetry collector.  If specified,
 Garage will send traces in the OpenTelemetry format to this endpoint. These

doc/book/reference-manual/features.md

@@ -52,7 +52,7 @@ This is particularly usefull when nodes are far from one another and talk to one
 
 Garage supports a variety of replication modes, with 1 copy, 2 copies or 3 copies of your data,
 and with various levels of consistency, in order to adapt to a variety of usage scenarios.
-Read our reference page on [supported replication modes](@/documentation/reference-manual/configuration.md#replication-mode)
+Read our reference page on [supported replication modes](@/documentation/reference-manual/configuration.md#replication_mode)
 to select the replication mode best suited to your use case (hint: in most cases, `replication_mode = "3"` is what you want).
 
 ### Web server for static websites

flake.lock

@@ -1,31 +1,5 @@
 {
   "nodes": {
-    "cargo2nix": {
-      "inputs": {
-        "flake-compat": [
-          "flake-compat"
-        ],
-        "flake-utils": "flake-utils",
-        "nixpkgs": [
-          "nixpkgs"
-        ],
-        "rust-overlay": "rust-overlay"
-      },
-      "locked": {
-        "lastModified": 1666087781,
-        "narHash": "sha256-trKVdjMZ8mNkGfLcY5LsJJGtdV3xJDZnMVrkFjErlcs=",
-        "owner": "Alexis211",
-        "repo": "cargo2nix",
-        "rev": "a7a61179b66054904ef6a195d8da736eaaa06c36",
-        "type": "github"
-      },
-      "original": {
-        "owner": "Alexis211",
-        "repo": "cargo2nix",
-        "rev": "a7a61179b66054904ef6a195d8da736eaaa06c36",
-        "type": "github"
-      }
-    },
     "flake-compat": {
       "locked": {
         "lastModified": 1688025799,
@@ -46,54 +20,19 @@
         "systems": "systems"
       },
       "locked": {
-        "lastModified": 1681202837,
-        "narHash": "sha256-H+Rh19JDwRtpVPAWp64F+rlEtxUWBAQW28eAi3SRSzg=",
+        "lastModified": 1701680307,
+        "narHash": "sha256-kAuep2h5ajznlPMD9rnQyffWG8EM/C73lejGofXvdM8=",
         "owner": "numtide",
         "repo": "flake-utils",
-        "rev": "cfacdce06f30d2b68473a46042957675eebb3401",
+        "rev": "4022d587cbbfd70fe950c1e2083a02621806a725",
         "type": "github"
       },
       "original": {
-        "owner": "numtide",
-        "repo": "flake-utils",
-        "type": "github"
-      }
-    },
-    "flake-utils_2": {
-      "inputs": {
-        "systems": "systems_2"
-      },
-      "locked": {
-        "lastModified": 1681202837,
-        "narHash": "sha256-H+Rh19JDwRtpVPAWp64F+rlEtxUWBAQW28eAi3SRSzg=",
-        "owner": "numtide",
-        "repo": "flake-utils",
-        "rev": "cfacdce06f30d2b68473a46042957675eebb3401",
-        "type": "github"
-      },
-      "original": {
-        "owner": "numtide",
-        "repo": "flake-utils",
-        "type": "github"
+        "id": "flake-utils",
+        "type": "indirect"
       }
     },
     "nixpkgs": {
-      "locked": {
-        "lastModified": 1682109806,
-        "narHash": "sha256-d9g7RKNShMLboTWwukM+RObDWWpHKaqTYXB48clBWXI=",
-        "owner": "NixOS",
-        "repo": "nixpkgs",
-        "rev": "2362848adf8def2866fabbffc50462e929d7fffb",
-        "type": "github"
-      },
-      "original": {
-        "owner": "NixOS",
-        "ref": "nixpkgs-unstable",
-        "repo": "nixpkgs",
-        "type": "github"
-      }
-    },
-    "nixpkgs_2": {
       "locked": {
         "lastModified": 1682423271,
         "narHash": "sha256-WHhl1GiOij1ob4cTLL+yhqr+vFOUH8E5wAX8Ir8fvjE=",
@@ -111,32 +50,9 @@
     },
     "root": {
       "inputs": {
-        "cargo2nix": "cargo2nix",
         "flake-compat": "flake-compat",
-        "flake-utils": [
-          "cargo2nix",
-          "flake-utils"
-        ],
-        "nixpkgs": "nixpkgs_2"
-      }
-    },
-    "rust-overlay": {
-      "inputs": {
-        "flake-utils": "flake-utils_2",
+        "flake-utils": "flake-utils",
         "nixpkgs": "nixpkgs"
-      },
-      "locked": {
-        "lastModified": 1682389182,
-        "narHash": "sha256-8t2nmFnH+8V48+IJsf8AK51ebXNlVbOSVYOpiqJKvJE=",
-        "owner": "oxalica",
-        "repo": "rust-overlay",
-        "rev": "74f1a64dd28faeeb85ef081f32cad2989850322c",
-        "type": "github"
-      },
-      "original": {
-        "owner": "oxalica",
-        "repo": "rust-overlay",
-        "type": "github"
       }
     },
     "systems": {
@@ -153,21 +69,6 @@
         "repo": "default",
         "type": "github"
       }
-    },
-    "systems_2": {
-      "locked": {
-        "lastModified": 1681028828,
-        "narHash": "sha256-Vy1rq5AaRuLzOxct8nz4T6wlgyUR7zLU309k9mBC768=",
-        "owner": "nix-systems",
-        "repo": "default",
-        "rev": "da67096a3b9bf56a91d16901293e51ba5b49a27e",
-        "type": "github"
-      },
-      "original": {
-        "owner": "nix-systems",
-        "repo": "default",
-        "type": "github"
-      }
     }
   },
   "root": "root",

flake.nix

@@ -8,49 +8,23 @@
 
   inputs.flake-compat.url = "github:nix-community/flake-compat";
 
-  inputs.cargo2nix = {
-    # As of 2022-10-18: two small patches over unstable branch, one for clippy and one to fix feature detection
-    url = "github:Alexis211/cargo2nix/a7a61179b66054904ef6a195d8da736eaaa06c36";
-
-    # As of 2023-04-25:
-    # - my two patches were merged into unstable (one for clippy and one to "fix" feature detection)
-    # - rustc v1.66
-    # url = "github:cargo2nix/cargo2nix/8fb57a670f7993bfc24099c33eb9c5abb51f29a2";
-
-    # Rust overlay as of 2023-04-25
-    inputs.rust-overlay.url =
-      "github:oxalica/rust-overlay/74f1a64dd28faeeb85ef081f32cad2989850322c";
-
-    inputs.nixpkgs.follows = "nixpkgs";
-    inputs.flake-compat.follows = "flake-compat";
-  };
-
-  inputs.flake-utils.follows = "cargo2nix/flake-utils";
-
-  outputs = { self, nixpkgs, cargo2nix, flake-utils, ... }:
+  outputs = { self, nixpkgs, flake-utils, ... }:
     let
-      git_version = self.lastModifiedDate;
+      gitVersion = self.lastModifiedDate;
       compile = import ./nix/compile.nix;
     in
     flake-utils.lib.eachDefaultSystem (system:
       let pkgs = nixpkgs.legacyPackages.${system};
       in {
         packages = {
-          default = (compile {
-            inherit system git_version;
-            pkgsSrc = nixpkgs;
-            cargo2nixOverlay = cargo2nix.overlays.default;
+          default = (import ./default.nix {
+            inherit gitVersion;
+            buildSystem = system;
             release = true;
-          }).workspace.garage { compileMode = "build"; };
+          }).build;
         };
-        devShell = (compile {
-          inherit system git_version;
-          pkgsSrc = nixpkgs;
-          cargo2nixOverlay = cargo2nix.overlays.default;
-          release = false;
-        }).workspaceShell { packages = with pkgs; [
-          rustfmt
-          mold
-        ]; };
+        devShell = (import ./shell.nix {
+          buildSystem = system;
+        }).rust;
       });
 }

nix/build_index.nix

@@ -1,6 +1,6 @@
 { path ? "/../aws-list.txt", }:
 
-with import ./common.nix;
+with import ./pkgs.nix;
 let
   pkgs = import pkgsSrc { };
   lib = pkgs.lib;

nix/common.nix

@@ -1,17 +0,0 @@
-let
-  lock = builtins.fromJSON (builtins.readFile ../flake.lock);
-
-  inherit (lock.nodes.flake-compat.locked) owner repo rev narHash;
-
-  flake-compat = fetchTarball {
-    url = "https://github.com/${owner}/${repo}/archive/${rev}.tar.gz";
-    sha256 = narHash;
-  };
-
-  flake = (import flake-compat { system = builtins.currentSystem; src = ../.; });
-in
-rec {
-  pkgsSrc = flake.defaultNix.inputs.nixpkgs;
-  cargo2nix = flake.defaultNix.inputs.cargo2nix;
-  cargo2nixOverlay = cargo2nix.overlays.default;
-}

nix/pkgs.nix

@@ -0,0 +1,8 @@
+let
+  lock = builtins.fromJSON (builtins.readFile ../flake.lock);
+  inherit (lock.nodes.nixpkgs.locked) owner repo rev narHash;
+in
+  fetchTarball {
+    url = "https://github.com/${owner}/${repo}/archive/${rev}.tar.gz";
+    sha256 = narHash;
+  }

shell.nix

@@ -1,12 +1,12 @@
-{ system ? builtins.currentSystem, }:
+{
+  buildSystem ? builtins.currentSystem,
+  targetSystem ? buildSystem,
+}:
 
-with import ./nix/common.nix;
+with import ./nix/pkgs.nix;
 
 let
-  pkgs = import pkgsSrc {
-    inherit system;
-    overlays = [ cargo2nixOverlay ];
-  };
+  inherit (import ./default.nix { inherit buildSystem targetSystem; }) pkgs pkgsCross buildEnv;
   kaniko = (import ./nix/kaniko.nix) pkgs;
   manifest-tool = (import ./nix/manifest-tool.nix) pkgs;
   winscp = (import ./nix/winscp.nix) pkgs;
@@ -14,21 +14,13 @@ let
 in {
   # --- Rust Shell ---
   # Use it to compile Garage
-  rust = pkgs.mkShell {
-    nativeBuildInputs = with pkgs; [
-      #rustPlatform.rust.rustc
-      rustPlatform.rust.cargo
-      mold
-      #clippy
-      rustfmt
-      #perl
-      #protobuf
-      #pkg-config
-      #openssl
-      file
-      #cargo2nix.packages.x86_64-linux.cargo2nix
+  rust = pkgsCross.mkShell (buildEnv // {
+    inputsFrom = [
+      kaniko
+      manifest-tool
+      winscp
     ];
-  };
+  });
 
   # --- Integration shell ---
   # Use it to test Garage with common S3 clients

src/api/Cargo.toml

@@ -45,7 +45,7 @@ http = "0.2"
 httpdate = "1.0"
 http-range = "0.1"
 hyper = { version = "0.14", features = ["server", "http1", "runtime", "tcp", "stream"] }
-hyperlocal = { version = "0.8.0", default-features = false, features = ["server"] }
+#hyperlocal = { version = "0.8.0", default-features = false, features = ["server"] }
 multer = "2.0"
 percent-encoding = "2.1.0"
 roxmltree = "0.18"

src/api/admin/api_server.rs

@@ -182,7 +182,7 @@ impl AdminApiServer {
 			),
 		};
 		let status_str = format!(
-			"{}\nConsult the full health check API endpoint at /v0/health for more details\n",
+			"{}\nConsult the full health check API endpoint at /v1/health for more details\n",
 			status_str
 		);
 

src/api/generic_server.rs

@@ -1,5 +1,4 @@
-use std::fs::{self, Permissions};
-use std::os::unix::fs::PermissionsExt;
+//use std::fs::{self, Permissions};
 use std::sync::Arc;
 
 use async_trait::async_trait;
@@ -12,9 +11,9 @@ use hyper::service::{make_service_fn, service_fn};
 use hyper::{Body, Request, Response, Server};
 use hyper::{HeaderMap, StatusCode};
 
-use hyperlocal::UnixServerExt;
+//use hyperlocal::UnixServerExt;
 
-use tokio::net::UnixStream;
+//use tokio::net::UnixStream;
 
 use opentelemetry::{
 	global,
@@ -114,18 +113,18 @@ impl<A: ApiHandler> ApiServer<A> {
 			}
 		});
 
-		let unix_service = make_service_fn(|_: &UnixStream| {
-			let this = self.clone();
+		//let unix_service = make_service_fn(|_: &UnixStream| {
+		//	let this = self.clone();
 
-			let path = bind_addr.to_string();
-			async move {
-				Ok::<_, GarageError>(service_fn(move |req: Request<Body>| {
-					let this = this.clone();
+		//	let path = bind_addr.to_string();
+		//	async move {
+		//		Ok::<_, GarageError>(service_fn(move |req: Request<Body>| {
+		//			let this = this.clone();
 
-					this.handler(req, path.clone())
-				}))
-			}
-		});
+		//			this.handler(req, path.clone())
+		//		}))
+		//	}
+		//});
 
 		info!(
 			"{} API server listening on {}",
@@ -140,23 +139,24 @@ impl<A: ApiHandler> ApiServer<A> {
 					.with_graceful_shutdown(shutdown_signal)
 					.await?
 			}
-			UnixOrTCPSocketAddress::UnixSocket(ref path) => {
-				if path.exists() {
-					fs::remove_file(path)?
-				}
+			UnixOrTCPSocketAddress::UnixSocket(_path) => {
+				panic!("Unix sockets are not supported in this fork") // TODO(mediocregopher)
+			} //UnixOrTCPSocketAddress::UnixSocket(ref path) => {
+			  //    use std::os::unix::fs::PermissionsExt;
+			  //    remove_unix_socket_if_present(path).await?;
 
-				let bound = Server::bind_unix(path)?;
+			  //	let bound = Server::bind_unix(path)?;
 
-				fs::set_permissions(
-					path,
-					Permissions::from_mode(unix_bind_addr_mode.unwrap_or(0o222)),
-				)?;
+			  //	fs::set_permissions(
+			  //		path,
+			  //		Permissions::from_mode(unix_bind_addr_mode.unwrap_or(0o222)),
+			  //	)?;
 
-				bound
-					.serve(unix_service)
-					.with_graceful_shutdown(shutdown_signal)
-					.await?;
-			}
+			  //	bound
+			  //		.serve(unix_service)
+			  //		.with_graceful_shutdown(shutdown_signal)
+			  //		.await?;
+			  //}
 		};
 
 		Ok(())

src/api/s3/api_server.rs

@@ -344,7 +344,7 @@ impl ApiHandler for S3ApiServer {
 						bucket_id,
 						key,
 						upload_id,
-						part_number_marker: part_number_marker.map(|p| p.clamp(1, 10000)),
+						part_number_marker: part_number_marker.map(|p| p.min(10000)),
 						max_parts: max_parts.unwrap_or(1000).clamp(1, 1000),
 					},
 				)

src/api/s3/delete.rs

@@ -3,12 +3,12 @@ use std::sync::Arc;
 use hyper::{Body, Request, Response, StatusCode};
 
 use garage_util::data::*;
-use garage_util::time::*;
 
 use garage_model::garage::Garage;
 use garage_model::s3::object_table::*;
 
 use crate::s3::error::*;
+use crate::s3::put::next_timestamp;
 use crate::s3::xml as s3_xml;
 use crate::signature::verify_signed_content;
 
@@ -23,40 +23,36 @@ async fn handle_delete_internal(
 		.await?
 		.ok_or(Error::NoSuchKey)?; // No need to delete
 
-	let interesting_versions = object.versions().iter().filter(|v| {
-		!matches!(
-			v.state,
-			ObjectVersionState::Aborted
-				| ObjectVersionState::Complete(ObjectVersionData::DeleteMarker)
-		)
-	});
+	let del_timestamp = next_timestamp(Some(&object));
+	let del_uuid = gen_uuid();
 
-	let mut version_to_delete = None;
-	let mut timestamp = now_msec();
-	for v in interesting_versions {
-		if v.timestamp + 1 > timestamp || version_to_delete.is_none() {
-			version_to_delete = Some(v.uuid);
+	let deleted_version = object
+		.versions()
+		.iter()
+		.rev()
+		.find(|v| !matches!(&v.state, ObjectVersionState::Aborted))
+		.or_else(|| object.versions().iter().rev().next());
+	let deleted_version = match deleted_version {
+		Some(dv) => dv.uuid,
+		None => {
+			warn!("Object has no versions: {:?}", object);
+			Uuid::from([0u8; 32])
 		}
-		timestamp = std::cmp::max(timestamp, v.timestamp + 1);
-	}
-
-	let deleted_version = version_to_delete.ok_or(Error::NoSuchKey)?;
-
-	let version_uuid = gen_uuid();
+	};
 
 	let object = Object::new(
 		bucket_id,
 		key.into(),
 		vec![ObjectVersion {
-			uuid: version_uuid,
-			timestamp,
+			uuid: del_uuid,
+			timestamp: del_timestamp,
 			state: ObjectVersionState::Complete(ObjectVersionData::DeleteMarker),
 		}],
 	);
 
 	garage.object_table.insert(&object).await?;
 
-	Ok((deleted_version, version_uuid))
+	Ok((deleted_version, del_uuid))
 }
 
 pub async fn handle_delete(

src/api/s3/list.rs

@@ -426,8 +426,10 @@ where
 		// Drop the first key if needed
 		// Only AfterKey requires it according to the S3 spec and our implem.
 		match (&cursor, iter.peek()) {
-			(RangeBegin::AfterKey { key }, Some(object)) if &object.key == key => iter.next(),
-			(_, _) => None,
+			(RangeBegin::AfterKey { key }, Some(object)) if &object.key == key => {
+				iter.next();
+			}
+			_ => (),
 		};
 
 		while let Some(object) = iter.peek() {
@@ -436,16 +438,22 @@ where
 				return Ok(None);
 			}
 
-			cursor = match acc.extract(query, &cursor, &mut iter) {
-				ExtractionResult::Extracted { key } => RangeBegin::AfterKey { key },
+			match acc.extract(query, &cursor, &mut iter) {
+				ExtractionResult::Extracted { key } => {
+					cursor = RangeBegin::AfterKey { key };
+				}
 				ExtractionResult::SkipTo { key, fallback_key } => {
-					RangeBegin::IncludingKey { key, fallback_key }
+					cursor = RangeBegin::IncludingKey { key, fallback_key };
 				}
 				ExtractionResult::FilledAtUpload { key, upload } => {
-					return Ok(Some(RangeBegin::AfterUpload { key, upload }))
+					return Ok(Some(RangeBegin::AfterUpload { key, upload }));
+				}
+				ExtractionResult::Filled => {
+					return Ok(Some(cursor));
+				}
+				ExtractionResult::NoMore => {
+					return Ok(None);
 				}
-				ExtractionResult::Filled => return Ok(Some(cursor)),
-				ExtractionResult::NoMore => return Ok(None),
 			};
 		}
 
@@ -519,8 +527,8 @@ fn fetch_part_info<'a>(
 /// This key can be the prefix in the base case, or intermediate
 /// points in the dataset if we are continuing a previous listing.
 impl ListObjectsQuery {
-	fn build_accumulator(&self) -> Accumulator<String, ObjectInfo> {
-		Accumulator::<String, ObjectInfo>::new(self.common.page_size)
+	fn build_accumulator(&self) -> ObjectAccumulator {
+		ObjectAccumulator::new(self.common.page_size)
 	}
 
 	fn begin(&self) -> Result<RangeBegin, Error> {
@@ -529,9 +537,10 @@ impl ListObjectsQuery {
 				// In V2 mode, the continuation token is defined as an opaque
 				// string in the spec, so we can do whatever we want with it.
 				// In our case, it is defined as either [ or ] (for include
+				// or exclude), followed by a base64-encoded string
 				// representing the key to start with.
-				(Some(token), _) => match &token[..1] {
-					"[" => Ok(RangeBegin::IncludingKey {
+				(Some(token), _) => match &token.get(..1) {
+					Some("[") => Ok(RangeBegin::IncludingKey {
 						key: String::from_utf8(
 							BASE64_STANDARD
 								.decode(token[1..].as_bytes())
@@ -539,7 +548,7 @@ impl ListObjectsQuery {
 						)?,
 						fallback_key: None,
 					}),
-					"]" => Ok(RangeBegin::AfterKey {
+					Some("]") => Ok(RangeBegin::AfterKey {
 						key: String::from_utf8(
 							BASE64_STANDARD
 								.decode(token[1..].as_bytes())
@@ -580,8 +589,8 @@ impl ListObjectsQuery {
 }
 
 impl ListMultipartUploadsQuery {
-	fn build_accumulator(&self) -> Accumulator<Uuid, UploadInfo> {
-		Accumulator::<Uuid, UploadInfo>::new(self.common.page_size)
+	fn build_accumulator(&self) -> UploadAccumulator {
+		UploadAccumulator::new(self.common.page_size)
 	}
 
 	fn begin(&self) -> Result<RangeBegin, Error> {
@@ -665,6 +674,7 @@ impl<K: std::cmp::Ord, V> Accumulator<K, V> {
 			Some(p) => p,
 			None => return None,
 		};
+		assert!(pfx.starts_with(&query.prefix));
 
 		// Try to register this prefix
 		// If not possible, we can return early
@@ -675,8 +685,11 @@ impl<K: std::cmp::Ord, V> Accumulator<K, V> {
 		// We consume the whole common prefix from the iterator
 		let mut last_pfx_key = &object.key;
 		loop {
-			last_pfx_key = match objects.peek() {
-				Some(o) if o.key.starts_with(pfx) => &o.key,
+			match objects.peek() {
+				Some(o) if o.key.starts_with(pfx) => {
+					last_pfx_key = &o.key;
+					objects.next();
+				}
 				Some(_) => {
 					return Some(ExtractionResult::Extracted {
 						key: last_pfx_key.to_owned(),
@@ -692,8 +705,6 @@ impl<K: std::cmp::Ord, V> Accumulator<K, V> {
 					}
 				}
 			};
-
-			objects.next();
 		}
 	}
 
@@ -708,12 +719,11 @@ impl<K: std::cmp::Ord, V> Accumulator<K, V> {
 		}
 
 		// Otherwise, we need to check if we can add it
-		match self.is_full() {
-			true => false,
-			false => {
-				self.common_prefixes.insert(key);
-				true
-			}
+		if self.is_full() {
+			false
+		} else {
+			self.common_prefixes.insert(key);
+			true
 		}
 	}
 
@@ -721,12 +731,11 @@ impl<K: std::cmp::Ord, V> Accumulator<K, V> {
 		// It is impossible to add twice a key, this is an error
 		assert!(!self.keys.contains_key(&key));
 
-		match self.is_full() {
-			true => false,
-			false => {
-				self.keys.insert(key, value);
-				true
-			}
+		if self.is_full() {
+			false
+		} else {
+			self.keys.insert(key, value);
+			true
 		}
 	}
 }
@@ -743,6 +752,7 @@ impl ExtractAccumulator for ObjectAccumulator {
 		}
 
 		let object = objects.next().expect("This iterator can not be empty as it is checked earlier in the code. This is a logic bug, please report it.");
+		assert!(object.key.starts_with(&query.prefix));
 
 		let version = match object.versions().iter().find(|x| x.is_data()) {
 			Some(v) => v,

src/api/s3/multipart.rs

@@ -9,7 +9,6 @@ use md5::{Digest as Md5Digest, Md5};
 use garage_table::*;
 use garage_util::async_hash::*;
 use garage_util::data::*;
-use garage_util::time::*;
 
 use garage_model::bucket_table::Bucket;
 use garage_model::garage::Garage;
@@ -30,10 +29,13 @@ pub async fn handle_create_multipart_upload(
 	req: &Request<Body>,
 	bucket_name: &str,
 	bucket_id: Uuid,
-	key: &str,
+	key: &String,
 ) -> Result<Response<Body>, Error> {
+	let existing_object = garage.object_table.get(&bucket_id, &key).await?;
+
 	let upload_id = gen_uuid();
-	let timestamp = now_msec();
+	let timestamp = next_timestamp(existing_object.as_ref());
+
 	let headers = get_headers(req.headers())?;
 
 	// Create object in object table
@@ -233,7 +235,8 @@ pub async fn handle_complete_multipart_upload(
 
 	// Get object and multipart upload
 	let key = key.to_string();
-	let (_, mut object_version, mpu) = get_upload(&garage, &bucket.id, &key, &upload_id).await?;
+	let (object, mut object_version, mpu) =
+		get_upload(&garage, &bucket.id, &key, &upload_id).await?;
 
 	if mpu.parts.is_empty() {
 		return Err(Error::bad_request("No data was uploaded"));
@@ -331,7 +334,7 @@ pub async fn handle_complete_multipart_upload(
 	// Calculate total size of final object
 	let total_size = parts.iter().map(|x| x.size.unwrap()).sum();
 
-	if let Err(e) = check_quotas(&garage, bucket, &key, total_size).await {
+	if let Err(e) = check_quotas(&garage, bucket, total_size, Some(&object)).await {
 		object_version.state = ObjectVersionState::Aborted;
 		let final_object = Object::new(bucket.id, key.clone(), vec![object_version]);
 		garage.object_table.insert(&final_object).await?;

src/api/s3/put.rs

@@ -3,6 +3,7 @@ use std::sync::Arc;
 
 use base64::prelude::*;
 use futures::prelude::*;
+use futures::try_join;
 use hyper::body::{Body, Bytes};
 use hyper::header::{HeaderMap, HeaderValue};
 use hyper::{Request, Response};
@@ -35,7 +36,7 @@ pub async fn handle_put(
 	garage: Arc<Garage>,
 	req: Request<Body>,
 	bucket: &Bucket,
-	key: &str,
+	key: &String,
 	content_sha256: Option<Hash>,
 ) -> Result<Response<Body>, Error> {
 	// Retrieve interesting headers from request
@@ -68,16 +69,24 @@ pub(crate) async fn save_stream<S: Stream<Item = Result<Bytes, Error>> + Unpin>(
 	headers: ObjectVersionHeaders,
 	body: S,
 	bucket: &Bucket,
-	key: &str,
+	key: &String,
 	content_md5: Option<String>,
 	content_sha256: Option<FixedBytes32>,
 ) -> Result<(Uuid, String), Error> {
+	let mut chunker = StreamChunker::new(body, garage.config.block_size);
+	let (first_block_opt, existing_object) = try_join!(
+		chunker.next(),
+		garage
+			.object_table
+			.get(&bucket.id, key)
+			.map_err(Error::from),
+	)?;
+
+	let first_block = first_block_opt.unwrap_or_default();
+
 	// Generate identity of new version
 	let version_uuid = gen_uuid();
-	let version_timestamp = now_msec();
-
-	let mut chunker = StreamChunker::new(body, garage.config.block_size);
-	let first_block = chunker.next().await?.unwrap_or_default();
+	let version_timestamp = next_timestamp(existing_object.as_ref());
 
 	// If body is small enough, store it directly in the object table
 	// as "inline data". We can then return immediately.
@@ -97,7 +106,7 @@ pub(crate) async fn save_stream<S: Stream<Item = Result<Bytes, Error>> + Unpin>(
 			content_sha256,
 		)?;
 
-		check_quotas(&garage, bucket, key, size).await?;
+		check_quotas(&garage, bucket, size, existing_object.as_ref()).await?;
 
 		let object_version = ObjectVersion {
 			uuid: version_uuid,
@@ -176,7 +185,7 @@ pub(crate) async fn save_stream<S: Stream<Item = Result<Bytes, Error>> + Unpin>(
 		content_sha256,
 	)?;
 
-	check_quotas(&garage, bucket, key, total_size).await?;
+	check_quotas(&garage, bucket, total_size, existing_object.as_ref()).await?;
 
 	// Save final object state, marked as Complete
 	let md5sum_hex = hex::encode(data_md5sum);
@@ -229,19 +238,19 @@ pub(crate) fn ensure_checksum_matches(
 pub(crate) async fn check_quotas(
 	garage: &Arc<Garage>,
 	bucket: &Bucket,
-	key: &str,
 	size: u64,
+	prev_object: Option<&Object>,
 ) -> Result<(), Error> {
 	let quotas = bucket.state.as_option().unwrap().quotas.get();
 	if quotas.max_objects.is_none() && quotas.max_size.is_none() {
 		return Ok(());
 	};
 
-	let key = key.to_string();
-	let (prev_object, counters) = futures::try_join!(
-		garage.object_table.get(&bucket.id, &key),
-		garage.object_counter_table.table.get(&bucket.id, &EmptyKey),
-	)?;
+	let counters = garage
+		.object_counter_table
+		.table
+		.get(&bucket.id, &EmptyKey)
+		.await?;
 
 	let counters = counters
 		.map(|x| x.filtered_values(&garage.system.ring.borrow()))
@@ -275,7 +284,7 @@ pub(crate) async fn check_quotas(
 		if cnt_size_diff > 0 && current_size + cnt_size_diff > ms as i64 {
 			return Err(Error::forbidden(format!(
 				"Bucket size quota is reached, maximum total size of objects for this bucket: {}. The bucket is already {} bytes, and this object would add {} bytes.",
-				ms, current_size, size
+				ms, current_size, cnt_size_diff
 			)));
 		}
 	}
@@ -519,3 +528,11 @@ pub(crate) fn get_headers(headers: &HeaderMap<HeaderValue>) -> Result<ObjectVers
 		other,
 	})
 }
+
+pub(crate) fn next_timestamp(existing_object: Option<&Object>) -> u64 {
+	existing_object
+		.as_ref()
+		.and_then(|obj| obj.versions().iter().map(|v| v.timestamp).max())
+		.map(|t| std::cmp::max(t + 1, now_msec()))
+		.unwrap_or_else(now_msec)
+}

src/block/manager.rs

@@ -771,11 +771,7 @@ impl BlockManagerLocked {
 			// Now, we do an fsync on the containing directory, to ensure that the rename
 			// is persisted properly. See:
 			// http://thedjbway.b0llix.net/qmail/syncdir.html
-			let dir = fs::OpenOptions::new()
-				.read(true)
-				.mode(0)
-				.open(directory)
-				.await?;
+			let dir = fs::OpenOptions::new().read(true).open(directory).await?;
 			dir.sync_all().await?;
 			drop(dir);
 		}

src/rpc/system.rs

@@ -3,7 +3,6 @@ use std::collections::HashMap;
 use std::io::{Read, Write};
 use std::net::{IpAddr, SocketAddr};
 use std::path::{Path, PathBuf};
-use std::sync::atomic::Ordering;
 use std::sync::{Arc, RwLock};
 use std::time::{Duration, Instant};
 
@@ -198,6 +197,20 @@ pub fn read_node_id(metadata_dir: &Path) -> Result<NodeID, Error> {
 	Ok(NodeID::from_slice(&key[..]).unwrap())
 }
 
+#[cfg(not(windows))]
+fn set_private_key_perms(path: &Path) -> Result<(), Error> {
+	use std::os::unix::fs::PermissionsExt;
+	let perm = std::fs::Permissions::from_mode(0o600);
+	std::fs::set_permissions(path, perm)?;
+	Ok(())
+}
+
+#[cfg(windows)]
+fn set_private_key_perms(_path: &Path) -> Result<(), Error> {
+	// TODO(mediocregopher) figure out how to do this, but it's not strictly necessary
+	Ok(())
+}
+
 pub fn gen_node_key(metadata_dir: &Path) -> Result<NodeKey, Error> {
 	let mut key_file = metadata_dir.to_path_buf();
 	key_file.push("node_key");
@@ -222,11 +235,8 @@ pub fn gen_node_key(metadata_dir: &Path) -> Result<NodeKey, Error> {
 		let (pubkey, key) = ed25519::gen_keypair();
 
 		{
-			use std::os::unix::fs::PermissionsExt;
 			let mut f = std::fs::File::create(key_file.as_path())?;
-			let mut perm = f.metadata()?.permissions();
-			perm.set_mode(0o600);
-			std::fs::set_permissions(key_file.as_path(), perm)?;
+			set_private_key_perms(key_file.as_path())?;
 			f.write_all(&key[..])?;
 		}
 
@@ -890,6 +900,18 @@ impl NodeStatus {
 		}
 	}
 
+	#[cfg(windows)]
+	fn update_disk_usage(
+		&mut self,
+		_meta_dir: &Path,
+		_data_dir: &DataDirEnum,
+		_metrics: &SystemMetrics,
+	) {
+		// TODO(mediocregopher) it'd be nice to have this for windows too, but it seems to only be
+		// used for OpenTelemetry so it's not a real requirement.
+	}
+
+	#[cfg(not(windows))]
 	fn update_disk_usage(
 		&mut self,
 		meta_dir: &Path,
@@ -897,6 +919,7 @@ impl NodeStatus {
 		metrics: &SystemMetrics,
 	) {
 		use nix::sys::statvfs::statvfs;
+		use std::sync::atomic::Ordering;
 		let mount_avail = |path: &Path| match statvfs(path) {
 			Ok(x) => {
 				let avail = x.blocks_available() as u64 * x.fragment_size() as u64;
@@ -955,6 +978,7 @@ impl NodeStatus {
 	}
 }
 
+#[cfg(not(windows))]
 fn get_default_ip() -> Option<IpAddr> {
 	pnet_datalink::interfaces()
 		.iter()
@@ -963,6 +987,11 @@ fn get_default_ip() -> Option<IpAddr> {
 		.map(|a| a.ip())
 }
 
+#[cfg(windows)]
+fn get_default_ip() -> Option<IpAddr> {
+    None
+}
+
 async fn resolve_peers(peers: &[String]) -> Vec<(NodeID, SocketAddr)> {
 	let mut ret = vec![];
 

src/web/Cargo.toml

@@ -27,7 +27,7 @@ futures = "0.3"
 
 http = "0.2"
 hyper = { version = "0.14", features = ["server", "http1", "runtime", "tcp", "stream"] }
-hyperlocal = { version = "0.8.0", default-features = false, features = ["server"] }
+#hyperlocal = { version = "0.8.0", default-features = false, features = ["server"] }
 
 tokio = { version = "1.0", default-features = false, features = ["net"] }
 

src/web/web_server.rs

@@ -1,5 +1,5 @@
-use std::fs::{self, Permissions};
-use std::os::unix::prelude::PermissionsExt;
+//use std::fs::{self, Permissions};
+//use std::os::unix::prelude::PermissionsExt;
 use std::{convert::Infallible, sync::Arc};
 
 use futures::future::Future;
@@ -11,9 +11,9 @@ use hyper::{
 	Body, Method, Request, Response, Server, StatusCode,
 };
 
-use hyperlocal::UnixServerExt;
+//use hyperlocal::UnixServerExt;
 
-use tokio::net::UnixStream;
+//use tokio::net::UnixStream;
 
 use opentelemetry::{
 	global,
@@ -100,18 +100,18 @@ impl WebServer {
 			}
 		});
 
-		let unix_service = make_service_fn(|_: &UnixStream| {
-			let web_server = web_server.clone();
+		//let unix_service = make_service_fn(|_: &UnixStream| {
+		//	let web_server = web_server.clone();
 
-			let path = addr.to_string();
-			async move {
-				Ok::<_, Error>(service_fn(move |req: Request<Body>| {
-					let web_server = web_server.clone();
-
-					web_server.handle_request(req, path.clone())
-				}))
-			}
-		});
+		//	let path = addr.to_string();
+		//	async move {
+		//		remove_unix_socket_if_present(&path).await.expect("could not remove existing unix socket");
+		//		Ok::<_, Error>(service_fn(move |req: Request<Body>| {
+		//			let web_server = web_server.clone();
+		//			web_server.handle_request(req, path.clone())
+		//		}))
+		//	}
+		//});
 
 		info!("Web server listening on {}", addr);
 
@@ -122,20 +122,22 @@ impl WebServer {
 					.with_graceful_shutdown(shutdown_signal)
 					.await?
 			}
-			UnixOrTCPSocketAddress::UnixSocket(ref path) => {
-				if path.exists() {
-					fs::remove_file(path)?
-				}
+			UnixOrTCPSocketAddress::UnixSocket(_path) => {
+				panic!("Unix sockets are not supported in this fork") // TODO(mediocregopher)
+			} //UnixOrTCPSocketAddress::UnixSocket(ref path) => {
+			  //	if path.exists() {
+			  //		fs::remove_file(path)?
+			  //	}
 
-				let bound = Server::bind_unix(path)?;
+			  //	let bound = Server::bind_unix(path)?;
 
-				fs::set_permissions(path, Permissions::from_mode(0o222))?;
+			  //	fs::set_permissions(path, Permissions::from_mode(0o222))?;
 
-				bound
-					.serve(unix_service)
-					.with_graceful_shutdown(shutdown_signal)
-					.await?;
-			}
+			  //	bound
+			  //		.serve(unix_service)
+			  //		.with_graceful_shutdown(shutdown_signal)
+			  //		.await?;
+			  //}
 		};
 
 		Ok(())