diff --git a/Cargo.lock b/Cargo.lock index a4b94cb6..f8246f9c 100644 --- a/Cargo.lock +++ b/Cargo.lock @@ -1319,7 +1319,6 @@ dependencies = [ "http-body-util", "hyper 1.6.0", "hyper-util", - "idna 0.5.0", "md-5", "nom", "opentelemetry", @@ -2189,16 +2188,6 @@ version = "1.0.1" source = "registry+https://github.com/rust-lang/crates.io-index" checksum = "b9e0384b61958566e926dc50660321d12159025e767c18e043daf26b70104c39" -[[package]] -name = "idna" -version = "0.5.0" -source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "634d9b1461af396cad843f47fdba5597a4f9e6ddd4bfb6ff5d85028c25cb12f6" -dependencies = [ - "unicode-bidi", - "unicode-normalization", -] - [[package]] name = "idna" version = "1.0.3" @@ -4301,21 +4290,6 @@ dependencies = [ "zerovec", ] -[[package]] -name = "tinyvec" -version = "1.9.0" -source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "09b3661f17e86524eccd4371ab0429194e0d7c008abb45f7a7495b1719463c71" -dependencies = [ - "tinyvec_macros", -] - -[[package]] -name = "tinyvec_macros" -version = "0.1.1" -source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "1f3ccbac311fea05f86f61904b462b55fb3df8837a366dfc601a0161d0532f20" - [[package]] name = "tokio" version = "1.44.1" @@ -4636,27 +4610,12 @@ version = "0.1.7" source = "registry+https://github.com/rust-lang/crates.io-index" checksum = "2896d95c02a80c6d6a5d6e953d479f5ddf2dfdb6a244441010e373ac0fb88971" -[[package]] -name = "unicode-bidi" -version = "0.3.18" -source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "5c1cb5db39152898a79168971543b1cb5020dff7fe43c8dc468b0885f5e29df5" - [[package]] name = "unicode-ident" version = "1.0.18" source = "registry+https://github.com/rust-lang/crates.io-index" checksum = "5a5f39404a5da50712a4c1eecf25e90dd62b613502b7e925fd4e4d19b5c96512" -[[package]] -name = "unicode-normalization" -version = "0.1.24" -source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "5033c97c4262335cded6d6fc3e5c18ab755e1a3dc96376350f3d8e9f009ad956" -dependencies = [ - "tinyvec", -] - [[package]] name = "unicode-segmentation" version = "1.12.0" @@ -4704,7 +4663,7 @@ source = "registry+https://github.com/rust-lang/crates.io-index" checksum = "32f8b686cadd1473f4bd0117a5d28d36b1ade384ea9b5069a1c40aefed7fda60" dependencies = [ "form_urlencoded", - "idna 1.0.3", + "idna", "percent-encoding", ] diff --git a/Cargo.toml b/Cargo.toml index 004472f6..fdf86a0f 100644 --- a/Cargo.toml +++ b/Cargo.toml @@ -57,7 +57,6 @@ git-version = "0.3.4" hex = "0.4" hexdump = "0.1" hmac = "0.12" -idna = "0.5" itertools = "0.12" ipnet = "2.9.0" lazy_static = "1.4" diff --git a/doc/book/connect/apps/index.md b/doc/book/connect/apps/index.md index 14868373..5ec9686c 100644 --- a/doc/book/connect/apps/index.md +++ b/doc/book/connect/apps/index.md @@ -69,7 +69,7 @@ $CONFIG = array( 'hostname' => '127.0.0.1', // Can also be a domain name, eg. garage.example.com 'port' => 3900, // Put your reverse proxy port or your S3 API port 'use_ssl' => false, // Set it to true if you have a TLS enabled reverse proxy - 'region' => 'garage', // Garage has only one region named "garage" + 'region' => 'garage', // Garage default region is named "garage", edit according to your cluster config 'use_path_style' => true // Garage supports only path style, must be set to true ], ], @@ -135,7 +135,7 @@ bucket but doesn't also know the secret encryption key. *Click on the picture to zoom* Add a new external storage. Put what you want in "folder name" (eg. "shared"). Select "Amazon S3". Keep "Access Key" for the Authentication field. -In Configuration, put your bucket name (eg. nextcloud), the host (eg. 127.0.0.1), the port (eg. 3900 or 443), the region (garage). Tick the SSL box if you have put an HTTPS proxy in front of garage. You must tick the "Path access" box and you must leave the "Legacy authentication (v2)" box empty. Put your Key ID (eg. GK...) and your Secret Key in the last two input boxes. Finally click on the tick symbol on the right of your screen. +In Configuration, put your bucket name (eg. nextcloud), the host (eg. 127.0.0.1), the port (eg. 3900 or 443), the region ("garage" if you use the default, or the one your configured in your `garage.toml`). Tick the SSL box if you have put an HTTPS proxy in front of garage. You must tick the "Path access" box and you must leave the "Legacy authentication (v2)" box empty. Put your Key ID (eg. GK...) and your Secret Key in the last two input boxes. Finally click on the tick symbol on the right of your screen. Now go to your "Files" app and a new "linked folder" has appeared with the name you chose earlier (eg. "shared"). @@ -238,7 +238,7 @@ object_storage: # Put localhost only if you have a garage instance running on that node endpoint: 'http://localhost:3900' # or "garage.example.com" if you have TLS on port 443 - # Garage supports only one region for now, named garage + # Garage default region is named "garage", edit according to your config region: 'garage' credentials: @@ -441,7 +441,7 @@ media_storage_providers: store_synchronous: True # do we want to wait that the file has been written before returning? config: bucket: matrix # the name of our bucket, we chose matrix earlier - region_name: garage # only "garage" is supported for the region field + region_name: garage # "garage" by default, edit according to your cluster config endpoint_url: http://localhost:3900 # the path to the S3 endpoint access_key_id: "GKxxx" # your Key ID secret_access_key: "xxxx" # your Secret Key diff --git a/doc/book/cookbook/kubernetes.md b/doc/book/cookbook/kubernetes.md index afa4fdb1..fde6ee4e 100644 --- a/doc/book/cookbook/kubernetes.md +++ b/doc/book/cookbook/kubernetes.md @@ -26,6 +26,13 @@ Or deploy with custom values: helm install --create-namespace --namespace garage garage ./garage -f values.override.yaml ``` +If you want to manage the CustomRessourceDefinition used by garage for its `kubernetes_discovery` outside of the helm chart, add `garage.kubernetesSkipCrd: true` to your custom values and use the kustomization before deploying the helm chart: + +```bash +kubectl apply -k ../k8s/crd +helm install --create-namespace --namespace garage garage ./garage -f values.override.yaml +``` + After deploying, cluster layout must be configured manually as described in [Creating a cluster layout](@/documentation/quick-start/_index.md#creating-a-cluster-layout). Use the following command to access garage CLI: ```bash diff --git a/doc/book/cookbook/systemd.md b/doc/book/cookbook/systemd.md index c0ed7d1f..ebff8c15 100644 --- a/doc/book/cookbook/systemd.md +++ b/doc/book/cookbook/systemd.md @@ -28,6 +28,7 @@ StateDirectory=garage DynamicUser=true ProtectHome=true NoNewPrivileges=true +LimitNOFILE=42000 [Install] WantedBy=multi-user.target diff --git a/doc/book/quick-start/_index.md b/doc/book/quick-start/_index.md index b94257d5..b86b0f91 100644 --- a/doc/book/quick-start/_index.md +++ b/doc/book/quick-start/_index.md @@ -129,9 +129,9 @@ docker run \ -d \ --name garaged \ -p 3900:3900 -p 3901:3901 -p 3902:3902 -p 3903:3903 \ - -v /etc/garage.toml:/path/to/garage.toml \ - -v /var/lib/garage/meta:/path/to/garage/meta \ - -v /var/lib/garage/data:/path/to/garage/data \ + -v /path/to/garage.toml:/etc/garage.toml \ + -v /path/to/garage/meta:/var/lib/garage/meta \ + -v /path/to/garage/data:/var/lib/garage/data \ dxflrs/garage:v2.0.0 ``` diff --git a/doc/book/reference-manual/configuration.md b/doc/book/reference-manual/configuration.md index 6e4daea0..b84162ee 100644 --- a/doc/book/reference-manual/configuration.md +++ b/doc/book/reference-manual/configuration.md @@ -46,6 +46,7 @@ bootstrap_peers = [ "212fd62eeaca72c122b45a7f4fa0f55e012aa5e24ac384a72a3016413fa724ff@[fc00:F::1]:3901", ] +allow_punycode = false [consul_discovery] api = "catalog" @@ -116,6 +117,7 @@ Top-level configuration options: [`rpc_public_addr`](#rpc_public_addr), [`rpc_public_addr_subnet`](#rpc_public_addr_subnet) [`rpc_secret`/`rpc_secret_file`](#rpc_secret). +[`allow_punycode`](#allow_punycode). The `[consul_discovery]` section: [`api`](#consul_api), @@ -606,7 +608,7 @@ be obtained by running `garage node id` and then included directly in the key will be returned by `garage node id` and you will have to add the IP yourself. -### `allow_world_readable_secrets` or `GARAGE_ALLOW_WORLD_READABLE_SECRETS` (env) {#allow_world_readable_secrets} +#### `allow_world_readable_secrets` or `GARAGE_ALLOW_WORLD_READABLE_SECRETS` (env) {#allow_world_readable_secrets} Garage checks the permissions of your secret files to make sure they're not world-readable. In some cases, the check might fail and consider your files as @@ -618,6 +620,13 @@ permission verification. Alternatively, you can set the `GARAGE_ALLOW_WORLD_READABLE_SECRETS` environment variable to `true` to bypass the permissions check. +#### `allow_punycode` {#allow_punycode} + +Allow creating buckets with names containing punycode. When used for buckets served +as websites, this allows using almost any unicode character in the domain name. + +Default to `false`. + ### The `[consul_discovery]` section Garage supports discovering other nodes of the cluster using Consul. For this diff --git a/script/helm/garage/Chart.yaml b/script/helm/garage/Chart.yaml index 5fe180a0..d71b27c9 100644 --- a/script/helm/garage/Chart.yaml +++ b/script/helm/garage/Chart.yaml @@ -1,24 +1,18 @@ apiVersion: v2 name: garage description: S3-compatible object store for small self-hosted geo-distributed deployments - -# A chart can be either an 'application' or a 'library' chart. -# -# Application charts are a collection of templates that can be packaged into versioned archives -# to be deployed. -# -# Library charts provide useful utilities or functions for the chart developer. They're included as -# a dependency of application charts to inject those utilities and functions into the rendering -# pipeline. Library charts do not define any templates and therefore cannot be deployed. type: application - -# 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: 0.8.0 - -# 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 -# follow Semantic Versioning. They should reflect the version the application is using. -# It is recommended to use it with quotes. appVersion: "v2.0.0" +home: https://garagehq.deuxfleurs.fr/ +icon: https://garagehq.deuxfleurs.fr/images/garage-logo.svg + +keywords: +- geo-distributed +- read-after-write-consistency +- s3-compatible + +sources: +- https://git.deuxfleurs.fr/Deuxfleurs/garage.git + +maintainers: [] diff --git a/script/helm/garage/README.md b/script/helm/garage/README.md index 55a809b8..55ddfcd0 100644 --- a/script/helm/garage/README.md +++ b/script/helm/garage/README.md @@ -1,9 +1,15 @@ # garage -![Version: 0.6.0](https://img.shields.io/badge/Version-0.6.0-informational?style=flat-square) ![Type: application](https://img.shields.io/badge/Type-application-informational?style=flat-square) ![AppVersion: v1.0.1](https://img.shields.io/badge/AppVersion-v1.0.1-informational?style=flat-square) +![Version: 0.7.0](https://img.shields.io/badge/Version-0.7.0-informational?style=flat-square) ![Type: application](https://img.shields.io/badge/Type-application-informational?style=flat-square) ![AppVersion: v1.1.0](https://img.shields.io/badge/AppVersion-v1.1.0-informational?style=flat-square) S3-compatible object store for small self-hosted geo-distributed deployments +**Homepage:** + +## Source Code + +* + ## Values | Key | Type | Default | Description | @@ -25,6 +31,7 @@ S3-compatible object store for small self-hosted geo-distributed deployments | garage.kubernetesSkipCrd | bool | `false` | Set to true if you want to use k8s discovery but install the CRDs manually outside of the helm chart, for example if you operate at namespace level without cluster ressources | | garage.replicationFactor | string | `"3"` | Default to 3 replicas, see the replication_factor section at https://garagehq.deuxfleurs.fr/documentation/reference-manual/configuration/#replication_factor | | garage.consistencyMode | string | `"consistent"` | Default to read-after-write consistency, see the consistency_mode section at https://garagehq.deuxfleurs.fr/documentation/reference-manual/configuration/#consistency_mode | +| garage.metadataAutoSnapshotInterval | string | `""` | If this value is set, Garage will automatically take a snapshot of the metadata DB file at a regular interval and save it in the metadata directory. https://garagehq.deuxfleurs.fr/documentation/reference-manual/configuration/#metadata_auto_snapshot_interval | | garage.rpcBindAddr | string | `"[::]:3901"` | | | garage.rpcSecret | string | `""` | If not given, a random secret will be generated and stored in a Secret object | | garage.s3.api.region | string | `"garage"` | | @@ -50,6 +57,7 @@ S3-compatible object store for small self-hosted geo-distributed deployments | initImage.pullPolicy | string | `"IfNotPresent"` | | | initImage.repository | string | `"busybox"` | | | initImage.tag | string | `"stable"` | | +| livenessProbe | object | `{}` | Specifies a livenessProbe | | monitoring.metrics.enabled | bool | `false` | If true, a service for monitoring is created with a prometheus.io/scrape annotation | | monitoring.metrics.serviceMonitor.enabled | bool | `false` | If true, a ServiceMonitor CRD is created for a prometheus operator https://github.com/coreos/prometheus-operator | | monitoring.metrics.serviceMonitor.interval | string | `"15s"` | | @@ -72,6 +80,7 @@ S3-compatible object store for small self-hosted geo-distributed deployments | podSecurityContext.runAsGroup | int | `1000` | | | podSecurityContext.runAsNonRoot | bool | `true` | | | podSecurityContext.runAsUser | int | `1000` | | +| readinessProbe | object | `{}` | Specifies a readinessProbe | | resources | object | `{}` | | | securityContext.capabilities | object | `{"drop":["ALL"]}` | The default security context is heavily restricted, feel free to tune it to your requirements | | securityContext.readOnlyRootFilesystem | bool | `true` | | diff --git a/script/helm/garage/templates/configmap.yaml b/script/helm/garage/templates/configmap.yaml index 38ee5c25..be162aa0 100644 --- a/script/helm/garage/templates/configmap.yaml +++ b/script/helm/garage/templates/configmap.yaml @@ -20,6 +20,10 @@ data: compression_level = {{ .Values.garage.compressionLevel }} + {{- if .Values.garage.metadataAutoSnapshotInterval }} + metadata_auto_snapshot_interval = {{ .Values.garage.metadataAutoSnapshotInterval | quote }} + {{- end }} + rpc_bind_addr = "{{ .Values.garage.rpcBindAddr }}" # rpc_secret will be populated by the init container from a k8s secret object rpc_secret = "__RPC_SECRET_REPLACE__" diff --git a/script/helm/garage/templates/workload.yaml b/script/helm/garage/templates/workload.yaml index cb9e76a2..d144cb41 100644 --- a/script/helm/garage/templates/workload.yaml +++ b/script/helm/garage/templates/workload.yaml @@ -78,15 +78,14 @@ spec: {{- with .Values.extraVolumeMounts }} {{- toYaml . | nindent 12 }} {{- end }} - # TODO - # livenessProbe: - # httpGet: - # path: / - # port: 3900 - # readinessProbe: - # httpGet: - # path: / - # port: 3900 + {{- with .Values.livenessProbe }} + livenessProbe: + {{- toYaml . | nindent 12 }} + {{- end }} + {{- with .Values.readinessProbe }} + readinessProbe: + {{- toYaml . | nindent 12 }} + {{- end }} resources: {{- toYaml .Values.resources | nindent 12 }} volumes: diff --git a/script/helm/garage/values.yaml b/script/helm/garage/values.yaml index f8ea30e5..beb5bc63 100644 --- a/script/helm/garage/values.yaml +++ b/script/helm/garage/values.yaml @@ -25,6 +25,10 @@ garage: # https://garagehq.deuxfleurs.fr/documentation/reference-manual/configuration/#compression_level compressionLevel: "1" + # -- If this value is set, Garage will automatically take a snapshot of the metadata DB file at a regular interval and save it in the metadata directory. + # https://garagehq.deuxfleurs.fr/documentation/reference-manual/configuration/#metadata_auto_snapshot_interval + metadataAutoSnapshotInterval: "" + rpcBindAddr: "[::]:3901" # -- If not given, a random secret will be generated and stored in a Secret object rpcSecret: "" @@ -195,6 +199,21 @@ resources: {} # cpu: 100m # memory: 512Mi +# -- Specifies a livenessProbe +livenessProbe: {} + #httpGet: + # path: /health + # port: 3903 + #initialDelaySeconds: 5 + #periodSeconds: 30 +# -- Specifies a readinessProbe +readinessProbe: {} + #httpGet: + # path: /health + # port: 3903 + #initialDelaySeconds: 5 + #periodSeconds: 30 + nodeSelector: {} tolerations: [] diff --git a/script/k8s/crd/garagenodes.deuxfleurs.fr.yaml b/script/k8s/crd/garagenodes.deuxfleurs.fr.yaml new file mode 100644 index 00000000..cd0fb166 --- /dev/null +++ b/script/k8s/crd/garagenodes.deuxfleurs.fr.yaml @@ -0,0 +1,43 @@ +apiVersion: apiextensions.k8s.io/v1 +kind: CustomResourceDefinition +metadata: + name: garagenodes.deuxfleurs.fr +spec: + conversion: + strategy: None + group: deuxfleurs.fr + names: + kind: GarageNode + listKind: GarageNodeList + plural: garagenodes + singular: garagenode + scope: Namespaced + versions: + - name: v1 + schema: + openAPIV3Schema: + description: Auto-generated derived type for Node via `CustomResource` + properties: + spec: + properties: + address: + format: ip + type: string + hostname: + type: string + port: + format: uint16 + minimum: 0 + type: integer + required: + - address + - hostname + - port + type: object + required: + - spec + title: GarageNode + type: object + served: true + storage: true + subresources: {} \ No newline at end of file diff --git a/script/k8s/crd/kustomization.yaml b/script/k8s/crd/kustomization.yaml new file mode 100644 index 00000000..9f20eccf --- /dev/null +++ b/script/k8s/crd/kustomization.yaml @@ -0,0 +1,5 @@ +apiVersion: kustomize.config.k8s.io/v1beta1 +kind: Kustomization + +resources: +- garagenodes.deuxfleurs.fr.yaml \ No newline at end of file diff --git a/src/api/admin/api.rs b/src/api/admin/api.rs index 1766ae28..faf7150d 100644 --- a/src/api/admin/api.rs +++ b/src/api/admin/api.rs @@ -1114,6 +1114,7 @@ pub enum RepairType { BlockRc, Rebalance, Scrub(ScrubCommand), + Aliases, } #[derive(Debug, Clone, Serialize, Deserialize, ToSchema)] diff --git a/src/api/admin/bucket.rs b/src/api/admin/bucket.rs index b0fd101b..d5c7f34f 100644 --- a/src/api/admin/bucket.rs +++ b/src/api/admin/bucket.rs @@ -159,7 +159,7 @@ impl RequestHandler for CreateBucketRequest { let helper = garage.locked_helper().await; if let Some(ga) = &self.global_alias { - if !is_valid_bucket_name(ga) { + if !is_valid_bucket_name(ga, garage.config.allow_punycode) { return Err(Error::bad_request(format!( "{}: {}", ga, INVALID_BUCKET_NAME_MESSAGE @@ -174,7 +174,7 @@ impl RequestHandler for CreateBucketRequest { } if let Some(la) = &self.local_alias { - if !is_valid_bucket_name(&la.alias) { + if !is_valid_bucket_name(&la.alias, garage.config.allow_punycode) { return Err(Error::bad_request(format!( "{}: {}", la.alias, INVALID_BUCKET_NAME_MESSAGE @@ -255,7 +255,7 @@ impl RequestHandler for DeleteBucketRequest { for ((key_id, alias), _, active) in state.local_aliases.items().iter() { if *active { helper - .unset_local_bucket_alias(bucket.id, key_id, alias) + .purge_local_bucket_alias(bucket.id, key_id, alias) .await?; } } diff --git a/src/api/admin/repair.rs b/src/api/admin/repair.rs index a9b8c36a..95bec980 100644 --- a/src/api/admin/repair.rs +++ b/src/api/admin/repair.rs @@ -89,6 +89,10 @@ impl RequestHandler for LocalLaunchRepairOperationRequest { garage.block_manager.clone(), )); } + RepairType::Aliases => { + info!("Repairing bucket aliases (foreground)"); + garage.locked_helper().await.repair_aliases().await?; + } } Ok(LocalLaunchRepairOperationResponse) } diff --git a/src/api/common/Cargo.toml b/src/api/common/Cargo.toml index 75838148..9c09e4bf 100644 --- a/src/api/common/Cargo.toml +++ b/src/api/common/Cargo.toml @@ -27,7 +27,6 @@ err-derive.workspace = true hex.workspace = true hmac.workspace = true md-5.workspace = true -idna.workspace = true tracing.workspace = true nom.workspace = true pin-project.workspace = true diff --git a/src/api/common/helpers.rs b/src/api/common/helpers.rs index c8586de4..6fc4aa13 100644 --- a/src/api/common/helpers.rs +++ b/src/api/common/helpers.rs @@ -8,7 +8,6 @@ use hyper::{ body::{Body, Bytes}, Request, Response, }; -use idna::domain_to_unicode; use serde::{Deserialize, Serialize}; use garage_model::bucket_table::BucketParams; @@ -97,7 +96,7 @@ pub fn authority_to_host(authority: &str) -> Result { authority ))), }; - authority.map(|h| domain_to_unicode(h).0) + authority.map(|h| h.to_ascii_lowercase()) } /// Extract the bucket name and the key name from an HTTP path and possibly a bucket provided in diff --git a/src/api/s3/bucket.rs b/src/api/s3/bucket.rs index 7b5d714f..1bdcf32d 100644 --- a/src/api/s3/bucket.rs +++ b/src/api/s3/bucket.rs @@ -167,7 +167,7 @@ pub async fn handle_create_bucket( } // Create the bucket! - if !is_valid_bucket_name(&bucket_name) { + if !is_valid_bucket_name(&bucket_name, garage.config.allow_punycode) { return Err(Error::bad_request(format!( "{}: {}", bucket_name, INVALID_BUCKET_NAME_MESSAGE @@ -236,11 +236,11 @@ pub async fn handle_delete_bucket(ctx: ReqCtx) -> Result, Erro // 1. delete bucket alias if is_local_alias { helper - .unset_local_bucket_alias(*bucket_id, &api_key.key_id, bucket_name) + .purge_local_bucket_alias(*bucket_id, &api_key.key_id, bucket_name) .await?; } else { helper - .unset_global_bucket_alias(*bucket_id, bucket_name) + .purge_global_bucket_alias(*bucket_id, bucket_name) .await?; } diff --git a/src/api/s3/copy.rs b/src/api/s3/copy.rs index 174e548d..b40f3161 100644 --- a/src/api/s3/copy.rs +++ b/src/api/s3/copy.rs @@ -29,6 +29,7 @@ use crate::error::*; use crate::get::{full_object_byte_stream, PreconditionHeaders}; use crate::multipart; use crate::put::{extract_metadata_headers, save_stream, ChecksumMode, SaveStreamResult}; +use crate::website::X_AMZ_WEBSITE_REDIRECT_LOCATION; use crate::xml::{self as s3_xml, xmlns_tag}; pub const X_AMZ_COPY_SOURCE_IF_MATCH: HeaderName = @@ -109,7 +110,18 @@ pub async fn handle_copy( Some(v) if v == hyper::header::HeaderValue::from_static("REPLACE") => { extract_metadata_headers(req.headers())? } - _ => source_object_meta_inner.into_owned().headers, + _ => { + // The x-amz-website-redirect-location header is not copied, instead + // it is replaced by the value from the request (or removed if no + // value was specified) + let is_redirect = + |(key, _): &(String, String)| key == X_AMZ_WEBSITE_REDIRECT_LOCATION.as_str(); + let mut headers: Vec<_> = source_object_meta_inner.headers.clone(); + headers.retain(|h| !is_redirect(h)); + let new_headers = extract_metadata_headers(req.headers())?; + headers.extend(new_headers.into_iter().filter(is_redirect)); + headers + } }, checksum: source_checksum, checksum_type: source_checksum_type, diff --git a/src/api/s3/lifecycle.rs b/src/api/s3/lifecycle.rs index c140494e..ccda6cfd 100644 --- a/src/api/s3/lifecycle.rs +++ b/src/api/s3/lifecycle.rs @@ -27,7 +27,7 @@ pub async fn handle_get_lifecycle(ctx: ReqCtx) -> Result, Erro .body(string_body(xml))?) } else { Ok(Response::builder() - .status(StatusCode::NO_CONTENT) + .status(StatusCode::NOT_FOUND) .body(empty_body())?) } } diff --git a/src/db/lmdb_adapter.rs b/src/db/lmdb_adapter.rs index 40f1c867..259aa566 100644 --- a/src/db/lmdb_adapter.rs +++ b/src/db/lmdb_adapter.rs @@ -109,7 +109,7 @@ impl IDb for LmdbDb { let mut path = to.clone(); path.push("data.mdb"); self.db - .copy_to_path(path, heed::CompactionOption::Disabled)?; + .copy_to_path(path, heed::CompactionOption::Enabled)?; Ok(()) } diff --git a/src/garage/cli/remote/node.rs b/src/garage/cli/remote/node.rs index d3017da7..2ca8843f 100644 --- a/src/garage/cli/remote/node.rs +++ b/src/garage/cli/remote/node.rs @@ -91,6 +91,7 @@ impl Cli { ScrubCmd::Pause => ScrubCommand::Pause, ScrubCmd::Resume => ScrubCommand::Resume, }), + RepairWhat::Aliases => RepairType::Aliases, }; let res = self diff --git a/src/garage/cli/structs.rs b/src/garage/cli/structs.rs index fadfcc66..e4c8f001 100644 --- a/src/garage/cli/structs.rs +++ b/src/garage/cli/structs.rs @@ -657,6 +657,9 @@ pub enum RepairWhat { /// Recalculate block reference counters #[structopt(name = "block-rc", version = garage_version())] BlockRc, + /// Fix inconsistency in bucket aliases (WARNING: EXPERIMENTAL) + #[structopt(name = "aliases", version = garage_version())] + Aliases, /// Verify integrity of all blocks on disc #[structopt(name = "scrub", version = garage_version())] Scrub { diff --git a/src/garage/tests/common/garage.rs b/src/garage/tests/common/garage.rs index 3d4efbc2..14a81069 100644 --- a/src/garage/tests/common/garage.rs +++ b/src/garage/tests/common/garage.rs @@ -65,6 +65,8 @@ rpc_bind_addr = "127.0.0.1:{rpc_port}" rpc_public_addr = "127.0.0.1:{rpc_port}" rpc_secret = "{secret}" +allow_punycode = true + [s3_api] s3_region = "{region}" api_bind_addr = "127.0.0.1:{s3_port}" diff --git a/src/garage/tests/s3/website.rs b/src/garage/tests/s3/website.rs index c125df3b..b4820864 100644 --- a/src/garage/tests/s3/website.rs +++ b/src/garage/tests/s3/website.rs @@ -984,3 +984,76 @@ async fn test_website_invalid_redirect() { .await .unwrap_err(); } + +#[tokio::test] +async fn test_website_puny() { + const BCKT_NAME: &str = "xn--pda.eu"; + let ctx = common::context(); + let bucket = ctx.create_bucket(BCKT_NAME); + + let data = ByteStream::from_static(BODY); + + ctx.client + .put_object() + .bucket(&bucket) + .key("index.html") + .body(data) + .send() + .await + .unwrap(); + + let client = Client::builder(TokioExecutor::new()).build_http(); + + let req = |suffix| { + Request::builder() + .method("GET") + .uri(format!("http://127.0.0.1:{}/", ctx.garage.web_port)) + .header("Host", format!("{}{}", BCKT_NAME, suffix)) + .body(Body::new(Bytes::new())) + .unwrap() + }; + + ctx.garage + .command() + .args(["bucket", "website", "--allow", BCKT_NAME]) + .quiet() + .expect_success_status("Could not allow website on bucket"); + + let mut resp = client.request(req("")).await.unwrap(); + assert_eq!(resp.status(), StatusCode::OK); + assert_eq!( + resp.into_body().collect().await.unwrap().to_bytes(), + BODY.as_ref() + ); + + resp = client.request(req(".web.garage")).await.unwrap(); + assert_eq!(resp.status(), StatusCode::OK); + assert_eq!( + resp.into_body().collect().await.unwrap().to_bytes(), + BODY.as_ref() + ); + + for bname in [ + BCKT_NAME.to_string(), + format!("{BCKT_NAME}.web.garage"), + format!("{BCKT_NAME}.s3.garage"), + ] { + let admin_req = || { + Request::builder() + .method("GET") + .uri(format!( + "http://127.0.0.1:{0}/check?domain={1}", + ctx.garage.admin_port, bname + )) + .body(Body::new(Bytes::new())) + .unwrap() + }; + + let admin_resp = client.request(admin_req()).await.unwrap(); + assert_eq!(admin_resp.status(), StatusCode::OK); + assert_eq!( + admin_resp.into_body().collect().await.unwrap().to_bytes(), + format!("Domain '{bname}' is managed by Garage").as_bytes() + ); + } +} diff --git a/src/model/bucket_alias_table.rs b/src/model/bucket_alias_table.rs index 8bbe4118..276d0d1c 100644 --- a/src/model/bucket_alias_table.rs +++ b/src/model/bucket_alias_table.rs @@ -22,14 +22,10 @@ mod v08 { pub use v08::*; impl BucketAlias { - pub fn new(name: String, ts: u64, bucket_id: Option) -> Option { - if !is_valid_bucket_name(&name) { - None - } else { - Some(BucketAlias { - name, - state: crdt::Lww::raw(ts, bucket_id), - }) + pub fn new(name: String, ts: u64, bucket_id: Option) -> Self { + BucketAlias { + name, + state: crdt::Lww::raw(ts, bucket_id), } } @@ -80,7 +76,7 @@ impl TableSchema for BucketAliasTable { /// In the case of Garage, bucket names must not be hex-encoded /// 32 byte string, which is excluded thanks to the /// maximum length of 63 bytes given in the spec. -pub fn is_valid_bucket_name(n: &str) -> bool { +pub fn is_valid_bucket_name(n: &str, puny: bool) -> bool { // Bucket names must be between 3 and 63 characters n.len() >= 3 && n.len() <= 63 // Bucket names must be composed of lowercase letters, numbers, @@ -92,7 +88,9 @@ pub fn is_valid_bucket_name(n: &str) -> bool { // Bucket names must not be formatted as an IP address && n.parse::().is_err() // Bucket names must not start with "xn--" - && !n.starts_with("xn--") + && (!n.starts_with("xn--") || puny) + // We are a bit stricter, to properly restrict punycode in all labels + && (!n.contains(".xn--") || puny) // Bucket names must not end with "-s3alias" && !n.ends_with("-s3alias") } diff --git a/src/model/helper/locked.rs b/src/model/helper/locked.rs index 482e91b0..98344b63 100644 --- a/src/model/helper/locked.rs +++ b/src/model/helper/locked.rs @@ -1,3 +1,7 @@ +use std::collections::{HashMap, HashSet}; + +use garage_db as db; + use garage_util::crdt::*; use garage_util::data::*; use garage_util::error::{Error as GarageError, OkOrMessage}; @@ -47,6 +51,10 @@ impl<'a> LockedHelper<'a> { KeyHelper(self.0) } + // ================================================ + // global bucket aliases + // ================================================ + /// Sets a new alias for a bucket in global namespace. /// This function fails if: /// - alias name is not valid according to S3 spec @@ -57,7 +65,7 @@ impl<'a> LockedHelper<'a> { bucket_id: Uuid, alias_name: &String, ) -> Result<(), Error> { - if !is_valid_bucket_name(alias_name) { + if !is_valid_bucket_name(alias_name, self.0.config.allow_punycode) { return Err(Error::InvalidBucketName(alias_name.to_string())); } @@ -88,8 +96,7 @@ impl<'a> LockedHelper<'a> { // writes are now done and all writes use timestamp alias_ts let alias = match alias { - None => BucketAlias::new(alias_name.clone(), alias_ts, Some(bucket_id)) - .ok_or_else(|| Error::InvalidBucketName(alias_name.clone()))?, + None => BucketAlias::new(alias_name.clone(), alias_ts, Some(bucket_id)), Some(mut a) => { a.state = Lww::raw(alias_ts, Some(bucket_id)); a @@ -180,13 +187,14 @@ impl<'a> LockedHelper<'a> { .ok_or_else(|| Error::NoSuchBucket(alias_name.to_string()))?; // Checks ok, remove alias - let alias_ts = match bucket.state.as_option() { - Some(bucket_state) => increment_logical_clock_2( - alias.state.timestamp(), - bucket_state.aliases.get_timestamp(alias_name), - ), - None => increment_logical_clock(alias.state.timestamp()), - }; + let alias_ts = increment_logical_clock_2( + alias.state.timestamp(), + bucket + .state + .as_option() + .map(|p| p.aliases.get_timestamp(alias_name)) + .unwrap_or(0), + ); // ---- timestamp-ensured causality barrier ---- // writes are now done and all writes use timestamp alias_ts @@ -204,6 +212,10 @@ impl<'a> LockedHelper<'a> { Ok(()) } + // ================================================ + // local bucket aliases + // ================================================ + /// Sets a new alias for a bucket in the local namespace of a key. /// This function fails if: /// - alias name is not valid according to S3 spec @@ -216,14 +228,12 @@ impl<'a> LockedHelper<'a> { key_id: &String, alias_name: &String, ) -> Result<(), Error> { - let key_helper = KeyHelper(self.0); - - if !is_valid_bucket_name(alias_name) { + if !is_valid_bucket_name(alias_name, self.0.config.allow_punycode) { return Err(Error::InvalidBucketName(alias_name.to_string())); } let mut bucket = self.bucket().get_existing_bucket(bucket_id).await?; - let mut key = key_helper.get_existing_key(key_id).await?; + let mut key = self.key().get_existing_key(key_id).await?; let key_param = key.state.as_option_mut().unwrap(); @@ -272,23 +282,13 @@ impl<'a> LockedHelper<'a> { key_id: &String, alias_name: &String, ) -> Result<(), Error> { - let key_helper = KeyHelper(self.0); - let mut bucket = self.bucket().get_existing_bucket(bucket_id).await?; - let mut key = key_helper.get_existing_key(key_id).await?; + let mut key = self.key().get_existing_key(key_id).await?; + let key_p = key.state.as_option().unwrap(); let bucket_p = bucket.state.as_option_mut().unwrap(); - if key - .state - .as_option() - .unwrap() - .local_aliases - .get(alias_name) - .cloned() - .flatten() - != Some(bucket_id) - { + if key_p.local_aliases.get(alias_name).cloned().flatten() != Some(bucket_id) { return Err(GarageError::Message(format!( "Bucket {:?} does not have alias {} in namespace of key {}", bucket_id, alias_name, key_id @@ -305,17 +305,17 @@ impl<'a> LockedHelper<'a> { .local_aliases .items() .iter() - .any(|((k, n), _, active)| *k == key.key_id && n == alias_name && *active); + .any(|((k, n), _, active)| (*k != key.key_id || n != alias_name) && *active); + if !has_other_global_aliases && !has_other_local_aliases { return Err(Error::BadRequest(format!("Bucket {} doesn't have other aliases, please delete it instead of just unaliasing.", alias_name))); } // Checks ok, remove alias - let key_param = key.state.as_option_mut().unwrap(); let bucket_p_local_alias_key = (key.key_id.clone(), alias_name.clone()); let alias_ts = increment_logical_clock_2( - key_param.local_aliases.get_timestamp(alias_name), + key_p.local_aliases.get_timestamp(alias_name), bucket_p .local_aliases .get_timestamp(&bucket_p_local_alias_key), @@ -324,7 +324,8 @@ impl<'a> LockedHelper<'a> { // ---- timestamp-ensured causality barrier ---- // writes are now done and all writes use timestamp alias_ts - key_param.local_aliases = LwwMap::raw_item(alias_name.clone(), alias_ts, None); + key.state.as_option_mut().unwrap().local_aliases = + LwwMap::raw_item(alias_name.clone(), alias_ts, None); self.0.key_table.insert(&key).await?; bucket_p.local_aliases = LwwMap::raw_item(bucket_p_local_alias_key, alias_ts, false); @@ -333,21 +334,68 @@ impl<'a> LockedHelper<'a> { Ok(()) } + /// Ensures a bucket does not have a certain local alias. + /// Contrarily to unset_local_bucket_alias, this does not + /// fail on any condition other than: + /// - bucket cannot be found (its fine if it is in deleted state) + /// - key cannot be found (its fine if alias in key points to nothing + /// or to another bucket) + pub async fn purge_local_bucket_alias( + &self, + bucket_id: Uuid, + key_id: &String, + alias_name: &String, + ) -> Result<(), Error> { + let mut bucket = self.bucket().get_internal_bucket(bucket_id).await?; + let mut key = self.key().get_internal_key(key_id).await?; + + let bucket_p_local_alias_key = (key.key_id.clone(), alias_name.clone()); + + let alias_ts = increment_logical_clock_2( + key.state + .as_option() + .map(|p| p.local_aliases.get_timestamp(alias_name)) + .unwrap_or(0), + bucket + .state + .as_option() + .map(|p| p.local_aliases.get_timestamp(&bucket_p_local_alias_key)) + .unwrap_or(0), + ); + + // ---- timestamp-ensured causality barrier ---- + // writes are now done and all writes use timestamp alias_ts + + if let Some(kp) = key.state.as_option_mut() { + kp.local_aliases = LwwMap::raw_item(alias_name.clone(), alias_ts, None); + self.0.key_table.insert(&key).await?; + } + + if let Some(bp) = bucket.state.as_option_mut() { + bp.local_aliases = LwwMap::raw_item(bucket_p_local_alias_key, alias_ts, false); + self.0.bucket_table.insert(&bucket).await?; + } + + Ok(()) + } + + // ================================================ + // permissions + // ================================================ + /// Sets permissions for a key on a bucket. /// This function fails if: /// - bucket or key cannot be found at all (its ok if they are in deleted state) - /// - bucket or key is in deleted state and we are trying to set permissions other than "deny - /// all" + /// - bucket or key is in deleted state and we are trying to set + /// permissions other than "deny all" pub async fn set_bucket_key_permissions( &self, bucket_id: Uuid, key_id: &String, mut perm: BucketKeyPerm, ) -> Result<(), Error> { - let key_helper = KeyHelper(self.0); - let mut bucket = self.bucket().get_internal_bucket(bucket_id).await?; - let mut key = key_helper.get_internal_key(key_id).await?; + let mut key = self.key().get_internal_key(key_id).await?; if let Some(bstate) = bucket.state.as_option() { if let Some(kp) = bstate.authorized_keys.get(key_id) { @@ -384,21 +432,20 @@ impl<'a> LockedHelper<'a> { Ok(()) } - // ---- + // ================================================ + // keys + // ================================================ /// Deletes an API access key pub async fn delete_key(&self, key: &mut Key) -> Result<(), Error> { let state = key.state.as_option_mut().unwrap(); // --- done checking, now commit --- - // (the step at unset_local_bucket_alias will fail if a bucket - // does not have another alias, the deletion will be - // interrupted in the middle if that happens) // 1. Delete local aliases for (alias, _, to) in state.local_aliases.items().iter() { if let Some(bucket_id) = to { - self.unset_local_bucket_alias(*bucket_id, &key.key_id, alias) + self.purge_local_bucket_alias(*bucket_id, &key.key_id, alias) .await?; } } @@ -415,4 +462,193 @@ impl<'a> LockedHelper<'a> { Ok(()) } + + // ================================================ + // repair procedure + // ================================================ + + pub async fn repair_aliases(&self) -> Result<(), GarageError> { + self.0.db.transaction(|tx| { + info!("--- begin repair_aliases transaction ----"); + + // 1. List all non-deleted buckets, so that we can fix bad aliases + let mut all_buckets: HashSet = HashSet::new(); + + for item in tx.range::<&[u8], _>(&self.0.bucket_table.data.store, ..)? { + let bucket = self + .0 + .bucket_table + .data + .decode_entry(&(item?.1)) + .map_err(db::TxError::Abort)?; + if !bucket.is_deleted() { + all_buckets.insert(bucket.id); + } + } + + info!("number of buckets: {}", all_buckets.len()); + + // 2. List all aliases declared in bucket_alias_table and key_table + // Take note of aliases that point to non-existing buckets + let mut global_aliases: HashMap = HashMap::new(); + + { + let mut delete_global = vec![]; + for item in tx.range::<&[u8], _>(&self.0.bucket_alias_table.data.store, ..)? { + let mut alias = self + .0 + .bucket_alias_table + .data + .decode_entry(&(item?.1)) + .map_err(db::TxError::Abort)?; + if let Some(id) = alias.state.get() { + if all_buckets.contains(id) { + // keep aliases + global_aliases.insert(alias.name().to_string(), *id); + } else { + // delete alias + warn!( + "global alias: remove {} -> {:?} (bucket is deleted)", + alias.name(), + id + ); + alias.state.update(None); + delete_global.push(alias); + } + } + } + + info!("number of global aliases: {}", global_aliases.len()); + + info!("global alias table: {} entries fixed", delete_global.len()); + for ga in delete_global { + debug!("Enqueue update to global alias table: {:?}", ga); + self.0.bucket_alias_table.queue_insert(tx, &ga)?; + } + } + + let mut local_aliases: HashMap<(String, String), Uuid> = HashMap::new(); + + { + let mut delete_local = vec![]; + + for item in tx.range::<&[u8], _>(&self.0.key_table.data.store, ..)? { + let mut key = self + .0 + .key_table + .data + .decode_entry(&(item?.1)) + .map_err(db::TxError::Abort)?; + let Some(p) = key.state.as_option_mut() else { + continue; + }; + let mut has_changes = false; + for (name, _, to) in p.local_aliases.items().to_vec() { + if let Some(id) = to { + if all_buckets.contains(&id) { + local_aliases.insert((key.key_id.clone(), name), id); + } else { + warn!( + "local alias: remove ({}, {}) -> {:?} (bucket is deleted)", + key.key_id, name, id + ); + p.local_aliases.update_in_place(name, None); + has_changes = true; + } + } + } + if has_changes { + delete_local.push(key); + } + } + + info!("number of local aliases: {}", local_aliases.len()); + + info!("key table: {} entries fixed", delete_local.len()); + for la in delete_local { + debug!("Enqueue update to key table: {:?}", la); + self.0.key_table.queue_insert(tx, &la)?; + } + } + + // 4. Reverse the alias maps to determine the aliases per-bucket + let mut bucket_global: HashMap> = HashMap::new(); + let mut bucket_local: HashMap> = HashMap::new(); + + for (name, bucket) in global_aliases { + bucket_global.entry(bucket).or_default().push(name); + } + for ((key, name), bucket) in local_aliases { + bucket_local.entry(bucket).or_default().push((key, name)); + } + + // 5. Fix the bucket table to ensure consistency + let mut bucket_updates = vec![]; + + for item in tx.range::<&[u8], _>(&self.0.bucket_table.data.store, ..)? { + let bucket = self + .0 + .bucket_table + .data + .decode_entry(&(item?.1)) + .map_err(db::TxError::Abort)?; + let mut bucket2 = bucket.clone(); + let Some(param) = bucket2.state.as_option_mut() else { + continue; + }; + + // fix global aliases + { + let ga = bucket_global.remove(&bucket.id).unwrap_or_default(); + for (name, _, active) in param.aliases.items().to_vec() { + if active && !ga.contains(&name) { + warn!("bucket {:?}: remove global alias {}", bucket.id, name); + param.aliases.update_in_place(name, false); + } + } + for name in ga { + if param.aliases.get(&name).copied() != Some(true) { + warn!("bucket {:?}: add global alias {}", bucket.id, name); + param.aliases.update_in_place(name, true); + } + } + } + + // fix local aliases + { + let la = bucket_local.remove(&bucket.id).unwrap_or_default(); + for (pair, _, active) in param.local_aliases.items().to_vec() { + if active && !la.contains(&pair) { + warn!("bucket {:?}: remove local alias {:?}", bucket.id, pair); + param.local_aliases.update_in_place(pair, false); + } + } + for pair in la { + if param.local_aliases.get(&pair).copied() != Some(true) { + warn!("bucket {:?}: add local alias {:?}", bucket.id, pair); + param.local_aliases.update_in_place(pair, true); + } + } + } + + if bucket2 != bucket { + bucket_updates.push(bucket2); + } + } + + info!("bucket table: {} entries fixed", bucket_updates.len()); + for b in bucket_updates { + debug!("Enqueue update to bucket table: {:?}", b); + self.0.bucket_table.queue_insert(tx, &b)?; + } + + info!("--- end repair_aliases transaction ----"); + + Ok(()) + })?; + + info!("repair_aliases is done"); + + Ok(()) + } } diff --git a/src/util/config.rs b/src/util/config.rs index 47247718..26367983 100644 --- a/src/util/config.rs +++ b/src/util/config.rs @@ -135,6 +135,10 @@ pub struct Config { /// Configuration for the admin API endpoint #[serde(default = "Default::default")] pub admin: AdminConfig, + + /// Allow punycode in bucket names + #[serde(default)] + pub allow_punycode: bool, } /// Value for data_dir: either a single directory or a list of dirs with attributes