mirror of
https://github.com/rustfs/rustfs.git
synced 2026-08-23 04:39:04 +00:00
Compare commits
3 Commits
| Author | SHA1 | Date | |
|---|---|---|---|
 houseme
|
37d79c9740 | ||
|
overtrue
|
641f4d580b | ||
|
overtrue
|
7747582d83 |
@@ -1,2 +1,2 @@
|
||||
sha256-darwin=9f767b37ed8b1c82da62ea441462d75487785c8086e56f08fb6f6cd89c6e2e52
|
||||
sha256-linux=fbdaf42b220958d4b1e8880e0f8b5a7992d38e21051bb60596dd4538424757d6
|
||||
sha256-darwin=52a05fdfae8bcf6f5828cc2b1e91b2a268139d3f7e1fc47d7b875b55fffb3995
|
||||
sha256-linux=a22d8af72e250595ac4445e8c880f3f9706202e09ed196e5b7baac632dead8d8
|
||||
|
||||
@@ -107,9 +107,10 @@ filter = 'package(e2e_test) & test(/^inline_fast_path_cluster_test::/)'
|
||||
test-group = 'e2e-inline-boundaries'
|
||||
|
||||
# Vault KMS tests share the fixed dev-server port 8200. serial_test's #[serial]
|
||||
# does not cross nextest process boundaries, so keep these tests in one group.
|
||||
# does not cross nextest process boundaries, so keep every Vault-backed test in
|
||||
# one group.
|
||||
[[profile.default.overrides]]
|
||||
filter = 'package(e2e_test) & test(/^kms::kms_vault_test::/)'
|
||||
filter = 'package(e2e_test) & (test(/^kms::kms_vault_test::/) | test(/^kms::configured_roundtrip_test::test_configured_vault_kms_admin_and_versioned_cleanup$/))'
|
||||
test-group = 'e2e-vault'
|
||||
|
||||
# ---------------------------------------------------------------------------
|
||||
@@ -443,5 +444,5 @@ filter = 'package(e2e_test) & test(/^inline_fast_path_cluster_test::/)'
|
||||
test-group = 'e2e-inline-boundaries'
|
||||
|
||||
[[profile.e2e-full.overrides]]
|
||||
filter = 'package(e2e_test) & test(/^kms::kms_vault_test::/)'
|
||||
filter = 'package(e2e_test) & (test(/^kms::kms_vault_test::/) | test(/^kms::configured_roundtrip_test::test_configured_vault_kms_admin_and_versioned_cleanup$/))'
|
||||
test-group = 'e2e-vault'
|
||||
|
||||
@@ -30,8 +30,7 @@ make build-docker BUILD_OS=ubuntu22.04
|
||||
- Crate membership: `Cargo.toml` `[workspace].members`
|
||||
- Architecture, layering, crate map: [ARCHITECTURE.md](ARCHITECTURE.md)
|
||||
- Migration guardrails & readiness contracts: [docs/architecture/](docs/architecture/README.md)
|
||||
- CI workflow steps: `.github/workflows/`; event, timeout, and required-status
|
||||
matrix: [docs/testing/ci-gates.md](docs/testing/ci-gates.md)
|
||||
- CI gates: `.github/workflows/ci.yml` (source of truth; never copy its steps into docs)
|
||||
- Test-layer taxonomy, per-layer entry commands, serial/nextest rules, flake
|
||||
policy: [docs/testing/README.md](docs/testing/README.md)
|
||||
- Tier/ILM transition debugging (xl.meta inspection, versionId tracing):
|
||||
|
||||
@@ -70,8 +70,6 @@ make pre-pr
|
||||
|
||||
> For the full test-layer taxonomy (unit / ecstore black-box / e2e / s3s-e2e / S3 compatibility / chaos / fuzz / bench), each layer's entry command, the naming conventions the migration gate depends on, and the serial/nextest rules, see [docs/testing/README.md](docs/testing/README.md).
|
||||
|
||||
> For the event, timeout, required-status, and local reproduction matrix, see [docs/testing/ci-gates.md](docs/testing/ci-gates.md).
|
||||
|
||||
### 🔒 Automated Pre-commit Hooks
|
||||
#### What `make pre-commit` and `make pre-pr` actually run
|
||||
|
||||
|
||||
@@ -15,14 +15,12 @@
|
||||
use crate::common::RustFSTestClusterEnvironment;
|
||||
use aws_sdk_s3::Client;
|
||||
use aws_sdk_s3::error::SdkError;
|
||||
use aws_sdk_s3::types::{CorsConfiguration, CorsRule};
|
||||
use bytes::Bytes;
|
||||
use std::sync::Arc;
|
||||
use tokio::sync::Barrier;
|
||||
use tracing::{info, warn};
|
||||
|
||||
const BUCKET: &str = "conditional-put-race-bucket";
|
||||
const BUCKET_METADATA_RELOAD_BUCKET: &str = "bucket-metadata-reload-barrier";
|
||||
|
||||
async fn cleanup_object(client: &Client, key: &str) {
|
||||
if let Err(e) = client.delete_object().bucket(BUCKET).key(key).send().await {
|
||||
@@ -30,16 +28,6 @@ async fn cleanup_object(client: &Client, key: &str) {
|
||||
}
|
||||
}
|
||||
|
||||
async fn assert_bucket_cors_missing(client: &Client) {
|
||||
let result = client.get_bucket_cors().bucket(BUCKET_METADATA_RELOAD_BUCKET).send().await;
|
||||
match result {
|
||||
Err(SdkError::ServiceError(error)) => {
|
||||
assert_eq!(error.err().meta().code(), Some("NoSuchCORSConfiguration"));
|
||||
}
|
||||
result => panic!("expected the peer to report a missing CORS configuration: {result:?}"),
|
||||
}
|
||||
}
|
||||
|
||||
async fn conditional_put(
|
||||
client: &Client,
|
||||
key: &str,
|
||||
@@ -248,48 +236,3 @@ async fn test_conditional_put_basic_cluster() -> Result<(), Box<dyn std::error::
|
||||
cleanup_object(&client, test_key).await;
|
||||
Ok(())
|
||||
}
|
||||
|
||||
#[tokio::test]
|
||||
async fn test_bucket_cors_write_is_visible_on_peer_before_response() -> Result<(), Box<dyn std::error::Error + Send + Sync>> {
|
||||
crate::common::init_logging();
|
||||
|
||||
let mut cluster = RustFSTestClusterEnvironment::new(2).await?;
|
||||
cluster.start().await?;
|
||||
cluster.create_test_bucket(BUCKET_METADATA_RELOAD_BUCKET).await?;
|
||||
|
||||
let writer = cluster.create_s3_client(0)?;
|
||||
let reader = cluster.create_s3_client(1)?;
|
||||
assert_bucket_cors_missing(&reader).await;
|
||||
|
||||
let rule = CorsRule::builder()
|
||||
.allowed_methods("GET")
|
||||
.allowed_origins("https://example.com")
|
||||
.build()?;
|
||||
let configuration = CorsConfiguration::builder().cors_rules(rule).build()?;
|
||||
|
||||
writer
|
||||
.put_bucket_cors()
|
||||
.bucket(BUCKET_METADATA_RELOAD_BUCKET)
|
||||
.cors_configuration(configuration)
|
||||
.send()
|
||||
.await?;
|
||||
|
||||
let response = reader.get_bucket_cors().bucket(BUCKET_METADATA_RELOAD_BUCKET).send().await?;
|
||||
let rules = response.cors_rules();
|
||||
assert_eq!(
|
||||
rules.len(),
|
||||
1,
|
||||
"peer should observe the committed CORS rule before the write response returns"
|
||||
);
|
||||
assert_eq!(rules[0].allowed_methods(), ["GET"]);
|
||||
assert_eq!(rules[0].allowed_origins(), ["https://example.com"]);
|
||||
|
||||
writer
|
||||
.delete_bucket_cors()
|
||||
.bucket(BUCKET_METADATA_RELOAD_BUCKET)
|
||||
.send()
|
||||
.await?;
|
||||
assert_bucket_cors_missing(&reader).await;
|
||||
writer.delete_bucket().bucket(BUCKET_METADATA_RELOAD_BUCKET).send().await?;
|
||||
Ok(())
|
||||
}
|
||||
|
||||
@@ -432,7 +432,6 @@ async fn test_configured_local_kms_admin_and_versioned_cleanup() -> TestResult {
|
||||
}
|
||||
|
||||
#[tokio::test]
|
||||
#[ignore = "requires a Vault binary"]
|
||||
async fn test_configured_vault_kms_admin_and_versioned_cleanup() -> TestResult {
|
||||
let mut env = VaultTestEnvironment::new().await?;
|
||||
env.start_vault().await?;
|
||||
|
||||
@@ -85,7 +85,6 @@ const PEER_REST_RECOVERY_MAX_ATTEMPTS: u32 = 60;
|
||||
const PEER_REST_RECOVERY_MAX_BACKOFF: Duration = Duration::from_secs(30);
|
||||
const SCANNER_ACTIVITY_MAX_MESSAGE_SIZE: usize = 1024;
|
||||
const REPLICATION_STATS_MAX_MESSAGE_SIZE: usize = 8 * 1024 * 1024;
|
||||
const BUCKET_METADATA_RELOAD_TIMEOUT: Duration = Duration::from_secs(5);
|
||||
|
||||
/// Error for a peer that reported `success = false` without an `error_info` payload.
|
||||
///
|
||||
@@ -1329,38 +1328,27 @@ impl PeerRestClient {
|
||||
}
|
||||
|
||||
pub async fn load_bucket_metadata(&self, bucket: &str, scanner_maintenance_change: bool) -> Result<()> {
|
||||
let result = tokio::time::timeout(BUCKET_METADATA_RELOAD_TIMEOUT, async {
|
||||
let result = self.load_bucket_metadata_once(bucket, scanner_maintenance_change).await;
|
||||
if let Err(err) = &result
|
||||
&& Self::is_network_like_error(err)
|
||||
{
|
||||
self.prepare_retry().await;
|
||||
return self.load_bucket_metadata_once(bucket, scanner_maintenance_change).await;
|
||||
self.finalize_result(
|
||||
async {
|
||||
let mut client = self.get_client().await?;
|
||||
let mut request = Request::new(LoadBucketMetadataRequest {
|
||||
bucket: bucket.to_string(),
|
||||
scanner_maintenance_change,
|
||||
});
|
||||
set_tonic_mutation_body_digest(&mut request)?;
|
||||
|
||||
let response = client.load_bucket_metadata(request).await?.into_inner();
|
||||
if !response.success {
|
||||
if let Some(msg) = response.error_info {
|
||||
return Err(Error::other(msg));
|
||||
}
|
||||
return Err(peer_failure_without_details("load_bucket_metadata", Some(bucket)));
|
||||
}
|
||||
Ok(())
|
||||
}
|
||||
result
|
||||
})
|
||||
.await,
|
||||
)
|
||||
.await
|
||||
.unwrap_or_else(|_| Err(Error::other(format!("load_bucket_metadata({bucket}) timed out"))));
|
||||
self.finalize_result(result).await
|
||||
}
|
||||
|
||||
async fn load_bucket_metadata_once(&self, bucket: &str, scanner_maintenance_change: bool) -> Result<()> {
|
||||
let mut client = self.get_client().await?;
|
||||
let mut request = Request::new(LoadBucketMetadataRequest {
|
||||
bucket: bucket.to_string(),
|
||||
scanner_maintenance_change,
|
||||
});
|
||||
set_tonic_mutation_body_digest(&mut request)?;
|
||||
request.set_timeout(BUCKET_METADATA_RELOAD_TIMEOUT);
|
||||
|
||||
let response = client.load_bucket_metadata(request).await?.into_inner();
|
||||
if !response.success {
|
||||
if let Some(msg) = response.error_info {
|
||||
return Err(Error::other(msg));
|
||||
}
|
||||
return Err(peer_failure_without_details("load_bucket_metadata", Some(bucket)));
|
||||
}
|
||||
Ok(())
|
||||
}
|
||||
|
||||
pub async fn delete_bucket_metadata(&self, bucket: &str) -> Result<()> {
|
||||
|
||||
@@ -784,24 +784,6 @@ pub(crate) fn create_deferred_bitrot_reader_with_stripe_handle(
|
||||
///
|
||||
/// # Returns
|
||||
/// A Result containing the BitrotWriterWrapper or an error
|
||||
/// Size hint handed to `DiskAPI::create_file` for a bitrot-wrapped shard.
|
||||
///
|
||||
/// A known length is grown by one checksum per shard so the on-disk file size
|
||||
/// matches what the bitrot writer emits. A negative length is the
|
||||
/// unknown-size sentinel (`HashReader::SIZE_PRESERVE_LAYER`, used by SSE and
|
||||
/// compression) and must be preserved: `RemoteDisk::create_file` forwards it
|
||||
/// in the `put_file_stream` query, and the receiver only treats `size > 0` as
|
||||
/// a fixed body length when locating the authenticated trailer. Clamping it
|
||||
/// to `0` would claim an empty body and misframe the stream. `0` stays `0`
|
||||
/// because a genuinely empty object still means an empty body.
|
||||
fn bitrot_create_file_size(length: i64, shard_size: usize, checksum_algo: &HashAlgorithm) -> i64 {
|
||||
if length <= 0 {
|
||||
return length;
|
||||
}
|
||||
let length = length as usize;
|
||||
(length.div_ceil(shard_size) * checksum_algo.size() + length) as i64
|
||||
}
|
||||
|
||||
pub async fn create_bitrot_writer(
|
||||
is_inline_buffer: bool,
|
||||
disk: Option<&DiskStore>,
|
||||
@@ -814,7 +796,12 @@ pub async fn create_bitrot_writer(
|
||||
let writer = if is_inline_buffer {
|
||||
CustomWriter::new_inline_buffer()
|
||||
} else if let Some(disk) = disk {
|
||||
let length = bitrot_create_file_size(length, shard_size, &checksum_algo);
|
||||
let length = if length > 0 {
|
||||
let length = length as usize;
|
||||
(length.div_ceil(shard_size) * checksum_algo.size() + length) as i64
|
||||
} else {
|
||||
0
|
||||
};
|
||||
|
||||
let file = disk.create_file("", volume, path, length).await?;
|
||||
#[cfg(feature = "hotpath")]
|
||||
@@ -833,25 +820,6 @@ mod tests {
|
||||
use rustfs_rio::ChunkReader;
|
||||
use std::collections::VecDeque;
|
||||
|
||||
#[test]
|
||||
fn bitrot_create_file_size_grows_known_length_by_checksums() {
|
||||
// 10 bytes over 4-byte shards = 3 shards, each followed by a 32-byte hash.
|
||||
assert_eq!(bitrot_create_file_size(10, 4, &HashAlgorithm::HighwayHash256), 10 + 3 * 32);
|
||||
assert_eq!(bitrot_create_file_size(10, 4, &HashAlgorithm::None), 10);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn bitrot_create_file_size_keeps_empty_and_unknown_distinct() {
|
||||
assert_eq!(bitrot_create_file_size(0, 4, &HashAlgorithm::HighwayHash256), 0);
|
||||
// SSE/compression streams advertise SIZE_PRESERVE_LAYER (-1); the remote
|
||||
// put_file_stream receiver relies on a non-positive size to parse the auth
|
||||
// trailer from the stream tail, so the sentinel must survive untouched.
|
||||
assert_eq!(
|
||||
bitrot_create_file_size(rustfs_rio::HashReader::SIZE_PRESERVE_LAYER, 4, &HashAlgorithm::HighwayHash256),
|
||||
rustfs_rio::HashReader::SIZE_PRESERVE_LAYER
|
||||
);
|
||||
}
|
||||
|
||||
struct TestChunkReader {
|
||||
chunks: VecDeque<Bytes>,
|
||||
}
|
||||
|
||||
@@ -1,149 +0,0 @@
|
||||
# CI gate matrix
|
||||
|
||||
This file is the source of truth for which validation runs on each event, its
|
||||
configured wall-clock budget, and whether it can block a merge. Test taxonomy,
|
||||
naming, and nextest serialization rules remain in [README.md](README.md); e2e
|
||||
membership and counts remain in
|
||||
[e2e-suite-inventory.md](e2e-suite-inventory.md).
|
||||
|
||||
The distinction between **required** and **report-only** is load-bearing:
|
||||
a failing job blocks a merge only when its exact check name is present in the
|
||||
live `main` ruleset. A workflow name, a `merge_group` trigger, or a red PR check
|
||||
does not make a job required by itself.
|
||||
|
||||
## Required merge checks
|
||||
|
||||
The live `main` ruleset (`6436880`) currently requires exactly these contexts:
|
||||
|
||||
| Required context | Producer | Validation |
|
||||
|---|---|---|
|
||||
| `CLA Check` | `.github/workflows/cla.yml` | Contributor agreement |
|
||||
| `Quick Checks` | `.github/workflows/ci.yml` | Formatting and repository guard scripts |
|
||||
| `Test and Lint` | `.github/workflows/ci.yml` | Clippy, workspace nextest excluding `e2e_test`, doctests, and migration proofs |
|
||||
|
||||
For pull requests limited to the paths excluded by the main CI workflow,
|
||||
`.github/workflows/ci-docs-only.yml` reports `Quick Checks` and
|
||||
`Test and Lint` under the same names. It runs the real quick checks and the
|
||||
planning-document guard; it does not claim that Rust compilation or runtime
|
||||
tests ran. Despite the workflow name, these paths also include selected deploy,
|
||||
workflow, and lock files.
|
||||
|
||||
Verify the live rule rather than trusting this snapshot before changing merge
|
||||
policy:
|
||||
|
||||
```bash
|
||||
gh api repos/rustfs/rustfs/rulesets/6436880 \
|
||||
--jq '.rules[] | select(.type == "required_status_checks") | .parameters'
|
||||
```
|
||||
|
||||
The ruleset currently has `strict_required_status_checks_policy=false`.
|
||||
`Continuous Integration` accepts `merge_group` events and runs `e2e-full` for
|
||||
them, but `End-to-End Tests (full merge gate)` is not currently a required
|
||||
context. Therefore the repository is prepared to test a merge-queue SHA, but
|
||||
the workflow alone does not prove that every merge passed that lane.
|
||||
|
||||
## Pull request and merge matrix
|
||||
|
||||
Budgets below are job `timeout-minutes`, not typical runtimes. “Report-only”
|
||||
means the result is visible and actionable but is not in the live required
|
||||
context list.
|
||||
|
||||
| Event | Validation | Budget | Merge status | Reproduction |
|
||||
|---|---|---:|---|---|
|
||||
| PR, non-doc change | `Quick Checks` | 10 min | Required | `make pre-commit` (broader local umbrella) |
|
||||
| PR, non-doc change | `Test and Lint` | 90 min | Required | `cargo nextest run --profile ci --all --exclude e2e_test` |
|
||||
| PR, non-doc change | `Typos` | 10 min | Report-only | `typos` |
|
||||
| PR, non-doc change | `ILM Integration (serial)` | 90 min | Report-only | Use the exact command in `.github/workflows/ci.yml` |
|
||||
| PR, non-doc change | rio-v2 / swift / sftp test-and-lint variants | 90 min each | Report-only | `cargo nextest run` with the workflow's feature set |
|
||||
| PR, non-doc change | `Build RustFS Debug Binary` | 30 min | Report-only; prerequisite for black-box lanes | `cargo build -p rustfs --bins` |
|
||||
| PR, non-doc change | `io_uring Integration (real)` | 30 min | Report-only | `cargo test -p rustfs-ecstore --lib uring_ -- --test-threads=1 --nocapture` |
|
||||
| PR, non-doc change | `End-to-End Tests` (`e2e-smoke` plus `s3s-e2e`) | 30 min | Report-only | `cargo nextest run --profile e2e-smoke -p e2e_test`; then `./scripts/e2e-run.sh ./target/debug/rustfs <data-dir>` |
|
||||
| PR, non-doc change | `S3 Implemented Tests` | 60 min | Report-only | Build `rustfs`, then run `scripts/s3-tests/run.sh` with `DEPLOY_MODE=binary`, `TEST_MODE=single`, and `MAXFAIL=0` |
|
||||
| PR, non-doc change | `S3 Lifecycle Behavior Tests` | 30 min | Report-only | Use the accelerated scanner environment in `.github/workflows/ci.yml` with `scripts/s3-tests/run.sh` |
|
||||
| PR touching dependency or workflow inputs | Cargo Deny / Workflow Pin Report / Dependency Review | 20 / 5 / 30 min | Report-only | `cargo deny check`; `scripts/security/check_workflow_pins.sh` |
|
||||
| PR touching architecture rules or architecture docs | `Architecture Migration Rules` | 10 min | Report-only | `scripts/check_architecture_migration_rules.sh` |
|
||||
| PR touching Nix or workspace manifests | `Nix Build & Check` | 60 min | Report-only | `nix flake check` |
|
||||
| PR limited to main-CI-excluded paths | companion `Quick Checks` and `Test and Lint` | 10 min each | Required | `git diff --check`; `make doc-paths-check` when documentation paths changed |
|
||||
| `merge_group` | Standard CI plus `e2e-full` | 55 min for `e2e-full` | Standard required contexts only; `e2e-full` report-only | `cargo nextest run --profile e2e-full -p e2e_test` |
|
||||
| Push to `main` | Standard CI plus `e2e-full` | 55 min for `e2e-full` | Post-merge detection | Same as `merge_group` |
|
||||
| PR touching fuzz inputs or harness paths | Build plus five 60-second fuzz smoke targets | 60 min build; 30 min per target | Report-only | `MAX_TOTAL_TIME=60 ./scripts/fuzz/run.sh` |
|
||||
| PR touching selected ecstore disk/format paths | `Rename Safety` on Windows | 60 min | Report-only | Run the four `cargo test -p rustfs-ecstore --lib <filter>` commands in `windows-filesystem.yml` on Windows |
|
||||
|
||||
The authoritative e2e filters live in `.config/nextest.toml`; extend a profile
|
||||
instead of adding a second ad-hoc selector. Before a profile runs,
|
||||
`scripts/check_test_wiring.py` compares its exact membership to the committed
|
||||
digest so a silent test drop fails closed.
|
||||
|
||||
## Scheduled and manual validation
|
||||
|
||||
Scheduled lanes are independent fault domains. They do not block a pull
|
||||
request, but their workflow-local gate can fail the run and scheduled failures
|
||||
are routed to the shared failure-issue action. The scheduled-validation
|
||||
watchdog and freshness workflow separately detect incomplete runs and missing
|
||||
schedules.
|
||||
|
||||
| Cadence (UTC unless noted) | Workflow / validation | Budget | Verdict and artifacts | Reproduction |
|
||||
|---|---|---:|---|---|
|
||||
| Daily 02:17 | Fuzz: five nightly corpus targets | 60 min build; 60 min per target | Gate; corpus/crash artifacts, scheduled failure alert | `MAX_TOTAL_TIME=<seconds> ./scripts/fuzz/run.sh` |
|
||||
| Daily 03:17 | MinIO interop (EC + SSE read parity) | 40 min | Gate; scheduled failure alert | Dispatch `minio-interop.yml` or follow its pinned Docker fixture steps |
|
||||
| Daily 04:29 | Replication / cluster-fault / protocol e2e | 45 / 90 / 90 min | Three independent gates; JUnit, membership, and server logs | `cargo nextest run --profile e2e-repl-nightly -p e2e_test`; `--profile e2e-nightly`; `-j 1 --profile e2e-protocols` |
|
||||
| Daily 06:31 | Warp performance A/B | 180 min | Regression budget gate; A/B summaries and server logs | `bash scripts/run_hotpath_warp_abba.sh --help` |
|
||||
| Daily 00:07 Asia/Shanghai (16:07 UTC previous day) | Nightly GNU build and Vault lanes | 150 / 90 / 60 min | Build, live Vault, and HA failover gates | Use the commands and pinned Vault images in `nightly-gnu.yml` |
|
||||
| Daily 03:23 | Security Audit | 20 / 5 min, plus 30 min on PR dependency review | Cargo Deny and workflow-pin gates; scheduled failure alert | `cargo deny check`; `scripts/security/check_workflow_pins.sh` |
|
||||
| Daily 23:47 | Scheduled Validation Freshness | 10 min | Fails when a critical schedule was never created or is stale | Dispatch `scheduled-validation-freshness.yml` |
|
||||
| Sunday 00:11 | Full `Continuous Integration` matrix | Per-job budgets above | Weekly variant coverage, including dormant rio-v2 binary/e2e lanes | Dispatch `ci.yml` |
|
||||
| Sunday 01:13 | Seven-platform build matrix | 150 min per platform | Build/package integrity; scheduled failure alert | Dispatch `build.yml` with an exact platform set |
|
||||
| Sunday 02:19 | Ceph s3-tests full sweep: single and real four-node, four shards each | 180 min per shard | Compatibility gate; report, JUnit, exact node IDs, and server logs | `scripts/s3-tests/run.sh` against an existing single or distributed target |
|
||||
| Sunday 06:41 | Mint | 120 min | **Report-only by design**; per-suite PASS/FAIL/NA and raw `log.json` | Reproduce the pinned Docker sequence in `mint.yml` or dispatch it |
|
||||
| Sunday 07:43 | Workspace line coverage | 120 min | Report-only trend; lcov and JSON retained 90 days | `make coverage` |
|
||||
| Monthly, day 1 06:37 | Runner Hygiene | 15 min | Validates runner ephemerality; scheduled failure alert | Dispatch `runner-hygiene.yml` |
|
||||
|
||||
Manual `workflow_dispatch` exists for the scheduled workflows above. Manual
|
||||
runs are debugging evidence and intentionally do not open scheduled-failure
|
||||
issues. A manual performance run may explicitly allow a known regression; that
|
||||
override must not be treated as an ordinary passing baseline.
|
||||
|
||||
## Release validation
|
||||
|
||||
Release validation is post-merge and tag-driven; it does not substitute for a
|
||||
pull-request gate.
|
||||
|
||||
| Event | Validation | Budget | Result |
|
||||
|---|---|---:|---|
|
||||
| Push to `main` or weekly schedule | `Build and Release` platform matrix | 150 min per platform | Build artifacts for all selected targets; no release publication on a main push |
|
||||
| Valid release or preview tag | `Build and Release` plus asset checks | 150 min per platform | Draft release, checksummed assets, and publish step |
|
||||
| Successful non-preview release-tag build | Docker image build and image scan | 60 min build; 30 min scan | Multi-architecture images plus vulnerability report |
|
||||
| Successful release-tag build | DEB/RPM packaging | 30 min per architecture | Packages and checksum files uploaded to the release |
|
||||
| Successful non-preview release-tag build | Helm template test and package | 30 min build; 30 min publish | Versioned chart and repository index |
|
||||
|
||||
Use an exact preview tag for end-to-end release rehearsal. Manual dispatches
|
||||
are backfill/debug paths and do not prove the automatic `workflow_run` chain.
|
||||
|
||||
## Evidence requirements
|
||||
|
||||
A green check is useful only when it proves the intended behavior ran:
|
||||
|
||||
- Record the exact commit SHA and run URL.
|
||||
- Separate product failure from runner prerequisites, service readiness, and
|
||||
cancellation. Repair the precondition, then rerun the exact workload.
|
||||
- Preserve membership manifests, JUnit, raw compatibility logs, seeds, and
|
||||
server logs where the workflow provides them.
|
||||
- For a bug fix or a new fault checker, provide sensitivity evidence: the old
|
||||
behavior or an intentional mutation must fail the new oracle, and the fixed
|
||||
behavior must pass it.
|
||||
- Never promote a report-only lane to required from one green run. Require at
|
||||
least 14 days and 30 representative pull requests with at least 99% complete
|
||||
execution, then update the ruleset and this table together.
|
||||
|
||||
## Change checklist
|
||||
|
||||
Update this file in the same pull request when any of these change:
|
||||
|
||||
- workflow triggers, job names, timeouts, or nextest profile ownership;
|
||||
- required status contexts or strict/merge-queue policy;
|
||||
- scheduled cadence, alert routing, artifact contract, or local reproduction;
|
||||
- report-only versus gating semantics.
|
||||
|
||||
Do not copy per-module test counts here. Update
|
||||
[e2e-suite-inventory.md](e2e-suite-inventory.md) and its enforced membership
|
||||
digest instead.
|
||||
@@ -58,7 +58,7 @@
|
||||
| heal_erasure_disk_rebuild_test | 4 | 🌙 |
|
||||
| inline_fast_path_cluster_test | 16 | |
|
||||
| internode_rpc_signature_e2e_test | 5 | |
|
||||
| kms | 46 | |
|
||||
| kms | 47 | |
|
||||
| leading_slash_key_test | 2 | ✅ |
|
||||
| lifecycle_regression_test | 4 | |
|
||||
| list_buckets_auth_test | 1 | ✅ |
|
||||
@@ -99,4 +99,4 @@
|
||||
| tls_hot_reload_test | 1 | ✅ |
|
||||
| version_id_regression_test | 10 | ✅ |
|
||||
|
||||
**Total listed: 575 tests across 82 modules · PR smoke: 163 tests / 36 modules · merge/main full: 453 tests / 73 modules · nightly replication: 55 tests · nightly cluster faults: 28 tests / 7 modules · nightly protocols: 16 tests** · updated 2026-08-23.
|
||||
**Total listed: 576 tests across 82 modules · PR smoke: 163 tests / 36 modules · merge/main full: 454 tests / 73 modules · nightly replication: 55 tests · nightly cluster faults: 28 tests / 7 modules · nightly protocols: 16 tests** · updated 2026-08-23.
|
||||
|
||||
@@ -513,15 +513,13 @@ fn sr_bucket_meta_item(bucket: String, item_type: &str) -> SRBucketMeta {
|
||||
}
|
||||
}
|
||||
|
||||
async fn notify_bucket_metadata_reload(
|
||||
fn notify_bucket_metadata_reload(
|
||||
bucket: String,
|
||||
operation: &'static str,
|
||||
request_context: Option<request_context::RequestContext>,
|
||||
scanner_maintenance_change: bool,
|
||||
) {
|
||||
record_local_scanner_maintenance_reload(&bucket, scanner_maintenance_change);
|
||||
// Keep reload detached across request cancellation, but wait before a healthy peer can serve the previous config.
|
||||
let (completed_tx, completed_rx) = tokio::sync::oneshot::channel();
|
||||
spawn_background_with_context(request_context, async move {
|
||||
if let Some(notification_sys) = current_notification_system() {
|
||||
let result = if scanner_maintenance_change {
|
||||
@@ -533,9 +531,7 @@ async fn notify_bucket_metadata_reload(
|
||||
warn!(bucket = %bucket, error = %err, "failed to notify peers after {operation}");
|
||||
}
|
||||
}
|
||||
let _ = completed_tx.send(());
|
||||
});
|
||||
let _ = completed_rx.await;
|
||||
}
|
||||
|
||||
fn record_local_scanner_maintenance_reload(bucket: &str, scanner_maintenance_change: bool) {
|
||||
@@ -1480,7 +1476,7 @@ impl DefaultBucketUsecase {
|
||||
.await
|
||||
.map_err(ApiError::from)?;
|
||||
|
||||
notify_bucket_metadata_reload(bucket.clone(), "delete bucket encryption", request_context, false).await;
|
||||
notify_bucket_metadata_reload(bucket.clone(), "delete bucket encryption", request_context, false);
|
||||
|
||||
let item = sr_bucket_meta_item(bucket.clone(), "sse-config");
|
||||
if let Err(err) = site_replication_bucket_meta_hook(item).await {
|
||||
@@ -1512,7 +1508,7 @@ impl DefaultBucketUsecase {
|
||||
.await
|
||||
.map_err(ApiError::from)?;
|
||||
|
||||
notify_bucket_metadata_reload(bucket.clone(), "delete bucket cors", request_context, false).await;
|
||||
notify_bucket_metadata_reload(bucket.clone(), "delete bucket cors", request_context, false);
|
||||
|
||||
let item = sr_bucket_meta_item(bucket.clone(), "cors-config");
|
||||
if let Err(err) = site_replication_bucket_meta_hook(item).await {
|
||||
@@ -1544,7 +1540,7 @@ impl DefaultBucketUsecase {
|
||||
.await
|
||||
.map_err(ApiError::from)?;
|
||||
|
||||
notify_bucket_metadata_reload(bucket.clone(), "delete bucket lifecycle", request_context, true).await;
|
||||
notify_bucket_metadata_reload(bucket.clone(), "delete bucket lifecycle", request_context, true);
|
||||
|
||||
let item = sr_bucket_meta_item(bucket.clone(), "lc-config");
|
||||
if let Err(err) = site_replication_bucket_meta_hook(item).await {
|
||||
@@ -1576,7 +1572,7 @@ impl DefaultBucketUsecase {
|
||||
.await
|
||||
.map_err(ApiError::from)?;
|
||||
|
||||
notify_bucket_metadata_reload(bucket.clone(), "delete bucket policy", request_context, false).await;
|
||||
notify_bucket_metadata_reload(bucket.clone(), "delete bucket policy", request_context, false);
|
||||
|
||||
let item = sr_bucket_meta_item(bucket.clone(), "policy");
|
||||
if let Err(err) = site_replication_bucket_meta_hook(item).await {
|
||||
@@ -1634,7 +1630,7 @@ impl DefaultBucketUsecase {
|
||||
}
|
||||
drop(targets_guard);
|
||||
|
||||
notify_bucket_metadata_reload(bucket.clone(), "delete bucket replication", request_context, true).await;
|
||||
notify_bucket_metadata_reload(bucket.clone(), "delete bucket replication", request_context, true);
|
||||
|
||||
let item = sr_bucket_meta_item(bucket.clone(), "replication-config");
|
||||
if let Err(err) = site_replication_bucket_meta_hook(item).await {
|
||||
@@ -1659,7 +1655,7 @@ impl DefaultBucketUsecase {
|
||||
.await
|
||||
.map_err(ApiError::from)?;
|
||||
|
||||
notify_bucket_metadata_reload(bucket.clone(), "delete bucket tagging", request_context, false).await;
|
||||
notify_bucket_metadata_reload(bucket.clone(), "delete bucket tagging", request_context, false);
|
||||
|
||||
let item = sr_bucket_meta_item(bucket.clone(), "tags");
|
||||
if let Err(err) = site_replication_bucket_meta_hook(item).await {
|
||||
@@ -1692,7 +1688,7 @@ impl DefaultBucketUsecase {
|
||||
.await
|
||||
.map_err(ApiError::from)?;
|
||||
|
||||
notify_bucket_metadata_reload(bucket.clone(), "delete public access block", request_context, false).await;
|
||||
notify_bucket_metadata_reload(bucket.clone(), "delete public access block", request_context, false);
|
||||
|
||||
Ok(S3Response::with_status(DeletePublicAccessBlockOutput::default(), StatusCode::NO_CONTENT))
|
||||
}
|
||||
@@ -2147,7 +2143,7 @@ impl DefaultBucketUsecase {
|
||||
.await
|
||||
.map_err(ApiError::from)?;
|
||||
|
||||
notify_bucket_metadata_reload(bucket.clone(), "put bucket encryption", request_context, false).await;
|
||||
notify_bucket_metadata_reload(bucket.clone(), "put bucket encryption", request_context, false);
|
||||
|
||||
let mut item = sr_bucket_meta_item(bucket.clone(), "sse-config");
|
||||
item.sse_config = Some(
|
||||
@@ -2226,7 +2222,7 @@ impl DefaultBucketUsecase {
|
||||
.await
|
||||
.map_err(ApiError::from)?;
|
||||
|
||||
notify_bucket_metadata_reload(bucket.clone(), "put bucket lifecycle", request_context, true).await;
|
||||
notify_bucket_metadata_reload(bucket.clone(), "put bucket lifecycle", request_context, true);
|
||||
|
||||
let mut item = sr_bucket_meta_item(bucket.clone(), "lc-config");
|
||||
item.expiry_lc_config =
|
||||
@@ -2311,7 +2307,7 @@ impl DefaultBucketUsecase {
|
||||
.await
|
||||
.map_err(ApiError::from)?;
|
||||
|
||||
notify_bucket_metadata_reload(bucket.clone(), "put bucket notification", request_context, false).await;
|
||||
notify_bucket_metadata_reload(bucket.clone(), "put bucket notification", request_context, false);
|
||||
|
||||
let region = resolve_notification_region(self.global_region(), request_region);
|
||||
let notify = current_notify_interface_for_context(self.context.as_deref());
|
||||
@@ -2416,7 +2412,7 @@ impl DefaultBucketUsecase {
|
||||
.await
|
||||
.map_err(ApiError::from)?;
|
||||
|
||||
notify_bucket_metadata_reload(bucket.clone(), "put bucket policy", request_context, false).await;
|
||||
notify_bucket_metadata_reload(bucket.clone(), "put bucket policy", request_context, false);
|
||||
|
||||
let mut item = sr_bucket_meta_item(bucket.clone(), "policy");
|
||||
item.policy = Some(serde_json::from_str(&policy).map_err(|e| s3_error!(InvalidArgument, "parse policy failed {:?}", e))?);
|
||||
@@ -2451,7 +2447,7 @@ impl DefaultBucketUsecase {
|
||||
.await
|
||||
.map_err(ApiError::from)?;
|
||||
|
||||
notify_bucket_metadata_reload(bucket.clone(), "put bucket cors", request_context, false).await;
|
||||
notify_bucket_metadata_reload(bucket.clone(), "put bucket cors", request_context, false);
|
||||
|
||||
let mut item = sr_bucket_meta_item(bucket.clone(), "cors-config");
|
||||
item.cors =
|
||||
@@ -2495,7 +2491,7 @@ impl DefaultBucketUsecase {
|
||||
.map_err(ApiError::from)?;
|
||||
drop(targets_guard);
|
||||
|
||||
notify_bucket_metadata_reload(bucket.clone(), "put bucket replication", request_context, true).await;
|
||||
notify_bucket_metadata_reload(bucket.clone(), "put bucket replication", request_context, true);
|
||||
|
||||
let mut item = sr_bucket_meta_item(bucket.clone(), "replication-config");
|
||||
item.replication_config = Some(
|
||||
@@ -2535,7 +2531,7 @@ impl DefaultBucketUsecase {
|
||||
.await
|
||||
.map_err(ApiError::from)?;
|
||||
|
||||
notify_bucket_metadata_reload(bucket.clone(), "put public access block", request_context, false).await;
|
||||
notify_bucket_metadata_reload(bucket.clone(), "put public access block", request_context, false);
|
||||
|
||||
Ok(S3Response::new(PutPublicAccessBlockOutput::default()))
|
||||
}
|
||||
@@ -2564,7 +2560,7 @@ impl DefaultBucketUsecase {
|
||||
.await
|
||||
.map_err(ApiError::from)?;
|
||||
|
||||
notify_bucket_metadata_reload(bucket.clone(), "put bucket tagging", request_context, false).await;
|
||||
notify_bucket_metadata_reload(bucket.clone(), "put bucket tagging", request_context, false);
|
||||
|
||||
let mut item = sr_bucket_meta_item(bucket.clone(), "tags");
|
||||
item.tags = Some(serialize_config(&tagging).and_then(|bytes| String::from_utf8(bytes).map_err(to_internal_error))?);
|
||||
@@ -2597,7 +2593,7 @@ impl DefaultBucketUsecase {
|
||||
.await
|
||||
.map_err(ApiError::from)?;
|
||||
|
||||
notify_bucket_metadata_reload(bucket.clone(), "put bucket versioning", request_context, false).await;
|
||||
notify_bucket_metadata_reload(bucket.clone(), "put bucket versioning", request_context, false);
|
||||
|
||||
let mut item = sr_bucket_meta_item(bucket.clone(), "version-config");
|
||||
item.versioning = Some(
|
||||
@@ -3048,7 +3044,7 @@ mod tests {
|
||||
"{method} should identify the bucket metadata operation in reload logs"
|
||||
);
|
||||
let expected_reload = format!(
|
||||
"notify_bucket_metadata_reload(bucket.clone(), \"{operation}\", request_context, {scanner_maintenance_change}).await;"
|
||||
"notify_bucket_metadata_reload(bucket.clone(), \"{operation}\", request_context, {scanner_maintenance_change});"
|
||||
);
|
||||
assert!(
|
||||
body.contains(&expected_reload),
|
||||
|
||||
Reference in New Issue
Block a user