mirror of
https://github.com/rustfs/rustfs.git
synced 2026-08-23 04:39:04 +00:00
Compare commits
1 Commits
| Author | SHA1 | Date | |
|---|---|---|---|
 overtrue
|
432a56f6e1 |
@@ -178,9 +178,14 @@ jobs:
|
||||
|
||||
- name: Install Python tools
|
||||
run: |
|
||||
python3 -m pip install --user --upgrade pip awscurl tox
|
||||
python3 -m pip install --user --upgrade pip "awscurl==0.44" "tox==4.60.0"
|
||||
echo "$HOME/.local/bin" >> "$GITHUB_PATH"
|
||||
|
||||
- name: Verify Python tools
|
||||
run: |
|
||||
test "$(python3 -c 'import importlib.metadata as m; print(m.version("awscurl"))')" = "0.44"
|
||||
test "$(python3 -c 'import importlib.metadata as m; print(m.version("tox"))')" = "4.60.0"
|
||||
|
||||
- name: Enable buildx
|
||||
uses: docker/setup-buildx-action@8d2750c68a42422c14e847fe6c8ac0403b4cbd6f # v3
|
||||
|
||||
|
||||
@@ -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
|
||||
|
||||
|
||||
Generated
+27
-23
@@ -1858,9 +1858,9 @@ dependencies = [
|
||||
|
||||
[[package]]
|
||||
name = "cc"
|
||||
version = "1.4.4"
|
||||
version = "1.4.3"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "0ad534f4357a5264cce5019c989cf66a4f0dc4e0d1b1d15f8aacec0ff7360273"
|
||||
checksum = "509591b7bcd67f4ef775afad7662703b4935daaa6ec0e5605cfb1090b32a2b6d"
|
||||
dependencies = [
|
||||
"find-msvc-tools",
|
||||
"jobserver",
|
||||
@@ -2522,6 +2522,12 @@ dependencies = [
|
||||
"subtle",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "cty"
|
||||
version = "0.2.2"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "b365fabc795046672053e29c954733ec3b05e4be654ab130fe8f1f94d7051f35"
|
||||
|
||||
[[package]]
|
||||
name = "curve25519-dalek"
|
||||
version = "4.1.3"
|
||||
@@ -5982,6 +5988,15 @@ version = "0.2.16"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "b6d2cec3eae94f9f509c767b45932f1ada8350c4bdb85af2fcab4a3c14807981"
|
||||
|
||||
[[package]]
|
||||
name = "libmimalloc-sys"
|
||||
version = "0.1.49"
|
||||
source = "git+https://github.com/xonatius/mimalloc_rust.git?rev=6d4c41bb10c6d9da1d1b6f07b38c4cc051667f11#6d4c41bb10c6d9da1d1b6f07b38c4cc051667f11"
|
||||
dependencies = [
|
||||
"cc",
|
||||
"cty",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "libredox"
|
||||
version = "0.1.20"
|
||||
@@ -6382,6 +6397,14 @@ dependencies = [
|
||||
"synstructure 0.13.2",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "mimalloc"
|
||||
version = "0.1.52"
|
||||
source = "git+https://github.com/xonatius/mimalloc_rust.git?rev=6d4c41bb10c6d9da1d1b6f07b38c4cc051667f11#6d4c41bb10c6d9da1d1b6f07b38c4cc051667f11"
|
||||
dependencies = [
|
||||
"libmimalloc-sys",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "mime"
|
||||
version = "0.3.17"
|
||||
@@ -9139,11 +9162,13 @@ dependencies = [
|
||||
"insta",
|
||||
"jiff",
|
||||
"libc",
|
||||
"libmimalloc-sys",
|
||||
"libsystemd",
|
||||
"matchit 0.9.2",
|
||||
"md-5 0.11.0",
|
||||
"metrics",
|
||||
"metrics-util",
|
||||
"mimalloc",
|
||||
"mime_guess",
|
||||
"opentelemetry",
|
||||
"opentelemetry_sdk",
|
||||
@@ -9179,8 +9204,6 @@ dependencies = [
|
||||
"rustfs-lock",
|
||||
"rustfs-log-analyzer",
|
||||
"rustfs-madmin",
|
||||
"rustfs-mimalloc",
|
||||
"rustfs-mimalloc-sys",
|
||||
"rustfs-notify",
|
||||
"rustfs-object-capacity",
|
||||
"rustfs-object-data-cache",
|
||||
@@ -9852,24 +9875,6 @@ dependencies = [
|
||||
"tokio",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "rustfs-mimalloc"
|
||||
version = "0.5.0"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "a406f4aa07084301d485beec873af6dccc8e3f8762da244743df92038b1db1a6"
|
||||
dependencies = [
|
||||
"rustfs-mimalloc-sys",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "rustfs-mimalloc-sys"
|
||||
version = "0.5.0"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "c3051b819175f58445d4c369a72f0ab88149f3885ba8bea2aff3be01f53fe7cd"
|
||||
dependencies = [
|
||||
"cc",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "rustfs-notify"
|
||||
version = "1.0.0-rc.3"
|
||||
@@ -12683,7 +12688,6 @@ dependencies = [
|
||||
"js-sys",
|
||||
"rand 0.10.2",
|
||||
"serde_core",
|
||||
"sha1_smol",
|
||||
"wasm-bindgen",
|
||||
]
|
||||
|
||||
|
||||
+2
-2
@@ -350,8 +350,8 @@ russh-sftp = "2.4.0"
|
||||
dav-server = "0.11.0"
|
||||
|
||||
# Performance Analysis and Memory Profiling
|
||||
rustfs-mimalloc = { version = "0.5.0" }
|
||||
rustfs-mimalloc-sys = { version = "0.5.0" }
|
||||
mimalloc = { version = "0.1.52", git = "https://github.com/xonatius/mimalloc_rust.git", rev = "6d4c41bb10c6d9da1d1b6f07b38c4cc051667f11" }
|
||||
libmimalloc-sys = { version = "0.1.49", git = "https://github.com/xonatius/mimalloc_rust.git", rev = "6d4c41bb10c6d9da1d1b6f07b38c4cc051667f11", features = ["extended"] }
|
||||
hotpath = { version = "0.23.3", default-features = false }
|
||||
# Snapshot testing for output format regression detection
|
||||
insta = { version = "1.48" }
|
||||
|
||||
@@ -32,10 +32,6 @@ pub struct Credentials {
|
||||
pub access_key: String,
|
||||
#[serde(rename = "secretKey")]
|
||||
pub secret_key: String,
|
||||
// The aliases accept madmin's JSON tags (MinIO-written bucket-targets
|
||||
// metadata and mc request bodies) without changing the snake_case
|
||||
// persisted/peer wire format this struct serializes to.
|
||||
#[serde(alias = "sessionToken")]
|
||||
pub session_token: Option<String>,
|
||||
pub expiration: Option<Timestamp>,
|
||||
}
|
||||
@@ -206,14 +202,12 @@ pub struct BucketTarget {
|
||||
#[serde(default)]
|
||||
pub region: String,
|
||||
|
||||
// madmin-go v3.0.109 tags this `bandwidthlimit`; `bandwidth` is a legacy
|
||||
// alias kept for inputs written before the madmin tag was verified.
|
||||
#[serde(alias = "bandwidthlimit", alias = "bandwidth", default)]
|
||||
#[serde(alias = "bandwidth", default)]
|
||||
pub bandwidth_limit: i64,
|
||||
|
||||
#[serde(rename = "replicationSync", default)]
|
||||
pub replication_sync: bool,
|
||||
#[serde(alias = "storageclass", default)]
|
||||
#[serde(default)]
|
||||
pub storage_class: String,
|
||||
#[serde(rename = "skipTlsVerify", default)]
|
||||
pub skip_tls_verify: bool,
|
||||
@@ -226,7 +220,7 @@ pub struct BucketTarget {
|
||||
|
||||
#[serde(rename = "resetBeforeDate", with = "time::serde::rfc3339::option", default)]
|
||||
pub reset_before_date: Option<OffsetDateTime>,
|
||||
#[serde(alias = "resetID", default)]
|
||||
#[serde(default)]
|
||||
pub reset_id: String,
|
||||
#[serde(rename = "totalDowntime", with = "duration_seconds", default)]
|
||||
pub total_downtime: Duration,
|
||||
@@ -239,7 +233,7 @@ pub struct BucketTarget {
|
||||
#[serde(default)]
|
||||
pub latency: LatencyStat,
|
||||
|
||||
#[serde(alias = "deploymentID", default)]
|
||||
#[serde(default)]
|
||||
pub deployment_id: String,
|
||||
|
||||
#[serde(default)]
|
||||
@@ -537,85 +531,6 @@ mod tests {
|
||||
assert_eq!(value["totalDowntime"], 90);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn bucket_target_persisted_wire_keys_stay_snake_case() {
|
||||
// bucket-targets.json (persisted via `serde_json::to_vec(&BucketTargets)`
|
||||
// in the admin set/remove handlers) and the msgpack struct-map form
|
||||
// (`BucketTargets::marshal_msg`) both come straight from this struct's
|
||||
// serde field names. madmin naming is applied only in the admin
|
||||
// response layer (`remote_target_admin_json`); renaming here would
|
||||
// silently break every existing deployment's persisted metadata.
|
||||
let targets = BucketTargets {
|
||||
targets: vec![BucketTarget {
|
||||
credentials: Some(Credentials {
|
||||
access_key: "ak".to_string(),
|
||||
secret_key: "sk".to_string(),
|
||||
session_token: Some("token".to_string()),
|
||||
expiration: None,
|
||||
}),
|
||||
bandwidth_limit: 5,
|
||||
storage_class: "STANDARD".to_string(),
|
||||
reset_id: "reset-1".to_string(),
|
||||
deployment_id: "deploy-1".to_string(),
|
||||
..Default::default()
|
||||
}],
|
||||
};
|
||||
|
||||
let json = serde_json::to_value(&targets).expect("targets should serialize to JSON");
|
||||
let msgpack: serde_json::Value =
|
||||
rmp_serde::from_slice(&targets.marshal_msg().expect("targets should marshal to msgpack"))
|
||||
.expect("msgpack struct map should decode into a JSON value");
|
||||
|
||||
for (wire, entry) in [("JSON", &json["targets"][0]), ("msgpack", &msgpack["targets"][0])] {
|
||||
assert_eq!(entry["bandwidth_limit"], 5, "{wire} key `bandwidth_limit` must stay");
|
||||
assert_eq!(entry["storage_class"], "STANDARD", "{wire} key `storage_class` must stay");
|
||||
assert_eq!(entry["reset_id"], "reset-1", "{wire} key `reset_id` must stay");
|
||||
assert_eq!(entry["deployment_id"], "deploy-1", "{wire} key `deployment_id` must stay");
|
||||
assert_eq!(entry["credentials"]["session_token"], "token", "{wire} key `session_token` must stay");
|
||||
}
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn minio_written_bucket_targets_json_populates_madmin_named_fields() {
|
||||
// A MinIO-written bucket-targets.json carries madmin's JSON tags
|
||||
// (`bandwidthlimit`, `storageclass`, `resetID`, `deploymentID`,
|
||||
// `credentials.sessionToken` — madmin-go v3.0.109 bucket-targets.go).
|
||||
// On migration these must land in the matching fields instead of
|
||||
// silently defaulting (backlog#1951).
|
||||
let targets: BucketTargets = serde_json::from_value(serde_json::json!({
|
||||
"targets": [{
|
||||
"sourcebucket": "src",
|
||||
"endpoint": "minio.example:9000",
|
||||
"credentials": {
|
||||
"accessKey": "ak",
|
||||
"secretKey": "sk",
|
||||
"sessionToken": "minio-session-token"
|
||||
},
|
||||
"targetbucket": "dst",
|
||||
"type": "replication",
|
||||
"replicationSync": true,
|
||||
"bandwidthlimit": 107374182400i64,
|
||||
"storageclass": "STANDARD",
|
||||
"resetID": "reset-789",
|
||||
"deploymentID": "deploy-123"
|
||||
}]
|
||||
}))
|
||||
.expect("MinIO-written bucket-targets.json must deserialize");
|
||||
|
||||
let target = &targets.targets[0];
|
||||
assert_eq!(target.bandwidth_limit, 107374182400);
|
||||
assert_eq!(target.storage_class, "STANDARD");
|
||||
assert_eq!(target.reset_id, "reset-789");
|
||||
assert_eq!(target.deployment_id, "deploy-123");
|
||||
assert_eq!(
|
||||
target
|
||||
.credentials
|
||||
.as_ref()
|
||||
.and_then(|credentials| credentials.session_token.as_deref()),
|
||||
Some("minio-session-token")
|
||||
);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn test_bucket_target_debug_redacts_credentials() {
|
||||
let target = BucketTarget {
|
||||
|
||||
@@ -2026,7 +2026,7 @@ impl PoolMeta {
|
||||
self.load_no_lock(pool).await
|
||||
}
|
||||
|
||||
pub(crate) async fn load_no_lock<S>(&mut self, pool: Arc<S>) -> Result<()>
|
||||
async fn load_no_lock<S>(&mut self, pool: Arc<S>) -> Result<()>
|
||||
where
|
||||
S: EcstoreObjectIO,
|
||||
{
|
||||
|
||||
@@ -988,11 +988,14 @@ impl crate::storage_api_contracts::multipart::MultipartOperations for Sets {
|
||||
}
|
||||
}
|
||||
|
||||
impl Sets {
|
||||
pub(crate) async fn heal_format_with_fence<F>(&self, dry_run: bool, fence_lost: F) -> Result<(HealResultItem, Option<Error>)>
|
||||
where
|
||||
F: Fn() -> bool + Send + Sync,
|
||||
{
|
||||
#[async_trait::async_trait]
|
||||
impl crate::storage_api_contracts::heal::HealOperations for Sets {
|
||||
type Error = Error;
|
||||
type HealResultItem = HealResultItem;
|
||||
type HealOptions = HealOpts;
|
||||
|
||||
#[tracing::instrument(skip(self))]
|
||||
async fn heal_format(&self, dry_run: bool) -> Result<(HealResultItem, Option<Error>)> {
|
||||
let (disks, init_errs) = init_storage_disks_with_errors(
|
||||
&self.endpoints.endpoints,
|
||||
&DiskOption {
|
||||
@@ -1065,9 +1068,6 @@ impl Sets {
|
||||
// Save new formats `format.json` on unformatted disks.
|
||||
for (index, (fm, disk)) in tmp_new_formats.iter_mut().zip(disks.iter()).enumerate() {
|
||||
if fm.is_some() && disk.is_some() {
|
||||
if fence_lost() {
|
||||
return Ok((res, Some(StorageError::SlowDown)));
|
||||
}
|
||||
if let Err(err) = save_format_file(disk, fm).await {
|
||||
if let Some(disk) = disk.as_ref() {
|
||||
let _ = disk.close().await;
|
||||
@@ -1101,18 +1101,6 @@ impl Sets {
|
||||
}
|
||||
Ok((res, None))
|
||||
}
|
||||
}
|
||||
|
||||
#[async_trait::async_trait]
|
||||
impl crate::storage_api_contracts::heal::HealOperations for Sets {
|
||||
type Error = Error;
|
||||
type HealResultItem = HealResultItem;
|
||||
type HealOptions = HealOpts;
|
||||
|
||||
#[tracing::instrument(skip(self))]
|
||||
async fn heal_format(&self, dry_run: bool) -> Result<(HealResultItem, Option<Error>)> {
|
||||
self.heal_format_with_fence(dry_run, || false).await
|
||||
}
|
||||
#[tracing::instrument(skip(self))]
|
||||
async fn heal_bucket(&self, bucket: &str, opts: &HealOpts) -> Result<HealResultItem> {
|
||||
let mut result = HealResultItem {
|
||||
|
||||
@@ -2124,13 +2124,26 @@ impl SetDisks {
|
||||
|
||||
let put_object_size = known_put_object_storage_size(data.size());
|
||||
let shard_file_size_raw = erasure.shard_file_size(put_object_size);
|
||||
let is_inline_buffer = storage_class_config.should_inline(shard_file_size_raw, erasure.data_shards, opts.versioned);
|
||||
let is_inline_buffer =
|
||||
storage_class_config.should_inline(shard_file_size_raw, erasure.data_shards, opts.versioned);
|
||||
|
||||
let collect_stage_timing = rustfs_io_metrics::put_stage_metrics_enabled() || issue3031_diag_enabled();
|
||||
let shard_file_size = shard_file_size_raw;
|
||||
let shard_size = erasure.shard_size();
|
||||
let write_path = classify_put_write_path(is_inline_buffer, put_object_size, fi.erasure.block_size);
|
||||
let direct_inline_commit = matches!(write_path, SmallWritePath::Inline);
|
||||
{
|
||||
use std::io::Write;
|
||||
let msg = format!(
|
||||
"INLINE_DEBUG: bucket={} obj={} size={} shard_fs={} ds={} bs={} inline={} direct={} path={} iblock={} ver={}\n",
|
||||
bucket, object, put_object_size, shard_file_size_raw, erasure.data_shards, fi.erasure.block_size,
|
||||
is_inline_buffer, direct_inline_commit, write_path.metric_label(), storage_class_config.inline_block(), opts.versioned
|
||||
);
|
||||
if let Ok(mut f) = std::fs::OpenOptions::new().create(true).append(true).open("/tmp/rustfs_inline_debug.log") {
|
||||
let _ = f.write_all(msg.as_bytes());
|
||||
}
|
||||
let _ = std::io::stderr().write_all(msg.as_bytes());
|
||||
}
|
||||
rustfs_io_metrics::record_put_object_path(write_path.metric_label());
|
||||
let writer_setup_stage_start = collect_stage_timing.then(Instant::now);
|
||||
let (mut writers, errors) = if direct_inline_commit {
|
||||
|
||||
@@ -13,12 +13,7 @@
|
||||
// limitations under the License.
|
||||
|
||||
use super::*;
|
||||
use crate::core::pools::POOL_META_NAME;
|
||||
use crate::services::rebalance::{REBAL_META_NAME, RebalStatus};
|
||||
use crate::set_disk::get_lock_acquire_timeout;
|
||||
use crate::storage_api_contracts::heal::HealOperations as _;
|
||||
use crate::storage_api_contracts::namespace::NamespaceLocking as _;
|
||||
use rustfs_lock::NamespaceLockGuard;
|
||||
use tracing::trace;
|
||||
|
||||
const LOG_COMPONENT_ECSTORE: &str = "ecstore";
|
||||
@@ -35,119 +30,7 @@ fn invalid_heal_pool_index(pool_idx: usize, pool_count: usize) -> Error {
|
||||
)
|
||||
}
|
||||
|
||||
#[derive(Debug, Clone, Copy)]
|
||||
enum HealFormatPoolSkip {
|
||||
Completed,
|
||||
Retryable,
|
||||
}
|
||||
|
||||
fn classify_heal_format_pool(
|
||||
pool_idx: usize,
|
||||
pool_cmd_line: &str,
|
||||
pool_meta: &PoolMeta,
|
||||
rebalance_meta: Option<&RebalanceMeta>,
|
||||
) -> Option<HealFormatPoolSkip> {
|
||||
let Some(pool) = pool_meta.pools.get(pool_idx) else {
|
||||
return Some(HealFormatPoolSkip::Retryable);
|
||||
};
|
||||
|
||||
if pool.id != pool_idx || pool_cmd_line.is_empty() || pool.cmd_line.is_empty() || pool.cmd_line != pool_cmd_line {
|
||||
return Some(HealFormatPoolSkip::Retryable);
|
||||
}
|
||||
|
||||
if let Some(decommission) = pool.decommission.as_ref() {
|
||||
if decommission.complete {
|
||||
return Some(HealFormatPoolSkip::Completed);
|
||||
}
|
||||
if decommission.failed || decommission.canceled || decommission.queued || pool_meta.is_suspended(pool_idx) {
|
||||
return Some(HealFormatPoolSkip::Retryable);
|
||||
}
|
||||
}
|
||||
|
||||
if let Some(meta) = rebalance_meta {
|
||||
let Some(pool_stats) = meta.pool_stats.get(pool_idx) else {
|
||||
return Some(HealFormatPoolSkip::Retryable);
|
||||
};
|
||||
if pool_stats.info.stopping || (pool_stats.participating && pool_stats.info.status == RebalStatus::Started) {
|
||||
return Some(HealFormatPoolSkip::Retryable);
|
||||
}
|
||||
}
|
||||
|
||||
None
|
||||
}
|
||||
|
||||
fn heal_format_pool_skip_error(skip: HealFormatPoolSkip) -> Error {
|
||||
match skip {
|
||||
HealFormatPoolSkip::Completed => StorageError::NoHealRequired,
|
||||
HealFormatPoolSkip::Retryable => StorageError::SlowDown,
|
||||
}
|
||||
}
|
||||
|
||||
fn heal_format_fence_lost_error() -> Error {
|
||||
StorageError::SlowDown
|
||||
}
|
||||
|
||||
impl ECStore {
|
||||
async fn acquire_heal_format_fence(
|
||||
&self,
|
||||
) -> Result<(NamespaceLockGuard, NamespaceLockGuard, PoolMeta, Option<RebalanceMeta>)> {
|
||||
let metadata_pool = self
|
||||
.pools
|
||||
.first()
|
||||
.cloned()
|
||||
.ok_or_else(|| Error::other("heal format requires at least one storage pool"))?;
|
||||
|
||||
// Metadata fence order is part of the decommission/rebalance protocol:
|
||||
// pool.bin must always be acquired before rebalance.bin.
|
||||
let pool_lock = metadata_pool.new_ns_lock(RUSTFS_META_BUCKET, POOL_META_NAME).await?;
|
||||
let pool_guard = pool_lock.get_write_lock(get_lock_acquire_timeout()).await?;
|
||||
let rebalance_lock = metadata_pool.new_ns_lock(RUSTFS_META_BUCKET, REBAL_META_NAME).await?;
|
||||
let rebalance_guard = rebalance_lock.get_write_lock(get_lock_acquire_timeout()).await?;
|
||||
|
||||
if pool_guard.is_lock_lost() || rebalance_guard.is_lock_lost() {
|
||||
return Err(heal_format_fence_lost_error());
|
||||
}
|
||||
|
||||
let mut pool_meta = PoolMeta::default();
|
||||
pool_meta.load_no_lock(metadata_pool.clone()).await?;
|
||||
if pool_meta.pools.len() != self.pools.len()
|
||||
|| pool_meta.pools.iter().enumerate().any(|(pool_idx, pool)| {
|
||||
pool.id != pool_idx || pool.cmd_line.is_empty() || pool.cmd_line != self.pools[pool_idx].endpoints.cmd_line
|
||||
})
|
||||
{
|
||||
return Err(heal_format_fence_lost_error());
|
||||
}
|
||||
|
||||
let mut rebalance_meta = RebalanceMeta::new();
|
||||
let rebalance_meta = match rebalance_meta
|
||||
.load_with_opts(
|
||||
metadata_pool,
|
||||
ObjectOptions {
|
||||
no_lock: true,
|
||||
..Default::default()
|
||||
},
|
||||
)
|
||||
.await
|
||||
{
|
||||
Ok(()) => Some(rebalance_meta),
|
||||
Err(Error::ConfigNotFound) => None,
|
||||
Err(err) => return Err(err),
|
||||
};
|
||||
|
||||
if rebalance_meta
|
||||
.as_ref()
|
||||
.is_some_and(|meta| meta.pool_stats.len() != self.pools.len())
|
||||
{
|
||||
return Err(heal_format_fence_lost_error());
|
||||
}
|
||||
|
||||
if pool_guard.is_lock_lost() || rebalance_guard.is_lock_lost() {
|
||||
return Err(heal_format_fence_lost_error());
|
||||
}
|
||||
|
||||
Ok((pool_guard, rebalance_guard, pool_meta, rebalance_meta))
|
||||
}
|
||||
|
||||
fn get_pools_for_heal_object(&self, opts: &HealOpts) -> Result<Vec<Arc<Sets>>> {
|
||||
match opts.pool {
|
||||
Some(pool_idx) => Ok(vec![
|
||||
@@ -169,26 +52,9 @@ impl ECStore {
|
||||
};
|
||||
|
||||
let mut count_no_heal = 0;
|
||||
let mut count_completed = 0;
|
||||
let mut first_error = None;
|
||||
for (pool_idx, pool) in self.pools.iter().enumerate() {
|
||||
let (pool_guard, rebalance_guard, pool_meta, rebalance_meta) = self.acquire_heal_format_fence().await?;
|
||||
if pool_guard.is_lock_lost() || rebalance_guard.is_lock_lost() {
|
||||
first_error.get_or_insert(heal_format_fence_lost_error());
|
||||
break;
|
||||
}
|
||||
if let Some(skip) = classify_heal_format_pool(pool_idx, &pool.endpoints.cmd_line, &pool_meta, rebalance_meta.as_ref())
|
||||
{
|
||||
if matches!(skip, HealFormatPoolSkip::Completed) {
|
||||
count_completed += 1;
|
||||
} else {
|
||||
first_error.get_or_insert(heal_format_pool_skip_error(skip));
|
||||
}
|
||||
continue;
|
||||
}
|
||||
|
||||
let fence_lost = || pool_guard.is_lock_lost() || rebalance_guard.is_lock_lost();
|
||||
let (mut result, err) = pool.heal_format_with_fence(dry_run, fence_lost).await?;
|
||||
for pool in self.pools.iter() {
|
||||
let (mut result, err) = pool.heal_format(dry_run).await?;
|
||||
if let Some(err) = err {
|
||||
match err {
|
||||
StorageError::NoHealRequired => {
|
||||
@@ -203,18 +69,11 @@ impl ECStore {
|
||||
r.set_count += result.set_count;
|
||||
r.before.drives.append(&mut result.before.drives);
|
||||
r.after.drives.append(&mut result.after.drives);
|
||||
|
||||
// A lease can be lost after the final write; fail closed before
|
||||
// reporting the pool as successfully healed.
|
||||
if pool_guard.is_lock_lost() || rebalance_guard.is_lock_lost() {
|
||||
first_error.get_or_insert(heal_format_fence_lost_error());
|
||||
break;
|
||||
}
|
||||
}
|
||||
if let Some(err) = first_error {
|
||||
return Ok((r, Some(err)));
|
||||
}
|
||||
if count_no_heal + count_completed == self.pools.len() {
|
||||
if count_no_heal == self.pools.len() {
|
||||
info!(
|
||||
event = EVENT_HEAL_FORMAT_COMPLETED,
|
||||
component = LOG_COMPONENT_ECSTORE,
|
||||
@@ -443,7 +302,6 @@ mod tests {
|
||||
use crate::disk::{DeleteOptions, DiskOption, format::FormatV3, new_disk};
|
||||
use crate::layout::endpoints::{EndpointServerPools, Endpoints, PoolEndpoints};
|
||||
use crate::runtime::instance::InstanceContext;
|
||||
use crate::services::rebalance::{RebalanceInfo, RebalanceStats};
|
||||
use crate::storage_api_contracts::bucket::{BucketOperations, MakeBucketOptions};
|
||||
use crate::storage_api_contracts::object::{ObjectIO as _, ObjectOperations};
|
||||
use crate::store::init_format::{load_format_erasure, save_format_file};
|
||||
@@ -495,164 +353,6 @@ mod tests {
|
||||
}
|
||||
}
|
||||
|
||||
fn pool_meta_with_decommission(info: PoolDecommissionInfo) -> PoolMeta {
|
||||
PoolMeta {
|
||||
pools: vec![PoolStatus {
|
||||
id: 0,
|
||||
cmd_line: "pool-0".to_string(),
|
||||
last_update: OffsetDateTime::UNIX_EPOCH,
|
||||
decommission: Some(info),
|
||||
}],
|
||||
..Default::default()
|
||||
}
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn heal_format_pool_state_barriers_are_classified() {
|
||||
let active = pool_meta_with_decommission(PoolDecommissionInfo {
|
||||
start_time: Some(OffsetDateTime::UNIX_EPOCH),
|
||||
..Default::default()
|
||||
});
|
||||
assert!(matches!(
|
||||
classify_heal_format_pool(0, "pool-0", &active, None),
|
||||
Some(HealFormatPoolSkip::Retryable)
|
||||
));
|
||||
|
||||
for info in [
|
||||
PoolDecommissionInfo {
|
||||
failed: true,
|
||||
..Default::default()
|
||||
},
|
||||
PoolDecommissionInfo {
|
||||
canceled: true,
|
||||
..Default::default()
|
||||
},
|
||||
] {
|
||||
assert!(matches!(
|
||||
classify_heal_format_pool(0, "pool-0", &pool_meta_with_decommission(info), None),
|
||||
Some(HealFormatPoolSkip::Retryable)
|
||||
));
|
||||
}
|
||||
|
||||
let completed = pool_meta_with_decommission(PoolDecommissionInfo {
|
||||
complete: true,
|
||||
..Default::default()
|
||||
});
|
||||
assert!(matches!(
|
||||
classify_heal_format_pool(0, "pool-0", &completed, None),
|
||||
Some(HealFormatPoolSkip::Completed)
|
||||
));
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn heal_format_pool_rebalance_barriers_and_identity_are_fail_closed() {
|
||||
let identity_meta = pool_meta_with_decommission(PoolDecommissionInfo::default());
|
||||
let rebalance = RebalanceMeta {
|
||||
pool_stats: vec![RebalanceStats {
|
||||
participating: true,
|
||||
info: RebalanceInfo {
|
||||
status: RebalStatus::Started,
|
||||
..Default::default()
|
||||
},
|
||||
..Default::default()
|
||||
}],
|
||||
..Default::default()
|
||||
};
|
||||
assert!(matches!(
|
||||
classify_heal_format_pool(0, "pool-0", &identity_meta, Some(&rebalance)),
|
||||
Some(HealFormatPoolSkip::Retryable)
|
||||
));
|
||||
|
||||
let stopping = RebalanceMeta {
|
||||
pool_stats: vec![RebalanceStats {
|
||||
info: RebalanceInfo {
|
||||
stopping: true,
|
||||
..Default::default()
|
||||
},
|
||||
..Default::default()
|
||||
}],
|
||||
..Default::default()
|
||||
};
|
||||
assert!(matches!(
|
||||
classify_heal_format_pool(0, "pool-0", &identity_meta, Some(&stopping)),
|
||||
Some(HealFormatPoolSkip::Retryable)
|
||||
));
|
||||
|
||||
let identity = pool_meta_with_decommission(PoolDecommissionInfo::default());
|
||||
assert!(matches!(
|
||||
classify_heal_format_pool(0, "pool-new", &identity, None),
|
||||
Some(HealFormatPoolSkip::Retryable)
|
||||
));
|
||||
|
||||
let identity_without_decommission = PoolMeta {
|
||||
pools: vec![PoolStatus {
|
||||
id: 0,
|
||||
cmd_line: "pool-0".to_string(),
|
||||
last_update: OffsetDateTime::UNIX_EPOCH,
|
||||
decommission: None,
|
||||
}],
|
||||
..Default::default()
|
||||
};
|
||||
assert!(matches!(
|
||||
classify_heal_format_pool(0, "pool-new", &identity_without_decommission, None),
|
||||
Some(HealFormatPoolSkip::Retryable)
|
||||
));
|
||||
|
||||
assert!(matches!(
|
||||
classify_heal_format_pool(0, "", &identity_meta, None),
|
||||
Some(HealFormatPoolSkip::Retryable)
|
||||
));
|
||||
|
||||
assert!(matches!(
|
||||
classify_heal_format_pool(0, "pool-0", &PoolMeta::default(), None),
|
||||
Some(HealFormatPoolSkip::Retryable)
|
||||
));
|
||||
|
||||
let stopped = RebalanceMeta {
|
||||
stopped_at: Some(OffsetDateTime::UNIX_EPOCH),
|
||||
pool_stats: vec![RebalanceStats {
|
||||
participating: true,
|
||||
info: RebalanceInfo {
|
||||
status: RebalStatus::Stopped,
|
||||
..Default::default()
|
||||
},
|
||||
..Default::default()
|
||||
}],
|
||||
..Default::default()
|
||||
};
|
||||
assert!(classify_heal_format_pool(0, "pool-0", &identity_meta, Some(&stopped)).is_none());
|
||||
|
||||
let stopping_after_stop = RebalanceMeta {
|
||||
stopped_at: Some(OffsetDateTime::UNIX_EPOCH),
|
||||
pool_stats: vec![RebalanceStats {
|
||||
participating: true,
|
||||
info: RebalanceInfo {
|
||||
status: RebalStatus::Started,
|
||||
stopping: true,
|
||||
..Default::default()
|
||||
},
|
||||
..Default::default()
|
||||
}],
|
||||
..Default::default()
|
||||
};
|
||||
assert!(matches!(
|
||||
classify_heal_format_pool(0, "pool-0", &identity_meta, Some(&stopping_after_stop)),
|
||||
Some(HealFormatPoolSkip::Retryable)
|
||||
));
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn skipped_heal_format_pool_is_never_reported_as_success() {
|
||||
assert!(matches!(
|
||||
heal_format_pool_skip_error(HealFormatPoolSkip::Retryable),
|
||||
StorageError::SlowDown
|
||||
));
|
||||
assert!(matches!(
|
||||
heal_format_pool_skip_error(HealFormatPoolSkip::Completed),
|
||||
StorageError::NoHealRequired
|
||||
));
|
||||
}
|
||||
|
||||
async fn multi_pool_heal_store() -> (tempfile::TempDir, Arc<ECStore>, CancellationToken) {
|
||||
let temp_dir = tempfile::tempdir().expect("multi-pool heal test directory should be created");
|
||||
let mut pool_endpoints = Vec::new();
|
||||
@@ -1189,18 +889,6 @@ mod tests {
|
||||
bucket_fence_registry: std::sync::Arc::default(),
|
||||
};
|
||||
|
||||
let err = store
|
||||
.handle_heal_format(false)
|
||||
.await
|
||||
.expect_err("missing pool metadata must fail closed before format writes");
|
||||
assert!(matches!(err, StorageError::SlowDown));
|
||||
|
||||
let pool_meta = PoolMeta::new(&store.pools, &PoolMeta::default());
|
||||
pool_meta
|
||||
.save(store.pools.clone())
|
||||
.await
|
||||
.expect("pool metadata should be persisted before format heal");
|
||||
|
||||
let (result, err) = store
|
||||
.handle_heal_format(false)
|
||||
.await
|
||||
@@ -1214,22 +902,5 @@ mod tests {
|
||||
.await
|
||||
.expect("the later pool should be healed despite the first pool error");
|
||||
assert_eq!(healed.erasure.this, recoverable_format.erasure.sets[0][2]);
|
||||
|
||||
let mut completed_meta = PoolMeta::new(&store.pools, &PoolMeta::default());
|
||||
for status in &mut completed_meta.pools {
|
||||
status.decommission = Some(PoolDecommissionInfo {
|
||||
complete: true,
|
||||
..Default::default()
|
||||
});
|
||||
}
|
||||
completed_meta
|
||||
.save(store.pools.clone())
|
||||
.await
|
||||
.expect("completed pool metadata should be persisted");
|
||||
let (_, err) = store
|
||||
.handle_heal_format(false)
|
||||
.await
|
||||
.expect("completed pools should be reported as a no-op");
|
||||
assert!(matches!(err, Some(StorageError::NoHealRequired)));
|
||||
}
|
||||
}
|
||||
|
||||
@@ -3194,7 +3194,7 @@ impl ECStore {
|
||||
|
||||
// Default return value
|
||||
let mut del_objects = vec![DeletedObject::default(); objects.len()];
|
||||
let accounting = vec![None; objects.len()];
|
||||
let mut accounting = vec![None; objects.len()];
|
||||
|
||||
let mut del_errs = Vec::with_capacity(objects.len());
|
||||
for _ in 0..objects.len() {
|
||||
|
||||
@@ -271,7 +271,7 @@ pub(super) fn resolve_latest_object_info_candidates(
|
||||
.filter(|candidate| latest_candidate_mod_time(candidate) == Some(latest_mod_time))
|
||||
.collect::<Vec<_>>();
|
||||
|
||||
latest_candidates.sort_by_key(|candidate| std::cmp::Reverse(candidate.idx));
|
||||
latest_candidates.sort_by(|left, right| right.idx.cmp(&left.idx));
|
||||
|
||||
let Some(winner) = latest_candidates.first() else {
|
||||
return Err(Error::ErasureReadQuorum);
|
||||
|
||||
@@ -231,10 +231,6 @@ impl HealTask {
|
||||
"Heal erasure set format repair skipped because no format heal was required"
|
||||
);
|
||||
} else {
|
||||
let error = e;
|
||||
if error.is_recoverable_heal() {
|
||||
return Err(error);
|
||||
}
|
||||
error!(
|
||||
target: "rustfs::heal::task",
|
||||
event = EVENT_HEAL_ERASURE_SET_RESULT,
|
||||
@@ -243,7 +239,7 @@ impl HealTask {
|
||||
task_id = %self.id,
|
||||
set_disk_id,
|
||||
result = "format_failed",
|
||||
error = %error,
|
||||
error = %e,
|
||||
"Heal erasure set failed"
|
||||
);
|
||||
{
|
||||
@@ -251,7 +247,7 @@ impl HealTask {
|
||||
progress.update_progress(4, 4, 0, 0);
|
||||
}
|
||||
return Err(Error::TaskExecutionFailed {
|
||||
message: format!("Failed to heal disk format for {set_disk_id}: {error}"),
|
||||
message: format!("Failed to heal disk format for {set_disk_id}: {e}"),
|
||||
});
|
||||
}
|
||||
} else {
|
||||
@@ -288,9 +284,6 @@ impl HealTask {
|
||||
Err(Error::TaskCancelled) => return Err(Error::TaskCancelled),
|
||||
Err(Error::TaskTimeout) => return Err(Error::TaskTimeout),
|
||||
Err(e) => {
|
||||
if e.is_recoverable_heal() {
|
||||
return Err(e);
|
||||
}
|
||||
error!(
|
||||
target: "rustfs::heal::task",
|
||||
event = EVENT_HEAL_ERASURE_SET_RESULT,
|
||||
|
||||
@@ -547,7 +547,6 @@ struct MockStorage {
|
||||
heal_object_outcome: Mutex<Option<MockHealObjectOutcome>>,
|
||||
heal_object_outcomes: Mutex<HashMap<String, VecDeque<MockHealObjectOutcome>>>,
|
||||
format_no_heal_required: Mutex<bool>,
|
||||
format_error: Mutex<Option<Error>>,
|
||||
global_format_calls: Mutex<u32>,
|
||||
replacement_format_calls: Mutex<Vec<(usize, usize, Vec<String>)>>,
|
||||
replacement_targets_ready: Mutex<bool>,
|
||||
@@ -868,9 +867,6 @@ impl HealStorageAPI for MockStorage {
|
||||
|
||||
async fn heal_format(&self, _dry_run: bool) -> Result<(HealResultItem, Option<Error>)> {
|
||||
*self.global_format_calls.lock().unwrap() += 1;
|
||||
if let Some(error) = self.format_error.lock().unwrap().take() {
|
||||
return Err(error);
|
||||
}
|
||||
let no_heal_required = *self.format_no_heal_required.lock().unwrap();
|
||||
if no_heal_required {
|
||||
Ok((HealResultItem::default(), Some(Error::Storage(EcstoreError::NoHealRequired))))
|
||||
@@ -2056,30 +2052,6 @@ async fn test_erasure_set_heal_continues_after_format_no_heal_required() {
|
||||
);
|
||||
}
|
||||
|
||||
#[tokio::test]
|
||||
async fn erasure_set_format_slowdown_is_propagated() {
|
||||
let storage = Arc::new(MockStorage {
|
||||
format_error: Mutex::new(Some(Error::Storage(EcstoreError::SlowDown))),
|
||||
..Default::default()
|
||||
});
|
||||
let request = HealRequest::new(
|
||||
HealType::ErasureSet {
|
||||
buckets: Vec::new(),
|
||||
set_disk_id: "pool_0_set_0".to_string(),
|
||||
},
|
||||
HealOptions::default(),
|
||||
HealPriority::Normal,
|
||||
);
|
||||
let task = HealTask::from_request(request, storage);
|
||||
|
||||
let error = task
|
||||
.execute()
|
||||
.await
|
||||
.expect_err("format SlowDown must remain recoverable for the task manager");
|
||||
|
||||
assert!(matches!(error, Error::Storage(EcstoreError::SlowDown)));
|
||||
}
|
||||
|
||||
#[tokio::test]
|
||||
async fn erasure_set_bucket_prepass_failure_stops_before_object_heal() {
|
||||
let temp = TempDir::new().expect("temporary directory should be created");
|
||||
|
||||
@@ -245,18 +245,6 @@ impl TestECStoreEnvBuilder {
|
||||
.await
|
||||
.expect("build test ECStore");
|
||||
|
||||
// The production bootstrap only persists pool.bin from the elected
|
||||
// first cluster node. Test stores intentionally have no cluster
|
||||
// election, but heal-format still requires that durable fence before
|
||||
// it can write any disk format. Materialize the validated topology
|
||||
// here so the shared fixture models a ready single-node store.
|
||||
let mut pool_meta = ecstore.pool_meta.read().await.clone();
|
||||
pool_meta.dont_save = false;
|
||||
pool_meta
|
||||
.save(ecstore.pools.clone())
|
||||
.await
|
||||
.expect("persist test pool metadata");
|
||||
|
||||
if self.init_bucket_metadata {
|
||||
let buckets_list = ecstore
|
||||
.list_bucket(&BucketOptions {
|
||||
|
||||
@@ -43,6 +43,9 @@ allow-git = [
|
||||
# RustFS fork carrying presigned expiry and constant-time authentication fixes.
|
||||
# owner: rustfs-maintainers review: 2026-10
|
||||
"https://github.com/rustfs/s3s.git",
|
||||
# MiMalloc fork pinned for hotpath allocation counting support.
|
||||
# owner: houseme review: 2026-10
|
||||
"https://github.com/xonatius/mimalloc_rust.git",
|
||||
]
|
||||
|
||||
[bans]
|
||||
|
||||
@@ -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.
|
||||
+4
-4
@@ -322,7 +322,7 @@ thiserror = { workspace = true }
|
||||
tracing.workspace = true
|
||||
url = { workspace = true }
|
||||
urlencoding = { workspace = true }
|
||||
uuid = { workspace = true, features = ["v4", "v5", "fast-rng", "macro-diagnostics"] }
|
||||
uuid = { workspace = true, features = ["v4", "fast-rng", "macro-diagnostics"] }
|
||||
zip = { workspace = true }
|
||||
libc = { workspace = true }
|
||||
rand = { workspace = true, features = ["serde"] }
|
||||
@@ -336,16 +336,16 @@ opentelemetry = { workspace = true }
|
||||
tracing-opentelemetry = { workspace = true }
|
||||
# Data structures
|
||||
hashbrown = { workspace = true, features = ["serde", "rayon"] }
|
||||
rustfs-mimalloc = { workspace = true }
|
||||
mimalloc = { workspace = true }
|
||||
|
||||
[target.'cfg(target_os = "linux")'.dependencies]
|
||||
libsystemd.workspace = true
|
||||
|
||||
[target.'cfg(not(target_os = "windows"))'.dependencies]
|
||||
rustfs-mimalloc-sys.workspace = true
|
||||
libmimalloc-sys.workspace = true
|
||||
|
||||
[dev-dependencies]
|
||||
uuid = { workspace = true, features = ["v4", "v5", "fast-rng", "macro-diagnostics"] }
|
||||
uuid = { workspace = true, features = ["v4", "fast-rng", "macro-diagnostics"] }
|
||||
serial_test = { workspace = true }
|
||||
tempfile = { workspace = true }
|
||||
aws-config = { workspace = true }
|
||||
|
||||
@@ -376,10 +376,7 @@ impl RemoteTargetRequest {
|
||||
/// Admin-response encoding of a remote target: the persisted bucket-targets
|
||||
/// format keeps `healthCheckDuration`/`totalDowntime` in seconds and the
|
||||
/// `latency` stats in milliseconds, but madmin decodes all of them as Go
|
||||
/// `time.Duration` (nanoseconds) — and it looks the fields up under its own
|
||||
/// JSON tags (`bandwidthlimit`, `storageclass`, `resetID`, `deploymentID`,
|
||||
/// `credentials.sessionToken` — madmin-go v3.0.109 `bucket-targets.go`), not
|
||||
/// the persisted snake_case keys. Re-encode just those fields here without
|
||||
/// `time.Duration` (nanoseconds) — re-encode just those fields without
|
||||
/// touching the persistence wire format.
|
||||
fn remote_target_admin_json(target: &BucketTarget) -> Result<serde_json::Value, serde_json::Error> {
|
||||
fn go_duration_nanos(duration: Duration) -> serde_json::Value {
|
||||
@@ -388,12 +385,6 @@ fn remote_target_admin_json(target: &BucketTarget) -> Result<serde_json::Value,
|
||||
u64::try_from(duration.as_nanos()).unwrap_or(u64::MAX).into()
|
||||
}
|
||||
|
||||
fn rename_key(value: &mut serde_json::Value, from: &str, to: &str) {
|
||||
if let Some(moved) = value.as_object_mut().and_then(|object| object.remove(from)) {
|
||||
value[to] = moved;
|
||||
}
|
||||
}
|
||||
|
||||
let mut value = serde_json::to_value(target)?;
|
||||
value["healthCheckDuration"] = go_duration_nanos(target.health_check_duration);
|
||||
value["totalDowntime"] = go_duration_nanos(target.total_downtime);
|
||||
@@ -402,11 +393,6 @@ fn remote_target_admin_json(target: &BucketTarget) -> Result<serde_json::Value,
|
||||
"avg": go_duration_nanos(target.latency.avg),
|
||||
"max": go_duration_nanos(target.latency.max),
|
||||
});
|
||||
rename_key(&mut value, "bandwidth_limit", "bandwidthlimit");
|
||||
rename_key(&mut value, "storage_class", "storageclass");
|
||||
rename_key(&mut value, "reset_id", "resetID");
|
||||
rename_key(&mut value, "deployment_id", "deploymentID");
|
||||
rename_key(&mut value["credentials"], "session_token", "sessionToken");
|
||||
Ok(value)
|
||||
}
|
||||
|
||||
@@ -1490,7 +1476,7 @@ mod tests {
|
||||
parse_remote_target_update_ops, render_mrf_backlog, render_replication_diff, unique_replication_peers,
|
||||
validate_remote_target_tls_settings,
|
||||
};
|
||||
use crate::admin::storage_api::bucket::target::{BucketTarget, Credentials as TargetCredentials, LatencyStat};
|
||||
use crate::admin::storage_api::bucket::target::{BucketTarget, LatencyStat};
|
||||
use crate::admin::storage_api::replication::{BucketStats, DurableMrfBacklog, MrfOpKind, MrfReplicateEntry};
|
||||
use http::Uri;
|
||||
|
||||
@@ -2286,129 +2272,6 @@ mod tests {
|
||||
assert_eq!(persisted["latency"]["max"], 250);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn list_remote_targets_response_uses_madmin_key_names() {
|
||||
// madmin-go v3.0.109 BucketTarget JSON tags are `bandwidthlimit`,
|
||||
// `storageclass`, `resetID`, `deploymentID`, and
|
||||
// `credentials.sessionToken` (backlog#1951); the persisted snake_case
|
||||
// keys decode to zero values in mc, blanking the bandwidth and
|
||||
// reset-id columns of `mc replicate ls`.
|
||||
let target = BucketTarget {
|
||||
endpoint: "192.168.1.10:9000".to_string(),
|
||||
target_bucket: "target".to_string(),
|
||||
credentials: Some(TargetCredentials {
|
||||
access_key: "access".to_string(),
|
||||
secret_key: String::new(),
|
||||
session_token: Some("session-token".to_string()),
|
||||
expiration: None,
|
||||
}),
|
||||
bandwidth_limit: 107_374_182_400,
|
||||
storage_class: "STANDARD".to_string(),
|
||||
reset_id: "reset-123".to_string(),
|
||||
deployment_id: "deploy-456".to_string(),
|
||||
..Default::default()
|
||||
};
|
||||
|
||||
let value = super::remote_target_admin_json(&target).expect("admin response should serialize");
|
||||
|
||||
assert_eq!(value["bandwidthlimit"], 107_374_182_400i64);
|
||||
assert_eq!(value["storageclass"], "STANDARD");
|
||||
assert_eq!(value["resetID"], "reset-123");
|
||||
assert_eq!(value["deploymentID"], "deploy-456");
|
||||
assert_eq!(value["credentials"]["sessionToken"], "session-token");
|
||||
// The madmin keys replace the snake_case ones rather than duplicating
|
||||
// them next to each other.
|
||||
for stale in ["bandwidth_limit", "bandwidth", "storage_class", "reset_id", "deployment_id"] {
|
||||
assert!(value.get(stale).is_none(), "admin response must not carry `{stale}`");
|
||||
}
|
||||
assert!(value["credentials"].get("session_token").is_none());
|
||||
}
|
||||
|
||||
/// Decode-side mirror of madmin-go v3.0.109 `BucketTarget`/`Credentials`
|
||||
/// (`bucket-targets.go`): the exact `json:"..."` tags mc's `encoding/json`
|
||||
/// looks fields up under. Unknown keys are ignored like Go does, and a
|
||||
/// missing key leaves the Go zero value, which is exactly how a misnamed
|
||||
/// key turns into a blank column in `mc replicate ls`.
|
||||
#[derive(Debug, Default, serde::Deserialize)]
|
||||
#[serde(default)]
|
||||
struct MadminBucketTarget {
|
||||
sourcebucket: String,
|
||||
endpoint: String,
|
||||
credentials: Option<MadminCredentials>,
|
||||
targetbucket: String,
|
||||
arn: String,
|
||||
bandwidthlimit: i64,
|
||||
#[serde(rename = "replicationSync")]
|
||||
replication_sync: bool,
|
||||
storageclass: String,
|
||||
#[serde(rename = "healthCheckDuration")]
|
||||
health_check_duration: i64,
|
||||
#[serde(rename = "resetID")]
|
||||
reset_id: String,
|
||||
#[serde(rename = "totalDowntime")]
|
||||
total_downtime: i64,
|
||||
#[serde(rename = "deploymentID")]
|
||||
deployment_id: String,
|
||||
}
|
||||
|
||||
#[derive(Debug, Default, serde::Deserialize)]
|
||||
#[serde(default)]
|
||||
struct MadminCredentials {
|
||||
#[serde(rename = "accessKey")]
|
||||
access_key: String,
|
||||
#[serde(rename = "secretKey")]
|
||||
secret_key: String,
|
||||
#[serde(rename = "sessionToken")]
|
||||
session_token: String,
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn list_remote_targets_response_decodes_through_madmin_tags() {
|
||||
// Regression for the review on backlog#1951: the response must decode
|
||||
// a nonzero bandwidth limit through madmin's `bandwidthlimit` tag (not
|
||||
// `bandwidth`, which Go would silently drop as an unknown key).
|
||||
let target = BucketTarget {
|
||||
source_bucket: "src".to_string(),
|
||||
endpoint: "192.168.1.10:9000".to_string(),
|
||||
target_bucket: "target".to_string(),
|
||||
arn: "arn:rustfs:replication:us-east-1:dep:target".to_string(),
|
||||
credentials: Some(TargetCredentials {
|
||||
access_key: "access".to_string(),
|
||||
secret_key: String::new(),
|
||||
session_token: Some("session-token".to_string()),
|
||||
expiration: None,
|
||||
}),
|
||||
bandwidth_limit: 1_073_741_824,
|
||||
replication_sync: true,
|
||||
storage_class: "STANDARD".to_string(),
|
||||
health_check_duration: std::time::Duration::from_secs(60),
|
||||
reset_id: "reset-123".to_string(),
|
||||
total_downtime: std::time::Duration::from_secs(90),
|
||||
deployment_id: "deploy-456".to_string(),
|
||||
..Default::default()
|
||||
};
|
||||
|
||||
let wire = serde_json::to_string(&super::remote_target_admin_json(&target).expect("admin response should serialize"))
|
||||
.expect("admin response should encode");
|
||||
let decoded: MadminBucketTarget = serde_json::from_str(&wire).expect("madmin-shaped decode must succeed");
|
||||
|
||||
assert_eq!(decoded.bandwidthlimit, 1_073_741_824, "mc must see the nonzero bandwidth limit");
|
||||
assert_eq!(decoded.sourcebucket, "src");
|
||||
assert_eq!(decoded.endpoint, "192.168.1.10:9000");
|
||||
assert_eq!(decoded.targetbucket, "target");
|
||||
assert_eq!(decoded.arn, "arn:rustfs:replication:us-east-1:dep:target");
|
||||
assert!(decoded.replication_sync);
|
||||
assert_eq!(decoded.storageclass, "STANDARD");
|
||||
assert_eq!(decoded.health_check_duration, 60_000_000_000);
|
||||
assert_eq!(decoded.reset_id, "reset-123");
|
||||
assert_eq!(decoded.total_downtime, 90_000_000_000);
|
||||
assert_eq!(decoded.deployment_id, "deploy-456");
|
||||
let credentials = decoded.credentials.expect("credentials must decode");
|
||||
assert_eq!(credentials.access_key, "access");
|
||||
assert_eq!(credentials.secret_key, "");
|
||||
assert_eq!(credentials.session_token, "session-token");
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn remote_target_admin_json_latency_round_trips_through_go_duration() {
|
||||
// Round trip: a madmin reader decodes the latency values as Go
|
||||
|
||||
@@ -41,7 +41,7 @@ use crate::admin::storage_api::config::save_admin_config;
|
||||
use crate::admin::storage_api::contract::bucket::{
|
||||
BucketOperations, BucketOptions, DeleteBucketOptions, MakeBucketOptions, SRBucketDeleteOp,
|
||||
};
|
||||
use crate::admin::storage_api::error::{Error as StorageError, is_err_bucket_not_found};
|
||||
use crate::admin::storage_api::error::Error as StorageError;
|
||||
use crate::admin::storage_api::runtime::ECStore;
|
||||
use crate::admin::utils::{encode_compatible_admin_payload, read_compatible_admin_body};
|
||||
use crate::auth::constant_time_eq;
|
||||
@@ -55,7 +55,6 @@ use crate::storage::storage_api::{
|
||||
use base64::Engine;
|
||||
use base64::engine::general_purpose::STANDARD as BASE64_STANDARD;
|
||||
use base64::engine::general_purpose::URL_SAFE_NO_PAD;
|
||||
use futures::StreamExt;
|
||||
use hmac::{Hmac, Mac};
|
||||
use http::header::{CONTENT_TYPE, HOST};
|
||||
use http::{HeaderMap, HeaderValue, Uri};
|
||||
@@ -2097,18 +2096,6 @@ async fn remote_add_preflight_info(site: &PeerSite) -> S3Result<SiteReplicationA
|
||||
format!("invalid site replication metainfo from `{}`: {e}", site.endpoint),
|
||||
)
|
||||
})?;
|
||||
if info.deployment_id.is_empty() {
|
||||
// The peer will be tracked under a locally derived fallback ID
|
||||
// (deployment_id_for_endpoint) instead of its real deployment ID.
|
||||
warn!(
|
||||
event = EVENT_ADMIN_SITE_REPLICATION_STATE,
|
||||
component = LOG_COMPONENT_ADMIN,
|
||||
subsystem = LOG_SUBSYSTEM_SITE_REPLICATION,
|
||||
result = "peer_deployment_id_missing",
|
||||
peer_endpoint = %site.endpoint,
|
||||
"admin site replication state"
|
||||
);
|
||||
}
|
||||
|
||||
let idp_body = send_peer_admin_get_request_with_client(
|
||||
&client,
|
||||
@@ -2219,30 +2206,20 @@ fn site_replication_bootstrap_token(uri: &Uri) -> Option<String> {
|
||||
query_pairs(uri).get("bootstrapToken").cloned()
|
||||
}
|
||||
|
||||
/// Query for a peer `make-with-versioning` bucket op. `versioningEnabled`
|
||||
/// always travels so the outbound query matches MinIO's site-replication
|
||||
/// make-bucket wire contract: MinIO's own create-bucket hook sends
|
||||
/// `versioningEnabled=true` on this op. RustFS's inbound handler
|
||||
/// force-enables versioning either way.
|
||||
fn make_with_versioning_bucket_op_path(bucket: &str, created_at: Option<&str>, lock_enabled: bool) -> String {
|
||||
fn bootstrap_bucket_make_op_path(bucket: &SRBucketInfo) -> String {
|
||||
let mut query = form_urlencoded::Serializer::new(String::new());
|
||||
query.append_pair("bucket", bucket);
|
||||
query.append_pair("operation", SITE_REPLICATION_BUCKET_OP_MAKE_WITH_VERSIONING);
|
||||
query.append_pair("versioningEnabled", "true");
|
||||
if let Some(created_at) = created_at {
|
||||
query.append_pair("createdAt", created_at);
|
||||
query.append_pair("bucket", &bucket.bucket);
|
||||
query.append_pair("operation", "make-with-versioning");
|
||||
if let Some(created_at) = bucket
|
||||
.created_at
|
||||
.and_then(|value| value.format(&time::format_description::well_known::Rfc3339).ok())
|
||||
{
|
||||
query.append_pair("createdAt", &created_at);
|
||||
}
|
||||
if lock_enabled {
|
||||
if bucket.object_lock_config.is_some() {
|
||||
query.append_pair("lockEnabled", "true");
|
||||
}
|
||||
format!("{SITE_REPLICATION_PEER_BUCKET_OPS_PATH}?{}", query.finish())
|
||||
}
|
||||
|
||||
fn bootstrap_bucket_make_op_path(bucket: &SRBucketInfo) -> String {
|
||||
let created_at = bucket
|
||||
.created_at
|
||||
.and_then(|value| value.format(&time::format_description::well_known::Rfc3339).ok());
|
||||
make_with_versioning_bucket_op_path(&bucket.bucket, created_at.as_deref(), bucket.object_lock_config.is_some())
|
||||
format!("/rustfs/admin/v3/site-replication/peer/bucket-ops?{}", query.finish())
|
||||
}
|
||||
|
||||
fn bootstrap_bucket_meta_item(bucket: &SRBucketInfo, item_type: &str, updated_at: Option<OffsetDateTime>) -> SRBucketMeta {
|
||||
@@ -4269,7 +4246,16 @@ async fn broadcast_site_replication_make_bucket(
|
||||
.format(&time::format_description::well_known::Rfc3339)
|
||||
.unwrap_or_default();
|
||||
|
||||
let path = make_with_versioning_bucket_op_path(bucket, Some(&created_at), lock_enabled);
|
||||
let path = {
|
||||
let mut query = form_urlencoded::Serializer::new(String::new());
|
||||
query.append_pair("bucket", bucket);
|
||||
query.append_pair("operation", "make-with-versioning");
|
||||
query.append_pair("createdAt", &created_at);
|
||||
if lock_enabled {
|
||||
query.append_pair("lockEnabled", "true");
|
||||
}
|
||||
format!("/rustfs/admin/v3/site-replication/peer/bucket-ops?{}", query.finish())
|
||||
};
|
||||
let path = if let Some(token) = bootstrap_token {
|
||||
with_site_replication_bootstrap_token(&path, token)
|
||||
} else {
|
||||
@@ -10220,25 +10206,13 @@ impl Operation for SiteReplicationStatusHandler {
|
||||
}
|
||||
}
|
||||
|
||||
/// `POST /v3/site-replication/devnull` — peer link-check upload drain.
|
||||
/// MinIO streams multi-megabyte probe bodies here during site netperf link
|
||||
/// checks and expects an unbounded discard (its handler copies to io.Discard);
|
||||
/// buffering through the 1MB admin body cap turned any larger probe into a
|
||||
/// 400 and a false link failure. Stream and discard instead — no size cap.
|
||||
async fn drain_site_replication_devnull(mut input: Body) -> S3Result<()> {
|
||||
while let Some(chunk) = input.next().await {
|
||||
chunk.map_err(|e| s3_error!(InvalidRequest, "failed to read devnull stream: {}", e))?;
|
||||
}
|
||||
Ok(())
|
||||
}
|
||||
|
||||
pub struct SiteReplicationDevNullHandler {}
|
||||
|
||||
#[async_trait::async_trait]
|
||||
impl Operation for SiteReplicationDevNullHandler {
|
||||
async fn call(&self, req: S3Request<Body>, _params: Params<'_, '_>) -> S3Result<S3Response<(StatusCode, Body)>> {
|
||||
validate_site_replication_admin_request(&req, AdminAction::SiteReplicationOperationAction).await?;
|
||||
drain_site_replication_devnull(req.input).await?;
|
||||
let _ = read_plain_admin_body(req.input).await?;
|
||||
Ok(empty_response(StatusCode::NO_CONTENT))
|
||||
}
|
||||
}
|
||||
@@ -10497,19 +10471,6 @@ impl Operation for SRPeerJoinHandler {
|
||||
}
|
||||
}
|
||||
|
||||
/// Outcome of a peer-driven `purge-deleted-bucket` replay. A bucket that is
|
||||
/// already gone means the purge raced an earlier replay or a local delete —
|
||||
/// that is success — but any other failure must reach the sender like the
|
||||
/// sibling delete branches do: swallowing it answered 200 while the bucket
|
||||
/// survived on this site.
|
||||
fn purge_deleted_bucket_result(result: Result<(), StorageError>) -> S3Result<()> {
|
||||
match result {
|
||||
Ok(()) => Ok(()),
|
||||
Err(err) if is_err_bucket_not_found(&err) => Ok(()),
|
||||
Err(err) => Err(ApiError::from(err).into()),
|
||||
}
|
||||
}
|
||||
|
||||
pub struct SRPeerBucketOpsHandler {}
|
||||
|
||||
#[async_trait::async_trait]
|
||||
@@ -10609,18 +10570,16 @@ impl Operation for SRPeerBucketOpsHandler {
|
||||
.map_err(ApiError::from)?;
|
||||
}
|
||||
"purge-deleted-bucket" => {
|
||||
purge_deleted_bucket_result(
|
||||
store
|
||||
.delete_bucket(
|
||||
&bucket,
|
||||
&DeleteBucketOptions {
|
||||
force: true,
|
||||
srdelete_op: SRBucketDeleteOp::Purge,
|
||||
..Default::default()
|
||||
},
|
||||
)
|
||||
.await,
|
||||
)?;
|
||||
let _ = store
|
||||
.delete_bucket(
|
||||
&bucket,
|
||||
&DeleteBucketOptions {
|
||||
force: true,
|
||||
srdelete_op: SRBucketDeleteOp::Purge,
|
||||
..Default::default()
|
||||
},
|
||||
)
|
||||
.await;
|
||||
}
|
||||
_ => return Err(s3_error!(InvalidRequest, "unsupported site replication bucket operation")),
|
||||
}
|
||||
@@ -13966,54 +13925,6 @@ mod tests {
|
||||
assert!(!query_flag(&uri, "missing"));
|
||||
}
|
||||
|
||||
/// A5 red-light: a `purge-deleted-bucket` replay must report success when
|
||||
/// the bucket is already gone, and must propagate every other failure —
|
||||
/// the swallowed error answered 200 while the bucket survived.
|
||||
#[test]
|
||||
fn test_purge_deleted_bucket_result_tolerates_only_missing_bucket() {
|
||||
assert!(purge_deleted_bucket_result(Ok(())).is_ok());
|
||||
assert!(purge_deleted_bucket_result(Err(StorageError::BucketNotFound("photos".to_string()))).is_ok());
|
||||
assert!(purge_deleted_bucket_result(Err(StorageError::VolumeNotFound)).is_ok());
|
||||
let err = purge_deleted_bucket_result(Err(StorageError::StorageFull))
|
||||
.expect_err("non-not-found delete failures must propagate");
|
||||
assert_ne!(*err.code(), S3ErrorCode::NoSuchBucket);
|
||||
}
|
||||
|
||||
/// C5 red-light: the site-replication devnull drain must accept bodies
|
||||
/// beyond the 1MB admin body cap — MinIO's link check streams large
|
||||
/// probe bodies and treats a 400 as a broken link.
|
||||
#[tokio::test]
|
||||
async fn test_site_replication_devnull_drains_body_beyond_admin_cap() {
|
||||
let body = Body::from(vec![0u8; MAX_ADMIN_REQUEST_BODY_SIZE + 1]);
|
||||
drain_site_replication_devnull(body)
|
||||
.await
|
||||
.expect("devnull must drain bodies larger than the admin body cap");
|
||||
}
|
||||
|
||||
/// A3 red-light: `versioningEnabled` must travel on every outbound
|
||||
/// make-with-versioning bucket op so the query matches MinIO's
|
||||
/// site-replication make-bucket wire contract (MinIO's own hook sends
|
||||
/// `versioningEnabled=true` on this op).
|
||||
#[test]
|
||||
fn test_make_with_versioning_op_paths_send_versioning_enabled() {
|
||||
let bucket = SRBucketInfo {
|
||||
bucket: "photos".to_string(),
|
||||
created_at: Some(OffsetDateTime::UNIX_EPOCH),
|
||||
object_lock_config: Some(BASE64_STANDARD.encode("<ObjectLockConfiguration/>")),
|
||||
..Default::default()
|
||||
};
|
||||
let bootstrap = bootstrap_bucket_make_op_path(&bucket);
|
||||
assert!(bootstrap.contains("operation=make-with-versioning"), "{bootstrap}");
|
||||
assert!(bootstrap.contains("versioningEnabled=true"), "{bootstrap}");
|
||||
assert!(bootstrap.contains("createdAt="), "{bootstrap}");
|
||||
assert!(bootstrap.contains("lockEnabled=true"), "{bootstrap}");
|
||||
|
||||
// The broadcast path (create-bucket hook) shares the same builder.
|
||||
let broadcast = make_with_versioning_bucket_op_path("photos", Some("1970-01-01T00:00:00Z"), false);
|
||||
assert!(broadcast.contains("versioningEnabled=true"), "{broadcast}");
|
||||
assert!(!broadcast.contains("lockEnabled"), "{broadcast}");
|
||||
}
|
||||
|
||||
#[tokio::test]
|
||||
#[serial]
|
||||
async fn test_add_bootstrap_scope_only_allows_expected_bucket_setup_until_guard_drops() {
|
||||
|
||||
@@ -13,9 +13,9 @@
|
||||
// limitations under the License.
|
||||
|
||||
use rustfs_madmin::{PeerInfo, SyncStatus};
|
||||
use std::collections::BTreeMap;
|
||||
use std::collections::{BTreeMap, hash_map::DefaultHasher};
|
||||
use std::hash::{Hash, Hasher};
|
||||
use url::Url;
|
||||
use uuid::Uuid;
|
||||
|
||||
fn has_http_scheme(endpoint: &str) -> bool {
|
||||
endpoint.get(..7).is_some_and(|prefix| prefix.eq_ignore_ascii_case("http://"))
|
||||
@@ -66,12 +66,10 @@ pub fn site_identity_key(endpoint: &str) -> String {
|
||||
.unwrap_or_else(|| trimmed.to_ascii_lowercase())
|
||||
}
|
||||
|
||||
/// Fallback deployment ID for a peer that reported none. UUIDv5 over the
|
||||
/// canonical endpoint: the ID is persisted in site-replication state and
|
||||
/// broadcast to peers, so it must be identical across Rust toolchains
|
||||
/// (`DefaultHasher` is not) and across spellings of the same endpoint.
|
||||
pub fn deployment_id_for_endpoint(endpoint: &str) -> String {
|
||||
Uuid::new_v5(&Uuid::NAMESPACE_URL, canonical_endpoint(endpoint).as_bytes()).to_string()
|
||||
let mut hasher = DefaultHasher::new();
|
||||
endpoint.hash(&mut hasher);
|
||||
format!("{:016x}", hasher.finish())
|
||||
}
|
||||
|
||||
pub fn same_identity_endpoint(left: &str, right: &str) -> bool {
|
||||
@@ -176,23 +174,6 @@ mod tests {
|
||||
}
|
||||
}
|
||||
|
||||
/// B8 red-light: the fallback deployment ID must be a toolchain-stable
|
||||
/// UUIDv5 over the canonical endpoint — `DefaultHasher` output is not
|
||||
/// guaranteed stable across Rust releases, yet the ID is persisted in
|
||||
/// site-replication state and broadcast to peers.
|
||||
#[test]
|
||||
fn deployment_id_for_endpoint_is_stable_uuid_v5_over_canonical_endpoint() {
|
||||
let endpoint = "https://node-a.example.com:9000";
|
||||
let id = deployment_id_for_endpoint(endpoint);
|
||||
let parsed = uuid::Uuid::parse_str(&id).expect("fallback deployment ID must be a UUID");
|
||||
assert_eq!(parsed.get_version_num(), 5, "fallback deployment ID must be UUIDv5");
|
||||
// Deterministic for the same endpoint and for spelling variants that
|
||||
// share a canonical form; distinct endpoints stay distinct.
|
||||
assert_eq!(id, deployment_id_for_endpoint(endpoint));
|
||||
assert_eq!(id, deployment_id_for_endpoint(" HTTPS://Node-A.Example.Com:9000/ "));
|
||||
assert_ne!(id, deployment_id_for_endpoint("https://node-b.example.com:9000"));
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn canonical_endpoint_accepts_case_insensitive_scheme() {
|
||||
assert_eq!(
|
||||
|
||||
@@ -51,7 +51,7 @@ mod ecstore_disk {
|
||||
}
|
||||
|
||||
mod ecstore_error {
|
||||
pub(crate) use crate::storage::storage_api::ecstore_error::{StorageError, is_err_bucket_not_found};
|
||||
pub(crate) use crate::storage::storage_api::ecstore_error::StorageError;
|
||||
}
|
||||
|
||||
#[allow(unused_imports)]
|
||||
@@ -919,7 +919,6 @@ pub(crate) mod contract {
|
||||
}
|
||||
|
||||
pub(crate) mod error {
|
||||
pub(crate) use super::ecstore_error::is_err_bucket_not_found;
|
||||
pub(crate) use super::{Error, StorageError};
|
||||
}
|
||||
|
||||
|
||||
@@ -369,8 +369,14 @@ pub fn allocator_reclaim_controller_snapshot(ctx: &CancellationToken) -> Allocat
|
||||
}
|
||||
|
||||
#[cfg(not(target_os = "windows"))]
|
||||
#[allow(unsafe_code)]
|
||||
fn collect_allocator_memory(force: bool) -> Result<(), String> {
|
||||
rustfs_mimalloc::MiMalloc::collect(force);
|
||||
// SAFETY: `mi_collect` is provided by the active global allocator backend
|
||||
// on this target family. It is explicitly intended to reclaim retained
|
||||
// pages/segments and does not require additional invariants from the caller.
|
||||
unsafe {
|
||||
libmimalloc_sys::mi_collect(force);
|
||||
}
|
||||
Ok(())
|
||||
}
|
||||
|
||||
|
||||
+8
-10
@@ -26,22 +26,22 @@ struct MiMallocAllocator;
|
||||
unsafe impl GlobalAlloc for MiMallocAllocator {
|
||||
unsafe fn alloc(&self, layout: Layout) -> *mut u8 {
|
||||
// SAFETY: the caller upholds GlobalAlloc's contract for layout.
|
||||
unsafe { rustfs_mimalloc::MiMalloc.alloc(layout) }
|
||||
unsafe { mimalloc::MiMalloc.alloc(layout) }
|
||||
}
|
||||
|
||||
unsafe fn alloc_zeroed(&self, layout: Layout) -> *mut u8 {
|
||||
// SAFETY: the caller upholds GlobalAlloc's contract for layout.
|
||||
unsafe { rustfs_mimalloc::MiMalloc.alloc_zeroed(layout) }
|
||||
unsafe { mimalloc::MiMalloc.alloc_zeroed(layout) }
|
||||
}
|
||||
|
||||
unsafe fn dealloc(&self, ptr: *mut u8, layout: Layout) {
|
||||
// SAFETY: ptr and layout came from this allocator and are forwarded unchanged.
|
||||
unsafe { rustfs_mimalloc::MiMalloc.dealloc(ptr, layout) }
|
||||
unsafe { mimalloc::MiMalloc.dealloc(ptr, layout) }
|
||||
}
|
||||
|
||||
unsafe fn realloc(&self, ptr: *mut u8, layout: Layout, new_size: usize) -> *mut u8 {
|
||||
// SAFETY: ptr and layout came from this allocator and are forwarded unchanged.
|
||||
unsafe { rustfs_mimalloc::MiMalloc.realloc(ptr, layout, new_size) }
|
||||
unsafe { mimalloc::MiMalloc.realloc(ptr, layout, new_size) }
|
||||
}
|
||||
}
|
||||
|
||||
@@ -51,7 +51,7 @@ static GLOBAL: hotpath::CountingAllocator<MiMallocAllocator> = hotpath::Counting
|
||||
|
||||
#[cfg(not(all(feature = "hotpath", feature = "hotpath-alloc")))]
|
||||
#[global_allocator]
|
||||
static GLOBAL: rustfs_mimalloc::MiMalloc = rustfs_mimalloc::MiMalloc;
|
||||
static GLOBAL: mimalloc::MiMalloc = mimalloc::MiMalloc;
|
||||
|
||||
fn main() {
|
||||
let _hotpath_guard = hotpath::HotpathGuardBuilder::new("main").build();
|
||||
@@ -71,9 +71,8 @@ mod tests {
|
||||
allocation.extend_from_slice(&[7_u8; 64]);
|
||||
|
||||
assert_eq!(allocation.len(), 64);
|
||||
let heap = rustfs_mimalloc::heap::Heap::main();
|
||||
// SAFETY: the live Vec pointer is valid to inspect for heap ownership.
|
||||
assert!(unsafe { heap.contains(allocation.as_ptr()) });
|
||||
assert!(unsafe { libmimalloc_sys::mi_is_in_heap_region(allocation.as_ptr().cast()) });
|
||||
}
|
||||
|
||||
#[test]
|
||||
@@ -86,13 +85,12 @@ mod tests {
|
||||
let layout = Layout::from_size_align(32, 8).expect("valid test allocation layout");
|
||||
let grown_layout = Layout::from_size_align(64, 8).expect("valid grown test allocation layout");
|
||||
let allocator = super::MiMallocAllocator;
|
||||
let heap = rustfs_mimalloc::heap::Heap::main();
|
||||
|
||||
// SAFETY: The pointer is checked for null before use and later released
|
||||
// through the same allocator with the corresponding layout.
|
||||
let ptr = unsafe { allocator.alloc_zeroed(layout) };
|
||||
assert!(!ptr.is_null());
|
||||
assert!(unsafe { heap.contains(ptr) });
|
||||
assert!(unsafe { libmimalloc_sys::mi_is_in_heap_region(ptr.cast()) });
|
||||
assert!(unsafe { std::slice::from_raw_parts(ptr, 32).iter().all(|byte| *byte == 0) });
|
||||
|
||||
// SAFETY: `ptr` was allocated by `allocator` with `layout`; on failure
|
||||
@@ -104,7 +102,7 @@ mod tests {
|
||||
panic!("mimalloc realloc failed in allocator smoke test");
|
||||
}
|
||||
|
||||
assert!(unsafe { heap.contains(grown_ptr) });
|
||||
assert!(unsafe { libmimalloc_sys::mi_is_in_heap_region(grown_ptr.cast()) });
|
||||
// SAFETY: `grown_ptr` was reallocated by `allocator` and is released
|
||||
// with the matching grown layout.
|
||||
unsafe { allocator.dealloc(grown_ptr, grown_layout) };
|
||||
|
||||
@@ -17,7 +17,10 @@ use rustfs_io_metrics::{
|
||||
record_cpu_usage, record_memory_usage, record_process_memory_split,
|
||||
};
|
||||
use serde::Serialize;
|
||||
#[cfg(any(test, not(target_os = "windows")))]
|
||||
use serde_json::Value;
|
||||
#[cfg(not(target_os = "windows"))]
|
||||
use std::ffi::CStr;
|
||||
use std::path::Path;
|
||||
use std::sync::{Arc, Mutex, OnceLock};
|
||||
use std::time::Duration;
|
||||
@@ -228,18 +231,7 @@ fn read_cgroup_memory_snapshot() -> Option<CgroupMemorySnapshot> {
|
||||
read_cgroup_v2().or_else(read_cgroup_v1)
|
||||
}
|
||||
|
||||
fn read_allocator_memory_snapshot() -> Option<AllocatorMemorySnapshot> {
|
||||
let json = rustfs_mimalloc::MiMalloc::stats_json();
|
||||
if json.is_empty() {
|
||||
return None;
|
||||
}
|
||||
let observation = parse_mimalloc_stats_json(&json)?;
|
||||
Some(AllocatorMemorySnapshot {
|
||||
backend: crate::allocator_reclaim::allocator_backend(),
|
||||
observation,
|
||||
})
|
||||
}
|
||||
|
||||
#[cfg(any(test, not(target_os = "windows")))]
|
||||
fn numeric_json_value(value: &Value) -> Option<u64> {
|
||||
match value {
|
||||
Value::Number(number) => number
|
||||
@@ -250,6 +242,7 @@ fn numeric_json_value(value: &Value) -> Option<u64> {
|
||||
}
|
||||
}
|
||||
|
||||
#[cfg(any(test, not(target_os = "windows")))]
|
||||
fn numeric_json_field(value: &Value, field: &str) -> Option<u64> {
|
||||
match value {
|
||||
Value::Object(fields) => fields
|
||||
@@ -261,6 +254,7 @@ fn numeric_json_field(value: &Value, field: &str) -> Option<u64> {
|
||||
}
|
||||
}
|
||||
|
||||
#[cfg(any(test, not(target_os = "windows")))]
|
||||
fn mimalloc_stat_field(value: &Value, metric: &str, field: &str) -> Option<u64> {
|
||||
match value {
|
||||
Value::Object(fields) => {
|
||||
@@ -277,10 +271,12 @@ fn mimalloc_stat_field(value: &Value, metric: &str, field: &str) -> Option<u64>
|
||||
}
|
||||
}
|
||||
|
||||
#[cfg(any(test, not(target_os = "windows")))]
|
||||
fn mimalloc_stat_current(value: &Value, metric: &str) -> Option<u64> {
|
||||
mimalloc_stat_field(value, metric, "current")
|
||||
}
|
||||
|
||||
#[cfg(any(test, not(target_os = "windows")))]
|
||||
fn mimalloc_stat_sum(value: &Value, metrics: &[&str], field: &str) -> Option<u64> {
|
||||
metrics
|
||||
.iter()
|
||||
@@ -289,6 +285,7 @@ fn mimalloc_stat_sum(value: &Value, metrics: &[&str], field: &str) -> Option<u64
|
||||
.filter(|value| *value > 0)
|
||||
}
|
||||
|
||||
#[cfg(any(test, not(target_os = "windows")))]
|
||||
fn parse_mimalloc_stats_json(stats_json: &str) -> Option<AllocatorMemoryObservation> {
|
||||
let value = serde_json::from_str::<Value>(stats_json).ok()?;
|
||||
let malloc_metrics = ["malloc_normal", "malloc_huge"];
|
||||
@@ -315,6 +312,33 @@ fn parse_mimalloc_stats_json(stats_json: &str) -> Option<AllocatorMemoryObservat
|
||||
}
|
||||
}
|
||||
|
||||
#[cfg(not(target_os = "windows"))]
|
||||
#[allow(unsafe_code)]
|
||||
fn read_allocator_memory_snapshot() -> Option<AllocatorMemorySnapshot> {
|
||||
// SAFETY: `mi_stats_get_json` returns a null-terminated JSON buffer owned by
|
||||
// mimalloc when called with a null input buffer. The mimalloc API requires
|
||||
// freeing that buffer with `mi_free`; parsing finishes before the buffer is freed.
|
||||
let observation = unsafe {
|
||||
let stats_ptr = libmimalloc_sys::mi_stats_get_json(0, std::ptr::null_mut());
|
||||
if stats_ptr.is_null() {
|
||||
return None;
|
||||
}
|
||||
|
||||
let observation = CStr::from_ptr(stats_ptr).to_str().ok().and_then(parse_mimalloc_stats_json);
|
||||
libmimalloc_sys::mi_free(stats_ptr.cast());
|
||||
observation?
|
||||
};
|
||||
Some(AllocatorMemorySnapshot {
|
||||
backend: crate::allocator_reclaim::allocator_backend(),
|
||||
observation,
|
||||
})
|
||||
}
|
||||
|
||||
#[cfg(target_os = "windows")]
|
||||
fn read_allocator_memory_snapshot() -> Option<AllocatorMemorySnapshot> {
|
||||
None
|
||||
}
|
||||
|
||||
fn configured_memory_observability_interval_secs() -> u64 {
|
||||
rustfs_utils::get_env_u64(ENV_MEMORY_OBSERVABILITY_INTERVAL_SECS, DEFAULT_MEMORY_OBSERVABILITY_INTERVAL_SECS).max(1)
|
||||
}
|
||||
@@ -542,13 +566,6 @@ mod tests {
|
||||
assert_eq!(parse_mimalloc_stats_json(r#"{ "allocator": "unknown" }"#), None);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn read_allocator_memory_snapshot_uses_mimalloc_stats_json() {
|
||||
let snapshot = super::read_allocator_memory_snapshot();
|
||||
#[cfg(not(target_os = "windows"))]
|
||||
assert!(snapshot.is_some(), "allocator snapshot should be available on non-Windows");
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn memory_observability_snapshot_reports_disabled_when_metrics_are_disabled() {
|
||||
let snapshot = build_memory_observability_status_snapshot(false, 15, false);
|
||||
|
||||
Reference in New Issue
Block a user