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
|
1ac09383ad |
@@ -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
-22
@@ -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"
|
||||
|
||||
+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 {
|
||||
|
||||
@@ -1120,6 +1120,48 @@ fn rollback_decommission_pool_meta(pool_meta: &mut PoolMeta, previous_pool_meta:
|
||||
*pool_meta = previous_pool_meta;
|
||||
}
|
||||
|
||||
#[derive(Debug)]
|
||||
struct DecommissionCancelCommit {
|
||||
previous_start_time: Option<OffsetDateTime>,
|
||||
previous_queued: bool,
|
||||
previous_last_update: OffsetDateTime,
|
||||
canceled_pool: PoolStatus,
|
||||
}
|
||||
|
||||
fn commit_decommission_cancel(pool_meta: &mut PoolMeta, idx: usize, commit: DecommissionCancelCommit) -> Result<()> {
|
||||
let pool_count = pool_meta.pools.len();
|
||||
let Some(current) = pool_meta.pools.get(idx) else {
|
||||
return Err(invalid_decommission_pool_index_error(pool_count, idx));
|
||||
};
|
||||
// A peer reload can install the saved cancel while runtime-only fields are reconstructed.
|
||||
let cancel_already_published = commit
|
||||
.canceled_pool
|
||||
.decommission
|
||||
.as_ref()
|
||||
.is_some_and(|info| info.canceled && !info.complete && !info.failed && info.start_time.is_none())
|
||||
&& PersistedPoolStatus::from(current) == PersistedPoolStatus::from(&commit.canceled_pool);
|
||||
if cancel_already_published {
|
||||
return Ok(());
|
||||
}
|
||||
|
||||
let matches_generation = current.id == commit.canceled_pool.id
|
||||
&& current.cmd_line == commit.canceled_pool.cmd_line
|
||||
&& current.decommission.as_ref().is_some_and(|info| {
|
||||
info.start_time == commit.previous_start_time
|
||||
&& info.queued == commit.previous_queued
|
||||
&& is_decommission_active(info.complete, info.failed, info.canceled)
|
||||
&& (commit.previous_start_time.is_some() || current.last_update == commit.previous_last_update)
|
||||
});
|
||||
if !matches_generation {
|
||||
return Err(Error::other(format!(
|
||||
"failed to publish decommission cancel for pool {idx}: operation generation changed"
|
||||
)));
|
||||
}
|
||||
|
||||
pool_meta.pools[idx] = commit.canceled_pool;
|
||||
Ok(())
|
||||
}
|
||||
|
||||
fn rollback_start_decommission_pool_meta(pool_meta: &mut PoolMeta, previous_pool_meta: PoolMeta) {
|
||||
rollback_decommission_pool_meta(pool_meta, previous_pool_meta);
|
||||
}
|
||||
@@ -1570,7 +1612,7 @@ struct PersistedPoolMeta {
|
||||
pub pools: Vec<PersistedPoolStatus>,
|
||||
}
|
||||
|
||||
#[derive(Debug, Clone, Serialize, Deserialize)]
|
||||
#[derive(Debug, Clone, PartialEq, Serialize, Deserialize)]
|
||||
#[serde(deny_unknown_fields)]
|
||||
struct PersistedPoolStatus {
|
||||
#[serde(rename = "id")]
|
||||
@@ -1583,7 +1625,7 @@ struct PersistedPoolStatus {
|
||||
pub decommission: Option<PersistedPoolDecommissionInfo>,
|
||||
}
|
||||
|
||||
#[derive(Debug, Clone, Default, Serialize, Deserialize)]
|
||||
#[derive(Debug, Clone, Default, PartialEq, Serialize, Deserialize)]
|
||||
#[serde(deny_unknown_fields)]
|
||||
struct PersistedPoolDecommissionInfo {
|
||||
#[serde(rename = "startTime", with = "time::serde::rfc3339::option")]
|
||||
@@ -3004,14 +3046,156 @@ impl ECStore {
|
||||
}
|
||||
|
||||
#[tracing::instrument(skip(self))]
|
||||
pub async fn decommission_cancel(&self, idx: usize) -> Result<()> {
|
||||
pub async fn decommission_cancel(self: &Arc<Self>, idx: usize) -> Result<()> {
|
||||
self.decommission_cancel_with_owner(idx, None).await
|
||||
}
|
||||
|
||||
async fn decommission_cancel_for_operation(&self, idx: usize, owner: &DecommissionCanceler) -> Result<()> {
|
||||
async fn decommission_cancel_for_operation(self: &Arc<Self>, idx: usize, owner: &DecommissionCanceler) -> Result<()> {
|
||||
self.decommission_cancel_with_owner(idx, Some(owner)).await
|
||||
}
|
||||
|
||||
async fn decommission_cancel_with_owner_and_save<Save, SaveFuture>(
|
||||
self: &Arc<Self>,
|
||||
idx: usize,
|
||||
owner: Option<&DecommissionCanceler>,
|
||||
save_pool_meta: Save,
|
||||
) -> Result<()>
|
||||
where
|
||||
Save: FnOnce(PoolMeta) -> SaveFuture + Send + 'static,
|
||||
SaveFuture: Future<Output = Result<()>> + Send + 'static,
|
||||
{
|
||||
let store = self.clone();
|
||||
let owner = owner.cloned();
|
||||
// Dropping the RPC waiter detaches this task; the transaction retains
|
||||
// the store and exact owner until persistence is resolved.
|
||||
tokio::spawn(async move { store.decommission_cancel_transaction(idx, owner, save_pool_meta).await })
|
||||
.await
|
||||
.map_err(|err| Error::other(format!("decommission cancel transaction task join error: {err}")))?
|
||||
}
|
||||
|
||||
async fn decommission_cancel_transaction<Save, SaveFuture>(
|
||||
&self,
|
||||
idx: usize,
|
||||
owner: Option<DecommissionCanceler>,
|
||||
save_pool_meta: Save,
|
||||
) -> Result<()>
|
||||
where
|
||||
Save: FnOnce(PoolMeta) -> SaveFuture,
|
||||
SaveFuture: Future<Output = Result<()>>,
|
||||
{
|
||||
let owner = owner.as_ref();
|
||||
ensure_decommission_terminal_operation_supported(self.single_pool(), "cancel decommission")?;
|
||||
let _start_guard = self.start_gate.lock().await;
|
||||
let operation_gate = self.ctx.decommission_operation_gate();
|
||||
let operation_guard = operation_gate.write().await;
|
||||
let save_guard = self.pool_meta_save_gate.lock().await;
|
||||
|
||||
// Lock order: start gate, operation gate, save gate,
|
||||
// decommission_cancelers, then pool_meta. The state guards stay held
|
||||
// across persistence so publication and owner termination are
|
||||
// synchronous once the save reports success.
|
||||
let mut cancelers = self.decommission_cancelers.write().await;
|
||||
let mut pool_meta = self.pool_meta.write().await;
|
||||
let (pending, should_reload_pool_meta, already_canceled, terminal_canceler) = {
|
||||
let mut already_canceled = false;
|
||||
let (pool_present, decommission_present, terminal) = if let Some(pool) = pool_meta.pools.get(idx) {
|
||||
if let Some(info) = pool.decommission.as_ref() {
|
||||
already_canceled = info.canceled;
|
||||
(
|
||||
true,
|
||||
info.has_decommission_state(),
|
||||
should_reject_decommission_cancel_as_terminal(info.complete, info.failed),
|
||||
)
|
||||
} else {
|
||||
(true, false, false)
|
||||
}
|
||||
} else {
|
||||
(false, false, false)
|
||||
};
|
||||
|
||||
ensure_decommission_cancel_allowed(pool_present, decommission_present, terminal)?;
|
||||
let previous_pool = pool_meta
|
||||
.pools
|
||||
.get(idx)
|
||||
.cloned()
|
||||
.ok_or_else(|| invalid_decommission_pool_index_error(pool_meta.pools.len(), idx))?;
|
||||
let previous_decommission = previous_pool
|
||||
.decommission
|
||||
.as_ref()
|
||||
.ok_or_else(|| decommission_metadata_not_initialized_error("cancel decommission"))?;
|
||||
let mut snapshot = pool_meta.clone();
|
||||
let Some(changed) = update_decommission_for_operation(cancelers.as_slice(), &mut snapshot, idx, owner, |pool_meta| {
|
||||
pool_meta.decommission_cancel(idx)
|
||||
}) else {
|
||||
return Ok(());
|
||||
};
|
||||
let pending = if changed {
|
||||
let canceled_pool = snapshot
|
||||
.pools
|
||||
.get(idx)
|
||||
.cloned()
|
||||
.ok_or_else(|| invalid_decommission_pool_index_error(pool_meta.pools.len(), idx))?;
|
||||
Some((
|
||||
snapshot,
|
||||
DecommissionCancelCommit {
|
||||
previous_start_time: previous_decommission.start_time,
|
||||
previous_queued: previous_decommission.queued,
|
||||
previous_last_update: previous_pool.last_update,
|
||||
canceled_pool,
|
||||
},
|
||||
))
|
||||
} else {
|
||||
None
|
||||
};
|
||||
let terminal_canceler = if let Some(owner) = owner {
|
||||
Some(owner.clone())
|
||||
} else {
|
||||
cancelers.get(idx).and_then(Option::as_ref).cloned()
|
||||
};
|
||||
(
|
||||
pending,
|
||||
should_retry_decommission_cancel_reload(changed, already_canceled),
|
||||
already_canceled,
|
||||
terminal_canceler,
|
||||
)
|
||||
};
|
||||
let active_worker = terminal_canceler.as_ref().is_some_and(DecommissionCanceler::is_active);
|
||||
if !active_worker && !already_canceled {
|
||||
warn!(
|
||||
event = EVENT_DECOMMISSION_STATE,
|
||||
component = LOG_COMPONENT_ECSTORE,
|
||||
subsystem = LOG_SUBSYSTEM_POOLS,
|
||||
pool_index = idx,
|
||||
state = "cancel_skipped",
|
||||
reason = "no_active_canceler",
|
||||
"Decommission cancel skipped"
|
||||
);
|
||||
}
|
||||
|
||||
let commit_result = if let Some((snapshot, commit)) = pending {
|
||||
save_pool_meta(snapshot).await?;
|
||||
commit_decommission_cancel(&mut pool_meta, idx, commit)
|
||||
} else {
|
||||
Ok(())
|
||||
};
|
||||
|
||||
if let Some(canceler) = terminal_canceler.as_ref() {
|
||||
take_and_cancel_decommission_canceler_for_operation(cancelers.as_mut_slice(), idx, canceler);
|
||||
}
|
||||
commit_result?;
|
||||
drop(pool_meta);
|
||||
drop(cancelers);
|
||||
drop(save_guard);
|
||||
drop(operation_guard);
|
||||
|
||||
if should_reload_pool_meta && let Some(notification_sys) = runtime_sources::notification_sys() {
|
||||
let stage = format!("decommission_cancel for pool {idx}");
|
||||
resolve_decommission_pool_meta_reload_result(notification_sys.reload_pool_meta().await, stage.as_str())?;
|
||||
}
|
||||
|
||||
Ok(())
|
||||
}
|
||||
|
||||
async fn release_decommission_canceler_slot(&self, idx: usize, owner: &DecommissionCanceler) {
|
||||
let mut cancelers = self.decommission_cancelers.write().await;
|
||||
take_and_cancel_decommission_canceler_for_operation(cancelers.as_mut_slice(), idx, owner);
|
||||
@@ -3039,7 +3223,11 @@ impl ECStore {
|
||||
retryable
|
||||
}
|
||||
|
||||
async fn retry_decommission_cancel_for_operation(&self, idx: usize, owner: &DecommissionCanceler) {
|
||||
async fn retry_decommission_cancel_for_operation(self: &Arc<Self>, idx: usize, owner: &DecommissionCanceler) {
|
||||
if !self.decommission_terminal_retryable_for_operation(idx, owner).await {
|
||||
return;
|
||||
}
|
||||
|
||||
let mut attempt = 0usize;
|
||||
loop {
|
||||
let Err(err) = self.decommission_cancel_for_operation(idx, owner).await else {
|
||||
@@ -3089,87 +3277,10 @@ impl ECStore {
|
||||
}
|
||||
}
|
||||
|
||||
async fn decommission_cancel_with_owner(&self, idx: usize, owner: Option<&DecommissionCanceler>) -> Result<()> {
|
||||
ensure_decommission_terminal_operation_supported(self.single_pool(), "cancel decommission")?;
|
||||
let _start_guard = self.start_gate.lock().await;
|
||||
|
||||
// Lock order: decommission_cancelers before pool_meta. Holding both makes
|
||||
// owner validation and the terminal transition one atomic operation.
|
||||
let (should_save_pool_meta, should_reload_pool_meta, already_canceled, previous_pool_meta, terminal_canceler) = {
|
||||
let cancelers = self.decommission_cancelers.read().await;
|
||||
let mut lock = self.pool_meta.write().await;
|
||||
let mut already_canceled = false;
|
||||
let (pool_present, decommission_present, terminal) = if let Some(pool) = lock.pools.get(idx) {
|
||||
if let Some(info) = pool.decommission.as_ref() {
|
||||
already_canceled = info.canceled;
|
||||
(
|
||||
true,
|
||||
info.has_decommission_state(),
|
||||
should_reject_decommission_cancel_as_terminal(info.complete, info.failed),
|
||||
)
|
||||
} else {
|
||||
(true, false, false)
|
||||
}
|
||||
} else {
|
||||
(false, false, false)
|
||||
};
|
||||
|
||||
ensure_decommission_cancel_allowed(pool_present, decommission_present, terminal)?;
|
||||
let previous_pool_meta = lock.clone();
|
||||
let Some(changed) = update_decommission_for_operation(cancelers.as_slice(), &mut lock, idx, owner, |pool_meta| {
|
||||
pool_meta.decommission_cancel(idx)
|
||||
}) else {
|
||||
return Ok(());
|
||||
};
|
||||
let terminal_canceler = if let Some(owner) = owner {
|
||||
Some(owner.clone())
|
||||
} else {
|
||||
cancelers.get(idx).and_then(Option::as_ref).cloned()
|
||||
};
|
||||
if let Some(canceler) = terminal_canceler.as_ref() {
|
||||
canceler.cancel();
|
||||
}
|
||||
(
|
||||
changed,
|
||||
should_retry_decommission_cancel_reload(changed, already_canceled),
|
||||
already_canceled,
|
||||
changed.then_some(previous_pool_meta),
|
||||
terminal_canceler,
|
||||
)
|
||||
};
|
||||
let canceled_worker = terminal_canceler.as_ref().is_some_and(DecommissionCanceler::is_active);
|
||||
if !canceled_worker && !already_canceled {
|
||||
warn!(
|
||||
event = EVENT_DECOMMISSION_STATE,
|
||||
component = LOG_COMPONENT_ECSTORE,
|
||||
subsystem = LOG_SUBSYSTEM_POOLS,
|
||||
pool_index = idx,
|
||||
state = "cancel_skipped",
|
||||
reason = "no_active_canceler",
|
||||
"Decommission cancel skipped"
|
||||
);
|
||||
}
|
||||
|
||||
self.wait_for_decommission_side_effects().await;
|
||||
|
||||
if should_save_pool_meta && let Err(err) = self.save_current_pool_meta().await {
|
||||
if let Some(previous_pool_meta) = previous_pool_meta {
|
||||
let mut pool_meta = self.pool_meta.write().await;
|
||||
rollback_decommission_pool_meta(&mut pool_meta, previous_pool_meta);
|
||||
}
|
||||
return Err(err);
|
||||
}
|
||||
|
||||
if let Some(canceler) = terminal_canceler.as_ref() {
|
||||
self.release_decommission_canceler_slot(idx, canceler).await;
|
||||
}
|
||||
|
||||
if should_reload_pool_meta && let Some(notification_sys) = runtime_sources::notification_sys() {
|
||||
let stage = format!("decommission_cancel for pool {idx}");
|
||||
resolve_decommission_pool_meta_reload_result(notification_sys.reload_pool_meta().await, stage.as_str())?;
|
||||
}
|
||||
|
||||
Ok(())
|
||||
async fn decommission_cancel_with_owner(self: &Arc<Self>, idx: usize, owner: Option<&DecommissionCanceler>) -> Result<()> {
|
||||
let pools = self.pools.clone();
|
||||
self.decommission_cancel_with_owner_and_save(idx, owner, move |snapshot| async move { snapshot.save(pools).await })
|
||||
.await
|
||||
}
|
||||
|
||||
#[tracing::instrument(skip(self))]
|
||||
@@ -9645,6 +9756,525 @@ mod pools_tests {
|
||||
assert!(store.decommission_cancelers.read().await.iter().all(Option::is_none));
|
||||
}
|
||||
|
||||
#[tokio::test]
|
||||
async fn test_decommission_cancel_save_failure_preserves_generation_and_token_until_retry() {
|
||||
let generation = OffsetDateTime::UNIX_EPOCH;
|
||||
let canceler = DecommissionCanceler::new(CancellationToken::new());
|
||||
let pool_meta = PoolMeta {
|
||||
version: super::POOL_META_VERSION,
|
||||
pools: vec![decommission_test_pool_status(
|
||||
0,
|
||||
Some(PoolDecommissionInfo {
|
||||
start_time: Some(generation),
|
||||
..Default::default()
|
||||
}),
|
||||
)],
|
||||
..Default::default()
|
||||
};
|
||||
let store = decommission_worker_test_store(pool_meta, vec![Some(canceler.clone())]);
|
||||
|
||||
let err = store
|
||||
.decommission_cancel_with_owner_and_save(0, Some(&canceler), |_| async { Err(Error::Timeout) })
|
||||
.await
|
||||
.expect_err("injected pool metadata timeout should fail cancel");
|
||||
assert!(matches!(err, Error::Timeout));
|
||||
|
||||
{
|
||||
let pool_meta = store.pool_meta.read().await;
|
||||
let info = pool_meta.pools[0]
|
||||
.decommission
|
||||
.as_ref()
|
||||
.expect("failed cancel must retain decommission metadata");
|
||||
assert_eq!(info.start_time, Some(generation));
|
||||
assert!(!info.canceled);
|
||||
assert!(!info.complete);
|
||||
assert!(!info.failed);
|
||||
assert!(ensure_decommission_generation(&pool_meta, 0, generation).is_ok());
|
||||
}
|
||||
{
|
||||
let cancelers = store.decommission_cancelers.read().await;
|
||||
let current = cancelers[0].as_ref().expect("failed cancel must retain the worker owner");
|
||||
assert!(current.owns_same_operation(&canceler));
|
||||
assert!(current.is_active());
|
||||
}
|
||||
assert!(!canceler.is_cancelled());
|
||||
assert!(store.decommission_terminal_retryable_for_operation(0, &canceler).await);
|
||||
|
||||
let persisted = Arc::new(std::sync::Mutex::new(None));
|
||||
let persisted_for_save = persisted.clone();
|
||||
store
|
||||
.decommission_cancel_with_owner_and_save(0, Some(&canceler), move |snapshot| async move {
|
||||
let data = snapshot.encode_config_data()?;
|
||||
*persisted_for_save
|
||||
.lock()
|
||||
.expect("persisted snapshot lock should not be poisoned") = Some(data);
|
||||
Ok(())
|
||||
})
|
||||
.await
|
||||
.expect("cancel retry should commit");
|
||||
|
||||
{
|
||||
let pool_meta = store.pool_meta.read().await;
|
||||
let info = pool_meta.pools[0]
|
||||
.decommission
|
||||
.as_ref()
|
||||
.expect("committed cancel metadata should remain present");
|
||||
assert!(info.canceled);
|
||||
assert!(!info.complete);
|
||||
assert!(!info.failed);
|
||||
assert!(info.start_time.is_none());
|
||||
}
|
||||
assert!(store.decommission_cancelers.read().await[0].is_none());
|
||||
assert!(!canceler.is_active());
|
||||
assert!(canceler.is_cancelled());
|
||||
|
||||
let repeated_save_called = Arc::new(AtomicBool::new(false));
|
||||
let repeated_save_called_by_closure = repeated_save_called.clone();
|
||||
store
|
||||
.decommission_cancel_with_owner_and_save(0, None, move |_| async move {
|
||||
repeated_save_called_by_closure.store(true, Ordering::SeqCst);
|
||||
Ok(())
|
||||
})
|
||||
.await
|
||||
.expect("repeated cancel should be idempotent");
|
||||
assert!(!repeated_save_called.load(Ordering::SeqCst));
|
||||
|
||||
let persisted = persisted
|
||||
.lock()
|
||||
.expect("persisted snapshot lock should not be poisoned")
|
||||
.take()
|
||||
.expect("successful retry should capture persisted bytes");
|
||||
let mut restarted = PoolMeta::default();
|
||||
restarted
|
||||
.load_from_config_data(persisted)
|
||||
.expect("a restarted process should decode the committed cancel");
|
||||
assert!(
|
||||
restarted.pools[0]
|
||||
.decommission
|
||||
.as_ref()
|
||||
.is_some_and(|info| info.canceled && info.start_time.is_none())
|
||||
);
|
||||
assert!(first_resumable_decommission_queue_indices(&restarted).is_empty());
|
||||
}
|
||||
|
||||
#[tokio::test]
|
||||
async fn test_decommission_cancel_serializes_reload_until_local_commit() {
|
||||
let generation = OffsetDateTime::UNIX_EPOCH;
|
||||
let canceler = DecommissionCanceler::new(CancellationToken::new());
|
||||
let pool_meta = PoolMeta {
|
||||
version: super::POOL_META_VERSION,
|
||||
pools: vec![decommission_test_pool_status(
|
||||
0,
|
||||
Some(PoolDecommissionInfo {
|
||||
start_time: Some(generation),
|
||||
stage: "migrate_object".to_string(),
|
||||
..Default::default()
|
||||
}),
|
||||
)],
|
||||
..Default::default()
|
||||
};
|
||||
let store = decommission_worker_test_store(pool_meta, vec![Some(canceler.clone())]);
|
||||
let (persisted_tx, persisted_rx) = tokio::sync::oneshot::channel();
|
||||
let save_release = Arc::new(tokio::sync::Notify::new());
|
||||
|
||||
let cancel = tokio::spawn({
|
||||
let store = store.clone();
|
||||
let canceler = canceler.clone();
|
||||
let save_release = save_release.clone();
|
||||
async move {
|
||||
store
|
||||
.decommission_cancel_with_owner_and_save(0, Some(&canceler), move |snapshot| async move {
|
||||
persisted_tx
|
||||
.send(snapshot.encode_config_data()?)
|
||||
.map_err(|_| Error::other("failed to expose saved cancel snapshot"))?;
|
||||
save_release.notified().await;
|
||||
Ok(())
|
||||
})
|
||||
.await
|
||||
}
|
||||
});
|
||||
let persisted = persisted_rx.await.expect("save should expose the canceled snapshot");
|
||||
let reload_started = Arc::new(tokio::sync::Notify::new());
|
||||
let reload = tokio::spawn({
|
||||
let store = store.clone();
|
||||
let reload_started = reload_started.clone();
|
||||
async move {
|
||||
let mut reloaded = PoolMeta::default();
|
||||
reloaded.load_from_config_data(persisted)?;
|
||||
reload_started.notify_one();
|
||||
*store.pool_meta.write().await = reloaded;
|
||||
Ok::<(), Error>(())
|
||||
}
|
||||
});
|
||||
reload_started.notified().await;
|
||||
assert!(!reload.is_finished(), "peer reload must wait for cancel publication");
|
||||
|
||||
save_release.notify_one();
|
||||
cancel
|
||||
.await
|
||||
.expect("cancel task should not panic")
|
||||
.expect("cancel should commit before releasing the reload");
|
||||
reload
|
||||
.await
|
||||
.expect("reload task should not panic")
|
||||
.expect("reload should install the saved cancel after publication");
|
||||
|
||||
let pool_meta = store.pool_meta.read().await;
|
||||
let info = pool_meta.pools[0]
|
||||
.decommission
|
||||
.as_ref()
|
||||
.expect("reloaded cancel metadata should remain present");
|
||||
assert!(info.canceled);
|
||||
assert!(!info.complete);
|
||||
assert!(!info.failed);
|
||||
assert!(info.start_time.is_none());
|
||||
assert!(info.stage.is_empty(), "the persisted snapshot should have been decoded before commit");
|
||||
drop(pool_meta);
|
||||
assert!(store.decommission_cancelers.read().await[0].is_none());
|
||||
assert!(!canceler.is_active());
|
||||
assert!(canceler.is_cancelled());
|
||||
}
|
||||
|
||||
#[tokio::test]
|
||||
async fn test_decommission_cancel_transaction_survives_caller_abort_after_durable_save() {
|
||||
let generation = OffsetDateTime::UNIX_EPOCH;
|
||||
let canceler = DecommissionCanceler::new(CancellationToken::new());
|
||||
let pool_meta = PoolMeta {
|
||||
pools: vec![decommission_test_pool_status(
|
||||
0,
|
||||
Some(PoolDecommissionInfo {
|
||||
start_time: Some(generation),
|
||||
..Default::default()
|
||||
}),
|
||||
)],
|
||||
..Default::default()
|
||||
};
|
||||
let store = decommission_worker_test_store(pool_meta, vec![Some(canceler.clone())]);
|
||||
let persisted = Arc::new(std::sync::Mutex::new(None));
|
||||
let (durable_tx, durable_rx) = tokio::sync::oneshot::channel();
|
||||
let save_release = Arc::new(tokio::sync::Notify::new());
|
||||
let cancel = tokio::spawn({
|
||||
let store = store.clone();
|
||||
let canceler = canceler.clone();
|
||||
let persisted = persisted.clone();
|
||||
let save_release = save_release.clone();
|
||||
async move {
|
||||
store
|
||||
.decommission_cancel_with_owner_and_save(0, Some(&canceler), move |snapshot| async move {
|
||||
assert!(
|
||||
snapshot.pools[0]
|
||||
.decommission
|
||||
.as_ref()
|
||||
.is_some_and(|info| info.canceled && info.start_time.is_none())
|
||||
);
|
||||
*persisted.lock().expect("persisted cancel lock should not be poisoned") =
|
||||
Some(snapshot.encode_config_data()?);
|
||||
durable_tx
|
||||
.send(())
|
||||
.map_err(|_| Error::other("failed to report durable cancel snapshot"))?;
|
||||
save_release.notified().await;
|
||||
Ok(())
|
||||
})
|
||||
.await
|
||||
}
|
||||
});
|
||||
durable_rx.await.expect("save hook should report the durable cancel snapshot");
|
||||
cancel.abort();
|
||||
let join_err = cancel.await.expect_err("caller cancel future should be aborted");
|
||||
assert!(join_err.is_cancelled());
|
||||
assert!(
|
||||
store.pool_meta.try_read().is_err(),
|
||||
"the detached transaction must retain its state guard"
|
||||
);
|
||||
assert!(
|
||||
store.decommission_cancelers.try_read().is_err(),
|
||||
"the detached transaction must retain its owner guard"
|
||||
);
|
||||
|
||||
save_release.notify_one();
|
||||
tokio::time::timeout(StdDuration::from_secs(1), canceler.token().cancelled())
|
||||
.await
|
||||
.expect("detached cancel transaction should terminate the old token");
|
||||
|
||||
let persisted = persisted
|
||||
.lock()
|
||||
.expect("persisted cancel lock should not be poisoned")
|
||||
.take()
|
||||
.expect("save should capture the durable cancel snapshot");
|
||||
let mut durable = PoolMeta::default();
|
||||
durable
|
||||
.load_from_config_data(persisted)
|
||||
.expect("durable cancel snapshot should decode");
|
||||
assert!(
|
||||
durable.pools[0]
|
||||
.decommission
|
||||
.as_ref()
|
||||
.is_some_and(|info| info.canceled && info.start_time.is_none())
|
||||
);
|
||||
assert!(store.decommission_cancelers.read().await[0].is_none());
|
||||
assert!(!canceler.is_active());
|
||||
assert!(canceler.is_cancelled());
|
||||
|
||||
let side_effect_ran = Arc::new(AtomicBool::new(false));
|
||||
let operation_gate = store.ctx.decommission_operation_gate();
|
||||
let result = run_decommission_side_effect(canceler.token(), &operation_gate, {
|
||||
let side_effect_ran = side_effect_ran.clone();
|
||||
move || async move {
|
||||
side_effect_ran.store(true, Ordering::SeqCst);
|
||||
Ok(())
|
||||
}
|
||||
})
|
||||
.await;
|
||||
assert!(matches!(result, Err(Error::OperationCanceled)));
|
||||
assert!(!side_effect_ran.load(Ordering::SeqCst));
|
||||
assert!(
|
||||
store.pool_meta.read().await.pools[0]
|
||||
.decommission
|
||||
.as_ref()
|
||||
.is_some_and(|info| info.canceled && !info.failed)
|
||||
);
|
||||
}
|
||||
|
||||
#[tokio::test]
|
||||
async fn test_decommission_cancel_quiesces_and_publishes_only_after_save() {
|
||||
let generation = OffsetDateTime::UNIX_EPOCH;
|
||||
let canceler = DecommissionCanceler::new(CancellationToken::new());
|
||||
let pool_meta = PoolMeta {
|
||||
pools: vec![decommission_test_pool_status(
|
||||
0,
|
||||
Some(PoolDecommissionInfo {
|
||||
start_time: Some(generation),
|
||||
..Default::default()
|
||||
}),
|
||||
)],
|
||||
..Default::default()
|
||||
};
|
||||
let store = decommission_worker_test_store(pool_meta, vec![Some(canceler.clone())]);
|
||||
let operation_gate = store.ctx.decommission_operation_gate();
|
||||
let side_effect = operation_gate.read().await;
|
||||
let save_started = Arc::new(tokio::sync::Notify::new());
|
||||
let save_release = Arc::new(tokio::sync::Notify::new());
|
||||
let save_entered = Arc::new(AtomicBool::new(false));
|
||||
|
||||
let mut cancel = tokio::spawn({
|
||||
let store = store.clone();
|
||||
let canceler = canceler.clone();
|
||||
let save_started = save_started.clone();
|
||||
let save_release = save_release.clone();
|
||||
let save_entered = save_entered.clone();
|
||||
async move {
|
||||
store
|
||||
.decommission_cancel_with_owner_and_save(0, Some(&canceler), move |_| async move {
|
||||
save_entered.store(true, Ordering::SeqCst);
|
||||
save_started.notify_one();
|
||||
save_release.notified().await;
|
||||
Ok(())
|
||||
})
|
||||
.await
|
||||
}
|
||||
});
|
||||
|
||||
let mut cancel_holds_start_gate = false;
|
||||
for _ in 0..100 {
|
||||
if store.start_gate.try_lock().is_err() {
|
||||
cancel_holds_start_gate = true;
|
||||
break;
|
||||
}
|
||||
tokio::task::yield_now().await;
|
||||
}
|
||||
assert!(cancel_holds_start_gate, "cancel should reach the operation-gate wait");
|
||||
assert!(!cancel.is_finished(), "cancel must wait for the in-flight side effect");
|
||||
assert!(!save_entered.load(Ordering::SeqCst), "cancel must quiesce side effects before saving");
|
||||
{
|
||||
let pool_meta = store.pool_meta.read().await;
|
||||
assert!(ensure_decommission_generation(&pool_meta, 0, generation).is_ok());
|
||||
}
|
||||
assert!(!canceler.is_cancelled());
|
||||
|
||||
drop(side_effect);
|
||||
tokio::time::timeout(StdDuration::from_secs(1), save_started.notified())
|
||||
.await
|
||||
.expect("cancel should reach the injected save after side effects quiesce");
|
||||
assert!(
|
||||
store.pool_meta_save_gate.try_lock().is_err(),
|
||||
"the cancel save must exclude stale full-document saves until publication"
|
||||
);
|
||||
assert!(
|
||||
store.pool_meta.try_read().is_err(),
|
||||
"the active generation must stay write-locked through persistence"
|
||||
);
|
||||
assert!(!canceler.is_cancelled(), "the token must remain live until persistence commits");
|
||||
|
||||
let mut complete = tokio::spawn({
|
||||
let store = store.clone();
|
||||
async move { store.complete_decommission(0).await }
|
||||
});
|
||||
let mut fail = tokio::spawn({
|
||||
let store = store.clone();
|
||||
async move { store.decommission_failed(0).await }
|
||||
});
|
||||
tokio::task::yield_now().await;
|
||||
assert!(!complete.is_finished(), "complete must serialize behind the pending cancel");
|
||||
assert!(!fail.is_finished(), "fail must serialize behind the pending cancel");
|
||||
|
||||
save_release.notify_one();
|
||||
tokio::time::timeout(StdDuration::from_secs(1), &mut cancel)
|
||||
.await
|
||||
.expect("cancel should finish after persistence commits")
|
||||
.expect("cancel task should not panic")
|
||||
.expect("cancel should commit");
|
||||
tokio::time::timeout(StdDuration::from_secs(1), &mut complete)
|
||||
.await
|
||||
.expect("complete should finish after cancel commits")
|
||||
.expect("complete task should not panic")
|
||||
.expect("stale complete should be a no-op");
|
||||
tokio::time::timeout(StdDuration::from_secs(1), &mut fail)
|
||||
.await
|
||||
.expect("fail should finish after cancel commits")
|
||||
.expect("fail task should not panic")
|
||||
.expect("stale fail should be a no-op");
|
||||
|
||||
let pool_meta = store.pool_meta.read().await;
|
||||
let info = pool_meta.pools[0]
|
||||
.decommission
|
||||
.as_ref()
|
||||
.expect("cancel metadata should remain present");
|
||||
assert!(info.canceled);
|
||||
assert!(!info.complete);
|
||||
assert!(!info.failed);
|
||||
assert!(info.start_time.is_none());
|
||||
drop(pool_meta);
|
||||
assert!(canceler.is_cancelled());
|
||||
assert!(!canceler.is_active());
|
||||
assert!(store.decommission_cancelers.read().await[0].is_none());
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn test_decommission_cancel_commit_rejects_a_replaced_generation() {
|
||||
let old_generation = OffsetDateTime::UNIX_EPOCH;
|
||||
let new_generation = old_generation + Duration::seconds(1);
|
||||
let mut canceled = PoolMeta {
|
||||
pools: vec![decommission_test_pool_status(
|
||||
0,
|
||||
Some(PoolDecommissionInfo {
|
||||
start_time: Some(old_generation),
|
||||
..Default::default()
|
||||
}),
|
||||
)],
|
||||
..Default::default()
|
||||
};
|
||||
let previous_last_update = canceled.pools[0].last_update;
|
||||
assert!(canceled.decommission_cancel(0));
|
||||
let canceled_pool = canceled.pools.remove(0);
|
||||
let commit = super::DecommissionCancelCommit {
|
||||
previous_start_time: Some(old_generation),
|
||||
previous_queued: false,
|
||||
previous_last_update,
|
||||
canceled_pool,
|
||||
};
|
||||
let mut current = PoolMeta {
|
||||
pools: vec![decommission_test_pool_status(
|
||||
0,
|
||||
Some(PoolDecommissionInfo {
|
||||
start_time: Some(new_generation),
|
||||
..Default::default()
|
||||
}),
|
||||
)],
|
||||
..Default::default()
|
||||
};
|
||||
|
||||
let err = super::commit_decommission_cancel(&mut current, 0, commit)
|
||||
.expect_err("an old cancel must not publish over a replacement generation");
|
||||
assert!(err.to_string().contains("operation generation changed"));
|
||||
let info = current.pools[0]
|
||||
.decommission
|
||||
.as_ref()
|
||||
.expect("replacement generation should remain present");
|
||||
assert_eq!(info.start_time, Some(new_generation));
|
||||
assert!(!info.canceled);
|
||||
}
|
||||
|
||||
#[tokio::test]
|
||||
async fn test_decommission_cancel_rejects_stale_retry_after_queued_replacement() {
|
||||
let old_generation = OffsetDateTime::UNIX_EPOCH;
|
||||
let canceler = DecommissionCanceler::new(CancellationToken::new());
|
||||
let pool_meta = PoolMeta {
|
||||
pools: vec![decommission_test_pool_status(
|
||||
0,
|
||||
Some(PoolDecommissionInfo {
|
||||
start_time: Some(old_generation),
|
||||
..Default::default()
|
||||
}),
|
||||
)],
|
||||
..Default::default()
|
||||
};
|
||||
let store = decommission_worker_test_store(pool_meta, vec![Some(canceler.clone())]);
|
||||
let queued_replacement = Arc::new(std::sync::Mutex::new(None));
|
||||
let queued_replacement_for_save = queued_replacement.clone();
|
||||
|
||||
store
|
||||
.decommission_cancel_with_owner_and_save(0, Some(&canceler), move |snapshot| async move {
|
||||
let saved_cancel = snapshot.pools[0]
|
||||
.decommission
|
||||
.as_ref()
|
||||
.expect("saved snapshot should contain decommission metadata");
|
||||
assert!(saved_cancel.canceled);
|
||||
assert!(saved_cancel.start_time.is_none());
|
||||
let mut queued_replacement = snapshot.clone();
|
||||
let replacement = queued_replacement
|
||||
.pools
|
||||
.get_mut(0)
|
||||
.expect("cancel snapshot should contain the pool");
|
||||
replacement.last_update += Duration::seconds(1);
|
||||
let info = replacement
|
||||
.decommission
|
||||
.as_mut()
|
||||
.expect("cancel snapshot should contain decommission metadata");
|
||||
info.canceled = false;
|
||||
info.queued = true;
|
||||
*queued_replacement_for_save
|
||||
.lock()
|
||||
.expect("queued replacement lock should not be poisoned") = Some(queued_replacement);
|
||||
Ok(())
|
||||
})
|
||||
.await
|
||||
.expect("cancel should commit before a queued replacement is installed");
|
||||
assert!(store.decommission_cancelers.read().await[0].is_none());
|
||||
assert!(!canceler.is_active());
|
||||
assert!(canceler.is_cancelled());
|
||||
|
||||
let queued_replacement = queued_replacement
|
||||
.lock()
|
||||
.expect("queued replacement lock should not be poisoned")
|
||||
.take()
|
||||
.expect("save should prepare the queued replacement");
|
||||
*store.pool_meta.write().await = queued_replacement;
|
||||
|
||||
let replacement_revision = {
|
||||
let pool_meta = store.pool_meta.read().await;
|
||||
let info = pool_meta.pools[0]
|
||||
.decommission
|
||||
.as_ref()
|
||||
.expect("queued replacement should remain present");
|
||||
assert!(info.queued);
|
||||
assert!(!info.canceled);
|
||||
assert!(info.start_time.is_none());
|
||||
pool_meta.pools[0].last_update
|
||||
};
|
||||
|
||||
store.retry_decommission_cancel_for_operation(0, &canceler).await;
|
||||
|
||||
let pool_meta = store.pool_meta.read().await;
|
||||
let info = pool_meta.pools[0]
|
||||
.decommission
|
||||
.as_ref()
|
||||
.expect("stale retry must preserve the queued replacement");
|
||||
assert_eq!(pool_meta.pools[0].last_update, replacement_revision);
|
||||
assert!(info.queued);
|
||||
assert!(!info.canceled);
|
||||
assert!(info.start_time.is_none());
|
||||
}
|
||||
|
||||
#[tokio::test]
|
||||
async fn test_decommission_failed_save_failure_preserves_owner_until_retry_succeeds() {
|
||||
let canceler = DecommissionCanceler::new(CancellationToken::new());
|
||||
|
||||
@@ -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 {
|
||||
|
||||
@@ -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);
|
||||
|
||||
@@ -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.
|
||||
+2
-2
@@ -336,13 +336,13 @@ 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"] }
|
||||
|
||||
@@ -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
|
||||
|
||||
@@ -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