gsadmin/rustfs
1
0
Fork 0
mirror of https://github.com/rustfs/rustfs.git synced 2026-08-28 16:07:05 +00:00
Code Issues Packages Projects Releases Wiki Activity

fix(ilm): preserve lifecycle version groups (#5239)

Browse Source 
* fix(ilm): evaluate complete version groups

Co-Authored-By: heihutu <heihutu@gmail.com>

* feat(ilm): log replication expiry blocks

Co-Authored-By: heihutu <heihutu@gmail.com>

* fix(ilm): diagnose incomplete noncurrent chains

Co-Authored-By: heihutu <heihutu@gmail.com>

* test(ilm): cover purge-pending version groups

Add regression coverage for lifecycle-only version listing so purge-pending versions stay present for ILM evaluation while the public ListObjectVersions projection remains filtered.

Refs rustfs/backlog#1500

Co-Authored-By: heihutu <heihutu@gmail.com>

* feat(ilm): log lifecycle evaluation failures

Emit structured lifecycle_evaluation_failed events when version group loading or evaluation fails during immediate and existing-object expiry scans.

Refs rustfs/backlog#1503

Co-Authored-By: heihutu <heihutu@gmail.com>

* test(ilm): cover incomplete noncurrent chains

Pin the fail-closed behavior for noncurrent expiration when successor_mod_time is missing and reuse a stable structured event name for that skip path.

Refs rustfs/backlog#1502

Co-Authored-By: heihutu <heihutu@gmail.com>

* test(ilm): cover one-day noncurrent expiry boundary

Add a runtime regression test proving NoncurrentVersionExpiration Days=1 stays inactive before expected_expiry_time and deletes exactly at the computed due boundary.

Refs rustfs/backlog#1504

Co-Authored-By: heihutu <heihutu@gmail.com>

* fix(ilm): keep transition checks after incomplete expiry

Co-Authored-By: heihutu <heihutu@gmail.com>

---------

Co-authored-by: heihutu <heihutu@gmail.com>
This commit is contained in:
houseme
2026-07-26 01:42:02 +08:00
committed by GitHub
parent 516f7fecc1
commit 23a5db4012
5 changed files with 374 additions and 29 deletions
Download Patch File Download Diff File Expand all files Collapse all files
crates/ecstore/src/bucket/lifecycle/bucket_lifecycle_ops.rs
+63 -9
View File
@@ -112,6 +112,7 @@ const EVENT_LIFECYCLE_WORKER_STATE: &str = "lifecycle_worker_state";
const EVENT_LIFECYCLE_TRANSITION_COMPENSATION: &str = "lifecycle_transition_compensation";
const EVENT_LIFECYCLE_STALE_MULTIPART_CLEANUP: &str = "lifecycle_stale_multipart_cleanup";
const EVENT_LIFECYCLE_SCAN_SKIPPED: &str = "lifecycle_scan_skipped";
const EVENT_LIFECYCLE_EVALUATION_FAILED: &str = "lifecycle_evaluation_failed";
const EVENT_LIFECYCLE_TIER_AUDIT: &str = "lifecycle_tier_audit";
const EVENT_LIFECYCLE_TIER_OPERATION_FAILED: &str = "lifecycle_tier_operation_failed";
const EVENT_LIFECYCLE_DELETE_FAILED: &str = "lifecycle_delete_failed";
@@ -2647,12 +2648,25 @@ pub async fn enqueue_immediate_expiry(oi: &ObjectInfo, src: LcEventSrc) {
let mut object_infos = Vec::new();
loop {
let Ok(page) = api
let page = match api
.clone()
.list_object_versions(&oi.bucket, &oi.name, marker.clone(), version_marker.clone(), None, 1000)
.list_object_versions_for_lifecycle(&oi.bucket, &oi.name, marker.clone(), version_marker.clone(), None, 1000)
.await
else {
return;
{
Ok(page) => page,
Err(err) => {
warn!(
event = EVENT_LIFECYCLE_EVALUATION_FAILED,
component = LOG_COMPONENT_ECSTORE,
subsystem = LOG_SUBSYSTEM_LIFECYCLE,
bucket = %oi.bucket,
object = %oi.name,
error = %err,
reason = "list_versions_failed",
"Failed to load lifecycle version group"
);
return;
}
};
object_infos.extend(page.objects.into_iter().filter(|object| object.name == oi.name));
@@ -2677,12 +2691,27 @@ pub async fn enqueue_immediate_expiry(oi: &ObjectInfo, src: LcEventSrc) {
.iter()
.map(lifecycle::object_opts_from_object_info)
.collect::<Vec<ObjectOpts>>();
let Ok(events) = Evaluator::new(Arc::new(lifecycle))
let events = match Evaluator::new(Arc::new(lifecycle))
.with_lock_retention(lock_config)
.eval(&object_opts)
.await
else {
return;
{
Ok(events) => events,
Err(err) => {
warn!(
event = EVENT_LIFECYCLE_EVALUATION_FAILED,
component = LOG_COMPONENT_ECSTORE,
subsystem = LOG_SUBSYSTEM_LIFECYCLE,
bucket = %oi.bucket,
object = %oi.name,
expected_version_count = oi.num_versions,
observed_version_count = object_infos.len(),
error = %err,
reason = "version_group_evaluation_failed",
"Failed to evaluate lifecycle version group"
);
return;
}
};
let mut to_delete_objs = Vec::new();
@@ -3099,10 +3128,16 @@ async fn enqueue_expiry_for_existing_object_group(
Ok(events) => events,
Err(err) => {
warn!(
event = EVENT_LIFECYCLE_EVALUATION_FAILED,
component = LOG_COMPONENT_ECSTORE,
subsystem = LOG_SUBSYSTEM_LIFECYCLE,
bucket = context.bucket,
object = %object_infos[0].name,
expected_version_count = object_infos[0].num_versions,
observed_version_count = object_infos.len(),
error = %err,
"failed to evaluate lifecycle events for existing object versions"
reason = "version_group_evaluation_failed",
"Failed to evaluate lifecycle version group"
);
return;
}
@@ -3210,7 +3245,7 @@ pub async fn enqueue_expiry_for_existing_objects(api: Arc<ECStore>, bucket: &str
loop {
let page = api
.clone()
.list_object_versions(bucket, "", marker.clone(), version_marker.clone(), None, 1000)
.list_object_versions_for_lifecycle(bucket, "", marker.clone(), version_marker.clone(), None, 1000)
.await?;
for object in page.objects {
@@ -3835,6 +3870,25 @@ pub async fn eval_action_from_lifecycle(
}
if lifecycle_action_blocked_by_replication(event.action, oi) {
let reason = if oi.version_purge_status.is_pending() {
"version_purge_pending"
} else if oi.replication_status == ReplicationStatusType::Failed {
"replication_failed"
} else {
"replication_pending"
};
debug!(
event = EVENT_LIFECYCLE_SCAN_SKIPPED,
component = LOG_COMPONENT_ECSTORE,
subsystem = LOG_SUBSYSTEM_LIFECYCLE,
object = %oi.name,
version_id = ?oi.version_id,
action = ?event.action,
replication_status = ?oi.replication_status,
version_purge_status = ?oi.version_purge_status,
reason,
"Skipped lifecycle action because replication is not terminal"
);
return lifecycle::Event::default();
}