mirror of
https://github.com/rustfs/rustfs.git
synced 2026-09-07 20:46:11 +00:00
7ff578ff20
The batch `NewerNoncurrentVersions` expiry path took a lifecycle event argument and ignored it: after `delete_objects` committed it only evicted the cache and scheduled replication deletes, so a successful noncurrent version expiry was invisible to notification subscribers while the equivalent current-version path emitted a lifecycle expiration event. Emit that event from the batch path too, reusing the existing lifecycle audit sink and event contract. Only entries that actually mutated something are announced, and cache eviction and replication scheduling keep their existing order and admission — the event is derived from the committed result and a send failure never rolls back a delete. "No error" is not enough to prove a mutation: the disk layer skips an absent version and reports success, so a batch entry for a version that was already gone came back indistinguishable from a committed delete. The delete plan already resolves whether the source exists, so carry that `source_missing` result on `DeletedObject` and let the lifecycle path stay silent for versions it did not remove. backlog#2202
141 lines
5.4 KiB
Rust
141 lines
5.4 KiB
Rust
// Copyright 2024 RustFS Team
|
|
//
|
|
// Licensed under the Apache License, Version 2.0 (the "License");
|
|
// you may not use this file except in compliance with the License.
|
|
// You may obtain a copy of the License at
|
|
//
|
|
// http://www.apache.org/licenses/LICENSE-2.0
|
|
//
|
|
// Unless required by applicable law or agreed to in writing, software
|
|
// distributed under the License is distributed on an "AS IS" BASIS,
|
|
// WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
|
// See the License for the specific language governing permissions and
|
|
// limitations under the License.
|
|
|
|
use std::sync::Arc;
|
|
use tracing::debug;
|
|
|
|
const LOG_COMPONENT_ECSTORE: &str = "ecstore";
|
|
const LOG_SUBSYSTEM_LIFECYCLE: &str = "lifecycle";
|
|
const EVENT_LIFECYCLE_CLEANUP_SKIPPED: &str = "lifecycle_cleanup_skipped";
|
|
const EVENT_LIFECYCLE_CLEANUP_FAILED: &str = "lifecycle_cleanup_failed";
|
|
|
|
use crate::bucket::lifecycle::bucket_lifecycle_audit::emit_noncurrent_expiration_event;
|
|
use crate::bucket::lifecycle::lifecycle;
|
|
use crate::bucket::lifecycle::replication_sink::{self, ReplicationObjectBridge};
|
|
use crate::object_api::ObjectOptions;
|
|
use crate::storage_api_contracts::object::{ObjectOperations as _, ObjectToDelete};
|
|
use crate::store::ECStore;
|
|
use rustfs_lock::MAX_DELETE_LIST;
|
|
use uuid::Uuid;
|
|
|
|
pub async fn delete_object_versions(
|
|
api: &Arc<ECStore>,
|
|
bucket: &str,
|
|
to_del: &[ObjectToDelete],
|
|
_lc_event: lifecycle::Event,
|
|
bucket_incarnation_id: Uuid,
|
|
) -> usize {
|
|
if to_del.iter().any(|target| {
|
|
target.version_id.is_none()
|
|
|| (target.version_id.is_some_and(|version_id| version_id.is_nil()) && target.expected_identity.is_none())
|
|
}) {
|
|
debug!(
|
|
event = EVENT_LIFECYCLE_CLEANUP_SKIPPED,
|
|
component = LOG_COMPONENT_ECSTORE,
|
|
subsystem = LOG_SUBSYSTEM_LIFECYCLE,
|
|
bucket,
|
|
target_count = to_del.len(),
|
|
reason = "incomplete_version_identity",
|
|
"Skipped lifecycle noncurrent version cleanup"
|
|
);
|
|
return to_del.len();
|
|
}
|
|
|
|
let delete_config_snapshot = match ReplicationObjectBridge::delete_request_config(api, bucket).await {
|
|
Ok(snapshot) => Arc::new(snapshot),
|
|
Err(err) => {
|
|
debug!(
|
|
event = EVENT_LIFECYCLE_CLEANUP_SKIPPED,
|
|
component = LOG_COMPONENT_ECSTORE,
|
|
subsystem = LOG_SUBSYSTEM_LIFECYCLE,
|
|
bucket,
|
|
error = ?err,
|
|
reason = "delete_config_snapshot_unavailable",
|
|
"Skipped lifecycle noncurrent version cleanup"
|
|
);
|
|
return to_del.len();
|
|
}
|
|
};
|
|
let mut remaining = to_del;
|
|
let mut failed = 0;
|
|
loop {
|
|
let mut to_del = remaining;
|
|
if to_del.len() > MAX_DELETE_LIST {
|
|
remaining = &to_del[MAX_DELETE_LIST..];
|
|
to_del = &to_del[..MAX_DELETE_LIST];
|
|
} else {
|
|
remaining = &[];
|
|
}
|
|
|
|
let (mut deleted_objs, errors) = api
|
|
.delete_objects(
|
|
bucket,
|
|
to_del.to_vec(),
|
|
ObjectOptions {
|
|
delete_replication_config_snapshot: Some(Arc::clone(&delete_config_snapshot)),
|
|
expected_bucket_incarnation_id: Some(bucket_incarnation_id),
|
|
..Default::default()
|
|
},
|
|
)
|
|
.await;
|
|
failed += errors.iter().filter(|err| err.is_some()).count();
|
|
|
|
for (i, deleted_obj) in deleted_objs.iter_mut().enumerate() {
|
|
if errors.get(i).and_then(|err| err.as_ref()).is_some() {
|
|
continue;
|
|
}
|
|
// Evict any cached body for the successfully deleted noncurrent
|
|
// version so it does not sit resident until TTL (ODC-26).
|
|
if let Some(target) = to_del.get(i) {
|
|
crate::object_api::notify_object_mutation(bucket, &target.object_name).await;
|
|
// Announce the version this batch actually removed. Cache
|
|
// eviction and replication scheduling keep their existing
|
|
// order and admission; the event is derived from the committed
|
|
// result, and a send failure never rolls back a delete that
|
|
// already happened (backlog#2202).
|
|
emit_noncurrent_expiration_event(bucket, target, deleted_obj, false);
|
|
}
|
|
if deleted_obj.replication_state.is_none() {
|
|
continue;
|
|
}
|
|
replication_sink::schedule_delete(bucket.to_string(), deleted_obj.clone()).await;
|
|
}
|
|
|
|
for (i, err) in errors.iter().enumerate() {
|
|
if let Some(e) = err {
|
|
let obj_name = to_del.get(i).map(|o| o.object_name.as_str()).unwrap_or("<unknown>");
|
|
let vid = to_del
|
|
.get(i)
|
|
.and_then(|o| o.version_id)
|
|
.map(|v| v.to_string())
|
|
.unwrap_or_default();
|
|
debug!(
|
|
event = EVENT_LIFECYCLE_CLEANUP_FAILED,
|
|
component = LOG_COMPONENT_ECSTORE,
|
|
subsystem = LOG_SUBSYSTEM_LIFECYCLE,
|
|
bucket,
|
|
object = obj_name,
|
|
version_id = %vid,
|
|
error = ?e,
|
|
"Failed lifecycle noncurrent version cleanup"
|
|
);
|
|
}
|
|
}
|
|
if remaining.is_empty() {
|
|
break;
|
|
}
|
|
}
|
|
failed
|
|
}
|