Files
rustfs/crates/ecstore/src/client/object_handlers_common.rs
T
houseme 85fd824581 feat(object-data-cache): close write-side invalidation gaps and add an admin surface (#4694)
* feat(object-data-cache): close write/delete-side invalidation gaps

The object data cache exposed only a single per-(bucket,object)
invalidation primitive and no write-side ecstore hook, so several
delete paths left dead bodies resident until TTL (hygiene/capacity, not
stale-serving: lookups follow a fresh metadata quorum and cannot serve a
gone object). This adds the missing primitives and wires them in.

ODC-26 (backlog#1131): add an `ObjectMutationHook` trait beside the GET
body hook, registered next to it at startup, and call it from the
ecstore-internal delete paths (`apply_expiry_on_non_transitioned_objects`,
`expire_transitioned_object` including the restored-copy branch, and
`delete_object_versions`). The app impl is one `invalidate_object` call
under a new `AfterLifecycleExpiry` reason.

ODC-27 (backlog#1132): force prefix delete now invalidates the whole
prefix, not just the prefix string. `store.delete_object(delete_prefix)`
returns no deleted-name list, so this uses a new prefix primitive rather
than the batch path.

ODC-28 (backlog#1133): DeleteBucket now flushes the bucket via a new
bucket-scope primitive (covers force and non-force, which share the
delete_bucket call).

ODC-C2 (backlog#1143): add `ObjectDataCache::clear()` and two admin
handlers (GET stats, POST flush) routed through admin runtime_sources.

The starshard identity index gains a single `remove_matching` full-scan
API backing prefix/bucket/clear; it is documented as admin/delete-path
only and never runs on the GET or fill hot path. New invalidation
reasons and metric labels added; outcome (removed/noop) labelling kept
correct for every new primitive.

Also fixes a pre-existing broken intra-doc link in memory.rs.

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

* refactor(ecstore): extract the shared HookSlot behind both cache hooks

This PR introduced object_mutation_hook.rs by mirroring body_cache_hook.rs,
which left two process-global registration slots whose register/get/clear
bodies were line-for-line identical except the trait type and the WARN string:
a RwLock<Option<Arc<dyn _>>>, an Arc::ptr_eq "different instance" warning, the
poison-recovery closure, and the same read-lock-and-clone read. Two copies of
the same swap-vs-warn logic can drift apart under maintenance.

Hoist it into a generic HookSlot<T: ?Sized> that owns the logic once. Each hook
module keeps its `static HOOK: HookSlot<dyn XxxHook>` and its thin, unchanged
public wrappers (register_/get_/clear_), so the crate's public surface and
every call site are untouched — this is an internal consolidation, not a
contract change.

The load-bearing #1126 guarantee (newest registration wins, so a rebuilt
AppContext is never stranded on a first-wins slot) previously had no direct
test — the hook tests only covered register-then-notify. HookSlot now has its
own unit tests including re_registration_swaps_to_the_latest_instance;
mutation-testing confirms a first-wins regression fails exactly that test.

No behavior change: the two hooks' existing tests, the P0 body_cache_hook_e2e
regressions, and the app-layer mutation-hook tests all pass unchanged.

Refs: backlog#1126, backlog#1131

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

* fix(admin): register the object-data-cache routes in the policy inventory

This PR added GET /object-data-cache/stats and POST /object-data-cache/flush
but did not list them in the two registries that must account for every
admin route: the route-policy inventory (route_policy.rs) and the route
matrix (route_registration_test.rs). Their coverage tests —
route_policy_inventory_covers_registered_routes and
test_admin_route_matrix_matches_registered_routes — failed on CI because a
registered route had no policy/matrix entry.

These two tests are not part of `make pre-commit` (which runs fmt + arch +
quick-check, not the full suite), so the gap passed local pre-commit and
only surfaced in the CI Test-and-Lint lane.

stats is a read (ServerInfoAdminAction, Sensitive); flush mutates
(ConfigUpdateAdminAction, High) — matching the actions the handlers already
enforce. The MinIO-alias matrix test is unaffected: these are native rustfs
endpoints with no MinIO equivalent.

Refs: backlog#1143

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

---------

Co-authored-by: heihutu <heihutu@gmail.com>
2026-07-10 20:04:05 +00:00

143 lines
5.7 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::lifecycle;
use crate::bucket::replication::{ReplicationLifecycleBridge, ReplicationState, replication_state_to_filemeta};
use crate::bucket::versioning::VersioningApi;
use crate::bucket::versioning_sys::BucketVersioningSys;
use crate::object_api::ObjectOptions;
use crate::storage_api_contracts::object::{ObjectOperations as _, ObjectToDelete};
use crate::store::ECStore;
use rustfs_lock::MAX_DELETE_LIST;
pub async fn delete_object_versions(api: &Arc<ECStore>, bucket: &str, to_del: &[ObjectToDelete], _lc_event: lifecycle::Event) {
let version_suspended = match BucketVersioningSys::get(bucket).await {
Ok(vc) => vc.suspended(),
Err(err) => {
debug!(
event = EVENT_LIFECYCLE_CLEANUP_SKIPPED,
component = LOG_COMPONENT_ECSTORE,
subsystem = LOG_SUBSYSTEM_LIFECYCLE,
bucket,
error = ?err,
reason = "versioning_config_unavailable",
"Skipped lifecycle noncurrent version cleanup"
);
return;
}
};
let mut remaining = to_del;
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 replication_candidates: Vec<Option<ReplicationState>> = Vec::with_capacity(to_del.len());
for object in to_del.iter() {
let version_id = object.version_id.map(|vid| vid.to_string());
let opts = ObjectOptions {
version_id: version_id.clone(),
versioned: true,
version_suspended,
..Default::default()
};
let candidate = match api.get_object_info(bucket, &object.object_name, &opts).await {
Ok(info) => {
let dsc = ReplicationLifecycleBridge::check_delete_replication(bucket, object, &info, &opts).await;
dsc.replicate_any()
.then(|| ReplicationLifecycleBridge::version_delete_replication_state(&dsc))
}
Err(err) => {
debug!(
event = EVENT_LIFECYCLE_CLEANUP_SKIPPED,
component = LOG_COMPONENT_ECSTORE,
subsystem = LOG_SUBSYSTEM_LIFECYCLE,
bucket,
object = %object.object_name,
version_id = ?version_id,
error = ?err,
reason = "object_info_unavailable",
"Skipped lifecycle delete replication scheduling"
);
None
}
};
replication_candidates.push(candidate);
}
let (mut deleted_objs, errors) = api
.delete_objects(
bucket,
to_del.to_vec(),
ObjectOptions {
version_suspended,
..Default::default()
},
)
.await;
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;
}
let Some(replication_state) = replication_candidates.get(i).and_then(|c| c.clone()) else {
continue;
};
deleted_obj.replication_state = Some(replication_state_to_filemeta(&replication_state));
ReplicationLifecycleBridge::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;
}
}
}