mirror of
https://github.com/rustfs/rustfs.git
synced 2026-08-31 01:09:23 +00:00
fix(ecstore): never cache fabricated bucket metadata as authoritative (#5307)
BucketMetadataSys::get_config lazily fabricated a default BucketMetadata (object-lock off) for any bucket whose .metadata.bin was ConfigNotFound and cached it in the map that the map-only, fail-closed metadata_sys::get() serves. The object-lock batch-delete gate (object_lock_delete_check_required, backlog#929 / #4297) treats that map as authoritative, so a metadata miss became a cached "no lock" answer: a versioning peek could poison the cache and let delete_objects skip the per-object retention/legal-hold stat. The same fabrication raced make_bucket (lost update overwriting freshly persisted lock-enabled metadata) and let the 15-minute refresh loop replace good cached metadata on a transient quorum dip. Production changes: - get_config caches only metadata actually read from disk; misses are recorded in a bounded negative cache (30s TTL, 10k entries, invalidated by set()) so repeated lookups for metadata-less names cost no extra namespace-lock + erasure-set fanout (reachable pre-auth via CORS preflight and per-key in DeleteObjects). - concurrent_load never lets a fabricated default REPLACE an existing map entry; startup insert-if-vacant behavior for legacy buckets is preserved. - delete_objects and new_ns_lock resolve dist-erasure, versioning, and the object-lock gate from the set's own instance context (backlog#1052) instead of the ambient facade, so a second in-process instance (or, in tests, another test's transient DistErasure window) cannot reroute locking onto an empty dist locker list or answer with the wrong instance's bucket state. Test-isolation changes (the bug that surfaced all of the above: the delete_objects lock-gating test failed deterministically when sharing a process with the lifecycle env tests): - The MinIO-migration test builds on an isolated InstanceContext instead of registering soon-deleted disks in the shared bootstrap registry. - The cached lifecycle env re-registers its disks on every use, surviving other serial tests' reset_local_disk_test_state. - Hermetic SetDisks helpers gain isolated-context variants pinned to plain erasure; tier-free non-serial test modules use them, guard-based SetupTypeGuard tests stay on the bootstrap context. - Three deterministic pin tests (nextest-safe) cover the caching contract, the delete gate resolution source, and the ns-lock resolution source. Verification: - cargo test -p rustfs-ecstore --lib -- --exact <4-test combo from the report> (previously failing, now green) - cargo test -p rustfs-ecstore --lib: 3169 passed / 0 failed across repeated runs; cargo fmt --check and cargo clippy --lib --tests clean - Adversarial validation (high-risk tier, all seven roles) run per AGENTS.md; all findings fixed or rebutted with evidence
This commit is contained in:
@@ -649,7 +649,7 @@ impl BucketMetadata {
|
||||
Ok(())
|
||||
}
|
||||
|
||||
fn default_timestamps(&mut self) {
|
||||
pub(crate) fn default_timestamps(&mut self) {
|
||||
if self.policy_config_updated_at == OffsetDateTime::UNIX_EPOCH {
|
||||
self.policy_config_updated_at = self.created
|
||||
}
|
||||
@@ -1093,16 +1093,25 @@ pub async fn load_bucket_metadata(api: Arc<ECStore>, bucket: &str) -> Result<Buc
|
||||
}
|
||||
|
||||
pub async fn load_bucket_metadata_parse(api: Arc<ECStore>, bucket: &str, parse: bool) -> Result<BucketMetadata> {
|
||||
let mut bm = match read_bucket_metadata(api.clone(), bucket).await {
|
||||
Ok(res) => res,
|
||||
Ok(load_bucket_metadata_parse_with_presence(api, bucket, parse).await?.0)
|
||||
}
|
||||
|
||||
/// The returned `bool` reports whether the metadata was actually read from
|
||||
/// persisted storage; `false` means no metadata exists for this bucket on this
|
||||
/// store and the returned value is a fabricated in-memory default.
|
||||
pub(crate) async fn load_bucket_metadata_parse_with_presence(
|
||||
api: Arc<ECStore>,
|
||||
bucket: &str,
|
||||
parse: bool,
|
||||
) -> Result<(BucketMetadata, bool)> {
|
||||
let (mut bm, persisted) = match read_bucket_metadata(api.clone(), bucket).await {
|
||||
Ok(res) => (res, true),
|
||||
Err(err) => {
|
||||
if err != Error::ConfigNotFound {
|
||||
return Err(err);
|
||||
}
|
||||
|
||||
// info!("bucketmeta {} not found with err {:?}, start to init ", bucket, &err);
|
||||
|
||||
BucketMetadata::new(bucket)
|
||||
(BucketMetadata::new(bucket), false)
|
||||
}
|
||||
};
|
||||
|
||||
@@ -1112,7 +1121,7 @@ pub async fn load_bucket_metadata_parse(api: Arc<ECStore>, bucket: &str, parse:
|
||||
bm.parse_all_configs()?;
|
||||
}
|
||||
|
||||
Ok(bm)
|
||||
Ok((bm, persisted))
|
||||
}
|
||||
|
||||
async fn read_bucket_metadata(api: Arc<ECStore>, bucket: &str) -> Result<BucketMetadata> {
|
||||
|
||||
Reference in New Issue
Block a user