Since 1.0.2 an encrypted object's ETag is a keyed fingerprint, not the
plaintext MD5. A target that computes its own ETag (AWS S3, Wasabi) never
reports it, so every "find the existing replica by exact ETag" step missed
encrypted objects on targets that mint their own version ids:
- a heal / MRF re-drive after a lost PUT response wrote a second version;
- an existing-object resync re-PUT a replica its ledger already named
(the ledger-located HEAD was confirmed by ETag only), and on the AWS
400 shape the ledger was not consulted at all;
- resync verification counted such replicas as failed;
- a ledger-less version purge reported the replica as already gone.
Encrypted sources now recognise their replica by shape: the byte count the
replication PUT sent (plaintext for managed SSE, ciphertext for SSE-C) and
a target write time no earlier than the source version. An ETag match
still wins (RustFS/MinIO targets). The ledger is consulted first on both
the 404 and the AWS 400 shape. Without a ledger, only a unique shape match
among the unclaimed ListObjectVersions candidates is adopted and recorded;
several shape matches mean re-PUT for convergence and a refused purge. The
AWS current-version fallback stays ETag-only, and a listing the
target refuses on the 400/403 shape keeps that fallback (re-PUT) rather
than stalling. An unversioned target's `null` version is never matched by
shape: it holds whichever generation was written last. Plaintext sources keep exact
ETag identity.
Builds on the ETag-computing fake target mode and the ComputesOwnEtags
matrix row from rustfs#8583. Adds an SSE-S3 variant of the mint-own-ids
re-drive test (red before this change: the heal left two target versions),
and both variants now also assert the purge.
* fix(scanner): treat replication status writebacks as status-class hits
A replication status writeback (persist_replication_state_if_current in
Update mode, including the heals the scanner queues during its own walk)
marked the bucket dirty on the namespace path: it advanced the dirty-usage
generation, woke the scanner, reached the durable dirty journal and
entered the activity snapshot. Any replicated bucket therefore made every
scanner cycle Superseded, the authoritative usage baseline was never
certified and usage freshness stayed stale for as long as replication ran
(#8375).
The writeback is now status class: record_status_class_mutation records
only the process-local producer coverage bit and nothing else. There is
no rescan queue for it, because a deployment with an active replication
rule already walks every bucket on every cycle
(ScannerMaintenanceFeatures::needs_regular_cycle) and that walk refreshes
replication_stats. The routing lives in a named, unit-tested function in
rustfs/src/storage/storage_api.rs; tier-expiration cleanup removes data
and stays on the namespace path.
No persisted format, protocol, admin API or configuration changes.
This is phase 1 of docs/architecture/scanner-per-bucket-convergence.md,
which this change adds together with its index entry.
Refs #8375, #8494, rustfs/backlog#2816.
* fix(scanner): refresh replication statistics during maintenance
Refresh compacted prefixes and completed bucket caches during replication maintenance. Bind set execution reuse to the observed replication statistics so a same-cycle retry cannot restore older counters.
Co-Authored-By: heihutu <heihutu@gmail.com>
Co-Authored-By: zhi22915 <qiuzgang@gmail.com>
* test(scanner): avoid expanding the legacy S3 DTO surface
Decode the existing replication configuration type from a JSON fixture instead of adding direct S3 DTO references to a new file. Preserve the compacted-prefix and same-cycle assertions and the footprint ratchet.
Co-Authored-By: heihutu <heihutu@gmail.com>
Co-Authored-By: zhi22915 <qiuzgang@gmail.com>
* perf(scanner): keep raw enumeration bookkeeping linear per entry
The page writer inserted into its building page with a push-and-sort on
every entry and committed each page through a clone. Insert in sorted
position and move the committed page into the index instead.
Add a regression test that records 20,000 entries in one prefix and pins
the cost to one hash per entry and well under a second, so the quadratic
re-normalization removed by #8114 (rustfs#8113) cannot return once pacing
builds on this walker.
* feat(scanner): decouple bucket walkers from disk count
Add the scanner key walkers_per_disk (RUSTFS_SCANNER_WALKERS_PER_DISK,
1 through 16, default 1). Each local coordinator disk of a set spawns that
many bucket walkers; remote disks keep one. The walker count is what
max_concurrent_disk_scans caps and the disk count stays the floor.
The walkers of one disk share its scanner admission through
LocalDiskAdmissionShare: the first walker to start a bucket takes the
per-disk permit and the last to finish releases it, so a peer's remote
request still sees one scan session per physical disk. Without the share
the second walker was rejected as busy and retired.
The disk_concurrency_budget log line reports walkers_per_disk, walkers and
the reason for the effective limit. The default stays 1 because no local
disk reports rotational media today; the design keeps a higher flash
default as the intent.
* docs(scanner): document walkers_per_disk in the Helm chart and configuration manuals
RUSTFS_SCANNER_WALKERS_PER_DISK was only described in the scanner runtime
controls table. Add it to the Helm chart (values, configmap rendering,
README table, template test), the configuration crate's environment
reference with operator guidance, and a short section in the operations
manual on when to raise it and how to confirm it took effect.
---------
Co-authored-by: Hauser <housemecn@gmail.com>
Co-authored-by: heihutu <heihutu@gmail.com>
Co-authored-by: zhi22915 <qiuzgang@gmail.com>
The outbound target matrix only modeled targets that adopt the forwarded
source ETag, so the post-PUT replica ETag audit was never exercised against
a target that computes its own ETag (AWS S3 and most compatible stores),
and no matrix shape was encrypted. That gap let the SSE-S3 "replica etag
mismatch" regression fixed in #8573 ship unnoticed.
Add an ignore_source_etags mode to the fake S3 target, a ComputesOwnEtags
matrix row that uses it, and an SseS3 object shape (the source runs with the
local KMS). The shape asserts its source ETag is not the plaintext MD5 so
the cell cannot pass vacuously. Against a build without #8573 the new row
fails exactly computes-own-etags/SseS3 with "replica etag mismatch"; with it
the whole matrix passes.
Also correct the #8573 docs and comment that called the replication PUT
checksum the integrity check for encrypted sources: managed-SSE sources
forward no checksum, so their replicas have no post-PUT content audit.
New encrypted writes store a keyed HMAC fingerprint as the object ETag
(docs/operations/encrypted-etags.md). Replication forwards that ETag on
x-rustfs-source-etag, but a target that computes its own ETag (AWS S3 and
most compatible stores) answers the plaintext PUT with the MD5 of what it
received. Both values are 32 hex characters, so verify_single_part_replica
treated the fingerprint as a comparable MD5 and failed every single-part
SSE-S3 / SSE-KMS replica with "replica etag mismatch"; MRF and resync then
retried the object forever. RustFS and MinIO targets adopt the source ETag
and were unaffected.
Exempt sources whose stored ETag cannot describe the wire bytes: any
managed-SSE or SSE-C source, decided by the existing replication
source-encryption classifier. The checksum header on the replication PUT
remains the integrity check for those objects; plaintext sources keep the
audit unchanged.
Claude-Session: https://claude.ai/code/session_01CezCdjE9AdShFUi9tNk797
Co-authored-by: Claude Fable 5.1 <noreply@anthropic.com>
* fix(ecstore): retain system metadata repair ownership
Return system metadata convergence failures to the fenced writer after
committed cleanup instead of submitting an unexecutable MRF handoff.
Drain system rename tails before acknowledging and preserve ordinary
incarnation-bound object repair.
Co-Authored-By: heihutu <heihutu@gmail.com>
Co-Authored-By: zhi22915 <qiuzgang@gmail.com>
* refactor(ecstore): separate PUT commit and completion outcomes
Keep committed metadata writes on their retained cleanup owner when the
writer must handle repair. Propagate the completion error at the API
boundary without a duplicate temporary-data deletion or worker wait.
Co-Authored-By: heihutu <heihutu@gmail.com>
Co-Authored-By: zhi22915 <qiuzgang@gmail.com>
* fix(ecstore): scope repair completion to pool metadata owners
Keep ordinary system metadata quorum-compatible and explicitly select
owner-observed repair completion for fenced pool metadata CAS writes.
Seed format-heal metadata before injecting the missing-format fault.
Preserve degraded bucket recreation and test all completion modes.
Co-Authored-By: heihutu <heihutu@gmail.com>
Co-Authored-By: zhi22915 <qiuzgang@gmail.com>
---------
Co-authored-by: heihutu <heihutu@gmail.com>
Co-authored-by: zhi22915 <qiuzgang@gmail.com>
Retain typed retryable catalog lock failures and route S3 publication
errors through the canonical storage conversion for bounded metrics,
public-message redaction, and existing retry advice.
Borrow CAS results for metrics instead of cloning opaque error sources.
Cover authorization under a real publication writer, HTTP serialization,
source preservation, recovery, and established catalog error categories.
Co-authored-by: heihutu <heihutu@gmail.com>
Co-authored-by: zhi22915 <qiuzgang@gmail.com>
Add a one-second Retry-After hint at the canonical S3 error conversion
only for ServiceUnavailable responses retaining a typed lock timeout.
Keep existing error codes, source chains, and lock budgets unchanged.
Cover actual HTTP/XML serialization, nested causes, private-resource
redaction, and unrelated disk/quorum/text failures. Document the response
contract and the limits of log-count and five-second timeout attribution.
Co-authored-by: heihutu <heihutu@gmail.com>
Co-authored-by: zhi22915 <qiuzgang@gmail.com>
refactor(heal): index replacement generation reconciliation
Reconcile owned records and their definitive sources in one pass. Group claims by target slot and use a shared-anchor fast path while retaining pairwise ambiguity checks.
Co-authored-by: heihutu <heihutu@gmail.com>
Co-authored-by: zhi22915 <qiuzgang@gmail.com>
Keep same-name buckets in independent clusters separate while deduplicating
replicated usage observations. Document the existing scanner-backed exporter
and cover its gauge contract and cluster-scoped queries.
Co-authored-by: heihutu <heihutu@gmail.com>
Co-authored-by: zhi22915 <qiuzgang@gmail.com>
* fix(scanner): reuse observations and expose complete usage
Allow superseded retries to reach the existing validated cache planner while
bootstrap remains pending. Serve complete observations in server info without
changing quota authority or dirty acknowledgements.
Co-Authored-By: heihutu <heihutu@gmail.com>
Co-Authored-By: zhi22915 <qiuzgang@gmail.com>
* test(scanner): route fixture setup through storage boundary
Keep the single-disk scanner fixture on the existing storage_api boundary
instead of importing the ECStore API facade directly.
Co-Authored-By: heihutu <heihutu@gmail.com>
Co-Authored-By: zhi22915 <qiuzgang@gmail.com>
---------
Co-authored-by: heihutu <heihutu@gmail.com>
Co-authored-by: zhi22915 <qiuzgang@gmail.com>
* fix(ecstore): recover crash-interrupted delete retries
Retain set-quorum cleanup proof and restore metadata before dropping rollback
markers. Reclaim eligible exact-key residue during explicit delete retries,
with bucket identity, version, retention and namespace fencing guards.
Preserve prefix children and snapshot ownership through batched physical
cleanup, and cover interrupted transactions and failure boundaries.
Co-Authored-By: heihutu <heihutu@gmail.com>
Co-Authored-By: zhi22915 <qiuzgang@gmail.com>
* fix(ecstore): route recovery test imports through contracts
Co-Authored-By: heihutu <heihutu@gmail.com>
Co-Authored-By: zhi22915 <qiuzgang@gmail.com>
* fix(ecstore): preserve missing-key deletes at quorum
* feat(ecstore): add certified set-wide delete recovery
Atomically prepare deletion journals and exact targets, publish durable set
receipts, and recover through one fenced disk/RPC core used by startup and
scoped administrator healing. Preserve returning generations, ordinary
missing-key quorum semantics, and legacy rollback wire compatibility.
Retain namespace and volume ownership through late physical operations,
order related transactions causally, and keep proof until full convergence.
Remove the superseded local-only recovery path and add storage, protocol,
RPC, durability and isolated Docker regression coverage.
Co-Authored-By: heihutu <heihutu@gmail.com>
Co-Authored-By: zhi22915 <qiuzgang@gmail.com>
* fix(ecstore): reclaim completed multipart delete sidecars
* fix(ecstore): recover multipart sidecars with verified proofs
Recognize native multipart sidecars at the shared recovery boundary and
restore them without treating metadata or proof files as shard payloads.
Validate required proof generations and bind every present live/staged
shard copy to its metadata-bound Merkle proof before restoring metadata.
Cover protected native MPU rollback, split source layouts, missing or
corrupt proofs, and payload corruption with recomputed bitrot checksums.
Add real multipart Docker regressions in both integrity modes.
Co-Authored-By: heihutu <heihutu@gmail.com>
Co-Authored-By: zhi22915 <qiuzgang@gmail.com>
* fix(ecstore): settle superseded committed version deletes
Allow a validated committed decision to finish its own data cleanup after
a later decision removes current metadata. Prepared copies need an
inspected same-transaction receipt matching immutable local intent before
promotion, and retain their local journal without importing peer hashes.
Reuse the authority matcher for dry-run and settlement. Cover chained
explicit-version deletions, partial receipt publication, mismatch rejection
and no-resurrection, while retaining the no-decision absence protection.
Co-Authored-By: heihutu <heihutu@gmail.com>
Co-Authored-By: zhi22915 <qiuzgang@gmail.com>
* test(ecstore): clarify delete recovery case label
Co-Authored-By: heihutu <heihutu@gmail.com>
Co-Authored-By: zhi22915 <qiuzgang@gmail.com>
* fix(ecstore): restore recovery CI guard coverage
Keep production error sites visible to the ratchet by placing test modules last. Preserve native encoding errors, group preparation identity and ownership, and reduce RPC enum size without changing the wire payload.
Co-Authored-By: heihutu <heihutu@gmail.com>
Co-Authored-By: zhi22915 <qiuzgang@gmail.com>
* fix(admin): preserve owned OIDC validation errors
Co-Authored-By: heihutu <heihutu@gmail.com>
Co-Authored-By: zhi22915 <qiuzgang@gmail.com>
* refactor(ecstore): unify recovery authority and snapshot work
Use one user-bucket legacy settlement boundary and one adoption source predicate for preview and execution. Reuse immutable snapshot digests, consume owned generation metadata, index version membership, and prepare empty witnesses through the canonical journal path.
Co-Authored-By: heihutu <heihutu@gmail.com>
Co-Authored-By: zhi22915 <qiuzgang@gmail.com>
* fix(ecstore): preserve delete recovery invariants
---------
Co-authored-by: heihutu <heihutu@gmail.com>
Co-authored-by: zhi22915 <qiuzgang@gmail.com>
Co-authored-by: overtrue <anzhengchao@gmail.com>
* feat(tls): reload external certificate snapshots coherently
Pin projected certificate generations, validate complete TLS material, coordinate server consumers, and invalidate outbound RPC caches coherently. Add externally managed TLS Secret support and rotation guidance.
Co-Authored-By: heihutu <heihutu@gmail.com>
Co-Authored-By: zhi22915 <qiuzgang@gmail.com>
* feat(tls): publish server certificates through a fenced admin API
Add opt-in server-leaf publication with dedicated IAM actions, actual TLS
transport checks, immutable generations, durable captured-token CAS and
idempotent receipts. Preserve independent trust and client identity sources
and distinguish visible publication state from the full serving chain.
Validate 64 TLS tests, 41 TLS-runtime tests, the focused IAM policy test,
and eight live local API scenarios including least privilege and restart.
Co-Authored-By: heihutu <heihutu@gmail.com>
Co-Authored-By: zhi22915 <qiuzgang@gmail.com>
* fix(admin): route certificate handler types through S3 facade
Use the existing admin S3 facade to keep direct s3s imports within the footprint ratchet.
Co-Authored-By: heihutu <heihutu@gmail.com>
Co-Authored-By: zhi22915 <qiuzgang@gmail.com>
* test(admin): include TLS certificate routes in route matrix
Account for the registered certificate-state GET and certificate publication POST without changing route behavior or weakening matrix assertions.
Co-Authored-By: heihutu <heihutu@gmail.com>
Co-Authored-By: zhi22915 <qiuzgang@gmail.com>
* fix(tls): reconcile startup trust before skipping reloads
Compare the initialized listener bundle with coherently published outbound material, retain startup trust and client identity when sources disappear, and cover independent startup rotations through real reload passes.
Co-Authored-By: heihutu <heihutu@gmail.com>
Co-Authored-By: zhi22915 <qiuzgang@gmail.com>
* refactor(tls): reuse pinned generations and prepared listener state
Co-Authored-By: heihutu <heihutu@gmail.com>
Co-Authored-By: zhi22915 <qiuzgang@gmail.com>
* fix(tls): preserve startup trust source requirements
---------
Co-authored-by: heihutu <heihutu@gmail.com>
Co-authored-by: zhi22915 <qiuzgang@gmail.com>
Co-authored-by: overtrue <anzhengchao@gmail.com>
* fix(scanner): bound old-cache lookups and recover checkpoint saves
Keep missing child lookups read-only and preserve the checkpoint receiver
after ordinary persistence errors. Reload on stale CAS or indeterminate
revision refresh, and report confirmed periodic saves separately.
Co-Authored-By: heihutu <heihutu@gmail.com>
Co-Authored-By: zhi22915 <qiuzgang@gmail.com>
* fix(scanner): remove redundant checkpoint error conversion
Return the existing StorageError directly so strict Clippy passes.
Co-Authored-By: heihutu <heihutu@gmail.com>
Co-Authored-By: zhi22915 <qiuzgang@gmail.com>
* docs(scanner): clarify checkpoint persistence guarantees
Distinguish a confirmed periodic save from validated restart coverage.
Keep adoption and subtree-skip requirements explicit.
Co-Authored-By: heihutu <heihutu@gmail.com>
Co-Authored-By: zhi22915 <qiuzgang@gmail.com>
* fix(scanner): preserve resumable periodic coverage
Materialize active ancestor accounting in bounded periodic snapshots and
seal completed coverage independently of raw enumeration state. Preserve
durable coverage during early resumed enumeration and exclude unfinished
out-of-order heal work from periodic and cancellation receipts.
Reuse ancestor frame slots to avoid growing child-set copies on descent,
retain compacted accumulator safety, and report checkpoint adoption resets.
Co-Authored-By: heihutu <heihutu@gmail.com>
Co-Authored-By: zhi22915 <qiuzgang@gmail.com>
* fix(scanner): reject covered active ancestors in checkpoints
Check every suspended ancestor alongside the current folder before
certifying completed coverage. An unfinished covered ancestor must not
become a resumable subtree merely because its descendant sorts later.
Co-Authored-By: heihutu <heihutu@gmail.com>
Co-Authored-By: zhi22915 <qiuzgang@gmail.com>
* fix(scanner): retain an incomplete root for missing namespaces
Create the empty bucket root explicitly at the missing-namespace boundary.
Preserve nonempty durable caches and keep namespace results unpublished.
Co-Authored-By: heihutu <heihutu@gmail.com>
Co-Authored-By: zhi22915 <qiuzgang@gmail.com>
---------
Co-authored-by: heihutu <heihutu@gmail.com>
Co-authored-by: zhi22915 <qiuzgang@gmail.com>
* fix(lifecycle): coordinate tier free-version recovery scans
* fix(lifecycle): remove obsolete recovery enqueue entry point
* test(upgrade): wait for writers after each rolling replacement
Reuse the existing UTF-8 byte minimum for credential creation so long service account secrets remain intact. Keep generated secrets at 40 bytes and document older receiver and import constraints.
* feat(table-catalog): support disabling empty catalogs
* fix(admin): use the storage error domain module
* style(admin): format the publication fence error
* fix(table-catalog): use shared API error constructors
* fix(oidc): ignore groups without a matching policy at login
OIDC login failed with "OIDC policy mapping did not resolve to current
policies" whenever any mapped group lacked a policy of the same name.
Directory-backed providers such as Active Directory always emit groups
like `DOMAIN\Domain Users` that can never be mapped, so group-based
authorization was impossible there.
Keep only policy names that resolve to an existing policy and are valid
in session claims, and reject the login only when none remain. The
signed `policy` claim still lists only resolved names, so request-time
evaluation and site replication receivers keep their invariant.
Refs #8163
* fix(oidc): only ignore unmapped groups-claim values
Limit the relaxed resolution to policy names derived solely from the
groups claim. Names from ROLE_POLICY, a dedicated CLAIM_NAME claim, or
an explicit IAM policy mapping must still all resolve.
Reject the login when a mapped name refers to an existing policy whose
name is not allowed in session claims: dropping it could remove an
explicit Deny and broaden access.
Claim-unsafe names are only checked against the in-memory policy cache
and never passed to storage-backed policy loading.
Refs #8163
* docs(oidc): document ignorable roles claim values and cover wiring
Roles claim values are merged into the canonical groups, so values
without a matching policy are ignored like groups-claim values. This
covers built-in provider roles such as Keycloak's `offline_access`.
Document that in the field and method docs and in the provider
requirements, and pin it with a test.
Assert that the OIDC authorization carries the group claim policies so
a regression in the wiring cannot silently disable the relaxation.
Refs #8163
* fix(oidc): ignore group policies only after confirmed absence
merge_policies drops names whose load fails, so a storage or decode
error for an uncached group policy was indistinguishable from a missing
one. The group name was then ignored and the session signed without it,
which could remove an existing Deny that request-time checks cannot
restore.
Add IamSys::policy_exists, which consults the cache and then storage and
reports false only for NoSuchPolicy while returning every other error.
The OIDC binding now ignores a group-derived name only after a confirmed
absence and rejects the login when a lookup fails.
Refs #8163
---------
Co-authored-by: cxymds <cxymds@gmail.com>
Co-authored-by: Chris <anzhengchao@gmail.com>
* fix(ci): include pagination regression in full E2E selection
* fix(deps): replace yanked yoke-derive release
* fix(scanner): expose pause backlog replica diagnostics (#8258)
* fix(scanner): expose pause backlog replica diagnostics
Co-Authored-By: heihutu <heihutu@gmail.com>
Co-Authored-By: zhi22915 <qiuzgang@gmail.com>
* fix(connect): stabilize runtime profile lease cancellation
Co-Authored-By: heihutu <heihutu@gmail.com>
Co-Authored-By: zhi22915 <qiuzgang@gmail.com>
* test(connect): tolerate delayed schedule startup in CI
Co-Authored-By: heihutu <heihutu@gmail.com>
Co-Authored-By: zhi22915 <qiuzgang@gmail.com>
* test(e2e): retry quota reads during usage warmup
Co-Authored-By: heihutu <heihutu@gmail.com>
Co-Authored-By: zhi22915 <qiuzgang@gmail.com>
* fix(ecstore): avoid meta-bucket incarnation self-deadlock
Co-Authored-By: heihutu <heihutu@gmail.com>
Co-Authored-By: zhi22915 <qiuzgang@gmail.com>
* fix(test): use persisted incarnation in heal fixture
Co-Authored-By: heihutu <heihutu@gmail.com>
Co-Authored-By: zhi22915 <qiuzgang@gmail.com>
---------
Co-authored-by: zhi22915 <qiuzgang@gmail.com>
* fix(usage): reconcile stale counters after lifecycle expiration (#8108)
* fix(usage): reconcile stale counters after lifecycle expiration
* fix(usage): account lifecycle expiry during continuous writes
* test(usage): run lifecycle usage scenarios on one scanner store
* test(usage): use a Windows-representable pre-mutation offset
* fix(usage): harden expiry accounting recovery and quota checks
Borrow expiry receipt bucket names and avoid allocating a map key on cache hits. Cover cancelled receipts, durable snapshot recovery, and legacy quota admission after scanner confirmation. Use representable timestamp offsets in the quota regression.
Refs rustfs/backlog#2689
Co-Authored-By: heihutu <heihutu@gmail.com>
Co-Authored-By: zhi22915 <qiuzgang@gmail.com>
* test(usage): recover stale persisted counts through the scanner
Seed incorrect complete usage for empty and retained-object buckets, then run the real scanner and publication consumer without further object mutations. Verify durable and admin usage over two cycles instead of writing a corrected snapshot in the test.
Refs rustfs/backlog#2689
Refs rustfs/backlog#2691
Co-Authored-By: heihutu <heihutu@gmail.com>
Co-Authored-By: zhi22915 <qiuzgang@gmail.com>
* test(e2e): bound delimiter pagination fixture concurrency
The 120-second smoke timeout expired after 1018 of 1200 serial fixture PUTs, before LIST ran. Prepare the same objects with at most eight concurrent requests and await every PUT. Retain the timeout and strengthen exact prefix, KeyCount, empty Contents, and continuation-token assertions with phase diagnostics.
Refs rustfs/backlog#2689
Co-Authored-By: heihutu <heihutu@gmail.com>
Co-Authored-By: zhi22915 <qiuzgang@gmail.com>
* test(upgrade): establish a persisted previous-release baseline
Seed the pinned previous-release cluster and restart it once with its data intact before replacing any node. Require every old writer to pass the strict readiness probe and preserve the seed through both mixed phases and the final current cluster. Keep InternalError fail-fast behavior and all existing compatibility deadlines and assertions.
Refs rustfs/backlog#2689
Refs rustfs/backlog#2384
Co-Authored-By: heihutu <heihutu@gmail.com>
Co-Authored-By: zhi22915 <qiuzgang@gmail.com>
* test(ecstore): bound cancellation metadata persistence waits
Use the system-bucket incarnation boundary now supplied by main PR #8268. Bound the three cancellation waits that previously hung during pool.bin persistence, retaining their remote-generation, target-cohort, and durable-state assertions.
Refs rustfs/backlog#2697
Refs rustfs/backlog#2689
Co-Authored-By: heihutu <heihutu@gmail.com>
Co-Authored-By: zhi22915 <qiuzgang@gmail.com>
---------
Co-authored-by: Chris <anzhengchao@gmail.com>
Co-authored-by: Hauser <housemecn@gmail.com>
Co-authored-by: heihutu <heihutu@gmail.com>
Co-authored-by: zhi22915 <qiuzgang@gmail.com>
* test(e2e): retain startup and shutdown failure diagnostics
* fix(test): supply CPU workload for sampler regression
* fix(ci): locate security chain scripts in the workspace
* fix(usage): recover historical counters with generation fencing (#8273)
* fix(usage): recover historical counters during continued writes
Use newer converged scanner snapshots to reconcile stale absolute usage
baselines while preserving concurrent mutation and expiry receipt fences.
Cover durable publication, admin and quota reads, and legacy generations.
Co-Authored-By: heihutu <heihutu@gmail.com>
Co-Authored-By: zhi22915 <qiuzgang@gmail.com>
* refactor(usage): fence snapshots and move preserved cache entries
Apply the cached scanner generation floor before every reconciliation path
and retain it even when an older snapshot happens to match core counts.
Move preserved usage entries instead of cloning their histogram maps under
the cache lock, retaining expiry receipt identity and cancellation fences.
Co-Authored-By: heihutu <heihutu@gmail.com>
Co-Authored-By: zhi22915 <qiuzgang@gmail.com>
---------
Co-authored-by: heihutu <heihutu@gmail.com>
Co-authored-by: zhi22915 <qiuzgang@gmail.com>
* test(scanner): verify checkpoint takeover and repair dispatch (#8275)
* test(scanner): cover checkpoint handoff and repair dispatch
Drive runtime budget expiry, partial-cycle persistence, leadership claims,
and stale checkpoint rejection between real disk-backed fixture scans.
Verify that a metadata repair beyond the first bounded prefix is saved in
the scanner ledger and dispatched by the MRF consumer.
Co-Authored-By: heihutu <heihutu@gmail.com>
Co-Authored-By: zhi22915 <qiuzgang@gmail.com>
* ci: isolate scanner fixtures and refresh full e2e membership
Reserve nextest capacity for the real-disk scanner publication and MRF
admission fixtures. Bind both platform membership checks to the reviewed
pagination deadline test added on main.
Co-Authored-By: heihutu <heihutu@gmail.com>
Co-Authored-By: zhi22915 <qiuzgang@gmail.com>
* refactor(scanner): consolidate checkpoint fixture lifecycle
Keep one durable control store across timeout and leadership transitions,
and inject generation advancement into the shared checkpoint scenario.
Check the actual saved metadata path so late-write rejection also proves
that existing checkpoint bytes remain intact.
Centralize MRF fixture isolation and reuse nextest process isolation when
the startup environment already satisfies the test contract.
Co-Authored-By: heihutu <heihutu@gmail.com>
Co-Authored-By: zhi22915 <qiuzgang@gmail.com>
---------
Co-authored-by: heihutu <heihutu@gmail.com>
Co-authored-by: zhi22915 <qiuzgang@gmail.com>
* fix(obs): distinguish allocator counters from live memory (#8274)
* fix(obs): distinguish allocator counters from live memory
Preserve count/counter semantics and mark requested-byte attribution unavailable when live statistics or sampling are missing. Document sustained multipart memory diagnosis.
Co-Authored-By: heihutu <heihutu@gmail.com>
Co-Authored-By: zhi22915 <qiuzgang@gmail.com>
* refactor(obs): parse allocator statistics from one node
Resolve each statistic before interpreting its shape, avoiding unsupported-field tree scans and mixing data across wrapper scopes. Preserve unavailable-statistics policy and add precedence regressions.
Co-Authored-By: heihutu <heihutu@gmail.com>
Co-Authored-By: zhi22915 <qiuzgang@gmail.com>
* test(ecstore): isolate late parity recovery from metadata hedges
Use the existing object-scoped hedge timer barrier in exact-count recovery fixtures. Preserve payload and total-read assertions and verify that the omitted parity disk is read only during late refresh.
Co-Authored-By: heihutu <heihutu@gmail.com>
Co-Authored-By: zhi22915 <qiuzgang@gmail.com>
---------
Co-authored-by: heihutu <heihutu@gmail.com>
Co-authored-by: zhi22915 <qiuzgang@gmail.com>
* fix(usage): combine identical snapshot retention branches
* fix(test): await HTTP sender readiness in Top RPC fixture
* [release/1.0.1] Gate multipart copy through write admission (#8284)
Gate multipart copy through write admission
Make UploadPartCopy acquire the shared foreground write admission permit before lifecycle locks or source readers so server-side multipart copy cannot bypass the same backpressure used by UploadPart. Document the shared queue semantics and add focused coverage for saturation, cancellation, lock ordering, and disabled admission.
Co-authored-by: zhi22915 <qiuzgang@gmail.com>
* Gate multipart copy through write admission (#8283)
Make UploadPartCopy acquire the shared foreground write admission permit before lifecycle locks or source readers so server-side multipart copy cannot bypass the same backpressure used by UploadPart. Document the shared queue semantics and add focused coverage for saturation, cancellation, lock ordering, and disabled admission.
Co-authored-by: zhi22915 <qiuzgang@gmail.com>
* fix: add UploadPart OOM validation guardrails (#8287)
* docs(release): validate candidates on release branch
* fix(scanner): validate checkpoints against global cycle fence (#8278)
## Related Issues
Related to rustfs/backlog#2701.
## Summary of Changes
Route scanner checkpoint cycle and leader validation through the global store while retaining the owning set for cache persistence, CAS revisions and publication admission.
## Verification
Two independent final-diff source reviews found no issues across correctness, concurrency and durability, test coverage, compatibility, performance and simplicity on head `8b8fe51d092090b053f552ae283960e2e306be33`. Root approval `5373624714` is bound to that exact head. Regression tests cover real two-pool routing, stale fences, post-save rejection and CAS conflicts; their reported local execution belongs to the PR author, not this merge operation. Current required CI remains pending, and this authorized admin squash does not establish CI or runtime acceptance.
## Impact
Restores checkpoint progress when global cycle and leader state differ from a set-scoped view. No format, retry, timeout, assertion or scanner-policy changes are introduced by this diff. The three prior main scanner failures remain unproved repaired.
## Additional Notes
Full validation must run on the resulting exact main revision. Reverting this patch restores the earlier set-scoped fence lookup and its checkpoint rejection behavior.
* fix(ci): restore E2E membership and pagination timeouts (#8281)
* ci: locate the auto-testing checkout for lanes that run evidence from a subdirectory (#8279)
## Related Issues
Follow-up to #8229.
## Summary of Changes
Locate the private auto-testing checkout from the lane root or the workspace root so the nested security checkout can record functional-chain evidence.
## Verification
The exact PR head b66129ab9f passed one mechanical correctness and simplicity review, nine real-Git layout and provenance checks, and sixteen existing evidence/envelope tests. The baseline sibling layout failed with git exit 128; the corrected layout succeeded while revision mismatches and missing checkouts stayed rejected. Current PR checks are completed with successful or skipped conclusions, including the aggregate.
## Impact
Both lane and private-script revision checks remain intact. No time limits, assertions, production behavior, or evidence validation requirements change. The synthetic layout checks do not execute the actual scheduled security suite; integrated main CI and release acceptance remain separate gates.
## Additional Notes
Approved review 5374559393 is bound to the exact head above. Reverting the single-file change restores the previous checkout lookup.
* fix: add UploadPart OOM validation guardrails
Add a Docker validation harness for backlog#2704 so the ordinary UploadPart
low-concurrency memory workload can be reproduced with comparable case metadata,
process/cgroup sampling, TLS and metrics toggles, cache-env controls, and write
reclaim/direct-write experiments.
Warn when operators set the unrecognized RUSTFS_OBJECT_CACHE_* variables that
appeared in the reporter compose file. The variables are reported but remain
ignored, so startup does not silently change object data cache behavior.
Co-Authored-By: heihutu <heihutu@gmail.com>
Co-Authored-By: zhi22915 <qiuzgang@gmail.com>
---------
Co-authored-by: overtrue <anzhengchao@gmail.com>
Co-authored-by: AL <allan.bednarowski@gmail.com>
Co-authored-by: hector <42570491+majinghe@users.noreply.github.com>
Co-authored-by: heihutu <heihutu@gmail.com>
Co-authored-by: zhi22915 <qiuzgang@gmail.com>
* fix(scanner): pass fence store to checkpoint fixture
* fix(s3): queue bucket operations and restore strict Clippy checks (#8290)
* fix(s3): queue concurrent bucket creation and deletion
Keep eight active bucket transactions and bound admission waiting to 128 requests and 30 seconds. Preserve detached transaction ownership and return Retry-After with overload responses.
Co-Authored-By: heihutu <heihutu@gmail.com>
Co-Authored-By: zhi22915 <qiuzgang@gmail.com>
* fix(ecstore): restore strict Clippy compatibility on Rust 1.99
Use try_update without changing atomic ordering or overflow behavior. Keep
recursive storage futures boxed once at each frame and remove the redundant
async-recursion macro, including its non-recursive SQL planner use. Remove
needless closure borrows and orphaned dependency entries.
Co-Authored-By: heihutu <heihutu@gmail.com>
Co-Authored-By: zhi22915 <qiuzgang@gmail.com>
---------
Co-authored-by: heihutu <heihutu@gmail.com>
Co-authored-by: zhi22915 <qiuzgang@gmail.com>
* chore: refresh dependencies and atomic update APIs
Update workspace dependencies and the lockfile. Replace deprecated
atomic fetch_update aliases with try_update while preserving closures
and memory ordering.
Co-Authored-By: heihutu <heihutu@gmail.com>
Co-Authored-By: zhi22915 <qiuzgang@gmail.com>
* improve
* fix(scanner): diagnose and verify pause backlog recovery (#8293)
* fix(scanner): diagnose and verify pause backlog recovery
Expose the retained replica snapshot and claimed membership in abnormal
admin status responses. Keep diagnostics off metrics updates and verify
single-pool recovery and conflicting-proof preservation across 24 sets.
Co-Authored-By: heihutu <heihutu@gmail.com>
Co-Authored-By: zhi22915 <qiuzgang@gmail.com>
* refactor(scanner): move replica snapshots into diagnostics
Consume the terminal admin read snapshot in a single state match and move
membership, revision, and error buffers into the response. Verify buffer
handoff and the unchanged JSON contract without altering ledger authority.
Co-Authored-By: heihutu <heihutu@gmail.com>
Co-Authored-By: zhi22915 <qiuzgang@gmail.com>
---------
Co-authored-by: heihutu <heihutu@gmail.com>
Co-authored-by: zhi22915 <qiuzgang@gmail.com>
* fix(heal): wait for held legacy responsibility in replay test
* ci: remove Docker Hub description sync
* fix: emit NextPartNumberMarker only when ListParts is truncated
ListPartsInfo.next_part_number_marker was a non-optional usize that
defaulted to 0 and was only assigned when the response was truncated.
The S3 serializer then emitted it unconditionally as Some(0), causing
AWS SDK paginators to loop infinitely on part_number_marker=0 instead
of terminating.
Change the field to Option<usize> (None by default) and set it only
inside the is_truncated branch. The S3 output layer now uses
.and_then() so NextPartNumberMarker is absent when IsTruncated=false,
matching AWS S3 behavior.
Fixes#8208
(cherry picked from commit 44de803a38)
* fix(s3): honor sparse ListParts markers and verify termination
Resume part listings at the first part above the numeric marker, even
when that marker is absent. Use binary search over the sorted part
numbers and retain the existing exact-tail empty-slice path.
Add storage, XML, and real AWS SDK paginator regressions for empty and
terminal pages, sparse markers, and multipart completion integrity.
Co-Authored-By: heihutu <heihutu@gmail.com>
Co-Authored-By: zhi22915 <qiuzgang@gmail.com>
(cherry picked from commit 673031eea1)
* fix(storage): publish delete rollback backups atomically
Stage rollback metadata outside the rollback directory and publish it only after the full write succeeds. A short write must not leave a backup that quorum rollback can rename over acknowledged version history.
Add an isolated real short-write regression and register the backported ListParts SDK test in the smoke and Linux full inventories.
* test(e2e): register paginator regression in Darwin inventory
* fix(release): install yq before Helm template checks
* chore(release): align installation references for 1.0.1
---------
Co-authored-by: Hauser <housemecn@gmail.com>
Co-authored-by: zhi22915 <qiuzgang@gmail.com>
Co-authored-by: Peder Bergan <pederbe@users.noreply.github.com>
Co-authored-by: heihutu <heihutu@gmail.com>
Co-authored-by: AL <allan.bednarowski@gmail.com>
Co-authored-by: hector <42570491+majinghe@users.noreply.github.com>
Co-authored-by: Chapman <touch65536@gmail.com>
* fix(sse): count copy-source SSE-C headers in the TLS transport guard
The SSE-C transport guard only looked at the object's own customer-key
headers. A CopyObject or UploadPartCopy that read an SSE-C source into a
non-SSE-C destination carried the source key only in the
x-amz-copy-source-server-side-encryption-customer-* headers, so it was
accepted on a plaintext transport with RUSTFS_SSE_C_REQUIRE_TLS=true and
was missing from rustfs_ssec_plaintext_requests_total.
Treat the copy-source triple as SSE-C headers too.
* fix(sse): reject a KMS context key that replaces the location entry
Managed SSE wraps each data key under an encryption context that carries
{bucket: bucket/key}, added with or_insert, while only the client context
is persisted and the entry is rebuilt on read. A client context entry
keyed by the bucket name therefore replaced the location entry on write
and on every read, so the data key was no longer tied to the object's
location.
Reject such a context with 400 InvalidArgument at the single managed-SSE
write entry, before the KMS is called. The read side is unchanged, so
objects stored with such an entry stay readable, and other keys,
including other bucket names, are still accepted.
---------
Co-authored-by: Hauser <housemecn@gmail.com>
## Related Issues
Resolves the corrected lifecycle fixture findings in PR #8254.
## Summary of Changes
Preserve separate incarnation-bound durable MRF responsibilities and their lifecycle audit records, and align replay fixtures with their checkpoint identities.
## Verification
Two independent source reviews and changed-delta reviews are complete. The final review approved 607a0b9bb0 with no remaining supported findings. Local runtime claims were not independently reproduced for this pull request.
## Impact
Keeps storage generation fences and retained responsibility semantics. Test-capacity reservations preserve existing deadlines and assertions.
## Additional Notes
Squash merge of the currently approved fix under the authorized CI-bypass exception. Main CI and release acceptance remain required.
## Related Issues
rustfs/backlog#2682 and rustfs/rustfs#8192.
## Summary of Changes
Reviewed ca970f55ec against d2175d1e1e. No blocking code findings. The hold requires a completed healthy legacy check and an exact incarnation, lease, object, version and scope; it preserves the durable journal and rechecks on restart.
## Verification
Two independent source reviews completed, covering the lenses below. The frozen diff matches Git and passes diff whitespace checks. Reported Cargo and Docker results were not rerun or independently audited in this review.
One factual correction to the PR description: `legacy_sigkill_replay_repairs_without_releasing_unverified_responsibility` uses the default four-member fixture, with three replicas before restoration and four afterward (`mrf_partial_write_test.rs:559,567`). That named regression exercises the production manager path, but is not EC12+4. Other tests in the file use sixteen disks.
## Impact
Correctness: no findings; proofless legacy health never becomes a verified receipt. Security/trust: no findings; exact identity fences remain. Compatibility: no findings; journal encoding remains unchanged. Concurrency/durability: no findings; replay retains one checkpointed owner and replacement generations become retryable. Simplicity: no findings. Coverage: no blocking gap identified, with the test-scope correction above. Performance: no findings; held entries leave the retry index without adding per-admission queue scans.
## Additional Notes
The current main journal failure concerns DecodeFailure, which follows the separate ECDecode task path. This review does not establish that this PR fixes that failure or the scanner-cycle failure, and does not establish a passing main CI or release gate.
EC 2+2 still meets read quorum with two of four nodes up. A survivor
that had not cached a bucket returned 503 on GET, HEAD, and List, and
/health/ready left the Service once write quorum was lost. Reads and
Service membership now follow read quorum and shared locks. Writes and
/minio/health/cluster still require write quorum and exclusive locks.
Signed-off-by: loverustfs <155562731+loverustfs@users.noreply.github.com>
Co-authored-by: Hauser <housemecn@gmail.com>
* fix(storage): weight automatic multipart admission by part size
* fix(ci): restore filesystem runner capabilities and typos dependency
* fix(ci): make release guard portable and spell out part variables
* ci: restore sm-standard-2 runners for io_uring and distributed e2e jobs
---------
Co-authored-by: hector <42570491+majinghe@users.noreply.github.com>
Co-authored-by: Hauser <housemecn@gmail.com>
唐小鸭