mirror of https://github.com/rustfs/rustfs.git synced 2026-11-01 08:40:23 +00:00

Files

T

overtrue 67fbafa13e chore(gateway): merge main into integration

Source: main 4e48c390e7
Target: gateway/integration 1000860cb8

Conflicts resolved, keeping both sides:
- crates/ecstore/src/disk/{fs,local}.rs: main's batched rollback writes,
  unified blocking write path and relocated open_file, with integration's
  native publication records restored at each publication point and the
  publication_history field kept beside main's multipart proof authority.
- crates/ecstore/src/set_disk/ops/multipart.rs: union of the imports.
- rustfs/src/storage/rpc/node_service.rs: main's MRF lifecycle reader
  capability branch; the heal capability keeps integration's restore
  copy-back probe.
- rustfs/src/admin/handlers/{audit,event,plugins_instances}.rs: main's
  target_read inventory snapshot on integration's owned request boundary;
  the new event.rs inventory test now builds owned requests.
- scripts/check_s3s_footprint.sh: integration's baseline-file version.
- .config/e2e-{full,smoke}-selection.txt: digests recomputed over the
  union of both heads' CI listings (full 700 darwin / 708 linux, smoke 232).

Also migrated main's new rebalance delete-all expiry test to the persisted
lifecycle types integration uses in ecstore, and raised the test-count
baseline to the merged counts (every decrease comes from main).

2026-10-27 08:38:17 +08:00

architecture

chore(gateway): merge main into integration

2026-10-27 08:38:17 +08:00

operations

fix(storage): 404 for dangling objects and strict list quorum default (#8963 )

2026-10-26 23:52:49 +08:00

postmortems

fix(replication): send an integrity header on Object Lock PUTs (#7097 )

2026-09-03 20:26:44 +08:00

testing

chore(gateway): merge main into integration

2026-10-27 08:38:17 +08:00

README.md

fix(heal): retain MRF state when bucket identity is unresolved (#8905 )

2026-10-25 03:58:46 +08:00

README.md

Documentation

Use the focused indexes rather than treating this directory as an unordered collection:

Operations

Retained MRF responsibilities — unknown bucket identities, bounded probes, and unreadable checkpoint recovery.
Internode HTTP streaming transport — protocol selection, pooled connection isolation, and distributed read validation.
Persisted config compatibility — ignored MinIO settings, bounded diagnostics, alias retention, and safe resets.
Table maintenance periodic queueing — opt-in scheduling, limits, worker handoff, and recovery.

For PUT cleanup admission, blocking-pool isolation, and optional CPU affinity, see PUT cleanup isolation.

External certificate issuance and TLS rotation — publication, native reload, trust separation and failure handling.
Architecture guard troubleshooting — diagnose repository guard failures.
Logging governance — broad event audits, migrations, and guardrail changes.
Multipart upload memory diagnosis — allocator attribution, Docker reproduction and sustained upload checks.

For the logical per-operation io_uring read cap, see io_uring read chunk size.

For bounded local read-backend startup and cancellation, see io_uring backend initialization.

For legacy protection assessment and bounded protected copies, see Object integrity inventory, audit, and migration.

For encrypted listing compatibility and older stored fingerprints, see Encrypted object ETags.

For durable hard quota accounting, node-outage behavior, and fence protocol upgrades, see Durable hard quotas.

Operational runbooks live under operations/. Replication operators should start with:

Runbook	Use it for
Site replication operations	Health fields, pending operations, outage recovery, re-pair admission, IAM/SSE boundaries, and upgrades.
Replication target check	Validating an S3 destination and version fidelity before enabling replication.
Replication object size limits	Multipart routing, large-object limits, and retry characteristics.
Replication outbound transport	Integrity headers, generic target behavior, and transport knobs.

For the erasure-coded cluster lifecycle (planning, parity and EC:0, expansion, rebalance, decommission, heal, drive replacement, restart recovery, and the rc CLI mapping), start with Cluster and erasure-coding lifecycle operations.

For concurrent bucket creation and deletion, see Bucket operation admission.

For persisted administrator bucket tasks and bucket recreation, see Bucket heal recovery.

For interrupted object deletions and returning drives, see Delete transaction recovery.

For disk replacement across VM restarts and schema 5/6 maintenance migration, see Replacement generation recovery.

For historical GET timeouts during PUT or Heal, see Object lock contention diagnostics.

Other runbooks remain grouped by filename in operations/; architecture pages link to the relevant runbook where a cross-boundary procedure is required.

For storage dashboards, see Storage metrics and observer selection: drive ownership, snapshot freshness, counter queries, and rolling upgrades.

For per-bucket capacity and object counts, see Bucket usage metrics: OTLP export, cluster deduplication, accounting semantics, and scanner freshness.

For optional shard commitments, see Independent shard integrity rollout: activation, legacy repair results, multipart mode changes, and rollback limits.

For crates.io publication of workspace crates, see Workspace Cargo Publish: dependency ordering, dry-run, publish, and failure handling.