Commit Graph

  • b56d155b31 admin: native at-a-glance trend sparklines on the dashboard (#9957) Chris Lu 2026-06-14 13:55:26 -07:00
  • c1636ac41c s3: give STS sessions a distinct owner account instead of admin (#9963) Chris Lu 2026-06-14 13:55:11 -07:00
  • e64c821139 s3: give account-less identities a distinct owner instead of admin (#9962) Chris Lu 2026-06-14 13:54:49 -07:00
  • 3fd5018bd2 metrics: overhaul Grafana dashboard for full metric coverage (#9956) Chris Lu 2026-06-14 11:48:30 -07:00
  • 7e608c877a refactor(ec_balance): make the balance planner per-volume ratio-capable (#9960) Chris Lu 2026-06-14 11:33:31 -07:00
  • 138220b961 fix(ec): recover EC shards with the volume's own ratio, not the build default (#9958) Chris Lu 2026-06-14 07:32:36 -07:00
  • c7781bfca2 fix(ec): remove shared EC index only when no shard remains node-wide (#9955) Chris Lu 2026-06-14 06:36:50 -07:00
  • ef5fee6c28 fix(storage): delete/unmount every copy of a duplicate volume id (#9954) Chris Lu 2026-06-14 06:36:47 -07:00
  • 284796c7b6 fix(ec): fence stale-worker EC shard cleanup by encode generation (#9953) Chris Lu 2026-06-14 01:54:04 -07:00
  • 561768a426 [s3]: preserve multipart copy checksums (#9948) Chris Lu 2026-06-14 00:16:14 -07:00
  • da243b9423 fix(ec): group orphan-source completeness by encode generation (topology encode_ts_ns) (#9952) Chris Lu 2026-06-14 00:14:12 -07:00
  • 26754fca4d fix(ec): don't fabricate a stub .vif when mounting an EC volume (#9951) Chris Lu 2026-06-13 22:15:13 -07:00
  • 94357ac6a9 [volume] preserve compression state during replication (#9946) Chris Lu 2026-06-13 21:52:59 -07:00
  • 240f82d6d2 fix(ec): persist EC source readonly mark and skip writable replicas on orphan cleanup (#9950) Chris Lu 2026-06-13 21:26:16 -07:00
  • 1e858d8af0 fix(ec): make ec.decode write-path crash-safe and atomic (#9949) Chris Lu 2026-06-13 21:26:07 -07:00
  • 4fb3e22a01 fix(tiering): never delete a shared remote object while replicas still reference it (#9942) Chris Lu 2026-06-13 20:09:00 -07:00
  • 339a597e7e fix(vacuum): crash-safe compaction commit with a durable .cpc marker, fsync-before-rename, and a reload fence (#9944) Chris Lu 2026-06-13 20:06:24 -07:00
  • c2591b4395 fix(replication): verify-before-destroy in VolumeCopy, check.disk, and over-replication trim (#9943) Chris Lu 2026-06-13 20:05:33 -07:00
  • aabd44fbb5 [volume] preserve volume data mtime across tier moves (#9947) Chris Lu 2026-06-13 15:11:39 -07:00
  • f724828bcb fix(ec): never delete recoverable EC shards on startup/reconcile (the non-empty-.dat sibling of the stub bug) (#9941) Chris Lu 2026-06-12 23:51:29 -07:00
  • 3718301599 shell: stop ec.encode/ec.rebuild from destroying live EC shards (no crash needed) (#9939) Chris Lu 2026-06-12 22:30:17 -07:00
  • 18cdb3819b fix(ec): crash-safe ecx-journal fold and shard rebuild (fsync before publish, no short-read-as-success) (#9938) Chris Lu 2026-06-12 22:28:56 -07:00
  • 871d7ddc02 [helm]: configure JWT expiration (#9940) Chris Lu 2026-06-12 21:11:30 -07:00
  • 5468707289 fix(util): ignore comment only sql input (#9933) 7y-9 2026-06-13 01:10:27 +08:00
  • 0345658ea8 [s3] validate indirect filer path inputs (#9931) Chris Lu 2026-06-11 21:56:16 -07:00
  • 34f9b91d69 fix(storage): never let an empty .dat delete healthy distributed EC shards (#9930) Chris Lu 2026-06-11 20:26:20 -07:00
  • b44cf51fe9 s3: validate copy source path segments (#9929) Chris Lu 2026-06-11 17:07:15 -07:00
  • 4f8af455bf feat(storage): sweep leftover empty EC .dat stubs on volume server startup (#9927) Chris Lu 2026-06-11 12:26:21 -07:00
  • 37962e2445 admin: configure maintenance tasks via admin.toml (#9926) Chris Lu 2026-06-11 11:04:52 -07:00
  • 42030381ae shell: volume.tier.move can move volumes between data centers (#9925) Chris Lu 2026-06-11 10:46:34 -07:00
  • c3b06bf809 ci: run weed tests on linux/386 (#9924) Chris Lu 2026-06-11 09:49:07 -07:00
  • 3eb550a3f1 fix(tests): 32-bit build of EC e2e tests, type-check linux/386 in CI (#9922) Chris Lu 2026-06-11 09:05:54 -07:00
  • 582b7268f5 s3: export per-bucket quota and read-only state metrics (#9923) Chris Lu 2026-06-11 09:03:00 -07:00
  • bc1d56daf1 Publish seaweedfs-4.33.0.tgz chrislusf 2026-06-11 09:14:02 +00:00
  • 03f5e4cde5 Publish seaweedfs-4.33.0.tgz chrislusf 2026-06-11 08:00:12 +00:00
  • 55010be19b 4.33 4.33 Chris Lu 2026-06-11 00:52:31 -07:00
  • 79ac279fe1 fix(ec): don't mix EC shards from different encode runs (#9880) Chris Lu 2026-06-10 22:31:18 -07:00
  • 1dd292fb84 batch drain delta heartbeat messages (#9914) Bruce Zou 2026-06-11 04:33:45 +08:00
  • 6b4d20a6f3 volume.scrub and ec.scrub shell commands: make the display of scrub details optional. (#9911) Lisandro Pin 2026-06-10 22:29:07 +02:00
  • caadd6ca79 ci(s3tables): stop Lakekeeper flaking on Docker Hub pull timeouts (#9920) Chris Lu 2026-06-10 13:26:30 -07:00
  • 594fc667d5 Cut per-subscriber replay decode and widen replay concurrency (#9917) Chris Lu 2026-06-10 13:08:34 -07:00
  • e56a1c4c05 admin: pre-gzip embedded static assets, add cache headers (#9918) Chris Lu 2026-06-10 12:54:36 -07:00
  • c2271d59bb log_buffer: stop dumping the whole log entry on callback errors (#9919) Chris Lu 2026-06-10 12:47:35 -07:00
  • 2ac5aa72c7 add elastic8 filer store for Elasticsearch 8 (#9916) Chris Lu 2026-06-10 12:10:49 -07:00
  • 689b5b61bf fix(s3api): reject empty v4 signed header names (#9910) 7y-9 2026-06-11 02:00:35 +08:00
  • 7bf2dfc9ab Bound the metadata-log flush queue (#9907) Chris Lu 2026-06-10 10:57:30 -07:00
  • bf76040046 Share metadata-log replays per chunk instead of per file (#9906) Chris Lu 2026-06-10 10:57:11 -07:00
  • 5150c86934 Make shell command ec.scrub return shard details upon scrub failures in LOCAL mode. (#9913) Lisandro Pin 2026-06-10 19:55:16 +02:00
  • 7c0a9acb30 fix(s3api): normalize checksum trailer header names (#9905) 7y-9 2026-06-10 15:30:43 +08:00
  • 0c2576c3d0 ci: route Docker Hub pulls through a mirror to cut registry timeouts (#9904) Chris Lu 2026-06-09 17:12:42 -07:00
  • 9e98ec4b2e Share decoded metadata-log entries across subscriber replays (#9903) Chris Lu 2026-06-09 13:34:11 -07:00
  • e12052ee6b fix(filer.sync): replicate a rename as an atomic move, not a no-op update (#9895) Chris Lu 2026-06-09 12:54:28 -07:00
  • a9e4995d76 fix(http): accept no content delete responses (#9893) 7y-9 2026-06-10 02:45:14 +08:00
  • 048f9ece2d Fix filer metadata-replay OOM under mount reconnect storms (#9901) Chris Lu 2026-06-09 11:43:12 -07:00
  • 8776b9d311 feat(filer): object size distribution metric and dashboard panels (#9902) Chris Lu 2026-06-09 10:41:11 -07:00
  • 7b07d8177a fix(filer.sync): scope filesystem key sanitization to the local sink (#9894) Chris Lu 2026-06-09 10:18:49 -07:00
  • 202517c02a fix(filer.backup): skip replay events whose source chunk was superseded or deleted (#9886) Jaehoon Kim 2026-06-10 00:53:29 +09:00
  • 1cf92f6c2e fix(s3api): clear stale object lock years (#9890) 7y-9 2026-06-09 15:48:38 +08:00
  • 7aba10fa1a fix(mongodb): merge URI auth fields with username/password override (#9889) Chris Lu 2026-06-09 00:18:33 -07:00
  • 2871e6552a fix(s3api): drop ancestor directory markers from prefixed ListObjectVersions (#9885) Chris Lu 2026-06-09 00:01:06 -07:00
  • d569dd686f fix(shell): move files into existing destination directories (#9887) 7y-9 2026-06-09 14:42:13 +08:00
  • 1c9039d3ac fix(seaweed-volume): stop EC shard deletion from phantom .dat on restart (#9874) Chris Lu 2026-06-08 22:10:16 -07:00
  • a5f9c55479 build(deps): bump github.com/redis/go-redis/v9 from 9.19.0 to 9.20.0 (#9867) dependabot[bot] 2026-06-08 22:08:47 -07:00
  • 837c6f82a6 build(deps): bump io.netty:netty-codec-http2 from 4.2.13.Final to 4.2.15.Final in /test/java/spark (#9882) dependabot[bot] 2026-06-08 22:08:25 -07:00
  • fc6ea8c2da build(deps): bump io.netty:netty-transport-native-epoll from 4.2.13.Final to 4.2.15.Final in /test/java/spark (#9881) dependabot[bot] 2026-06-08 22:08:14 -07:00
  • 2945f7e226 build(deps): bump io.netty:netty-handler from 4.2.13.Final to 4.2.15.Final in /test/java/spark (#9875) dependabot[bot] 2026-06-08 22:08:07 -07:00
  • 7bbd28634a fix(util): return full uint64 randomness (#9864) 7y-9 2026-06-09 13:07:24 +08:00
  • 4a96f624d9 build(deps): bump gocloud.dev/pubsub/rabbitpubsub from 0.45.0 to 0.46.0 (#9870) dependabot[bot] 2026-06-08 22:06:54 -07:00
  • 3fadbef3eb feat(admin): export full cluster volume list as JSON (#9876) Chris Lu 2026-06-08 15:01:02 -07:00
  • ed470dccb1 mini: grow volumes one at a time Chris Lu 2026-06-08 14:51:40 -07:00
  • d67fc48fbd fix(filer.sync): guard batched events against nil EventNotification (#9877) Chris Lu 2026-06-08 13:56:16 -07:00
  • 4c050ad76b Don't mangle filer paths with the OS separator on Windows (#9878) Chris Lu 2026-06-08 13:56:02 -07:00
  • 8cc10460b4 fix(remote): correct content and permissions when syncing/caching remote objects (#9879) Chris Lu 2026-06-08 13:55:53 -07:00
  • 6475d22774 build(deps): bump github.com/apache/cassandra-gocql-driver/v2 from 2.1.0 to 2.1.1 (#9869) dependabot[bot] 2026-06-08 12:20:46 -07:00
  • feb3adfc21 build(deps): bump github.com/aws/aws-sdk-go-v2 from 1.41.10 to 1.41.12 (#9871) dependabot[bot] 2026-06-08 12:20:11 -07:00
  • 70f18fa4d0 build(deps): bump golang.org/x/sync from 0.20.0 to 0.21.0 (#9868) dependabot[bot] 2026-06-08 12:19:10 -07:00
  • 5a4ff2a122 fix(mq): don't cache topic non-existence on transient filer errors Chris Lu 2026-06-08 12:04:48 -07:00
  • 194517214e Publish seaweedfs-4.32.0.tgz chrislusf 2026-06-08 08:38:25 +00:00
  • b408705f5b fix(s3api): accept HTTP-date conditionals (#9863) 7y-9 2026-06-08 16:12:07 +08:00
  • 341eca8c85 Publish seaweedfs-4.32.0.tgz chrislusf 2026-06-08 07:13:56 +00:00
  • 78da9572ae 4.32 4.32 Chris Lu 2026-06-07 23:37:57 -07:00
  • 1b5f1c1f3b feat(filer.backup): -initialSnapshot re-seeds a reinitialized destination (#9828) Jaehoon Kim 2026-06-08 15:35:53 +09:00
  • 9053d61504 rust release: fix large-disk/normal binary overwrite + publish md5 checksums (#9862) Chris Lu 2026-06-07 23:20:33 -07:00
  • 8a4fdf06c0 admin/maintenance: reload in-flight tasks on startup instead of discarding them (#9857) Chris Lu 2026-06-07 22:45:38 -07:00
  • 7c542128c7 vacuum: compact a read-only volume when an explicit volumeId is given (#9861) Chris Lu 2026-06-07 22:42:51 -07:00
  • a549580e65 ec.balance: verify shard landed on destination before deleting the source (#9858) Chris Lu 2026-06-07 21:31:53 -07:00
  • e6ab9e7b09 fix(s3api): reject zero default retention years (#9860) 7y-9 2026-06-08 11:53:45 +08:00
  • f9d3105e80 ec placement: spread EC shards evenly across machines, not onto the lowest-id one (#9855) Chris Lu 2026-06-07 20:45:17 -07:00
  • 89cbb1c558 admin: default -dataDir to "." so maintenance task state persists across restarts (#9856) Chris Lu 2026-06-07 20:45:03 -07:00
  • f0d2a0d417 Treat co-located volume servers as one fault domain when balancing and allocating (#9854) Chris Lu 2026-06-07 14:14:45 -07:00
  • 25f36cd13d fix(s3api): require space in v2 auth prefix (#9852) 7y-9 2026-06-08 02:52:09 +08:00
  • 99bb5db1e3 fix(needle): use discovered file content type (#9851) 7y-9 2026-06-08 02:50:34 +08:00
  • 058569c77b operation: index VidCache by map instead of slice (#9853) Chris Lu 2026-06-07 11:46:57 -07:00
  • 755af4adf4 s3: actually bind outbound connections when -ip.bind is set (#9849) Chris Lu 2026-06-07 10:20:58 -07:00
  • 0e9fc6c5ba worker: drop ec.balance from the default admin script (#9848) Chris Lu 2026-06-07 00:55:11 -07:00
  • b2127c86f4 admin: show S3 servers under Cluster (#9847) Chris Lu 2026-06-07 00:32:20 -07:00
  • 01637410e2 test(s3): address review feedback on the versioning suite (#9846) Chris Lu 2026-06-06 20:50:09 -07:00
  • d321f9efb4 s3: collapse suspended-versioning deletes onto one null marker (#9845) Chris Lu 2026-06-06 20:49:38 -07:00
  • fa9bf58c86 test(s3): make the whole versioning suite pass and gate it in CI (#9844) Chris Lu 2026-06-06 18:38:28 -07:00
  • 795349d796 test(s3): deref Object.Size in versioned list assertion (#9843) Chris Lu 2026-06-06 18:02:36 -07:00