Commit Graph

62 Commits

Author SHA1 Message Date
Henry Guo d5df66ac4f fix(scanner): require authoritative usage snapshots (#5333) 2026-07-28 07:29:57 +08:00
Henry Guo a63b79004c fix(scanner): make distributed usage convergence authoritative (#5151)
* fix(scanner): make distributed usage cycles authoritative

* fix(scanner): close distributed refresh races

* fix(config): align scanner reload integration

* fix(admin): scope config test helpers

* fix(scanner): harden distributed usage convergence

* fix(scanner): preserve rolling activity compatibility

* fix(admin): expose non-secret optional config values

* fix(scanner): acknowledge distributed dirty usage

* fix(ecstore): make bucket mutations cancellation safe

* fix(scanner): preserve pending dirty acknowledgements

* test(obs): account for superseded scanner metric

* fix(api): reject excess detached bucket mutations

* test: close scanner convergence coverage gaps

* fix(scanner): make path tracking cleanup one-shot

---------

Co-authored-by: Henry Guo <marshawcoco@users.noreply.github.com>
Co-authored-by: houseme <housemecn@gmail.com>
2026-07-25 18:45:16 +08:00
Henry Guo 889a45ad4d fix(scanner): back off clean idle scans across erasure clusters (#4984)
* fix(scanner): back off clean single-disk cycles

* fix(scanner): extend idle backoff across erasure clusters

---------

Co-authored-by: Henry Guo <marshawcoco@users.noreply.github.com>
2026-07-18 10:49:45 +08:00
Zhengchao An 627c396649 fix(scanner): allow usage snapshot save when existing timestamp is future-dated beyond clock tolerance (#4982) 2026-07-17 16:04:43 +00:00
houseme 6780140318 fix(object-data-cache): make the GET key write-unique and dedup the lookup (#4693)
fix(object-data-cache): make GET body cache key write-unique and dedup lookups

Address four object-data-cache GET-path findings (backlog#1107 batch):

ODC-06 (backlog#1111): the cache key was content-unique, not write-unique.
Extend ObjectDataCacheKey with the resolved version's modification time
(i128 unix nanoseconds, None -> 0), derived once in the shared planner so the
ecstore hook and the usecase layer produce an identical key. An unversioned
overwrite advances mod_time, so a stale node can no longer serve old bytes for
up to the TTL under an MD5 collision; etag + size stay as belt-and-braces.

ODC-16 (backlog#1121): every cacheable GET planned and looked up twice (once in
the ecstore hook, once in the usecase layer), double-counting hits, hit_bytes
and lookups. GetObjectReader now carries a GetObjectBodySource marker
(Unprobed / HookMissed / HookServed); the hook stamps it, and
build_get_object_body_with_cache serves a hook-served body directly and skips
its lookup whenever the hook already probed. One hook-served GET now records
exactly one lookup.

ODC-19 (backlog#1124): ENABLE=true with no explicit mode defaulted to HitOnly,
which never fills and keeps a permanent 0% hit rate. Default to
FillBufferedOnly, log the resolved mode at startup, and warn when HitOnly is
selected explicitly.

ODC-24 (backlog#1129): max_entry_bytes above the in-memory GET fill limits was
silently inert. Clamp the planner's size eligibility to
min(max_entry_bytes, seek-support threshold, 64 MiB buffer cap) so ineligible
sizes plan SkipTooLarge instead of being reported eligible, and warn at startup
when the excess is inert.

Co-authored-by: heihutu <heihutu@gmail.com>
2026-07-10 18:22:20 +00:00
Rafael Peroco 54496f2796 fix(scanner): advance cycle counter when a cycle ends on budget (#4163) 2026-07-02 17:15:51 +08:00
cxymds b21b27dddd fix: preserve scanner usage backups (#4179) 2026-07-02 16:33:59 +08:00
houseme b16120dbcc feat: optimize small GET read paths (#4022) 2026-07-01 15:40:00 +08:00
cxymds 0ff261864a fix(scanner): harden data scanner integrity handling (#4012)
* fix(scanner): heal metadata scan failures

* fix(scanner): preserve dirty buckets after scan failures

* feat(scanner): record leader lock liveness

* fix(scanner): preserve failed deep scan state

* fix(scanner): reject untimestamped stale usage

* fix(scanner): report topology-derived admission limit

* fix(scanner): accumulate tier usage stats

* fix(scanner): guard data usage cache recursion

* feat(scanner): expose startup enabled status

* fix(scanner): continue after heal admission rejection

* fix(scanner): avoid cyclic root usage double count

* fix(scanner): preserve dirty markers on cache save failure

* feat(scanner): expose leader liveness status

* fix(scanner): avoid heal escalation for transient metadata reads

* feat(scanner): persist rejected heal retry candidates

* test(scanner): satisfy freshness status clippy

* test(app): avoid global store reinit in context test

* test(app): gate global store helper to tests
2026-06-29 08:19:58 +08:00
Zhengchao An 1f7e159388 refactor: segment external storage api boundaries (#3903) 2026-06-26 15:10:49 +08:00
Zhengchao An 4d6ea453a7 refactor: route scanner heal storage boundaries (#3888) 2026-06-26 05:24:41 +08:00
Henry Guo 30f781871d fix(scanner): preserve dirty usage convergence (#3844)
Co-authored-by: Henry Guo <marshawcoco@users.noreply.github.com>
2026-06-25 21:09:12 +08:00
Zhengchao An a935854b32 refactor: centralize scanner runtime source helpers (#3827)
* refactor: batch lifecycle runtime source handles

* refactor: centralize scanner runtime source helpers
2026-06-24 22:05:03 +08:00
Zhengchao An 5c60f0cae9 refactor: centralize owner server config reads (#3793) 2026-06-23 21:27:30 +08:00
Zhengchao An d3796d6c10 refactor: remove external owner compat bridges (#3741) 2026-06-22 18:28:35 +08:00
安正超 cca9e83a8b refactor: use relative standalone compat consumers (#3734) 2026-06-22 15:07:58 +08:00
安正超 7eb9a4759e refactor: wrap bucket compat trait methods (#3706) 2026-06-22 04:32:37 +08:00
安正超 6b3d96fde3 refactor: prune trait import compat re-exports (#3699) 2026-06-21 23:17:58 +08:00
Henry Guo a689ff3c39 feat(scanner): wake cycles for dirty usage refresh (#3617) 2026-06-19 18:36:48 +08:00
Henry Guo 80144ec886 feat(scanner): expose usage freshness status (#3577)
* feat(scanner): expose usage freshness status

* fix(scanner): reset dirty usage cycle state

---------

Co-authored-by: Henry Guo <marshawcoco@users.noreply.github.com>
2026-06-18 21:14:55 +08:00
安正超 bdb2461b55 refactor: clean scanner heal runtime boundaries (#3571) 2026-06-18 16:12:27 +08:00
安正超 acdf439371 refactor: clean external DTO consumers (#3566)
* refactor: clean external DTO consumers

* fix: handle empty erasure shard recovery
2026-06-18 14:22:44 +08:00
安正超 99941f7e7c refactor: clean external operation consumers (#3565) 2026-06-18 12:39:41 +08:00
安正超 57403525ee refactor: move heal and namespace contracts (#3560) 2026-06-18 11:00:21 +08:00
安正超 e5cad7ed20 refactor: move object operation contracts (#3559) 2026-06-18 09:48:13 +08:00
安正超 53337a6f71 refactor: move HTTP range helper contracts (#3533) 2026-06-18 00:47:23 +08:00
Henry Guo a9aba323c6 fix(scanner): restore prompt bucket usage scans (#3516)
Co-authored-by: Henry Guo <marshawcoco@users.noreply.github.com>
Co-authored-by: houseme <housemecn@gmail.com>
2026-06-17 21:49:56 +08:00
安正超 ed55857bca refactor: move bucket operations contract (#3507) 2026-06-17 09:10:38 +08:00
abdullahnah92 c2e0792f6f fix(scanner): skip startup delay when replication is active so failed… (#3455)
fix(scanner): skip startup delay when replication is active so failed objects heal promptly after restart

Co-authored-by: houseme <housemecn@gmail.com>
2026-06-15 09:02:21 +08:00
houseme e8012bd1ba refactor(logging): normalize admin telemetry and error messages (#3430) 2026-06-14 13:27:10 +08:00
houseme 7da10db852 refactor(logging): standardize heal and scanner events (#3414)
* refactor(logging): standardize heal and scanner events

* chore(git): untrack local logging governance note

* chore(git): ignore local logging governance note
2026-06-14 01:47:39 +08:00
Henry Guo 19ff378e9b fix(scanner): preserve newer usage snapshots (#3370)
* fix(scanner): preserve newer usage snapshots

* fix(table-catalog): require namespace locking backend

---------

Co-authored-by: Henry Guo <marshawcoco@users.noreply.github.com>
2026-06-12 07:06:08 +08:00
安正超 a85cc0354c refactor(storage-api): remove namespace lock from StorageAPI (#3365)
* refactor(storage-api): remove namespace lock from StorageAPI

* test(scanner): wait for runtime budget cancellation

---------

Co-authored-by: loverustfs <hello@rustfs.com>
2026-06-11 22:42:12 +08:00
安正超 7146c893cb refactor(storage-api): remove legacy bucket DTO re-export (#3364) 2026-06-11 21:24:56 +08:00
安正超 b4524033e3 refactor(config): move global config accessors (#3360) 2026-06-11 19:16:02 +08:00
Henry Guo f40dd2f93c fix(scanner): publish partial usage for compacted scans (#3277)
* fix(scanner): publish partial usage for compacted scans

* fix(scanner): publish first partial usage immediately

* fix(scanner): skip startup delay for cold usage cache

* fix(scanner): tighten cold usage publish gate

---------

Co-authored-by: Henry Guo <marshawcoco@users.noreply.github.com>
Co-authored-by: houseme <housemecn@gmail.com>
2026-06-08 06:18:35 +00:00
Henry Guo 4ae070c8cc feat(scanner): expose scan partial source status (#3247)
* feat(scanner): expose scan partial source status

* fix(scanner): expose partial source in aggregated metrics

---------

Co-authored-by: Henry Guo <marshawcoco@users.noreply.github.com>
Co-authored-by: cxymds <Cxymds@qq.com>
Co-authored-by: houseme <housemecn@gmail.com>
2026-06-07 06:40:04 +00:00
Henry Guo 6850457707 feat(scanner): add runtime scanner controls and status (#3203)
* feat(scanner): add runtime scanner controls and status

* fix(scanner): validate persisted scanner config

* docs(scanner): clarify start delay behavior

---------

Co-authored-by: Henry Guo <marshawcoco@users.noreply.github.com>
Co-authored-by: houseme <housemecn@gmail.com>
2026-06-04 05:16:26 +00:00
Henry Guo ad1a489f75 feat(scanner): add scanner budget progress controls (#3185)
Co-authored-by: Henry Guo <marshawcoco@users.noreply.github.com>
2026-06-03 14:37:58 +00:00
Henry Guo cc07946782 feat(scanner): add cycle budget observability (#3166)
* feat(scanner): add cycle budget observability

* fix(scanner): clear cycle state after budget stop

* test(scanner): stabilize timeout-based scanner tests

* fix(scanner): keep cycle ILM counts scanner-only

* test(scanner): avoid test-only pending import

---------

Co-authored-by: Henry Guo <marshawcoco@users.noreply.github.com>
Co-authored-by: houseme <housemecn@gmail.com>
Co-authored-by: 安正超 <anzhengchao@gmail.com>
2026-06-03 03:32:41 +00:00
Henry Guo 1d46047d6f feat(scanner): expand scanner observability metrics (#3159)
* feat(scanner): expand scanner observability metrics

* chore(scanner): align bucket-drive metric wording

---------

Co-authored-by: Henry Guo <marshawcoco@users.noreply.github.com>
2026-06-02 01:29:53 +00:00
Henry Guo f3bd838925 feat(scanner): expose cycle progress metrics (#3152)
Co-authored-by: Henry Guo <marshawcoco@users.noreply.github.com>
Co-authored-by: houseme <housemecn@gmail.com>
2026-06-01 07:54:39 +00:00
Henry Guo 76da2a48d0 feat(scanner): expose cycle observability controls (#3147)
Co-authored-by: Henry Guo <marshawcoco@users.noreply.github.com>
2026-05-31 21:55:46 +00:00
Henry Guo a99ef64db2 feat(scanner): add scanner budgets and progress metrics (#3145)
* fix(scanner): preserve maintenance scan cadence

* feat(scanner): add scanner concurrency budget

* feat(scanner): expose scanner runtime progress

* fix(scanner): address scanner review feedback

---------

Co-authored-by: Henry Guo <marshawcoco@users.noreply.github.com>
Co-authored-by: houseme <housemecn@gmail.com>
2026-05-31 16:42:38 +00:00
Henry Guo 92104cb354 fix(scanner): reduce single-disk scanner churn (#3135)
* fix(scanner): slow single-disk default scans

* fix(scanner): reduce single-disk scanner churn

---------

Co-authored-by: Henry Guo <marshawcoco@users.noreply.github.com>
Co-authored-by: houseme <housemecn@gmail.com>
2026-05-31 05:05:04 +00:00
Henry Guo d921af6ef7 fix(heal): normalize completed root heal state (#3140)
Clear persisted background heal active state after a deep scanner cycle completes so root heal status does not remain in progress between cycles.

Treat path-based stop for an already missing heal task as stopped while keeping client-token cancellation strict.

Co-authored-by: Henry Guo <marshawcoco@users.noreply.github.com>
2026-05-31 04:47:36 +00:00
Henry Guo 62d1f80dbf fix(data-usage): refresh admin usage after object changes (#3081)
Co-authored-by: Henry Guo <marshawcoco@users.noreply.github.com>
2026-05-25 14:24:00 +00:00
weisd 69345fe059 fix(scanner): preserve background heal compatibility (#3041) 2026-05-22 14:38:35 +08:00
houseme 50d03ef021 perf(memory): add reclaim signals and cache controls (#2689) 2026-04-26 16:42:35 +00:00
houseme 6ce24f3b63 feat(lifecycle): improve ILM compatibility and scanner runtime config (#2534)
Co-authored-by: copilot-swe-agent[bot] <198982749+Copilot@users.noreply.github.com>
Co-authored-by: houseme <4829346+houseme@users.noreply.github.com>
Co-authored-by: cxymds <Cxymds@qq.com>
2026-04-16 10:28:03 +00:00