Add an authenticated scanner usage-state reset endpoint that publishes a fenced bootstrap marker for full rebuilds instead of requiring operators to delete usage metadata by hand.
Guard the reset with the scanner leader lock, storage publication epoch, and per-slot revision preconditions, and make startup resumable across stale cleanup leftovers while still rejecting newer conflicting usage state.
Co-authored-by: heihutu <heihutu@gmail.com>
Co-authored-by: Zhengchao An <anzhengchao@gmail.com>
* fix(ecstore): fence pool metadata replica updates
* fix(ecstore): block decommission on unsafe pool metadata
* fix(ecstore): block writes after pool metadata save errors
* fix(ecstore): latch pool metadata writes before await
* fix(scanner): bootstrap pristine usage baseline
* fix(scanner): defer usage publication during pool recovery
* fix(scanner): preserve metrics when publication is deferred
* fix(scanner): route test types through storage boundary
* fix(scanner): keep cache floor deferred during movement
Split the 8178-line scanner.rs (48% inline tests) into a canonical
scanner.rs + scanner/ module tree with zero behavior change:
- scanner.rs (~2140): cycle constants, schedule status, budget/config
helpers, startup, maintenance features, the two run loops, and
cycle-result finalization
- scanner/activity.rs (~770): wake/backoff policy and scanner activity
observation (probing, generations, topology digest)
- scanner/heal_info.rs (~110): the background-heal info object
- scanner/cycle_state.rs (~500): cycle-state codec, persisted usage
floors, and cycle-state persistence
- scanner/leadership.rs (~360): leader-lock claiming, usage-epoch
fencing, and lock-loss handling
- scanner/usage_store.rs (~480): the CAS data-usage store pipeline and
observed-snapshot cleanup
- scanner/tests.rs (~3920): the inline test module as a child module
All crate paths are unchanged: scanner::BackgroundHealInfo,
scanner::read_background_heal_info, scanner::store_data_usage_in_backend,
and scanner_topology_digest resolve through root re-exports with their
original visibilities, and the pub(crate) surface used by scanner_io and
remote_scanner re-exports at pub(crate). Cross-module items gain
pub(super), whose scope equals the old single-module privacy domain.
Code is moved verbatim apart from those markers, per-module import
headers, and rustfmt re-wraps.
Co-authored-by: heihutu <heihutu@gmail.com>
* refactor(scanner): drop the always-None single-disk default cycle hook
single_disk_default_cycle_secs returned None for every maintenance
feature combination, so the single-disk startup path already resolved
its default cycle from the speed preset (60s at 'default'). Remove the
never-wired hook and its pin tests, keep the explicit reset, and record
the decision: no special single-disk cycle override without measured
cold-start ILM latency evidence; clean-idle backoff already stretches
idle cadence (backlog#1878 HS-16).
Co-Authored-By: heihutu <heihutu@gmail.com>
* docs(operations): add heal/scanner MinIO parity decision notes
Document the HS-14/16/18 decision batch from backlog#1878: the scanner
idle throttling semantics matrix (RUSTFS_SCANNER_IDLE_MODE x speed
preset x foreground read backoff) side by side with MinIO's current
static idle_speed switch as verified against upstream master, the
migration warnings for env names and value vocabularies, the bitrot
cycle default divergence (30d vs off), the stale-multipart / tmp / trash
three-stage cleanup comparison with the crash-residue window grading,
and the single-disk default cycle decision.
Co-Authored-By: heihutu <heihutu@gmail.com>
---------
Co-authored-by: heihutu <heihutu@gmail.com>
Second batch of the #[serial] sweep started in #6209. nextest is the
repository's authoritative runner and executes every test in its own
process, so serial_test's in-process mutex cannot serialize tests against
each other -- docs/testing/README.md documents this, and the mechanism
that actually serializes across the process boundary is a
.config/nextest.toml [test-groups] entry with max-threads = 1.
Unlike the first batch (e2e, process-isolated by construction), these are
in-crate unit tests that could genuinely share process state under the
`cargo test` fallback runner, where #[serial] IS still effective. Every
marker was therefore reviewed individually and removed only where the
test provably touches neither the process environment nor a process-global.
Removed (47, pure deletions, no test bodies touched):
crates/lifecycle/src/core.rs 35
crates/scanner/src/scanner.rs 12
The lifecycle removals are all validate_* / filter_rules_* /
has_active_rules_* / noncurrent_versions_expiration_limit_* tests that
build a local BucketLifecycleConfiguration and call a &self method
walking only that value. The scanner removals are pure duration
arithmetic (randomized_cycle_delay_for, initial_scanner_delay_for with an
explicit Some(secs), the bitrot-disabled early return of
scanner_clean_idle_max_interval) and background_heal_info_for_scan_complete
/ _for_scan_result field comparisons over locally built values.
Retained deliberately -- see the PR body for the full list and reasons:
crates/ecstore/src/bucket/lifecycle/bucket_lifecycle_ops.rs 101 (all)
crates/lifecycle/src/core.rs 44
crates/scanner/src/scanner.rs 53
bucket_lifecycle_ops.rs keeps every marker: its test module caches a
process-wide `static STALE_MULTIPART_TEST_ENV: OnceLock<(Vec<PathBuf>,
Arc<ECStore>)>`, and its own reregister_env_local_disks helper documents
in-tree that sibling #[serial] tests reset and reshape the shared
local-disk registry for each other. That sharing is real, so the markers
stay.
No test was renamed, added, or deleted; no reserved migration-gate name
substring is affected; no .config/nextest.toml entry references any of
the 47 removed tests.
A superseded cycle is the expected outcome of the dirty-usage fast path, not a signal of pathological load: a write burst marks buckets dirty, the scanner wakes within milliseconds, and the still-landing writes then supersede the snapshot it just took. Charging that first race SUPERSEDED_RETRY_BASE_INTERVAL = 60s meant the burst surfaced in usage and quota accounting roughly two cycles late.
Measured on an idle single-node instance (fresh data dir, 10 PUTs, polling /rustfs/admin/v3/datausageinfo every 5s): the dirty-usage wake fires 0.3s after the PUTs, its cycle is superseded 0.2s later, and the retry was then scheduled 55.6s out; usage first became visible at t+120s. With the base at 5s the retry is scheduled 4.7s out and usage becomes visible at t+70s.
The exponential growth in retry_interval is what protects against a persistently hot bucket driving an unbroken full-scan loop, so the base does not need to be a whole cycle: 5s, 10s, 20s, 40s ... still reaches minute-scale backoff within a handful of consecutive supersedes and keeps the SUPERSEDED_RETRY_MAX_INTERVAL cap. A configured cycle shorter than the base still wins, since retrying faster than the operator's own cadence buys nothing.
Verification: cargo test -p rustfs-scanner --lib (444 passed) with the three superseded-backoff tests updated to the new schedule; make pre-commit green; end-to-end probe above.
Add opt-in hotpath feature surfaces to every workspace crate and wire the root rustfs feature passthrough for function, allocation, and CPU profiling.
Add a focused set of function-level measurements for scanner, heal, lock, target replay, IAM, KMS, Keystone, trusted proxy, and capacity paths without adding request-scoped primitive wrappers.
Co-authored-by: heihutu <heihutu@gmail.com>
* 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>
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>
Zhengchao An