mirror of
https://github.com/seaweedfs/seaweedfs.git
synced 2026-10-19 20:44:28 +02:00
* s3 lifecycle: replay only the rules that fit the retention window runShard handed drainShardEvents the full snapshot, so rules the retention window assigns to the walk were also matched during meta-log replay. Their matches are not due yet, and drainShardEvents freezes the cursor at the first event with a not-yet-due match. With a 3-day and a 30-day expiration rule on one bucket and RetentionWindow of 8 days, every shard's cursor stopped at the first 30-day object's PUT and stayed there until that object came due. Each pass then re-read the log from that point and re-dispatched every 3-day expiration already handled, which surfaces as NOOP_RESOLVED dispatches, a growing cursor_lag_max, and passes that still report status=ok. Snapshot.ReplayView drops the replay-kind actions promoted to the walk and keeps every other action as compiled, and the drain uses it. Promoted rules are served by the walk as before. RulesForShard, PromotedHash and ReplayView share one isPromoted predicate. With RetentionWindow unset no active rule is promoted, so behaviour without a configured window is unchanged. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com> * s3 lifecycle: scale the replay-view test with DaysToDuration The test took its retention window from DaysToDuration but dated its PUTs in hours, so under the s3tests build tag (one lifecycle day = 10s) every event fell before the seeded cursor and replay never ran. Express the event ages in DaysToDuration too, so the test exercises replay at both scales. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com> * s3 lifecycle: rehabilitate scan_only mode in the replay drain view ReplayView shared the base CompiledAction pointers, so a replay-kind rule locked into ModeScanOnly by a prior compile stayed invisible to router.Route's event_driven gate even when the runtime retention window kept it in the replay partition - and it is absent from the walk view too, so the rule would be served by neither. Clone non-promoted replay-kind actions the way RulesForShard does (Mode forced to event_driven), reactivating the scan_only case whose bootstrap rendezvous already completed, while preserving the base active bit for genuinely pre-bootstrap actions. Disabled actions are excluded for parity with the other views, and DESIGN.md now documents the view. * s3 lifecycle: keep drain activation observable, require walker with retention ReplayView now shares pointers for event-driven actions so a mid-pass MarkActive flip remains visible to the drain; only a scan_only-locked action is cloned to event_driven, and reactivated only when its bootstrap rendezvous completed (tracked via a new bootstrapComplete field on CompiledAction). validate() rejects RetentionWindow without Walker: promoted rules would lose their only dispatch path while the drain cursor still advanced past their events. --------- Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com> Co-authored-by: Chris Lu <chris.lu@gmail.com>
135 lines
4.3 KiB
Go
135 lines
4.3 KiB
Go
package engine
|
|
|
|
import (
|
|
"bytes"
|
|
"sort"
|
|
"sync/atomic"
|
|
"time"
|
|
|
|
"github.com/seaweedfs/seaweedfs/weed/s3api/s3lifecycle"
|
|
)
|
|
|
|
var snapshotIDSeq atomic.Uint64
|
|
|
|
// CompileInput: at most one entry per Bucket. Duplicates would overwrite
|
|
// earlier entries' BucketIndex.
|
|
type CompileInput struct {
|
|
Bucket string
|
|
Rules []*s3lifecycle.Rule
|
|
Versioned bool
|
|
}
|
|
|
|
// PriorState carries durable per-action state into Compile. Missing keys
|
|
// are treated as bootstrap_complete=false.
|
|
type PriorState struct {
|
|
BootstrapComplete bool
|
|
Mode RuleMode
|
|
}
|
|
|
|
// MetaLogRetention=0 means unbounded; the retention gate doesn't trip.
|
|
type CompileOptions struct {
|
|
MetaLogRetention time.Duration
|
|
BootstrapLookbackMin time.Duration
|
|
PriorStates map[s3lifecycle.ActionKey]PriorState
|
|
}
|
|
|
|
const defaultBootstrapLookbackMin = 5 * s3lifecycle.SmallDelay
|
|
|
|
func (e *Engine) Compile(inputs []CompileInput, opts CompileOptions) *Snapshot {
|
|
if opts.BootstrapLookbackMin == 0 {
|
|
opts.BootstrapLookbackMin = defaultBootstrapLookbackMin
|
|
}
|
|
|
|
snap := &Snapshot{
|
|
id: snapshotIDSeq.Add(1),
|
|
buckets: make(map[string]*BucketIndex),
|
|
actions: make(map[s3lifecycle.ActionKey]*CompiledAction),
|
|
originalDelayGroups: make(map[time.Duration][]s3lifecycle.ActionKey),
|
|
dateActions: make(map[s3lifecycle.ActionKey]time.Time),
|
|
}
|
|
|
|
for _, in := range inputs {
|
|
bi := &BucketIndex{bucket: in.Bucket, versioned: in.Versioned}
|
|
snap.buckets[in.Bucket] = bi
|
|
|
|
for _, rule := range in.Rules {
|
|
ruleHash := s3lifecycle.RuleHash(rule)
|
|
for _, kind := range s3lifecycle.RuleActionKinds(rule) {
|
|
key := s3lifecycle.ActionKey{Bucket: in.Bucket, RuleHash: ruleHash, ActionKind: kind}
|
|
// Durable Mode wins; decideMode is only the seed for new
|
|
// or legacy-zero actions. Otherwise lag-fallback / operator
|
|
// SCAN_ONLY would re-promote on every rebuild.
|
|
prior, hasPrior := opts.PriorStates[key]
|
|
mode := prior.Mode
|
|
if !hasPrior || mode == ModeUnspecified {
|
|
mode = decideMode(rule, kind, opts.MetaLogRetention, opts.BootstrapLookbackMin)
|
|
}
|
|
// Active gates routing: MatchPath / MatchOriginalWrite skip
|
|
// !IsActive actions. ScanAtDate's only dispatch path is the
|
|
// bootstrap walk's MatchPath call, so the action must be
|
|
// considered active there or its rule is silently a no-op.
|
|
// Bootstrap-completion state is per-action and event-driven-
|
|
// shaped; date-based actions don't need a bootstrap rendezvous.
|
|
active := mode == ModeScanAtDate ||
|
|
(prior.BootstrapComplete && mode == ModeEventDriven)
|
|
|
|
ca := &CompiledAction{
|
|
Rule: rule,
|
|
Bucket: in.Bucket,
|
|
Key: key,
|
|
Delay: s3lifecycle.MinTriggerAge(rule, kind),
|
|
PredicateSensitive: rulePredicateSensitive(rule),
|
|
Mode: mode,
|
|
bootstrapComplete: prior.BootstrapComplete,
|
|
}
|
|
if active {
|
|
ca.markActive()
|
|
}
|
|
snap.actions[key] = ca
|
|
bi.actionKeys = append(bi.actionKeys, key)
|
|
|
|
// Index every action regardless of `active`; routing
|
|
// re-filters on IsActive() so MarkActive flips are visible
|
|
// without a recompile.
|
|
if mode == ModeScanAtDate {
|
|
snap.dateActions[key] = rule.ExpirationDate
|
|
}
|
|
if mode == ModeEventDriven {
|
|
snap.originalDelayGroups[ca.Delay] = append(snap.originalDelayGroups[ca.Delay], key)
|
|
if ca.PredicateSensitive {
|
|
snap.predicateActions = append(snap.predicateActions, key)
|
|
}
|
|
}
|
|
}
|
|
}
|
|
}
|
|
|
|
snap.allActionsSorted = make([]*CompiledAction, 0, len(snap.actions))
|
|
for _, a := range snap.actions {
|
|
snap.allActionsSorted = append(snap.allActionsSorted, a)
|
|
}
|
|
sort.Slice(snap.allActionsSorted, func(i, j int) bool {
|
|
a, b := snap.allActionsSorted[i], snap.allActionsSorted[j]
|
|
if a.Bucket != b.Bucket {
|
|
return a.Bucket < b.Bucket
|
|
}
|
|
if c := bytes.Compare(a.Key.RuleHash[:], b.Key.RuleHash[:]); c != 0 {
|
|
return c < 0
|
|
}
|
|
return a.Key.ActionKind < b.Key.ActionKind
|
|
})
|
|
|
|
e.current.Store(snap)
|
|
return snap
|
|
}
|
|
|
|
// rulePredicateSensitive: only tag filters can flip post-PUT. Size is
|
|
// immutable once written; a size change is a fresh write through the
|
|
// original-write stream.
|
|
func rulePredicateSensitive(rule *s3lifecycle.Rule) bool {
|
|
if rule == nil {
|
|
return false
|
|
}
|
|
return len(rule.FilterTags) > 0
|
|
}
|