mirror of
https://github.com/seaweedfs/seaweedfs.git
synced 2026-11-01 18:00:46 +01:00
* feat(s3/lifecycle): scheduler — N pipelines over an even shard split
Scheduler.Run spawns Workers Pipeline goroutines plus one engine-refresh
ticker. Each worker owns a contiguous AssignShards(idx, total) slice of
[0, ShardCount) and runs Pipeline.Run with EventBudget bounding each
iteration; brief RetryBackoff between iterations avoids hot-loop on
errors. The refresh ticker rebuilds the engine snapshot from the filer's
bucket configs every RefreshInterval.
LoadCompileInputs / IsBucketVersioned / AllActivePriorStates are
exported from a configload.go sibling so the shell command can move to
this shared implementation in a follow-up.
* refactor(shell): reuse scheduler.LoadCompileInputs in run-shard
Drop the local copies of loadLifecycleCompileInputs / isBucketVersioned
/ allActivePriorStates / lifecycleParseError that the new
scheduler package now exports. Same behavior, one source of truth.
* feat(worker/s3_lifecycle): plugin handler with admin UI config
Registers a JobHandler for s3_lifecycle via pluginworker.RegisterHandler.
Admin pulls the descriptor over the worker plugin gRPC and renders the
AdminConfigForm + WorkerConfigForm in the existing UI:
Admin form (cluster shape):
- workers (1..16, default 1)
- s3_grpc_endpoints (comma list)
Worker form (operational tuning):
- dispatch_tick_ms (default 5000)
- checkpoint_tick_ms (default 30000)
- refresh_interval_ms (default 300000)
- event_budget (default 0 = unbounded)
Detect emits a single proposal whenever S3 endpoints + filer addresses
are configured. MaxExecutionConcurrency=1 so admin only ever runs one
lifecycle daemon per worker; a fresh proposal next cycle restarts it
if the prior Execute exits.
Execute dials the configured S3 endpoint + filer, builds a
scheduler.Scheduler with the parsed config, and runs it until
ctx cancellation. Reuses the existing scheduler / dispatcher /
reader / engine packages — the handler is the thin glue that
parses descriptor values and wires the long-running daemon.
* proto(plugin): add s3_grpc_addresses to ClusterContext
So workers can dial s3 servers discovered by the master rather than a
hand-typed list in the admin form.
* feat(admin): populate ClusterContext.s3_grpc_addresses from master
ListClusterNodes(S3Type) returns the live S3 servers; the plugin
scheduler now hands these to job handlers alongside filer/volume
addresses.
* feat(worker/s3_lifecycle): discover s3 endpoints from cluster context
Drop the s3_grpc_endpoints admin form field and read the master-supplied
ClusterContext.S3GrpcAddresses instead. Operators no longer maintain a
hand-typed list, and a stale entry self-heals when the master's view
updates.
* feat(worker/s3_lifecycle): time-based runtime cap, friendlier cadence units
- dispatch_tick_minutes (was *_ms): minutes is the natural granularity
for a daily batch; default 1 minute.
- checkpoint_tick_seconds: seconds for the durable cursor write; default
30 seconds.
- refresh_interval_minutes: minutes for the engine snapshot rebuild.
- max_runtime_minutes replaces event_budget. Each daily run is bounded
by wall clock — typical run wraps in well under an hour because the
cursor persists and the meta-log streams fast. Default 60 minutes.
- AdminRuntimeDefaults.DetectionIntervalSeconds = 86400 so the admin
schedules one job per day.
167 lines
4.0 KiB
Go
167 lines
4.0 KiB
Go
package scheduler
|
|
|
|
import (
|
|
"context"
|
|
"errors"
|
|
"fmt"
|
|
"sync"
|
|
"time"
|
|
|
|
"github.com/seaweedfs/seaweedfs/weed/glog"
|
|
"github.com/seaweedfs/seaweedfs/weed/pb/filer_pb"
|
|
"github.com/seaweedfs/seaweedfs/weed/s3api/s3lifecycle"
|
|
"github.com/seaweedfs/seaweedfs/weed/s3api/s3lifecycle/dispatcher"
|
|
"github.com/seaweedfs/seaweedfs/weed/s3api/s3lifecycle/engine"
|
|
"github.com/seaweedfs/seaweedfs/weed/s3api/s3lifecycle/reader"
|
|
)
|
|
|
|
const (
|
|
defaultRefreshInterval = 5 * time.Minute
|
|
defaultRetryBackoff = 5 * time.Second
|
|
)
|
|
|
|
// Scheduler runs N pipeline goroutines, one per worker, each owning a
|
|
// contiguous shard slice of [0, ShardCount). It periodically rebuilds the
|
|
// engine snapshot from the filer's bucket configs.
|
|
type Scheduler struct {
|
|
BucketsPath string
|
|
Engine *engine.Engine
|
|
Persister reader.Persister
|
|
Client dispatcher.LifecycleClient
|
|
FilerClient filer_pb.SeaweedFilerClient
|
|
ClientID int32
|
|
ClientName string
|
|
|
|
Workers int
|
|
DispatchTick time.Duration
|
|
CheckpointTick time.Duration
|
|
RefreshInterval time.Duration
|
|
RetryBackoff time.Duration
|
|
}
|
|
|
|
// Run blocks until ctx is canceled. Spawns Workers + 1 goroutines: one
|
|
// engine-refresh ticker plus one Pipeline runner per worker.
|
|
func (s *Scheduler) Run(ctx context.Context) error {
|
|
if s.Engine == nil || s.Persister == nil || s.Client == nil || s.FilerClient == nil {
|
|
return errors.New("scheduler: missing required dependency")
|
|
}
|
|
if s.BucketsPath == "" {
|
|
return errors.New("scheduler: BucketsPath required")
|
|
}
|
|
|
|
workers := s.Workers
|
|
if workers <= 0 {
|
|
workers = 1
|
|
}
|
|
refresh := s.RefreshInterval
|
|
if refresh <= 0 {
|
|
refresh = defaultRefreshInterval
|
|
}
|
|
retry := s.RetryBackoff
|
|
if retry <= 0 {
|
|
retry = defaultRetryBackoff
|
|
}
|
|
|
|
s.refreshEngine(ctx)
|
|
|
|
var wg sync.WaitGroup
|
|
wg.Add(1)
|
|
go func() {
|
|
defer wg.Done()
|
|
t := time.NewTicker(refresh)
|
|
defer t.Stop()
|
|
for {
|
|
select {
|
|
case <-ctx.Done():
|
|
return
|
|
case <-t.C:
|
|
s.refreshEngine(ctx)
|
|
}
|
|
}
|
|
}()
|
|
|
|
for i := 0; i < workers; i++ {
|
|
shards := AssignShards(i, workers)
|
|
if len(shards) == 0 {
|
|
continue
|
|
}
|
|
wg.Add(1)
|
|
go func(idx int, shardSet []int) {
|
|
defer wg.Done()
|
|
for {
|
|
select {
|
|
case <-ctx.Done():
|
|
return
|
|
default:
|
|
}
|
|
p := &dispatcher.Pipeline{
|
|
Shards: shardSet,
|
|
BucketsPath: s.BucketsPath,
|
|
Engine: s.Engine,
|
|
Persister: s.Persister,
|
|
Client: s.Client,
|
|
FilerClient: s.FilerClient,
|
|
ClientID: s.ClientID,
|
|
ClientName: fmt.Sprintf("%s-w%02d", s.ClientName, idx),
|
|
DispatchTick: s.DispatchTick,
|
|
CheckpointTick: s.CheckpointTick,
|
|
}
|
|
if err := p.Run(ctx); err != nil && !errors.Is(err, context.Canceled) {
|
|
glog.Warningf("lifecycle scheduler: worker=%d shards=%v: %v", idx, shardSet, err)
|
|
}
|
|
select {
|
|
case <-ctx.Done():
|
|
return
|
|
case <-time.After(retry):
|
|
}
|
|
}
|
|
}(i, shards)
|
|
}
|
|
|
|
wg.Wait()
|
|
return nil
|
|
}
|
|
|
|
func (s *Scheduler) refreshEngine(ctx context.Context) {
|
|
inputs, parseErrors, err := LoadCompileInputs(ctx, s.FilerClient, s.BucketsPath)
|
|
if err != nil {
|
|
glog.Warningf("lifecycle scheduler: refresh engine: %v", err)
|
|
return
|
|
}
|
|
for _, pe := range parseErrors {
|
|
glog.Warningf("lifecycle scheduler: malformed config in bucket %s: %v", pe.Bucket, pe.Err)
|
|
}
|
|
s.Engine.Compile(inputs, engine.CompileOptions{PriorStates: AllActivePriorStates(inputs)})
|
|
}
|
|
|
|
// AssignShards returns the contiguous shard slice for worker idx of total.
|
|
// Shards distribute as evenly as possible: with ShardCount=16 and total=3,
|
|
// workers receive [0..5], [6..10], [11..15].
|
|
func AssignShards(idx, total int) []int {
|
|
if total <= 0 || idx < 0 || idx >= total {
|
|
return nil
|
|
}
|
|
shardCount := s3lifecycle.ShardCount
|
|
base := shardCount / total
|
|
extra := shardCount % total
|
|
var lo, hi int
|
|
if idx < extra {
|
|
lo = idx * (base + 1)
|
|
hi = lo + base + 1
|
|
} else {
|
|
lo = idx*base + extra
|
|
hi = lo + base
|
|
}
|
|
if hi > shardCount {
|
|
hi = shardCount
|
|
}
|
|
if lo >= hi {
|
|
return nil
|
|
}
|
|
out := make([]int, 0, hi-lo)
|
|
for i := lo; i < hi; i++ {
|
|
out = append(out, i)
|
|
}
|
|
return out
|
|
}
|