mirror of
https://github.com/seaweedfs/seaweedfs.git
synced 2026-09-17 20:10:51 +02:00
* 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.
104 lines
3.2 KiB
Go
104 lines
3.2 KiB
Go
package scheduler
|
|
|
|
import (
|
|
"context"
|
|
"strings"
|
|
|
|
"github.com/seaweedfs/seaweedfs/weed/pb/filer_pb"
|
|
"github.com/seaweedfs/seaweedfs/weed/s3api/lifecycle_xml"
|
|
"github.com/seaweedfs/seaweedfs/weed/s3api/s3_constants"
|
|
"github.com/seaweedfs/seaweedfs/weed/s3api/s3lifecycle"
|
|
"github.com/seaweedfs/seaweedfs/weed/s3api/s3lifecycle/engine"
|
|
)
|
|
|
|
const BucketLifecycleConfigurationXMLKey = "s3-bucket-lifecycle-configuration-xml"
|
|
|
|
// ParseError is returned alongside successfully-loaded inputs so callers can
|
|
// surface malformed bucket configs rather than silently dropping them.
|
|
type ParseError struct {
|
|
Bucket string
|
|
Err error
|
|
}
|
|
|
|
// LoadCompileInputs walks the buckets directory and returns one
|
|
// engine.CompileInput per bucket that carries a non-empty lifecycle
|
|
// configuration. Pagination loops with startFrom so clusters with more
|
|
// than one page of buckets don't drop the tail.
|
|
func LoadCompileInputs(ctx context.Context, client filer_pb.SeaweedFilerClient, bucketsPath string) ([]engine.CompileInput, []ParseError, error) {
|
|
var (
|
|
inputs []engine.CompileInput
|
|
parseErrors []ParseError
|
|
startFrom string
|
|
)
|
|
const pageSize uint32 = 1024
|
|
for {
|
|
pageCount := 0
|
|
var lastName string
|
|
err := filer_pb.SeaweedList(ctx, client, bucketsPath, "", func(entry *filer_pb.Entry, isLast bool) error {
|
|
pageCount++
|
|
lastName = entry.Name
|
|
if !entry.IsDirectory {
|
|
return nil
|
|
}
|
|
xmlBytes, ok := entry.Extended[BucketLifecycleConfigurationXMLKey]
|
|
if !ok || len(xmlBytes) == 0 {
|
|
return nil
|
|
}
|
|
rules, err := lifecycle_xml.ParseCanonical(xmlBytes)
|
|
if err != nil {
|
|
parseErrors = append(parseErrors, ParseError{Bucket: entry.Name, Err: err})
|
|
return nil
|
|
}
|
|
if len(rules) == 0 {
|
|
return nil
|
|
}
|
|
inputs = append(inputs, engine.CompileInput{
|
|
Bucket: entry.Name,
|
|
Rules: rules,
|
|
Versioned: IsBucketVersioned(entry),
|
|
})
|
|
return nil
|
|
}, startFrom, false, pageSize)
|
|
if err != nil {
|
|
return nil, nil, err
|
|
}
|
|
if uint32(pageCount) < pageSize {
|
|
break
|
|
}
|
|
startFrom = lastName
|
|
}
|
|
return inputs, parseErrors, nil
|
|
}
|
|
|
|
// IsBucketVersioned returns true when the bucket's filer entry has the
|
|
// versioning extended attribute set to Enabled or Suspended.
|
|
func IsBucketVersioned(entry *filer_pb.Entry) bool {
|
|
v, ok := entry.Extended[s3_constants.ExtVersioningKey]
|
|
if !ok {
|
|
return false
|
|
}
|
|
s := strings.ToLower(strings.TrimSpace(string(v)))
|
|
return s == "enabled" || s == "suspended"
|
|
}
|
|
|
|
// AllActivePriorStates seeds every compiled action as bootstrap-complete +
|
|
// event-driven so the scheduler dispatches whatever fires immediately.
|
|
// Production bootstrap walks set this incrementally per bucket; the
|
|
// scheduler runs out-of-band of that flow for now.
|
|
func AllActivePriorStates(inputs []engine.CompileInput) map[s3lifecycle.ActionKey]engine.PriorState {
|
|
prior := map[s3lifecycle.ActionKey]engine.PriorState{}
|
|
for _, in := range inputs {
|
|
for _, rule := range in.Rules {
|
|
hash := s3lifecycle.RuleHash(rule)
|
|
for _, kind := range s3lifecycle.RuleActionKinds(rule) {
|
|
key := s3lifecycle.ActionKey{Bucket: in.Bucket, RuleHash: hash, ActionKind: kind}
|
|
prior[key] = engine.PriorState{
|
|
BootstrapComplete: true,
|
|
Mode: engine.ModeEventDriven,
|
|
}
|
|
}
|
|
}
|
|
}
|
|
return prior
|
|
}
|