Files
seaweedfs/weed/shell/command_s3_lifecycle_run_shard.go
T
Chris Lu 7f254e158e feat(worker/s3_lifecycle): plugin handler with admin UI config (#9362)
* 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.
2026-05-08 10:30:02 -07:00

284 lines
9.1 KiB
Go

package shell
import (
"context"
"flag"
"fmt"
"io"
"sort"
"strconv"
"strings"
"time"
"github.com/seaweedfs/seaweedfs/weed/pb"
"github.com/seaweedfs/seaweedfs/weed/pb/filer_pb"
"github.com/seaweedfs/seaweedfs/weed/pb/s3_lifecycle_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/scheduler"
"github.com/seaweedfs/seaweedfs/weed/util"
)
func init() {
Commands = append(Commands, &commandS3LifecycleRunShard{})
}
type commandS3LifecycleRunShard struct{}
func (c *commandS3LifecycleRunShard) Name() string {
return "s3.lifecycle.run-shard"
}
func (c *commandS3LifecycleRunShard) Help() string {
return `manually run one or more shards of the event-driven S3 lifecycle worker
Subscribes once to the filer meta-log, filters events to the configured
(bucket, key-prefix-hash) shards, routes them through the compiled lifecycle
engine, and dispatches due actions to the S3 server's LifecycleDelete RPC.
Persists each shard's cursor to /etc/s3/lifecycle/cursors/shard-NN.json so
subsequent runs resume.
The -shards form covers a range or set; one filer subscription handles the
whole set, with no per-shard goroutine fan-out. Provide either -shard or
-shards, not both.
# single shard
s3.lifecycle.run-shard -shard 0 -s3 localhost:8333 -events 100
# contiguous range, all 16 shards via one subscription
s3.lifecycle.run-shard -shards 0-15 -s3 localhost:8333 -events 5000
# explicit set
s3.lifecycle.run-shard -shards 0,3,7 -s3 localhost:8333
# custom cadence
s3.lifecycle.run-shard -shards 0-15 -s3 s3-host:8333 -dispatch 1s -checkpoint 10s
`
}
func (c *commandS3LifecycleRunShard) HasTag(CommandTag) bool { return false }
func (c *commandS3LifecycleRunShard) Do(args []string, env *CommandEnv, writer io.Writer) error {
fs := flag.NewFlagSet(c.Name(), flag.ContinueOnError)
shard := fs.Int("shard", -1, "single shard id in [0, 16); use -shards for a range or set")
shardsSpec := fs.String("shards", "", "shard range \"lo-hi\" or comma list \"a,b,c\"; mutually exclusive with -shard")
s3Endpoint := fs.String("s3", "", "s3 server gRPC endpoint, host:port")
eventBudget := fs.Int("events", 1000, "max in-shard events to process before returning (0 = unbounded; counts only events that pass the shard filter)")
dispatchTick := fs.Duration("dispatch", 5*time.Second, "dispatcher tick cadence")
checkpointTick := fs.Duration("checkpoint", 30*time.Second, "cursor checkpoint cadence")
runtime := fs.Duration("runtime", 0, "wall-clock cap on the run; 0 = no timeout. -events alone can hang on quiet shards")
if err := fs.Parse(args); err != nil {
return err
}
shards, err := resolveShardSelection(*shard, *shardsSpec)
if err != nil {
return err
}
if *s3Endpoint == "" {
return fmt.Errorf("-s3 required (host:port of s3 server gRPC)")
}
if *eventBudget < 0 {
return fmt.Errorf("-events must be >= 0 (0 = unbounded)")
}
bucketsPath, err := resolveBucketsPath(env)
if err != nil {
return fmt.Errorf("resolve buckets path: %w", err)
}
fmt.Fprintf(writer, "buckets path: %s\n", bucketsPath)
dialCtx, dialCancel := context.WithTimeout(context.Background(), 30*time.Second)
conn, err := pb.GrpcDial(dialCtx, *s3Endpoint, false, env.option.GrpcDialOption)
dialCancel()
if err != nil {
return fmt.Errorf("dial s3 %s: %w", *s3Endpoint, err)
}
defer conn.Close()
rpcClient := s3_lifecycle_pb.NewSeaweedS3LifecycleInternalClient(conn)
// Run the whole pipeline inside one WithFilerClient so the reader's
// SubscribeMetadata stream and the persister share a single connection.
return env.WithFilerClient(true, func(filerClient filer_pb.SeaweedFilerClient) error {
inputs, parseErrors, err := scheduler.LoadCompileInputs(context.Background(), filerClient, bucketsPath)
if err != nil {
return fmt.Errorf("load lifecycle configs: %w", err)
}
for i, pe := range parseErrors {
if i < 3 {
fmt.Fprintf(writer, "warning: %s: %v\n", pe.Bucket, pe.Err)
}
}
if extra := len(parseErrors) - 3; extra > 0 {
fmt.Fprintf(writer, "warning: %d additional bucket(s) had malformed lifecycle config\n", extra)
}
if len(inputs) == 0 {
fmt.Fprintln(writer, "no buckets with enabled lifecycle rules found")
return nil
}
fmt.Fprintf(writer, "loaded lifecycle for %d bucket(s)\n", len(inputs))
eng := engine.New()
eng.Compile(inputs, engine.CompileOptions{PriorStates: scheduler.AllActivePriorStates(inputs)})
pipeline := &dispatcher.Pipeline{
Shards: shards,
BucketsPath: bucketsPath,
Engine: eng,
Persister: &dispatcher.FilerPersister{Store: dispatcher.NewFilerStoreClient(filerClient)},
Client: &lifecycleClientCallable{c: rpcClient},
FilerClient: filerClient,
ClientID: util.RandomInt32(),
ClientName: fmt.Sprintf("shell-lifecycle-%s", formatShardLabel(shards)),
DispatchTick: *dispatchTick,
CheckpointTick: *checkpointTick,
EventBudget: *eventBudget,
}
var ctx context.Context
var cancel context.CancelFunc
if *runtime > 0 {
ctx, cancel = context.WithTimeout(context.Background(), *runtime)
} else {
ctx, cancel = context.WithCancel(context.Background())
}
defer cancel()
fmt.Fprintf(writer, "running shards %s (event budget=%d, runtime=%s)…\n", formatShardLabel(shards), *eventBudget, *runtime)
if err := pipeline.Run(ctx); err != nil {
return fmt.Errorf("pipeline: %w", err)
}
fmt.Fprintf(writer, "shards %s complete; cursors checkpointed\n", formatShardLabel(shards))
return nil
})
}
// resolveShardSelection turns the -shard / -shards flags into a sorted,
// deduplicated []int. Exactly one form must be specified.
func resolveShardSelection(singleShard int, shardsSpec string) ([]int, error) {
if singleShard >= 0 && shardsSpec != "" {
return nil, fmt.Errorf("-shard and -shards are mutually exclusive")
}
if singleShard < 0 && shardsSpec == "" {
return nil, fmt.Errorf("specify -shard <id> or -shards <range|set>")
}
if singleShard >= 0 {
if singleShard >= s3lifecycle.ShardCount {
return nil, fmt.Errorf("-shard %d out of [0,%d)", singleShard, s3lifecycle.ShardCount)
}
return []int{singleShard}, nil
}
return parseShardsSpec(shardsSpec)
}
// parseShardsSpec accepts "lo-hi" (inclusive) or "a,b,c" and returns a
// sorted, deduplicated, in-range []int.
func parseShardsSpec(spec string) ([]int, error) {
spec = strings.TrimSpace(spec)
seen := map[int]struct{}{}
add := func(v int) error {
if v < 0 || v >= s3lifecycle.ShardCount {
return fmt.Errorf("shard %d out of [0,%d)", v, s3lifecycle.ShardCount)
}
seen[v] = struct{}{}
return nil
}
if strings.Contains(spec, "-") && !strings.Contains(spec, ",") {
parts := strings.SplitN(spec, "-", 2)
lo, err := strconv.Atoi(strings.TrimSpace(parts[0]))
if err != nil {
return nil, fmt.Errorf("range lo: %w", err)
}
hi, err := strconv.Atoi(strings.TrimSpace(parts[1]))
if err != nil {
return nil, fmt.Errorf("range hi: %w", err)
}
if lo > hi {
return nil, fmt.Errorf("range lo %d > hi %d", lo, hi)
}
for v := lo; v <= hi; v++ {
if err := add(v); err != nil {
return nil, err
}
}
} else {
for _, part := range strings.Split(spec, ",") {
part = strings.TrimSpace(part)
if part == "" {
continue
}
v, err := strconv.Atoi(part)
if err != nil {
return nil, fmt.Errorf("shard list: %w", err)
}
if err := add(v); err != nil {
return nil, err
}
}
}
if len(seen) == 0 {
return nil, fmt.Errorf("empty shard set")
}
out := make([]int, 0, len(seen))
for v := range seen {
out = append(out, v)
}
sort.Ints(out)
return out, nil
}
func formatShardLabel(shards []int) string {
if len(shards) == 1 {
return fmt.Sprintf("%d", shards[0])
}
// Detect contiguous range.
contiguous := true
for i := 1; i < len(shards); i++ {
if shards[i] != shards[i-1]+1 {
contiguous = false
break
}
}
if contiguous {
return fmt.Sprintf("%d-%d", shards[0], shards[len(shards)-1])
}
parts := make([]string, len(shards))
for i, v := range shards {
parts[i] = strconv.Itoa(v)
}
return strings.Join(parts, ",")
}
// lifecycleClientCallable adapts the generated grpc client (variadic
// CallOption tail) to the dispatcher.LifecycleClient interface.
type lifecycleClientCallable struct {
c s3_lifecycle_pb.SeaweedS3LifecycleInternalClient
}
func (l *lifecycleClientCallable) LifecycleDelete(ctx context.Context, req *s3_lifecycle_pb.LifecycleDeleteRequest) (*s3_lifecycle_pb.LifecycleDeleteResponse, error) {
return l.c.LifecycleDelete(ctx, req)
}
// resolveBucketsPath fetches the filer's configured buckets directory.
// Falls back to /buckets when the filer doesn't return one.
func resolveBucketsPath(env *CommandEnv) (string, error) {
var path string
err := env.WithFilerClient(false, func(client filer_pb.SeaweedFilerClient) error {
resp, err := client.GetFilerConfiguration(context.Background(), &filer_pb.GetFilerConfigurationRequest{})
if err != nil {
return err
}
path = resp.GetDirBuckets()
return nil
})
if err != nil {
return "", err
}
if path == "" {
path = "/buckets"
}
return path, nil
}