mirror of
https://github.com/seaweedfs/seaweedfs.git
synced 2026-10-28 16:00:37 +01:00
Chris Lu
7f254e158e
* 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.
78 lines
2.8 KiB
Go
78 lines
2.8 KiB
Go
package s3_lifecycle
|
|
|
|
import (
|
|
"testing"
|
|
"time"
|
|
|
|
"github.com/seaweedfs/seaweedfs/weed/pb/plugin_pb"
|
|
)
|
|
|
|
func TestParseConfigDefaults(t *testing.T) {
|
|
cfg := ParseConfig(nil, nil)
|
|
if cfg.Workers != defaultWorkers {
|
|
t.Errorf("Workers default=%d, want %d", cfg.Workers, defaultWorkers)
|
|
}
|
|
if cfg.DispatchTick != 1*time.Minute {
|
|
t.Errorf("DispatchTick default=%v, want 1m", cfg.DispatchTick)
|
|
}
|
|
if cfg.CheckpointTick != 30*time.Second {
|
|
t.Errorf("CheckpointTick default=%v, want 30s", cfg.CheckpointTick)
|
|
}
|
|
if cfg.RefreshInterval != 5*time.Minute {
|
|
t.Errorf("RefreshInterval default=%v, want 5m", cfg.RefreshInterval)
|
|
}
|
|
if cfg.MaxRuntime != 60*time.Minute {
|
|
t.Errorf("MaxRuntime default=%v, want 60m", cfg.MaxRuntime)
|
|
}
|
|
}
|
|
|
|
func TestParseConfigOverrides(t *testing.T) {
|
|
admin := map[string]*plugin_pb.ConfigValue{
|
|
"workers": {Kind: &plugin_pb.ConfigValue_Int64Value{Int64Value: 4}},
|
|
}
|
|
worker := map[string]*plugin_pb.ConfigValue{
|
|
"dispatch_tick_minutes": {Kind: &plugin_pb.ConfigValue_Int64Value{Int64Value: 2}},
|
|
"checkpoint_tick_seconds": {Kind: &plugin_pb.ConfigValue_Int64Value{Int64Value: 15}},
|
|
"refresh_interval_minutes": {Kind: &plugin_pb.ConfigValue_Int64Value{Int64Value: 10}},
|
|
"max_runtime_minutes": {Kind: &plugin_pb.ConfigValue_Int64Value{Int64Value: 120}},
|
|
}
|
|
cfg := ParseConfig(admin, worker)
|
|
if cfg.Workers != 4 {
|
|
t.Errorf("Workers=%d, want 4", cfg.Workers)
|
|
}
|
|
if cfg.DispatchTick != 2*time.Minute {
|
|
t.Errorf("DispatchTick=%v, want 2m", cfg.DispatchTick)
|
|
}
|
|
if cfg.CheckpointTick != 15*time.Second {
|
|
t.Errorf("CheckpointTick=%v, want 15s", cfg.CheckpointTick)
|
|
}
|
|
if cfg.RefreshInterval != 10*time.Minute {
|
|
t.Errorf("RefreshInterval=%v, want 10m", cfg.RefreshInterval)
|
|
}
|
|
if cfg.MaxRuntime != 120*time.Minute {
|
|
t.Errorf("MaxRuntime=%v, want 120m", cfg.MaxRuntime)
|
|
}
|
|
}
|
|
|
|
func TestParseConfigClampsZeroAndNegative(t *testing.T) {
|
|
worker := map[string]*plugin_pb.ConfigValue{
|
|
"dispatch_tick_minutes": {Kind: &plugin_pb.ConfigValue_Int64Value{Int64Value: 0}},
|
|
"checkpoint_tick_seconds": {Kind: &plugin_pb.ConfigValue_Int64Value{Int64Value: 0}},
|
|
"refresh_interval_minutes": {Kind: &plugin_pb.ConfigValue_Int64Value{Int64Value: 0}},
|
|
"max_runtime_minutes": {Kind: &plugin_pb.ConfigValue_Int64Value{Int64Value: -5}},
|
|
}
|
|
cfg := ParseConfig(nil, worker)
|
|
if cfg.DispatchTick != 1*time.Minute {
|
|
t.Errorf("zero DispatchTick should clamp to default, got %v", cfg.DispatchTick)
|
|
}
|
|
if cfg.CheckpointTick != 30*time.Second {
|
|
t.Errorf("zero CheckpointTick should clamp to default, got %v", cfg.CheckpointTick)
|
|
}
|
|
if cfg.RefreshInterval != 5*time.Minute {
|
|
t.Errorf("zero RefreshInterval should clamp to default, got %v", cfg.RefreshInterval)
|
|
}
|
|
if cfg.MaxRuntime != 60*time.Minute {
|
|
t.Errorf("negative MaxRuntime should clamp to default, got %v", cfg.MaxRuntime)
|
|
}
|
|
}
|