add admin script worker (#8491)

* admin: add plugin lock coordination * shell: allow bypassing lock checks * plugin worker: add admin script handler * mini: include admin_script in plugin defaults * admin script UI: drop name and enlarge text * admin script: add default script * admin_script: make run interval configurable * plugin: gate other jobs during admin_script runs * plugin: use last completed admin_script run * admin: backfill plugin config defaults * templ Co-Authored-By: Copilot <223556219+Copilot@users.noreply.github.com> * comparable to default version Co-Authored-By: Copilot <223556219+Copilot@users.noreply.github.com> * default to run Co-Authored-By: Copilot <223556219+Copilot@users.noreply.github.com> * format Co-Authored-By: Copilot <223556219+Copilot@users.noreply.github.com> * shell: respect pre-set noLock for fix.replication * shell: add force no-lock mode for admin scripts * volume balance worker already exists Co-Authored-By: Copilot <223556219+Copilot@users.noreply.github.com> * admin: expose scheduler status JSON * shell: add sleep command * shell: restrict sleep syntax * Revert "shell: respect pre-set noLock for fix.replication" This reverts commit 2b14e8b82602a740d3a473c085e3b3a14f1ddbb3. * templ Co-Authored-By: Copilot <223556219+Copilot@users.noreply.github.com> * fix import Co-Authored-By: Copilot <223556219+Copilot@users.noreply.github.com> * less logs Co-Authored-By: Copilot <223556219+Copilot@users.noreply.github.com> * Reduce master client logs on canceled contexts * Update mini default job type count --------- Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
2026-03-03 15:10:40 -08:00
parent 16f2269a33
commit e1e5b4a8a6
27 changed files with 1888 additions and 27 deletions
--- a/weed/admin/plugin/plugin_cancel_test.go
+++ b/weed/admin/plugin/plugin_cancel_test.go
@@ -4,8 +4,10 @@ import (
 	"context"
 	"errors"
 	"testing"
+	"time"

 	"github.com/seaweedfs/seaweedfs/weed/pb/plugin_pb"
+	"google.golang.org/protobuf/types/known/timestamppb"
 )

 func TestRunDetectionSendsCancelOnContextDone(t *testing.T) {
@@ -110,3 +112,165 @@ func TestExecuteJobSendsCancelOnContextDone(t *testing.T) {
 		t.Fatalf("expected context canceled error, got %v", runErr)
 	}
 }
+
+func TestAdminScriptExecutionBlocksOtherDetection(t *testing.T) {
+	pluginSvc, err := New(Options{})
+	if err != nil {
+		t.Fatalf("New plugin error: %v", err)
+	}
+	defer pluginSvc.Shutdown()
+
+	const adminWorkerID = "worker-admin-script"
+	const otherWorkerID = "worker-vacuum"
+
+	pluginSvc.registry.UpsertFromHello(&plugin_pb.WorkerHello{
+		WorkerId: adminWorkerID,
+		Capabilities: []*plugin_pb.JobTypeCapability{
+			{JobType: "admin_script", CanExecute: true, MaxExecutionConcurrency: 1},
+		},
+	})
+	pluginSvc.registry.UpsertFromHello(&plugin_pb.WorkerHello{
+		WorkerId: otherWorkerID,
+		Capabilities: []*plugin_pb.JobTypeCapability{
+			{JobType: "vacuum", CanDetect: true, MaxDetectionConcurrency: 1},
+		},
+	})
+	adminSession := &streamSession{workerID: adminWorkerID, outgoing: make(chan *plugin_pb.AdminToWorkerMessage, 8)}
+	otherSession := &streamSession{workerID: otherWorkerID, outgoing: make(chan *plugin_pb.AdminToWorkerMessage, 8)}
+	pluginSvc.putSession(adminSession)
+	pluginSvc.putSession(otherSession)
+
+	adminErrCh := make(chan error, 1)
+	go func() {
+		_, runErr := pluginSvc.ExecuteJob(context.Background(), &plugin_pb.JobSpec{
+			JobId:   "job-admin-script-1",
+			JobType: "admin_script",
+		}, &plugin_pb.ClusterContext{}, 1)
+		adminErrCh <- runErr
+	}()
+
+	adminExecMessage := <-adminSession.outgoing
+	if adminExecMessage.GetExecuteJobRequest() == nil {
+		t.Fatalf("expected admin_script execute request")
+	}
+
+	detectErrCh := make(chan error, 1)
+	go func() {
+		_, runErr := pluginSvc.RunDetection(context.Background(), "vacuum", &plugin_pb.ClusterContext{}, 10)
+		detectErrCh <- runErr
+	}()
+
+	select {
+	case unexpected := <-otherSession.outgoing:
+		t.Fatalf("expected vacuum detection to wait while admin_script runs, got message: %+v", unexpected)
+	case <-time.After(100 * time.Millisecond):
+	}
+
+	pluginSvc.handleJobCompleted(&plugin_pb.JobCompleted{
+		RequestId:   adminExecMessage.RequestId,
+		JobId:       "job-admin-script-1",
+		JobType:     "admin_script",
+		Success:     true,
+		CompletedAt: timestamppb.Now(),
+	})
+	if runErr := <-adminErrCh; runErr != nil {
+		t.Fatalf("admin_script ExecuteJob error: %v", runErr)
+	}
+
+	detectMessage := <-otherSession.outgoing
+	detectRequest := detectMessage.GetRunDetectionRequest()
+	if detectRequest == nil {
+		t.Fatalf("expected vacuum detection request after admin_script completion")
+	}
+	pluginSvc.handleDetectionComplete(otherWorkerID, &plugin_pb.DetectionComplete{
+		RequestId: detectMessage.RequestId,
+		JobType:   "vacuum",
+		Success:   true,
+	})
+	if runErr := <-detectErrCh; runErr != nil {
+		t.Fatalf("vacuum RunDetection error: %v", runErr)
+	}
+}
+
+func TestAdminScriptExecutionBlocksOtherExecution(t *testing.T) {
+	pluginSvc, err := New(Options{})
+	if err != nil {
+		t.Fatalf("New plugin error: %v", err)
+	}
+	defer pluginSvc.Shutdown()
+
+	const adminWorkerID = "worker-admin-script"
+	const otherWorkerID = "worker-vacuum"
+
+	pluginSvc.registry.UpsertFromHello(&plugin_pb.WorkerHello{
+		WorkerId: adminWorkerID,
+		Capabilities: []*plugin_pb.JobTypeCapability{
+			{JobType: "admin_script", CanExecute: true, MaxExecutionConcurrency: 1},
+		},
+	})
+	pluginSvc.registry.UpsertFromHello(&plugin_pb.WorkerHello{
+		WorkerId: otherWorkerID,
+		Capabilities: []*plugin_pb.JobTypeCapability{
+			{JobType: "vacuum", CanExecute: true, MaxExecutionConcurrency: 1},
+		},
+	})
+	adminSession := &streamSession{workerID: adminWorkerID, outgoing: make(chan *plugin_pb.AdminToWorkerMessage, 8)}
+	otherSession := &streamSession{workerID: otherWorkerID, outgoing: make(chan *plugin_pb.AdminToWorkerMessage, 8)}
+	pluginSvc.putSession(adminSession)
+	pluginSvc.putSession(otherSession)
+
+	adminErrCh := make(chan error, 1)
+	go func() {
+		_, runErr := pluginSvc.ExecuteJob(context.Background(), &plugin_pb.JobSpec{
+			JobId:   "job-admin-script-2",
+			JobType: "admin_script",
+		}, &plugin_pb.ClusterContext{}, 1)
+		adminErrCh <- runErr
+	}()
+
+	adminExecMessage := <-adminSession.outgoing
+	if adminExecMessage.GetExecuteJobRequest() == nil {
+		t.Fatalf("expected admin_script execute request")
+	}
+
+	otherErrCh := make(chan error, 1)
+	go func() {
+		_, runErr := pluginSvc.ExecuteJob(context.Background(), &plugin_pb.JobSpec{
+			JobId:   "job-vacuum-1",
+			JobType: "vacuum",
+		}, &plugin_pb.ClusterContext{}, 1)
+		otherErrCh <- runErr
+	}()
+
+	select {
+	case unexpected := <-otherSession.outgoing:
+		t.Fatalf("expected vacuum execute to wait while admin_script runs, got message: %+v", unexpected)
+	case <-time.After(100 * time.Millisecond):
+	}
+
+	pluginSvc.handleJobCompleted(&plugin_pb.JobCompleted{
+		RequestId:   adminExecMessage.RequestId,
+		JobId:       "job-admin-script-2",
+		JobType:     "admin_script",
+		Success:     true,
+		CompletedAt: timestamppb.Now(),
+	})
+	if runErr := <-adminErrCh; runErr != nil {
+		t.Fatalf("admin_script ExecuteJob error: %v", runErr)
+	}
+
+	otherExecMessage := <-otherSession.outgoing
+	if otherExecMessage.GetExecuteJobRequest() == nil {
+		t.Fatalf("expected vacuum execute request after admin_script completion")
+	}
+	pluginSvc.handleJobCompleted(&plugin_pb.JobCompleted{
+		RequestId:   otherExecMessage.RequestId,
+		JobId:       "job-vacuum-1",
+		JobType:     "vacuum",
+		Success:     true,
+		CompletedAt: timestamppb.Now(),
+	})
+	if runErr := <-otherErrCh; runErr != nil {
+		t.Fatalf("vacuum ExecuteJob error: %v", runErr)
+	}
+}