op-node: parallel events executor

op-node/rollup/derive/pipeline.go

@@ -5,6 +5,7 @@ import (
 	"errors"
 	"fmt"
 	"io"
+	"sync/atomic"
 
 	"github.com/ethereum/go-ethereum/common"
 	"github.com/ethereum/go-ethereum/log"
@@ -58,7 +59,7 @@ type DerivationPipeline struct {
 
 	// Index of the stage that is currently being reset.
 	// >= len(stages) if no additional resetting is required
-	resetting int
+	resetting int32
 	stages    []ResettableStage
 
 	// Special stages to keep track of
@@ -70,7 +71,8 @@ type DerivationPipeline struct {
 	origin         eth.L1BlockRef
 	resetL2Safe    eth.L2BlockRef
 	resetSysConfig eth.SystemConfig
-	engineIsReset  bool
+	// Its value is only 1 or 0
+	engineIsReset int32
 
 	metrics Metrics
 }
@@ -112,14 +114,16 @@ func NewDerivationPipeline(log log.Logger, rollupCfg *rollup.Config, l1Fetcher L
 // DerivationReady returns true if the derivation pipeline is ready to be used.
 // When it's being reset its state is inconsistent, and should not be used externally.
 func (dp *DerivationPipeline) DerivationReady() bool {
-	return dp.engineIsReset && dp.resetting > 0
+	engineIsReset := atomic.LoadInt32(&dp.engineIsReset)
+	resetting := atomic.LoadInt32(&dp.resetting)
+	return engineIsReset != 0 && resetting > 0
 }
 
 func (dp *DerivationPipeline) Reset() {
-	dp.resetting = 0
+	atomic.StoreInt32(&dp.resetting, 0)
 	dp.resetSysConfig = eth.SystemConfig{}
 	dp.resetL2Safe = eth.L2BlockRef{}
-	dp.engineIsReset = false
+	atomic.StoreInt32(&dp.engineIsReset, 0)
 }
 
 // Origin is the L1 block of the inner-most stage of the derivation pipeline,
@@ -145,8 +149,8 @@ func (dp *DerivationPipeline) Step(ctx context.Context, pendingSafeHead eth.L2Bl
 	}()
 
 	// if any stages need to be reset, do that first.
-	if dp.resetting < len(dp.stages) {
-		if !dp.engineIsReset {
+	if atomic.LoadInt32(&dp.resetting) < int32(len(dp.stages)) {
+		if atomic.LoadInt32(&dp.engineIsReset) == 0 {
 			return nil, NewResetError(errors.New("cannot continue derivation until Engine has been reset"))
 		}
 
@@ -159,12 +163,13 @@ func (dp *DerivationPipeline) Step(ctx context.Context, pendingSafeHead eth.L2Bl
 			}
 		}
 
-		if err := dp.stages[dp.resetting].Reset(ctx, dp.origin, dp.resetSysConfig); err == io.EOF {
-			dp.log.Debug("reset of stage completed", "stage", dp.resetting, "origin", dp.origin)
-			dp.resetting += 1
+		resetting := atomic.LoadInt32(&dp.resetting)
+		if err := dp.stages[resetting].Reset(ctx, dp.origin, dp.resetSysConfig); err == io.EOF {
+			dp.log.Debug("reset of stage completed", "stage", resetting, "origin", dp.origin)
+			atomic.AddInt32(&dp.resetting, 1)
 			return nil, nil
 		} else if err != nil {
-			return nil, fmt.Errorf("stage %d failed resetting: %w", dp.resetting, err)
+			return nil, fmt.Errorf("stage %d failed resetting: %w", atomic.LoadInt32(&dp.resetting), err)
 		} else {
 			return nil, nil
 		}
@@ -239,5 +244,5 @@ func (dp *DerivationPipeline) initialReset(ctx context.Context, resetL2Safe eth.
 }
 
 func (dp *DerivationPipeline) ConfirmEngineReset() {
-	dp.engineIsReset = true
+	atomic.StoreInt32(&dp.engineIsReset, 1)
 }

op-node/rollup/driver/driver.go

@@ -172,9 +172,8 @@ func NewDriver(
 	var drain func() error
 	// This instantiation will be one of more options: soon there will be a parallel events executor
 	{
-		s := event.NewGlobalSynchronous(driverCtx)
-		executor = s
-		drain = s.Drain
+		executor = event.NewParallelExec()
+		drain = func() error { return nil } // no-op
 	}
 	sys := event.NewSystem(log, executor)
 	sys.AddTracer(event.NewMetricsTracer(metrics))

op-node/rollup/driver/state.go

@@ -199,6 +199,8 @@ func (s *Driver) eventLoop() {
 	defer altSyncTicker.Stop()
 	lastUnsafeL2 := s.Engine.UnsafeL2Head()
 
+	var currentNextDelayedStep <-chan time.Time = nil
+
 	for {
 		if s.driverCtx.Err() != nil { // don't try to schedule/handle more work when we are closing.
 			return
@@ -227,6 +229,7 @@ func (s *Driver) eventLoop() {
 		select {
 		case <-sequencerCh:
 			s.Emitter.Emit(sequencing.SequencerActionEvent{})
+		case <-s.sequencer.NextActionStep():
 		case <-altSyncTicker.C:
 			// Check if there is a gap in the current unsafe payload queue.
 			ctx, cancel := context.WithTimeout(s.driverCtx, time.Second*2)
@@ -265,7 +268,9 @@ func (s *Driver) eventLoop() {
 		case newL1Finalized := <-s.l1FinalizedSig:
 			s.emitter.Emit(finality.FinalizeL1Event{FinalizedL1: newL1Finalized})
 			reqStep() // we may be able to mark more L2 data as finalized now
-		case <-s.sched.NextDelayedStep():
+		case req := <-s.sched.UpdateDelayedStepReq:
+			currentNextDelayedStep = req
+		case <-currentNextDelayedStep:
 			s.emitter.Emit(StepAttemptEvent{})
 		case <-s.sched.NextStep():
 			s.emitter.Emit(StepAttemptEvent{})

op-node/rollup/driver/steps.go

@@ -62,7 +62,8 @@ type StepSchedulingDeriver struct {
 	bOffStrategy retry.Strategy
 
 	// channel, nil by default (not firing), but used to schedule re-attempts with delay
-	delayedStepReq <-chan time.Time
+	delayedStepReq       <-chan time.Time
+	UpdateDelayedStepReq chan (<-chan time.Time)
 
 	// stepReqCh is used to request that the driver attempts to step forward by one L1 block.
 	stepReqCh chan struct{}
@@ -74,11 +75,12 @@ type StepSchedulingDeriver struct {
 
 func NewStepSchedulingDeriver(log log.Logger) *StepSchedulingDeriver {
 	return &StepSchedulingDeriver{
-		stepAttempts:   0,
-		bOffStrategy:   retry.Exponential(),
-		stepReqCh:      make(chan struct{}, 1),
-		delayedStepReq: nil,
-		log:            log,
+		stepAttempts:         0,
+		bOffStrategy:         retry.Exponential(),
+		stepReqCh:            make(chan struct{}, 1),
+		delayedStepReq:       nil,
+		log:                  log,
+		UpdateDelayedStepReq: make(chan (<-chan time.Time), 1),
 	}
 }
 
@@ -102,6 +104,11 @@ func (s *StepSchedulingDeriver) NextDelayedStep() <-chan time.Time {
 func (s *StepSchedulingDeriver) OnEvent(ev event.Event) bool {
 	step := func() {
 		s.delayedStepReq = nil
+		select {
+		case s.UpdateDelayedStepReq <- s.delayedStepReq:
+		default:
+		}
+
 		select {
 		case s.stepReqCh <- struct{}{}:
 		// Don't deadlock if the channel is already full
@@ -113,6 +120,10 @@ func (s *StepSchedulingDeriver) OnEvent(ev event.Event) bool {
 	case StepDelayedReqEvent:
 		if s.delayedStepReq == nil {
 			s.delayedStepReq = time.After(x.Delay)
+			select {
+			case s.UpdateDelayedStepReq <- s.delayedStepReq:
+			default:
+			}
 		}
 	case StepReqEvent:
 		if x.ResetBackoff {
@@ -124,6 +135,10 @@ func (s *StepSchedulingDeriver) OnEvent(ev event.Event) bool {
 				delay := s.bOffStrategy.Duration(s.stepAttempts)
 				s.log.Debug("scheduling re-attempt with delay", "attempts", s.stepAttempts, "delay", delay)
 				s.delayedStepReq = time.After(delay)
+				select {
+				case s.UpdateDelayedStepReq <- s.delayedStepReq:
+				default:
+				}
 			} else {
 				s.log.Debug("ignoring step request, already scheduled re-attempt after previous failure", "attempts", s.stepAttempts)
 			}
@@ -133,6 +148,10 @@ func (s *StepSchedulingDeriver) OnEvent(ev event.Event) bool {
 	case StepAttemptEvent:
 		// clear the delayed-step channel
 		s.delayedStepReq = nil
+		select {
+		case s.UpdateDelayedStepReq <- s.delayedStepReq:
+		default:
+		}
 		if s.stepAttempts > 0 {
 			s.log.Debug("Running step retry", "attempts", s.stepAttempts)
 		}

op-node/rollup/event/executor_parallel.go

@@ -0,0 +1,116 @@
+package event
+
+import (
+	"context"
+	"fmt"
+	"slices"
+	"sync"
+	"sync/atomic"
+	"time"
+)
+
+type ParallelExec struct {
+	workers []*worker
+	mu      sync.RWMutex
+}
+
+var _ Executor = (*ParallelExec)(nil)
+
+func NewParallelExec() *ParallelExec {
+	return &ParallelExec{}
+}
+
+func (p *ParallelExec) Add(d Executable, opts *ExecutorOpts) (leaveExecutor func()) {
+	p.mu.Lock()
+	defer p.mu.Unlock()
+	fmt.Println(time.Now().Format("2006-01-02 15:04:05.00000"), ", add handler parallel, handler name:,", opts.Capacity)
+	w := newWorker(p, d, opts)
+	p.workers = append(p.workers, w)
+	return w.leave
+}
+
+func (p *ParallelExec) remove(w *worker) {
+	p.mu.Lock()
+	defer p.mu.Unlock()
+	// Linear search to delete is fine,
+	// since we delete much less frequently than we process events with these.
+	for i, v := range p.workers {
+		if v == w {
+			p.workers = slices.Delete(p.workers, i, i+1)
+			return
+		}
+	}
+}
+
+func (p *ParallelExec) Enqueue(ev AnnotatedEvent) error {
+	p.mu.RLock()
+	defer p.mu.RUnlock()
+	for _, w := range p.workers {
+		w.enqueue(ev) // this will block if its capacity is full, providing back-pressure to the Enqueue caller
+	}
+	return nil
+}
+
+type worker struct {
+	// ctx signals when the worker is exiting.
+	// No additional events will be accepted after cancellation.
+	ctx    context.Context
+	cancel context.CancelFunc
+
+	// closed as channel is closed upon exit of the run loop
+	closed chan struct{}
+
+	// ingress is the buffered channel of events to process
+	ingress chan AnnotatedEvent
+
+	// d is the underlying executable to process events on
+	d Executable
+
+	// p is a reference to the ParallelExec that owns this worker.
+	// The worker removes itself from this upon leaving.
+	p atomic.Pointer[ParallelExec]
+}
+
+func newWorker(p *ParallelExec, d Executable, opts *ExecutorOpts) *worker {
+	ctx, cancel := context.WithCancel(context.Background())
+	w := &worker{
+		ctx:     ctx,
+		cancel:  cancel,
+		closed:  make(chan struct{}),
+		ingress: make(chan AnnotatedEvent, opts.Capacity),
+		d:       d,
+	}
+	w.p.Store(p)
+	go w.run()
+	return w
+}
+
+func (w *worker) enqueue(ev AnnotatedEvent) {
+	select {
+	case <-w.ctx.Done():
+	case w.ingress <- ev:
+	}
+
+}
+
+func (w *worker) leave() {
+	w.cancel()
+	if old := w.p.Swap(nil); old != nil {
+		// remove from worker pool
+		old.remove(w)
+	}
+	// wait for run loop to exit
+	<-w.closed
+}
+
+func (w *worker) run() {
+	for {
+		select {
+		case <-w.ctx.Done():
+			close(w.closed)
+			return
+		case ev := <-w.ingress:
+			w.d.RunEvent(ev)
+		}
+	}
+}

op-node/rollup/event/system.go

@@ -61,7 +61,7 @@ func (r *systemActor) Emit(ev Event) {
 	if r.ctx.Err() != nil {
 		return
 	}
-	r.sys.emit(r.name, r.currentEvent, ev)
+	r.sys.emit(r.name, atomic.LoadUint64(&r.currentEvent), ev)
 }
 
 // RunEvent is called by the events executor.
@@ -74,13 +74,13 @@ func (r *systemActor) RunEvent(ev AnnotatedEvent) {
 		return
 	}
 
-	prev := r.currentEvent
+	prev := atomic.LoadUint64(&r.currentEvent)
 	start := time.Now()
-	r.currentEvent = r.sys.recordDerivStart(r.name, ev, start)
+	atomic.StoreUint64(&r.currentEvent, r.sys.recordDerivStart(r.name, ev, start))
 	effect := r.deriv.OnEvent(ev.Event)
 	elapsed := time.Since(start)
-	r.sys.recordDerivEnd(r.name, ev, r.currentEvent, start, elapsed, effect)
-	r.currentEvent = prev
+	r.sys.recordDerivEnd(r.name, ev, atomic.LoadUint64(&r.currentEvent), start, elapsed, effect)
+	atomic.StoreUint64(&r.currentEvent, prev)
 }
 
 // Sys is the canonical implementation of System.
@@ -130,7 +130,7 @@ func (s *Sys) Register(name string, deriver Deriver, opts *RegisterOpts) Emitter
 	if opts.Emitter.Limiting {
 		limitedCallback := opts.Emitter.OnLimited
 		em = NewLimiter(ctx, r, opts.Emitter.Rate, opts.Emitter.Burst, func() {
-			r.sys.recordRateLimited(name, r.currentEvent)
+			r.sys.recordRateLimited(name, atomic.LoadUint64(&r.currentEvent))
 			if limitedCallback != nil {
 				limitedCallback()
 			}

op-node/rollup/sequencing/disabled.go

@@ -24,6 +24,8 @@ func (ds DisabledSequencer) NextAction() (t time.Time, ok bool) {
 	return time.Time{}, false
 }
 
+func (ds DisabledSequencer) NextActionStep() <-chan struct{} { return nil }
+
 func (ds DisabledSequencer) Active() bool {
 	return false
 }

op-node/rollup/sequencing/iface.go

@@ -13,6 +13,7 @@ type SequencerIface interface {
 	event.Deriver
 	// NextAction returns when the sequencer needs to do the next change, and iff it should do so.
 	NextAction() (t time.Time, ok bool)
+	NextActionStep() <-chan struct{}
 	Active() bool
 	Init(ctx context.Context, active bool) error
 	Start(ctx context.Context, head common.Hash) error