Files
notarius/internal/framework/llm/scheduler.go

126 lines
2.4 KiB
Go

package llm
import (
"context"
"fmt"
"sync"
)
// Scheduler bounds concurrent LLM backend calls.
type Scheduler struct {
maxConcurrency int
mu sync.Mutex
inFlight int
queue []*waiter
}
type waiter struct {
ready chan struct{}
queued bool
granted bool
}
// NewScheduler creates a scheduler with a fixed concurrency limit.
func NewScheduler(maxConcurrency int) (*Scheduler, error) {
if maxConcurrency <= 0 {
return nil, fmt.Errorf("max concurrency must be greater than zero")
}
return &Scheduler{
maxConcurrency: maxConcurrency,
}, nil
}
// Acquire blocks until a permit is available or the context is canceled.
// The returned release function is safe to call multiple times.
func (s *Scheduler) Acquire(ctx context.Context) (func(), error) {
if s == nil {
return nil, fmt.Errorf("scheduler must not be nil")
}
if err := ctx.Err(); err != nil {
return nil, err
}
s.mu.Lock()
if s.inFlight < s.maxConcurrency && len(s.queue) == 0 {
s.inFlight++
s.mu.Unlock()
return s.releaseFunc(), nil
}
w := &waiter{
ready: make(chan struct{}),
queued: true,
}
s.queue = append(s.queue, w)
s.mu.Unlock()
select {
case <-w.ready:
return s.releaseFunc(), nil
case <-ctx.Done():
s.mu.Lock()
if w.queued {
s.removeQueuedWaiterLocked(w)
s.mu.Unlock()
return nil, ctx.Err()
}
if w.granted {
s.inFlight--
s.grantQueuedLocked()
}
s.mu.Unlock()
return nil, ctx.Err()
}
}
// Run acquires a permit, executes fn, and releases the permit.
func (s *Scheduler) Run(ctx context.Context, fn func(context.Context) error) error {
if fn == nil {
return fmt.Errorf("scheduler function must not be nil")
}
release, err := s.Acquire(ctx)
if err != nil {
return err
}
defer release()
if err := ctx.Err(); err != nil {
return err
}
return fn(ctx)
}
func (s *Scheduler) releaseFunc() func() {
var once sync.Once
return func() {
once.Do(func() {
s.mu.Lock()
if s.inFlight > 0 {
s.inFlight--
s.grantQueuedLocked()
}
s.mu.Unlock()
})
}
}
func (s *Scheduler) grantQueuedLocked() {
for s.inFlight < s.maxConcurrency && len(s.queue) > 0 {
w := s.queue[0]
s.queue = s.queue[1:]
w.queued = false
w.granted = true
s.inFlight++
close(w.ready)
}
}
func (s *Scheduler) removeQueuedWaiterLocked(target *waiter) {
for i, w := range s.queue {
if w == target {
w.queued = false
s.queue = append(s.queue[:i], s.queue[i+1:]...)
return
}
}
}