Sobes.tech
Senior

What to say to the interviewer (if asked) "I would use a worker pool with a fixed number of workers, a channel for tasks, and a sync.WaitGroup. The workers will execute requests, and timeout and cancellation will be controlled through the context. I will collect the results in a slice, protected by a mutex (or through a separate channel)."} Now it's your turn Write the code in this chat. I will review and give feedback. If you don't know where to start – ask for a hint. Good luck!

sobes.tech AI

Answer from AI

go package main

import ( "context" "fmt" "sync" "time" )

// Task represents a task for processing type Task struct { id int // other fields }

// WorkerPool implements a pool of workers func WorkerPool(ctx context.Context, tasks <-chan Task, results chan<- string, wg *sync.WaitGroup) { defer wg.Done() for { select { case <-ctx.Done(): return case task, ok := <-tasks: if !ok { return } // Process task res := processTask(task) select { case results <- res: case <-ctx.Done(): return } } } }

func processTask(t Task) string { // simulate work time.Sleep(100 * time.Millisecond) return fmt.Sprintf("result for task %d", t.id) }

func main() { tasks := make(chan Task) results := make(chan string) var wg sync.WaitGroup

ctx, cancel := context.WithTimeout(context.Background(), 2*time.Second)
defer cancel()

workerCount := 5
wg.Add(workerCount)
for i := 0; i < workerCount; i++ {
	go WorkerPool(ctx, tasks, results, &wg)
}

// Separate goroutine to close results channel after workers finish
go func() {
	wg.Wait()
	close(results)
}()

// Send tasks
go func() {
	for i := 0; i < 20; i++ {
		tasks <- Task{id: i}
	}
	close(tasks)
}()

// Collect results
for res := range results {
	fmt.Println(res)
}

}

What to say to the interviewer (if asked) "I would… - sobes.tech