03-写一个控制器

想系统学习k8s源码，云原生的可以加：mkjnnm

背景

informer 设计之初是为了更好的写 controller，本章我们来手写一个 controller，下图是官方推荐的编程模式：

• 控制器包含三部分： informer ，workqueue，control loop
• informer 负责同步远端集群资源到本地缓存Indexer
• informer 负责将资源变化放入 workqueue
• controller 需要有个 sync 方法，不停从workqueue 中获取变化并处理

代码设计

1.定义控制器

// Controller demonstrates how to implement a controller with client-go.
type Controller struct {
	indexer  cache.Indexer
	queue    workqueue.TypedRateLimitingInterface[string]
	informer cache.Controller
}

// NewController creates a new Controller.
func NewController(queue workqueue.TypedRateLimitingInterface[string], indexer cache.Indexer, informer cache.Controller) *Controller {
	return &Controller{
		informer: informer,
		indexer:  indexer,
		queue:    queue,
	}
}

2.给控制器添加Run方法

启动控制器前要先启动 informer 并等待同步完成，然后起携程调用 runworker 方法。

// Run begins watching and syncing.
func (c *Controller) Run(workers int, stopCh chan struct{}) {
	defer runtime.HandleCrash()

	// Let the workers stop when we are done
	defer c.queue.ShutDown()
	klog.Info("Starting Pod controller")

	go c.informer.Run(stopCh)

	// Wait for all involved caches to be synced, before processing items from the queue is started
	if !cache.WaitForCacheSync(stopCh, c.informer.HasSynced) {
		runtime.HandleError(fmt.Errorf("Timed out waiting for caches to sync"))
		return
	}

	for i := 0; i < workers; i++ {
		go wait.Until(c.runWorker, time.Second, stopCh)
	}

	<-stopCh
	klog.Info("Stopping Pod controller")
}

3.实现 runworker方法

在 runWorker 方法中，我们一直调用 processNextItem 方法，这个方法会从 queue 中取出资源的 key，调用 syncToStdout 处理，如果出错，调用handleErr

func (c *Controller) runWorker() {
	for c.processNextItem() {
	}
}
func (c *Controller) processNextItem() bool {
	// Wait until there is a new item in the working queue
	key, quit := c.queue.Get()
	if quit {
		return false
	}
	// Tell the queue that we are done with processing this key. This unblocks the key for other workers
	// This allows safe parallel processing because two pods with the same key are never processed in
	// parallel.
	defer c.queue.Done(key)

	// Invoke the method containing the business logic
	err := c.syncToStdout(key)
	// Handle the error if something went wrong during the execution of the business logic
	c.handleErr(err, key)
	return true
}

4.实现 syncToStdout 和 handleErr

• syncToStdout : 根据key去本地缓存查询出完整对象 obj，然后简单打印
• handleErr：出错重新放回队列，延迟一段时间继续处理

// syncToStdout is the business logic of the controller. In this controller it simply prints
// information about the pod to stdout. In case an error happened, it has to simply return the error.
// The retry logic should not be part of the business logic.
func (c *Controller) syncToStdout(key string) error {
	obj, exists, err := c.indexer.GetByKey(key)
	if err != nil {
		klog.Errorf("Fetching object with key %s from store failed with %v", key, err)
		return err
	}

	if !exists {
		// Below we will warm up our cache with a Pod, so that we will see a delete for one pod
		fmt.Printf("Pod %s does not exist anymore\n", key)
	} else {
		// Note that you also have to check the uid if you have a local controlled resource, which
		// is dependent on the actual instance, to detect that a Pod was recreated with the same name
		fmt.Printf("Sync/Add/Update for Pod %s\n", obj.(*v1.Pod).GetName())
	}
	return nil
}

// handleErr checks if an error happened and makes sure we will retry later.
func (c *Controller) handleErr(err error, key string) {
	if err == nil {
		// Forget about the #AddRateLimited history of the key on every successful synchronization.
		// This ensures that future processing of updates for this key is not delayed because of
		// an outdated error history.
		c.queue.Forget(key)
		return
	}

	// This controller retries 5 times if something goes wrong. After that, it stops trying.
	if c.queue.NumRequeues(key) < 5 {
		klog.Infof("Error syncing pod %v: %v", key, err)

		// Re-enqueue the key rate limited. Based on the rate limiter on the
		// queue and the re-enqueue history, the key will be processed later again.
		c.queue.AddRateLimited(key)
		return
	}

	c.queue.Forget(key)
	// Report to an external entity that, even after several retries, we could not successfully process this key
	runtime.HandleError(err)
	klog.Infof("Dropping pod %q out of the queue: %v", key, err)
}

5.实现main方法

func main() {
	var kubeconfig string
	var master string

	flag.StringVar(&kubeconfig, "kubeconfig", "", "absolute path to the kubeconfig file")
	flag.StringVar(&master, "master", "", "master url")
	flag.Parse()

	// creates the connection
	config, err := clientcmd.BuildConfigFromFlags(master, kubeconfig)
	if err != nil {
		klog.Fatal(err)
	}

	// creates the clientset
	clientset, err := kubernetes.NewForConfig(config)
	if err != nil {
		klog.Fatal(err)
	}

	// create the pod watcher
	podListWatcher := cache.NewListWatchFromClient(clientset.CoreV1().RESTClient(), "pods", v1.NamespaceDefault, fields.Everything())

	// create the workqueue
	queue := workqueue.NewTypedRateLimitingQueue(workqueue.DefaultTypedControllerRateLimiter[string]())

	// Bind the workqueue to a cache with the help of an informer. This way we make sure that
	// whenever the cache is updated, the pod key is added to the workqueue.
	// Note that when we finally process the item from the workqueue, we might see a newer version
	// of the Pod than the version which was responsible for triggering the update.
	indexer, informer := cache.NewIndexerInformer(podListWatcher, &v1.Pod{}, 0, cache.ResourceEventHandlerFuncs{
		AddFunc: func(obj interface{}) {
			key, err := cache.MetaNamespaceKeyFunc(obj)
			if err == nil {
				queue.Add(key)
			}
		},
		UpdateFunc: func(old interface{}, new interface{}) {
			key, err := cache.MetaNamespaceKeyFunc(new)
			if err == nil {
				queue.Add(key)
			}
		},
		DeleteFunc: func(obj interface{}) {
			// IndexerInformer uses a delta queue, therefore for deletes we have to use this
			// key function.
			key, err := cache.DeletionHandlingMetaNamespaceKeyFunc(obj)
			if err == nil {
				queue.Add(key)
			}
		},
	}, cache.Indexers{})

	controller := NewController(queue, indexer, informer)

	// We can now warm up the cache for initial synchronization.
	// Let's suppose that we knew about a pod "mypod" on our last run, therefore add it to the cache.
	// If this pod is not there anymore, the controller will be notified about the removal after the
	// cache has synchronized.
	indexer.Add(&v1.Pod{
		ObjectMeta: meta_v1.ObjectMeta{
			Name:      "mypod",
			Namespace: v1.NamespaceDefault,
		},
	})

	// Now let's start the controller
	stop := make(chan struct{})
	defer close(stop)
	go controller.Run(1, stop)

	// Wait forever
	select {}
}