【容器】k8s获取的节点oom事件并输出到node事件

在debug k8s node不可用过程中，有可能会看到:

System OOM encountered, victim process: xx

为了搞清楚oom事件是什么，以及如何产生的，我们做了一定探索，并输出了下面的信息。（本文关注oom事件是如何生成&传输的，具体cadvisor如何判定oom不在本片的讨论范围）

解析

主要代码文件：

1）pkg.kubelet.oom.oom_watcher_linux.go

oom_watcher主要描述了kubelet是如何接受并log系统产生的oom事件的

2）oom_watcher_linux.go：

NewWatcher方法会返回一个Watcher类型的对象，该对象包含recorder和oomStreamer。recorder用于记录，oomStreamer是一个OomParser(Cadvisor)类型的对象, 用于将OomInstance类型的对象写入outStream管道（channel）

package oomimport ("fmt"v1 "k8s.io/api/core/v1""k8s.io/apimachinery/pkg/util/runtime""k8s.io/client-go/tools/record""k8s.io/klog/v2""github.com/google/cadvisor/utils/oomparser"
)// streamer 接口定义了一个 StreamOoms 函数，
// 它接收一个 oomparser.OomInstance 类型的 channel，存储OomInstance类型数据
type streamer interface {StreamOoms(chan<- *oomparser.OomInstance)
}var _ streamer = &oomparser.OomParser{}type realWatcher struct {recorder    record.EventRecorderoomStreamer streamer
}var _ Watcher = &realWatcher{}// NewWatcher creates and initializes a OOMWatcher backed by Cadvisor as
// the oom streamer.
// 启动一个新的OOM watcher, 参数是一个 EventRecorder
// EventRecorder 是一个能够存储event并记录到一个queue里的Interface
// 函数声明中前面的括号里面是函数形参列表；后面的括号里面是函数返回值列表。
func NewWatcher(recorder record.EventRecorder) (Watcher, error) {
// 生成一个oomStreamer，由cadvisor的oomparser创建oomStreamer, err := oomparser.New()if err != nil {return nil, err}
// 生成一个watcher，包含上面的两个对象： recorder 和 oomStreamerwatcher := &realWatcher{recorder:    recorder,oomStreamer: oomStreamer,}return watcher, nil
}// Start watches for system oom's and records an event for every system oom encountered.
func (ow *realWatcher) Start(ref *v1.ObjectReference) error {
// 这段代码用来创建一个outStream channel，它是一个由 oomparser.OomInstance 
// 类型指针元素的channel，并可以向channel中传输10个元素。接着就启动了一个goroutine，
// 该goroutine调用ow.oomStreamer.StreamOoms方法并将outStream作为参数传入。该方法会往outStream channel中不断地写数据（即oom instance对象）outStream := make(chan *oomparser.OomInstance, 10)go ow.oomStreamer.StreamOoms(outStream)go func() {defer runtime.HandleCrash()
// 从outStream 读取event，并根据判断条件做是否oom。并输出相应的logfor event := range outStream {if event.VictimContainerName == recordEventContainerName {klog.V(1).InfoS("Got sys oom event", "event", event)eventMsg := "System OOM encountered"if event.ProcessName != "" && event.Pid != 0 {eventMsg = fmt.Sprintf("%s, victim process: %s, pid: %d", eventMsg, event.ProcessName, event.Pid)}ow.recorder.Eventf(ref, v1.EventTypeWarning, systemOOMEvent, eventMsg)}}klog.ErrorS(nil, "Unexpectedly stopped receiving OOM notifications")}()return nil
}

再来看下kubelet.go中如何应用
kubelet.go:
创建oomWatcher

# 通过上面的NewWathcher方法创建一个新的oomWatcher
oomWatcher, err := oomwatcher.NewWatcher(kubeDeps.Recorder)
# 如果创建新的oomWatcher报错，则查看原因
if err != nil {if libcontaineruserns.RunningInUserNS() {if utilfeature.DefaultFeatureGate.Enabled(features.KubeletInUserNamespace) {// oomwatcher.NewWatcher returns "open /dev/kmsg: operation not permitted" error,// when running in a user namespace with sysctl value `kernel.dmesg_restrict=1`.klog.V(2).InfoS("Failed to create an oomWatcher (running in UserNS, ignoring)", "err", err)oomWatcher = nil} else {klog.ErrorS(err, "Failed to create an oomWatcher (running in UserNS, Hint: enable KubeletInUserNamespace feature flag to ignore the error)")return nil, err}} else {return nil, err}
}

启动oomWatcher

    // Start out of memory watcher.if kl.oomWatcher != nil {if err := kl.oomWatcher.Start(kl.nodeRef); err != nil {return fmt.Errorf("failed to start OOM watcher: %w", err)}}