Question

kubernetes很复杂，在某些情况下长时间运行后kubelet会陷入死锁。

是否可以转储正在运行的kubelet的goroutine堆栈跟踪？

如下所示的预期输出对于调试kubelet的死锁类问题非常有帮助。

Route::group(['namespace'=>'Auth'],function(){

    Route::GET('/dang-nhap','LoginController@showLoginForm')->name('login');
    Route::POST('/dang-nhap', 'LoginController@login');
    Route::GET('/dang-xuat', 'LoginController@logout')->name('logout');

    Route::GET('/dang-ky', 'RegisterController@showRegistrationForm')->name('register');
    Route::POST('/dang-ky', 'RegisterController@register');

    Route::GET('/mat-khau/dat-lai-mat-khau', 'ForgotPasswordController@showLinkRequestForm')->name('password.request');
    Route::POST('/mat-khau/email', 'ForgotPasswordController@sendResetLinkEmail')->name('password.email');
    Route::GET('/mat-khau/dat-lai-mat-khau/{token}', 'ResetPasswordController@showResetForm')->name('password.reset');
    Route::POST('/mat-khau/dat-lai-mat-khau', 'ResetPasswordController@reset')->name('password.update');

    Route::GET('email/verify', 'VerificationController@show')->name('verification.notice');
    Route::GET('email/verify/{id}', 'VerificationController@verify')->name('verification.verify');
    Route::GET('email/resend', 'VerificationController@resend')->name('verification.resend');

});

我很感谢任何人都可以分享有关如何抛弃kubelet的goroutines堆栈竞赛的经验，就像docker提供的东西[1]

goroutine 386 [chan send, 1140 minutes]:
k8s.io/kubernetes/pkg/kubelet/pleg.(*GenericPLEG).relist(0xc42069ea20)
    /workspace/anago-v1.11.5-beta.0.24+753b2dbc622f5c/src/k8s.io/kubernetes/_output/dockerized/go/src/k8s.io/kubernetes/pkg/kubelet/pleg/generic.go:261 +0x74e
k8s.io/kubernetes/pkg/kubelet/pleg.(*GenericPLEG).(k8s.io/kubernetes/pkg/kubelet/pleg.relist)-fm()
    /workspace/anago-v1.11.5-beta.0.24+753b2dbc622f5c/src/k8s.io/kubernetes/_output/dockerized/go/src/k8s.io/kubernetes/pkg/kubelet/pleg/generic.go:130 +0x2a
k8s.io/kubernetes/vendor/k8s.io/apimachinery/pkg/util/wait.JitterUntil.func1(0xc4212ee520)
    /workspace/anago-v1.11.5-beta.0.24+753b2dbc622f5c/src/k8s.io/kubernetes/_output/dockerized/go/src/k8s.io/kubernetes/vendor/k8s.io/apimachinery/pkg/util/wait/wait.go:133 +0x54
k8s.io/kubernetes/vendor/k8s.io/apimachinery/pkg/util/wait.JitterUntil(0xc4212ee520, 0x3b9aca00, 0x0, 0x1, 0xc420056540)
    /workspace/anago-v1.11.5-beta.0.24+753b2dbc622f5c/src/k8s.io/kubernetes/_output/dockerized/go/src/k8s.io/kubernetes/vendor/k8s.io/apimachinery/pkg/util/wait/wait.go:134 +0xbd
k8s.io/kubernetes/vendor/k8s.io/apimachinery/pkg/util/wait.Until(0xc4212ee520, 0x3b9aca00, 0xc420056540)
    /workspace/anago-v1.11.5-beta.0.24+753b2dbc622f5c/src/k8s.io/kubernetes/_output/dockerized/go/src/k8s.io/kubernetes/vendor/k8s.io/apimachinery/pkg/util/wait/wait.go:88 +0x4d
created by k8s.io/kubernetes/pkg/kubelet/pleg.(*GenericPLEG).Start
    /workspace/anago-v1.11.5-beta.0.24+753b2dbc622f5c/src/k8s.io/kubernetes/_output/dockerized/go/src/k8s.io/kubernetes/pkg/kubelet/pleg/generic.go:130 +0x88
...
goroutine 309 [sleep]:
time.Sleep(0x12a05f200)
    /usr/local/go/src/runtime/time.go:102 +0x166
k8s.io/kubernetes/pkg/kubelet.(*Kubelet).syncLoop(0xc4205e3b00, 0xc420ff2780, 0x3e56a60, 0xc4205e3b00)
    /workspace/anago-v1.11.5-beta.0.24+753b2dbc622f5c/src/k8s.io/kubernetes/_output/dockerized/go/src/k8s.io/kubernetes/pkg/kubelet/kubelet.go:1777 +0x1e7
k8s.io/kubernetes/pkg/kubelet.(*Kubelet).Run(0xc4205e3b00, 0xc420ff2780)
    /workspace/anago-v1.11.5-beta.0.24+753b2dbc622f5c/src/k8s.io/kubernetes/_output/dockerized/go/src/k8s.io/kubernetes/pkg/kubelet/kubelet.go:1396 +0x27f
k8s.io/kubernetes/cmd/kubelet/app.startKubelet.func1()
    /workspace/anago-v1.11.5-beta.0.24+753b2dbc622f5c/src/k8s.io/kubernetes/_output/dockerized/go/src/k8s.io/kubernetes/cmd/kubelet/app/server.go:998 +0x67
k8s.io/kubernetes/vendor/k8s.io/apimachinery/pkg/util/wait.JitterUntil.func1(0xc42105dfb0)
    /workspace/anago-v1.11.5-beta.0.24+753b2dbc622f5c/src/k8s.io/kubernetes/_output/dockerized/go/src/k8s.io/kubernetes/vendor/k8s.io/apimachinery/pkg/util/wait/wait.go:133 +0x54
k8s.io/kubernetes/vendor/k8s.io/apimachinery/pkg/util/wait.JitterUntil(0xc42105dfb0, 0x0, 0x0, 0x1, 0xc420056540)
    /workspace/anago-v1.11.5-beta.0.24+753b2dbc622f5c/src/k8s.io/kubernetes/_output/dockerized/go/src/k8s.io/kubernetes/vendor/k8s.io/apimachinery/pkg/util/wait/wait.go:134 +0xbd
k8s.io/kubernetes/vendor/k8s.io/apimachinery/pkg/util/wait.Until(0xc42105dfb0, 0x0, 0xc420056540)
    /workspace/anago-v1.11.5-beta.0.24+753b2dbc622f5c/src/k8s.io/kubernetes/_output/dockerized/go/src/k8s.io/kubernetes/vendor/k8s.io/apimachinery/pkg/util/wait/wait.go:88 +0x4d
created by k8s.io/kubernetes/cmd/kubelet/app.startKubelet
    /workspace/anago-v1.11.5-beta.0.24+753b2dbc622f5c/src/k8s.io/kubernetes/_output/dockerized/go/src/k8s.io/kubernetes/cmd/kubelet/app/server.go:996 +0xea
...

[1]。 https://success.docker.com/article/how-to-dump-goroutines-stacktraces

Answer 1

pprof，它将使kubelet保持运行
- 在节点x上安装
- 在一个终端上运行“ kubectl代理”
- 卷曲http://localhost:8001/api/v1/proxy/nodes/node-x/debug/pprof/goroutine?debug=2
发送信号到kubelet，这导致kubelet退出堆栈转储

kill -SIGABRT

如何转储正在运行的kubelet的goroutines堆栈竞赛

1 个答案: