github
/
k3s
mirror of https://github.com/k3s-io/k3s
1
0
Fork 0
Code Issues Projects Releases Wiki Activity

Merge pull request #53318 from sjenning/fix-http-probe-conn-pools 

Automatic merge from submit-queue. If you want to cherry-pick this change to another branch, please follow the instructions <a href="https://github.com/kubernetes/community/blob/master/contributors/devel/cherry-picks.md">here</a>.

create separate transports for liveness and readiness probes

There is currently an issue with the http2 connection pools in golang such that two GETs to the same host:port using the same Transport can collide and one gets rejected with `http2: no cached connection was available`.  This happens with readiness and liveness probes if the intervals line up such that worker goroutines invoke the two probes at the exact same time.

The result is a transient probe error that appears in the events.  If the failureThreshold is 1, which is kinda crazy, it would cause a pod restart.

The PR creates a separate `httprobe` instance for readiness and liveness probes so that they don't share a Transport and connection pool.

Fixes https://github.com/kubernetes/kubernetes/issues/49740

@smarterclayton @jhorwit2
pull/6/head
Kubernetes Submit Queue 2017-10-01 21:45:50 -07:00 committed by GitHub
parent 5e2ce3aaf2 343036e350
commit 6ed207374f
1 changed files with 24 additions and 15 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

39
pkg/kubelet/prober/prober.go
View File

@ -46,10 +46,14 @@ const maxProbeRetries = 3
// Prober helps to check the liveness/readiness of a container.
type prober struct {
exec execprobe.ExecProber
http httprobe.HTTPProber
tcp tcprobe.TCPProber
runner kubecontainer.ContainerCommandRunner
exec execprobe.ExecProber
// probe types needs different httprobe instances so they don't
// share a connection pool which can cause collsions to the
// same host:port and transient failures. See #49740.
readinessHttp httprobe.HTTPProber
livenessHttp httprobe.HTTPProber
tcp tcprobe.TCPProber
runner kubecontainer.ContainerCommandRunner
refManager *kubecontainer.RefManager
recorder record.EventRecorder
@ -63,12 +67,13 @@ func newProber(
recorder record.EventRecorder) *prober {
return &prober{
exec: execprobe.New(),
http: httprobe.New(),
tcp: tcprobe.New(),
runner: runner,
refManager: refManager,
recorder: recorder,
exec: execprobe.New(),
readinessHttp: httprobe.New(),
livenessHttp: httprobe.New(),
tcp: tcprobe.New(),
runner: runner,
refManager: refManager,
recorder: recorder,
}
}
@ -90,7 +95,7 @@ func (pb *prober) probe(probeType probeType, pod *v1.Pod, status v1.PodStatus, c
return results.Success, nil
}
result, output, err := pb.runProbeWithRetries(probeSpec, pod, status, container, containerID, maxProbeRetries)
result, output, err := pb.runProbeWithRetries(probeType, probeSpec, pod, status, container, containerID, maxProbeRetries)
if err != nil || result != probe.Success {
// Probe failed in one way or another.
ref, hasRef := pb.refManager.GetRef(containerID)
@ -116,12 +121,12 @@ func (pb *prober) probe(probeType probeType, pod *v1.Pod, status v1.PodStatus, c
// runProbeWithRetries tries to probe the container in a finite loop, it returns the last result
// if it never succeeds.
func (pb *prober) runProbeWithRetries(p *v1.Probe, pod *v1.Pod, status v1.PodStatus, container v1.Container, containerID kubecontainer.ContainerID, retries int) (probe.Result, string, error) {
func (pb *prober) runProbeWithRetries(probeType probeType, p *v1.Probe, pod *v1.Pod, status v1.PodStatus, container v1.Container, containerID kubecontainer.ContainerID, retries int) (probe.Result, string, error) {
var err error
var result probe.Result
var output string
for i := 0; i < retries; i++ {
result, output, err = pb.runProbe(p, pod, status, container, containerID)
result, output, err = pb.runProbe(probeType, p, pod, status, container, containerID)
if err == nil {
return result, output, nil
}
@ -139,7 +144,7 @@ func buildHeader(headerList []v1.HTTPHeader) http.Header {
return headers
}
func (pb *prober) runProbe(p *v1.Probe, pod *v1.Pod, status v1.PodStatus, container v1.Container, containerID kubecontainer.ContainerID) (probe.Result, string, error) {
func (pb *prober) runProbe(probeType probeType, p *v1.Probe, pod *v1.Pod, status v1.PodStatus, container v1.Container, containerID kubecontainer.ContainerID) (probe.Result, string, error) {
timeout := time.Duration(p.TimeoutSeconds) * time.Second
if p.Exec != nil {
glog.V(4).Infof("Exec-Probe Pod: %v, Container: %v, Command: %v", pod, container, p.Exec.Command)
@ -161,7 +166,11 @@ func (pb *prober) runProbe(p *v1.Probe, pod *v1.Pod, status v1.PodStatus, contai
url := formatURL(scheme, host, port, path)
headers := buildHeader(p.HTTPGet.HTTPHeaders)
glog.V(4).Infof("HTTP-Probe Headers: %v", headers)
return pb.http.Probe(url, headers, timeout)
if probeType == liveness {
return pb.livenessHttp.Probe(url, headers, timeout)
} else { // readiness
return pb.readinessHttp.Probe(url, headers, timeout)
}
}
if p.TCPSocket != nil {
port, err := extractPort(p.TCPSocket.Port, container)