github/kubernetes
1
0
Fork 0
mirror of https://github.com/k3s-io/kubernetes.git synced 2025-07-30 06:54:01 +00:00
Code Issues Projects Releases Wiki Activity

Merge pull request #54410 from intelsdi-x/cpu-reconcile-state

Browse Source 
Automatic merge from submit-queue (batch tested with PRs 54410, 56184, 56199, 56191, 56231). 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>.

Cpu manager reconcile loop - restore state

**What this PR does / why we need it**:
Cpu manager reconcile loop can add orphaned containers to `State` calling `policy.AddContainer()`
Previous PR: #54409 
e2e tests PR: #53378

Blocked by #56191
This commit is contained in:
Kubernetes Submit Queue 2017-12-14 05:33:08 -08:00 committed by GitHub
commit e9a9da8aa3
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
3 changed files with 30 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

23
pkg/kubelet/cm/cpumanager/cpu_manager.go
View File

@ -160,8 +160,8 @@ func NewManager(
}
func (m *manager) Start(activePods ActivePodsFunc, podStatusProvider status.PodStatusProvider, containerRuntime runtimeService) {
glog.Infof("[cpumanger] starting with %s policy", m.policy.Name())
glog.Infof("[cpumanger] reconciling every %v", m.reconcilePeriod)
glog.Infof("[cpumanager] starting with %s policy", m.policy.Name())
glog.Infof("[cpumanager] reconciling every %v", m.reconcilePeriod)
m.activePods = activePods
m.podStatusProvider = podStatusProvider
@ -242,6 +242,25 @@ func (m *manager) reconcileState() (success []reconciledContainer, failure []rec
continue
}
// Check whether container is present in state, there may be 3 reasons why it's not present:
// - policy does not want to track the container
// - kubelet has just been restarted - and there is no previous state file
// - container has been removed from state by RemoveContainer call (DeletionTimestamp is set)
if _, ok := m.state.GetCPUSet(containerID); !ok {
if status.Phase == v1.PodRunning && pod.DeletionTimestamp == nil {
glog.V(4).Infof("[cpumanager] reconcileState: container is not present in state - trying to add (pod: %s, container: %s, container id: %s)", pod.Name, container.Name, containerID)
err := m.AddContainer(pod, &container, containerID)
if err != nil {
glog.Errorf("[cpumanager] reconcileState: failed to add container (pod: %s, container: %s, container id: %s, error: %v)", pod.Name, container.Name, containerID, err)
failure = append(failure, reconciledContainer{pod.Name, container.Name, containerID})
}
} else {
// if DeletionTimestamp is set, pod has already been removed from state
// skip the pod/container since it's not running and will be deleted soon
continue
}
}
cset := m.state.GetCPUSetOrDefault(containerID)
if cset.IsEmpty() {
// NOTE: This should not happen outside of tests.

2
pkg/kubelet/cm/cpumanager/policy.go
View File

@ -25,6 +25,8 @@ import (
type Policy interface {
Name() string
Start(s state.State)
// AddContainer call is idempotent
AddContainer(s state.State, pod *v1.Pod, container *v1.Container, containerID string) error
// RemoveContainer call is idempotent
RemoveContainer(s state.State, containerID string) error
}

8
pkg/kubelet/cm/cpumanager/policy_static.go
View File

@ -156,9 +156,15 @@ func (p *staticPolicy) assignableCPUs(s state.State) cpuset.CPUSet {
}
func (p *staticPolicy) AddContainer(s state.State, pod *v1.Pod, container *v1.Container, containerID string) error {
glog.Infof("[cpumanager] static policy: AddContainer (pod: %s, container: %s, container id: %s)", pod.Name, container.Name, containerID)
if numCPUs := guaranteedCPUs(pod, container); numCPUs != 0 {
glog.Infof("[cpumanager] static policy: AddContainer (pod: %s, container: %s, container id: %s)", pod.Name, container.Name, containerID)
// container belongs in an exclusively allocated pool
if _, ok := s.GetCPUSet(containerID); ok {
glog.Infof("[cpumanager] static policy: container already present in state, skipping (container: %s, container id: %s)", container.Name, containerID)
return nil
}
cpuset, err := p.allocateCPUs(s, numCPUs)
if err != nil {
glog.Errorf("[cpumanager] unable to allocate %d CPUs (container id: %s, error: %v)", numCPUs, containerID, err)