Skip to content

Optimize monitor #683

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
archlitchi merged 1 commit into from
Dec 5, 2024
Merged

Optimize monitor #683

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
6 changes: 4 additions & 2 deletions cmd/vGPUmonitor/metrics.go
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -18,8 +18,10 @@ package main

import (
"fmt"
"github.com/Project-HAMi/HAMi/pkg/util"
"log"
"net/http"
"os"
"strings"
"time"

Expand Down Expand Up @@ -229,8 +231,8 @@ func (cc ClusterManagerCollector) Collect(ch chan<- prometheus.Metric) {

}
}

pods, err := cc.ClusterManager.PodLister.List(labels.Everything())
nodeName := os.Getenv(util.NodeNameEnvName)
pods, err := cc.ClusterManager.PodLister.List(labels.SelectorFromSet(labels.Set{util.AssignedNodeAnnotations: nodeName}))
if err != nil {
klog.Error("failed to list pods with err=", err.Error())
}
Expand Down
9 changes: 8 additions & 1 deletion pkg/monitor/nvidia/cudevshr.go
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -20,6 +20,7 @@ import (
"context"
"errors"
"fmt"
"github.com/Project-HAMi/HAMi/pkg/util"
"os"
"path/filepath"
"strings"
Expand Down Expand Up @@ -122,7 +123,13 @@ func (l *ContainerLister) Clientset() *kubernetes.Clientset {
}

func (l *ContainerLister) Update() error {
pods, err := l.clientset.CoreV1().Pods("").List(context.Background(), metav1.ListOptions{})
nodename := os.Getenv(util.NodeNameEnvName)
if nodename == "" {
return fmt.Errorf("env %s not set", util.NodeNameEnvName)
}
pods, err := l.clientset.CoreV1().Pods("").List(context.Background(), metav1.ListOptions{
FieldSelector: fmt.Sprintf("spec.nodeName=%s", nodename),
})
if err != nil {
return err
}
Expand Down
6 changes: 6 additions & 0 deletions pkg/util/util.go
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -363,6 +363,7 @@ func PatchNodeAnnotations(node *corev1.Node, annotations map[string]string) erro
func PatchPodAnnotations(pod *corev1.Pod, annotations map[string]string) error {
type patchMetadata struct {
Annotations map[string]string `json:"annotations,omitempty"`
Labels map[string]string `json:"labels,omitempty"`
}
type patchPod struct {
Metadata patchMetadata `json:"metadata"`
Expand All @@ -371,6 +372,11 @@ func PatchPodAnnotations(pod *corev1.Pod, annotations map[string]string) error {

p := patchPod{}
p.Metadata.Annotations = annotations
label := make(map[string]string)
if v, ok := annotations[AssignedNodeAnnotations]; ok && v != "" {
label[AssignedNodeAnnotations] = v
p.Metadata.Labels = label
}

bytes, err := json.Marshal(p)
if err != nil {
Expand Down