Manuel Ganter
5e470c33a5
All checks were successful
ci / build (push) Successful in 30s
Add cgroup-based process grouping to the resource collector. Processes are grouped by their cgroup path, with container names resolved via configurable process-to-container mapping. New features: - Read cgroup info from /proc/[pid]/cgroup (supports v1 and v2) - Parse K8s resource notation (500m, 1Gi, etc.) for CPU/memory limits - Group metrics by container using CGROUP_PROCESS_MAP env var - Calculate usage percentages against limits from CGROUP_LIMITS env var - Output cgroup metrics with CPU cores used, memory RSS, and percentages Environment variables: - CGROUP_PROCESS_MAP: Map process names to container names for discovery - CGROUP_LIMITS: Define CPU/memory limits per container in K8s notation Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
148 lines
3.7 KiB
YAML
148 lines
3.7 KiB
YAML
# Test manifest to verify cgroup grouping behavior
|
|
# This pod runs multiple containers with different resource limits
|
|
# and a collector sidecar that groups metrics by cgroup/container
|
|
apiVersion: v1
|
|
kind: Pod
|
|
metadata:
|
|
name: test-cgroup-grouping
|
|
labels:
|
|
app: test-cgroup-grouping
|
|
spec:
|
|
# Share PID namespace so collector can see all processes
|
|
shareProcessNamespace: true
|
|
|
|
containers:
|
|
# Main workload container - simulates a runner
|
|
- name: runner
|
|
image: busybox:latest
|
|
command:
|
|
- /bin/sh
|
|
- -c
|
|
- |
|
|
echo "Runner container started"
|
|
# Simulate some CPU work
|
|
while true; do
|
|
dd if=/dev/zero of=/dev/null bs=1M count=100 2>/dev/null
|
|
sleep 1
|
|
done
|
|
resources:
|
|
requests:
|
|
cpu: "100m"
|
|
memory: "64Mi"
|
|
limits:
|
|
cpu: "500m"
|
|
memory: "256Mi"
|
|
|
|
# Sidecar container - simulates nginx or another service
|
|
- name: sidecar
|
|
image: busybox:latest
|
|
command:
|
|
- /bin/sh
|
|
- -c
|
|
- |
|
|
echo "Sidecar container started"
|
|
# Simulate some lighter work
|
|
while true; do
|
|
sleep 5
|
|
done
|
|
resources:
|
|
requests:
|
|
cpu: "50m"
|
|
memory: "32Mi"
|
|
limits:
|
|
cpu: "100m"
|
|
memory: "128Mi"
|
|
|
|
# Resource collector sidecar
|
|
- name: collector
|
|
image: ghcr.io/your-org/forgejo-runner-resource-collector:latest # Replace with your image
|
|
args:
|
|
- --interval=5s
|
|
- --top=3
|
|
env:
|
|
# Map process names to container names
|
|
# "sh" is the main process in busybox containers
|
|
# You may need to adjust based on actual process names
|
|
- name: CGROUP_PROCESS_MAP
|
|
value: |
|
|
{"sh":"runner","sleep":"sidecar","collector":"collector"}
|
|
# Define limits for each container (must match names in CGROUP_PROCESS_MAP)
|
|
- name: CGROUP_LIMITS
|
|
value: |
|
|
{"runner":{"cpu":"500m","memory":"256Mi"},"sidecar":{"cpu":"100m","memory":"128Mi"},"collector":{"cpu":"100m","memory":"64Mi"}}
|
|
resources:
|
|
requests:
|
|
cpu: "50m"
|
|
memory: "32Mi"
|
|
limits:
|
|
cpu: "100m"
|
|
memory: "64Mi"
|
|
# Mount proc read-only for process discovery
|
|
volumeMounts:
|
|
- name: proc
|
|
mountPath: /proc
|
|
readOnly: true
|
|
|
|
volumes:
|
|
- name: proc
|
|
hostPath:
|
|
path: /proc
|
|
type: Directory
|
|
|
|
restartPolicy: Never
|
|
---
|
|
# Alternative: Using a Deployment for longer-running tests
|
|
apiVersion: v1
|
|
kind: Pod
|
|
metadata:
|
|
name: test-cgroup-simple
|
|
labels:
|
|
app: test-cgroup-simple
|
|
spec:
|
|
shareProcessNamespace: true
|
|
|
|
containers:
|
|
# Stress container to generate CPU/memory load
|
|
- name: stress
|
|
image: progrium/stress:latest
|
|
args:
|
|
- --cpu
|
|
- "1"
|
|
- --vm
|
|
- "1"
|
|
- --vm-bytes
|
|
- "64M"
|
|
- --timeout
|
|
- "300s"
|
|
resources:
|
|
limits:
|
|
cpu: "500m"
|
|
memory: "128Mi"
|
|
|
|
# Collector
|
|
- name: collector
|
|
image: ghcr.io/your-org/forgejo-runner-resource-collector:latest # Replace with your image
|
|
args:
|
|
- --interval=2s
|
|
- --top=5
|
|
env:
|
|
- name: CGROUP_PROCESS_MAP
|
|
value: '{"stress":"stress","collector":"collector"}'
|
|
- name: CGROUP_LIMITS
|
|
value: '{"stress":{"cpu":"500m","memory":"128Mi"},"collector":{"cpu":"100m","memory":"64Mi"}}'
|
|
resources:
|
|
limits:
|
|
cpu: "100m"
|
|
memory: "64Mi"
|
|
volumeMounts:
|
|
- name: proc
|
|
mountPath: /proc
|
|
readOnly: true
|
|
|
|
volumes:
|
|
- name: proc
|
|
hostPath:
|
|
path: /proc
|
|
type: Directory
|
|
|
|
restartPolicy: Never
|