Add prometheus export metrics functional testing

Without this, we can't know if the exposed prometheus metrics
behave properly.

This is a problem, as the only way we can evaluate the success
(right now), is a compilation success or failure from kured.
While this is a good start, it doesn't translate to what we
claim to offer: A boolean showing if a reboot is required.

This fixes it by creating a new github action workflow testing
if the float64 gauge is properly showing 0 for no reboot, 1 for reboot.
This is done by exposing the metrics endpoint through a node port.
A helm chart change was required to have the ability to expose
the service on a node port. We connect to the kind node through
docker in the `tests/test-metrics.sh`, where we curl the nodeport,
extract the only relevant metric, and compare it to the expected result.
This commit is contained in:
Jean-Philippe Evrard
2021-04-13 13:33:15 +02:00
parent d2c9ef8cba
commit 240a669727
6 changed files with 119 additions and 2 deletions

View File

@@ -211,3 +211,84 @@ jobs:
retry_wait_seconds: 60
# DESIRED CURRENT READY UP-TO-DATE AVAILABLE should all be = to cluster_size
command: "kubectl get ds -n kube-system kured | grep -E 'kured.*5.*5.*5.*5.*5'"
test-prom:
name: "Test prometheus with latest code from HEAD"
runs-on: ubuntu-latest
# only build with oldest and newest supported, it should be good enough.
strategy:
fail-fast: false
matrix:
kubernetes:
- "1.20"
steps:
- uses: actions/checkout@v2
- name: Find go version
run: |
GO_VERSION=$(awk '/^go/ {print $2};' go.mod)
echo "::set-output name=version::${GO_VERSION}"
id: awk_gomod
- name: Ensure go version
uses: actions/setup-go@v2
with:
go-version: "${{ steps.awk_gomod.outputs.version }}"
- name: Build artifacts
run: |
make DH_ORG="${{ github.repository_owner }}" VERSION="${{ github.sha }}" image
make DH_ORG="${{ github.repository_owner }}" VERSION="${{ github.sha }}" helm-chart
- name: "Workaround 'Failed to attach 1 to compat systemd cgroup /actions_job/...' on gh actions"
run: |
sudo bash << EOF
cp /etc/docker/daemon.json /etc/docker/daemon.json.old
echo '{}' > /etc/docker/daemon.json
systemctl restart docker || journalctl --no-pager -n 500
systemctl status docker
EOF
# Default name for helm/kind-action kind clusters is "chart-testing"
- name: Create 1 node kind cluster
uses: helm/kind-action@master
- name: Preload previously built images onto kind cluster
run: kind load docker-image docker.io/${{ github.repository_owner }}/kured:${{ github.sha }} --name chart-testing
- name: Deploy kured on default namespace with its helm chart
run: |
# Documented in official helm doc to live on the edge
curl https://raw.githubusercontent.com/helm/helm/main/scripts/get-helm-3 | bash
# Refresh bins
hash -r
helm install kured ./charts/kured/ --wait --values ./charts/kured/ci/prometheus-values.yaml
kubectl config set-context kind-chart-testing
kubectl get ds --all-namespaces
kubectl describe ds kured
- name: Ensure kured is ready
uses: nick-invision/retry@v2.4.0
with:
timeout_minutes: 10
max_attempts: 10
retry_wait_seconds: 60
# DESIRED CURRENT READY UP-TO-DATE AVAILABLE
command: "kubectl get ds kured | grep -E 'kured.*1.*1.*1.*1.*1' "
- name: Get metrics (healthy)
uses: nick-invision/retry@v2.4.0
with:
timeout_minutes: 2
max_attempts: 12
retry_wait_seconds: 5
command: "./tests/kind/test-metrics.sh 0"
- name: Create reboot sentinel files
run: |
./tests/kind/create-reboot-sentinels.sh
- name: Get metrics (need reboot)
uses: nick-invision/retry@v2.4.0
with:
timeout_minutes: 15
max_attempts: 10
retry_wait_seconds: 60
command: "./tests/kind/test-metrics.sh 1"