-
Notifications
You must be signed in to change notification settings - Fork 27
233 lines (203 loc) · 8.58 KB
/
gcp-experiment-pipeline.yml
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
---
name: GCP-Experiment-Pipeline
on:
workflow_dispatch:
inputs:
experimentImage:
default: "litmuschaos/go-runner:ci"
operatorImage:
default: "litmuschaos/chaos-operator:ci"
runnerImage:
default: "litmuschaos/chaos-runner:ci"
chaosNamespace:
default: "default"
experimentImagePullPolicy:
default: "Always"
jobs:
GCP_VM_Instance_Stop:
runs-on: ubuntu-latest
env:
KUBECONFIG: /etc/rancher/k3s/k3s.yaml
steps:
#Install and configure a k3s cluster
- name: Installing Prerequisites (K3S Cluster)
run: |
curl -sfL https://get.k3s.io | INSTALL_K3S_VERSION=v1.21.11+k3s1 sh -s - --docker --write-kubeconfig-mode 664
kubectl wait node --all --for condition=ready --timeout=90s
mkdir -p $HOME/.kube && cat /etc/rancher/k3s/k3s.yaml > $HOME/.kube/config
kubectl get nodes
- uses: actions/checkout@v2
- uses: actions/setup-go@v2
with:
go-version: '1.16'
- name: Create Kubernetes secret for gcp experiment
if: always()
run: |
cat <<EOF | kubectl apply -f -
apiVersion: v1
kind: Secret
metadata:
name: cloud-secret
type: Opaque
stringData:
type: "service_account"
project_id: "${{ secrets.GCP_PROJECT_ID }}"
private_key_id: "${{ secrets.PRIVATE_KEY_ID }}"
private_key: ${{ secrets.PRIVATE_KEY }}
client_email: "${{ secrets.CLIENT_EMAIL }}"
client_id: "${{ secrets.CLIENT_ID }}"
auth_uri: "${{ secrets.AUTH_URI }}"
token_uri: "${{ secrets.TOKEN_URI }}"
auth_provider_x509_cert_url: "${{ secrets.AUTH_PROVIDER_CERT_URL }}"
client_x509_cert_url: "${{ secrets.CLIENT_CERT_URL }}"
EOF
- name: Authenticate Google Cloud SDK
if: always()
uses: 'google-github-actions/auth@v0'
with:
credentials_json: '${{ secrets.GCP_SA_KEY }}'
- name: Set up Google Cloud SDK
if: always()
uses: google-github-actions/setup-gcloud@v0
- name: Create target GCP VM Instances
if: always()
run: |
gcloud compute instances create litmus-e2e-first-vm-${{ github.run_number }} litmus-e2e-second-vm-${{ github.run_number }} \
--machine-type=f1-micro \
--zone=us-central1-a
- name: Litmus Infra Setup
if: always()
run: make build-litmus
env:
OPERATOR_IMAGE: "${{ github.event.inputs.operatorImage }}"
RUNNER_IMAGE: "${{ github.event.inputs.runnerImage }}"
- name: Run GCP VM Instance Stop experiment in serial & parallel mode
if: always()
env:
GCP_PROJECT_ID: ${{ secrets.GCP_PROJECT_ID }}
VM_INSTANCE_NAMES: "litmus-e2e-first-vm-${{ github.run_number }},litmus-e2e-second-vm-${{ github.run_number }}"
INSTANCE_ZONES: "us-central1-a,us-central1-a"
EXPERIMENT_IMAGE: "${{ github.event.inputs.experimentImage }}"
EXPERIMENT_IMAGE_PULL_POLICY: "${{ github.event.inputs.experimentImagePullPolicy }}"
CHAOS_NAMESPACE: "${{ github.event.inputs.chaosNamespace }}"
run: make gcp-vm-instance-stop
- name: Delete target GCP VM Instances
if: always()
run: |
gcloud compute instances delete litmus-e2e-first-vm-${{ github.run_number }} litmus-e2e-second-vm-${{ github.run_number }} \
--zone=us-central1-a \
--quiet
- name: "[Debug]: check chaos resources"
if: ${{ failure() }}
continue-on-error: true
run: |
bash <(curl -s https://raw.githubusercontent.com/litmuschaos/litmus-e2e/master/build/debug.sh)
- name: "[Debug]: check operator logs"
if: ${{ failure() }}
continue-on-error: true
run: |
operator_name=$(kubectl get pods -n litmus -l app.kubernetes.io/component=operator --no-headers | awk '{print$1}')
kubectl logs $operator_name -n litmus > logs.txt
cat logs.txt
- name: Litmus Cleanup
if: ${{ always() }}
run: make litmus-cleanup
- name: Deleting K3S cluster
if: always()
run: /usr/local/bin/k3s-uninstall.sh
GCP_VM_Disk_Loss:
runs-on: ubuntu-latest
env:
KUBECONFIG: /etc/rancher/k3s/k3s.yaml
needs: GCP_VM_Instance_Stop
steps:
#Install and configure a k3s cluster
- name: Installing Prerequisites (K3S Cluster)
run: |
curl -sfL https://get.k3s.io | INSTALL_K3S_VERSION=v1.21.11+k3s1 sh -s - --docker --write-kubeconfig-mode 664
kubectl wait node --all --for condition=ready --timeout=90s
mkdir -p $HOME/.kube && cat /etc/rancher/k3s/k3s.yaml > $HOME/.kube/config
kubectl get nodes
- uses: actions/checkout@v2
- uses: actions/setup-go@v2
with:
go-version: '1.16'
- name: Create Kubernetes secret for gcp experiment
if: always()
run: |
cat <<EOF | kubectl apply -f -
apiVersion: v1
kind: Secret
metadata:
name: cloud-secret
type: Opaque
stringData:
type: "service_account"
project_id: "${{ secrets.GCP_PROJECT_ID }}"
private_key_id: "${{ secrets.PRIVATE_KEY_ID }}"
private_key: ${{ secrets.PRIVATE_KEY }}
client_email: "${{ secrets.CLIENT_EMAIL }}"
client_id: "${{ secrets.CLIENT_ID }}"
auth_uri: "${{ secrets.AUTH_URI }}"
token_uri: "${{ secrets.TOKEN_URI }}"
auth_provider_x509_cert_url: "${{ secrets.AUTH_PROVIDER_CERT_URL }}"
client_x509_cert_url: "${{ secrets.CLIENT_CERT_URL }}"
EOF
- name: Authenticate Google Cloud SDK
if: always()
uses: 'google-github-actions/auth@v0'
with:
credentials_json: '${{ secrets.GCP_SA_KEY }}'
- name: Set up Google Cloud SDK
if: always()
uses: google-github-actions/setup-gcloud@v0
- name: Create a GCP VM Instance with target Disk Volumes
if: always()
run: |
gcloud compute instances create litmus-e2e-vm-${{ github.run_number }} \
--machine-type=f1-micro \
--zone=us-central1-a \
--create-disk name=litmus-e2e-first-disk-${{ github.run_number }},size=1GB,device-name=litmus-e2e-first-disk-${{ github.run_number }} \
--create-disk name=litmus-e2e-second-disk-${{ github.run_number }},size=1GB,device-name=litmus-e2e-second-disk-${{ github.run_number }}
- name: Litmus Infra Setup
if: always()
run: make build-litmus
env:
OPERATOR_IMAGE: "${{ github.event.inputs.operatorImage }}"
RUNNER_IMAGE: "${{ github.event.inputs.runnerImage }}"
- name: Run GCP VM Disk Loss experiment in serial & parallel mode
if: always()
env:
GCP_PROJECT_ID: ${{ secrets.GCP_PROJECT_ID }}
DISK_VOLUME_NAMES: "litmus-e2e-first-disk-${{ github.run_number }},litmus-e2e-second-disk-${{ github.run_number }}"
DISK_ZONES: "us-central1-a,us-central1-a"
DEVICE_NAMES: "litmus-e2e-first-disk-${{ github.run_number }},litmus-e2e-second-disk-${{ github.run_number }}"
EXPERIMENT_IMAGE: "${{ github.event.inputs.experimentImage }}"
EXPERIMENT_IMAGE_PULL_POLICY: "${{ github.event.inputs.experimentImagePullPolicy }}"
CHAOS_NAMESPACE: "${{ github.event.inputs.chaosNamespace }}"
run: make gcp-vm-disk-loss
- name: Delete the VM Instance and target Disk Volumes
if: always()
run: |
gcloud compute instances delete litmus-e2e-vm-${{ github.run_number }} \
--zone=us-central1-a \
--delete-disks=all \
--quiet
- name: "[Debug]: check chaos resources"
if: ${{ failure() }}
continue-on-error: true
run: |
bash <(curl -s https://raw.githubusercontent.com/litmuschaos/litmus-e2e/master/build/debug.sh)
- name: "[Debug]: check operator logs"
if: ${{ failure() }}
continue-on-error: true
run: |
operator_name=$(kubectl get pods -n litmus -l app.kubernetes.io/component=operator --no-headers | awk '{print$1}')
kubectl logs $operator_name -n litmus > logs.txt
cat logs.txt
- name: Litmus Cleanup
if: ${{ always() }}
run: make litmus-cleanup
- name: Deleting K3S cluster
if: always()
run: /usr/local/bin/k3s-uninstall.sh