-
Notifications
You must be signed in to change notification settings - Fork 0
285 lines (256 loc) · 13.7 KB
/
dotnet-ec2-asg-test.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
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
## Copyright Amazon.com, Inc. or its affiliates. All Rights Reserved.
## SPDX-License-Identifier: Apache-2.0
# This is a reusable workflow for running the Dotnet E2E Canary test for Application Signals.
# It is meant to be called from another workflow.
# Read more about reusable workflows: https://docs.github.com/en/actions/using-workflows/reusing-workflows#overview
name: Dotnet EC2 ASG Use Case
on:
workflow_call:
inputs:
aws-region:
required: true
type: string
staging_distro_name:
required: false
default: 'aws-opentelemetry-distro'
type: string
caller-workflow-name:
required: true
type: string
outputs:
job-started:
value: ${{ jobs.dotnet-ec2-asg.outputs.job-started }}
validation-result:
value: ${{ jobs.dotnet-ec2-asg.outputs.validation-result }}
permissions:
id-token: write
contents: read
env:
E2E_TEST_AWS_REGION: ${{ inputs.aws-region }}
E2E_TEST_ACCOUNT_ID: ${{ secrets.APPLICATION_SIGNALS_E2E_TEST_ACCOUNT_ID }}
E2E_TEST_ROLE_NAME: ${{ secrets.APPLICATION_SIGNALS_E2E_TEST_ROLE_NAME }}
SAMPLE_APP_ZIP: s3://aws-appsignals-sample-app-prod-${{ inputs.aws-region }}/dotnet-sample-app.zip
METRIC_NAMESPACE: ApplicationSignals
LOG_GROUP_NAME: /aws/application-signals/data
ADOT_DISTRO_NAME: ${{ inputs.staging_distro_name }}
TEST_RESOURCES_FOLDER: ${GITHUB_WORKSPACE}
jobs:
dotnet-ec2-asg:
runs-on: ubuntu-latest
timeout-minutes: 30
outputs:
job-started: ${{ steps.job-started.outputs.job-started }}
validation-result: ${{ steps.validation-result.outputs.validation-result }}
steps:
- name: Check if the job started
id: job-started
run: echo "job-started=true" >> $GITHUB_OUTPUT
- uses: actions/checkout@v4
with:
repository: aws-observability/aws-application-signals-test-framework
ref: ${{ inputs.caller-workflow-name == 'main-build' && 'main' || github.ref }}
fetch-depth: 0
- name: Initiate Gradlew Daemon
id: initiate-gradlew
uses: ./.github/workflows/actions/execute_and_retry
continue-on-error: true
with:
command: "./gradlew :validator:build"
cleanup: "./gradlew clean"
max_retry: 3
sleep_time: 60
- name: Generate testing id
run: echo TESTING_ID="${{ github.job }}-${{ github.run_id }}-${{ github.run_number }}-${{ github.run_attempt }}" >> $GITHUB_ENV
- name: Configure AWS Credentials
uses: aws-actions/configure-aws-credentials@v4
with:
role-to-assume: arn:aws:iam::${{ env.E2E_TEST_ACCOUNT_ID }}:role/${{ env.E2E_TEST_ROLE_NAME }}
aws-region: us-east-1
- name: Retrieve account
uses: aws-actions/aws-secretsmanager-get-secrets@v1
with:
secret-ids:
ACCOUNT_ID, region-account/${{ env.E2E_TEST_AWS_REGION }}
- name: Configure AWS Credentials
uses: aws-actions/configure-aws-credentials@v4
with:
role-to-assume: arn:aws:iam::${{ env.ACCOUNT_ID }}:role/${{ env.E2E_TEST_ROLE_NAME }}
aws-region: ${{ env.E2E_TEST_AWS_REGION }}
- name: Set Get ADOT Distro command environment variable
run: |
if [ "${{ github.event.repository.name }}" = "aws-otel-dotnet-instrumentation" ]; then
# Get staging distro file from staging bucket
echo GET_ADOT_DISTRO_COMMAND="aws s3 cp s3://adot-autoinstrumentation-dotnet-staging/${{ env.ADOT_DISTRO_NAME }} ./${{ env.ADOT_DISTRO_NAME }} && unzip -d dotnet-distro ${{ env.ADOT_DISTRO_NAME }}" >> $GITHUB_ENV
else
# After Release will switch to latest tag instead of hard code version for canary purpose
echo GET_ADOT_DISTRO_COMMAND="wget -O aws-distro-opentelemetry-dotnet-instrumentation-linux-glibc-x64.zip https://github.com/aws-observability/aws-otel-dotnet-instrumentation/releases/download/v1.2.0/aws-distro-opentelemetry-dotnet-instrumentation-linux-glibc-x64.zip && unzip -d dotnet-distro aws-distro-opentelemetry-dotnet-instrumentation-linux-glibc-x64.zip" >> $GITHUB_ENV
fi
- name: Set Get CW Agent command environment variable
run: |
if [ "${{ github.event.repository.name }}" = "amazon-cloudwatch-agent" ]; then
# Get cloudwatch agent staging file if triggered by cw-a repo
echo GET_CW_AGENT_RPM_COMMAND= "aws s3 cp s3://${{ secrets.S3_INTEGRATION_BUCKET }}/integration-test/binary/${{ github.sha }}/amazon_linux/amd64/latest/amazon-cloudwatch-agent.rpm ./cw-agent.rpm" >> $GITHUB_ENV
else
echo GET_CW_AGENT_RPM_COMMAND="wget -O cw-agent.rpm https://amazoncloudwatch-agent-${{ env.E2E_TEST_AWS_REGION }}.s3.${{ env.E2E_TEST_AWS_REGION }}.amazonaws.com/amazon_linux/amd64/latest/amazon-cloudwatch-agent.rpm" >> $GITHUB_ENV
fi
- name: Set up terraform
uses: ./.github/workflows/actions/execute_and_retry
with:
command: "wget -O- https://apt.releases.hashicorp.com/gpg | sudo gpg --dearmor -o /usr/share/keyrings/hashicorp-archive-keyring.gpg"
post-command: 'echo "deb [signed-by=/usr/share/keyrings/hashicorp-archive-keyring.gpg] https://apt.releases.hashicorp.com $(lsb_release -cs) main" | sudo tee /etc/apt/sources.list.d/hashicorp.list
&& sudo apt update && sudo apt install terraform'
sleep_time: 60
- name: Initiate Terraform
uses: ./.github/workflows/actions/execute_and_retry
with:
command: "cd ${{ env.TEST_RESOURCES_FOLDER }}/terraform/dotnet/ec2/asg && terraform init && terraform validate"
cleanup: "rm -rf .terraform && rm -rf .terraform.lock.hcl"
max_retry: 6
sleep_time: 60
- name: Deploy sample app via terraform and wait for endpoint to come online
working-directory: terraform/dotnet/ec2/asg
run: |
# Attempt to deploy the sample app on an EC2 instance and wait for its endpoint to come online.
# There may be occasional failures due to transitivity issues, so try up to 2 times.
# deployment_failed of 0 indicates that both the terraform deployment and the endpoint are running, while 1 indicates
# that it failed at some point
retry_counter=0
max_retry=2
while [ $retry_counter -lt $max_retry ]; do
echo "Attempt $retry_counter"
deployment_failed=0
terraform apply -auto-approve \
-var="aws_region=${{ env.E2E_TEST_AWS_REGION }}" \
-var="test_id=${{ env.TESTING_ID }}" \
-var="sample_app_zip=${{ env.SAMPLE_APP_ZIP }}" \
-var="get_cw_agent_rpm_command=${{ env.GET_CW_AGENT_RPM_COMMAND }}" \
-var="get_adot_distro_command=${{ env.GET_ADOT_DISTRO_COMMAND }}" \
|| deployment_failed=$?
if [ $deployment_failed -eq 1 ]; then
echo "Terraform deployment was unsuccessful. Will attempt to retry deployment."
fi
# If the success is 1 then either the terraform deployment or the endpoint connection failed, so first destroy the
# resources created from terraform and try again.
if [ $deployment_failed -eq 1 ]; then
echo "Destroying terraform"
terraform destroy -auto-approve \
-var="test_id=${{ env.TESTING_ID }}"
retry_counter=$(($retry_counter+1))
else
# If deployment succeeded, then exit the loop
break
fi
if [ $retry_counter -eq $max_retry ]; then
echo "Max retry reached, failed to deploy terraform and connect to the endpoint. Exiting code"
exit 1
fi
done
- name: Wait for ASG instance to be ready
run: |
# Wait for up to 15 minutes
retry_counter=0
max_retry=90
while [ $retry_counter -lt $max_retry ]; do
instance_id=$(aws autoscaling describe-auto-scaling-groups --auto-scaling-group-names dotnet-ec2-single-asg-${{ env.TESTING_ID }} --region ${{ env.E2E_TEST_AWS_REGION }} --query "AutoScalingGroups[].Instances[0].InstanceId" --output text)
status_ok=$(aws ec2 describe-instance-status --instance-ids $instance_id | jq '(.InstanceStatuses[] | select(.InstanceStatus.Status == "ok" and .SystemStatus.Status == "ok")) != {}')
if [ "$status_ok" == "true" ]; then
echo "The instance $instance_id is ready."
echo "MAIN_SERVICE_INSTANCE_ID=$instance_id" >> $GITHUB_ENV
break
fi
if [ $retry_counter -eq $max_retry ]; then
echo "Instance Id $instance_id did not become ready with status $status_ok"
exit 1
fi
sleep 10
done
- name: Get the sample app and EC2 instance information
working-directory: terraform/dotnet/ec2/asg
run: |
main_service_private_dns_name=$(aws ec2 describe-instances --instance-ids ${{ env.MAIN_SERVICE_INSTANCE_ID }} --region ${{ env.E2E_TEST_AWS_REGION }} --query "Reservations[].Instances[].PrivateDnsName" --output text)
echo "MAIN_SERVICE_ENDPOINT=localhost:8080" >> $GITHUB_ENV
echo "PRIVATE_DNS_NAME=$main_service_private_dns_name" >> $GITHUB_ENV
echo "EC2_INSTANCE_AMI=$(terraform output ec2_instance_ami)" >> $GITHUB_ENV
echo "REMOTE_SERVICE_IP=$(terraform output sample_app_remote_service_private_ip)" >> $GITHUB_ENV
- name: Initiate Gradlew Daemon
if: steps.initiate-gradlew == 'failure'
uses: ./.github/workflows/actions/execute_and_retry
continue-on-error: true
with:
command: "./gradlew"
cleanup: "./gradlew clean"
max_retry: 3
sleep_time: 60
# Validation for pulse telemetry data
- name: Validate generated EMF logs
id: log-validation
run: ./gradlew validator:run --args='-c dotnet/ec2/asg/log-validation.yml
--testing-id ${{ env.TESTING_ID }}
--endpoint http://${{ env.MAIN_SERVICE_ENDPOINT }}
--remote-service-deployment-name ${{ env.REMOTE_SERVICE_IP }}:8081
--region ${{ env.E2E_TEST_AWS_REGION }}
--metric-namespace ${{ env.METRIC_NAMESPACE }}
--log-group ${{ env.LOG_GROUP_NAME }}
--service-name dotnet-sample-application-${{ env.TESTING_ID }}
--remote-service-name dotnet-sample-remote-application-${{ env.TESTING_ID }}
--query-string ip=${{ env.REMOTE_SERVICE_IP }}&testingId=${{ env.TESTING_ID }}
--instance-ami ${{ env.EC2_INSTANCE_AMI }}
--platform-info dotnet-ec2-single-asg-${{ env.TESTING_ID }}
--instance-id ${{ env.MAIN_SERVICE_INSTANCE_ID }}
--private-dns-name ${{ env.PRIVATE_DNS_NAME }}
--rollup'
- name: Validate generated metrics
id: metric-validation
if: (success() || steps.log-validation.outcome == 'failure') && !cancelled()
run: ./gradlew validator:run --args='-c dotnet/ec2/asg/metric-validation.yml
--testing-id ${{ env.TESTING_ID }}
--endpoint http://${{ env.MAIN_SERVICE_ENDPOINT }}
--remote-service-deployment-name ${{ env.REMOTE_SERVICE_IP }}:8081
--region ${{ env.E2E_TEST_AWS_REGION }}
--metric-namespace ${{ env.METRIC_NAMESPACE }}
--log-group ${{ env.LOG_GROUP_NAME }}
--service-name dotnet-sample-application-${{ env.TESTING_ID }}
--remote-service-name dotnet-sample-remote-application-${{ env.TESTING_ID }}
--query-string ip=${{ env.REMOTE_SERVICE_IP }}&testingId=${{ env.TESTING_ID }}
--instance-ami ${{ env.EC2_INSTANCE_AMI }}
--platform-info dotnet-ec2-single-asg-${{ env.TESTING_ID }}
--instance-id ${{ env.MAIN_SERVICE_INSTANCE_ID }}
--private-dns-name ${{ env.PRIVATE_DNS_NAME }}
--rollup'
#
- name: Validate generated traces
id: trace-validation
if: (success() || steps.log-validation.outcome == 'failure' || steps.metric-validation.outcome == 'failure') && !cancelled()
run: ./gradlew validator:run --args='-c dotnet/ec2/asg/trace-validation.yml
--testing-id ${{ env.TESTING_ID }}
--endpoint http://${{ env.MAIN_SERVICE_ENDPOINT }}
--remote-service-deployment-name ${{ env.REMOTE_SERVICE_IP }}:8081
--region ${{ env.E2E_TEST_AWS_REGION }}
--account-id ${{ env.ACCOUNT_ID }}
--metric-namespace ${{ env.METRIC_NAMESPACE }}
--log-group ${{ env.LOG_GROUP_NAME }}
--service-name dotnet-sample-application-${{ env.TESTING_ID }}
--remote-service-name dotnet-sample-remote-application-${{ env.TESTING_ID }}
--query-string ip=${{ env.REMOTE_SERVICE_IP }}&testingId=${{ env.TESTING_ID }}
--instance-ami ${{ env.EC2_INSTANCE_AMI }}
--platform-info dotnet-ec2-single-asg-${{ env.TESTING_ID }}
--instance-id ${{ env.MAIN_SERVICE_INSTANCE_ID }}
--private-dns-name ${{ env.PRIVATE_DNS_NAME }}
--rollup'
- name: Save test results
if: always()
id: validation-result
run: |
if [ "${{ steps.log-validation.outcome }}" = "success" ] && [ "${{ steps.metric-validation.outcome }}" = "success" ] && [ "${{ steps.trace-validation.outcome }}" = "success" ]; then
echo "validation-result=success" >> $GITHUB_OUTPUT
else
echo "validation-result=failure" >> $GITHUB_OUTPUT
fi
# Clean up Procedures
- name: Terraform destroy
if: always()
continue-on-error: true
working-directory: terraform/dotnet/ec2/asg
run: |
terraform destroy -auto-approve \
-var="test_id=${{ env.TESTING_ID }}"