Skip to content

Fix Lambda canary trace validation failure #345

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
merged 3 commits into from
Jan 3, 2025
Merged

Fix Lambda canary trace validation failure #345

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
688b8fa
Revert "extend and print trace search time range (#342)"
wangzlei Jan 3, 2025
484474f
move trace validation --end-time to be close to the trace end time
wangzlei Jan 3, 2025
59c6f70
fix comment
wangzlei Jan 3, 2025
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
24 changes: 12 additions & 12 deletions .github/workflows/node-lambda-test.yml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -148,12 +148,11 @@ jobs:
shell: bash
run: sleep 30s; curl -sS ${{ env.API_GATEWAY_URL }}

# Validation for pulse telemetry data
- name: Validate generated EMF logs
id: log-validation
- name: Validate generated traces
id: trace-validation
# will be removed after data quality bug fixed
continue-on-error: true
run: ./gradlew validator:run --args='-c node/lambda/log-validation.yml
run: ./gradlew validator:run --args='-c node/lambda/trace-validation.yml
--testing-id ${{ env.TESTING_ID }}
--endpoint http://${{ env.API_GATEWAY_URL }}
--region ${{ inputs.aws-region }}
Expand All @@ -163,12 +162,13 @@ jobs:
--service-name ${{ env.TERRAFORM_LAMBDA_FUNCTION_NAME }}
--rollup'

- name: Validate generated metrics
id: metric-validation
if: (success() || steps.log-validation.outcome == 'failure') && !cancelled()
# Validation for pulse telemetry data
- name: Validate generated EMF logs
id: log-validation
if: (success() || steps.trace-validation.outcome == 'failure') && !cancelled()
# will be removed after data quality bug fixed
continue-on-error: true
run: ./gradlew validator:run --args='-c node/lambda/metric-validation.yml
run: ./gradlew validator:run --args='-c node/lambda/log-validation.yml
--testing-id ${{ env.TESTING_ID }}
--endpoint http://${{ env.API_GATEWAY_URL }}
--region ${{ inputs.aws-region }}
Expand All @@ -178,12 +178,12 @@ jobs:
--service-name ${{ env.TERRAFORM_LAMBDA_FUNCTION_NAME }}
--rollup'

- name: Validate generated traces
id: trace-validation
if: (success() || steps.log-validation.outcome == 'failure' || steps.metric-validation.outcome == 'failure') && !cancelled()
- name: Validate generated metrics
id: metric-validation
if: (success() || steps.trace-validation.outcome == 'failure' || steps.log-validation.outcome == 'failure') && !cancelled()
# will be removed after data quality bug fixed
continue-on-error: true
run: ./gradlew validator:run --args='-c node/lambda/trace-validation.yml
run: ./gradlew validator:run --args='-c node/lambda/metric-validation.yml
--testing-id ${{ env.TESTING_ID }}
--endpoint http://${{ env.API_GATEWAY_URL }}
--region ${{ inputs.aws-region }}
Expand Down
26 changes: 13 additions & 13 deletions .github/workflows/python-lambda-test.yml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -174,12 +174,11 @@ jobs:
max_retry: 3
sleep_time: 60

# Validation for pulse telemetry data
- name: Validate generated EMF logs
id: log-validation
- name: Validate generated traces
id: trace-validation
# will be removed after data quality bug fixed
continue-on-error: true
run: ./gradlew validator:run --args='-c python/lambda/log-validation.yml
run: ./gradlew validator:run --args='-c python/lambda/trace-validation.yml
--testing-id ${{ env.TESTING_ID }}
--endpoint http://${{ env.API_GATEWAY_URL }}
--region ${{ inputs.aws-region }}
Expand All @@ -189,12 +188,13 @@ jobs:
--service-name ${{ env.TERRAFORM_LAMBDA_FUNCTION_NAME }}
--rollup'

- name: Validate generated metrics
id: metric-validation
# Validation for pulse telemetry data
- name: Validate generated EMF logs
id: log-validation
if: (success() || steps.trace-validation.outcome == 'failure') && !cancelled()
# will be removed after data quality bug fixed
continue-on-error: true
if: (success() || steps.log-validation.outcome == 'failure') && !cancelled()
run: ./gradlew validator:run --args='-c python/lambda/metric-validation.yml
run: ./gradlew validator:run --args='-c python/lambda/log-validation.yml
--testing-id ${{ env.TESTING_ID }}
--endpoint http://${{ env.API_GATEWAY_URL }}
--region ${{ inputs.aws-region }}
Expand All @@ -204,12 +204,12 @@ jobs:
--service-name ${{ env.TERRAFORM_LAMBDA_FUNCTION_NAME }}
--rollup'

- name: Validate generated traces
id: trace-validation
- name: Validate generated metrics
id: metric-validation
# will be removed after data quality bug fixed
continue-on-error: true
if: (success() || steps.log-validation.outcome == 'failure' || steps.metric-validation.outcome == 'failure') && !cancelled()
run: ./gradlew validator:run --args='-c python/lambda/trace-validation.yml
if: (success() || steps.trace-validation.outcome == 'failure' || steps.log-validation.outcome == 'failure') && !cancelled()
run: ./gradlew validator:run --args='-c python/lambda/metric-validation.yml
--testing-id ${{ env.TESTING_ID }}
--endpoint http://${{ env.API_GATEWAY_URL }}
--region ${{ inputs.aws-region }}
Expand Down Expand Up @@ -246,4 +246,4 @@ jobs:
-var="function_name=${{env.TERRAFORM_LAMBDA_FUNCTION_NAME}}" \
-var="layer_artifacts_directory=${{ env.ARTIFACTS_DIR }}" \
-var="region=${{ env.E2E_TEST_AWS_REGION }}" \
-var="is_canary=${{ env.IS_CANARY }}"
-var="is_canary=${{ env.IS_CANARY }}"
2 changes: 1 addition & 1 deletion validator/src/main/java/com/amazon/aoc/enums/GenericConstants.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -20,7 +20,7 @@
@Getter
public enum GenericConstants {
// retry
SLEEP_IN_MILLISECONDS("30000"), // ms
SLEEP_IN_MILLISECONDS("10000"), // ms
SLEEP_IN_SECONDS("30"),
MAX_RETRIES("10"),

Expand Down
5 changes: 1 addition & 4 deletions validator/src/main/java/com/amazon/aoc/services/XRayService.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -25,13 +25,11 @@
import com.amazonaws.services.xray.model.TraceSummary;
import java.util.Date;
import java.util.List;
import lombok.extern.log4j.Log4j2;
import org.joda.time.DateTime;

@Log4j2
public class XRayService {
private AWSXRay awsxRay;
private final int SEARCH_PERIOD = 600 * 3;
private final int SEARCH_PERIOD = 600;
public static String DEFAULT_TRACE_ID = "1-00000000-000000000000000000000000";

public XRayService(String region) {
Expand All @@ -55,7 +53,6 @@ public List<Trace> listTraceByIds(List<String> traceIdList) {
public List<TraceSummary> searchTraces(String traceFilter) {
Date currentDate = new Date();
Date pastDate = new DateTime(currentDate).minusSeconds(SEARCH_PERIOD).toDate();
log.info("--start-time: " + pastDate + ", --end-time: " + currentDate + ", traceFilter: " + traceFilter);
GetTraceSummariesResult traceSummaryResult =
awsxRay.getTraceSummaries(
new GetTraceSummariesRequest()
Expand Down
Loading