Skip to content

Explicitly clear the pending action after passing it to the step runtime. #131

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
jun-he merged 4 commits into from
Aug 12, 2025
Merged

Explicitly clear the pending action after passing it to the step runtime. #131

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
d88ea08
Explicitly clear the pending action after passing it to the step runt…
jun-he Aug 7, 2025
630988e
Add tests to verify that the pending action is reset.
jun-he Aug 7, 2025
cf930eb
Add comments for the config.
jun-he Aug 7, 2025
44660c4
Improve the test a bit.
jun-he Aug 7, 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
1 change: 1 addition & 0 deletions maestro-engine/src/main/java/com/netflix/maestro/engine/execution/StepRuntimeManager.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -61,6 +61,7 @@ private StepRuntimeSummary cloneSummary(StepRuntimeSummary summary) {
StepAction latestAction = summary.getPendingAction();
StepRuntimeSummary cloned = objectMapper.convertValue(summary, StepRuntimeSummary.class);
cloned.setPendingAction(latestAction);
summary.setPendingAction(null); // clear the pending action after passing it to step runtime
return cloned;
}

Expand Down
40 changes: 29 additions & 11 deletions ...tro-engine/src/test/java/com/netflix/maestro/engine/execution/StepRuntimeManagerTest.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -15,10 +15,12 @@
import static org.junit.Assert.assertEquals;
import static org.junit.Assert.assertFalse;
import static org.junit.Assert.assertNotNull;
import static org.junit.Assert.assertNull;
import static org.junit.Assert.assertTrue;
import static org.mockito.Mockito.when;

import com.netflix.maestro.engine.MaestroEngineBaseTest;
import com.netflix.maestro.engine.db.StepAction;
import com.netflix.maestro.engine.params.DefaultParamManager;
import com.netflix.maestro.engine.params.ParamsManager;
import com.netflix.maestro.engine.steps.StepRuntime;
Expand Down Expand Up @@ -138,17 +140,22 @@ public void testStart() {
.type(StepType.NOOP)
.stepRetry(StepInstance.StepRetry.from(Defaults.DEFAULT_RETRY_POLICY))
.build();
summary.setPendingAction(StepAction.builder().build());
assertNotNull(summary.getPendingAction());
boolean ret = runtimeManager.start(workflowSummary, null, summary);
assertTrue(ret);
assertEquals(StepInstance.Status.RUNNING, summary.getRuntimeState().getStatus());
assertNotNull(summary.getRuntimeState().getExecuteTime());
assertNotNull(summary.getRuntimeState().getModifyTime());
assertEquals(1, summary.getPendingRecords().size());
assertEquals(
StepInstance.Status.NOT_CREATED, summary.getPendingRecords().get(0).getOldStatus());
assertEquals(StepInstance.Status.RUNNING, summary.getPendingRecords().get(0).getNewStatus());
StepInstance.Status.NOT_CREATED, summary.getPendingRecords().getFirst().getOldStatus());
assertEquals(
StepInstance.Status.RUNNING, summary.getPendingRecords().getFirst().getNewStatus());
assertEquals(artifact, summary.getArtifacts().get("test-artifact"));
assertTrue(summary.getTimeline().isEmpty());
// The pending action should have been cleared after passing it to step runtime
assertNull(summary.getPendingAction());
}

@Test
Expand All @@ -167,9 +174,9 @@ public void testStartFailure() {
assertNotNull(summary.getRuntimeState().getModifyTime());
assertEquals(1, summary.getPendingRecords().size());
assertEquals(
StepInstance.Status.NOT_CREATED, summary.getPendingRecords().get(0).getOldStatus());
StepInstance.Status.NOT_CREATED, summary.getPendingRecords().getFirst().getOldStatus());
assertEquals(
StepInstance.Status.USER_FAILED, summary.getPendingRecords().get(0).getNewStatus());
StepInstance.Status.USER_FAILED, summary.getPendingRecords().getFirst().getNewStatus());
assertTrue(summary.getArtifacts().isEmpty());

stepRetry.incrementByStatus(StepInstance.Status.USER_FAILED);
Expand All @@ -193,17 +200,22 @@ public void testExecute() {
.type(StepType.NOOP)
.stepRetry(StepInstance.StepRetry.from(Defaults.DEFAULT_RETRY_POLICY))
.build();
summary.setPendingAction(StepAction.builder().build());
assertNotNull(summary.getPendingAction());
boolean ret = runtimeManager.execute(workflowSummary, null, summary);
assertTrue(ret);
assertEquals(StepInstance.Status.FINISHING, summary.getRuntimeState().getStatus());
assertNotNull(summary.getRuntimeState().getFinishTime());
assertNotNull(summary.getRuntimeState().getModifyTime());
assertEquals(1, summary.getPendingRecords().size());
assertEquals(
StepInstance.Status.NOT_CREATED, summary.getPendingRecords().get(0).getOldStatus());
assertEquals(StepInstance.Status.FINISHING, summary.getPendingRecords().get(0).getNewStatus());
StepInstance.Status.NOT_CREATED, summary.getPendingRecords().getFirst().getOldStatus());
assertEquals(
StepInstance.Status.FINISHING, summary.getPendingRecords().getFirst().getNewStatus());
assertEquals(artifact, summary.getArtifacts().get("test-artifact"));
assertTrue(summary.getTimeline().isEmpty());
// The pending action should have been cleared after passing it to step runtime
assertNull(summary.getPendingAction());
}

@Test
Expand All @@ -222,9 +234,9 @@ public void testExecuteFailure() {
assertNotNull(summary.getRuntimeState().getModifyTime());
assertEquals(1, summary.getPendingRecords().size());
assertEquals(
StepInstance.Status.NOT_CREATED, summary.getPendingRecords().get(0).getOldStatus());
StepInstance.Status.NOT_CREATED, summary.getPendingRecords().getFirst().getOldStatus());
assertEquals(
StepInstance.Status.PLATFORM_FAILED, summary.getPendingRecords().get(0).getNewStatus());
StepInstance.Status.PLATFORM_FAILED, summary.getPendingRecords().getFirst().getNewStatus());
assertTrue(summary.getArtifacts().isEmpty());

stepRetry.incrementByStatus(StepInstance.Status.PLATFORM_FAILED);
Expand All @@ -248,17 +260,23 @@ public void testTerminate() {
.type(StepType.NOOP)
.stepRetry(StepInstance.StepRetry.from(Defaults.DEFAULT_RETRY_POLICY))
.build();
summary.setPendingAction(StepAction.builder().build());
assertNotNull(summary.getPendingAction());
runtimeManager.terminate(workflowSummary, summary, StepInstance.Status.STOPPED);
assertEquals(StepInstance.Status.STOPPED, summary.getRuntimeState().getStatus());
assertNotNull(summary.getRuntimeState().getEndTime());
assertNotNull(summary.getRuntimeState().getModifyTime());
assertEquals(1, summary.getPendingRecords().size());
assertEquals(
StepInstance.Status.NOT_CREATED, summary.getPendingRecords().get(0).getOldStatus());
assertEquals(StepInstance.Status.STOPPED, summary.getPendingRecords().get(0).getNewStatus());
StepInstance.Status.NOT_CREATED, summary.getPendingRecords().getFirst().getOldStatus());
assertEquals(
StepInstance.Status.STOPPED, summary.getPendingRecords().getFirst().getNewStatus());
assertEquals(artifact, summary.getArtifacts().get("test-artifact"));
assertEquals(1, summary.getTimeline().getTimelineEvents().size());
assertEquals("test termination", summary.getTimeline().getTimelineEvents().get(0).getMessage());
assertEquals(
"test termination", summary.getTimeline().getTimelineEvents().getFirst().getMessage());
// The pending action should have been cleared after passing it to step runtime
assertNull(summary.getPendingAction());
}

@Test
Expand Down
5 changes: 3 additions & 2 deletions maestro-server/src/main/resources/application-aws.yml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -16,7 +16,7 @@ server:
port: 8080

maestro:
queue:
queue: # check MaestroJobEvent class for queue id
properties:
1:
worker-num: 8
Expand All @@ -32,7 +32,8 @@ maestro:
scan-interval: 5000
5:
worker-num: 3
scan-interval: 10000
scan-interval: 30000
ownership-timeout: 125000 # larger than the deletion processor timeout
notifier:
type: sns
alerting:
Expand Down
2 changes: 1 addition & 1 deletion maestro-server/src/main/resources/application.yml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -11,7 +11,7 @@ server:
port: 8080

maestro:
queue:
queue: # check MaestroJobEvent class for queue id
properties:
1:
worker-num: 8
Expand Down