Samrat002 commented on code in PR #27921:
URL: https://github.com/apache/flink/pull/27921#discussion_r3102467994
##########
flink-tests/src/test/java/org/apache/flink/test/scheduling/RescaleOnCheckpointITCase.java:
##########
@@ -175,4 +175,59 @@ void testRescaleOnCheckpoint(
restClusterClient.cancel(jobGraph.getJobID()).join();
}
}
+
+ @Test
+ void testRescaleWithActiveCheckpointTrigger(
+ @InjectMiniCluster MiniCluster miniCluster,
+ @InjectClusterClient RestClusterClient<?> restClusterClient)
+ throws Exception {
+ final Configuration config = new Configuration();
+
+ final StreamExecutionEnvironment env =
+ StreamExecutionEnvironment.getExecutionEnvironment(config);
+ env.setParallelism(BEFORE_RESCALE_PARALLELISM);
+ env.enableCheckpointing(Duration.ofHours(1).toMillis());
+ env.fromSequence(0, Integer.MAX_VALUE).sinkTo(new DiscardingSink<>());
+
+ final JobGraph jobGraph = env.getStreamGraph().getJobGraph();
+ final Iterator<JobVertex> jobVertexIterator =
jobGraph.getVertices().iterator();
+ assertThat(jobVertexIterator.hasNext()).isTrue();
+ final JobVertexID jobVertexId = jobVertexIterator.next().getID();
+
+ final JobResourceRequirements jobResourceRequirements =
+ JobResourceRequirements.newBuilder()
+ .setParallelismForJobVertex(jobVertexId, 1,
AFTER_RESCALE_PARALLELISM)
+ .build();
+
+ restClusterClient.submitJob(jobGraph).join();
+
+ final JobID jobId = jobGraph.getJobID();
+ try {
+ LOG.info(
+ "Waiting for job {} to reach parallelism of {} for vertex
{}.",
+ jobId,
+ BEFORE_RESCALE_PARALLELISM,
+ jobVertexId);
+ waitForRunningTasks(restClusterClient, jobId,
BEFORE_RESCALE_PARALLELISM);
+
+ LOG.info(
+ "Updating job {} resource requirements: parallelism {} ->
{}.",
+ jobId,
+ BEFORE_RESCALE_PARALLELISM,
+ AFTER_RESCALE_PARALLELISM);
+ restClusterClient.updateJobResourceRequirements(jobId,
jobResourceRequirements).join();
+ LOG.info(
+ "Waiting for job {} to rescale to parallelism {} via
active checkpoint trigger.",
+ jobId,
+ AFTER_RESCALE_PARALLELISM);
+ waitForRunningTasks(restClusterClient, jobId,
AFTER_RESCALE_PARALLELISM);
+ final int expectedFreeSlotCount = NUMBER_OF_SLOTS -
AFTER_RESCALE_PARALLELISM;
+ LOG.info(
+ "Waiting for {} slot(s) to become available after scale
down.",
+ expectedFreeSlotCount);
+ waitForAvailableSlots(restClusterClient, expectedFreeSlotCount);
Review Comment:
Updated checkpointing to 24 hours. also added assertions for min-pause
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
