flink-issues mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From GitBox <...@apache.org>
Subject [GitHub] [flink] zhuzhurk commented on a change in pull request #13284: [FLINK-17016][runtime] Change blink planner batch jobs to run with pipelined region scheduling
Date Tue, 01 Sep 2020 10:04:17 GMT

zhuzhurk commented on a change in pull request #13284:
URL: https://github.com/apache/flink/pull/13284#discussion_r481020499



##########
File path: flink-tests/src/test/java/org/apache/flink/test/scheduling/PipelinedRegionSchedulingITCase.java
##########
@@ -0,0 +1,130 @@
+/*
+ * Licensed to the Apache Software Foundation (ASF) under one
+ * or more contributor license agreements.  See the NOTICE file
+ * distributed with this work for additional information
+ * regarding copyright ownership.  The ASF licenses this file
+ * to you under the Apache License, Version 2.0 (the
+ * "License"); you may not use this file except in compliance
+ * with the License.  You may obtain a copy of the License at
+ *
+ *     http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+
+package org.apache.flink.test.scheduling;
+
+import org.apache.flink.api.common.JobID;
+import org.apache.flink.client.program.MiniClusterClient;
+import org.apache.flink.configuration.Configuration;
+import org.apache.flink.configuration.JobManagerOptions;
+import org.apache.flink.configuration.RestOptions;
+import org.apache.flink.runtime.io.network.partition.ResultPartitionType;
+import org.apache.flink.runtime.jobgraph.DistributionPattern;
+import org.apache.flink.runtime.jobgraph.JobGraph;
+import org.apache.flink.runtime.jobgraph.JobVertex;
+import org.apache.flink.runtime.jobgraph.ScheduleMode;
+import org.apache.flink.runtime.jobmanager.scheduler.NoResourceAvailableException;
+import org.apache.flink.runtime.jobmanager.scheduler.SlotSharingGroup;
+import org.apache.flink.runtime.jobmaster.JobResult;
+import org.apache.flink.runtime.minicluster.MiniCluster;
+import org.apache.flink.runtime.minicluster.MiniClusterConfiguration;
+import org.apache.flink.runtime.testtasks.NoOpInvokable;
+import org.apache.flink.util.ExceptionUtils;
+import org.apache.flink.util.TestLogger;
+
+import org.junit.Test;
+
+import java.util.Optional;
+import java.util.concurrent.CompletableFuture;
+
+import static org.hamcrest.CoreMatchers.containsString;
+import static org.hamcrest.CoreMatchers.is;
+import static org.junit.Assert.assertThat;
+
+/**
+ * IT case for pipelined region scheduling.
+ */
+public class PipelinedRegionSchedulingITCase extends TestLogger {
+
+	@Test
+	public void testSuccessWithSlotsNoFewerThanTheMaxRegionRequired() throws Exception {
+		final JobResult jobResult = executeSchedulingTest(2);
+		assertThat(jobResult.getSerializedThrowable().isPresent(), is(false));
+	}
+
+	@Test
+	public void testFailsOnInsufficientSlots() throws Exception {
+		final JobResult jobResult = executeSchedulingTest(1);
+		assertThat(jobResult.getSerializedThrowable().isPresent(), is(true));
+
+		final Throwable jobFailure = jobResult
+			.getSerializedThrowable()
+			.get()
+			.deserializeError(ClassLoader.getSystemClassLoader());
+
+		final Optional<NoResourceAvailableException> cause = ExceptionUtils.findThrowable(
+			jobFailure,
+			NoResourceAvailableException.class);
+		assertThat(cause.isPresent(), is(true));
+		assertThat(cause.get().getMessage(), containsString("Slot request bulk is not fulfillable!"));
+	}
+
+	private JobResult executeSchedulingTest(int numSlots) throws Exception {
+		final Configuration configuration = new Configuration();
+		configuration.setString(RestOptions.BIND_PORT, "0");
+		configuration.setLong(JobManagerOptions.SLOT_REQUEST_TIMEOUT, 5000L);

Review comment:
       The JM needs to wait RM connected and TM registered before it can obtain slot. So a
timeout is needed otherwise the case `testSuccessWithSlotsNoFewerThanTheMaxRegionRequired`
can fail (e.g. setting the timeout to 10ms the test almost fails every time).
   The larger timeout, the less chance it will fail. I think 5s is not pain for such kind
of tests.




----------------------------------------------------------------
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.

For queries about this service, please contact Infrastructure at:
users@infra.apache.org



Mime
View raw message