Skip to content

TEZ-4561: Improve reported exception when DAGAppMaster is shutting down. #365

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
ayushtkn merged 6 commits into from
Sep 3, 2024
Merged

TEZ-4561: Improve reported exception when DAGAppMaster is shutting down. #365

Show file tree
Hide file tree
Changes from 3 commits
Commits
Show all changes
6 commits
Select commit Hold shift + click to select a range
00a4dfa
TEZ-4561: Improve reported exception when DAGAppMaster is shutting down.
ayushtkn Aug 16, 2024
115fc4b
Add Test Case.
ayushtkn Aug 16, 2024
616981d
Fix Checkstyle.
ayushtkn Aug 16, 2024
9dc1b51
Move FullStop Above.
ayushtkn Aug 28, 2024
1790462
Use setter & getter.
ayushtkn Aug 28, 2024
fa43d37
FindBugs
ayushtkn Aug 28, 2024
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
17 changes: 14 additions & 3 deletions tez-dag/src/main/java/org/apache/tez/dag/app/DAGAppMaster.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -36,6 +36,7 @@
import java.util.Arrays;
import java.util.Calendar;
import java.util.Collections;
import java.util.Date;
import java.util.EnumSet;
import java.util.HashMap;
import java.util.HashSet;
Expand Down Expand Up @@ -936,7 +937,7 @@ public void handle(DAGAppMasterEvent event) {
protected class DAGAppMasterShutdownHandler {
private AtomicBoolean shutdownHandled = new AtomicBoolean(false);
private long sleepTimeBeforeExit = TezConstants.TEZ_DAG_SLEEP_TIME_BEFORE_EXIT;

Date shutdownTime;
void setSleepTimeBeforeExit(long sleepTimeBeforeExit) {
this.sleepTimeBeforeExit = sleepTimeBeforeExit;
}
Expand All @@ -954,6 +955,7 @@ public void shutdown(boolean now) {

synchronized (shutdownHandlerRunning) {
shutdownHandlerRunning.set(true);
shutdownTime = new Date(System.currentTimeMillis());
}
LOG.info("Handling DAGAppMaster shutdown");

Expand Down Expand Up @@ -1680,9 +1682,11 @@ public HadoopShim getHadoopShim() {

@Override
public Map<ApplicationAccessType, String> getApplicationACLs() {
if (getServiceState() != STATE.STARTED) {
STATE serviceState = getServiceState();
if (serviceState != STATE.STARTED) {
throw new TezUncheckedException(
"Cannot get ApplicationACLs before all services have started");
"Cannot get ApplicationACLs before all services have started, The current service state is " + serviceState
+ getShutdownTimeString());
}
return taskSchedulerManager.getApplicationAcls();
}
Expand Down Expand Up @@ -1743,6 +1747,13 @@ public void setQueueName(String queueName) {
}
}

private String getShutdownTimeString() {
if (shutdownHandler != null && shutdownHandler.shutdownTime != null) {
return ". The shutdown hook started at " + shutdownHandler.shutdownTime;
Copy link
Contributor

@abstractdog abstractdog Aug 27, 2024

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

It's strange that this separate string generation method takes care of the closing point of the previous sentence, I believe that should go back to getApplicationACLs

Copy link
Member Author

@ayushtkn ayushtkn Aug 28, 2024

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

I moved the "." back to the {{getApplicationACLs}}

}
return "";
}

private static class ServiceWithDependency implements ServiceStateChangeListener {
ServiceWithDependency(Service service) {
this.service = service;
Expand Down
28 changes: 25 additions & 3 deletions tez-dag/src/test/java/org/apache/tez/dag/app/TestDAGAppMaster.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -32,7 +32,8 @@
import org.apache.hadoop.security.token.SecretManager;
import org.apache.hadoop.security.token.Token;
import org.apache.hadoop.security.token.TokenIdentifier;
import org.apache.hadoop.util.Progressable;
import org.apache.hadoop.test.LambdaTestUtils;
import org.apache.hadoop.util.Time;
import org.apache.hadoop.yarn.api.records.ApplicationAttemptId;
import org.apache.hadoop.yarn.api.records.ApplicationId;
import org.apache.hadoop.yarn.api.records.ContainerId;
Expand All @@ -49,6 +50,7 @@
import org.apache.tez.dag.api.NamedEntityDescriptor;
import org.apache.tez.dag.api.TezConfiguration;
import org.apache.tez.dag.api.TezConstants;
import org.apache.tez.dag.api.TezUncheckedException;
import org.apache.tez.dag.api.UserPayload;
import org.apache.tez.dag.api.records.DAGProtos;
import org.apache.tez.dag.api.records.DAGProtos.AMPluginDescriptorProto;
Expand All @@ -73,12 +75,12 @@
import java.io.DataInputStream;
import java.io.DataOutput;
import java.io.File;
import java.io.FileNotFoundException;
import java.io.FileOutputStream;
import java.io.IOException;
import java.lang.reflect.Field;
import java.net.URI;
import java.nio.ByteBuffer;
import java.time.Instant;
import java.util.Date;
import java.util.HashMap;
import java.util.LinkedList;
import java.util.List;
Expand Down Expand Up @@ -493,6 +495,26 @@ public void testDagCredentialsWithMerge() throws Exception {
testDagCredentials(true);
}

@Test
public void testGetACLFailure() throws Exception {
ApplicationId appId = ApplicationId.newInstance(1, 1);
ApplicationAttemptId attemptId = ApplicationAttemptId.newInstance(appId, 2);
DAGAppMasterForTest dam = new DAGAppMasterForTest(attemptId, true);
TezConfiguration conf = new TezConfiguration(false);
conf.setBoolean(TezConfiguration.DAG_RECOVERY_ENABLED, false);
dam.init(conf);
LambdaTestUtils.intercept(TezUncheckedException.class,
"Cannot get ApplicationACLs before all services have started, The current service state is INITED",
() -> dam.getContext().getApplicationACLs());
dam.start();
dam.stop();
dam.mockShutdown.shutdownTime = Date.from(Instant.ofEpochMilli(Time.now()));
LambdaTestUtils.intercept(TezUncheckedException.class,
" Cannot get ApplicationACLs before all services have started, "
+ "The current service state is STOPPED. The shutdown hook started at "
+ dam.mockShutdown.shutdownTime, () -> dam.getContext().getApplicationACLs());
}

@Test
public void testBadProgress() throws Exception {
TezConfiguration conf = new TezConfiguration();
Expand Down