Skip to content
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
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
Original file line number Diff line number Diff line change
@@ -0,0 +1,73 @@
/*
* 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.paimon.tests;

import org.junit.jupiter.api.Test;

import static org.assertj.core.api.Assertions.assertThat;

/** Tests for {@link SparkE2eTest#stripTrailingSparkErrorLogs(String)}. Does not need Docker. */
public class SparkE2eOutputTest {

private static final String ROWS = "1\t10\tHi\n2\t20\tHello\n3\t30\tTable\n";

private static final String COARSE_GRAINED_SCHEDULER_ERROR =
"26/07/29 04:25:43 ERROR Utils: Uncaught exception in thread dispatcher-CoarseGrainedScheduler\n"
+ "org.apache.spark.SparkException: Could not find CoarseGrainedScheduler.\n"
+ "\tat org.apache.spark.rpc.netty.Dispatcher.postMessage(Dispatcher.scala:178)\n";

private static final String TRANSPORT_REQUEST_HANDLER_ERROR =
"26/08/30 07:28:25 ERROR TransportRequestHandler: Error while invoking RpcHandler#receive() for one-way message.\n"
+ "org.apache.spark.SparkException: Could not find AppClient.\n"
+ "\tat org.apache.spark.rpc.netty.Dispatcher.postMessage(Dispatcher.scala:178)\n"
+ "\tat java.lang.Thread.run(Thread.java:748)\n";

@Test
public void testNoErrorLogIsUnchanged() {
assertThat(SparkE2eTest.stripTrailingSparkErrorLogs(ROWS)).isEqualTo(ROWS);
}

@Test
public void testStripsCoarseGrainedSchedulerError() {
assertThat(SparkE2eTest.stripTrailingSparkErrorLogs(ROWS + COARSE_GRAINED_SCHEDULER_ERROR))
.isEqualTo(ROWS);
}

@Test
public void testStripsRepeatedTransportRequestHandlerErrors() {
assertThat(
SparkE2eTest.stripTrailingSparkErrorLogs(
ROWS
+ TRANSPORT_REQUEST_HANDLER_ERROR
+ TRANSPORT_REQUEST_HANDLER_ERROR))
.isEqualTo(ROWS);
}

@Test
public void testErrorOnFirstLineYieldsEmptyOutput() {
assertThat(SparkE2eTest.stripTrailingSparkErrorLogs(TRANSPORT_REQUEST_HANDLER_ERROR))
.isEmpty();
}

@Test
public void testErrorWordInsideResultRowIsKept() {
String rows = "1\t10\tsome ERROR text\n2\t20\tERROR Foo\n";
assertThat(SparkE2eTest.stripTrailingSparkErrorLogs(rows)).isEqualTo(rows);
}
}
Original file line number Diff line number Diff line change
Expand Up @@ -18,6 +18,8 @@

package org.apache.paimon.tests;

import org.apache.paimon.annotation.VisibleForTesting;

import org.junit.jupiter.api.Test;
import org.junit.jupiter.api.condition.DisabledOnJre;
import org.slf4j.Logger;
Expand All @@ -27,6 +29,8 @@

import java.util.Arrays;
import java.util.UUID;
import java.util.regex.Matcher;
import java.util.regex.Pattern;
import java.util.stream.Collectors;

import static org.junit.jupiter.api.condition.JRE.JAVA_11;
Expand All @@ -36,8 +40,14 @@
public class SparkE2eTest extends E2eReaderTestBase {

private static final Logger LOG = LoggerFactory.getLogger(SparkE2eTest.class);
private static final String COARSE_GRAINED_SCHEDULER_SHUTDOWN_ERROR =
"ERROR Utils: Uncaught exception in thread dispatcher-CoarseGrainedScheduler";

/**
* Start of a Spark ERROR log line in the default log4j2 pattern ({@code %d{yy/MM/dd HH:mm:ss}
* %p %c{1}: %m%n%ex}), which spark-sql writes to stdout. Anchoring on the timestamp prefix
* avoids matching an "ERROR" word inside a result row.
*/
private static final Pattern SPARK_ERROR_LOG_LINE =
Pattern.compile("(?m)^\\d{2}/\\d{2}/\\d{2} \\d{2}:\\d{2}:\\d{2} ERROR ");

public SparkE2eTest() {
super(false, false, true);
Expand Down Expand Up @@ -77,23 +87,25 @@ public void testFlinkWriteAndSparkRead() throws Exception {
LOG.info(execResult.getStderr());
throw new AssertionError("Failed when running spark sql.");
}
String stdout =
stripCoarseGrainedSchedulerShutdownError(execResult.getStdout());
String stdout = stripTrailingSparkErrorLogs(execResult.getStdout());
return Arrays.stream(stdout.split("\n"))
.filter(s -> !s.contains("WARN"))
.collect(Collectors.joining("\n"))
+ "\n";
});
}

private static String stripCoarseGrainedSchedulerShutdownError(String stdout) {
int errorIndex = stdout.indexOf(COARSE_GRAINED_SCHEDULER_SHUTDOWN_ERROR);
if (errorIndex < 0) {
return stdout;
}

int errorLineStart = stdout.lastIndexOf('\n', errorIndex);
return errorLineStart < 0 ? "" : stdout.substring(0, errorLineStart);
/**
* Drops everything from the first Spark ERROR log line onwards. When spark-sql exits, the
* driver shutdown races with RPC dispatch and may log after the query result, with exit code 0,
* e.g. {@code ERROR Utils: Uncaught exception in thread dispatcher-CoarseGrainedScheduler} or
* {@code ERROR TransportRequestHandler: Error while invoking RpcHandler#receive() for one-way
* message.} followed by a stack trace.
*/
@VisibleForTesting
static String stripTrailingSparkErrorLogs(String stdout) {
Matcher matcher = SPARK_ERROR_LOG_LINE.matcher(stdout);
return matcher.find() ? stdout.substring(0, matcher.start()) : stdout;
}

private ContainerState getSpark() {
Expand Down
Loading