Repository: spark Updated Branches: refs/heads/master 2d4e00efe -> 517975d89
http://git-wip-us.apache.org/repos/asf/spark/blob/517975d8/launcher/src/test/java/org/apache/spark/launcher/SparkSubmitOptionParserSuite.java ---------------------------------------------------------------------- diff --git a/launcher/src/test/java/org/apache/spark/launcher/SparkSubmitOptionParserSuite.java b/launcher/src/test/java/org/apache/spark/launcher/SparkSubmitOptionParserSuite.java new file mode 100644 index 0000000..f3d2109 --- /dev/null +++ b/launcher/src/test/java/org/apache/spark/launcher/SparkSubmitOptionParserSuite.java @@ -0,0 +1,108 @@ +/* + * 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.spark.launcher; + +import java.util.Arrays; +import java.util.Collections; +import java.util.List; + +import org.junit.Before; +import org.junit.Test; +import static org.junit.Assert.*; +import static org.mockito.Mockito.*; + +import static org.apache.spark.launcher.SparkSubmitOptionParser.*; + +public class SparkSubmitOptionParserSuite { + + private SparkSubmitOptionParser parser; + + @Before + public void setUp() { + parser = spy(new DummyParser()); + } + + @Test + public void testAllOptions() { + int count = 0; + for (String[] optNames : parser.opts) { + for (String optName : optNames) { + String value = optName + "-value"; + parser.parse(Arrays.asList(optName, value)); + count++; + verify(parser).handle(eq(optNames[0]), eq(value)); + verify(parser, times(count)).handle(anyString(), anyString()); + verify(parser, times(count)).handleExtraArgs(eq(Collections.<String>emptyList())); + } + } + + for (String[] switchNames : parser.switches) { + int switchCount = 0; + for (String name : switchNames) { + parser.parse(Arrays.asList(name)); + count++; + switchCount++; + verify(parser, times(switchCount)).handle(eq(switchNames[0]), same((String) null)); + verify(parser, times(count)).handle(anyString(), any(String.class)); + verify(parser, times(count)).handleExtraArgs(eq(Collections.<String>emptyList())); + } + } + } + + @Test + public void testExtraOptions() { + List<String> args = Arrays.asList(parser.MASTER, parser.MASTER, "foo", "bar"); + parser.parse(args); + verify(parser).handle(eq(parser.MASTER), eq(parser.MASTER)); + verify(parser).handleUnknown(eq("foo")); + verify(parser).handleExtraArgs(eq(Arrays.asList("bar"))); + } + + @Test(expected=IllegalArgumentException.class) + public void testMissingArg() { + parser.parse(Arrays.asList(parser.MASTER)); + } + + @Test + public void testEqualSeparatedOption() { + List<String> args = Arrays.asList(parser.MASTER + "=" + parser.MASTER); + parser.parse(args); + verify(parser).handle(eq(parser.MASTER), eq(parser.MASTER)); + verify(parser).handleExtraArgs(eq(Collections.<String>emptyList())); + } + + private static class DummyParser extends SparkSubmitOptionParser { + + @Override + protected boolean handle(String opt, String value) { + return true; + } + + @Override + protected boolean handleUnknown(String opt) { + return false; + } + + @Override + protected void handleExtraArgs(List<String> extra) { + + } + + } + +} http://git-wip-us.apache.org/repos/asf/spark/blob/517975d8/launcher/src/test/resources/log4j.properties ---------------------------------------------------------------------- diff --git a/launcher/src/test/resources/log4j.properties b/launcher/src/test/resources/log4j.properties new file mode 100644 index 0000000..00c20ad --- /dev/null +++ b/launcher/src/test/resources/log4j.properties @@ -0,0 +1,31 @@ +# +# 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. +# + +# Set everything to be logged to the file core/target/unit-tests.log +log4j.rootCategory=INFO, file +log4j.appender.file=org.apache.log4j.FileAppender +log4j.appender.file.append=false + +# Some tests will set "test.name" to avoid overwriting the main log file. +log4j.appender.file.file=target/unit-tests${test.name}.log + +log4j.appender.file.layout=org.apache.log4j.PatternLayout +log4j.appender.file.layout.ConversionPattern=%d{yy/MM/dd HH:mm:ss.SSS} %t %p %c{1}: %m%n + +# Ignore messages below warning level from Jetty, because it's a bit verbose +log4j.logger.org.eclipse.jetty=WARN +org.eclipse.jetty.LEVEL=WARN http://git-wip-us.apache.org/repos/asf/spark/blob/517975d8/make-distribution.sh ---------------------------------------------------------------------- diff --git a/make-distribution.sh b/make-distribution.sh index dd990d4..82d3340 100755 --- a/make-distribution.sh +++ b/make-distribution.sh @@ -127,6 +127,7 @@ if [ ! $(command -v "$MVN") ] ; then fi VERSION=$("$MVN" help:evaluate -Dexpression=project.version 2>/dev/null | grep -v "INFO" | tail -n 1) +SCALA_VERSION=$("$MVN" help:evaluate -Dexpression=scala.binary.version 2>/dev/null | grep -v "INFO" | tail -n 1) SPARK_HADOOP_VERSION=$("$MVN" help:evaluate -Dexpression=hadoop.version $@ 2>/dev/null\ | grep -v "INFO"\ | tail -n 1) @@ -196,6 +197,7 @@ echo "Build flags: $@" >> "$DISTDIR/RELEASE" # Copy jars cp "$SPARK_HOME"/assembly/target/scala*/*assembly*hadoop*.jar "$DISTDIR/lib/" cp "$SPARK_HOME"/examples/target/scala*/spark-examples*.jar "$DISTDIR/lib/" +cp "$SPARK_HOME"/launcher/target/spark-launcher_$SCALA_VERSION-$VERSION.jar "$DISTDIR/lib/" # This will fail if the -Pyarn profile is not provided # In this case, silence the error and ignore the return code of this command cp "$SPARK_HOME"/network/yarn/target/scala*/spark-*-yarn-shuffle.jar "$DISTDIR/lib/" &> /dev/null || : http://git-wip-us.apache.org/repos/asf/spark/blob/517975d8/pom.xml ---------------------------------------------------------------------- diff --git a/pom.xml b/pom.xml index 51bef30..a19da73 100644 --- a/pom.xml +++ b/pom.xml @@ -105,6 +105,7 @@ <module>external/zeromq</module> <module>examples</module> <module>repl</module> + <module>launcher</module> </modules> <properties> @@ -1195,7 +1196,7 @@ </environmentVariables> <systemProperties> <java.awt.headless>true</java.awt.headless> - <spark.test.home>${session.executionRootDirectory}</spark.test.home> + <spark.test.home>${spark.test.home}</spark.test.home> <spark.testing>1</spark.testing> <spark.ui.enabled>false</spark.ui.enabled> <spark.ui.showConsoleProgress>false</spark.ui.showConsoleProgress> http://git-wip-us.apache.org/repos/asf/spark/blob/517975d8/project/SparkBuild.scala ---------------------------------------------------------------------- diff --git a/project/SparkBuild.scala b/project/SparkBuild.scala index 4f17df5..35e748f 100644 --- a/project/SparkBuild.scala +++ b/project/SparkBuild.scala @@ -34,11 +34,11 @@ object BuildCommons { val allProjects@Seq(bagel, catalyst, core, graphx, hive, hiveThriftServer, mllib, repl, sql, networkCommon, networkShuffle, streaming, streamingFlumeSink, streamingFlume, streamingKafka, - streamingMqtt, streamingTwitter, streamingZeromq) = + streamingMqtt, streamingTwitter, streamingZeromq, launcher) = Seq("bagel", "catalyst", "core", "graphx", "hive", "hive-thriftserver", "mllib", "repl", "sql", "network-common", "network-shuffle", "streaming", "streaming-flume-sink", "streaming-flume", "streaming-kafka", "streaming-mqtt", "streaming-twitter", - "streaming-zeromq").map(ProjectRef(buildLocation, _)) + "streaming-zeromq", "launcher").map(ProjectRef(buildLocation, _)) val optionallyEnabledProjects@Seq(yarn, yarnStable, java8Tests, sparkGangliaLgpl, sparkKinesisAsl) = Seq("yarn", "yarn-stable", "java8-tests", "ganglia-lgpl", @@ -155,8 +155,9 @@ object SparkBuild extends PomBuild { (allProjects ++ optionallyEnabledProjects).foreach(enable(TestSettings.settings)) // TODO: Add Sql to mima checks + // TODO: remove launcher from this list after 1.3. allProjects.filterNot(x => Seq(spark, sql, hive, hiveThriftServer, catalyst, repl, - networkCommon, networkShuffle, networkYarn).contains(x)).foreach { + networkCommon, networkShuffle, networkYarn, launcher).contains(x)).foreach { x => enable(MimaBuild.mimaSettings(sparkHome, x))(x) } http://git-wip-us.apache.org/repos/asf/spark/blob/517975d8/python/pyspark/java_gateway.py ---------------------------------------------------------------------- diff --git a/python/pyspark/java_gateway.py b/python/pyspark/java_gateway.py index 936857e..43d2cf5 100644 --- a/python/pyspark/java_gateway.py +++ b/python/pyspark/java_gateway.py @@ -41,7 +41,7 @@ def launch_gateway(): submit_args = os.environ.get("PYSPARK_SUBMIT_ARGS") submit_args = submit_args if submit_args is not None else "" submit_args = shlex.split(submit_args) - command = [os.path.join(SPARK_HOME, script)] + submit_args + ["pyspark-shell"] + command = [os.path.join(SPARK_HOME, script)] + submit_args # Start a socket that will be used by PythonGatewayServer to communicate its port to us callback_socket = socket.socket(socket.AF_INET, socket.SOCK_STREAM) @@ -58,7 +58,6 @@ def launch_gateway(): # Don't send ctrl-c / SIGINT to the Java gateway: def preexec_func(): signal.signal(signal.SIGINT, signal.SIG_IGN) - env["IS_SUBPROCESS"] = "1" # tell JVM to exit after python exits proc = Popen(command, stdin=PIPE, preexec_fn=preexec_func, env=env) else: # preexec_fn not supported on Windows http://git-wip-us.apache.org/repos/asf/spark/blob/517975d8/sbin/spark-daemon.sh ---------------------------------------------------------------------- diff --git a/sbin/spark-daemon.sh b/sbin/spark-daemon.sh index 5e812a1..92e76a3 100755 --- a/sbin/spark-daemon.sh +++ b/sbin/spark-daemon.sh @@ -121,45 +121,63 @@ if [ "$SPARK_NICENESS" = "" ]; then export SPARK_NICENESS=0 fi +run_command() { + mode="$1" + shift -case $option in + mkdir -p "$SPARK_PID_DIR" - (start|spark-submit) + if [ -f "$pid" ]; then + TARGET_ID="$(cat "$pid")" + if [[ $(ps -p "$TARGET_ID" -o args=) =~ $command ]]; then + echo "$command running as process $TARGET_ID. Stop it first." + exit 1 + fi + fi - mkdir -p "$SPARK_PID_DIR" + if [ "$SPARK_MASTER" != "" ]; then + echo rsync from "$SPARK_MASTER" + rsync -a -e ssh --delete --exclude=.svn --exclude='logs/*' --exclude='contrib/hod/logs/*' "$SPARK_MASTER/" "$SPARK_HOME" + fi - if [ -f $pid ]; then - TARGET_ID="$(cat "$pid")" - if [[ $(ps -p "$TARGET_ID" -o args=) =~ $command ]]; then - echo "$command running as process $TARGET_ID. Stop it first." - exit 1 - fi - fi + spark_rotate_log "$log" + echo "starting $command, logging to $log" + + case "$mode" in + (class) + nohup nice -n "$SPARK_NICENESS" "$SPARK_PREFIX"/bin/spark-class $command "$@" >> "$log" 2>&1 < /dev/null & + newpid="$!" + ;; + + (submit) + nohup nice -n "$SPARK_NICENESS" "$SPARK_PREFIX"/bin/spark-submit --class $command "$@" >> "$log" 2>&1 < /dev/null & + newpid="$!" + ;; + + (*) + echo "unknown mode: $mode" + exit 1 + ;; + esac + + echo "$newpid" > "$pid" + sleep 2 + # Check if the process has died; in that case we'll tail the log so the user can see + if [[ ! $(ps -p "$newpid" -o args=) =~ $command ]]; then + echo "failed to launch $command:" + tail -2 "$log" | sed 's/^/ /' + echo "full log in $log" + fi +} - if [ "$SPARK_MASTER" != "" ]; then - echo rsync from "$SPARK_MASTER" - rsync -a -e ssh --delete --exclude=.svn --exclude='logs/*' --exclude='contrib/hod/logs/*' $SPARK_MASTER/ "$SPARK_HOME" - fi +case $option in - spark_rotate_log "$log" - echo "starting $command, logging to $log" - if [ $option == spark-submit ]; then - source "$SPARK_HOME"/bin/utils.sh - gatherSparkSubmitOpts "$@" - nohup nice -n $SPARK_NICENESS "$SPARK_PREFIX"/bin/spark-submit --class $command \ - "${SUBMISSION_OPTS[@]}" spark-internal "${APPLICATION_OPTS[@]}" >> "$log" 2>&1 < /dev/null & - else - nohup nice -n $SPARK_NICENESS "$SPARK_PREFIX"/bin/spark-class $command "$@" >> "$log" 2>&1 < /dev/null & - fi - newpid=$! - echo $newpid > $pid - sleep 2 - # Check if the process has died; in that case we'll tail the log so the user can see - if [[ ! $(ps -p "$newpid" -o args=) =~ $command ]]; then - echo "failed to launch $command:" - tail -2 "$log" | sed 's/^/ /' - echo "full log in $log" - fi + (submit) + run_command submit "$@" + ;; + + (start) + run_command class "$@" ;; (stop) http://git-wip-us.apache.org/repos/asf/spark/blob/517975d8/sbin/start-thriftserver.sh ---------------------------------------------------------------------- diff --git a/sbin/start-thriftserver.sh b/sbin/start-thriftserver.sh index 070cc7a..5b0aeb1 100755 --- a/sbin/start-thriftserver.sh +++ b/sbin/start-thriftserver.sh @@ -52,4 +52,4 @@ fi export SUBMIT_USAGE_FUNCTION=usage -exec "$FWDIR"/sbin/spark-daemon.sh spark-submit $CLASS 1 "$@" +exec "$FWDIR"/sbin/spark-daemon.sh submit $CLASS 1 "$@" --------------------------------------------------------------------- To unsubscribe, e-mail: [email protected] For additional commands, e-mail: [email protected]
