在 MacBook pro（16gb 内存）上使用kbastani/spark-neo4j和docker -compose，我正在尝试分析我的图表的strong_connected_components。
我有一个包含大约 60,000 个节点的图表(n1:Node {id:1})-[r:NEXT {count:100}]->(n2:Node {id:2})。
使用 neo4j 浏览器，我设法将pagerank处理回我的节点。
但是，当我尝试运行更复杂的算法时，例如strong_connected_components，我收到以下错误：
mazerunner_1 | 16/11/29 14:58:01 ERROR Utils: Uncaught exception in thread SparkListenerBus
mazerunner_1 | java.lang.OutOfMemoryError: Java heap space
mazerunner_1 | at org.apache.spark.ui.jobs.JobProgressListener$$anonfun$onJobStart$5$$anonfun$apply$9.apply(JobProgressListener.scala:200)
mazerunner_1 | at org.apache.spark.ui.jobs.JobProgressListener$$anonfun$onJobStart$5$$anonfun$apply$9.apply(JobProgressListener.scala:200)
mazerunner_1 | at scala.collection.mutable.MapLike$class.getOrElseUpdate(MapLike.scala:189)
mazerunner_1 | at scala.collection.mutable.AbstractMap.getOrElseUpdate(Map.scala:91)
mazerunner_1 | at org.apache.spark.ui.jobs.JobProgressListener$$anonfun$onJobStart$5.apply(JobProgressListener.scala:200)
mazerunner_1 | at org.apache.spark.ui.jobs.JobProgressListener$$anonfun$onJobStart$5.apply(JobProgressListener.scala:198)
mazerunner_1 | at scala.collection.IndexedSeqOptimized$class.foreach(IndexedSeqOptimized.scala:33)
mazerunner_1 | at scala.collection.mutable.WrappedArray.foreach(WrappedArray.scala:34)
mazerunner_1 | at org.apache.spark.ui.jobs.JobProgressListener.onJobStart(JobProgressListener.scala:198)
mazerunner_1 | at org.apache.spark.scheduler.SparkListenerBus$class.onPostEvent(SparkListenerBus.scala:34)
mazerunner_1 | at org.apache.spark.scheduler.LiveListenerBus.onPostEvent(LiveListenerBus.scala:31)
mazerunner_1 | at org.apache.spark.scheduler.LiveListenerBus.onPostEvent(LiveListenerBus.scala:31)
mazerunner_1 | at org.apache.spark.util.ListenerBus$class.postToAll(ListenerBus.scala:53)
mazerunner_1 | at org.apache.spark.util.AsynchronousListenerBus.postToAll(AsynchronousListenerBus.scala:36)
mazerunner_1 | at org.apache.spark.util.AsynchronousListenerBus$$anon$1$$anonfun$run$1.apply$mcV$sp(AsynchronousListenerBus.scala:76)
mazerunner_1 | at org.apache.spark.util.AsynchronousListenerBus$$anon$1$$anonfun$run$1.apply(AsynchronousListenerBus.scala:61)
mazerunner_1 | at org.apache.spark.util.AsynchronousListenerBus$$anon$1$$anonfun$run$1.apply(AsynchronousListenerBus.scala:61)
mazerunner_1 | at org.apache.spark.util.Utils$.logUncaughtExceptions(Utils.scala:1618)
mazerunner_1 | at org.apache.spark.util.AsynchronousListenerBus$$anon$1.run(AsynchronousListenerBus.scala:60)
mazerunner_1 | Exception in thread "SparkListenerBus" java.lang.OutOfMemoryError: Java heap space
mazerunner_1 | at org.apache.spark.ui.jobs.JobProgressListener$$anonfun$onJobStart$5$$anonfun$apply$9.apply(JobProgressListener.scala:200)
mazerunner_1 | at org.apache.spark.ui.jobs.JobProgressListener$$anonfun$onJobStart$5$$anonfun$apply$9.apply(JobProgressListener.scala:200)
mazerunner_1 | at scala.collection.mutable.MapLike$class.getOrElseUpdate(MapLike.scala:189)
mazerunner_1 | at scala.collection.mutable.AbstractMap.getOrElseUpdate(Map.scala:91)
mazerunner_1 | at org.apache.spark.ui.jobs.JobProgressListener$$anonfun$onJobStart$5.apply(JobProgressListener.scala:200)
mazerunner_1 | at org.apache.spark.ui.jobs.JobProgressListener$$anonfun$onJobStart$5.apply(JobProgressListener.scala:198)
mazerunner_1 | at scala.collection.IndexedSeqOptimized$class.foreach(IndexedSeqOptimized.scala:33)
mazerunner_1 | at scala.collection.mutable.WrappedArray.foreach(WrappedArray.scala:34)
mazerunner_1 | at org.apache.spark.ui.jobs.JobProgressListener.onJobStart(JobProgressListener.scala:198)
mazerunner_1 | at org.apache.spark.scheduler.SparkListenerBus$class.onPostEvent(SparkListenerBus.scala:34)
mazerunner_1 | at org.apache.spark.scheduler.LiveListenerBus.onPostEvent(LiveListenerBus.scala:31)
mazerunner_1 | at org.apache.spark.scheduler.LiveListenerBus.onPostEvent(LiveListenerBus.scala:31)
mazerunner_1 | at org.apache.spark.util.ListenerBus$class.postToAll(ListenerBus.scala:53)
mazerunner_1 | at org.apache.spark.util.AsynchronousListenerBus.postToAll(AsynchronousListenerBus.scala:36)
mazerunner_1 | at org.apache.spark.util.AsynchronousListenerBus$$anon$1$$anonfun$run$1.apply$mcV$sp(AsynchronousListenerBus.scala:76)
mazerunner_1 | at org.apache.spark.util.AsynchronousListenerBus$$anon$1$$anonfun$run$1.apply(AsynchronousListenerBus.scala:61)
mazerunner_1 | at org.apache.spark.util.AsynchronousListenerBus$$anon$1$$anonfun$run$1.apply(AsynchronousListenerBus.scala:61)
mazerunner_1 | at org.apache.spark.util.Utils$.logUncaughtExceptions(Utils.scala:1618)
mazerunner_1 | at org.apache.spark.util.AsynchronousListenerBus$$anon$1.run(AsynchronousListenerBus.scala:60)
我试图像这样修改我的 docker-compose.yml 文件：
hdfs:
environment:
- "JAVA_OPTS=-Xmx5g"
image: sequenceiq/hadoop-docker:2.4.1
command: /etc/bootstrap.sh -d -bash
mazerunner:
environment:
- "JAVA_OPTS=-Xmx5g"
image: kbastani/neo4j-graph-analytics:latest
links:
- hdfs
graphdb:
environment:
- "JAVA_OPTS=-Xmx2g"
image: kbastani/docker-neo4j:latest
ports:
- "7474:7474"
- "1337:1337"
volumes:
- /opt/data
links:
- mazerunner
- hdfs
没有成功。如何配置 spark & hdfs 以使用最大可用内存？
