zhoujunkun created YARN-1475: -------------------------------- Summary: Container out of memery Key: YARN-1475 URL: https://issues.apache.org/jira/browse/YARN-1475 Project: Hadoop YARN Issue Type: Bug Components: nodemanager Affects Versions: 2.2.0 Environment: mapreduce.reduce.java.opts=-Xmx4000m mapreduce.reduce.shuffle.merge.percent=0.4 mapreduce.reduce.shuffle.parallelcopies=5 mapreduce.reduce.shuffle.input.buffer.percent=0.6 mapreduce.reduce.shuffle.memory.limit.percent=0.17 Reporter: zhoujunkun
when I input 60G of random word, I run wordcount job, the stage of shuffle is error. the reduce is run 13%. Container [pid=21073,containerID=container_1385657333160_0001_01_000073] is running beyond physical memory limits. Current usage: 4.0 GB of 4 GB physical memory used; 5.5 GB of 13 GB virtual memory used. Killing container. why do it need so much memory? -- This message was sent by Atlassian JIRA (v6.1#6144)