Hi Franco Maria,
Try with:
MAP_MEMORY=1500
JAVA_CHILD_OPTS=-Xmx1G
-Dmapred.job.map.memory.mb="${MAP_MEMORY}" \
-Dmapred.map.child.java.opts="${JAVA_CHILD_OPTS}" \
Cheers,
--
Gianmarco
On Thu, Sep 13, 2012 at 11:01 PM, Franco Maria Nardini <
[email protected]> wrote:
> Hi all,
>
> I am running the PageRank code on single machine hadoop installation.
> In particular, I am running the code using four workers on a graph of
> 100.000 nodes. I am getting this exception:
>
> 012-09-13 22:54:38,379 INFO org.apache.hadoop.mapred.Task:
> Communication exception: java.lang.OutOfMemoryError: GC overhead limit
> exceeded
> at
> org.apache.hadoop.util.ProcfsBasedProcessTree.getProcessList(ProcfsBasedProcessTree.java:365)
> at
> org.apache.hadoop.util.ProcfsBasedProcessTree.getProcessTree(ProcfsBasedProcessTree.java:138)
> at
> org.apache.hadoop.util.LinuxResourceCalculatorPlugin.getProcResourceValues(LinuxResourceCalculatorPlugin.java:401)
> at
> org.apache.hadoop.mapred.Task.updateResourceCounters(Task.java:808)
> at org.apache.hadoop.mapred.Task.updateCounters(Task.java:830)
> at org.apache.hadoop.mapred.Task.access$600(Task.java:66)
> at org.apache.hadoop.mapred.Task$TaskReporter.run(Task.java:666)
> at java.lang.Thread.run(Thread.java:662)
>
> It's seems to be a problem related to communication stuff. Do I have
> to specify or modify some options to hadoop to avoid this?
>
> Best,
>
> Franco Maria
>
