Hi,
We are running Elasticsearch 0.90.7 on Linux sever (1 node cluster).
From time to time, Elasticsearch stop responding and the issue looks
related to the Garbage Collector. The log file is shown blow:
[2014-06-16 09:35:48,563][WARN ][monitor.jvm ] [node01]
[gc][ConcurrentMarkSweep][1674153][113273] duration [12.1s], collections
[1]/[12.3s], total [12.1s]/[17.9h], memory [7.3gb]->[7.2gb]/[7.9gb],
all_pools {[Code Cache] [15.5mb]->[15.5mb]/[48mb]}{[Par Eden Space]
[158.2mb]->[95.3mb]/[665.6mb]}{[Par Survivor Space]
[0b]->[0b]/[83.1mb]}{[CMS Old Gen] [7.1gb]->[7.1gb]/[7.1gb]}{[CMS Perm Gen]
[34.7mb]->[34.7mb]/[82mb]}
[2014-06-16 09:35:58,800][INFO ][monitor.jvm ] [node01]
[gc][ConcurrentMarkSweep][1674154][113274] duration [9.9s], collections
[1]/[10.2s], total [9.9s]/[17.9h], memory [7.2gb]->[7.2gb]/[7.9gb],
all_pools {[Code Cache] [15.5mb]->[15.5mb]/[48mb]}{[Par Eden Space]
[95.3mb]->[58.6mb]/[665.6mb]}{[Par Survivor Space]
[0b]->[0b]/[83.1mb]}{[CMS Old Gen] [7.1gb]->[7.1gb]/[7.1gb]}{[CMS Perm Gen]
[34.7mb]->[34.7mb]/[82mb]}
[2014-06-16 09:36:11,236][WARN ][monitor.jvm ] [node01]
[gc][ConcurrentMarkSweep][1674155][113275] duration [12s], collections
[1]/[12.4s], total [12s]/[17.9h], memory [7.2gb]->[7.3gb]/[7.9gb],
all_pools {[Code Cache] [15.5mb]->[15.5mb]/[48mb]}{[Par Eden Space]
[58.6mb]->[138.1mb]/[665.6mb]}{[Par Survivor Space]
[0b]->[0b]/[83.1mb]}{[CMS Old Gen] [7.1gb]->[7.1gb]/[7.1gb]}{[CMS Perm Gen]
[34.7mb]->[34.7mb]/[82mb]}
[2014-06-16 09:36:23,879][WARN ][monitor.jvm ] [node01]
[gc][ConcurrentMarkSweep][1674156][113276] duration [12.3s], collections
[1]/[12.6s], total [12.3s]/[17.9h], memory [7.3gb]->[7.2gb]/[7.9gb],
all_pools {[Code Cache] [15.5mb]->[15.5mb]/[48mb]}{[Par Eden Space]
[138.1mb]->[113mb]/[665.6mb]}{[Par Survivor Space]
[0b]->[0b]/[83.1mb]}{[CMS Old Gen] [7.1gb]->[7.1gb]/[7.1gb]}{[CMS Perm Gen]
[34.7mb]->[34.7mb]/[82mb]}
[2014-06-16 09:36:34,043][INFO ][monitor.jvm ] [node01]
[gc][ConcurrentMarkSweep][1674157][113277] duration [9.8s], collections
[1]/[10.1s], total [9.8s]/[17.9h], memory [7.2gb]->[7.2gb]/[7.9gb],
all_pools {[Code Cache] [15.5mb]->[15.5mb]/[48mb]}{[Par Eden Space]
[113mb]->[79mb]/[665.6mb]}{[Par Survivor Space] [0b]->[0b]/[83.1mb]}{[CMS
Old Gen] [7.1gb]->[7.1gb]/[7.1gb]}{[CMS Perm Gen]
[34.7mb]->[34.7mb]/[82mb]}
[2014-06-16 09:36:46,486][WARN ][monitor.jvm ] [node01]
[gc][ConcurrentMarkSweep][1674158][113278] duration [12.1s], collections
[1]/[12.4s], total [12.1s]/[17.9h], memory [7.2gb]->[7.2gb]/[7.9gb],
all_pools {[Code Cache] [15.5mb]->[15.5mb]/[48mb]}{[Par Eden Space]
[79mb]->[107.2mb]/[665.6mb]}{[Par Survivor Space] [0b]->[0b]/[83.1mb]}{[CMS
Old Gen] [7.1gb]->[7.1gb]/[7.1gb]}{[CMS Perm Gen]
[34.7mb]->[34.7mb]/[82mb]}
[2014-06-16 09:36:56,649][INFO ][monitor.jvm ] [node01]
[gc][ConcurrentMarkSweep][1674159][113279] duration [9.9s], collections
[1]/[10.1s], total [9.9s]/[18h], memory [7.2gb]->[7.2gb]/[7.9gb], all_pools
{[Code Cache] [15.5mb]->[15.5mb]/[48mb]}{[Par Eden Space]
[107.2mb]->[68.7mb]/[665.6mb]}{[Par Survivor Space]
[0b]->[0b]/[83.1mb]}{[CMS Old Gen] [7.1gb]->[7.1gb]/[7.1gb]}{[CMS Perm Gen]
[34.7mb]->[34.7mb]/[82mb]}
[2014-06-16 09:37:08,995][WARN ][monitor.jvm ] [node01]
[gc][ConcurrentMarkSweep][1674160][113280] duration [12s], collections
[1]/[12.3s], total [12s]/[18h], memory [7.2gb]->[7.2gb]/[7.9gb], all_pools
{[Code Cache] [15.5mb]->[15.5mb]/[48mb]}{[Par Eden Space]
[68.7mb]->[79.7mb]/[665.6mb]}{[Par Survivor Space]
[0b]->[0b]/[83.1mb]}{[CMS Old Gen] [7.1gb]->[7.1gb]/[7.1gb]}{[CMS Perm Gen]
[34.7mb]->[34.7mb]/[82mb]}
*The garbage collector logs long passes (around 10 seconds). Our system has
total memory of 32G and we set the ES_HEAP_SIZA to be 8G. *
We are almost sure this issue comes from long GC run.
What can we do to prevent this behavior and run ES smoothly ?
Thanks,
Kevin
--
You received this message because you are subscribed to the Google Groups "elasticsearch" group.
To unsubscribe from this group and stop receiving emails from it, send an email to elasticsearch+unsubscribe@googlegroups.com.
To view this discussion on the web visit https://groups.google.com/d/msgid/elasticsearch/bac7e7fb-e166-457f-89af-e832ce76010d%40googlegroups.com.
For more options, visit https://groups.google.com/d/optout.