High CPU usage on a thread, ES doesn't respond anymore

Hi,

First, thank you for this wonderful product!
I'm using it for search and tags on EklaBlog, a french blogs platform.

I have a problem with ES for some weeks: some minutes or hours after
start, a thread of ES takes 100% of a CPU, other threads 0%, and ES
doesn't respond anymore to any request.
Then I restart ES and it works again for some minutes...

ES is installed on a single serveur with this configuration:

network.publish_host: meriadec
cluster:
name: eklablog
path:
logs: /var/log/elasticsearch
data: /home/elasticsearch
discovery.zen.ping:
multicast.enabled: false
set.default.ES_HOME=/opt/elasticsearch
set.default.ES_MIN_MEM=1024
set.default.ES_MAX_MEM=5000

I actually have an error which occurs everytime, but I don't if it's
the cause:

[2011-11-08 00:38:52,263][WARN ][common.jna ] Unknown
mlockall error 0
[2011-11-08 00:38:52,268][INFO ][node ] [Pip the
Troll] {0.18.2}[23851]: initializing ...
[2011-11-08 00:38:52,271][INFO ][plugins ] [Pip the
Troll] loaded [], sites []
[2011-11-08 00:38:53,720][INFO ][node ] [Pip the
Troll] {0.18.2}[23851]: initialized
[2011-11-08 00:38:53,721][INFO ][node ] [Pip the
Troll] {0.18.2}[23851]: starting ...
[2011-11-08 00:38:53,767][INFO ][transport ] [Pip the
Troll] bound_address {inet[/0.0.0.0:9300]}, publish_address
{inet[meriadec/94.23.13.10:9300]}
[2011-11-08 00:38:56,776][INFO ][cluster.service ] [Pip the
Troll] new_master [Pip the Troll][83bg-5soRT-7QqHFEhVfmA]
[inet[meriadec/94.23.13.10:9300]], reason: zen-disco-join
(elected_as_master)
[2011-11-08 00:38:56,816][INFO ][discovery ] [Pip the
Troll] eklablog/83bg-5soRT-7QqHFEhVfmA
[2011-11-08 00:38:56,899][INFO ][http ] [Pip the
Troll] bound_address {inet[/0.0.0.0:9200]}, publish_address
{inet[meriadec/94.23.13.10:9200]}
[2011-11-08 00:38:56,900][INFO ][node ] [Pip the
Troll] {0.18.2}[23851]: started
[2011-11-08 00:38:57,745][INFO ][gateway ] [Pip the
Troll] recovered [4] indices into cluster_state
[2011-11-08 00:52:37,793][DEBUG][action.search.type ] [Pip the
Troll] [1094] Failed to execute fetch phase
org.elasticsearch.search.SearchContextMissingException: No search
context found for id [1094]
at
org.elasticsearch.search.SearchService.findContext(SearchService.java:
411)
at
org.elasticsearch.search.SearchService.executeFetchPhase(SearchService.java:
386)
at
org.elasticsearch.search.action.SearchServiceTransportAction.sendExecuteFetch(SearchServiceTransportAction.java:
314)
at
org.elasticsearch.action.search.type.TransportSearchQueryThenFetchAction
$AsyncAction.executeFetch(TransportSearchQueryThenFetchAction.java:
145)
at
org.elasticsearch.action.search.type.TransportSearchQueryThenFetchAction
$AsyncAction$2.run(TransportSearchQueryThenFetchAction.java:132)
at java.util.concurrent.ThreadPoolExecutor
$Worker.runTask(ThreadPoolExecutor.java:886)
at java.util.concurrent.ThreadPoolExecutor
$Worker.run(ThreadPoolExecutor.java:908)
at java.lang.Thread.run(Thread.java:662)
[2011-11-08 00:52:38,101][DEBUG][action.search.type ] [Pip the
Troll] [912] Failed to execute fetch phase
org.elasticsearch.search.SearchContextMissingException: No search
context found for id [912]
at
org.elasticsearch.search.SearchService.findContext(SearchService.java:
411)
at
org.elasticsearch.search.SearchService.executeFetchPhase(SearchService.java:
386)
at
org.elasticsearch.search.action.SearchServiceTransportAction.sendExecuteFetch(SearchServiceTransportAction.java:
314)
at
org.elasticsearch.action.search.type.TransportSearchQueryThenFetchAction
$AsyncAction.executeFetch(TransportSearchQueryThenFetchAction.java:
145)
at
org.elasticsearch.action.search.type.TransportSearchQueryThenFetchAction
$AsyncAction$2.run(TransportSearchQueryThenFetchAction.java:132)
at java.util.concurrent.ThreadPoolExecutor
$Worker.runTask(ThreadPoolExecutor.java:886)
at java.util.concurrent.ThreadPoolExecutor
$Worker.run(ThreadPoolExecutor.java:908)
at java.lang.Thread.run(Thread.java:662)

And I've sometimes another error:

[2011-11-08 01:49:04,063][WARN ][http.netty ] [Pip the
Troll] Caught exception while handling client http traffic, closing
connection
java.io.IOException: Relais brisé (pipe)
at sun.nio.ch.FileDispatcher.write0(Native Method)
at sun.nio.ch.SocketDispatcher.write(SocketDispatcher.java:29)
at sun.nio.ch.IOUtil.writeFromNativeBuffer(IOUtil.java:72)
at sun.nio.ch.IOUtil.write(IOUtil.java:28)
at sun.nio.ch.SocketChannelImpl.write(SocketChannelImpl.java:334)
at
org.elasticsearch.common.netty.channel.socket.nio.SocketSendBufferPool
$PooledSendBuffer.transferTo(SocketSendBufferPool.java:239)
at
org.elasticsearch.common.netty.channel.socket.nio.NioWorker.write0(NioWorker.java:
470)
at
org.elasticsearch.common.netty.channel.socket.nio.NioWorker.writeFromUserCode(NioWorker.java:
388)
at
org.elasticsearch.common.netty.channel.socket.nio.NioServerSocketPipelineSink.handleAcceptedSocket(NioServerSocketPipelineSink.java:
137)
at
org.elasticsearch.common.netty.channel.socket.nio.NioServerSocketPipelineSink.eventSunk(NioServerSocketPipelineSink.java:
76)
at org.elasticsearch.common.netty.channel.DefaultChannelPipeline
$DefaultChannelHandlerContext.sendDownstream(DefaultChannelPipeline.java:
771)
at
org.elasticsearch.common.netty.channel.Channels.write(Channels.java:
632)
at
org.elasticsearch.common.netty.channel.Channels.write(Channels.java:
593)
at
org.elasticsearch.common.netty.handler.codec.http.HttpChunkAggregator.messageReceived(HttpChunkAggregator.java:
99)
at
org.elasticsearch.common.netty.channel.SimpleChannelUpstreamHandler.handleUpstream(SimpleChannelUpstreamHandler.java:
80)
at
org.elasticsearch.common.netty.channel.DefaultChannelPipeline.sendUpstream(DefaultChannelPipeline.java:
564)
at org.elasticsearch.common.netty.channel.DefaultChannelPipeline
$DefaultChannelHandlerContext.sendUpstream(DefaultChannelPipeline.java:
783)
at
org.elasticsearch.common.netty.handler.codec.http.HttpContentDecoder.messageReceived(HttpContentDecoder.java:
104)
at
org.elasticsearch.common.netty.channel.SimpleChannelUpstreamHandler.handleUpstream(SimpleChannelUpstreamHandler.java:
80)
at
org.elasticsearch.common.netty.channel.DefaultChannelPipeline.sendUpstream(DefaultChannelPipeline.java:
564)
at org.elasticsearch.common.netty.channel.DefaultChannelPipeline
$DefaultChannelHandlerContext.sendUpstream(DefaultChannelPipeline.java:
783)
at
org.elasticsearch.common.netty.channel.Channels.fireMessageReceived(Channels.java:
302)
at
org.elasticsearch.common.netty.handler.codec.replay.ReplayingDecoder.unfoldAndFireMessageReceived(ReplayingDecoder.java:
522)
at
org.elasticsearch.common.netty.handler.codec.replay.ReplayingDecoder.callDecode(ReplayingDecoder.java:
506)
at
org.elasticsearch.common.netty.handler.codec.replay.ReplayingDecoder.messageReceived(ReplayingDecoder.java:
443)
at
org.elasticsearch.common.netty.channel.SimpleChannelUpstreamHandler.handleUpstream(SimpleChannelUpstreamHandler.java:
80)
at
org.elasticsearch.common.netty.channel.DefaultChannelPipeline.sendUpstream(DefaultChannelPipeline.java:
564)
at org.elasticsearch.common.netty.channel.DefaultChannelPipeline
$DefaultChannelHandlerContext.sendUpstream(DefaultChannelPipeline.java:
783)
at
org.elasticsearch.common.netty.OpenChannelsHandler.handleUpstream(OpenChannelsHandler.java:
65)
at
org.elasticsearch.common.netty.channel.DefaultChannelPipeline.sendUpstream(DefaultChannelPipeline.java:
564)
at
org.elasticsearch.common.netty.channel.DefaultChannelPipeline.sendUpstream(DefaultChannelPipeline.java:
559)
at
org.elasticsearch.common.netty.channel.Channels.fireMessageReceived(Channels.java:
274)
at
org.elasticsearch.common.netty.channel.Channels.fireMessageReceived(Channels.java:
261)
at
org.elasticsearch.common.netty.channel.socket.nio.NioWorker.read(NioWorker.java:
349)
at
org.elasticsearch.common.netty.channel.socket.nio.NioWorker.processSelectedKeys(NioWorker.java:
280)
at
org.elasticsearch.common.netty.channel.socket.nio.NioWorker.run(NioWorker.java:
200)
at
org.elasticsearch.common.netty.util.ThreadRenamingRunnable.run(ThreadRenamingRunnable.java:
108)
at org.elasticsearch.common.netty.util.internal.DeadLockProofWorker
$1.run(DeadLockProofWorker.java:44)
at java.util.concurrent.ThreadPoolExecutor
$Worker.runTask(ThreadPoolExecutor.java:886)
at java.util.concurrent.ThreadPoolExecutor
$Worker.run(ThreadPoolExecutor.java:908)
at java.lang.Thread.run(Thread.java:662)

And ES seems to restart sometimes again and again without
intervention:

[2011-11-08 01:59:09,348][DEBUG][action.search.type ] [Pip the
Troll] [3606] Failed to execute fetch phase
org.elasticsearch.search.SearchContextMissingException: No search
context found for id [3606]
at
org.elasticsearch.search.SearchService.findContext(SearchService.java:
411)
at
org.elasticsearch.search.SearchService.executeFetchPhase(SearchService.java:
386)
at
org.elasticsearch.search.action.SearchServiceTransportAction.sendExecuteFetch(SearchServiceTransportAction.java:
314)
at
org.elasticsearch.action.search.type.TransportSearchQueryThenFetchAction
$AsyncAction.executeFetch(TransportSearchQueryThenFetchAction.java:
145)
at
org.elasticsearch.action.search.type.TransportSearchQueryThenFetchAction
$AsyncAction$2.run(TransportSearchQueryThenFetchAction.java:132)
at java.util.concurrent.ThreadPoolExecutor
$Worker.runTask(ThreadPoolExecutor.java:886)
at java.util.concurrent.ThreadPoolExecutor
$Worker.run(ThreadPoolExecutor.java:908)
at java.lang.Thread.run(Thread.java:662)
[2011-11-08 02:02:42,419][WARN ][common.jna ] Unknown
mlockall error 0
[2011-11-08 02:02:42,424][INFO ][node ] [Bengal]
{0.18.2}[28365]: initializing ...
[2011-11-08 02:02:42,427][INFO ][plugins ] [Bengal]
loaded [], sites []
[2011-11-08 02:02:43,873][INFO ][node ] [Bengal]
{0.18.2}[28365]: initialized
[2011-11-08 02:02:43,874][INFO ][node ] [Bengal]
{0.18.2}[28365]: starting ...
[2011-11-08 02:02:43,920][INFO ][transport ] [Bengal]
bound_address {inet[/0.0.0.0:9300]}, publish_address {inet[meriadec/
94.23.13.10:9300]}
[2011-11-08 02:02:46,929][INFO ][cluster.service ] [Bengal]
new_master [Bengal][P8GUsHRtRc-GAn88FELsYA][inet[meriadec/
94.23.13.10:9300]], reason: zen-disco-join (elected_as_master)
[2011-11-08 02:02:46,967][INFO ][discovery ] [Bengal]
eklablog/P8GUsHRtRc-GAn88FELsYA
[2011-11-08 02:02:47,051][INFO ][http ] [Bengal]
bound_address {inet[/0.0.0.0:9200]}, publish_address {inet[meriadec/
94.23.13.10:9200]}
[2011-11-08 02:02:47,052][INFO ][node ] [Bengal]
{0.18.2}[28365]: started
[2011-11-08 02:02:47,905][INFO ][gateway ] [Bengal]
recovered [4] indices into cluster_state
[2011-11-08 02:04:06,603][DEBUG][action.index ] [Bengal]
[eklablog][2], node[P8GUsHRtRc-GAn88FELsYA], [P], s[STARTED]: Failed
to execute [index {[eklablog][mod_html][247468], source[]}]
org.elasticsearch.ElasticSearchParseException: Failed to derive
xcontent from (offset=0, length=0): []
at
org.elasticsearch.common.xcontent.XContentFactory.xContent(XContentFactory.java:
147)
at
org.elasticsearch.index.mapper.DocumentMapper.parse(DocumentMapper.java:
430)
at
org.elasticsearch.index.mapper.DocumentMapper.parse(DocumentMapper.java:
409)
at
org.elasticsearch.index.shard.service.InternalIndexShard.prepareIndex(InternalIndexShard.java:
302)
at
org.elasticsearch.action.index.TransportIndexAction.shardOperationOnPrimary(TransportIndexAction.java:
181)
at
org.elasticsearch.action.support.replication.TransportShardReplicationOperationAction
$AsyncShardOperationAction.performOnPrimary(TransportShardReplicationOperationAction.java:
487)
at
org.elasticsearch.action.support.replication.TransportShardReplicationOperationAction
$AsyncShardOperationAction
$1.run(TransportShardReplicationOperationAction.java:400)
at java.util.concurrent.ThreadPoolExecutor
$Worker.runTask(ThreadPoolExecutor.java:886)
at java.util.concurrent.ThreadPoolExecutor
$Worker.run(ThreadPoolExecutor.java:908)
at java.lang.Thread.run(Thread.java:662)
[2011-11-08 02:12:16,600][WARN ][common.jna ] Unknown
mlockall error 0
[2011-11-08 02:12:16,604][INFO ][node ] [Wrath]
{0.18.2}[29245]: initializing ...
[2011-11-08 02:12:16,608][INFO ][plugins ] [Wrath]
loaded [], sites []
[2011-11-08 02:12:18,054][INFO ][node ] [Wrath]
{0.18.2}[29245]: initialized
[2011-11-08 02:12:18,055][INFO ][node ] [Wrath]
{0.18.2}[29245]: starting ...
[2011-11-08 02:12:18,101][INFO ][transport ] [Wrath]
bound_address {inet[/0.0.0.0:9300]}, publish_address {inet[meriadec/
94.23.13.10:9300]}
[2011-11-08 02:12:21,109][INFO ][cluster.service ] [Wrath]
new_master [Wrath][I-Ps5UZiQYOKaHakZqRw8g][inet[meriadec/
94.23.13.10:9300]], reason: zen-disco-join (elected_as_master)
[2011-11-08 02:12:21,138][INFO ][discovery ] [Wrath]
eklablog/I-Ps5UZiQYOKaHakZqRw8g
[2011-11-08 02:12:21,223][INFO ][http ] [Wrath]
bound_address {inet[/0.0.0.0:9200]}, publish_address {inet[meriadec/
94.23.13.10:9200]}
[2011-11-08 02:12:21,223][INFO ][node ] [Wrath]
{0.18.2}[29245]: started
[2011-11-08 02:12:22,248][INFO ][gateway ] [Wrath]
recovered [4] indices into cluster_state
[2011-11-08 02:30:46,460][WARN ][common.jna ] Unknown
mlockall error 0
[2011-11-08 02:30:46,464][INFO ][node ] [Warstar]
{0.18.2}[30351]: initializing ...
[2011-11-08 02:30:46,468][INFO ][plugins ] [Warstar]
loaded [], sites []
[2011-11-08 02:30:47,917][INFO ][node ] [Warstar]
{0.18.2}[30351]: initialized
[2011-11-08 02:30:47,917][INFO ][node ] [Warstar]
{0.18.2}[30351]: starting ...
[2011-11-08 02:30:47,963][INFO ][transport ] [Warstar]
bound_address {inet[/0.0.0.0:9300]}, publish_address {inet[meriadec/
94.23.13.10:9300]}
[2011-11-08 02:30:51,093][INFO ][node ] [Warstar]
{0.18.2}[30351]: started
[2011-11-08 02:30:52,001][INFO ][gateway ] [Warstar]
recovered [4] indices into cluster_state
[2011-11-08 02:54:00,009][WARN ][common.jna ] Unknown
mlockall error 0
[2011-11-08 02:54:00,013][INFO ][node ] [Starr the
Slayer] {0.18.2}[31715]: initializing ...
[2011-11-08 02:54:00,017][INFO ][plugins ] [Starr the
Slayer] loaded [], sites []
[2011-11-08 02:54:01,469][INFO ][node ] [Starr the
Slayer] {0.18.2}[31715]: initialized
[2011-11-08 02:54:01,469][INFO ][node ] [Starr the
Slayer] {0.18.2}[31715]: starting ...
[2011-11-08 02:54:01,516][INFO ][transport ] [Starr the
Slayer] bound_address {inet[/0.0.0.0:9300]}, publish_address
{inet[meriadec/94.23.13.10:9300]}
[2011-11-08 02:54:04,524][INFO ][cluster.service ] [Starr the
Slayer] new_master [Starr the Slayer][jQhaiX6MRhaZFor1FPB-jg]
[inet[meriadec/94.23.13.10:9300]], reason: zen-disco-join
(elected_as_master)
[2011-11-08 02:54:04,551][INFO ][discovery ] [Starr the
Slayer] eklablog/jQhaiX6MRhaZFor1FPB-jg
[2011-11-08 02:54:04,635][INFO ][http ] [Starr the
Slayer] bound_address {inet[/0.0.0.0:9200]}, publish_address
{inet[meriadec/94.23.13.10:9200]}
[2011-11-08 02:54:04,635][INFO ][node ] [Starr the
Slayer] {0.18.2}[31715]: started
[2011-11-08 02:54:05,613][INFO ][gateway ] [Starr the
Slayer] recovered [4] indices into cluster_state
[2011-11-08 02:56:00,649][WARN ][http.netty ] [Starr the
Slayer] Caught exception while handling client http traffic, closing
connection
java.io.IOException: Connexion ré-initialisée par le correspondant
at sun.nio.ch.FileDispatcher.read0(Native Method)
at sun.nio.ch.SocketDispatcher.read(SocketDispatcher.java:21)
at sun.nio.ch.IOUtil.readIntoNativeBuffer(IOUtil.java:202)
at sun.nio.ch.IOUtil.read(IOUtil.java:169)
at sun.nio.ch.SocketChannelImpl.read(SocketChannelImpl.java:243)
at
org.elasticsearch.common.netty.channel.socket.nio.NioWorker.read(NioWorker.java:
321)
at
org.elasticsearch.common.netty.channel.socket.nio.NioWorker.processSelectedKeys(NioWorker.java:
280)
at
org.elasticsearch.common.netty.channel.socket.nio.NioWorker.run(NioWorker.java:
200)
at
org.elasticsearch.common.netty.util.ThreadRenamingRunnable.run(ThreadRenamingRunnable.java:
108)
at org.elasticsearch.common.netty.util.internal.DeadLockProofWorker
$1.run(DeadLockProofWorker.java:44)
at java.util.concurrent.ThreadPoolExecutor
$Worker.runTask(ThreadPoolExecutor.java:886)
at java.util.concurrent.ThreadPoolExecutor
$Worker.run(ThreadPoolExecutor.java:908)
at java.lang.Thread.run(Thread.java:662)
[2011-11-08 03:05:50,114][WARN ][common.jna ] Unknown
mlockall error 0
[2011-11-08 03:05:50,119][INFO ][node ] [Golden
Oldie] {0.18.2}[554]: initializing ...
[2011-11-08 03:05:50,122][INFO ][plugins ] [Golden
Oldie] loaded [], sites []
[2011-11-08 03:05:51,568][INFO ][node ] [Golden
Oldie] {0.18.2}[554]: initialized
[2011-11-08 03:05:51,569][INFO ][node ] [Golden
Oldie] {0.18.2}[554]: starting ...
[2011-11-08 03:05:51,614][INFO ][transport ] [Golden
Oldie] bound_address {inet[/0.0.0.0:9300]}, publish_address
{inet[meriadec/94.23.13.10:9300]}
[2011-11-08 03:05:54,623][INFO ][cluster.service ] [Golden
Oldie] new_master [Golden Oldie][jK09VMmGS62LZpII6CDKSQ][inet[meriadec/
94.23.13.10:9300]], reason: zen-disco-join (elected_as_master)
[2011-11-08 03:05:54,663][INFO ][discovery ] [Golden
Oldie] eklablog/jK09VMmGS62LZpII6CDKSQ
[2011-11-08 03:05:54,747][INFO ][http ] [Golden
Oldie] bound_address {inet[/0.0.0.0:9200]}, publish_address
{inet[meriadec/94.23.13.10:9200]}
[2011-11-08 03:05:54,748][INFO ][node ] [Golden
Oldie] {0.18.2}[554]: started
[2011-11-08 03:05:55,721][INFO ][gateway ] [Golden
Oldie] recovered [4] indices into cluster_state
[2011-11-08 03:16:23,876][WARN ][common.jna ] Unknown
mlockall error 0
[2011-11-08 03:16:23,881][INFO ][node ] [Kraven
the Hunter] {0.18.2}[1345]: initializing ...
[2011-11-08 03:16:23,885][INFO ][plugins ] [Kraven
the Hunter] loaded [], sites []
[2011-11-08 03:16:25,334][INFO ][node ] [Kraven
the Hunter] {0.18.2}[1345]: initialized
[2011-11-08 03:16:25,334][INFO ][node ] [Kraven
the Hunter] {0.18.2}[1345]: starting ...
[2011-11-08 03:16:25,380][INFO ][transport ] [Kraven
the Hunter] bound_address {inet[/0.0.0.0:9300]}, publish_address
{inet[meriadec/94.23.13.10:9300]}
[2011-11-08 03:16:28,389][INFO ][cluster.service ] [Kraven
the Hunter] new_master [Kraven the Hunter][_d9OtWCkQ_e3NZ-ncuotcQ]
[inet[meriadec/94.23.13.10:9300]], reason: zen-disco-join
(elected_as_master)
[2011-11-08 03:16:28,423][INFO ][discovery ] [Kraven
the Hunter] eklablog/_d9OtWCkQ_e3NZ-ncuotcQ
[2011-11-08 03:16:28,511][INFO ][http ] [Kraven
the Hunter] bound_address {inet[/0.0.0.0:9200]}, publish_address
{inet[meriadec/94.23.13.10:9200]}
[2011-11-08 03:16:28,511][INFO ][node ] [Kraven
the Hunter] {0.18.2}[1345]: started
[2011-11-08 03:16:29,475][INFO ][gateway ] [Kraven
the Hunter] recovered [4] indices into cluster_state
[2011-11-08 03:36:34,137][WARN ][common.jna ] Unknown
mlockall error 0
[2011-11-08 03:36:34,141][INFO ][node ]
[Dragoness] {0.18.2}[2557]: initializing ...
[2011-11-08 03:36:34,145][INFO ][plugins ]
[Dragoness] loaded [], sites []
[2011-11-08 03:36:35,592][INFO ][node ]
[Dragoness] {0.18.2}[2557]: initialized
[2011-11-08 03:36:35,592][INFO ][node ]
[Dragoness] {0.18.2}[2557]: starting ...
[2011-11-08 03:36:35,638][INFO ][transport ]
[Dragoness] bound_address {inet[/0.0.0.0:9300]}, publish_address
{inet[meriadec/94.23.13.10:9300]}
[2011-11-08 03:36:38,647][INFO ][cluster.service ]
[Dragoness] new_master [Dragoness][JWxLhulPTPif66_2a0giKg]
[inet[meriadec/94.23.13.10:9300]], reason: zen-disco-join
(elected_as_master)
[2011-11-08 03:36:38,671][INFO ][discovery ]
[Dragoness] eklablog/JWxLhulPTPif66_2a0giKg
[2011-11-08 03:36:38,756][INFO ][http ]
[Dragoness] bound_address {inet[/0.0.0.0:9200]}, publish_address
{inet[meriadec/94.23.13.10:9200]}
[2011-11-08 03:36:38,757][INFO ][node ]
[Dragoness] {0.18.2}[2557]: started
[2011-11-08 03:36:39,669][INFO ][gateway ]
[Dragoness] recovered [4] indices into cluster_state
[2011-11-08 03:53:02,838][WARN ][common.jna ] Unknown
mlockall error 0
[2011-11-08 03:53:02,842][INFO ][node ] [Ghaur]
{0.18.2}[3612]: initializing ...
[2011-11-08 03:53:02,846][INFO ][plugins ] [Ghaur]
loaded [], sites []
[2011-11-08 03:53:04,294][INFO ][node ] [Ghaur]
{0.18.2}[3612]: initialized
[2011-11-08 03:53:04,294][INFO ][node ] [Ghaur]
{0.18.2}[3612]: starting ...
[2011-11-08 03:53:04,340][INFO ][transport ] [Ghaur]
bound_address {inet[/0.0.0.0:9300]}, publish_address {inet[meriadec/
94.23.13.10:9300]}
[2011-11-08 03:53:07,349][INFO ][cluster.service ] [Ghaur]
new_master [Ghaur][gGw47XfjT2ih_UcdOcScnw][inet[meriadec/
94.23.13.10:9300]], reason: zen-disco-join (elected_as_master)
[2011-11-08 03:53:07,378][INFO ][discovery ] [Ghaur]
eklablog/gGw47XfjT2ih_UcdOcScnw
[2011-11-08 03:53:07,468][INFO ][http ] [Ghaur]
bound_address {inet[/0.0.0.0:9200]}, publish_address {inet[meriadec/
94.23.13.10:9200]}
[2011-11-08 03:53:07,469][INFO ][node ] [Ghaur]
{0.18.2}[3612]: started
[2011-11-08 03:53:08,463][INFO ][gateway ] [Ghaur]
recovered [4] indices into cluster_state

Thanks in advance for your help!!

CPU problems are the hardest ones to solve... . First, can you try and run
it without the service wrapper, just to get it out of the picture? Second,
how versed are you with Java? Can you run something like VisualVM against
the process?

On Tue, Nov 8, 2011 at 4:45 PM, Godefroy compreignac@gmail.com wrote:

Hi,

First, thank you for this wonderful product!
I'm using it for search and tags on EklaBlog, a french blogs platform.

I have a problem with ES for some weeks: some minutes or hours after
start, a thread of ES takes 100% of a CPU, other threads 0%, and ES
doesn't respond anymore to any request.
Then I restart ES and it works again for some minutes...

ES is installed on a single serveur with this configuration:

network.publish_host: meriadec
cluster:
name: eklablog
path:
logs: /var/log/elasticsearch
data: /home/elasticsearch
discovery.zen.ping:
multicast.enabled: false
set.default.ES_HOME=/opt/elasticsearch
set.default.ES_MIN_MEM=1024
set.default.ES_MAX_MEM=5000

I actually have an error which occurs everytime, but I don't if it's
the cause:

[2011-11-08 00:38:52,263][WARN ][common.jna ] Unknown
mlockall error 0
[2011-11-08 00:38:52,268][INFO ][node ] [Pip the
Troll] {0.18.2}[23851]: initializing ...
[2011-11-08 00:38:52,271][INFO ][plugins ] [Pip the
Troll] loaded , sites
[2011-11-08 00:38:53,720][INFO ][node ] [Pip the
Troll] {0.18.2}[23851]: initialized
[2011-11-08 00:38:53,721][INFO ][node ] [Pip the
Troll] {0.18.2}[23851]: starting ...
[2011-11-08 00:38:53,767][INFO ][transport ] [Pip the
Troll] bound_address {inet[/0.0.0.0:9300]}, publish_address
{inet[meriadec/94.23.13.10:9300]}
[2011-11-08 00:38:56,776][INFO ][cluster.service ] [Pip the
Troll] new_master [Pip the Troll][83bg-5soRT-7QqHFEhVfmA]
[inet[meriadec/94.23.13.10:9300]], reason: zen-disco-join
(elected_as_master)
[2011-11-08 00:38:56,816][INFO ][discovery ] [Pip the
Troll] eklablog/83bg-5soRT-7QqHFEhVfmA
[2011-11-08 00:38:56,899][INFO ][http ] [Pip the
Troll] bound_address {inet[/0.0.0.0:9200]}, publish_address
{inet[meriadec/94.23.13.10:9200]}
[2011-11-08 00:38:56,900][INFO ][node ] [Pip the
Troll] {0.18.2}[23851]: started
[2011-11-08 00:38:57,745][INFO ][gateway ] [Pip the
Troll] recovered [4] indices into cluster_state
[2011-11-08 00:52:37,793][DEBUG][action.search.type ] [Pip the
Troll] [1094] Failed to execute fetch phase
org.elasticsearch.search.SearchContextMissingException: No search
context found for id [1094]
at
org.elasticsearch.search.SearchService.findContext(SearchService.java:
411)
at

org.elasticsearch.search.SearchService.executeFetchPhase(SearchService.java:
386)
at

org.elasticsearch.search.action.SearchServiceTransportAction.sendExecuteFetch(SearchServiceTransportAction.java:
314)
at
org.elasticsearch.action.search.type.TransportSearchQueryThenFetchAction
$AsyncAction.executeFetch(TransportSearchQueryThenFetchAction.java:
145)
at
org.elasticsearch.action.search.type.TransportSearchQueryThenFetchAction
$AsyncAction$2.run(TransportSearchQueryThenFetchAction.java:132)
at java.util.concurrent.ThreadPoolExecutor
$Worker.runTask(ThreadPoolExecutor.java:886)
at java.util.concurrent.ThreadPoolExecutor
$Worker.run(ThreadPoolExecutor.java:908)
at java.lang.Thread.run(Thread.java:662)
[2011-11-08 00:52:38,101][DEBUG][action.search.type ] [Pip the
Troll] [912] Failed to execute fetch phase
org.elasticsearch.search.SearchContextMissingException: No search
context found for id [912]
at
org.elasticsearch.search.SearchService.findContext(SearchService.java:
411)
at

org.elasticsearch.search.SearchService.executeFetchPhase(SearchService.java:
386)
at

org.elasticsearch.search.action.SearchServiceTransportAction.sendExecuteFetch(SearchServiceTransportAction.java:
314)
at
org.elasticsearch.action.search.type.TransportSearchQueryThenFetchAction
$AsyncAction.executeFetch(TransportSearchQueryThenFetchAction.java:
145)
at
org.elasticsearch.action.search.type.TransportSearchQueryThenFetchAction
$AsyncAction$2.run(TransportSearchQueryThenFetchAction.java:132)
at java.util.concurrent.ThreadPoolExecutor
$Worker.runTask(ThreadPoolExecutor.java:886)
at java.util.concurrent.ThreadPoolExecutor
$Worker.run(ThreadPoolExecutor.java:908)
at java.lang.Thread.run(Thread.java:662)

And I've sometimes another error:

[2011-11-08 01:49:04,063][WARN ][http.netty ] [Pip the
Troll] Caught exception while handling client http traffic, closing
connection
java.io.IOException: Relais brisé (pipe)
at sun.nio.ch.FileDispatcher.write0(Native Method)
at sun.nio.ch.SocketDispatcher.write(SocketDispatcher.java:29)
at sun.nio.ch.IOUtil.writeFromNativeBuffer(IOUtil.java:72)
at sun.nio.ch.IOUtil.write(IOUtil.java:28)
at sun.nio.ch.SocketChannelImpl.write(SocketChannelImpl.java:334)
at
org.elasticsearch.common.netty.channel.socket.nio.SocketSendBufferPool
$PooledSendBuffer.transferTo(SocketSendBufferPool.java:239)
at

org.elasticsearch.common.netty.channel.socket.nio.NioWorker.write0(NioWorker.java:
470)
at

org.elasticsearch.common.netty.channel.socket.nio.NioWorker.writeFromUserCode(NioWorker.java:
388)
at

org.elasticsearch.common.netty.channel.socket.nio.NioServerSocketPipelineSink.handleAcceptedSocket(NioServerSocketPipelineSink.java:
137)
at

org.elasticsearch.common.netty.channel.socket.nio.NioServerSocketPipelineSink.eventSunk(NioServerSocketPipelineSink.java:
76)
at org.elasticsearch.common.netty.channel.DefaultChannelPipeline
$DefaultChannelHandlerContext.sendDownstream(DefaultChannelPipeline.java:
771)
at
org.elasticsearch.common.netty.channel.Channels.write(Channels.java:
632)
at
org.elasticsearch.common.netty.channel.Channels.write(Channels.java:
593)
at

org.elasticsearch.common.netty.handler.codec.http.HttpChunkAggregator.messageReceived(HttpChunkAggregator.java:
99)
at

org.elasticsearch.common.netty.channel.SimpleChannelUpstreamHandler.handleUpstream(SimpleChannelUpstreamHandler.java:
80)
at

org.elasticsearch.common.netty.channel.DefaultChannelPipeline.sendUpstream(DefaultChannelPipeline.java:
564)
at org.elasticsearch.common.netty.channel.DefaultChannelPipeline
$DefaultChannelHandlerContext.sendUpstream(DefaultChannelPipeline.java:
783)
at

org.elasticsearch.common.netty.handler.codec.http.HttpContentDecoder.messageReceived(HttpContentDecoder.java:
104)
at

org.elasticsearch.common.netty.channel.SimpleChannelUpstreamHandler.handleUpstream(SimpleChannelUpstreamHandler.java:
80)
at

org.elasticsearch.common.netty.channel.DefaultChannelPipeline.sendUpstream(DefaultChannelPipeline.java:
564)
at org.elasticsearch.common.netty.channel.DefaultChannelPipeline
$DefaultChannelHandlerContext.sendUpstream(DefaultChannelPipeline.java:
783)
at

org.elasticsearch.common.netty.channel.Channels.fireMessageReceived(Channels.java:
302)
at

org.elasticsearch.common.netty.handler.codec.replay.ReplayingDecoder.unfoldAndFireMessageReceived(ReplayingDecoder.java:
522)
at

org.elasticsearch.common.netty.handler.codec.replay.ReplayingDecoder.callDecode(ReplayingDecoder.java:
506)
at

org.elasticsearch.common.netty.handler.codec.replay.ReplayingDecoder.messageReceived(ReplayingDecoder.java:
443)
at

org.elasticsearch.common.netty.channel.SimpleChannelUpstreamHandler.handleUpstream(SimpleChannelUpstreamHandler.java:
80)
at

org.elasticsearch.common.netty.channel.DefaultChannelPipeline.sendUpstream(DefaultChannelPipeline.java:
564)
at org.elasticsearch.common.netty.channel.DefaultChannelPipeline
$DefaultChannelHandlerContext.sendUpstream(DefaultChannelPipeline.java:
783)
at

org.elasticsearch.common.netty.OpenChannelsHandler.handleUpstream(OpenChannelsHandler.java:
65)
at

org.elasticsearch.common.netty.channel.DefaultChannelPipeline.sendUpstream(DefaultChannelPipeline.java:
564)
at

org.elasticsearch.common.netty.channel.DefaultChannelPipeline.sendUpstream(DefaultChannelPipeline.java:
559)
at

org.elasticsearch.common.netty.channel.Channels.fireMessageReceived(Channels.java:
274)
at

org.elasticsearch.common.netty.channel.Channels.fireMessageReceived(Channels.java:
261)
at

org.elasticsearch.common.netty.channel.socket.nio.NioWorker.read(NioWorker.java:
349)
at

org.elasticsearch.common.netty.channel.socket.nio.NioWorker.processSelectedKeys(NioWorker.java:
280)
at

org.elasticsearch.common.netty.channel.socket.nio.NioWorker.run(NioWorker.java:
200)
at

org.elasticsearch.common.netty.util.ThreadRenamingRunnable.run(ThreadRenamingRunnable.java:
108)
at org.elasticsearch.common.netty.util.internal.DeadLockProofWorker
$1.run(DeadLockProofWorker.java:44)
at java.util.concurrent.ThreadPoolExecutor
$Worker.runTask(ThreadPoolExecutor.java:886)
at java.util.concurrent.ThreadPoolExecutor
$Worker.run(ThreadPoolExecutor.java:908)
at java.lang.Thread.run(Thread.java:662)

And ES seems to restart sometimes again and again without
intervention:

[2011-11-08 01:59:09,348][DEBUG][action.search.type ] [Pip the
Troll] [3606] Failed to execute fetch phase
org.elasticsearch.search.SearchContextMissingException: No search
context found for id [3606]
at
org.elasticsearch.search.SearchService.findContext(SearchService.java:
411)
at

org.elasticsearch.search.SearchService.executeFetchPhase(SearchService.java:
386)
at

org.elasticsearch.search.action.SearchServiceTransportAction.sendExecuteFetch(SearchServiceTransportAction.java:
314)
at
org.elasticsearch.action.search.type.TransportSearchQueryThenFetchAction
$AsyncAction.executeFetch(TransportSearchQueryThenFetchAction.java:
145)
at
org.elasticsearch.action.search.type.TransportSearchQueryThenFetchAction
$AsyncAction$2.run(TransportSearchQueryThenFetchAction.java:132)
at java.util.concurrent.ThreadPoolExecutor
$Worker.runTask(ThreadPoolExecutor.java:886)
at java.util.concurrent.ThreadPoolExecutor
$Worker.run(ThreadPoolExecutor.java:908)
at java.lang.Thread.run(Thread.java:662)
[2011-11-08 02:02:42,419][WARN ][common.jna ] Unknown
mlockall error 0
[2011-11-08 02:02:42,424][INFO ][node ] [Bengal]
{0.18.2}[28365]: initializing ...
[2011-11-08 02:02:42,427][INFO ][plugins ] [Bengal]
loaded , sites
[2011-11-08 02:02:43,873][INFO ][node ] [Bengal]
{0.18.2}[28365]: initialized
[2011-11-08 02:02:43,874][INFO ][node ] [Bengal]
{0.18.2}[28365]: starting ...
[2011-11-08 02:02:43,920][INFO ][transport ] [Bengal]
bound_address {inet[/0.0.0.0:9300]}, publish_address {inet[meriadec/
94.23.13.10:9300]}
[2011-11-08 02:02:46,929][INFO ][cluster.service ] [Bengal]
new_master [Bengal][P8GUsHRtRc-GAn88FELsYA][inet[meriadec/
94.23.13.10:9300]], reason: zen-disco-join (elected_as_master)
[2011-11-08 02:02:46,967][INFO ][discovery ] [Bengal]
eklablog/P8GUsHRtRc-GAn88FELsYA
[2011-11-08 02:02:47,051][INFO ][http ] [Bengal]
bound_address {inet[/0.0.0.0:9200]}, publish_address {inet[meriadec/
94.23.13.10:9200]}
[2011-11-08 02:02:47,052][INFO ][node ] [Bengal]
{0.18.2}[28365]: started
[2011-11-08 02:02:47,905][INFO ][gateway ] [Bengal]
recovered [4] indices into cluster_state
[2011-11-08 02:04:06,603][DEBUG][action.index ] [Bengal]
[eklablog][2], node[P8GUsHRtRc-GAn88FELsYA], [P], s[STARTED]: Failed
to execute [index {[eklablog][mod_html][247468], source}]
org.elasticsearch.ElasticSearchParseException: Failed to derive
xcontent from (offset=0, length=0):
at

org.elasticsearch.common.xcontent.XContentFactory.xContent(XContentFactory.java:
147)
at
org.elasticsearch.index.mapper.DocumentMapper.parse(DocumentMapper.java:
430)
at
org.elasticsearch.index.mapper.DocumentMapper.parse(DocumentMapper.java:
409)
at

org.elasticsearch.index.shard.service.InternalIndexShard.prepareIndex(InternalIndexShard.java:
302)
at

org.elasticsearch.action.index.TransportIndexAction.shardOperationOnPrimary(TransportIndexAction.java:
181)
at

org.elasticsearch.action.support.replication.TransportShardReplicationOperationAction

$AsyncShardOperationAction.performOnPrimary(TransportShardReplicationOperationAction.java:
487)
at

org.elasticsearch.action.support.replication.TransportShardReplicationOperationAction
$AsyncShardOperationAction
$1.run(TransportShardReplicationOperationAction.java:400)
at java.util.concurrent.ThreadPoolExecutor
$Worker.runTask(ThreadPoolExecutor.java:886)
at java.util.concurrent.ThreadPoolExecutor
$Worker.run(ThreadPoolExecutor.java:908)
at java.lang.Thread.run(Thread.java:662)
[2011-11-08 02:12:16,600][WARN ][common.jna ] Unknown
mlockall error 0
[2011-11-08 02:12:16,604][INFO ][node ] [Wrath]
{0.18.2}[29245]: initializing ...
[2011-11-08 02:12:16,608][INFO ][plugins ] [Wrath]
loaded , sites
[2011-11-08 02:12:18,054][INFO ][node ] [Wrath]
{0.18.2}[29245]: initialized
[2011-11-08 02:12:18,055][INFO ][node ] [Wrath]
{0.18.2}[29245]: starting ...
[2011-11-08 02:12:18,101][INFO ][transport ] [Wrath]
bound_address {inet[/0.0.0.0:9300]}, publish_address {inet[meriadec/
94.23.13.10:9300]}
[2011-11-08 02:12:21,109][INFO ][cluster.service ] [Wrath]
new_master [Wrath][I-Ps5UZiQYOKaHakZqRw8g][inet[meriadec/
94.23.13.10:9300]], reason: zen-disco-join (elected_as_master)
[2011-11-08 02:12:21,138][INFO ][discovery ] [Wrath]
eklablog/I-Ps5UZiQYOKaHakZqRw8g
[2011-11-08 02:12:21,223][INFO ][http ] [Wrath]
bound_address {inet[/0.0.0.0:9200]}, publish_address {inet[meriadec/
94.23.13.10:9200]}
[2011-11-08 02:12:21,223][INFO ][node ] [Wrath]
{0.18.2}[29245]: started
[2011-11-08 02:12:22,248][INFO ][gateway ] [Wrath]
recovered [4] indices into cluster_state
[2011-11-08 02:30:46,460][WARN ][common.jna ] Unknown
mlockall error 0
[2011-11-08 02:30:46,464][INFO ][node ] [Warstar]
{0.18.2}[30351]: initializing ...
[2011-11-08 02:30:46,468][INFO ][plugins ] [Warstar]
loaded , sites
[2011-11-08 02:30:47,917][INFO ][node ] [Warstar]
{0.18.2}[30351]: initialized
[2011-11-08 02:30:47,917][INFO ][node ] [Warstar]
{0.18.2}[30351]: starting ...
[2011-11-08 02:30:47,963][INFO ][transport ] [Warstar]
bound_address {inet[/0.0.0.0:9300]}, publish_address {inet[meriadec/
94.23.13.10:9300]}
[2011-11-08 02:30:51,093][INFO ][node ] [Warstar]
{0.18.2}[30351]: started
[2011-11-08 02:30:52,001][INFO ][gateway ] [Warstar]
recovered [4] indices into cluster_state
[2011-11-08 02:54:00,009][WARN ][common.jna ] Unknown
mlockall error 0
[2011-11-08 02:54:00,013][INFO ][node ] [Starr the
Slayer] {0.18.2}[31715]: initializing ...
[2011-11-08 02:54:00,017][INFO ][plugins ] [Starr the
Slayer] loaded , sites
[2011-11-08 02:54:01,469][INFO ][node ] [Starr the
Slayer] {0.18.2}[31715]: initialized
[2011-11-08 02:54:01,469][INFO ][node ] [Starr the
Slayer] {0.18.2}[31715]: starting ...
[2011-11-08 02:54:01,516][INFO ][transport ] [Starr the
Slayer] bound_address {inet[/0.0.0.0:9300]}, publish_address
{inet[meriadec/94.23.13.10:9300]}
[2011-11-08 02:54:04,524][INFO ][cluster.service ] [Starr the
Slayer] new_master [Starr the Slayer][jQhaiX6MRhaZFor1FPB-jg]
[inet[meriadec/94.23.13.10:9300]], reason: zen-disco-join
(elected_as_master)
[2011-11-08 02:54:04,551][INFO ][discovery ] [Starr the
Slayer] eklablog/jQhaiX6MRhaZFor1FPB-jg
[2011-11-08 02:54:04,635][INFO ][http ] [Starr the
Slayer] bound_address {inet[/0.0.0.0:9200]}, publish_address
{inet[meriadec/94.23.13.10:9200]}
[2011-11-08 02:54:04,635][INFO ][node ] [Starr the
Slayer] {0.18.2}[31715]: started
[2011-11-08 02:54:05,613][INFO ][gateway ] [Starr the
Slayer] recovered [4] indices into cluster_state
[2011-11-08 02:56:00,649][WARN ][http.netty ] [Starr the
Slayer] Caught exception while handling client http traffic, closing
connection
java.io.IOException: Connexion ré-initialisée par le correspondant
at sun.nio.ch.FileDispatcher.read0(Native Method)
at sun.nio.ch.SocketDispatcher.read(SocketDispatcher.java:21)
at sun.nio.ch.IOUtil.readIntoNativeBuffer(IOUtil.java:202)
at sun.nio.ch.IOUtil.read(IOUtil.java:169)
at sun.nio.ch.SocketChannelImpl.read(SocketChannelImpl.java:243)
at

org.elasticsearch.common.netty.channel.socket.nio.NioWorker.read(NioWorker.java:
321)
at

org.elasticsearch.common.netty.channel.socket.nio.NioWorker.processSelectedKeys(NioWorker.java:
280)
at

org.elasticsearch.common.netty.channel.socket.nio.NioWorker.run(NioWorker.java:
200)
at

org.elasticsearch.common.netty.util.ThreadRenamingRunnable.run(ThreadRenamingRunnable.java:
108)
at org.elasticsearch.common.netty.util.internal.DeadLockProofWorker
$1.run(DeadLockProofWorker.java:44)
at java.util.concurrent.ThreadPoolExecutor
$Worker.runTask(ThreadPoolExecutor.java:886)
at java.util.concurrent.ThreadPoolExecutor
$Worker.run(ThreadPoolExecutor.java:908)
at java.lang.Thread.run(Thread.java:662)
[2011-11-08 03:05:50,114][WARN ][common.jna ] Unknown
mlockall error 0
[2011-11-08 03:05:50,119][INFO ][node ] [Golden
Oldie] {0.18.2}[554]: initializing ...
[2011-11-08 03:05:50,122][INFO ][plugins ] [Golden
Oldie] loaded , sites
[2011-11-08 03:05:51,568][INFO ][node ] [Golden
Oldie] {0.18.2}[554]: initialized
[2011-11-08 03:05:51,569][INFO ][node ] [Golden
Oldie] {0.18.2}[554]: starting ...
[2011-11-08 03:05:51,614][INFO ][transport ] [Golden
Oldie] bound_address {inet[/0.0.0.0:9300]}, publish_address
{inet[meriadec/94.23.13.10:9300]}
[2011-11-08 03:05:54,623][INFO ][cluster.service ] [Golden
Oldie] new_master [Golden Oldie][jK09VMmGS62LZpII6CDKSQ][inet[meriadec/
94.23.13.10:9300]], reason: zen-disco-join (elected_as_master)
[2011-11-08 03:05:54,663][INFO ][discovery ] [Golden
Oldie] eklablog/jK09VMmGS62LZpII6CDKSQ
[2011-11-08 03:05:54,747][INFO ][http ] [Golden
Oldie] bound_address {inet[/0.0.0.0:9200]}, publish_address
{inet[meriadec/94.23.13.10:9200]}
[2011-11-08 03:05:54,748][INFO ][node ] [Golden
Oldie] {0.18.2}[554]: started
[2011-11-08 03:05:55,721][INFO ][gateway ] [Golden
Oldie] recovered [4] indices into cluster_state
[2011-11-08 03:16:23,876][WARN ][common.jna ] Unknown
mlockall error 0
[2011-11-08 03:16:23,881][INFO ][node ] [Kraven
the Hunter] {0.18.2}[1345]: initializing ...
[2011-11-08 03:16:23,885][INFO ][plugins ] [Kraven
the Hunter] loaded , sites
[2011-11-08 03:16:25,334][INFO ][node ] [Kraven
the Hunter] {0.18.2}[1345]: initialized
[2011-11-08 03:16:25,334][INFO ][node ] [Kraven
the Hunter] {0.18.2}[1345]: starting ...
[2011-11-08 03:16:25,380][INFO ][transport ] [Kraven
the Hunter] bound_address {inet[/0.0.0.0:9300]}, publish_address
{inet[meriadec/94.23.13.10:9300]}
[2011-11-08 03:16:28,389][INFO ][cluster.service ] [Kraven
the Hunter] new_master [Kraven the Hunter][_d9OtWCkQ_e3NZ-ncuotcQ]
[inet[meriadec/94.23.13.10:9300]], reason: zen-disco-join
(elected_as_master)
[2011-11-08 03:16:28,423][INFO ][discovery ] [Kraven
the Hunter] eklablog/_d9OtWCkQ_e3NZ-ncuotcQ
[2011-11-08 03:16:28,511][INFO ][http ] [Kraven
the Hunter] bound_address {inet[/0.0.0.0:9200]}, publish_address
{inet[meriadec/94.23.13.10:9200]}
[2011-11-08 03:16:28,511][INFO ][node ] [Kraven
the Hunter] {0.18.2}[1345]: started
[2011-11-08 03:16:29,475][INFO ][gateway ] [Kraven
the Hunter] recovered [4] indices into cluster_state
[2011-11-08 03:36:34,137][WARN ][common.jna ] Unknown
mlockall error 0
[2011-11-08 03:36:34,141][INFO ][node ]
[Dragoness] {0.18.2}[2557]: initializing ...
[2011-11-08 03:36:34,145][INFO ][plugins ]
[Dragoness] loaded , sites
[2011-11-08 03:36:35,592][INFO ][node ]
[Dragoness] {0.18.2}[2557]: initialized
[2011-11-08 03:36:35,592][INFO ][node ]
[Dragoness] {0.18.2}[2557]: starting ...
[2011-11-08 03:36:35,638][INFO ][transport ]
[Dragoness] bound_address {inet[/0.0.0.0:9300]}, publish_address
{inet[meriadec/94.23.13.10:9300]}
[2011-11-08 03:36:38,647][INFO ][cluster.service ]
[Dragoness] new_master [Dragoness][JWxLhulPTPif66_2a0giKg]
[inet[meriadec/94.23.13.10:9300]], reason: zen-disco-join
(elected_as_master)
[2011-11-08 03:36:38,671][INFO ][discovery ]
[Dragoness] eklablog/JWxLhulPTPif66_2a0giKg
[2011-11-08 03:36:38,756][INFO ][http ]
[Dragoness] bound_address {inet[/0.0.0.0:9200]}, publish_address
{inet[meriadec/94.23.13.10:9200]}
[2011-11-08 03:36:38,757][INFO ][node ]
[Dragoness] {0.18.2}[2557]: started
[2011-11-08 03:36:39,669][INFO ][gateway ]
[Dragoness] recovered [4] indices into cluster_state
[2011-11-08 03:53:02,838][WARN ][common.jna ] Unknown
mlockall error 0
[2011-11-08 03:53:02,842][INFO ][node ] [Ghaur]
{0.18.2}[3612]: initializing ...
[2011-11-08 03:53:02,846][INFO ][plugins ] [Ghaur]
loaded , sites
[2011-11-08 03:53:04,294][INFO ][node ] [Ghaur]
{0.18.2}[3612]: initialized
[2011-11-08 03:53:04,294][INFO ][node ] [Ghaur]
{0.18.2}[3612]: starting ...
[2011-11-08 03:53:04,340][INFO ][transport ] [Ghaur]
bound_address {inet[/0.0.0.0:9300]}, publish_address {inet[meriadec/
94.23.13.10:9300]}
[2011-11-08 03:53:07,349][INFO ][cluster.service ] [Ghaur]
new_master [Ghaur][gGw47XfjT2ih_UcdOcScnw][inet[meriadec/
94.23.13.10:9300]], reason: zen-disco-join (elected_as_master)
[2011-11-08 03:53:07,378][INFO ][discovery ] [Ghaur]
eklablog/gGw47XfjT2ih_UcdOcScnw
[2011-11-08 03:53:07,468][INFO ][http ] [Ghaur]
bound_address {inet[/0.0.0.0:9200]}, publish_address {inet[meriadec/
94.23.13.10:9200]}
[2011-11-08 03:53:07,469][INFO ][node ] [Ghaur]
{0.18.2}[3612]: started
[2011-11-08 03:53:08,463][INFO ][gateway ] [Ghaur]
recovered [4] indices into cluster_state

Thanks in advance for your help!!

Without looking too much on the stack traces in your log: are you using any
custom analyzers (more specifically decompounding)? If so, you might (also)
be hitting this
issue: https://github.com/elasticsearch/elasticsearch/issues/1449, which
might cause similar CPU-usage behavior as you described.