CPU High load

Hi Team,

I am using ES-1.3.7(version) In sometimes it causes very high load on particular node what can we do for this type of issue.

I Checked with logs too there is no abnormal logs at all.

Please help on this.Thanks in advance.

::: [NODE_NAME][NODE_ID][elasticseasrch][inet[XXX__IP__XXX]]{master=false}

102.2% (510.8ms out of 500ms) cpu usage by thread 'elasticsearch[NODE_NAME][management][T#3]'
4/10 snapshots sharing following 30 elements
sun.reflect.Reflection.getCallerClass(Native Method)
java.lang.Class.getDeclaredFields(Class.java:1805)
org.apache.lucene.util.RamUsageEstimator.shallowSizeOfInstance(RamUsageEstimator.java:382)
org.apache.lucene.util.RamUsageEstimator.shallowSizeOf(RamUsageEstimator.java:360)
org.apache.lucene.util.fst.Outputs.ramBytesUsed(Outputs.java:104)
org.apache.lucene.util.fst.ByteSequenceOutputs.ramBytesUsed(ByteSequenceOutputs.java:152)
org.apache.lucene.util.fst.ByteSequenceOutputs.ramBytesUsed(ByteSequenceOutputs.java:34)
org.apache.lucene.util.fst.FST.ramBytesUsed(FST.java:409)
org.apache.lucene.util.fst.FST.ramBytesUsed(FST.java:427)102.2% (510.8ms out of 500ms) cpu usage by thread 'elasticsearch[NODE_NAME][management][T#3]'
org.apache.lucene.codecs.blocktree.FieldReader.ramBytesUsed(FieldReader.java:187)
org.apache.lucene.codecs.blocktree.BlockTreeTermsReader.ramBytesUsed(BlockTreeTermsReader.java:308)
org.elasticsearch.index.codec.postingsformat.BloomFilterPostingsFormat$BloomFilteredFieldsProducer.ramBytesUsed(BloomFilterPostingsFormat.java:201)
org.apache.lucene.codecs.perfield.PerFieldPostingsFormat$FieldsReader.ramBytesUsed(PerFieldPostingsFormat.java:238)
org.apache.lucene.index.SegmentCoreReaders.ramBytesUsed(SegmentCoreReaders.java:226)
org.apache.lucene.index.SegmentReader.ramBytesUsed(SegmentReader.java:620)
org.elasticsearch.index.engine.internal.InternalEngine.getReaderRamBytesUsed(InternalEngine.java:1152)
org.elasticsearch.index.engine.internal.InternalEngine.segmentsStats(InternalEngine.java:1164)
org.elasticsearch.index.shard.service.InternalIndexShard.segmentStats(InternalIndexShard.java:540)
org.elasticsearch.action.admin.indices.stats.CommonStats.(CommonStats.java:166)
org.elasticsearch.action.admin.indices.stats.ShardStats.(ShardStats.java:49)
org.elasticsearch.indices.InternalIndicesService.stats(InternalIndicesService.java:209)
org.elasticsearch.node.service.NodeService.stats(NodeService.java:156)
org.elasticsearch.action.admin.cluster.node.stats.TransportNodesStatsAction.nodeOperation(TransportNodesStatsAction.java:95)
org.elasticsearch.action.admin.cluster.node.stats.TransportNodesStatsAction.nodeOperation(TransportNodesStatsAction.java:43)
org.elasticsearch.action.support.nodes.TransportNodesOperationAction$NodeTransportHandler.messageReceived(TransportNodesOperationAction.java:277)
org.elasticsearch.action.support.nodes.TransportNodesOperationAction$NodeTransportHandler.messageReceived(TransportNodesOperationAction.java:268)
org.elasticsearch.transport.netty.MessageChannelHandler$RequestHandler.run(MessageChannelHandler.java:275)
java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1145)
java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:615)
java.lang.Thread.run(Thread.java:745)
2/10 snapshots sharing following 11 elements
org.elasticsearch.action.admin.indices.stats.ShardStats.(ShardStats.java:49)
org.elasticsearch.indices.InternalIndicesService.stats(InternalIndicesService.java:209)
org.elasticsearch.node.service.NodeService.stats(NodeService.java:156)
org.elasticsearch.action.admin.cluster.node.stats.TransportNodesStatsAction.nodeOperation(TransportNodesStatsAction.java:95)
org.elasticsearch.action.admin.cluster.node.stats.TransportNodesStatsAction.nodeOperation(TransportNodesStatsAction.java:43)
org.elasticsearch.action.support.nodes.TransportNodesOperationAction$NodeTransportHandler.messageReceived(TransportNodesOperationAction.java:277)
org.elasticsearch.action.support.nodes.TransportNodesOperationAction$NodeTransportHandler.messageReceived(TransportNodesOperationAction.java:268)
org.elasticsearch.transport.netty.MessageChannelHandler$RequestHandler.run(MessageChannelHandler.java:275)
java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1145)
java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:615)
java.lang.Thread.run(Thread.java:745)
4/10 snapshots sharing following 2 elements
java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:615)
java.lang.Thread.run(Thread.java:745)

That is a very old version of Elasticsearch. You should really consider upgrading.

It seems the node is very busy with node management. Do you have a very large number of indices and/or shards in the cluster? Do you have large mappings and/or mappings that are frequently updated dynamically?

Thanks.

Yes, we are work with UPGRADATION So, we do reindex to own index.

Indices: 16
Shards: 80

No, we disabled the dynamic mapping already.

How can we fix the node management

Can you provide the full output of the cluster stats API to give us a better idea about the state of the cluster?

{
"timestamp": 1513328024278,
"cluster_name": "es",
"status": "green",
"indices": {
"count": 16,
"shards": {
"total": 165,
"primaries": 80,
"replication": 1.0625,
"index": {
"shards": {
"min": 10,
"max": 15,
"avg": 10.3125
},
"primaries": {
"min": 5,
"max": 5,
"avg": 5.0
},
"replication": {
"min": 1.0,
"max": 2.0,
"avg": 1.0625
}
}
},
"docs": {
"count": 163556517,
"deleted": 21877877
},
"store": {
"size_in_bytes": 457061600407,
"throttle_time_in_millis": 709241
},
"fielddata": {
"memory_size_in_bytes": 2750871813,
"evictions": 1671603
},
"filter_cache": {
"memory_size_in_bytes": 1811523164,
"evictions": 37689953
},
"id_cache": {
"memory_size_in_bytes": 0
},
"completion": {
"size_in_bytes": 0
},
"segments": {
"count": 2043,
"memory_in_bytes": 9052378464,
"index_writer_memory_in_bytes": 1384276,
"version_map_memory_in_bytes": 680
},
"percolate": {
"total": 1412351,
"time_in_millis": 521584959,
"current": 0,
"memory_size_in_bytes": -1,
"memory_size": "-1b",
"queries": 10623
}
},
"nodes": {
"count": {
"total": 8,
"master_only": 3,
"data_only": 5,
"master_data": 0,
"client": 0
},
"versions": [
"1.3.7"
],
"os": {
"available_processors": 256,
"mem": {
"total_in_bytes": 2163187679232
},
"cpu": [
{
"vendor": "Intel",
"model": "Xeon",
"mhz": 3000,
"total_cores": 32,
"total_sockets": 1,
"cores_per_socket": 32,
"cache_size_in_bytes": 20480,
"count": 8
}
]
},
"process": {
"cpu": {
"percent": 534
},
"open_file_descriptors": {
"min": 846,
"max": 2690,
"avg": 1887
}
},
"jvm": {
"max_uptime_in_millis": 6551538023,
"versions": [
{
"version": "1.7.0_65",
"vm_name": "Java HotSpot(TM) 64-Bit Server VM",
"vm_version": "24.65-b04",
"vm_vendor": "Oracle Corporation",
"count": 8
}
],
"mem": {
"heap_used_in_bytes": 28083885288,
"heap_max_in_bytes": 46170898432
},
"threads": 2985
},
"fs": {
"total_in_bytes": 38981224026112,
"free_in_bytes": 18850588155904,
"available_in_bytes": 17080571420672,
"disk_reads": 187516718,
"disk_writes": 5414807503,
"disk_io_op": 5602324221,
"disk_read_size_in_bytes": 11904572949504,
"disk_write_size_in_bytes": 147740532974080,
"disk_io_size_in_bytes": 159645105923584,
"disk_queue": "1.4",
"disk_service_time": "0.1"
},
"plugins": [
{
"name": "migration",
"version": "NA",
"description": "No description found.",
"url": "/_plugin/migration/",
"jvm": false,
"site": true
},
{
"name": "kopf",
"version": "1.6.1",
"description": "kopf - simple web administration tool for ElasticSearch",
"url": "/_plugin/kopf/",
"jvm": false,
"site": true
},
{
"name": "cloud-aws",
"version": "2.3.0",
"description": "Cloud AWS Plugin",
"jvm": true,
"site": false
},
{
"name": "head",
"version": "NA",
"description": "No description found.",
"url": "/_plugin/head/",
"jvm": false,
"site": true
}
]
}
}

Do you have any non-default configuration in your Elasticsearch configuration?

we use the default configuration on Elasticsearch.

Team, Please help on this.

This topic was automatically closed 28 days after the last reply. New replies are no longer allowed.