Created
October 14, 2021 10:06
-
-
Save bunste/5fcc43a4d6bc37527b8a0a8eaf0aaf85 to your computer and use it in GitHub Desktop.
Log files for elasticsearch crash
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
[2021-10-13T14:15:08,671][TRACE][o.e.c.s.ClusterApplierService] [es-node05-a] connecting to nodes of cluster state with version 5429193 | |
[2021-10-13T14:15:08,671][DEBUG][o.e.c.s.ClusterApplierService] [es-node05-a] applying settings from cluster state with version 5429193 | |
[2021-10-13T14:15:08,671][DEBUG][o.e.c.s.ClusterApplierService] [es-node05-a] apply cluster state with version 5429193 | |
[2021-10-13T14:15:08,671][TRACE][o.e.c.s.ClusterApplierService] [es-node05-a] calling [org.elasticsearch.repositories.RepositoriesService@4a0995e7] with change to version [5429193] | |
[2021-10-13T14:15:08,671][TRACE][o.e.c.s.ClusterApplierService] [es-node05-a] calling [org.elasticsearch.indices.cluster.IndicesClusterStateService@c418f17] with change to version [5429193] | |
[2021-10-13T14:17:09,136][INFO ][o.e.i.r.PeerRecoveryTargetService] [es-node05-a] recovery of [events-2021.10.05][0] from [{es-node06-a}{R00-RxIuQGud85biVet1XA}{rPoopo8EQQCMkkaXnIu0Xg}{192.168.200.185}{192.168.200.185:19301}{cdhilrstw}{ml.machine_memory=67085619200, ml.max_open_jobs=20, xpack.installed=true, disks=ssd, machine=192.168.6.185, transform.node=true}] interrupted by network disconnect, will retry in [5s]; cause: [[es-node05-a][192.168.200.184:19301][internal:index/shard/recovery/file_chunk] disconnected] | |
[2021-10-13T14:17:09,185][INFO ][o.e.i.r.PeerRecoveryTargetService] [es-node05-a] recovery of [groot_news_bucket_23_v3][0] from [{es-node03-a}{O_DOHlu7QqChJNdkgZHtbQ}{6F2-uSzeSka08lRdaE2VIw}{192.168.200.182}{192.168.200.182:19301}{cdhilrstw}{ml.machine_memory=135073177600, ml.max_open_jobs=20, xpack.installed=true, disks=ssd, machine=192.168.6.182, transform.node=true}] interrupted by network disconnect, will retry in [5s]; cause: [[es-node05-a][192.168.200.184:19301][internal:index/shard/recovery/file_chunk] disconnected] | |
[2021-10-13T14:17:11,607][INFO ][o.e.c.c.Coordinator ] [es-node05-a] master node [{es-master02}{RLYFvvrgSCymDsgMDbx-dw}{LVDIbVeiQ4qtVEg8CaWq6w}{192.168.200.52}{192.168.200.52:9300}{ilmr}{ml.machine_memory=8376066048, ml.max_open_jobs=20, xpack.installed=true, transform.node=false}] failed, restarting discovery | |
org.elasticsearch.ElasticsearchException: node [{es-master02}{RLYFvvrgSCymDsgMDbx-dw}{LVDIbVeiQ4qtVEg8CaWq6w}{192.168.200.52}{192.168.200.52:9300}{ilmr}{ml.machine_memory=8376066048, ml.max_open_jobs=20, xpack.installed=true, transform.node=false}] failed [3] consecutive checks | |
at org.elasticsearch.cluster.coordination.LeaderChecker$CheckScheduler$1.handleException(LeaderChecker.java:293) ~[elasticsearch-7.10.1.jar:7.10.1] | |
at org.elasticsearch.transport.TransportService$ContextRestoreResponseHandler.handleException(TransportService.java:1181) ~[elasticsearch-7.10.1.jar:7.10.1] | |
at org.elasticsearch.transport.TransportService$ContextRestoreResponseHandler.handleException(TransportService.java:1181) ~[elasticsearch-7.10.1.jar:7.10.1] | |
at org.elasticsearch.transport.InboundHandler.lambda$handleException$3(InboundHandler.java:277) ~[elasticsearch-7.10.1.jar:7.10.1] | |
at org.elasticsearch.common.util.concurrent.EsExecutors$DirectExecutorService.execute(EsExecutors.java:224) ~[elasticsearch-7.10.1.jar:7.10.1] | |
at org.elasticsearch.transport.InboundHandler.handleException(InboundHandler.java:275) ~[elasticsearch-7.10.1.jar:7.10.1] | |
at org.elasticsearch.transport.InboundHandler.handlerResponseError(InboundHandler.java:267) ~[elasticsearch-7.10.1.jar:7.10.1] | |
at org.elasticsearch.transport.InboundHandler.messageReceived(InboundHandler.java:131) ~[elasticsearch-7.10.1.jar:7.10.1] | |
at org.elasticsearch.transport.InboundHandler.inboundMessage(InboundHandler.java:89) ~[elasticsearch-7.10.1.jar:7.10.1] | |
at org.elasticsearch.transport.TcpTransport.inboundMessage(TcpTransport.java:700) ~[elasticsearch-7.10.1.jar:7.10.1] | |
at org.elasticsearch.transport.InboundPipeline.forwardFragments(InboundPipeline.java:142) ~[elasticsearch-7.10.1.jar:7.10.1] | |
at org.elasticsearch.transport.InboundPipeline.doHandleBytes(InboundPipeline.java:117) ~[elasticsearch-7.10.1.jar:7.10.1] | |
at org.elasticsearch.transport.InboundPipeline.handleBytes(InboundPipeline.java:82) ~[elasticsearch-7.10.1.jar:7.10.1] | |
at org.elasticsearch.transport.netty4.Netty4MessageChannelHandler.channelRead(Netty4MessageChannelHandler.java:74) ~[?:?] | |
at io.netty.channel.AbstractChannelHandlerContext.invokeChannelRead(AbstractChannelHandlerContext.java:379) ~[?:?] | |
at io.netty.channel.AbstractChannelHandlerContext.invokeChannelRead(AbstractChannelHandlerContext.java:365) ~[?:?] | |
at io.netty.channel.AbstractChannelHandlerContext.fireChannelRead(AbstractChannelHandlerContext.java:357) ~[?:?] | |
at io.netty.handler.logging.LoggingHandler.channelRead(LoggingHandler.java:271) ~[?:?] | |
at io.netty.channel.AbstractChannelHandlerContext.invokeChannelRead(AbstractChannelHandlerContext.java:379) ~[?:?] | |
at io.netty.channel.AbstractChannelHandlerContext.invokeChannelRead(AbstractChannelHandlerContext.java:365) ~[?:?] | |
at io.netty.channel.AbstractChannelHandlerContext.fireChannelRead(AbstractChannelHandlerContext.java:357) ~[?:?] | |
at io.netty.channel.DefaultChannelPipeline$HeadContext.channelRead(DefaultChannelPipeline.java:1410) ~[?:?] | |
at io.netty.channel.AbstractChannelHandlerContext.invokeChannelRead(AbstractChannelHandlerContext.java:379) ~[?:?] | |
at io.netty.channel.AbstractChannelHandlerContext.invokeChannelRead(AbstractChannelHandlerContext.java:365) ~[?:?] | |
at io.netty.channel.DefaultChannelPipeline.fireChannelRead(DefaultChannelPipeline.java:919) ~[?:?] | |
at io.netty.channel.nio.AbstractNioByteChannel$NioByteUnsafe.read(AbstractNioByteChannel.java:163) ~[?:?] | |
at io.netty.channel.nio.NioEventLoop.processSelectedKey(NioEventLoop.java:714) ~[?:?] | |
at io.netty.channel.nio.NioEventLoop.processSelectedKeysPlain(NioEventLoop.java:615) ~[?:?] | |
at io.netty.channel.nio.NioEventLoop.processSelectedKeys(NioEventLoop.java:578) ~[?:?] | |
at io.netty.channel.nio.NioEventLoop.run(NioEventLoop.java:493) ~[?:?] | |
at io.netty.util.concurrent.SingleThreadEventExecutor$4.run(SingleThreadEventExecutor.java:989) ~[?:?] | |
at io.netty.util.internal.ThreadExecutorMap$2.run(ThreadExecutorMap.java:74) ~[?:?] | |
at java.lang.Thread.run(Thread.java:829) [?:?] | |
Caused by: org.elasticsearch.transport.RemoteTransportException: [es-master02][192.168.200.52:9300][internal:coordination/fault_detection/leader_check] | |
Caused by: org.elasticsearch.cluster.coordination.CoordinationStateRejectedException: rejecting leader check since [{es-node05-a}{KEWUUnwASICujt430nUhOA}{0nN2CmrJT5Wsape0a_OxgA}{192.168.200.184}{192.168.200.184:19301}{cdhilrstw}{ml.machine_memory=67185217536, ml.max_open_jobs=20, xpack.installed=true, disks=ssd, machine=192.168.6.184, transform.node=true}] has been removed from the cluster |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
# Ansible managed | |
node.name: es-node05-a | |
node.attr.machine: 192.168.6.184 | |
node.attr.disks: ssd | |
cluster.name: wilma_van_der_heel | |
node.master: false | |
node.data: true | |
http.port: 19201 | |
http.host: | |
- 192.168.6.184 | |
- 127.0.0.1 | |
transport.port: 19301 | |
transport.host: | |
- 192.168.200.184 | |
- 127.0.0.1 | |
# Don't put replicas on the same physical host (works together with node.attr.machine) | |
cluster.routing.allocation.awareness.attributes: machine | |
# Disable swapping | |
bootstrap.memory_lock: false # our data nodes have no swap space configured and don't need mlockall | |
# For security, don't allow delete operation with wildcards | |
action.destructive_requires_name: true | |
http.cors.enabled: true | |
http.cors.allow-origin: "*" | |
http.max_initial_line_length: 8kb | |
discovery.seed_hosts: ["192.168.200.51:9300", "192.168.200.52:9300", "192.168.200.53:9300"] | |
path.data: | |
- /var/lib/elasticsearch/es-node05-a/1 | |
- /var/lib/elasticsearch/es-node05-a/2 | |
- /var/lib/elasticsearch/es-node05-a/3 | |
- /var/lib/elasticsearch/es-node05-a/4 | |
- /var/lib/elasticsearch/es-node05-a/5 | |
- /var/lib/elasticsearch/es-node05-a/6 | |
path.logs: /var/log/elasticsearch/es-node05-a | |
gateway.recover_after_time: 5m | |
gateway.recover_after_master_nodes: 2 | |
gateway.recover_after_data_nodes: 3 | |
gateway.expected_master_nodes: 3 | |
gateway.expected_data_nodes: 6 | |
# Performance improvements | |
indices.recovery.max_bytes_per_sec: 100mb | |
cluster.routing.allocation.node_concurrent_recoveries: 4 | |
cluster.routing.allocation.cluster_concurrent_rebalance: 8 | |
cluster.routing.allocation.enable: all | |
# Joining queries requires to use a lot of terms | |
indices.query.bool.max_clause_count: 100000 | |
# Allow regular expressions for update_by_query via Painless | |
# https://www.elastic.co/guide/en/elasticsearch/painless/6.7/painless-examples.html | |
script.painless.regex.enabled: true | |
search.max_buckets: 1000000 |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
2021-10-14T11:03:30,026][INFO ][o.e.c.c.C.CoordinatorPublication] [es-master02] after [9.9s] publication of cluster state version [5430424] is still waiting for {es-node05-a}{AcV5mJL5T-SPk4LiV7x2qA}{IFo3Hlz0QjaPjhlXc3xfmQ}{192.168.200.184}{192.168.200.184:19301}{cdhilrstw}{ml.machine_memory=67185217536, ml.max_open_jobs=20, xpack.installed=true, disks=ssd, machine=192.168.6.184, transform.node=true} [SENT_APPLY_COMMIT] | |
[2021-10-14T11:03:50,053][WARN ][o.e.c.c.C.CoordinatorPublication] [es-master02] after [30s] publication of cluster state version [5430424] is still waiting for {es-node05-a}{AcV5mJL5T-SPk4LiV7x2qA}{IFo3Hlz0QjaPjhlXc3xfmQ}{192.168.200.184}{192.168.200.184:19301}{cdhilrstw}{ml.machine_memory=67185217536, ml.max_open_jobs=20, xpack.installed=true, disks=ssd, machine=192.168.6.184, transform.node=true} [SENT_APPLY_COMMIT] | |
[2021-10-14T11:04:12,298][INFO ][o.e.m.j.JvmGcMonitorService] [es-master02] [gc][23585102] overhead, spent [299ms] collecting in the last [1s] | |
[2021-10-14T11:04:42,444][INFO ][o.e.m.j.JvmGcMonitorService] [es-master02] [gc][23585132] overhead, spent [311ms] collecting in the last [1s] | |
[2021-10-14T11:04:53,449][INFO ][o.e.m.j.JvmGcMonitorService] [es-master02] [gc][23585143] overhead, spent [312ms] collecting in the last [1s] | |
[2021-10-14T11:05:19,461][INFO ][o.e.m.j.JvmGcMonitorService] [es-master02] [gc][23585169] overhead, spent [253ms] collecting in the last [1s] | |
[2021-10-14T11:05:20,053][WARN ][o.e.c.c.LagDetector ] [es-master02] node [{es-node05-a}{AcV5mJL5T-SPk4LiV7x2qA}{IFo3Hlz0QjaPjhlXc3xfmQ}{192.168.200.184}{192.168.200.184:19301}{cdhilrstw}{ml.machine_memory=67185217536, ml.max_open_jobs=20, xpack.installed=true, disks=ssd, machine=192.168.6.184, transform.node=true}] is lagging at cluster state version [5430423], although publication of cluster state version [5430424] completed [1.5m] ago | |
[2021-10-14T11:05:23,455][INFO ][o.e.c.c.C.CoordinatorPublication] [es-master02] after [10.1s] publication of cluster state version [5430425] is still waiting for {es-node05-a}{AcV5mJL5T-SPk4LiV7x2qA}{IFo3Hlz0QjaPjhlXc3xfmQ}{192.168.200.184}{192.168.200.184:19301}{cdhilrstw}{ml.machine_memory=67185217536, ml.max_open_jobs=20, xpack.installed=true, disks=ssd, machine=192.168.6.184, transform.node=true} [SENT_APPLY_COMMIT] | |
[2021-10-14T11:05:23,528][INFO ][o.e.m.j.JvmGcMonitorService] [es-master02] [gc][23585173] overhead, spent [316ms] collecting in the last [1s] | |
[2021-10-14T11:05:33,556][INFO ][o.e.m.j.JvmGcMonitorService] [es-master02] [gc][23585183] overhead, spent [266ms] collecting in the last [1s] | |
[2021-10-14T11:05:43,504][WARN ][o.e.c.c.C.CoordinatorPublication] [es-master02] after [30.1s] publication of cluster state version [5430425] is still waiting for {es-node05-a}{AcV5mJL5T-SPk4LiV7x2qA}{IFo3Hlz0QjaPjhlXc3xfmQ}{192.168.200.184}{192.168.200.184:19301}{cdhilrstw}{ml.machine_memory=67185217536, ml.max_open_jobs=20, xpack.installed=true, disks=ssd, machine=192.168.6.184, transform.node=true} [SENT_APPLY_COMMIT] | |
[2021-10-14T11:05:43,676][INFO ][o.e.c.s.MasterService ] [es-master02] node-left[{es-node05-a}{AcV5mJL5T-SPk4LiV7x2qA}{IFo3Hlz0QjaPjhlXc3xfmQ}{192.168.200.184}{192.168.200.184:19301}{cdhilrstw}{ml.machine_memory=67185217536, ml.max_open_jobs=20, xpack.installed=true, disks=ssd, machine=192.168.6.184, transform.node=true} reason: lagging], term: 9, version: 5430426, delta: removed {{es-node05-a}{AcV5mJL5T-SPk4LiV7x2qA}{IFo3Hlz0QjaPjhlXc3xfmQ}{192.168.200.184}{192.168.200.184:19301}{cdhilrstw}{ml.machine_memory=67185217536, ml.max_open_jobs=20, xpack.installed=true, disks=ssd, machine=192.168.6.184, transform.node=true}} | |
[2021-10-14T11:05:43,896][INFO ][o.e.c.s.ClusterApplierService] [es-master02] removed {{es-node05-a}{AcV5mJL5T-SPk4LiV7x2qA}{IFo3Hlz0QjaPjhlXc3xfmQ}{192.168.200.184}{192.168.200.184:19301}{cdhilrstw}{ml.machine_memory=67185217536, ml.max_open_jobs=20, xpack.installed=true, disks=ssd, machine=192.168.6.184, transform.node=true}}, term: 9, version: 5430426, reason: Publication{term=9, version=5430426} | |
[2021-10-14T11:05:43,927][INFO ][o.e.c.r.DelayedAllocationService] [es-master02] scheduling reroute for delayed shards in [59.5s] (15 delayed shards) | |
[2021-10-14T11:05:44,016][WARN ][o.e.c.r.a.AllocationService] [es-master02] [keyword_statistics-2021.10][0] marking unavailable shards as stale: [Icrrqj16T5iMn4JtLlUGtw] | |
[2021-10-14T11:05:46,744][INFO ][o.e.c.s.MasterService ] [es-master02] node-join[{es-node05-a}{AcV5mJL5T-SPk4LiV7x2qA}{IFo3Hlz0QjaPjhlXc3xfmQ}{192.168.200.184}{192.168.200.184:19301}{cdhilrstw}{ml.machine_memory=67185217536, ml.max_open_jobs=20, xpack.installed=true, disks=ssd, machine=192.168.6.184, transform.node=true} join existing leader], term: 9, version: 5430429, delta: added {{es-node05-a}{AcV5mJL5T-SPk4LiV7x2qA}{IFo3Hlz0QjaPjhlXc3xfmQ}{192.168.200.184}{192.168.200.184:19301}{cdhilrstw}{ml.machine_memory=67185217536, ml.max_open_jobs=20, xpack.installed=true, disks=ssd, machine=192.168.6.184, transform.node=true}} | |
[2021-10-14T11:05:56,919][INFO ][o.e.c.c.C.CoordinatorPublication] [es-master02] after [10.1s] publication of cluster state version [5430429] is still waiting for {es-node05-a}{AcV5mJL5T-SPk4LiV7x2qA}{IFo3Hlz0QjaPjhlXc3xfmQ}{192.168.200.184}{192.168.200.184:19301}{cdhilrstw}{ml.machine_memory=67185217536, ml.max_open_jobs=20, xpack.installed=true, disks=ssd, machine=192.168.6.184, transform.node=true} [SENT_APPLY_COMMIT] | |
[2021-10-14T11:06:16,919][INFO ][o.e.c.s.ClusterApplierService] [es-master02] added {{es-node05-a}{AcV5mJL5T-SPk4LiV7x2qA}{IFo3Hlz0QjaPjhlXc3xfmQ}{192.168.200.184}{192.168.200.184:19301}{cdhilrstw}{ml.machine_memory=67185217536, ml.max_open_jobs=20, xpack.installed=true, disks=ssd, machine=192.168.6.184, transform.node=true}}, term: 9, version: 5430429, reason: Publication{term=9, version=5430429} | |
[2021-10-14T11:06:17,007][WARN ][o.e.c.c.C.CoordinatorPublication] [es-master02] after [30.2s] publication of cluster state version [5430429] is still waiting for {es-node05-a}{AcV5mJL5T-SPk4LiV7x2qA}{IFo3Hlz0QjaPjhlXc3xfmQ}{192.168.200.184}{192.168.200.184:19301}{cdhilrstw}{ml.machine_memory=67185217536, ml.max_open_jobs=20, xpack.installed=true, disks=ssd, machine=192.168.6.184, transform.node=true} [SENT_APPLY_COMMIT] | |
[2021-10-14T11:06:17,109][WARN ][o.e.c.r.a.AllocationService] [es-master02] [groot_news_bucket_18_v3][0] marking unavailable shards as stale: [yJohWFMyRNisYU7tJ1Cp5g] | |
[2021-10-14T11:06:27,180][INFO ][o.e.c.c.C.CoordinatorPublication] [es-master02] after [10s] publication of cluster state version [5430430] is still waiting for {es-node05-a}{AcV5mJL5T-SPk4LiV7x2qA}{IFo3Hlz0QjaPjhlXc3xfmQ}{192.168.200.184}{192.168.200.184:19301}{cdhilrstw}{ml.machine_memory=67185217536, ml.max_open_jobs=20, xpack.installed=true, disks=ssd, machine=192.168.6.184, transform.node=true} [SENT_APPLY_COMMIT] | |
[2021-10-14T11:06:32,957][INFO ][o.e.m.j.JvmGcMonitorService] [es-master02] [gc][23585242] overhead, spent [289ms] collecting in the last [1s] | |
[2021-10-14T11:06:43,962][INFO ][o.e.m.j.JvmGcMonitorService] [es-master02] [gc][23585253] overhead, spent [351ms] collecting in the last [1s] | |
[2021-10-14T11:06:47,213][WARN ][o.e.c.c.C.CoordinatorPublication] [es-master02] after [30s] publication of cluster state version [5430430] is still waiting for {es-node05-a}{AcV5mJL5T-SPk4LiV7x2qA}{IFo3Hlz0QjaPjhlXc3xfmQ}{192.168.200.184}{192.168.200.184:19301}{cdhilrstw}{ml.machine_memory=67185217536, ml.max_open_jobs=20, xpack.installed=true, disks=ssd, machine=192.168.6.184, transform.node=true} [SENT_APPLY_COMMIT] | |
[2021-10-14T11:06:51,965][INFO ][o.e.m.j.JvmGcMonitorService] [es-master02] [gc][23585261] overhead, spent [263ms] collecting in the last [1s] | |
[2021-10-14T11:06:57,358][INFO ][o.e.c.c.C.CoordinatorPublication] [es-master02] after [10.1s] publication of cluster state version [5430431] is still waiting for {es-node05-a}{AcV5mJL5T-SPk4LiV7x2qA}{IFo3Hlz0QjaPjhlXc3xfmQ}{192.168.200.184}{192.168.200.184:19301}{cdhilrstw}{ml.machine_memory=67185217536, ml.max_open_jobs=20, xpack.installed=true, disks=ssd, machine=192.168.6.184, transform.node=true} [SENT_APPLY_COMMIT] | |
[2021-10-14T11:06:59,968][INFO ][o.e.m.j.JvmGcMonitorService] [es-master02] [gc][23585269] overhead, spent [282ms] collecting in the last [1s] | |
[2021-10-14T11:07:02,969][INFO ][o.e.m.j.JvmGcMonitorService] [es-master02] [gc][23585272] overhead, spent [284ms] collecting in the last [1s] | |
[2021-10-14T11:07:17,390][WARN ][o.e.c.c.C.CoordinatorPublication] [es-master02] after [30s] publication of cluster state version [5430431] is still waiting for {es-node05-a}{AcV5mJL5T-SPk4LiV7x2qA}{IFo3Hlz0QjaPjhlXc3xfmQ}{192.168.200.184}{192.168.200.184:19301}{cdhilrstw}{ml.machine_memory=67185217536, ml.max_open_jobs=20, xpack.installed=true, disks=ssd, machine=192.168.6.184, transform.node=true} [SENT_APPLY_COMMIT] | |
[2021-10-14T11:07:27,418][INFO ][o.e.c.c.C.CoordinatorPublication] [es-master02] after [10.1s] publication of cluster state version [5430432] is still waiting for {es-node05-a}{AcV5mJL5T-SPk4LiV7x2qA}{IFo3Hlz0QjaPjhlXc3xfmQ}{192.168.200.184}{192.168.200.184:19301}{cdhilrstw}{ml.machine_memory=67185217536, ml.max_open_jobs=20, xpack.installed=true, disks=ssd, machine=192.168.6.184, transform.node=true} [SENT_APPLY_COMMIT] | |
[2021-10-14T11:07:47,007][WARN ][o.e.c.c.LagDetector ] [es-master02] node [{es-node05-a}{AcV5mJL5T-SPk4LiV7x2qA}{IFo3Hlz0QjaPjhlXc3xfmQ}{192.168.200.184}{192.168.200.184:19301}{cdhilrstw}{ml.machine_memory=67185217536, ml.max_open_jobs=20, xpack.installed=true, disks=ssd, machine=192.168.6.184, transform.node=true}] is lagging at cluster state version [0], although publication of cluster state version [5430429] completed [1.5m] ago | |
[2021-10-14T11:07:47,032][INFO ][o.e.m.j.JvmGcMonitorService] [es-master02] [gc][23585316] overhead, spent [304ms] collecting in the last [1s] | |
[2021-10-14T11:07:47,441][WARN ][o.e.c.c.C.CoordinatorPublication] [es-master02] after [30.1s] publication of cluster state version [5430432] is still waiting for {es-node05-a}{AcV5mJL5T-SPk4LiV7x2qA}{IFo3Hlz0QjaPjhlXc3xfmQ}{192.168.200.184}{192.168.200.184:19301}{cdhilrstw}{ml.machine_memory=67185217536, ml.max_open_jobs=20, xpack.installed=true, disks=ssd, machine=192.168.6.184, transform.node=true} [SENT_APPLY_COMMIT] | |
[2021-10-14T11:07:47,504][INFO ][o.e.c.s.MasterService ] [es-master02] node-left[{es-node05-a}{AcV5mJL5T-SPk4LiV7x2qA}{IFo3Hlz0QjaPjhlXc3xfmQ}{192.168.200.184}{192.168.200.184:19301}{cdhilrstw}{ml.machine_memory=67185217536, ml.max_open_jobs=20, xpack.installed=true, disks=ssd, machine=192.168.6.184, transform.node=true} reason: lagging], term: 9, version: 5430433, delta: removed {{es-node05-a}{AcV5mJL5T-SPk4LiV7x2qA}{IFo3Hlz0QjaPjhlXc3xfmQ}{192.168.200.184}{192.168.200.184:19301}{cdhilrstw}{ml.machine_memory=67185217536, ml.max_open_jobs=20, xpack.installed=true, disks=ssd, machine=192.168.6.184, transform.node=true}} | |
[2021-10-14T11:07:47,864][INFO ][o.e.c.s.ClusterApplierService] [es-master02] removed {{es-node05-a}{AcV5mJL5T-SPk4LiV7x2qA}{IFo3Hlz0QjaPjhlXc3xfmQ}{192.168.200.184}{192.168.200.184:19301}{cdhilrstw}{ml.machine_memory=67185217536, ml.max_open_jobs=20, xpack.installed=true, disks=ssd, machine=192.168.6.184, transform.node=true}}, term: 9, version: 5430433, reason: Publication{term=9, version=5430433} | |
[2021-10-14T11:07:47,895][INFO ][o.e.c.r.DelayedAllocationService] [es-master02] scheduling reroute for delayed shards in [59.5s] (4 delayed shards) | |
[2021-10-14T11:07:47,896][WARN ][o.e.c.r.a.AllocationService] [es-master02] [events-long-term-2017.11-v2][0] marking unavailable shards as stale: [LTaHQEUXT4eAWF_wIkeheA] | |
[2021-10-14T11:07:47,896][WARN ][o.e.c.r.a.AllocationService] [es-master02] [news-2023.17][0] marking unavailable shards as stale: [dvAibW4WRYiHc1xzEUiIlw] | |
[2021-10-14T11:07:47,896][WARN ][o.e.c.r.a.AllocationService] [es-master02] [news-2021.46][1] marking unavailable shards as stale: [NTBo9qWtQ9mUrt6T2JSIrA] | |
[2021-10-14T11:07:48,116][WARN ][o.e.c.r.a.AllocationService] [es-master02] [events-long-term-2019.10][0] marking unavailable shards as stale: [HueqjVwgSpGNNSvFQHCi1Q] | |
[2021-10-14T11:07:48,116][WARN ][o.e.c.r.a.AllocationService] [es-master02] [news-2023.25][0] marking unavailable shards as stale: [CaGPoZlGTRm7XpKMGZIQBQ] | |
[2021-10-14T11:07:49,040][WARN ][o.e.c.r.a.AllocationService] [es-master02] [prnews_news-2021.03][0] marking unavailable shards as stale: [iGuGI5Z6QEiD6shX-eJOgA] | |
[2021-10-14T11:07:49,474][WARN ][o.e.c.r.a.AllocationService] [es-master02] [news-2022.44][0] marking unavailable shards as stale: [MVai_gOOSSyGIRpycMznqg] | |
[2021-10-14T11:07:49,474][WARN ][o.e.c.r.a.AllocationService] [es-master02] [news-2023.35][1] marking unavailable shards as stale: [x_WzXOVZTKa-Z5Jwv82i5A] | |
[2021-10-14T11:07:50,200][INFO ][o.e.c.s.MasterService ] [es-master02] node-join[{es-node05-a}{AcV5mJL5T-SPk4LiV7x2qA}{IFo3Hlz0QjaPjhlXc3xfmQ}{192.168.200.184}{192.168.200.184:19301}{cdhilrstw}{ml.machine_memory=67185217536, ml.max_open_jobs=20, xpack.installed=true, disks=ssd, machine=192.168.6.184, transform.node=true} join existing leader], term: 9, version: 5430443, delta: added {{es-node05-a}{AcV5mJL5T-SPk4LiV7x2qA}{IFo3Hlz0QjaPjhlXc3xfmQ}{192.168.200.184}{192.168.200.184:19301}{cdhilrstw}{ml.machine_memory=67185217536, ml.max_open_jobs=20, xpack.installed=true, disks=ssd, machine=192.168.6.184, transform.node=true}} | |
[2021-10-14T11:08:00,324][INFO ][o.e.c.c.C.CoordinatorPublication] [es-master02] after [10s] publication of cluster state version [5430443] is still waiting for {es-node05-a}{AcV5mJL5T-SPk4LiV7x2qA}{IFo3Hlz0QjaPjhlXc3xfmQ}{192.168.200.184}{192.168.200.184:19301}{cdhilrstw}{ml.machine_memory=67185217536, ml.max_open_jobs=20, xpack.installed=true, disks=ssd, machine=192.168.6.184, transform.node=true} [SENT_APPLY_COMMIT] | |
[2021-10-14T11:08:13,212][INFO ][o.e.m.j.JvmGcMonitorService] [es-master02] [gc][23585342] overhead, spent [295ms] collecting in the last [1s] | |
[2021-10-14T11:08:20,324][INFO ][o.e.c.s.ClusterApplierService] [es-master02] added {{es-node05-a}{AcV5mJL5T-SPk4LiV7x2qA}{IFo3Hlz0QjaPjhlXc3xfmQ}{192.168.200.184}{192.168.200.184:19301}{cdhilrstw}{ml.machine_memory=67185217536, ml.max_open_jobs=20, xpack.installed=true, disks=ssd, machine=192.168.6.184, transform.node=true}}, term: 9, version: 5430443, reason: Publication{term=9, version=5430443} | |
[2021-10-14T11:08:20,377][WARN ][o.e.c.c.C.CoordinatorPublication] [es-master02] after [29.9s] publication of cluster state version [5430443] is still waiting for {es-node05-a}{AcV5mJL5T-SPk4LiV7x2qA}{IFo3Hlz0QjaPjhlXc3xfmQ}{192.168.200.184}{192.168.200.184:19301}{cdhilrstw}{ml.machine_memory=67185217536, ml.max_open_jobs=20, xpack.installed=true, disks=ssd, machine=192.168.6.184, transform.node=true} [SENT_APPLY_COMMIT] | |
[2021-10-14T11:08:22,298][WARN ][o.e.c.NodeConnectionsService] [es-master02] failed to connect to {es-node05-a}{AcV5mJL5T-SPk4LiV7x2qA}{IFo3Hlz0QjaPjhlXc3xfmQ}{192.168.200.184}{192.168.200.184:19301}{cdhilrstw}{ml.machine_memory=67185217536, ml.max_open_jobs=20, xpack.installed=true, disks=ssd, machine=192.168.6.184, transform.node=true} (tried [1] times) | |
org.elasticsearch.transport.ConnectTransportException: [es-node05-a][192.168.200.184:19301] connect_exception | |
at org.elasticsearch.transport.TcpTransport$ChannelsConnectedListener.onFailure(TcpTransport.java:978) ~[elasticsearch-7.10.1.jar:7.10.1] | |
at org.elasticsearch.action.ActionListener.lambda$toBiConsumer$2(ActionListener.java:198) ~[elasticsearch-7.10.1.jar:7.10.1] | |
at org.elasticsearch.common.concurrent.CompletableContext.lambda$addListener$0(CompletableContext.java:42) ~[elasticsearch-core-7.10.1.jar:7.10.1] | |
at java.util.concurrent.CompletableFuture.uniWhenComplete(CompletableFuture.java:859) ~[?:?] | |
at java.util.concurrent.CompletableFuture$UniWhenComplete.tryFire(CompletableFuture.java:837) ~[?:?] | |
at java.util.concurrent.CompletableFuture.postComplete(CompletableFuture.java:506) ~[?:?] | |
at java.util.concurrent.CompletableFuture.completeExceptionally(CompletableFuture.java:2088) ~[?:?] | |
at org.elasticsearch.common.concurrent.CompletableContext.completeExceptionally(CompletableContext.java:57) ~[elasticsearch-core-7.10.1.jar:7.10.1] | |
at org.elasticsearch.transport.netty4.Netty4TcpChannel.lambda$addListener$0(Netty4TcpChannel.java:68) ~[?:?] | |
at io.netty.util.concurrent.DefaultPromise.notifyListener0(DefaultPromise.java:577) ~[?:?] | |
at io.netty.util.concurrent.DefaultPromise.notifyListeners0(DefaultPromise.java:570) ~[?:?] | |
at io.netty.util.concurrent.DefaultPromise.notifyListenersNow(DefaultPromise.java:549) ~[?:?] | |
at io.netty.util.concurrent.DefaultPromise.notifyListeners(DefaultPromise.java:490) ~[?:?] | |
at io.netty.util.concurrent.DefaultPromise.setValue0(DefaultPromise.java:615) ~[?:?] | |
at io.netty.util.concurrent.DefaultPromise.setFailure0(DefaultPromise.java:608) ~[?:?] | |
at io.netty.util.concurrent.DefaultPromise.tryFailure(DefaultPromise.java:117) ~[?:?] | |
at io.netty.channel.nio.AbstractNioChannel$AbstractNioUnsafe.fulfillConnectPromise(AbstractNioChannel.java:321) ~[?:?] | |
at io.netty.channel.nio.AbstractNioChannel$AbstractNioUnsafe.finishConnect(AbstractNioChannel.java:337) ~[?:?] | |
at io.netty.channel.nio.NioEventLoop.processSelectedKey(NioEventLoop.java:702) ~[?:?] | |
at io.netty.channel.nio.NioEventLoop.processSelectedKeysPlain(NioEventLoop.java:615) ~[?:?] | |
at io.netty.channel.nio.NioEventLoop.processSelectedKeys(NioEventLoop.java:578) ~[?:?] | |
at io.netty.channel.nio.NioEventLoop.run(NioEventLoop.java:493) ~[?:?] | |
at io.netty.util.concurrent.SingleThreadEventExecutor$4.run(SingleThreadEventExecutor.java:989) ~[?:?] | |
at io.netty.util.internal.ThreadExecutorMap$2.run(ThreadExecutorMap.java:74) ~[?:?] | |
at java.lang.Thread.run(Thread.java:834) [?:?] | |
Caused by: io.netty.channel.AbstractChannel$AnnotatedConnectException: Connection refused: 192.168.200.184/192.168.200.184:19301 | |
Caused by: java.net.ConnectException: Connection refused | |
at sun.nio.ch.SocketChannelImpl.checkConnect(Native Method) ~[?:?] | |
at sun.nio.ch.SocketChannelImpl.finishConnect(SocketChannelImpl.java:779) ~[?:?] | |
at io.netty.channel.socket.nio.NioSocketChannel.doFinishConnect(NioSocketChannel.java:330) ~[?:?] | |
at io.netty.channel.nio.AbstractNioChannel$AbstractNioUnsafe.finishConnect(AbstractNioChannel.java:334) ~[?:?] | |
... 7 more | |
[2021-10-14T11:08:22,633][INFO ][o.e.c.s.MasterService ] [es-master02] node-left[{es-node05-a}{AcV5mJL5T-SPk4LiV7x2qA}{IFo3Hlz0QjaPjhlXc3xfmQ}{192.168.200.184}{192.168.200.184:19301}{cdhilrstw}{ml.machine_memory=67185217536, ml.max_open_jobs=20, xpack.installed=true, disks=ssd, machine=192.168.6.184, transform.node=true} reason: disconnected], term: 9, version: 5430445, delta: removed {{es-node05-a}{AcV5mJL5T-SPk4LiV7x2qA}{IFo3Hlz0QjaPjhlXc3xfmQ}{192.168.200.184}{192.168.200.184:19301}{cdhilrstw}{ml.machine_memory=67185217536, ml.max_open_jobs=20, xpack.installed=true, disks=ssd, machine=192.168.6.184, transform.node=true}} | |
[2021-10-14T11:08:22,774][INFO ][o.e.c.s.ClusterApplierService] [es-master02] removed {{es-node05-a}{AcV5mJL5T-SPk4LiV7x2qA}{IFo3Hlz0QjaPjhlXc3xfmQ}{192.168.200.184}{192.168.200.184:19301}{cdhilrstw}{ml.machine_memory=67185217536, ml.max_open_jobs=20, xpack.installed=true, disks=ssd, machine=192.168.6.184, transform.node=true}}, term: 9, version: 5430445, reason: Publication{term=9, version=5430445} | |
[2021-10-14T11:08:22,815][INFO ][o.e.c.r.DelayedAllocationService] [es-master02] scheduling reroute for delayed shards in [59.5s] (4 delayed shards) |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
# Ansible managed | |
node.name: es-master02 | |
cluster.name: wilma_van_der_heel | |
node.master: true | |
node.data: false | |
http.port: 9200 | |
http.host: | |
- 192.168.6.52 | |
- 127.0.0.1 | |
transport.port: 9300 | |
transport.host: | |
- 192.168.200.52 | |
- 127.0.0.1 | |
# Don't put replicas on the same physical host (works together with node.attr.machine) | |
cluster.routing.allocation.awareness.attributes: machine | |
# Disable swapping | |
bootstrap.memory_lock: true | |
# For security, don't allow delete operation with wildcards | |
action.destructive_requires_name: true | |
http.cors.enabled: true | |
http.cors.allow-origin: "*" | |
http.max_initial_line_length: 8kb | |
discovery.seed_hosts: ["192.168.200.51:9300", "192.168.200.52:9300", "192.168.200.53:9300"] | |
path.data: | |
- /var/lib/elasticsearch/es-master02/1 | |
path.logs: /var/log/elasticsearch/es-master02 | |
gateway.recover_after_time: 5m | |
gateway.recover_after_master_nodes: 2 | |
gateway.recover_after_data_nodes: 3 | |
gateway.expected_master_nodes: 3 | |
gateway.expected_data_nodes: 6 | |
# Performance improvements | |
indices.recovery.max_bytes_per_sec: 100mb | |
cluster.routing.allocation.node_concurrent_recoveries: 4 | |
cluster.routing.allocation.cluster_concurrent_rebalance: 8 | |
cluster.routing.allocation.enable: all | |
# Joining queries requires to use a lot of terms | |
indices.query.bool.max_clause_count: 100000 | |
# Allow regular expressions for update_by_query via Painless | |
# https://www.elastic.co/guide/en/elasticsearch/painless/6.7/painless-examples.html | |
script.painless.regex.enabled: true | |
search.max_buckets: 65535 |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment