[ 
https://issues.apache.org/jira/browse/IOTDB-4331?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=17608185#comment-17608185
 ] 

Jinrui Zhang commented on IOTDB-4331:
-------------------------------------

It is caused by write rejection from MultiLeaderConsensus. I will add the error 
status code to make this response more generic.

> [ ERROR message ] ERROR o.a.i.d.m.p.s.FragmentInstanceDispatcherImpl:286 - 
> unknown error message
> ------------------------------------------------------------------------------------------------
>
>                 Key: IOTDB-4331
>                 URL: https://issues.apache.org/jira/browse/IOTDB-4331
>             Project: Apache IoTDB
>          Issue Type: Bug
>          Components: mpp-cluster
>    Affects Versions: 0.14.0-SNAPSHOT
>            Reporter: 刘珍
>            Assignee: Jinrui Zhang
>            Priority: Major
>         Attachments: 1000_sess.conf, log-all-20220904.1.log.gz
>
>
> m_0902_41f74a5 , 3副本3C3D,
> 报错信息不明确。
> grep "20220904_035643_15454_3" log-all-20220904.1.log 
> 2022-09-04 11:56:43,561 [20220904_035643_15454_3.1.0-1836] INFO  
> o.a.i.c.m.MultiLeaderServerImpl:121 - [Throttle Down] index:223535, 
> safeIndex:138017 
> 2022-09-04 11:57:13,672 [20220904_035643_15454_3.1.0-1836] ERROR 
> o.a.i.d.m.p.s.FragmentInstanceDispatcherImpl:286 -{color:#DE350B}* unknown 
> error message *{color}
> 2022-09-04 11:57:13,673 [20220904_035643_15454_3-2126] INFO  
> o.a.i.d.m.p.e.QueryExecution:156 - release resource because Query State is: 
> FAILED 
> 复现流程:
> 1. 192.168.10.72/73/74  48核384GB
> benchmark在ip71
> 2. 数据库配置
> ConfigNode
> MAX_HEAP_SIZE="8G"
> schema_region_consensus_protocol_class=org.apache.iotdb.consensus.ratis.RatisConsensus
> data_region_consensus_protocol_class=org.apache.iotdb.consensus.multileader.MultiLeaderConsensus
> schema_replication_factor=3
> data_replication_factor=3
> DataNode
> MAX_HEAP_SIZE="256G"
> MAX_DIRECT_MEMORY_SIZE="32G"
> max_connection_for_internal_service=1100
> max_waiting_time_when_insert_blocked=3600000
> query_timeout_threshold=3600000
> 2. benchmark配置见附件
> 连ip72
> 1000用户并发
> 3. log见附件(ip72)



--
This message was sent by Atlassian Jira
(v8.20.10#820010)

Reply via email to