You are viewing a plain text version of this content. The canonical link for it is here.
Posted to notifications@iotdb.apache.org by "Jialin Qiao (Jira)" <ji...@apache.org> on 2022/10/05 03:05:00 UTC
[jira] [Assigned] (IOTDB-4521) ERROR o.a.t.s.AbstractNonblockingServer$FrameBuffer:356 - Read a frame size of 562223808, which is bigger than the maximum allowable buffer size for ALL connections
[ https://issues.apache.org/jira/browse/IOTDB-4521?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ]
Jialin Qiao reassigned IOTDB-4521:
----------------------------------
Assignee: Jinrui Zhang (was: Jialin Qiao)
> ERROR o.a.t.s.AbstractNonblockingServer$FrameBuffer:356 - Read a frame size of 562223808, which is bigger than the maximum allowable buffer size for ALL connections
> --------------------------------------------------------------------------------------------------------------------------------------------------------------------
>
> Key: IOTDB-4521
> URL: https://issues.apache.org/jira/browse/IOTDB-4521
> Project: Apache IoTDB
> Issue Type: Bug
> Components: mpp-cluster
> Affects Versions: 0.14.0-SNAPSHOT
> Reporter: 刘珍
> Assignee: Jinrui Zhang
> Priority: Major
> Attachments: image-2022-09-26-10-04-30-709.png, image-2022-09-26-10-05-57-896.png, ip72_datanode_logs.tar.gz, more_ts.conf
>
>
> m_0922_0d65058
> 3副本3C3D
> schemaregion ：RatisConsensus
> dataregion ：MultiLeaderConsensus
> DEVICE_NUMBER=600
> SENSOR_NUMBER=50000
> CLIENT_NUMBER=100
> （5万dev，600sensor /dev 全部数据写入成功）600dev，5万序列/dev，写入 datanode error ：
> 2022-09-24 00:00:02,666 [pool-25-IoTDB-ClientRPC-Processor-142$20220923_155931_09082_3.1.0] ERROR {color:#DE350B}*o.a.i.d.m.p.s.FragmentInstanceDispatcherImpl:179 - null*{color}
> 2022-09-24 00:00:02,685 [Thread-18] ERROR {color:#DE350B}*o.a.t.s.AbstractNonblockingServer$FrameBuffer:356 - Read a frame size of 722859150, which is bigger than the maximum allowable buffer size for ALL connections.*{color}
> 2022-09-24 00:00:02,726 [pool-25-IoTDB-ClientRPC-Processor-83$20220923_155931_09083_3.1.0] ERROR o.a.i.d.m.p.s.FragmentInstanceDispatcherImpl:179 - null
> 2022-09-24 00:00:03,501 [pool-25-IoTDB-ClientRPC-Processor-23$20220923_155932_09084_3.1.0] ERROR o.a.i.d.m.p.s.FragmentInstanceDispatcherImpl:179 - null
> 2022-09-24 00:00:05,059 [pool-25-IoTDB-ClientRPC-Processor-113$20220923_155934_09085_3.1.0] ERROR o.a.i.d.m.p.s.FragmentInstanceDispatcherImpl:179 - null
> 2022-09-24 00:00:05,138 [Thread-18] ERROR o.a.t.s.AbstractNonblockingServer$FrameBuffer:356 - Read a frame size of 803176833, which is bigger than the maximum allowable buffer size for ALL connections.
> 2022-09-24 00:00:07,448 [pool-25-IoTDB-ClientRPC-Processor-47$20220923_155935_09086_3.1.0] ERROR o.a.i.d.m.p.s.FragmentInstanceDispatcherImpl:179 - null
> 2022-09-24 00:00:08,220 [pool-25-IoTDB-ClientRPC-Processor-59$20220923_155937_09087_3.1.0] ERROR o.a.i.d.m.p.s.FragmentInstanceDispatcherImpl:179 - null
> 2022-09-24 00:00:09,320 [Thread-18] ERROR o.a.t.s.AbstractNonblockingServer$FrameBuffer:356 - Read a frame size of 669314043, which is bigger than the maximum allowable buffer size for ALL connections.
> 2022-09-24 00:00:12,375 [Thread-18] ERROR o.a.t.s.AbstractNonblockingServer$FrameBuffer:356 - Read a frame size of 803176825, which is bigger than the maximum allowable buffer size for ALL connections.
> 测试环境
> 1. 192.168.10.72/73/74 48CPU 384GB
> bm在71
> 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
> connection_timeout_ms=36000000
> DataNode
> MAX_HEAP_SIZE="256G"
> MAX_DIRECT_MEMORY_SIZE="32G"
> connection_timeout_ms=36000000
> max_connection_for_internal_service=300
> enable_timed_flush_seq_memtable=true
> seq_memtable_flush_interval_in_ms=3600000
> seq_memtable_flush_check_interval_in_ms=600000
> enable_timed_flush_unseq_memtable=true
> unseq_memtable_flush_interval_in_ms=3600000
> unseq_memtable_flush_check_interval_in_ms=600000
> max_waiting_time_when_insert_blocked=3600000
> query_timeout_threshold=36000000
> 2. bm配置见附件
> 600dev，5万序列/dev, bm结果
> !image-2022-09-26-10-04-30-709.png!
> 5万dev，600sensor 全部数据写入成功
> !image-2022-09-26-10-05-57-896.png!
> 3. ip72 datanode log见附件
--
This message was sent by Atlassian Jira
(v8.20.10#820010)