You are viewing a plain text version of this content. The canonical link for it is here.
Posted to issues@drill.apache.org by "wtf (Jira)" <ji...@apache.org> on 2021/12/01 12:38:00 UTC
[jira] [Updated] (DRILL-8059) Fragment starts late
[ https://issues.apache.org/jira/browse/DRILL-8059?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ]
wtf updated DRILL-8059:
-----------------------
Description:
One of the minor fragment starts late sometimes. All fragments transterred between the same node pair take muck longer time during that period.
Three profiles attached. The slow communication happens around 11:45:18~11:45:38 between node1 and node2.
On node1:
drillbit.log.1:2021-11-30 11:45:25,258 [1e5a61ab-1b3e-8956-ad52-6786ccece9e2:foreman] INFO o.a.d.e.work.foreman.FragmentsRunner - Sending remote fragments to node: node2, Fragments: [1e5a61ab-1b3e-8956-ad52-6786ccece9e2:1:17]
On node2:
drillbit.log.3:2021-11-30 11:45:47,269 [BitServer-10] INFO o.a.d.e.w.b.ControlMessageHandler - 1e5a61ab-1b3e-8956-ad52-6786ccece9e2:1:17 remote fragment received
We can see that it takes more than 22 seconds to send the fragment.
was:
One of the minor fragment starts late sometimes. All fragments transterred between the same node pair take muck longer time during that period.
Three profiles attached. The slow communication happens around 11:45:18~11:45:38 between node explorersha-49-7146.ET15.alipay.com and node explorersha-49-6019.ET15.alipay.com.
On node explorersha-49-7146.ET15.alipay.com:
drillbit.log.1:2021-11-30 11:45:25,258 [1e5a61ab-1b3e-8956-ad52-6786ccece9e2:foreman] INFO o.a.d.e.work.foreman.FragmentsRunner - Sending remote fragments to node: explorersha-49-6019.ET15.alipay.com, Fragments: [1e5a61ab-1b3e-8956-ad52-6786ccece9e2:1:17]
On node explorersha-49-6019.ET15.alipay.com:
drillbit.log.3:2021-11-30 11:45:47,269 [BitServer-10] INFO o.a.d.e.w.b.ControlMessageHandler - 1e5a61ab-1b3e-8956-ad52-6786ccece9e2:1:17 remote fragment received
We can see that it takes more than 22 seconds to send the fragment.
> Fragment starts late
> --------------------
>
> Key: DRILL-8059
> URL: https://issues.apache.org/jira/browse/DRILL-8059
> Project: Apache Drill
> Issue Type: Bug
> Components: Execution - RPC
> Affects Versions: 1.13.0
> Reporter: wtf
> Priority: Major
> Attachments: 1e5a6196-f2c1-46d5-7126-1d9f1aada180.json, 1e5a61ab-1b3e-8956-ad52-6786ccece9e2.json, 1e5a61b1-256b-3b57-f76a-8b2b5f8a72c9.json
>
>
> One of the minor fragment starts late sometimes. All fragments transterred between the same node pair take muck longer time during that period.
> Three profiles attached. The slow communication happens around 11:45:18~11:45:38 between node1 and node2.
> On node1:
> drillbit.log.1:2021-11-30 11:45:25,258 [1e5a61ab-1b3e-8956-ad52-6786ccece9e2:foreman] INFO o.a.d.e.work.foreman.FragmentsRunner - Sending remote fragments to node: node2, Fragments: [1e5a61ab-1b3e-8956-ad52-6786ccece9e2:1:17]
> On node2:
> drillbit.log.3:2021-11-30 11:45:47,269 [BitServer-10] INFO o.a.d.e.w.b.ControlMessageHandler - 1e5a61ab-1b3e-8956-ad52-6786ccece9e2:1:17 remote fragment received
> We can see that it takes more than 22 seconds to send the fragment.
--
This message was sent by Atlassian Jira
(v8.20.1#820001)