[
https://issues.apache.org/jira/browse/SPARK-27505?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=16820951#comment-16820951
]
Mike Chan commented on SPARK-27505:
-----------------------------------
Table desc extended result:
Statistics |24452111 bytes
> autoBroadcastJoinThreshold including bigger table
> -------------------------------------------------
>
> Key: SPARK-27505
> URL: https://issues.apache.org/jira/browse/SPARK-27505
> Project: Spark
> Issue Type: Question
> Components: PySpark
> Affects Versions: 2.3.1
> Environment: Hive table with Spark 2.3.1 on Azure, using Azure
> storage as storage layer
> Reporter: Mike Chan
> Priority: Major
> Attachments: explain_plan.txt
>
>
> I'm on a case that when certain table being exposed to broadcast join, the
> query will eventually failed with remote block error.
>
> Firstly. We set the spark.sql.autoBroadcastJoinThreshold to 10MB, namely
> 10485760
> !https://mail.google.com/mail/u/1?ui=2&ik=6f09461656&attid=0.0.2&permmsgid=msg-a:r2073778291349183964&th=16a2fd58ea74551c&view=fimg&sz=s0-l75-ft&attbid=ANGjdJ96l-PZQKRrU2lSlUA7MGbz1DAK62y0fMFOG07rfgI3oXkalm4An9eHtd6hX3hsKDd9EJK46cGTaqj_qKVrzs7xLyJgvx8XHuu36HSSfBtxW9OnrckzikIDRPI&disp=emb&realattid=ii_jumg5jxd1|width=542,height=66!
>
> Then we proceed to perform query. In the SQL plan, we found that one table
> that is 25MB in size is broadcast as well.
>
> !https://mail.google.com/mail/u/1?ui=2&ik=6f09461656&attid=0.0.1&permmsgid=msg-a:r2073778291349183964&th=16a2fd58ea74551c&view=fimg&sz=s0-l75-ft&attbid=ANGjdJ_Fx_sEOI2n4yYfOn0gCUYqFYMDrxsSzd-S9ehtl67Imi87NN3y8cCFUOrHwKYO3MTfi3LVCIGg7J9jEuqnlqa76pvrUaAzEKSUm9VtBoH-Zsf9qepJiS4NKLE&disp=emb&realattid=ii_jumg53fq0|width=227,height=542!
>
> Also in desc extended the table is 24452111 bytes. It is a Hive table. We
> always ran into error when this table being broadcast. Below is the sample
> error
>
> Caused by: java.io.IOException: org.apache.spark.SparkException: corrupt
> remote block broadcast_477_piece0 of broadcast_477: 298778625 != -992055931
> at org.apache.spark.util.Utils$.tryOrIOException(Utils.scala:1350) at
> org.apache.spark.broadcast.TorrentBroadcast.readBroadcastBlock(TorrentBroadcast.scala:207)
> at
> org.apache.spark.broadcast.TorrentBroadcast._value$lzycompute(TorrentBroadcast.scala:66)
> at
> org.apache.spark.broadcast.TorrentBroadcast._value(TorrentBroadcast.scala:66)
> at
> org.apache.spark.broadcast.TorrentBroadcast.getValue(TorrentBroadcast.scala:96)
>
> Also attached the physical plan if you're interested. One thing to note that,
> if I turn down autoBroadcastJoinThreshold{color:#000000}to 5MB, this query
> will get successfully executed and default.product NOT broadcasted.{color}
> {color:#000000}
> {color}{color:#000000}However, when I change to another query that querying
> even less columns than pervious one, even in 5MB this table still get
> broadcasted and failed with the same error. I even changed to 1MB and still
> the same. {color}
--
This message was sent by Atlassian JIRA
(v7.6.3#76005)
---------------------------------------------------------------------
To unsubscribe, e-mail: issues-unsubscr...@spark.apache.org
For additional commands, e-mail: issues-h...@spark.apache.org
