You are viewing a plain text version of this content. The canonical link for it is here.
Posted to issues@spark.apache.org by "Jiandan Yang (JIRA)" <ji...@apache.org> on 2019/08/15 08:56:00 UTC
[jira] [Created] (SPARK-28743) YarnShuffleService leads to
NodeManager OOM because ChannelOutboundBuffer has to many entry
Jiandan Yang created SPARK-28743:
-------------------------------------
Summary: YarnShuffleService leads to NodeManager OOM because ChannelOutboundBuffer has to many entry
Key: SPARK-28743
URL: https://issues.apache.org/jira/browse/SPARK-28743
Project: Spark
Issue Type: Bug
Components: Shuffle
Affects Versions: 2.2.3
Reporter: Jiandan Yang
NodeManager heap size is 4G, io.netty.channel.ChannelOutboundBuffer$Entry occupied about 2.8G by looking at Histogram of Mat, and those Entries were hold by ChannelOutboundBuffer by looking at dominator_tree of mat. By analyzing one fo ChannelOutboundBuffer object, I found there were 248867 entries in the object of ChannelOutboundBuffer (ChannelOutboundBuffer#flushed=248867), and ChannelOutboundBuffer#totalPengdingSize=23891232 which is more than highwaterMark(64K), and unwritable=1 meaning sending buffer was full. But ChannelHandler seems not check unwritable flag when write message, and finally NodeManager occurs OOM.
--
This message was sent by Atlassian JIRA
(v7.6.14#76016)
---------------------------------------------------------------------
To unsubscribe, e-mail: issues-unsubscribe@spark.apache.org
For additional commands, e-mail: issues-help@spark.apache.org