You are viewing a plain text version of this content. The canonical link for it is here.
Posted to issues@drill.apache.org by "Deneche A. Hakim (JIRA)" <ji...@apache.org> on 2016/03/25 17:26:25 UTC

[jira] [Commented] (DRILL-3241) Query with window function runs out of direct memory and does not report back to client that it did

    [ https://issues.apache.org/jira/browse/DRILL-3241?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15212015#comment-15212015 ] 

Deneche A. Hakim commented on DRILL-3241:
-----------------------------------------

In the latest master, I could no longer reproduce the same exact issue. I still see an OutOfMemory error but it's similar to DRILL-3714.

I do have one question though. The original issue happens when ProtobufLengthDecoder.decode() can't allocate enough memory to copy the message, it would then call an implementation of OutOfMemoryHandler. On the client side, the implementation throws an UnsupportedOperationException (I've seen it when I reproduced the issue in 1.2.0) but on the server side it just logs an error message and ignores the error!

[~sphillips], [~jacques@dremio.com]: what is the motivation behind the OutOfMemoryHandler ? Why not just let the out of memory exception propagate through the RPC layer which would cause the channel to close and fail any fragment that was sending data to the server (after we fix DRILL-3714) ?

> Query with window function runs out of direct memory and does not report back to client that it did
> ---------------------------------------------------------------------------------------------------
>
>                 Key: DRILL-3241
>                 URL: https://issues.apache.org/jira/browse/DRILL-3241
>             Project: Apache Drill
>          Issue Type: Bug
>          Components: Execution - Relational Operators
>    Affects Versions: 1.0.0
>            Reporter: Victoria Markman
>            Assignee: Deneche A. Hakim
>            Priority: Critical
>             Fix For: 1.7.0
>
>
> Even though query run out of memory and was cancelled on the server, client (sqlline) was never notified of the event and it appears to the user that query is hung. 
> Configuration:
> Single drillbit configured with:
> DRILL_MAX_DIRECT_MEMORY="2G"
> DRILL_HEAP="1G"
> TPCDS100 parquet files
> Query:
> {code}
> select 
>   sum(ss_quantity) over(partition by ss_store_sk order by ss_sold_date_sk) 
> from store_sales;
> {code}
> drillbit.log
> {code}
> 2015-06-01 21:42:29,514 [BitServer-5] ERROR o.a.d.exec.rpc.RpcExceptionHandler - Exception in RPC communication.  Connection: /10.10.88.133:31012 <--> /10.10.88.133:38887 (data server).  Closing connection.
> io.netty.handler.codec.DecoderException: java.lang.OutOfMemoryError: Direct buffer memory
>         at io.netty.handler.codec.ByteToMessageDecoder.channelRead(ByteToMessageDecoder.java:233) ~[netty-codec-4.0.27.Final.jar:4.0.27.Final]
>         at io.netty.channel.AbstractChannelHandlerContext.invokeChannelRead(AbstractChannelHandlerContext.java:339) [netty-transport-4.0.27.Final.jar:4.0.27.Final]
>         at io.netty.channel.AbstractChannelHandlerContext.fireChannelRead(AbstractChannelHandlerContext.java:324) [netty-transport-4.0.27.Final.jar:4.0.27.Final]
>         at io.netty.channel.ChannelInboundHandlerAdapter.channelRead(ChannelInboundHandlerAdapter.java:86) [netty-transport-4.0.27.Final.jar:4.0.27.Final]
>         at io.netty.channel.AbstractChannelHandlerContext.invokeChannelRead(AbstractChannelHandlerContext.java:339) [netty-transport-4.0.27.Final.jar:4.0.27.Final]
>         at io.netty.channel.AbstractChannelHandlerContext.fireChannelRead(AbstractChannelHandlerContext.java:324) [netty-transport-4.0.27.Final.jar:4.0.27.Final]
>         at io.netty.channel.DefaultChannelPipeline.fireChannelRead(DefaultChannelPipeline.java:847) [netty-transport-4.0.27.Final.jar:4.0.27.Final]
>         at io.netty.channel.epoll.AbstractEpollStreamChannel$EpollStreamUnsafe.epollInReady(AbstractEpollStreamChannel.java:618) [netty-transport-native-epoll-4.0.27.Final-linux-x86_64.jar:na]
>         at io.netty.channel.epoll.EpollEventLoop.processReady(EpollEventLoop.java:329) [netty-transport-native-epoll-4.0.27.Final-linux-x86_64.jar:na]
>         at io.netty.channel.epoll.EpollEventLoop.run(EpollEventLoop.java:250) [netty-transport-native-epoll-4.0.27.Final-linux-x86_64.jar:na]
>         at io.netty.util.concurrent.SingleThreadEventExecutor$2.run(SingleThreadEventExecutor.java:111) [netty-common-4.0.27.Final.jar:4.0.27.Final]
>         at java.lang.Thread.run(Thread.java:745) [na:1.7.0_71]
> Caused by: java.lang.OutOfMemoryError: Direct buffer memory
>         at java.nio.Bits.reserveMemory(Bits.java:658) ~[na:1.7.0_71]
>         at java.nio.DirectByteBuffer.<init>(DirectByteBuffer.java:123) ~[na:1.7.0_71]
>         at java.nio.ByteBuffer.allocateDirect(ByteBuffer.java:306) ~[na:1.7.0_71]
>         at io.netty.buffer.PoolArena$DirectArena.newChunk(PoolArena.java:437) ~[netty-buffer-4.0.27.Final.jar:4.0.27.Final]
>         at io.netty.buffer.PoolArena.allocateNormal(PoolArena.java:179) ~[netty-buffer-4.0.27.Final.jar:4.0.27.Final]
>         at io.netty.buffer.PoolArena.allocate(PoolArena.java:168) ~[netty-buffer-4.0.27.Final.jar:4.0.27.Final]
>         at io.netty.buffer.PoolArena.reallocate(PoolArena.java:280) ~[netty-buffer-4.0.27.Final.jar:4.0.27.Final]
>         at io.netty.buffer.PooledByteBuf.capacity(PooledByteBuf.java:110) ~[netty-buffer-4.0.27.Final.jar:4.0.27.Final]
>         at io.netty.buffer.AbstractByteBuf.ensureWritable(AbstractByteBuf.java:251) ~[netty-buffer-4.0.27.Final.jar:4.0.27.Final]
>         at io.netty.buffer.AbstractByteBuf.writeBytes(AbstractByteBuf.java:849) ~[netty-buffer-4.0.27.Final.jar:4.0.27.Final]
>         at io.netty.buffer.AbstractByteBuf.writeBytes(AbstractByteBuf.java:841) ~[netty-buffer-4.0.27.Final.jar:4.0.27.Final]
>         at io.netty.buffer.AbstractByteBuf.writeBytes(AbstractByteBuf.java:831) ~[netty-buffer-4.0.27.Final.jar:4.0.27.Final]
>         at io.netty.buffer.WrappedByteBuf.writeBytes(WrappedByteBuf.java:600) ~[netty-buffer-4.0.27.Final.jar:4.0.27.Final]
>         at io.netty.buffer.UnsafeDirectLittleEndian.writeBytes(UnsafeDirectLittleEndian.java:28) ~[drill-java-exec-1.0.0-mapr-r1-rebuffed.jar:4.0.27.Final]
>         at io.netty.handler.codec.ByteToMessageDecoder$1.cumulate(ByteToMessageDecoder.java:92) ~[netty-codec-4.0.27.Final.jar:4.0.27.Final]
>         at io.netty.handler.codec.ByteToMessageDecoder.channelRead(ByteToMessageDecoder.java:227) ~[netty-codec-4.0.27.Final.jar:4.0.27.Final]
>         ... 11 common frames omitted
> 2015-06-01 21:42:29,516 [BitClient-1] ERROR o.a.d.exec.rpc.RpcExceptionHandler - Exception in RPC communication.  Connection: /10.10.88.133:38887 <--> /10.10.88.133:31012 (data client).  Closing connection.
> java.io.IOException: syscall:read(...)() failed: Connection reset by peer
> 2015-06-01 21:42:29,516 [BitClient-1] INFO  o.a.drill.exec.rpc.data.DataClient - Channel closed /10.10.88.133:38887 <--> /10.10.88.133:31012.
> {code}



--
This message was sent by Atlassian JIRA
(v6.3.4#6332)