hadoop-hdfs-issues mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From "Colin Patrick McCabe (JIRA)" <j...@apache.org>
Subject [jira] [Commented] (HDFS-347) DFS read performance suboptimal when client co-located on nodes with data
Date Thu, 04 Apr 2013 18:25:25 GMT

    [ https://issues.apache.org/jira/browse/HDFS-347?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=13622614#comment-13622614

Colin Patrick McCabe commented on HDFS-347:

The purpose of the patch with 'Jenkins' in the name is to get a Jenkins run.  In order to
do that, the patch needs to be such that applying it to a directory containing the trunk code
results in exactly the code which is in the HDFS-347 branch.

What you have suggested may be helpful for review.  If it is, feel free to use it locally,
since you clearly know how to generate it.  But there is no need to post it here.  And if
you do post it, it will just result in Jenkins spitting out a "build failure" message.  If
you don't believe me, try it yourself.
> DFS read performance suboptimal when client co-located on nodes with data
> -------------------------------------------------------------------------
>                 Key: HDFS-347
>                 URL: https://issues.apache.org/jira/browse/HDFS-347
>             Project: Hadoop HDFS
>          Issue Type: Improvement
>          Components: datanode, hdfs-client, performance
>            Reporter: George Porter
>            Assignee: Colin Patrick McCabe
>         Attachments: 2013.01.28.design.pdf, 2013.01.31.consolidated2.patch, 2013.01.31.consolidated.patch,
2013.02.15.consolidated4.patch, 2013-04-01-jenkins.patch, all.tsv, BlockReaderLocal1.txt,
full.patch, HADOOP-4801.1.patch, HADOOP-4801.2.patch, HADOOP-4801.3.patch, HDFS-347-016_cleaned.patch,
HDFS-347.016.patch, HDFS-347.017.clean.patch, HDFS-347.017.patch, HDFS-347.018.clean.patch,
HDFS-347.018.patch2, HDFS-347.019.patch, HDFS-347.020.patch, HDFS-347.021.patch, HDFS-347.022.patch,
HDFS-347.024.patch, HDFS-347.025.patch, HDFS-347.026.patch, HDFS-347.027.patch, HDFS-347.029.patch,
HDFS-347.030.patch, HDFS-347.033.patch, HDFS-347.035.patch, HDFS-347-branch-20-append.txt,
hdfs-347-merge.txt, hdfs-347-merge.txt, hdfs-347-merge.txt, hdfs-347.png, hdfs-347.txt, local-reads-doc
> One of the major strategies Hadoop uses to get scalable data processing is to move the
code to the data.  However, putting the DFS client on the same physical node as the data blocks
it acts on doesn't improve read performance as much as expected.
> After looking at Hadoop and O/S traces (via HADOOP-4049), I think the problem is due
to the HDFS streaming protocol causing many more read I/O operations (iops) than necessary.
 Consider the case of a DFSClient fetching a 64 MB disk block from the DataNode process (running
in a separate JVM) running on the same machine.  The DataNode will satisfy the single disk
block request by sending data back to the HDFS client in 64-KB chunks.  In BlockSender.java,
this is done in the sendChunk() method, relying on Java's transferTo() method.  Depending
on the host O/S and JVM implementation, transferTo() is implemented as either a sendfilev()
syscall or a pair of mmap() and write().  In either case, each chunk is read from the disk
by issuing a separate I/O operation for each chunk.  The result is that the single request
for a 64-MB block ends up hitting the disk as over a thousand smaller requests for 64-KB each.
> Since the DFSClient runs in a different JVM and process than the DataNode, shuttling
data from the disk to the DFSClient also results in context switches each time network packets
get sent (in this case, the 64-kb chunk turns into a large number of 1500 byte packet send
operations).  Thus we see a large number of context switches for each block send operation.
> I'd like to get some feedback on the best way to address this, but I think providing
a mechanism for a DFSClient to directly open data blocks that happen to be on the same machine.
 It could do this by examining the set of LocatedBlocks returned by the NameNode, marking
those that should be resident on the local host.  Since the DataNode and DFSClient (probably)
share the same hadoop configuration, the DFSClient should be able to find the files holding
the block data, and it could directly open them and send data back to the client.  This would
avoid the context switches imposed by the network layer, and would allow for much larger read
buffers than 64KB, which should reduce the number of iops imposed by each read block operation.

This message is automatically generated by JIRA.
If you think it was sent incorrectly, please contact your JIRA administrators
For more information on JIRA, see: http://www.atlassian.com/software/jira

View raw message