[
https://issues.apache.org/jira/browse/HDFS-347?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=12992766#comment-12992766
]
ryan rawson commented on HDFS-347:
----------------------------------
dhruba, I am not seeing the file
src/hdfs/org/apache/hadoop/hdfs/metrics/DFSClientMetrics.java in
branch-20-append (nor cdh3b2). I also got a number of rejects, here are some
highlights:
ClientDatanodeProtocol, your variant has copyBlock, ours does not (hence the
rej).
Misc field differences in DFSClient, including the metrics object
After resolving them I was able to get it up and going.
I'm not able to get the unit test to pass, I'm guessing it's this:
2011-02-09 14:35:49,926 DEBUG hdfs.DFSClient
(DFSClient.java:fetchBlockByteRange(1927)) - fetchBlockByteRange
shortCircuitLocalReads true localhst h132.sfo.stumble.net/10.10.1.132
targetAddr /127.0.0.1:62665
Since we don't recognize that we are 'local', we do the normal read path which
is failing. Any tips?
> 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
> Reporter: George Porter
> Assignee: Todd Lipcon
> Attachments: BlockReaderLocal1.txt, HADOOP-4801.1.patch,
> HADOOP-4801.2.patch, HADOOP-4801.3.patch, all.tsv, 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.
-
For more information on JIRA, see: http://www.atlassian.com/software/jira
