hadoop-hdfs-issues mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From "Todd Lipcon (JIRA)" <j...@apache.org>
Subject [jira] [Commented] (HDFS-4190) Read complete block into memory once in BlockScanning and reduce concurrent disk access
Date Thu, 15 Nov 2012 19:02:12 GMT

    [ https://issues.apache.org/jira/browse/HDFS-4190?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=13498247#comment-13498247

Todd Lipcon commented on HDFS-4190:

Even if it's calling read wiht a 4096 byte buffer, the OS is certainly doing readahead on
your behalf and coalescing the requests into larger chunks. You won't get a seek per read.
You could also just use fadvise here to force readahead of larger chunks of the file -- the
code's already there in BlockSender, we'd just need to make sure it's getting set properly
for the scanner code path. (I think it is).

I'm generally against the idea of mmapping - in various benchmarks I've run in the past, it
comes out to basically the same speed as large chunked read() calls, and sometimes slower
in multi-threaded environments. The added complication of not being able to munmap easily
in Java makes it even worse.
> Read complete block into memory once in BlockScanning and reduce concurrent disk access
> ---------------------------------------------------------------------------------------
>                 Key: HDFS-4190
>                 URL: https://issues.apache.org/jira/browse/HDFS-4190
>             Project: Hadoop HDFS
>          Issue Type: Bug
>          Components: data-node
>    Affects Versions: 3.0.0
>            Reporter: Uma Maheswara Rao G
> When we perform bulk write operations to DFS we observed that block scan is one bottleneck
for concurrent disk access.
> To see real load on disks, keep single data node and local client flushing data to DFS.
> When we switch off block scanning we have seen >10% improvement. I will update real
figures in comment.
> Even though I am doing only write operation, implicitly there will be a read operation
for each block due to block scanning. Next scan will happen only after 21 days, but once scan
will happen after adding the block. This will be the concurrent access to disks.
> Other point to note is that, we will read the block, packet by packet in block scanning
as well. We know that, we have to read&scan complete block, so, it may be correct to load
complete block once and do checksums verification for that data?
> I tried with MemoryMappedBuffers:
> mapped the complete block once in blockScanning and does the checksum verification with
that. Seen good improvement in that bulk write scenario.
> But we don't have any API to clean the mapped buffer immediately. With my experiment
I just used, Cleaner class from sun package. That will not be correct to use in production.
So, we have to write JNI call to clean that mmapped buffer.
> I am not sure I missed something here. please correct me If i missed some points.
> Thoughts?

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