hama-dev mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From "Thomas Jungblut (JIRA)" <j...@apache.org>
Subject [jira] [Commented] (HAMA-559) Add a spilling message queue
Date Sat, 03 Nov 2012 06:50:12 GMT

    [ https://issues.apache.org/jira/browse/HAMA-559?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=13489951#comment-13489951
] 

Thomas Jungblut commented on HAMA-559:
--------------------------------------

Java7&Windows.

Exactly, GC will come into picture, also my implementation does not really make messaging
more scalable. If the producer is way faster than the consumer, you'll end up with the memory
problems we are facing currently. I see it when I profile the stream, the flusher is basically
never blocked and always writes to the underlying stream, BUT on closing the stream the closer
must wait until all the stuff is written. 
So your implementation is smarter, because you limit the buffer numbers (we should limit it
on an amount of memory actually). 

bq.Could it be because we are not setting cpu affinity for both the threads?

I don't think this is a problem, maybe the cachemiss is just pretty high. 

Sorry for anything wrong, it is 8 in the morning :D
                
> Add a spilling message queue
> ----------------------------
>
>                 Key: HAMA-559
>                 URL: https://issues.apache.org/jira/browse/HAMA-559
>             Project: Hama
>          Issue Type: Sub-task
>          Components: bsp core
>    Affects Versions: 0.5.0
>            Reporter: Thomas Jungblut
>            Assignee: Suraj Menon
>            Priority: Minor
>             Fix For: 0.7.0
>
>         Attachments: HAMA-559.patch-v1, spillbench_code.tar.gz, spilling_buffer_cpu_usage_text_write.png,
SpillingBufferProfile-2012-10-27.snapshot, spilling_buffer_profile_cpu_graph_test_write.png,
spilling_buffer_profile_cpugraph_writeUTF.png, spillingbuffer_profile_cpu_writeUTF.png, spilling_buffer_profile_LOCK.JPG,
spilling_buffer_profile_timesplit_text_write.png, spilling_buffer_profile_writeUTF.png
>
>
> After HAMA-521 is done, we can add a spilling queue which just holds the messages in
RAM that fit into the heap space. The rest can be flushed to disk.
> We may call this a HybridQueue or something like that.
> The benefits should be that we don't have to flush to disk so often and get faster. However
we may have more GC so it is always overall faster.
> The requirements for this queue also include:
> - The message object once written to the queue (after returning from the write call)
could be modified, but the changes should not be reflected in the messages stored in the queue.
> - For now let's implement a queue that does not support concurrent reading and writing.
This feature is needed when we implement asynchronous communication.

--
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

Mime
View raw message