Home | About | Sematext search-lucene.com search-hadoop.com
 Search Hadoop and all its subprojects:

Switch to Plain View
Hadoop, mail # dev - Question about Hadoop-8192 and rackToBlocks ordering

Kumar Ravi 2012-03-22, 12:24
Robert Evans 2012-03-22, 16:54
Amir Sanjar 2012-03-22, 18:45
Devaraj Das 2012-03-22, 21:40
Kumar Ravi 2012-03-23, 14:26
Devaraj Das 2012-03-23, 17:10
Copy link to this message
Re: Question about Hadoop-8192 and rackToBlocks ordering
Amir Sanjar 2012-03-23, 17:55
Devaraj ,
I respectfully disagree, fixing the testcase for IBM JVM  will break SUN
JVM, unless we remove the assertion causing the problem. However that might
in return mask other problems  . Before any changes we need to understand
the logic behind split process. Is there any documentation? Who owned the
Best Regards
Amir Sanjar

Linux System Management Architect and Lead
IBM Senior Software Engineer
Phone# 512-286-8393
Fax#      512-838-8858

From: Devaraj Das <[EMAIL PROTECTED]>
Cc: Jeffrey J Heroux/Poughkeepsie/IBM@IBMUS, John
Date: 03/23/2012 12:15 PM
Subject: Re: Question about Hadoop-8192 and rackToBlocks ordering

Thanks for the explanation, Kumar.

This looks like a testcase problem. We can get into a discussion on whether
we should tweak the split selection process to output more/less splits when
given an input set, but for now we should fix the testcase. Makes sense?

On Mar 23, 2012, at 7:26 AM, Kumar Ravi wrote:

> Hi Devaraj,
>  The issue Amir brings up has to do with the Testcase scenario.
> We are trying to determine if this is a Design issue with the
getMoreSplits() method in CombineFileInputFormat class or if the testcase
needs modification.
> Like I mentioned in my earlier note, the observation we made while
debugging this issue is that the order by which the racksToBlocks HashMap
gets populated seems to matter. From the comments by Robert Evans and you,
it appears by design that the order should not matter.
> Amir's point is - The reason order happens to play a role here is that as
soon as all the blocks are accounted for, getMoreSplits() stops iterating
through the racks, and depending upon which rack(s) each block is
replicated on, and depending upon when each rack is processed in the loop
within getMoreSplits(), one can end up with different split counts, and as
a result fail the testcase in some situations.
> Specifically for this testcase, there are 3 racks that are simulated
where each of these 3 racks have a datanode each. Datanode 1 has replicas
of all the blocks of all the 3 files (file1, file2, and file3) while
Datanode 2 has all the blocks of files file2 and file 3 and Datanode 3 has
all the blocks of only file3. As soon as Rack 1 is processed, getMoreSplits
() exits with a split count of the number of times it stays in this loop.
So in this scenario, if Rack1 gets processed last, one will end up with a
split count of 3. If Rack1 gets processed in the beginning, split count
will be 1. The testcase is expecting a return value of 3 but can get a 1 or
2 depending on when it gets processed.
> Hope this clarifies things a bit.
> Regards,
> Kumar
> Kumar Ravi
> IBM Linux Technology Center
> Austin, TX
> Tel.: (512)286-8179
> Devaraj Das ---03/22/2012 04:41:36 PM---On Mar 22, 2012, at 11:45 AM,
Amir Sanjar wrote:
> From:
> Devaraj Das <[EMAIL PROTECTED]>
> To:
> Cc:
> Jeffrey J Heroux/Poughkeepsie/IBM@IBMUS, John Williams/Austin/IBM@IBMUS
> Date:
> 03/22/2012 04:41 PM
> Subject:
> Re: Question about Hadoop-8192 and rackToBlocks ordering
> On Mar 22, 2012, at 11:45 AM, Amir Sanjar wrote:
> > Thanks for the reply Robert,
> > However I believe the main design issue is:
> > If there is a rack ( listed in rackToBlock hashMap) that contains all
> > blocks (stored in blockToNode hashMap), regardless of the order, the
> > operation terminates after the rack gets processed,  That means
> > racks  ( listed in rackToBlock hashMap)  will not get processed . For
> > details look at file CombineFileInputFormat.JAVA, method getMoreSplits
> > while loop starting at  line 344.
> >
> I haven't looked at the code much yet. But trying to understand your
question - what issue are you trying to bring out? Is it overloading one
task with too much input (there is a min/max limit on that one though)?
> > Best Regards
> > Amir Sanjar
splits is
Devaraj Das 2012-03-23, 18:15