Mailing-List: contact commits-help@cassandra.apache.org; run by ezmlm
Precedence: bulk
Reply-To: dev@cassandra.apache.org
Date: Fri, 18 May 2012 17:09:10 +0000 (UTC)
From: =?utf-8?Q?Bart=C5=82omiej_Roma=C5=84ski_=28JIRA=29?= <jira@apache.org>
To: commits@cassandra.apache.org
Message-ID: 
 <1206312509.14894.1337360950849.JavaMail.tomcat@hel.zones.apache.org>
In-Reply-To: 
 <197316129.14891.1337360950721.JavaMail.tomcat@hel.zones.apache.org>
Subject: [jira] [Updated] (CASSANDRA-4259) Bug in
 SSTableReader.getSampleIndexesForRanges(...) causes uneven InputSplits
 generation for Hadoop mappers
MIME-Version: 1.0
Content-Type: text/plain; charset=utf-8
Content-Transfer-Encoding: quoted-printable


     [ https://issues.apache.org/jira/browse/CASSANDRA-4259?page=3Dcom.atla=
ssian.jira.plugin.system.issuetabpanels:all-tabpanel ]

Bart=C5=82omiej Roma=C5=84ski updated CASSANDRA-4259:
-------------------------------------------

    Description:=20
Running a simple mapreduce job on cassandra column family results in creati=
ng multiple small mappers for one half of the ring and one big mapper for t=
he other half. Upper part (85... - 0) is cut into smaller slices. Lower par=
t (0 - 85...) generates one big input slice. One mapper processing half of =
the ring causes huge inefficiency. Also the progress meter for this mapper =
is incorrect - it goes to 100% in a couple of seconds, than stays at 100% f=
or an hour or two.

I've investigated the problem a bit. I think it is related to incorrect out=
put of 'nodetool rangekeysample'. On the node resposible for part (0 - 85..=
.) the output is empty! On the other node it works fine.

I think the bug is in SSTableReader.getSampleIndexesForRanges(...). These t=
wo lines:

   RowPosition leftPosition =3D range.left.maxKeyBound();
   RowPosition rightPosition =3D range.left.maxKeyBound();

should be changed to:

   RowPosition leftPosition =3D range.left.maxKeyBound();
   RowPosition rightPosition =3D range.right.maxKeyBound();

After that fix the output of nodetool is correct and the whole ring is spli=
t into small mappers.

The other half of the ring works fine because of extra 'if' in the code:

   int right =3D Range.isWrapAround(range.left, range.right)...

This causes that the bug does not show up in one-node cluster or in the "la=
st" ring partition in muli-node clusters.

Can anyone look at it and verify my thoughts? I'm rather new to Cassandra.


  was:
Running a simple mapreduce job on cassandra column family results in creati=
ng multiple small mappers for one half of the ring and one big mapper for t=
he other half. Upper part (85... - 0) is cut into smaller slices. Lower par=
t (0 - 85...) generates one big input slice. One mapper processing half of =
the ring causes huge inefficiency. Also the progress meter for this mapper =
is incorrect - it goes to 100% in a couple of second that stays at 100% for=
 an hour or two.

I've investigated the problem a bit. I think it is related to incorrect out=
put of 'nodetool rangekeysample'. On the node resposible for part (0 - 85..=
.) the output is empty! On the other node it works fine.

I think the bug is in SSTableReader.getSampleIndexesForRanges(...). This to=
 lines:

   RowPosition leftPosition =3D range.left.maxKeyBound();
   RowPosition rightPosition =3D range.left.maxKeyBound();

should be changed to:

   RowPosition leftPosition =3D range.left.maxKeyBound();
   RowPosition rightPosition =3D range.right.maxKeyBound();

After that fix the output of nodetool is correct and the whole ring is spli=
t into small mappers.

The other half of the ring works fine because of extra 'if' in the code:

   int right =3D Range.isWrapAround(range.left, range.right)...

This causes that the bug does not show up in one-node cluster or in the "la=
st" ring partition in muli-node clusters.

Can anyone look at it and verify my thoughts? I'm rather new to Cassandra.


   =20
> Bug in SSTableReader.getSampleIndexesForRanges(...) causes uneven InputSp=
lits generation for Hadoop mappers
> -------------------------------------------------------------------------=
----------------------------------
>
>                 Key: CASSANDRA-4259
>                 URL: https://issues.apache.org/jira/browse/CASSANDRA-4259
>             Project: Cassandra
>          Issue Type: Bug
>          Components: Hadoop
>    Affects Versions: 1.1.0
>         Environment: Small cassandra cluster with 2 nodes. Version 1.1.0.=
=20
> Tokens: 0, 85070591730234615865843651857942052864
> Hadoop 1.0.1 and Pig 0.10.0.
>            Reporter: Bart=C5=82omiej Roma=C5=84ski
>
> Running a simple mapreduce job on cassandra column family results in crea=
ting multiple small mappers for one half of the ring and one big mapper for=
 the other half. Upper part (85... - 0) is cut into smaller slices. Lower p=
art (0 - 85...) generates one big input slice. One mapper processing half o=
f the ring causes huge inefficiency. Also the progress meter for this mappe=
r is incorrect - it goes to 100% in a couple of seconds, than stays at 100%=
 for an hour or two.
> I've investigated the problem a bit. I think it is related to incorrect o=
utput of 'nodetool rangekeysample'. On the node resposible for part (0 - 85=
...) the output is empty! On the other node it works fine.
> I think the bug is in SSTableReader.getSampleIndexesForRanges(...). These=
 two lines:
>    RowPosition leftPosition =3D range.left.maxKeyBound();
>    RowPosition rightPosition =3D range.left.maxKeyBound();
> should be changed to:
>    RowPosition leftPosition =3D range.left.maxKeyBound();
>    RowPosition rightPosition =3D range.right.maxKeyBound();
> After that fix the output of nodetool is correct and the whole ring is sp=
lit into small mappers.
> The other half of the ring works fine because of extra 'if' in the code:
>    int right =3D Range.isWrapAround(range.left, range.right)...
> This causes that the bug does not show up in one-node cluster or in the "=
last" ring partition in muli-node clusters.
> Can anyone look at it and verify my thoughts? I'm rather new to Cassandra=
.

--
This message is automatically generated by JIRA.
If you think it was sent incorrectly, please contact your JIRA administrato=
rs: https://issues.apache.org/jira/secure/ContactAdministrators!default.jsp=
a
For more information on JIRA, see: http://www.atlassian.com/software/jira