incubator-cassandra-user mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From Jonathan Ellis <jbel...@gmail.com>
Subject Re: Task's map reading more record than CFIF's inputSplitSize
Date Wed, 07 Sep 2011 16:04:38 GMT
getSplits looks pretty foolproof to me but I guess we'd need to add
more debug logging to rule out a bug there for sure.

I guess the main alternative would be a bug in the recordreader paging.

On Wed, Sep 7, 2011 at 6:35 AM, Mck <mck@apache.org> wrote:
> Cassandra-0.8.4 w/ ByteOrderedPartitioner
>
> CFIF's inputSplitSize=196608
>
> 3 map tasks (from 4013) is still running after read 25 million rows.
>
> Can this be a bug in StorageService.getSplits(..) ?
>
> With this data I've had general headache with using tokens that are
> longer than usual (and trying to move nodes around to balance the ring).
>
>  nodetool ring gives
> Address         Status State   Load            Owns    Token
>                                                       Token(bytes[76118303760208547436305468318170713656])
> 152.90.241.22   Up     Normal  270.46 GB       33.33%  Token(bytes[30303030303031333131313739353337303038d4e7f72db2ed11e09d7c68b59973a5d8])
> 152.90.241.24   Up     Normal  247.89 GB       33.33%  Token(bytes[303030303030313331323631393735313231381778518cc00711e0acb968b59973a5d8])
> 152.90.241.23   Up     Normal  1.1 TB          33.33%  Token(bytes[76118303760208547436305468318170713656])
>
>
> ~mck
>
>



-- 
Jonathan Ellis
Project Chair, Apache Cassandra
co-founder of DataStax, the source for professional Cassandra support
http://www.datastax.com

Mime
View raw message