Home | About | Sematext search-lucene.com search-hadoop.com
clear query|facets|time Search criteria: .   Results from 141 to 150 from 198 (0.143s).
Loading phrases to help you
refine your search...
[expand - 1 more] - Re: Intra-datanode balancing? - Hadoop - [mail # user]
...It used to matter quite a lot.  On Tue, Aug 25, 2009 at 1:25 PM, Kris Jirapinyo wrote:  ...
   Author: Ted Dunning, 2009-08-25, 20:36
Re: NN memory consumption on 0.20/0.21 with compressed pointers/ - Hadoop - [mail # user]
...On Tue, Aug 25, 2009 at 2:57 AM, Steve Loughran  wrote:    Since the codes running on these machines tend to be matrix oriented Fortran, I would expect almost all of this is a...
   Author: Ted Dunning, 2009-08-25, 15:59
Re: File Chunk to Map Thread Association - Hadoop - [mail # user]
...Uhh.... hadoop already goes to considerable lengths to make sure that computation is local.  In my experience it is common for 90% of the map invocations to be working from local data. ...
   Author: Ted Dunning, 2009-08-20, 17:36
[expand - 2 more] - Re: How to deal with "too many fetch failures"? - Hadoop - [mail # user]
...I think that the problem that I am remembering was due to poor recovery from this problem.  The underlying fault is likely due to poor connectivity between your machines.  Test tha...
   Author: Ted Dunning, 2009-08-20, 06:25
Re: Ubuntu/Hadoop incompatibilities? - Hadoop - [mail # user]
...I use ubuntu both in-house and on EC2 for hadoop.  Zero problems once you have the real java.  On Mon, Aug 17, 2009 at 10:34 AM, Jakob Homan  wrote:  ...
   Author: Ted Dunning, 2009-08-17, 17:46
Re: Why the jobs are suspended when I add new nodes? - Hadoop - [mail # user]
...Have you looked at the logs?  On Sun, Aug 16, 2009 at 11:36 PM, yang song  wrote:  ...
   Author: Ted Dunning, 2009-08-17, 08:00
Re: How to re-read the config files - Hadoop - [mail # user]
...You can do a rolling restart of the nodes.  The customer won't notice and running programs will still complete in good order.  If you have rack awareness configured, you can restar...
   Author: Ted Dunning, 2009-08-13, 22:21
[expand - 1 more] - Re: What will we encounter if we add a lot of nodes into the current cluster? - Hadoop - [mail # user]
...There is a parameter (dfs.balance.bandwidthPerSec) that limits the rebalancing bandwidth.  The default is rather low.  See http://developer.yahoo.com/hadoop/tutorial/module2.html#r...
   Author: Ted Dunning, 2009-08-13, 05:25
[expand - 1 more] - Re: How to break a hadoop-cluster in subclusters (how to group physical nodes)? - Hadoop - [mail # user]
...On Sun, Aug 9, 2009 at 8:17 AM, Harold Valdivia Garcia  wrote:    I think so.  In this configuration as you say I'd loss data-locatily because map-task   Yes.  ...
   Author: Ted Dunning, 2009-08-09, 18:37
[expand - 1 more] - Re: How to redistribute files on HDFS after adding new machines to cluster? - Hadoop - [mail # user]
...I think that I remember that you essentially doubled your storage before starting balancing.  This means that about 1 TB will need to be copied.  By default the balancer only moves...
   Author: Ted Dunning, 2009-08-08, 05:42
Sort:
project
Drill (262)
Zookeeper (250)
Hadoop (193)
HBase (134)
Pig (38)
HDFS (37)
MapReduce (35)
Chukwa (1)
Impala (1)
type
mail # user (136)
mail # general (34)
mail # dev (27)
issue (1)
date
last 7 days (0)
last 30 days (0)
last 90 days (1)
last 6 months (1)
last 9 months (198)
author
Harsh J (559)
Owen O'Malley (394)
Steve Loughran (385)
Todd Lipcon (237)
Eli Collins (182)
Alejandro Abdelnur (171)
Arun C Murthy (163)
Chris Nauroth (145)
Allen Wittenauer (142)
Ted Yu (122)
Tom White (121)
Daryn Sharp (115)
Nigel Daley (115)
Konstantin Shvachko (107)
Doug Cutting (96)
Aaron Kimball (94)
Colin Patrick McCabe (90)
Edward Capriolo (88)
Mark Kerzner (87)
jason hadoop (82)
Hairong Kuang (74)
Konstantin Boudnik (72)
Runping Qi (72)
Benoy Antony (70)
Suresh Srinivas (64)
Ted Dunning