Home | About | Sematext search-lucene.com search-hadoop.com
clear query|facets|time Search criteria: .   Results from 1 to 10 from 22 (0.134s).
Loading phrases to help you
refine your search...
Re: Replication factor affecting write performance - Hadoop - [mail # user]
...Isn't it logical that if your replication factor -> number of data nodesthat your performance will drop? Probably if repl factor approaches 18 forcluster A the write performance will drop...
   Author: Dieter De Witte, 2014-09-02, 14:26
Re: mr1 and mr2 - Hadoop - [mail # user]
...In my experience mixing APIs is probably the reason things do not work. Ifyou are using JobConf then you are not using MR1 I think. MR1 correspondsto Hadoop 1.x.x and JobConf is from Hadoop ...
   Author: Dieter De Witte, 2014-05-11, 06:56
Re: Eclipse-Plugin - Hadoop - [mail # user]
...Maybe you can install the Amazon AWS SDK, and then run EMR jobs, I thinkthese can be submitted via Eclipse but I haven't tried it myself.Regards, Dieter2014-04-06 20:44 GMT+02:00 João Paulo ...
   Author: Dieter De Witte, 2014-04-06, 18:51
Re: when it's safe to read map-reduce result? - Hadoop - [mail # user]
..._SUCCES implies that the job has succesfully terminated, so this seems likea reasonable criterion.Regards, Dieter2014-03-28 9:33 GMT+01:00 Li Li : ...
   Author: Dieter De Witte, 2014-03-28, 08:36
Re: Maps stuck on Pending - Hadoop - [mail # user]
...There's is a big chance that your map output is being copied to yourreducer, this could take quite some time if you have a lot of data andcould be resolved by:1) having more reducers2) adjus...
   Author: Dieter De Witte, 2014-03-28, 07:53
Re: Job froze for hours because of an unresponsive disk on one of the task trackers - Hadoop - [mail # user]
...The ids of the tasks are different so the node got killed after failing on3 different(!) reduce tasks. The reduce task 48 will probably have beenresubmitted to another node.2014-03-27 10:22 ...
   Author: Dieter De Witte, 2014-03-27, 09:33
[expand - 1 more] - Re: Use Cases for Structured Data - Hadoop - [mail # user]
...Sandbox is just meant to be a learning environment i guess, to see what'spossible, how things can be connected. The real distribution will have muchhigher performance and is the one you need...
   Author: Dieter De Witte, 2014-03-13, 09:56
[expand - 1 more] - Re: Logic of isSplittable() of class FileInputFormat - Hadoop - [mail # user]
...if you have a simple one line record format you should allow files to besplitted, since your simulations will be better balanced.2014-02-26 11:31 GMT+01:00 Sugandha Naolekar : ...
   Author: Dieter De Witte, 2014-02-26, 11:05
Re: Mappers vs. Map tasks - Hadoop - [mail # user]
...Each node has a tasktracker with a number of map slots. A map slot hosts asmapper. A mapper executes map tasks. If there are more map tasks than slotsobviously there will be multiple rounds ...
   Author: Dieter De Witte, 2014-02-25, 07:50
Re: Performance - Hadoop - [mail # user]
...Hi,The terasort benchmark is probably the most common. It has mappers andreducers doing 'nothing', this way you only use the framework's mergesortfunctionalities.Regards, Dieter2014-02-24 16...
   Author: Dieter De Witte, 2014-02-24, 15:56
Hadoop (14)
MapReduce (8)
mail # user (21)
issue (1)
last 7 days (0)
last 30 days (0)
last 90 days (1)
last 6 months (2)
last 9 months (22)
Ted Yu (1683)
Harsh J (1295)
Jun Rao (1056)
Todd Lipcon (1001)
Stack (977)
Jonathan Ellis (843)
Andrew Purtell (818)
Jean-Daniel Cryans (754)
jacques@... (738)
Yusaku Sako (733)
stack (717)
Jarek Jarcec Cecho (702)
Eric Newton (697)
Jonathan Hsieh (675)
Brock Noland (666)
Roman Shaposhnik (665)
Neha Narkhede (660)
Namit Jain (649)
Hitesh Shah (626)
Owen O'Malley (625)
Steve Loughran (619)
Siddharth Seth (614)
Josh Elser (584)
Eli Collins (545)
Arun C Murthy (543)
Dieter De Witte