Home | About | Sematext search-lucene.com search-hadoop.com
clear query|facets|time Search criteria: .   Results from 31 to 40 from 71 (0.101s).
Loading phrases to help you
refine your search...
[expand - 1 more] - Re: Force job to use all reducers evenly? - Hadoop - [mail # user]
...On Mar 25, 2011, at 2:02 AM, Harsh J wrote:  wrote: designate the job to have at least (or precisely) 4 reducers.  I have  noticed that it is not guaranteed that all four redu...
   Author: Keith Wiley, 2011-03-25, 14:18
[expand - 2 more] - Re: Direct HDFS access from a streaming job - Hadoop - [mail # user]
...On Mar 24, 2011, at 8:31 AM, Harsh J wrote:  wrote: quoted in my first post, the unstated intent was to simply do a system()  call and invoke "hadoop fs -get" or "hadoop fs -copyTo...
   Author: Keith Wiley, 2011-03-24, 16:09
[expand - 1 more] - Re: kill-task syntax? - Hadoop - [mail # user]
...On Mar 23, 2011, at 2:02 PM, Keith Wiley wrote:  the job tracker?  Killing a job generally works for me........although  much to my dismay the job often doesn't actually die, ...
   Author: Keith Wiley, 2011-03-23, 22:04
[expand - 1 more] - Re: Streaming reporter counter vs status - Hadoop - [mail # user]
...I suppose this bit of documentation answers part of my question:  'The number of milliseconds before a task will be terminated if it  neither reads an input, writes an output, nor ...
   Author: Keith Wiley, 2011-03-23, 18:57
[expand - 2 more] - Re: Streaming mappers frequently time out - Hadoop - [mail # user]
...Maybe I could just turn it down to two or three minutes.  It wouldn't  fix the problem where the task doesn't start, but it would kill it and  restart it more quickly.  T...
   Author: Keith Wiley, 2011-03-23, 18:49
Kill jobs take awhile to clear off job tracker - Hadoop - [mail # user]
...Why does it take a long time (fractions of an hour or more sometimes)  for kill jobs to disappear from the running jobs list of the job  tracker?  Clicking on such jobs will o...
   Author: Keith Wiley, 2011-03-18, 17:20
Re: c++ problem - Hadoop - [mail # user]
...Why don't you write up a typical Hello World in C++, then make that run  as a mapper on Hadoop streaming (or pipes).  If you send the "Hello  World" to cout (as opposed to cer...
   Author: Keith Wiley, 2011-03-16, 15:43
Frustrating "pending" statuses - Hadoop - [mail # dev]
...Despite plenty of available mapper slots (as inferred by "Map Task  Capacity" minus "Maps" on the jobtracker) our jobs often linger with all  or many of the map tasks stuck in a pe...
   Author: Keith Wiley, 2011-03-15, 07:55
Re: Not able to Run C++ code in Hadoop Cluster - Hadoop - [mail # user]
...Not to speak against pipes because I don't have much experience with it,  but I eventually abandoned my pipes efforts and went with streaming.  If  you don't get pipes to work...
   Author: Keith Wiley, 2011-03-14, 16:40
[expand - 1 more] - Re: Linear slowdown producing streaming output - Hadoop - [mail # user]
...I'm still trying to solve this problem.  One person mentioned that  mappers have to sort the data and that the sort buffer may be relevant  but I'm seeing the same linear slow...
   Author: Keith Wiley, 2011-03-10, 09:00
Hadoop (71)
Hive (30)
MapReduce (11)
HDFS (5)
mail # user (67)
mail # dev (2)
mail # general (2)
last 7 days (0)
last 30 days (0)
last 90 days (0)
last 6 months (0)
last 9 months (71)
Harsh J (558)
Owen O'Malley (394)
Steve Loughran (384)
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)
Keith Wiley