Home | About | Sematext search-lucene.com search-hadoop.com
clear query|facets|time Search criteria: .   Results from 1 to 10 from 10 (0.119s).
Loading phrases to help you
refine your search...
Re: Hadoop efficient resource isolation - MapReduce - [mail # user]
...This is one reason to consider virtualizing Hadoop clusters. The idea is to create multiple virtual clusters on a single physical cluster and apply various kinds of resource controls (CPU, m...
   Author: Jeffrey Buell, 2013-02-25, 21:37
Re: question of how to take full advantage of cluster resources - MapReduce - [mail # user]
...Number of CPU cores is just one of several hardware constraints on the number of tasks that can be run efficiently at the same time. Other constraints:   - Usually 1 to 2 map tasks per ...
   Author: Jeffrey Buell, 2012-12-14, 23:29
RE: HDFS using SAN - MapReduce - [mail # user]
...It will be difficult to make a SAN work well for Hadoop, but not impossible .  I have done direct comparisons (but not published them yet).  Direct loc al storage is likely to have...
   Author: Jeffrey Buell, 2012-10-16, 21:24
RE: Spindle per Cores - MapReduce - [mail # user]
...I've done some experiments along these lines.  I'm using high-performance 1 5K RPM SAS drives instead of the more usual SATA drives, which should reduc e the number of drives I need. &n...
   Author: Jeffrey Buell, 2012-10-12, 21:19
RE: Cannot browse job.xml while running the job - MapReduce - [mail # user]
...Does /var/log/hadoop have write permission for the hadoop user?  From: Gaurav Dasgupta [mailto:[EMAIL PROTECTED]] Sent: Thursday, September 06, 2012 9:45 AM To: [EMAIL PROTECTED] Subjec...
   Author: Jeffrey Buell, 2012-09-06, 16:49
RE: Hadoop hardware failure recovery - MapReduce - [mail # user]
...This is never an issue on vSphere.  The ESXi hypervisor does not send the completion interrupt back to the guest until the IO is finished, so if the guest OS thinks an IO is flushed to ...
   Author: Jeffrey Buell, 2012-08-14, 00:15
RE: Idle nodes with terasort and MRv2/YARN (0.23.1) - MapReduce - [mail # user]
...I ran into the same issue.  In the end I gave up and went back to 0.20 wher e I can specify the number of mappers and reducers per node (6 and 4 in you r case).  You can try increa...
   Author: Jeffrey Buell, 2012-05-29, 22:10
RE: Terasort - MapReduce - [mail # user]
...I have slowstart set to 0.05 (I think that is the default).  In MR1 all of  the reducers start when 5% of the maps finish (expected and desired behavio r).  This allows the sh...
   Author: Jeffrey Buell, 2012-05-10, 23:16
[expand - 1 more] - RE: max 1 mapper per node - MapReduce - [mail # user]
...I have the right #slots to fill up memory across the cluster, and all those  slots are filled with tasks. The problem I ran into was that the maps grab bed all the slots initially and t...
   Author: Jeffrey Buell, 2012-05-10, 22:40
RE: Enable Hyperthreading? / Typical M/R ratios and rules of thumb - MapReduce - [mail # user]
...Tom,  I can't speak for other virtualization vendors, but VMware does not recomme nd disabling HT.  Do you have a source that says otherwise (so we can fix i t)?  The benefit ...
   Author: Jeffrey Buell, 2011-11-16, 17:29
MapReduce (10)
HDFS (8)
Hadoop (3)
mail # user (10)
last 7 days (0)
last 30 days (0)
last 90 days (0)
last 6 months (0)
last 9 months (10)
Harsh J (454)
Arun C Murthy (326)
Vinod Kumar Vavilapalli (308)
Todd Lipcon (223)
Amar Kamat (181)
Thomas Graves (166)
Jason Lowe (163)
Amareshwari Sriramadasu (152)
Sandy Ryza (124)
Tom White (111)
Siddharth Seth (109)
Aaron Kimball (107)
Owen O'Malley (105)
Alejandro Abdelnur (103)
Devaraj K (103)
Ramya Sunil (103)
Robert Joseph Evans (101)
Hemanth Yamijala (97)
Steve Loughran (90)
Ted Yu (80)
Eli Collins (77)
Ravi Gummadi (76)
Karthik Kambatla (71)
Mahadev konar (67)
Ravi Prakash (66)
Jeffrey Buell