Home | About | Sematext search-lucene.com search-hadoop.com
clear query|facets|time Search criteria: .   Results from 31 to 40 from 46 (0.067s).
Loading phrases to help you
refine your search...
Re: How to remove three disks from three different nodes in a ten node cluster in less than an hour without losing replicas? - HDFS - [mail # user]
...It sounds like what you would like is a way to decommission just one storage directory on the DataNode. We don't currently support that.  You might be able to get something approaching ...
   Author: Colin McCabe, 2013-02-04, 22:53
Re: JournalNode desynchronized - HDFS - [mail # user]
...You can rsync from one of your other JournalNodes into the correct directory on the new one. You can safely do this while the old one is running.  In the future, there will be a way to ...
   Author: Colin McCabe, 2013-02-04, 22:49
HDFS-347 (Short-circuit local reads with security) - HDFS - [mail # dev]
...Hi all,  The HDFS-347 branch implements short-circuit local reads with support for security.  This is just a "heads up" that it is getting ready to merge, and we will probably send...
   Author: Colin McCabe, 2013-01-16, 04:41
Re: /etc/hosts - HDFS - [mail # user]
...Hi Pavel,  There's some information about the need for 127.0.1.1 here:  http://www.leonardoborda.com/blog/127-0-1-1-ubuntu-debian/  If you have more questions about this, I re...
   Author: Colin McCabe, 2013-01-14, 20:36
[expand - 1 more] - Re: question about ZKFC daemon - HDFS - [mail # user]
...On Mon, Jan 14, 2013 at 11:49 AM, Colin McCabe  wrote:  Er, this should read "You also need to run ZooKeeper on at least 3 nodes."  ZKFC, which talks to ZooKeeper, runs on onl...
   Author: Colin McCabe, 2013-01-14, 20:34
Re: Release of Decompressor resources in CodecPool - HDFS - [mail # dev]
...I think that you're right.  It looks like BuiltInGzipDecompressor, which is marked as DoNotPool, ends up owning some JNI-managed resources.  In this case, just relying on the GC to...
   Author: Colin McCabe, 2012-12-27, 21:08
Re: Recovering fsImage from Namenode Logs - HDFS - [mail # dev]
...On Thu, Dec 20, 2012 at 12:33 AM, ishan chhabra  wrote:  The generation stamp is stored by the datanode in the block directory, as part of the .meta filename.  For example, if...
   Author: Colin McCabe, 2012-12-27, 20:41
Re: FSDataInputStream.read returns -1 with growing file and never continues reading - HDFS - [mail # dev]
...Also, read() returning -1 is not an error, it's EOF.  This is the same as for the regular Java InputStream.  best, Colin   On Thu, Dec 20, 2012 at 10:32 AM, Christoph Rupp &nb...
   Author: Colin McCabe, 2012-12-27, 20:37
Re: Can we declare some HDFS nodes "primary" - HDFS - [mail # user]
...It seems like those 10 nodes out of 500 would be a hot spot for writes, if there was a hard requirement that they accept all writes. This might be acceptable on a very read-focused workload,...
   Author: Colin McCabe, 2012-12-11, 23:53
Re: Hadoop V/S Cassandra - HDFS - [mail # user]
...On Thu, Dec 6, 2012 at 8:55 AM, yogesh dhari  wrote:  As Harsh commented, HDFS doesn't have a single point of failure any more.  Hadoop and Cassandara are not really competito...
   Author: Colin McCabe, 2012-12-06, 19:27
Sort:
project
HDFS (42)
Hadoop (34)
MapReduce (13)
Spark (4)
HBase (1)
type
mail # dev (39)
mail # user (7)
date
last 7 days (1)
last 30 days (4)
last 90 days (6)
last 6 months (8)
last 9 months (46)
author
Todd Lipcon (326)
Eli Collins (263)
Harsh J (261)
Colin Patrick McCabe (235)
Tsz Wo (205)
Jing Zhao (173)
Chris Nauroth (166)
Aaron T. Myers (141)
Andrew Wang (139)
Suresh Srinivas (138)
Arpit Agarwal (137)
Brandon Li (135)
Haohui Mai (135)
Kihwal Lee (114)
Daryn Sharp (104)
Uma Maheswara Rao G (82)
Ted Yu (80)
Alejandro Abdelnur (70)
Akira AJISAKA (62)
Konstantin Shvachko (60)
Stephen Chu (57)
Tsz Wo Nicholas Sze (55)
Steve Loughran (52)
Yongjun Zhang (52)
Azuryy Yu (48)
Colin McCabe