Home | About | Sematext search-lucene.com search-hadoop.com
clear query|facets|time Search criteria: .   Results from 11 to 20 from 44 (0.072s).
Loading phrases to help you
refine your search...
[HBASE-8778] Region assigments scan table directory making them slow for huge tables - HBase - [issue]
...On a table with 130k regions it takes about 3 seconds for a region server to open a region once it has been assigned.Watching the threads for a region server running 0.94.5 that is opening m...
http://issues.apache.org/jira/browse/HBASE-8778    Author: Dave Latham, 2013-08-07, 02:40
[HBASE-9132] Use table dir modtime to avoid scanning table dir to check cached table descriptor in 0.94 - HBase - [issue]
...As described in HBASE-8778, anything that needs to read table descriptors (such as region assignments) currently results in a table directory scan which is slow on tables with many regions. ...
http://issues.apache.org/jira/browse/HBASE-9132    Author: Dave Latham, 2013-08-06, 17:20
[HBASE-9133] Use table dir modtime to avoid scanning table dir to check cached table descriptor - HBase - [issue]
...As described in HBASE-8778, anything that needs to read table descriptors (such as region assignments) currently results in a table directory scan which is slow on tables with many regions. ...
http://issues.apache.org/jira/browse/HBASE-9133    Author: Dave Latham, 2013-08-06, 04:48
[HBASE-9089] HRegion.heapSize is missing many fields - HBase - [issue]
...HRegion's heapSize method is missing many fields from its calculation.The static value DEEP_OVERHEAD is missing these:  // 1 x HashMap - coprocessorServiceHandlers  // 6 ...
http://issues.apache.org/jira/browse/HBASE-9089    Author: Dave Latham, 2013-07-30, 17:37
HRegion heapSize out of date - HBase - [mail # dev]
...While working on HBASE-8877 I noticed that HRegion.heapSize was missing many things.  I fixed FIXED_OVERHEAD as part of the issue, but didn't try to fix about a dozen missing fields fro...
   Author: Dave Latham, 2013-07-29, 22:33
removing lock ids from RegionObserver - HBase - [mail # dev]
...In HBASE-8877 I'm proposing to change row locks to be reentrant and thread based rather than tracking lock ids.  Part of that change would mean altering the RegionObserver coprocessor. ...
   Author: Dave Latham, 2013-07-06, 21:49
Re: data loss after cluster wide power loss - HBase - [mail # user]
...On Mon, Jul 1, 2013 at 4:52 PM, Azuryy Yu  wrote:  Set dfs.datanode.synconclose to true  See https://issues.apache.org/jira/browse/HDFS-1539...
   Author: Dave Latham, 2013-07-02, 00:34
region opening slow on large tables - HBase - [mail # dev]
...I'd really appreciate some input on HBASE-8778 from the developers.  Short summary: When opening regions, the region server (via FSTableDescriptors) scans the entire table directory to ...
   Author: Dave Latham, 2013-06-24, 17:32
[HBASE-8605] Backport HBASE-6921 to 0.94 - HBase - [issue]
...HBASE-8014 ported FLURRY-6915 to 0.94 but FLURRY-6921 extended the work of FLURRY-6915 so should also be backported....
http://issues.apache.org/jira/browse/HBASE-8605    Author: Dave Latham, 2013-05-25, 06:23
[HBASE-8025] zkcli fails when SERVER_GC_OPTS is enabled - HBase - [issue]
...HBASE-7091 added logic to separate GC logging options for some client commands versus server commands.  It uses a list of known client commands ("shell" "hbck" "hlog" "hfile" "zkcli") a...
http://issues.apache.org/jira/browse/HBASE-8025    Author: Dave Latham, 2013-03-23, 04:53
Sort:
project
HBase (43)
MapReduce (2)
Zookeeper (2)
HDFS (1)
type
mail # user (17)
issue (16)
mail # dev (11)
date
last 7 days (0)
last 30 days (0)
last 90 days (0)
last 6 months (3)
last 9 months (44)
author
Ted Yu (1086)
Stack (930)
Jean-Daniel Cryans (730)
Andrew Purtell (590)
stack (573)
Jonathan Hsieh (276)
Jean-Marc Spaggiari (270)
Jimmy Xiang (268)
Elliott Clark (232)
Lars Hofhansl (225)
lars hofhansl (224)
Enis Soztutar (216)
Sergey Shelukhin (195)
Doug Meil (187)
Lars George (169)
Dave Latham