Home | About | Sematext search-lucene.com search-hadoop.com
clear query|facets|time Search criteria: .   Results from 11 to 20 from 95 (0.137s).
Loading phrases to help you
refine your search...
[HDFS-6221] Webhdfs should recover from dead DNs - HDFS - [issue]
...We've repeatedly observed the jetty acceptor thread silently dying in the DNs.  The webhdfs servlet may also "disappear" and jetty returns non-json 404s.One approach to make webhdfs mor...
http://issues.apache.org/jira/browse/HDFS-6221    Author: Daryn Sharp, 2014-04-09, 17:56
[HDFS-6220] Webhdfs should differentiate remote exceptions - HDFS - [issue]
...Webhdfs's validateResponse should use a distinct exception for json decoded exceptions than it does for servlet exceptions.  Ex. A servlet generated 404 with a json payload should be di...
http://issues.apache.org/jira/browse/HDFS-6220    Author: Daryn Sharp, 2014-04-09, 17:00
[HDFS-6216] Issues with webhdfs and http proxies - HDFS - [issue]
...Umbrella jira for issues related to webhdfs functioning via a http proxy....
http://issues.apache.org/jira/browse/HDFS-6216    Author: Daryn Sharp, 2014-04-09, 16:22
[HDFS-4564] Webhdfs returns incorrect http response codes for denied operations - HDFS - [issue]
...Webhdfs is returning 401 (Unauthorized) instead of 403 (Forbidden) when it's denying operations.  Examples including rejecting invalid proxy user attempts and renew/cancel with an inval...
http://issues.apache.org/jira/browse/HDFS-4564    Author: Daryn Sharp, 2014-04-07, 19:24
[HDFS-1751] Intrinsic limits for HDFS files, directories - HDFS - [issue]
...Enforce a configurable limit on:  the length of a path component  the number of names in a directoryThe intention is to prevent a too-long name or a too-full directory. T...
http://issues.apache.org/jira/browse/HDFS-1751    Author: Daryn Sharp, 2014-03-12, 21:50
[HDFS-5681] renewLease should not hold fsn write lock - HDFS - [issue]
...Lease renewals unnecessarily hold the write lock which reduces throughput.  Currently the fsn lock doubles as an "operational lock" to prevent state transitions.  If the lease mana...
http://issues.apache.org/jira/browse/HDFS-5681    Author: Daryn Sharp, 2014-02-15, 19:02
[HDFS-5946] Webhdfs DN choosing code is flawed - HDFS - [issue]
...HDFS-5891 improved the performance of redirecting webhdfs clients to a DN.  Instead of attempting a connection with a 1-minute timeout, the NN skips decommissioned nodes.The logic appea...
http://issues.apache.org/jira/browse/HDFS-5946    Author: Daryn Sharp, 2014-02-13, 20:11
[HDFS-5947] Improve dead node detection and handling - HDFS - [issue]
...When HeartbeatManager.heartbeatCheck runs: All DNs are scanned to count dead nodes Processes the first dead node If there was a dead node, loops to re-scan all DNs againProcessing the dead n...
http://issues.apache.org/jira/browse/HDFS-5947    Author: Daryn Sharp, 2014-02-13, 16:12
[HDFS-5875] Add iterator support to INodesInPath - HDFS - [issue]
..."Resolve as you go" inode iteration will help with the implementation of alternative locking schemes.  It will also be the pre-cursor for resolving paths once and only once per operatio...
http://issues.apache.org/jira/browse/HDFS-5875    Author: Daryn Sharp, 2014-02-04, 03:29
[HDFS-5514] FSNamesystem's fsLock should allow custom implementation - HDFS - [issue]
...Changing fsLock from a ReentrantReadWriteLock to an API compatible class that encapsulates the rwLock will allow for more sophisticated locking implementations such as fine grain locking....
http://issues.apache.org/jira/browse/HDFS-5514    Author: Daryn Sharp, 2014-01-28, 23:36
Sort:
project
Hadoop (125)
HDFS (93)
MapReduce (41)
type
issue (83)
mail # dev (6)
mail # user (6)
date
last 7 days (5)
last 30 days (14)
last 90 days (21)
last 6 months (26)
last 9 months (95)
author
Todd Lipcon (312)
Eli Collins (261)
Harsh J (261)
Colin Patrick McCabe (222)
Tsz Wo (209)
Jing Zhao (155)
Chris Nauroth (151)
Suresh Srinivas (136)
Aaron T. Myers (134)
Haohui Mai (118)
Brandon Li (115)
Arpit Agarwal (101)
Andrew Wang (100)
Kihwal Lee (95)
Daryn Sharp (90)