Home | About | Sematext search-lucene.com search-hadoop.com
clear query|facets|time Search criteria: .   Results from 1 to 10 from 17 (0.05s).
Loading phrases to help you
refine your search...
[HDFS-6658] Namenode memory optimization - Block replicas list - HDFS - [issue]
...Part of the memory consumed by every BlockInfo object in the Namenode is a linked list of block references for every DatanodeStorageInfo (called "triplets"). We propose to change the way we ...
http://issues.apache.org/jira/browse/HDFS-6658    Author: Amir Langer, 2014-10-22, 23:35
[HDFS-7246] Use ids for DatanodeStorageInfo in the BlockInfo triplets - HDFS 6660 - HDFS - [issue]
...Identical to HDFS-6660...
http://issues.apache.org/jira/browse/HDFS-7246    Author: Amir Langer, 2014-10-22, 09:57
[HDFS-6660] Use int instead of object reference to DatanodeStorageInfo in BlockInfo triplets, - HDFS - [issue]
...Map an int index to every DatanodeStorageInfo and use it instead of object reference in the BlockInfo triplets data structure....
http://issues.apache.org/jira/browse/HDFS-6660    Author: Amir Langer, 2014-10-22, 09:57
[HDFS-7244] Reduce Namenode memory using Flyweight pattern - HDFS - [issue]
...Using the flyweight pattern can dramatically reduce memory usage in the Namenode. The pattern also abstracts the actual storage type and allows the decision of whether it is off-heap or not ...
http://issues.apache.org/jira/browse/HDFS-7244    Author: Amir Langer, 2014-10-22, 00:51
[HDFS-7250] Store blocks in slabs rather than a Map inside BlocksMap - HDFS - [issue]
...Key to every block is the replication factor + slab key (address).When setting a different replication factor for a block we need to move its data from one slab to another....
http://issues.apache.org/jira/browse/HDFS-7250    Author: Amir Langer, 2014-10-14, 12:43
[HDFS-7249] Define block slabs per replication factor and initialise them in advance (inc. size config) - HDFS - [issue]
...The plan is to create a slab per replication factor inside the BlocksMap....
http://issues.apache.org/jira/browse/HDFS-7249    Author: Amir Langer, 2014-10-14, 12:42
[HDFS-7248] Use ids for blocks in InodeFile - HDFS - [issue]
...Getting access to a block will be via lookup in the BlocksMap by id....
http://issues.apache.org/jira/browse/HDFS-7248    Author: Amir Langer, 2014-10-14, 12:41
[HDFS-7247] Use ids for Block collection in Block - HDFS - [issue]
...Getting the BlockCollection will be done via lookup by Id....
http://issues.apache.org/jira/browse/HDFS-7247    Author: Amir Langer, 2014-10-14, 12:40
[HDFS-6659] Create a Block List - HDFS - [issue]
...BlockList - An efficient array based list that can extend its capacity with two main features:1. Gaps (result of remove operations) are managed internally without the need for extra memory -...
http://issues.apache.org/jira/browse/HDFS-6659    Author: Amir Langer, 2014-09-04, 15:21
[HDFS-6552] add DN storage to a BlockInfo will not replace the different storage from same DN - HDFS - [issue]
...In BlockInfo - addStorage code looks wrong.At line 10 (below) - we remove the storage we're about to add from the list of storages, then add it. If the aim was to replace the different stora...
http://issues.apache.org/jira/browse/HDFS-6552    Author: Amir Langer, 2014-09-03, 21:34
HDFS (17)
issue (17)
last 7 days (4)
last 30 days (8)
last 90 days (10)
last 6 months (11)
last 9 months (17)
Todd Lipcon (326)
Eli Collins (263)
Harsh J (261)
Colin Patrick McCabe (241)
Tsz Wo (203)
Jing Zhao (175)
Chris Nauroth (166)
Arpit Agarwal (152)
Andrew Wang (143)
Aaron T. Myers (141)
Haohui Mai (141)
Suresh Srinivas (138)
Brandon Li (137)
Kihwal Lee (114)
Daryn Sharp (105)
Ted Yu (83)
Uma Maheswara Rao G (82)
Alejandro Abdelnur (73)
Tsz Wo Nicholas Sze (64)
Konstantin Shvachko (63)
Akira AJISAKA (61)
Stephen Chu (58)
Yongjun Zhang (57)
Steve Loughran (53)
Allen Wittenauer (49)
Amir Langer