Home | About | Sematext search-lucene.com search-hadoop.com
clear query|facets|time Search criteria: .   Results from 51 to 60 from 80 (0.169s).
Loading phrases to help you
refine your search...
Re: High throughput input, low latency output? - HBase - [mail # user]
...We found that 2 cores is not enough to run hbase.  1 core can easily get tied up with a compaction while the other is doing garbage collection.  That doesn't leave any headroom for...
   Author: Matt Corgan, 2011-10-07, 20:15
Re: HBase HMaster/HServer 32bit/64bit issue - HBase - [mail # user]
...You'd probably have more of an issue with the amount of memory on 32 bit instance types.  ~1.7gb.   On Wed, Sep 21, 2011 at 12:45 PM, Ronen Itkin  wrote:  ...
   Author: Matt Corgan, 2011-09-21, 20:00
[expand - 6 more] - Re: prefix compression implementation - HBase - [mail # dev]
...jacek >> It is a huge chance. It would be great if we could prototype a few things. Especially I would like to avoid any optimizations before we know a got way to measure them.  m...
   Author: Matt Corgan, 2011-09-21, 01:04
ByteBuffer usage - HBase - [mail # dev]
...Ryan said this on an earlier email:  So if the HCell or whatever ends up returning ByteBuffers, then that plays straight in to scatter/gather NIO calls, and if some of them are DBB, the...
   Author: Matt Corgan, 2011-09-20, 19:03
[expand - 1 more] - Re: HBase as a large, auto-partitioned, sorted, *in-memory* database (was: Re: prefix compression implementation) - HBase - [mail # dev]
...inline below:  On Mon, Sep 19, 2011 at 10:08 PM, Stack  wrote:  is  i've given it some thought, but i think it can wait till after the block format stuff is in place. &nb...
   Author: Matt Corgan, 2011-09-20, 18:23
CPU cache effectiveness - HBase - [mail # dev]
...I mentioned a bunch of stuff in that prefix compression email about cache lines, prefetching, trie node sizes, etc...  The gist of it all is that memory has become relatively slow to th...
   Author: Matt Corgan, 2011-06-04, 23:25
[expand - 4 more] - Re: prefix compression - HBase - [mail # dev]
...Ah - I see.  It's generating multiple duplicate timestamps per millisecond, so there are fewer than 50mm unique strings.  Duplicates just require incrementing a counter.  Agre...
   Author: Matt Corgan, 2011-06-04, 04:57
Re: feature request (count) - HBase - [mail # user]
...Storing numPuts, numDelets, and maxVersions of each block in the block index could be useful.  If a block is all puts, no deletes, and maxVersions=1, then you are more sure of the count...
   Author: Matt Corgan, 2011-06-03, 23:12
[expand - 1 more] - Re: block index comparator - HBase - [mail # user]
...I see now.  Comparator class is written into the HFile.  Got confused because the tests use a ByteArrayComparator even though most HFiles will use KeyComparator (i think...)  ...
   Author: Matt Corgan, 2011-05-27, 20:14
[expand - 2 more] - Re: a question storefileIndexSize - HBase - [mail # user]
...I was thinking it would be a nice feature if each time an hfile was written it kept a count of the raw bytes (before compression) to make it easy to compare to the file size on disk.  I...
   Author: Matt Corgan, 2011-05-25, 23:49
HBase (80)
Avro (1)
mail # dev (35)
mail # user (34)
issue (11)
last 7 days (0)
last 30 days (0)
last 90 days (0)
last 6 months (0)
last 9 months (80)
Ted Yu (1296)
Stack (972)
Andrew Purtell (737)
Jean-Daniel Cryans (733)
stack (677)
Jean-Marc Spaggiari (332)
Jimmy Xiang (307)
Jonathan Hsieh (290)
Elliott Clark (255)
Enis Soztutar (249)
lars hofhansl (249)
Lars Hofhansl (240)
Nick Dimiduk (207)
Nicolas Liochon (200)
Sergey Shelukhin (195)
Doug Meil (189)
Todd Lipcon (176)
Lars George (172)
ramkrishna.s.vasudevan (172)
Matteo Bertozzi (168)
Anoop Sam John (150)
Ryan Rawson (126)
Jonathan Gray (114)
Jesse Yates (104)
Michael Segel (93)
Matt Corgan