Home | About | Sematext search-lucene.com search-hadoop.com
 Search Hadoop and all its subprojects:

Switch to Plain View
HBase, mail # user - Re: 0.92 and Read/writes not scaling


+
Juhani Connolly 2012-04-03, 02:52
+
Jonathan Hsieh 2012-04-03, 00:21
+
Juhani Connolly 2012-04-03, 03:02
+
Jonathan Hsieh 2012-04-03, 03:19
+
Stack 2012-04-03, 03:50
+
Jonathan Hsieh 2012-04-03, 16:56
+
Stack 2012-04-03, 17:42
+
Juhani Connolly 2012-04-05, 01:45
+
Ted Yu 2012-04-05, 02:43
+
Juhani Connolly 2012-04-05, 03:02
+
Todd Lipcon 2012-04-14, 03:02
+
Stack 2012-04-14, 04:06
+
Jonathan Hsieh 2012-04-14, 12:43
+
Todd Lipcon 2012-04-15, 06:28
+
Alok Singh 2012-04-02, 17:15
+
Juhani Connolly 2012-04-03, 02:56
+
Stack 2012-04-02, 17:41
+
Juhani Connolly 2012-03-19, 10:41
+
Ramkrishna.S.Vasudevan 2012-03-19, 11:03
+
Mingjian Deng 2012-03-19, 11:56
+
Juhani Connolly 2012-03-19, 12:02
+
Ramkrishna.S.Vasudevan 2012-03-19, 12:27
+
Christian Schäfer 2012-03-19, 12:21
+
Juhani Connolly 2012-03-19, 12:31
+
Matt Corgan 2012-03-19, 16:55
+
Juhani Connolly 2012-03-21, 03:09
+
Mikael Sitruk 2012-03-21, 05:29
+
Juhani Connolly 2012-03-23, 07:40
+
Stack 2012-03-26, 16:37
+
Juhani Connolly 2012-03-23, 07:48
+
Matt Corgan 2012-03-26, 13:58
+
Stack 2012-03-26, 16:42
+
Juhani Connolly 2012-03-26, 17:08
+
Todd Lipcon 2012-03-27, 01:43
+
Juhani Connolly 2012-03-27, 03:18
+
Juhani Connolly 2012-03-28, 08:27
+
Buckley,Ron 2012-03-28, 12:41
+
Stack 2012-03-28, 17:12
Copy link to this message
-
RE: 0.92 and Read/writes not scaling
Buckley,Ron 2012-03-28, 17:56
Stack,

We're about 80% random read and 20% random write. So, that would have been the mix that we were running.

We'll try a test with Nagel On and then Nagel off, random write only, later this afternoon and see if the same pattern emerges.

Ron

-----Original Message-----
From: [EMAIL PROTECTED] [mailto:[EMAIL PROTECTED]] On Behalf Of Stack
Sent: Wednesday, March 28, 2012 1:12 PM
To: [EMAIL PROTECTED]
Subject: Re: 0.92 and Read/writes not scaling

On Wed, Mar 28, 2012 at 5:41 AM, Buckley,Ron <[EMAIL PROTECTED]> wrote:
> For us, setting these two, got rid of  all of the 20 and 40 ms response
> times and dropped the average response time we measured from HBase by
> more than half.  Plus, we can push HBase a lot harder.
>

That had an effect on random read workload only Ron?
Thanks,
St.Ack
+
Juhani Connolly 2012-03-29, 02:36
+
Juhani Connolly 2012-03-26, 16:48
+
Mikael Sitruk 2012-03-26, 14:21
+
Juhani Connolly 2012-03-26, 16:59
+
Stack 2012-03-20, 19:27
+
Juhani Connolly 2012-03-19, 11:09
+
Stack 2012-03-26, 16:29
+
Juhani Connolly 2012-03-26, 17:02