+1

Sweet.

On Mon, Dec 21, 2009 at 11:06 AM, Andrew Purtell <[email protected]> wrote:
> Well that should be a blocker on trunk and 0.20 branch...
>
> Nice Ryan.
>
>  - Andy
>
>
> ----- Original Message ----
>> From: Ryan Rawson <[email protected]>
>> To: [email protected]
>> Sent: Sun, December 20, 2009 11:49:54 PM
>> Subject: i made this fix in my own code
>>
>> https://gist.github.com/a0abf6092abf63d394c2
>>
>> It is very very disturbing... basically cache delete code in the
>> client doesnt work at all.  I was relying on that code in my new
>> threaded-put implementation, but it wasnt working and my entire
>> enterprise was failing.
>>
>> I have a kick ass patch I'll put up soon. I am seeing substantially
>> higher aggregate performance left and right. On a huge region count
>> table (1200), previously a single thread was lucky to get 2000
>> rows/sec (small rows).  Now I can do 16k rows/sec.  In a map reduce
>> situation performance is up there at like 300k ops/sec and stays high
>> with very few brownouts.
>>
>> Previously I was having problems with cluster performance increasingly
>> frequently dipping to 0, but now with this multithreaded ability,
>> things are just groovy.  We survive a split even!
>>
>> -ryan
>
>
>
>
>
>

Reply via email to