No, shards can be spread even across machines. It's when they changed 
default lighttpd from single thread (fast but bottlenecked) to external 
processes (relieve bottleneck but overhead) to worker threads for latent IO 
only.


On Jul 17, 2007, at 2:43 AM, "Raul Miller" <[EMAIL PROTECTED]> wrote:

On 7/17/07, Oleg Kobchenko <[EMAIL PROTECTED]> wrote:
One observation not realizable in J: worker threads
significantly beat worker processes.

The partitioning of their database into shards used
threads and not processes?

-- 
Raul
----------------------------------------------------------------------
For information about J forums see http://www.jsoftware.com/forums.htm



       
____________________________________________________________________________________
Boardwalk for $500? In 2007? Ha! Play Monopoly Here and Now (it's updated for 
today's economy) at Yahoo! Games.
http://get.games.yahoo.com/proddesc?gamekey=monopolyherenow  
----------------------------------------------------------------------
For information about J forums see http://www.jsoftware.com/forums.htm

Reply via email to