The benchmark numbers on the page were done with 4 client threads. I
did a little testing with more and there wasn't any problem. I didn't
expect that it would given that there were no changes to the
networking code, locking or thread management.

I plan on making memcached-prefix into a plugin engine when pluggable
engine branch is more stable. Right now the new commands are a compile
time option. And it reverts back to using the standard memcached
hashtable if you comment out the line "#define SKIPLIST" in
memcached.h.

-Josh

On Apr 13, 9:26 pm, Mike Panchenko <[email protected]> wrote:
> Interesting... have you tested it with multiple clients? Do you think
> there's any reason to believe that more clients would cause degradation?
>
> Have you considered making this an option? I'm assuming the most common
> response to this will be "Memcached works very well for what it was
> designed. Don't mess with that."
>
> Mike.
>
> On Mon, Apr 13, 2009 at 9:10 PM, Josh Dybnis <[email protected]> wrote:
>
> > memcached-prefix is an experimental fork off of the memcached 1.3
> > development branch. It adds commands pget and pdelete that operate on
> > ranges of keys having a common prefix. The new commands can be used as
> > a simple namespace mechanism. It also adds a memcachedb compatible
> > rget command.
>
> > Performance is very close to the standard memcached (see the
> > benchmarks on the project page). Space usage is also roughly
> > unchanged.
>
> > Project page:http://jdybnis.github.com/memcached/

Reply via email to