ketama - a consistent hashing algo for memcache clients

Dustin Sallings dustin at spy.net
Tue Apr 10 21:35:37 UTC 2007


On Apr 10, 2007, at 9:56 , Richard Jones wrote:

> Every time we added memcached servers to the pool, the rehashing of  
> all keys
> would kill our database while the cache filled up again. We  
> implemented a
> consistent hashing algorithm that our memcached clients are now  
> using to map
> keys to servers. Now we can add new memcached servers without causing
> chaos :)
>
> Here is the blurb and the code:
> http://www.last.fm/user/RJ/journal/2007/04/10/392555/

	This is a very interesting idea, and I'd like to add a consistent  
hash driver to my java interface, but there's a bit of gap between  
your writeup and what the implementation.

	In the java interface, all I see is that you've added a new hash  
type that's based off an MD5.  Is that actually an important detail?   
It seems like you should be able to use any hash that produces an  
even 32-bits.

	Is it OK if I use your C implementation as a specification?

-- 
Dustin Sallings


-------------- next part --------------
An HTML attachment was scrubbed...
URL: http://lists.danga.com/pipermail/memcached/attachments/20070410/37571258/attachment.html


More information about the memcached mailing list