Why not let the fs handle this ??

Brian Moon brianm at dealnews.com
Wed Jun 7 17:38:53 UTC 2006

Jon Drukman wrote:
> Has this actually worked out well in practice for anybody?  I've found 
> that losing one machine (out of about 100) results in so much db 
> thrashing as the keys get repopulated into different places that the 
> site becomes basically unusable until enough of the cache has been 
> regenerated (5-10 minutes if i'm lucky).

For us, if just one server goes down, the other servers still server
their normal stuff.  Only the keys that would have gone to/from the down
server are reshuffled.

Now, if we add or remove a server from the pool in code, that is
different.  But, we never do that.  Are you removing a server from the
pool manually if it goes down?  If so, that will result in a full
reshuffle of your keys.


Brian Moon
Its good to be cheap =)

More information about the memcached mailing list