invalidation by namespace Re: Listing all keys on a server: why?

[Serhat Sakarya]

On 7/29/06, Martin Atkins <mart at degeneration.co.uk> wrote:
>
>
> The "best practice" for memcached is not to do remapping on node failure,
> despite that being the plan to start with, because node deaths are often
> brief and so all you really achieve is screwing up the hash so that all of
> the keys need to get recreated, and so you end up storing loads of things
> twice.


I agree that this is more responsible from a consistency standpoint, but in
practical situations with only 2-5 memcache nodes, a single failure would
increase the load on the backend by a rather large margin.

One compromise may be to lower the expiration times for entries not on their
"home" nodes. That way, stale data should disappear much more quickly and
the load on the backend is nicely mitigated.

Does that sound like a reasonable approach?

Regards,

Serhat
-------------- next part --------------
An HTML attachment was scrubbed...
URL: http://lists.danga.com/pipermail/memcached/attachments/20060729/6d36bb86/attachment.html