On Friday 10 February 2006 01:21, Nick Piggin wrote:

Con Kolivas wrote:

quoted

I really don't want to go throwing out pagecache without some smart
semantics and then swap in random stuff that could be crap I agree. The
answer to this is for the vm itself to have an ageing algorithm like the
clockpro stuff which does this in a smart way. It could certainly age
away the updatedb wrinkles and leave some free ram - which would help/be
helped by prefetching.

AFAIK clockpro will not leave free ram, will it?

Getting a little hand-wavy; I don't think the updatedb problem needs to
be fixed by a really fancy page reclaim algorithm (IMO, and that's not to
say that a fancy reclaim algorithm wouldn't be nice for other reasons).
Just small improvements here and there, and there will always be a tradeoff
between throughput and interactive pagein latency so in the end it might
need a tunable (hey there is one - maybe it needs to be improved)

Well I have a handful of patches for just that issue... However they all fall 
into the "it's too hard to prove to Andrew and Nick that they help" so I've 
never bothered trying to push them to mainline.

Cheers,
Con

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>