Re: [RFC] Convert pgtable cache to slab

From: Jesse Barnes <jbarnes_at_sgi.com>
Date: 2004-10-14 05:28:21
On Wednesday, October 13, 2004 2:07 pm, Luck, Tony wrote:
> >With this patch I got a significant improvement in page fault time.
> >Standard 2.4.x was about 700ns on average.  Generic 2.6.9rc4 is 3-4
> >usec, whereas the slabified pgtcache drops us back down to 600-700 ns.
>
> What was the benchmark you were running when you measured these?
>
> >Tested on zx1 and sn2.
>
> How does this scale on big sn2 systems? I assume that the answers are
> going to be just fine as the slab allocator per-cpu lists should be
> just as nice as local quicklists, but it would be nice to see some
> data.

Yeah, it would be interesting, though page faults in general don't scale very 
well due to the way page_table_lock is used.  Christoph had some patches for 
that, but I don't think he's had time to work on them lately.

> Overall looks nice ... less code, and goes faster too, what more
> could we ask for!
>
> Perhaps "zero_cache" isn't as descriptive a name as it might be (not
> that I have any better suggestions :-(

Maybe pgtable_zero_cache or something?

Jesse
-
To unsubscribe from this list: send the line "unsubscribe linux-ia64" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Received on Wed Oct 13 15:28:58 2004

This archive was generated by hypermail 2.1.8 : 2005-08-02 09:20:31 EST