Re: [ltt-dev] [PATCH] Fix dirty page accounting in redirty_page_for_writepage()

[Mathieu Desnoyers <compudj@krystal.dyndns.org>]

* Christoph Lameter (cl@linux.com) wrote:
> On Fri, 1 May 2009, Mathieu Desnoyers wrote:
> 
> > What I do here is to let those u8 counters increment as free-running
> > counters. Yes, they will periodically overflow the 8 bits. But I don't
> > rely on this for counting the number of increments we need between
> > global counter updates : I use the bitmask taken from the threshold
> > value (which is now required to be a power of two) to detect 0, 1, 2, 3,
> > 4, 5, 6 or 7-bit counter overflow. Therefore we can still have the kind
> > of granularity currently provided. The only limitation is that we have
> > to use powers of two for the threshold, so we end up counting in power
> > of two modulo, which will be unaffected by the u8 overflow.
> 
> Ack. Got it. Looks good.
> 

Modifying mmzone.h "struct per_cpu_pageset" so it uses percpu dynamic
allocation seems to be the far-reaching part of the modification (of a
subsystem I'm not completely familiar with, including NUMA special
cases). Is there any patch already doing this kind of modification
floating around ?

I'd be glad to give a try at some percpu_add_return counters experiments
if percpu struct per_cpu_pageset allocation happens to be already
available.

Mathieu

-- 
Mathieu Desnoyers
OpenPGP key fingerprint: 8CD5 52C3 8E3C 4140 715F  BA06 3F25 A8FE 3BAE 9A68