Re: [QUICKLIST 0/4] Arch independent quicklists V2

From: David Miller <davem@davemloft.net>
To: mpm@selenic.com
Cc: jeremy@goop.org, nickpiggin@yahoo.com.au,
	akpm@linux-foundation.org, clameter@sgi.com, linux-mm@kvack.org,
	linux-kernel@vger.kernel.org
Subject: Re: [QUICKLIST 0/4] Arch independent quicklists V2
Date: Tue, 13 Mar 2007 14:48:05 -0700 (PDT)	[thread overview]
Message-ID: <20070313.144805.28789513.davem@davemloft.net> (raw)
In-Reply-To: <20070313211435.GP10394@waste.org>

From: Matt Mackall <mpm@selenic.com>
Date: Tue, 13 Mar 2007 16:14:35 -0500

> Well you -could- do this:
> 
> - reuse a long in struct page as a used map that divides the page up
>   into 32 or 64 segments
> - every time you set a PTE, set the corresponding bit in the mask
> - when we zap, only visit the regions set in the mask
> 
> Thus, you avoid visiting most of a PMD page in the sparse case,
> assuming PTEs aren't evenly spread across the PMD.
> 
> This might not even be too horrible as the appropriate struct page
> should be in cache with the appropriate bits of the mm already locked,
> etc.

Yes, I've even had that idea before.

You can even hide it behind pmd_none() et al., the generic VM
doesn't even have to know that the page table macros are doing
this optimization.