Subject: Re: Faster pipes, now with uvm_loan()
To: Thor Lancelot Simon <tls@rek.tjls.com>
From: Hubert Feyrer <hubert.feyrer@informatik.fh-regensburg.de>
List: tech-kern
Date: 04/10/2001 23:36:11
On Tue, 10 Apr 2001, Thor Lancelot Simon wrote:
> > BTW, I see the performance drop with hbench too - the bandwidth
> > for 128KB transfer size is ~50% of 64KB one on my PIII.
>
> I ran into an issue like this (oh, boy, did I ever!) with CRC-32 in
> one of my programs. Doing a whole large buffer at once stomped on all
> the cache lines the CRC table (think, the kernel stack or whatever other
> might be in the D cache) and code itself (remember, the L2 cache is not
> split I/D) was in, causing cache thrashing as the data being worked on
> and the "other process state" fought for lines. I bet paring things down
> to 64K or even smaller chunks done in a loop will in fact help.
Would something like "page coloring" help here? (Do we have that?)
- Hubert
--
Hubert Feyrer <hubert.feyrer@informatik.fh-regensburg.de>