From owner-freebsd-hackers  Mon Oct  7 18:26:52 1996
Return-Path: owner-hackers
Received: (from root@localhost)
          by freefall.freebsd.org (8.7.5/8.7.3) id SAA17191
          for hackers-outgoing; Mon, 7 Oct 1996 18:26:52 -0700 (PDT)
Received: from parkplace.cet.co.jp (parkplace.cet.co.jp [202.32.64.1])
          by freefall.freebsd.org (8.7.5/8.7.3) with ESMTP id SAA17185
          for <Hackers@FreeBSD.ORG>; Mon, 7 Oct 1996 18:26:49 -0700 (PDT)
Received: from localhost (michaelh@localhost) by parkplace.cet.co.jp (8.8.0/CET-v2.1) with SMTP id BAA19878 for <Hackers@FreeBSD.ORG>; Tue, 8 Oct 1996 01:26:47 GMT
Date: Tue, 8 Oct 1996 10:26:47 +0900 (JST)
From: Michael Hancock <michaelh@cet.co.jp>
To: FreeBSD Hackers <Hackers@FreeBSD.ORG>
Subject: Determining L2 cache size
Message-ID: <Pine.SV4.3.93.961008101431.19738A-100000@parkplace.cet.co.jp>
MIME-Version: 1.0
Content-Type: TEXT/PLAIN; charset=US-ASCII
Sender: owner-hackers@FreeBSD.ORG
X-Loop: FreeBSD.org
Precedence: bulk

Being able to probe for cache size would be a good thing for things like
page coloring, etc.

I've been looking around to see if it's being done elsewhere. 

I noticed UnixWare has a /system/processor fs which stores characteristics
of the CPU.  It has a field for cachesize.

I'm not sure if it's being used for the Intel architecture, I'll have to
probe a little bit...

typedef struct procfile {
        int status;
        int chip;
        int clockspeed; /* in MHz */
        int cachesize;  /* in Kbytes */
        int fpu;
        int bdrivers;
        timestruc_t modtime;
} procfile_t;


Regards,


Mike Hancock