From owner-freebsd-hackers Tue Apr 18 01:55:09 1995 Return-Path: hackers-owner Received: (from majordom@localhost) by freefall.cdrom.com (8.6.10/8.6.6) id BAA25196 for hackers-outgoing; Tue, 18 Apr 1995 01:55:09 -0700 Received: from godzilla.zeta.org.au (godzilla.zeta.org.au [203.2.228.34]) by freefall.cdrom.com (8.6.10/8.6.6) with ESMTP id BAA25179 for ; Tue, 18 Apr 1995 01:54:52 -0700 Received: (from bde@localhost) by godzilla.zeta.org.au (8.6.9/8.6.9) id SAA14349; Tue, 18 Apr 1995 18:51:13 +1000 Date: Tue, 18 Apr 1995 18:51:13 +1000 From: Bruce Evans Message-Id: <199504180851.SAA14349@godzilla.zeta.org.au> To: julian@ref.tfs.com, luigi@labinfo.iet.unipi.it Subject: Re: help with timeouts Cc: chitra@CS.SunySB.EDU, freebsd-hackers@FreeBSD.org Sender: hackers-owner@FreeBSD.org Precedence: bulk >> There is already code that 'turns up' the system clock frequency >> (I believe the pc-audio code to be exact) to (I think) 10KHz >> so you could do similar and get 100uSec time, >pcaudio runs at 16 KHz, I think. This means one interrupt every >62.5 uS; this is *not* something you want to run continuously on >your system: the overhead is high, some interrupts are missed, >even on my 486/66, and you see you clock slowing down (due to the >missed interrupts). A 486/66 shouldn't miss clock interrupts at 16 KHz unless it is handicapped by a bus-hogging (broken) busmastering controller or multiple high speed FIFOed serial lines (about 3 lines with 16550's at 115200 bps). Bruce