From owner-freebsd-hackers  Sun Oct  8 09:24:32 1995
Return-Path: owner-hackers
Received: (from root@localhost)
          by freefall.freebsd.org (8.6.12/8.6.6) id JAA06260
          for hackers-outgoing; Sun, 8 Oct 1995 09:24:32 -0700
Received: from etinc.com (etinc-gw.new-york.net [165.254.13.209])
          by freefall.freebsd.org (8.6.12/8.6.6) with ESMTP id JAA06254
          for <hackers@freebsd.org>; Sun, 8 Oct 1995 09:24:27 -0700
Received: from et.htp.com (et.htp.com [199.171.4.228]) by etinc.com (8.6.11/8.6.9) with SMTP id MAA26478 for <hackers@freebsd.org>; Sun, 8 Oct 1995 12:32:11 -0400
Date: Sun, 8 Oct 1995 12:32:11 -0400
Message-Id: <199510081632.MAA26478@etinc.com>
X-Sender: dennis@etinc.com
X-Mailer: Windows Eudora Version 2.0.3
Mime-Version: 1.0
Content-Type: text/plain; charset="us-ascii"
To: hackers@freebsd.org
From: dennis@etinc.com (dennis)
Subject: Re: VLB Disk Controllers
Sender: owner-hackers@freebsd.org
Precedence: bulk


>>Yup, but your whole machine is affected by a PIO device.
>
>That's mainly because IDE PIO is slow, not because it's PIO.  The
>overhead for SCSI DMA is not insignificant.  For the BT455C, which
>has a DMA speed of up to 40MB/sec (I doubt that my bus can keep up
>with this), the overhead for reading from a Grand Prix at 5MB/sec
>seems to be about 27%.  This is hard to measure accurately.  I
>measured it by running a hog process in the background: on an idle
>system it took 7.58 sec (real) and while transferring it took 10.42
>sec.  7.58/10.42 = 73%.

Realize that much of this is highly dependent on the MB. Every make of MB is
different...literally. We've measured lots of them (with a scope) and its
almost impossible to compare any two these days.

Dennis