From owner-freebsd-hardware  Wed Feb 19 12:00:03 1997
Return-Path: <owner-hardware>
Received: (from root@localhost)
          by freefall.freebsd.org (8.8.5/8.8.5) id MAA15066
          for hardware-outgoing; Wed, 19 Feb 1997 12:00:03 -0800 (PST)
Received: from Sisyphos.MI.Uni-Koeln.DE (Sisyphos.MI.Uni-Koeln.DE [134.95.212.10])
          by freefall.freebsd.org (8.8.5/8.8.5) with SMTP id LAA15017;
          Wed, 19 Feb 1997 11:59:26 -0800 (PST)
Received: from x14.mi.uni-koeln.de (annexr3-5.slip.Uni-Koeln.DE) by Sisyphos.MI.Uni-Koeln.DE with SMTP id AA27652
  (5.67b/IDA-1.5); Wed, 19 Feb 1997 20:59:18 +0100
Received: (from se@localhost) by x14.mi.uni-koeln.de (8.8.5/8.6.9) id UAA02253; Wed, 19 Feb 1997 20:59:15 +0100 (CET)
Message-Id: <19970219205914.RB27571@x14.mi.uni-koeln.de>
Date: Wed, 19 Feb 1997 20:59:14 +0100
From: se@freebsd.org (Stefan Esser)
To: msmith@atrad.adelaide.edu.au (Michael Smith)
Cc: se@freebsd.org (Stefan Esser), hardware@freebsd.org
Subject: Re: _big_ IDE disks?
References: <19970213175603.JR15968@x14.mi.uni-koeln.de> <199702140035.LAA21975@genesis.atrad.adelaide.edu.au>
X-Mailer: Mutt 0.60-PL0
Mime-Version: 1.0
In-Reply-To: <199702140035.LAA21975@genesis.atrad.adelaide.edu.au>; from Michael Smith on Feb 14, 1997 11:05:39 +1030
Sender: owner-hardware@freebsd.org
X-Loop: FreeBSD.org
Precedence: bulk

On Feb 14, msmith@atrad.adelaide.edu.au (Michael Smith) wrote:
> wdc0 at 0x1f0-0x1f7 irq 14 flags 0x80ff80ff on isa
> wdc0: unit 0 (wd0): <Maxtor 85120 A8  ->, 32-bit, multi-block-16
> wd0: 788MB (10003392 sectors), 9924 cyls, 16 heads, 63 S/T, 512 B/S

> IOZONE performance measurements:
>         8339742 bytes/second for writing the file
>         9316631 bytes/second for reading the file
> 
>               -------Sequential Output-------- ---Sequential Input-- --Random--
>               -Per Char- --Block--- -Rewrite-- -Per Char- --Block--- --Seeks---
> Machine    MB K/sec %CPU K/sec %CPU K/sec %CPU K/sec %CPU K/sec %CPU  /sec %CPU
>           128  3858 71.8  8178 28.2  2486 14.1  4210 71.1  8280 28.1 117.0  4.7

Ok. Quite good performance for an (E)IDE drive ...
Bruce Evans recently pointed out, that the CPU% load actually
is 100%, but the cycles not accounted for are spent in the WD
driver's interrupt handler.
This indicates, that 30% of a P5-166 is required for 4MB/s,
or that the CPU overhead for the PIO mode transfer is some 8%
of the P5-166 per MB/s ...
The 8MB/s on block transfers should thus correspond to some 
65%CPU spent in the interrupt handler, which would mean, that 
the CPU is near 100% busy doing these transfers (while there 
would be some 70% of the CPU left for other processes, if the
disk was driven by a bus-master controller.)

> (Just for amusement, I ran iozone without any of the go-faster options 
> for the 'wd' driver enabled :
> 
> Writing the 128 Megabyte file, 'iozone.tmp'...22.453125 seconds
> Reading the file...23.945312 seconds
> 
> IOZONE performance measurements:
>         5977685 bytes/second for writing the file
>         5605177 bytes/second for reading the file
> 
> .... so they definitely help 8)

We really should be able to compare with a bus-master EIDE
driver. The PIIX3 docs (available from Intel's WWW server as 
a PDF file) give enough detail, to implement DMA transfers 
for that chip IMHO, so somebody should go for it ...

Regards, STefan