From owner-freebsd-hackers  Sat Oct  7 19:10:48 1995
Return-Path: owner-hackers
Received: (from root@localhost)
          by freefall.freebsd.org (8.6.12/8.6.6) id TAA10619
          for hackers-outgoing; Sat, 7 Oct 1995 19:10:48 -0700
Received: from godzilla.zeta.org.au (godzilla.zeta.org.au [203.2.228.34])
          by freefall.freebsd.org (8.6.12/8.6.6) with ESMTP id TAA10586
          for <hackers@freebsd.org>; Sat, 7 Oct 1995 19:10:19 -0700
Received: (from bde@localhost) by godzilla.zeta.org.au (8.6.9/8.6.9) id MAA11808; Sun, 8 Oct 1995 12:04:47 +1000
Date: Sun, 8 Oct 1995 12:04:47 +1000
From: Bruce Evans <bde@zeta.org.au>
Message-Id: <199510080204.MAA11808@godzilla.zeta.org.au>
To: gibbs@freefall.freebsd.org, se@ZPR.Uni-Koeln.DE
Subject: Re: VLB Disk Controllers
Cc: hackers@freebsd.org, ken@rflab1.gtri.gatech.edu
Sender: owner-hackers@freebsd.org
Precedence: bulk

>>Something I just noticed is the big difference 
>>in results I get using /dev/rsd0 vs. /dev/rsd0a:
>>
>># disklatency /dev/rsd0
>>Command overhead is 719 usec (time_4096 = 1198, time_8192 = 1677)
>>transfer speed is 8.55617e+06 bytes/sec
>>
>># disklatency /dev/rsd0a
>>Command overhead is 807 usec (time_4096 = 1272, time_8192 = 1738)
>>transfer speed is 8.80588e+06 bytes/sec
>>
>>Any ideas ???

>Slice code?  It may be that we take some steps to validate the disklable
>for that partition, do additional range checks etc.  Bruce probably
>knows.

It shouldn't be that large.  Perhaps the first 16 sectors of rsd0a span
a physical track boundary and the drive doesn't handle this well.  Perhaps
the benchmark is less accurate than you expect.  It takes a difference of
two times that may be close together so the variance of the difference
may be large.

Bruce