Skip site navigation (1)Skip section navigation (2)
Date:      Mon, 06 Nov 2000 16:26:19 -0500
From:      Doug Ledford <dledford@redhat.com>
To:        Mads Bondo Dydensborg <madsdyd@challenge.dk>
Cc:        "'aic7xxx@FreeBSD.ORG'" <aic7xxx@FreeBSD.ORG>
Subject:   Re: Question about throughput
Message-ID:  <3A0721FB.1F9DA31@redhat.com>
References:  <Pine.LNX.4.21.0011061716370.2261-100000@challenge.dk>

next in thread | previous in thread | raw e-mail | index | archive | help
Mads Bondo Dydensborg wrote:

> I do meet those two items. I assume tagged queueing to be the case then.

On my later aic7xxx drivers (I assume my driver was the basis for your work, I
could be wrong on that), the aic7xxx_proc.c file prints out the
tagged_queueing status for each device in the /proc/scsi/aic7xxx/? files.  If
TQ isn't enabled in the driver though, then it will create a bottleneck in
your tests.  In earlier aic7xxx drivers, TQ was enabled by a compile time
define.  In later drivers the compile time define just changed whether TQ was
turned on by default and support was always compiled into the driver.  If
you'll send the output of your /proc/scsi/aic7xxx/0 (or whatever controller
number these devices are on) file then I can tell easy enough if it's enabled
(it should probably be pretty obvious to you as well).

-- 

 Doug Ledford <dledford@redhat.com>  http://people.redhat.com/dledford
      Please check my web site for aic7xxx updates/answers before
                      e-mailing me about problems


To Unsubscribe: send mail to majordomo@FreeBSD.org
with "unsubscribe aic7xxx" in the body of the message




Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?3A0721FB.1F9DA31>