From owner-freebsd-stable@FreeBSD.ORG  Thu Feb 10 09:26:29 2005
Return-Path: <owner-freebsd-stable@FreeBSD.ORG>
Delivered-To: freebsd-stable@freebsd.org
Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125])
	by hub.freebsd.org (Postfix) with ESMTP id 3A96D16A4CE
	for <freebsd-stable@freebsd.org>;
	Thu, 10 Feb 2005 09:26:29 +0000 (GMT)
Received: from f13.mail.ru (f13.mail.ru [194.67.57.43])
	by mx1.FreeBSD.org (Postfix) with ESMTP id DFFD543D49
	for <freebsd-stable@freebsd.org>;
	Thu, 10 Feb 2005 09:26:28 +0000 (GMT)	(envelope-from _pppp@mail.ru)
Received: from mail by f13.mail.ru with local 
	id 1CzAak-0004Cc-00; Thu, 10 Feb 2005 12:26:30 +0300
Received: from [81.200.13.122] by win.mail.ru with HTTP;
	Thu, 10 Feb 2005 12:26:30 +0300
From: dima <_pppp@mail.ru>
To: Thomas Hurst <tom.hurst@clara.net>
Mime-Version: 1.0
X-Mailer: mPOP Web-Mail 2.19
X-Originating-IP: [81.200.13.122]
Date: Thu, 10 Feb 2005 12:26:30 +0300
In-Reply-To: <20050209174743.GA81628@voi.aagh.net>
Content-Type: text/plain; charset=koi8-r
Content-Transfer-Encoding: 8bit
Message-Id: <E1CzAak-0004Cc-00._pppp-mail-ru@f13.mail.ru>
cc: freebsd-stable@freebsd.org
Subject: Re[2]: interrupt routing
X-BeenThere: freebsd-stable@freebsd.org
X-Mailman-Version: 2.1.1
Precedence: list
Reply-To: dima <_pppp@mail.ru>
List-Id: Production branch of FreeBSD source code
	<freebsd-stable.freebsd.org>
List-Unsubscribe: <http://lists.freebsd.org/mailman/listinfo/freebsd-stable>,
	<mailto:freebsd-stable-request@freebsd.org?subject=unsubscribe>
List-Archive: <http://lists.freebsd.org/pipermail/freebsd-stable>
List-Post: <mailto:freebsd-stable@freebsd.org>
List-Help: <mailto:freebsd-stable-request@freebsd.org?subject=help>
List-Subscribe: <http://lists.freebsd.org/mailman/listinfo/freebsd-stable>,
	<mailto:freebsd-stable-request@freebsd.org?subject=subscribe>
X-List-Received-Date: Thu, 10 Feb 2005 09:26:29 -0000

>> Ah, so they are all on the same bus.  Yuck, performance is going to be
>> sucky. Bad Tyan, no cookie.  That'll also explain the limited number
>> of interrupts available.  I don't think there's anything we can do to
>> help the situation, sadly.
> 
> Buy a PCI-X SCSI/GigE card, and use that instead of the on-board one?
> Neither of our S288[12]'s are sharing any IRQ's; we're using Adaptec
> 2120S RAID cards, and they have a bus and IRQ to themselves.
Thanks for your suggestion; I will think about purchasing a NIC.

> MySQL performance still sucks on our FreeBSD machine, but that's an OS
> problem; the hardware looks fine to me.  If you have suggestions for a
> better dual Opteron motherboard I'm all ears :)
I didnt have a chance to try MSI stuff yet; it contains a single channel SCSI onboard though. Its not that good for future HD expansion in my deployment. I set up 4 drives (60MB/s*4 is quite ok for a SCSI-320) for database now and directed the 2nd SCSI channel to the backplane.