From owner-freebsd-stable Tue May 25 23:19:54 1999 Delivered-To: freebsd-stable@freebsd.org Received: from panzer.plutotech.com (panzer.plutotech.com [206.168.67.125]) by hub.freebsd.org (Postfix) with ESMTP id B794515362 for ; Tue, 25 May 1999 23:19:18 -0700 (PDT) (envelope-from ken@panzer.plutotech.com) Received: (from ken@localhost) by panzer.plutotech.com (8.9.3/8.8.5) id AAA10735; Wed, 26 May 1999 00:18:56 -0600 (MDT) From: "Kenneth D. Merry" Message-Id: <199905260618.AAA10735@panzer.plutotech.com> Subject: Re: [help] 3.2-stable LVD transfer rate drop to 11.xxx MB/s??? In-Reply-To: <374B8B54.ECA3EF85@tomail.com.tw> from Silver CHEN at "May 26, 1999 01:49:08 pm" To: silver@tomail.com.tw (Silver CHEN) Date: Wed, 26 May 1999 00:18:56 -0600 (MDT) Cc: freebsd-stable@FreeBSD.ORG (freebsd-stable@FreeBSD.ORG) X-Mailer: ELM [version 2.4ME+ PL54 (25)] MIME-Version: 1.0 Content-Type: text/plain; charset=US-ASCII Content-Transfer-Encoding: 7bit Sender: owner-freebsd-stable@FreeBSD.ORG Precedence: bulk X-Loop: FreeBSD.ORG Silver CHEN wrote... > Dear Sir: > > I've upgraded my 3.1R box to 3.2 due to the kernel panic under > heavy load. Now it's all done, and I reboot the box, then I > found my LVD disks' tranfer rate becomes: > > da0 at ahc1 bus 0 target 0 lun 0 > da0: Fixed Direct Access SCSI-2 device > da0: 11.626MB/s transfers (5.813MHz, offset 15, 16bit) > ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ > da0: 4340MB (8888924 512 byte sectors: 255H 63S/T 553C) > > This is very funny, compared to 3.1R: > > da0 at ahc0 bus 0 target 0 lun 0 > da0: Fixed Direct Access SCSI-2 device > da0: 80.0MB/s transfers (40.0MHz, offset 15, 16bit), Tagged Queueing Enabled > ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^!!! > da0: 4340MB (8888924 512 byte sectors: 255H 63S/T 553C) > > I'm using the GENERIC kernel now, and both 3.1R/3.2 has detected the > SCSI controller sucessfully during boot: Are you running 3.2-RELEASE or 3.2-STABLE?? This bug was introduced only a few days ago, and a couple of weeks after 3.2-RELEASE. > ahc0: rev 0x00 int a irq 10 on > pci0.12.0 > ahc0: aic7896/97 Wide Channel A, SCSI Id=7, 16/255 SCBs > ahc1: rev 0x00 int a irq 10 on > pci0.12.1 > ahc1: aic7896/97 Wide Channel B, SCSI Id=7, 16/255 SCBs > > Should I do something to 'fix' the transfer rate and the tagged > queue option? > > The controller is expansive, the LVD disk is expansive, even the > LVD cable is expansive - this setting makes me very upset....:( This problem was fixed today (Tuesday). Sync to FreeBSD-stable (RELENG_3) and things should work properly again. You can fix it for a given boot using camcontrol(8). Look specifically at the 'negotiate' option. You should be able to change the sync rate and tagged queueing status like this: camcontrol negotiate da0 -R 40 -T enable -a Of course that won't last across boots. The best thing to do is upgrade your sources to the latest stuff. Ken -- Kenneth Merry ken@plutotech.com To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-stable" in the body of the message