From owner-freebsd-scsi@FreeBSD.ORG  Fri Feb  4 10:26:51 2005
Return-Path: <owner-freebsd-scsi@FreeBSD.ORG>
Delivered-To: freebsd-scsi@freebsd.org
Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125])
	by hub.freebsd.org (Postfix) with ESMTP id 2F0D916A4CE
	for <scsi@freebsd.org>; Fri,  4 Feb 2005 10:26:51 +0000 (GMT)
Received: from svm.csie.ntu.edu.tw (svm.csie.ntu.edu.tw [140.112.90.75])
	by mx1.FreeBSD.org (Postfix) with ESMTP id 73E6343D49
	for <scsi@freebsd.org>; Fri,  4 Feb 2005 10:26:48 +0000 (GMT)
	(envelope-from rafan@svm.csie.ntu.edu.tw)
Received: from svm.csie.ntu.edu.tw (localhost [127.0.0.1])
	by svm.csie.ntu.edu.tw (8.13.1/8.13.1) with ESMTP id j14AQ8qg002230;
	Fri, 4 Feb 2005 18:26:08 +0800 (CST)
	(envelope-from rafan@svm.csie.ntu.edu.tw)
Received: (from rafan@localhost)
	by svm.csie.ntu.edu.tw (8.13.1/8.13.1/Submit) id j14APxOY002220;
	Fri, 4 Feb 2005 18:25:59 +0800 (CST)
	(envelope-from rafan)
Date: Fri, 4 Feb 2005 18:25:59 +0800
From: Rong-En Fan <rafan@csie.org>
To: scsi@freebsd.org
Message-ID: <20050204102558.GA2001@svm.csie.ntu.edu.tw>
Mime-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Content-Disposition: inline
User-Agent: Mutt/1.5.6i
cc: ob@e-Gitt.NET
Subject: Problem with mpt(4) and Infortrend RAID
X-BeenThere: freebsd-scsi@freebsd.org
X-Mailman-Version: 2.1.1
Precedence: list
List-Id: SCSI subsystem <freebsd-scsi.freebsd.org>
List-Unsubscribe: <http://lists.freebsd.org/mailman/listinfo/freebsd-scsi>,
	<mailto:freebsd-scsi-request@freebsd.org?subject=unsubscribe>
List-Archive: <http://lists.freebsd.org/pipermail/freebsd-scsi>
List-Post: <mailto:freebsd-scsi@freebsd.org>
List-Help: <mailto:freebsd-scsi-request@freebsd.org?subject=help>
List-Subscribe: <http://lists.freebsd.org/mailman/listinfo/freebsd-scsi>,
	<mailto:freebsd-scsi-request@freebsd.org?subject=subscribe>
X-List-Received-Date: Fri, 04 Feb 2005 10:26:51 -0000

[please CC me, thanks]

hello,

I also have a mpt(4) (LSI21320) here and a 
SilverStar TN6016 RAID (which is also produced
by Infortrend). OS is FreeBSD/amd64 (on EM64)
5.3-RELEASE-p5. Hardware is IBM x236.

mpt0: <LSILogic 1030 Ultra4 Adapter> port 0x5000-0x50ff mem
0xcdee0000-0xcdeefff
f,0xcdef0000-0xcdefffff irq 52 at device 1.0 on pci4
mpt0: [GIANT-LOCKED]

If I map two 1.6T logical drive to the same channel
with different LUN, I got similar problem like yours
However, if I do ONE of following will solve:

  1. set the channel to 160MB/s (sync clock is 80Mhz)
  2. map 1 logical drive to 1 channel (I have two channels
     on raid)

I'm using 2 now, but I just did a little io traffic
(< 5MB/s and < 30secs) then got following messages:

mpt0: time out on request index = 0x5e sequence = 0x0000156d
mpt0: Status 00000001; Mask 00000001; Doorbell 24000000
request state On Chip
SCSI IO Request @ 0xffffffffb1b61af0
        Chain Offset  0x10
        MsgFlags      0x00
        MsgContext    0x0000005e
        Bus:                0
        TargetID            0
        SenseBufferLength   32
        LUN:              0x0
        Control           0x01000000  WRITE  SIMPLEQ
        DataLength      0x00010000
        SenseBufAddr    0x7b460de0
        CDB[0:10]       2a 00 04 3f c0 df 00 00 80 00
        SE32 0xffffffffb1c06c30: Addr=0x69446000 FlagsLength=0x14001000
         HOST_TO_IOC
        SE32 0xffffffffb1c06c38: Addr=0x694a7000 FlagsLength=0x94001000
         HOST_TO_IOC LAST_ELEMENT
        CE32 0xffffffffb1c06c40: Addr=0x7b460c48 NxtChnO=0x16 Flgs=0x30 Len=0x60
        SE32 0xffffffffb1c06c48: Addr=0x69348000 FlagsLength=0x14001000
         HOST_TO_IOC
        SE32 0xffffffffb1c06c50: Addr=0x688e9000 FlagsLength=0x14001000
         HOST_TO_IOC
        SE32 0xffffffffb1c06c58: Addr=0x692ea000 FlagsLength=0x14001000
         HOST_TO_IOC
        SE32 0xffffffffb1c06c60: Addr=0x6b5eb000 FlagsLength=0x14001000
         HOST_TO_IOC
        SE32 0xffffffffb1c06c68: Addr=0x69c4c000 FlagsLength=0x14001000
         HOST_TO_IOC
        SE32 0xffffffffb1c06c70: Addr=0x68d0d000 FlagsLength=0x14001000
         HOST_TO_IOC
        SE32 0xffffffffb1c06c78: Addr=0x6866e000 FlagsLength=0x14001000
         HOST_TO_IOC
        SE32 0xffffffffb1c06c80: Addr=0x67faf000 FlagsLength=0x14001000
         HOST_TO_IOC
        SE32 0xffffffffb1c06c88: Addr=0x68b90000 FlagsLength=0x14001000
         HOST_TO_IOC
        SE32 0xffffffffb1c06c90: Addr=0x6a811000 FlagsLength=0x14001000
         HOST_TO_IOC
        SE32 0xffffffffb1c06c98: Addr=0x68b32000 FlagsLength=0x94001000
         HOST_TO_IOC LAST_ELEMENT
        CE32 0xffffffffb1c06ca0: Addr=0x7b460ca8 NxtChnO=0x0 Flgs=0x30 Len=0x18
        SE32 0xffffffffb1c06ca8: Addr=0x68173000 FlagsLength=0x14001000
         HOST_TO_IOC
        SE32 0xffffffffb1c06cb0: Addr=0x682f4000 FlagsLength=0x14001000
         HOST_TO_IOC
        SE32 0xffffffffb1c06cb8: Addr=0x68695000 FlagsLength=0xd5001000
         HOST_TO_IOC LAST_ELEMENT END_OF_BUFFER END_OF_LIST


By the way, if I use 320MB/s and plug the RAID into another
Adaptec 29320LP (ahd(4)), it fails when bus scanning. On the
other hand, 160MB/s is fine.

any suggestion about this?

Thanks,
Rong-En Fan