From asami@silvia.hip.berkeley.edu  Sat Oct 12 18:09:16 1996
Received: from dfw-ix11.ix.netcom.com (dfw-ix11.ix.netcom.com [206.214.98.11])
          by freefall.freebsd.org (8.7.5/8.7.3) with SMTP id SAA19484
          for <FreeBSD-gnats-submit@freebsd.org>; Sat, 12 Oct 1996 18:09:15 -0700 (PDT)
Received: from baloon.mimi.com (sjx-ca13-17.ix.netcom.com [199.182.128.177]) by dfw-ix11.ix.netcom.com (8.6.13/8.6.12) with ESMTP id SAA02894 for <FreeBSD-gnats-submit@freebsd.org>; Sat, 12 Oct 1996 18:08:43 -0700
Received: (from asami@localhost) by baloon.mimi.com (8.7.6/8.6.12) id SAA01054; Sat, 12 Oct 1996 18:08:41 -0700 (PDT)
Message-Id: <199610130108.SAA01054@baloon.mimi.com>
Date: Sat, 12 Oct 1996 18:08:41 -0700 (PDT)
From: asami@freebsd.org
To: FreeBSD-gnats-submit@freebsd.org
Subject: ncr driver thinks all drives are created asynchronous
X-Send-Pr-Version: 3.2

>Number:         1782
>Category:       kern
>Synopsis:       ncr driver thinks all drives are created asynchronous
>Confidential:   no
>Severity:       serious
>Priority:       high
>Responsible:    se
>State:          closed
>Quarter:
>Keywords:
>Date-Required:
>Class:          sw-bug
>Submitter-Id:   current-users
>Arrival-Date:   Sat Oct 12 18:10:00 PDT 1996
>Closed-Date:    Mon Oct 14 06:05:35 PDT 1996
>Last-Modified:  Mon Oct 14 06:08:32 PDT 1996
>Originator:     Satoshi Asami
>Release:        FreeBSD 2.2-CURRENT i386
>Organization:
The FreeBSD Project
>Environment:

	Asus SC-200 
	Quantum Atlas (narrow, 2GB)
	ncr.c, revision 1.80 onwards

>Description:

Starting from revision 1.80 of /sys/pci/ncr.c, the boot message
started to print out

===
ncr0 <ncr 53c810 scsi> rev 2 int a irq 10 on pci0:12
ncr0 waiting for scsi devices to settle
(ncr0:0:0): "FUJITSU M1606S-512 6226" type 0 fixed SCSI 2
sd0(ncr0:0:0): Direct-Access 
sd0(ncr0:0:0): asynchronous.
1041MB (2131992 512 byte sectors)
(ncr0:1:0): "Quantum XP32150 576D" type 0 fixed SCSI 2
sd1(ncr0:1:0): Direct-Access 
sd1(ncr0:1:0): asynchronous.
2050MB (4199760 512 byte sectors)
(ncr0:6:0): "SONY CD-ROM CDU-76S 1.1c" type 5 removable SCSI 2
cd0(ncr0:6:0): CD-ROM 
cd0(ncr0:6:0): asynchronous.

cd0(ncr0:6:0): UNIT ATTENTION asc:28,0
cd0(ncr0:6:0):  Not ready to ready transition, medium may have changed
cd present [400000 x 2048 byte records]
===

whereas rev. 1.79 prints out

===
ncr0 <ncr 53c810 scsi> rev 2 int a irq 10 on pci0:12
ncr0 waiting for scsi devices to settle
(ncr0:0:0): "FUJITSU M1606S-512 6226" type 0 fixed SCSI 2
sd0(ncr0:0:0): Direct-Access 
sd0(ncr0:0:0): FAST SCSI-2 100ns (10 Mb/sec) offset 8.
1041MB (2131992 512 byte sectors)
(ncr0:1:0): "Quantum XP32150 576D" type 0 fixed SCSI 2
sd1(ncr0:1:0): Direct-Access 
sd1(ncr0:1:0): FAST SCSI-2 100ns (10 Mb/sec) offset 8.
2050MB (4199760 512 byte sectors)
(ncr0:6:0): "SONY CD-ROM CDU-76S 1.1c" type 5 removable SCSI 2
cd0(ncr0:6:0): CD-ROM 
cd0(ncr0:6:0): 200ns (5 Mb/sec) offset 8.

cd0(ncr0:6:0): UNIT ATTENTION asc:28,0
cd0(ncr0:6:0):  Not ready to ready transition, medium may have changed
cd present [400000 x 2048 byte records]
===

Note the three "asynchronous" lines in the first example.  I'm not
sure about the CDROM, but the disks are definitely capable of doing
sync transfer.

I verified that it's really running slower by running "iozone 100 65536"
on the 2nd disk (Quantum Atlas).  I get 3.2write/4.1read (MB/s) for
"asynchronous" kernels, while it goes up to 3.9write/4.8read with
ncr.c reverted to revision 1.79.

>How-To-Repeat:

	see above

>Fix:
	
	I'm sure Stefan will find it soon. :)
>Release-Note:
>Audit-Trail:
Responsible-Changed-From-To: freebsd-bugs->se 
Responsible-Changed-By: asami 
Responsible-Changed-When: Sat Oct 12 18:11:26 PDT 1996 
Responsible-Changed-Why:  
His driver. 
State-Changed-From-To: open->closed 
State-Changed-By: se 
State-Changed-When: Mon Oct 14 06:05:35 PDT 1996 
State-Changed-Why:  
Fixed in ncr.c 1.82. 
>Unformatted:
