Re: -current, IBM A30p & 2 external FW-disks

2003-02-07 Thread Hidetoshi Shimokawa
At Fri, 7 Feb 2003 10:56:33 +0100 (CET), Michael Reifenberger wrote: > > On Fri, 7 Feb 2003, Hidetoshi Shimokawa wrote: > > ... > > Do you have any timeout while the test? > No. Not any longer. > > I think SBP_QUEUE_LEN or maxopenings is the important parameter. > > Can you try to change thoes va

Re: -current, IBM A30p & 2 external FW-disks

2003-02-07 Thread Michael Reifenberger
On Fri, 7 Feb 2003, Hidetoshi Shimokawa wrote: ... > Do you have any timeout while the test? No. Not any longer. > I think SBP_QUEUE_LEN or maxopenings is the important parameter. > Can you try to change thoes values? > The are at their defaults at the moment. Do you want me to increase them? By

Re: -current, IBM A30p & 2 external FW-disks

2003-02-07 Thread Hidetoshi Shimokawa
At Thu, 6 Feb 2003 12:15:38 +0100 (CET), Michael Reifenberger wrote: > > On Wed, 5 Feb 2003, Michael Reifenberger wrote: > ... > > > I have improved recovery code after timeout in -current. > > > Could you try that? > > > > Is scheduled for this evening. > > Thanks so far! > > > ... > > > > > - fw

Re: -current, IBM A30p & 2 external FW-disks

2003-02-06 Thread Michael Reifenberger
On Wed, 5 Feb 2003, Michael Reifenberger wrote: ... > > I have improved recovery code after timeout in -current. > > Could you try that? > > Is scheduled for this evening. > Thanks so far! > ... > > > > - fwcontorl -g 20 > > > > - sysctl hw.firewire.sbp.max_speed=0 > > > > - change SBP_QUEUE_LEN in

Re: -current, IBM A30p & 2 external FW-disks

2003-02-05 Thread Michael Reifenberger
On Wed, 5 Feb 2003, Hidetoshi Shimokawa wrote: > Date: Wed, 05 Feb 2003 12:07:05 +0900 > From: Hidetoshi Shimokawa <[EMAIL PROTECTED]> > To: mike <[EMAIL PROTECTED]> > Cc: Hidetoshi Shimokawa <[EMAIL PROTECTED]>, > FreeBSD-Current <[EMAIL PROTECTED]>

Re: -current, IBM A30p & 2 external FW-disks

2003-02-04 Thread Hidetoshi Shimokawa
I have improved recovery code after timeout in -current. Could you try that? /\ Hidetoshi Shimokawa \/ [EMAIL PROTECTED] PGP public key: http://www.sat.t.u-tokyo.ac.jp/~simokawa/pgp.html At Sun, 2 Feb 2003 13:28:33 +0200, mike wrote: > > [1 ] > On Thu, 30 Jan 2003 14:41:59 +0900, Hidetoshi Shi

Re: -current, IBM A30p & 2 external FW-disks

2003-02-02 Thread Hidetoshi Shimokawa
At Sun, 2 Feb 2003 13:28:33 +0200, mike wrote: > > try some of the following: > > > > - fwcontorl -g 20 > > - sysctl hw.firewire.sbp.max_speed=0 > > - change SBP_QUEUE_LEN in sbp.c to 1 and rebuld module. > > - sysctl machdep.cpu_idle_hlt=0 > > - sysctl debug.sbp_debug=1 and send me a dmesg.

Re: -current, IBM A30p & 2 external FW-disks

2003-02-02 Thread mike
On Thu, 30 Jan 2003 14:41:59 +0900, Hidetoshi Shimokawa wrote > Do you get timeout only for sbp0:0:0? > Is the other drive still working? > > I have no problem with concurrent accesses with `iozone -s 102400m -r > 1024k`. ... > try some of the following: > > - fwcontorl -g 20 > - sysctl

Re: -current, IBM A30p & 2 external FW-disks

2003-01-30 Thread Michael Reifenberger
PROTECTED]> > Subject: Re: -current, IBM A30p & 2 external FW-disks > > Do you get timeout only for sbp0:0:0? > Is the other drive still working? yes, no. > > I have no problem with concurrent accesses with `iozone -s 102400m -r > 1024k`. Me too when only with one

Re: -current, IBM A30p & 2 external FW-disks

2003-01-29 Thread Hidetoshi Shimokawa
Do you get timeout only for sbp0:0:0? Is the other drive still working? I have no problem with concurrent accesses with `iozone -s 102400m -r 1024k`. tty ad0 da0 da1 tin tout KB/t tps MB/s KB/t tps MB/s KB/t tps MB/s 21 360 0.00 0 0.00

-current, IBM A30p & 2 external FW-disks

2003-01-28 Thread Michael Reifenberger
Hi, I have the following scenario: A30p <==> disk1 <==> disk2 disk1 and disk2 are identical 200GB disks in an extarnal ICE-cube case. My dmesg output is attached. After creating and mounting them as UFS2 filesystems under /mnt/a /mnt/b and starting a `iozone -s 102400m -r 1024k` in parallel unde