2005-01-20 19:56:54

by Trever L. Adams

[permalink] [raw]
Subject: IEEE-1394 and disks

I have a few questions: How stable is firewire (running at 800Mbps or
faster, if any is available yet)? How stable is the Linux subsystem,
especially for firewire disks? Is there any particularly 800Mbps bridge
chips that should be avoided or used?

How stable is the subsystem when the chain is nearly full (62 devices is
full right?)

How many controllers may be in the system before the Firewire subsystem
gets confused?

Trever Adams
--
"There are two ways to live your life. One is as though nothing is a
miracle. The other is as though everything is a miracle." -- Albert
Einstein


2005-01-20 20:23:50

by Trever L. Adams

[permalink] [raw]
Subject: Re: IEEE-1394 and disks

By bridge chips I mean IEEE-1394 to IDE. Also, is it possible to set
spin down time for these IDE disks through 1394? i.e. if they are
inactive for 1 hour, I would like them to spin down. Is this possible?

Trever

On Thu, 2005-01-20 at 12:53 -0700, Trever L. Adams wrote:
> I have a few questions: How stable is firewire (running at 800Mbps or
> faster, if any is available yet)? How stable is the Linux subsystem,
> especially for firewire disks? Is there any particularly 800Mbps bridge
> chips that should be avoided or used?
>
> How stable is the subsystem when the chain is nearly full (62 devices is
> full right?)
>
> How many controllers may be in the system before the Firewire subsystem
> gets confused?
>
> Trever Adams
> --
> "There are two ways to live your life. One is as though nothing is a
> miracle. The other is as though everything is a miracle." -- Albert
> Einstein
>
> -
> To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
> the body of a message to [email protected]
> More majordomo info at http://vger.kernel.org/majordomo-info.html
> Please read the FAQ at http://www.tux.org/lkml/
>
--
"If there was strife and contention in the home, very little else in
life could compensate for it." -- Lawana Blackwell, The Courtship of the
Vicar's Daughter, 1998

2005-01-27 00:22:35

by Jody McIntyre

[permalink] [raw]
Subject: Re: IEEE-1394 and disks

On Thu, Jan 20, 2005 at 12:53:32PM -0700, Trever L. Adams wrote:
> I have a few questions: How stable is firewire (running at 800Mbps or
> faster, if any is available yet)? How stable is the Linux subsystem,
> especially for firewire disks? Is there any particularly 800Mbps bridge
> chips that should be avoided or used?

The sbp2 subsystem has stability problems, but I'm not exactly sure what
they are. The core also has a few issues, but I don't think they'll
affect you. This assumes you're running the latest from linux1394.org
svn as there are quite a few unmerged changes (which will hopefully make
it in to 2.6.12).

> How stable is the subsystem when the chain is nearly full (62 devices is
> full right?)

Having lots of devices shouldn't make any difference, one way or the
other. 62 devices is full. For performance reasons, a tree topology is
preferred to daisy chaining all the devices.

> How many controllers may be in the system before the Firewire subsystem
> gets confused?

Again, it shouldn't matter. I'm not sure if the SCSI subsystem imposes
a limit on the number of drives.

I suggest asking future 1394 questions on one of the linux1394 lists:
http://sourceforge.net/mail/?group_id=2252 - someone may even have
tried what you're attempting.

Jody

>
> Trever Adams
> --
> "There are two ways to live your life. One is as though nothing is a
> miracle. The other is as though everything is a miracle." -- Albert
> Einstein
>
> -
> To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
> the body of a message to [email protected]
> More majordomo info at http://vger.kernel.org/majordomo-info.html
> Please read the FAQ at http://www.tux.org/lkml/

--

2005-02-14 23:50:10

by Jody McIntyre

[permalink] [raw]
Subject: Re: IEEE-1394 and disks

On Thu, Jan 20, 2005 at 01:23:47PM -0700, Trever L. Adams wrote:
> By bridge chips I mean IEEE-1394 to IDE. Also, is it possible to set
> spin down time for these IDE disks through 1394? i.e. if they are
> inactive for 1 hour, I would like them to spin down. Is this possible?

Not currently. I'm not sure if this is a hardware limitation or just
something that isn't implemented yet.

Jody

>
> Trever