Re: Storage - redundant path failover / failback - quo vadis linux?

From: Lars Marowsky-Bree (lmb@suse.de)
Date: Wed May 16 2001 - 02:17:03 EST


On 2001-05-16T08:34:00,
   Christoph Biardzki <cbi@cebis.net> said:

> I was investigating redundant path failover with FibreChannel disk devices
> during the last weeks. The idea is to use a second, redundant path to a
> storage device when the first one fails. Ideally one could also implement
> load balancing with these paths.
>
> The problem is really important when using linux for mission-critical
> applications which require large amounts of external storage.

Yes.

Device handling under Linux in the face of HA generally faces some annoying
issues - the one you mention is actually the least of it ;-)

Error handling and reporting is the most annoying one to me - no good way to
find out whether a device has had an error. And even if the kernel logs a read
error on device sda1 - great, what LVM volumes are affected?

But on to your question... ;-)

> - The "T3"-Patch for 2.2-Kernels which patches the sd-Driver und the
> Qlogic-FC-HBA-Driver. When you pull an FC-Cable on a host equiped with two
> HBAs the failover is almost immediate and an automatic failback (after
> "repairing") is possible

I actually like this one best, if it was forward ported to 2.4.

> The low-level-approach of the "T3"-patch requires changes to the
> scsi-drivers and the hardware-drivers but provides optimal communication
> between the driver and the hardware

The changes required for the hardware drivers are rather minimal.

Sincerely,
    Lars Marowsky-Brée <lmb@suse.de>

-- 
Perfection is our goal, excellence will be tolerated. -- J. Yahl

- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/



This archive was generated by hypermail 2b29 : Wed May 23 2001 - 21:00:15 EST