>>> Hannes Dorbath <[EMAIL PROTECTED]> 24.08.2007 00:20 >>>
> # time mount /raid/
> real    0m0.023s
> user    0m0.001s
> sys     0m0.007s
> 
> # df -h|grep raid
> /dev/mapper/raid-data 2.8T 1021G  1.8T  37% /raid
> 
> 
> No offense, but as you can see, a 3 TB file system is mounted in 0.023s.
> Maybe consider using a better suited file system, instead of working
> around scaling problems of your current one.

Hi Hannes,

the timing is amazing. But: This is the case where everything is o.k. and
you mount a cleanly unmounted filesystem. I assume so.
When a node is "stonithed" or crashed and the filesystem is in a unclean
state, I'm sure it will last a little bit longer.

So, it would be also interesting to see the following.
* Generate as much random write I/O as possible => fills the buffers.
* Turn off power of the machine or storage subsystem.
* Start up
* mount the filesystem again.

So this result would be a good measure for a lower bound of timeout
values. :-)

Nice weekend
Andreas



_______________________________________________
Linux-HA mailing list
[email protected]
http://lists.linux-ha.org/mailman/listinfo/linux-ha
See also: http://linux-ha.org/ReportingProblems

Reply via email to