mkfs.xfs with a 9TB realtime volume hangs

[Eric Sandeen]

Dave Chinner wrote:
> On Sat, Jan 10, 2009 at 03:13:23PM -0600, Eric Sandeen wrote:


>> With the default 4k extent size this takes forever (the man page claims
>> default is 64k, maybe this got broken at some point).
> 
> It got changed a few years back by Nathan, IIRC. 

Yep, I found the commit yesterday, it was for buffered IO's benefit on
the rt subvol, to reduce unwritten extent conversion IIRC.

I was going to follow up w/ the commit etc yesterday, but the mailing
list was down (again, sigh - this is indicative of sgi's staunch
commitment to xfs, I'm sure) so had nothing to reply to.

-Eric

> I bet the time
> being taken a result of the blow-out in bitmap size caused by reducing
> the extent size. Given it is non-linear, it may have something to do
> with cache sizes as well.  e.g buftarg hashes not large enough.
> 
> Cheers,
> 
> Dave.