On Wed, Sep 23, 2015 at 4:42 PM, Handzik, Joe <joseph.t.handzik@xxxxxxx> wrote: > Ok. When configuring with ceph-disk, it does something nifty and actually gives the OSD the uuid of the disk's partition as its fsid. I bootstrap off that to get an argument to pass into the function you have identified as the bottleneck. I ran it by sage and we both realized there would be cases where it wouldn't work...I'm sure neither of us realized the failure would take three minutes though. > > In the short term, it makes sense to create an option to disable or short-circuit the blkid code. I would prefer that the default be left with the code enabled, but I'm open to default disabled if others think this will be a widespread problem. You could also make sure your OSD fsids are set to match your disk partition uuids for now too, if that's a faster workaround for you (it'll get rid of the failure). I'd leave it enabled by default — ceph-disk is the standard way of setting up a Ceph cluster, and mkcephfs is definitely going bye-bye. -Greg -- To unsubscribe from this list: send the line "unsubscribe ceph-devel" in the body of a message to majordomo@xxxxxxxxxxxxxxx More majordomo info at http://vger.kernel.org/majordomo-info.html
