> > Hi, > > > I just tested with tap2:aio and that worked (had an old image of the VM on > lvm still so just tested with that). Switching back to rbd and it crashes every > time, just as postgres is starting in the vm. Booting into single user mode, > waiting 30 seconds, then letting the boot continue it still crashes at the same > point so I think it's not a timing thing - maybe postgres has a disk access > pattern that is triggering the bug? > > Mmm, that's really interesting. > > Could you try to disable request merging ? Just give option > max_merge_size=0 in the tap2 disk description. Something like > 'tap2:tapdisk:rbd:rbd/test:max_merge_size=0,xvda2,w' > Just as suddenly the problem went away and I can no longer reproduce the crash on startup. Very frustrating. Most likely it still crashed during heavy use but that can take days. I've just upgraded librbd to dumpling (from cuttlefish) on that one server and will see what it's doing by morning. I'll disable merging when I can reproduce it next. Thanks James -- 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
