I think you're facing https://tracker.ceph.com/issues/53266
Which is fixed in the main branch but hasn't been backported to Quincy yet.
You may try to set osd_fast_shutdown to false and check if the error
goes away to check the hypothesis. Not sure it makes much sense to
leave that setting permanently unless you're suffering form long OSD
startups.
Thanks,
Igor
On 9/7/2022 7:53 PM, Vladimir Brik wrote:
I observed this behavior when I used "ceph orch daemon restart ...",
"systemd restart ...", and just rebooting. This doesn't happen all the
time, but usually it does.
I attached the logs.
I am running 17.2.1
Vlad
On 9/7/22 11:21, Igor Fedotov wrote:
Hi Vladimir,
curious what Ceph release are you running and how do you stop your
OSDs. Can you share OSD log lines (e.g. last 1K) before the shutdown?
Thanks,
Igor
On 9/6/2022 6:54 PM, Vladimir Brik wrote:
Whenever I restart an OSD I get the following messages:
bluestore::NCB::__restore_allocator::No Valid allocation info on
disk (empty file)
bluestore(/var/lib/ceph/osd/ceph-99)
_init_alloc::NCB::restore_allocator() failed! Run Full Recovery from
ONodes (might take a while) ...
Does this indicate a problem? Is there a way to avoid this?
Thanks
Vlad
_______________________________________________
ceph-users mailing list -- ceph-users@xxxxxxx
To unsubscribe send an email to ceph-users-leave@xxxxxxx
--
Igor Fedotov
Ceph Lead Developer
Looking for help with your Ceph cluster? Contact us at https://croit.io
croit GmbH, Freseniusstr. 31h, 81247 Munich
CEO: Martin Verges - VAT-ID: DE310638492
Com. register: Amtsgericht Munich HRB 231263
Web: https://croit.io | YouTube: https://goo.gl/PGE1Bx
_______________________________________________
ceph-users mailing list -- ceph-users@xxxxxxx
To unsubscribe send an email to ceph-users-leave@xxxxxxx
