Hi Matthew, *Thanks for the update.* *For the Part:* [my Query] > *Other Query:* > What if the complete cluster goes down, i.e mon crashes another daemon > crashes, can we try to restore the data in OSDs, maybe by reusing the > OSD's in another or new Ceph Cluster or something to save the data. *[My added query]* In this same situation, we are not sure about the OSD daemon service as well, i.e it may be the case that all the services including OSD/MON/MGR/others are completely dead and can't be accessed. So in this case, we have data still on the disks, so is there a way to recover such data in a completely new setup of Ceph or something? Hope I am not confusing you more. Best Regards, Lokendra On Wed, Sep 8, 2021 at 7:03 PM Matthew Vernon <mvernon@xxxxxxxxxxxxx> wrote: > Hi, > > On 06/09/2021 08:37, Lokendra Rathour wrote: > > Thanks, Mathew for the Update. > > The upgrade got failed for some random wired reasons, Checking further > > Ceph's status shows that "Ceph health is OK" and times it gives certain > > warnings but I think that is ok. > > OK... > > > but what if we see the Version mismatch between the daemons, i.e few > > services have upgraded and the remaining could not be upgraded. So in > > this state, we do two things: > > > > * Retrying the upgrade activity (to Pacific) - it might work this time. > > * Going back to the older Version (Octopus) - is this possible and if > > yes then how? > > In general downgrades are not supported, so I think continuing with the > upgrade is the best answer. > > > *Other Query:* > > What if the complete cluster goes down, i.e mon crashes other daemon > > crashes, can we try to restore the data in OSDs, maybe by reusing the > > OSD's in another or new Ceph Cluster or something to save the data. > > You will generally have more than 1 mon (typically 3, some people have > 5), and as long as a quorum remains, you will still have a working > cluster. If you somehow manage to break all your mons, there is an > emergency procedure for recreating the mon map from an OSD - > > > https://docs.ceph.com/en/pacific/rados/troubleshooting/troubleshooting-mon/#recovery-using-osds > > ...but you don't want to end up in that situation! > > RADOS typically splits objects across multiple placement groups (and > thus across multiple OSDs); while there are tools to extract data from > OSDs (e.g. https://docs.ceph.com/en/latest/man/8/ceph-objectstore-tool/ > ), you won't get complete objects this way. Instead, the advice would be > to try and get enough mons back up to get your cluster at least to a > read-only state and then attempt recovery that way. > > HTH, > > Matthew > _______________________________________________ > ceph-users mailing list -- ceph-users@xxxxxxx > To unsubscribe send an email to ceph-users-leave@xxxxxxx > -- ~ Lokendra www.inertiaspeaks.com www.inertiagroups.com skype: lokendrarathour _______________________________________________ ceph-users mailing list -- ceph-users@xxxxxxx To unsubscribe send an email to ceph-users-leave@xxxxxxx
 |