Re: Stale PG data loss

[Surya Bala <sooriya.balan@xxxxxxxxx>]

We have configured cephfs . 

Yes i can restore the data. But i need to know which files are corrupted. So that i can delete those files and copy them again. 

In normal state i can get inode id of files and mapping inode id with object id. So that i can get files to object mapping . using ceph osd map command i can find objects to PG ans OSD mapping.

But once the objects are losts that time how can i find which are the objects lost. Is there any way to list the objects of a PG

Regards

Surya Balan

On Mon, Aug 13, 2018 at 6:12 PM, Janne Johansson <icepic.dz@xxxxxxxxx> wrote:

"Don't run with replication 1 ever".

Even if this is a test, it tests something for which a resilient cluster is specifically designed to avoid.

As for enumerating what data is missing, it would depend on if the pool(s) had cephfs, rbd images or rgw data in them.

When this kind of data loss happens to you, you restore from your backups.

Den mån 13 aug. 2018 kl 14:26 skrev Surya Bala <sooriya.balan@xxxxxxxxx>:

Any suggestion on this please

Regards

Surya Balan

On Fri, Aug 10, 2018 at 11:28 AM, Surya Bala <sooriya.balan@xxxxxxxxx> wrote:

Hi folks,

 I was trying to test the below case 

Having pool with replication count as 1 and if one osd goes down, then the PGs mapped to that OSD become stale. 

If the hardware failure happen then the data in that OSD lost. So some parts of some files are lost . How can i find what are the files which got currupted. 

Regards

Surya Balan

 

_______________________________________________
ceph-users mailing list
ceph-users@xxxxxxxxxxxxxx
http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com

--

May the most significant bit of your life be positive.

_______________________________________________
ceph-users mailing list
ceph-users@xxxxxxxxxxxxxx
http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com