Replace the raid controller in the chassis with an HBA before moving into the new hardware? ;)
If you do move to the HP controller, make sure you're monitoring the health of the cache battery in the controller. We notice a significant increase to await on our OSD nodes behind these when the cache battery fails. We've replaced over 10 batteries on HP raid controllers for our OSD nodes and the first time we noticed it, there were 6 of them failed across multiple clusters causing the OSDs to be slower in those nodes.
On Wed, Aug 29, 2018 at 7:21 AM Marco Gaiarin <gaio@xxxxxxxxx> wrote:
Probably a complex question, with a simple answer: NO. ;-)
I need to move disks from a ceph node (still on hammer) from an
hardware to another one. The source hardware have a simple SATA/SAS
controller, the 'new' server have a RAID controller with no JBOD mode
(the infamous HP P410i), so i need to create some 'RAID 0 with a single
disk' fake raid.
These controller, seems to ''eat'' some space at the end of the disk,
so (doing some tests) the disk does not get corrupted with the
'raid0-ification', but lost some bytes at the end, and linux then
complain that the (last) partition are corrupted.
hammer use filestore, so practically i need to shrunk an xfs
filesystem, that is not supported by XFS.
Clearly i can do 'xfsdump' of disks in some scratch space and rebuild
filesystem but...
I've some escape path?
Thanks.
--
dott. Marco Gaiarin GNUPG Key ID: 240A3D66
Associazione ``La Nostra Famiglia'' http://www.lanostrafamiglia.it/
Polo FVG - Via della Bontà, 7 - 33078 - San Vito al Tagliamento (PN)
marco.gaiarin(at)lanostrafamiglia.it t +39-0434-842711 f +39-0434-842797
Dona il 5 PER MILLE a LA NOSTRA FAMIGLIA!
http://www.lanostrafamiglia.it/index.php/it/sostienici/5x1000
(cf 00307430132, categoria ONLUS oppure RICERCA SANITARIA)
_______________________________________________
ceph-users mailing list
ceph-users@xxxxxxxxxxxxxx
http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com
_______________________________________________ ceph-users mailing list ceph-users@xxxxxxxxxxxxxx http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com
