Re: Resizing a cache tier rbd

[Götz Reinicke <goetz.reinicke@xxxxxxxxxxxxxxx>]

Thanks I did resized using the base tier pool and the RBD is back online without a problem.

Regarding the depreciation, our initial design and setup was well designed with cache tiering for the expected workload. Today (3 - 4 releases later) with cephfs and our real world experiences, we would start different, if we start today.

For some workload a cache tier would still be amazing. e.g. old file archives for RO workload from time to time on a cheep EC pool 12TB SATA drives… Other vendors showed us some designs with nice features, even putting really old „never“ used data to LTO transparently. (The LTO is the end of the tier.)

But there are so many different workloads, environments, requirements, budgets etc, so there is never the one-fits-all.

From my POV ceph offers all kind of features for a lot of different workloads and is fast improving, but it is not for everybody the best choice. Check, evaluate and talk to a consultant.

Or ask the list :)

BTW thanks to the community for the feedback, help and suggestions. Regards . Götz

Am 27.03.2019 um 00:18 schrieb Jason Dillaman <jdillama@xxxxxxxxxx>:

When using cache pools (which are essentially deprecated functionality
BTW), you should always reference the base tier pool. The fact that a
cache tier sits in front of a slower, base tier is transparently
handled.

On Tue, Mar 26, 2019 at 5:41 PM Götz Reinicke
<goetz.reinicke@xxxxxxxxxxxxxxx> wrote:

Hi,

I have a rbd in a cache tier setup which I need to extend.  The question is, do I resize it trough the cache pool or directly on the slow/storage pool? Or dosen t that matter at all?


Thanks for feedback and regards . Götz

Attachment: smime.p7s
Description: S/MIME cryptographic signature

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