Hi Erik,
On 3/10/2022 6:19 PM, Anderson, Erik wrote:
Hi Everyone,
I am running a containerized pacific cluster 15.2.15 with 80 spinning disks and 20 SSD. Currently the SSDs are being used as a cach tier and holds the metadata pool for cephfs. I think we could make better use of the SSDs by moving block.wal and block.db to the SSDs and I have a few questions about this.
* How do I change my config to hold block.db and block.wal? Do I need to fail out drives and then re-create them? What is the proper procedure for this?
This is doable without OSD recreation starting v15.2.15 via new
ceph-volume migrate/new-db/new-wal commands. This supports LVM-based
deployments only though. Technically that's doable for partition based
deployments as well but it might be tricky.
* How do I determine the number of spinning drives that can share one SSD?
I think running some experiments on a test cluster would be the best
option given the variety of parameters which might affect the answer...
* Is this a good idea? Am I likely to see a performance increase – what kinds of workflows will benefit from this change?
Thanks for your help!
Erik Anderson
_______________________________________________
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
