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? * How do I determine the number of spinning drives that can share one SSD? * 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
 |