Hi, the default rbd chunk size is 4MB, it's the "order" that defines the chunk size: rbd info pool/volume1 rbd image 'volume1': size 8 GiB in 2048 objects order 22 (4 MiB objects) You can create images with a different order using the '--object-size' parameter: rbd create temp/rbd-16K --object-size 16K --size 100M rbd info temp/rbd-16K rbd image 'rbd-16K': size 100 MiB in 6400 objects order 14 (16 KiB objects) There also '--stripe-unit' and '--stripe-count' parameters to keep in mind, but I'd start simple as possible. Just a few months back we had to migrate a customer galera cluster (OpenStack) into CephFS (on SSD pool) because the response times were awful from the local (rotating) disks of the control nodes. I also thought about attaching a RBD from a SSD pool, but since the nodes were already connected to CephFS, we decided to stay with CephFS. Zitat von filip Mutterer <filip@3dds.io>:

Hi!

Is Block alignment for Databases a thing with RBD?

I heard something with 16K alignment ...

If yes how can be checked what alignment a RBD got.

And yes I need to run my Database in Ceph as I have no other storage with redundandency.

Hints for optimizing a single Block device for a Database are very welcome.

Greetings

filip _______________________________________________ ceph-users mailing list -- ceph-users@ceph.io To unsubscribe send an email to ceph-users-leave@ceph.io