Ceph User Survey 2019

[martin]

The Ceph team is conducting another Ceph community survey. The results will help the developers to learn more about the Ceph deployments.

I encourage all Proxmox VE Ceph users to participate in the survey. It only takes a few minutes to answer:

https://ceph.io/user-survey/

Thanks for your help!
__________________
Best regards,

Martin Maurer
Proxmox VE project leader

 

[sherminator]

done

 

[RobFantini]

For a standard pve ceph install, what are the answers for these:

What Ceph Manager modules do you enable?

Which messenger type is in use? [ I answered default]

Do you use the Rados Gateway (RGW) interface in your Ceph cluster?

Interfaces to access CephFS
MDS cache size
Do you use subtree pinning? [ cephfs section]

at Deployment and configuration , is ceph-deploy used by pve?

 

[t.lamprecht]

What Ceph Manager modules do you enable?

Modules and their state can be listed with: ceph mgr module ls, by default the "iostat" and "restful" modules are enabled.

Which messenger type is in use? [ I answered default]

v2 by default for new ones, IIRC, backward compatible for upgrades https://docs.ceph.com/docs/master/rados/configuration/msgr2/

Do you use the Rados Gateway (RGW) interface in your Ceph cluster?

No, by default, or Proxmox VE in general, not used.

Interfaces to access CephFS

Kernel or CephFS-FUSE client (default the former)

MDS cache size

1 GiB (upstream default)

Do you use subtree pinning? [ cephfs section]

No.

at Deployment and configuration , is ceph-deploy used by pve?

No, we use our own deployment code since the beginning of the integration in PVE 3.X, were ceph-deploy wasn't avialable (IIRC).
Our deployment code levearages our clustered realtime configuration filesystem.

 

[psionic]

done

 

[RokaKen]

Done.

 

[elurex]

done...
i really wish there is a way bcache can be use with ceph nautilus. DM-Cache really under performed.