Search results

With licensing it's hard. Either have every node fully licensed,or split into smaller clusters,even one-node clusters,set up replication(depending on RTO/RPO) and work with that.

I guess this could pose a security issue if allowed?

Also,is this a problem with too much pg per osd?

[WRN] MDS_INSUFFICIENT_STANDBY: insufficient standby MDS daemons available have 0; want 1 more Why is this if mds is 1/1?

The beauty of ceph it can run on anything. You need extra network card(even 2.5g works in small environment),and one disk per node and off you go! Yes,performance isnt maximum you can get, but it works, and you can test it, failover,HA and everything. I also have one customer with 3 node 2.5gb...

what do your vms have that needs object instead of lets say file storage?

It is in testing repo atm.

I have these disks(SSDPE2NV153T8) in one of the cluster i'm maitaining. They are okay. But i would always stick more disks than bigger disks.

Are you using host cpu type or x86_64_v3?

Thats okay for single threaded iperf3, around 20-25gbp/s.

Disc model? LACP is usually 2x25,hardly you will fill the full double throughput.

You didn't say which disks.

That is why you have RTO/RPO , if the boss says you have few hours, then you are okay with everything.

You have disks for everything, but what will be on CEPH in this case?

Usually up to whole machine you can get away with.

For compatibility reasons it is always best to use VMs.

But HW raid is faster,as always.

Yes if you use nvme disks, something like 4-6 per node.

But i'm talking about push,not pull.

Why does source PBS needs to be Internet-accessible in this case?