Search results

The total capacity of the cluster is defined as the sum of all OSDs. This number only changes when you add or remove disks. Do not confuse that with the maximum available space for pools which depends on replication factor or erasure code settings and currently used capacity.

So you will lose 25% capacity in case of a dead node. Make sure to set the nearfull ratio to 0.75 so that you get a warning when OSDs have less than 25% free space. https://bennetgallein.de/tools/ceph-calculator

Do not run pools with size=2 and min_size=1. You will lose data.

Ich kenne das Problem nur von OCFS2.

This is correct. But depending on how many nodes you have this is not critical.

The rbd_data.* objects seem to be leftovers. As long as there are no rbd_id.* and rbd_header.* objects there are no RBD images in the pool any more. The easiest way (and when you are really sure) would be to just delete the whole pool.

Seit 6.14 ist aio=threads nicht mehr notwendig.

Buy a non-defective enclosure.

You need to configure the old IP addresses from the Ceph public_network on the interfaces before you can do anything with the Ceph cluster.

You cannot just change IPs in ceph.conf. The first step is to add the new network to the Ceph public_neteork setting, then add new MONs with the new IPs to the cluster and after that remove the old MONs. Only after that was successful the old network can be removed from public_network and the...

You can change the crush_rule for a pool. This will not cause issues for the VMs except a maybe slower performance during the time the cluster reorganizes the data.

You will only lose the affected PGs and their objects. This will lead to corrupted files (when the data pool is affected) or a corrupted filesystem (if the metadata pool is affected). Depending on which directory is corrupted you may not be able to access a large part of the CephFS any more...

You may be able to extract the cluster map from the OSDs following this procedure: https://docs.ceph.com/en/squid/rados/troubleshooting/troubleshooting-mon/#recovery-using-osds But as you also changed the IP addresses you will have to change them manually in the MON map before being able to...

IMHO you do not need pool separation between VMs for security reasons. You may want to configure multiple pools for quota or multiple Proxmox clusters. Or if you want to set defferent permissions for users in Proxmox. AFAIK Proxmox does not show the quota max_size value.

Bau die Systeme mit Ansible o.ä. auf und die Config liegt eh schon "extern".

Keep in mind that clustering only works with latencies below 5 milliseconds.

If vmbr0 is VLAN-aware.

It's hard to tell from afar. Try it. And maybe you should move the conversation to the Checkmk forum. https://forum.checkmk.com/

Does the host mepprox01 have the Checkmk agent installed? Is it configured to query the agent?

What version of Checkmk are you running? Starting with 2.4 my extension was incorporated upstream and does not need to be installed separately any more. The mk_ceph.py agent plugin (for Python 3) needs to be deployed to /usr/lib/check_mk_agent/plugins on all Ceph nodes, not on the monitoring...