Search results

~ Please explain this?

Which Samsung drives are you using?

That's quite a bit performance loss. Is this expected?

I want / wanted to move CEPH to the 2nd IP subnet, but that failed. Both IP subnets can communicate. And all worked fine, till I had to reinstall Proxmox onto another drive. So, shortly after my last reply, I added the 2nd IP subnet (rather, 192.168.11.243) to SRV3 and now all 3 nodes can see...

root@SRV1:~# corosync-cfgtool -s Local node ID 1, transport knet LINK ID 0 addr = 192.168.11.241 status: nodeid: 1: localhost nodeid: 2: connected nodeid: 3: disconnected root@SRV1:~# corosync-cfgtool -s Local...

Thanx I ran the update and rebooted. Now SRV3 is on it's own, and SRV1 and SRV2 are in the cluster: root@192.168.10.241's password: Linux SRV1 5.4.98-1-pve #1 SMP PVE 5.4.98-1 (Mon, 15 Feb 2021 16:33:27 +0100) x86_64 The programs included with the Debian GNU/Linux system are free software...

root@SRV1:~# pveversion -v proxmox-ve: 6.3-1 (running kernel: 5.4.98-1-pve) pve-manager: 6.3-4 (running version: 6.3-4/0a38c56f) pve-kernel-5.4: 6.3-5 pve-kernel-helper: 6.3-5 pve-kernel-5.4.98-1-pve: 5.4.98-1 pve-kernel-5.4.65-1-pve: 5.4.65-1 pve-kernel-5.4.34-1-pve: 5.4.34-2 ceph...

ok, Ok, I can now login. Had to run the following commands on all 3 servers: On every node do systemctl stop pve-cluster This may take a while On every node do sudo rm -f /var/lib/pve-cluster/.pmxcfs.lockfile On each node – one by one do systemctl start pve-cluster And then it's like...

That's the problem. When I login to SRV1, only SRV1 is online. When I login to SRV2 and SRV3, both SRV2 and SRV3 are online - almost asif there's 2 clusters. root@SRV1:~# pvecm status Cluster information ------------------- Name: WHZ Config Version: 5 Transport: knet...

Did you ever get this working?

I have a 3 host cluster and changed one of the hardware nodes. The new machine didn't want to boot from the proxmox OS drive, so I decided to Install Proxmox onto another drive. Before I did this, however, I removed the 3rd node (SRV3) from the cluster. Then i wanted to re-add the node, but...

Thank you for the explanation. CEPH is the better option then.

Is it possible to setup a ZFS multi node cluster, like one would do with CEPH? Let's say I have 20x servers, each with 24 SSD's, and I want to use ZFS on each server. Can I have replicated storage across the cluster, so that in the event that a node fails, or I need to move some VM's off one...

Is the RAM ECC or not? Like I said, only my one machine, which doesn't have ECC RAM has this behaviour, till I added extra cooling to the RAM. memtest didn't show any errors either.

Here's the ceph.conf file: root@SRV1:/home# more /etc/ceph/ceph.conf [global] auth_client_required = cephx auth_cluster_required = cephx auth_service_required = cephx cluster network = 192.168.10.0/24 cluster_network = 192.168.10.0/24 fsid =...

I found that one of my "servers" which doesn't have ECC RAM also sometimes do (or used to) do this, so I put some extra fans on my the memory modules and now it doesn't crash like this anymore. Your RAM might pass memtest, but it's probably too little RAM for the processes on the cluster.

Please help. I tried to change my CEPH IP's from 192.168.10.0/24 to 192.168.11.0/24, but it wen't horribly wrong. My initital setup is / was as follows: 3 servers: SRV1 - 192.168.10.241 SRV2 - 192.168.10.242 SRV3 - 192.168.10.243 I wanted to move CEPH to a 2nd IP subnet, with different network...

This is also great, thanx. I also found which helps a bit

Thank you.

How do I see which /dev/sdx an OSD is running on? I need to remove some drives from my cluster, but don't know which OSD to stop and remove, to remove /dev/sdh (for example).