Search results

This option is to enable numa on vm, which is recommended when you have numa enabled hardware, it is not mandatory. If you have numa hardware, it will give you better performance if you use it

Not mandatory Read the text below If your system has a NUMA architecture [33] we recommend to activate the option, as this will allow proper distribution of the VM resources on the host system. This option is also required to hot-plug cores or RAM in a VM.

@Alwin According to this documentation If the NUMA option is used, it is recommended to set the number of sockets to the number of nodes of the host system Now if I see my hardware root@inc1pve17:~# numactl --hardware available: 4 nodes (0-3) node 0 cpus: 0 1 2 5 6 7 24 25 26 29 30 31 node 0...

These are not Proxmox logs, these are your OS logs. No relationship with Proxmox

Ok great, you can now mark the thread as solved

Please refrain from adding system with same IP back to existing cluster directly, first remove the configuration of old server from cluster and then add the same

On further analysis it was wrong crush rule applied to the cluster which triggered the same

Problem is solved by reapplying crush-map using following command ceph osd setcrushmap -i crush2.bin where crush2 is my crushmap downloaded earlier

Better don't go for RAID and use JBOD Mode instead, see if your raid controller has that option

I am getting following error on newly create ceph cluster, its been 8 hours since i created new Pool cluster: id: 1411ea40-86a9-4ff5-aabf-74213d6e0785 health: HEALTH_WARN Degraded data redundancy: 1030 pgs undersized services: mon: 8 daemons, quorum...

Why you need to build from scratch for update, just download updated driver from your OEM

How the two nodes connected ??? back to back or via Switch? if it is a switch, check lagg status in switch

Can you post output of command pvecm status ceph -s

Dear @sanojs Proxmox cluster and Ceph cluster are two independent cluster Proxmox cluster can even work with Single node by manually calling "pvecm expected 1" Ceph cluster requires minimum 3 nodes, If you look at your crush map using "ceph osd tree" You will see that osd are identified...

@frednks Please use virtio in the VM>Hardware>Network Devices if you have use Intel E1000 it is 1G Max

Questions: 1. Each VM needs high performance storage (like 1500Mb/s). Will this setup work fine? if it is Mb/s = >> 187MB/s which is low performance and it is achievable with even SAS 2. Can 5-ports bonding substitute expensive 10Gbe expansion? (To the degree of 3Gbps, I mean) if you do a...

Ok good, you can mark the thread as solved if problem is solved

What do you mean by that ??

It look good , I don't see any issue in cluster , just verify ceph nodes are able to communicate check the logs

pvecm status whether it is shown activity blocked ??