Search results

Wondering why they would class 40Gbps as expiremental..?

I'm sure due to some changes in their license you need to use their repo / install from them @ https://docs.linbit.com/docs/users-guide-9.0/#ch-proxmox

Hey, So in the latest 5.3 Kernel object-map & fast-diff have been added : https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?id=d9b9c893048e9d308a833619f0866f1f52778cf5 This means we can get enhanced performance in certain operations and also means we can enable...

When you say 80/50% hit you do realise CEPH is 3 way replication. Meaning for every bit of data your saving it 3 times, so technically and overhead of 300%

What's the output of apt-get update

That is completely up to the apps / data you are running on the VM's you want to be able to HA across the 3 servers. There is no simple plugin for all cases.

No, the only way you would get HA is at the VM software level. You can't cluster LVM as you want to.

1) If your cluster never needs to grow past the 2 servers being in a pair linked by some dual 25/40 then I would go with that option, you generally can get up to 50% lower latency vs 10Gbps let alone any small overhead from bonding. 2) Very hard to say, but if you look at the 4K random IOPS...

Just to confirm the node itself its kernel panicking? Not just the VM's? What I meant was as in physically connecting a screen or via ILO to see what the physical server is doing. For example could be a new driver update or kernel that is causing the crash/panic. You really need to catch the...

Have you been able to attach a console to the server and see the kernel panic? Most kernel panics wont be in the log due to the fact its the kernel itself that has crashed.

Correct, however CEPH you should never run at full capacity as a single drive failure can make the system full and stop operating. So the fact your nearly using 4TB out of 6TB I would say your getting close to the point of having to upgrade. This may be why they set the pool to only 4 out of...

Your RBD pool is set to 4000G, which is what Proxmox will report. Your CEPH cluster has 6000G, but the RBD pool only has 4000G assigned to it.

1) Speaking from experience latency has a bigger effect than pure bandwidth, if you can go for the higher speed low latency NIC's over multiple 10Gbps then I would say go that way. If not if your 2 x 10GBit/s are going to separate switches then it also gives you some redundancy over a single...

Where in Proxmox are you seeing only 4TB? As above if you can attach the output of 'ceph df'

I wouldn't worry to much about the extra NVME, the main bottleneck is 100% your network. If you can add just the 10Gbps LAN, use a small part of each NVME for RAID10 for the OS and the rest for CEPH you should see much better performance than you are currently seeing.

You should stop opening new topics, every time you do your just making it harder for someone to see the full story. Post the above log in your main topic and that way someone can see it's more than just a single file that has gone missing. If this is really urgent then you need to pay for a...

You are being massively limited by your network, a single NVME can do more than your 1Gbps network can handle. You will need to upgrade to 10Gbps atleast to be able to see some of the NVME performance.

So your looking at only having one CEPH storage node? If so that's really not what CEPH is designed for, yes it can run on one node but the benefits of CEPH are lost. If you want a large single storage server your better running Raid10 on the 720 and then using scsi it some other network based...

As per the PM it looks like you have some issues with the /etc/pve* DB file's and folders. If you can post all the log's and status from the sevices as per the PM someone may be able to help you resolve the issue.

Once you have done the steps I listed earlier and added the discard statement in the config your just need to wait for windows to run the internal cleanup. You can force this / change how often it runs here ...