Search results

No Direct IO enabled here...

Like I said, I **want** to use virtiofs and get rid of NFS for this particular purpose, but the performance hit is just too great for me.

Yep. Cache=always is enabled. ZFS draid2 is being used as backing storage.

It's so slow compared to NFS. Like less than 1/4 the performance in my testing with FIO. I want to use it because it seems like a cleaner implementation on how to share files with the host. But, I cannot take that big of a performance hit. Shame really. DIRECT: server:/mnt/server1:# show disk...

Thanks for all the discussion. Good stuff. However, none of this is my point. I don't wish to discuss the merits of one storage type or another. I simply would like a usable snapshot feature when using a ZFS volume. It's totally doable. Just change the resulting dialog box and a little code...

Honestly, if they wanted to make it usable, get rid of the "failed" dialog box and replace it with a "This will remove these other snapshots if you want to rollback to here. Do you wish to continue? yes/no" As it stands it's not useful -- at least not from the GUI. Okay, the limitation exists...

This is not a true statement. Selecting a snapshot a few down the list does not destroy in-between snapshots. It simply fails the rollback operation with a popup that says "can't rollback, 'snapshot' is not the most recent snapshot on 'disk'." I *wish* it destroyed the in-between snapshots and...

What's the point of ZFS snapshots if only the very last one can be rolled back to? Seems kind of pointless.

I have a 5 node cluster that has been in production for more than 5 years now. Since PVE6, I'm starting to see things like this in my VM config files: [^A^@^@^@^@^@^@&^@^@^@^@^@^@^@^@^@^@^@nodes/lphxpve16/qemu-server/1150.conf^@agent: 1 balloon: 0 boot: dcn bootdisk: virtio0 cores: 15 ide2...

I'm on PVE 6.0.4. Great job on this release. The upgrade was relatively painless for me. I have a bunch of VMs under HA management. I bulk migrate these HA VMs from one host to another and set the Parallel Jobs value to 1 or more. All VMs are moved at once and the Parallel Jobs restriction is...

That is fantastic news. Thanks you so much.

Hi, Why are network bridges, both OVS and Linux, configured at the host level and not at the Datacenter level? To me, bridges should be configured at the Datacenter level so that the bridge definitions can be shared by all clustered hosts within the Datacenter. I understand that physical NICs...

At least provide the option to delete the backups when deleting the VMs. A simple tick box is all it would take.

In addition to all of this, I would like the backup process to be able to delete orphaned backups. If a VM no longer exists for the backup files, remove all the backup files for the no longer existing VM.

Phoronix benchmarking shows that Spectre and Meltdown patches can affect both cpu and disk performance. Perhaps that is what is going on here.

I use fail2ban on all VMs and hosts. However, I don't use it to monitor PVE firewall log entries. I use it for its intended main purpose of banning brute force attacks over network sockets, mostly for SSH access.

Netflow/SFlow/IPFIX do not require port mirroring. It's the entire point of the different protocols. Network devices deliver packet summaries to a destination IP address with an appropriate logging/parsing/presentation tool (ElastiFlow in this case).

For ZFS, a lot of RAM is required (the more the better as by default it takes half), and for spinning disks it is recommended (basically required) to have an enterprise class SSD to offload ZIL/L2ARC operations to increase performance. Your performance should improve after that, but it will...

Thank you for your opinion. I've used ZFS on different operating systems in the past. I have had mixed results with it depending on the situation. Search this forum for ZFS issues. You will find a lot of results. However, you are correct when you state that I must have reliable rock solid...

Create a new NFS share on your NAS one level deeper than the current one and mount that. Instead of mounting host:/share do host:/share/mount/ instead.