@olivierlambert said in NUMA-impact - Xeon/Epyc - 1P vs 2P:

There is no universal answer (because it's mostly depending on your VM load and what do you expect). As usual, my advice is to keep it simple if you don't have a problem with it (ie: you are satisfied by the perf.). Even a default EPYC configuration will be likely always better than a Xeon one.

After that, if you want to go deeper and learn the details, it's OK, let me just ping @tjkreidl who did a remarkable job (if I remember correctly) on this very topic.

Thanks for the mention, @olivierlambert ! Here's a link to part 3, which contains links back to parts 1 and 2. Note that NUMA will affect EPYC processors differently as they changed the die configuration at one point with the number of cores. I'm open for any questions on this topic. https://blogs.mycugc.org/2019/04/30/a-tale-of-two-servers-part-3-the-influence-of-numa-cpus-and-sockets-cores-persocket-plus-other-vm-settings-on-apps-and-gpu-performance/

@epretorious I would add that you have to be careful about overprovisioning when NUMA/vNUMA kicks in, that is when you allocate more VCPUs to exceed the number of physical CPUs of a bank of them as well as the associated physical memory (assume, for the sake of argument, you have two banks of physical CPUs and each has directly accessible to it one of two banks of memory) then things get inefficient because a CPU may need to go across to a different bank of memory to access data and there is additional overhead involved. See for example this article and the two preceding it:
https://blogs.mycugc.org/2019/04/30/a-tale-of-two-servers-part-3-the-influence-of-numa-cpus-and-sockets-cores-persocket-plus-other-vm-settings-on-apps-and-gpu-performance/

-=Tobias

@jhansen I'd suggest booting off some Linux rescue disk and just redoing all the partitions manually. I ran into an upgrade issue once on a Dell box because of some stupid little extra utility partition they had in there. See: http://xenserver.pl/author/tobias-kreidl
Look for "The (In)famous Dell Utility Partition."

Tapdisk is just palin not good as a storage control mechanism, IMO. There's only so much you can pull out of it.

@Andrew Thank you for that, much appreciated. Although I was aware of this process for SSD drives, I did not know that spinning disks had become that much smarter in the interim (~40 years!). But in any case, raw drives are very powerful if you have decent code to access them and the overhead can be appreciably less than with formatted drives.

@gustavoninetyone -- it's not on the supported hardware list, hence highly unlikely. See Olivier's response near the top of this category to see what GPUs are supported.
-=Tobias

@olivierlambert Indeed. NVIDIA in particular is bent on your having to license any sort of vGPU technology and it would not surprise me to see even passthrough leveraged at some point in the future. There are already restrictions on being able to make use of Quadro features, for example, of you don't have licenses.

Also, note that you need one video board reserved to run the native OS (XCP-ng) dom0 instance itself, so the server has to effectovely have at least two graphics boards such that one can be used as a GPU.

@Berrick Run iostat and see if anything shows up as slow or saturated with your storage I/O.

@gsrfan01 Not sure that was ever officially supported, though I did implement a direct connection to a VM on XenServer with better results than with the standard process. You're right, it may or may not work with much newer versions of XCP-NG/XS/CH.

@vsaad A PERC-6 is pretty old technology. Getting in the 50 MB/sec I/O range seems pretty good and some of the limitations will be on the disks, themselves. You might try running "iostat -x" while the Crystal Mark test is running to see if anything saturates, like the CPU, or if you get high wait states or other tell-tale signs,

@Danp said in Unable to export OVA:

page

Might those page fault entries indicate a memory error?

@chcnetconsulting Glad to hear and nice debugging work! Yes, the HA-Lizard folks are very responsive and I'm sure will have this taken care of in the next release.
I published an article originally on xenserver.org back in 2016 on tests and improvements to HA-Lizard I did in cooperation with the company, but alas, the chart with all the findings didn't translate properly when taken over by this site. I may have the original squirreled away somewhere.
https://xenserver.pl/citrix-xenserver/xenserver-high-availability-alternative-ha-lizard-2/9122

@chcnetconsulting Are you running the latest version of HA-Lizard? They care very responsive to issues if you contact them. And, yes, see if you see anything odd in the logs. Also make sure you hosts are properly time-synched with each other.

@EddieCh08666741 Indeed. Run top and make sure you have adequate resources allocated for dom0 for both memory and CPU. There should be no swapping to speak of and the CPU should be nowhere close to 100% in use.

@jhansen Great news! Maybe the SR-IOV issue is driver-related - is there a newer driver available or perhaps some setting in the BIOS?

And, yes, I bet wiping all the old partitions made a big difference.

@jhansen said in XCP-ng 8.3 public alpha :

@tjkreidl
Although it's my test lab, I have a backup of everything. I'm something of a burned child with many years of bad experience.
Unfortunately it would take a few days to play everything back.
But I'll get a new SSD and give it a try.
But first thanks for the help, I'll write if it worked.
Regards Joerg

Sounds good, Joerg. Good luck!

@jhansen If you have the full metadata, I would think that's possible. What about any VM backups, custom network settings, etc.? Lots to make sure you have before anything that drastic.

@jhansen said in XCP-ng 8.3 public alpha :

@tjkreidl
Mayby you are on the right trace.
It is a Dell Server.
This time i will wipe the disk before installation.
As the Data is on other disk i will try to mount then afterwards.
Thanks

I am willing to bet you got bitten by the Dell utility partition disk issue. And, yes, best to wipe it out. Or delete it and redo one of the other partitions. But frankly, you will really want the new 36.5 GB total layout with the dual 18GB partitions, etc., that was mentioned above. You will want the right order of partitions to match what the XCP-ng installation wants to do at some point, but it should redo the layout I hope once you get rid of that extra Dell partition. Check out what I did in my article referenced above:
"The solution was simply to delete that sda1 partition altogether using fdisk and re-install. Deleting the partition can be performed live on the host prior to the installation process."

@jhansen Any old Linux distribution recovery-like boot disk should work, as long as you can get to the partitioning app.

@jhansen I'd suggest booting off some Linux rescue disk and just redoing all the partitions manually. I ran into an upgrade issue once on a Dell box because of some stupid little extra utility partition they had in there. See: http://xenserver.pl/author/tobias-kreidl
Look for "The (In)famous Dell Utility Partition."