Tag-Based Automation: Manage VM CPU Priority via assigned tag.

Pilow

@johnnezero this could be a plugin in XOA !

johnnezero

@Pilow Sounds like an awesome idea. Send any details you may have on how to make plugins (if you know how that is).
Adding to the ToDo list - Thanks!

john.c

@johnnezero said:

@Pilow Sounds like an awesome idea. Send any details you may have on how to make plugins (if you know how that is).
Adding to the ToDo list - Thanks!

Looks like I can help out again just tracked down this past thread on the forums.

https://xcp-ng.org/forum/topic/7202/how-do-i-create-a-new-plugin

How’s your JavaScript (Typescript), JSON etc? These are the languages needed to develop plugins for Xen Orchestra.

johnnezero

@john.c Thanks much, looking into it.
"Open-Source for the Win!"

john.c

@johnnezero said:

@john.c Thanks much, looking into it.
"Open-Source for the Win!"

Your welcome!

tjkreidl

@johnnezero It would be also interesting to take UMA/NUMA into account as VMs -- in particular, VMs with vGPUS -- can run much more efficiently if they do not cross memory bank boundaries that span more than one CPU instance. On some Linux systems -- not sure about the one hosting XCP-ng -- you can even disable NUMA. Just an additional thought here. I published a number of years ago a three-part series "A Tale of Two Servers" discussing a number of related optimizations but alas, the Citrix blogs were eliminated and I'm snot sure where copies of these articles exist anymore. But there are plenty of articles on this, in particular by Frank Denneman, and also ones like the following;
https://indico.cern.ch/event/304944/contributions/1672535/attachments/578723/796898/numa.pdf
https://docs.xenserver.com/en-us/xenserver/9/numa.html

john.c

@tjkreidl said:

@johnnezero It would be also interesting to take UMA/NUMA into account as VMs -- in particular, VMs with vGPUS -- can run much more efficiently if they do not cross memory bank boundaries that span more than one CPU instance. On some Linux systems -- not sure about the one hosting XCP-ng -- you can even disable NUMA. Just an additional thought here. I published a number of years ago a three-part series "A Tale of Two Servers" discussing a number of related optimizations but alas, the Citrix blogs were eliminated and I'm snot sure where copies of these articles exist anymore. But there are plenty of articles on this, in particular by Frank Denneman, and also ones like the following;
https://indico.cern.ch/event/304944/contributions/1672535/attachments/578723/796898/numa.pdf
https://docs.xenserver.com/en-us/xenserver/9/numa.html

If you remember the URL and date maybe try the wayback machine of Internet Archive. They’re known to archive sites and articles wherever they can, may hold a copy that’s accessible.

johnnezero

@tjkreidl Wow that all sounds pretty intense - will keep it in mind (but it's probably way above my $0 pay grade - haha). Thanks much!

tjkreidl

@john.c Not found with the Wayback Machine, alas. Still not finding it anywhere else, but will keep looking!
It's a crying shame Citrix didn't preserve the treasure trove of old community blogs.

john.c

@tjkreidl said:

@john.c Not found with the Wayback Machine, alas. Still not finding it anywhere else, but will keep looking!
It's a crying shame Citrix didn't preserve the treasure trove of old community blogs.

I did a bit of digging with the aid of AI and I’ve managed to uncover the original three blog posts of NUMA and references to UMA. If you do some more digging you may be able to uncover the rest, so it can be rewritten and/or updated, then be hosted somewhere that won’t go down so easily, or be lost as easily. If you do an update or write etc, may I suggest switching the images used to WebP or AVIF format, will seriously help file size while maintaining their quality (or even giving room for higher quality). Consider switching to SVG for diagrams rather than raster (or as the default). I’d suggest checking out to consider using Mermaid for diagrams (https://mermaid.ai/open-source/?utm_medium=hero&utm_campaign=variant_a&utm_source=mermaid_js). Maybe if you do a rewrite use markdown and something like Hugo, to generate it from the files to host on GitHub or some other pages providing repository (e.g. GitLab Pages or Codeberg Pages).

https://web.archive.org/web/20220527221535/https://www.mycugc.org/blogs/tobias-kreidl/2019/03/07/tale-of-two-servers-bios-settings-affect-apps-gpu

https://web.archive.org/web/20220527213026/https://www.mycugc.org/blogs/tobias-kreidl/2019/04/30/a-tale-of-two-servers-part-2

https://web.archive.org/web/20220527215004/https://www.mycugc.org/blogs/tobias-kreidl/2019/04/30/a-tale-of-two-servers-part-3

https://community.citrix.com/forums/topic/235895-xenserver-vm-citrix-worker-sizing-question/

https://xcp-ng.org/forum/topic/9359/cpu-provisioning

https://community.citrix.com/forums/topic/237493-memory-and-cpus-assigning-to-vms-in-order-to-obtain-maximum-performance-according-to-numa-topology/

https://community.citrix.com/forums/topic/241553-bios-power-performance-settings/

https://community.citrix.com/forums/topic/243640-citrix-hypervisor-performance-tips/