[pve-devel] proxmox French days conference feedback

Thomas Lamprecht t.lamprecht at proxmox.com
Thu Jun 23 12:59:42 CEST 2022


Hi,

Am 23/06/2022 um 10:43 schrieb DERUMIER, Alexandre:
> So the conference was a success.
> Overall experience with proxmox VE/PBS is really good.
> Nobody had serious problem with PVE/PBS.
> 
> Some are coming from openstack (too big, too complex to manage)
> Some others are coming from vmware.
> Some others are using proxmox since 0.9 😉
> Some return of experience with ceph too. (with some problems).
> 
> 

Thanks for the feedback and talking about Proxmox projects!

> Maybe for the most requested missing features:
> 
> - cross cluster management + replication/disaster recovery.  (They have
> a lot of dual room / dual site.  But 3 sites to keep quorum is not
> always possible)

That's in the pipeline, cross cluster migration is not that far off and Fabian
should be soon able to pick that up (he works on some infrastructure projects
currently to make air-gapped offline updates possible in a relatively easy and
integrated way), that's one of the biggest pre-requisites left.

> 
> - a drs feature like vmware for vm balancing 
> (I'm still working on it, I'll try to have a working after this summer.
>  I still need vm pressure stats pending patches apply first 😉

I'd really like to more actively work on this from our part too, I thought about
7.3 feature planning a  bit yesterday and wrote a few (rough) edge points for
tackling this, using the alogrithm and rough direction you already worked on in
your proof of concepts (thx!):

- [ ] Static (and later Dynamic) Resource Scheduling (S/DRS)
    - [ ] Coordinate with Alexandre as he's working partly on that too, but we
          may want to use a bit of a different design and/or feature set (at
          least initially) and integration timeline
    - [ ] checkout TOPSIS more closely and implement relevant parts in rust to
          expose via perlmod, that's then fast and much easier to reason
          correctness in static, and safety focused language like rust.
    - [ ] Make basic static resource capacity like CPU (# of socket, core and
          hyper threads) and memory available for other cluster nodes (for
          example, via kv_broadcast after (re)start of pve-cluster)
    - [ ] Add infrastructure to use that static (!) information for balancing
          out the cluster.
        - [ ] spit out a list of actions that would result in a balanced
              cluster: migrate guest A to node X, migrate guest B to node Y
        - [ ] use that for creating a simulation and regression testing system
              in the spirit of the ha-managers simulation and regression test
              system, but as independent test & executable
    - [ ] integrate in HA, due to static-ness and safe-and-slow integration it
          should be first only be done on recovery, for better balancing out.
    - [ ] add API create support for creating a CT/VM to the best fitting node,
          i.e., the lowest used one
    - [ ] make balancing algo available for non-ha too, allow a cluster wide
          manual re-balance (e.g., with action-proposal shown to user for
          confirmation)
    - [ ] Extend with dynamic information like IO/memory/CPU pressure
    - [ ] Finally: Allow to opt-in in periodic auto-balancing for HA managed

IMO the semi-static resource availability and usage would be nice in general as
first step, that could then also allow one to relatively easily pre-error/warn out
on VM start if there won't be enough memory available (maybe overridable for odd
zram/KSM cases, or when one just doesn't want to care about that and likes OOMs ;)

> 
> - Pool quota (restrict the total mem/cpu/disk allocated to all vms in a
> pool). as they have some clusters shared between differents
> departements / students/ ...
> 

It'd need a bit new infrastructure, but it wouldn't be /that/ hard to implement.

> 
> A big thanks to Daniela for the T-shirts and other goodies !
> 
> Also, another recurrent question:
> 
> "Why proxmox team is not more present on differents events/conference 
> like fosdem, ... ?"
> 

Some colleagues frequent fosdem, but in the last two and a half years doing
or attending presence conferences was a bit difficult.

> Yes, we would like to drink some beers with you guys 😉

Would be nice! :-)




More information about the pve-devel mailing list