Search results

@aaron any news? by the way, is there any change to build 5.15 kernel for PVE 8 for testing or build 6.2 with patch applied?

And bellow how ICPM response time spikes look

One more observation: Disabling KSM requires rebooting the host because stopping KSM service (and/or disabling it) does not really stop it. ksmd becomes ghost and cannot be killed (I didnt manage to kill it) This screen shows: kernel with mitigations=off and ksdtuned stopped and disabled (but...

Host1 - problems CPU(s) 56 x Intel(R) Xeon(R) CPU E5-2690 v4 @ 2.60GHz (2 Sockets) Kernel Version Linux 6.2.16-14-pve #1 SMP PREEMPT_DYNAMIC PMX 6.2.16-14 (2023-09-19T08:17Z) Intel-microcodes installed VM: W2019 (96GB RAM + 42 cores, NUMA) Host2 - problems CPU(s) 48 x Intel(R)...

Is there any plans to integrate full mail backup/restore in PGM? Something like: https://www.mailpiler.org/

Could you try to continuously ping your VM (from any other device in network) like gateway? Huge ping delay spikes are common for the topic issue. If you don't have any then probably there is something else interfere P.S. Do not ping from another VM on the same host P.S.S In my case before...

Well, now it looks reasonable Next, what about KSM? Have you disabled it?

If I am not mistaken mitigations=off is not applied What filesystem behind your root partition? In my case (zfs) i had to edit cmdfile file Check this post: https://forum.proxmox.com/threads/disable-spectre-meltdown-mitigations.112553/post-485863

If on your systems KSM is in use then try to disable it with "systemctl disable --now ksmtuned" on top of and cross-check that mitigations are really off with lscpu

@t.lamprecht Is there any progress on sorting out the degradation in KSM and huge performance (CPU 100% spikes) loss in Windows guests with 6.2 kernels?

Already done on page 2

For non-root limited user I would like to limit view to pool only in pve cluster. Is there any way to disable datacenter view or/and set another view (pool view) for given user as default The idea behind is to hide number of cluster nodes and their names Thanks in advance

I can confirm that with 6.2.16-14 problem still exists Setting "mitigations=off" the only solution @ProxmoxTeam Any progress on this issue? P.S Taking into consideration that KSM with kernel 6.x is broken on dual socket boards +1 vote to release 5.15 kernel

did you check dmesg output?

check /etc/hosts and update accordantly

Holly cow! My bad. You made my day. Thanks!

Sure all the screens are made from the node WITH CEPH binary installed (CEPH cluster node)

I had 3 nodes cluster with CEPH installed (several OSDs on each node) in network 10.63.210.0/24 for PVE (1Gb) and 10.10.10.0/24 for CEPH (10Gbe). It was OK until I added 4-th node to PVE cluster only from another network 10.63.200.0/24 (no CEPH/OSD on that node). PVE cluster is happy, CEPH...

On Windows guest we got ~ +10%

Try mitigations=off as workaround. It could compensate performance drop, especially under memory pressure