Sorry, I honestly don't quite understand what you mean by your first sentence.
I can say however, that the Proxmox hosts don't have any other cpu performance problems. Other CPU-intensive tasks that we tested on both systems were comparable or...
Hallo!
die Überprüfung von der Lizenz schlägt fehl mit einem timeout.
Das Problem ist, dass für shop.proxmox.com A und AAAA Einträge gibt aber der Server nicht auf IPv6 antwortet.
Wenn ich IPv4 Adresse von shop.proxmox.com in /etc/hosts...
Hi @FrancisS,
The loop happens because Proxmox cluster HA tries to honor the node shutdown/migration policy, but VMs with PCI/USB passthrough can't be live-migrated across nodes without host-specific device re-mapping, so HA gets stuck in an...
Hey @infoplus,
Have run into a very similar bottleneck with PowerVault ME4/ME5 series over iSCSI on Linux kernels. A couple of things to check in your multipath and block layer configs:
1. What path_grouping_policy and path selector are you...
Yes, Jumbo Frames (MTU 9000) are fully enabled end-to-end across the entire path (PVE interfaces, switch ports, and ME5 iSCSI portals). Ping tests with -s 8972 -D complete with 0% packet loss.
I see dropped packets though:
root@PM8161:~# ip -s...
Thanks for your explanation. I guess that I will do a lot of tests before we think about production usage. Since we automate everything, an ansible module will calculate the placement.
Striping has some advantages and disadvantages. Its not...
Why should this be a problem with PVE specifically? You may have to ask the people / company developing it. PVE "just" provides the virtual machine. What you do with it is totally up to you.
Snapshotting shared thick LVM? Yes, you would need LVM locking, which was required in the past and you will have the problems you talked about. AFAIK, newer PVE versions do not require the locking daemon if and only if you do all metadata...
When I add 64 PVEs each 64TB to one single VG, I`am afraid that it may be a longer downtime in case of any issue. A single PVE down will cause the full VG to crash. This can happen not only when a SAN Issue occours, but only in high load...
Hello,
I did some additional testing based on your suggestion to use -mem-prealloc, and I think this gives a much better picture of what is happening.
I create test VM 3005 with 128 GiB of memory, and do qm set 3005 --args '-mem-prealloc'
Fill...
not sure if this is related, but since the change of the new keys when you do a fresh ceph install (for example when adding a new ceph node), ceph pool status (via pvestatd) (server-view storage-pool) is showing a "?" which only disappears after...
Once upon a time Linux network interface names followed the unpredictable pattern: eth0, eth1, eth2, eth3, eth4, eth5.
With the advent of the miraculous systemd and "Predictable Network Interface Names" they have a variety of names. On one...
11. RAPL showed the CPU was already extremely efficient
At around 9 W wall power I also measured Intel RAPL energy.
Over roughly 30 seconds I obtained approximately:
CPU Package : 1.89 W
CPU Core : 0.085 W
DRAM : 1.47 W
This was...
Stimmt, bei 75% bläst PVE nichts auf. Zwei Sachen aber: stell den Graph mal von Durchschnitt auf Maximum um, in der Wochen- oder Jahresansicht ist ein 20-Minuten-Peak sonst komplett weggemittelt und du siehst nur eine glatte Linie. Und der ZFS...
Die 30% Systemunterbrechungen, die @richik75 gemessen hat, riechen für mich weniger nach VBS als nach den Windows-eigenen Software-Mitigations. Mit cpu: host sieht der Gast auf den alten Xeons (E5 v2 bis v4) die ganzen Spectre/MDS-Geschichten so...
You mean in a stripped setup? Yes, I agree. In a filesystem, you have this too, but don't see it (see next answer)
As someone who has worked with both of them in the past, I can say that they have a lot of drawbacks, one is performance (which...
Good question — this is one of the main safety concerns the plugin was designed around.
SharedLvmThin does not rely on multiple PVE nodes independently modifying LVM metadata at the same time.
All shared-LVM metadata mutations are serialized...
Hi everyone,
I wanted to document a power-consumption problem I spent quite a lot of time investigating, because some of the results were very unintuitive and may also be relevant to other people running Proxmox/Linux on older laptops or Haswell...
To clarify: The patches mentioned by @fabian fix an issue where restores from PBS/VMA to ZFS can cause increased IO latencies on other ZFS-backed VMs during page writeback. The patches are included in pve-qemu-kvm 11.0.3-3 and qemu-server 9.2.7...