Latest activity
-
RSorry in advance if this is not the right place to post: I am new to Proxmox and would like to setup a home lab to learn. I was able to get a few old RSA servers from my job they were getting rid of. I did have a basic version of VMware running...
-
G_gabriel replied to the thread Windows Server 2025 CPU suddenly at 100%.Modern Windows like Win11 or 2025 virtualizes itself (=nested virtualization) when cpu type is set to host.
-
JMaybe this helps?: https://forum.proxmox.com/threads/update-impossible-after-upgrade-to-pdm-1-1-1.184018/post-855918
-
Jsee this old blog: https://www.sebastien-han.fr/blog/2014/10/10/ceph-how-to-test-if-your-ssd-is-suitable-as-a-journal-device/ The main reason is sync write, without plp, the ssd need to write directly to a full nand. for example, you need to...
-
Jdon't use consumer ssd with ceph or zfs. you need PLP to handle sync write
-
JHi. I never said that PLP is a cache. it's indeed acondensator to allow to keep data in volatile memory buffer cache.
-
JSlow networking also adds latency.
-
Wwaltar reacted to ICantDecide's post in the thread Metro/Stretch cluster mit Proxmox als Alternative zu vSphere oder Nutanix with
Like.
Das Thema kommt gerade wieder hoch, nach dem es lange links liegen gelassen wurde. Mit v9 gibt es nun die Snapshots für LVM/FC. Welche Nachteile handelt man sich denn ganz konkret mit FC-Storage ein? Wir haben bisher eine klassische Aufteilung... -
Rrlopez replied to the thread Windows Server 2025 CPU suddenly at 100%.Hello, After a few hours of running, I can confirm that the change of the CPU type seems to solve the problem. The question is why? is this a bug or a normal behavior? I have other servers running with same config and didn´t appreciate this...
-
JFor erasure coding with k=8 and m=3 you need at least 12 nodes.
-
don't use consumer ssd with ceph or zfs. you need PLP to handle sync write -
gurubert replied to the thread latency on ceph ssd.Slow networking also adds latency. -
see this old blog: https://www.sebastien-han.fr/blog/2014/10/10/ceph-how-to-test-if-your-ssd-is-suitable-as-a-journal-device/ The main reason is sync write, without plp, the ssd need to write directly to a full nand. for example, you need to...
-
It's just that these are SSD consumer drives without PLP. These are slow if you force them to write the data (sync writes). You'll find many threads about this on the forum. Maybe you could buy small enterprise SSDs with PLP and put the WAL+DB...
-
don't use consumer ssd with ceph or zfs. you need PLP to handle sync write
-
Jj.theisen replied to the thread GPU Passthrough Problem After Upgrading to Proxmox 9.2.3. [RESOLVED].Perfect, glad to hear you got that resolved and thanks for the pointer to the command in the docs! Please mark the thread as solved. Best regards Jonas
-
I went through the list. I see two problems with your SSDs: - All the SSDs have no Power-Loss-Protection (PLP). Without PLP all writes have to be completed to report it as finished. This slows Ceph writes down. With PLP the drive could report...
-
Jj.theisen reacted to IT_Tooling's post in the thread GPU Passthrough Problem After Upgrading to Proxmox 9.2.3. [RESOLVED] with Like.
Hi Jonas, thanks for the response. I researched the Proxmox Documentation Site at https://pve.proxmox.com/wiki/PCI_Passthrough and identified the recommended solution as follows: Fix H100 GPU passthrough by adding phys-bits=host to the...
-
gurubert replied to the thread Ceph in 2026 HDD.For erasure coding with k=8 and m=3 you need at least 12 nodes.
-
Those were hacks and only accelerated specific workloads or patterns. Cache misses still gave the worst case scenario performance and VM and databases both are workloads that should be calculated accordingly (unlike filer NAS). Ceph/Linux has a...