Latest activity
-
FFunar replied to the thread S3 Storage via CEPH RGW & cache datastore?.So, as a real world example, I have 233 snapshots with 14 VMs which comes to 2.1tb (34% dedup) in the S3 bucket that PBS uses. My cache disk is occupying 680gb of 2tb. This is only a small fraction of what we're currently utilizing PBS for. My...
-
BBadej replied to the thread Get specific rule by log code.Hmm... DefBlockSubject - is the name of the rule (filter) that triggered. AC81C21C94 - is most likely the message ESMTP ID (you can check it in the first Received: header). Ex.: ... (Proxmox) with ESMTP ID Judging by the rule name, the message...
-
Ddimante replied to the thread Not getting good network throughput even with LACP bond.Thank you for your reply. I use speedtest.net as an internet throughput guide. Let's start with the core windows server 2022 server I have. Here is the vhardware configuration. Here is throughput from a device on my net (non-virt) So why is...
-
-
Ttenstareri replied to the thread Tips on core assignment to VMs.Thank you UdoB for your thoughts! What about Proxmox itself, how much CPU time does it need? Lets say if one would give a single VM all the threads on the CPU (and a workload that would make use of all of them), does that then somehow starve the...
-
JJohannes S replied to the thread Ceph performance.10Gbps is the minimum for a productive cluster and one should have at least three nodes. And with three nodes you won't have auto-healing and can only loose one node as explained by @UdoB in his writeup on small clusters...
-
Moayad replied to the thread Pveproxy shows non actual status in webinterface.Hi, To investigate more could you please provide syslog when the OOM and split brain happened until you started the 109 VM? -
Pprinskarnatie replied to the thread Minisforum MS-A2 - intel x710.I did some testing between 2 MS-A2's connecting 1 X710 port on each via a Mikrotik CRS309 using DAC cables. Getting ~9.4 Gbps in both directions using iperf3. I also did a test to a Windows 11 PC using an older Intel 82599 10Gb SFP+ NIC connected...
-
JLack of power-loss protection (PLP) on those SSDs is the primary reason for horrible IOPS. Read other posts on why PLP is important for SSDs. I get IOPS in the low thousands on a 7-node Ceph cluster using 10K RPM SAS drives on 16-drive bay...
-
JJohannes S reacted to bbgeek17's post in the thread Proxmox 9 with shared LVM on iSCSI problem with
Like.
You can create a non-production cluster with two nodes The example references a PVE cluster with 2+ nodes This ^ is not a step in the referenced document. Blockbridge : Ultra low latency all-NVME shared storage for Proxmox -... -
Jjtru reacted to t.lamprecht's post in the thread New Archive CDN for End-of-Life (EOL) Releases with Like.
Today, we announce the availability of a new archive CDN dedicated to the long-term archival of our old and End-of-Life (EOL) releases. Effective immediately, this archive hosts all repositories for releases based on Debian 10 (Buster) and older...
-
Jjtru replied to the thread Not getting good network throughput even with LACP bond.How exactly do you measure Ethernet throughput performance, which guest OS do you use, and which network devices/adapters did you choose to configure/emulate in your VMs?
-
TTobiWanKenobi replied to the thread ILOAmplifer PACK no networkconnection.Yes, somehow no one can help. It seems to be a problem with the amplifier. Unfortunately, there’s no access to the underlying Linux system in the background. I previously ran it on Hyper-V without any issues, but I replaced that Hyper-V setup...
-
Jjtru reacted to spirit's post in the thread ESXi → Proxmox migration: Host CPU vs x86-64-v4-AES performance & 10 Gbit VirtIO speeds with Like.
seem than freebsd have fixed the checksum bug with virtio-net recently (september 2015 / freebsd15) https://cgit.freebsd.org/src/commit/?id=5a8f33f52ae38bbf12f8f45b8e0f75166805c386 I don't known if it's already available in pfsense/opensense...
-
jsterr replied to the thread Ceph 20.2 Tentacle Release Available as test preview and Ceph 18.2 Reef soon to be fully EOL.Thanks! Im curious about the improvements they made to EC (should be a lot faster now). Will update soon and report back. -
Kkoby replied to the thread Get specific rule by log code.Hi Badej , I am seeking to know what is the AC81C21C94 refer to. I my case I block by mistake a valid mail which I like to retest again the rule that blocked it.
-
PPredis replied to the thread [SOLVED] VMs shutting down on remaining host when powering off second node in 2-node Proxmox cluster.I solved the issue by disabling pve-ha-crm and pve-ha-lrm. It's weird because i didn't use any HA or anyting. I don't know why that fixed the issue
-
Ddimante posted the thread Not getting good network throughput even with LACP bond in Proxmox VE: Installation and configuration.I'm seeing full line‑rate performance (around 945 Mbps up and down) from my non‑virtualized devices over a single 1 GbE NIC. My Proxmox host is configured with four NICs bonded in LACP, and the switch side is correctly set up. However, any guest...
-
Mmpit replied to the thread Modifying ISO for Automated Installation.Thank you. I eventually resorted to an Ansible playbook, some advantages include being able to form the cluster(s) and install ceph etc. along the way. firstboot.sh I ended up including with the ISO for future reference: #!/bin/bash set...
-
VictorSTS replied to the thread HDD usage option..Because it has just 750GB and I bet that all metadata is already cached. Try rebooting the server and running GC again or try running GC on a 140TB datastore on BTRFS. I've done such tests and performance is similar to ZFS. Not to mention that... -
bbgeek17 replied to the thread Proxmox 9 with shared LVM on iSCSI problem.You can create a non-production cluster with two nodes The example references a PVE cluster with 2+ nodes This ^ is not a step in the referenced document. Blockbridge : Ultra low latency all-NVME shared storage for Proxmox -...
