Search results

Hi, We are currently experiencing issues with Broadcom cards. (Dell R440) 5e:00.0 Ethernet controller: Broadcom Limited BCM57416 NetXtreme-E 10GBase-T RDMA Ethernet Controller (rev 01) 5e:00.1 Ethernet controller: Broadcom Limited BCM57416 NetXtreme-E 10GBase-T RDMA Ethernet Controller (rev...

Hi, Seems that there are new updates on pve-enterprise repository. Do they solve the issue ? Thanks

Thanks for your answer. My question would be : is there a need to settle iothread while only one disk require IOPS ? Antoine

Hi, Same issue for me here root@tco-prox-03:~# systemctl status pvesr.service ● pvesr.service - Proxmox VE replication runner Loaded: loaded (/lib/systemd/system/pvesr.service; static; vendor preset: enabled) Active: failed (Result: exit-code) since Mon 2018-10-29 00:04:09 CET; 27s ago...

Hi, I just built a new KVM virtual machine, I first decided to put only one vdisk with few partitions (on a RAID10 ZFS pool with fast SSD), one partition for OS and the other for datas (SQL Server databases). I'm wondering if instead of using only one vdisk it could be better to use 2 vdisks...

Caution : idle=poll is not compatible with hyperthreading (slow down performance) https://software.intel.com/en-us/forums/software-tuning-performance-optimization-platform-monitoring/topic/535130

Ok so another question : I plan to add 2 vdisk (on zfs pool), one for OS and the other for datas. Adding more than one vdisk on a scsi virtio controller affects IOPS ? iothread could not be used due to backup issue... What are your recommendations ? Thanks.

Hi, I plan to build same kind of VM Win2012R2 with 32 Gigs of RAM VM Disk on RAID-10 ZFS (4 SSD) SQL Server 2016 Any tricks to give me ?

Ok thanks!

Hi! I recently upgraded a 3 nodes cluster, I was about to add a new ceph pool and I saw a new checkbox option related to hyperconverged ceph tool : What is it ? Thanks!

grub with only idle=poll is enough to put CPU at its maximum speed.

I don't monit power consumption sorry. Just noticed that I tried all possibles values : processor.max_cstate=0 intel_idle.max_cstate=0 idle=poll processor.max_cstate=1 intel_idle.max_cstate=1 idle=poll processor.max_cstate=0 intel_idle.max_cstate=1 idle=poll processor.max_cstate=1...

Works as expected !! Thank you so much :)

Thanks I will. I keep you guys in touch :)

Hi, Seems that settle 'intel_pstate=disable' in /etc/default/grub is not working anymore. However, intel_idle.max_cstate=0 processor.max_cstate=1 permit cpus to work at higher frequency but turbo still active. In order to avoid sync issues inside vms, I'd prefer want my cpus working at constant...

Hi, From proxmox documentation : Maybe settle multiqueue for Windows guest OS is not enough

Thanks, that makes sense. I will investigate on my netgear switch stack

Also what I noticed, mac_address used to send traffic to 232.43.211.234 correspond to bond1 but was send by bond0 ? ip link show 10: bond0: <BROADCAST,MULTICAST,MASTER,UP,LOWER_UP> mtu 1500 qdisc noqueue master vmbr0 state UP mode DEFAULT group default qlen 1000 link/ether d0:94:66:5a:3f:1a...

Just took a trace of bond0 with tcpdump when running omping. Graph indicates that there's a lot of incoming traffic but in pcap I found lots of outgoing packets from 10.198.0.0/24 to multicast address

Here is my conf and routes. vmbr0 on bond0 (LACP layer 3+4) - 10.192.5.32/27 bond1 (LACP layer 3+4) - 10.198.0.0/24 root@dc-prox-09:~# route Kernel IP routing table Destination Gateway Genmask Flags Metric Ref Use Iface default 10.192.5.33 0.0.0.0...