Proxmox 5 and unusual Disk I/O

2g.Storm

New Member
Oct 26, 2020
1
0
1
42
Hi everyone i have recently (August 2020) installed proxmox 5 on a Dell R710 configured as follows:
  • CPU: Dual Xeon X5670 @2.93GHz (24 cores in total with HT enabled)
  • RAM: 72G
  • Storage: 6x crucial BX500 SSD configured with ZFS raidz1 (configured during the installation)
  • RAID controller LSI 2008 in IT mode
here's the detailed package version i am on:
Code:
proxmox-ve: 5.4-2 (running kernel: 4.15.18-30-pve)
pve-manager: 5.4-15 (running version: 5.4-15/d0ec33c6)
pve-kernel-4.15: 5.4-19
pve-kernel-4.15.18-30-pve: 4.15.18-58
pve-kernel-4.15.18-12-pve: 4.15.18-36
corosync: 2.4.4-pve1
criu: 2.11.1-1~bpo90
glusterfs-client: 3.8.8-1
ksm-control-daemon: 1.2-2
libjs-extjs: 6.0.1-2
libpve-access-control: 5.1-12
libpve-apiclient-perl: 2.0-5
libpve-common-perl: 5.0-56
libpve-guest-common-perl: 2.0-20
libpve-http-server-perl: 2.0-14
libpve-storage-perl: 5.0-44
libqb0: 1.0.3-1~bpo9
lvm2: 2.02.168-pve6
lxc-pve: 3.1.0-7
lxcfs: 3.0.3-pve1
novnc-pve: 1.0.0-3
proxmox-widget-toolkit: 1.0-28
pve-cluster: 5.0-38
pve-container: 2.0-42
pve-docs: 5.4-2
pve-edk2-firmware: 1.20190312-1
pve-firewall: 3.0-22
pve-firmware: 2.0-7
pve-ha-manager: 2.0-9
pve-i18n: 1.1-4
pve-libspice-server1: 0.14.1-2
pve-qemu-kvm: 3.0.1-4
pve-xtermjs: 3.12.0-1
qemu-server: 5.0-56
smartmontools: 6.5+svn4324-1
spiceterm: 3.0-5
vncterm: 1.5-3
zfsutils-linux: 0.7.13-pve1~bpo2

This machine is running 2 Windows 2k19 VM servers one of which acts as a DC and the other one is the application server as i am using terminal server gateway to make applications available to users (Office Suite, Adobe Applications suite and few more)

The DC is configured as follows:
  • 2 Sockets 4 cores each
  • 12 Gigabytes of ram
  • 1HDD 250G, SSD emulation enabled (Discard disabled both in Proxmox and in the guest OS), for the system. SCSI
  • 1HDD 40G SSD same as the aforementioned one, this one is used for a local DB backup (scheduled at 9PM). SCSI
  • This machine runs AD services and a local CRM with a MsSQL DB
The Terminal server gateway machine instead:
  • 2 sockets 5 cores each
  • 24G Ram
  • 1HDD 350G for the system and the applications (MS Office, Adobe suite)
  • This machine runs the terminal services. The user connects to a website and then they access the applications directly from there
The problem is that the windows VM at about 8am and at about 2pm they clog my SSD pool with high CPU and high disks I/O both operations last for about 30 minutes.
I thought it was the trimming command causing an excess of IO and i tried to disable that on both O/S by running :
Code:
fsutil behavior set DisableDeleteNotify 1

I disabled the discard option on the disks configurations too... that only caused an extreme sinking in the machines performances and the users were unable to use them, restoring the functionality solved the performances sink entirely. I left the functionality disabled on the Proxmox VM disks config (no more discard). I have disabled the C: drives optimizations so that no more defrag operations will be performed by the Windows guests but i am running out of possible solutions. Has anybody got some other hints to give me?

For any clarifications please do not hesitate to ask me

Thank you in advance
 

About

The Proxmox community has been around for many years and offers help and support for Proxmox VE, Proxmox Backup Server, and Proxmox Mail Gateway.
We think our community is one of the best thanks to people like you!

Get your subscription!

The Proxmox team works very hard to make sure you are running the best software and getting stable updates and security enhancements, as well as quick enterprise support. Tens of thousands of happy customers have a Proxmox subscription. Get yours easily in our online shop.

Buy now!