[SOLVED] 2 same GPUs, different IMMOU groups, passthrough problem

U

ukro

Member
May 16, 2021
122
13
23
38
Greetings,
I have 2 GPUs with same vendor ID but different memory and brand.
I can't make them both work on 2VMs(win10,linux). Its always that it is working only when one VM is off and one is on. Otherwise Windows 10 and Linux both see each gpu correctly.

Error when turning on second VM(linux):
Code: 
TASK ERROR: start failed: command '/usr/bin/kvm -id 104 -name 'vulcan,debug-threads=on' -no-shutdown -chardev 'socket,id=qmp,path=/var/run/qemu-server/104.qmp,server=on,wait=off' -mon 'chardev=qmp,mode=control' -chardev 'socket,id=qmp-event,path=/var/run/qmeventd.sock,reconnect=5' -mon 'chardev=qmp-event,mode=control' -pidfile /var/run/qemu-server/104.pid -daemonize -smbios 'type=1,uuid=dff6acff-84da-4212-9bb5-79fd38a1a9f9' -drive 'if=pflash,unit=0,format=raw,readonly=on,file=/usr/share/pve-edk2-firmware//OVMF_CODE.fd' -drive 'if=pflash,unit=1,format=raw,id=drive-efidisk0,size=131072,file=/dev/zvol/vms/vm-104-disk-0' -global 'ICH9-LPC.acpi-pci-hotplug-with-bridge-support=off' -smp '4,sockets=1,cores=4,maxcpus=4' -nodefaults -boot 'menu=on,strict=on,reboot-timeout=1000,splash=/usr/share/qemu-server/bootsplash.jpg' -vnc 'unix:/var/run/qemu-server/104.vnc,password=on' -cpu kvm64,enforce,+kvm_pv_eoi,+kvm_pv_unhalt,+lahf_lm,+sep -m 8192 -readconfig /usr/share/qemu-server/pve-q35-4.0.cfg -device 'vmgenid,guid=f0f7a2bf-f245-4bbd-b0b3-8aedba67adb1' -device 'usb-tablet,id=tablet,bus=ehci.0,port=1' -device 'vfio-pci,host=0000:06:00.0,id=hostpci0.0,bus=ich9-pcie-port-1,addr=0x0.0,multifunction=on,romfile=/usr/share/kvm/gt710ddr5new.rom' -device 'vfio-pci,host=0000:06:00.1,id=hostpci0.1,bus=ich9-pcie-port-1,addr=0x0.1' -device 'VGA,id=vga,bus=pcie.0,addr=0x1' -device 'virtio-balloon-pci,id=balloon0,bus=pci.0,addr=0x3,free-page-reporting=on' -iscsi 'initiator-name=iqn.1993-08.org.debian:01:b61aadf3b61e' -device 'virtio-scsi-pci,id=scsihw0,bus=pci.0,addr=0x5' -drive 'file=/dev/zvol/vms/vm-104-disk-1,if=none,id=drive-scsi0,format=raw,cache=none,aio=io_uring,detect-zeroes=on' -device 'scsi-hd,bus=scsihw0.0,channel=0,scsi-id=0,lun=0,drive=drive-scsi0,id=scsi0,rotation_rate=1,bootindex=100' -device 'ahci,id=ahci0,multifunction=on,bus=pci.0,addr=0x7' -drive 'if=none,id=drive-sata0,media=cdrom,aio=io_uring' -device 'ide-cd,bus=ahci0.0,drive=drive-sata0,id=sata0,bootindex=102' -netdev 'type=tap,id=net0,ifname=tap104i0,script=/var/lib/qemu-server/pve-bridge,downscript=/var/lib/qemu-server/pve-bridgedown,vhost=on' -device 'virtio-net-pci,mac=2A:7F:3D:A3:53:B8,netdev=net0,bus=pci.0,addr=0x12,id=net0,rx_queue_size=1024,tx_queue_size=1024,bootindex=101' -netdev 'type=tap,id=net1,ifname=tap104i1,script=/var/lib/qemu-server/pve-bridge,downscript=/var/lib/qemu-server/pve-bridgedown,vhost=on' -device 'virtio-net-pci,mac=92:60:1E:A2:B3:EB,netdev=net1,bus=pci.0,addr=0x13,id=net1,rx_queue_size=1024,tx_queue_size=1024' -machine 'type=q35+pve0'' failed: got timeout

Code: 
IOMMU Group 57 03:00.0 VGA compatible controller [0300]: NVIDIA Corporation GK208B [GeForce GT 710] [10de:128b] (rev a1)
IOMMU Group 58 03:00.1 Audio device [0403]: NVIDIA Corporation GK208 HDMI/DP Audio Controller [10de:0e0f] (rev a1)
IOMMU Group 59 06:00.0 VGA compatible controller [0300]: NVIDIA Corporation GK208B [GeForce GT 710] [10de:128b] (rev a1)
IOMMU Group 60 06:00.1 Audio device [0403]: NVIDIA Corporation GK208 HDMI/DP Audio Controller [10de:0e0f] (rev a1)

Code: 
06:00.0 VGA compatible controller: NVIDIA Corporation GK208B [GeForce GT 710] (rev a1) (prog-if 00 [VGA controller])
        Subsystem: ASUSTeK Computer Inc. GT710-SL-1GD5
        Physical Slot: 2
        Flags: bus master, fast devsel, latency 0, IRQ 87, NUMA node 0, IOMMU group 59
        Memory at 93000000 (32-bit, non-prefetchable) [size=16M]
        Memory at 39ff0000000 (64-bit, prefetchable) [size=128M]
        Memory at 39ff8000000 (64-bit, prefetchable) [size=32M]
        I/O ports at 2000 [size=128]
        Expansion ROM at 94080000 [disabled] [size=512K]
        Capabilities: [60] Power Management version 3
        Capabilities: [68] MSI: Enable+ Count=1/1 Maskable- 64bit+
        Capabilities: [78] Express Legacy Endpoint, MSI 00
        Capabilities: [100] Virtual Channel
        Capabilities: [128] Power Budgeting <?>
        Capabilities: [600] Vendor Specific Information: ID=0001 Rev=1 Len=024 <?>
        Kernel driver in use: vfio-pci
        Kernel modules: nvidiafb, nouveau
       
        03:00.0 VGA compatible controller: NVIDIA Corporation GK208B [GeForce GT 710] (rev a1) (prog-if 00 [VGA controller])
        Subsystem: Micro-Star International Co., Ltd. [MSI] GK208B [GeForce GT 710]
        Physical Slot: 1
        Flags: fast devsel, IRQ 16, NUMA node 0, IOMMU group 57
        Memory at 95000000 (32-bit, non-prefetchable) [size=16M]
        Memory at 39fe0000000 (64-bit, prefetchable) [size=128M]
        Memory at 39fe8000000 (64-bit, prefetchable) [size=32M]
        I/O ports at 3000 [size=128]
        Expansion ROM at 96080000 [virtual] [disabled] [size=512K]
        Capabilities: [60] Power Management version 3
        Capabilities: [68] MSI: Enable- Count=1/1 Maskable- 64bit+
        Capabilities: [78] Express Legacy Endpoint, MSI 00
        Capabilities: [100] Virtual Channel
        Capabilities: [128] Power Budgeting <?>
        Capabilities: [600] Vendor Specific Information: ID=0001 Rev=1 Len=024 <?>
        Kernel driver in use: vfio-pci
        Kernel modules: nvidiafb, nouveau

Win conf:
Code: 
args: -cpu 'host,+kvm_pv_unhalt,+kvm_pv_eoi,hv_vendor_id=NV43FIX,kvm=off' -machine 'max-ram-below-4g=1G,kernel_irqchip=on'
balloon: 0
bios: ovmf
boot: order=virtio0;ide2;sata0
cores: 4
cpu: host,hidden=1,flags=+pcid
efidisk0: vms:vm-102-disk-0,efitype=4m,pre-enrolled-keys=1,size=1M
hostpci0: 0000:03:00,pcie=1,romfile=gt7101gnew.bin
machine: pc-q35-6.2
memory: 8192
meta: creation-qemu=7.1.0,ctime=1673976195
name: win10
net0: virtio=3E:A9:68:F3:78:28,bridge=vmbr0,firewall=1
net1: virtio=EE:6A:4C:D3:19:AE,bridge=vmbr2,firewall=1
numa: 0
ostype: win10
sata0: none,media=cdrom
scsihw: virtio-scsi-single
smbios1: uuid=079631b6-1c98-4e2d-ae5a-287a0845cfd3
sockets: 1
virtio0: vms:vm-102-disk-1,size=70G
vmgenid: 162955d9-f3fd-47c6-b8fd-c278dd96040d

Linux conf:
Code: 
args: -cpu 'host,+kvm_pv_unhalt,+kvm_pv_eoi,hv_vendor_id=NV43FIX,kvm=off' -machine 'max-ram-below-4g=1G,kernel_irqchip=on'
bios: ovmf
boot: order=scsi0;net0;sata0
cores: 4
efidisk0: vms:vm-104-disk-0,size=1M
hostpci0: 0000:06:00,pcie=1,romfile=gt710ddr5new.rom
machine: q35
memory: 8192
name: vulcan
net0: virtio=2A:7F:3D:A3:53:B8,bridge=vmbr0
net1: virtio=92:60:1E:A2:B3:EB,bridge=vmbr2
numa: 0
ostype: l26
sata0: none,media=cdrom
scsi0: vms:vm-104-disk-1,size=32G,ssd=1
scsihw: virtio-scsi-pci
smbios1: uuid=dff6acff-84da-4212-9bb5-79fd38a1a9f9
sockets: 1
vmgenid: f0f7a2bf-f245-4bbd-b0b3-8aedba67adb1
 
ukro said:
I have 2 GPUs with same vendor ID but different memory and brand.
Click to expand...
Since you want to passthrough both, it is not a problem that the numeric IDs used for early binding to vfio-pci are identical.
ukro said:
Error when turning on second VM(linux):
Code: 
TASK ERROR: start failed: command '/usr/bin/kvm -id 104 -name 'vulcan,debug-threads=on' -no-shutdown -chardev 'socket,id=qmp,path=/var/run/qemu-server/104.qmp,server=on,wait=off' -mon 'chardev=qmp,mode=control' -chardev 'socket,id=qmp-event,path=/var/run/qmeventd.sock,reconnect=5' -mon 'chardev=qmp-event,mode=control' -pidfile /var/run/qemu-server/104.pid -daemonize -smbios 'type=1,uuid=dff6acff-84da-4212-9bb5-79fd38a1a9f9' -drive 'if=pflash,unit=0,format=raw,readonly=on,file=/usr/share/pve-edk2-firmware//OVMF_CODE.fd' -drive 'if=pflash,unit=1,format=raw,id=drive-efidisk0,size=131072,file=/dev/zvol/vms/vm-104-disk-0' -global 'ICH9-LPC.acpi-pci-hotplug-with-bridge-support=off' -smp '4,sockets=1,cores=4,maxcpus=4' -nodefaults -boot 'menu=on,strict=on,reboot-timeout=1000,splash=/usr/share/qemu-server/bootsplash.jpg' -vnc 'unix:/var/run/qemu-server/104.vnc,password=on' -cpu kvm64,enforce,+kvm_pv_eoi,+kvm_pv_unhalt,+lahf_lm,+sep -m 8192 -readconfig /usr/share/qemu-server/pve-q35-4.0.cfg -device 'vmgenid,guid=f0f7a2bf-f245-4bbd-b0b3-8aedba67adb1' -device 'usb-tablet,id=tablet,bus=ehci.0,port=1' -device 'vfio-pci,host=0000:06:00.0,id=hostpci0.0,bus=ich9-pcie-port-1,addr=0x0.0,multifunction=on,romfile=/usr/share/kvm/gt710ddr5new.rom' -device 'vfio-pci,host=0000:06:00.1,id=hostpci0.1,bus=ich9-pcie-port-1,addr=0x0.1' -device 'VGA,id=vga,bus=pcie.0,addr=0x1' -device 'virtio-balloon-pci,id=balloon0,bus=pci.0,addr=0x3,free-page-reporting=on' -iscsi 'initiator-name=iqn.1993-08.org.debian:01:b61aadf3b61e' -device 'virtio-scsi-pci,id=scsihw0,bus=pci.0,addr=0x5' -drive 'file=/dev/zvol/vms/vm-104-disk-1,if=none,id=drive-scsi0,format=raw,cache=none,aio=io_uring,detect-zeroes=on' -device 'scsi-hd,bus=scsihw0.0,channel=0,scsi-id=0,lun=0,drive=drive-scsi0,id=scsi0,rotation_rate=1,bootindex=100' -device 'ahci,id=ahci0,multifunction=on,bus=pci.0,addr=0x7' -drive 'if=none,id=drive-sata0,media=cdrom,aio=io_uring' -device 'ide-cd,bus=ahci0.0,drive=drive-sata0,id=sata0,bootindex=102' -netdev 'type=tap,id=net0,ifname=tap104i0,script=/var/lib/qemu-server/pve-bridge,downscript=/var/lib/qemu-server/pve-bridgedown,vhost=on' -device 'virtio-net-pci,mac=2A:7F:3D:A3:53:B8,netdev=net0,bus=pci.0,addr=0x12,id=net0,rx_queue_size=1024,tx_queue_size=1024,bootindex=101' -netdev 'type=tap,id=net1,ifname=tap104i1,script=/var/lib/qemu-server/pve-bridge,downscript=/var/lib/qemu-server/pve-bridgedown,vhost=on' -device 'virtio-net-pci,mac=92:60:1E:A2:B3:EB,netdev=net1,bus=pci.0,addr=0x13,id=net1,rx_queue_size=1024,tx_queue_size=1024' -machine 'type=q35+pve0'' failed: got timeout
Click to expand...
If there are no errors to be found in journalctl, then the timeout is usually because of not enough continuous free memory. With passthrough all of the VM memory must be pinned into actual host memory. Try starting both VMs with half the memory. And use journalctl -e and scoll up to find any errors related to starting the VM.
ukro said:
Code: 
IOMMU Group 57 03:00.0 VGA compatible controller [0300]: NVIDIA Corporation GK208B [GeForce GT 710] [10de:128b] (rev a1)
IOMMU Group 58 03:00.1 Audio device [0403]: NVIDIA Corporation GK208 HDMI/DP Audio Controller [10de:0e0f] (rev a1)
IOMMU Group 59 06:00.0 VGA compatible controller [0300]: NVIDIA Corporation GK208B [GeForce GT 710] [10de:128b] (rev a1)
IOMMU Group 60 06:00.1 Audio device [0403]: NVIDIA Corporation GK208 HDMI/DP Audio Controller [10de:0e0f] (rev a1)
Click to expand...
Both functions of each device in a separate group is strange. What is the output of cat /proc/cmdline? Please remove any use of pcie_acs_override and check the real IOMMU groups again.

It sometimes helps to known what motherboard (make and model) you are using since it determines the IOMMU groups and how much memory it has install.
 
  • Like
Reactions: ukro
Thank you for reply!
You were right, lowering the linux VM from 8 to 4GB, everything is working ^^ that is strange, because i have 64GB RAM installed and all the VMs are using only +-24GB
HP ML110 Gen9
cmdline:
Code: 
BOOT_IMAGE=/boot/vmlinuz-5.15.83-1-pve root=/dev/mapper/pve-root ro quiet intel_iommu=on iommu=pt vfio_iommu_type1.allow_unsafe_interrupts=1 pcie_acs_override=downstream,multifunction initcall_blacklist=sysfb_init

I think i will keep this settings as its fine for now, if i were in need to increase the RAM will tinker with it further.
Much Thanks !!!!!!!!!!!!!!!!! <3
 
If i put 8GB back again i have this errors:
Code: 
Feb 12 09:33:11 node pvestatd[4209]: VM 104 qmp command failed - VM 104 qmp command 'query-proxmox-support' failed - unable to connect to VM 104 qmp socket - timeout after 51 retries
Feb 12 09:33:12 node pvedaemon[3052572]: VM 104 qmp command failed - VM 104 qmp command 'query-proxmox-support' failed - unable to connect to VM 104 qmp socket - timeout after 51 retries
Feb 12 09:33:12 node pvestatd[4209]: status update time (9.216 seconds)
 
Code: 
Feb 12 09:33:33 node pvestatd[4209]: status update time (9.251 seconds)
Feb 12 09:33:33 node pvedaemon[3292225]: start failed: command '/usr/bin/kvm -id 104 -name 'vulcan,debug-threads=on' -no-shutdown -chardev 'socket,id=qmp,path=/var/run/qemu-server/104.qmp,server=on,wait=off' -mon 'chardev=qmp,mode=control' -chardev 'socket,id=qmp-event,path=/var/run/qmeventd.sock,reconnect=5' -mon 'chardev=qmp-event,mode=control' -pidfile /var/run/qemu-server/104.pid -daemonize -smbios 'type=1,uuid=dff6acff-84da-4212-9bb5-79fd38a1a9f9' -drive 'if=pflash,unit=0,format=raw,readonly=on,file=/usr/share/pve-edk2-firmware//OVMF_CODE.fd' -drive 'if=pflash,unit=1,format=raw,id=drive-efidisk0,size=131072,file=/dev/zvol/vms/vm-104-disk-0' -global 'ICH9-LPC.acpi-pci-hotplug-with-bridge-support=off' -smp '4,sockets=1,cores=4,maxcpus=4' -nodefaults -boot 'menu=on,strict=on,reboot-timeout=1000,splash=/usr/share/qemu-server/bootsplash.jpg' -vnc 'unix:/var/run/qemu-server/104.vnc,password=on' -cpu kvm64,enforce,+kvm_pv_eoi,+kvm_pv_unhalt,+lahf_lm,+sep -m 8192 -readconfig /usr/share/qemu-server/pve-q35-4.0.cfg -device 'vmgenid,guid=f0f7a2bf-f245-4bbd-b0b3-8aedba67adb1' -device 'usb-tablet,id=tablet,bus=ehci.0,port=1' -device 'vfio-pci,host=0000:06:00.0,id=hostpci0.0,bus=ich9-pcie-port-1,addr=0x0.0,multifunction=on' -device 'vfio-pci,host=0000:06:00.1,id=hostpci0.1,bus=ich9-pcie-port-1,addr=0x0.1' -device 'VGA,id=vga,bus=pcie.0,addr=0x1' -iscsi 'initiator-name=iqn.1993-08.org.debian:01:b61aadf3b61e' -device 'virtio-scsi-pci,id=scsihw0,bus=pci.0,addr=0x5' -drive 'file=/dev/zvol/vms/vm-104-disk-1,if=none,id=drive-scsi0,format=raw,cache=none,aio=io_uring,detect-zeroes=on' -device 'scsi-hd,bus=scsihw0.0,channel=0,scsi-id=0,lun=0,drive=drive-scsi0,id=scsi0,rotation_rate=1,bootindex=100' -device 'ahci,id=ahci0,multifunction=on,bus=pci.0,addr=0x7' -drive 'if=none,id=drive-sata0,media=cdrom,aio=io_uring' -device 'ide-cd,bus=ahci0.0,drive=drive-sata0,id=sata0,bootindex=102' -netdev 'type=tap,id=net0,ifname=tap104i0,script=/var/lib/qemu-server/pve-bridge,downscript=/var/lib/qemu-server/pve-bridgedown,vhost=on' -device 'virtio-net-pci,mac=2A:7F:3D:A3:53:B8,netdev=net0,bus=pci.0,addr=0x12,id=net0,rx_queue_size=1024,tx_queue_size=1024,bootindex=101' -netdev 'type=tap,id=net1,ifname=tap104i1,script=/var/lib/qemu-server/pve-bridge,downscript=/var/lib/qemu-server/pve-bridgedown,vhost=on' -device 'virtio-net-pci,mac=92:60:1E:A2:B3:EB,netdev=net1,bus=pci.0,addr=0x13,id=net1,rx_queue_size=1024,tx_queue_size=1024' -machine 'type=q35+pve0' -cpu 'host,+kvm_pv_unhalt,+kvm_pv_eoi,hv_vendor_id=NV43FIX,kvm=off' -machine 'max-ram-below-4g=1G,kernel_irqchip=on'' failed: got timeout
Feb 12 09:33:33 node pvedaemon[2460013]: <root@pam> end task UPID:node:00323C41:01E0AAD7:63E8A43F:qmstart:104:root@pam: start failed: command '/usr/bin/kvm -id 104 -name 'vulcan,debug-threads=on' -no-shutdown -chardev 'socket,id=qmp,path=/var/run/qemu-server/104.qmp,server=on,wait=off' -mon 'chardev=qmp,mode=control' -chardev 'socket,id=qmp-event,path=/var/run/qmeventd.sock,reconnect=5' -mon 'chardev=qmp-event,mode=control' -pidfile /var/run/qemu-server/104.pid -daemonize -smbios 'type=1,uuid=dff6acff-84da-4212-9bb5-79fd38a1a9f9' -drive 'if=pflash,unit=0,format=raw,readonly=on,file=/usr/share/pve-edk2-firmware//OVMF_CODE.fd' -drive 'if=pflash,unit=1,format=raw,id=drive-efidisk0,size=131072,file=/dev/zvol/vms/vm-104-disk-0' -global 'ICH9-LPC.acpi-pci-hotplug-with-bridge-support=off' -smp '4,sockets=1,cores=4,maxcpus=4' -nodefaults -boot 'menu=on,strict=on,reboot-timeout=1000,splash=/usr/share/qemu-server/bootsplash.jpg' -vnc 'unix:/var/run/qemu-server/104.vnc,password=on' -cpu kvm64,enforce,+kvm_pv_eoi,+kvm_pv_unhalt,+lahf_lm,+sep -m 8192 -readconfig /usr/share/qemu-server/pve-q35-4.0.cfg -device 'vmgenid,guid=f0f7a2bf-f245-4bbd-b0b3-8aedba67adb1' -device 'usb-tablet,id=tablet,bus=ehci.0,port=1' -device 'vfio-pci,host=0000:06:00.0,id=hostpci0.0,bus=ich9-pcie-port-1,addr=0x0.0,multifunction=on' -device 'vfio-pci,host=0000:06:00.1,id=hostpci0.1,bus=ich9-pcie-port-1,addr=0x0.1' -device 'VGA,id=vga,bus=pcie.0,addr=0x1' -iscsi 'initiator-name=iqn.1993-08.org.debian:01:b61aadf3b61e' -device 'virtio-scsi-pci,id=scsihw0,bus=pci.0,addr=0x5' -drive 'file=/dev/zvol/vms/vm-104-disk-1,if=none,id=drive-scsi0,format=raw,cache=none,aio=io_uring,detect-zeroes=on' -device 'scsi-hd,bus=scsihw0.0,channel=0,scsi-id=0,lun=0,drive=drive-scsi0,id=scsi0,rotation_rate=1,bootindex=100' -device 'ahci,id=ahci0,multifunction=on,bus=pci.0,addr=0x7' -drive 'if=none,id=drive-sata0,media=cdrom,aio=io_uring' -device 'ide-cd,bus=ahci0.0,drive=drive-sata0,id=sata0,bootindex=102' -netdev 'type=tap,id=net0,ifname=tap104i0,script=/var/lib/qemu-server/pve-bridge,downscript=/var/lib/qemu-server/pve-bridgedown,vhost=on' -device 'virtio-net-pci,mac=2A:7F:3D:A3:53:B8,netdev=net0,bus=pci.0,addr=0x12,id=net0,rx_queue_size=1024,tx_queue_size=1024,bootindex=101' -netdev 'type=tap,id=net1,ifname=tap104i1,script=/var/lib/qemu-server/pve-bridge,downscript=/var/lib/qemu-server/pve-bridgedown,vhost=on' -device 'virtio-net-pci,mac=92:60:1E:A2:B3:EB,netdev=net1,bus=pci.0,addr=0x13,id=net1,rx_queue_size=1024,tx_queue_size=1024' -machine 'type=q35+pve0' -cpu 'host,+kvm_pv_unhalt,+kvm_pv_eoi,hv_vendor_id=NV43FIX,kvm=off' -machine 'max-ram-below-4g=1G,kernel_irqchip=on'' failed: got timeout
Feb 12 09:33:37 node pvedaemon[734423]: VM 104 qmp command failed - VM 104 qmp command 'query-proxmox-support' failed - unable to connect to VM 104 qmp socket - timeout after 51 retries
Feb 12 09:33:41 node pvestatd[4209]: VM 104 qmp command failed - VM 104 qmp command 'query-proxmox-support' failed - unable to connect to VM 104 qmp socket - timeout after 51 retries
Feb 12 09:33:42 node pvestatd[4209]: status update time (9.276 seconds)
 
I don't see any actual errors, except the VM start timeout and additional timeouts because the VM is taking too long to start. Looks like there is not enough free host memory suitable for pinning the VM memory. By the way, do you really need all of this for your VMs args: -cpu 'host,+kvm_pv_unhalt,+kvm_pv_eoi,hv_vendor_id=NV43FIX,kvm=off' -machine 'max-ram-below-4g=1G,kernel_irqchip=on'?
 
  • Like
Reactions: ukro
leesteken said:
I don't see any actual errors, except the VM start timeout and additional timeouts because the VM is taking too long to start. Looks like there is not enough free host memory suitable for pinning the VM memory. By the way, do you really need all of this for your VMs args: -cpu 'host,+kvm_pv_unhalt,+kvm_pv_eoi,hv_vendor_id=NV43FIX,kvm=off' -machine 'max-ram-below-4g=1G,kernel_irqchip=on'?
Click to expand...
xD for windows yes, for linux no :D
As i had problem with passing through GPU to Win10VM. For linux i was just checking why it was not working :D
Maybe ZFS caching have higher priority than VM memory?
 
ukro said:
Maybe ZFS caching have higher priority than VM memory?
Click to expand...
ZFS takes up to 50% of the host memory by default. The manual explains how to limit it. It should release memory (down to the set minumim) but this appear to happen very slowly (if at all).
Note that ballooning does not work for VMs with passthrough and also only kicks in at 80% of host memory (or memory+swap?) used. KSM (for non-passthrough VMs) also only starts at 80% but this can be changed.
Maybe all these systems are responding too late and too slowly for the sudden single large allocation of memory for the VM.
 
  • Like
Reactions: ukro
You must log in or register to reply here.

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!

Quick Navigation

Home Get Subscription Wiki Downloads Proxmox Customer Portal About

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!
Community platform by XenForo® © 2010-2024 XenForo Ltd.
Top Bottom
Back