<div dir="ltr">On Wed, Dec 10, 2014 at 2:10 PM, <span dir="ltr"><<a href="mailto:nans_nans1@yahoo.de" target="_blank">nans_nans1@yahoo.de</a>></span> wrote:<br><div class="gmail_extra"><div class="gmail_quote"><blockquote class="gmail_quote" style="margin:0px 0px 0px 0.8ex;border-left:1px solid rgb(204,204,204);padding-left:1ex">In Proxmox the storage is configured as "virtio0".<br>
<br>
I attached a part of dmesg:<br>
<br>
atapci0: <Intel PIIX3 WDMA2 controller> port 0xc0a0-0xc0af,0x376,0x170-0x177,0x3f6,0x1f0-0x1f7 at device 1.1 on pci0<br>
ata0: <ATA channel 0> on atapci0<br>
ata1: <ATA channel 1> on atapci0<br>
disk scheduler: set policy of acd0 to noop<br>
acd0: DVDROM <QEMU DVD-ROM/2.1.2> at ata1-master WDMA2<br>
uhci0: <Intel 82371SB (PIIX3) USB controller> port 0xc040-0xc05f irq 11 at device 1.2 on pci0<br>
usbus0: controller did not stop<br>
usbus0: <Intel 82371SB (PIIX3) USB controller> on uhci0<br>
pci0: <bridge> (vendor 0x8086, dev 0x7113) at device 1.3 irq 9<br>
vgapci0: <VGA-compatible display> mem 0xfebf0000-0xfebf0fff,0xfc000000-0xfdffffff at device 2.0 on pci0<br>
vgapci0: Boot video device<br>
virtio_pci0: <VirtIO PCI Balloon adapter> port 0xc060-0xc07f irq 11 at device 3.0 on pci0<br>
virtio_pci1: <VirtIO PCI Block adapter> port 0xc000-0xc03f mem 0xfebf1000-0xfebf1fff irq 10 at device 10.0 on pci0<br>
vtblk0: <VirtIO Block Adapter> on virtio_pci1<br>
virtio_pci1: host features: 0x71000ed4 <EventIdx,0x10000000,NotifyOnEmpty,0x800,Topology,FlushCmd,SCSICmds,BlockSize,DiskGeometry,MaxNumSegs><br>
virtio_pci1: negotiated features: 0x254 <FlushCmd,BlockSize,DiskGeometry,MaxNumSegs><br>
disk scheduler: set policy of vbd0 to noop<br></blockquote><div><br></div><div>DragonFly BSD's virtio-pci driver does not (at least 'did not') support indirect ring entries; qemu/kvm default to a 128-entry queue for each virtio-blk device; Dfly systems were regularly bandwidth limited by filling that queue; (at 64 KiB I/Os and fragmented physmem, you can only have 12-16 inflight IOs per disk).<br><br></div><div>DFly also appears to not be using MSI-X for the virtio-blk device; fixing that should result in modest but real per-I/O improvements<br></div><div><br>Bug: <a href="http://bugs.dragonflybsd.org/issues/2577">http://bugs.dragonflybsd.org/issues/2577</a> is related.<br></div><div><br></div><div>HTH,<br></div><div></div><div>-- vs; <br></div></div><br></div></div>