Take the 2-minute tour ×
Server Fault is a question and answer site for system and network administrators. It's 100% free, no registration required.

So we got a shiny new 48-port switch that supports Gigabit. Between two computers, with CAT5e cables I get 20-35 MB/s, which I guess could be improved even more with CAT6 cables. But for some reason, between a Hyper-V VM (also running W2008) and my computer, I only get 100 mbit/s speeds, even tho the Hyper-V host computer it is connected to the switch with a CAT6 cable and uses a Gigabit network card (and the VM uses the same). Any ideas why?

Edit: One thing that may be possible is that the traffic somehow gets routed thru our router which can only do 100 mbits. But why (would it)?

share|improve this question
2  
Category 5e cables will run gigabit Ethernet fine. You've got something other than a cabling problem wrong if you're seeing such performance. –  Evan Anderson Jul 22 '09 at 6:33

5 Answers 5

I get 26 MB/s (quick test) with my 1 Gb Network through Hyper-V.

Make sure in the settings for the guest that you are not using a 'Legacy Network Adapter'. That alone will kill performance. However, to use the 'Network Adapter' instead, you will need to install integration services in the guest (supported in Windows 2008, but you'll need to update the Windows 2008 RTM install with the later Hyper-V integration services).

share|improve this answer

There's appreciable CPU time required to emulate a network card into the VM; that, combined with the rather atrocious speed you're getting NIC to NIC, would account for the fairly dodgy performance you're seeing.

share|improve this answer

Cat5e cables should be capable of dealing with gigabit traffic, unless you have damaged or low quality cabling, so I doubt upgrading to Cat6 will help.

With regard to your host->host speed of 20-35MByte/s I suspect that you are seeing delay due to other factors. Is that "20-35" just an estimate, or does the rate vary that much during your tests? If it does genuinely vary that much then I would first suspect that contention for disk IO at one end of the transfer is the bottleneck (try running the test with no other VMS or other major processes running on either host). Also, how good is that new switch and how much other traffic is running through it? It could be that you have tens of machines merrily pushing as much data as they can and the backplane of the switch is not capable of transmitting data fast enough to serve every port with gbit speeds simultaneously.

With regard to the VMs transmitting data slower, the fact that the host machines can transfer data at the faster rate implies that the VM solution is introducing a limit or bottleneck. Again, when you say "100mbit speeds" do you mean the speed tops out at (but usually reaches) the speed you'd expect for a 100mbit NIC, or is the observed speed less than that, or does the speed very a lot (even with no other VMs competing for the bandwidth)? Does HyperV advertise itself as giving better-then-100mbit performance to virtual network adaptors (I've yet to use HyperV so can't offer you direct experience)? If it does then what spec are your host machines and what load do you see imposed on the host when transferring the data? It could be that you are seeing the natural performance hit of the virtualisation process exacerbated by older server kit.

share|improve this answer
    
"Again, when you say "100mbit speeds" do you mean the speed tops out at (but usually reaches) the speed you'd expect for a 100mbit NIC" Exactly. I use total commander for copying which shows the actual transfer rate. –  KTamas Jul 22 '09 at 7:31
    
I also tested it when there was pretty much no load on the switch. –  KTamas Jul 22 '09 at 8:01
1  
If it reliably tops out at 100mbit it could be that HyperV is explicitly trying to exactly emulate a 100Mbit NIC, if that is possible (again I've not used HyperV yet myself, VMWare is my main area of expertise in the VM world). What does the guest OS report the virtual netwrok card as? –  David Spillett Jul 22 '09 at 9:30

This is more than likely a misconfiguration of the virtual machine's networking. Are you using a physical nic for the guest or a virtual?

share|improve this answer

Are you measuring the speed of a file transfer? If so, what kind of disks are your VMs running on? Are you using dynamically expanding disks or snapshots on the VM? These both incur an I/O performance penalty. This may be disk I/O limited rather than network limited.

share|improve this answer

Your Answer

 
discard

By posting your answer, you agree to the privacy policy and terms of service.

Not the answer you're looking for? Browse other questions tagged or ask your own question.