Re: Re: Still struggling with HVM: tx timeouts on emulated nics

[Stefano Stabellini <stefano.stabellini@eu.citrix.com>]

On Wed, 21 Sep 2011, Stefan Bader wrote:
> On 21.09.2011 15:31, Stefano Stabellini wrote:
> > On Wed, 21 Sep 2011, Stefan Bader wrote:
> >> This is on 3.0.4 based dom0 and domU with 4.1.1 hypervisor. I tried using the
> >> default 8139cp and ne2k_pci emulated nic. The 8139cp one at least comes up and
> >> gets configured via dhcp. And initial pings also get routed and done correctly.
> >> But slightly higher traffic (like checking for updates) hangs. And after a while
> >> there are messages about tx timeouts.
> >> The ne2k_pci type nic almost immediately has those issues and never comes up
> >> correctly.
> >>
> >> I am attaching the dmesg of the guest with apic=debug enabled. I am not sure how
> >> this should be but both nics get configured with level,low IRQs. Disk emulation
> >> seems to be ok but that seem to use IO-APIC-edge. And any other IRQs seem to be
> >> at least not level.
> > 
> 
> > Does the e1000 emulated card work correctly?
> 
> Yes, that one seems to work ok.
> 
> > What happens if you disable interrupt remapping (see patch below)?
> 
> 8139cp seems to work correctly now (much higher irq stats as well) and e1000
> still works. Both then using IOAPIC-fasteoi.
> 

That means there must be another subtle bug in Xen in interrupt
remapping that only affects 8139p emulation


> >> Another problem came up recently though that may just be me doing the wrong
> >> thing. Normally I boot with xen_emul_unplug=unnecessary as I want the emulated
> >> devices. xen-blkfront is a module in my case and I thought I once had been able
> >> to use that by removing the unplug arg and making the blkfront driver load. But
> >> when I recently tried the module loaded but no disks appeared... Again, not sure
> >> I just forgot how to do that right or that was different when using a 4.1.0
> >> hypervisor still...
> >  
> > xen_emul_unplug=unnecessary allows the kernel to use PV interfaces on
> > older hypervisors that didn't support the unplug protocol and had other
> > ways to cope with multiple drivers accessing the same devices.
> > You can use xen_emul_unplug=never to prevent any unplug but you won't
> > get any PV interfaces.
> 
> Hm, odd. Somehow I thought that I had been using pv interfaces that way when the
> interrupts for the emulated ide was broken.
> A bit suboptimal atm, because without any option and a kernel compiled with the
> platform pci and pv drivers (as modules) booting in HVM mode the kernel decides
> that having both is no use and unplugs the emulated devices. Which then leaves
> you with ... none.

In theory you would have the PV frontend modules in the initrd.
On the other hand having both can easily cause data corruptions on your
drive.