Re: [Xen-devel] pci-passthrough in pvops causing offline raid

From: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
To: Mark Adams <mark@campbell-lange.net>
Cc: xen-devel@lists.xensource.com, xen-users@lists.xensource.com
Subject: Re: [Xen-devel] pci-passthrough in pvops causing offline raid
Date: Thu, 11 Nov 2010 11:53:40 -0500	[thread overview]
Message-ID: <20101111165340.GB30006@dumpdata.com> (raw)
In-Reply-To: <20101111102416.GA32457@campbell-lange.net>

On Thu, Nov 11, 2010 at 10:24:17AM +0000, Mark Adams wrote:
> Hi All,
> 
> Running xen 4.0.1-rc6, debian squeeze 2.6.32-21.
> 
> In a voip setup, where I have forwarded the onboard NIC interfaces
> through to domU using the following grub config:
> 
> module  /vmlinuz-2.6.32-5-xen-amd64 placeholder root=UUID=25c3ac79-6850-498d-afcf-ea42970e94fd ro  quiet xen-pciback.permissive xen-pciback.hide=(02:00.0)(03:00.0) pci=resource_alignment=02:00.0;03:00.0
> 
> I'm having a serious issue where the raid card goes offline after an
> indefinate period of time. Sometimes runs fine for a week, other times 1
> day before I get "offline device" errors. Rebooting the machine fixes it
> straight away, and everything is back online.
> 
> What in the Xen pciback is causing the raid card to go offline? The
> only devices hidden are the 2 onboard NIC's.

You need to give more details. Is the RAID card a 3Ware? An LSI? Do you
run with an IOMMU? When the RAID card goes offline, do you see a stop of
IRQs going to the device? Are the IRQs for the RAID card sent to all of your
CPUs or just a specific one? Are you pinning your guests to specific CPUs?
Does the issue disappear if you don't passthrough the NIC interfaces? If so have
you run this setup for "a week" to make sure?
> 
> I know that this issue is with Xen, as I had this running on a different
> server (same xen setup) and it had the same issues, which I initially
> thought were to do with the raid card.

So you never ran this setup on this kernel (2.6.32-5) without the Xen hypervisor?

> 
> Is there known issues in this kernel and xen version with pciback? I'm

No. It all works perfectly :-)

> going to update to the current package versions this evening (4.0.1-1
> and 2.6.32-27) however would appreciate if anyone has any other insight
> into this issue, or even just a note to say it is a bug that has been
> fixed in current versions!

Well, there were issues with the LSI cards having a hidden PCI device. But those
are pretty obvious as you can't even use it correctly. There is also
a problem with 3Ware 9506 IDE card - which on my box stops sending IRQs
on the IOAPIC it has been assigned (28) and instead uses another one (17).
Not sure if this is just the PCI card using the wrong PCI interrupt pin on the
card and it ends up poking the wrong IOAPIC.