[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

[Xen-devel] SMP boot time-out with PCI Passthrough


  • To: "xen-devel@xxxxxxxxxxxxxxxxxxx" <xen-devel@xxxxxxxxxxxxxxxxxxx>
  • From: "Fredin, Jerry" <Jerry.Fredin@xxxxxxx>
  • Date: Wed, 2 Sep 2009 07:29:05 -0600
  • Accept-language: en-US
  • Acceptlanguage: en-US
  • Delivery-date: Wed, 02 Sep 2009 06:34:10 -0700
  • List-id: Xen developer discussion <xen-devel.lists.xensource.com>
  • Thread-index: Acor0VeI87nkPLcNRx2pUaIuS4Ncrg==
  • Thread-topic: SMP boot time-out with PCI Passthrough

I am running a Linux 2.6.30.1 hvm guest and the boot cpu is timing out waiting for a secondary cpu to initialize.  The timeout is coded to 5 seconds.  In this time the AP disables and re-enables cpu caches by writing to cr0.  In dom0, I see hvm_set_cr0 take about .8 seconds per GB of memory allocated to the guest OS.  So if the memory is below about 3 GB (5sec/1.6sec per GB), the initialization completes.  If greater than that, the boot cpu gives up. 

 

This only happens with a passthrough device defined in the guest config file with pci=…

 

I’ve tracked it down so far to the ept_change_entry_emt_with_range function taking the majority of the time.  Since this function is not executed if has_arch_pdevs(v->domain) returns zero, it explains why it only happens with a passthrough device.  

 

Is the .8 seconds per GB an expected execution time or is this a known problem I missed in my searches?

 

My configuration is:

 

Intel Xeon E5506 @ 2.1GHz  L1=32k/32k, L2=256k, L3-4096k Quad core  12GB memory

Dom0=CentOS 5.2/Xen 3.4-unstable

 

 

Thanks,  Jerry

_______________________________________________
Xen-devel mailing list
Xen-devel@xxxxxxxxxxxxxxxxxxx
http://lists.xensource.com/xen-devel

 


Rackspace

Lists.xenproject.org is hosted with RackSpace, monitoring our
servers 24x7x365 and backed by RackSpace's Fanatical Support®.