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

Re: [Xen-devel] [PATCH] x86/EPT: flush cache when (potentially) limiting cachability

Sorry to update.
The bug refers to http://bugzilla.xensource.com/bugzilla/show_bug.cgi?id=1887.
L2 guest vnc console hangs at black screen with cursor flashing at the top left 
After several minutes, the Seabios screen shows up, but the screen still flush 
slowly, the guest could not boot up.
For the good point(L0 git:06bbcaf48d09c18a41c482866941ddd5d2846b44), the L2 
rhel_x64 could boot up less in than 90s.

> -----Original Message-----
> From: Jan Beulich [mailto:jbeulich@xxxxxxxx]
> Sent: Friday, May 30, 2014 3:02 PM
> To: Liu, SongtaoX; xen-devel@xxxxxxxxxxxxxxxxxxxx
> Cc: Dong, Eddie; Nakajima, Jun; Tian, Kevin; Pang, LongtaoX; Hu, Robert; 
> Zhang,
> Yang Z; keir@xxxxxxx; tim@xxxxxxx
> Subject: Re: [Xen-devel] [PATCH] x86/EPT: flush cache when (potentially)
> limiting cachability
> >>>> "Jan Beulich" <jbeulich@xxxxxxxx> 05/30/14 8:28 AM >>> "Liu,
> >>>> SongtaoX" <songtaox.liu@xxxxxxxxx> 05/30/14 4:07 AM >>>
> >>The following patch leads nested (Xen on Xen ,KVM on Xen) L2 guest
> >>failed to boot up with default EPT option "hap=1". L2 guest with "hap=0" 
> >>still
> works.
> >
> >That's way to vague a problem description. In what way does it fail?
> >Are there any relevant log messages anywhere? Without suitable detail,
> >how am I (or is anyone else) supposed to help with this?
> I should have added that the patch here solely adding cache flushes, it can't
> reasonable have affected correctness. Hence unless it introduces a live lock 
> of
> some sort, the only possibility I see is that it uncovered some other 
> previously
> latent/hidden problem.
> Jan

Xen-devel mailing list



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