On Friday, 19.06.2015 at 17:50, Justin Cormack wrote: > On 19 June 2015 at 17:42, Martin Lucina <[email protected]> wrote: > > Also note that I have no idea what the stability of TSC is under KVM and > > the current code makes no attempt to figure out if TSC is invariant, > > constant, or anything else. So option 3) would also be a safe(r) bet in > > that the PIT should "just work". > > KVM has a PV clock, see summary of how it works here > https://rwmj.wordpress.com/tag/kvmclock/ > > Because clocks under virtualization are problematic, using this is > probably the best solution longer term.
Thanks for that. Yay for KVM documentation being a gaggle of blog posts all over the net. I got as far as https://www.kernel.org/doc/Documentation/virtual/kvm/timekeeping.txt which has absolutely *nothing* to say about a pvclock :-/ I'll try this out, if it works then it looks like the best combination (in terms of least code complexity) is to use pvclock when running under KVM and just use classic tick counting with PIT for everything else (ie. my option 3). Martin
