Re: [Qemu-devel] [RFC PATCH V3 0/6] icount: Implement delay algorithm between guest and host clocks

[Sebastian Tanase <sebastian.tanase@openwide.fr>]

----- Mail original -----
> De: "Paolo Bonzini" <pbonzini@redhat.com>
> À: "Sebastian Tanase" <sebastian.tanase@openwide.fr>, qemu-devel@nongnu.org
> Cc: aliguori@amazon.com, afaerber@suse.de, rth@twiddle.net, "peter maydell" <peter.maydell@linaro.org>,
> michael@walle.cc, alex@alex.org.uk, stefanha@redhat.com, lcapitulino@redhat.com, crobinso@redhat.com,
> armbru@redhat.com, wenchaoqemu@gmail.com, quintela@redhat.com, kwolf@redhat.com, mjt@tls.msk.ru, mst@redhat.com
> Envoyé: Lundi 30 Juin 2014 19:16:48
> Objet: Re: [RFC PATCH V3 0/6] icount: Implement delay algorithm between guest and host clocks
> 
> Il 30/06/2014 15:59, Sebastian Tanase ha scritto:
> > The icount option already implemented in QEMU allows the guest to
> > run at a theoretical
> > frequency of 1/(2^N) GHz (N is the icount parameter). The goal of
> > this patch is to have a
> > real guest frequency close to the one imposed by using the icount
> > option.
> >
> > The main idea behind the algorithm is that we compare the virtual
> > monotonic clock and the
> > host monotonic clock. For big icounts (on our test machine, an i5
> > CPU @ 3.10GHz, icounts
> > starting at 6) the guest clock will be ahead of the host clock. In
> > this case, we try to
> > sleep QEMU for the difference between the 2 clocks. Therefore, the
> > guest would have
> > executed for a period almost equally to the one imposed by icount.
> > We should point out
> > that the algorithm works only for those icounts that allow the
> > guest clock to be in front
> > of the host clock.
> >
> > The first patch adds support for QemuOpts for the 'icount'
> > parameter. It also adds a
> > suboption called 'shift' that will hold the value for 'icount'.
> > Therefore we now have
> > -icount shift=N|auto or -icount N|auto.
> >
> > The second patch adds the 'align' suboption for icount.
> >
> > The third patch exports 'icount_time_shift' so that it can be used
> > in places other than
> > cpus.c; we need it in cpu-exec.c for calculating for how long we
> > want QEMU to sleep.
> >
> > The forth patch implements the algorithm used for calculating the
> > delay we want to sleep.
> > It uses the number of instructions executed by the virtual cpu and
> > also the icount_time_shift.
> >
> > The fifth patch prints to the console whenever the guest clock runs
> > behind the host
> > clock. The fastest printing speed is every 2 seconds, and we only
> > print if the align option
> > is enabled. We also have a limit to 100 printed messages.
> >
> > The sixth patch adds information about the difference between the
> > host and guest clocks
> > (taking into account the offset) in the 'info jit' command. We also
> > print the maximum
> > delay and advance of the guest clock compared to the host clock.
> 
> I think the changes I made are too big to get this in 2.1, but we can
> certainly get this very early in 2.2 instead.  I'll shortly push my
> changes to an "icount" branch at github.com/bonzini/qemu.git.  Can
> you
> look at it and rebase patches 5 and 6 on top (plus the small change I
> asked for in my review of patch 2)?
> 
> Thanks,
> 
> Paolo
> 
> 

Sure, I'll prepare a V4 with all the changes, rebased on your "icount" branch.


Sebastian