[Libguestfs] [PATCH v2 0/7] tests/qemu: Add program for tracing and analyzing boot times.

[Richard W.M. Jones]

On Sun, Mar 20, 2016 at 05:28:05PM +0200, Török Edwin wrote:
> On 03/20/2016 14:30, Richard W.M. Jones wrote:
> > v1 was here:
> > 
> >   https://www.redhat.com/archives/libguestfs/2016-March/thread.html#00157
> 
> Thanks, this is much better than looking at 'ts -i' output.
> 
> BTW I have use 'git am' to apply them to latest git HEAD and try it.
> Is this the preferred way, or is there a git branch/repo somewhere that I missed which would already have these applied?

I've just pushed what I'm working on to my fork of the repo
(https://github.com/rwmjones/libguestfs/commits/master).

> Ah, I didn't have sgabios installed, and it complained it couldn't
> find an event (qemu:overhead?).

Right - it's very sensitive to the exact debug output.

> Installed it and I got similar results to yours, the largest
> overhead is BIOS:
> https://gist.github.com/anonymous/37cfb3d4eb3d3a1c86b2

Your qemu overhead is lower.  That could be because of:

  https://bugzilla.redhat.com/show_bug.cgi?id=1319483

Interestingly your total time is at least double mine.  Either your
hardware is slower or there's something else going on.

> Thought to try booting a Xen PV domain for comparison, but AFAICT
> libguestfs doesn't support LIBGUESTFS_BACKEND=libvirt:xen:///

No, this isn't really going to work.  It's a bunch of work to support
completely different hypervisors like Xen, even with libvirt helping.

> >, and the other ⅔rds is something else in SeaBIOS.
> > Simply removing SGABIOS improves boot times to below 2s, but at a cost
> > that we cannot see any messages from SeaBIOS so further measurement
> > and therefore improvement becomes impossible.  I'm going to try to fix
> > SeaBIOS/SGABIOS first.  See also:
> > 
> >   http://thread.gmane.org/gmane.comp.emulators.qemu/402196

SGABIOS turns out to be caused by something different from what I
thought.  See my attempt (not yet working) to fix this:

  https://github.com/rwmjones/libguestfs/commit/8ffab2d708e9480741b373c0702d12ed86dd572a

I haven't looked at SeaBIOS yet.  That's the biggest issue.

> Nice, this would benefit booting regular VMs too, not just
> libguestfs appliances, right?

Yes, this work benefits everyone.

Rich.

-- 
Richard Jones, Virtualization Group, Red Hat http://people.redhat.com/~rjones
Read my programming and virtualization blog: http://rwmj.wordpress.com
libguestfs lets you edit virtual machines.  Supports shell scripting,
bindings from many languages.  http://libguestfs.org