Re: [Gems-users] Processor Lost

[Daniel Nussbaum - Sun Microsystems - Burlington United States <dan.nussbaum@xxxxxxx>]

Hi James.

It might help to boot the (simulated) OS down to single-user mode, to
reduce the range of possible background tasks that might interfere
with your runs.

To do this, type

  shutdown -y -g0 -is

at the shell prompt (running simics -fast, without ruby loaded), then
wait for a fairly long time, then when it asks for the root password,
hit ENTER.  At that point, (simulated) Solaris will booted in
single-user mode.  Save the configuration, and run all of your tests
starting from that point.

You'll need to do this separately for 1-, 2-, 4-, etc. processor
machines as needed.

This is the environment from which we run all of our tests.

dann

>
> Date: Thu, 03 May 2007 09:22:54 -0500
> From: Kevin Moore <kmoore@xxxxxxxxxxx>
>
> James,
>
> 	Binding a thread to a processor does not mean that it will run
> there continuously.  It just means that the thread will only run on
> that processor.  If you've created a processor set (psrset), and
> bound only the one thread to that set, no other user threads will
> run in that set.  But, OS processes can and do sometimes run on
> bound processors.  For whatever reason, Solaris likes to run mostly
> on processor 0.  For that reason, what we typically do is to create
> a processor set for each other processor (not p0) and bind our
> threads to those sets.
>
> --Kevin
>
> James Wang wrote:
> >
> > Hi Dan:
> >
> >     Thank you very much for your prompt reply. But I don't really
> >     understand what the nature of this situation is. Why would the
> >     OS want to deschedule my benchmark? Also, I bound the thread
> >     to the processor, should it just stay there and run? I did
> >     this with a four processor simulated machine, why other
> >     processors are not affected by this problem?
> >
> > Regards
> > James
> >
> > ----- Original Message ----
> > From: Dan Gibson <degibson@xxxxxxxx>
> > To: Gems Users <gems-users@xxxxxxxxxxx>
> > Sent: Friday, May 4, 2007 1:03:42 AM
> > Subject: Re: [Gems-users] Processor Lost
> >
> > The OS could be descheduling your transactional benchmark, though
> > I'm not sure why that might be happening. Try quiescing the system
> > by killing background processes, and then pre-fetch any binaries
> > or data you might be using in your benchmark by running it once to
> > completion before loading Ruby (and hence, without
> > synchronization). That should eliminate any I/O you might
> > inadvertenly cause at runtime. It will also cause your benchmark
> > to run with different system interactions, and will hopefully fix
> > the Processor Lost/Processor Found problem.
> >
> > Regards,
> > Dan
> >
> > James Wang wrote:
> >
> >>
> >> Hi All:
> >>
> >>    I am running some transactional memory benchmark using a
> >>    customized SMP cache coherent protocol. For some reason, p0
> >>    will run code other than the transactional benchmark and the
> >>    other processors finishes fine. I cannot really tell what p0
> >>    is doing. I tried a few different random seed, the same
> >>    situation happens every time.
> >>
> >>    Any idea?
> >>
> >>    Thanks for any reply in advance.
> >>
> >> Regards
> >> James
> >>
> >
>