[Zope] Re: [Zope-Annce] Report into Solaris Zope Performance - The Postscript

[Tim Hoffman]

Hi Paul

Processor set's have been in Solaris since around 2.6. and are very
usefull if you have multiple cpu's

In a multicpu environment you can create a set of 1 or more cpu's and
nothing else will run on them except for processes assigned to the set.

You can even force things like the NFS kernel threads to occupy a single
CPU (if that is something you really want to do ;-) by starting up nfsd
in a processor set, the nfsd process is schedulable entity for the
kernel threads, and if it runs in a processor set which has a single cpu
then the kernel threads will get scheduled to run there.

The big difference is with pbind you bind a process to a CPU, but other
stuff can and will run on the CPU. If you use processor set's you can
exclude all other processes from running on the CPU, other than those
processes that have been assigned to the set.

Processor set's have really replaced pbind. You would only use pbind if
you want to force processor affinity and limit the task to a single CPU,
but let other tasks use the cpu.

try docs.sun.com and search for psrset.

Solaris 9 introduces a Resource manager and even finer grain scheduling
of resources, and using resource pools and projects, and new scheduling
classes such as fixed priority and fair share scheduling.

People really shouldn't be afraid of running python/zope on solaris,
especially in multi-cpu environments, as long as they understand how
python works, because you actually have much better resource control
than pretty well any other O/S out there, but as they say use the right
tool for the job, and make informed decisions ;-)

See ya

Tim



On Thu, 2002-08-29 at 16:03, Paul Browning wrote:
> 
> Tim:
> 
> Thanks for the feedback. I'm not that familiar with Solaris - where
> can I read more about processor sets? Is that pbind sort of stuff?
> 
> Paul
> 
> --On 29 August 2002 14:12 +0800 Tim Hoffman <timhoffman@cams.wa.gov.au> 
> wrote:
> 
> > Just a few more comments on Zope on Solaris
> >
> > I have been running Zope almost exclusively on Solaris since May 2000.
> > Anecdotally I have found certainly in the python 1.5.2 days and in fact
> > prior to python 2.1.3 that I too experienced some of the performance
> > scalability issues on heavily loaded zope servers using oracle. By using
> > processor set's and limiting the Zope instance to a single CPU, I then
> > never ran into the bogging down issues. If you then split Zeo/ZODB into
> > processor set's then you can get multi cpu scalability.
> >
> > I would have to say though that since Solaris 8, Python 2.1.3, Zope
> > 2.5.1 my experience running Zope on UltraSPARC III type boxes I haven't
> > had any occurances of multicpu slow down, and so I am not currently
> > using processor sets. (That doesn't say it isn't going to happen,
> > I just am not experiencing it any more ;-)
> >
> > See ya
> >
> > Tim
> >
> >
> >
> > On Thu, 2002-08-29 at 03:23, Paul Browning wrote:
> >>
> >>
> >> --On 28 August 2002 14:30 -0400 "Matthew T. Kromer" <matt@zope.com>
> >> wrote:
> >>
> >> >
> >> > Paul, I'm glad you took the time to write that up; I'm generally
> >> > available to answer specific questions (or provide misdirection) if you
> >> > have any further questions.
> >>
> >> Thanks, Matt. We're trying to collect some more data points on the
> >> performance of DCOracle on Solaris. I'll keep people posted.
> >>
> >> Paul
> >>
> >> --
> >>  The Library, Tyndall Avenue, Univ. of Bristol, Bristol, BS8 1TJ, UK
> >>    E-mail: paul.browning@bristol.ac.uk  URL: http://www.bris.ac.uk/
> >>
> >>
> >> _______________________________________________
> >> Zope maillist  -  Zope@zope.org
> >> http://lists.zope.org/mailman/listinfo/zope
> >> **   No cross posts or HTML encoding!  **
> >> (Related lists -
> >>  http://lists.zope.org/mailman/listinfo/zope-announce
> >>  http://lists.zope.org/mailman/listinfo/zope-dev )
> >
> >
> 
> 
> 
> --
>  The Library, Tyndall Avenue, Univ. of Bristol, Bristol, BS8 1TJ, UK
>    E-mail: paul.browning@bristol.ac.uk  URL: http://www.bris.ac.uk/