[Info-vax] What choices are available to the OpenVMS Process Scheduler once all the CPUs are in use?

[Kerry Main]

> -----Original Message-----
> From: Info-vax [mailto:info-vax-bounces at info-vax.com] On Behalf Of
> David Froble via Info-vax
> Sent: 10-Feb-16 1:53 AM
> To: info-vax at info-vax.com
> Cc: David Froble <davef at tsoft-inc.com>
> Subject: Re: [New Info-vax] What choices are available to the OpenVMS
> Process Scheduler once all the CPUs are in use?
> 
> sean at obanion.us wrote:
> > We had an unusual beginning of Feb., where our typical heavy month
> end (of Jan.) pushed us to an unexpected 32 CUR processes (25 or so are
> typical for month end) for about 7 hours during the day, resulting in
> unusual performance. With a peak of about 120 COM processes
> (measured from PAWZ from PerfCap, and a typical value for month end),
> CPU utilization averaged below 20% (on Monitor System, CPU Busy
> reported 500-600% out of 3200). We observed that higher Priority
> processes, including internal connected users and external networked
> companies/services all expecting responses in 2-4 seconds had no
> complaints, but many reports in batch took 8 to 10 times as long as typical
> to complete.
> > Additionally, disk I/O rates and response times were good, paging rates
> were low and there was substantial memory on the free page list, and
> virtual IO cache (approximately 32 GB) appeared to be fully used.
> >
> > We are on OpenVMS 8.4, patches to Update 10, BL870 (16 cores with
> Hyper threading enabled = 32 CPUs seen, as recommended by our Cache
> application vendor), 64GB memory, Fibre Channel to P9500 storage array,
> Cache 2010 database and applications.
> >
> > We have engaged PerfCap, HP support, and our application vendor to
> understand what we measured and observed, including loading T4 onto
> a production scale test system to validate what PAWZ is saying and to try
> to replicate some of the issues.
> >
> > But my question is:
> >
> > What choices are available to the OpenVMS Process Scheduler once all
> the CPUs are in use?
> > And if (I suspect) the Scheduler was struggling to choose what
> processes to execute, how would it's efforts (CPU cycles) be
> reported/measured?
> >
> >
> > Sean
> 
> You mention "higher Priority processes" ...
> 
> Are you mucking around with process priorities?  While I don't have any
> specific
> suggestions for you, I will observe that usually when process priority is
> mucked
> with, you don't get what you desire, and most often things get worse.
> Well
> except for the user running at elevated priority ....
> 
> If there are differing priorities, if a higher priority process is runable, it
> will get scheduled.  You might think there is excess CPU cycles, but,
> switching
> processes does have overhead, and even with excess CPU cycles,
> thrashing can occur.
> 
> There is a lot of people who know a lot more about this than I do.
> Perhaps I'm
> rather inaccurate.  It's just, my past experiences say "maybe not".
> 
> Caviet, past experiences were not with the itanic, or even Alpha.
> 

Another option is to use the native OpenVMS class scheduler to ensure 
certain processes and/or groups of processes do not take over more 
than their share of the system.

$ mcr sysman
SYSMAN> help class

Reference:
http://h71000.www7.hp.com/openvms/journal/v15/class_schedule.html

"The class scheduler provides the ability to limit the amount of CPU time 
that a system's users may receive by placing the users into scheduling 
classes. Each class is assigned a percentage of the overall system's CPU 
time. As the system runs, the combined sets of users in a class are limited 
to the percentage of CPU execution time allocated to their class. To 
invoke the class scheduler, use the SYSMAN interface."

Regards,

Kerry Main
Kerry dot main at starkgaming dot com