On 30/08/2023 10:22 pm, Horne, Jim wrote:
Peter,
In theory, I agree with you. In practice, I know of at least one shop with one
system where overall throughput was worse with SMT=2 than with SMT=1 - and none
of their systems got the benefits IBM predicted. I'm not saying it's common
but it has happened.
Do you know why, or the nature of the workload?
It seems like it should be rare - until there are more processes than
processors, everything should run at 100%. If you have more processes
than processors, SMT means you have work being dispatched that otherwise
would be waiting.
Work that might be negatively impacted would be work that occupied close
to 100% of a processor, and forced other work to wait. SMT would allow
the other work to run improving overall throughput but reducing the
speed of the first job.
That's the theory anyway - what does it look like in practice?
--
Andrew Rowley
Black Hill Software
----------------------------------------------------------------------
For IBM-MAIN subscribe / signoff / archive access instructions,
send email to [email protected] with the message: INFO IBM-MAIN
