On Mon, 13 Apr 2020 19:18:06 +0200, Bernd Oppolzer wrote:
>
>At one of the two sites, we experimented with USS, because it was a
>requirement for rDz,
>    ...
>To enable all users to use USS segments for rDz was a performance
>nightmare;
>
I have wondered previously in these lists whether more address spaces
are created nowadays for fork() or for job steps.  Of course it depends 
on the site.

If the former, it would make sense for performance to refracture job
step to piggyback on fork(), rather as at present fork() piggybacks
on job step.

-- gil

----------------------------------------------------------------------
For IBM-MAIN subscribe / signoff / archive access instructions,
send email to [email protected] with the message: INFO IBM-MAIN

Reply via email to