Re: Is there a current known getrusage() problem (amd64)

[Robert Elz <kre%munnari.OZ.AU@localhost>]

    Date:        Wed, 4 Apr 2018 15:43:48 -0400 (EDT)
    From:        Mouse <mouse%Rodents-Montreal.ORG@localhost>
    Message-ID:  <201804041943.PAA05984%Stone.Rodents-Montreal.ORG@localhost>

  | Hmm...have you tried a non-MP kernel?  Have you tried nailing your test
  | down on each of the available CPUs?  Have you tried running various
  | numbers of infinite-loop CPU-burners at the same time?

No, to all of those - and all good suggestions (and since this is a XEN DomU
I can give it just 1 CPU as well...)

WIll do all that, tomorrow... (or, that is, today, but later, much later...)

What I have done more recently is

	time cgdconfig ...

and that reports (when I killed it the cgdconfig, in a couple
of attempts)  3.xx and 5.xx seconds elapsed time,
and the same amount of system time  and 0 user time.

SInce this program (used this way) does just about no sys
calls (other than my diagnostic printfs, which should consume
almost nothing - there are not all that many) but is CPU
intensive, that is clearly backwards.

I have not been able to kill it while it is still in
the period when it is getting sane user cpu times,
to see what the time command says then (that usually
ends within a few milliseconfds of CPU (and elapsed) time.)

I might see if I can rig a debugger session and breakpoint it,
so I can keep it within those initial steps, and then kill it.

Or with your suggestions, and what I can see already,
I might just be able to read the kernel code and spot
a bug.

kre