On Thu, 14 Jun 2012, Mark Dixon wrote:
...
* I do NOT believe that AS should be summed when the processes of a job
are being polled. Instead it should be RSS+SWAP (or similar).
(sorry, ignore that 2nd sentence)
* I DO believe that the per-process AS setrlimit should be settable to a
value specified by the user (but defaulting to unlimited), to maintain the
existing functionality described in earlier messages.
...
I suspect that everyone's got board of this conversation by now, but I'm
replying for my own piece of mind...
Interestingly enough, I'm seeing things a little more your way now: I
guess that using a resource named "h_vmem" to control
memory.memsw.limit_in_bytes makes more sense than the old behaviour. And
it fits in more naturally with existing job accounting attributes like
'mem' and 'maxvmem'.
However, I still think that RLIMIT_AS should be controllable by the user
somehow, independently of memory.memsw.limit_in_bytes. I'm also still
skeptical that the old sum-RLIMIT_AS-over-multiple-processes behaviour is
actually useful when you have memory.memsw.limit_in_bytes control.
But we're all allowed our opinions, I suppose ;)
All the best,
Mark
PS I hope the new release is shaping up well
--
-----------------------------------------------------------------
Mark Dixon Email : [email protected]
HPC/Grid Systems Support Tel (int): 35429
Information Systems Services Tel (ext): +44(0)113 343 5429
University of Leeds, LS2 9JT, UK
-----------------------------------------------------------------
_______________________________________________
users mailing list
[email protected]
https://gridengine.org/mailman/listinfo/users
