Constraining CPU usage

Hi Guys!

It seems i cannot get a clear answer wherther it is possible to limit a CPU usage by a user process and should i do that at all.

I just wana run "tar -xzvf /usr/backup/pub.tar.gz /usr/home/pub" and do not cause something like this:

PID USERNAME PRI NICE SIZE RES STATE TIME WCPU CPU
3993 backup 139 20 8672K 8068K RUN 19:56 87.65% 87.65%
load averages: 0.99, 0.98, 0.88

As you can see in the figure above, renicing wont work.

Any hints? What to read? Thank you.


Nash

FreeBSD 5.3-RELEASE
Timecounter "i8254" frequency 1193182 Hz quality 0
CPU: AMD Duron(tm) processor (1202.73-MHz 686-class CPU)



---------------------------------
Yahoo! Personals
Skip the bars and set-ups and start using Yahoo! Personals for free
_______________________________________________
freebsd-performance@xxxxxxxxxxx mailing list
http://lists.freebsd.org/mailman/listinfo/freebsd-performance
To unsubscribe, send any mail to "freebsd-performance-unsubscribe@xxxxxxxxxxx"

Relevant Pages

  • Re: New optimized soreceive_stream() for TCP sockets, proof of concept
    ... >> those OSes do much better when CPU affinity ... You can slap a sched_bindinto the interrupt> handler the first time it runs and it should stick appropriately, and add> a sysctl to sched_bindfor a user process as a hack to test it out. ... Right now we have a facility to bind kernel threads to specific CPUs ), but not an API or mature facility to bind user threads. ...
    (freebsd-current)
  • Re: New optimized soreceive_stream() for TCP sockets, proof of concept
    ... >> those OSes do much better when CPU affinity ... You can slap a sched_bindinto the interrupt> handler the first time it runs and it should stick appropriately, and add> a sysctl to sched_bindfor a user process as a hack to test it out. ... Right now we have a facility to bind kernel threads to specific CPUs ), but not an API or mature facility to bind user threads. ...
    (freebsd-net)
  • Re: Setting priority for exe built in DFf6.6
    ... Because its the only USER process and as such it gets the CPU scheduler's ... Windows scheduler is VERY sophisticated with its multi-thread ... setting capability and still does the RIGHT thing for your unwashed user ...
    (comp.lang.fortran)
  • Re: can I bring Linux down by running "renice -20 cpu_intensive_process"?
    ... If it's _just_ CPU (as in `perl ... you get a chance that you can input some ... But why should this hang anything, when there should be enough i/o to get out of the user process. ...
    (Linux-Kernel)
  • Re: can I bring Linux down by running "renice -20 cpu_intensive_process"?
    ... If it's _just_ CPU (as in `perl ... you get a chance that you can input some ... to get out of the user process. ... Ever heard of bugs? ...
    (Linux-Kernel)