Hi Robert,

28.01.2016 00:45, Robert Jonsson пишет:
Hi Andrew,

I recall you changed the cpu usage calculation a while ago, what is it counting now?

If I compare what I get with the load in htop it seems very high, though I guess that is better than it counting too low :)
It simply counts how much time elapsed from last control point, then takes process's cpu time (via rusage system call, also from last control point) and divides second by the first. The main difference between jack algorithm is that muse counts not only dsp usage, but also gui drawings etc.. I thought that it can be useful for optimizing drawing operations (and it really helped in some cases). And the difference between top/htop etc. I think in time slice - in muse it's equal to gui hartbeat timer, but in top it is nearly 1 second. So top and friends can give more coarse results, I think.

/Robert



------------------------------------------------------------------------------
Site24x7 APM Insight: Get Deep Visibility into Application Performance
APM + Mobile APM + RUM: Monitor 3 App instances at just $35/Month
Monitor end-to-end web transactions and take corrective actions now
Troubleshoot faster and improve end-user experience. Signup Now!
http://pubads.g.doubleclick.net/gampad/clk?id=267308311&iu=/4140


_______________________________________________
Lmuse-developer mailing list
[email protected]
https://lists.sourceforge.net/lists/listinfo/lmuse-developer

--
Regards,
Andrew

------------------------------------------------------------------------------
Site24x7 APM Insight: Get Deep Visibility into Application Performance
APM + Mobile APM + RUM: Monitor 3 App instances at just $35/Month
Monitor end-to-end web transactions and take corrective actions now
Troubleshoot faster and improve end-user experience. Signup Now!
http://pubads.g.doubleclick.net/gampad/clk?id=267308311&iu=/4140
_______________________________________________
Lmuse-developer mailing list
[email protected]
https://lists.sourceforge.net/lists/listinfo/lmuse-developer

Reply via email to