Re: [REPORT] cfs-v4 vs sd-0.44

On Tue, Apr 24, 2007 at 06:22:53PM -0700, Li, Tong N wrote:
The goal of a proportional-share scheduling algorithm is to minimize the
above metrics. If the lag function is bounded by a constant for any
thread in any time interval, then the algorithm is considered to be
fair. You may notice that the second metric is actually weaker than
first. In fact, if an algorithm achieves a constant lag bound, it must
also achieve a constant bound for the second metric, but the reverse is
not necessarily true. But in some settings, people have focused on the
second metric and still consider an algorithm to be fair as long as the
second metric is bounded by a constant.

Using these metrics it is possible to write benchmarks quantifying
fairness as a performance metric, provided weights for nice numbers.

Not so coincidentally, this also entails a test of whether nice numbers
are working as intended.


-- wli

P.S. Divide by the length of the time interval to rephrase in terms of
CPU bandwidth.
-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/

Relevant Pages

  • Re: How can you tell if two metrics describe the same manifold?
    ... > Is there an algorithm that would allow one to tell if two ... > different metrics describe the same manifold? ... of the Riemann tensor of the metrics ... Then there is the classification algorithm of Karlhede, ...
    (sci.physics.relativity)
  • Re: Statistical Methods for Ranks?
    ... So Algorithm A's performance on Dataset 1 is the ... frames in that dataset; the standard deviation is also reported from ... are not matched from one data set to another (i.e., ... crossed with algorithms and metrics)? ...
    (sci.stat.math)
  • How can you tell if two metrics describe the same manifold?
    ... Is there an algorithm that would allow one to tell if two ... find a change of coordinates that transfers the first metric into the ... Some very seemingly different metrics like ... both really describe the same manifold. ...
    (sci.physics.relativity)
  • Re: TCM decoder (Viterbi). Prevent overflow in metric path
    ... but in this case I need subtruct constant value from all ... path metrics on current step of algorithm, on next step this value may be ... overflow in metric path. ...
    (comp.dsp)
Loading