>On Sat, 5 Sep 1998, Bruno Haible wrote:
>
>>Here are timings of the three alternatives, for the "common" case.
>
>The standard kernel profiling is really not realiable in the short term so
No, my real profiling is not what you want. You need that the number say
you how much time the kernel passed in such functions and not how many
times such function is been recalled.
But why not account the time (or better cpu cyles) without use profiling
at all? I don' t think that the standard profiling can give us realiable
numbers in some minutes of testing...
Andrea[s] Arcangeli
-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.rutgers.edu
Please read the FAQ at http://www.tux.org/lkml/faq.html