Author nirai
Recipients DazWorrall, aconrad, alex, brian.curtin, carljm, coderanger, dabeaz, djc, eric.smith, flox, jcea, jhylton, karld, kevinwatters, konryd, loewis, mahmoudimus, movement, nirai, pitrou, rcohen, rh0dium, salgado, tarek
Date 2010-03-26.20:25:05
SpamBayes Score 3.52015e-07
Marked as misclassified No
Message-id <>
> But on a busy system, won't measuring wall clock time rather than CPU time give bogus results?

This was the motivation for using clock_gettime(). I tried the wall clock version under load (including on single core system) and it seems to behave. Now it remains to rationalize it :)
Date User Action Args
2010-03-26 20:25:06niraisetrecipients: + nirai, loewis, jhylton, jcea, pitrou, movement, eric.smith, kevinwatters, tarek, djc, karld, carljm, coderanger, alex, konryd, brian.curtin, flox, DazWorrall, salgado, rh0dium, rcohen, dabeaz, mahmoudimus, aconrad
2010-03-26 20:25:06niraisetmessageid: <>
2010-03-26 20:25:05nirailinkissue7946 messages
2010-03-26 20:25:05niraicreate