On Mon, Jul 15, 2013 at 09:19:17AM -0400, George Greer wrote: > At least on my machine (Core i7-920 2.67GHz, 4core/8thread, > Nehalem), the benchmark probably fails when the CPU adjusts its > frequency. Normally it runs at 2675MHz but sometimes the > Test::Smoke CPU identification lists it as 1600MHz, which could be > due to either heat throttling or sleep states. > > If you have a laptop you might be able to reproduce the effect by > pulling out the power cable and making it run on battery for the > last half of the test, which should throttle the CPU down lower. > > Not that the test could likely compensate for what the CPU/OS is up > to there. I've now removed the test with commit 9eba9e102c2f8c2ec41a50f4bbe6b09a64dddd31 -- More than any other time in history, mankind faces a crossroads. One path leads to despair and utter hopelessness. The other, to total extinction. Let us pray we have the wisdom to choose correctly. -- Woody AllenThread Previous