On 17/12/2013 17:13, Peter Zijlstra wrote: > On Tue, Dec 17, 2013 at 04:03:58PM +0200, Eliezer Tamir wrote: >> >> I'm not sure that subtracting the spin time is the optimal thing to do. >> >> The busy poll time is supposed to be limited to something less than 1ms. >> (I'm using 50us in most of my tests) >> This is typically orders of magnitude smaller than the poll timeout. >> Would it make more sense to just enforce a limit on poll time? >> >> What do you think? > > I've no idea what people normally expect of select/poll wakeup > granularity but typically we already have 50us of timer slack, although > RT tasks go without this.
If RT tasks can't accept 50us of fuzziness, then the path of least astonishment would be to have fully accurate timekeeping, as you suggested. OK, so that's the plan. Thanks, Eliezer -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majord...@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/