Hi, 2013/1/25 Greg KH <gregkh@xxxxxxxxxxxxxxxxxxx>: > On Thu, Jan 24, 2013 at 11:34:59AM +0100, Ivo Sieben wrote: >> >> On a 240 MHz AT91SAM9261 processor setup this fixes about 100us of scheduling >> overhead on the TTY read call. > > Out of how many us total? > I tested with a TTY read call that before all optimizations had an average 76 us and a maximum of 305 us. After the optimizations the average dropped to 59 us and the maximum dropped to 135 us. Of course that gain of 170us is not completely due to this patch, also the other TTY patches that I've posted have contributed to this. I will remove this remark on the exact numbers from the commit message... it prevents unnecessary scheduling overhead, which is I think sufficient to describe what this patch does. > And this really makes a difference? I'd like to hear the rt developers > opinoin of this. > > greg k-h I will repost this patch and ask Thomas Gleixner and Steven Rostedt to take a look at it. Regards, Ivo Sieben -- To unsubscribe from this list: send the line "unsubscribe linux-serial" in the body of a message to majordomo@xxxxxxxxxxxxxxx More majordomo info at http://vger.kernel.org/majordomo-info.html
