Hello Oleg, On Wed, Jun 11, 2008 at 5:14 PM, Oleg Galimov <Galimov@xxxxxx> wrote: > I use cyclictest as a benchmark for my diploma thesis. I have a strange behavior however, which I can't explain: > > I have a dual-core cpu. When I run cyclictest on both cores and then start a time hog (like cp /dev/zero /dev/null), then the average latency on the core where it runs goes down significantly (on my machine it is like 30us before and 10us after, when using rt-patch). It returns to the original values, when I kill the cp process. > Possibly, without the single-threaded 'time hog', your cyclictest threads maybe are scheduled across the two cores, resulting in increased (peak and average) latencies. See if you can use the CPU affinity feature to fix each thread to a dedicated core, and see if this matters. I'm quite sure cyclictest has an option for this, but please check. Regards, -- Leon -- To unsubscribe from this list: send the line "unsubscribe linux-rt-users" in the body of a message to majordomo@xxxxxxxxxxxxxxx More majordomo info at http://vger.kernel.org/majordomo-info.html
