Yes. I have an old micro-benchmark (old, but extremely stable) that measures
how many times "signal();kill(myself,..)" can be run per second :
With 2.1.130 : 164564..164606 loops/s
With 2.1.130 + your patch : 164243..164329 loops/s
lat_sig (from lmbench) says :
2.1.130 2.1.130 + your patch
Signal handler installation: 1.490us 1.490 us
Signal handler overhead: 3.844us 3.854 us
So it look like micro-benchmarks agree with the simulation ;-)
-- Benoit
-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.rutgers.edu
Please read the FAQ at http://www.tux.org/lkml/