On Wed, Nov 23, 2016 at 06:55:52AM -0500, Philippe Meunier wrote: > Otto Moerbeek wrote: > >It is not a problem of crashing or not, S does incur a performance hit > >that we are not willing accept by default. > > I've seen this claim several times on this mailing list over the past > few years but does anyone have actual data about it? How much of a > performance hit is it in practice for, say, some typical tasks > (whatever "typical" means)?
[...] > Does anyone know of a relatively common program for which S > is a human-noticeable performance hit? I now see that otto already gave the same example, but since I ran the tests, here's some more numbers. In my experience, build times are increased by something between 50% and 100% when I switch from CJ (what I usually run) to S. Here's five consecutive runs of 'make -j4' of GENERIC.MP on my otherwise mostly idle T420 with 4 cores: Intel(R) Core(TM) i7-2620M CPU @ 2.70GHz, 2691.64 MHz. CJ 1m56.34s real 5m28.56s user 1m04.40s system S 4m10.98s real 6m03.39s user 8m45.45s system CJ 1m50.48s real 5m38.03s user 1m03.00s system S 4m06.88s real 5m59.65s user 7m57.17s system none 1m41.22s real 5m16.35s user 1m02.65s system