> Now it seems that you are finally running the right benchmarks,
> and that is a good thing.
That sounds a tad defensive. Pardon me for evolving my benchmarks
as I investigate where all the different bottlenecks are (and
remove them).
There is no "right" benchmark. Anyways, people might find it more
interesting to measure select/poll latencies using lat_select from
the lmbench 2.0-alpha test pre-release.
http://reality.sgi.com/employees/lm/lmbench/lmbench2.0-alpha2.tgz
Later,
David "Sparc" Miller
davem@caip.rutgers.edu