CVS commit: src/sys/rump/librump/rumpkern

[Antti Kantee <pooka%netbsd.org@localhost>]

Module Name:    src
Committed By:   pooka
Date:           Tue May 18 16:29:36 UTC 2010

Modified Files:
        src/sys/rump/librump/rumpkern: Makefile.rumpkern
Added Files:
        src/sys/rump/librump/rumpkern: locks_up.c

Log Message:
Add uniprocessor versions of mutex/rw/cv.  They work only on virtual
unicpu configurations (i.e. RUMP_NCPU==1), but are massively faster
than the multiprocessor versions since the fast path does not have
to perform any cache coherent operations.  _Applications_ with
lock-happy kernel paths, i.e. _not_ lock microbenchmarks, measure
up to tens of percents speedup on my Core2 Duo.  Every globally
atomic state required by normal locks/atomic ops implies a hideous
speed penalty even for the fast path.

While this requires a unicpu configuration, it should be noted that
we are talking about a virtual unicpu configuration.  The host can
have as many processors as it desires, and the speed benefit of
virtual unicpu is still there.  It's pretty obvious that in terms
of scalability simple workload partitioning and replication into
multiple kernels wins hands down over complicated locking or
locklessing algorithms which depend on globally atomic state.


To generate a diff of this commit:
cvs rdiff -u -r1.85 -r1.86 src/sys/rump/librump/rumpkern/Makefile.rumpkern
cvs rdiff -u -r0 -r1.1 src/sys/rump/librump/rumpkern/locks_up.c

Please note that diffs are not public domain; they are subject to the
copyright notices on the relevant files.