[erlang-questions] performance drop in R15A?

[Tomas Abrahamsson]

Nico Kruber wrote:
NK>>>>>>> With our internal benchmarks ("make bench") showed a drop of
NK>>>>>>> around 15% in performance compared to R14B04. [...]

Kenneth Lundin wrote:
KL>> When working with R15B we are of course performing a number of
KL>> bencmarks to keep track of the performance.
KL>>
KL>> Whe always strive to improve general performance in each release AND
KL>> OUR BENCHMARKS INDICATE THAT R15B IS FASTER IN GENERAL THAN R14B04.
KL>>
KL>> It is however always possible that some specific operations or
KL>> combinations of operations get slower while others are optimized.

I wrote:
TA> We, too, have seen a performance drop similar to what
TA> Nico has observed [...]

Hi again, (replying to self ... hmm :) )

well, anyway, status update: we've further developed
our prototype a bit, experimented a bit with various
scheduler bind settings and also a bit with erlang
process communication patterns, and now it seems that
the performance of R15A for our protoype is well on par
with R14B04. We can no longer say that R15 is slower.
(We haven't tracked down exactly why we earlier saw R15
to be slower, but we don't see it anymore.)


BRs
Tomas