Hello,
May be it is time to change the hash function used
for the table with connections. Today I played with some data
from my 2.2 director and fixed the tools that measure different
hash functions. I tested the default LVS function, one
that uses 2654435761 and the Jenkins hash that is present in
recent 2.4 and 2.5 kernels. We need some help from math
perspective.
http://www.ssi.bg/~ja/hashlvs-0.2.tgz - tools for tests
I created test patch against ipvs-1.0.9 (not tested). This is an
attempt to introduce randomness on IPVS load. As for the tests
with the different hash functions you can see my results and
of course to try them yourself. My conclusion is that 2654435761
is better and faster but I hope we will see other results.
http://www.ssi.bg/~ja/lvs/
test.txt contains short instructions for testing.
ipvs-1.0.9-hash1.diff - test version for 2.4.21
Regards
--
Julian Anastasov <ja@xxxxxx>
|