I think that if Linux does go ahead with the rematch, we add the following
added requirements:
They create two identical copies of the testbed, one running each OS.
(couse the approiate fareness protection should be applied).
Each team should have access to their servers for 72 hours before the test
and can have the benchmark run whenever they want. But NO ability to tune
the clients, the clients must stock from the box (cept with test sofware
installed by third party).
Finally, the test should be run in continous mode for *1 month* and if a
server crashes it must be complete rebuilt before restarting the test (or
perhaps not allowed to restart at all). At the end of the test, the one
with the highest average performance wins.
I'm sure MS can tune NT to beat Linux, and I'm sure NT can 99.9% (not that
good but) under load if tuned right.. But I bet MS can't make NT stable
and fast at the same time.
Some of the tuning done on the orignal test makes NT very unstable,
without such tuning, Linux will win, esp if it uses patched apache or
zeus.
-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.rutgers.edu
Please read the FAQ at http://www.tux.org/lkml/