Okey, good to know Vincent. Do you know the memory impact using 10k, 20k etc?
/E -----Original Message----- From: Vincent Bernat [mailto:ber...@luffy.cx] Sent: den 2 november 2011 15:40 To: Erik Torlen Cc: Lukas Tribus; haproxy@formilux.org Subject: Re: Haproxy timing issues OoO En ce début de soirée du mercredi 02 novembre 2011, vers 21:13, Erik Torlen <erik.tor...@apicasystem.com> disait : > /usr/local/bin/stud -b 127.0.0.1 85 -f *,443 --ssl -B 1000 -n 2 -C > 40000 -u stud -r /home/stud --write-proxy /usr/share/ssl-cert/ > cert.pem > I have tried stud using 10k of shared cache which gave me worse > performance. Has anyone tried stud with different sizes of the shared > session cache? It depends on the profile of your traffic. With about 4000 conn/s and 1000 new client/s, a cache of 20k seems to provide the best performance. Increasing it does not hinder the performance. However, the benchmark was a bit artificial because each client will do 4 conn and will disappear forever. -- Vincent Bernat ☯ http://vincent.bernat.im # Okay, what on Earth is this one supposed to be used for? 2.4.0 linux/drivers/char/cp437.uni
