On Fri, 9 Jul 2004 11:18:47 +0100, Matt Sergeant <[EMAIL PROTECTED]> wrote: > On 9 Jul 2004, at 11:12, karthikeyan s wrote: > > > I've timed an empty SA, SA with razor2, SA with dccifd, SA with > > dccproc, SA with pyzor and got the following timings on my Athlon Xp > > 2100+ with 512 MB RAM and Gentoo with 2.6.5 kernel: > > > > SA alone with DNS lookup of received from IP:1.199s > > SA with dccproc:1.857s > > SA with dccifd:1.859s > > SA with pyzor:1.654s > > SA with razor2:2.560s > > SA with dccifd+pyzor+razor:3.660s > > You should check User+Sys time, not Wallclock time, as you can probably > safely assume you will get emails in parallel, and in parallel the > User+Sys time is the only thing that matters.
Well, SA with no tests gives the following times: real 0m1.134s user 0m1.059s sys 0m0.057s SA with dcc+pyzor+razor: real 0m3.660s user 0m1.147s sys 0m0.083s So, user space difference is just 1.059 to 1.147. Then, i'm rewriting the wrapper as a multithreaded one and see the timings for 1000 mails coming in at different rates(1/sec to maybe 100/sec is the realistic range). cheers, Karthikeyan,S.
