Hi, ok thanks for the advice. I will try a setup with all of the tuning adjustments turned off and see how we perform :)
Ok I understand and appreciate that. Is their any other advice that anyone could offer to improve the interrupt processing limit until an SMP kernel? Incidentally, I understand their are some huge technical chalenges associated with developing an SMP kernel without undermining the security, but how is progress coming along? Andy (An OBSD fanboy! ;) On Wed, 15 May 2013 11:53:18 +0200, Peter Hessler <phess...@theapt.org> wrote: > On 2013 May 15 (Wed) at 10:29:24 +0100 (+0100), andy wrote: > :I have tunned the boxes as much as possible using information from > :calomel XXX etc and overall we have been extremely happy with them, expect > :for the performance limits. > > Do Not Use Any Information From This Site(tm). It is wrong and bad. > > > :Can you please tell me when ToE support will be added for the Intel series > > Never. There are many security issues with running ToE, and we do > need the per-packet information for the session tracking in PF.