Date: Tue, 27 Aug 2019 22:22:47 +0300 From: Victor Gamov <vit@otcnet.ru> To: Eugene Grosbein <eugen@grosbein.net>, "Andrey V. Elsukov" <bu7cher@yandex.ru>, freebsd-net@freebsd.org Subject: Re: finding optimal ipfw strategy Message-ID: <60d075ee-0d39-6606-ea5a-35e27818162a@otcnet.ru> In-Reply-To: <50b0748d-bf8a-4de9-58bf-800ddd4f9c27@grosbein.net> References: <f38b21a5-8f9f-4f60-4b27-c810f78cdc88@otcnet.ru> <4ff39c8f-341c-5d72-1b26-6558c57bff8d@grosbein.net> <a559d2bd-5218-f344-2e88-c00893272222@otcnet.ru> <ddaa55bc-1fa5-151b-258e-e3e9844802ef@yandex.ru> <c275f853-62a7-6bb7-d309-bf8a27d3dbae@grosbein.net> <50b0748d-bf8a-4de9-58bf-800ddd4f9c27@grosbein.net>
next in thread | previous in thread | raw e-mail | index | archive | help
On 27/08/2019 21:50, Eugene Grosbein wrote: > 28.08.2019 1:46, Eugene Grosbein wrote: > >> 28.08.2019 1:03, Andrey V. Elsukov wrote: >> >>> As you can see, when ipfw produces high load, interrupt column is more >>> than system. >> >> Interrupt numbers higher than others generally mean that traffic is processed without netisr queueing mostly. >> That is expected for plain routing. I'm not sure if this would be same in case of bridging. >> >> Victor, do you have some non-default tuning in your /boot/loader.conf or /etc/sysctl.conf? >> If yes, could you show them? If not, you should try something like this. For loader.conf: >> >> hw.igb.rxd=4096 >> hw.igb.txd=4096 >> net.isr.bindthreads=1 >> net.isr.defaultqlimit=4096 >> #substitute total number of CPU cores in the system here >> net.isr.maxthreads=4 >> # EOF > > Also, you should monitor interrupt numbers shown by "systat -vm 3" for igb* devices > at hours of most load. If they approach 8000 limit but not exceed it, > you may be suffering from this and should raise the limit with /boot/loader.conf: > > hw.igb.max_interrupt_rate=32000 It's about 5000-7000 per rxq -- CU, Victor Gamov
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?60d075ee-0d39-6606-ea5a-35e27818162a>