Re: FreeBSD-6 and em interface speed
> Probably due to the test tool you're using. Does the tool serialize the > UDP stream (ie: wait for a response for each packet)? As far as I understand, not it doesn't. The tool is nepim, version 0.17. > > BTW, this should go on freebsd-net. OK, next time it will. Thanks! -- rea BOFH excuse #9: doppler effect ___ freebsd-hackers@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-hackers To unsubscribe, send any mail to "[EMAIL PROTECTED]"
Re: FreeBSD-6 and em interface speed
> I'd start by going back to SCHED_4BSD and seeing how that affects things. ULE > is an experimental scheduler that may produce inconsistent or undesirable > results depending on workload. OK, I will. And I'll follow your next advice about the tcp_inflight and Mike's advice. Following Nate Nielsen I will post my next results to the freebsd-net. Thanks! -- rea BOFH excuse #51: Cosmic ray particles crashed through the hard disk platter ___ freebsd-hackers@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-hackers To unsubscribe, send any mail to "[EMAIL PROTECTED]"
Re: FreeBSD-6 and em interface speed
On Tue, 21 Feb 2006 19:54:56 +0300, in sentex.lists.freebsd.hackers you wrote: > Good day! > I've obtained the following strang results with the em Ethernet interface >speeds on a 6.1-PRERELEASE: > Polling on: > UDP stream to FreeBSD: 327843.84 Kbit/sec, > TCP stream to FreeBSD: 524550.12 Kbit/sec. > Polling off: > UDP stream to FreeBSD: 740409.38 Kbit/sec, > TCP stream to FreeBSD: 794348.44 Kbit/sec. > > It is funny that TCP speed is greater than UDP. It can be related to the >hardware, not to the OS, because I've seen such behaviour on a linux-2.6. >But on linux-2.4 with the same hardware as for FreeBSD and with the same >source host I've got > UDP stream to Linux: 927891.44 Kbit/sec, > TCP stream to Linux: 850202.50 Kbit/sec. >The figures are higher and UDP rate > TCP rate. > I found that setting kern.polling.idle_poll=1 made a big difference to the forwarding rate. Also, on your tcp tests, try sysctl -w net.inet.tcp.inflight.enable=0 You might also adjust the amount of CPU allocated to userland when using polling. Without polling, I found I was able to livelock the middle box with just a dozen rules. I had FreeBSD boxA --FreeBSD-B---FreeBSD-C Where A = AMD 3800 with PCI-e BGE B = P4 3Ghz with PCI-X 82546EB Dual Port Gigabit C = AMD 3800 with PCI-e BGE using netrate and iperf from A to C going across B, I had to switch to polling so as not to live lock B using /usr/src/tools/tools/netrate/netblast. Without ipfw or pflog, it was not an issue. but load up ipfw or pf, B would become unresponsive in non polling mode. > The questions: can anyone explain the relation 'TCP rate > UDP rate'? Why >polling slows down the interface? And can FreeBSD stack can be tuned to >get the Linux performance? > > Kernel config deviations from GENERIC: >optionsSCHED_ULE get rid of that and use SCHED_4BSD ---Mike >optionsADAPTIVE_GIANT >device pf >device pflog >device pfsync > > System is running at hz = 1000. > > Thanks! Mike Tancsa, Sentex communications http://www.sentex.net Providing Internet Access since 1994 [EMAIL PROTECTED], (http://www.tancsa.com) ___ freebsd-hackers@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-hackers To unsubscribe, send any mail to "[EMAIL PROTECTED]"
Re: FreeBSD-6 and em interface speed
On Tue, 21 Feb 2006, FreeLSD wrote: options SCHED_ULE I'd start by going back to SCHED_4BSD and seeing how that affects things. ULE is an experimental scheduler that may produce inconsistent or undesirable results depending on workload. Robert N M Watson ___ freebsd-hackers@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-hackers To unsubscribe, send any mail to "[EMAIL PROTECTED]"
Re: FreeBSD-6 and em interface speed
FreeLSD wrote: > Good day! > I've obtained the following strang results with the em Ethernet interface > speeds on a 6.1-PRERELEASE: > Polling on: > UDP stream to FreeBSD: 327843.84 Kbit/sec, > TCP stream to FreeBSD: 524550.12 Kbit/sec. > Polling off: > UDP stream to FreeBSD: 740409.38 Kbit/sec, > TCP stream to FreeBSD: 794348.44 Kbit/sec. Probably due to the test tool you're using. Does the tool serialize the UDP stream (ie: wait for a response for each packet)? In many cases polling will slow down an individual stream slightly, while upping the total throughput (hundreds of streams). In addition if your CPU and bus is fast enough to handle the interrupt rate (well behaved NICs mitigate interrupts) then polling will slow things down in most cases. BTW, this should go on freebsd-net. Cheers, Nate ___ freebsd-hackers@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-hackers To unsubscribe, send any mail to "[EMAIL PROTECTED]"
FreeBSD-6 and em interface speed
Good day! I've obtained the following strang results with the em Ethernet interface speeds on a 6.1-PRERELEASE: Polling on: UDP stream to FreeBSD: 327843.84 Kbit/sec, TCP stream to FreeBSD: 524550.12 Kbit/sec. Polling off: UDP stream to FreeBSD: 740409.38 Kbit/sec, TCP stream to FreeBSD: 794348.44 Kbit/sec. It is funny that TCP speed is greater than UDP. It can be related to the hardware, not to the OS, because I've seen such behaviour on a linux-2.6. But on linux-2.4 with the same hardware as for FreeBSD and with the same source host I've got UDP stream to Linux: 927891.44 Kbit/sec, TCP stream to Linux: 850202.50 Kbit/sec. The figures are higher and UDP rate > TCP rate. The questions: can anyone explain the relation 'TCP rate > UDP rate'? Why polling slows down the interface? And can FreeBSD stack can be tuned to get the Linux performance? Kernel config deviations from GENERIC: options SCHED_ULE options ADAPTIVE_GIANT device pf device pflog device pfsync System is running at hz = 1000. Thanks! -- rea I often think it's a pity that Noah and his party didn't miss the boat. -Mark Twain ___ freebsd-hackers@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-hackers To unsubscribe, send any mail to "[EMAIL PROTECTED]"