Date: Sun, 8 Feb 2015 08:17:55 -0800 From: Adrian Chadd <adrian@freebsd.org> To: Wolfgang Zenker <wolfgang@lyxys.ka.sub.org> Cc: "freebsd-mips@freebsd.org" <freebsd-mips@freebsd.org> Subject: Re: IPv6 throughput only half of IPv4 on ERL Message-ID: <CAJ-VmoncgB__VtVryu67PeLU8-t18K41NdbJgvtKwDWvtqKbBA@mail.gmail.com> In-Reply-To: <20150208130034.GA80972@lyxys.ka.sub.org> References: <20150208130034.GA80972@lyxys.ka.sub.org>
next in thread | previous in thread | raw e-mail | index | archive | help
everything's bigger in ipv6? Well, try kldload hwpmc and see if pmcstat works for you. I haven't tried it on the Octeon hardware. That'll be useful for chasing down why it's chewing CPU. -adrian On 8 February 2015 at 05:00, Wolfgang Zenker <wolfgang@lyxys.ka.sub.org> wrote: > Hi, > > I just started to experiment with FreeBSD MIPS, using an Edge Router Lite > as testmachine, running a recent 10.1-STABLE. > > To test network throughput, I enabled the discard port in inetd and transfered > a large file there, via both IPv4 and IPv6. > > Results: > $ dd if=vc.tar bs=1m|nc -4 pomona.lyx 9 > 552+1 records in > 552+1 records out > 579002368 bytes transferred in 21.193134 secs (27320281 bytes/sec) > $ dd if=vc.tar bs=1m|nc -6 pomona.lyx 9 > 552+1 records in > 552+1 records out > 579002368 bytes transferred in 38.638252 secs (14985211 bytes/sec) > > Testing the same against an Atom-based machine on the same switch > took 8.725300 secs (v4) and 10.364100 secs (v6), so the difference > between both protocol stacks is much smaller on the Atom target. > > Any ideas what is the cause of this huge difference on the MIPS > platform? Just curious ... > > Wolfgang > _______________________________________________ > freebsd-mips@freebsd.org mailing list > http://lists.freebsd.org/mailman/listinfo/freebsd-mips > To unsubscribe, send any mail to "freebsd-mips-unsubscribe@freebsd.org"
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?CAJ-VmoncgB__VtVryu67PeLU8-t18K41NdbJgvtKwDWvtqKbBA>