Date: Fri, 30 Oct 2015 04:20:49 +0700 From: Eugene Grosbein <eugen@grosbein.net> To: Adrian Chadd <adrian.chadd@gmail.com> Cc: "freebsd-mips@freebsd.org" <freebsd-mips@freebsd.org> Subject: Re: arge1 on TL WDR3600 Message-ID: <56328DB1.9010105@grosbein.net> In-Reply-To: <56328C54.1050709@grosbein.net> References: <562CBEC3.8030308@rdtc.ru> <CAJ-Vmok__9mD8OaFnU-sfVfr=xMRMW6-nfDUHScT_LNm6Ry2iA@mail.gmail.com> <562E3027.4020806@grosbein.net> <CAJ-VmonRt6OVOQDGLZBx-4OxbGgzcetuKtBf3eB-6yn3m-EEsQ@mail.gmail.com> <562F75E2.9000505@grosbein.net> <CAJ-VmomocPQ=%2BjKYt8bsLHEWjT1vz=37U_yNB3YMsmxz__5qVw@mail.gmail.com> <CAJ-Vmo=BRP-vyg5=7cyA9v9c_cDjo6Ozv0SLmNj3RZGCKjLYAg@mail.gmail.com> <CAJ-VmokD2vHZ0%2BzO655_csRQw==JUDbaBCDMa%2BU7b1aRv=4BJQ@mail.gmail.com> <5630E844.2080807@grosbein.net> <CAJ-VmonH%2BVfT1zUyAq=fXv6PbwQuiw1_k4CRw1yMgfm6CRaAwA@mail.gmail.com> <CAJ-VmomjWOccaaVyPrGBrf7ACL8KGGOuuFo1QWw02%2BM9smVGFA@mail.gmail.com> <56321ED9.4050602@grosbein.net> <CAJ-Vmom1Tagn6WL-qfNZ7xqPznrLygB6JzMMJdyLU=ROybnEGA@mail.gmail.com> <56323496.609@grosbein.net> <CAJ-Vmond--pm8-rjn55qD8thjneaNiL0eV89Opd1u8p%2BK3BF3w@mail.gmail.com> <56325769.8070202@grosbein.net> <CAJ-Vmo=iD1TdWdPU91TdKL8oW42C_fXUODeigTj55_xJF86AvA@mail.gmail.com> <56328C54.1050709@grosbein.net>
next in thread | previous in thread | raw e-mail | index | archive | help
On 30.10.2015 04:15, Eugene Grosbein wrote: > I do not think that hardware is buggy because several versions of "official" > TP-Link firmware work just fine with this particular device and earlier > versions of FreeBSD 11 also work without interrupt storms. > > In fact, I've applied dichotomy and found guilty commit. It took 12 iterations > but here is it: kernel built using head at r289897 runs my test without a storm > (but forwarding speed is pretty bad) and kernel built with r289898 or later > revisions has interrupt storm. > > This is the change: > https://svnweb.freebsd.org/base/head/sys/mips/atheros/if_arge.c?r1=289744&r2=289898&view=patch > > My device has hw.model: Atheros AR9344 rev 2 Also, for slow but stable (pre-289898) revisions stats show that all tx packets are unaligned: dev.arge.0.tx_pkts_unaligned: 1189534 dev.arge.0.tx_pkts_aligned: 0 And, as I've already wrote, later revisions show opposite, like: > dev.arge.0.tx_pkts_unaligned: 0 > dev.arge.0.tx_pkts_aligned: 345184 Hope this helps.
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?56328DB1.9010105>