Date: Tue, 17 Sep 2013 12:28:41 -0600 From: Ian Lepore <ian@FreeBSD.org> To: Harald Schmalzbauer <h.schmalzbauer@omnilan.de> Cc: lev@FreeBSD.org, FreeBSD Stable <freebsd-stable@FreeBSD.org>, freebsd-usb@FreeBSD.org, Hans Petter Selasky <hans.petter.selasky@bitfrost.no> Subject: Re: umcs (4-Port-USB-serial) triggering way too much ehci IRQs Message-ID: <1379442521.1197.50.camel@revolution.hippie.lan> In-Reply-To: <52389248.7080109@omnilan.de> References: <52372DBA.6020703@omnilan.de> <zarafa.5237e529.2bc6.08fde6eb34c27a87@mail.lockless.no> <875323075.20130917124437@serebryakov.spb.ru> <523816E1.10603@omnilan.de> <1857258551.20130917124737@serebryakov.spb.ru> <5238198C.3070604@bitfrost.no> <52381BAC.5010801@omnilan.de> <52381FCA.5030509@bitfrost.no> <5238775C.8010000@omnilan.de> <1379434567.1197.48.camel@revolution.hippie.lan> <52389248.7080109@omnilan.de>
next in thread | previous in thread | raw e-mail | index | archive | help
On Tue, 2013-09-17 at 19:32 +0200, Harald Schmalzbauer wrote: > Bez=FCglich Ian Lepore's Nachricht vom 17.09.2013 18:16 (localtime): > > On Tue, 2013-09-17 at 17:38 +0200, Harald Schmalzbauer wrote: > >> ... > >>> Try this patch and see what happens: > >>> > >>> =3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D= =3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D= =3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D > >>> --- umcs.c (revision 255492) > >>> +++ umcs.c (local) > >>> @@ -230,6 +230,7 @@ > >>> .bufsize =3D 0, /* use wMaxPacketSize */ > >>> .callback =3D &umcs7840_intr_callback, > >>> .if_index =3D 0, > >>> + .interval =3D 20, /* ms */ > >>> }, > >>> }; > >>> > >>> > >>> BTW: I see that the umcs driver shouldn't do synchronous control > >>> transfers from the USB interrupt transfer callback. This should be > >>> postponed into some worker thread, for example the USB explore thre= ad. > >>> See USB audio driver for an example. > >>> > >>> --HPS > >> I tried your patch and it works as expected: IRQs decreased to ~64/s > >> when idle/disconnected. > >> > >> One interesting thing I never measured before: > >> Console connection with 115k2 via umcs and 'while ( 2>1 ) echo "---.= .." > >> end' results in 8000 irqs/s :-( But that's also true for the prolifi= c > >> (uplcom). The latter just goes down to 0.0 irqs/s when idle. > >> > >> Doing the same with uart0 results in 1444irqs/s. > >> Is it by design/unavoidable that transfering the same via USB multip= lies > >> by factor 5-6? > >> > >> Thanks, > >> > >> -Harry > >> > > I don't know about that chipset, but with the FTDI chips it does xfer= s > > in 64 byte chunks and high speed bulk data results in an astronomical > > number of interrupts (and if you go fast enough, lost data). I have >=20 > According to ASIX product brief, MCS7840 has 512 byte buffer. Pretty > much for an UART I think, which should make 115k2 baud connections wit= h > less than 30 transfers/s work, or am I missing something? That's the internal buffer, it still does usb transfers in smaller chunks. Some ftdi chips have 4k onboard buffers but do 64-byte usb transfers. -- Ian
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?1379442521.1197.50.camel>