Date: Wed, 2 May 2018 06:57:14 -0700 From: Eitan Adler <lists@eitanadler.com> To: Hans Petter Selasky <hps@selasky.org> Cc: usb@freebsd.org Subject: Re: IRQ storm on xhci0 Message-ID: <CAF6rxgm29tJqN=_rkRSV=CcOQV18ySExioQhuWG-%2B-w%2Bh1Socg@mail.gmail.com> In-Reply-To: <a2cadeb3-973a-cca6-3909-eedfc948c120@selasky.org> References: <CAF6rxgk4u%2B2SrrOO18ceAJOWp1wMdGxAHfGVE40Y0t-=bzJFnQ@mail.gmail.com> <CAF6rxgmdAVEvwC0cgaXE_Oz1Z84TjMPfKJ3MYPYm5KQbKH7E=Q@mail.gmail.com> <a2cadeb3-973a-cca6-3909-eedfc948c120@selasky.org>
next in thread | previous in thread | raw e-mail | index | archive | help
On 2 May 2018 at 00:22, Hans Petter Selasky <hps@selasky.org> wrote: > On 05/02/18 06:22, Eitan Adler wrote: >> >> On 1 May 2018 at 20:53, Eitan Adler <lists@eitanadler.com> wrote: >>> >>> Hi all, >>> >>> I am noticing consistently high IRQ rates on xhci0 >>> >>> example from vmstat -i right now: >>> irq259: xhci0 2222153 1876 >>> >>> and this is not the highest I've seen. >>> >>> My understanding is that a rate of 1876/s is insane for USB devices. >>> Any suggestions of what I can do to debug? >>> >>> Things I've tried: >>> - disabling MSI interrupts >>> - disabling MSI-X interrupts >>> - powering off all usb devices using usbconfig >>> - unplugging all USB devices >>> >>> One thing of note: >>> My mobo has a broken USB connector resulting in one of the two front >>> USB-3 ports not working. I'm guessing this is related but I'd like >>> some confirmation and/or a way to bypass the issue in software. >> >> >> with insane debugging enabled: >> > > Try to see with usbdump if any traffic is passing on xhci0. Heh. should have added that to the list of things I did. There is no traffic. -- Eitan Adler
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?CAF6rxgm29tJqN=_rkRSV=CcOQV18ySExioQhuWG-%2B-w%2Bh1Socg>