Date: Tue, 8 Aug 2017 09:04:39 +0200 From: Ben RUBSON <ben.rubson@gmail.com> To: FreeBSD Net <freebsd-net@freebsd.org> Subject: Re: mlx4en, timer irq @100%... Message-ID: <4C91C6E5-0725-42E7-9813-1F3ACF3DDD6E@gmail.com> In-Reply-To: <e6f9df1c-8b55-8a3b-9f44-e67c26561543@selasky.org> References: <BF3A3E47-A726-49FB-B83F-666EFC5C0FF1@gmail.com> <72b9de84-5572-3737-b274-34d2c5cdf634@selasky.org> <91DCB96E-4C08-44C5-94E7-E7C686DEFE5F@gmail.com> <c3fdf0bb-833d-915f-c246-9459819cd825@selasky.org> <4DF74CB8-23D2-4CCF-B699-5B86DAEA65E5@gmail.com> <40602CEA-D417-4E5B-8C68-916958D49A0B@gmail.com> <9c306f10-7c05-d28d-e551-a930603aaafa@selasky.org> <896dd782-cb2c-0259-65d1-b00daae452de@FreeBSD.org> <0DB9F6FF-8BC9-48F5-B359-AC1905B9EB06@gmail.com> <7f14c95d-1ef8-bf82-c469-e6566c3aba66@selasky.org> <76A5EE7E-1D2E-46B4-86F1-F219C3DCE6EA@gmail.com> <e6f9df1c-8b55-8a3b-9f44-e67c26561543@selasky.org>
next in thread | previous in thread | raw e-mail | index | archive | help
> On 08 Aug 2017, at 08:51, Hans Petter Selasky <hps@selasky.org> wrote: >=20 > On 08/08/17 01:52, Ben RUBSON wrote: >>> On 07 Aug 2017, at 19:57, Hans Petter Selasky <hps@selasky.org> = wrote: >>>=20 >>> On 08/07/17 19:19, Ben RUBSON wrote: >>>>> On 07 Aug 2017, at 18:19, Matt Joras <mjoras@FreeBSD.org> wrote: >>>>>=20 >>>>> On 08/07/2017 09:11, Hans Petter Selasky wrote: >>>>>> Hi, >>>>>>=20 >>>>>> Try to enter "kgdb" and run: >>>>>>=20 >>>>>> thread apply all bt >>>>>>=20 >>>>>> Look for the callout function in question. >>>>>>=20 >>>>>> --HPS >>>>>>=20 >>>>> If you don't have a way to attach kgdb handy you could also break = into >>>>> ddb(4) and run "alltrace". Though gdb would be more useful for an >>>>> ongoing session if we need more than the backtrace since you could >>>>> switch to that thread and investigate it directly. >>>>>=20 >>>> Hi Hans & Matt, >>>> Thank you for your answers, glad to hear from you :) >>>> So here is the full kgdb(thread apply all bt) command log : >>>> https://benrubson.github.io/kgdb.log >>>> We found the faulty thread : >>>> # procstat -ak | grep "swi4.*tcp" >>>> 12 100029 intr swi4: clock (0) tcp_tw_2msl_scan = pfslowtimo softclock_call_cc softclock intr_event_execute_handlers = ithread_loop fork_exit fork_trampoline >>>> # kgdb >>>> (...) >>>> Thread 747 (Thread 100029): >>>> #0 sched_switch (td=3D0xfffff8000f337500, = newtd=3D0xfffff8010e144000, flags=3D<value optimized out>) at = /usr/src/sys/kern/sched_ule.c:1973 >>>> #1 0xfffffe1000f92d80 in ?? () >>>> #2 0xfffffe0f8f74b6e0 in ?? () >>>> #3 0xffffffff810bd274 in handleevents (now=3D<value optimized = out>, fake=3DError accessing memory address 0xffffffffffffffcc: Bad = address. >>>> ) at /usr/src/sys/kern/kern_clocksource.c:223 >>>> Previous frame inner to this frame (corrupt stack?) >>>> (...) >>>> Of course let me know if you need further info. >>>=20 >>> Can you try to dump "td": >>>=20 >>> set print pretty on >>> thread 747 >>> frame 0 >>> print *td >>>=20 >>> It might give some more clues. >> Here it is : >> https://benrubson.github.io/td.log >> Thx ! >=20 > Can you show output from: >=20 > vmstat -z >=20 > Can you from kgdb do: >=20 > print V_twq_2msl >=20 > And follow the next link field and see where it goes? Here is vmstat -z : https://benrubson.github.io/vmstatz.log "print V_twq_2msl" returns the following : No symbol "V_twq_2msl" in current context. Even if I rerun this before (as I exited kgdb) : set print pretty on thread 747 frame 0 Ben=
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?4C91C6E5-0725-42E7-9813-1F3ACF3DDD6E>