11.0 stuck on high network load
Slawa Olhovchenkov
slw at zxy.spb.ru
Sun Sep 18 16:43:04 UTC 2016
On Fri, Sep 16, 2016 at 12:11:55PM -0700, hiren panchasara wrote:
> + jch@
> On 09/16/16 at 10:03P, Slawa Olhovchenkov wrote:
> > On Fri, Sep 16, 2016 at 11:30:53AM -0700, hiren panchasara wrote:
> >
> > > On 09/16/16 at 09:18P, Slawa Olhovchenkov wrote:
> > > > On Thu, Sep 15, 2016 at 12:06:33PM +0300, Slawa Olhovchenkov wrote:
> > > >
> > > > > On Thu, Sep 15, 2016 at 11:59:38AM +0300, Konstantin Belousov wrote:
> > > > >
> > > > > > On Thu, Sep 15, 2016 at 12:35:04AM +0300, Slawa Olhovchenkov wrote:
> > > > > > > On Sun, Sep 04, 2016 at 06:46:12PM -0700, hiren panchasara wrote:
> > > > > > >
> > > > > > > > On 09/05/16 at 12:57P, Slawa Olhovchenkov wrote:
> > > > > > > > > I am try using 11.0 on Dual E5-2620 (no X2APIC).
> > > > > > > > > Under high network load and may be addtional conditional system go to
> > > > > > > > > unresponsible state -- no reaction to network and console (USB IPMI
> > > > > > > > > emulation). INVARIANTS give to high overhad. Is this exist some way to
> > > > > > > > > debug this?
> > > > > > > >
> > > > > > > > Can you panic it from console to get to db> to get backtrace and other
> > > > > > > > info when it goes unresponsive?
> > > > > > >
> > > > > > > ipmi console don't respond (chassis power diag don't react)
> > > > > > > login on sol console stuck on *tcp.
> > > > > >
> > > > > > Is 'login' you reference is the ipmi client state, or you mean login(1)
> > > > > > on the wedged host ?
> > > > >
> > > > > on the wedged host
> > > > >
> > > > > > If BMC stops responding simultaneously with the host, I would suspect
> > > > > > the hardware platform issues instead of a software problem. Do you have
> > > > > > dedicated LAN port for BMC ?
> > > > >
> > > > > Yes.
> > > > > But BMC emulate USB keyboard and this is may be lock inside USB
> > > > > system.
> > > > > "ipmi console don't respond" must be read as "ipmi console runnnig and
> > > > > attached but system don't react to keypress on this console".
> > > > > at the sime moment system respon to `enter` on ipmi sol console, but
> > > > > after enter `root` stuck in login in the '*tcp' state (I think this is
> > > > > NIS related).
> > > >
> > > > ~^B don't break to debuger.
> > > > But I can login to sol console.
> > >
> > > You can probably:
> > > debug.kdb.enter: set to enter the debugger
> > >
> > > or force a panic and get vmcore:
> > > debug.kdb.panic: set to panic the kernel
> >
> > I am reset this host.
> > PMC samples collected and decoded:
> >
> > @ CPU_CLK_UNHALTED_CORE [4653445 samples]
> >
> > 51.86% [2413083] lock_delay @ /boot/kernel.VSTREAM/kernel
> > 100.0% [2413083] __rw_wlock_hard
> > 100.0% [2413083] tcp_tw_2msl_scan
> > 99.99% [2412958] pfslowtimo
> > 100.0% [2412958] softclock_call_cc
> > 100.0% [2412958] softclock
> > 100.0% [2412958] intr_event_execute_handlers
> > 100.0% [2412958] ithread_loop
> > 100.0% [2412958] fork_exit
> > 00.01% [125] tcp_twstart
> > 100.0% [125] tcp_do_segment
> > 100.0% [125] tcp_input
> > 100.0% [125] ip_input
> > 100.0% [125] swi_net
> > 100.0% [125] intr_event_execute_handlers
> > 100.0% [125] ithread_loop
> > 100.0% [125] fork_exit
> >
> > 09.43% [438774] _rw_runlock_cookie @ /boot/kernel.VSTREAM/kernel
> > 100.0% [438774] tcp_tw_2msl_scan
> > 99.99% [438735] pfslowtimo
> > 100.0% [438735] softclock_call_cc
> > 100.0% [438735] softclock
> > 100.0% [438735] intr_event_execute_handlers
> > 100.0% [438735] ithread_loop
> > 100.0% [438735] fork_exit
> > 00.01% [39] tcp_twstart
> > 100.0% [39] tcp_do_segment
> > 100.0% [39] tcp_input
> > 100.0% [39] ip_input
> > 100.0% [39] swi_net
> > 100.0% [39] intr_event_execute_handlers
> > 100.0% [39] ithread_loop
> > 100.0% [39] fork_exit
> >
> > 08.57% [398970] __rw_wlock_hard @ /boot/kernel.VSTREAM/kernel
> > 100.0% [398970] tcp_tw_2msl_scan
> > 99.99% [398940] pfslowtimo
> > 100.0% [398940] softclock_call_cc
> > 100.0% [398940] softclock
> > 100.0% [398940] intr_event_execute_handlers
> > 100.0% [398940] ithread_loop
> > 100.0% [398940] fork_exit
> > 00.01% [30] tcp_twstart
> > 100.0% [30] tcp_do_segment
> > 100.0% [30] tcp_input
> > 100.0% [30] ip_input
> > 100.0% [30] swi_net
> > 100.0% [30] intr_event_execute_handlers
> > 100.0% [30] ithread_loop
> > 100.0% [30] fork_exit
> >
> > 05.79% [269224] __rw_try_rlock @ /boot/kernel.VSTREAM/kernel
> > 100.0% [269224] tcp_tw_2msl_scan
> > 99.99% [269203] pfslowtimo
> > 100.0% [269203] softclock_call_cc
> > 100.0% [269203] softclock
> > 100.0% [269203] intr_event_execute_handlers
> > 100.0% [269203] ithread_loop
> > 100.0% [269203] fork_exit
> > 00.01% [21] tcp_twstart
> > 100.0% [21] tcp_do_segment
> > 100.0% [21] tcp_input
> > 100.0% [21] ip_input
> > 100.0% [21] swi_net
> > 100.0% [21] intr_event_execute_handlers
> > 100.0% [21] ithread_loop
> > 100.0% [21] fork_exit
> >
> > 05.35% [249141] _rw_wlock_cookie @ /boot/kernel.VSTREAM/kernel
> > 99.76% [248543] tcp_tw_2msl_scan
> > 99.99% [248528] pfslowtimo
> > 100.0% [248528] softclock_call_cc
> > 100.0% [248528] softclock
> > 100.0% [248528] intr_event_execute_handlers
> > 100.0% [248528] ithread_loop
> > 100.0% [248528] fork_exit
> > 00.01% [15] tcp_twstart
> > 100.0% [15] tcp_do_segment
> > 100.0% [15] tcp_input
> > 100.0% [15] ip_input
> > 100.0% [15] swi_net
> > 100.0% [15] intr_event_execute_handlers
> > 100.0% [15] ithread_loop
> > 100.0% [15] fork_exit
> > 00.24% [598] pfslowtimo
> > 100.0% [598] softclock_call_cc
> > 100.0% [598] softclock
> > 100.0% [598] intr_event_execute_handlers
> > 100.0% [598] ithread_loop
> > 100.0% [598] fork_exit
> >
>
> As I suspected, this looks like a hang trying to lock V_tcbinfo.
>
> I'm ccing Julien here who worked on WLOCK -> RLOCK transition to improve
> performance for short-lived connections. I am not too sure if thats the
> problem but looks in similar area so he may be able to provide some
> insights.
I am point to tcp_tw_2msl_scan.
I am expect traveling by list V_twq_2msl.
But I am see only endless attempt to lock first element from this
list.
Is this correct?
More information about the freebsd-stable
mailing list