[Fuego] [PATCH 9/9] pi_tests: add meaningful specs
Daniel Sangorrin
daniel.sangorrin at toshiba.co.jp
Fri Jan 12 08:25:33 UTC 2018
Hi Tim,
>
> Sorry this is a bug on my side. I will fix it soon.
>
Actually, I'm not sure. See below.
> -----Original Message-----
> From: fuego-bounces at lists.linuxfoundation.org [mailto:fuego-bounces at lists.linuxfoundation.org] On Behalf Of Daniel Sangorrin
> > Starting PI Stress Test
> > Number of thread groups: 20
> > Duration of test run: 60 seconds
> > Number of inversions per group: unlimited
> > Admin thread SCHED_FIFO priority 4
> > 20 groups of 3 threads will be created
> > High thread SCHED_FIFO priority 3
> > Med thread SCHED_FIFO priority 2
> > Low thread SCHED_FIFO priority 1
> > Current Inversions: 122740
> > WATCHDOG triggered: group 2 is deadlocked!
> > WATCHDOG triggered: group 3 is deadlocked!
> > WATCHDOG triggered: group 4 is deadlocked!
> > WATCHDOG triggered: group 5 is deadlocked!
> > WATCHDOG triggered: group 6 is deadlocked!
> > WATCHDOG triggered: group 7 is deadlocked!
> > WATCHDOG triggered: group 8 is deadlocked!
> > WATCHDOG triggered: group 9 is deadlocked!
> > WATCHDOG triggered: group 10 is deadlocked!
> > WATCHDOG triggered: group 11 is deadlocked!
> > WATCHDOG triggered: group 12 is deadlocked!
> > WATCHDOG triggered: group 13 is deadlocked!
> > WATCHDOG triggered: group 14 is deadlocked!
> > WATCHDOG triggered: group 15 is deadlocked!
> > WATCHDOG triggered: group 17 is deadlocked!
> > WATCHDOG triggered: group 19 is deadlocked!
> > reporter stopping due to watchdog event
> > Stopping test
> > Terminated
Threads being deadlocked is supposed to be a problem with the kernel in your board.
In test_processing there is already a log_compare to deal with "is deadlocked!"
messages. Did we found a bug? :O
> > ---------------------------------
> >
> > The testlog.txt file for a run from Fuego is:
> >
> > Starting PI Stress Test
> > Number of thread groups: 20
> > Duration of test run: 60 seconds
> > Number of inversions per group: unlimited
> > Admin thread SCHED_FIFO priority 4
> > 20 groups of 3 threads will be created
> > High thread SCHED_FIFO priority 3
> > Med thread SCHED_FIFO priority 2
> > Low thread SCHED_FIFO priority 1
> >
> > [1ACurrent Inversions: 42702
> > [1ACurrent Inversions: 62390
> > [1ACurrent Inversions: 82293
> > [1ACurrent Inversions: 103649
> >
> > In the console log, I see a signal from the Jenkins handling process (I think).
> >
> > I need to dig into this and see:
> > 1) is the failure expected for this board? - if not, it's a bug with the board or software
Not sure what board is but it is not expected. I tested this on an x86_64 PC only.
Now, i tested it on BBB but I am getting EPERM problems related to SCHED_FIFO and
I couldn't solve them with the usual /etc/security/limits.conf...
> > 2) why does Fuego not have the full program output?
This is really strange :O
Are you running it as a root user?
Thanks,
Daniel
> >
> > In any event - these have nothing to do with the spec additions per se.
> > But I need to track down if the stress test has uncovered some board bugs
> > or other Fuego bugs.
> >
> > The spec changes are approved, and I applied the patch.
> >
> > Thanks!
> > -- Tim
> >
>
>
>
>
>
> _______________________________________________
> Fuego mailing list
> Fuego at lists.linuxfoundation.org
> https://lists.linuxfoundation.org/mailman/listinfo/fuego
More information about the Fuego
mailing list