Re: NOHZ: local_softirq_pending 08

[Francois Romieu]

Thomas Gleixner <tglx@xxxxxxxxxxxxx> :
[
> So it goes idle with NET_RX softirq pending. That really should not
> happen. I fear you need to fire up the tracer :)

Can you elaborate what "should not happen" mean ? AFAIU nothing prevents
softirq to be interrupted after NET_RX processing and thus NET_RX_SOFTIRQ
to be pending again before tick_nohz_irq_exit() runs.

Dave can you:
- specify if there much traffic when the message appears
- send /proc/interrupts + ethtool -S ethX

Thanks.

-- 
Ueimor
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/