Re: wait_on_irq, CPU1

Manfred Spraul (manfreds@colorfullife.com)
Mon, 27 Dec 1999 18:32:01 +0100


Oleg Drokin wrote:
>
> wait_on_irq, CPU1:
> irq: 0 [0 0]
> bh: 1 [1 0]

CPU0 was executing a bottom half handler.

> [<c010b5dd>] [<c01a4005>] [<c01ac015>] [<c01abf3f>] [<c01ae293>] [<c01ae5f8>] [<c01ab7e7>]
> All over screen. Server was dead, except sysrq-b works.
> I decoded above code trace:
> Trace: c010b5dd <__global_cli+b9/130>

CPU1 tried to acquire the global-cli lock.

> Trace: c01a4005 <rs_write+141/1f4>
> Trace: c01ac015 <ppp_tty_push+c5/180>
> Trace: c01abf3f <ppp_async_send+67/78>
> Trace: c01ae293 <ppp_send_frame+267/29c>
> Trace: c01ae5f8 <ppp_send_ctrl+e0/11c>
> Trace: c01ab7e7 <ppp_tty_write+103/110>
>

Could you post a few more details about your server? ie which serial
card are you using, how many serial ports, how many interrupts for
serial ports, SCSI or IDE, which network card, any special kernel
drivers?

--
	Manfred

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