twe0 interrupt storm
FreeBSD
freebsd at n9.ru
Fri Jun 13 00:47:52 UTC 2008
Hi,
Thank you for fast reply.
I'm sorry, on old server controller was installed on irq20, on new on irq21.
The hardware is same on both servers, I use another slot, and error
persist on both servers.
So now:
[root at gans /home/sg]# vmstat -i
interrupt total rate
irq1: atkbd0 3 0
irq16: ohci0 1 0
irq17: ohci1 ohci3 1 0
irq18: ohci2 ohci4 1 0
irq20: twe0 2392173 61
cpu0: timer 77623998 1999
cpu1: timer 77623962 1999
Total 157640139 4061
But after some time irq20 rate heavely increases to 100000+ and than
system hangs...
gstat shows disk usage avg. 20%.
Don't know what to do, because I have used different kernels, and
changed controller to new one.
Kind Regards
2008/6/13 adam radford <aradford at gmail.com>:
> On Thu, Jun 12, 2008 at 6:43 AM, FreeBSD <freebsd at n9.ru> wrote:
>> Jun 11 21:38:00 gans kernel: twe0: <3ware Storage Controller. Driver
>> version 1.50.01.002> port 0xe800-0xe80f mem
>> 0xfebffc00-0xfebffc0f,0xfe000000-0xfe7fffff irq 20 at device 2.0
>> on pci3
>
> That's strange, the driver thinks it's hooked to irq 20, see above.
>
>> [root at gans /home/sg]# vmstat -i
> snip
>> irq21: twe0 38629583391 101980
> snip
>> Total 40144758213 105980
>>
>
> But here we are irq 21?
>
> -Adam
>
>
>
More information about the freebsd-hardware
mailing list