Re: 2.6.{30,31} x86_64 ahci problem - irq 23: nobody cared

[David Daney <ddaney@caviumnetworks.com>]

Alexander Huemer wrote:
> David Daney wrote:
>> Alexander Huemer wrote:
>>> the problem appears under heavy system load and slows down the system to
>>> unusable speed.
>>> kernels before .30 were not affected.
>>> irqpoll does not change behavior.
>>>
>>> error message from .31:
>>>
>>>     [157152.418524] irq 23: nobody cared (try booting with the "irqpoll"
>>>     option)
>>>     [157152.418530] Pid: 1359, comm: cc1plus Tainted: G        W 
>> Right here is the problem  ->         ^^^^^^^^
>>
>> Haven't you read all the threads about the evil of C++.  This is just
>> one more example of the why we shouldn't be using it. :-)
>>
>> David Daney
>>
[...]
> thanks for your quick answer, david.
> so, this isn't a kernel issue at all ?
> imho a user process shouldn't be able to cause such a situation.
> what can i do against that phenomenon ?
> 

Just for avoidance of doubt, it was an attempt at a joke.

You are of course correct.  It looks like a real bug.  User-space 
shouldn't matter.

David Daney