Re: ipc,sem: sysv semaphore scalability

[Emmanuel Benisty]

On Mon, Mar 25, 2013 at 10:53 PM, Rik van Riel <riel@xxxxxxxxxxx> wrote:
> On 03/25/2013 11:20 AM, Emmanuel Benisty wrote:
>>
>> On Mon, Mar 25, 2013 at 9:03 PM, Rik van Riel <riel@xxxxxxxxxxx> wrote:
>>>>>
>>>>> With the first four patches only, I got some X server freeze (just
>>>>> tried once).
>>>>
>>>>
>>>>
>>>> Could you try booting with panic=1 so the kernel panics on the first
>>>> oops?
>>>
>>>
>>>
>>> Sorry that should be "oops=panic"
>>>
>>>
>>>> Maybe that way (if we are lucky) we will be able to capture the first
>>>> oops, and maybe get an idea of what causes the problem.
>>
>>
>> Sorry Rik, I get all kind of weird behaviors (wireless dies, compiling
>> gets stuck and is impossible to kill, can't kill X) with the 4
>> patches+oops=panic but no trace. Here after is 7+1 patches with
>> oops=panic boot: http://i.imgur.com/1jep1qx.jpg
>
>
> This may be a stupid question, but you re-compile and re-install
> the kernel modules every time you changed the kernel?
>
> The behaviour you report with just the first four patches is so
> random, it sounds almost like a mismatched data structure between
> compiles...

Yes it's OK. I even started from scratch just in case but I'm still
getting the same weird things. Everything works just fine with a build
from Linus' tree which I normally use. I'll try the patches on another
machine tomorrow.
--
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/