>Andrew Morton <[email protected]> writes:
>>
>> Doing the same thing on 2.6.26-rc5-mm3, msgctl08 also runs to
>> completion, in 20.9 seconds. So
>>
>> - it got slower
>
>That is because it scales itself to the number of available msg queues.
>So with Nadia's patch there are more and it runs slower.
>
>In fact it seems to start one process per message queue, so perhaps it's
>just running out of processes or something. Ok it should not segfault.
>
>BTW a great way to debug slab corruptions with LTP faster is to run with
>a slab thrasher stress module like http://firstfloor.org/~andi/crasher-26.diff
>
>-Andi
any reason why only suse has this, but not mainline ?
i came across that module in suse kernel just some days ago and asked novell ( https://bugzilla.novell.com/show_bug.cgi?id=396132 ) , but they don`t have any objections.
chris mason didn`t reply on direct request....
so, if it`s useful, who is reponsible for pushing it upstream ?
______________________________________________________________
Jeden Monat 1 hochkar?tiger maxdome-Blockbuster GRATIS!
Exklusiv f?r alle WEB.DE Nutzer. http://www.blockbuster.web.de
>
> so, if it`s useful, who is reponsible for pushing it upstream ?
Nobody is. That is why it isn't. Feel free to do the work.
It would need some cleanup before submission. e.g. the ooops/panic etc. options
are fairly useless and should be removed and there needs to be more documentation.
-Andi