Re: Interesting analysis of linux kernel threading by IBM

From: Davide Libenzi (dlibenzi@maticad.it)
Date: Sun Jan 23 2000 - 07:48:52 EST


On Fri, 21 Jan 2000, Horst von Brand wrote:
> > But the fact is that normally 2 tasks switches at a very lower factor then
> > 300.
>
> Why? That depends mostly on the tasks, and if the tasks are the same, this
> should not change very much (unless the machine is swamped with interrupts,
> and then your problem is another one).
If You have a great number of processes running on a system, some of them
probably are processing ( feeding the runqueue ) while others, if You exclude
tasks that do nothing but "for(;;)", are stressing devices plugged on Your
system ( disks, netcards, serials, etc ..).
These devices are highly susceptible to stress, and it defends Yourself firing
interrupts.
Now highly is the number of processes running on Your system higher is the
number of tasks stressing devices, and this stress reflect an high number of
interrupts == switches.

Davide.

-- 
All this stuff is IMVHO

- 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/



This archive was generated by hypermail 2b29 : Sun Jan 23 2000 - 21:00:29 EST