Re: Calling sys_sysinfo from sched.c

[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

 



Quoting Arjan van de Ven <arjan@xxxxxxxxxxxxx>:

> On Sat, 2005-04-16 at 17:03 +0100, A.M. Fradley wrote:
> > I want to use larger time slices when the ram starts to get full to try to
> > reduce the time spent swapping the pages in and out.
> 
> is that very different to the swap token technique currently used?
> 
> >
> >   I added the following to
> > the scheduler in linux 2.6.9 and I can't figure out
> > why it's not working.  There were two different sysinfo() functions I found
> and
> > this is what I think is confusing me. 
> 
> you really shouldn't be calling system calls from within the kernel.
> What information do you actually need?
> 
> 
> 
> --
> Kernelnewbies: Help each other learn about the Linux kernel.
> Archive:       http://mail.nl.linux.org/kernelnewbies/
> FAQ:           http://kernelnewbies.org/faq/
> 


I'm not sure if it's much different to the swap token thing.  What area should
I
look in for that if I want to get data from there to the scheduler?  (I mean
which files in the kernel and what headings for documentation might be.)  The
info I need is the total memory available for a particular computer.  I'm not
using a networked version of linux, I'm trying to optimise the processing time
and reduce the time spent swapping pages in and out.  My assignment is to
attempt to do that from within the scheduler.  I can get the scheduler to refer
to other parts of the kernel and stuff like that but I've been advised to do as
much as possible from the scheduler to prevent the scope of the project from
getting out of hand.  However the info on memory available and memory used that
can be found using sysinfo seemed so usefull that I wanted to try to get at that
from the scheduler.  My plan was that as the ram gets full (I chose 90% or above
to start with) then the page swapping must have started.  Any info I can get to
base the size of the time slices and possible other scheduler tunables on, I
want to be able to access from the scheduler.  In other words I want the
schduler to be able to tune itself i some circumstances.  Even if it's a bad
idea I think this is what my assignment involves.  I have to improve the
schedulers performance for a single computer rather than a net work but I
should do more than just configure the tunables for my own computer because
that wouldn't make much of a project.  As for the sys_sysinfo thing I just have
no idea why it wouldn't work from the scheduler even if it's all being
recognised.

Anything you can suggest would be appreciated.


----------------------------------------------------------------
This message was sent using IMP, the Internet Messaging Program.

--
Kernelnewbies: Help each other learn about the Linux kernel.
Archive:       http://mail.nl.linux.org/kernelnewbies/
FAQ:           http://kernelnewbies.org/faq/


[Index of Archives]     [Newbies FAQ]     [Linux Kernel Mentors]     [Linux Kernel Development]     [IETF Annouce]     [Git]     [Networking]     [Security]     [Bugtraq]     [Yosemite]     [MIPS Linux]     [ARM Linux]     [Linux RAID]     [Linux SCSI]     [Linux ACPI]
  Powered by Linux