MESSAGE
| DATE | 2015-03-11 |
| FROM | Ruben Safir
|
| SUBJECT | Re: [LIU Comp Sci] Operating Systems class submition
|
From owner-learn-outgoing-at-mrbrklyn.com Wed Mar 11 18:18:37 2015
Return-Path:
X-Original-To: archive-at-mrbrklyn.com
Delivered-To: archive-at-mrbrklyn.com
Received: by mrbrklyn.com (Postfix)
id 258C11612E0; Wed, 11 Mar 2015 18:18:37 -0400 (EDT)
Delivered-To: learn-outgoing-at-mrbrklyn.com
Received: by mrbrklyn.com (Postfix, from userid 28)
id 135601612ED; Wed, 11 Mar 2015 18:18:37 -0400 (EDT)
Delivered-To: learn-at-nylxs.com
Received: from mailbackend.panix.com (mailbackend.panix.com [166.84.1.89])
by mrbrklyn.com (Postfix) with ESMTP id 700021612E0
for ; Wed, 11 Mar 2015 18:18:13 -0400 (EDT)
Received: from panix2.panix.com (panix2.panix.com [166.84.1.2])
by mailbackend.panix.com (Postfix) with ESMTP id 8CA6A10EBE;
Wed, 11 Mar 2015 18:18:12 -0400 (EDT)
Received: by panix2.panix.com (Postfix, from userid 20529)
id 8D2E333CA2; Wed, 11 Mar 2015 18:18:12 -0400 (EDT)
Date: Wed, 11 Mar 2015 18:18:12 -0400
From: Ruben Safir
To: Tehreem , keisha.sylvester-at-my.liu.edu,
"rshanashurriah-at-gmail.com" ,
justinml-at-gmail.com, learn-at-nylxs.com
Subject: Re: [LIU Comp Sci] Operating Systems class submition
Message-ID: <20150311221812.GA20667-at-panix.com>
References: <2B450783-936B-4340-AF4E-CFC0A38B8037-at-gmail.com>
<54FBC32E.3070609-at-panix.com>
MIME-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Content-Disposition: inline
In-Reply-To: <54FBC32E.3070609-at-panix.com>
User-Agent: Mutt/1.5.23 (2014-03-12)
Sender: owner-learn-at-mrbrklyn.com
Precedence: bulk
Reply-To: learn-at-mrbrklyn.com
I'm going to work on this over the remaioned of the week and I wantto
have a rough draft for everyone by the end of the weekend. I want to
make this a Journal article for the NYLXS Journal in March, and i think
I can knock this out. If you wish to help, email or call me
718-715-1771
Ruben
On Sat, Mar 07, 2015 at 10:34:06PM -0500, Ruben Safir wrote:
> On 03/02/2015 04:49 PM, Tehreem wrote:
> > This is what Keisha, Maneesh and I came up with. It???s just a draft, you guys can edit it further if you like but we???re kind of tight on schedule since we have to submit scope and questions of interest with the topic of our paper.
> >
>
>
> Yeah, this is completely not going to work. If you want to just drop
> something in his lap and hope he doesn't notice, then go ahead with this
> but this is NOT in the correct format. He is ASKING FOR ORIGINAL
> RESEARCH. What you need to do is write a hypothesis that you chose to
> QUESTION and then the plan you have in order to prove the hypothesis.
>
> CS-635 Operating Systems
> Group Project
>
> Topic: Process Scheduling
>
>
> Team Composition:
> Justin
> Keisha Sylvester
> Maneesh Kongara
> Rshana Suhrriah
> Ruben Saffir
> Tehreem Mirza
>
>
> Background: From the beginning of operating system design, how to
> schedule tasks, processes and jobs has been at the very front of the
> debates and designs of operating systems. From the earliest batch
> systems, all the way to today's multitasking cloud and cluster
> environments, just how to schedule CPU time and tasks has sparks
> controversy and been at the forefront of Operating Systems Research.
>
> The standard Linux kernel today uses what is called the Completely Fair
> Scheduler, an algorithm spearheaded by Mike Galbraith and which was
> included into the Linux Kernel under the direction of Linus Tovalds.
> But this has not been without controversy.
>
> While certain aspects of scheduling have to take place on the Kernel
> level, after all timers need to be set and interrupts handled, how much
> should be implemented in kernel space has remained a question. One
> thing is clear, when it comes to Operating System Scheduling, not all
> users need the same kind of scheduling and how the operating system
> schedules largely defined the operating systems personality.
>
> In 2009, developers with focus on embedded systems, particularly
> embedded systems within industry and robots, wanted to have a Linux
> Kernel with real time capability. The advantages of having a completely
> free implementation of a Real Time Operating system would be a huge boon
> for these developers, particularly since they are often short on cash
> but long intellectual firepower. Out of this efforts came -rt Patchset
> Scheduling Algorithm which was reviewed in the Linux Journal by Ankita
> Garg in August of 2009.1
>
>
> Le Trung Thang, on April 24th, 2012 in Embedded Magazine did a review
> and comparision between the normal preemptive operating system design of
> Linux which is "rescheduled" with the RT patch, as compared to some of
> the more standard RTOS and outlines the problems that need to be
> overcome. 2 Thang concludes:
>
> "Conclusion: Viewed in this context, the typical RTOS scheduler is just
> a special case of real time Linux scheduler, or in other words, the RTOS
> scheduler is the real time Linux scheduler running with the Round Robin
> policy. (Some RTOSes allow configuration of the scheduler to run in a
> non-preemption mode. However this mode is seldom used.)"
>
>
> Project and Analysis: Our purpose is to peer review the work published
> by Thang and to find support or a lack of support for his position based
> on both source code evaluation and compilation trials. After thi, we
> will look at possibly newer research on real time scheduling problems
> and see how new ideas have succeeded or failed in wild.
>
>
>
> 1:http://www.linuxjournal.com/magazine/real-time-linux-kernel-scheduler
> 2:
> http://www.embedded.com/design/operating-systems/4371651/Comparing-the-real-time-scheduling-policies-of-the-Linux-kernel-and-an-RTOS-
>
|
|
