1.2.45 Linux Scheduler
--------- Received message begins Here ---------
Quoted 7 lines
In the Linux scheduler they use a circular queue implementation with round robin. What is the advantage of this over just using a normal queue with a back and front. Also does anyone know what a test plan for such a design would even begin to look like. This is a project for a proposal going around in my neighborhood and I am wondering why in the world someone would want to modify the Linux scheduler to this extent.
This is not an authoritive answer but:
It's simple, and fast. Locks only needed when adding/removing entries.
It is also nearly optimum when the queue only has 5 (or so) number of entries. It will not be optimum if there are 32/64 CPUs with 120 or more runnable entries. There are other schedulers available that may do a better job for that situation.
-------------------------------------------------------------------------
Jesse I Pollard, II
Email: [email protected]
Any opinions expressed are solely my own.
-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to [email protected]
Please read the FAQ at http://www.tux.org/lkml/
----- Original Message -----
From: Jesse Pollard <[email protected]>
To: <[email protected]>; <[email protected]>
Sent: Wednesday, November 01, 2000 2:27 PM
Subject: Re: 1.2.45 Linux Scheduler
Quoted 4 lines
--------- Received message begins Here ---------
Quoted 2 lines
In the Linux scheduler they use a circular queue implementation with
round
Quoted 1 line
Quoted 1 line
robin. What is the advantage of this over just using a normal queue with
a
Quoted 2 lines
Quoted 2 lines
back and front. Also does anyone know what a test plan for such a design would even begin to look like. This is a project for a proposal going
around
Quoted 1 line
Quoted 1 line
in my neighborhood and I am wondering why in the world someone would
want to
Quoted 11 lines
Quoted 1 line
modify the Linux scheduler to this extent.
This is not an authoritive answer but:
It's simple, and fast. Locks only needed when adding/removing entries.
It is also nearly optimum when the queue only has 5 (or so) number of entries. It will not be optimum if there are 32/64 CPUs with 120 or more runnable entries. There are other schedulers available that may do a better job for that situation.
I don't know who runs Linux w/ 32/64 CPUs and w/ 120 active procs but if someone on earth exist ... :
http://www.mycio.com/davidel/lk/adapt-sched-v3.0-2.2.14.gz
- Davide
-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to [email protected]
Please read the FAQ at http://www.tux.org/lkml/