Browse Prior Art Database

Maximum Response Time Control

IP.com Disclosure Number: IPCOM000076045D
Original Publication Date: 1972-Jan-01
Included in the Prior Art Database: 2005-Feb-24
Document File: 2 page(s) / 50K

Publishing Venue

IBM

Related People

LaMaire, OR: AUTHOR [+3]

Abstract

An expanded table driven task scheduling algorithm is provided, which allows for a change in priority for a given user if a predefined time limit is exceeded. This permits a task which is given a relatively low priority under normal loading conditions to be assured of service during short duration peak conditions.

This text was extracted from a PDF file.
At least one non-text object (such as an image or picture) has been suppressed.
This is the abbreviated version, containing approximately 62% of the total text.

Page 1 of 2

Maximum Response Time Control

An expanded table driven task scheduling algorithm is provided, which allows for a change in priority for a given user if a predefined time limit is exceeded. This permits a task which is given a relatively low priority under normal loading conditions to be assured of service during short duration peak conditions.

Task scheduling refers to the order in which tasks are moved from the eligible list (i.e., those tasks that are ready to be brought into core storage and require CPU service) to the dispatchable list (i.e., those tasks that occupy core storage and can receive CPU service). Normally, the tasks in the eligible list have two table parameters associated with them which are used to make a decision as to which task is to be scheduled next. These are (1) the priority number, which refers to the relative importance of the task and (2) the scheduled start time (SST), which refers to when the task is expected to be placed in the dispatchable list. The scheduling algorithm orders the eligible list first by priority number and second by SST within the same priority classification. Therefore, the eligible list is ordered from high to low priority and from lowest to highest SST within priority class. The scheduling algorithm searches for the highest priority task that is behind the SST. If no task is behind schedule, the highest priority task will be scheduled next. However, this algorithm does not work well under heavy loads inasmuch as...