Browse Prior Art Database

Dynamic Buffering Via Request Queue Element Scheduling

IP.com Disclosure Number: IPCOM000075629D
Original Publication Date: 1971-Oct-01
Included in the Prior Art Database: 2005-Feb-24
Document File: 2 page(s) / 63K

Publishing Venue

IBM

Related People

Elliott, TM: AUTHOR [+2]

Abstract

A set of program routines are used in combination to allocate main storage I/O areas (buffers) from a shared pool, to request for data transmission to and from I/O devices. The process described uses the appendage facilities of the Operating System 360 Input/Output Supervisor (IOS), but would be adaptable to operation under any supervisory system providing comparable facilities. Basic Elements of Process 1) User Application Program (USER) which submits requests for data transfer to IOS. 2) IOS which schedules requests from USER programs, initiates I/O device activity, exits to appendages and accepts Central Processing Unit (CPU) interrupts from I/O devices. 3) Pool of buffers. 4) Start Input/Output appendage (SIO) which is entered from IOS prior to initiating device activity.

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 53% of the total text.

Page 1 of 2

Dynamic Buffering Via Request Queue Element Scheduling

A set of program routines are used in combination to allocate main storage I/O areas (buffers) from a shared pool, to request for data transmission to and from I/O devices. The process described uses the appendage facilities of the Operating System 360 Input/Output Supervisor (IOS), but would be adaptable to operation under any supervisory system providing comparable facilities. Basic Elements of Process 1) User Application Program (USER) which submits requests for data transfer to IOS. 2) IOS which schedules requests from USER programs, initiates I/O device activity, exits to appendages and accepts Central Processing Unit (CPU) interrupts from I/O devices. 3) Pool of buffers. 4) Start Input/Output appendage (SIO) which is entered from IOS prior to initiating device activity. SIO may cancel or alter the nature of the request about to be initiated. 5) Channel End Appendage (CHEND) which is entered from IOS, when a CPU interrupt signals that a request for data transfer is complete. CHEND may notify USER that the request is complete and/or schedule a new request to IOS. 6) Request Queue Element (RQE) which is used by IOS to control scheduling of requests to various devices. 7) Device Dependent No Operation (NOP) which is used by SIO to allow the device to be activated, causing a time delay and a completion CPU interrupt, without any data transfer occurring.

The interaction of these elements to accomplish dynamic buffering is shown in the flow diagram.

The USER submit...