Browse Prior Art Database

Fault-Tolerant BATTERY BACK-UP POWER SYSTEM for Controlling I/O DEVICES for Continuous On-Line TRANSACTIONS

IP.com Disclosure Number: IPCOM000036645D
Original Publication Date: 1989-Oct-01
Included in the Prior Art Database: 2005-Jan-29
Document File: 4 page(s) / 109K

Publishing Venue

IBM

Related People

Baker, ED: AUTHOR [+4]

Abstract

This article describes a fault-tolerant battery back-up power system in which the system optimizes resources while maintaining continuous operation during an unplanned power outage in a manner transparent to the user. (Image Omitted)

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 55% of the total text.

Page 1 of 4

Fault-Tolerant BATTERY BACK-UP POWER SYSTEM for Controlling I/O DEVICES for Continuous On-Line TRANSACTIONS

This article describes a fault-tolerant battery back-up power system in which the system optimizes resources while maintaining continuous operation during an unplanned power outage in a manner transparent to the user.

(Image Omitted)

This disclosure extends typical "hot-start" and "warm-start" initial program load (IPL) capability from configuration limited, temporary memory-hold of application data to the perpetual archive of a direct-access storage device (DASD). This allows full retention of system application data until the return of AC power. It is fully within the scope of this disclosure to provide maintenance functions and continuous non-stop transactions during power outages using system resources that are now generally unavailable.

A typical fault-tolerant non-stop transaction processor system is shown in block diagram in Fig. 1. It includes the following:

(Image Omitted)

AC POWER DISTRIBUTION BUS.

DC POWER DISTRIBUTION BUS.

REDUNDANT CENTRAL PROCESSING UNITS (CPUS).

BATTERY BACK-UP POWER SUB-SYSTEM.

INPUT/OUTPUT (I/O) DEVICES SUPPORTING TRANSACTION PROCESSING.

Control and data lines connecting system in fault-tolerant manner.

he assembly provides for redundant hardware configured/connected to self- test at the field-replaceable unit (FRU) level to operate in lock step with its partner and produce fault-tolerant highly available transaction processing.

In addition, all the elements of a hardware oriented fault-tolerant operating system are preserved as follows: RECORD AND MAINTAIN SYSTEM REDUNDANT CONFIGURATION.

ACCESS RESOURCES OVER A NETWORK AS SINGLE-SYSTEM IMAGE.

BRING SYSTEM RESOURCES ON/OFF-LINE IN MAINTENANCE MODE.

INITIATE/TERMINATE DEVICE TEST.

TRAFFIC MULTIPROCESSOR TRANSACTIONS.

Initiate application sequence in lock-step with

partnered devices.

Service power interrupts by rescheduling resources and

transfer I/O calls.

The system disclosed herein is shown in block diagram in Fig. 2. It includes elements similar to those in Fig. 1. However, an obvious difference to the typical configuration of Fig. 1 is the extensive use of DC power in the system to service all components of the system. The total system has access to battery back-up

1

Page 2 of 4

during unplanned outages. A critical resource to system availability is the amount of battery power and I/O load during VAC power outages. Utilizing the VDC power bus to power I/O devices and the communication interface (I/O device controller) for power control, a system can exchange resources during power...