Samll essay

Tandem : A Summary of Fault Tolerance Strategies

Introduction

Tandem 16 attempts to provide a general-purpose , multi-computer system which is more reliable than conventional offerings . This was designed to provide a system for online applications . Through software abstractions a multiple-computer structure and fault tolerant one is transformed into a symmetric multiprocessor which gives programming ease . The hardware structure for this is consists of multiple processor modules interconnected by redundant interprocessor buses . Each I /O controller is powered and connected to two different I /O channels which results to not affecting the

ability of a processor to communicate with any other processor . The system is not a true multiprocessor , but rather a multiple computer system . This is preferable since no module is shared by the entire system , thus , it increases the system 's reliability . It also not requires a complex hardware needed to handle multiple access paths to a common memory . This system is meant to provide any solution to the problem of providing a failure-tolerant , online environment suitable for commercial use . The system was designed to solve problems related to system requirements , not just hardware and software problems .The main goal of this system is provide a failure-tolerant system . This has translated the design axioms and requirements enumerated below

The operating system should be able to remain operational after any single detected module or bus failure

The operating system should allow any module or bus to be repaired online and then reintegrate into the system

The operating system should be implemented in a reliable manner

The operating system should support all possible hardware configurations

The operating system should hide the physical configurations as much as possible such that applications could be written to run on a great variety of system configurations

Redundancy Used

Additional software error checks are provided aside from the hardware single-error detection and correction on memory and single-error detection on the interprocessor and I /O buses . The software error checks added is detection of a down processor . Every second , each processor on the system sends a message I 'm alive ' over each bus to all processors in the system and every two seconds the processor checks to see that it has received one of these messages from each processor . The processor is down if the message has not been received . The interprocessor bus protocol is designed to correct single bus errors and provides an extensive checking on the control information received over the buses to verify if it is consistent with the state of the receiving processor Each processor is provided with power-fail /automatic restart . A power failure is detected by each processor module . This system was designed to recover from either a complete system failure or a transient which causes some processors to power fail and eventually restart

Fault /Detection Error

An interactive access to the system is provided by the command interpreter , COMINT . In normal operations , command interpreter is run interactively from a terminal but commands are read from any type of s . The command interpreter...