Error Recovery Scheme for the IBM 3850 Mass Storage System

Abstract

The IBM 3850 Mass Storage System (MSS) stores digital data on flexible magnetic tape media; however, it is different in many respects from the conventional midtitrack tape machines. In particular, the use of a single-element rotary readwrite head imposes new demands in the areas of data encoding and error recovery. This paper presents a comprehensive scheme for error recovery for the 3850 MSS which features a new error-correction code in a serial, single-stripe data format. The recovery procedure is designed around resynchronizahle sections of data which are rendered independent of each other in error modes through the use of zero-modulation encoding and self-contained error-detection pointers. These error-detection pointers and the resynchroniiation signals are utilized in conjunction with interleaved codewords of the error-correction code. The code is designed with a generating polynomial in which the roots are chosen from the set of elements of a I6-element subfield of the Galois field GF(2^). This choice provides the necessary code structure for desired code capabilities and facilitates fast decoding of errors with an economical implementation of the decoder. The scheme provides correction capabilities for various combinations of mixed-mode short and long errors common to magnetic tape recording of digital data.

Developments in Error Control Coding Techniques and some Results on Concatenated Codes

“…Hsiao and Tou's paper [100] is an excellent tutorial exposition to the relevance of error correcting codes in computer system design. Additional information on specific applications of error control codes in storage systems arc available in [101,102]. Here we cite one example of a modified cyclic code, used for error correction in IBM 800 bpi magnetic tape [103].…”

Reliability, Availability, and Serviceability of IBM Computer Systems: A Quarter Century of Progress

“…The cartridge concept provides a diflferent data format from the conventional parallel-track system, thus abandoning the track correction scheme. Instead, it uses an interleaved subfleld code to correct a single burst of 128-bit-long or nonoverlapped 8-bit burst in 16 different sections [48]. The ZM code not only has a self-clocking feature and 100% recording efficiency, but also provides a powerful pointer to pick up extra error-detection capability in addition to what ECC provides.…”

On-the-fly decoder for multiple byte errors

“…A relatively greater number of soft errors, including multiple burst errors, will need on-the-fly correction. Reed-Solomon [1] or BCH [2,3] codes in Galois field GF(l'') can be used [4] for correction of burst errors by interleaving codewords. In these codes, each symbol is represented by a binary byte, and an error is a byte error.…”