In system software:
– Extremely high reliability of software and supportive schemes for hardware fault
tolerance,
– High performance and real-time scheduling with assumption of HW faults,
– Fault-tolerant concurrency monitoring,
– Language support of hardware deficiency,
– Control and monitoring of system reconfiguration in case of hardware fault,
– Program, system, and object (using applications) reconfigurability,
– Supportive mechanisms for system recovery, and
– Support for degraded hardware mode, where only the core applications are
executed.
The achievable reliability of the FT RT system depends on the available technologies and the use of hardware and system software solutions. The performance
also depends on existing technologies and, in particular, on the efficiency of the
algorithmic solutions used for the implementation of fault tolerance.
Finally, power consumption is another overarching limit, which affects the
FT RT architecture. This, in turn, demands minimum redundancy use along with
limiting the processor frequency and voltage at the lowest feasible rate. Here, a
solution might be the use of multiple frequency capable hardware, where the
processor and other hardware components are able to operate at reduced (when
necessary to save power) and full (when performance is crucial) speed.
References
1. Laprie J-C et al (2004) Basic concepts and taxonomy of dependable and secure computing,
IEEE Trans Dependable Secur Comput 1(1):11–33
2. Sogomonian E, Schagaev I (1988) Hardware and software fault tolerance of computer
systems. Avtomatika i Telemekhanika, pp 3–39. 2
3. Pliaskota S, Schagaev I (1995) Economic effectiveness of fault tolerance. Autom Remote
Control 7. 2
4. Schagaev I (1989) Instructions retry in microprocessor recovery algorithms. In: IMEKO—
FTSD symposium. 2
5. Pliaskota S, Schagaev I (2001) Life cycle economic efficiency analysis. In: IEEE TESADI-01
6. Schagaev I (2008) Reliability of malfunction tolerance. In: International Multiconference on
Computer Science and Information Technology, IMCSIT, pp 733–737
7. Wirth N, Gutknecht J (1992) Project Oberon: the design of an operating system and compiler.
Addison-Wesley, New York
8. Johannes M (2002) The active object system—design and multiprocessor implementation.
ETH Zurich, Zurich. 4, 82, 109, 173
9. Mossenbock H, Wirth N (1991) The programming language Oberon-2. Technical report,
Johannes Kepler Universitat Linz
10. Reiser M, Wirth N (1992) Programming in Oberon: steps beyond Pascal and Modula.
Addison-Wesley, Wokingham
11. Wirth N (1977) Modula: a language for modular multiprogramming. Softw: Pract Experience
7(1):1–35
1 Introduction
5
– Extremely high reliability of software and supportive schemes for hardware fault
tolerance,
– High performance and real-time scheduling with assumption of HW faults,
– Fault-tolerant concurrency monitoring,
– Language support of hardware deficiency,
– Control and monitoring of system reconfiguration in case of hardware fault,
– Program, system, and object (using applications) reconfigurability,
– Supportive mechanisms for system recovery, and
– Support for degraded hardware mode, where only the core applications are
executed.
The achievable reliability of the FT RT system depends on the available technologies and the use of hardware and system software solutions. The performance
also depends on existing technologies and, in particular, on the efficiency of the
algorithmic solutions used for the implementation of fault tolerance.
Finally, power consumption is another overarching limit, which affects the
FT RT architecture. This, in turn, demands minimum redundancy use along with
limiting the processor frequency and voltage at the lowest feasible rate. Here, a
solution might be the use of multiple frequency capable hardware, where the
processor and other hardware components are able to operate at reduced (when
necessary to save power) and full (when performance is crucial) speed.
References
1. Laprie J-C et al (2004) Basic concepts and taxonomy of dependable and secure computing,
IEEE Trans Dependable Secur Comput 1(1):11–33
2. Sogomonian E, Schagaev I (1988) Hardware and software fault tolerance of computer
systems. Avtomatika i Telemekhanika, pp 3–39. 2
3. Pliaskota S, Schagaev I (1995) Economic effectiveness of fault tolerance. Autom Remote
Control 7. 2
4. Schagaev I (1989) Instructions retry in microprocessor recovery algorithms. In: IMEKO—
FTSD symposium. 2
5. Pliaskota S, Schagaev I (2001) Life cycle economic efficiency analysis. In: IEEE TESADI-01
6. Schagaev I (2008) Reliability of malfunction tolerance. In: International Multiconference on
Computer Science and Information Technology, IMCSIT, pp 733–737
7. Wirth N, Gutknecht J (1992) Project Oberon: the design of an operating system and compiler.
Addison-Wesley, New York
8. Johannes M (2002) The active object system—design and multiprocessor implementation.
ETH Zurich, Zurich. 4, 82, 109, 173
9. Mossenbock H, Wirth N (1991) The programming language Oberon-2. Technical report,
Johannes Kepler Universitat Linz
10. Reiser M, Wirth N (1992) Programming in Oberon: steps beyond Pascal and Modula.
Addison-Wesley, Wokingham
11. Wirth N (1977) Modula: a language for modular multiprogramming. Softw: Pract Experience
7(1):1–35
1 Introduction
5