Design for fault-tolerance in system ES model 900

Spainhower, Lisa; Isenberg, J.; Chillarege, Ram; Berding, J.

doi:10.1109/ftcs.1992.243617

Cited by 22 publications

(13 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The second category includes a variety of more or less sophisticated heuristics, based on thresholding schemes, e.g. [3,13,8]. They count errors, and when the count crosses a pre-set threshold a permanent fault is assumed.…”

Section: Related Workmentioning

confidence: 99%

Hidden Markov Models as a Support for Diagnosis: Formalization of the Problem and Synthesis of the Solution

Daidone

Giandomenico

Chiaradonna

et al. 2006

2006 25th IEEE Symposium on Reliable Distributed Systems (SRDS'06)

View full text Add to dashboard Cite

In modern information infrastructures, diagnosis must be able to assess the status or the extent of the damage of individual components. Traditional one-shot diagnosis is not adequate, but streams of data on component behavior need to be collected and filtered over time as done by some existing heuristics. This paper proposes instead a general framework and a formalism to model such over-time diagnosis scenarios, and to find appropriate solutions. As such, it is very beneficial to system designers to support design choices. Taking advantage of the characteristics of the hidden Markov models formalism, widely used in pattern recognition, the paper proposes a formalization of the diagnosis process, addressing the complete chain constituted by monitored component, deviation detection and state diagnosis. Hidden Markov models are well suited to represent problems where the internal state of a certain entity is not known and can only be inferred from external observations of what this entity emits. Such over-time diagnosis is a first class representative of this category of problems. The accuracy of diagnosis carried out through the proposed formalization is then discussed, as well as how to concretely use it to perform state diagnosis and allow direct comparison of alternative solutions.

show abstract

Section: Related Workmentioning

confidence: 99%

Hidden Markov Models as a Support for Diagnosis: Formalization of the Problem and Synthesis of the Solution

Daidone

Giandomenico

Chiaradonna

et al. 2006

2006 25th IEEE Symposium on Reliable Distributed Systems (SRDS'06)

View full text Add to dashboard Cite

show abstract

“…If the system [8] incremental variable register file history buffer history file [8] incremental variable register file shadow file VAX 9000 [12] fuff single instr. register file not required IBM E/S 9000 [5] incremental variable virtual file physical file state has changed prior to detection of the error, a flag is set to indicate that instruction rollback cannot be accomplished. Redundant data storage is not required for the VAX 8600 and VAX 9000.…”

Section: H Ardware-based Instruction R Ollbackmentioning

confidence: 99%

“…Multiple instruction retry within a sliding window of a few instructions [2][3][4][5], or re-execution of a few cycles [7], can be implemented in parallel with concurrent, algorithm-based, or control-flow error detection methods for recovery from transient processor errors.…”

Section: Introductionmentioning

confidence: 99%

“…When transient processor errors occur, multiple instruction rollback (also referred to as mul tiple instruction retry or simply instruction retry) can be an effective alternative to system-level checkpointing and rollback recovery [1][2][3][4][5][6]. Multiple instruction retry within a sliding window of a few instructions [2][3][4][5], or re-execution of a few cycles [7], can be implemented in parallel with concurrent, algorithm-based, or control-flow error detection methods for recovery from transient processor errors.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Compiler-assisted multiple instruction rollback recovery using a read buffer

Alewine¹,

Chen

Fuchs

et al. 1995

IEEE Trans. Comput.

View full text Add to dashboard Cite

“…[1] for an assessment of a heuristic via modelling). Most on-line techniques [1,5,8,12,13] use thresholding schemes. They count errors, and when the count crosses a pre-set threshold a permanent fault is assumed.…”

Section: Introductionmentioning

confidence: 99%