Dependability under malicious agreement in N-modular redundancy-on-demand systems. Al-Hashimi, M., Pu, H. H., Park, N., & Lombardi, F. In IEEE International Symposium on Network Computing and Applications, 2001. NCA 2001, pages 80--91, 2001. doi abstract bibtex In a multiprocessor under normal loading conditions, idle processors offer a natural spare capacity. Previous work attempted to utilize this redundancy to overcome the limitations of classic diagnosability and modular redundancy techniques while providing significant fault tolerance. A common approach is task duplexing. The usefulness of this approach for critical applications, unfortunately, is seriously undermined by its susceptibility to agreement on faulty outcomes (malicious agreement). To assess dependability of duplexing under malicious agreement, we propose a stochastic model which dynamically profiles behavior in the presence of malicious faults. The model uses the so-called policy referred to as NMR on demand (NMROD). Each task in a multiprocessor is duplicated, with additional processors allocated for recovery as needed. NMROD relies on a fault model favoring response correctness over actual fault status, and integrates online repair to provide non-stop operation over an extended period
@inproceedings{ al-hashimi_dependability_2001,
title = {Dependability under malicious agreement in {N}-modular redundancy-on-demand systems},
doi = {10.1109/NCA.2001.962518},
abstract = {In a multiprocessor under normal loading conditions, idle processors offer a natural spare capacity. Previous work attempted to utilize this redundancy to overcome the limitations of classic diagnosability and modular redundancy techniques while providing significant fault tolerance. A common approach is task duplexing. The usefulness of this approach for critical applications, unfortunately, is seriously undermined by its susceptibility to agreement on faulty outcomes (malicious agreement). To assess dependability of duplexing under malicious agreement, we propose a stochastic model which dynamically profiles behavior in the presence of malicious faults. The model uses the so-called policy referred to as NMR on demand (NMROD). Each task in a multiprocessor is duplicated, with additional processors allocated for recovery as needed. NMROD relies on a fault model favoring response correctness over actual fault status, and integrates online repair to provide non-stop operation over an extended period},
booktitle = {{IEEE} {International} {Symposium} on {Network} {Computing} and {Applications}, 2001. {NCA} 2001},
author = {Al-Hashimi, M. and Pu, H. H. and Park, N. and Lombardi, F.},
year = {2001},
keywords = {Application software, Checkpointing, Costs, Fault model, Fault tolerance, Fault tolerant systems, Multitasking, NMR on demand, NMROD, Navigation, Nuclear magnetic resonance, TMR, Vehicles, _done, classic diagnosability, critical applications, fault status, fault tolerant computing, faulty outcomes, idle processors, malicious agreement, malicious faults, modular redundancy techniques, multiprocessing systems, multiprocessor, n-modular redundancy-on-demand systems, natural spare capacity, non-stop operation, normal loading conditions, online repair, probability, processor allocation, processor scheduling, redundancy, response correctness, task duplexing},
pages = {80--91}
}
Downloads: 0
{"_id":"Qb4JeFKoSLcsN8oy2","bibbaseid":"alhashimi-pu-park-lombardi-dependabilityundermaliciousagreementinnmodularredundancyondemandsystems-2001","downloads":0,"creationDate":"2015-04-15T11:01:18.533Z","title":"Dependability under malicious agreement in N-modular redundancy-on-demand systems","author_short":["Al-Hashimi, M.","Pu, H.<nbsp>H.","Park, N.","Lombardi, F."],"year":2001,"bibtype":"inproceedings","biburl":"http://bibbase.org/zotero/troeger","bibdata":{"abstract":"In a multiprocessor under normal loading conditions, idle processors offer a natural spare capacity. Previous work attempted to utilize this redundancy to overcome the limitations of classic diagnosability and modular redundancy techniques while providing significant fault tolerance. A common approach is task duplexing. The usefulness of this approach for critical applications, unfortunately, is seriously undermined by its susceptibility to agreement on faulty outcomes (malicious agreement). To assess dependability of duplexing under malicious agreement, we propose a stochastic model which dynamically profiles behavior in the presence of malicious faults. The model uses the so-called policy referred to as NMR on demand (NMROD). Each task in a multiprocessor is duplicated, with additional processors allocated for recovery as needed. NMROD relies on a fault model favoring response correctness over actual fault status, and integrates online repair to provide non-stop operation over an extended period","author":["Al-Hashimi, M.","Pu, H. H.","Park, N.","Lombardi, F."],"author_short":["Al-Hashimi, M.","Pu, H.<nbsp>H.","Park, N.","Lombardi, F."],"bibtex":"@inproceedings{ al-hashimi_dependability_2001,\n title = {Dependability under malicious agreement in {N}-modular redundancy-on-demand systems},\n doi = {10.1109/NCA.2001.962518},\n abstract = {In a multiprocessor under normal loading conditions, idle processors offer a natural spare capacity. Previous work attempted to utilize this redundancy to overcome the limitations of classic diagnosability and modular redundancy techniques while providing significant fault tolerance. A common approach is task duplexing. The usefulness of this approach for critical applications, unfortunately, is seriously undermined by its susceptibility to agreement on faulty outcomes (malicious agreement). To assess dependability of duplexing under malicious agreement, we propose a stochastic model which dynamically profiles behavior in the presence of malicious faults. The model uses the so-called policy referred to as NMR on demand (NMROD). Each task in a multiprocessor is duplicated, with additional processors allocated for recovery as needed. NMROD relies on a fault model favoring response correctness over actual fault status, and integrates online repair to provide non-stop operation over an extended period},\n booktitle = {{IEEE} {International} {Symposium} on {Network} {Computing} and {Applications}, 2001. {NCA} 2001},\n author = {Al-Hashimi, M. and Pu, H. H. and Park, N. and Lombardi, F.},\n year = {2001},\n keywords = {Application software, Checkpointing, Costs, Fault model, Fault tolerance, Fault tolerant systems, Multitasking, NMR on demand, NMROD, Navigation, Nuclear magnetic resonance, TMR, Vehicles, _done, classic diagnosability, critical applications, fault status, fault tolerant computing, faulty outcomes, idle processors, malicious agreement, malicious faults, modular redundancy techniques, multiprocessing systems, multiprocessor, n-modular redundancy-on-demand systems, natural spare capacity, non-stop operation, normal loading conditions, online repair, probability, processor allocation, processor scheduling, redundancy, response correctness, task duplexing},\n pages = {80--91}\n}","bibtype":"inproceedings","booktitle":"IEEE International Symposium on Network Computing and Applications, 2001. NCA 2001","doi":"10.1109/NCA.2001.962518","id":"al-hashimi_dependability_2001","key":"al-hashimi_dependability_2001","keywords":"Application software, Checkpointing, Costs, Fault model, Fault tolerance, Fault tolerant systems, Multitasking, NMR on demand, NMROD, Navigation, Nuclear magnetic resonance, TMR, Vehicles, _done, classic diagnosability, critical applications, fault status, fault tolerant computing, faulty outcomes, idle processors, malicious agreement, malicious faults, modular redundancy techniques, multiprocessing systems, multiprocessor, n-modular redundancy-on-demand systems, natural spare capacity, non-stop operation, normal loading conditions, online repair, probability, processor allocation, processor scheduling, redundancy, response correctness, task duplexing","pages":"80--91","title":"Dependability under malicious agreement in N-modular redundancy-on-demand systems","type":"inproceedings","year":"2001","bibbaseid":"alhashimi-pu-park-lombardi-dependabilityundermaliciousagreementinnmodularredundancyondemandsystems-2001","role":"author","urls":{},"keyword":["Application software","Checkpointing","Costs","Fault model","Fault tolerance","Fault tolerant systems","Multitasking","NMR on demand","NMROD","Navigation","Nuclear magnetic resonance","TMR","Vehicles","_done","classic diagnosability","critical applications","fault status","fault tolerant computing","faulty outcomes","idle processors","malicious agreement","malicious faults","modular redundancy techniques","multiprocessing systems","multiprocessor","n-modular redundancy-on-demand systems","natural spare capacity","non-stop operation","normal loading conditions","online repair","probability","processor allocation","processor scheduling","redundancy","response correctness","task duplexing"],"downloads":0},"search_terms":["dependability","under","malicious","agreement","modular","redundancy","demand","systems","al-hashimi","pu","park","lombardi"],"keywords":["application software","checkpointing","costs","fault model","fault tolerance","fault tolerant systems","multitasking","nmr on demand","nmrod","navigation","nuclear magnetic resonance","tmr","vehicles","_done","classic diagnosability","critical applications","fault status","fault tolerant computing","faulty outcomes","idle processors","malicious agreement","malicious faults","modular redundancy techniques","multiprocessing systems","multiprocessor","n-modular redundancy-on-demand systems","natural spare capacity","non-stop operation","normal loading conditions","online repair","probability","processor allocation","processor scheduling","redundancy","response correctness","task duplexing"],"authorIDs":[],"dataSources":["zHc5HdgBCDgkarEqH"]}