The fail-heterogeneous architectural model

Marco Serafini, Neeraj Suri

Research output: Chapter in Book/Report/Conference proceedingConference contribution

5 Citations (Scopus)

Abstract

Fault tolerant distributed protocols typically utilize a homogeneous fault model, either fail-crash or fail-Byzantine, where all processors are assumed to fail in the same manner. In practice, due to complexity and evolvability reasons, only a subset of the nodes can actually be designed to have a restricted, fail-crash failure mode, provided that they are free of design faults. Based on this consideration, we propose a fail-heterogeneous architectural model for distributed systems which considers two classes of nodes: (a) full-fledged execution nodes, which can be fail-Byzantine, and (b) lightweight, validated coordination nodes, which can only be fail-crash. To illustrate the model we introduce HeterTrust as a practical trustworthy service replication protocol. It has a low latency overhead, requires few execution nodes with diversified design, and prevents intruded servers from disclosing confidential data. We also discuss applications of the model to DoS attacks mitigation and to group membership.

Original languageEnglish
Title of host publicationProceedings of the IEEE Symposium on Reliable Distributed Systems
Pages103-113
Number of pages11
DOIs
Publication statusPublished - 1 Dec 2007
Externally publishedYes
Event26th IEEE International Symposium on Reliable Distributed Systems, SRDS 2007 - Beijing, China
Duration: 10 Oct 200712 Oct 2007

Other

Other26th IEEE International Symposium on Reliable Distributed Systems, SRDS 2007
CountryChina
CityBeijing
Period10/10/0712/10/07

Fingerprint

Network protocols
Failure modes
Servers
Denial-of-service attack

ASJC Scopus subject areas

  • Hardware and Architecture

Cite this

Serafini, M., & Suri, N. (2007). The fail-heterogeneous architectural model. In Proceedings of the IEEE Symposium on Reliable Distributed Systems (pp. 103-113). [4365688] https://doi.org/10.1109/SRDS.2007.4365688

The fail-heterogeneous architectural model. / Serafini, Marco; Suri, Neeraj.

Proceedings of the IEEE Symposium on Reliable Distributed Systems. 2007. p. 103-113 4365688.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Serafini, M & Suri, N 2007, The fail-heterogeneous architectural model. in Proceedings of the IEEE Symposium on Reliable Distributed Systems., 4365688, pp. 103-113, 26th IEEE International Symposium on Reliable Distributed Systems, SRDS 2007, Beijing, China, 10/10/07. https://doi.org/10.1109/SRDS.2007.4365688
Serafini M, Suri N. The fail-heterogeneous architectural model. In Proceedings of the IEEE Symposium on Reliable Distributed Systems. 2007. p. 103-113. 4365688 https://doi.org/10.1109/SRDS.2007.4365688
Serafini, Marco ; Suri, Neeraj. / The fail-heterogeneous architectural model. Proceedings of the IEEE Symposium on Reliable Distributed Systems. 2007. pp. 103-113
@inproceedings{386010f2f43e4ab3932b4c6b044b275c,
title = "The fail-heterogeneous architectural model",
abstract = "Fault tolerant distributed protocols typically utilize a homogeneous fault model, either fail-crash or fail-Byzantine, where all processors are assumed to fail in the same manner. In practice, due to complexity and evolvability reasons, only a subset of the nodes can actually be designed to have a restricted, fail-crash failure mode, provided that they are free of design faults. Based on this consideration, we propose a fail-heterogeneous architectural model for distributed systems which considers two classes of nodes: (a) full-fledged execution nodes, which can be fail-Byzantine, and (b) lightweight, validated coordination nodes, which can only be fail-crash. To illustrate the model we introduce HeterTrust as a practical trustworthy service replication protocol. It has a low latency overhead, requires few execution nodes with diversified design, and prevents intruded servers from disclosing confidential data. We also discuss applications of the model to DoS attacks mitigation and to group membership.",
author = "Marco Serafini and Neeraj Suri",
year = "2007",
month = "12",
day = "1",
doi = "10.1109/SRDS.2007.4365688",
language = "English",
isbn = "076952995X",
pages = "103--113",
booktitle = "Proceedings of the IEEE Symposium on Reliable Distributed Systems",

}

TY - GEN

T1 - The fail-heterogeneous architectural model

AU - Serafini, Marco

AU - Suri, Neeraj

PY - 2007/12/1

Y1 - 2007/12/1

N2 - Fault tolerant distributed protocols typically utilize a homogeneous fault model, either fail-crash or fail-Byzantine, where all processors are assumed to fail in the same manner. In practice, due to complexity and evolvability reasons, only a subset of the nodes can actually be designed to have a restricted, fail-crash failure mode, provided that they are free of design faults. Based on this consideration, we propose a fail-heterogeneous architectural model for distributed systems which considers two classes of nodes: (a) full-fledged execution nodes, which can be fail-Byzantine, and (b) lightweight, validated coordination nodes, which can only be fail-crash. To illustrate the model we introduce HeterTrust as a practical trustworthy service replication protocol. It has a low latency overhead, requires few execution nodes with diversified design, and prevents intruded servers from disclosing confidential data. We also discuss applications of the model to DoS attacks mitigation and to group membership.

AB - Fault tolerant distributed protocols typically utilize a homogeneous fault model, either fail-crash or fail-Byzantine, where all processors are assumed to fail in the same manner. In practice, due to complexity and evolvability reasons, only a subset of the nodes can actually be designed to have a restricted, fail-crash failure mode, provided that they are free of design faults. Based on this consideration, we propose a fail-heterogeneous architectural model for distributed systems which considers two classes of nodes: (a) full-fledged execution nodes, which can be fail-Byzantine, and (b) lightweight, validated coordination nodes, which can only be fail-crash. To illustrate the model we introduce HeterTrust as a practical trustworthy service replication protocol. It has a low latency overhead, requires few execution nodes with diversified design, and prevents intruded servers from disclosing confidential data. We also discuss applications of the model to DoS attacks mitigation and to group membership.

UR - http://www.scopus.com/inward/record.url?scp=47249126755&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=47249126755&partnerID=8YFLogxK

U2 - 10.1109/SRDS.2007.4365688

DO - 10.1109/SRDS.2007.4365688

M3 - Conference contribution

SN - 076952995X

SN - 9780769529950

SP - 103

EP - 113

BT - Proceedings of the IEEE Symposium on Reliable Distributed Systems

ER -