HAFT: Hardware-assisted fault tolerance

Dmitrii Kuvaiskii, Rasha Faqeh, Pramod Bhatotia, Pascal Felber, Christof Fetzer

Publikation: Beitrag in Buch/Bericht/KonferenzbandKonferenzbeitragBegutachtung

48 Zitate (Scopus)

Abstract

Transient hardware faults during the execution of a program can cause data corruptions. We present HAFT, a fault tolerance technique using hardware extensions of commodity CPUs to protect unmodified multithreaded applications against such corruptions. HAFT utilizes instruction-level redundancy for fault detection and hardware transactional memory for fault recovery. We evaluated HAFT with Phoenix and PARSEC benchmarks. The observed normalized runtime is 2x, with 98.9% of the injected data corruptions being detected and 91.2% being corrected. To demonstrate the effectiveness of HAFT, we applied it to real-world case studies including Memcached, Apache, and SQLite.

OriginalspracheEnglisch
TitelProceedings of the 11th European Conference on Computer Systems, EuroSys 2016
Herausgeber (Verlag)Association for Computing Machinery, Inc
ISBN (elektronisch)9781450342407
DOIs
PublikationsstatusVeröffentlicht - 18 Apr. 2016
Extern publiziertJa
Veranstaltung11th European Conference on Computer Systems, EuroSys 2016 - London, Großbritannien/Vereinigtes Königreich
Dauer: 18 Apr. 201621 Apr. 2016

Publikationsreihe

NameProceedings of the 11th European Conference on Computer Systems, EuroSys 2016

Konferenz

Konferenz11th European Conference on Computer Systems, EuroSys 2016
Land/GebietGroßbritannien/Vereinigtes Königreich
OrtLondon
Zeitraum18/04/1621/04/16

Fingerprint

Untersuchen Sie die Forschungsthemen von „HAFT: Hardware-assisted fault tolerance“. Zusammen bilden sie einen einzigartigen Fingerprint.

Dieses zitieren