Abstract | ||
---|---|---|
A common way for a distributed system to tolerate crashes is to explicitly detect them and then recover from them. Interestingly, detection can take much longer than recovery, as a result of many advances in recovery techniques, making failure detection the dominant factor in these systems' unavailability when a crash occurs. This paper presents the design, implementation, and evaluation of Falcon, a failure detector with several features. First, Falcon's common-case detection time is sub-second, which keeps unavailability low. Second, Falcon is reliable: it never reports a process as down when it is actually up. Third, Falcon sometimes kills to achieve reliable detection but aims to kill the smallest needed component. Falcon achieves these features by coordinating a network of spies, each monitoring a layer of the system. Falcon's main cost is a small amount of platform-specific logic. Falcon is thus the first failure detector that is fast, reliable, and viable. As such, it could change the way that a class of distributed systems is built. |
Year | DOI | Venue |
---|---|---|
2011 | 10.1145/2043556.2043583 | SOSP |
Keywords | Field | DocType |
common-case detection time,small amount,dominant factor,detecting failure,main cost,unavailability low,recovery technique,reliable detection,failure detector,platform-specific logic,falcon spy network,failure detection,performance,algorithms,design,distributed system,high availability | Failure detector,Crash,Falcon,Computer science,Real-time computing,Unavailability,High availability,Embedded system,Distributed computing | Conference |
Citations | PageRank | References |
34 | 1.34 | 31 |
Authors | ||
5 |
Name | Order | Citations | PageRank |
---|---|---|---|
Joshua B. Leners | 1 | 85 | 4.92 |
Hao Wu | 2 | 34 | 1.68 |
Wei-Lun Hung | 3 | 155 | 8.07 |
Marcos Kawazoe Aguilera | 4 | 2519 | 153.60 |
Michael Walfish | 5 | 1007 | 69.58 |