The /spl phi/ accrual failure detector

The detection of failures is a fundamental issue for fault-tolerance in distributed systems. Recently, many people have come to realize that failure detection ought to be provided as some form of generic service, similar to IP address lookup or time synchronization. However, this has not been successful so far; one of the reasons being the fact that classical failure detectors were not designed to satisfy several application requirements simultaneously. We present a novel abstraction, called accrual failure detectors, that emphasizes flexibility and expressiveness and can serve as a basic building block to implementing failure detectors in distributed systems. Instead of providing information of a binary nature (trust vs. suspect), accrual failure detectors output a suspicion level on a continuous scale. The principal merit of this approach is that it favors a nearly complete decoupling between application requirements and the monitoring of the environment. In this paper, we describe an implementation of such an accrual failure detector, that we call the /spl phi/ failure detector. The particularity of the /spl phi/ failure detector is that it dynamically adjusts to current network conditions the scale on which the suspicion level is expressed. We analyzed the behavior of our /spl phi/ failure detector over an intercontinental communication link over a week. Our experimental results show that if performs equally well as other known adaptive failure detection mechanisms, with an improved flexibility.