Year-end Sale % OFF 
Abstract
Unreliable failure detectors are a basic building block of reliable distributed systems. Failure detectors are used to monitor processes of any application and provide process state information. This work presents an Internet Failure Detector Service (IFDS) for processes running in the Internet on multiple autonomous systems. The failure detection service is adaptive, and can be easily integrated into applications that require configurable QoS guarantees. The service is based on monitors which are capable of providing global process state information through a SNMP MIB. Monitors at different networks communicate across the Internet using Web Services. The system was implemented and evaluated for monitored processes running both on single LAN and on PlanetLab. Experimental results are presented, showing the performance of the detector, in particular the advantages of using the self-tuning strategies to address the requirements of multiple concurrent applications running on a dynamic environment.
Highlights
Consensus [1] and other equivalent problems, such as atomic broadcast and group membership are used to implement dependable distributed systems [2, 3]
In this work we describe an Internet Failure Detection Service (IFDS) that can be used by applications that consist of processes running on independent autonomous systems of the Internet
The main purpose of Step1 is to compute an upper bound for the heartbeat interval ηmax, given the input values provided by the application: the upper bound on the detection time (TDU ), upper bound on the average mistake duration (TMU ), and lower bound on the average mistake recurrence time (TML R)
Summary
Consensus [1] and other equivalent problems, such as atomic broadcast and group membership are used to implement dependable distributed systems [2, 3]. The user must provide a specification of the average mistake recurrence time (TMR defined above) and the minimum coverage (CL), which corresponds to a lower bound on the probability that heartbeat messages are received before the timeout interval expires These parameters are used by a configurator which relies on another system called Adaptare that is a middleware that computes the timeout by estimating distributions based on the stochastic properties of the system on which the failure detector is running. With respect to previous SNMP-based implementations of failure detectors, the major benefit of our proposed service is that it allows the user to specify QoS requirements for each application that is monitored, including: the failure detection time, mistake recurrence time and mistake duration Given this input, and the perceived network conditions, our service configures and continuously adapt the failure detector parameters, including the heartbeat rate.
Sign-in/Register to view highlights & summary 
Published Version (
Free)
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
