Achieving Robust Self Management for Large Scale Distributed Applications using Management Elements

Sammanfattning: Abstract Autonomic computing is an approach proposed by IBM that enables a system to self-con gure, self-heal, self-optimize, and self-protect itself, usually referred to as self-' or self-management. Humans should only specify higher level policies to guide the self-' behavior of the system. Self-Management is achieved using control feedback loops that consist of four stages: monitor, analyze, plan, and execute. Management is more challenging in dynamic distributed environments where resources can join, leave, and fail. To address this problem a Distributed Component Management System (DCMS), a.k.a Niche, is being developed at KTH and SICS (Swedish Institute of Computer Science). DCMS provides abstractions that enable the construction of distributed control feedback loops. Each loop consists of a number of management elements (MEs) that do one or more of the four stages of a control loop mentioned above. The current implementation of DCMS assumes that management elements (MEs) are deployed on stable nodes that do not fail. This assumption is dicult to guarantee in many environments and application scenarios. One solution to this limitation is to replicate MEs so that if one fails other MEs can continue working and restore the failed one. The problem is that MEs are stateful. We need to keep the state consistent among replicas. We also want to be sure that all events are processed (nothing is lost) and all actions are applied exactly once. This report explains a proposal for the replication of stateful MEs under DCMS framework. For improved scalability, load-balancing and fault-tolerance, dierent breakthroughs in the eld of replicated state machine has been taken into account and discussed in this report. Chord has been used as an underlying structured overlay network (SON). This report also describes a prototype implementation of this proposal and discusses the results.