Files

Abstract

In today's systems, application are composed from various components that may be located on different machines. The components may have to collaborate in order to service a client request. More specifically, a client request to one component may trigger a request to another component. Moreover, to ensure fault-tolerance, components are generally replicated. This poses the problem of a replicated server invoking another replicated server. We call it the problem of replicated invocation. Replicated invocation has been considered in the context of deterministic servers. However, the problem is more difficult to address when servers are non-deterministic. In this context, work has been done to enforce deterministic execution. In the paper we consider a different approach. Instead of preventing non-deterministic execution of servers, we discuss how to handle it. The paper first discusses the problem of non-deterministic replicated invocation. Then the paper proposes a different solution to solve these problems.

Details

Actions

Preview