Abstract
Geo-replicated systems provide a number of desirable properties such as globally low latency, high availability, scalability, and built-in fault tolerance. Unfortunately, programming correct applications on top of such systems has proven to be very challenging, in large part because of the weak consistency guarantees they offer. These complexities are exacerbated when we try to adapt existing highly-performant concurrent libraries developed for shared-memory environments to this setting. The use of these libraries, developed with performance and scalability in mind, is highly desirable. But, identifying a suitable notion of correctness to check their validity under a weakly consistent execution model has not been well-studied, in large part because it is problematic to naïvely transplant criteria such as linearizability that has a useful interpretation in a shared-memory context to a distributed one where the cost of imposing a (logical) global ordering on all actions is prohibitive. In this paper, we tackle these issues by proposing appropriate semantics and specifications for highly-concurrent libraries in a weakly-consistent, replicated setting. We use these specifications to develop a static analysis framework that can automatically detect correctness violations of library implementations parameterized with respect to the different consistency policies provided by the underlying system. We use our framework to analyze the behavior of a number of highly non-trivial library implementations of stacks, queues, and exchangers. Our results provide the first demonstration that automated correctness checking of concurrent libraries in a weakly geo-replicated setting is both feasible and practical.
Highlights
Geo-replicated systems maintain multiple copies of data at different locations and provide a number of attractive properties such as globally uniform low access-latency, always-on availability, fault tolerance, and improved scalability
In order to bridge this gap, we study how to automatically transplant concurrent library implementations developed for shared memory systems to replicated ones
We make the following major contributions: 1. We propose a novel operational semantics for replicated systems parameterized under realistic consistency policies which can be used to describe executions of sophisticated concurrent library implementations
Summary
Geo-replicated systems maintain multiple copies of data at different locations and provide a number of attractive properties such as globally uniform low access-latency, always-on availability, fault tolerance, and improved scalability. The first Pop operation returns 2 and sets the Top to point at L1, which is read by the second Pop. MW+MR only guarantees that all write operations performed by the first Pop will be witnessed by the second Pop. just like, the second Pop operation may see the node at location L1 but not the write to the Val field (which was performed by PUSH(1)), resulting in violation of the specification. That writes witnessed in a session are propagated to all replicas before writes of the session itself (as opposed to MW which only ensures that writes performed in a session are propagated in session order) We note that both the violations described above (along with their repairs) were automatically discovered using our proposed methods, which devised solutions significantly less expensive than imposing strong consistency (aka global coordination) on all accesses.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
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 call
