CS assistant professor Mohammad Sadoghi and Ph.D. student Thamir Qadah at Purdue University win Best Paper Award at ACM/USENIX/IFIP Middleware Conference 2018 for their paper titled QueCC: A Queue-oriented, Control-free Concurrency Architecture.
Summary of the paper:
Motivated by a simple profound question: is it possible to have concurrent execution over shared data without having any concurrency control? To answer this question, we investigate a deterministic approach to transaction processing geared towards multi-socket, many-core architectures. We propose QueCC, pronounced Quick, a novel queue-oriented, control-free concurrency architecture that exhibits minimal contention during execution and imposes no coordination among transactions while offering serializable guarantees. The key intuition behind our QueCC’s design is to eliminate concurrency control by executing a set of batched transactions in two independent and deterministic phases of planning followed by execution, namely, decompose transactions into (predetermined) priority queues followed by priority-queue-oriented execution. In other words, we impose a deterministic plan of execution on batches of transactions, which eliminates the need for concurrency control during the actual execution of transactions, hence, preventing all execution-induced aborts.