Timestamp tokens: a better coordination primitive for data-processing systems

Abstract

Distributed data processing systems have advanced through models that expose more and more opportunities for concurrency within a computation. The scheduling of these increasingly sophisticated models has become the bottleneck for improved throughput and reduced latency. We present a new coordination primitive for dataflow systems, the timestamp token, which minimizes the volume of information shared between the computation and host system, without surrendering precision about concurrency. Several projects have now used timestamp tokens, and were able to explore computational idioms that could not be expressed easily, if at all, in other platforms. Importantly, these projects did not need to design and implement whole systems to support their research.