Towards Concurrent Stateful Stream Processing on Multicore Processors (Technical Report)

TL;DR

This paper presents TStream, a new data stream processing system that significantly improves concurrent state access scalability on multicore processors using dual-mode scheduling and dynamic restructuring, outperforming existing solutions.

Contribution

TStream introduces two novel techniques for scalable concurrent state access in stream processing, enabling higher throughput and workload flexibility on multicore architectures.

Findings

Achieves up to 4.8x higher throughput than state-of-the-art systems.

Maintains similar latency while improving scalability.

Handles workload variations like key skewness effectively.

Abstract

Recent data stream processing systems (DSPSs) can achieve excellent performance when processing large volumes of data under tight latency constraints. However, they sacrifice support for concurrent state access that eases the burden of developing stateful stream applications. Recently, some have proposed managing concurrent state access during stream processing by modeling state accesses as transactions. However, these are realized with locks involving serious contention overhead. Their coarse-grained processing paradigm further magnifies contention issues and tends to poorly utilize modern multicore architectures. This paper introduces TStream , a novel DSPS supporting efficient concurrent state access on multicore processors. Transactional semantics is employed like previous work, but scalability is greatly improved due to two novel designs: 1) dual-mode scheduling, which exposes more parallelism opportunities, 2) dynamic restructuring execution, which aggressively exploits the parallelism opportunities from dual-mode scheduling without centralized lock contentions. To validate our proposal, we evaluate TStream with a benchmark of four applications on a modern multicore machine. The experimental results show that 1) TStream achieves up to 4.8 times higher throughput with similar processing latency compared to the state-of-the-art and 2) unlike prior solutions, TStream is highly tolerant of varying application workloads such as key skewness and multi-partition state accesses.