Towards Low-Latency Batched Stream Processing by Pre-Scheduling
Research output: Contribution to journal › Journal article › Research › peer-review
Hai Jin, Fei Chen, Song Wu, Yin Yao, Zhiyi Liu, Lin Gu, Yongluan Zhou
Many stream processing frameworks have been developed to meet the requirements of real-time processing. Among them, batched stream processing frameworks are widely advocated with the consideration of their fault-tolerance and high throughput. In batched stream processing frameworks, straggler, happened due to the uneven task execution time, has been regarded as a major hurdle of latency-sensitive applications. Existing straggler mitigation techniques, operating in either reactive or proactive manner, are all post-scheduling methods, and therefore inevitably result in high resource overhead or long job completion time. We notice that batched stream processing jobs are usually recurring with predictable characteristics. By exploring such a feature, we present a pre-scheduling straggler mitigation framework called Lever. Lever first identifies potential stragglers and evaluates nodes capacity by analyzing execution information of historical jobs. Then, Lever carefully pre-schedules job input data to each node before task scheduling so as to mitigate potential stragglers. We implement Lever and contribute it as an extension of Apache Spark Streaming. Our experimental results show that Lever can reduce job completion time by 30.72% to 42.19% over Spark Streaming, a widely adopted batched stream processing system and outperforms traditional techniques significantly.
|Journal||IEEE Transactions on Parallel and Distributed Systems|
|Publication status||Published - 2019|
- data assignment, recurring jobs, scheduling, straggler, stream processing