SONIC: Application-aware Data Passing for Chained Serverless Applications
SONIC: Application-aware Data Passing for Chained Serverless Applications
复制标题
DOI：
--
复制
发表时间：
2021
期刊：
影响因子：
--
通讯作者：
Ashraf Y. Mahgoub;K. Shankar;S. Mitra;Ana Klimovic;S. Chaterji;S. Bagchi
中科院分区：
文献类型：
--
作者：
Ashraf Y. Mahgoub;K. Shankar;S. Mitra;Ana Klimovic;S. Chaterji;S. Bagchi
数据分析应用程序越来越多地利用无服务器的执行环境，以使其易用性和付费账单越来越多，此类应用程序是由在某些工作流中安排的多个功能的。 ）通过远程存储的功能（例如S3）之间的数据引入了大量的性能开销。 . Crucally, We show that no single data-passing method prevails under all scenarios and the optimal choice depends on dynamic factors such as the size of input data, the size of intermediate data, the application's degree of parallelism, and network bandwidth. We propose Sonic是一个通过透明地选择“无服务器工作流”的每个边缘的最佳数据填充方法来优化应用程序性能和成本的数据，并实现了通信感知功能。相应的数据，我们将Sonic与OpenLambda集成，并在Amazon EC2上使用三个分析应用程序，在无服务器环境中流行。 Sand [Usenixatc -18]，Vanilla Openlambda [HotCloud-16]，Openlambda与Pocket [OSDI-18]和AWS Lambda（实践状态）集成在一起。
Data analytics applications are increasingly leveraging serverless execution environments for their ease-of-use and pay-as-you-go billing. Increasingly, such applications are composed of multiple functions arranged in some workflow. However, the current approach of exchanging intermediate (ephemeral) data between functions through remote storage (such as S3) introduces significant performance overhead. We show that there are three alternative data-passing methods, which we call VM-Storage, Direct-Passing, and state-ofpractice Remote-Storage. Crucially, we show that no single data-passing method prevails under all scenarios and the optimal choice depends on dynamic factors such as the size of input data, the size of intermediate data, the application’s degree of parallelism, and network bandwidth. We propose SONIC, a data-passing manager that optimizes application performance and cost, by transparently selecting the optimal datapassing method for each edge of a serverless workflow DAG and implementing communication-aware function placement. SONIC monitors application parameters and uses simple regression models to adapt its hybrid data passing accordingly. We integrate SONIC with OpenLambda and evaluate the system on Amazon EC2 with three analytics applications, popular in the serverless environment. SONIC provides lower latency (raw performance) and higher performance/$ across diverse conditions, compared to four different baselines: SAND [UsenixATC-18], Vanilla OpenLambda [HotCloud-16], OpenLambda integrated with Pocket [OSDI-18], and AWS Lambda (state of practice).