Jiffy: elastic far-memory for stateful serverless analytics
Jiffy: elastic far-memory for stateful serverless analytics
复制标题
DOI：
10.1145/3492321.3527539
复制
发表时间：
2022-03
期刊：
影响因子：
--
通讯作者：
Anurag Khandelwal;Yupeng Tang;R. Agarwal;Aditya Akella;I. Stoica
中科院分区：
文献类型：
--
作者：
Anurag Khandelwal;Yupeng Tang;R. Agarwal;Aditya Akella;I. Stoica
有状态无服务器分析可以使用远程存储器系统来实现任务间通信，以及存储和交换中间数据。然而，现有的系统分配内存资源在作业粒度--作业指定其内存需求在提交的时间，并且，系统分配的内存等于作业的需求，其整个生命周期。当中间数据大小在作业执行期间发生变化时，这会导致资源利用不足和/或性能下降。本文介绍了Jiffy，这是一个用于有状态无服务器分析的弹性远内存系统，可以满足秒级作业的瞬时内存需求。Jiffy有效地跨并发运行的作业多路复用内存容量，减少了对较慢的持久性存储的读写开销，从而使作业执行时间比生产工作负载提高了1.6 - 2.5倍。Jiffy实现目前在Amazon EC2上运行，支持各种分布式编程模型，包括MapReduce、Dryad、StreamScope和Piccolo，并在AWS Lambda上原生支持大量分析应用程序。
Stateful serverless analytics can be enabled using a remote memory system for inter-task communication, and for storing and exchanging intermediate data. However, existing systems allocate memory resources at job granularity---jobs specify their memory demands at the time of the submission; and, the system allocates memory equal to the job's demand for the entirety of its lifetime. This leads to resource underutilization and/or performance degradation when intermediate data sizes vary during job execution. This paper presents Jiffy, an elastic far-memory system for stateful serverless analytics that meets the instantaneous memory demand of a job at seconds timescales. Jiffy efficiently multiplexes memory capacity across concurrently running jobs, reducing the overheads of reads and writes to slower persistent storage, resulting in 1.6 -- 2.5× improvements in job execution time over production workloads. Jiffy implementation currently runs on Amazon EC2, enables a wide variety of distributed programming models including MapReduce, Dryad, StreamScope, and Piccolo, and natively supports a large class of analytics applications on AWS Lambda.