A Generic Service to Provide In-Network Aggregation for Key-Value Streams
A Generic Service to Provide In-Network Aggregation for Key-Value Streams
复制标题
DOI：
10.1145/3575693.3575708
复制
发表时间：
2023-01
期刊：
影响因子：
--
通讯作者：
Yongchao He;Wenfei Wu;Yanfang Le;Ming Liu;Chon-In Lao
中科院分区：
文献类型：
--
作者：
Yongchao He;Wenfei Wu;Yanfang Le;Ming Liu;Chon-In Lao
键值流聚合是分布式系统中的一种常见操作，它需要大量的计算和网络资源。我们提出了一个通用的网络聚合服务的键值流，ASK，以加速聚合操作在不同的分布式应用程序。ASK是一个交换机-主机协同设计的系统，其中可编程交换机提供尽力而为的聚合服务，主机运行守护程序来与应用程序交互。ASK针对流量特性、硬件限制和网络不可靠性进行了深入的优化：将一个数据包在一个交换管道通道中的多个键值元组聚合向量化，提高了每台主机的有效吞吐量;它为键偏斜的工作负载设计了一个与热键无关的优先级，这提高了交换机内存利用率。我们对ASK进行了原型化，并使用它来支持Spark和BytePS。评估表明，ASK可以将纯键值聚合任务加速高达155倍，将大数据任务加速3-5倍，并且向后兼容现有的INA授权的分布式训练解决方案，具有相同的加速比。
Key-value stream aggregation is a common operation in distributed systems, which requires intensive computation and network resources. We propose a generic in-network aggregation service for key-value streams, ASK, to accelerate the aggregation operations in diverse distributed applications. ASK is a switch-host co-designed system, where the programmable switch provides a best-effort aggregation service, and the host runs a daemon to interact with applications. ASK makes in-depth optimization tailored to traffic characteristics, hardware restrictions, and network unreliable natures: it vectorizes multiple key-value tuples’ aggregation of one packet in one switch pipeline pass, which improves the per-host’s goodput; it develops a lightweight reliability mechanism for key-value stream’s asynchronous aggregation, which guarantees computation correctness; it designs a hot-key agnostic prioritization for key-skewed workloads, which improves the switch memory utilization. We prototype ASK and use it to support Spark and BytePS. The evaluation shows that ASK could accelerate pure key-value aggregation tasks by up to 155 times and big data jobs by 3-5 times, and be backward compatible with existing INA-empowered distributed training solutions with the same speedup.