Hermit: Low-Latency, High-Throughput, and Transparent Remote Memory via Feedback-Directed Asynchrony
Hermit: Low-Latency, High-Throughput, and Transparent Remote Memory via Feedback-Directed Asynchrony
复制标题
DOI：
--
复制
发表时间：
2023
期刊：
影响因子：
--
通讯作者：
Yifan Qiao;Chenxi Wang;Zhenyuan Ruan;A. Belay;Q. Lu;Yiying Zhang;Miryung Kim;Guoqing Harry Xu
中科院分区：
文献类型：
--
作者：
Yifan Qiao;Chenxi Wang;Zhenyuan Ruan;A. Belay;Q. Lu;Yiying Zhang;Miryung Kim;Guoqing Harry Xu
远程存储器技术在数据中心中获得了牵引力，因为它们可以显着改善内存利用率。不幸的是，当前的实现遭受了较高的软件间接费用，导致相对于本地记忆的尾部潜伏期和吞吐量的显着性较差但是，耗时的操作（例如，交换，cgroup充电，I/O重复程序等）远离了故障处理路径，并与先前的工作（例如FastSwap）不同，Hermit会收集运行时反馈并使用它来使用它直接应如何执行异步操作 - 即，是否应启用异步操作，异步的水平以及如何安排异步操作。例如，低延迟的远程内存。它从36毫秒降低到99毫秒，将第99.7％的人降低到91 µs。用户代码的一行。
Remote memory techniques are gaining traction in datacenters because they can significantly improve memory utilization. A popular approach is to use kernel-level, page-based memory swapping to deliver remote memory as it is transparent, enabling existing applications to benefit without modifi-cations. Unfortunately, current implementations suffer from high software overheads, resulting in significantly worse tail latency and throughput relative to local memory. Hermit is a redesigned swap system that overcomes this limitation through a novel technique called adaptive, feedback-directed asynchrony . It takes non-urgent but time-consuming operations ( e.g. , swap-out, cgroup charge, I/O deduplication, etc. ) off the fault-handling path and executes them asynchronously. Different from prior work such as Fastswap, Hermit collects runtime feedback and uses it to direct how asynchrony should be performed— i.e. , whether asynchronous operations should be enabled, the level of asynchrony, and how asynchronous operations should be scheduled. We implemented Hermit in Linux 5.14. An evaluation with a set of latency-critical applications shows that Hermit delivers low-latency remote memory. For example, it reduces the 99 th percentile latency of Memcached by 99.7% from 36 ms to 91 µ s . Running Hermit over batch applications improves their overall throughput by 1.24 × on average. These results are achieved without changing a single line of user code.