实现终端主机RDMA的最大效益

Xiaoliang Wang, Hexiang Song, Cam-Tu Nguyen, Dongxu Cheng, Tiancheng Jin
{"title":"实现终端主机RDMA的最大效益","authors":"Xiaoliang Wang, Hexiang Song, Cam-Tu Nguyen, Dongxu Cheng, Tiancheng Jin","doi":"10.1109/INFOCOM42981.2021.9488875","DOIUrl":null,"url":null,"abstract":"RDMA is increasingly deployed in data center to meet the demands of ultra-low latency, high throughput and low CPU overhead. However, it is not easy to migrate existing applications from the TCP/IP stack to the RDMA. The developers usually need to carefully select communication primitives and manually tune the parameters for each single-purpose system. After operating the high-speed RDMA network, we identify multiple hidden costs which may cause degraded and/or unpredictable performance of RDMA-based applications. We demonstrate these hidden costs including the combination of complicated parameter settings, scalability of Reliable Connections, two-sided memory management and page alignment, resource contention among diverse traffics, etc. Furthermore, to address these problems, we introduce Nem, a suite that allows developers to maximize the benefit of RDMA by i) eliminating the resource contention at NIC cache through asynchronous resource sharing; ii) introducing hybrid page management based on messages sizes; iii) isolating flows of different traffic classes based hardware features. We implement the prototype of Nem and verify its effectiveness by rebuilding the RPC message service, which demonstrates the high throughput for large messages, low latency for small messages without compromising the low CPU utilization and good scalability performance for a large number of active connections.","PeriodicalId":293079,"journal":{"name":"IEEE INFOCOM 2021 - IEEE Conference on Computer Communications","volume":"33 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2021-05-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"3","resultStr":"{\"title\":\"Maximizing the Benefit of RDMA at End Hosts\",\"authors\":\"Xiaoliang Wang, Hexiang Song, Cam-Tu Nguyen, Dongxu Cheng, Tiancheng Jin\",\"doi\":\"10.1109/INFOCOM42981.2021.9488875\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"RDMA is increasingly deployed in data center to meet the demands of ultra-low latency, high throughput and low CPU overhead. However, it is not easy to migrate existing applications from the TCP/IP stack to the RDMA. The developers usually need to carefully select communication primitives and manually tune the parameters for each single-purpose system. After operating the high-speed RDMA network, we identify multiple hidden costs which may cause degraded and/or unpredictable performance of RDMA-based applications. We demonstrate these hidden costs including the combination of complicated parameter settings, scalability of Reliable Connections, two-sided memory management and page alignment, resource contention among diverse traffics, etc. Furthermore, to address these problems, we introduce Nem, a suite that allows developers to maximize the benefit of RDMA by i) eliminating the resource contention at NIC cache through asynchronous resource sharing; ii) introducing hybrid page management based on messages sizes; iii) isolating flows of different traffic classes based hardware features. We implement the prototype of Nem and verify its effectiveness by rebuilding the RPC message service, which demonstrates the high throughput for large messages, low latency for small messages without compromising the low CPU utilization and good scalability performance for a large number of active connections.\",\"PeriodicalId\":293079,\"journal\":{\"name\":\"IEEE INFOCOM 2021 - IEEE Conference on Computer Communications\",\"volume\":\"33 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2021-05-10\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"3\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"IEEE INFOCOM 2021 - IEEE Conference on Computer Communications\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/INFOCOM42981.2021.9488875\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"IEEE INFOCOM 2021 - IEEE Conference on Computer Communications","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/INFOCOM42981.2021.9488875","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 3

摘要

RDMA越来越多地应用于数据中心,以满足超低延迟、高吞吐量和低CPU开销的需求。然而,将现有的应用程序从TCP/IP栈迁移到RDMA并不容易。开发人员通常需要仔细选择通信原语,并手动调整每个单一用途系统的参数。在运行高速RDMA网络后,我们确定了多个隐藏成本,这些成本可能导致基于RDMA的应用程序性能下降和/或不可预测。我们展示了这些隐藏成本,包括复杂参数设置的组合、可靠连接的可扩展性、双边内存管理和页面对齐、不同流量之间的资源争用等。此外,为了解决这些问题,我们引入了Nem,这是一个套件,允许开发人员通过以下方式最大化RDMA的好处:1)通过异步资源共享消除NIC缓存中的资源争用;Ii)引入基于消息大小的混合页面管理;Iii)基于硬件特性隔离不同流量类别的流。我们实现了Nem的原型,并通过重新构建RPC消息服务验证了其有效性,这证明了大消息的高吞吐量,小消息的低延迟,而不影响低CPU利用率和大量活动连接的良好可伸缩性性能。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
Maximizing the Benefit of RDMA at End Hosts
RDMA is increasingly deployed in data center to meet the demands of ultra-low latency, high throughput and low CPU overhead. However, it is not easy to migrate existing applications from the TCP/IP stack to the RDMA. The developers usually need to carefully select communication primitives and manually tune the parameters for each single-purpose system. After operating the high-speed RDMA network, we identify multiple hidden costs which may cause degraded and/or unpredictable performance of RDMA-based applications. We demonstrate these hidden costs including the combination of complicated parameter settings, scalability of Reliable Connections, two-sided memory management and page alignment, resource contention among diverse traffics, etc. Furthermore, to address these problems, we introduce Nem, a suite that allows developers to maximize the benefit of RDMA by i) eliminating the resource contention at NIC cache through asynchronous resource sharing; ii) introducing hybrid page management based on messages sizes; iii) isolating flows of different traffic classes based hardware features. We implement the prototype of Nem and verify its effectiveness by rebuilding the RPC message service, which demonstrates the high throughput for large messages, low latency for small messages without compromising the low CPU utilization and good scalability performance for a large number of active connections.
求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
自引率
0.00%
发文量
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信