利用RDMA增强NFSv4的性能

Fourth International Workshop on Storage Network Architecture and Parallel I/Os (SNAPI 2007) Pub Date : 2007-09-24 DOI:10.1109/SNAPI.2007.21

R. Noronha, Lei Chai, S. Shepler, D. Panda

{"title":"利用RDMA增强NFSv4的性能","authors":"R. Noronha, Lei Chai, S. Shepler, D. Panda","doi":"10.1109/SNAPI.2007.21","DOIUrl":null,"url":null,"abstract":"NFS is a widely deployed storage technology. It has gone through several revisions. One of the latest revisions, v4 has started to become deployed. NFSv4 on OpenSolaris uses TCP as the underlying transport. This has limited its performance. In this paper, we take on the challenge of designing an RDMA transport for NFSv4. Challenges include COMPOUND procedures, which might potentially have unbounded request and reply sizes. Performance evaluation shows that NFSv4 can achieve an IOzone Read throughput of over 700 MB/s and an IOzone Write bandwidth of over 500 MB/s. It also significantly outperforms NFSv4/TCP","PeriodicalId":347839,"journal":{"name":"Fourth International Workshop on Storage Network Architecture and Parallel I/Os (SNAPI 2007)","volume":"76 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2007-09-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"6","resultStr":"{\"title\":\"Enhancing the Performance of NFSv4 with RDMA\",\"authors\":\"R. Noronha, Lei Chai, S. Shepler, D. Panda\",\"doi\":\"10.1109/SNAPI.2007.21\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"NFS is a widely deployed storage technology. It has gone through several revisions. One of the latest revisions, v4 has started to become deployed. NFSv4 on OpenSolaris uses TCP as the underlying transport. This has limited its performance. In this paper, we take on the challenge of designing an RDMA transport for NFSv4. Challenges include COMPOUND procedures, which might potentially have unbounded request and reply sizes. Performance evaluation shows that NFSv4 can achieve an IOzone Read throughput of over 700 MB/s and an IOzone Write bandwidth of over 500 MB/s. It also significantly outperforms NFSv4/TCP\",\"PeriodicalId\":347839,\"journal\":{\"name\":\"Fourth International Workshop on Storage Network Architecture and Parallel I/Os (SNAPI 2007)\",\"volume\":\"76 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2007-09-24\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"6\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Fourth International Workshop on Storage Network Architecture and Parallel I/Os (SNAPI 2007)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/SNAPI.2007.21\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Fourth International Workshop on Storage Network Architecture and Parallel I/Os (SNAPI 2007)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/SNAPI.2007.21","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}

引用次数: 6

摘要

NFS是一种广泛应用的存储技术。它经过了几次修改。作为最新版本之一，v4已经开始部署。OpenSolaris上的NFSv4使用TCP作为底层传输。这限制了它的性能。在本文中，我们承担了为NFSv4设计RDMA传输的挑战。挑战包括COMPOUND过程，它可能具有无限的请求和应答大小。性能评估表明，NFSv4可实现IOzone读吞吐量700mb /s以上，IOzone写带宽500mb /s以上。它也明显优于NFSv4/TCP

本文章由计算机程序翻译，如有差异，请以英文原文为准。

查看原文本刊更多论文

Enhancing the Performance of NFSv4 with RDMA

NFS is a widely deployed storage technology. It has gone through several revisions. One of the latest revisions, v4 has started to become deployed. NFSv4 on OpenSolaris uses TCP as the underlying transport. This has limited its performance. In this paper, we take on the challenge of designing an RDMA transport for NFSv4. Challenges include COMPOUND procedures, which might potentially have unbounded request and reply sizes. Performance evaluation shows that NFSv4 can achieve an IOzone Read throughput of over 700 MB/s and an IOzone Write bandwidth of over 500 MB/s. It also significantly outperforms NFSv4/TCP

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

Fourth International Workshop on Storage Network Architecture and Parallel I/Os (SNAPI 2007)

自引率

0.00%

发文量