iostat来对linux硬盘io性能进行了解（Iostat to understand the performance of Linux hard disk IO）.docVIP

下载本文档

5
0
约7.05千字
约 7页
2017-09-05 发布于河南
举报
版权申诉

iostat来对linux硬盘io性能进行了解（Iostat to understand the performance of Linux hard disk IO）.doc

1、原创力文档（book118）网站文档一经付费（服务费），不意味着购买了该文档的版权，仅供个人/单位学习、研究之用，不得用于商业用途，未经授权，严禁复制、发行、汇编、翻译或者网络传播等，侵权必究。。
2、本站所有内容均由合作方或网友上传，本站不对文档的完整性、权威性及其观点立场正确性做任何保证或承诺！文档内容仅供研究参考，付费前请自行鉴别。如您付费，意味着您自己接受本站规则且自行承担风险，本站不退款、不进行额外附加服务；查看《如何避免下载的几个坑》。如果您已付费下载过本站文档，您可以点击这里二次下载。
3、如文档侵犯商业秘密、侵犯著作权、侵犯人身权等，请点击“版权申诉”（推荐），也可以打举报电话：400-050-0827(电话支持时间：9:00-18:30)。
4、该文档为VIP文档，如果想要下载，成为VIP会员后，下载免费。
5、成为VIP后，下载本文档将扣除1次下载权益。下载后，不支持退款、换文档。如有疑问请联系我们。
6、成为VIP后，您将拥有八大权益，权益包括：VIP文档下载权益、阅读免打扰、文档格式转换、高级专利检索、专属身份标志、高级客服、多端互通、版权登记。
7、VIP文档为合作方或网友上传，每下载1次，网站将根据用户上传文档的质量评分、类型等，对文档贡献者给予高额补贴、流量扶持。如果你也想贡献VIP文档。上传文档

iostat来对linux硬盘io性能进行了解（Iostat to understand the performance of Linux hard disk IO）

iostat来对linux硬盘io性能进行了解（Iostat to understand the performance of Linux hard disk IO） Iostat for the understanding of the Linux hard disk IO performance Feb 3rd, 2009 Leave a comment Trackback | reprint this article please indicate, reprinted from: Fu Kai [] This link: /2009/02/03/iostat.html Never too will use this parameter. Now carefully studying iostat, just because the server pressure is high, so put up analysis. The following is a IO server too much pressure $iostat -x 1 Linux 2.6.33-fukai (fukai-laptop) _i686_ (2 CPU) Avg-cpu:%user%nice%system%iowait%steal%idle 5.47 0.50 8.96 48.26 0 36.82 Device: rrqm/s wrqm/s r/s w/s rsec/s wsec/s avgrq-sz avgqu-sz await svctm%util SDA 6 273 99 7 2240 2240 42.26 1.12 10.57 7.96 84.40 SDB 0 4 0 350 0 2068 5.91 0.55 1.58 0.54 18.80 Rrqm/s: merge the number of reads per second. Delta (rmerge) /s The number of wrqm/s: per second operation to write merge. Delta (wmerge) /s Read I/O r/s: complete the number of devices per second. Delta (Rio) /s W/s: finished writing I/O device number per second. Delta (WIO) /s Rsec/s: read the number of sectors per second. Delta (rsect) /s Wsec/s: write the number of sectors per second. Delta (wsect) /s RkB/s: read K bytes per second. Rsect/s is half, because each sector size of 512 bytes. (calculated) WkB/s: write K bytes per second. Wsect/s is half. (calculated) Avgrq-sz: average I/O equipment data size (sector). Delta (rsect+wsect) /delta (rio+wio) The average queue length of I/O avgqu-sz. Delta (aveq) /s/1000 (for aveq milliseconds). The average waiting time of await: equipment I/O operation (MS). Delta (ruse+wuse) /delta (rio+wio) Svctm: average equipment operation I/O Business Hours (MS). Delta (use) /delta (rio+wio) A second%util: how many percent of the time for the I/O operation, or a second how much time the I/O queue is not empty. Delta (use) /s/1000 (for use milliseconds) If the%util is close to 100%, showing that the I/O request is too much, the I/O system has full load, the disk There