glusterfs多节点读写性能测试Word文件下载.docx

1、eth0设置固定，eth1、eth2、eth3三个网口做bond0，ip设为 ，四个网口四根网线连接到交换机上。系统节点：IP 别名 Brick data-node3 /brick/brick1/ data-node4 /brick/brick1/ data-node5 /brick/brick1/ data-node6 /brick/brick1/ data-client测试目的： 测试不同节点数下使用glusterfs建立stripe卷 挂载到3网口做bond0的client端上，测试他的读写性能 测试方法测试工具： dd fio测试方法：不同节点数下建立stripe卷，挂载到client

2、端使用dd命令测试他的吞吐量,fio测试iops测试过程测试步骤1、添加信任池gluster peer probe data-node3gluster peer probe data-node4gluster peer probe data-node5gluster peer probe data-node62、创建stripe卷 两个节点gluster volume create test stripe 2 data-node4:/brick/brick1/testw data-node3:/brick/brick1/testw 三个节点gluster volume create test1

3、 stripe 3 data-node4:/brick/brick1/test data-node3:/brick/brick1/test data-node5:/brick/brick1/test四个节点gluster volume create test2 stripe 4 data-node4:/brick/brick1/teste data-node3:/brick/brick1/teste data-node5:/brick/brick1/teste data-node6:/brick/brick1/teste3、启动stripe卷gluster volume start testg

4、luster volume start test1gluster volume start test25、挂载到client端 data-node3:/test /mnt6、使用dd命令测试吞吐率dd if=/dev/zero of=/mnt/ bs=1M count=600007、使用fio测试iops测试脚本#!/bin/bashcd /mntsleep 10rm -rf test*sleep 30cd /usr/local/bin/fio -name=/mnt/test -direct=0 -iodepth=96 -rw=randread -ioengine=posixaio -bs=4

5、k -size=16G -numjobs=20 -runtime=3600 -group_reporting /fiotest/sleep 100sleep 60sleep 300umount testpoolmount -t glusterfs data-node3:/test /mnt/usr/local/bin/fio -name=/mnt/test -direct=0 -iodepth=96 -rw=randwrite -ioengine=posixaio -bs=4k -size=16G -numjobs=20 -runtime=3600 -group_reporting /usr/

6、local/bin/fio -name=/mnt/test -direct=0 -iodepth=96 -rw=randread -ioengine=posixaio -bs=8k -size=16G -numjobs=20 -runtime=3600 -group_reporting /usr/local/bin/fio -name=/mnt/test -direct=0 -iodepth=96 -rw=randwrite -ioengine=posixaio -bs=8k -size=16G -numjobs=20 -runtime=3600 -group_reporting /usr/l

7、ocal/bin/fio -name=/mnt/test -direct=0 -iodepth=96 -rw=randread -ioengine=posixaio -bs=16k -size=16G -numjobs=20 -runtime=3600 -group_reporting /usr/local/bin/fio -name=/mnt/test -direct=0 -iodepth=96 -rw=randwrite -ioengine=posixaio -bs=16k -size=16G -numjobs=20 -runtime=3600 -group_reporting /usr/

8、local/bin/fio -name=/mnt/test -direct=0 -iodepth=96 -rw=randread -ioengine=posixaio -bs=32k -size=16G -numjobs=20 -runtime=3600 -group_reporting /usr/local/bin/fio -name=/mnt/test -direct=0 -iodepth=96 -rw=randwrite -ioengine=posixaio -bs=32k -size=16G -numjobs=20 -runtime=3600 -group_reporting /usr

9、/local/bin/fio -name=/mnt/test -direct=0 -iodepth=96 -rw=randread -ioengine=posixaio -bs=64k -size=16G -numjobs=20 -runtime=3600 -group_reporting /usr/local/bin/fio -name=/mnt/test -direct=0 -iodepth=96 -rw=randwrite -ioengine=posixaio -bs=64k -size=16G -numjobs=20 -runtime=3600 -group_reporting 测试结

10、果使用dd命令测试结果：节点数234吞吐率 MB/s135 MB/s335 MB/s使用fio的测试结果：、1）随机读写的iops读写类型块大小iopsrandread4k280s3607228k218 KB/s35360016k21036355932k19335011221KB/s54917581 KB/s64k19512483 KB/s35522782KB/s56536204KB/srandwrite41467413285561104206616532 KB/s38974611945KB/s130320851 KB/s27843914064KB/s69822346KB/s19812713

11、KB/s29819075KB/s42227039KB/siops randread 条形图iops randwrite 条形图2）顺序读写iopsread1844273772KB/s1491659666KB/s26578106315KB/s844267539KB/s783662694KB/s13437107503KB/s421267394KB/s431569042KB/s6656106498KB/s213768396KB/s251280410KB/s3337106811KB/s76649080KB/s141890767KB/s2080133154KB/swrite479819196KB/s1016640665KB/s1969278771KB/s220817666KB/s619049523KB/s1019481552KB/s111917906KB/s273743806KB/s515282436KB/s 57418387KB/s113936471KB/s262784089KB/s27417540KB/s52433594KB/s136487302KB/siops 条形图：