Just find out set features.quota-timeout to an acceptable value like 30 significantly helps. for example:
sudo gluster volume set test_replica2_dis4 features.quota-timeout 30 -sh-4.1$ sudo dd if=/dev/zero of=/mnt/iotest/xferd bs=1M count=2000 2000+0 records in 2000+0 records out 2097152000 bytes (2.1 GB) copied, 10.4415 s, 201 MB/s 2012/9/29 符永涛 <yongta...@gmail.com> > Dear gluster experts, > > We have encountered a severe performance issue related to quota feature of > gluster. > > My underlying fs is lvm with xfs format. > The problem is if quota is enabled the io performance is about 26MB/s but > with quota disabled the io performance is 216MB/s. > Any one known what's the problem? BTW I have reproduce it several times > and it is related to quota indeed. > > Here's the test: > > __________________quota enabled________________________________________ > > -sh-4.1$ sudo gluster volume info test_replica2_dis4 > > Volume Name: test_replica2_dis4 > Type: Distributed-Replicate > Volume ID: 9004b9d8-88f9-4312-9c22-1f1a62fd9784 > Status: Started > Number of Bricks: 4 x 2 = 8 > Transport-type: tcp > Bricks: > Brick1: > bjzw.miaoyan.cluster1.node1.qiyi.domain:/mnt/xfsd/test_replica2_dis4 > Brick2: > bjzw.miaoyan.cluster1.node2.qiyi.domain:/mnt/xfsd/test_replica2_dis4 > Brick3: > bjzw.miaoyan.cluster1.node3.qiyi.domain:/mnt/xfsd/test_replica2_dis4 > Brick4: > bjzw.miaoyan.cluster1.node4.qiyi.domain:/mnt/xfsd/test_replica2_dis4 > Brick5: > bjzw.miaoyan.cluster1.node5.qiyi.domain:/mnt/xfsd/test_replica2_dis4 > Brick6: > bjzw.miaoyan.cluster1.node6.qiyi.domain:/mnt/xfsd/test_replica2_dis4 > Brick7: > bjzw.miaoyan.cluster1.node7.qiyi.domain:/mnt/xfsd/test_replica2_dis4 > Brick8: > bjzw.miaoyan.cluster1.node8.qiyi.domain:/mnt/xfsd/test_replica2_dis4 > Options Reconfigured: > features.limit-usage: /:5TB > features.quota: enable > -sh-4.1$ sudo dd if=/dev/zero of=iotest/testfff2 bs=1M count=1000 > 1000+0 records in > 1000+0 records out > 1048576000 bytes (1.0 GB) copied, 40.3801 s, 26.0 MB/s > ______________________________________________________________________ > > > __________________quota disabled________________________________________ > > -sh-4.1$ sudo gluster volume info test_replica2_dis4 > > Volume Name: test_replica2_dis4 > Type: Distributed-Replicate > Volume ID: 9004b9d8-88f9-4312-9c22-1f1a62fd9784 > Status: Started > Number of Bricks: 4 x 2 = 8 > Transport-type: tcp > Bricks: > Brick1: > bjzw.miaoyan.cluster1.node1.qiyi.domain:/mnt/xfsd/test_replica2_dis4 > Brick2: > bjzw.miaoyan.cluster1.node2.qiyi.domain:/mnt/xfsd/test_replica2_dis4 > Brick3: > bjzw.miaoyan.cluster1.node3.qiyi.domain:/mnt/xfsd/test_replica2_dis4 > Brick4: > bjzw.miaoyan.cluster1.node4.qiyi.domain:/mnt/xfsd/test_replica2_dis4 > Brick5: > bjzw.miaoyan.cluster1.node5.qiyi.domain:/mnt/xfsd/test_replica2_dis4 > Brick6: > bjzw.miaoyan.cluster1.node6.qiyi.domain:/mnt/xfsd/test_replica2_dis4 > Brick7: > bjzw.miaoyan.cluster1.node7.qiyi.domain:/mnt/xfsd/test_replica2_dis4 > Brick8: > bjzw.miaoyan.cluster1.node8.qiyi.domain:/mnt/xfsd/test_replica2_dis4 > Options Reconfigured: > features.limit-usage: /:5TB > features.quota: disable > -sh-4.1$ sudo dd if=/dev/zero of=iotest/testfff2 bs=1M count=1000 > 1000+0 records in > 1000+0 records out > 1048576000 bytes (1.0 GB) copied, 4.86384 s, 216 MB/s > ______________________________________________________________________ > > Thank you! > > -- > 符永涛 > -- 符永涛
_______________________________________________ Gluster-users mailing list Gluster-users@gluster.org http://gluster.org/cgi-bin/mailman/listinfo/gluster-users