Can someone explain why there are a big read performance difference {ls -l)
on a glusterfs mount-point than on the bricks mount-point?[root@pdsraid5 ~]# gluster volume info Volume Name: gv0 Type: Replicate Volume ID: b3052157-b234-45a6-b4f4-ceacf9390567 Status: Started Number of Bricks: 1 x 2 = 2 Transport-type: tcp Bricks: Brick1: pdsraid5:/export/pdsdata1 Brick2: pdsmirror1:/export/pdsdata1 [root@pdsraid5 ~]# [root@pdsraid5 ~]# df -h Filesystem Size Used Avail Use% Mounted on /dev/sdb1 19T 1.3T 18T 7% /export/pdsdata1 pdsraid5:/gv0 19T 1.3T 18T 7% /export/pdsdata [root@pdsraid5 ]# time ls -lR /export/pdsdata1/marci real 0m0.465s user 0m0.126s sys 0m0.337s [root@pdsraid5 ]# time ls -lR /export/pdsdata/marci real 0m37.429s user 0m0.228s sys 0m1.031s
_______________________________________________ Gluster-users mailing list [email protected] http://supercolony.gluster.org/mailman/listinfo/gluster-users
