Downstream patch : https://code.engineering.redhat.com/gerrit/#/c/70346/
With the 3.1.3 build 'glusterfs-3.7.9-1.el7rhgs.x86_64', these are the default values set [root@dhcp47-90 ~]# gluster v get testvol all | grep 'features.ctr-sql-db-wal-autocheckpoint' features.ctr-sql-db-wal-autocheckpoint 25000 [root@dhcp47-90 ~]# gluster v get testvol all | grep 'features.ctr-sql-db-cachesize' features.ctr-sql-db-cachesize 12500 This are the expected values. Additionally, On a tiered volume [cold tier-2 x(8+4) and hot tier 4x2] creation of 50k files takes 10m50s tiered vol: time for i in {1..50000}; do echo $i >> file-$i; done real 10m50.131s user 0m4.090s sys 0m15.571s On a dist-rep volume(4x2), creation of 50k files takes 6m35s time for i in {1..50000}; do echo $i >> file-$i; done real 6m35.411s user 0m3.838s sys 0m16.239s However, Marking this bug as verified as the issue being addressed here is changing the default value of ctr-sql.
Since the problem described in this bug report should be resolved in a recent advisory, it has been closed with a resolution of ERRATA. For information on the advisory, and where to find the updated files, follow the link below. If the solution does not work for you, open a new bug report. https://access.redhat.com/errata/RHBA-2016:1240
*** Bug 1319696 has been marked as a duplicate of this bug. ***