Description of problem: Enumerations of large directories are slow with Samba/SMB on top of Gluster compared to NFS and native client. On the other hand, on local file systems, SMB is fast. More details to follow.
List of patches: RHGS 3.2: https://code.engineering.redhat.com/gerrit/87024 Upstream master: http://review.gluster.org/12995 RHGS 3.2: https://code.engineering.redhat.com/gerrit/87025 Upstream master: http://review.gluster.org/12996 RHGS 3.2: https://code.engineering.redhat.com/gerrit/87026 Upstream master: http://review.gluster.org/14824 RHGS 3.2: https://code.engineering.redhat.com/gerrit/87027 Upstream master: http://review.gluster.org/14828 RHGS 3.2: https://code.engineering.redhat.com/gerrit/87028 Upstream master: http://review.gluster.org/14879 RHGS 3.2: https://code.engineering.redhat.com/gerrit/87029 Upstream master: http://review.gluster.org/12951 RHGS 3.2: https://code.engineering.redhat.com/gerrit/87030 Upstream master: http://review.gluster.org/14971 RHGS 3.2: https://code.engineering.redhat.com/gerrit/87031 Upstream master: http://review.gluster.org/15043 RHGS 3.2: https://code.engineering.redhat.com/gerrit/87032 Upstream master: http://review.gluster.org/15069 RHGS 3.2: https://code.engineering.redhat.com/gerrit/87033 Upstream master: http://review.gluster.org/15185 RHGS 3.2: https://code.engineering.redhat.com/gerrit/87034 Upstream master: http://review.gluster.org/15314 RHGS 3.2: https://code.engineering.redhat.com/gerrit/87035 Upstream master: http://review.gluster.org/15045 RHGS 3.2: https://code.engineering.redhat.com/gerrit/87036 Upstream master: http://review.gluster.org/15331 RHGS 3.2: https://code.engineering.redhat.com/gerrit/87037 Upstream master: http://review.gluster.org/15225 RHGS 3.2: https://code.engineering.redhat.com/gerrit/87038 Upstream master: http://review.gluster.org/15224 RHGS 3.2: https://code.engineering.redhat.com/gerrit/87039 Upstream master: http://review.gluster.org/15301 RHGS 3.2: https://code.engineering.redhat.com/gerrit/87040 Upstream master: http://review.gluster.org/15002 RHGS 3.2: https://code.engineering.redhat.com/gerrit/87041 Upstream master: http://review.gluster.org/15300 RHGS 3.2: https://code.engineering.redhat.com/gerrit/87042 Upstream master: http://review.gluster.org/15324 RHGS 3.2: https://code.engineering.redhat.com/gerrit/87043 Upstream master: http://review.gluster.org/15313 RHGS 3.2: https://code.engineering.redhat.com/gerrit/87044 Upstream master: http://review.gluster.org/15193 RHGS 3.2: https://code.engineering.redhat.com/gerrit/87045 Upstream master: http://review.gluster.org/15387 RHGS 3.2: https://code.engineering.redhat.com/gerrit/87046 Upstream master: http://review.gluster.org/15378 RHGS 3.2: https://code.engineering.redhat.com/gerrit/87047 Upstream master: http://review.gluster.org/15398
Marking this verified. Ls -l tests for me showed: Before MD Cache - 10m41.861 After MD Cache - 1m45.756s
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://rhn.redhat.com/errata/RHSA-2017-0486.html
The needinfo request[s] on this closed bug have been removed as they have been unresolved for 1000 days