Description of problem: md-cache on the server stack can help in avoiding stat and xattr calls from reaching the kernel & disks underneath gluster. This bug will track loading of md-cache on the server Version-Release number of selected component (if applicable): mainline
REVIEW: http://review.gluster.org/10127 (performance/md-cache: set right error check in {f}getxattr_cbk()) posted (#1) for review on master by Vijay Bellur (vbellur)
COMMIT: http://review.gluster.org/10127 committed in master by Kaleb KEITHLEY (kkeithle) ------ commit 0e23ce3fbcf1f138105476cf3b86342268e259d9 Author: Vijay Bellur <vbellur> Date: Fri Apr 3 14:14:35 2015 +0530 performance/md-cache: set right error check in {f}getxattr_cbk() Currently mdc_{f}getxattr_cbk() check(s) for a non-zero value to determine if any cache update has to be performed. Right from posix xlator, op_ret has a positive value upon success and -1 upon failure. This patch sets right the check in getxattr callbacks so that xattr cache update happens for successful calls. Change-Id: Ifa5ec38bdf7e3dc095de9a56d91559b13cd9e8b6 BUG: 1208784 Signed-off-by: Vijay Bellur <vbellur> Reviewed-on: http://review.gluster.org/10127 Tested-by: Gluster Build System <jenkins.com> Reviewed-by: Raghavendra Talur <rtalur>
This bug is getting closed because a release has been made available that should address the reported issue. In case the problem is still not fixed with glusterfs-3.7.0, please open a new bug report. glusterfs-3.7.0 has been announced on the Gluster mailinglists [1], packages for several distributions should become available in the near future. Keep an eye on the Gluster Users mailinglist [2] and the update infrastructure for your distribution. [1] http://thread.gmane.org/gmane.comp.file-systems.gluster.devel/10939 [2] http://thread.gmane.org/gmane.comp.file-systems.gluster.user