+++ This bug was initially created as a clone of Bug #1384906 +++ Description of problem: Max Raba reported that arbiter volume write performance is bad with sharding. See BZ 1375125 --- Additional comment from Worker Ant on 2016-10-14 06:58:54 EDT --- REVIEW: http://review.gluster.org/15641 (afr: Take full locks in arbiter only for data transactions) posted (#1) for review on master by Ravishankar N (ravishankar) --- Additional comment from Worker Ant on 2016-10-14 13:18:40 EDT --- COMMIT: http://review.gluster.org/15641 committed in master by Pranith Kumar Karampuri (pkarampu) ------ commit 3a97486d7f9d0db51abcb13dcd3bc9db935e3a60 Author: Ravishankar N <ravishankar> Date: Fri Oct 14 16:09:08 2016 +0530 afr: Take full locks in arbiter only for data transactions Problem: Sharding exposed a bug in arbiter config. where `dd` throughput was extremely slow. Shard xlator was sending a fxattrop to update the file size immediately after a writev. Arbiter was incorrectly over-riding the LLONGMAX-1 start offset (for metadata domain locks) for this fxattrop, causing the inodelk to be taken on the data domain. And since the preceeding writev hadn't released the lock (afr does a 'lazy' unlock if write succeeds on all bricks), this degraded to a blocking lock causing extra lock/unlock calls and delays. Fix: Modify flock.l_len and flock.l_start to take full locks only for data transactions. Change-Id: I906895da2f2d16813607e6c906cb4defb21d7c3b BUG: 1384906 Signed-off-by: Ravishankar N <ravishankar> Reported-by: Max Raba <max.raba> Reviewed-on: http://review.gluster.org/15641 Smoke: Gluster Build System <jenkins.org> NetBSD-regression: NetBSD Build System <jenkins.org> CentOS-regression: Gluster Build System <jenkins.org> Reviewed-by: Pranith Kumar Karampuri <pkarampu>
REVIEW: http://review.gluster.org/15648 (afr: Take full locks in arbiter only for data transactions) posted (#1) for review on release-3.9 by Ravishankar N (ravishankar)
COMMIT: http://review.gluster.org/15648 committed in release-3.9 by Pranith Kumar Karampuri (pkarampu) ------ commit 0cd21d981f469c3cdc57dcd84802ced1a9f34155 Author: Ravishankar N <ravishankar> Date: Fri Oct 14 16:09:08 2016 +0530 afr: Take full locks in arbiter only for data transactions Problem: Sharding exposed a bug in arbiter config. where `dd` throughput was extremely slow. Shard xlator was sending a fxattrop to update the file size immediately after a writev. Arbiter was incorrectly over-riding the LLONGMAX-1 start offset (for metadata domain locks) for this fxattrop, causing the inodelk to be taken on the data domain. And since the preceeding writev hadn't released the lock (afr does a 'lazy' unlock if write succeeds on all bricks), this degraded to a blocking lock causing extra lock/unlock calls and delays. Fix: Modify flock.l_len and flock.l_start to take full locks only for data transactions. > Reviewed-on: http://review.gluster.org/15641 > Smoke: Gluster Build System <jenkins.org> > NetBSD-regression: NetBSD Build System <jenkins.org> > CentOS-regression: Gluster Build System <jenkins.org> > Reviewed-by: Pranith Kumar Karampuri <pkarampu> (cherry picked from commit 3a97486d7f9d0db51abcb13dcd3bc9db935e3a60) Change-Id: I906895da2f2d16813607e6c906cb4defb21d7c3b BUG: 1385224 Signed-off-by: Ravishankar N <ravishankar> Reported-by: Max Raba <max.raba> Reviewed-on: http://review.gluster.org/15648 NetBSD-regression: NetBSD Build System <jenkins.org> Reviewed-by: Pranith Kumar Karampuri <pkarampu> CentOS-regression: Gluster Build System <jenkins.org> Smoke: Gluster Build System <jenkins.org>
glusterfs-3.9.0rc2 is released[1] and packages are available for different distributions[2] to test. [1] http://www.gluster.org/pipermail/maintainers/2016-October/001601.html [2] http://www.gluster.org/pipermail/maintainers/2016-October/001605.html and http://www.gluster.org/pipermail/maintainers/2016-October/001606.html
Gluster 3.9 GA is released http://blog.gluster.org/2016/11/announcing-gluster-3-9/