summaryrefslogtreecommitdiffstats
diff options
context:
space:
mode:
authorDustin Black <dblack@redhat.com>2016-06-14 09:53:31 -0400
committerNiels de Vos <ndevos@redhat.com>2016-06-14 07:26:38 -0700
commit7b972c02d6fd96ef85fff4518f4122341ab5c6b0 (patch)
tree90c0e5a8c90d9e5d5c047556828a33963fe95d5a
parent375c82dd7b73acb57197bda5e73c075c13c78533 (diff)
Added release notes for Compound Ops & Geo-rep for Shard
Change-Id: I4f5a92e9551d86e38512cf79dd04458806646272 BUG: 1317278 Signed-off-by: Dustin Black <dblack@redhat.com> Reviewed-on: http://review.gluster.org/14731 NetBSD-regression: NetBSD Build System <jenkins@build.gluster.org> CentOS-regression: Gluster Build System <jenkins@build.gluster.org> Reviewed-by: jiffin tony Thottan <jthottan@redhat.com> Smoke: Gluster Build System <jenkins@build.gluster.org> Reviewed-by: Niels de Vos <ndevos@redhat.com>
-rw-r--r--doc/release-notes/3.8.0.md22
1 files changed, 22 insertions, 0 deletions
diff --git a/doc/release-notes/3.8.0.md b/doc/release-notes/3.8.0.md
index 3f06a5e9ef5..0834a985799 100644
--- a/doc/release-notes/3.8.0.md
+++ b/doc/release-notes/3.8.0.md
@@ -80,6 +80,28 @@ sharding has not been implemented yet, and is expected to follow later in a 3.8
update (bug 1301647). NFS-Ganesha will support SEEK over NFSv4 in the near
future, posisbly with the upcoming nfs-ganesha 2.4.
+### Compound operations
+*Notes for users:*
+This feature is being introduced with the intention of improving performance
+for file operations on a glusterfs volume. A framework for combining two or
+more file operations is provided which will help in reducing the network round
+trips made for certain fops. This reduces latency of those fops and provides
+better performance than before.
+
+*Limitations:*
+Only very few and specific sets of operations can be compounded at this time.
+There is no interface in libgfapi for creating compound operations yet.
+
+### Geo-replication for Sharded Volumes
+*Notes for users:*
+With Sharding support, Geo-replication detects small sharded files and syncs to
+the slave(s) instead of syncing big files. This enables Geo-rep to sync files
+from the master volume to the slave volume(s) more efficiently.
+
+*Limitations:*
+If Sharding is enabled at the master volume then it should be enabled at slave
+volume as well.
+
### Tiering aware Geo-replication
*Notes for users:*
Tiering moves files between hot/cold tier bricks. Geo-replication syncs files