[Bugs] [Bug 1366817] AFR returns the node uuid of the same node for every file in the replica

bugzilla at redhat.com bugzilla at redhat.com
Tue May 16 16:01:45 UTC 2017


https://bugzilla.redhat.com/show_bug.cgi?id=1366817



--- Comment #28 from Worker Ant <bugzilla-bot at gluster.org> ---
COMMIT: https://review.gluster.org/17239 committed in master by Shyamsundar
Ranganathan (srangana at redhat.com) 
------
commit b23bd3dbc2c153171d0bb1205e6804afe022a55f
Author: N Balachandran <nbalacha at redhat.com>
Date:   Wed May 10 21:26:28 2017 +0530

    cluster/dht: Rebalance on all nodes should migrate files

    Problem:
    Rebalance compares the node-uuid of a file against its own
    to and migrates a file only if they match. However, the
    current behaviour in both AFR and EC is to return
    the node-uuid of the first brick in a replica set for all
    files. This means a single node ends up migrating all
    the files if the first brick of every replica set is on the
    same node.

    Fix:
    AFR and EC will return all node-uuids for the replica set.
    The rebalance process will divide the files to be migrated
    among all the nodes by hashing the gfid of the file and
    using that value to select a node to perform the migration.
    This patch makes the required DHT and tiering changes.

    Some tests in rebal-all-nodes-migrate.t will need to be
    uncommented once the AFR and EC changes are merged.

    Change-Id: I5ce41600f5ba0e244ddfd986e2ba8fa23329ff0c
    BUG: 1366817
    Signed-off-by: N Balachandran <nbalacha at redhat.com>
    Reviewed-on: https://review.gluster.org/17239
    Smoke: Gluster Build System <jenkins at build.gluster.org>
    NetBSD-regression: NetBSD Build System <jenkins at build.gluster.org>
    CentOS-regression: Gluster Build System <jenkins at build.gluster.org>
    Reviewed-by: Amar Tumballi <amarts at redhat.com>
    Reviewed-by: Jeff Darcy <jeff at pl.atyp.us>
    Reviewed-by: Shyamsundar Ranganathan <srangana at redhat.com>

-- 
You are receiving this mail because:
You are on the CC list for the bug.
Unsubscribe from this bug https://bugzilla.redhat.com/token.cgi?t=FB8sPqUbPe&a=cc_unsubscribe


More information about the Bugs mailing list