libceph: don't set weight to IN when OSD is destroyed
authorIlya Dryomov <idryomov@gmail.com>
Wed, 1 Mar 2017 16:33:27 +0000 (17:33 +0100)
committerIlya Dryomov <idryomov@gmail.com>
Tue, 7 Mar 2017 13:30:38 +0000 (14:30 +0100)
commitb581a5854eee4b7851dedb0f8c2ceb54fb902c06
tree04060808300c17ca8f4d0e6c8a923efe6f545206
parent9afd30dbc82a9dbea4101aba57beb2a2a7e1b8d5
libceph: don't set weight to IN when OSD is destroyed

Since ceph.git commit 4e28f9e63644 ("osd/OSDMap: clear osd_info,
osd_xinfo on osd deletion"), weight is set to IN when OSD is deleted.
This changes the result of applying an incremental for clients, not
just OSDs.  Because CRUSH computations are obviously affected,
pre-4e28f9e63644 servers disagree with post-4e28f9e63644 clients on
object placement, resulting in misdirected requests.

Mirrors ceph.git commit a6009d1039a55e2c77f431662b3d6cc5a8e8e63f.

Fixes: 930c53286977 ("libceph: apply new_state before new_up_client on incrementals")
Link: http://tracker.ceph.com/issues/19122
Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
Reviewed-by: Sage Weil <sage@redhat.com>
net/ceph/osdmap.c