ensure queues are fully initialsed before we advertise their presence

Previously in a clustered setup a channel on another node could have
found a recently recovered queue before that queue had been fully
initialised and recovered its content.

Fixing that turns out to be simple since the main obstacle - the
re-declaration check for recovered durable queues and the associated
atomic update of the record with the new queue pid - can be removed
since it became superfluous with the changes in bug 20916.

0 files changed, 0 insertions, 0 deletions