diff options
| -rw-r--r-- | src/rabbit_mirror_queue_coordinator.erl | 25 |
1 files changed, 22 insertions, 3 deletions
diff --git a/src/rabbit_mirror_queue_coordinator.erl b/src/rabbit_mirror_queue_coordinator.erl index 550423d209..48522af6c0 100644 --- a/src/rabbit_mirror_queue_coordinator.erl +++ b/src/rabbit_mirror_queue_coordinator.erl @@ -140,9 +140,28 @@ %% state of the master. The detection of the sync-status of a slave is %% done entirely based on length: if the slave and the master both %% agree on the length of the queue after the fetch of the head of the -%% queue, then the queues must be in sync. The only other possibility -%% is that the slave's queue is shorter, and thus the fetch should be -%% ignored. +%% queue (or a 'set_length' results in a slave having to drop some +%% messages from the head of its queue), then the queues must be in +%% sync. The only other possibility is that the slave's queue is +%% shorter, and thus the fetch should be ignored. In case slaves are +%% joined to an empty queue which only goes on to receive publishes, +%% they start by asking the master to broadcast its length. This is +%% enough for slaves to always be able to work out when their head +%% does not differ from the master (and is much simpler and cheaper +%% than getting the master to hang on to the guid of the msg at the +%% head of its queue). When a slave is promoted to a master, it +%% unilaterally broadcasts its length, in order to solve the problem +%% of length requests from new slaves being unanswered by a dead +%% master. +%% +%% Obviously, due to the async nature of communication across gm, the +%% slaves can fall behind. This does not matter from a sync pov: if +%% they fall behind and the master dies then a) no publishes are lost +%% because all publishes go to all mirrors anyway; b) the worst that +%% happens is that acks get lost and so messages come back to +%% life. This is no worse than normal given you never get confirmation +%% that an ack has been received (not quite true with QoS-prefetch, +%% but close enough for jazz). %% %% Because acktags are issued by the bq independently, and because %% there is no requirement for the master and all slaves to use the |