From 6a4fe7b9b068ae990d6404921a46631fe9ebcd31 Mon Sep 17 00:00:00 2001 From: Sage Weil Date: Tue, 20 Aug 2013 11:27:23 -0700 Subject: [PATCH] mon/Paxos: always refresh after any store_state If we store any new state, we need to refresh the services, even if we are still in the midst of Paxos recovery. This is because the subscription path will share any committed state even when paxos is still recovering. This prevents a race like: - we have maps 10..20 - we drop out of quorum - we are elected leader, paxos recovery starts - we get one LAST with committed states that trim maps 10..15 - we get a subscribe for map 10..20 - we crash because 10 is no longer on disk because the PaxosService is out of sync with the on-disk state. Fixes: #6045 Backport: dumpling Signed-off-by: Sage Weil Reviewed-by: Joao Eduardo Luis (cherry picked from commit 981eda9f7787c83dc457f061452685f499e7dd27) --- src/mon/Paxos.cc | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) diff --git a/src/mon/Paxos.cc b/src/mon/Paxos.cc index adb497b9d49f8..fa3e20898426b 100644 --- a/src/mon/Paxos.cc +++ b/src/mon/Paxos.cc @@ -384,6 +384,8 @@ void Paxos::_sanity_check_store() // leader void Paxos::handle_last(MMonPaxos *last) { + bool need_refresh = false; + dout(10) << "handle_last " << *last << dendl; if (!mon->is_leader()) { @@ -410,7 +412,7 @@ void Paxos::handle_last(MMonPaxos *last) assert(g_conf->paxos_kill_at != 1); // store any committed values if any are specified in the message - store_state(last); + need_refresh = store_state(last); assert(g_conf->paxos_kill_at != 2); @@ -486,6 +488,7 @@ void Paxos::handle_last(MMonPaxos *last) dout(10) << "that's everyone. active!" << dendl; extend_lease(); + need_refresh = false; if (do_refresh()) { finish_round(); @@ -500,6 +503,9 @@ void Paxos::handle_last(MMonPaxos *last) dout(10) << "old pn, ignoring" << dendl; } + if (need_refresh) + do_refresh(); + last->put(); } -- 2.39.5