diff options
author | Dan Gudmundsson <dgud@erlang.org> | 2015-02-10 14:43:19 +0100 |
---|---|---|
committer | Dan Gudmundsson <dgud@erlang.org> | 2015-02-10 14:52:16 +0100 |
commit | a0f9bb79004eeacc327d0bfaa891f0cbd71b3f04 (patch) | |
tree | 9374618f03b0e64e68a8cae0230974a9a6a61135 /lib | |
parent | 33156218401ba0ba489d0d787367af82f56c5f3c (diff) | |
parent | 70c4db1d0b57363e33a04c935b653092f68cb91a (diff) | |
download | otp-a0f9bb79004eeacc327d0bfaa891f0cbd71b3f04.tar.gz otp-a0f9bb79004eeacc327d0bfaa891f0cbd71b3f04.tar.bz2 otp-a0f9bb79004eeacc327d0bfaa891f0cbd71b3f04.zip |
Merge branch 'dumbbell/mnesia-hang-if-remote-stopped-after-proto-negotiation' into maint
* dumbbell/mnesia-hang-if-remote-stopped-after-proto-negotiation:
mnesia: Check nodes after protocol negotiation
OTP-12473
Diffstat (limited to 'lib')
-rw-r--r-- | lib/mnesia/src/mnesia_recover.erl | 31 |
1 files changed, 28 insertions, 3 deletions
diff --git a/lib/mnesia/src/mnesia_recover.erl b/lib/mnesia/src/mnesia_recover.erl index b6492707e2..eeb4fa0ced 100644 --- a/lib/mnesia/src/mnesia_recover.erl +++ b/lib/mnesia/src/mnesia_recover.erl @@ -689,12 +689,29 @@ handle_call({connect_nodes, Ns}, From, State) -> %% called from handle_info gen_server:reply(From, {[], AlreadyConnected}), {noreply, State}; - GoodNodes -> + ProbablyGoodNodes -> %% Now we have agreed upon a protocol with some new nodes - %% and we may use them when we recover transactions + %% and we may use them when we recover transactions. + %% + %% Just in case Mnesia was stopped on some of those nodes + %% between the protocol negotiation and now, we check one + %% more time the state of Mnesia. + %% + %% Of course, there is still a chance that mnesia_down + %% events occur during this check and we miss them. To + %% prevent it, handle_cast({mnesia_down, ...}, ...) removes + %% the down node again, in addition to mnesia_down/1. + %% + %% See a comment in handle_cast({mnesia_down, ...}, ...). + Verify = fun(N) -> + Run = mnesia_lib:is_running(N), + Run =:= yes orelse Run =:= starting + end, + GoodNodes = [N || N <- ProbablyGoodNodes, Verify(N)], + mnesia_lib:add_list(recover_nodes, GoodNodes), cast({announce_all, GoodNodes}), - case get_master_nodes(schema) of + case get_master_nodes(schema) of [] -> Context = starting_partitioned_network, mnesia_monitor:detect_inconcistency(GoodNodes, Context); @@ -842,6 +859,14 @@ handle_cast({what_decision, Node, OtherD}, State) -> {noreply, State}; handle_cast({mnesia_down, Node}, State) -> + %% The node was already removed from recover_nodes in mnesia_down/1, + %% but we do it again here in the mnesia_recover process, in case + %% another event incorrectly added it back. This can happen during + %% Mnesia startup which takes time betweenthe connection, the + %% protocol negotiation and the merge of the schema. + %% + %% See a comment in handle_call({connect_nodes, ...), ...). + mnesia_lib:del(recover_nodes, Node), case State#state.unclear_decision of undefined -> {noreply, State}; |