Merge pull request #11388 from SergeTupchiy/EMQX-10703-fix-replicant-crash-when-core-terminates-abnormally

fix: increase emqx_router_sup restart intensity

apps/emqx/src/emqx_router_helper.erl

@@ -146,13 +146,18 @@ handle_info({mnesia_table_event, Event}, State) ->
     ?SLOG(debug, #{msg => "unexpected_mnesia_table_event", event => Event}),
     {noreply, State};
 handle_info({nodedown, Node}, State = #{nodes := Nodes}) ->
+    case mria_rlog:role() of
+        core ->
             global:trans(
                 {?LOCK, self()},
                 fun() ->
                     mria:transaction(?ROUTE_SHARD, fun ?MODULE:cleanup_routes/1, [Node])
                 end
             ),
-    ok = mria:dirty_delete(?ROUTING_NODE, Node),
+            ok = mria:dirty_delete(?ROUTING_NODE, Node);
+        replicant ->
+            ok
+    end,
     ?tp(emqx_router_helper_cleanup_done, #{node => Node}),
     {noreply, State#{nodes := lists:delete(Node, Nodes)}, hibernate};
 handle_info({membership, {mnesia, down, Node}}, State) ->

apps/emqx/src/emqx_router_sup.erl

@@ -41,4 +41,9 @@ init([]) ->
         hash,
         {emqx_router, start_link, []}
     ]),
-    {ok, {{one_for_all, 0, 1}, [Helper, RouterPool]}}.
+    SupFlags = #{
+        strategy => one_for_one,
+        intensity => 10,
+        period => 100
+    },
+    {ok, {SupFlags, [Helper, RouterPool]}}.

changes/ce/fix-11388.en.md

@@ -0,0 +1,6 @@
+Increase `emqx_router_sup` restart intensity.
+
+The goal is to tolerate occasional crashes that can happen under relatively normal conditions
+and don't seem critical to shutdown the whole app (emqx).
+For example, mria write/delete call delegated from a replicant to a core node by `emqx_router_helper` may fail,
+if the core node is being stopped / restarted / not ready.