Test: processing of master stream in slave -BUSY state.

See #5297.

src/networking.c

@@ -827,8 +827,7 @@ void freeClient(client *c) {
         serverLog(LL_WARNING,"Connection with master lost.");
         if (!(c->flags & (CLIENT_CLOSE_AFTER_REPLY|
                           CLIENT_CLOSE_ASAP|
-                          CLIENT_BLOCKED|
-                          CLIENT_UNBLOCKED)))
+                          CLIENT_BLOCKED)))
         {
             replicationCacheMaster(c);
             return;
@@ -1362,6 +1361,12 @@ void processInputBuffer(client *c) {
         /* Immediately abort if the client is in the middle of something. */
         if (c->flags & CLIENT_BLOCKED) break;
 
+        /* Don't process input from the master while there is a busy script
+         * condition on the slave. We want just to accumulate the replication
+         * stream (instead of replying -BUSY like we do with other clients) and
+         * later resume the processing. */
+        if (server.lua_timedout && c->flags & CLIENT_MASTER) break;
+
         /* CLIENT_CLOSE_AFTER_REPLY closes the connection once the reply is
          * written to the client. Make sure to not let the reply grow after
          * this flag has been set (i.e. don't process more commands).

src/scripting.c

@@ -1222,11 +1222,12 @@ sds luaCreateFunction(client *c, lua_State *lua, robj *body) {
 
 /* This is the Lua script "count" hook that we use to detect scripts timeout. */
 void luaMaskCountHook(lua_State *lua, lua_Debug *ar) {
-    long long elapsed;
+    long long elapsed = mstime() - server.lua_time_start;
     UNUSED(ar);
     UNUSED(lua);
 
-    elapsed = mstime() - server.lua_time_start;
+    /* Set the timeout condition if not already set and the maximum
+     * execution time was reached. */
     if (elapsed >= server.lua_time_limit && server.lua_timedout == 0) {
         serverLog(LL_WARNING,"Lua slow script detected: still in execution after %lld milliseconds. You can try killing the script using the SCRIPT KILL command.",elapsed);
         server.lua_timedout = 1;
@@ -1345,9 +1346,7 @@ void evalGenericCommand(client *c, int evalsha) {
     server.lua_caller = c;
     server.lua_time_start = mstime();
     server.lua_kill = 0;
-    if (server.lua_time_limit > 0 && server.masterhost == NULL &&
-        ldb.active == 0)
-    {
+    if (server.lua_time_limit > 0 && ldb.active == 0) {
         lua_sethook(lua,luaMaskCountHook,LUA_MASKCOUNT,100000);
         delhook = 1;
     } else if (ldb.active) {
@@ -1368,6 +1367,10 @@ void evalGenericCommand(client *c, int evalsha) {
          * script timeout was detected. */
         aeCreateFileEvent(server.el,c->fd,AE_READABLE,
                           readQueryFromClient,c);
+        if (server.masterhost && server.master) {
+            server.master->flags |= CLIENT_UNBLOCKED;
+            listAddNodeTail(server.unblocked_clients,server.master);
+        }
     }
     server.lua_caller = NULL;
 
@@ -1497,6 +1500,8 @@ NULL
     } else if (c->argc == 2 && !strcasecmp(c->argv[1]->ptr,"kill")) {
         if (server.lua_caller == NULL) {
             addReplySds(c,sdsnew("-NOTBUSY No scripts in execution right now.\r\n"));
+        } else if (server.lua_caller->flags & CLIENT_MASTER) {
+            addReplySds(c,sdsnew("-UNKILLABLE The busy script was sent by a master instance in the context of replication and cannot be killed.\r\n"));
         } else if (server.lua_write_dirty) {
             addReplySds(c,sdsnew("-UNKILLABLE Sorry the script already executed write commands against the dataset. You can either wait the script termination or kill the server in a hard way using the SHUTDOWN NOSAVE command.\r\n"));
         } else {

tests/integration/replication.tcl

@@ -266,3 +266,47 @@ foreach dl {no yes} {
         }
     }
 }
+
+start_server {tags {"repl"}} {
+    set master [srv 0 client]
+    set master_host [srv 0 host]
+    set master_port [srv 0 port]
+    set load_handle0 [start_write_load $master_host $master_port 3]
+    start_server {} {
+        test "Master stream is correctly processed while the slave has a script in -BUSY state" {
+            set slave [srv 0 client]
+            puts [srv 0 port]
+            $slave config set lua-time-limit 500
+            $slave slaveof $master_host $master_port
+
+            # Wait for the slave to be online
+            wait_for_condition 500 100 {
+                [lindex [$slave role] 3] eq {connected}
+            } else {
+                fail "Slave still not connected after some time"
+            }
+
+            # Wait some time to make sure the master is sending data
+            # to the slave.
+            after 5000
+
+            # Stop the ability of the slave to process data by sendig
+            # a script that will put it in BUSY state.
+            $slave eval {for i=1,3000000000 do end} 0
+
+            # Wait some time again so that more master stream will
+            # be processed.
+            after 2000
+
+            # Stop the write load
+            stop_write_load $load_handle0
+
+            # number of keys
+            wait_for_condition 500 100 {
+                [$master debug digest] eq [$slave debug digest]
+            } else {
+                fail "Different datasets between slave and master"
+            }
+        }
+    }
+}