BUG#44581 Slave stops when transaction with non-transactional table gets lock wait

timeout
            
In STMT and MIXED modes, a statement that changes both non-transactional and
transactional tables must be written to the binary log whenever there are
changes to non-transactional tables. This means that the statement gets into the
binary log even when the changes to the transactional tables fail. In particular
, in the presence of a failure such statement is annotated with the error number
and wrapped in a begin/rollback. On the slave, while applying the statement, it
is expected the same failure and the rollback prevents the transactional changes
to be persisted.
            
Unfortunately, statements that fail due to concurrency issues (e.g. deadlocks,
timeouts) are logged in the same way causing the slave to stop as the statements
are applied sequentially by the SQL Thread. To fix this bug, we automatically
ignore concurrency failures on the slave. Specifically, the following failures
are ignored: ER_LOCK_WAIT_TIMEOUT, ER_LOCK_DEADLOCK and ER_XA_RBDEADLOCK.

1 files changed, 33 insertions, 4 deletions

diff --git a/sql/log_event.cc b/sql/log_event.cc
index 493db62e7ef..5f77ab3dcc4 100644
--- a/sql/log_event.cc
+++ b/sql/log_event.cc
@@ -369,6 +369,34 @@ int convert_handler_error(int error, THD* thd, TABLE *table)
   return (actual_error);
 }
 
+inline bool concurrency_error_code(int error)
+{
+  switch (error)
+  {
+  case ER_LOCK_WAIT_TIMEOUT:
+  case ER_LOCK_DEADLOCK:
+  case ER_XA_RBDEADLOCK:
+    return TRUE;
+  default: 
+    return (FALSE);
+  }
+}
+
+inline bool unexpected_error_code(int unexpected_error)
+{
+  switch (unexpected_error) 
+  {
+  case ER_NET_READ_ERROR:
+  case ER_NET_ERROR_ON_WRITE:
+  case ER_QUERY_INTERRUPTED:
+  case ER_SERVER_SHUTDOWN:
+  case ER_NEW_ABORTING_CONNECTION:
+    return(TRUE);
+  default:
+    return(FALSE);
+  }
+}
+
 /*
   pretty_print_str()
 */
@@ -3006,7 +3034,7 @@ int Query_log_event::do_apply_event(Relay_log_info const *rli,
     DBUG_PRINT("query",("%s",thd->query));
 
     if (ignored_error_code((expected_error= error_code)) ||
-	!check_expected_error(thd,rli,expected_error))
+	!unexpected_error_code(expected_error))
     {
       if (flags2_inited)
         /*
@@ -3138,8 +3166,8 @@ compare_errors:
     actual_error= thd->is_error() ? thd->main_da.sql_errno() : 0;
     DBUG_PRINT("info",("expected_error: %d  sql_errno: %d",
  		       expected_error, actual_error));
-    if ((expected_error != actual_error) &&
- 	expected_error &&
+    if ((expected_error && expected_error != actual_error &&
+         !concurrency_error_code(expected_error)) &&
  	!ignored_error_code(actual_error) &&
  	!ignored_error_code(expected_error))
     {
@@ -3158,7 +3186,8 @@ Default database: '%s'. Query: '%s'",
     /*
       If we get the same error code as expected, or they should be ignored. 
     */
-    else if (expected_error == actual_error ||
+    else if ((expected_error == actual_error && 
+              !concurrency_error_code(expected_error)) ||
  	     ignored_error_code(actual_error))
     {
       DBUG_PRINT("info",("error ignored"));