Merge lp:~vlad-lesin/percona-server/5.6-bugs-1268729-1268735 into lp:percona-server/5.6

[Vlad Lesin]

Bug #1268735 fixing is merged from 5.5.

The difference between 5.5 and this patches is the following:

      if (is_network_error(mysql_errno(mysql)))
      {
        mi->report(WARNING_LEVEL, mysql_errno(mysql),
                   "SET @master_heartbeat_period to master failed with error: %s",
                   mysql_error(mysql));
        mysql_free_result(mysql_store_result(mysql));
        goto network_err;
      }
- else if (!check_io_slave_killed(mi->io_thd, mi, NULL)) {
+ else {
        errmsg= "The slave I/O thread stops because SET @master_heartbeat_period "
          "on master failed.";
        err_code= ER_SLAVE_FATAL_ERROR;
        sprintf(err_buff, "%s Error: %s", errmsg, mysql_error(mysql));
        mysql_free_result(mysql_store_result(mysql));
        goto err;
      }

The initial code checked if the slave thread was killed in the case if there
was error in mysql_real_query(). To save this logic non-network error in
mysql_real_query() is treated as fatal error only if the slave thread was
not killed in 5.5. But as 5.6 upstream fix (see upstream revno: 2661.723.1)
does not contain this check it was decided do not include it in PS-5.6.

The fix for bug #1268729 merged from 5.5:
Slave I/O thread won't attempt to automatically reconnect to the master.

The fix is in including ER_NET_READ_INTERRUPTED error code to the set of
network related error codes in is_network_error() function.

The test case tests a couple of cases when get_master_version_and_clock()
fails due to ER_NET_READ_INTERRUPTED network error.

There are no big differences between 5.6 and 5.5 fixes.

http://jenkins.percona.com/view/PS%205.6/job/percona-server-5.6-param/498

[Laurynas Biveinis (laurynas-biveinis)]

review: Needs Fixing

[Laurynas Biveinis (laurynas-biveinis)]

ST 38489

[Vlad Lesin (vlad-lesin)]

http://jenkins.percona.com/view/PS%205.6/job/percona-server-5.6-param/531

[Laurynas Biveinis (laurynas-biveinis)]

review: Approve

=== added file 'mysql-test/suite/rpl/r/rpl_percona_gmvac_net_err.result'
--- mysql-test/suite/rpl/r/rpl_percona_gmvac_net_err.result	1970-01-01 00:00:00 +0000
+++ mysql-test/suite/rpl/r/rpl_percona_gmvac_net_err.result	2014-02-27 16:24:37 +0000
@@ -0,0 +1,33 @@
+include/master-slave.inc
+Warnings:
+Note	####	Sending passwords in plain text without SSL/TLS is extremely insecure.
+Note	####	Storing MySQL user name or password information in the master info repository is not secure and is therefore not recommended. Please consider using the USER and PASSWORD connection options for START SLAVE; see the 'START SLAVE Syntax' in the MySQL Manual for more information.
+[connection master]
+call mtr.add_suppression("Slave I/O: Get master clock failed with error: , Error_code: 1159");
+call mtr.add_suppression("Get master SERVER_ID failed with error: , Error_code: 1159");
+call mtr.add_suppression("Slave I/O: SET @master_heartbeat_period to master failed with error: , Error_code: 1159");
+call mtr.add_suppression("Slave I/O: Master command COM_REGISTER_SLAVE failed: .*");
+call mtr.add_suppression("Slave SQL.*Request to stop slave SQL Thread received while applying a group that has non-transactional changes; waiting for completion of the group");
+SET @debug_saved=@@global.debug;
+include/stop_slave.inc
+SET @@global.debug="+d,get_master_version.heartbeat.ER_NET_READ_INTERRUPTED";
+START SLAVE;
+include/wait_for_slave_io_to_start.inc
+[log_grep.inc] file:  pattern: The slave I/O thread stops because SET @master_heartbeat_period on master failed.
+[log_grep.inc] lines:   0
+include/stop_slave.inc
+SET @@global.debug="+d,get_master_version.serverid.ER_NET_READ_INTERRUPTED";
+START SLAVE;
+include/wait_for_slave_io_to_start.inc
+[log_grep.inc] file:  pattern: fatal error is encountered when it try to get the value of SERVER_ID variable from master
+[log_grep.inc] lines:   0
+include/stop_slave.inc
+SET @@global.debug="+d,get_master_version.timestamp.ER_NET_READ_INTERRUPTED";
+START SLAVE;
+include/wait_for_slave_io_to_start.inc
+[log_grep.inc] file:  pattern: "SELECT UNIX_TIMESTAMP.." failed on master, do not trust column
+[log_grep.inc] lines:   0
+include/stop_slave.inc
+SET @@global.debug='';
+include/start_slave.inc
+include/rpl_end.inc
 
=== added file 'mysql-test/suite/rpl/t/rpl_percona_gmvac_net_err.test'
--- mysql-test/suite/rpl/t/rpl_percona_gmvac_net_err.test	1970-01-01 00:00:00 +0000
+++ mysql-test/suite/rpl/t/rpl_percona_gmvac_net_err.test	2014-02-27 16:24:37 +0000
@@ -0,0 +1,67 @@
+# Bug #1268735:
+# Slave I/O thread won't attempt to automatically reconnect to the master
+# on ER_NET_READ_INTERRUPTED network error.
+#
+# The bug is in get_master_version_and_clock(). There are two places in this
+# function where the bug takes place. The first one is getting master server id
+# and the second one is getting master time. The error was injected to the code
+# to test the bug fix.
+
+source include/master-slave.inc;
+# The error injection works only with debug facilities.
+source include/have_debug.inc;
+source include/have_debug_sync.inc;
+# The test is not supposed to have any binglog affairs.
+# Hence it's enough it to run only with one binlog format
+source include/have_binlog_format_mixed.inc;
+
+call mtr.add_suppression("Slave I/O: Get master clock failed with error: , Error_code: 1159");
+call mtr.add_suppression("Get master SERVER_ID failed with error: , Error_code: 1159");
+call mtr.add_suppression("Slave I/O: SET @master_heartbeat_period to master failed with error: , Error_code: 1159");
+call mtr.add_suppression("Slave I/O: Master command COM_REGISTER_SLAVE failed: .*");
+call mtr.add_suppression("Slave SQL.*Request to stop slave SQL Thread received while applying a group that has non-transactional changes; waiting for completion of the group");
+
+let log_file_full_path= `SELECT @@GLOBAL.log_error`;
+if(!$log_file_full_path)
+{
+  # MySQL Server on windows is started with --console and thus
+  # does not know the location of its .err log, use default location
+  let log_file_full_path = $MYSQLTEST_VARDIR/log/mysqld.2.err;
+}
+
+connection slave;
+SET @debug_saved=@@global.debug;
+
+# i=1 for activating injected error during getting timestamp from master
+# i=2 for activating injected error during getting server id from master
+# i=3 for activating injected error during setting @master_heartbeat_period 
+let i=3;
+
+connection slave;
+source include/stop_slave.inc;
+let old_debug=`SELECT @@global.debug`;
+
+while($i)
+{
+  let debug_name=`SELECT CASE $i WHEN 1 THEN 'get_master_version.timestamp.ER_NET_READ_INTERRUPTED' WHEN 2 THEN 'get_master_version.serverid.ER_NET_READ_INTERRUPTED' WHEN 3 THEN 'get_master_version.heartbeat.ER_NET_READ_INTERRUPTED' END`;
+
+  # Stop slave and set debug variables
+  eval SET @@global.debug="+d,$debug_name";
+
+  START SLAVE;
+  # Crash if error during slave starting takes place
+  let $rpl_allow_error= 0;
+  source include/wait_for_slave_io_to_start.inc;
+
+  let grep_pattern=`SELECT CASE $i WHEN 1 THEN '"SELECT UNIX_TIMESTAMP.." failed on master, do not trust column' WHEN 2 THEN 'fatal error is encountered when it try to get the value of SERVER_ID variable from master' WHEN 3 THEN 'The slave I/O thread stops because SET @master_heartbeat_period on master failed.' END`;
+
+  source include/log_grep.inc;
+
+  source include/stop_slave.inc;
+  dec $i;
+}
+
+eval SET @@global.debug='$old_debug';
+
+source include/start_slave.inc;
+source include/rpl_end.inc;
 
=== modified file 'sql-common/client.c'
--- sql-common/client.c	2013-12-05 17:23:10 +0000
+++ sql-common/client.c	2014-02-27 16:24:37 +0000
@@ -4153,6 +4153,12 @@
   DBUG_ENTER("mysql_real_query");
   DBUG_PRINT("enter",("handle: %p", mysql));
   DBUG_PRINT("query",("Query = '%-.*s'", (int) length, query));
+  DBUG_EXECUTE_IF("inject_ER_NET_READ_INTERRUPTED",
+		   {
+                     mysql->net.last_errno= ER_NET_READ_INTERRUPTED;
+                     DBUG_SET("-d,inject_ER_NET_READ_INTERRUPTED");
+                     DBUG_RETURN(1);
+                   });
 
   if (mysql_send_query(mysql,query,length))
     DBUG_RETURN(1);
 
=== modified file 'sql/rpl_slave.cc'
--- sql/rpl_slave.cc	2014-02-17 11:12:40 +0000
+++ sql/rpl_slave.cc	2014-02-27 16:24:37 +0000
@@ -1471,7 +1471,8 @@
       errorno == CR_SERVER_GONE_ERROR ||
       errorno == CR_SERVER_LOST ||
       errorno == ER_CON_COUNT_ERROR ||
-      errorno == ER_SERVER_SHUTDOWN)
+      errorno == ER_SERVER_SHUTDOWN ||
+      errorno == ER_NET_READ_INTERRUPTED)
     return TRUE;
 
   return FALSE;   
@@ -1862,6 +1863,12 @@
                   };);
 
   master_res= NULL;
+  DBUG_EXECUTE_IF("get_master_version.timestamp.ER_NET_READ_INTERRUPTED",
+		  {
+		     DBUG_SET("+d,inject_ER_NET_READ_INTERRUPTED");
+		     DBUG_SET("-d,get_master_version.timestamp."
+			      "ER_NET_READ_INTERRUPTED");
+		  });
   if (!mysql_real_query(mysql, STRING_WITH_LEN("SELECT UNIX_TIMESTAMP()")) &&
       (master_res= mysql_store_result(mysql)) &&
       (master_row= mysql_fetch_row(master_res)))
@@ -1916,6 +1923,12 @@
                   };);
   master_res= NULL;
   master_row= NULL;
+  DBUG_EXECUTE_IF("get_master_version.server_id.ER_NET_READ_INTERRUPTED",
+		  {
+                    DBUG_SET("+d,inject_ER_NET_READ_INTERRUPTED");
+                    DBUG_SET("-d,get_master_version.server_id."
+                             "ER_NET_READ_INTERRUPTED");
+		  });
   if (!mysql_real_query(mysql,
                         STRING_WITH_LEN("SHOW VARIABLES LIKE 'SERVER_ID'")) &&
       (master_res= mysql_store_result(mysql)) &&
@@ -2105,7 +2118,12 @@
     */
     llstr((ulonglong) (mi->heartbeat_period*1000000000UL), llbuf);
     sprintf(query, query_format, llbuf);
-
+    DBUG_EXECUTE_IF("get_master_version.heartbeat.ER_NET_READ_INTERRUPTED",
+		    {
+		      DBUG_SET("+d,inject_ER_NET_READ_INTERRUPTED");
+		      DBUG_SET("-d,get_master_version.heartbeat."
+			       "ER_NET_READ_INTERRUPTED");
+		    });
     if (mysql_real_query(mysql, query, strlen(query)))
     {
       if (check_io_slave_killed(mi->info_thd, mi, NULL))