Merge gbichot@bk-internal.mysql.com:/home/bk/mysql-4.0

into mysql.com:/home/mysql_src/mysql-4.0

6 files changed, 105 insertions, 16 deletions

diff --git a/sql/handler.cc b/sql/handler.cc
index 96611301bfa..0d29dbeaa31 100644
--- a/sql/handler.cc
+++ b/sql/handler.cc
@@ -349,7 +349,7 @@ int ha_commit_trans(THD *thd, THD_TRANS* trans)
     if (trans == &thd->transaction.all && mysql_bin_log.is_open() &&
 	my_b_tell(&thd->transaction.trans_log))
     {
-      mysql_bin_log.write(thd, &thd->transaction.trans_log);
+      mysql_bin_log.write(thd, &thd->transaction.trans_log, 1);
       reinit_io_cache(&thd->transaction.trans_log,
 		      WRITE_CACHE, (my_off_t) 0, 0, 1);
       thd->transaction.trans_log.end_of_file= max_binlog_cache_size;
@@ -432,9 +432,21 @@ int ha_rollback_trans(THD *thd, THD_TRANS *trans)
     }
 #endif
     if (trans == &thd->transaction.all)
+    {
+      /* 
+         Update the binary log with a BEGIN/ROLLBACK block if we have cached some
+         queries and we updated some non-transactional table. Such cases should
+         be rare (updating a non-transactional table inside a transaction...).
+      */
+      if (unlikely((thd->options & OPTION_STATUS_NO_TRANS_UPDATE) &&
+                   mysql_bin_log.is_open() &&
+                   my_b_tell(&thd->transaction.trans_log)))
+        mysql_bin_log.write(thd, &thd->transaction.trans_log, 0);
+      /* Flushed or not, empty the binlog cache */
       reinit_io_cache(&thd->transaction.trans_log,
-		      WRITE_CACHE, (my_off_t) 0, 0, 1);
-    thd->transaction.trans_log.end_of_file= max_binlog_cache_size;
+                      WRITE_CACHE, (my_off_t) 0, 0, 1);
+      thd->transaction.trans_log.end_of_file= max_binlog_cache_size;
+    }
     thd->variables.tx_isolation=thd->session_tx_isolation;
     if (operation_done)
     {
@@ -448,9 +460,27 @@ int ha_rollback_trans(THD *thd, THD_TRANS *trans)
 
 
 /*
-Rolls the current transaction back to a savepoint.
-Return value: 0 if success, 1 if there was not a savepoint of the given
-name.
+  Rolls the current transaction back to a savepoint.
+  Return value: 0 if success, 1 if there was not a savepoint of the given
+  name.
+  NOTE: how do we handle this (unlikely but legal) case:
+  [transaction] + [update to non-trans table] + [rollback to savepoint] ?
+  The problem occurs when a savepoint is before the update to the
+  non-transactional table. Then when there's a rollback to the savepoint, if we
+  simply truncate the binlog cache, we lose the part of the binlog cache where
+  the update is. If we want to not lose it, we need to write the SAVEPOINT
+  command and the ROLLBACK TO SAVEPOINT command to the binlog cache. The latter
+  is easy: it's just write at the end of the binlog cache, but the former should
+  be *inserted* to the place where the user called SAVEPOINT. The solution is
+  that when the user calls SAVEPOINT, we write it to the binlog cache (so no
+  need to later insert it). As transactions are never intermixed in the binary log
+  (i.e. they are serialized), we won't have conflicts with savepoint names when
+  using mysqlbinlog or in the slave SQL thread.
+  Then when ROLLBACK TO SAVEPOINT is called, if we updated some
+  non-transactional table, we don't truncate the binlog cache but instead write
+  ROLLBACK TO SAVEPOINT to it; otherwise we truncate the binlog cache (which
+  will chop the SAVEPOINT command from the binlog cache, which is good as in
+  that case there is no need to have it in the binlog).
 */
 
 int ha_rollback_to_savepoint(THD *thd, char *savepoint_name)
@@ -475,8 +505,24 @@ int ha_rollback_to_savepoint(THD *thd, char *savepoint_name)
       error=1;
     }
     else
-      reinit_io_cache(&thd->transaction.trans_log, WRITE_CACHE,
-						 binlog_cache_pos, 0, 0);
+    {
+      /* 
+         Write ROLLBACK TO SAVEPOINT to the binlog cache if we have updated some
+         non-transactional table. Otherwise, truncate the binlog cache starting
+         from the SAVEPOINT command.
+      */
+      if (unlikely((thd->options & OPTION_STATUS_NO_TRANS_UPDATE) &&
+                   mysql_bin_log.is_open() &&
+                   my_b_tell(&thd->transaction.trans_log)))
+      {
+        Query_log_event qinfo(thd, thd->query, thd->query_length, TRUE);
+        if (mysql_bin_log.write(&qinfo))
+          error= 1;
+      }
+      else
+        reinit_io_cache(&thd->transaction.trans_log, WRITE_CACHE,
+                        binlog_cache_pos, 0, 0);
+    }
     operation_done=1;
 #endif
     if (operation_done)
@@ -505,6 +551,13 @@ int ha_savepoint(THD *thd, char *savepoint_name)
 #ifdef HAVE_INNOBASE_DB
     innobase_savepoint(thd,savepoint_name, binlog_cache_pos);
 #endif
+    /* Write it to the binary log (see comments of ha_rollback_to_savepoint). */
+    if (mysql_bin_log.is_open())
+    {
+      Query_log_event qinfo(thd, thd->query, thd->query_length, TRUE);
+      if (mysql_bin_log.write(&qinfo))
+	error= 1;
+    }
   }
 #endif /* USING_TRANSACTIONS */
   DBUG_RETURN(error);
diff --git a/sql/log.cc b/sql/log.cc
index ee774ea3700..6e9fa38c407 100644
--- a/sql/log.cc
+++ b/sql/log.cc
@@ -1062,7 +1062,17 @@ bool MYSQL_LOG::write(Log_event* event_info)
     bool should_rotate = 0;
     const char *local_db = event_info->get_db();
 #ifdef USING_TRANSACTIONS    
-    IO_CACHE *file = ((event_info->get_cache_stmt()) ?
+    /*
+      Should we write to the binlog cache or to the binlog on disk?
+      Write to the binlog cache if:
+      - it is already not empty (meaning we're in a transaction; note that the
+     present event could be about a non-transactional table, but still we need
+     to write to the binlog cache in that case to handle updates to mixed
+     trans/non-trans table types the best possible in binlogging)
+      - or if the event asks for it (cache_stmt == true).
+    */
+    IO_CACHE *file = ((event_info->get_cache_stmt() ||
+                       my_b_tell(&thd->transaction.trans_log)) ? 
 		      &thd->transaction.trans_log :
 		      &log_file);
 #else
@@ -1258,6 +1268,13 @@ uint MYSQL_LOG::next_file_id()
 /*
   Write a cached log entry to the binary log
 
+  SYNOPSIS
+    write()
+    thd 		
+    cache		The cache to copy to the binlog
+    commit_or_rollback  If true, will write "COMMIT" in the end, if false will
+                        write "ROLLBACK".
+
   NOTE
     - We only come here if there is something in the cache.
     - The thing in the cache is always a complete transaction
@@ -1265,10 +1282,13 @@ uint MYSQL_LOG::next_file_id()
 
   IMPLEMENTATION
     - To support transaction over replication, we wrap the transaction
-      with BEGIN/COMMIT in the binary log.
+      with BEGIN/COMMIT or BEGIN/ROLLBACK in the binary log.
+      We want to write a BEGIN/ROLLBACK block when a non-transactional table was
+      updated in a transaction which was rolled back. This is to ensure that the
+      same updates are run on the slave.
 */
 
-bool MYSQL_LOG::write(THD *thd, IO_CACHE *cache)
+bool MYSQL_LOG::write(THD *thd, IO_CACHE *cache, bool commit_or_rollback)
 {
   VOID(pthread_mutex_lock(&LOCK_log));
   DBUG_ENTER("MYSQL_LOG::write(cache");
@@ -1322,7 +1342,10 @@ bool MYSQL_LOG::write(THD *thd, IO_CACHE *cache)
     */
 
     {
-      Query_log_event qinfo(thd, "COMMIT", 6, TRUE);
+      Query_log_event qinfo(thd, 
+                            commit_or_rollback ? "COMMIT" : "ROLLBACK",
+                            commit_or_rollback ? 6        : 8, 
+                            TRUE);
       qinfo.set_log_pos(this);
       if (qinfo.write(&log_file) || flush_io_cache(&log_file))
 	goto err;
diff --git a/sql/log_event.cc b/sql/log_event.cc
index 9e7546dd635..54e4d34f77e 100644
--- a/sql/log_event.cc
+++ b/sql/log_event.cc
@@ -1803,7 +1803,7 @@ int Query_log_event::exec_event(struct st_relay_log_info* rli)
       */
       if (!strcmp(thd->query,"BEGIN"))
 	rli->inside_transaction= opt_using_transactions;
-      else if (!strcmp(thd->query,"COMMIT"))
+      else if (!(strcmp(thd->query,"COMMIT") && strcmp(thd->query,"ROLLBACK")))
 	rli->inside_transaction=0;
 
       /*
diff --git a/sql/sql_class.h b/sql/sql_class.h
index 49a364856eb..b30faa3e9d9 100644
--- a/sql/sql_class.h
+++ b/sql/sql_class.h
@@ -140,7 +140,7 @@ public:
   bool write(THD *thd, const char *query, uint query_length,
 	     time_t query_start=0);
   bool write(Log_event* event_info); // binary log write
-  bool write(THD *thd, IO_CACHE *cache);
+  bool write(THD *thd, IO_CACHE *cache, bool commit_or_rollback);
 
   /*
     v stands for vector
diff --git a/sql/sql_insert.cc b/sql/sql_insert.cc
index 167ccf974c7..0a83358e8c6 100644
--- a/sql/sql_insert.cc
+++ b/sql/sql_insert.cc
@@ -1367,6 +1367,8 @@ void select_insert::send_error(uint errcode,const char *err)
                             table->file->has_transactions());
       mysql_bin_log.write(&qinfo);
     }
+    if (!table->tmp_table)
+      thd->options|=OPTION_STATUS_NO_TRANS_UPDATE;    
   }
   ha_rollback_stmt(thd);
   if (info.copied || info.deleted)
@@ -1398,6 +1400,8 @@ bool select_insert::send_eof()
   if (info.copied || info.deleted)
   {
     query_cache_invalidate3(thd, table, 1);
+    if (!(table->file->has_transactions() || table->tmp_table))
+	thd->options|=OPTION_STATUS_NO_TRANS_UPDATE;
   }
   if (error)
   {
diff --git a/sql/sql_parse.cc b/sql/sql_parse.cc
index 1479a611b5a..548714345f8 100644
--- a/sql/sql_parse.cc
+++ b/sql/sql_parse.cc
@@ -2553,7 +2553,16 @@ mysql_execute_command(void)
     thd->server_status&= ~SERVER_STATUS_IN_TRANS;
     if (!ha_rollback(thd))
     {
-      if (thd->options & OPTION_STATUS_NO_TRANS_UPDATE)
+      /*
+        If a non-transactional table was updated, warn; don't warn if this is a
+        slave thread (because when a slave thread executes a ROLLBACK, it has
+        been read from the binary log, so it's 100% sure and normal to produce
+        error ER_WARNING_NOT_COMPLETE_ROLLBACK. If we sent the warning to the
+        slave SQL thread, it would not stop the thread but just be printed in
+        the error log; but we don't want users to wonder why they have this
+        message in the error log, so we don't send it.
+      */
+      if ((thd->options & OPTION_STATUS_NO_TRANS_UPDATE) && !thd->slave_thread)
 	send_warning(&thd->net,ER_WARNING_NOT_COMPLETE_ROLLBACK,0);
       else
 	send_ok(&thd->net);
@@ -2565,7 +2574,7 @@ mysql_execute_command(void)
   case SQLCOM_ROLLBACK_TO_SAVEPOINT:
     if (!ha_rollback_to_savepoint(thd, lex->savepoint_name))
     {
-      if (thd->options & OPTION_STATUS_NO_TRANS_UPDATE)
+      if ((thd->options & OPTION_STATUS_NO_TRANS_UPDATE) && !thd->slave_thread)
 	send_warning(&thd->net,ER_WARNING_NOT_COMPLETE_ROLLBACK,0);
       else
 	send_ok(&thd->net);