From 2f4a0c5be2c5d5153c4253a49ba8820ab333a9a0 Mon Sep 17 00:00:00 2001
From: Kristian Nielsen <knielsen@knielsen-hq.org>
Date: Sun, 7 Oct 2018 18:59:52 +0200
Subject: Fix accumulation of old rows in mysql.gtid_slave_pos

This would happen especially in optimistic parallel replication, where there
is a good chance that a transaction will be rolled back (due to conflicts)
after it has executed record_gtid(). If the transaction did any deletions of
old rows as part of record_gtid(), those deletions will be undone as well.
And the code did not properly ensure that the deletions would be re-tried.

This patch makes record_gtid() remember the list of deletions done as part
of a transaction. Then in rpl_slave_state::update() when the changes have
been committed, we discard the list. However, in case of error and rollback,
in cleanup_context() we will instead put the list back into
rpl_global_gtid_slave_state so that the deletions will be re-tried later.

Probably fixes part of the cause of MDEV-12147 as well.

Signed-off-by: Kristian Nielsen <knielsen@knielsen-hq.org>
---
 sql/rpl_rli.cc | 79 ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 79 insertions(+)

(limited to 'sql/rpl_rli.cc')

diff --git a/sql/rpl_rli.cc b/sql/rpl_rli.cc
index 64a1b535307..b35130c1505 100644
--- a/sql/rpl_rli.cc
+++ b/sql/rpl_rli.cc
@@ -1680,6 +1680,7 @@ rpl_group_info::reinit(Relay_log_info *rli)
   long_find_row_note_printed= false;
   did_mark_start_commit= false;
   gtid_ev_flags2= 0;
+  pending_gtid_delete_list= NULL;
   last_master_timestamp = 0;
   gtid_ignore_duplicate_state= GTID_DUPLICATE_NULL;
   speculation= SPECULATE_NO;
@@ -1804,6 +1805,12 @@ void rpl_group_info::cleanup_context(THD *thd, bool error)
       erroneously update the GTID position.
     */
     gtid_pending= false;
+
+    /*
+      Rollback will have undone any deletions of old rows we might have made
+      in mysql.gtid_slave_pos. Put those rows back on the list to be deleted.
+    */
+    pending_gtid_deletes_put_back();
   }
   m_table_map.clear_tables();
   slave_close_thread_tables(thd);
@@ -2027,6 +2034,78 @@ rpl_group_info::unmark_start_commit()
 }
 
 
+/*
+  When record_gtid() has deleted any old rows from the table
+  mysql.gtid_slave_pos as part of a replicated transaction, save the list of
+  rows deleted here.
+
+  If later the transaction fails (eg. optimistic parallel replication), the
+  deletes will be undone when the transaction is rolled back. Then we can
+  put back the list of rows into the rpl_global_gtid_slave_state, so that
+  we can re-do the deletes and avoid accumulating old rows in the table.
+*/
+void
+rpl_group_info::pending_gtid_deletes_save(uint32 domain_id,
+                                          rpl_slave_state::list_element *list)
+{
+  /*
+    We should never get to a state where we try to save a new pending list of
+    gtid deletes while we still have an old one. But make sure we handle it
+    anyway just in case, so we avoid leaving stray entries in the
+    mysql.gtid_slave_pos table.
+  */
+  DBUG_ASSERT(!pending_gtid_delete_list);
+  if (unlikely(pending_gtid_delete_list))
+    pending_gtid_deletes_put_back();
+
+  pending_gtid_delete_list= list;
+  pending_gtid_delete_list_domain= domain_id;
+}
+
+
+/*
+  Take the list recorded by pending_gtid_deletes_save() and put it back into
+  rpl_global_gtid_slave_state. This is needed if deletion of the rows was
+  rolled back due to transaction failure.
+*/
+void
+rpl_group_info::pending_gtid_deletes_put_back()
+{
+  if (pending_gtid_delete_list)
+  {
+    rpl_global_gtid_slave_state->put_back_list(pending_gtid_delete_list_domain,
+                                               pending_gtid_delete_list);
+    pending_gtid_delete_list= NULL;
+  }
+}
+
+
+/*
+  Free the list recorded by pending_gtid_deletes_save(). Done when the deletes
+  in the list have been permanently committed.
+*/
+void
+rpl_group_info::pending_gtid_deletes_clear()
+{
+  pending_gtid_deletes_free(pending_gtid_delete_list);
+  pending_gtid_delete_list= NULL;
+}
+
+
+void
+rpl_group_info::pending_gtid_deletes_free(rpl_slave_state::list_element *list)
+{
+  rpl_slave_state::list_element *next;
+
+  while (list)
+  {
+    next= list->next;
+    my_free(list);
+    list= next;
+  }
+}
+
+
 rpl_sql_thread_info::rpl_sql_thread_info(Rpl_filter *filter)
   : rpl_filter(filter)
 {
-- 
cgit v1.2.1