From 6c39eaeb126328e7813b146ecf652d51e4508981 Mon Sep 17 00:00:00 2001
From: Sujatha <sujatha.sivakumar@mariadb.com>
Date: Thu, 9 Apr 2020 20:45:45 +0530
Subject: MDEV-21117: refine the server binlog-based recovery for semisync

Problem:
=======
When the semisync master is crashed and restarted as slave it could
recover transactions that former slaves may never have seen.
A known method existed to clear out all prepared transactions
with --tc-heuristic-recover=rollback does not care to adjust
binlog accordingly.

Fix:
===
The binlog-based recovery is made to concern of the slave semisync role of
post-crash restarted server.
No changes in behavior is done to the "normal" binloggging server
and the semisync master.

When the restarted server is configured with
  --rpl-semi-sync-slave-enabled=1
the refined recovery attempts to roll back prepared transactions
and truncate binlog accordingly.
In case of a partially committed (that is committed at least
in one of the engine participants) such transaction gets committed.
It's guaranteed no (partially as well) committed transactions
exist beyond the truncate position.
In case there exists a non-transactional replication event
(being in a way a committed transaction) past the
computed truncate position the recovery ends with an error.

As after master crash and failover to slave, the demoted-to-slave
ex-master must be ready to face and accept its own (generated by)
events, without generally necessary --replicate-same-server-id.
So the acceptance conditions are relaxed for the semisync slave
to accept own events without that option.
While gtid_strict_mode ON ensures no duplicate transaction can be
(re-)executed the master_use_gtid=none slave has to be
configured with --replicate-same-server-id.

*NOTE* for reviewers.

This patch does not handle the user XA which is done
in next git commit.
---
 sql/log_event.cc | 31 ++++++++++++++++++++++++++++++-
 1 file changed, 30 insertions(+), 1 deletion(-)

(limited to 'sql/log_event.cc')

diff --git a/sql/log_event.cc b/sql/log_event.cc
index 9c7c56b1c34..c77059ee8f5 100644
--- a/sql/log_event.cc
+++ b/sql/log_event.cc
@@ -53,6 +53,7 @@
 #include "sql_digest.h"
 #include "zlib.h"
 #include "myisampack.h"
+#include <algorithm>
 
 #define my_b_write_string(A, B) my_b_write((A), (uchar*)(B), (uint) (sizeof(B) - 1))
 
@@ -2560,10 +2561,12 @@ Binlog_checkpoint_log_event::Binlog_checkpoint_log_event(
 Gtid_log_event::Gtid_log_event(const uchar *buf, uint event_len,
                                const Format_description_log_event
                                *description_event)
-  : Log_event(buf, description_event), seq_no(0), commit_id(0)
+  : Log_event(buf, description_event), seq_no(0), commit_id(0),
+    flags_extra(0), extra_engines(0)
 {
   uint8 header_size= description_event->common_header_len;
   uint8 post_header_len= description_event->post_header_len[GTID_EVENT-1];
+  const uchar *buf_0= buf;
   if (event_len < (uint) header_size + (uint) post_header_len ||
       post_header_len < GTID_HEADER_LEN)
     return;
@@ -2597,6 +2600,32 @@ Gtid_log_event::Gtid_log_event(const uchar *buf, uint event_len,
     memcpy(xid.data, buf, data_length);
     buf+= data_length;
   }
+
+  /* the extra flags check and actions */
+  if (static_cast<uint>(buf - buf_0) < event_len)
+  {
+    flags_extra= *buf++;
+    /*
+      extra engines flags presence is identifed by non-zero byte value
+      at this point
+    */
+    if (flags_extra & FL_EXTRA_MULTI_ENGINE)
+    {
+      DBUG_ASSERT(static_cast<uint>(buf - buf_0) < event_len);
+
+      extra_engines= *buf++;
+
+      DBUG_ASSERT(extra_engines > 0);
+    }
+  }
+  /*
+    the strict '<' part of the assert corresponds to extra zero-padded
+    trailing bytes,
+  */
+  DBUG_ASSERT(static_cast<uint>(buf - buf_0) <= event_len);
+  /* and the last of them is tested. */
+  DBUG_ASSERT(static_cast<uint>(buf - buf_0) == event_len ||
+              buf_0[event_len - 1] == 0);
 }
 
 
-- 
cgit v1.2.1