Add Commit Sequence Number (CSN) machinery into MVCC implementation f…

doc/src/sgml/config.sgml

@@ -10295,8 +10295,56 @@ dynamic_library_path = 'C:\tools\postgresql;H:\my_project\lib;$libdir'
      </varlistentry>
 
      </variablelist>
-   </sect1>
 
+    <sect2 id="runtime-config-CSN-based-snapshot">
+     <title>CSN Based Snapshot</title>
+      <para>
+       By default, snapshots in <productname>PostgreSQL</productname> contains a
+       XID (TransactionID) that allows to identify the status of a transaction
+       and make arbitrary visibility calculations.
+      </para>
+
+      <para>
+       <productname>PostgreSQL</productname> also provides a CSN (Commit
+        Sequence Number) based machinery as an additional tool for visibility
+        calculations. It may be used within distributed transactions when a xid of
+        a local transaction can't correctly identify order of the distributed one.
+      </para>
+
+     <variablelist>
+      <varlistentry id="guc-enable-csn-snapshot" xreflabel="enable_csn_snapshot">
+       <term><varname>enable_csn_snapshot</varname> (<type>boolean</type>)
+        <indexterm>
+         <primary><varname>enable_csn_snapshot</varname> configuration parameter</primary>
+        </indexterm>
+       </term>
+       <listitem>
+
+        <para>
+         Enable/disable the CSN tracking for the snapshot.
+        </para>
+
+        <para>
+        <productname>PostgreSQL</productname> uses a physical clock timestamp as
+        a CSN, so enabling the CSN based snapshots can be useful for implementing
+        cross-instance snapshots and visibility of distributed transaction.
+        </para>
+
+        <para>
+         when enabled <productname>PostgreSQL</productname> creates
+         <filename>pg_csn</filename> directory under <envar>PGDATA</envar> to keep
+         the track of CSN and XID mappings.
+        </para>
+
+        <para>
+         The default value is on.
+        </para>
+       </listitem>
+      </varlistentry>
+
+     </variablelist>
+    </sect2>
+   </sect1>
    <sect1 id="runtime-config-compatible">
     <title>Version and Platform Compatibility</title>
 

src/backend/access/rmgrdesc/Makefile

@@ -11,6 +11,7 @@ include $(top_builddir)/src/Makefile.global
 OBJS = \
 	brindesc.o \
 	clogdesc.o \
+	csnlogdesc.o \
 	committsdesc.o \
 	dbasedesc.o \
 	genericdesc.o \

src/backend/access/rmgrdesc/csnlogdesc.c

@@ -0,0 +1,95 @@
+/*-------------------------------------------------------------------------
+ *
+ * clogdesc.c
+ *	  rmgr descriptor routines for access/transam/csn_log.c
+ *
+ * Portions Copyright (c) 1996-2021, PostgreSQL Global Development Group
+ * Portions Copyright (c) 1994, Regents of the University of California
+ *
+ *
+ * IDENTIFICATION
+ *	  src/backend/access/rmgrdesc/csnlogdesc.c
+ *
+ *-------------------------------------------------------------------------
+ */
+#include "postgres.h"
+
+#include "access/csn_log.h"
+
+
+void
+csnlog_desc(StringInfo buf, XLogReaderState *record)
+{
+	char	   *rec = XLogRecGetData(record);
+	uint8		info = XLogRecGetInfo(record) & ~XLR_INFO_MASK;
+
+	if (info == XLOG_CSN_ZEROPAGE)
+	{
+		int pageno;
+
+		memcpy(&pageno, XLogRecGetData(record), sizeof(int));
+		appendStringInfo(buf, "pageno %d", pageno);
+	}
+	else if (info == XLOG_CSN_TRUNCATE)
+	{
+		int pageno;
+
+		memcpy(&pageno, XLogRecGetData(record), sizeof(int));
+		appendStringInfo(buf, "pageno %d", pageno);
+	}
+	else if (info == XLOG_CSN_ASSIGNMENT)
+	{
+		CSN csn;
+
+		memcpy(&csn, XLogRecGetData(record), sizeof(CSN));
+		appendStringInfo(buf, "assign "INT64_FORMAT"", csn);
+	}
+	else if (info == XLOG_CSN_SETCSN)
+	{
+		xl_csn_set *xlrec = (xl_csn_set *) rec;
+		int			  nsubxids;
+
+		appendStringInfo(buf, "set "INT64_FORMAT" for: %u",
+						 xlrec->csn,
+						 xlrec->xtop);
+		nsubxids = ((XLogRecGetDataLen(record) - MinSizeOfCSNSet) /
+					sizeof(TransactionId));
+		if (nsubxids > 0)
+		{
+			int			i;
+			TransactionId *subxids;
+
+			subxids = palloc(sizeof(TransactionId) * nsubxids);
+			memcpy(subxids,
+				   XLogRecGetData(record) + MinSizeOfCSNSet,
+				   sizeof(TransactionId) * nsubxids);
+			for (i = 0; i < nsubxids; i++)
+				appendStringInfo(buf, ", %u", subxids[i]);
+			pfree(subxids);
+		}
+	}
+}
+
+const char *
+csnlog_identify(uint8 info)
+{
+	const char *id = NULL;
+
+	switch (info & ~XLR_INFO_MASK)
+	{
+		case XLOG_CSN_ASSIGNMENT:
+			id = "ASSIGNMENT";
+			break;
+		case XLOG_CSN_SETCSN:
+			id = "SETCSN";
+			break;
+		case XLOG_CSN_ZEROPAGE:
+			id = "ZEROPAGE";
+			break;
+		case XLOG_CSN_TRUNCATE:
+			id = "TRUNCATE";
+			break;
+	}
+
+	return id;
+}

src/backend/access/rmgrdesc/xlogdesc.c

@@ -113,15 +113,17 @@ xlog_desc(StringInfo buf, XLogReaderState *record)
 		appendStringInfo(buf, "max_connections=%d max_worker_processes=%d "
 						 "max_wal_senders=%d max_prepared_xacts=%d "
 						 "max_locks_per_xact=%d wal_level=%s "
-						 "wal_log_hints=%s track_commit_timestamp=%s",
+						 "wal_log_hints=%s track_commit_timestamp=%s "
+						 "enable_csn_snapshot=%s",
 						 xlrec.MaxConnections,
 						 xlrec.max_worker_processes,
 						 xlrec.max_wal_senders,
 						 xlrec.max_prepared_xacts,
 						 xlrec.max_locks_per_xact,
 						 wal_level_str,
 						 xlrec.wal_log_hints ? "on" : "off",
-						 xlrec.track_commit_timestamp ? "on" : "off");
+						 xlrec.track_commit_timestamp ? "on" : "off",
+						 xlrec.enable_csn_snapshot ? "on" : "off");
 	}
 	else if (info == XLOG_FPW_CHANGE)
 	{

src/backend/access/transam/Makefile

@@ -15,6 +15,8 @@ include $(top_builddir)/src/Makefile.global
 OBJS = \
 	clog.o \
 	commit_ts.o \
+	csn_log.o \
+	csn_snapshot.o \
 	generic_xlog.o \
 	multixact.o \
 	parallel.o \