wait_after_within_v3.patch

diff --git a/doc/src/sgml/ref/allfiles.sgml b/doc/src/sgml/ref/allfiles.sgml
index fda4690eab..410018b79b 100644
--- a/doc/src/sgml/ref/allfiles.sgml
+++ b/doc/src/sgml/ref/allfiles.sgml
@@ -188,6 +188,7 @@ Complete list of usable sgml source files in this directory.
 <!ENTITY update             SYSTEM "update.sgml">
 <!ENTITY vacuum             SYSTEM "vacuum.sgml">
 <!ENTITY values             SYSTEM "values.sgml">
+<!ENTITY wait               SYSTEM "wait.sgml">
 
 <!-- applications and utilities -->
 <!ENTITY clusterdb          SYSTEM "clusterdb.sgml">
diff --git a/doc/src/sgml/ref/begin.sgml b/doc/src/sgml/ref/begin.sgml
index 016b021487..a2794763b1 100644
--- a/doc/src/sgml/ref/begin.sgml
+++ b/doc/src/sgml/ref/begin.sgml
@@ -21,13 +21,16 @@ PostgreSQL documentation
 
  <refsynopsisdiv>
 <synopsis>
-BEGIN [ WORK | TRANSACTION ] [ <replaceable class="parameter">transaction_mode</replaceable> [, ...] ]
+BEGIN [ WORK | TRANSACTION ] [ <replaceable class="parameter">transaction_mode</replaceable> [, ...] ] <replaceable class="parameter">wait_event</replaceable>
 
 <phrase>where <replaceable class="parameter">transaction_mode</replaceable> is one of:</phrase>
 
     ISOLATION LEVEL { SERIALIZABLE | REPEATABLE READ | READ COMMITTED | READ UNCOMMITTED }
     READ WRITE | READ ONLY
     [ NOT ] DEFERRABLE
+
+<phrase>where <replaceable class="parameter">wait_event</replaceable> is:</phrase>
+    AFTER <replaceable class="parameter">lsn_value</replaceable> [ WITHIN number_of_milliseconds ]
 </synopsis>
  </refsynopsisdiv>
 
diff --git a/doc/src/sgml/ref/start_transaction.sgml b/doc/src/sgml/ref/start_transaction.sgml
index 74ccd7e345..46a3bcf1a8 100644
--- a/doc/src/sgml/ref/start_transaction.sgml
+++ b/doc/src/sgml/ref/start_transaction.sgml
@@ -21,13 +21,16 @@ PostgreSQL documentation
 
  <refsynopsisdiv>
 <synopsis>
-START TRANSACTION [ <replaceable class="parameter">transaction_mode</replaceable> [, ...] ]
+START TRANSACTION [ <replaceable class="parameter">transaction_mode</replaceable> [, ...] ] <replaceable class="parameter">wait_event</replaceable>
 
 <phrase>where <replaceable class="parameter">transaction_mode</replaceable> is one of:</phrase>
 
     ISOLATION LEVEL { SERIALIZABLE | REPEATABLE READ | READ COMMITTED | READ UNCOMMITTED }
     READ WRITE | READ ONLY
     [ NOT ] DEFERRABLE
+
+<phrase>where <replaceable class="parameter">wait_event</replaceable> is:</phrase>
+    AFTER <replaceable class="parameter">lsn_value</replaceable> [ WITHIN number_of_milliseconds ]
 </synopsis>
  </refsynopsisdiv>
 
diff --git a/doc/src/sgml/reference.sgml b/doc/src/sgml/reference.sgml
index a07d2b5e01..138e52c563 100644
--- a/doc/src/sgml/reference.sgml
+++ b/doc/src/sgml/reference.sgml
@@ -216,6 +216,7 @@
    &update;
    &vacuum;
    &values;
+   &wait;
 
  </reference>
 
diff --git a/src/backend/access/transam/xlogrecovery.c b/src/backend/access/transam/xlogrecovery.c
index 1b48d7171a..8ab86a83b5 100644
--- a/src/backend/access/transam/xlogrecovery.c
+++ b/src/backend/access/transam/xlogrecovery.c
@@ -43,6 +43,7 @@
 #include "backup/basebackup.h"
 #include "catalog/pg_control.h"
 #include "commands/tablespace.h"
+#include "commands/wait.h"
 #include "common/file_utils.h"
 #include "miscadmin.h"
 #include "pgstat.h"
@@ -1784,6 +1785,15 @@ PerformWalRecovery(void)
 				break;
 			}
 
+			/*
+			* If we replayed an LSN that someone was waiting for,
+			* set latches in shared memory array to notify the waiter.
+			*/
+			if (XLogRecoveryCtl->lastReplayedEndRecPtr >= GetMinWait())
+			{
+				 WaitSetLatch(XLogRecoveryCtl->lastReplayedEndRecPtr);
+			}
+
 			/* Else, try to fetch the next WAL record */
 			record = ReadRecord(xlogprefetcher, LOG, false, replayTLI);
 		} while (record != NULL);
diff --git a/src/backend/commands/Makefile b/src/backend/commands/Makefile
index 48f7348f91..d8f6965d8c 100644
--- a/src/backend/commands/Makefile
+++ b/src/backend/commands/Makefile
@@ -61,6 +61,7 @@ OBJS = \
 	vacuum.o \
 	vacuumparallel.o \
 	variable.o \
-	view.o
+	view.o \
+	wait.o
 
 include $(top_srcdir)/src/backend/common.mk
diff --git a/src/backend/commands/meson.build b/src/backend/commands/meson.build
index 6dd00a4abd..3f06dc5341 100644
--- a/src/backend/commands/meson.build
+++ b/src/backend/commands/meson.build
@@ -50,4 +50,5 @@ backend_sources += files(
   'vacuumparallel.c',
   'variable.c',
   'view.c',
+  'wait.c',
 )
diff --git a/src/backend/commands/wait.c b/src/backend/commands/wait.c
new file mode 100644
index 0000000000..5baa6e2ee3
--- /dev/null
+++ b/src/backend/commands/wait.c
@@ -0,0 +1,338 @@
+/*-------------------------------------------------------------------------
+ *
+ * wait.c
+ *	  Implements WAIT FOR, which allows waiting for events such as
+ *	  time passing or LSN having been replayed on replica.
+ *
+ * Portions Copyright (c) 1996-2020, PostgreSQL Global Development Group
+ * Portions Copyright (c) 2020, Regents of PostgresPro
+ *
+ * IDENTIFICATION
+ *	  src/backend/commands/wait.c
+ *
+ *-------------------------------------------------------------------------
+ */
+
+#include <float.h>
+#include <math.h>
+#include "postgres.h"
+#include "pgstat.h"
+#include "fmgr.h"
+#include "access/transam.h"
+#include "access/xact.h"
+#include "access/xlog.h"
+#include "access/xlogdefs.h"
+#include "access/xlogrecovery.h"
+#include "catalog/pg_type.h"
+#include "commands/wait.h"
+#include "funcapi.h"
+#include "miscadmin.h"
+#include "storage/backendid.h"
+#include "storage/ipc.h"
+#include "storage/latch.h"
+#include "storage/pmsignal.h"
+#include "storage/proc.h"
+#include "storage/shmem.h"
+#include "storage/spin.h"
+#include "storage/sinvaladt.h"
+#include "utils/builtins.h"
+#include "utils/pg_lsn.h"
+#include "utils/timestamp.h"
+#include "executor/spi.h"
+#include "utils/fmgrprotos.h"
+
+/* Add to / delete from shared memory array */
+static void AddEvent(XLogRecPtr lsn_to_wait);
+static void DeleteEvent(void);
+
+/* Shared memory structure */
+typedef struct
+{
+	int			backend_maxid;
+	pg_atomic_uint64	min_lsn;
+	slock_t		mutex;
+	XLogRecPtr	waited_lsn[FLEXIBLE_ARRAY_MEMBER];
+} WaitState;
+
+static volatile WaitState *state;
+
+/* Add the event of the current backend to the shared memory array */
+static void
+AddEvent(XLogRecPtr lsn_to_wait)
+{
+	SpinLockAcquire(&state->mutex);
+	if (state->backend_maxid < MyBackendId)
+		state->backend_maxid = MyBackendId;
+
+	state->waited_lsn[MyBackendId] = lsn_to_wait;
+
+	if (lsn_to_wait < state->min_lsn.value)
+		state->min_lsn.value = lsn_to_wait;
+	SpinLockRelease(&state->mutex);
+}
+
+/*
+ * Delete event of the current backend from the shared memory array.
+ *
+ * TODO: Consider state cleanup on backend failure.
+ * Check:
+ * 1) nomal|smart|fast|immediate stop
+ * 2) SIGKILL and SIGTERM
+ */
+static void
+DeleteEvent(void)
+{
+	int			i;
+	XLogRecPtr	lsn_to_delete = state->waited_lsn[MyBackendId];
+
+	state->waited_lsn[MyBackendId] = InvalidXLogRecPtr;
+
+	SpinLockAcquire(&state->mutex);
+
+	/* If we need to choose the next min_lsn, update state->min_lsn */
+	if (state->min_lsn.value == lsn_to_delete)
+	{
+		state->min_lsn.value = PG_UINT64_MAX;
+		for (i = 2; i <= state->backend_maxid; i++)
+			if (state->waited_lsn[i] != InvalidXLogRecPtr &&
+				state->waited_lsn[i] < state->min_lsn.value)
+				state->min_lsn.value = state->waited_lsn[i];
+	}
+
+	if (state->backend_maxid == MyBackendId)
+		for (i = (MyBackendId); i >= 2; i--)
+			if (state->waited_lsn[i] != InvalidXLogRecPtr)
+			{
+				state->backend_maxid = i;
+				break;
+			}
+
+	SpinLockRelease(&state->mutex);
+}
+
+/*
+ * Report amount of shared memory space needed for WaitState
+ */
+Size
+WaitShmemSize(void)
+{
+	Size		size;
+
+	size = offsetof(WaitState, waited_lsn);
+	size = add_size(size, mul_size(MaxBackends + 1, sizeof(XLogRecPtr)));
+	return size;
+}
+
+/* Init array of events in shared memory */
+void
+WaitShmemInit(void)
+{
+	bool		found;
+	uint32		i;
+
+	state = (WaitState *) ShmemInitStruct("pg_wait_lsn",
+										  WaitShmemSize(),
+										  &found);
+	if (!found)
+	{
+		SpinLockInit(&state->mutex);
+
+		for (i = 0; i < (MaxBackends + 1); i++)
+			state->waited_lsn[i] = InvalidXLogRecPtr;
+
+		state->backend_maxid = 0;
+		state->min_lsn.value = PG_UINT64_MAX;
+	}
+}
+
+/* Set all latches in shared memory to signal that new LSN has been replayed */
+void
+WaitSetLatch(XLogRecPtr cur_lsn)
+{
+	uint32		i;
+	int 		backend_maxid;
+	PGPROC	   *backend;
+
+	SpinLockAcquire(&state->mutex);
+	backend_maxid = state->backend_maxid;
+	SpinLockRelease(&state->mutex);
+
+	for (i = 2; i <= backend_maxid; i++)
+	{
+		backend = BackendIdGetProc(i);
+		if (state->waited_lsn[i] != 0)
+		{
+			if (backend && state->waited_lsn[i] <= cur_lsn)
+				SetLatch(&backend->procLatch);
+		}
+	}
+}
+
+/* Get minimal LSN that will be next */
+XLogRecPtr
+GetMinWait(void)
+{
+	return pg_atomic_read_u64(&state->min_lsn);
+}
+
+/*
+ * On WAIT use MyLatch to wait till LSN is replayed,
+ * postmaster dies or timeout happens.
+ */
+int
+WaitUtility(XLogRecPtr lsn, const float8 secs)
+{
+	XLogRecPtr	cur_lsn = GetXLogReplayRecPtr(NULL);
+	int			latch_events;
+	float8		endtime;
+	uint		res = 0;
+
+	if (!RecoveryInProgress())
+	{
+		ereport(ERROR,
+				(errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE),
+				errmsg("Work only in standby mode")));
+		return false;
+	}
+
+#define GetNowFloat()	((float8) GetCurrentTimestamp() / 1000000.0)
+	endtime = GetNowFloat() + secs;
+
+	latch_events = WL_TIMEOUT | WL_EXIT_ON_PM_DEATH;
+
+	if (lsn != InvalidXLogRecPtr)
+	{
+		/* Just check if we reached */
+		if (lsn < cur_lsn || secs < 0)
+			return (lsn < cur_lsn);
+
+		latch_events |= WL_LATCH_SET;
+		AddEvent(lsn);
+	}
+	else if (!secs)
+		return 1;
+
+	for (;;)
+	{
+		int			rc;
+		float8		delay = 0;
+		long		delay_ms;
+
+		/* If LSN has been replayed */
+		if (lsn && lsn <= cur_lsn)
+			break;
+
+		if (secs > 0)
+			delay = endtime - GetNowFloat();
+		else if (secs == 0)
+			/*
+			* If we wait forever, then 1 minute timeout to check
+			* for Interupts.
+			*/
+			delay = 60;
+
+		if (delay > 0.0)
+			delay_ms = (long) ceil(delay * 1000.0);
+		else
+			break;
+
+		/*
+		 * If received an interruption from CHECK_FOR_INTERRUPTS,
+		 * then delete the current event from array.
+		 */
+		if (InterruptPending)
+		{
+			if (lsn != InvalidXLogRecPtr)
+				DeleteEvent();
+			ProcessInterrupts();
+		}
+
+		/* If postmaster dies, finish immediately */
+		if (!PostmasterIsAlive())
+			break;
+
+		rc = WaitLatch(MyLatch, latch_events, delay_ms,
+					   WAIT_EVENT_CLIENT_READ);
+
+		if (rc & WL_LATCH_SET)
+			ResetLatch(MyLatch);
+
+		if (lsn && rc & WL_LATCH_SET)
+			cur_lsn = GetXLogReplayRecPtr(NULL);
+	}
+
+	if (lsn != InvalidXLogRecPtr)
+		DeleteEvent();
+
+	if (lsn != InvalidXLogRecPtr && lsn > cur_lsn)
+		elog(NOTICE,"LSN is not reached. Try to increase wait time.");
+	else
+		res = 1;
+
+	return res;
+}
+
+/*
+ * Get the amount of seconds left till the specified time.
+ */
+float8
+WaitTimeResolve(Const *time)
+{
+	int			ret;
+	float8		val;
+	Oid			types[] = { time->consttype };
+	Datum		values[] = { time->constvalue };
+	char		nulls[] = { " " };
+	Datum		result;
+	bool		isnull;
+
+	SPI_connect();
+
+	if (time->consttype == 1083)
+		ret = SPI_execute_with_args("select extract (epoch from ($1 - now()::time))",
+									1, types, values, nulls, true, 0);
+	else if (time->consttype == 1266)
+		ret = SPI_execute_with_args("select extract (epoch from (timezone('UTC',$1)::time - timezone('UTC', now()::timetz)::time))",
+									1, types, values, nulls, true, 0);
+	else
+		ret = SPI_execute_with_args("select extract (epoch from ($1 - now()))",
+									1, types, values, nulls, true, 0);
+
+	Assert(ret >= 0);
+	result = SPI_getbinval(SPI_tuptable->vals[0],
+						   SPI_tuptable->tupdesc,
+						   1, &isnull);
+
+	Assert(!isnull);
+	val = DatumGetFloat8(result);
+
+	elog(INFO, "time: %f", val);
+
+	SPI_finish();
+	return val;
+}
+
+/* Implementation of WAIT FOR */
+int
+WaitMain(WaitStmt *stmt, DestReceiver *dest)
+{
+	TupleDesc	tupdesc;
+	TupOutputState *tstate;
+	XLogRecPtr	lsn = InvalidXLogRecPtr;
+	int		res = 0;
+
+	lsn = DatumGetLSN(DirectFunctionCall1(pg_lsn_in,
+												 CStringGetDatum(stmt->lsn)));
+	res = WaitUtility(lsn, stmt->delay);
+
+	/* Need a tuple descriptor representing a single TEXT column */
+	tupdesc = CreateTemplateTupleDesc(1);
+	TupleDescInitEntry(tupdesc, (AttrNumber) 1, "LSN reached", TEXTOID, -1, 0);
+	/* Prepare for projection of tuples */
+	tstate = begin_tup_output_tupdesc(dest, tupdesc, &TTSOpsMinimalTuple);
+
+	/* Send it */
+	do_text_output_oneline(tstate, res?"t":"f");
+	end_tup_output(tstate);
+	return res;
+}
diff --git a/src/backend/parser/analyze.c b/src/backend/parser/analyze.c
index 06fc8ce98b..f1d86ff435 100644
--- a/src/backend/parser/analyze.c
+++ b/src/backend/parser/analyze.c
@@ -405,7 +405,6 @@ transformStmt(ParseState *pstate, Node *parseTree)
 			result = transformCallStmt(pstate,
 									   (CallStmt *) parseTree);
 			break;
-
 		default:
 
 			/*
diff --git a/src/backend/parser/gram.y b/src/backend/parser/gram.y
index 6b88096e8e..da090b1285 100644
--- a/src/backend/parser/gram.y
+++ b/src/backend/parser/gram.y
@@ -312,7 +312,7 @@ static Node *makeRecursiveViewSelect(char *relname, List *aliases, Node *query);
 		SecLabelStmt SelectStmt TransactionStmt TransactionStmtLegacy TruncateStmt
 		UnlistenStmt UpdateStmt VacuumStmt
 		VariableResetStmt VariableSetStmt VariableShowStmt
-		ViewStmt CheckPointStmt CreateConversionStmt
+		ViewStmt WaitStmt CheckPointStmt CreateConversionStmt
 		DeallocateStmt PrepareStmt ExecuteStmt
 		DropOwnedStmt ReassignOwnedStmt
 		AlterTSConfigurationStmt AlterTSDictionaryStmt
@@ -644,6 +644,8 @@ static Node *makeRecursiveViewSelect(char *relname, List *aliases, Node *query);
 %type <partboundspec> PartitionBoundSpec
 %type <list>		hash_partbound
 %type <defelt>		hash_partbound_elem
+%type <ival>		wait_time
+%type <node>		wait_for
 
 %type <node>	json_format_clause
 				json_format_clause_opt
@@ -1102,6 +1104,7 @@ stmt:
 			| VariableSetStmt
 			| VariableShowStmt
 			| ViewStmt
+			| WaitStmt
 			| /*EMPTY*/
 				{ $$ = NULL; }
 		;
@@ -10921,12 +10924,13 @@ TransactionStmt:
 					n->location = -1;
 					$$ = (Node *) n;
 				}
-			| START TRANSACTION transaction_mode_list_or_empty
+			| START TRANSACTION transaction_mode_list_or_empty wait_for
 				{
 					TransactionStmt *n = makeNode(TransactionStmt);
 
 					n->kind = TRANS_STMT_START;
 					n->options = $3;
+					n->wait = $4;
 					n->location = -1;
 					$$ = (Node *) n;
 				}
@@ -11025,12 +11029,13 @@ TransactionStmt:
 		;
 
 TransactionStmtLegacy:
-			BEGIN_P opt_transaction transaction_mode_list_or_empty
+			BEGIN_P opt_transaction transaction_mode_list_or_empty wait_for
 				{
 					TransactionStmt *n = makeNode(TransactionStmt);
 
 					n->kind = TRANS_STMT_BEGIN;
 					n->options = $3;
+					n->wait = $4;
 					n->location = -1;
 					$$ = (Node *) n;
 				}
@@ -15862,6 +15867,37 @@ xml_passing_mech:
 			| BY VALUE_P
 		;
 
+/*****************************************************************************
+ *
+ *		QUERY:
+ *				AFTER LSN_value [WITHIN delay timestamp]
+ *
+ *****************************************************************************/
+WaitStmt:
+			AFTER Sconst wait_time
+				{
+					WaitStmt *n = makeNode(WaitStmt);
+					n->lsn = $2;
+					n->delay = $3;
+					$$ = (Node *)n;
+				}
+		;
+wait_for:
+			AFTER Sconst wait_time
+				{
+					WaitStmt *n = makeNode(WaitStmt);
+					n->lsn = $2;
+					n->delay = $3;
+					$$ = (Node *)n;
+				}
+			| /* EMPTY */		{ $$ = NULL; }
+		;
+
+wait_time:
+			WITHIN Iconst		{ $$ = $2; }
+			| /* EMPTY */           { $$ = 0; }
+		;
+
 
 /*
  * Aggregate decoration clauses
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index e5119ed55d..ff6a3db6a6 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -26,6 +26,7 @@
 #include "access/xlogprefetcher.h"
 #include "access/xlogrecovery.h"
 #include "commands/async.h"
+#include "commands/wait.h"
 #include "miscadmin.h"
 #include "pgstat.h"
 #include "postmaster/autovacuum.h"
@@ -149,6 +150,7 @@ CalculateShmemSize(int *num_semaphores)
 	size = add_size(size, AsyncShmemSize());
 	size = add_size(size, StatsShmemSize());
 	size = add_size(size, WaitEventExtensionShmemSize());
+	size = add_size(size, WaitShmemSize());
 #ifdef EXEC_BACKEND
 	size = add_size(size, ShmemBackendArraySize());
 #endif
@@ -241,6 +243,11 @@ CreateSharedMemoryAndSemaphores(void)
 	/* Initialize subsystems */
 	CreateOrAttachShmemStructs();
 
+	/*
+	 * Init array of Latches in shared memory for wait lsn
+	 */
+	WaitShmemInit();
+
 #ifdef EXEC_BACKEND
 
 	/*
diff --git a/src/backend/tcop/utility.c b/src/backend/tcop/utility.c
index 8de821f960..e884828011 100644
--- a/src/backend/tcop/utility.c
+++ b/src/backend/tcop/utility.c
@@ -15,6 +15,7 @@
  *-------------------------------------------------------------------------
  */
 #include "postgres.h"
+#include <float.h>
 
 #include "access/htup_details.h"
 #include "access/reloptions.h"
@@ -59,6 +60,7 @@
 #include "commands/user.h"
 #include "commands/vacuum.h"
 #include "commands/view.h"
+#include "commands/wait.h"
 #include "miscadmin.h"
 #include "parser/parse_utilcmd.h"
 #include "postmaster/bgwriter.h"
@@ -72,6 +74,9 @@
 #include "utils/lsyscache.h"
 #include "utils/rel.h"
 #include "utils/syscache.h"
+#include "executor/spi.h"
+#include "utils/fmgrprotos.h"
+#include "utils/pg_lsn.h"
 
 /* Hook for plugins to get control in ProcessUtility() */
 ProcessUtility_hook_type ProcessUtility_hook = NULL;
@@ -272,6 +277,7 @@ ClassifyUtilityCommandAsReadOnly(Node *parsetree)
 		case T_LoadStmt:
 		case T_PrepareStmt:
 		case T_UnlistenStmt:
+		case T_WaitStmt:
 		case T_VariableSetStmt:
 			{
 				/*
@@ -612,6 +618,11 @@ standard_ProcessUtility(PlannedStmt *pstmt,
 					case TRANS_STMT_START:
 						{
 							ListCell   *lc;
+							WaitStmt   *waitstmt = (WaitStmt *) stmt->wait;
+
+							/* If needed to WAIT FOR something but failed */
+							if (stmt->wait && WaitMain(waitstmt, dest) == 0)
+								break;
 
 							BeginTransactionBlock();
 							foreach(lc, stmt->options)
@@ -1069,6 +1080,13 @@ standard_ProcessUtility(PlannedStmt *pstmt,
 				break;
 			}
 
+		case T_WaitStmt:
+			{
+				WaitStmt   *stmt = (WaitStmt *) parsetree;
+				WaitMain(stmt, dest);
+				break;
+			}
+
 		default:
 			/* All other statement types have event trigger support */
 			ProcessUtilitySlow(pstate, pstmt, queryString,
@@ -2847,6 +2865,10 @@ CreateCommandTag(Node *parsetree)
 			tag = CMDTAG_NOTIFY;
 			break;
 
+		case T_WaitStmt:
+			tag = CMDTAG_WAIT;
+			break;
+
 		case T_ListenStmt:
 			tag = CMDTAG_LISTEN;
 			break;
@@ -3495,6 +3517,10 @@ GetCommandLogLevel(Node *parsetree)
 			lev = LOGSTMT_ALL;
 			break;
 
+		case T_WaitStmt:
+			lev = LOGSTMT_ALL;
+			break;
+
 		case T_ListenStmt:
 			lev = LOGSTMT_ALL;
 			break;
diff --git a/src/include/commands/wait.h b/src/include/commands/wait.h
new file mode 100644
index 0000000000..0270160d44
--- /dev/null
+++ b/src/include/commands/wait.h
@@ -0,0 +1,26 @@
+/*-------------------------------------------------------------------------
+ *
+ * wait.h
+ *	  prototypes for commands/wait.c
+ *
+ * Portions Copyright (c) 1996-2016, PostgreSQL Global Development Group
+ * Portions Copyright (c) 2016, Regents of PostgresPRO
+ *
+ * src/include/commands/wait.h
+ *
+ *-------------------------------------------------------------------------
+ */
+#ifndef WAIT_H
+#define WAIT_H
+#include "postgres.h"
+#include "tcop/dest.h"
+
+extern int WaitUtility(XLogRecPtr lsn, const float8 delay);
+extern Size WaitShmemSize(void);
+extern void WaitShmemInit(void);
+extern void WaitSetLatch(XLogRecPtr cur_lsn);
+extern XLogRecPtr GetMinWait(void);
+extern float8 WaitTimeResolve(Const *time);
+extern int WaitMain(WaitStmt *stmt, DestReceiver *dest);
+
+#endif   /* WAIT_H */
diff --git a/src/include/nodes/parsenodes.h b/src/include/nodes/parsenodes.h
index b3181f34ae..98379ae97e 100644
--- a/src/include/nodes/parsenodes.h
+++ b/src/include/nodes/parsenodes.h
@@ -3525,6 +3525,7 @@ typedef struct TransactionStmt
 	/* for two-phase-commit related commands */
 	char	   *gid pg_node_attr(query_jumble_ignore);
 	bool		chain;			/* AND CHAIN option */
+	Node		*wait;			/* wait lsn clause */
 	/* token location, or -1 if unknown */
 	int			location pg_node_attr(query_jumble_location);
 } TransactionStmt;
@@ -4076,4 +4077,16 @@ typedef struct DropSubscriptionStmt
 	DropBehavior behavior;		/* RESTRICT or CASCADE behavior */
 } DropSubscriptionStmt;
 
+/* ----------------------
+ *		AFTER Statement + AFTER clause of BEGIN statement
+ * ----------------------
+ */
+
+typedef struct WaitStmt
+{
+	NodeTag		type;
+	char	   *lsn;		/* LSN */
+	int			delay;		/* TIMEOUT */
+} WaitStmt;
+
 #endif							/* PARSENODES_H */
diff --git a/src/include/tcop/cmdtaglist.h b/src/include/tcop/cmdtaglist.h
index 7fdcec6dd9..567139963a 100644
--- a/src/include/tcop/cmdtaglist.h
+++ b/src/include/tcop/cmdtaglist.h
@@ -217,3 +217,4 @@ PG_CMDTAG(CMDTAG_TRUNCATE_TABLE, "TRUNCATE TABLE", false, false, false)
 PG_CMDTAG(CMDTAG_UNLISTEN, "UNLISTEN", false, false, false)
 PG_CMDTAG(CMDTAG_UPDATE, "UPDATE", false, false, true)
 PG_CMDTAG(CMDTAG_VACUUM, "VACUUM", false, false, false)
+PG_CMDTAG(CMDTAG_WAIT, "AFTER", false, false, false)
diff --git a/src/test/recovery/t/040_begin_after.pl b/src/test/recovery/t/040_begin_after.pl
new file mode 100644
index 0000000000..b22e63603c
--- /dev/null
+++ b/src/test/recovery/t/040_begin_after.pl
@@ -0,0 +1,86 @@
+# Checks waiting for lsn on standby AFTER
+use strict;
+use warnings;
+
+use PostgreSQL::Test::Cluster;
+use PostgreSQL::Test::Utils;
+use Test::More;
+
+# Initialize primary node
+my $node_primary = PostgreSQL::Test::Cluster->new('primary');
+$node_primary->init(allows_streaming => 1);
+$node_primary->start;
+
+# And some content and take a backup
+$node_primary->safe_psql('postgres',
+	"CREATE TABLE wait_test AS SELECT generate_series(1,10) AS a");
+my $backup_name = 'my_backup';
+$node_primary->backup($backup_name);
+
+# Create a streaming standby with a 1 second delay from the backup
+my $node_standby = PostgreSQL::Test::Cluster->new('standby');
+my $delay        = 1;
+$node_standby->init_from_backup($node_primary, $backup_name,
+	has_streaming => 1);
+$node_standby->append_conf('postgresql.conf', qq[
+	recovery_min_apply_delay = '${delay}s'
+]);
+$node_standby->start;
+
+
+
+# Make sure that AFTER works: add new content to primary and memorize
+# primary's new LSN, then wait for primary's LSN on standby. Prove that AFTER is
+# able to setup an infinite waiting loop and exit it if given no wait timeout.
+$node_primary->safe_psql('postgres',
+	"INSERT INTO wait_test VALUES (generate_series(11, 20))");
+my $lsn1 = $node_primary->safe_psql('postgres', "SELECT pg_current_wal_lsn()");
+$node_standby->safe_psql('postgres', "BEGIN AFTER '$lsn1'");
+
+# Get the current LSN on standby and make sure it's the same as primary's LSN
+my $lsn_standby = $node_standby->safe_psql('postgres',
+	"SELECT pg_last_wal_replay_lsn()");
+my $compare_lsns = $node_standby->safe_psql('postgres',
+	"SELECT pg_lsn_cmp('$lsn_standby'::pg_lsn, '$lsn1'::pg_lsn)");
+ok($compare_lsns eq 0, "standby reached the same LSN as primary AFTER");
+
+
+
+#===============================================================================
+# TODO: remove this test if we remove the standalone "AFTER" command
+#===============================================================================
+# We need to check that AFTER works fine inside transactions. For that, let's
+# get two LSNs that will correspond to two different max values in our table.
+$node_primary->safe_psql('postgres',
+	"INSERT INTO wait_test VALUES (generate_series(31, 40))");
+my $lsn3 = $node_primary->safe_psql('postgres', "SELECT pg_current_wal_lsn()");
+$node_primary->safe_psql('postgres',
+	"INSERT INTO wait_test VALUES (generate_series(41, 50))");
+my $lsn4 = $node_primary->safe_psql('postgres', "SELECT pg_current_wal_lsn()");
+
+# Before starting transaction, AFTER which ensures a max value of 40.
+# Inside the transaction, AFTER that ensures a max value of 50.
+# Due to ISOLATION LEVEL REPEATABLE READ, we should NOT see the new max value.
+my $standby_results = $node_standby->safe_psql(
+	'postgres', qq[
+	BEGIN TRANSACTION ISOLATION LEVEL REPEATABLE READ AFTER '$lsn3';
+	SELECT max(a) FROM wait_test;
+	BEGIN AFTER '$lsn4';
+	SELECT pg_last_wal_replay_lsn();
+	SELECT max(a) FROM wait_test;
+	COMMIT;
+]);
+
+# Make sure that we indeed reach primary's last LSN inside the transaction.
+# For that, check that calling pg_last_wal_replay_lsn returned that LSN.
+my $last_lsn_reached = $standby_results =~ /$lsn4/;
+ok($last_lsn_reached, "AFTER works inside a transaction");
+
+# Check that transaction doesn't break and show us the new max value after AFTER.
+# For that, make sure that the older max value is repeated twice in the results.
+my $count = () = $standby_results =~ /40/g;
+ok($count eq 2, "transaction isolation level doesn't get broken due to AFTER");
+
+$node_standby->stop;
+$node_primary->stop;
+done_testing();
diff --git a/src/test/recovery/t/041_after.pl b/src/test/recovery/t/041_after.pl
new file mode 100644
index 0000000000..480ba6b33b
--- /dev/null
+++ b/src/test/recovery/t/041_after.pl
@@ -0,0 +1,99 @@
+# Checks waiting for lsn on standby AFTER
+use strict;
+use warnings;
+
+use PostgreSQL::Test::Cluster;
+use PostgreSQL::Test::Utils;
+use Test::More;
+
+# Initialize primary node
+my $node_primary = PostgreSQL::Test::Cluster->new('primary');
+$node_primary->init(allows_streaming => 1);
+$node_primary->start;
+
+# And some content and take a backup
+$node_primary->safe_psql('postgres',
+	"CREATE TABLE wait_test AS SELECT generate_series(1,10) AS a");
+my $backup_name = 'my_backup';
+$node_primary->backup($backup_name);
+
+# Create a streaming standby with a 1 second delay from the backup
+my $node_standby = PostgreSQL::Test::Cluster->new('standby');
+my $delay        = 2;
+$node_standby->init_from_backup($node_primary, $backup_name,
+	has_streaming => 1);
+$node_standby->append_conf('postgresql.conf', qq[
+	recovery_min_apply_delay = '${delay}s'
+]);
+$node_standby->start;
+
+
+
+# Make sure that AFTER works: add new content to primary and memorize
+# primary's new LSN, then wait for primary's LSN on standby. Prove that AFTER is
+# able to setup an infinite waiting loop and exit it if given no wait timeout.
+$node_primary->safe_psql('postgres',
+	"INSERT INTO wait_test VALUES (generate_series(11, 20))");
+my $lsn1 = $node_primary->safe_psql('postgres', "SELECT pg_current_wal_lsn()");
+$node_standby->safe_psql('postgres', "AFTER '$lsn1'");
+
+# Get the current LSN on standby and make sure it's the same as primary's LSN
+my $lsn_standby = $node_standby->safe_psql('postgres',
+	"SELECT pg_last_wal_replay_lsn()");
+my $compare_lsns = $node_standby->safe_psql('postgres',
+	"SELECT pg_lsn_cmp('$lsn_standby'::pg_lsn, '$lsn1'::pg_lsn)");
+ok($compare_lsns eq 0, "standby reached the same LSN as primary AFTER");
+
+
+
+# Check that timeouts work on their own and let us wait for specified time (1s)
+my $current_time = $node_standby->safe_psql('postgres', "SELECT now()");
+my $one_second = 1000; # in milliseconds
+my $start_time = time();
+
+# Now, check that timeouts work as expected when waiting for LSN
+$node_primary->safe_psql('postgres',
+	"INSERT INTO wait_test VALUES (generate_series(21, 30))");
+my $lsn2 = $node_primary->safe_psql('postgres', "SELECT pg_current_wal_lsn()");
+my $reached_lsn = $node_standby->safe_psql('postgres',
+	"AFTER '$lsn2' WITHIN 1");
+ok($reached_lsn eq "f", "AFTER doesn't reach LSN if given too little wait time");
+
+
+
+# We need to check that WAIT works fine inside transactions. For that, let's
+# get two LSNs that will correspond to two different max values in our table.
+$node_primary->safe_psql('postgres',
+	"INSERT INTO wait_test VALUES (generate_series(31, 40))");
+my $lsn3 = $node_primary->safe_psql('postgres', "SELECT pg_current_wal_lsn()");
+$node_primary->safe_psql('postgres',
+	"INSERT INTO wait_test VALUES (generate_series(41, 50))");
+my $lsn4 = $node_primary->safe_psql('postgres', "SELECT pg_current_wal_lsn()");
+
+# Before starting transaction, AFTER which ensures a max value of 40.
+# Inside the transaction, AFTER that ensures a max value of 50.
+# Due to ISOLATION LEVEL REPEATABLE READ, we should NOT see the new max value.
+my $standby_results = $node_standby->safe_psql(
+	'postgres', qq[
+	AFTER '$lsn3';
+	BEGIN TRANSACTION ISOLATION LEVEL REPEATABLE READ;
+	SELECT max(a) FROM wait_test;
+	AFTER '$lsn4';
+	SELECT pg_last_wal_replay_lsn();
+	SELECT max(a) FROM wait_test;
+	COMMIT;
+]);
+
+# Make sure that we indeed reach primary's last LSN inside the transaction.
+# For that, check that calling pg_last_wal_replay_lsn returned that LSN.
+my $last_lsn_reached = $standby_results =~ /$lsn4/;
+ok($last_lsn_reached, "AFTER works inside a transaction");
+
+# Check that transaction doesn't break and show us the new max value after AFTER.
+# For that, make sure that the older max value is repeated twice in the results.
+my $count = () = $standby_results =~ /40/g;
+ok($count eq 2, "transaction isolation level doesn't get broken due to AFTER");
+
+$node_standby->stop;
+$node_primary->stop;
+done_testing();