public inbox for [email protected]  
help / color / mirror / Atom feed
[PATCH 4/6] TAP test for the slot limit feature
101+ messages / 6 participants
[nested] [flat]

* [PATCH 4/6] TAP test for the slot limit feature
@ 2017-12-21 08:33  Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 101+ messages in thread

From: Kyotaro Horiguchi @ 2017-12-21 08:33 UTC (permalink / raw)

---
 src/test/recovery/t/018_replslot_limit.pl | 198 ++++++++++++++++++++++++++++++
 1 file changed, 198 insertions(+)
 create mode 100644 src/test/recovery/t/018_replslot_limit.pl

diff --git a/src/test/recovery/t/018_replslot_limit.pl b/src/test/recovery/t/018_replslot_limit.pl
new file mode 100644
index 0000000000..2bd6fdf39c
--- /dev/null
+++ b/src/test/recovery/t/018_replslot_limit.pl
@@ -0,0 +1,198 @@
+# Test for replication slot limit
+# Ensure that max_slot_wal_keep_size limits the number of WAL files to
+# be kept by replication slots.
+
+use strict;
+use warnings;
+use File::Path qw(rmtree);
+use PostgresNode;
+use TestLib;
+use Test::More tests => 13;
+use Time::HiRes qw(usleep);
+
+$ENV{PGDATABASE} = 'postgres';
+
+# Initialize master node, setting wal-segsize to 1MB
+my $node_master = get_new_node('master');
+$node_master->init(allows_streaming => 1, extra => ['--wal-segsize=1']);
+$node_master->append_conf('postgresql.conf', qq(
+min_wal_size = 2MB
+max_wal_size = 3MB
+));
+$node_master->start;
+$node_master->safe_psql('postgres', "SELECT pg_create_physical_replication_slot('rep1')");
+
+# The slot state should be the state "unknown" before the first connection
+my $result = $node_master->safe_psql('postgres', "SELECT restart_lsn, wal_status, remain FROM pg_replication_slots WHERE slot_name = 'rep1'");
+is($result, "|unknown|0", 'check the state of non-reserved slot is "unknown"');
+
+
+# Take backup
+my $backup_name = 'my_backup';
+$node_master->backup($backup_name);
+
+# Create a standby linking to it using the replication slot
+my $node_standby = get_new_node('standby_1');
+$node_standby->init_from_backup($node_master, $backup_name, has_streaming => 1, primary_slot_name => 'rep1');
+
+$node_standby->start;
+
+# Wait until standby has replayed enough data
+my $start_lsn = $node_master->lsn('write');
+$node_master->wait_for_catchup($node_standby, 'replay', $start_lsn);
+
+# Stop standby
+$node_standby->stop;
+
+
+# Preparation done, the slot is the state "streaming" now
+$result = $node_master->safe_psql('postgres', "SELECT restart_lsn, wal_status, remain FROM pg_replication_slots WHERE slot_name = 'rep1'");
+is($result, "$start_lsn|streaming|0", 'check the catching-up state');
+
+# Advance WAL by five segments (= 5MB) on master
+advance_wal($node_master, 1);
+$node_master->safe_psql('postgres', "CHECKPOINT;");
+
+# The slot is always "safe" when fitting max_wal_size
+$result = $node_master->safe_psql('postgres', "SELECT restart_lsn, wal_status, remain FROM pg_replication_slots WHERE slot_name = 'rep1'");
+is($result, "$start_lsn|streaming|0", 'check that within max_wal_size');
+
+advance_wal($node_master, 4);
+$node_master->safe_psql('postgres', "CHECKPOINT;");
+
+# The slot is always "safe" when max_slot_wal_keep_size is not set
+$result = $node_master->safe_psql('postgres', "SELECT restart_lsn, wal_status, remain FROM pg_replication_slots WHERE slot_name = 'rep1'");
+is($result, "$start_lsn|keeping|0", 'check that slot is working');
+
+# The standby can reconnect to master
+$node_standby->start;
+
+$start_lsn = $node_master->lsn('write');
+$node_master->wait_for_catchup($node_standby, 'replay', $start_lsn);
+
+$node_standby->stop;
+
+# Set max_slot_wal_keep_size on master
+my $max_slot_wal_keep_size_mb = 4;
+$node_master->append_conf('postgresql.conf', qq(
+max_slot_wal_keep_size = ${max_slot_wal_keep_size_mb}MB
+));
+$node_master->reload;
+
+# The slot is in safe state. The remaining bytes should be as almost
+# (max_slot_wal_keep_size + 1) times large as the segment size
+$result = $node_master->safe_psql('postgres', "SELECT restart_lsn, wal_status, pg_size_pretty(remain) as remain FROM pg_replication_slots WHERE slot_name = 'rep1'");
+is($result, "$start_lsn|streaming|5120 kB", 'check that max_slot_wal_keep_size is working');
+
+# Advance WAL again then checkpoint, reducing remain by 2 MB.
+advance_wal($node_master, 2);
+$node_master->safe_psql('postgres', "CHECKPOINT;");
+
+# The slot is still working
+$result = $node_master->safe_psql('postgres', "SELECT restart_lsn, wal_status, pg_size_pretty(remain) as remain FROM pg_replication_slots WHERE slot_name = 'rep1'");
+is($result, "$start_lsn|streaming|3072 kB", 'check that remaining byte is calculated correctly');
+
+# wal_keep_segments overrides max_slot_wal_keep_size
+$result = $node_master->safe_psql('postgres', "ALTER SYSTEM SET wal_keep_segments to 6; SELECT pg_reload_conf();");
+$result = $node_master->safe_psql('postgres', "SELECT restart_lsn, wal_status, pg_size_pretty(remain) as remain FROM pg_replication_slots WHERE slot_name = 'rep1'");
+is($result, "$start_lsn|streaming|5120 kB", 'check that wal_keep_segments overrides max_slot_wal_keep_size');
+
+# restore wal_keep_segments
+$result = $node_master->safe_psql('postgres', "ALTER SYSTEM SET wal_keep_segments to 0; SELECT pg_reload_conf();");
+
+# Advance WAL again without checkpoint, reducing remain by 2 MB.
+advance_wal($node_master, 2);
+
+# Slot gets into 'keeping' state
+$result = $node_master->safe_psql('postgres', "SELECT restart_lsn, wal_status, pg_size_pretty(remain) as remain FROM pg_replication_slots WHERE slot_name = 'rep1'");
+is($result, "$start_lsn|keeping|1024 kB", 'check that the slot state changes to "keeping"');
+
+# Advance WAL again without checkpoint; remain goes to 0.
+advance_wal($node_master, 1);
+
+# Slot gets into 'keeping' state
+$result = $node_master->safe_psql('postgres', "SELECT restart_lsn, wal_status, pg_size_pretty(remain) as remain FROM pg_replication_slots WHERE slot_name = 'rep1'");
+is($result, "$start_lsn|lost|0 bytes", 'check that the slot state changes to "lost"');
+
+# The standby still can connect to master before a checkpoint
+$node_standby->start;
+
+$start_lsn = $node_master->lsn('write');
+$node_master->wait_for_catchup($node_standby, 'replay', $start_lsn);
+
+$node_standby->stop;
+
+ok(!find_in_log($node_standby,
+				"requested WAL segment [0-9A-F]+ has already been removed"),
+   'check that required WAL segments are still available');
+
+# Advance WAL again, the slot loses the oldest segment.
+my $logstart = get_log_size($node_master);
+advance_wal($node_master, 5);
+$node_master->safe_psql('postgres', "CHECKPOINT;");
+
+# WARNING should be issued
+ok(find_in_log($node_master,
+			   "some replication slots have lost required WAL segments\n".
+			   ".*Slot rep1 lost 1 segment\\(s\\)\\.",
+			   $logstart),
+   'check that the warning is logged');
+
+# This slot should be broken
+$result = $node_master->safe_psql('postgres', "SELECT restart_lsn, wal_status, pg_size_pretty(remain) as remain FROM pg_replication_slots WHERE slot_name = 'rep1'");
+is($result, "$start_lsn|lost|0 bytes", 'check that the slot state changes to "lost"');
+
+# The standby no longer can connect to the master
+$logstart = get_log_size($node_standby);
+$node_standby->start;
+
+my $failed = 0;
+for (my $i = 0 ; $i < 10000 ; $i++)
+{
+	if (find_in_log($node_standby,
+					"requested WAL segment [0-9A-F]+ has already been removed",
+					$logstart))
+	{
+		$failed = 1;
+		last;
+	}
+	usleep(100_000);
+}
+ok($failed, 'check that replication has been broken');
+
+$node_standby->stop;
+
+#####################################
+# Advance WAL of $node by $n segments
+sub advance_wal
+{
+	my ($node, $n) = @_;
+
+	# Advance by $n segments (= (16 * $n) MB) on master
+	for (my $i = 0 ; $i < $n ; $i++)
+	{
+		$node->safe_psql('postgres', "CREATE TABLE t (); DROP TABLE t; SELECT pg_switch_wal();");
+	}
+}
+
+# return the size of logfile of $node in bytes
+sub get_log_size
+{
+	my ($node) = @_;
+
+	return (stat $node->logfile)[7];
+}
+
+# find $pat in logfile of $node after $off-th byte
+sub find_in_log
+{
+	my ($node, $pat, $off) = @_;
+
+	$off = 0 unless defined $off;
+	my $log = TestLib::slurp_file($node->logfile);
+	return 0 if (length($log) <= $off);
+
+	$log = substr($log, $off);
+
+	return $log =~ m/$pat/;
+}
-- 
2.16.3


----Next_Part(Tue_Jul_30_21_30_45_2019_680)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v15-0005-Documentation-for-slot-limit-feature.patch"



^ permalink  raw  reply  [nested|flat] 101+ messages in thread

* [PATCH 4/6] TAP test for the slot limit feature
@ 2017-12-21 08:33  Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 101+ messages in thread

From: Kyotaro Horiguchi @ 2017-12-21 08:33 UTC (permalink / raw)

---
 src/test/recovery/t/018_replslot_limit.pl | 202 ++++++++++++++++++++++++++++++
 1 file changed, 202 insertions(+)
 create mode 100644 src/test/recovery/t/018_replslot_limit.pl

diff --git a/src/test/recovery/t/018_replslot_limit.pl b/src/test/recovery/t/018_replslot_limit.pl
new file mode 100644
index 0000000000..4b41a68faa
--- /dev/null
+++ b/src/test/recovery/t/018_replslot_limit.pl
@@ -0,0 +1,202 @@
+# Test for replication slot limit
+# Ensure that max_slot_wal_keep_size limits the number of WAL files to
+# be kept by replication slots.
+
+use strict;
+use warnings;
+use File::Path qw(rmtree);
+use PostgresNode;
+use TestLib;
+use Test::More tests => 13;
+use Time::HiRes qw(usleep);
+
+$ENV{PGDATABASE} = 'postgres';
+
+# Initialize master node, setting wal-segsize to 1MB
+my $node_master = get_new_node('master');
+$node_master->init(allows_streaming => 1, extra => ['--wal-segsize=1']);
+$node_master->append_conf('postgresql.conf', qq(
+min_wal_size = 2MB
+max_wal_size = 3MB
+log_checkpoints = yes
+));
+$node_master->start;
+$node_master->safe_psql('postgres', "SELECT pg_create_physical_replication_slot('rep1')");
+
+# The slot state and remain should be null before the first connection
+my $result = $node_master->safe_psql('postgres', "SELECT restart_lsn is NULL, wal_status is NULL, remain is NULL FROM pg_replication_slots WHERE slot_name = 'rep1'");
+is($result, "t|t|t", 'check the state of non-reserved slot is "unknown"');
+
+
+# Take backup
+my $backup_name = 'my_backup';
+$node_master->backup($backup_name);
+
+# Create a standby linking to it using the replication slot
+my $node_standby = get_new_node('standby_1');
+$node_standby->init_from_backup($node_master, $backup_name, has_streaming => 1, primary_slot_name => 'rep1');
+
+$node_standby->start;
+
+# Wait until standby has replayed enough data
+my $start_lsn = $node_master->lsn('write');
+$node_master->wait_for_catchup($node_standby, 'replay', $start_lsn);
+
+# Stop standby
+$node_standby->stop;
+
+
+# Preparation done, the slot is the state "streaming" now
+$result = $node_master->safe_psql('postgres', "SELECT restart_lsn, wal_status, remain is NULL FROM pg_replication_slots WHERE slot_name = 'rep1'");
+is($result, "$start_lsn|streaming|t", 'check the catching-up state');
+
+# Advance WAL by five segments (= 5MB) on master
+advance_wal($node_master, 1);
+$node_master->safe_psql('postgres', "CHECKPOINT;");
+
+# The slot is always "safe" when fitting max_wal_size
+$result = $node_master->safe_psql('postgres', "SELECT restart_lsn, wal_status, remain is NULL FROM pg_replication_slots WHERE slot_name = 'rep1'");
+is($result, "$start_lsn|streaming|t", 'check that restart_lsn is in max_wal_size');
+
+advance_wal($node_master, 4);
+$node_master->safe_psql('postgres', "CHECKPOINT;");
+
+# The slot is always "safe" when max_slot_wal_keep_size is not set
+$result = $node_master->safe_psql('postgres', "SELECT restart_lsn, wal_status, remain is NULL FROM pg_replication_slots WHERE slot_name = 'rep1'");
+is($result, "$start_lsn|streaming|t", 'check that slot is working');
+
+# The standby can reconnect to master
+$node_standby->start;
+
+$start_lsn = $node_master->lsn('write');
+$node_master->wait_for_catchup($node_standby, 'replay', $start_lsn);
+
+$node_standby->stop;
+
+# Set max_slot_wal_keep_size on master
+my $max_slot_wal_keep_size_mb = 4;
+$node_master->append_conf('postgresql.conf', qq(
+max_slot_wal_keep_size = ${max_slot_wal_keep_size_mb}MB
+));
+$node_master->reload;
+
+# The slot is in safe state. The remaining bytes should be as almost
+# (max_slot_wal_keep_size + 1) times large as the segment size
+$result = $node_master->safe_psql('postgres', "SELECT restart_lsn, wal_status, pg_size_pretty(remain) as remain FROM pg_replication_slots WHERE slot_name = 'rep1'");
+is($result, "$start_lsn|streaming|5120 kB", 'check that max_slot_wal_keep_size is working');
+
+# Advance WAL again then checkpoint, reducing remain by 2 MB.
+advance_wal($node_master, 2);
+$node_master->safe_psql('postgres', "CHECKPOINT;");
+
+# The slot is still working
+$result = $node_master->safe_psql('postgres', "SELECT restart_lsn, wal_status, pg_size_pretty(remain) as remain FROM pg_replication_slots WHERE slot_name = 'rep1'");
+is($result, "$start_lsn|streaming|3072 kB", 'check that remaining byte is calculated correctly');
+
+# wal_keep_segments overrides max_slot_wal_keep_size
+$result = $node_master->safe_psql('postgres', "ALTER SYSTEM SET wal_keep_segments to 6; SELECT pg_reload_conf();");
+$result = $node_master->safe_psql('postgres', "SELECT restart_lsn, wal_status, pg_size_pretty(remain) as remain FROM pg_replication_slots WHERE slot_name = 'rep1'");
+is($result, "$start_lsn|streaming|5120 kB", 'check that wal_keep_segments overrides max_slot_wal_keep_size');
+
+# restore wal_keep_segments
+$result = $node_master->safe_psql('postgres', "ALTER SYSTEM SET wal_keep_segments to 0; SELECT pg_reload_conf();");
+
+# Advance WAL again without checkpoint, reducing remain by 2 MB.
+advance_wal($node_master, 2);
+
+# Slot gets into 'keeping' state
+$result = $node_master->safe_psql('postgres', "SELECT restart_lsn, wal_status, pg_size_pretty(remain) as remain FROM pg_replication_slots WHERE slot_name = 'rep1'");
+is($result, "$start_lsn|keeping|1024 kB", 'check that the slot state changes to "keeping"');
+
+# do checkpoint so that the next checkpoint runs too early
+$node_master->safe_psql('postgres', "CHECKPOINT;");
+
+# Advance WAL again without checkpoint; remain goes to 0.
+advance_wal($node_master, 1);
+
+# Slot gets into 'lost' state
+$result = $node_master->safe_psql('postgres', "SELECT restart_lsn, wal_status, remain is NULL FROM pg_replication_slots WHERE slot_name = 'rep1'");
+is($result, "$start_lsn|lost|t", 'check that the slot state changes to "lost"');
+
+# The standby still can connect to master before a checkpoint
+$node_standby->start;
+
+$start_lsn = $node_master->lsn('write');
+$node_master->wait_for_catchup($node_standby, 'replay', $start_lsn);
+
+$node_standby->stop;
+
+ok(!find_in_log($node_standby,
+				"requested WAL segment [0-9A-F]+ has already been removed"),
+   'check that required WAL segments are still available');
+
+# Advance WAL again, the slot loses the oldest segment.
+my $logstart = get_log_size($node_master);
+advance_wal($node_master, 5);
+$node_master->safe_psql('postgres', "CHECKPOINT;");
+
+# WARNING should be issued
+ok(find_in_log($node_master,
+			   "some replication slots have lost required WAL segments\n".
+			   ".*Slot rep1 lost 1 segment\\(s\\)\\.",
+			   $logstart),
+   'check that the warning is logged');
+
+# This slot should be broken
+$result = $node_master->safe_psql('postgres', "SELECT restart_lsn, wal_status, remain is NULL FROM pg_replication_slots WHERE slot_name = 'rep1'");
+is($result, "$start_lsn|lost|t", 'check that the slot state changes to "lost"');
+
+# The standby no longer can connect to the master
+$logstart = get_log_size($node_standby);
+$node_standby->start;
+
+my $failed = 0;
+for (my $i = 0 ; $i < 10000 ; $i++)
+{
+	if (find_in_log($node_standby,
+					"requested WAL segment [0-9A-F]+ has already been removed",
+					$logstart))
+	{
+		$failed = 1;
+		last;
+	}
+	usleep(100_000);
+}
+ok($failed, 'check that replication has been broken');
+
+$node_standby->stop;
+
+#####################################
+# Advance WAL of $node by $n segments
+sub advance_wal
+{
+	my ($node, $n) = @_;
+
+	# Advance by $n segments (= (16 * $n) MB) on master
+	for (my $i = 0 ; $i < $n ; $i++)
+	{
+		$node->safe_psql('postgres', "CREATE TABLE t (); DROP TABLE t; SELECT pg_switch_wal();");
+	}
+}
+
+# return the size of logfile of $node in bytes
+sub get_log_size
+{
+	my ($node) = @_;
+
+	return (stat $node->logfile)[7];
+}
+
+# find $pat in logfile of $node after $off-th byte
+sub find_in_log
+{
+	my ($node, $pat, $off) = @_;
+
+	$off = 0 unless defined $off;
+	my $log = TestLib::slurp_file($node->logfile);
+	return 0 if (length($log) <= $off);
+
+	$log = substr($log, $off);
+
+	return $log =~ m/$pat/;
+}
-- 
2.16.3


----Next_Part(Wed_Jul_31_16_56_16_2019_668)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v16-0005-Documentation-for-slot-limit-feature.patch"



^ permalink  raw  reply  [nested|flat] 101+ messages in thread

* [PATCH 4/6] TAP test for the slot limit feature
@ 2017-12-21 08:33  Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 101+ messages in thread

From: Kyotaro Horiguchi @ 2017-12-21 08:33 UTC (permalink / raw)

---
 src/test/recovery/t/016_replslot_limit.pl | 184 ++++++++++++++++++++++
 1 file changed, 184 insertions(+)
 create mode 100644 src/test/recovery/t/016_replslot_limit.pl

diff --git a/src/test/recovery/t/016_replslot_limit.pl b/src/test/recovery/t/016_replslot_limit.pl
new file mode 100644
index 0000000000..e150ca7a54
--- /dev/null
+++ b/src/test/recovery/t/016_replslot_limit.pl
@@ -0,0 +1,184 @@
+# Test for replication slot limit
+# Ensure that max_slot_wal_keep_size limits the number of WAL files to
+# be kept by replication slots.
+
+use strict;
+use warnings;
+use File::Path qw(rmtree);
+use PostgresNode;
+use TestLib;
+use Test::More tests => 11;
+use Time::HiRes qw(usleep);
+
+$ENV{PGDATABASE} = 'postgres';
+
+# Initialize master node, setting wal-segsize to 1MB
+my $node_master = get_new_node('master');
+$node_master->init(allows_streaming => 1, extra => ['--wal-segsize=1']);
+$node_master->append_conf('postgresql.conf', qq(
+min_wal_size = 2MB
+max_wal_size = 3MB
+));
+$node_master->start;
+$node_master->safe_psql('postgres', "SELECT pg_create_physical_replication_slot('rep1')");
+
+# The slot state should be the state "unknown" before the first connection
+my $result = $node_master->safe_psql('postgres', "SELECT restart_lsn, wal_status, remain FROM pg_replication_slots WHERE slot_name = 'rep1'");
+is($result, "|unknown|0", 'check the state of non-reserved slot is "unknown"');
+
+
+# Take backup
+my $backup_name = 'my_backup';
+$node_master->backup($backup_name);
+
+# Create a standby linking to it using the replication slot
+my $node_standby = get_new_node('standby_1');
+$node_standby->init_from_backup($node_master, $backup_name, has_streaming => 1, primary_slot_name => 'rep1');
+
+$node_standby->start;
+
+# Wait until standby has replayed enough data
+my $start_lsn = $node_master->lsn('write');
+$node_master->wait_for_catchup($node_standby, 'replay', $start_lsn);
+
+# Stop standby
+$node_standby->stop;
+
+
+# Preparation done, the slot is the state "streaming" now
+$result = $node_master->safe_psql('postgres', "SELECT restart_lsn, wal_status, remain FROM pg_replication_slots WHERE slot_name = 'rep1'");
+is($result, "$start_lsn|streaming|0", 'check the catching-up state');
+
+# Advance WAL by five segments (= 5MB) on master
+advance_wal($node_master, 5);
+$node_master->safe_psql('postgres', "CHECKPOINT;");
+
+# The slot is always "safe" when max_slot_wal_keep_size is not set
+$result = $node_master->safe_psql('postgres', "SELECT restart_lsn, wal_status, remain FROM pg_replication_slots WHERE slot_name = 'rep1'");
+is($result, "$start_lsn|streaming|0", 'check that slot is working');
+
+# The standby can connect to master
+$node_standby->start;
+
+$start_lsn = $node_master->lsn('write');
+$node_master->wait_for_catchup($node_standby, 'replay', $start_lsn);
+
+$node_standby->stop;
+
+# Set max_slot_wal_keep_size on master
+my $max_slot_wal_keep_size_mb = 3;
+$node_master->append_conf('postgresql.conf', qq(
+max_slot_wal_keep_size = ${max_slot_wal_keep_size_mb}MB
+));
+$node_master->reload;
+
+# The slot is in safe state. The remaining bytes should be as almost
+# (max_slot_wal_keep_size + 1) times large as the segment size
+$result = $node_master->safe_psql('postgres', "SELECT restart_lsn, wal_status, pg_size_pretty(remain) as remain FROM pg_replication_slots WHERE slot_name = 'rep1'");
+is($result, "$start_lsn|streaming|4096 kB", 'check that max_slot_wal_keep_size is working');
+
+# Advance WAL again then checkpoint
+advance_wal($node_master, 2);
+$node_master->safe_psql('postgres', "CHECKPOINT;");
+
+# The slot is still working.
+$result = $node_master->safe_psql('postgres', "SELECT restart_lsn, wal_status, pg_size_pretty(remain) as remain FROM pg_replication_slots WHERE slot_name = 'rep1'");
+is($result, "$start_lsn|streaming|2048 kB", 'check that remaining byte is calculated correctly');
+
+# wal_keep_segments overrides max_slot_wal_keep_size
+$result = $node_master->safe_psql('postgres', "ALTER SYSTEM SET wal_keep_segments to 6; SELECT pg_reload_conf();");
+$result = $node_master->safe_psql('postgres', "SELECT restart_lsn, wal_status, pg_size_pretty(remain) as remain FROM pg_replication_slots WHERE slot_name = 'rep1'");
+is($result, "$start_lsn|streaming|5120 kB", 'check that wal_keep_segments overrides max_slot_wal_keep_size');
+
+# restore wal_keep_segments
+$result = $node_master->safe_psql('postgres', "ALTER SYSTEM SET wal_keep_segments to 0; SELECT pg_reload_conf();");
+
+# Advance WAL again without checkpoint
+advance_wal($node_master, 2);
+
+# Slot gets to 'keeping' state
+$result = $node_master->safe_psql('postgres', "SELECT restart_lsn, wal_status, pg_size_pretty(remain) as remain FROM pg_replication_slots WHERE slot_name = 'rep1'");
+is($result, "$start_lsn|keeping|0 bytes", 'check that the slot state changes to "keeping"');
+
+# The standby still can connect to master
+$node_standby->start;
+
+$start_lsn = $node_master->lsn('write');
+$node_master->wait_for_catchup($node_standby, 'replay', $start_lsn);
+
+$node_standby->stop;
+
+ok(!find_in_log($node_standby,
+				"requested WAL segment [0-9A-F]+ has already been removed"),
+   'check that required WAL segments are still available');
+
+# Advance WAL again, the slot loses some segments.
+my $logstart = get_log_size($node_master);
+advance_wal($node_master, 5);
+$node_master->safe_psql('postgres', "CHECKPOINT;");
+
+# WARNING should be issued
+ok(find_in_log($node_master,
+			   "some replication slots have lost required WAL segments\n".
+			   ".*Slot rep1 lost 2 segment\\(s\\)\\.",
+			   $logstart),
+   'check that the warning is logged');
+
+# This slot should be broken
+$result = $node_master->safe_psql('postgres', "SELECT restart_lsn, wal_status, pg_size_pretty(remain) as remain FROM pg_replication_slots WHERE slot_name = 'rep1'");
+is($result, "$start_lsn|lost|0 bytes", 'check that the slot state changes to "lost"');
+
+# The standby no longer can connect to the master
+$logstart = get_log_size($node_standby);
+$node_standby->start;
+
+my $failed = 0;
+for (my $i = 0 ; $i < 10000 ; $i++)
+{
+	if (find_in_log($node_standby,
+					"requested WAL segment [0-9A-F]+ has already been removed",
+					$logstart))
+	{
+		$failed = 1;
+		last;
+	}
+	usleep(100_000);
+}
+ok($failed, 'check that replication has been broken');
+
+$node_standby->stop;
+
+#####################################
+# Advance WAL of $node by $n segments
+sub advance_wal
+{
+	my ($node, $n) = @_;
+
+	# Advance by $n segments (= (16 * $n) MB) on master
+	for (my $i = 0 ; $i < $n ; $i++)
+	{
+		$node->safe_psql('postgres', "CREATE TABLE t (); DROP TABLE t; SELECT pg_switch_wal();");
+	}
+}
+
+# return the size of logfile of $node in bytes
+sub get_log_size
+{
+	my ($node) = @_;
+
+	return (stat $node->logfile)[7];
+}
+
+# find $pat in logfile of $node after $off-th byte
+sub find_in_log
+{
+	my ($node, $pat, $off) = @_;
+
+	$off = 0 unless defined $off;
+	my $log = TestLib::slurp_file($node->logfile);
+	return 0 if (length($log) <= $off);
+
+	$log = substr($log, $off);
+
+	return $log =~ m/$pat/;
+}
-- 
2.20.1


--MP_/68vU=6Ib.yoYOTdA.M=EVne
Content-Type: text/x-patch
Content-Transfer-Encoding: 7bit
Content-Disposition: attachment;
 filename=v14-0005-Documentation-for-slot-limit-feature.patch



^ permalink  raw  reply  [nested|flat] 101+ messages in thread

* [PATCH 4/6] TAP test for the slot limit feature
@ 2017-12-21 08:33  Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 101+ messages in thread

From: Kyotaro Horiguchi @ 2017-12-21 08:33 UTC (permalink / raw)

---
 src/test/recovery/t/016_replslot_limit.pl | 184 ++++++++++++++++++++++++++++++
 1 file changed, 184 insertions(+)
 create mode 100644 src/test/recovery/t/016_replslot_limit.pl

diff --git a/src/test/recovery/t/016_replslot_limit.pl b/src/test/recovery/t/016_replslot_limit.pl
new file mode 100644
index 0000000000..e150ca7a54
--- /dev/null
+++ b/src/test/recovery/t/016_replslot_limit.pl
@@ -0,0 +1,184 @@
+# Test for replication slot limit
+# Ensure that max_slot_wal_keep_size limits the number of WAL files to
+# be kept by replication slots.
+
+use strict;
+use warnings;
+use File::Path qw(rmtree);
+use PostgresNode;
+use TestLib;
+use Test::More tests => 11;
+use Time::HiRes qw(usleep);
+
+$ENV{PGDATABASE} = 'postgres';
+
+# Initialize master node, setting wal-segsize to 1MB
+my $node_master = get_new_node('master');
+$node_master->init(allows_streaming => 1, extra => ['--wal-segsize=1']);
+$node_master->append_conf('postgresql.conf', qq(
+min_wal_size = 2MB
+max_wal_size = 3MB
+));
+$node_master->start;
+$node_master->safe_psql('postgres', "SELECT pg_create_physical_replication_slot('rep1')");
+
+# The slot state should be the state "unknown" before the first connection
+my $result = $node_master->safe_psql('postgres', "SELECT restart_lsn, wal_status, remain FROM pg_replication_slots WHERE slot_name = 'rep1'");
+is($result, "|unknown|0", 'check the state of non-reserved slot is "unknown"');
+
+
+# Take backup
+my $backup_name = 'my_backup';
+$node_master->backup($backup_name);
+
+# Create a standby linking to it using the replication slot
+my $node_standby = get_new_node('standby_1');
+$node_standby->init_from_backup($node_master, $backup_name, has_streaming => 1, primary_slot_name => 'rep1');
+
+$node_standby->start;
+
+# Wait until standby has replayed enough data
+my $start_lsn = $node_master->lsn('write');
+$node_master->wait_for_catchup($node_standby, 'replay', $start_lsn);
+
+# Stop standby
+$node_standby->stop;
+
+
+# Preparation done, the slot is the state "streaming" now
+$result = $node_master->safe_psql('postgres', "SELECT restart_lsn, wal_status, remain FROM pg_replication_slots WHERE slot_name = 'rep1'");
+is($result, "$start_lsn|streaming|0", 'check the catching-up state');
+
+# Advance WAL by five segments (= 5MB) on master
+advance_wal($node_master, 5);
+$node_master->safe_psql('postgres', "CHECKPOINT;");
+
+# The slot is always "safe" when max_slot_wal_keep_size is not set
+$result = $node_master->safe_psql('postgres', "SELECT restart_lsn, wal_status, remain FROM pg_replication_slots WHERE slot_name = 'rep1'");
+is($result, "$start_lsn|streaming|0", 'check that slot is working');
+
+# The standby can connect to master
+$node_standby->start;
+
+$start_lsn = $node_master->lsn('write');
+$node_master->wait_for_catchup($node_standby, 'replay', $start_lsn);
+
+$node_standby->stop;
+
+# Set max_slot_wal_keep_size on master
+my $max_slot_wal_keep_size_mb = 3;
+$node_master->append_conf('postgresql.conf', qq(
+max_slot_wal_keep_size = ${max_slot_wal_keep_size_mb}MB
+));
+$node_master->reload;
+
+# The slot is in safe state. The remaining bytes should be as almost
+# (max_slot_wal_keep_size + 1) times large as the segment size
+$result = $node_master->safe_psql('postgres', "SELECT restart_lsn, wal_status, pg_size_pretty(remain) as remain FROM pg_replication_slots WHERE slot_name = 'rep1'");
+is($result, "$start_lsn|streaming|4096 kB", 'check that max_slot_wal_keep_size is working');
+
+# Advance WAL again then checkpoint
+advance_wal($node_master, 2);
+$node_master->safe_psql('postgres', "CHECKPOINT;");
+
+# The slot is still working.
+$result = $node_master->safe_psql('postgres', "SELECT restart_lsn, wal_status, pg_size_pretty(remain) as remain FROM pg_replication_slots WHERE slot_name = 'rep1'");
+is($result, "$start_lsn|streaming|2048 kB", 'check that remaining byte is calculated correctly');
+
+# wal_keep_segments overrides max_slot_wal_keep_size
+$result = $node_master->safe_psql('postgres', "ALTER SYSTEM SET wal_keep_segments to 6; SELECT pg_reload_conf();");
+$result = $node_master->safe_psql('postgres', "SELECT restart_lsn, wal_status, pg_size_pretty(remain) as remain FROM pg_replication_slots WHERE slot_name = 'rep1'");
+is($result, "$start_lsn|streaming|5120 kB", 'check that wal_keep_segments overrides max_slot_wal_keep_size');
+
+# restore wal_keep_segments
+$result = $node_master->safe_psql('postgres', "ALTER SYSTEM SET wal_keep_segments to 0; SELECT pg_reload_conf();");
+
+# Advance WAL again without checkpoint
+advance_wal($node_master, 2);
+
+# Slot gets to 'keeping' state
+$result = $node_master->safe_psql('postgres', "SELECT restart_lsn, wal_status, pg_size_pretty(remain) as remain FROM pg_replication_slots WHERE slot_name = 'rep1'");
+is($result, "$start_lsn|keeping|0 bytes", 'check that the slot state changes to "keeping"');
+
+# The standby still can connect to master
+$node_standby->start;
+
+$start_lsn = $node_master->lsn('write');
+$node_master->wait_for_catchup($node_standby, 'replay', $start_lsn);
+
+$node_standby->stop;
+
+ok(!find_in_log($node_standby,
+				"requested WAL segment [0-9A-F]+ has already been removed"),
+   'check that required WAL segments are still available');
+
+# Advance WAL again, the slot loses some segments.
+my $logstart = get_log_size($node_master);
+advance_wal($node_master, 5);
+$node_master->safe_psql('postgres', "CHECKPOINT;");
+
+# WARNING should be issued
+ok(find_in_log($node_master,
+			   "some replication slots have lost required WAL segments\n".
+			   ".*Slot rep1 lost 2 segment\\(s\\)\\.",
+			   $logstart),
+   'check that the warning is logged');
+
+# This slot should be broken
+$result = $node_master->safe_psql('postgres', "SELECT restart_lsn, wal_status, pg_size_pretty(remain) as remain FROM pg_replication_slots WHERE slot_name = 'rep1'");
+is($result, "$start_lsn|lost|0 bytes", 'check that the slot state changes to "lost"');
+
+# The standby no longer can connect to the master
+$logstart = get_log_size($node_standby);
+$node_standby->start;
+
+my $failed = 0;
+for (my $i = 0 ; $i < 10000 ; $i++)
+{
+	if (find_in_log($node_standby,
+					"requested WAL segment [0-9A-F]+ has already been removed",
+					$logstart))
+	{
+		$failed = 1;
+		last;
+	}
+	usleep(100_000);
+}
+ok($failed, 'check that replication has been broken');
+
+$node_standby->stop;
+
+#####################################
+# Advance WAL of $node by $n segments
+sub advance_wal
+{
+	my ($node, $n) = @_;
+
+	# Advance by $n segments (= (16 * $n) MB) on master
+	for (my $i = 0 ; $i < $n ; $i++)
+	{
+		$node->safe_psql('postgres', "CREATE TABLE t (); DROP TABLE t; SELECT pg_switch_wal();");
+	}
+}
+
+# return the size of logfile of $node in bytes
+sub get_log_size
+{
+	my ($node) = @_;
+
+	return (stat $node->logfile)[7];
+}
+
+# find $pat in logfile of $node after $off-th byte
+sub find_in_log
+{
+	my ($node, $pat, $off) = @_;
+
+	$off = 0 unless defined $off;
+	my $log = TestLib::slurp_file($node->logfile);
+	return 0 if (length($log) <= $off);
+
+	$log = substr($log, $off);
+
+	return $log =~ m/$pat/;
+}
-- 
2.16.3


----Next_Part(Fri_Feb_22_14_12_28_2019_076)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v13-0005-Documentation-for-slot-limit-feature.patch"



^ permalink  raw  reply  [nested|flat] 101+ messages in thread

* [PATCH v30 05/11] Add Incremental View Maintenance support to psql
@ 2019-12-20 01:21  Yugo Nagata <[email protected]>
  0 siblings, 0 replies; 101+ messages in thread

From: Yugo Nagata @ 2019-12-20 01:21 UTC (permalink / raw)

Add tab completion and meta-command output for IVM.
---
 src/bin/psql/describe.c     | 32 +++++++++++++++++++++++++++++++-
 src/bin/psql/tab-complete.c | 14 +++++++++-----
 2 files changed, 40 insertions(+), 6 deletions(-)

diff --git a/src/bin/psql/describe.c b/src/bin/psql/describe.c
index b6a4eb1d56..3664371aa6 100644
--- a/src/bin/psql/describe.c
+++ b/src/bin/psql/describe.c
@@ -1570,6 +1570,7 @@ describeOneTableDetails(const char *schemaname,
 		char		relpersistence;
 		char		relreplident;
 		char	   *relam;
+		bool		isivm;
 	}			tableinfo;
 	bool		show_column_details = false;
 
@@ -1582,7 +1583,26 @@ describeOneTableDetails(const char *schemaname,
 	initPQExpBuffer(&tmpbuf);
 
 	/* Get general table info */
-	if (pset.sversion >= 120000)
+	if (pset.sversion >= 170000)
+	{
+		printfPQExpBuffer(&buf,
+						  "SELECT c.relchecks, c.relkind, c.relhasindex, c.relhasrules, "
+						  "c.relhastriggers, c.relrowsecurity, c.relforcerowsecurity, "
+						  "false AS relhasoids, c.relispartition, %s, c.reltablespace, "
+						  "CASE WHEN c.reloftype = 0 THEN '' ELSE c.reloftype::pg_catalog.regtype::pg_catalog.text END, "
+						  "c.relpersistence, c.relreplident, am.amname, "
+						  "c.relisivm\n"
+						  "FROM pg_catalog.pg_class c\n "
+						  "LEFT JOIN pg_catalog.pg_class tc ON (c.reltoastrelid = tc.oid)\n"
+						  "LEFT JOIN pg_catalog.pg_am am ON (c.relam = am.oid)\n"
+						  "WHERE c.oid = '%s';",
+						  (verbose ?
+						   "pg_catalog.array_to_string(c.reloptions || "
+						   "array(select 'toast.' || x from pg_catalog.unnest(tc.reloptions) x), ', ')\n"
+						   : "''"),
+						  oid);
+	}
+	else if (pset.sversion >= 120000)
 	{
 		printfPQExpBuffer(&buf,
 						  "SELECT c.relchecks, c.relkind, c.relhasindex, c.relhasrules, "
@@ -1702,6 +1722,10 @@ describeOneTableDetails(const char *schemaname,
 			(char *) NULL : pg_strdup(PQgetvalue(res, 0, 14));
 	else
 		tableinfo.relam = NULL;
+	if (pset.sversion >= 170000)
+		tableinfo.isivm = strcmp(PQgetvalue(res, 0, 15), "t") == 0;
+	else
+		tableinfo.isivm = false;
 	PQclear(res);
 	res = NULL;
 
@@ -3555,6 +3579,12 @@ describeOneTableDetails(const char *schemaname,
 			printfPQExpBuffer(&buf, _("Access method: %s"), tableinfo.relam);
 			printTableAddFooter(&cont, buf.data);
 		}
+
+		/* Incremental view maintance info */
+		if (verbose && tableinfo.relkind == RELKIND_MATVIEW && tableinfo.isivm)
+		{
+			printTableAddFooter(&cont, _("Incremental view maintenance: yes"));
+		}
 	}
 
 	/* reloptions, if verbose */
diff --git a/src/bin/psql/tab-complete.c b/src/bin/psql/tab-complete.c
index aa1acf8523..9977df2e28 100644
--- a/src/bin/psql/tab-complete.c
+++ b/src/bin/psql/tab-complete.c
@@ -1245,6 +1245,7 @@ static const pgsql_thing_t words_after_create[] = {
 	{"FOREIGN TABLE", NULL, NULL, NULL},
 	{"FUNCTION", NULL, NULL, Query_for_list_of_functions},
 	{"GROUP", Query_for_list_of_roles},
+	{"INCREMENTAL MATERIALIZED VIEW", NULL, NULL, &Query_for_list_of_matviews, NULL, THING_NO_DROP | THING_NO_ALTER},
 	{"INDEX", NULL, NULL, &Query_for_list_of_indexes},
 	{"LANGUAGE", Query_for_list_of_languages},
 	{"LARGE OBJECT", NULL, NULL, NULL, NULL, THING_NO_CREATE | THING_NO_DROP},
@@ -3252,7 +3253,7 @@ psql_completion(const char *text, int start, int end)
 		if (HeadMatches("CREATE", "SCHEMA"))
 			COMPLETE_WITH("TABLE", "SEQUENCE");
 		else
-			COMPLETE_WITH("TABLE", "SEQUENCE", "MATERIALIZED VIEW");
+			COMPLETE_WITH("TABLE", "SEQUENCE", "MATERIALIZED VIEW", "INCREMENTAL MATERIALIZED VIEW");
 	}
 	/* Complete PARTITION BY with RANGE ( or LIST ( or ... */
 	else if (TailMatches("PARTITION", "BY"))
@@ -3597,13 +3598,16 @@ psql_completion(const char *text, int start, int end)
 		COMPLETE_WITH("SELECT");
 
 /* CREATE MATERIALIZED VIEW */
-	else if (Matches("CREATE", "MATERIALIZED"))
+	else if (Matches("CREATE", "MATERIALIZED") ||
+			 Matches("CREATE", "INCREMENTAL", "MATERIALIZED"))
 		COMPLETE_WITH("VIEW");
-	/* Complete CREATE MATERIALIZED VIEW <name> with AS */
-	else if (Matches("CREATE", "MATERIALIZED", "VIEW", MatchAny))
+	/* Complete CREATE MATERIALIZED VIEW <name> with AS  */
+	else if (Matches("CREATE", "MATERIALIZED", "VIEW", MatchAny) ||
+			 Matches("CREATE", "INCREMENTAL", "MATERIALIZED", "VIEW", MatchAny))
 		COMPLETE_WITH("AS");
 	/* Complete "CREATE MATERIALIZED VIEW <sth> AS with "SELECT" */
-	else if (Matches("CREATE", "MATERIALIZED", "VIEW", MatchAny, "AS"))
+	else if (Matches("CREATE", "MATERIALIZED", "VIEW", MatchAny, "AS") ||
+			 Matches("CREATE", "INCREMENTAL", "MATERIALIZED", "VIEW", MatchAny, "AS"))
 		COMPLETE_WITH("SELECT");
 
 /* CREATE EVENT TRIGGER */
-- 
2.25.1


--Multipart=_Mon__4_Mar_2024_11_58_46_+0900_UaponF/qQhQrVCFt
Content-Type: text/x-diff;
 name="v30-0006-Add-Incremental-View-Maintenance-support.patch"
Content-Disposition: attachment;
 filename="v30-0006-Add-Incremental-View-Maintenance-support.patch"
Content-Transfer-Encoding: 7bit



^ permalink  raw  reply  [nested|flat] 101+ messages in thread

* [PATCH v25 06/15] Add Incremental View Maintenance support to psql
@ 2019-12-20 01:21  Yugo Nagata <[email protected]>
  0 siblings, 0 replies; 101+ messages in thread

From: Yugo Nagata @ 2019-12-20 01:21 UTC (permalink / raw)

Add tab completion and meta-command output for IVM.
---
 src/bin/psql/describe.c     | 32 +++++++++++++++++++++++++++++++-
 src/bin/psql/tab-complete.c | 14 +++++++++-----
 2 files changed, 40 insertions(+), 6 deletions(-)

diff --git a/src/bin/psql/describe.c b/src/bin/psql/describe.c
index 346cd92793..601eca408b 100644
--- a/src/bin/psql/describe.c
+++ b/src/bin/psql/describe.c
@@ -1480,6 +1480,7 @@ describeOneTableDetails(const char *schemaname,
 		char		relpersistence;
 		char		relreplident;
 		char	   *relam;
+		bool		isivm;
 	}			tableinfo;
 	bool		show_column_details = false;
 
@@ -1492,7 +1493,26 @@ describeOneTableDetails(const char *schemaname,
 	initPQExpBuffer(&tmpbuf);
 
 	/* Get general table info */
-	if (pset.sversion >= 120000)
+	if (pset.sversion >= 150000)
+	{
+		printfPQExpBuffer(&buf,
+						  "SELECT c.relchecks, c.relkind, c.relhasindex, c.relhasrules, "
+						  "c.relhastriggers, c.relrowsecurity, c.relforcerowsecurity, "
+						  "false AS relhasoids, c.relispartition, %s, c.reltablespace, "
+						  "CASE WHEN c.reloftype = 0 THEN '' ELSE c.reloftype::pg_catalog.regtype::pg_catalog.text END, "
+						  "c.relpersistence, c.relreplident, am.amname, "
+						  "c.relisivm\n"
+						  "FROM pg_catalog.pg_class c\n "
+						  "LEFT JOIN pg_catalog.pg_class tc ON (c.reltoastrelid = tc.oid)\n"
+						  "LEFT JOIN pg_catalog.pg_am am ON (c.relam = am.oid)\n"
+						  "WHERE c.oid = '%s';",
+						  (verbose ?
+						   "pg_catalog.array_to_string(c.reloptions || "
+						   "array(select 'toast.' || x from pg_catalog.unnest(tc.reloptions) x), ', ')\n"
+						   : "''"),
+						  oid);
+	}
+	else if (pset.sversion >= 120000)
 	{
 		printfPQExpBuffer(&buf,
 						  "SELECT c.relchecks, c.relkind, c.relhasindex, c.relhasrules, "
@@ -1612,6 +1632,10 @@ describeOneTableDetails(const char *schemaname,
 			(char *) NULL : pg_strdup(PQgetvalue(res, 0, 14));
 	else
 		tableinfo.relam = NULL;
+	if (pset.sversion >= 150000)
+		tableinfo.isivm = strcmp(PQgetvalue(res, 0, 15), "t") == 0;
+	else
+		tableinfo.isivm = false;
 	PQclear(res);
 	res = NULL;
 
@@ -3375,6 +3399,12 @@ describeOneTableDetails(const char *schemaname,
 			printfPQExpBuffer(&buf, _("Access method: %s"), tableinfo.relam);
 			printTableAddFooter(&cont, buf.data);
 		}
+
+		/* Incremental view maintance info */
+		if (verbose && tableinfo.relkind == RELKIND_MATVIEW && tableinfo.isivm)
+		{
+			printTableAddFooter(&cont, _("Incremental view maintenance: yes"));
+		}
 	}
 
 	/* reloptions, if verbose */
diff --git a/src/bin/psql/tab-complete.c b/src/bin/psql/tab-complete.c
index d1e421bc0f..5832e37aa0 100644
--- a/src/bin/psql/tab-complete.c
+++ b/src/bin/psql/tab-complete.c
@@ -1172,6 +1172,7 @@ static const pgsql_thing_t words_after_create[] = {
 	{"FOREIGN TABLE", NULL, NULL, NULL},
 	{"FUNCTION", NULL, NULL, Query_for_list_of_functions},
 	{"GROUP", Query_for_list_of_roles},
+	{"INCREMENTAL MATERIALIZED VIEW", NULL, NULL, &Query_for_list_of_matviews, THING_NO_DROP | THING_NO_ALTER},
 	{"INDEX", NULL, NULL, &Query_for_list_of_indexes},
 	{"LANGUAGE", Query_for_list_of_languages},
 	{"LARGE OBJECT", NULL, NULL, NULL, NULL, THING_NO_CREATE | THING_NO_DROP},
@@ -2986,7 +2987,7 @@ psql_completion(const char *text, int start, int end)
 		COMPLETE_WITH("SEQUENCE", "TABLE", "VIEW");
 	/* Complete "CREATE UNLOGGED" with TABLE or MATVIEW */
 	else if (TailMatches("CREATE", "UNLOGGED"))
-		COMPLETE_WITH("TABLE", "MATERIALIZED VIEW");
+		COMPLETE_WITH("TABLE", "MATERIALIZED VIEW", "INCREMENTAL MATERIALIZED VIEW");
 	/* Complete PARTITION BY with RANGE ( or LIST ( or ... */
 	else if (TailMatches("PARTITION", "BY"))
 		COMPLETE_WITH("RANGE (", "LIST (", "HASH (");
@@ -3302,13 +3303,16 @@ psql_completion(const char *text, int start, int end)
 		COMPLETE_WITH("SELECT");
 
 /* CREATE MATERIALIZED VIEW */
-	else if (Matches("CREATE", "MATERIALIZED"))
+	else if (Matches("CREATE", "MATERIALIZED") ||
+			 Matches("CREATE", "INCREMENTAL", "MATERIALIZED"))
 		COMPLETE_WITH("VIEW");
-	/* Complete CREATE MATERIALIZED VIEW <name> with AS */
-	else if (Matches("CREATE", "MATERIALIZED", "VIEW", MatchAny))
+	/* Complete CREATE MATERIALIZED VIEW <name> with AS  */
+	else if (Matches("CREATE", "MATERIALIZED", "VIEW", MatchAny) ||
+			 Matches("CREATE", "INCREMENTAL", "MATERIALIZED", "VIEW", MatchAny))
 		COMPLETE_WITH("AS");
 	/* Complete "CREATE MATERIALIZED VIEW <sth> AS with "SELECT" */
-	else if (Matches("CREATE", "MATERIALIZED", "VIEW", MatchAny, "AS"))
+	else if (Matches("CREATE", "MATERIALIZED", "VIEW", MatchAny, "AS") ||
+			 Matches("CREATE", "INCREMENTAL", "MATERIALIZED", "VIEW", MatchAny, "AS"))
 		COMPLETE_WITH("SELECT");
 
 /* CREATE EVENT TRIGGER */
-- 
2.17.1


--Multipart=_Fri__4_Feb_2022_01_48_06_+0900_N8BNZpfOR27sWrgY
Content-Type: text/x-diff;
 name="v25-0005-Add-Incremental-View-Maintenance-support-to-pg_d.patch"
Content-Disposition: attachment;
 filename="v25-0005-Add-Incremental-View-Maintenance-support-to-pg_d.patch"
Content-Transfer-Encoding: 7bit



^ permalink  raw  reply  [nested|flat] 101+ messages in thread

* [PATCH v27 5/9] Add Incremental View Maintenance support to psql
@ 2019-12-20 01:21  Yugo Nagata <[email protected]>
  0 siblings, 0 replies; 101+ messages in thread

From: Yugo Nagata @ 2019-12-20 01:21 UTC (permalink / raw)

Add tab completion and meta-command output for IVM.
---
 src/bin/psql/describe.c     | 32 +++++++++++++++++++++++++++++++-
 src/bin/psql/tab-complete.c | 14 +++++++++-----
 2 files changed, 40 insertions(+), 6 deletions(-)

diff --git a/src/bin/psql/describe.c b/src/bin/psql/describe.c
index 583817b0cc..8cdcb3f048 100644
--- a/src/bin/psql/describe.c
+++ b/src/bin/psql/describe.c
@@ -1492,6 +1492,7 @@ describeOneTableDetails(const char *schemaname,
 		char		relpersistence;
 		char		relreplident;
 		char	   *relam;
+		bool		isivm;
 	}			tableinfo;
 	bool		show_column_details = false;
 
@@ -1504,7 +1505,26 @@ describeOneTableDetails(const char *schemaname,
 	initPQExpBuffer(&tmpbuf);
 
 	/* Get general table info */
-	if (pset.sversion >= 120000)
+	if (pset.sversion >= 150000)
+	{
+		printfPQExpBuffer(&buf,
+						  "SELECT c.relchecks, c.relkind, c.relhasindex, c.relhasrules, "
+						  "c.relhastriggers, c.relrowsecurity, c.relforcerowsecurity, "
+						  "false AS relhasoids, c.relispartition, %s, c.reltablespace, "
+						  "CASE WHEN c.reloftype = 0 THEN '' ELSE c.reloftype::pg_catalog.regtype::pg_catalog.text END, "
+						  "c.relpersistence, c.relreplident, am.amname, "
+						  "c.relisivm\n"
+						  "FROM pg_catalog.pg_class c\n "
+						  "LEFT JOIN pg_catalog.pg_class tc ON (c.reltoastrelid = tc.oid)\n"
+						  "LEFT JOIN pg_catalog.pg_am am ON (c.relam = am.oid)\n"
+						  "WHERE c.oid = '%s';",
+						  (verbose ?
+						   "pg_catalog.array_to_string(c.reloptions || "
+						   "array(select 'toast.' || x from pg_catalog.unnest(tc.reloptions) x), ', ')\n"
+						   : "''"),
+						  oid);
+	}
+	else if (pset.sversion >= 120000)
 	{
 		printfPQExpBuffer(&buf,
 						  "SELECT c.relchecks, c.relkind, c.relhasindex, c.relhasrules, "
@@ -1624,6 +1644,10 @@ describeOneTableDetails(const char *schemaname,
 			(char *) NULL : pg_strdup(PQgetvalue(res, 0, 14));
 	else
 		tableinfo.relam = NULL;
+	if (pset.sversion >= 150000)
+		tableinfo.isivm = strcmp(PQgetvalue(res, 0, 15), "t") == 0;
+	else
+		tableinfo.isivm = false;
 	PQclear(res);
 	res = NULL;
 
@@ -3424,6 +3448,12 @@ describeOneTableDetails(const char *schemaname,
 			printfPQExpBuffer(&buf, _("Access method: %s"), tableinfo.relam);
 			printTableAddFooter(&cont, buf.data);
 		}
+
+		/* Incremental view maintance info */
+		if (verbose && tableinfo.relkind == RELKIND_MATVIEW && tableinfo.isivm)
+		{
+			printTableAddFooter(&cont, _("Incremental view maintenance: yes"));
+		}
 	}
 
 	/* reloptions, if verbose */
diff --git a/src/bin/psql/tab-complete.c b/src/bin/psql/tab-complete.c
index 588c0841fe..87b5d3e107 100644
--- a/src/bin/psql/tab-complete.c
+++ b/src/bin/psql/tab-complete.c
@@ -1221,6 +1221,7 @@ static const pgsql_thing_t words_after_create[] = {
 	{"FOREIGN TABLE", NULL, NULL, NULL},
 	{"FUNCTION", NULL, NULL, Query_for_list_of_functions},
 	{"GROUP", Query_for_list_of_roles},
+	{"INCREMENTAL MATERIALIZED VIEW", NULL, NULL, &Query_for_list_of_matviews, NULL, THING_NO_DROP | THING_NO_ALTER},
 	{"INDEX", NULL, NULL, &Query_for_list_of_indexes},
 	{"LANGUAGE", Query_for_list_of_languages},
 	{"LARGE OBJECT", NULL, NULL, NULL, NULL, THING_NO_CREATE | THING_NO_DROP},
@@ -3074,7 +3075,7 @@ psql_completion(const char *text, int start, int end)
 		COMPLETE_WITH("SEQUENCE", "TABLE", "VIEW");
 	/* Complete "CREATE UNLOGGED" with TABLE or MATVIEW */
 	else if (TailMatches("CREATE", "UNLOGGED"))
-		COMPLETE_WITH("TABLE", "MATERIALIZED VIEW");
+		COMPLETE_WITH("TABLE", "MATERIALIZED VIEW", "INCREMENTAL MATERIALIZED VIEW");
 	/* Complete PARTITION BY with RANGE ( or LIST ( or ... */
 	else if (TailMatches("PARTITION", "BY"))
 		COMPLETE_WITH("RANGE (", "LIST (", "HASH (");
@@ -3390,13 +3391,16 @@ psql_completion(const char *text, int start, int end)
 		COMPLETE_WITH("SELECT");
 
 /* CREATE MATERIALIZED VIEW */
-	else if (Matches("CREATE", "MATERIALIZED"))
+	else if (Matches("CREATE", "MATERIALIZED") ||
+			 Matches("CREATE", "INCREMENTAL", "MATERIALIZED"))
 		COMPLETE_WITH("VIEW");
-	/* Complete CREATE MATERIALIZED VIEW <name> with AS */
-	else if (Matches("CREATE", "MATERIALIZED", "VIEW", MatchAny))
+	/* Complete CREATE MATERIALIZED VIEW <name> with AS  */
+	else if (Matches("CREATE", "MATERIALIZED", "VIEW", MatchAny) ||
+			 Matches("CREATE", "INCREMENTAL", "MATERIALIZED", "VIEW", MatchAny))
 		COMPLETE_WITH("AS");
 	/* Complete "CREATE MATERIALIZED VIEW <sth> AS with "SELECT" */
-	else if (Matches("CREATE", "MATERIALIZED", "VIEW", MatchAny, "AS"))
+	else if (Matches("CREATE", "MATERIALIZED", "VIEW", MatchAny, "AS") ||
+			 Matches("CREATE", "INCREMENTAL", "MATERIALIZED", "VIEW", MatchAny, "AS"))
 		COMPLETE_WITH("SELECT");
 
 /* CREATE EVENT TRIGGER */
-- 
2.17.1


--Multipart=_Fri__22_Apr_2022_14_58_01_+0900_MN3L/o2YUVF2g4zw
Content-Type: text/x-diff;
 name="v27-0006-Add-Incremental-View-Maintenance-support.patch"
Content-Disposition: attachment;
 filename="v27-0006-Add-Incremental-View-Maintenance-support.patch"
Content-Transfer-Encoding: 7bit



^ permalink  raw  reply  [nested|flat] 101+ messages in thread

* [PATCH v29 05/11] Add Incremental View Maintenance support to psql
@ 2019-12-20 01:21  Yugo Nagata <[email protected]>
  0 siblings, 0 replies; 101+ messages in thread

From: Yugo Nagata @ 2019-12-20 01:21 UTC (permalink / raw)

Add tab completion and meta-command output for IVM.
---
 src/bin/psql/describe.c     | 32 +++++++++++++++++++++++++++++++-
 src/bin/psql/tab-complete.c | 14 +++++++++-----
 2 files changed, 40 insertions(+), 6 deletions(-)

diff --git a/src/bin/psql/describe.c b/src/bin/psql/describe.c
index bac94a338c..f6c7e7163d 100644
--- a/src/bin/psql/describe.c
+++ b/src/bin/psql/describe.c
@@ -1575,6 +1575,7 @@ describeOneTableDetails(const char *schemaname,
 		char		relpersistence;
 		char		relreplident;
 		char	   *relam;
+		bool		isivm;
 	}			tableinfo;
 	bool		show_column_details = false;
 
@@ -1587,7 +1588,26 @@ describeOneTableDetails(const char *schemaname,
 	initPQExpBuffer(&tmpbuf);
 
 	/* Get general table info */
-	if (pset.sversion >= 120000)
+	if (pset.sversion >= 170000)
+	{
+		printfPQExpBuffer(&buf,
+						  "SELECT c.relchecks, c.relkind, c.relhasindex, c.relhasrules, "
+						  "c.relhastriggers, c.relrowsecurity, c.relforcerowsecurity, "
+						  "false AS relhasoids, c.relispartition, %s, c.reltablespace, "
+						  "CASE WHEN c.reloftype = 0 THEN '' ELSE c.reloftype::pg_catalog.regtype::pg_catalog.text END, "
+						  "c.relpersistence, c.relreplident, am.amname, "
+						  "c.relisivm\n"
+						  "FROM pg_catalog.pg_class c\n "
+						  "LEFT JOIN pg_catalog.pg_class tc ON (c.reltoastrelid = tc.oid)\n"
+						  "LEFT JOIN pg_catalog.pg_am am ON (c.relam = am.oid)\n"
+						  "WHERE c.oid = '%s';",
+						  (verbose ?
+						   "pg_catalog.array_to_string(c.reloptions || "
+						   "array(select 'toast.' || x from pg_catalog.unnest(tc.reloptions) x), ', ')\n"
+						   : "''"),
+						  oid);
+	}
+	else if (pset.sversion >= 120000)
 	{
 		printfPQExpBuffer(&buf,
 						  "SELECT c.relchecks, c.relkind, c.relhasindex, c.relhasrules, "
@@ -1707,6 +1727,10 @@ describeOneTableDetails(const char *schemaname,
 			(char *) NULL : pg_strdup(PQgetvalue(res, 0, 14));
 	else
 		tableinfo.relam = NULL;
+	if (pset.sversion >= 170000)
+		tableinfo.isivm = strcmp(PQgetvalue(res, 0, 15), "t") == 0;
+	else
+		tableinfo.isivm = false;
 	PQclear(res);
 	res = NULL;
 
@@ -3552,6 +3576,12 @@ describeOneTableDetails(const char *schemaname,
 			printfPQExpBuffer(&buf, _("Access method: %s"), tableinfo.relam);
 			printTableAddFooter(&cont, buf.data);
 		}
+
+		/* Incremental view maintance info */
+		if (verbose && tableinfo.relkind == RELKIND_MATVIEW && tableinfo.isivm)
+		{
+			printTableAddFooter(&cont, _("Incremental view maintenance: yes"));
+		}
 	}
 
 	/* reloptions, if verbose */
diff --git a/src/bin/psql/tab-complete.c b/src/bin/psql/tab-complete.c
index 779fdc90cb..9cc79b722f 100644
--- a/src/bin/psql/tab-complete.c
+++ b/src/bin/psql/tab-complete.c
@@ -1244,6 +1244,7 @@ static const pgsql_thing_t words_after_create[] = {
 	{"FOREIGN TABLE", NULL, NULL, NULL},
 	{"FUNCTION", NULL, NULL, Query_for_list_of_functions},
 	{"GROUP", Query_for_list_of_roles},
+	{"INCREMENTAL MATERIALIZED VIEW", NULL, NULL, &Query_for_list_of_matviews, NULL, THING_NO_DROP | THING_NO_ALTER},
 	{"INDEX", NULL, NULL, &Query_for_list_of_indexes},
 	{"LANGUAGE", Query_for_list_of_languages},
 	{"LARGE OBJECT", NULL, NULL, NULL, NULL, THING_NO_CREATE | THING_NO_DROP},
@@ -3217,7 +3218,7 @@ psql_completion(const char *text, int start, int end)
 		if (HeadMatches("CREATE", "SCHEMA"))
 			COMPLETE_WITH("TABLE", "SEQUENCE");
 		else
-			COMPLETE_WITH("TABLE", "SEQUENCE", "MATERIALIZED VIEW");
+			COMPLETE_WITH("TABLE", "SEQUENCE", "MATERIALIZED VIEW", "INCREMENTAL MATERIALIZED VIEW");
 	}
 	/* Complete PARTITION BY with RANGE ( or LIST ( or ... */
 	else if (TailMatches("PARTITION", "BY"))
@@ -3535,13 +3536,16 @@ psql_completion(const char *text, int start, int end)
 		COMPLETE_WITH("SELECT");
 
 /* CREATE MATERIALIZED VIEW */
-	else if (Matches("CREATE", "MATERIALIZED"))
+	else if (Matches("CREATE", "MATERIALIZED") ||
+			 Matches("CREATE", "INCREMENTAL", "MATERIALIZED"))
 		COMPLETE_WITH("VIEW");
-	/* Complete CREATE MATERIALIZED VIEW <name> with AS */
-	else if (Matches("CREATE", "MATERIALIZED", "VIEW", MatchAny))
+	/* Complete CREATE MATERIALIZED VIEW <name> with AS  */
+	else if (Matches("CREATE", "MATERIALIZED", "VIEW", MatchAny) ||
+			 Matches("CREATE", "INCREMENTAL", "MATERIALIZED", "VIEW", MatchAny))
 		COMPLETE_WITH("AS");
 	/* Complete "CREATE MATERIALIZED VIEW <sth> AS with "SELECT" */
-	else if (Matches("CREATE", "MATERIALIZED", "VIEW", MatchAny, "AS"))
+	else if (Matches("CREATE", "MATERIALIZED", "VIEW", MatchAny, "AS") ||
+			 Matches("CREATE", "INCREMENTAL", "MATERIALIZED", "VIEW", MatchAny, "AS"))
 		COMPLETE_WITH("SELECT");
 
 /* CREATE EVENT TRIGGER */
-- 
2.25.1


--Multipart=_Mon__28_Aug_2023_11_52_52_+0900_hj6L5h176QaSGtg7
Content-Type: text/x-diff;
 name="v29-0006-Add-Incremental-View-Maintenance-support.patch"
Content-Disposition: attachment;
 filename="v29-0006-Add-Incremental-View-Maintenance-support.patch"
Content-Transfer-Encoding: 7bit



^ permalink  raw  reply  [nested|flat] 101+ messages in thread

* [PATCH v29 05/11] Add Incremental View Maintenance support to psql
@ 2019-12-20 01:21  Yugo Nagata <[email protected]>
  0 siblings, 0 replies; 101+ messages in thread

From: Yugo Nagata @ 2019-12-20 01:21 UTC (permalink / raw)

Add tab completion and meta-command output for IVM.
---
 src/bin/psql/describe.c     | 32 +++++++++++++++++++++++++++++++-
 src/bin/psql/tab-complete.c | 14 +++++++++-----
 2 files changed, 40 insertions(+), 6 deletions(-)

diff --git a/src/bin/psql/describe.c b/src/bin/psql/describe.c
index bac94a338c..f6c7e7163d 100644
--- a/src/bin/psql/describe.c
+++ b/src/bin/psql/describe.c
@@ -1575,6 +1575,7 @@ describeOneTableDetails(const char *schemaname,
 		char		relpersistence;
 		char		relreplident;
 		char	   *relam;
+		bool		isivm;
 	}			tableinfo;
 	bool		show_column_details = false;
 
@@ -1587,7 +1588,26 @@ describeOneTableDetails(const char *schemaname,
 	initPQExpBuffer(&tmpbuf);
 
 	/* Get general table info */
-	if (pset.sversion >= 120000)
+	if (pset.sversion >= 170000)
+	{
+		printfPQExpBuffer(&buf,
+						  "SELECT c.relchecks, c.relkind, c.relhasindex, c.relhasrules, "
+						  "c.relhastriggers, c.relrowsecurity, c.relforcerowsecurity, "
+						  "false AS relhasoids, c.relispartition, %s, c.reltablespace, "
+						  "CASE WHEN c.reloftype = 0 THEN '' ELSE c.reloftype::pg_catalog.regtype::pg_catalog.text END, "
+						  "c.relpersistence, c.relreplident, am.amname, "
+						  "c.relisivm\n"
+						  "FROM pg_catalog.pg_class c\n "
+						  "LEFT JOIN pg_catalog.pg_class tc ON (c.reltoastrelid = tc.oid)\n"
+						  "LEFT JOIN pg_catalog.pg_am am ON (c.relam = am.oid)\n"
+						  "WHERE c.oid = '%s';",
+						  (verbose ?
+						   "pg_catalog.array_to_string(c.reloptions || "
+						   "array(select 'toast.' || x from pg_catalog.unnest(tc.reloptions) x), ', ')\n"
+						   : "''"),
+						  oid);
+	}
+	else if (pset.sversion >= 120000)
 	{
 		printfPQExpBuffer(&buf,
 						  "SELECT c.relchecks, c.relkind, c.relhasindex, c.relhasrules, "
@@ -1707,6 +1727,10 @@ describeOneTableDetails(const char *schemaname,
 			(char *) NULL : pg_strdup(PQgetvalue(res, 0, 14));
 	else
 		tableinfo.relam = NULL;
+	if (pset.sversion >= 170000)
+		tableinfo.isivm = strcmp(PQgetvalue(res, 0, 15), "t") == 0;
+	else
+		tableinfo.isivm = false;
 	PQclear(res);
 	res = NULL;
 
@@ -3552,6 +3576,12 @@ describeOneTableDetails(const char *schemaname,
 			printfPQExpBuffer(&buf, _("Access method: %s"), tableinfo.relam);
 			printTableAddFooter(&cont, buf.data);
 		}
+
+		/* Incremental view maintance info */
+		if (verbose && tableinfo.relkind == RELKIND_MATVIEW && tableinfo.isivm)
+		{
+			printTableAddFooter(&cont, _("Incremental view maintenance: yes"));
+		}
 	}
 
 	/* reloptions, if verbose */
diff --git a/src/bin/psql/tab-complete.c b/src/bin/psql/tab-complete.c
index 779fdc90cb..9cc79b722f 100644
--- a/src/bin/psql/tab-complete.c
+++ b/src/bin/psql/tab-complete.c
@@ -1244,6 +1244,7 @@ static const pgsql_thing_t words_after_create[] = {
 	{"FOREIGN TABLE", NULL, NULL, NULL},
 	{"FUNCTION", NULL, NULL, Query_for_list_of_functions},
 	{"GROUP", Query_for_list_of_roles},
+	{"INCREMENTAL MATERIALIZED VIEW", NULL, NULL, &Query_for_list_of_matviews, NULL, THING_NO_DROP | THING_NO_ALTER},
 	{"INDEX", NULL, NULL, &Query_for_list_of_indexes},
 	{"LANGUAGE", Query_for_list_of_languages},
 	{"LARGE OBJECT", NULL, NULL, NULL, NULL, THING_NO_CREATE | THING_NO_DROP},
@@ -3217,7 +3218,7 @@ psql_completion(const char *text, int start, int end)
 		if (HeadMatches("CREATE", "SCHEMA"))
 			COMPLETE_WITH("TABLE", "SEQUENCE");
 		else
-			COMPLETE_WITH("TABLE", "SEQUENCE", "MATERIALIZED VIEW");
+			COMPLETE_WITH("TABLE", "SEQUENCE", "MATERIALIZED VIEW", "INCREMENTAL MATERIALIZED VIEW");
 	}
 	/* Complete PARTITION BY with RANGE ( or LIST ( or ... */
 	else if (TailMatches("PARTITION", "BY"))
@@ -3535,13 +3536,16 @@ psql_completion(const char *text, int start, int end)
 		COMPLETE_WITH("SELECT");
 
 /* CREATE MATERIALIZED VIEW */
-	else if (Matches("CREATE", "MATERIALIZED"))
+	else if (Matches("CREATE", "MATERIALIZED") ||
+			 Matches("CREATE", "INCREMENTAL", "MATERIALIZED"))
 		COMPLETE_WITH("VIEW");
-	/* Complete CREATE MATERIALIZED VIEW <name> with AS */
-	else if (Matches("CREATE", "MATERIALIZED", "VIEW", MatchAny))
+	/* Complete CREATE MATERIALIZED VIEW <name> with AS  */
+	else if (Matches("CREATE", "MATERIALIZED", "VIEW", MatchAny) ||
+			 Matches("CREATE", "INCREMENTAL", "MATERIALIZED", "VIEW", MatchAny))
 		COMPLETE_WITH("AS");
 	/* Complete "CREATE MATERIALIZED VIEW <sth> AS with "SELECT" */
-	else if (Matches("CREATE", "MATERIALIZED", "VIEW", MatchAny, "AS"))
+	else if (Matches("CREATE", "MATERIALIZED", "VIEW", MatchAny, "AS") ||
+			 Matches("CREATE", "INCREMENTAL", "MATERIALIZED", "VIEW", MatchAny, "AS"))
 		COMPLETE_WITH("SELECT");
 
 /* CREATE EVENT TRIGGER */
-- 
2.25.1


--Multipart=_Mon__28_Aug_2023_11_52_52_+0900_hj6L5h176QaSGtg7
Content-Type: text/x-diff;
 name="v29-0006-Add-Incremental-View-Maintenance-support.patch"
Content-Disposition: attachment;
 filename="v29-0006-Add-Incremental-View-Maintenance-support.patch"
Content-Transfer-Encoding: 7bit



^ permalink  raw  reply  [nested|flat] 101+ messages in thread

* [PATCH v29 05/11] Add Incremental View Maintenance support to psql
@ 2019-12-20 01:21  Yugo Nagata <[email protected]>
  0 siblings, 0 replies; 101+ messages in thread

From: Yugo Nagata @ 2019-12-20 01:21 UTC (permalink / raw)

Add tab completion and meta-command output for IVM.
---
 src/bin/psql/describe.c     | 32 +++++++++++++++++++++++++++++++-
 src/bin/psql/tab-complete.c | 14 +++++++++-----
 2 files changed, 40 insertions(+), 6 deletions(-)

diff --git a/src/bin/psql/describe.c b/src/bin/psql/describe.c
index bac94a338c..f6c7e7163d 100644
--- a/src/bin/psql/describe.c
+++ b/src/bin/psql/describe.c
@@ -1575,6 +1575,7 @@ describeOneTableDetails(const char *schemaname,
 		char		relpersistence;
 		char		relreplident;
 		char	   *relam;
+		bool		isivm;
 	}			tableinfo;
 	bool		show_column_details = false;
 
@@ -1587,7 +1588,26 @@ describeOneTableDetails(const char *schemaname,
 	initPQExpBuffer(&tmpbuf);
 
 	/* Get general table info */
-	if (pset.sversion >= 120000)
+	if (pset.sversion >= 170000)
+	{
+		printfPQExpBuffer(&buf,
+						  "SELECT c.relchecks, c.relkind, c.relhasindex, c.relhasrules, "
+						  "c.relhastriggers, c.relrowsecurity, c.relforcerowsecurity, "
+						  "false AS relhasoids, c.relispartition, %s, c.reltablespace, "
+						  "CASE WHEN c.reloftype = 0 THEN '' ELSE c.reloftype::pg_catalog.regtype::pg_catalog.text END, "
+						  "c.relpersistence, c.relreplident, am.amname, "
+						  "c.relisivm\n"
+						  "FROM pg_catalog.pg_class c\n "
+						  "LEFT JOIN pg_catalog.pg_class tc ON (c.reltoastrelid = tc.oid)\n"
+						  "LEFT JOIN pg_catalog.pg_am am ON (c.relam = am.oid)\n"
+						  "WHERE c.oid = '%s';",
+						  (verbose ?
+						   "pg_catalog.array_to_string(c.reloptions || "
+						   "array(select 'toast.' || x from pg_catalog.unnest(tc.reloptions) x), ', ')\n"
+						   : "''"),
+						  oid);
+	}
+	else if (pset.sversion >= 120000)
 	{
 		printfPQExpBuffer(&buf,
 						  "SELECT c.relchecks, c.relkind, c.relhasindex, c.relhasrules, "
@@ -1707,6 +1727,10 @@ describeOneTableDetails(const char *schemaname,
 			(char *) NULL : pg_strdup(PQgetvalue(res, 0, 14));
 	else
 		tableinfo.relam = NULL;
+	if (pset.sversion >= 170000)
+		tableinfo.isivm = strcmp(PQgetvalue(res, 0, 15), "t") == 0;
+	else
+		tableinfo.isivm = false;
 	PQclear(res);
 	res = NULL;
 
@@ -3552,6 +3576,12 @@ describeOneTableDetails(const char *schemaname,
 			printfPQExpBuffer(&buf, _("Access method: %s"), tableinfo.relam);
 			printTableAddFooter(&cont, buf.data);
 		}
+
+		/* Incremental view maintance info */
+		if (verbose && tableinfo.relkind == RELKIND_MATVIEW && tableinfo.isivm)
+		{
+			printTableAddFooter(&cont, _("Incremental view maintenance: yes"));
+		}
 	}
 
 	/* reloptions, if verbose */
diff --git a/src/bin/psql/tab-complete.c b/src/bin/psql/tab-complete.c
index 779fdc90cb..9cc79b722f 100644
--- a/src/bin/psql/tab-complete.c
+++ b/src/bin/psql/tab-complete.c
@@ -1244,6 +1244,7 @@ static const pgsql_thing_t words_after_create[] = {
 	{"FOREIGN TABLE", NULL, NULL, NULL},
 	{"FUNCTION", NULL, NULL, Query_for_list_of_functions},
 	{"GROUP", Query_for_list_of_roles},
+	{"INCREMENTAL MATERIALIZED VIEW", NULL, NULL, &Query_for_list_of_matviews, NULL, THING_NO_DROP | THING_NO_ALTER},
 	{"INDEX", NULL, NULL, &Query_for_list_of_indexes},
 	{"LANGUAGE", Query_for_list_of_languages},
 	{"LARGE OBJECT", NULL, NULL, NULL, NULL, THING_NO_CREATE | THING_NO_DROP},
@@ -3217,7 +3218,7 @@ psql_completion(const char *text, int start, int end)
 		if (HeadMatches("CREATE", "SCHEMA"))
 			COMPLETE_WITH("TABLE", "SEQUENCE");
 		else
-			COMPLETE_WITH("TABLE", "SEQUENCE", "MATERIALIZED VIEW");
+			COMPLETE_WITH("TABLE", "SEQUENCE", "MATERIALIZED VIEW", "INCREMENTAL MATERIALIZED VIEW");
 	}
 	/* Complete PARTITION BY with RANGE ( or LIST ( or ... */
 	else if (TailMatches("PARTITION", "BY"))
@@ -3535,13 +3536,16 @@ psql_completion(const char *text, int start, int end)
 		COMPLETE_WITH("SELECT");
 
 /* CREATE MATERIALIZED VIEW */
-	else if (Matches("CREATE", "MATERIALIZED"))
+	else if (Matches("CREATE", "MATERIALIZED") ||
+			 Matches("CREATE", "INCREMENTAL", "MATERIALIZED"))
 		COMPLETE_WITH("VIEW");
-	/* Complete CREATE MATERIALIZED VIEW <name> with AS */
-	else if (Matches("CREATE", "MATERIALIZED", "VIEW", MatchAny))
+	/* Complete CREATE MATERIALIZED VIEW <name> with AS  */
+	else if (Matches("CREATE", "MATERIALIZED", "VIEW", MatchAny) ||
+			 Matches("CREATE", "INCREMENTAL", "MATERIALIZED", "VIEW", MatchAny))
 		COMPLETE_WITH("AS");
 	/* Complete "CREATE MATERIALIZED VIEW <sth> AS with "SELECT" */
-	else if (Matches("CREATE", "MATERIALIZED", "VIEW", MatchAny, "AS"))
+	else if (Matches("CREATE", "MATERIALIZED", "VIEW", MatchAny, "AS") ||
+			 Matches("CREATE", "INCREMENTAL", "MATERIALIZED", "VIEW", MatchAny, "AS"))
 		COMPLETE_WITH("SELECT");
 
 /* CREATE EVENT TRIGGER */
-- 
2.25.1


--Multipart=_Mon__28_Aug_2023_16_05_30_+0900_b1OvQD_3A3ZMTGvj
Content-Type: text/x-diff;
 name="v29-0006-Add-Incremental-View-Maintenance-support.patch"
Content-Disposition: attachment;
 filename="v29-0006-Add-Incremental-View-Maintenance-support.patch"
Content-Transfer-Encoding: 7bit



^ permalink  raw  reply  [nested|flat] 101+ messages in thread

* [PATCH v30 05/11] Add Incremental View Maintenance support to psql
@ 2019-12-20 01:21  Yugo Nagata <[email protected]>
  0 siblings, 0 replies; 101+ messages in thread

From: Yugo Nagata @ 2019-12-20 01:21 UTC (permalink / raw)

Add tab completion and meta-command output for IVM.
---
 src/bin/psql/describe.c     | 32 +++++++++++++++++++++++++++++++-
 src/bin/psql/tab-complete.c | 14 +++++++++-----
 2 files changed, 40 insertions(+), 6 deletions(-)

diff --git a/src/bin/psql/describe.c b/src/bin/psql/describe.c
index b6a4eb1d56..3664371aa6 100644
--- a/src/bin/psql/describe.c
+++ b/src/bin/psql/describe.c
@@ -1570,6 +1570,7 @@ describeOneTableDetails(const char *schemaname,
 		char		relpersistence;
 		char		relreplident;
 		char	   *relam;
+		bool		isivm;
 	}			tableinfo;
 	bool		show_column_details = false;
 
@@ -1582,7 +1583,26 @@ describeOneTableDetails(const char *schemaname,
 	initPQExpBuffer(&tmpbuf);
 
 	/* Get general table info */
-	if (pset.sversion >= 120000)
+	if (pset.sversion >= 170000)
+	{
+		printfPQExpBuffer(&buf,
+						  "SELECT c.relchecks, c.relkind, c.relhasindex, c.relhasrules, "
+						  "c.relhastriggers, c.relrowsecurity, c.relforcerowsecurity, "
+						  "false AS relhasoids, c.relispartition, %s, c.reltablespace, "
+						  "CASE WHEN c.reloftype = 0 THEN '' ELSE c.reloftype::pg_catalog.regtype::pg_catalog.text END, "
+						  "c.relpersistence, c.relreplident, am.amname, "
+						  "c.relisivm\n"
+						  "FROM pg_catalog.pg_class c\n "
+						  "LEFT JOIN pg_catalog.pg_class tc ON (c.reltoastrelid = tc.oid)\n"
+						  "LEFT JOIN pg_catalog.pg_am am ON (c.relam = am.oid)\n"
+						  "WHERE c.oid = '%s';",
+						  (verbose ?
+						   "pg_catalog.array_to_string(c.reloptions || "
+						   "array(select 'toast.' || x from pg_catalog.unnest(tc.reloptions) x), ', ')\n"
+						   : "''"),
+						  oid);
+	}
+	else if (pset.sversion >= 120000)
 	{
 		printfPQExpBuffer(&buf,
 						  "SELECT c.relchecks, c.relkind, c.relhasindex, c.relhasrules, "
@@ -1702,6 +1722,10 @@ describeOneTableDetails(const char *schemaname,
 			(char *) NULL : pg_strdup(PQgetvalue(res, 0, 14));
 	else
 		tableinfo.relam = NULL;
+	if (pset.sversion >= 170000)
+		tableinfo.isivm = strcmp(PQgetvalue(res, 0, 15), "t") == 0;
+	else
+		tableinfo.isivm = false;
 	PQclear(res);
 	res = NULL;
 
@@ -3555,6 +3579,12 @@ describeOneTableDetails(const char *schemaname,
 			printfPQExpBuffer(&buf, _("Access method: %s"), tableinfo.relam);
 			printTableAddFooter(&cont, buf.data);
 		}
+
+		/* Incremental view maintance info */
+		if (verbose && tableinfo.relkind == RELKIND_MATVIEW && tableinfo.isivm)
+		{
+			printTableAddFooter(&cont, _("Incremental view maintenance: yes"));
+		}
 	}
 
 	/* reloptions, if verbose */
diff --git a/src/bin/psql/tab-complete.c b/src/bin/psql/tab-complete.c
index aa1acf8523..9977df2e28 100644
--- a/src/bin/psql/tab-complete.c
+++ b/src/bin/psql/tab-complete.c
@@ -1245,6 +1245,7 @@ static const pgsql_thing_t words_after_create[] = {
 	{"FOREIGN TABLE", NULL, NULL, NULL},
 	{"FUNCTION", NULL, NULL, Query_for_list_of_functions},
 	{"GROUP", Query_for_list_of_roles},
+	{"INCREMENTAL MATERIALIZED VIEW", NULL, NULL, &Query_for_list_of_matviews, NULL, THING_NO_DROP | THING_NO_ALTER},
 	{"INDEX", NULL, NULL, &Query_for_list_of_indexes},
 	{"LANGUAGE", Query_for_list_of_languages},
 	{"LARGE OBJECT", NULL, NULL, NULL, NULL, THING_NO_CREATE | THING_NO_DROP},
@@ -3252,7 +3253,7 @@ psql_completion(const char *text, int start, int end)
 		if (HeadMatches("CREATE", "SCHEMA"))
 			COMPLETE_WITH("TABLE", "SEQUENCE");
 		else
-			COMPLETE_WITH("TABLE", "SEQUENCE", "MATERIALIZED VIEW");
+			COMPLETE_WITH("TABLE", "SEQUENCE", "MATERIALIZED VIEW", "INCREMENTAL MATERIALIZED VIEW");
 	}
 	/* Complete PARTITION BY with RANGE ( or LIST ( or ... */
 	else if (TailMatches("PARTITION", "BY"))
@@ -3597,13 +3598,16 @@ psql_completion(const char *text, int start, int end)
 		COMPLETE_WITH("SELECT");
 
 /* CREATE MATERIALIZED VIEW */
-	else if (Matches("CREATE", "MATERIALIZED"))
+	else if (Matches("CREATE", "MATERIALIZED") ||
+			 Matches("CREATE", "INCREMENTAL", "MATERIALIZED"))
 		COMPLETE_WITH("VIEW");
-	/* Complete CREATE MATERIALIZED VIEW <name> with AS */
-	else if (Matches("CREATE", "MATERIALIZED", "VIEW", MatchAny))
+	/* Complete CREATE MATERIALIZED VIEW <name> with AS  */
+	else if (Matches("CREATE", "MATERIALIZED", "VIEW", MatchAny) ||
+			 Matches("CREATE", "INCREMENTAL", "MATERIALIZED", "VIEW", MatchAny))
 		COMPLETE_WITH("AS");
 	/* Complete "CREATE MATERIALIZED VIEW <sth> AS with "SELECT" */
-	else if (Matches("CREATE", "MATERIALIZED", "VIEW", MatchAny, "AS"))
+	else if (Matches("CREATE", "MATERIALIZED", "VIEW", MatchAny, "AS") ||
+			 Matches("CREATE", "INCREMENTAL", "MATERIALIZED", "VIEW", MatchAny, "AS"))
 		COMPLETE_WITH("SELECT");
 
 /* CREATE EVENT TRIGGER */
-- 
2.25.1


--Multipart=_Mon__4_Mar_2024_11_58_46_+0900_UaponF/qQhQrVCFt
Content-Type: text/x-diff;
 name="v30-0006-Add-Incremental-View-Maintenance-support.patch"
Content-Disposition: attachment;
 filename="v30-0006-Add-Incremental-View-Maintenance-support.patch"
Content-Transfer-Encoding: 7bit



^ permalink  raw  reply  [nested|flat] 101+ messages in thread

* [PATCH v24 06/15] Add Incremental View Maintenance support to psql
@ 2019-12-20 01:21  Yugo Nagata <[email protected]>
  0 siblings, 0 replies; 101+ messages in thread

From: Yugo Nagata @ 2019-12-20 01:21 UTC (permalink / raw)

Add tab completion and meta-command output for IVM.
---
 src/bin/psql/describe.c     | 32 +++++++++++++++++++++++++++++++-
 src/bin/psql/tab-complete.c | 14 +++++++++-----
 2 files changed, 40 insertions(+), 6 deletions(-)

diff --git a/src/bin/psql/describe.c b/src/bin/psql/describe.c
index 90ff649be7..48efc436cc 100644
--- a/src/bin/psql/describe.c
+++ b/src/bin/psql/describe.c
@@ -1657,6 +1657,7 @@ describeOneTableDetails(const char *schemaname,
 		char		relpersistence;
 		char		relreplident;
 		char	   *relam;
+		bool		isivm;
 	}			tableinfo;
 	bool		show_column_details = false;
 
@@ -1669,7 +1670,26 @@ describeOneTableDetails(const char *schemaname,
 	initPQExpBuffer(&tmpbuf);
 
 	/* Get general table info */
-	if (pset.sversion >= 120000)
+	if (pset.sversion >= 150000)
+	{
+		printfPQExpBuffer(&buf,
+						  "SELECT c.relchecks, c.relkind, c.relhasindex, c.relhasrules, "
+						  "c.relhastriggers, c.relrowsecurity, c.relforcerowsecurity, "
+						  "false AS relhasoids, c.relispartition, %s, c.reltablespace, "
+						  "CASE WHEN c.reloftype = 0 THEN '' ELSE c.reloftype::pg_catalog.regtype::pg_catalog.text END, "
+						  "c.relpersistence, c.relreplident, am.amname, "
+						  "c.relisivm\n"
+						  "FROM pg_catalog.pg_class c\n "
+						  "LEFT JOIN pg_catalog.pg_class tc ON (c.reltoastrelid = tc.oid)\n"
+						  "LEFT JOIN pg_catalog.pg_am am ON (c.relam = am.oid)\n"
+						  "WHERE c.oid = '%s';",
+						  (verbose ?
+						   "pg_catalog.array_to_string(c.reloptions || "
+						   "array(select 'toast.' || x from pg_catalog.unnest(tc.reloptions) x), ', ')\n"
+						   : "''"),
+						  oid);
+	}
+	else if (pset.sversion >= 120000)
 	{
 		printfPQExpBuffer(&buf,
 						  "SELECT c.relchecks, c.relkind, c.relhasindex, c.relhasrules, "
@@ -1853,6 +1873,10 @@ describeOneTableDetails(const char *schemaname,
 			(char *) NULL : pg_strdup(PQgetvalue(res, 0, 14));
 	else
 		tableinfo.relam = NULL;
+	if (pset.sversion >= 150000)
+		tableinfo.isivm = strcmp(PQgetvalue(res, 0, 15), "t") == 0;
+	else
+		tableinfo.isivm = false;
 	PQclear(res);
 	res = NULL;
 
@@ -3630,6 +3654,12 @@ describeOneTableDetails(const char *schemaname,
 			printfPQExpBuffer(&buf, _("Access method: %s"), tableinfo.relam);
 			printTableAddFooter(&cont, buf.data);
 		}
+
+		/* Incremental view maintance info */
+		if (verbose && tableinfo.relkind == RELKIND_MATVIEW && tableinfo.isivm)
+		{
+			printTableAddFooter(&cont, _("Incremental view maintenance: yes"));
+		}
 	}
 
 	/* reloptions, if verbose */
diff --git a/src/bin/psql/tab-complete.c b/src/bin/psql/tab-complete.c
index 5cd5838668..ea12bbdec2 100644
--- a/src/bin/psql/tab-complete.c
+++ b/src/bin/psql/tab-complete.c
@@ -1059,6 +1059,7 @@ static const pgsql_thing_t words_after_create[] = {
 	{"FOREIGN TABLE", NULL, NULL, NULL},
 	{"FUNCTION", NULL, NULL, Query_for_list_of_functions},
 	{"GROUP", Query_for_list_of_roles},
+	{"INCREMENTAL MATERIALIZED VIEW", NULL, NULL, &Query_for_list_of_matviews, THING_NO_DROP | THING_NO_ALTER},
 	{"INDEX", NULL, NULL, &Query_for_list_of_indexes},
 	{"LANGUAGE", Query_for_list_of_languages},
 	{"LARGE OBJECT", NULL, NULL, NULL, THING_NO_CREATE | THING_NO_DROP},
@@ -2757,7 +2758,7 @@ psql_completion(const char *text, int start, int end)
 		COMPLETE_WITH("SEQUENCE", "TABLE", "VIEW");
 	/* Complete "CREATE UNLOGGED" with TABLE or MATVIEW */
 	else if (TailMatches("CREATE", "UNLOGGED"))
-		COMPLETE_WITH("TABLE", "MATERIALIZED VIEW");
+		COMPLETE_WITH("TABLE", "MATERIALIZED VIEW", "INCREMENTAL MATERIALIZED VIEW");
 	/* Complete PARTITION BY with RANGE ( or LIST ( or ... */
 	else if (TailMatches("PARTITION", "BY"))
 		COMPLETE_WITH("RANGE (", "LIST (", "HASH (");
@@ -3056,13 +3057,16 @@ psql_completion(const char *text, int start, int end)
 		COMPLETE_WITH("SELECT");
 
 /* CREATE MATERIALIZED VIEW */
-	else if (Matches("CREATE", "MATERIALIZED"))
+	else if (Matches("CREATE", "MATERIALIZED") ||
+			 Matches("CREATE", "INCREMENTAL", "MATERIALIZED"))
 		COMPLETE_WITH("VIEW");
-	/* Complete CREATE MATERIALIZED VIEW <name> with AS */
-	else if (Matches("CREATE", "MATERIALIZED", "VIEW", MatchAny))
+	/* Complete CREATE MATERIALIZED VIEW <name> with AS  */
+	else if (Matches("CREATE", "MATERIALIZED", "VIEW", MatchAny) ||
+			 Matches("CREATE", "INCREMENTAL", "MATERIALIZED", "VIEW", MatchAny))
 		COMPLETE_WITH("AS");
 	/* Complete "CREATE MATERIALIZED VIEW <sth> AS with "SELECT" */
-	else if (Matches("CREATE", "MATERIALIZED", "VIEW", MatchAny, "AS"))
+	else if (Matches("CREATE", "MATERIALIZED", "VIEW", MatchAny, "AS") ||
+			 Matches("CREATE", "INCREMENTAL", "MATERIALIZED", "VIEW", MatchAny, "AS"))
 		COMPLETE_WITH("SELECT");
 
 /* CREATE EVENT TRIGGER */
-- 
2.17.1


--Multipart=_Thu__23_Sep_2021_04_57_30_+0900_b5pmgR1N8oMaMz.U
Content-Type: text/x-diff;
 name="v24-0007-Add-Incremental-View-Maintenance-support.patch"
Content-Disposition: attachment;
 filename="v24-0007-Add-Incremental-View-Maintenance-support.patch"
Content-Transfer-Encoding: 7bit



^ permalink  raw  reply  [nested|flat] 101+ messages in thread

* [PATCH v30 05/11] Add Incremental View Maintenance support to psql
@ 2019-12-20 01:21  Yugo Nagata <[email protected]>
  0 siblings, 0 replies; 101+ messages in thread

From: Yugo Nagata @ 2019-12-20 01:21 UTC (permalink / raw)

Add tab completion and meta-command output for IVM.
---
 src/bin/psql/describe.c     | 32 +++++++++++++++++++++++++++++++-
 src/bin/psql/tab-complete.c | 14 +++++++++-----
 2 files changed, 40 insertions(+), 6 deletions(-)

diff --git a/src/bin/psql/describe.c b/src/bin/psql/describe.c
index b6a4eb1d56..3664371aa6 100644
--- a/src/bin/psql/describe.c
+++ b/src/bin/psql/describe.c
@@ -1570,6 +1570,7 @@ describeOneTableDetails(const char *schemaname,
 		char		relpersistence;
 		char		relreplident;
 		char	   *relam;
+		bool		isivm;
 	}			tableinfo;
 	bool		show_column_details = false;
 
@@ -1582,7 +1583,26 @@ describeOneTableDetails(const char *schemaname,
 	initPQExpBuffer(&tmpbuf);
 
 	/* Get general table info */
-	if (pset.sversion >= 120000)
+	if (pset.sversion >= 170000)
+	{
+		printfPQExpBuffer(&buf,
+						  "SELECT c.relchecks, c.relkind, c.relhasindex, c.relhasrules, "
+						  "c.relhastriggers, c.relrowsecurity, c.relforcerowsecurity, "
+						  "false AS relhasoids, c.relispartition, %s, c.reltablespace, "
+						  "CASE WHEN c.reloftype = 0 THEN '' ELSE c.reloftype::pg_catalog.regtype::pg_catalog.text END, "
+						  "c.relpersistence, c.relreplident, am.amname, "
+						  "c.relisivm\n"
+						  "FROM pg_catalog.pg_class c\n "
+						  "LEFT JOIN pg_catalog.pg_class tc ON (c.reltoastrelid = tc.oid)\n"
+						  "LEFT JOIN pg_catalog.pg_am am ON (c.relam = am.oid)\n"
+						  "WHERE c.oid = '%s';",
+						  (verbose ?
+						   "pg_catalog.array_to_string(c.reloptions || "
+						   "array(select 'toast.' || x from pg_catalog.unnest(tc.reloptions) x), ', ')\n"
+						   : "''"),
+						  oid);
+	}
+	else if (pset.sversion >= 120000)
 	{
 		printfPQExpBuffer(&buf,
 						  "SELECT c.relchecks, c.relkind, c.relhasindex, c.relhasrules, "
@@ -1702,6 +1722,10 @@ describeOneTableDetails(const char *schemaname,
 			(char *) NULL : pg_strdup(PQgetvalue(res, 0, 14));
 	else
 		tableinfo.relam = NULL;
+	if (pset.sversion >= 170000)
+		tableinfo.isivm = strcmp(PQgetvalue(res, 0, 15), "t") == 0;
+	else
+		tableinfo.isivm = false;
 	PQclear(res);
 	res = NULL;
 
@@ -3555,6 +3579,12 @@ describeOneTableDetails(const char *schemaname,
 			printfPQExpBuffer(&buf, _("Access method: %s"), tableinfo.relam);
 			printTableAddFooter(&cont, buf.data);
 		}
+
+		/* Incremental view maintance info */
+		if (verbose && tableinfo.relkind == RELKIND_MATVIEW && tableinfo.isivm)
+		{
+			printTableAddFooter(&cont, _("Incremental view maintenance: yes"));
+		}
 	}
 
 	/* reloptions, if verbose */
diff --git a/src/bin/psql/tab-complete.c b/src/bin/psql/tab-complete.c
index aa1acf8523..9977df2e28 100644
--- a/src/bin/psql/tab-complete.c
+++ b/src/bin/psql/tab-complete.c
@@ -1245,6 +1245,7 @@ static const pgsql_thing_t words_after_create[] = {
 	{"FOREIGN TABLE", NULL, NULL, NULL},
 	{"FUNCTION", NULL, NULL, Query_for_list_of_functions},
 	{"GROUP", Query_for_list_of_roles},
+	{"INCREMENTAL MATERIALIZED VIEW", NULL, NULL, &Query_for_list_of_matviews, NULL, THING_NO_DROP | THING_NO_ALTER},
 	{"INDEX", NULL, NULL, &Query_for_list_of_indexes},
 	{"LANGUAGE", Query_for_list_of_languages},
 	{"LARGE OBJECT", NULL, NULL, NULL, NULL, THING_NO_CREATE | THING_NO_DROP},
@@ -3252,7 +3253,7 @@ psql_completion(const char *text, int start, int end)
 		if (HeadMatches("CREATE", "SCHEMA"))
 			COMPLETE_WITH("TABLE", "SEQUENCE");
 		else
-			COMPLETE_WITH("TABLE", "SEQUENCE", "MATERIALIZED VIEW");
+			COMPLETE_WITH("TABLE", "SEQUENCE", "MATERIALIZED VIEW", "INCREMENTAL MATERIALIZED VIEW");
 	}
 	/* Complete PARTITION BY with RANGE ( or LIST ( or ... */
 	else if (TailMatches("PARTITION", "BY"))
@@ -3597,13 +3598,16 @@ psql_completion(const char *text, int start, int end)
 		COMPLETE_WITH("SELECT");
 
 /* CREATE MATERIALIZED VIEW */
-	else if (Matches("CREATE", "MATERIALIZED"))
+	else if (Matches("CREATE", "MATERIALIZED") ||
+			 Matches("CREATE", "INCREMENTAL", "MATERIALIZED"))
 		COMPLETE_WITH("VIEW");
-	/* Complete CREATE MATERIALIZED VIEW <name> with AS */
-	else if (Matches("CREATE", "MATERIALIZED", "VIEW", MatchAny))
+	/* Complete CREATE MATERIALIZED VIEW <name> with AS  */
+	else if (Matches("CREATE", "MATERIALIZED", "VIEW", MatchAny) ||
+			 Matches("CREATE", "INCREMENTAL", "MATERIALIZED", "VIEW", MatchAny))
 		COMPLETE_WITH("AS");
 	/* Complete "CREATE MATERIALIZED VIEW <sth> AS with "SELECT" */
-	else if (Matches("CREATE", "MATERIALIZED", "VIEW", MatchAny, "AS"))
+	else if (Matches("CREATE", "MATERIALIZED", "VIEW", MatchAny, "AS") ||
+			 Matches("CREATE", "INCREMENTAL", "MATERIALIZED", "VIEW", MatchAny, "AS"))
 		COMPLETE_WITH("SELECT");
 
 /* CREATE EVENT TRIGGER */
-- 
2.25.1


--Multipart=_Mon__4_Mar_2024_11_58_46_+0900_UaponF/qQhQrVCFt
Content-Type: text/x-diff;
 name="v30-0006-Add-Incremental-View-Maintenance-support.patch"
Content-Disposition: attachment;
 filename="v30-0006-Add-Incremental-View-Maintenance-support.patch"
Content-Transfer-Encoding: 7bit



^ permalink  raw  reply  [nested|flat] 101+ messages in thread

* [PATCH v29 05/11] Add Incremental View Maintenance support to psql
@ 2019-12-20 01:21  Yugo Nagata <[email protected]>
  0 siblings, 0 replies; 101+ messages in thread

From: Yugo Nagata @ 2019-12-20 01:21 UTC (permalink / raw)

Add tab completion and meta-command output for IVM.
---
 src/bin/psql/describe.c     | 32 +++++++++++++++++++++++++++++++-
 src/bin/psql/tab-complete.c | 14 +++++++++-----
 2 files changed, 40 insertions(+), 6 deletions(-)

diff --git a/src/bin/psql/describe.c b/src/bin/psql/describe.c
index bac94a338c..f6c7e7163d 100644
--- a/src/bin/psql/describe.c
+++ b/src/bin/psql/describe.c
@@ -1575,6 +1575,7 @@ describeOneTableDetails(const char *schemaname,
 		char		relpersistence;
 		char		relreplident;
 		char	   *relam;
+		bool		isivm;
 	}			tableinfo;
 	bool		show_column_details = false;
 
@@ -1587,7 +1588,26 @@ describeOneTableDetails(const char *schemaname,
 	initPQExpBuffer(&tmpbuf);
 
 	/* Get general table info */
-	if (pset.sversion >= 120000)
+	if (pset.sversion >= 170000)
+	{
+		printfPQExpBuffer(&buf,
+						  "SELECT c.relchecks, c.relkind, c.relhasindex, c.relhasrules, "
+						  "c.relhastriggers, c.relrowsecurity, c.relforcerowsecurity, "
+						  "false AS relhasoids, c.relispartition, %s, c.reltablespace, "
+						  "CASE WHEN c.reloftype = 0 THEN '' ELSE c.reloftype::pg_catalog.regtype::pg_catalog.text END, "
+						  "c.relpersistence, c.relreplident, am.amname, "
+						  "c.relisivm\n"
+						  "FROM pg_catalog.pg_class c\n "
+						  "LEFT JOIN pg_catalog.pg_class tc ON (c.reltoastrelid = tc.oid)\n"
+						  "LEFT JOIN pg_catalog.pg_am am ON (c.relam = am.oid)\n"
+						  "WHERE c.oid = '%s';",
+						  (verbose ?
+						   "pg_catalog.array_to_string(c.reloptions || "
+						   "array(select 'toast.' || x from pg_catalog.unnest(tc.reloptions) x), ', ')\n"
+						   : "''"),
+						  oid);
+	}
+	else if (pset.sversion >= 120000)
 	{
 		printfPQExpBuffer(&buf,
 						  "SELECT c.relchecks, c.relkind, c.relhasindex, c.relhasrules, "
@@ -1707,6 +1727,10 @@ describeOneTableDetails(const char *schemaname,
 			(char *) NULL : pg_strdup(PQgetvalue(res, 0, 14));
 	else
 		tableinfo.relam = NULL;
+	if (pset.sversion >= 170000)
+		tableinfo.isivm = strcmp(PQgetvalue(res, 0, 15), "t") == 0;
+	else
+		tableinfo.isivm = false;
 	PQclear(res);
 	res = NULL;
 
@@ -3552,6 +3576,12 @@ describeOneTableDetails(const char *schemaname,
 			printfPQExpBuffer(&buf, _("Access method: %s"), tableinfo.relam);
 			printTableAddFooter(&cont, buf.data);
 		}
+
+		/* Incremental view maintance info */
+		if (verbose && tableinfo.relkind == RELKIND_MATVIEW && tableinfo.isivm)
+		{
+			printTableAddFooter(&cont, _("Incremental view maintenance: yes"));
+		}
 	}
 
 	/* reloptions, if verbose */
diff --git a/src/bin/psql/tab-complete.c b/src/bin/psql/tab-complete.c
index 779fdc90cb..9cc79b722f 100644
--- a/src/bin/psql/tab-complete.c
+++ b/src/bin/psql/tab-complete.c
@@ -1244,6 +1244,7 @@ static const pgsql_thing_t words_after_create[] = {
 	{"FOREIGN TABLE", NULL, NULL, NULL},
 	{"FUNCTION", NULL, NULL, Query_for_list_of_functions},
 	{"GROUP", Query_for_list_of_roles},
+	{"INCREMENTAL MATERIALIZED VIEW", NULL, NULL, &Query_for_list_of_matviews, NULL, THING_NO_DROP | THING_NO_ALTER},
 	{"INDEX", NULL, NULL, &Query_for_list_of_indexes},
 	{"LANGUAGE", Query_for_list_of_languages},
 	{"LARGE OBJECT", NULL, NULL, NULL, NULL, THING_NO_CREATE | THING_NO_DROP},
@@ -3217,7 +3218,7 @@ psql_completion(const char *text, int start, int end)
 		if (HeadMatches("CREATE", "SCHEMA"))
 			COMPLETE_WITH("TABLE", "SEQUENCE");
 		else
-			COMPLETE_WITH("TABLE", "SEQUENCE", "MATERIALIZED VIEW");
+			COMPLETE_WITH("TABLE", "SEQUENCE", "MATERIALIZED VIEW", "INCREMENTAL MATERIALIZED VIEW");
 	}
 	/* Complete PARTITION BY with RANGE ( or LIST ( or ... */
 	else if (TailMatches("PARTITION", "BY"))
@@ -3535,13 +3536,16 @@ psql_completion(const char *text, int start, int end)
 		COMPLETE_WITH("SELECT");
 
 /* CREATE MATERIALIZED VIEW */
-	else if (Matches("CREATE", "MATERIALIZED"))
+	else if (Matches("CREATE", "MATERIALIZED") ||
+			 Matches("CREATE", "INCREMENTAL", "MATERIALIZED"))
 		COMPLETE_WITH("VIEW");
-	/* Complete CREATE MATERIALIZED VIEW <name> with AS */
-	else if (Matches("CREATE", "MATERIALIZED", "VIEW", MatchAny))
+	/* Complete CREATE MATERIALIZED VIEW <name> with AS  */
+	else if (Matches("CREATE", "MATERIALIZED", "VIEW", MatchAny) ||
+			 Matches("CREATE", "INCREMENTAL", "MATERIALIZED", "VIEW", MatchAny))
 		COMPLETE_WITH("AS");
 	/* Complete "CREATE MATERIALIZED VIEW <sth> AS with "SELECT" */
-	else if (Matches("CREATE", "MATERIALIZED", "VIEW", MatchAny, "AS"))
+	else if (Matches("CREATE", "MATERIALIZED", "VIEW", MatchAny, "AS") ||
+			 Matches("CREATE", "INCREMENTAL", "MATERIALIZED", "VIEW", MatchAny, "AS"))
 		COMPLETE_WITH("SELECT");
 
 /* CREATE EVENT TRIGGER */
-- 
2.25.1


--Multipart=_Mon__28_Aug_2023_16_05_30_+0900_b1OvQD_3A3ZMTGvj
Content-Type: text/x-diff;
 name="v29-0006-Add-Incremental-View-Maintenance-support.patch"
Content-Disposition: attachment;
 filename="v29-0006-Add-Incremental-View-Maintenance-support.patch"
Content-Transfer-Encoding: 7bit



^ permalink  raw  reply  [nested|flat] 101+ messages in thread

* [PATCH v28 05/11] Add Incremental View Maintenance support to psql
@ 2019-12-20 01:21  Yugo Nagata <[email protected]>
  0 siblings, 0 replies; 101+ messages in thread

From: Yugo Nagata @ 2019-12-20 01:21 UTC (permalink / raw)

Add tab completion and meta-command output for IVM.
---
 src/bin/psql/describe.c     | 32 +++++++++++++++++++++++++++++++-
 src/bin/psql/tab-complete.c | 14 +++++++++-----
 2 files changed, 40 insertions(+), 6 deletions(-)

diff --git a/src/bin/psql/describe.c b/src/bin/psql/describe.c
index 9325a46b8f..f555af7c95 100644
--- a/src/bin/psql/describe.c
+++ b/src/bin/psql/describe.c
@@ -1575,6 +1575,7 @@ describeOneTableDetails(const char *schemaname,
 		char		relpersistence;
 		char		relreplident;
 		char	   *relam;
+		bool		isivm;
 	}			tableinfo;
 	bool		show_column_details = false;
 
@@ -1587,7 +1588,26 @@ describeOneTableDetails(const char *schemaname,
 	initPQExpBuffer(&tmpbuf);
 
 	/* Get general table info */
-	if (pset.sversion >= 120000)
+	if (pset.sversion >= 170000)
+	{
+		printfPQExpBuffer(&buf,
+						  "SELECT c.relchecks, c.relkind, c.relhasindex, c.relhasrules, "
+						  "c.relhastriggers, c.relrowsecurity, c.relforcerowsecurity, "
+						  "false AS relhasoids, c.relispartition, %s, c.reltablespace, "
+						  "CASE WHEN c.reloftype = 0 THEN '' ELSE c.reloftype::pg_catalog.regtype::pg_catalog.text END, "
+						  "c.relpersistence, c.relreplident, am.amname, "
+						  "c.relisivm\n"
+						  "FROM pg_catalog.pg_class c\n "
+						  "LEFT JOIN pg_catalog.pg_class tc ON (c.reltoastrelid = tc.oid)\n"
+						  "LEFT JOIN pg_catalog.pg_am am ON (c.relam = am.oid)\n"
+						  "WHERE c.oid = '%s';",
+						  (verbose ?
+						   "pg_catalog.array_to_string(c.reloptions || "
+						   "array(select 'toast.' || x from pg_catalog.unnest(tc.reloptions) x), ', ')\n"
+						   : "''"),
+						  oid);
+	}
+	else if (pset.sversion >= 120000)
 	{
 		printfPQExpBuffer(&buf,
 						  "SELECT c.relchecks, c.relkind, c.relhasindex, c.relhasrules, "
@@ -1707,6 +1727,10 @@ describeOneTableDetails(const char *schemaname,
 			(char *) NULL : pg_strdup(PQgetvalue(res, 0, 14));
 	else
 		tableinfo.relam = NULL;
+	if (pset.sversion >= 170000)
+		tableinfo.isivm = strcmp(PQgetvalue(res, 0, 15), "t") == 0;
+	else
+		tableinfo.isivm = false;
 	PQclear(res);
 	res = NULL;
 
@@ -3508,6 +3532,12 @@ describeOneTableDetails(const char *schemaname,
 			printfPQExpBuffer(&buf, _("Access method: %s"), tableinfo.relam);
 			printTableAddFooter(&cont, buf.data);
 		}
+
+		/* Incremental view maintance info */
+		if (verbose && tableinfo.relkind == RELKIND_MATVIEW && tableinfo.isivm)
+		{
+			printTableAddFooter(&cont, _("Incremental view maintenance: yes"));
+		}
 	}
 
 	/* reloptions, if verbose */
diff --git a/src/bin/psql/tab-complete.c b/src/bin/psql/tab-complete.c
index 677847e434..6ec195b2e9 100644
--- a/src/bin/psql/tab-complete.c
+++ b/src/bin/psql/tab-complete.c
@@ -1240,6 +1240,7 @@ static const pgsql_thing_t words_after_create[] = {
 	{"FOREIGN TABLE", NULL, NULL, NULL},
 	{"FUNCTION", NULL, NULL, Query_for_list_of_functions},
 	{"GROUP", Query_for_list_of_roles},
+	{"INCREMENTAL MATERIALIZED VIEW", NULL, NULL, &Query_for_list_of_matviews, NULL, THING_NO_DROP | THING_NO_ALTER},
 	{"INDEX", NULL, NULL, &Query_for_list_of_indexes},
 	{"LANGUAGE", Query_for_list_of_languages},
 	{"LARGE OBJECT", NULL, NULL, NULL, NULL, THING_NO_CREATE | THING_NO_DROP},
@@ -3187,7 +3188,7 @@ psql_completion(const char *text, int start, int end)
 		COMPLETE_WITH("SEQUENCE", "TABLE", "VIEW");
 	/* Complete "CREATE UNLOGGED" with TABLE or MATVIEW */
 	else if (TailMatches("CREATE", "UNLOGGED"))
-		COMPLETE_WITH("TABLE", "MATERIALIZED VIEW");
+		COMPLETE_WITH("TABLE", "MATERIALIZED VIEW", "INCREMENTAL MATERIALIZED VIEW");
 	/* Complete PARTITION BY with RANGE ( or LIST ( or ... */
 	else if (TailMatches("PARTITION", "BY"))
 		COMPLETE_WITH("RANGE (", "LIST (", "HASH (");
@@ -3504,13 +3505,16 @@ psql_completion(const char *text, int start, int end)
 		COMPLETE_WITH("SELECT");
 
 /* CREATE MATERIALIZED VIEW */
-	else if (Matches("CREATE", "MATERIALIZED"))
+	else if (Matches("CREATE", "MATERIALIZED") ||
+			 Matches("CREATE", "INCREMENTAL", "MATERIALIZED"))
 		COMPLETE_WITH("VIEW");
-	/* Complete CREATE MATERIALIZED VIEW <name> with AS */
-	else if (Matches("CREATE", "MATERIALIZED", "VIEW", MatchAny))
+	/* Complete CREATE MATERIALIZED VIEW <name> with AS  */
+	else if (Matches("CREATE", "MATERIALIZED", "VIEW", MatchAny) ||
+			 Matches("CREATE", "INCREMENTAL", "MATERIALIZED", "VIEW", MatchAny))
 		COMPLETE_WITH("AS");
 	/* Complete "CREATE MATERIALIZED VIEW <sth> AS with "SELECT" */
-	else if (Matches("CREATE", "MATERIALIZED", "VIEW", MatchAny, "AS"))
+	else if (Matches("CREATE", "MATERIALIZED", "VIEW", MatchAny, "AS") ||
+			 Matches("CREATE", "INCREMENTAL", "MATERIALIZED", "VIEW", MatchAny, "AS"))
 		COMPLETE_WITH("SELECT");
 
 /* CREATE EVENT TRIGGER */
-- 
2.25.1


--Multipart=_Thu__1_Jun_2023_23_59_09_+0900_/G5+8nG46.f1T42K
Content-Type: text/x-diff;
 name="v28-0006-Add-Incremental-View-Maintenance-support.patch"
Content-Disposition: attachment;
 filename="v28-0006-Add-Incremental-View-Maintenance-support.patch"
Content-Transfer-Encoding: 7bit



^ permalink  raw  reply  [nested|flat] 101+ messages in thread

* [PATCH v27 5/9] Add Incremental View Maintenance support to psql
@ 2019-12-20 01:21  Yugo Nagata <[email protected]>
  0 siblings, 0 replies; 101+ messages in thread

From: Yugo Nagata @ 2019-12-20 01:21 UTC (permalink / raw)

Add tab completion and meta-command output for IVM.
---
 src/bin/psql/describe.c     | 32 +++++++++++++++++++++++++++++++-
 src/bin/psql/tab-complete.c | 14 +++++++++-----
 2 files changed, 40 insertions(+), 6 deletions(-)

diff --git a/src/bin/psql/describe.c b/src/bin/psql/describe.c
index 583817b0cc..aacfe8b82d 100644
--- a/src/bin/psql/describe.c
+++ b/src/bin/psql/describe.c
@@ -1492,6 +1492,7 @@ describeOneTableDetails(const char *schemaname,
 		char		relpersistence;
 		char		relreplident;
 		char	   *relam;
+		bool		isivm;
 	}			tableinfo;
 	bool		show_column_details = false;
 
@@ -1504,7 +1505,26 @@ describeOneTableDetails(const char *schemaname,
 	initPQExpBuffer(&tmpbuf);
 
 	/* Get general table info */
-	if (pset.sversion >= 120000)
+	if (pset.sversion >= 160000)
+	{
+		printfPQExpBuffer(&buf,
+						  "SELECT c.relchecks, c.relkind, c.relhasindex, c.relhasrules, "
+						  "c.relhastriggers, c.relrowsecurity, c.relforcerowsecurity, "
+						  "false AS relhasoids, c.relispartition, %s, c.reltablespace, "
+						  "CASE WHEN c.reloftype = 0 THEN '' ELSE c.reloftype::pg_catalog.regtype::pg_catalog.text END, "
+						  "c.relpersistence, c.relreplident, am.amname, "
+						  "c.relisivm\n"
+						  "FROM pg_catalog.pg_class c\n "
+						  "LEFT JOIN pg_catalog.pg_class tc ON (c.reltoastrelid = tc.oid)\n"
+						  "LEFT JOIN pg_catalog.pg_am am ON (c.relam = am.oid)\n"
+						  "WHERE c.oid = '%s';",
+						  (verbose ?
+						   "pg_catalog.array_to_string(c.reloptions || "
+						   "array(select 'toast.' || x from pg_catalog.unnest(tc.reloptions) x), ', ')\n"
+						   : "''"),
+						  oid);
+	}
+	else if (pset.sversion >= 120000)
 	{
 		printfPQExpBuffer(&buf,
 						  "SELECT c.relchecks, c.relkind, c.relhasindex, c.relhasrules, "
@@ -1624,6 +1644,10 @@ describeOneTableDetails(const char *schemaname,
 			(char *) NULL : pg_strdup(PQgetvalue(res, 0, 14));
 	else
 		tableinfo.relam = NULL;
+	if (pset.sversion >= 160000)
+		tableinfo.isivm = strcmp(PQgetvalue(res, 0, 15), "t") == 0;
+	else
+		tableinfo.isivm = false;
 	PQclear(res);
 	res = NULL;
 
@@ -3424,6 +3448,12 @@ describeOneTableDetails(const char *schemaname,
 			printfPQExpBuffer(&buf, _("Access method: %s"), tableinfo.relam);
 			printTableAddFooter(&cont, buf.data);
 		}
+
+		/* Incremental view maintance info */
+		if (verbose && tableinfo.relkind == RELKIND_MATVIEW && tableinfo.isivm)
+		{
+			printTableAddFooter(&cont, _("Incremental view maintenance: yes"));
+		}
 	}
 
 	/* reloptions, if verbose */
diff --git a/src/bin/psql/tab-complete.c b/src/bin/psql/tab-complete.c
index 588c0841fe..87b5d3e107 100644
--- a/src/bin/psql/tab-complete.c
+++ b/src/bin/psql/tab-complete.c
@@ -1221,6 +1221,7 @@ static const pgsql_thing_t words_after_create[] = {
 	{"FOREIGN TABLE", NULL, NULL, NULL},
 	{"FUNCTION", NULL, NULL, Query_for_list_of_functions},
 	{"GROUP", Query_for_list_of_roles},
+	{"INCREMENTAL MATERIALIZED VIEW", NULL, NULL, &Query_for_list_of_matviews, NULL, THING_NO_DROP | THING_NO_ALTER},
 	{"INDEX", NULL, NULL, &Query_for_list_of_indexes},
 	{"LANGUAGE", Query_for_list_of_languages},
 	{"LARGE OBJECT", NULL, NULL, NULL, NULL, THING_NO_CREATE | THING_NO_DROP},
@@ -3074,7 +3075,7 @@ psql_completion(const char *text, int start, int end)
 		COMPLETE_WITH("SEQUENCE", "TABLE", "VIEW");
 	/* Complete "CREATE UNLOGGED" with TABLE or MATVIEW */
 	else if (TailMatches("CREATE", "UNLOGGED"))
-		COMPLETE_WITH("TABLE", "MATERIALIZED VIEW");
+		COMPLETE_WITH("TABLE", "MATERIALIZED VIEW", "INCREMENTAL MATERIALIZED VIEW");
 	/* Complete PARTITION BY with RANGE ( or LIST ( or ... */
 	else if (TailMatches("PARTITION", "BY"))
 		COMPLETE_WITH("RANGE (", "LIST (", "HASH (");
@@ -3390,13 +3391,16 @@ psql_completion(const char *text, int start, int end)
 		COMPLETE_WITH("SELECT");
 
 /* CREATE MATERIALIZED VIEW */
-	else if (Matches("CREATE", "MATERIALIZED"))
+	else if (Matches("CREATE", "MATERIALIZED") ||
+			 Matches("CREATE", "INCREMENTAL", "MATERIALIZED"))
 		COMPLETE_WITH("VIEW");
-	/* Complete CREATE MATERIALIZED VIEW <name> with AS */
-	else if (Matches("CREATE", "MATERIALIZED", "VIEW", MatchAny))
+	/* Complete CREATE MATERIALIZED VIEW <name> with AS  */
+	else if (Matches("CREATE", "MATERIALIZED", "VIEW", MatchAny) ||
+			 Matches("CREATE", "INCREMENTAL", "MATERIALIZED", "VIEW", MatchAny))
 		COMPLETE_WITH("AS");
 	/* Complete "CREATE MATERIALIZED VIEW <sth> AS with "SELECT" */
-	else if (Matches("CREATE", "MATERIALIZED", "VIEW", MatchAny, "AS"))
+	else if (Matches("CREATE", "MATERIALIZED", "VIEW", MatchAny, "AS") ||
+			 Matches("CREATE", "INCREMENTAL", "MATERIALIZED", "VIEW", MatchAny, "AS"))
 		COMPLETE_WITH("SELECT");
 
 /* CREATE EVENT TRIGGER */
-- 
2.17.1


--Multipart=_Fri__22_Apr_2022_11_29_39_+0900_ZOAC7UMt5e8j1Nvx
Content-Type: text/x-diff;
 name="v27-0006-Add-Incremental-View-Maintenance-support.patch"
Content-Disposition: attachment;
 filename="v27-0006-Add-Incremental-View-Maintenance-support.patch"
Content-Transfer-Encoding: 7bit



^ permalink  raw  reply  [nested|flat] 101+ messages in thread

* [PATCH v32 05/11] Add Incremental View Maintenance support to psql
@ 2019-12-20 01:21  Yugo Nagata <[email protected]>
  0 siblings, 0 replies; 101+ messages in thread

From: Yugo Nagata @ 2019-12-20 01:21 UTC (permalink / raw)

Add tab completion and meta-command output for IVM.
---
 src/bin/psql/describe.c     | 32 +++++++++++++++++++++++++++++++-
 src/bin/psql/tab-complete.c | 14 +++++++++-----
 2 files changed, 40 insertions(+), 6 deletions(-)

diff --git a/src/bin/psql/describe.c b/src/bin/psql/describe.c
index 6433497bcd..df559dce42 100644
--- a/src/bin/psql/describe.c
+++ b/src/bin/psql/describe.c
@@ -1574,6 +1574,7 @@ describeOneTableDetails(const char *schemaname,
 		char		relpersistence;
 		char		relreplident;
 		char	   *relam;
+		bool		isivm;
 	}			tableinfo;
 	bool		show_column_details = false;
 
@@ -1586,7 +1587,26 @@ describeOneTableDetails(const char *schemaname,
 	initPQExpBuffer(&tmpbuf);
 
 	/* Get general table info */
-	if (pset.sversion >= 120000)
+	if (pset.sversion >= 170000)
+	{
+		printfPQExpBuffer(&buf,
+						  "SELECT c.relchecks, c.relkind, c.relhasindex, c.relhasrules, "
+						  "c.relhastriggers, c.relrowsecurity, c.relforcerowsecurity, "
+						  "false AS relhasoids, c.relispartition, %s, c.reltablespace, "
+						  "CASE WHEN c.reloftype = 0 THEN '' ELSE c.reloftype::pg_catalog.regtype::pg_catalog.text END, "
+						  "c.relpersistence, c.relreplident, am.amname, "
+						  "c.relisivm\n"
+						  "FROM pg_catalog.pg_class c\n "
+						  "LEFT JOIN pg_catalog.pg_class tc ON (c.reltoastrelid = tc.oid)\n"
+						  "LEFT JOIN pg_catalog.pg_am am ON (c.relam = am.oid)\n"
+						  "WHERE c.oid = '%s';",
+						  (verbose ?
+						   "pg_catalog.array_to_string(c.reloptions || "
+						   "array(select 'toast.' || x from pg_catalog.unnest(tc.reloptions) x), ', ')\n"
+						   : "''"),
+						  oid);
+	}
+	else if (pset.sversion >= 120000)
 	{
 		printfPQExpBuffer(&buf,
 						  "SELECT c.relchecks, c.relkind, c.relhasindex, c.relhasrules, "
@@ -1706,6 +1726,10 @@ describeOneTableDetails(const char *schemaname,
 			(char *) NULL : pg_strdup(PQgetvalue(res, 0, 14));
 	else
 		tableinfo.relam = NULL;
+	if (pset.sversion >= 170000)
+		tableinfo.isivm = strcmp(PQgetvalue(res, 0, 15), "t") == 0;
+	else
+		tableinfo.isivm = false;
 	PQclear(res);
 	res = NULL;
 
@@ -3560,6 +3584,12 @@ describeOneTableDetails(const char *schemaname,
 			printfPQExpBuffer(&buf, _("Access method: %s"), tableinfo.relam);
 			printTableAddFooter(&cont, buf.data);
 		}
+
+		/* Incremental view maintance info */
+		if (verbose && tableinfo.relkind == RELKIND_MATVIEW && tableinfo.isivm)
+		{
+			printTableAddFooter(&cont, _("Incremental view maintenance: yes"));
+		}
 	}
 
 	/* reloptions, if verbose */
diff --git a/src/bin/psql/tab-complete.c b/src/bin/psql/tab-complete.c
index fc6865fc70..456d042f09 100644
--- a/src/bin/psql/tab-complete.c
+++ b/src/bin/psql/tab-complete.c
@@ -1245,6 +1245,7 @@ static const pgsql_thing_t words_after_create[] = {
 	{"FOREIGN TABLE", NULL, NULL, NULL},
 	{"FUNCTION", NULL, NULL, Query_for_list_of_functions},
 	{"GROUP", Query_for_list_of_roles},
+	{"INCREMENTAL MATERIALIZED VIEW", NULL, NULL, &Query_for_list_of_matviews, NULL, THING_NO_DROP | THING_NO_ALTER},
 	{"INDEX", NULL, NULL, &Query_for_list_of_indexes},
 	{"LANGUAGE", Query_for_list_of_languages},
 	{"LARGE OBJECT", NULL, NULL, NULL, NULL, THING_NO_CREATE | THING_NO_DROP},
@@ -3256,7 +3257,7 @@ psql_completion(const char *text, int start, int end)
 		if (HeadMatches("CREATE", "SCHEMA"))
 			COMPLETE_WITH("TABLE", "SEQUENCE");
 		else
-			COMPLETE_WITH("TABLE", "SEQUENCE", "MATERIALIZED VIEW");
+			COMPLETE_WITH("TABLE", "SEQUENCE", "MATERIALIZED VIEW", "INCREMENTAL MATERIALIZED VIEW");
 	}
 	/* Complete PARTITION BY with RANGE ( or LIST ( or ... */
 	else if (TailMatches("PARTITION", "BY"))
@@ -3601,13 +3602,16 @@ psql_completion(const char *text, int start, int end)
 		COMPLETE_WITH("SELECT");
 
 /* CREATE MATERIALIZED VIEW */
-	else if (Matches("CREATE", "MATERIALIZED"))
+	else if (Matches("CREATE", "MATERIALIZED") ||
+			 Matches("CREATE", "INCREMENTAL", "MATERIALIZED"))
 		COMPLETE_WITH("VIEW");
-	/* Complete CREATE MATERIALIZED VIEW <name> with AS */
-	else if (Matches("CREATE", "MATERIALIZED", "VIEW", MatchAny))
+	/* Complete CREATE MATERIALIZED VIEW <name> with AS  */
+	else if (Matches("CREATE", "MATERIALIZED", "VIEW", MatchAny) ||
+			 Matches("CREATE", "INCREMENTAL", "MATERIALIZED", "VIEW", MatchAny))
 		COMPLETE_WITH("AS");
 	/* Complete "CREATE MATERIALIZED VIEW <sth> AS with "SELECT" */
-	else if (Matches("CREATE", "MATERIALIZED", "VIEW", MatchAny, "AS"))
+	else if (Matches("CREATE", "MATERIALIZED", "VIEW", MatchAny, "AS") ||
+			 Matches("CREATE", "INCREMENTAL", "MATERIALIZED", "VIEW", MatchAny, "AS"))
 		COMPLETE_WITH("SELECT");
 
 /* CREATE EVENT TRIGGER */
-- 
2.25.1


--Multipart=_Sun__31_Mar_2024_22_59_31_+0900_msknEviJj08_wgqO
Content-Type: text/x-diff;
 name="v32-0006-Add-Incremental-View-Maintenance-support.patch"
Content-Disposition: attachment;
 filename="v32-0006-Add-Incremental-View-Maintenance-support.patch"
Content-Transfer-Encoding: 7bit



^ permalink  raw  reply  [nested|flat] 101+ messages in thread

* [PATCH v24 06/15] Add Incremental View Maintenance support to psql
@ 2019-12-20 01:21  Yugo Nagata <[email protected]>
  0 siblings, 0 replies; 101+ messages in thread

From: Yugo Nagata @ 2019-12-20 01:21 UTC (permalink / raw)

Add tab completion and meta-command output for IVM.
---
 src/bin/psql/describe.c     | 32 +++++++++++++++++++++++++++++++-
 src/bin/psql/tab-complete.c | 14 +++++++++-----
 2 files changed, 40 insertions(+), 6 deletions(-)

diff --git a/src/bin/psql/describe.c b/src/bin/psql/describe.c
index 006661412e..edcc0d8c10 100644
--- a/src/bin/psql/describe.c
+++ b/src/bin/psql/describe.c
@@ -1656,6 +1656,7 @@ describeOneTableDetails(const char *schemaname,
 		char		relpersistence;
 		char		relreplident;
 		char	   *relam;
+		bool		isivm;
 	}			tableinfo;
 	bool		show_column_details = false;
 
@@ -1668,7 +1669,26 @@ describeOneTableDetails(const char *schemaname,
 	initPQExpBuffer(&tmpbuf);
 
 	/* Get general table info */
-	if (pset.sversion >= 120000)
+	if (pset.sversion >= 150000)
+	{
+		printfPQExpBuffer(&buf,
+						  "SELECT c.relchecks, c.relkind, c.relhasindex, c.relhasrules, "
+						  "c.relhastriggers, c.relrowsecurity, c.relforcerowsecurity, "
+						  "false AS relhasoids, c.relispartition, %s, c.reltablespace, "
+						  "CASE WHEN c.reloftype = 0 THEN '' ELSE c.reloftype::pg_catalog.regtype::pg_catalog.text END, "
+						  "c.relpersistence, c.relreplident, am.amname, "
+						  "c.relisivm\n"
+						  "FROM pg_catalog.pg_class c\n "
+						  "LEFT JOIN pg_catalog.pg_class tc ON (c.reltoastrelid = tc.oid)\n"
+						  "LEFT JOIN pg_catalog.pg_am am ON (c.relam = am.oid)\n"
+						  "WHERE c.oid = '%s';",
+						  (verbose ?
+						   "pg_catalog.array_to_string(c.reloptions || "
+						   "array(select 'toast.' || x from pg_catalog.unnest(tc.reloptions) x), ', ')\n"
+						   : "''"),
+						  oid);
+	}
+	else if (pset.sversion >= 120000)
 	{
 		printfPQExpBuffer(&buf,
 						  "SELECT c.relchecks, c.relkind, c.relhasindex, c.relhasrules, "
@@ -1852,6 +1872,10 @@ describeOneTableDetails(const char *schemaname,
 			(char *) NULL : pg_strdup(PQgetvalue(res, 0, 14));
 	else
 		tableinfo.relam = NULL;
+	if (pset.sversion >= 150000)
+		tableinfo.isivm = strcmp(PQgetvalue(res, 0, 15), "t") == 0;
+	else
+		tableinfo.isivm = false;
 	PQclear(res);
 	res = NULL;
 
@@ -3652,6 +3676,12 @@ describeOneTableDetails(const char *schemaname,
 			printfPQExpBuffer(&buf, _("Access method: %s"), tableinfo.relam);
 			printTableAddFooter(&cont, buf.data);
 		}
+
+		/* Incremental view maintance info */
+		if (verbose && tableinfo.relkind == RELKIND_MATVIEW && tableinfo.isivm)
+		{
+			printTableAddFooter(&cont, _("Incremental view maintenance: yes"));
+		}
 	}
 
 	/* reloptions, if verbose */
diff --git a/src/bin/psql/tab-complete.c b/src/bin/psql/tab-complete.c
index 8e01f54500..4533fd75d9 100644
--- a/src/bin/psql/tab-complete.c
+++ b/src/bin/psql/tab-complete.c
@@ -1059,6 +1059,7 @@ static const pgsql_thing_t words_after_create[] = {
 	{"FOREIGN TABLE", NULL, NULL, NULL},
 	{"FUNCTION", NULL, NULL, Query_for_list_of_functions},
 	{"GROUP", Query_for_list_of_roles},
+	{"INCREMENTAL MATERIALIZED VIEW", NULL, NULL, &Query_for_list_of_matviews, THING_NO_DROP | THING_NO_ALTER},
 	{"INDEX", NULL, NULL, &Query_for_list_of_indexes},
 	{"LANGUAGE", Query_for_list_of_languages},
 	{"LARGE OBJECT", NULL, NULL, NULL, THING_NO_CREATE | THING_NO_DROP},
@@ -2783,7 +2784,7 @@ psql_completion(const char *text, int start, int end)
 		COMPLETE_WITH("SEQUENCE", "TABLE", "VIEW");
 	/* Complete "CREATE UNLOGGED" with TABLE or MATVIEW */
 	else if (TailMatches("CREATE", "UNLOGGED"))
-		COMPLETE_WITH("TABLE", "MATERIALIZED VIEW");
+		COMPLETE_WITH("TABLE", "MATERIALIZED VIEW", "INCREMENTAL MATERIALIZED VIEW");
 	/* Complete PARTITION BY with RANGE ( or LIST ( or ... */
 	else if (TailMatches("PARTITION", "BY"))
 		COMPLETE_WITH("RANGE (", "LIST (", "HASH (");
@@ -3082,13 +3083,16 @@ psql_completion(const char *text, int start, int end)
 		COMPLETE_WITH("SELECT");
 
 /* CREATE MATERIALIZED VIEW */
-	else if (Matches("CREATE", "MATERIALIZED"))
+	else if (Matches("CREATE", "MATERIALIZED") ||
+			 Matches("CREATE", "INCREMENTAL", "MATERIALIZED"))
 		COMPLETE_WITH("VIEW");
-	/* Complete CREATE MATERIALIZED VIEW <name> with AS */
-	else if (Matches("CREATE", "MATERIALIZED", "VIEW", MatchAny))
+	/* Complete CREATE MATERIALIZED VIEW <name> with AS  */
+	else if (Matches("CREATE", "MATERIALIZED", "VIEW", MatchAny) ||
+			 Matches("CREATE", "INCREMENTAL", "MATERIALIZED", "VIEW", MatchAny))
 		COMPLETE_WITH("AS");
 	/* Complete "CREATE MATERIALIZED VIEW <sth> AS with "SELECT" */
-	else if (Matches("CREATE", "MATERIALIZED", "VIEW", MatchAny, "AS"))
+	else if (Matches("CREATE", "MATERIALIZED", "VIEW", MatchAny, "AS") ||
+			 Matches("CREATE", "INCREMENTAL", "MATERIALIZED", "VIEW", MatchAny, "AS"))
 		COMPLETE_WITH("SELECT");
 
 /* CREATE EVENT TRIGGER */
-- 
2.17.1


--Multipart=_Fri__29_Oct_2021_18_16_28_+0900_jlYRKjywLqhZ7oyk
Content-Type: text/x-diff;
 name="v24-0007-Add-Incremental-View-Maintenance-support.patch"
Content-Disposition: attachment;
 filename="v24-0007-Add-Incremental-View-Maintenance-support.patch"
Content-Transfer-Encoding: 7bit



^ permalink  raw  reply  [nested|flat] 101+ messages in thread

* [PATCH v31 05/11] Add Incremental View Maintenance support to psql
@ 2019-12-20 01:21  Yugo Nagata <[email protected]>
  0 siblings, 0 replies; 101+ messages in thread

From: Yugo Nagata @ 2019-12-20 01:21 UTC (permalink / raw)

Add tab completion and meta-command output for IVM.
---
 src/bin/psql/describe.c     | 32 +++++++++++++++++++++++++++++++-
 src/bin/psql/tab-complete.c | 14 +++++++++-----
 2 files changed, 40 insertions(+), 6 deletions(-)

diff --git a/src/bin/psql/describe.c b/src/bin/psql/describe.c
index 6433497bcd..df559dce42 100644
--- a/src/bin/psql/describe.c
+++ b/src/bin/psql/describe.c
@@ -1574,6 +1574,7 @@ describeOneTableDetails(const char *schemaname,
 		char		relpersistence;
 		char		relreplident;
 		char	   *relam;
+		bool		isivm;
 	}			tableinfo;
 	bool		show_column_details = false;
 
@@ -1586,7 +1587,26 @@ describeOneTableDetails(const char *schemaname,
 	initPQExpBuffer(&tmpbuf);
 
 	/* Get general table info */
-	if (pset.sversion >= 120000)
+	if (pset.sversion >= 170000)
+	{
+		printfPQExpBuffer(&buf,
+						  "SELECT c.relchecks, c.relkind, c.relhasindex, c.relhasrules, "
+						  "c.relhastriggers, c.relrowsecurity, c.relforcerowsecurity, "
+						  "false AS relhasoids, c.relispartition, %s, c.reltablespace, "
+						  "CASE WHEN c.reloftype = 0 THEN '' ELSE c.reloftype::pg_catalog.regtype::pg_catalog.text END, "
+						  "c.relpersistence, c.relreplident, am.amname, "
+						  "c.relisivm\n"
+						  "FROM pg_catalog.pg_class c\n "
+						  "LEFT JOIN pg_catalog.pg_class tc ON (c.reltoastrelid = tc.oid)\n"
+						  "LEFT JOIN pg_catalog.pg_am am ON (c.relam = am.oid)\n"
+						  "WHERE c.oid = '%s';",
+						  (verbose ?
+						   "pg_catalog.array_to_string(c.reloptions || "
+						   "array(select 'toast.' || x from pg_catalog.unnest(tc.reloptions) x), ', ')\n"
+						   : "''"),
+						  oid);
+	}
+	else if (pset.sversion >= 120000)
 	{
 		printfPQExpBuffer(&buf,
 						  "SELECT c.relchecks, c.relkind, c.relhasindex, c.relhasrules, "
@@ -1706,6 +1726,10 @@ describeOneTableDetails(const char *schemaname,
 			(char *) NULL : pg_strdup(PQgetvalue(res, 0, 14));
 	else
 		tableinfo.relam = NULL;
+	if (pset.sversion >= 170000)
+		tableinfo.isivm = strcmp(PQgetvalue(res, 0, 15), "t") == 0;
+	else
+		tableinfo.isivm = false;
 	PQclear(res);
 	res = NULL;
 
@@ -3560,6 +3584,12 @@ describeOneTableDetails(const char *schemaname,
 			printfPQExpBuffer(&buf, _("Access method: %s"), tableinfo.relam);
 			printTableAddFooter(&cont, buf.data);
 		}
+
+		/* Incremental view maintance info */
+		if (verbose && tableinfo.relkind == RELKIND_MATVIEW && tableinfo.isivm)
+		{
+			printTableAddFooter(&cont, _("Incremental view maintenance: yes"));
+		}
 	}
 
 	/* reloptions, if verbose */
diff --git a/src/bin/psql/tab-complete.c b/src/bin/psql/tab-complete.c
index f121216ddc..946d47fa1f 100644
--- a/src/bin/psql/tab-complete.c
+++ b/src/bin/psql/tab-complete.c
@@ -1245,6 +1245,7 @@ static const pgsql_thing_t words_after_create[] = {
 	{"FOREIGN TABLE", NULL, NULL, NULL},
 	{"FUNCTION", NULL, NULL, Query_for_list_of_functions},
 	{"GROUP", Query_for_list_of_roles},
+	{"INCREMENTAL MATERIALIZED VIEW", NULL, NULL, &Query_for_list_of_matviews, NULL, THING_NO_DROP | THING_NO_ALTER},
 	{"INDEX", NULL, NULL, &Query_for_list_of_indexes},
 	{"LANGUAGE", Query_for_list_of_languages},
 	{"LARGE OBJECT", NULL, NULL, NULL, NULL, THING_NO_CREATE | THING_NO_DROP},
@@ -3256,7 +3257,7 @@ psql_completion(const char *text, int start, int end)
 		if (HeadMatches("CREATE", "SCHEMA"))
 			COMPLETE_WITH("TABLE", "SEQUENCE");
 		else
-			COMPLETE_WITH("TABLE", "SEQUENCE", "MATERIALIZED VIEW");
+			COMPLETE_WITH("TABLE", "SEQUENCE", "MATERIALIZED VIEW", "INCREMENTAL MATERIALIZED VIEW");
 	}
 	/* Complete PARTITION BY with RANGE ( or LIST ( or ... */
 	else if (TailMatches("PARTITION", "BY"))
@@ -3601,13 +3602,16 @@ psql_completion(const char *text, int start, int end)
 		COMPLETE_WITH("SELECT");
 
 /* CREATE MATERIALIZED VIEW */
-	else if (Matches("CREATE", "MATERIALIZED"))
+	else if (Matches("CREATE", "MATERIALIZED") ||
+			 Matches("CREATE", "INCREMENTAL", "MATERIALIZED"))
 		COMPLETE_WITH("VIEW");
-	/* Complete CREATE MATERIALIZED VIEW <name> with AS */
-	else if (Matches("CREATE", "MATERIALIZED", "VIEW", MatchAny))
+	/* Complete CREATE MATERIALIZED VIEW <name> with AS  */
+	else if (Matches("CREATE", "MATERIALIZED", "VIEW", MatchAny) ||
+			 Matches("CREATE", "INCREMENTAL", "MATERIALIZED", "VIEW", MatchAny))
 		COMPLETE_WITH("AS");
 	/* Complete "CREATE MATERIALIZED VIEW <sth> AS with "SELECT" */
-	else if (Matches("CREATE", "MATERIALIZED", "VIEW", MatchAny, "AS"))
+	else if (Matches("CREATE", "MATERIALIZED", "VIEW", MatchAny, "AS") ||
+			 Matches("CREATE", "INCREMENTAL", "MATERIALIZED", "VIEW", MatchAny, "AS"))
 		COMPLETE_WITH("SELECT");
 
 /* CREATE EVENT TRIGGER */
-- 
2.25.1


--Multipart=_Fri__29_Mar_2024_23_47_00_+0900_KGpmmDOIs1266Ib1
Content-Type: text/x-diff;
 name="v31-0006-Add-Incremental-View-Maintenance-support.patch"
Content-Disposition: attachment;
 filename="v31-0006-Add-Incremental-View-Maintenance-support.patch"
Content-Transfer-Encoding: 7bit



^ permalink  raw  reply  [nested|flat] 101+ messages in thread

* [PATCH v26 06/10] Add Incremental View Maintenance support to psql
@ 2019-12-20 01:21  Yugo Nagata <[email protected]>
  0 siblings, 0 replies; 101+ messages in thread

From: Yugo Nagata @ 2019-12-20 01:21 UTC (permalink / raw)

Add tab completion and meta-command output for IVM.
---
 src/bin/psql/describe.c     | 32 +++++++++++++++++++++++++++++++-
 src/bin/psql/tab-complete.c | 14 +++++++++-----
 2 files changed, 40 insertions(+), 6 deletions(-)

diff --git a/src/bin/psql/describe.c b/src/bin/psql/describe.c
index 9229eacb6d..b880f5fe77 100644
--- a/src/bin/psql/describe.c
+++ b/src/bin/psql/describe.c
@@ -1480,6 +1480,7 @@ describeOneTableDetails(const char *schemaname,
 		char		relpersistence;
 		char		relreplident;
 		char	   *relam;
+		bool		isivm;
 	}			tableinfo;
 	bool		show_column_details = false;
 
@@ -1492,7 +1493,26 @@ describeOneTableDetails(const char *schemaname,
 	initPQExpBuffer(&tmpbuf);
 
 	/* Get general table info */
-	if (pset.sversion >= 120000)
+	if (pset.sversion >= 150000)
+	{
+		printfPQExpBuffer(&buf,
+						  "SELECT c.relchecks, c.relkind, c.relhasindex, c.relhasrules, "
+						  "c.relhastriggers, c.relrowsecurity, c.relforcerowsecurity, "
+						  "false AS relhasoids, c.relispartition, %s, c.reltablespace, "
+						  "CASE WHEN c.reloftype = 0 THEN '' ELSE c.reloftype::pg_catalog.regtype::pg_catalog.text END, "
+						  "c.relpersistence, c.relreplident, am.amname, "
+						  "c.relisivm\n"
+						  "FROM pg_catalog.pg_class c\n "
+						  "LEFT JOIN pg_catalog.pg_class tc ON (c.reltoastrelid = tc.oid)\n"
+						  "LEFT JOIN pg_catalog.pg_am am ON (c.relam = am.oid)\n"
+						  "WHERE c.oid = '%s';",
+						  (verbose ?
+						   "pg_catalog.array_to_string(c.reloptions || "
+						   "array(select 'toast.' || x from pg_catalog.unnest(tc.reloptions) x), ', ')\n"
+						   : "''"),
+						  oid);
+	}
+	else if (pset.sversion >= 120000)
 	{
 		printfPQExpBuffer(&buf,
 						  "SELECT c.relchecks, c.relkind, c.relhasindex, c.relhasrules, "
@@ -1612,6 +1632,10 @@ describeOneTableDetails(const char *schemaname,
 			(char *) NULL : pg_strdup(PQgetvalue(res, 0, 14));
 	else
 		tableinfo.relam = NULL;
+	if (pset.sversion >= 150000)
+		tableinfo.isivm = strcmp(PQgetvalue(res, 0, 15), "t") == 0;
+	else
+		tableinfo.isivm = false;
 	PQclear(res);
 	res = NULL;
 
@@ -3397,6 +3421,12 @@ describeOneTableDetails(const char *schemaname,
 			printfPQExpBuffer(&buf, _("Access method: %s"), tableinfo.relam);
 			printTableAddFooter(&cont, buf.data);
 		}
+
+		/* Incremental view maintance info */
+		if (verbose && tableinfo.relkind == RELKIND_MATVIEW && tableinfo.isivm)
+		{
+			printTableAddFooter(&cont, _("Incremental view maintenance: yes"));
+		}
 	}
 
 	/* reloptions, if verbose */
diff --git a/src/bin/psql/tab-complete.c b/src/bin/psql/tab-complete.c
index 17172827a9..6ee7c356d4 100644
--- a/src/bin/psql/tab-complete.c
+++ b/src/bin/psql/tab-complete.c
@@ -1181,6 +1181,7 @@ static const pgsql_thing_t words_after_create[] = {
 	{"FOREIGN TABLE", NULL, NULL, NULL},
 	{"FUNCTION", NULL, NULL, Query_for_list_of_functions},
 	{"GROUP", Query_for_list_of_roles},
+	{"INCREMENTAL MATERIALIZED VIEW", NULL, NULL, &Query_for_list_of_matviews, NULL, THING_NO_DROP | THING_NO_ALTER},
 	{"INDEX", NULL, NULL, &Query_for_list_of_indexes},
 	{"LANGUAGE", Query_for_list_of_languages},
 	{"LARGE OBJECT", NULL, NULL, NULL, NULL, THING_NO_CREATE | THING_NO_DROP},
@@ -3021,7 +3022,7 @@ psql_completion(const char *text, int start, int end)
 		COMPLETE_WITH("SEQUENCE", "TABLE", "VIEW");
 	/* Complete "CREATE UNLOGGED" with TABLE or MATVIEW */
 	else if (TailMatches("CREATE", "UNLOGGED"))
-		COMPLETE_WITH("TABLE", "MATERIALIZED VIEW");
+		COMPLETE_WITH("TABLE", "MATERIALIZED VIEW", "INCREMENTAL MATERIALIZED VIEW");
 	/* Complete PARTITION BY with RANGE ( or LIST ( or ... */
 	else if (TailMatches("PARTITION", "BY"))
 		COMPLETE_WITH("RANGE (", "LIST (", "HASH (");
@@ -3337,13 +3338,16 @@ psql_completion(const char *text, int start, int end)
 		COMPLETE_WITH("SELECT");
 
 /* CREATE MATERIALIZED VIEW */
-	else if (Matches("CREATE", "MATERIALIZED"))
+	else if (Matches("CREATE", "MATERIALIZED") ||
+			 Matches("CREATE", "INCREMENTAL", "MATERIALIZED"))
 		COMPLETE_WITH("VIEW");
-	/* Complete CREATE MATERIALIZED VIEW <name> with AS */
-	else if (Matches("CREATE", "MATERIALIZED", "VIEW", MatchAny))
+	/* Complete CREATE MATERIALIZED VIEW <name> with AS  */
+	else if (Matches("CREATE", "MATERIALIZED", "VIEW", MatchAny) ||
+			 Matches("CREATE", "INCREMENTAL", "MATERIALIZED", "VIEW", MatchAny))
 		COMPLETE_WITH("AS");
 	/* Complete "CREATE MATERIALIZED VIEW <sth> AS with "SELECT" */
-	else if (Matches("CREATE", "MATERIALIZED", "VIEW", MatchAny, "AS"))
+	else if (Matches("CREATE", "MATERIALIZED", "VIEW", MatchAny, "AS") ||
+			 Matches("CREATE", "INCREMENTAL", "MATERIALIZED", "VIEW", MatchAny, "AS"))
 		COMPLETE_WITH("SELECT");
 
 /* CREATE EVENT TRIGGER */
-- 
2.17.1


--Multipart=_Mon__14_Mar_2022_19_12_17_+0900_E9HVp8j5QFkIIek.
Content-Type: text/x-diff;
 name="v26-0005-Add-Incremental-View-Maintenance-support-to-pg_d.patch"
Content-Disposition: attachment;
 filename="v26-0005-Add-Incremental-View-Maintenance-support-to-pg_d.patch"
Content-Transfer-Encoding: 7bit



^ permalink  raw  reply  [nested|flat] 101+ messages in thread

* [PATCH v23 06/15] Add Incremental View Maintenance support to psql
@ 2019-12-20 01:21  Yugo Nagata <[email protected]>
  0 siblings, 0 replies; 101+ messages in thread

From: Yugo Nagata @ 2019-12-20 01:21 UTC (permalink / raw)

Add tab completion and meta-command output for IVM.
---
 src/bin/psql/describe.c     | 32 +++++++++++++++++++++++++++++++-
 src/bin/psql/tab-complete.c | 14 +++++++++-----
 2 files changed, 40 insertions(+), 6 deletions(-)

diff --git a/src/bin/psql/describe.c b/src/bin/psql/describe.c
index ba658f731b..0518c88b5f 100644
--- a/src/bin/psql/describe.c
+++ b/src/bin/psql/describe.c
@@ -1657,6 +1657,7 @@ describeOneTableDetails(const char *schemaname,
 		char		relpersistence;
 		char		relreplident;
 		char	   *relam;
+		bool		isivm;
 	}			tableinfo;
 	bool		show_column_details = false;
 
@@ -1669,7 +1670,26 @@ describeOneTableDetails(const char *schemaname,
 	initPQExpBuffer(&tmpbuf);
 
 	/* Get general table info */
-	if (pset.sversion >= 120000)
+	if (pset.sversion >= 150000)
+	{
+		printfPQExpBuffer(&buf,
+						  "SELECT c.relchecks, c.relkind, c.relhasindex, c.relhasrules, "
+						  "c.relhastriggers, c.relrowsecurity, c.relforcerowsecurity, "
+						  "false AS relhasoids, c.relispartition, %s, c.reltablespace, "
+						  "CASE WHEN c.reloftype = 0 THEN '' ELSE c.reloftype::pg_catalog.regtype::pg_catalog.text END, "
+						  "c.relpersistence, c.relreplident, am.amname, "
+						  "c.relisivm\n"
+						  "FROM pg_catalog.pg_class c\n "
+						  "LEFT JOIN pg_catalog.pg_class tc ON (c.reltoastrelid = tc.oid)\n"
+						  "LEFT JOIN pg_catalog.pg_am am ON (c.relam = am.oid)\n"
+						  "WHERE c.oid = '%s';",
+						  (verbose ?
+						   "pg_catalog.array_to_string(c.reloptions || "
+						   "array(select 'toast.' || x from pg_catalog.unnest(tc.reloptions) x), ', ')\n"
+						   : "''"),
+						  oid);
+	}
+	else if (pset.sversion >= 120000)
 	{
 		printfPQExpBuffer(&buf,
 						  "SELECT c.relchecks, c.relkind, c.relhasindex, c.relhasrules, "
@@ -1853,6 +1873,10 @@ describeOneTableDetails(const char *schemaname,
 			(char *) NULL : pg_strdup(PQgetvalue(res, 0, 14));
 	else
 		tableinfo.relam = NULL;
+	if (pset.sversion >= 150000)
+		tableinfo.isivm = strcmp(PQgetvalue(res, 0, 15), "t") == 0;
+	else
+		tableinfo.isivm = false;
 	PQclear(res);
 	res = NULL;
 
@@ -3630,6 +3654,12 @@ describeOneTableDetails(const char *schemaname,
 			printfPQExpBuffer(&buf, _("Access method: %s"), tableinfo.relam);
 			printTableAddFooter(&cont, buf.data);
 		}
+
+		/* Incremental view maintance info */
+		if (verbose && tableinfo.relkind == RELKIND_MATVIEW && tableinfo.isivm)
+		{
+			printTableAddFooter(&cont, _("Incremental view maintenance: yes"));
+		}
 	}
 
 	/* reloptions, if verbose */
diff --git a/src/bin/psql/tab-complete.c b/src/bin/psql/tab-complete.c
index d6bf725971..9fb97596dc 100644
--- a/src/bin/psql/tab-complete.c
+++ b/src/bin/psql/tab-complete.c
@@ -1055,6 +1055,7 @@ static const pgsql_thing_t words_after_create[] = {
 	{"FOREIGN TABLE", NULL, NULL, NULL},
 	{"FUNCTION", NULL, NULL, Query_for_list_of_functions},
 	{"GROUP", Query_for_list_of_roles},
+	{"INCREMENTAL MATERIALIZED VIEW", NULL, NULL, &Query_for_list_of_matviews, THING_NO_DROP | THING_NO_ALTER},
 	{"INDEX", NULL, NULL, &Query_for_list_of_indexes},
 	{"LANGUAGE", Query_for_list_of_languages},
 	{"LARGE OBJECT", NULL, NULL, NULL, THING_NO_CREATE | THING_NO_DROP},
@@ -2698,7 +2699,7 @@ psql_completion(const char *text, int start, int end)
 		COMPLETE_WITH("SEQUENCE", "TABLE", "VIEW");
 	/* Complete "CREATE UNLOGGED" with TABLE or MATVIEW */
 	else if (TailMatches("CREATE", "UNLOGGED"))
-		COMPLETE_WITH("TABLE", "MATERIALIZED VIEW");
+		COMPLETE_WITH("TABLE", "MATERIALIZED VIEW", "INCREMENTAL MATERIALIZED VIEW");
 	/* Complete PARTITION BY with RANGE ( or LIST ( or ... */
 	else if (TailMatches("PARTITION", "BY"))
 		COMPLETE_WITH("RANGE (", "LIST (", "HASH (");
@@ -2997,13 +2998,16 @@ psql_completion(const char *text, int start, int end)
 		COMPLETE_WITH("SELECT");
 
 /* CREATE MATERIALIZED VIEW */
-	else if (Matches("CREATE", "MATERIALIZED"))
+	else if (Matches("CREATE", "MATERIALIZED") ||
+			 Matches("CREATE", "INCREMENTAL", "MATERIALIZED"))
 		COMPLETE_WITH("VIEW");
-	/* Complete CREATE MATERIALIZED VIEW <name> with AS */
-	else if (Matches("CREATE", "MATERIALIZED", "VIEW", MatchAny))
+	/* Complete CREATE MATERIALIZED VIEW <name> with AS  */
+	else if (Matches("CREATE", "MATERIALIZED", "VIEW", MatchAny) ||
+			 Matches("CREATE", "INCREMENTAL", "MATERIALIZED", "VIEW", MatchAny))
 		COMPLETE_WITH("AS");
 	/* Complete "CREATE MATERIALIZED VIEW <sth> AS with "SELECT" */
-	else if (Matches("CREATE", "MATERIALIZED", "VIEW", MatchAny, "AS"))
+	else if (Matches("CREATE", "MATERIALIZED", "VIEW", MatchAny, "AS") ||
+			 Matches("CREATE", "INCREMENTAL", "MATERIALIZED", "VIEW", MatchAny, "AS"))
 		COMPLETE_WITH("SELECT");
 
 /* CREATE EVENT TRIGGER */
-- 
2.17.1


--Multipart=_Mon__2_Aug_2021_15_28_34_+0900_wlHCjIpnD/FrGAKu
Content-Type: text/x-diff;
 name="v23-0007-Add-Incremental-View-Maintenance-support.patch"
Content-Disposition: attachment;
 filename="v23-0007-Add-Incremental-View-Maintenance-support.patch"
Content-Transfer-Encoding: 7bit



^ permalink  raw  reply  [nested|flat] 101+ messages in thread

* [PATCH v30 04/11] Add Incremental View Maintenance support to pg_dump
@ 2020-11-11 08:01  Yugo Nagata <[email protected]>
  0 siblings, 0 replies; 101+ messages in thread

From: Yugo Nagata @ 2020-11-11 08:01 UTC (permalink / raw)

Support CREATE INCREMENTAL MATERIALIZED VIEW syntax.
---
 src/bin/pg_dump/pg_dump.c        | 18 +++++++++++++++---
 src/bin/pg_dump/pg_dump.h        |  2 ++
 src/bin/pg_dump/t/002_pg_dump.pl | 18 ++++++++++++++++++
 3 files changed, 35 insertions(+), 3 deletions(-)

diff --git a/src/bin/pg_dump/pg_dump.c b/src/bin/pg_dump/pg_dump.c
index 2225a12718..009958fdd4 100644
--- a/src/bin/pg_dump/pg_dump.c
+++ b/src/bin/pg_dump/pg_dump.c
@@ -6648,6 +6648,7 @@ getTables(Archive *fout, int *numTables)
 	int			i_relacl;
 	int			i_acldefault;
 	int			i_ispartition;
+	int			i_isivm;
 
 	/*
 	 * Find all the tables and table-like objects.
@@ -6750,10 +6751,17 @@ getTables(Archive *fout, int *numTables)
 
 	if (fout->remoteVersion >= 100000)
 		appendPQExpBufferStr(query,
-							 "c.relispartition AS ispartition ");
+							 "c.relispartition AS ispartition, ");
 	else
 		appendPQExpBufferStr(query,
-							 "false AS ispartition ");
+							 "false AS ispartition, ");
+
+	if (fout->remoteVersion >= 170000)
+		appendPQExpBufferStr(query,
+							 "c.relisivm AS isivm ");
+	else
+		appendPQExpBufferStr(query,
+							 "false AS isivm ");
 
 	/*
 	 * Left join to pg_depend to pick up dependency info linking sequences to
@@ -6862,6 +6870,7 @@ getTables(Archive *fout, int *numTables)
 	i_relacl = PQfnumber(res, "relacl");
 	i_acldefault = PQfnumber(res, "acldefault");
 	i_ispartition = PQfnumber(res, "ispartition");
+	i_isivm = PQfnumber(res, "isivm");
 
 	if (dopt->lockWaitTimeout)
 	{
@@ -6941,6 +6950,7 @@ getTables(Archive *fout, int *numTables)
 			tblinfo[i].amname = pg_strdup(PQgetvalue(res, i, i_amname));
 		tblinfo[i].is_identity_sequence = (strcmp(PQgetvalue(res, i, i_is_identity_sequence), "t") == 0);
 		tblinfo[i].ispartition = (strcmp(PQgetvalue(res, i, i_ispartition), "t") == 0);
+		tblinfo[i].isivm = (strcmp(PQgetvalue(res, i, i_isivm), "t") == 0);
 
 		/* other fields were zeroed above */
 
@@ -15977,9 +15987,11 @@ dumpTableSchema(Archive *fout, const TableInfo *tbinfo)
 			binary_upgrade_set_pg_class_oids(fout, q,
 											 tbinfo->dobj.catId.oid, false);
 
-		appendPQExpBuffer(q, "CREATE %s%s %s",
+		appendPQExpBuffer(q, "CREATE %s%s%s %s",
 						  tbinfo->relpersistence == RELPERSISTENCE_UNLOGGED ?
 						  "UNLOGGED " : "",
+						  tbinfo->relkind == RELKIND_MATVIEW && tbinfo->isivm ?
+						  "INCREMENTAL " : "",
 						  reltypename,
 						  qualrelname);
 
diff --git a/src/bin/pg_dump/pg_dump.h b/src/bin/pg_dump/pg_dump.h
index 77db42e354..7f05cbaec6 100644
--- a/src/bin/pg_dump/pg_dump.h
+++ b/src/bin/pg_dump/pg_dump.h
@@ -325,6 +325,8 @@ typedef struct _tableInfo
 	int			numParents;		/* number of (immediate) parent tables */
 	struct _tableInfo **parents;	/* TableInfos of immediate parents */
 
+	bool		isivm;			/* is incrementally maintainable materialized view? */
+
 	/*
 	 * These fields are computed only if we decide the table is interesting
 	 * (it's either a table to dump, or a direct parent of a dumpable table).
diff --git a/src/bin/pg_dump/t/002_pg_dump.pl b/src/bin/pg_dump/t/002_pg_dump.pl
index 00b5092713..fff9419347 100644
--- a/src/bin/pg_dump/t/002_pg_dump.pl
+++ b/src/bin/pg_dump/t/002_pg_dump.pl
@@ -2832,6 +2832,24 @@ my %tests = (
 		},
 	},
 
+	'CREATE MATERIALIZED VIEW matview_ivm' => {
+		create_order => 21,
+		create_sql   => 'CREATE INCREMENTAL MATERIALIZED VIEW dump_test.matview_ivm (col1) AS
+					   SELECT col1 FROM dump_test.test_table;',
+		regexp => qr/^
+			\QCREATE INCREMENTAL MATERIALIZED VIEW dump_test.matview_ivm AS\E
+			\n\s+\QSELECT col1\E
+			\n\s+\QFROM dump_test.test_table\E
+			\n\s+\QWITH NO DATA;\E
+			/xm,
+		like =>
+		  { %full_runs, %dump_test_schema_runs, section_pre_data => 1, },
+		unlike => {
+			exclude_dump_test_schema => 1,
+			only_dump_measurement => 1,
+		},
+	},
+
 	'CREATE POLICY p1 ON test_table' => {
 		create_order => 22,
 		create_sql => 'CREATE POLICY p1 ON dump_test.test_table
-- 
2.25.1


--Multipart=_Mon__4_Mar_2024_11_58_46_+0900_UaponF/qQhQrVCFt
Content-Type: text/x-diff;
 name="v30-0005-Add-Incremental-View-Maintenance-support-to-psql.patch"
Content-Disposition: attachment;
 filename="v30-0005-Add-Incremental-View-Maintenance-support-to-psql.patch"
Content-Transfer-Encoding: 7bit



^ permalink  raw  reply  [nested|flat] 101+ messages in thread

* [PATCH v37 04/11] Add Incremental View Maintenance support to pg_dump
@ 2020-11-11 08:01  Yugo Nagata <[email protected]>
  0 siblings, 0 replies; 101+ messages in thread

From: Yugo Nagata @ 2020-11-11 08:01 UTC (permalink / raw)

Support CREATE INCREMENTAL MATERIALIZED VIEW syntax.
---
 src/bin/pg_dump/pg_dump.c        | 18 +++++++++++++++---
 src/bin/pg_dump/pg_dump.h        |  2 ++
 src/bin/pg_dump/t/002_pg_dump.pl | 18 ++++++++++++++++++
 3 files changed, 35 insertions(+), 3 deletions(-)

diff --git a/src/bin/pg_dump/pg_dump.c b/src/bin/pg_dump/pg_dump.c
index d56dcc701ce..b1d37675f66 100644
--- a/src/bin/pg_dump/pg_dump.c
+++ b/src/bin/pg_dump/pg_dump.c
@@ -7323,6 +7323,7 @@ getTables(Archive *fout, int *numTables)
 	int			i_relacl;
 	int			i_acldefault;
 	int			i_ispartition;
+	int			i_isivm;
 
 	/*
 	 * Find all the tables and table-like objects.
@@ -7432,10 +7433,17 @@ getTables(Archive *fout, int *numTables)
 
 	if (fout->remoteVersion >= 100000)
 		appendPQExpBufferStr(query,
-							 "c.relispartition AS ispartition ");
+							 "c.relispartition AS ispartition, ");
 	else
 		appendPQExpBufferStr(query,
-							 "false AS ispartition ");
+							 "false AS ispartition, ");
+
+	if (fout->remoteVersion >= 180000)
+		appendPQExpBufferStr(query,
+							 "c.relisivm AS isivm ");
+	else
+		appendPQExpBufferStr(query,
+							 "false AS isivm ");
 
 	/*
 	 * Left join to pg_depend to pick up dependency info linking sequences to
@@ -7548,6 +7556,7 @@ getTables(Archive *fout, int *numTables)
 	i_relacl = PQfnumber(res, "relacl");
 	i_acldefault = PQfnumber(res, "acldefault");
 	i_ispartition = PQfnumber(res, "ispartition");
+	i_isivm = PQfnumber(res, "isivm");
 
 	if (dopt->lockWaitTimeout)
 	{
@@ -7630,6 +7639,7 @@ getTables(Archive *fout, int *numTables)
 			tblinfo[i].amname = pg_strdup(PQgetvalue(res, i, i_amname));
 		tblinfo[i].is_identity_sequence = (strcmp(PQgetvalue(res, i, i_is_identity_sequence), "t") == 0);
 		tblinfo[i].ispartition = (strcmp(PQgetvalue(res, i, i_ispartition), "t") == 0);
+		tblinfo[i].isivm = (strcmp(PQgetvalue(res, i, i_isivm), "t") == 0);
 
 		/* other fields were zeroed above */
 
@@ -17452,10 +17462,12 @@ dumpTableSchema(Archive *fout, const TableInfo *tbinfo)
 		 * PostgreSQL 18 has disabled UNLOGGED for partitioned tables, so
 		 * ignore it when dumping if it was set in this case.
 		 */
-		appendPQExpBuffer(q, "CREATE %s%s %s",
+		appendPQExpBuffer(q, "CREATE %s%s%s %s",
 						  (tbinfo->relpersistence == RELPERSISTENCE_UNLOGGED &&
 						   tbinfo->relkind != RELKIND_PARTITIONED_TABLE) ?
 						  "UNLOGGED " : "",
+						  tbinfo->relkind == RELKIND_MATVIEW && tbinfo->isivm ?
+						  "INCREMENTAL " : "",
 						  reltypename,
 						  qualrelname);
 
diff --git a/src/bin/pg_dump/pg_dump.h b/src/bin/pg_dump/pg_dump.h
index 5a6726d8b12..4408c504323 100644
--- a/src/bin/pg_dump/pg_dump.h
+++ b/src/bin/pg_dump/pg_dump.h
@@ -347,6 +347,8 @@ typedef struct _tableInfo
 	int			numParents;		/* number of (immediate) parent tables */
 	struct _tableInfo **parents;	/* TableInfos of immediate parents */
 
+	bool		isivm;			/* is incrementally maintainable materialized view? */
+
 	/*
 	 * These fields are computed only if we decide the table is interesting
 	 * (it's either a table to dump, or a direct parent of a dumpable table).
diff --git a/src/bin/pg_dump/t/002_pg_dump.pl b/src/bin/pg_dump/t/002_pg_dump.pl
index 3ee9fda50e4..7c38d3023f0 100644
--- a/src/bin/pg_dump/t/002_pg_dump.pl
+++ b/src/bin/pg_dump/t/002_pg_dump.pl
@@ -2992,6 +2992,24 @@ my %tests = (
 		},
 	},
 
+	'CREATE MATERIALIZED VIEW matview_ivm' => {
+		create_order => 21,
+		create_sql   => 'CREATE INCREMENTAL MATERIALIZED VIEW dump_test.matview_ivm (col1) AS
+					   SELECT col1 FROM dump_test.test_table;',
+		regexp => qr/^
+			\QCREATE INCREMENTAL MATERIALIZED VIEW dump_test.matview_ivm AS\E
+			\n\s+\QSELECT col1\E
+			\n\s+\QFROM dump_test.test_table\E
+			\n\s+\QWITH NO DATA;\E
+			/xm,
+		like =>
+		  { %full_runs, %dump_test_schema_runs, section_pre_data => 1, },
+		unlike => {
+			exclude_dump_test_schema => 1,
+			only_dump_measurement => 1,
+		},
+	},
+
 	'CREATE POLICY p1 ON test_table' => {
 		create_order => 22,
 		create_sql => 'CREATE POLICY p1 ON dump_test.test_table
-- 
2.43.0


--Multipart=_Fri__29_May_2026_23_14_17_+0900_Te0o73X2VqYK57Gd
Content-Type: text/x-diff;
 name="v37-0003-Allow-to-prolong-life-span-of-transition-tables-.patch"
Content-Disposition: attachment;
 filename="v37-0003-Allow-to-prolong-life-span-of-transition-tables-.patch"
Content-Transfer-Encoding: 7bit



^ permalink  raw  reply  [nested|flat] 101+ messages in thread

* [PATCH v30 04/11] Add Incremental View Maintenance support to pg_dump
@ 2020-11-11 08:01  Yugo Nagata <[email protected]>
  0 siblings, 0 replies; 101+ messages in thread

From: Yugo Nagata @ 2020-11-11 08:01 UTC (permalink / raw)

Support CREATE INCREMENTAL MATERIALIZED VIEW syntax.
---
 src/bin/pg_dump/pg_dump.c        | 18 +++++++++++++++---
 src/bin/pg_dump/pg_dump.h        |  2 ++
 src/bin/pg_dump/t/002_pg_dump.pl | 18 ++++++++++++++++++
 3 files changed, 35 insertions(+), 3 deletions(-)

diff --git a/src/bin/pg_dump/pg_dump.c b/src/bin/pg_dump/pg_dump.c
index 2225a12718..009958fdd4 100644
--- a/src/bin/pg_dump/pg_dump.c
+++ b/src/bin/pg_dump/pg_dump.c
@@ -6648,6 +6648,7 @@ getTables(Archive *fout, int *numTables)
 	int			i_relacl;
 	int			i_acldefault;
 	int			i_ispartition;
+	int			i_isivm;
 
 	/*
 	 * Find all the tables and table-like objects.
@@ -6750,10 +6751,17 @@ getTables(Archive *fout, int *numTables)
 
 	if (fout->remoteVersion >= 100000)
 		appendPQExpBufferStr(query,
-							 "c.relispartition AS ispartition ");
+							 "c.relispartition AS ispartition, ");
 	else
 		appendPQExpBufferStr(query,
-							 "false AS ispartition ");
+							 "false AS ispartition, ");
+
+	if (fout->remoteVersion >= 170000)
+		appendPQExpBufferStr(query,
+							 "c.relisivm AS isivm ");
+	else
+		appendPQExpBufferStr(query,
+							 "false AS isivm ");
 
 	/*
 	 * Left join to pg_depend to pick up dependency info linking sequences to
@@ -6862,6 +6870,7 @@ getTables(Archive *fout, int *numTables)
 	i_relacl = PQfnumber(res, "relacl");
 	i_acldefault = PQfnumber(res, "acldefault");
 	i_ispartition = PQfnumber(res, "ispartition");
+	i_isivm = PQfnumber(res, "isivm");
 
 	if (dopt->lockWaitTimeout)
 	{
@@ -6941,6 +6950,7 @@ getTables(Archive *fout, int *numTables)
 			tblinfo[i].amname = pg_strdup(PQgetvalue(res, i, i_amname));
 		tblinfo[i].is_identity_sequence = (strcmp(PQgetvalue(res, i, i_is_identity_sequence), "t") == 0);
 		tblinfo[i].ispartition = (strcmp(PQgetvalue(res, i, i_ispartition), "t") == 0);
+		tblinfo[i].isivm = (strcmp(PQgetvalue(res, i, i_isivm), "t") == 0);
 
 		/* other fields were zeroed above */
 
@@ -15977,9 +15987,11 @@ dumpTableSchema(Archive *fout, const TableInfo *tbinfo)
 			binary_upgrade_set_pg_class_oids(fout, q,
 											 tbinfo->dobj.catId.oid, false);
 
-		appendPQExpBuffer(q, "CREATE %s%s %s",
+		appendPQExpBuffer(q, "CREATE %s%s%s %s",
 						  tbinfo->relpersistence == RELPERSISTENCE_UNLOGGED ?
 						  "UNLOGGED " : "",
+						  tbinfo->relkind == RELKIND_MATVIEW && tbinfo->isivm ?
+						  "INCREMENTAL " : "",
 						  reltypename,
 						  qualrelname);
 
diff --git a/src/bin/pg_dump/pg_dump.h b/src/bin/pg_dump/pg_dump.h
index 77db42e354..7f05cbaec6 100644
--- a/src/bin/pg_dump/pg_dump.h
+++ b/src/bin/pg_dump/pg_dump.h
@@ -325,6 +325,8 @@ typedef struct _tableInfo
 	int			numParents;		/* number of (immediate) parent tables */
 	struct _tableInfo **parents;	/* TableInfos of immediate parents */
 
+	bool		isivm;			/* is incrementally maintainable materialized view? */
+
 	/*
 	 * These fields are computed only if we decide the table is interesting
 	 * (it's either a table to dump, or a direct parent of a dumpable table).
diff --git a/src/bin/pg_dump/t/002_pg_dump.pl b/src/bin/pg_dump/t/002_pg_dump.pl
index 00b5092713..fff9419347 100644
--- a/src/bin/pg_dump/t/002_pg_dump.pl
+++ b/src/bin/pg_dump/t/002_pg_dump.pl
@@ -2832,6 +2832,24 @@ my %tests = (
 		},
 	},
 
+	'CREATE MATERIALIZED VIEW matview_ivm' => {
+		create_order => 21,
+		create_sql   => 'CREATE INCREMENTAL MATERIALIZED VIEW dump_test.matview_ivm (col1) AS
+					   SELECT col1 FROM dump_test.test_table;',
+		regexp => qr/^
+			\QCREATE INCREMENTAL MATERIALIZED VIEW dump_test.matview_ivm AS\E
+			\n\s+\QSELECT col1\E
+			\n\s+\QFROM dump_test.test_table\E
+			\n\s+\QWITH NO DATA;\E
+			/xm,
+		like =>
+		  { %full_runs, %dump_test_schema_runs, section_pre_data => 1, },
+		unlike => {
+			exclude_dump_test_schema => 1,
+			only_dump_measurement => 1,
+		},
+	},
+
 	'CREATE POLICY p1 ON test_table' => {
 		create_order => 22,
 		create_sql => 'CREATE POLICY p1 ON dump_test.test_table
-- 
2.25.1


--Multipart=_Mon__4_Mar_2024_11_58_46_+0900_UaponF/qQhQrVCFt
Content-Type: text/x-diff;
 name="v30-0005-Add-Incremental-View-Maintenance-support-to-psql.patch"
Content-Disposition: attachment;
 filename="v30-0005-Add-Incremental-View-Maintenance-support-to-psql.patch"
Content-Transfer-Encoding: 7bit



^ permalink  raw  reply  [nested|flat] 101+ messages in thread

* [PATCH v38 04/11] Add Incremental View Maintenance support to pg_dump
@ 2020-11-11 08:01  Yugo Nagata <[email protected]>
  0 siblings, 0 replies; 101+ messages in thread

From: Yugo Nagata @ 2020-11-11 08:01 UTC (permalink / raw)

Support CREATE INCREMENTAL MATERIALIZED VIEW syntax.
---
 src/bin/pg_dump/pg_dump.c        | 18 +++++++++++++++---
 src/bin/pg_dump/pg_dump.h        |  2 ++
 src/bin/pg_dump/t/002_pg_dump.pl | 18 ++++++++++++++++++
 3 files changed, 35 insertions(+), 3 deletions(-)

diff --git a/src/bin/pg_dump/pg_dump.c b/src/bin/pg_dump/pg_dump.c
index c56437d6057..f7420e0db41 100644
--- a/src/bin/pg_dump/pg_dump.c
+++ b/src/bin/pg_dump/pg_dump.c
@@ -7323,6 +7323,7 @@ getTables(Archive *fout, int *numTables)
 	int			i_relacl;
 	int			i_acldefault;
 	int			i_ispartition;
+	int			i_isivm;
 
 	/*
 	 * Find all the tables and table-like objects.
@@ -7432,10 +7433,17 @@ getTables(Archive *fout, int *numTables)
 
 	if (fout->remoteVersion >= 100000)
 		appendPQExpBufferStr(query,
-							 "c.relispartition AS ispartition ");
+							 "c.relispartition AS ispartition, ");
 	else
 		appendPQExpBufferStr(query,
-							 "false AS ispartition ");
+							 "false AS ispartition, ");
+
+	if (fout->remoteVersion >= 200000)
+		appendPQExpBufferStr(query,
+							 "c.relisivm AS isivm ");
+	else
+		appendPQExpBufferStr(query,
+							 "false AS isivm ");
 
 	/*
 	 * Left join to pg_depend to pick up dependency info linking sequences to
@@ -7548,6 +7556,7 @@ getTables(Archive *fout, int *numTables)
 	i_relacl = PQfnumber(res, "relacl");
 	i_acldefault = PQfnumber(res, "acldefault");
 	i_ispartition = PQfnumber(res, "ispartition");
+	i_isivm = PQfnumber(res, "isivm");
 
 	if (dopt->lockWaitTimeout)
 	{
@@ -7630,6 +7639,7 @@ getTables(Archive *fout, int *numTables)
 			tblinfo[i].amname = pg_strdup(PQgetvalue(res, i, i_amname));
 		tblinfo[i].is_identity_sequence = (strcmp(PQgetvalue(res, i, i_is_identity_sequence), "t") == 0);
 		tblinfo[i].ispartition = (strcmp(PQgetvalue(res, i, i_ispartition), "t") == 0);
+		tblinfo[i].isivm = (strcmp(PQgetvalue(res, i, i_isivm), "t") == 0);
 
 		/* other fields were zeroed above */
 
@@ -17452,10 +17462,12 @@ dumpTableSchema(Archive *fout, const TableInfo *tbinfo)
 		 * PostgreSQL 18 has disabled UNLOGGED for partitioned tables, so
 		 * ignore it when dumping if it was set in this case.
 		 */
-		appendPQExpBuffer(q, "CREATE %s%s %s",
+		appendPQExpBuffer(q, "CREATE %s%s%s %s",
 						  (tbinfo->relpersistence == RELPERSISTENCE_UNLOGGED &&
 						   tbinfo->relkind != RELKIND_PARTITIONED_TABLE) ?
 						  "UNLOGGED " : "",
+						  tbinfo->relkind == RELKIND_MATVIEW && tbinfo->isivm ?
+						  "INCREMENTAL " : "",
 						  reltypename,
 						  qualrelname);
 
diff --git a/src/bin/pg_dump/pg_dump.h b/src/bin/pg_dump/pg_dump.h
index 5a6726d8b12..4408c504323 100644
--- a/src/bin/pg_dump/pg_dump.h
+++ b/src/bin/pg_dump/pg_dump.h
@@ -347,6 +347,8 @@ typedef struct _tableInfo
 	int			numParents;		/* number of (immediate) parent tables */
 	struct _tableInfo **parents;	/* TableInfos of immediate parents */
 
+	bool		isivm;			/* is incrementally maintainable materialized view? */
+
 	/*
 	 * These fields are computed only if we decide the table is interesting
 	 * (it's either a table to dump, or a direct parent of a dumpable table).
diff --git a/src/bin/pg_dump/t/002_pg_dump.pl b/src/bin/pg_dump/t/002_pg_dump.pl
index 9258948b583..8abde57e4f3 100644
--- a/src/bin/pg_dump/t/002_pg_dump.pl
+++ b/src/bin/pg_dump/t/002_pg_dump.pl
@@ -3033,6 +3033,24 @@ my %tests = (
 		},
 	},
 
+	'CREATE MATERIALIZED VIEW matview_ivm' => {
+		create_order => 21,
+		create_sql   => 'CREATE INCREMENTAL MATERIALIZED VIEW dump_test.matview_ivm (col1) AS
+					   SELECT col1 FROM dump_test.test_table;',
+		regexp => qr/^
+			\QCREATE INCREMENTAL MATERIALIZED VIEW dump_test.matview_ivm AS\E
+			\n\s+\QSELECT col1\E
+			\n\s+\QFROM dump_test.test_table\E
+			\n\s+\QWITH NO DATA;\E
+			/xm,
+		like =>
+		  { %full_runs, %dump_test_schema_runs, section_pre_data => 1, },
+		unlike => {
+			exclude_dump_test_schema => 1,
+			only_dump_measurement => 1,
+		},
+	},
+
 	'CREATE POLICY p1 ON test_table' => {
 		create_order => 22,
 		create_sql => 'CREATE POLICY p1 ON dump_test.test_table
-- 
2.43.0


--Multipart=_Wed__1_Jul_2026_00_04_01_+0900_OVSy2WWK_9aByzDJ
Content-Type: text/x-diff;
 name="v38-0003-Allow-to-prolong-life-span-of-transition-tables-.patch"
Content-Disposition: attachment;
 filename="v38-0003-Allow-to-prolong-life-span-of-transition-tables-.patch"
Content-Transfer-Encoding: 7bit



^ permalink  raw  reply  [nested|flat] 101+ messages in thread

* [PATCH v39 4/8] Add Incremental View Maintenance support to pg_dump
@ 2020-11-11 08:01  Yugo Nagata <[email protected]>
  0 siblings, 0 replies; 101+ messages in thread

From: Yugo Nagata @ 2020-11-11 08:01 UTC (permalink / raw)

Support CREATE INCREMENTAL MATERIALIZED VIEW syntax.
---
 src/bin/pg_dump/pg_dump.c        | 14 +++++++++++++-
 src/bin/pg_dump/pg_dump.h        |  2 ++
 src/bin/pg_dump/t/002_pg_dump.pl | 18 ++++++++++++++++++
 3 files changed, 33 insertions(+), 1 deletion(-)

diff --git a/src/bin/pg_dump/pg_dump.c b/src/bin/pg_dump/pg_dump.c
index f67daf85911..9a5f65659e3 100644
--- a/src/bin/pg_dump/pg_dump.c
+++ b/src/bin/pg_dump/pg_dump.c
@@ -7196,6 +7196,7 @@ getTables(Archive *fout, int *numTables)
 	int			i_relacl;
 	int			i_acldefault;
 	int			i_ispartition;
+	int			i_isivm;
 
 	/*
 	 * Find all the tables and table-like objects.
@@ -7277,6 +7278,13 @@ getTables(Archive *fout, int *numTables)
 	appendPQExpBufferStr(query,
 						 "c.relispartition AS ispartition ");
 
+	if (fout->remoteVersion >= 200000)
+		appendPQExpBufferStr(query,
+							 "c.relisivm AS isivm ");
+	else
+		appendPQExpBufferStr(query,
+							 "false AS isivm ");
+
 	/*
 	 * Left join to pg_depend to pick up dependency info linking sequences to
 	 * their owning column, if any (note this dependency is AUTO except for
@@ -7387,6 +7395,7 @@ getTables(Archive *fout, int *numTables)
 	i_relacl = PQfnumber(res, "relacl");
 	i_acldefault = PQfnumber(res, "acldefault");
 	i_ispartition = PQfnumber(res, "ispartition");
+	i_isivm = PQfnumber(res, "isivm");
 
 	if (dopt->lockWaitTimeout)
 	{
@@ -7469,6 +7478,7 @@ getTables(Archive *fout, int *numTables)
 			tblinfo[i].amname = pg_strdup(PQgetvalue(res, i, i_amname));
 		tblinfo[i].is_identity_sequence = (strcmp(PQgetvalue(res, i, i_is_identity_sequence), "t") == 0);
 		tblinfo[i].ispartition = (strcmp(PQgetvalue(res, i, i_ispartition), "t") == 0);
+		tblinfo[i].isivm = (strcmp(PQgetvalue(res, i, i_isivm), "t") == 0);
 
 		/* other fields were zeroed above */
 
@@ -17202,10 +17212,12 @@ dumpTableSchema(Archive *fout, const TableInfo *tbinfo)
 		 * PostgreSQL 18 has disabled UNLOGGED for partitioned tables, so
 		 * ignore it when dumping if it was set in this case.
 		 */
-		appendPQExpBuffer(q, "CREATE %s%s %s",
+		appendPQExpBuffer(q, "CREATE %s%s%s %s",
 						  (tbinfo->relpersistence == RELPERSISTENCE_UNLOGGED &&
 						   tbinfo->relkind != RELKIND_PARTITIONED_TABLE) ?
 						  "UNLOGGED " : "",
+						  tbinfo->relkind == RELKIND_MATVIEW && tbinfo->isivm ?
+						  "INCREMENTAL " : "",
 						  reltypename,
 						  qualrelname);
 
diff --git a/src/bin/pg_dump/pg_dump.h b/src/bin/pg_dump/pg_dump.h
index 5a6726d8b12..4408c504323 100644
--- a/src/bin/pg_dump/pg_dump.h
+++ b/src/bin/pg_dump/pg_dump.h
@@ -347,6 +347,8 @@ typedef struct _tableInfo
 	int			numParents;		/* number of (immediate) parent tables */
 	struct _tableInfo **parents;	/* TableInfos of immediate parents */
 
+	bool		isivm;			/* is incrementally maintainable materialized view? */
+
 	/*
 	 * These fields are computed only if we decide the table is interesting
 	 * (it's either a table to dump, or a direct parent of a dumpable table).
diff --git a/src/bin/pg_dump/t/002_pg_dump.pl b/src/bin/pg_dump/t/002_pg_dump.pl
index 9258948b583..8abde57e4f3 100644
--- a/src/bin/pg_dump/t/002_pg_dump.pl
+++ b/src/bin/pg_dump/t/002_pg_dump.pl
@@ -3033,6 +3033,24 @@ my %tests = (
 		},
 	},
 
+	'CREATE MATERIALIZED VIEW matview_ivm' => {
+		create_order => 21,
+		create_sql   => 'CREATE INCREMENTAL MATERIALIZED VIEW dump_test.matview_ivm (col1) AS
+					   SELECT col1 FROM dump_test.test_table;',
+		regexp => qr/^
+			\QCREATE INCREMENTAL MATERIALIZED VIEW dump_test.matview_ivm AS\E
+			\n\s+\QSELECT col1\E
+			\n\s+\QFROM dump_test.test_table\E
+			\n\s+\QWITH NO DATA;\E
+			/xm,
+		like =>
+		  { %full_runs, %dump_test_schema_runs, section_pre_data => 1, },
+		unlike => {
+			exclude_dump_test_schema => 1,
+			only_dump_measurement => 1,
+		},
+	},
+
 	'CREATE POLICY p1 ON test_table' => {
 		create_order => 22,
 		create_sql => 'CREATE POLICY p1 ON dump_test.test_table
-- 
2.43.0


--Multipart=_Fri__3_Jul_2026_19_11_16_+0900_CskxSIu_iGcDMEyM
Content-Type: text/x-diff;
 name="v39-0003-Allow-to-prolong-life-span-of-transition-tables-.patch"
Content-Disposition: attachment;
 filename="v39-0003-Allow-to-prolong-life-span-of-transition-tables-.patch"
Content-Transfer-Encoding: 7bit



^ permalink  raw  reply  [nested|flat] 101+ messages in thread

* [PATCH v28 04/11] Add Incremental View Maintenance support to pg_dump
@ 2020-11-11 08:01  Yugo Nagata <[email protected]>
  0 siblings, 0 replies; 101+ messages in thread

From: Yugo Nagata @ 2020-11-11 08:01 UTC (permalink / raw)

Support CREATE INCREMENTAL MATERIALIZED VIEW syntax.
---
 src/bin/pg_dump/pg_dump.c        | 18 +++++++++++++++---
 src/bin/pg_dump/pg_dump.h        |  1 +
 src/bin/pg_dump/t/002_pg_dump.pl | 15 +++++++++++++++
 3 files changed, 31 insertions(+), 3 deletions(-)

diff --git a/src/bin/pg_dump/pg_dump.c b/src/bin/pg_dump/pg_dump.c
index 3af97a6039..48f61b1af8 100644
--- a/src/bin/pg_dump/pg_dump.c
+++ b/src/bin/pg_dump/pg_dump.c
@@ -6352,6 +6352,7 @@ getTables(Archive *fout, int *numTables)
 	int			i_relacl;
 	int			i_acldefault;
 	int			i_ispartition;
+	int			i_isivm;
 
 	/*
 	 * Find all the tables and table-like objects.
@@ -6454,10 +6455,17 @@ getTables(Archive *fout, int *numTables)
 
 	if (fout->remoteVersion >= 100000)
 		appendPQExpBufferStr(query,
-							 "c.relispartition AS ispartition ");
+							 "c.relispartition AS ispartition, ");
 	else
 		appendPQExpBufferStr(query,
-							 "false AS ispartition ");
+							 "false AS ispartition, ");
+
+	if (fout->remoteVersion >= 170000)
+		appendPQExpBufferStr(query,
+							 "c.relisivm AS isivm ");
+	else
+		appendPQExpBufferStr(query,
+							 "false AS isivm ");
 
 	/*
 	 * Left join to pg_depend to pick up dependency info linking sequences to
@@ -6566,6 +6574,7 @@ getTables(Archive *fout, int *numTables)
 	i_relacl = PQfnumber(res, "relacl");
 	i_acldefault = PQfnumber(res, "acldefault");
 	i_ispartition = PQfnumber(res, "ispartition");
+	i_isivm = PQfnumber(res, "isivm");
 
 	if (dopt->lockWaitTimeout)
 	{
@@ -6645,6 +6654,7 @@ getTables(Archive *fout, int *numTables)
 			tblinfo[i].amname = pg_strdup(PQgetvalue(res, i, i_amname));
 		tblinfo[i].is_identity_sequence = (strcmp(PQgetvalue(res, i, i_is_identity_sequence), "t") == 0);
 		tblinfo[i].ispartition = (strcmp(PQgetvalue(res, i, i_ispartition), "t") == 0);
+		tblinfo[i].isivm = (strcmp(PQgetvalue(res, i, i_isivm), "t") == 0);
 
 		/* other fields were zeroed above */
 
@@ -15517,9 +15527,11 @@ dumpTableSchema(Archive *fout, const TableInfo *tbinfo)
 			binary_upgrade_set_pg_class_oids(fout, q,
 											 tbinfo->dobj.catId.oid, false);
 
-		appendPQExpBuffer(q, "CREATE %s%s %s",
+		appendPQExpBuffer(q, "CREATE %s%s%s %s",
 						  tbinfo->relpersistence == RELPERSISTENCE_UNLOGGED ?
 						  "UNLOGGED " : "",
+						  tbinfo->relkind == RELKIND_MATVIEW && tbinfo->isivm ?
+						  "INCREMENTAL " : "",
 						  reltypename,
 						  qualrelname);
 
diff --git a/src/bin/pg_dump/pg_dump.h b/src/bin/pg_dump/pg_dump.h
index ed6ce41ad7..119293a751 100644
--- a/src/bin/pg_dump/pg_dump.h
+++ b/src/bin/pg_dump/pg_dump.h
@@ -322,6 +322,7 @@ typedef struct _tableInfo
 
 	int			numParents;		/* number of (immediate) parent tables */
 	struct _tableInfo **parents;	/* TableInfos of immediate parents */
+	bool		isivm;			/* is incrementally maintainable materialized view? */
 
 	/*
 	 * These fields are computed only if we decide the table is interesting
diff --git a/src/bin/pg_dump/t/002_pg_dump.pl b/src/bin/pg_dump/t/002_pg_dump.pl
index 387c5d3afb..164c9eb110 100644
--- a/src/bin/pg_dump/t/002_pg_dump.pl
+++ b/src/bin/pg_dump/t/002_pg_dump.pl
@@ -2732,6 +2732,21 @@ my %tests = (
 		},
 	},
 
+	'CREATE MATERIALIZED VIEW matview_ivm' => {
+		create_order => 21,
+		create_sql   => 'CREATE INCREMENTAL MATERIALIZED VIEW dump_test.matview_ivm (col1) AS
+					   SELECT col1 FROM dump_test.test_table;',
+		regexp => qr/^
+			\QCREATE INCREMENTAL MATERIALIZED VIEW dump_test.matview_ivm AS\E
+			\n\s+\QSELECT test_table.col1\E
+			\n\s+\QFROM dump_test.test_table\E
+			\n\s+\QWITH NO DATA;\E
+			/xm,
+		like =>
+		  { %full_runs, %dump_test_schema_runs, section_pre_data => 1, },
+		unlike => { exclude_dump_test_schema => 1, },
+	},
+
 	'CREATE POLICY p1 ON test_table' => {
 		create_order => 22,
 		create_sql => 'CREATE POLICY p1 ON dump_test.test_table
-- 
2.25.1


--Multipart=_Thu__1_Jun_2023_23_59_09_+0900_/G5+8nG46.f1T42K
Content-Type: text/x-diff;
 name="v28-0005-Add-Incremental-View-Maintenance-support-to-psql.patch"
Content-Disposition: attachment;
 filename="v28-0005-Add-Incremental-View-Maintenance-support-to-psql.patch"
Content-Transfer-Encoding: 7bit



^ permalink  raw  reply  [nested|flat] 101+ messages in thread

* [PATCH v39 4/8] Add Incremental View Maintenance support to pg_dump
@ 2020-11-11 08:01  Yugo Nagata <[email protected]>
  0 siblings, 0 replies; 101+ messages in thread

From: Yugo Nagata @ 2020-11-11 08:01 UTC (permalink / raw)

Support CREATE INCREMENTAL MATERIALIZED VIEW syntax.
---
 src/bin/pg_dump/pg_dump.c        | 14 +++++++++++++-
 src/bin/pg_dump/pg_dump.h        |  2 ++
 src/bin/pg_dump/t/002_pg_dump.pl | 18 ++++++++++++++++++
 3 files changed, 33 insertions(+), 1 deletion(-)

diff --git a/src/bin/pg_dump/pg_dump.c b/src/bin/pg_dump/pg_dump.c
index f67daf85911..9a5f65659e3 100644
--- a/src/bin/pg_dump/pg_dump.c
+++ b/src/bin/pg_dump/pg_dump.c
@@ -7196,6 +7196,7 @@ getTables(Archive *fout, int *numTables)
 	int			i_relacl;
 	int			i_acldefault;
 	int			i_ispartition;
+	int			i_isivm;
 
 	/*
 	 * Find all the tables and table-like objects.
@@ -7277,6 +7278,13 @@ getTables(Archive *fout, int *numTables)
 	appendPQExpBufferStr(query,
 						 "c.relispartition AS ispartition ");
 
+	if (fout->remoteVersion >= 200000)
+		appendPQExpBufferStr(query,
+							 "c.relisivm AS isivm ");
+	else
+		appendPQExpBufferStr(query,
+							 "false AS isivm ");
+
 	/*
 	 * Left join to pg_depend to pick up dependency info linking sequences to
 	 * their owning column, if any (note this dependency is AUTO except for
@@ -7387,6 +7395,7 @@ getTables(Archive *fout, int *numTables)
 	i_relacl = PQfnumber(res, "relacl");
 	i_acldefault = PQfnumber(res, "acldefault");
 	i_ispartition = PQfnumber(res, "ispartition");
+	i_isivm = PQfnumber(res, "isivm");
 
 	if (dopt->lockWaitTimeout)
 	{
@@ -7469,6 +7478,7 @@ getTables(Archive *fout, int *numTables)
 			tblinfo[i].amname = pg_strdup(PQgetvalue(res, i, i_amname));
 		tblinfo[i].is_identity_sequence = (strcmp(PQgetvalue(res, i, i_is_identity_sequence), "t") == 0);
 		tblinfo[i].ispartition = (strcmp(PQgetvalue(res, i, i_ispartition), "t") == 0);
+		tblinfo[i].isivm = (strcmp(PQgetvalue(res, i, i_isivm), "t") == 0);
 
 		/* other fields were zeroed above */
 
@@ -17202,10 +17212,12 @@ dumpTableSchema(Archive *fout, const TableInfo *tbinfo)
 		 * PostgreSQL 18 has disabled UNLOGGED for partitioned tables, so
 		 * ignore it when dumping if it was set in this case.
 		 */
-		appendPQExpBuffer(q, "CREATE %s%s %s",
+		appendPQExpBuffer(q, "CREATE %s%s%s %s",
 						  (tbinfo->relpersistence == RELPERSISTENCE_UNLOGGED &&
 						   tbinfo->relkind != RELKIND_PARTITIONED_TABLE) ?
 						  "UNLOGGED " : "",
+						  tbinfo->relkind == RELKIND_MATVIEW && tbinfo->isivm ?
+						  "INCREMENTAL " : "",
 						  reltypename,
 						  qualrelname);
 
diff --git a/src/bin/pg_dump/pg_dump.h b/src/bin/pg_dump/pg_dump.h
index 5a6726d8b12..4408c504323 100644
--- a/src/bin/pg_dump/pg_dump.h
+++ b/src/bin/pg_dump/pg_dump.h
@@ -347,6 +347,8 @@ typedef struct _tableInfo
 	int			numParents;		/* number of (immediate) parent tables */
 	struct _tableInfo **parents;	/* TableInfos of immediate parents */
 
+	bool		isivm;			/* is incrementally maintainable materialized view? */
+
 	/*
 	 * These fields are computed only if we decide the table is interesting
 	 * (it's either a table to dump, or a direct parent of a dumpable table).
diff --git a/src/bin/pg_dump/t/002_pg_dump.pl b/src/bin/pg_dump/t/002_pg_dump.pl
index 9258948b583..8abde57e4f3 100644
--- a/src/bin/pg_dump/t/002_pg_dump.pl
+++ b/src/bin/pg_dump/t/002_pg_dump.pl
@@ -3033,6 +3033,24 @@ my %tests = (
 		},
 	},
 
+	'CREATE MATERIALIZED VIEW matview_ivm' => {
+		create_order => 21,
+		create_sql   => 'CREATE INCREMENTAL MATERIALIZED VIEW dump_test.matview_ivm (col1) AS
+					   SELECT col1 FROM dump_test.test_table;',
+		regexp => qr/^
+			\QCREATE INCREMENTAL MATERIALIZED VIEW dump_test.matview_ivm AS\E
+			\n\s+\QSELECT col1\E
+			\n\s+\QFROM dump_test.test_table\E
+			\n\s+\QWITH NO DATA;\E
+			/xm,
+		like =>
+		  { %full_runs, %dump_test_schema_runs, section_pre_data => 1, },
+		unlike => {
+			exclude_dump_test_schema => 1,
+			only_dump_measurement => 1,
+		},
+	},
+
 	'CREATE POLICY p1 ON test_table' => {
 		create_order => 22,
 		create_sql => 'CREATE POLICY p1 ON dump_test.test_table
-- 
2.43.0


--Multipart=_Fri__3_Jul_2026_19_11_16_+0900_CskxSIu_iGcDMEyM
Content-Type: text/x-diff;
 name="v39-0003-Allow-to-prolong-life-span-of-transition-tables-.patch"
Content-Disposition: attachment;
 filename="v39-0003-Allow-to-prolong-life-span-of-transition-tables-.patch"
Content-Transfer-Encoding: 7bit



^ permalink  raw  reply  [nested|flat] 101+ messages in thread

* [PATCH v38 04/11] Add Incremental View Maintenance support to pg_dump
@ 2020-11-11 08:01  Yugo Nagata <[email protected]>
  0 siblings, 0 replies; 101+ messages in thread

From: Yugo Nagata @ 2020-11-11 08:01 UTC (permalink / raw)

Support CREATE INCREMENTAL MATERIALIZED VIEW syntax.
---
 src/bin/pg_dump/pg_dump.c        | 18 +++++++++++++++---
 src/bin/pg_dump/pg_dump.h        |  2 ++
 src/bin/pg_dump/t/002_pg_dump.pl | 18 ++++++++++++++++++
 3 files changed, 35 insertions(+), 3 deletions(-)

diff --git a/src/bin/pg_dump/pg_dump.c b/src/bin/pg_dump/pg_dump.c
index c56437d6057..f7420e0db41 100644
--- a/src/bin/pg_dump/pg_dump.c
+++ b/src/bin/pg_dump/pg_dump.c
@@ -7323,6 +7323,7 @@ getTables(Archive *fout, int *numTables)
 	int			i_relacl;
 	int			i_acldefault;
 	int			i_ispartition;
+	int			i_isivm;
 
 	/*
 	 * Find all the tables and table-like objects.
@@ -7432,10 +7433,17 @@ getTables(Archive *fout, int *numTables)
 
 	if (fout->remoteVersion >= 100000)
 		appendPQExpBufferStr(query,
-							 "c.relispartition AS ispartition ");
+							 "c.relispartition AS ispartition, ");
 	else
 		appendPQExpBufferStr(query,
-							 "false AS ispartition ");
+							 "false AS ispartition, ");
+
+	if (fout->remoteVersion >= 200000)
+		appendPQExpBufferStr(query,
+							 "c.relisivm AS isivm ");
+	else
+		appendPQExpBufferStr(query,
+							 "false AS isivm ");
 
 	/*
 	 * Left join to pg_depend to pick up dependency info linking sequences to
@@ -7548,6 +7556,7 @@ getTables(Archive *fout, int *numTables)
 	i_relacl = PQfnumber(res, "relacl");
 	i_acldefault = PQfnumber(res, "acldefault");
 	i_ispartition = PQfnumber(res, "ispartition");
+	i_isivm = PQfnumber(res, "isivm");
 
 	if (dopt->lockWaitTimeout)
 	{
@@ -7630,6 +7639,7 @@ getTables(Archive *fout, int *numTables)
 			tblinfo[i].amname = pg_strdup(PQgetvalue(res, i, i_amname));
 		tblinfo[i].is_identity_sequence = (strcmp(PQgetvalue(res, i, i_is_identity_sequence), "t") == 0);
 		tblinfo[i].ispartition = (strcmp(PQgetvalue(res, i, i_ispartition), "t") == 0);
+		tblinfo[i].isivm = (strcmp(PQgetvalue(res, i, i_isivm), "t") == 0);
 
 		/* other fields were zeroed above */
 
@@ -17452,10 +17462,12 @@ dumpTableSchema(Archive *fout, const TableInfo *tbinfo)
 		 * PostgreSQL 18 has disabled UNLOGGED for partitioned tables, so
 		 * ignore it when dumping if it was set in this case.
 		 */
-		appendPQExpBuffer(q, "CREATE %s%s %s",
+		appendPQExpBuffer(q, "CREATE %s%s%s %s",
 						  (tbinfo->relpersistence == RELPERSISTENCE_UNLOGGED &&
 						   tbinfo->relkind != RELKIND_PARTITIONED_TABLE) ?
 						  "UNLOGGED " : "",
+						  tbinfo->relkind == RELKIND_MATVIEW && tbinfo->isivm ?
+						  "INCREMENTAL " : "",
 						  reltypename,
 						  qualrelname);
 
diff --git a/src/bin/pg_dump/pg_dump.h b/src/bin/pg_dump/pg_dump.h
index 5a6726d8b12..4408c504323 100644
--- a/src/bin/pg_dump/pg_dump.h
+++ b/src/bin/pg_dump/pg_dump.h
@@ -347,6 +347,8 @@ typedef struct _tableInfo
 	int			numParents;		/* number of (immediate) parent tables */
 	struct _tableInfo **parents;	/* TableInfos of immediate parents */
 
+	bool		isivm;			/* is incrementally maintainable materialized view? */
+
 	/*
 	 * These fields are computed only if we decide the table is interesting
 	 * (it's either a table to dump, or a direct parent of a dumpable table).
diff --git a/src/bin/pg_dump/t/002_pg_dump.pl b/src/bin/pg_dump/t/002_pg_dump.pl
index 9258948b583..8abde57e4f3 100644
--- a/src/bin/pg_dump/t/002_pg_dump.pl
+++ b/src/bin/pg_dump/t/002_pg_dump.pl
@@ -3033,6 +3033,24 @@ my %tests = (
 		},
 	},
 
+	'CREATE MATERIALIZED VIEW matview_ivm' => {
+		create_order => 21,
+		create_sql   => 'CREATE INCREMENTAL MATERIALIZED VIEW dump_test.matview_ivm (col1) AS
+					   SELECT col1 FROM dump_test.test_table;',
+		regexp => qr/^
+			\QCREATE INCREMENTAL MATERIALIZED VIEW dump_test.matview_ivm AS\E
+			\n\s+\QSELECT col1\E
+			\n\s+\QFROM dump_test.test_table\E
+			\n\s+\QWITH NO DATA;\E
+			/xm,
+		like =>
+		  { %full_runs, %dump_test_schema_runs, section_pre_data => 1, },
+		unlike => {
+			exclude_dump_test_schema => 1,
+			only_dump_measurement => 1,
+		},
+	},
+
 	'CREATE POLICY p1 ON test_table' => {
 		create_order => 22,
 		create_sql => 'CREATE POLICY p1 ON dump_test.test_table
-- 
2.43.0


--Multipart=_Wed__1_Jul_2026_00_04_01_+0900_OVSy2WWK_9aByzDJ
Content-Type: text/x-diff;
 name="v38-0003-Allow-to-prolong-life-span-of-transition-tables-.patch"
Content-Disposition: attachment;
 filename="v38-0003-Allow-to-prolong-life-span-of-transition-tables-.patch"
Content-Transfer-Encoding: 7bit



^ permalink  raw  reply  [nested|flat] 101+ messages in thread

* [PATCH v37 04/11] Add Incremental View Maintenance support to pg_dump
@ 2020-11-11 08:01  Yugo Nagata <[email protected]>
  0 siblings, 0 replies; 101+ messages in thread

From: Yugo Nagata @ 2020-11-11 08:01 UTC (permalink / raw)

Support CREATE INCREMENTAL MATERIALIZED VIEW syntax.
---
 src/bin/pg_dump/pg_dump.c        | 18 +++++++++++++++---
 src/bin/pg_dump/pg_dump.h        |  2 ++
 src/bin/pg_dump/t/002_pg_dump.pl | 18 ++++++++++++++++++
 3 files changed, 35 insertions(+), 3 deletions(-)

diff --git a/src/bin/pg_dump/pg_dump.c b/src/bin/pg_dump/pg_dump.c
index d56dcc701ce..b1d37675f66 100644
--- a/src/bin/pg_dump/pg_dump.c
+++ b/src/bin/pg_dump/pg_dump.c
@@ -7323,6 +7323,7 @@ getTables(Archive *fout, int *numTables)
 	int			i_relacl;
 	int			i_acldefault;
 	int			i_ispartition;
+	int			i_isivm;
 
 	/*
 	 * Find all the tables and table-like objects.
@@ -7432,10 +7433,17 @@ getTables(Archive *fout, int *numTables)
 
 	if (fout->remoteVersion >= 100000)
 		appendPQExpBufferStr(query,
-							 "c.relispartition AS ispartition ");
+							 "c.relispartition AS ispartition, ");
 	else
 		appendPQExpBufferStr(query,
-							 "false AS ispartition ");
+							 "false AS ispartition, ");
+
+	if (fout->remoteVersion >= 180000)
+		appendPQExpBufferStr(query,
+							 "c.relisivm AS isivm ");
+	else
+		appendPQExpBufferStr(query,
+							 "false AS isivm ");
 
 	/*
 	 * Left join to pg_depend to pick up dependency info linking sequences to
@@ -7548,6 +7556,7 @@ getTables(Archive *fout, int *numTables)
 	i_relacl = PQfnumber(res, "relacl");
 	i_acldefault = PQfnumber(res, "acldefault");
 	i_ispartition = PQfnumber(res, "ispartition");
+	i_isivm = PQfnumber(res, "isivm");
 
 	if (dopt->lockWaitTimeout)
 	{
@@ -7630,6 +7639,7 @@ getTables(Archive *fout, int *numTables)
 			tblinfo[i].amname = pg_strdup(PQgetvalue(res, i, i_amname));
 		tblinfo[i].is_identity_sequence = (strcmp(PQgetvalue(res, i, i_is_identity_sequence), "t") == 0);
 		tblinfo[i].ispartition = (strcmp(PQgetvalue(res, i, i_ispartition), "t") == 0);
+		tblinfo[i].isivm = (strcmp(PQgetvalue(res, i, i_isivm), "t") == 0);
 
 		/* other fields were zeroed above */
 
@@ -17452,10 +17462,12 @@ dumpTableSchema(Archive *fout, const TableInfo *tbinfo)
 		 * PostgreSQL 18 has disabled UNLOGGED for partitioned tables, so
 		 * ignore it when dumping if it was set in this case.
 		 */
-		appendPQExpBuffer(q, "CREATE %s%s %s",
+		appendPQExpBuffer(q, "CREATE %s%s%s %s",
 						  (tbinfo->relpersistence == RELPERSISTENCE_UNLOGGED &&
 						   tbinfo->relkind != RELKIND_PARTITIONED_TABLE) ?
 						  "UNLOGGED " : "",
+						  tbinfo->relkind == RELKIND_MATVIEW && tbinfo->isivm ?
+						  "INCREMENTAL " : "",
 						  reltypename,
 						  qualrelname);
 
diff --git a/src/bin/pg_dump/pg_dump.h b/src/bin/pg_dump/pg_dump.h
index 5a6726d8b12..4408c504323 100644
--- a/src/bin/pg_dump/pg_dump.h
+++ b/src/bin/pg_dump/pg_dump.h
@@ -347,6 +347,8 @@ typedef struct _tableInfo
 	int			numParents;		/* number of (immediate) parent tables */
 	struct _tableInfo **parents;	/* TableInfos of immediate parents */
 
+	bool		isivm;			/* is incrementally maintainable materialized view? */
+
 	/*
 	 * These fields are computed only if we decide the table is interesting
 	 * (it's either a table to dump, or a direct parent of a dumpable table).
diff --git a/src/bin/pg_dump/t/002_pg_dump.pl b/src/bin/pg_dump/t/002_pg_dump.pl
index 3ee9fda50e4..7c38d3023f0 100644
--- a/src/bin/pg_dump/t/002_pg_dump.pl
+++ b/src/bin/pg_dump/t/002_pg_dump.pl
@@ -2992,6 +2992,24 @@ my %tests = (
 		},
 	},
 
+	'CREATE MATERIALIZED VIEW matview_ivm' => {
+		create_order => 21,
+		create_sql   => 'CREATE INCREMENTAL MATERIALIZED VIEW dump_test.matview_ivm (col1) AS
+					   SELECT col1 FROM dump_test.test_table;',
+		regexp => qr/^
+			\QCREATE INCREMENTAL MATERIALIZED VIEW dump_test.matview_ivm AS\E
+			\n\s+\QSELECT col1\E
+			\n\s+\QFROM dump_test.test_table\E
+			\n\s+\QWITH NO DATA;\E
+			/xm,
+		like =>
+		  { %full_runs, %dump_test_schema_runs, section_pre_data => 1, },
+		unlike => {
+			exclude_dump_test_schema => 1,
+			only_dump_measurement => 1,
+		},
+	},
+
 	'CREATE POLICY p1 ON test_table' => {
 		create_order => 22,
 		create_sql => 'CREATE POLICY p1 ON dump_test.test_table
-- 
2.43.0


--Multipart=_Fri__29_May_2026_23_14_17_+0900_Te0o73X2VqYK57Gd
Content-Type: text/x-diff;
 name="v37-0003-Allow-to-prolong-life-span-of-transition-tables-.patch"
Content-Disposition: attachment;
 filename="v37-0003-Allow-to-prolong-life-span-of-transition-tables-.patch"
Content-Transfer-Encoding: 7bit



^ permalink  raw  reply  [nested|flat] 101+ messages in thread

* [PATCH v23 05/15] Add Incremental View Maintenance support to pg_dump
@ 2020-11-11 08:01  Yugo Nagata <[email protected]>
  0 siblings, 0 replies; 101+ messages in thread

From: Yugo Nagata @ 2020-11-11 08:01 UTC (permalink / raw)

Support CREATE INCREMENTAL MATERIALIZED VIEW syntax.
---
 src/bin/pg_dump/pg_dump.c        | 42 ++++++++++++++++++++++++--------
 src/bin/pg_dump/pg_dump.h        |  1 +
 src/bin/pg_dump/t/002_pg_dump.pl | 15 ++++++++++++
 3 files changed, 48 insertions(+), 10 deletions(-)

diff --git a/src/bin/pg_dump/pg_dump.c b/src/bin/pg_dump/pg_dump.c
index 90ac445bcd..17e0a2193d 100644
--- a/src/bin/pg_dump/pg_dump.c
+++ b/src/bin/pg_dump/pg_dump.c
@@ -6268,6 +6268,7 @@ getTables(Archive *fout, int *numTables)
 	int			i_ispartition;
 	int			i_partbound;
 	int			i_amname;
+	int			i_isivm;
 
 	/*
 	 * Find all the tables and table-like objects.
@@ -6299,6 +6300,7 @@ getTables(Archive *fout, int *numTables)
 		char	   *ispartition = "false";
 		char	   *partbound = "NULL";
 		char	   *relhasoids = "c.relhasoids";
+		char	   *isivm = "false";
 
 		PQExpBuffer acl_subquery = createPQExpBuffer();
 		PQExpBuffer racl_subquery = createPQExpBuffer();
@@ -6326,6 +6328,10 @@ getTables(Archive *fout, int *numTables)
 		if (fout->remoteVersion >= 120000)
 			relhasoids = "'f'::bool";
 
+		/* The information about incremental view maintenance */
+		if (fout->remoteVersion >= 150000)
+			isivm = "c.relisivm";
+
 		/*
 		 * Left join to pick up dependency info linking sequences to their
 		 * owning column, if any (note this dependency is AUTO as of 8.2)
@@ -6384,7 +6390,8 @@ getTables(Archive *fout, int *numTables)
 						  "AS changed_acl, "
 						  "%s AS partkeydef, "
 						  "%s AS ispartition, "
-						  "%s AS partbound "
+						  "%s AS partbound, "
+						  "%s AS isivm "
 						  "FROM pg_class c "
 						  "LEFT JOIN pg_depend d ON "
 						  "(c.relkind = '%c' AND "
@@ -6413,6 +6420,7 @@ getTables(Archive *fout, int *numTables)
 						  partkeydef,
 						  ispartition,
 						  partbound,
+						  isivm,
 						  RELKIND_SEQUENCE,
 						  RELKIND_PARTITIONED_TABLE,
 						  RELKIND_RELATION, RELKIND_SEQUENCE,
@@ -6466,7 +6474,8 @@ getTables(Archive *fout, int *numTables)
 						  "NULL AS changed_acl, "
 						  "NULL AS partkeydef, "
 						  "false AS ispartition, "
-						  "NULL AS partbound "
+						  "NULL AS partbound, "
+						  "false AS isivm "
 						  "FROM pg_class c "
 						  "LEFT JOIN pg_depend d ON "
 						  "(c.relkind = '%c' AND "
@@ -6519,7 +6528,8 @@ getTables(Archive *fout, int *numTables)
 						  "NULL AS changed_acl, "
 						  "NULL AS partkeydef, "
 						  "false AS ispartition, "
-						  "NULL AS partbound "
+						  "NULL AS partbound, "
+						  "false AS isivm "
 						  "FROM pg_class c "
 						  "LEFT JOIN pg_depend d ON "
 						  "(c.relkind = '%c' AND "
@@ -6572,7 +6582,8 @@ getTables(Archive *fout, int *numTables)
 						  "NULL AS changed_acl, "
 						  "NULL AS partkeydef, "
 						  "false AS ispartition, "
-						  "NULL AS partbound "
+						  "NULL AS partbound, "
+						  "false AS isivm "
 						  "FROM pg_class c "
 						  "LEFT JOIN pg_depend d ON "
 						  "(c.relkind = '%c' AND "
@@ -6623,7 +6634,8 @@ getTables(Archive *fout, int *numTables)
 						  "NULL AS changed_acl, "
 						  "NULL AS partkeydef, "
 						  "false AS ispartition, "
-						  "NULL AS partbound "
+						  "NULL AS partbound, "
+						  "false AS isivm "
 						  "FROM pg_class c "
 						  "LEFT JOIN pg_depend d ON "
 						  "(c.relkind = '%c' AND "
@@ -6672,7 +6684,8 @@ getTables(Archive *fout, int *numTables)
 						  "NULL AS changed_acl, "
 						  "NULL AS partkeydef, "
 						  "false AS ispartition, "
-						  "NULL AS partbound "
+						  "NULL AS partbound, "
+						  "false AS isivm "
 						  "FROM pg_class c "
 						  "LEFT JOIN pg_depend d ON "
 						  "(c.relkind = '%c' AND "
@@ -6720,7 +6733,8 @@ getTables(Archive *fout, int *numTables)
 						  "NULL AS changed_acl, "
 						  "NULL AS partkeydef, "
 						  "false AS ispartition, "
-						  "NULL AS partbound "
+						  "NULL AS partbound, "
+						  "false AS isivm "
 						  "FROM pg_class c "
 						  "LEFT JOIN pg_depend d ON "
 						  "(c.relkind = '%c' AND "
@@ -6768,7 +6782,8 @@ getTables(Archive *fout, int *numTables)
 						  "NULL AS changed_acl, "
 						  "NULL AS partkeydef, "
 						  "false AS ispartition, "
-						  "NULL AS partbound "
+						  "NULL AS partbound, "
+						  "false AS isivm "
 						  "FROM pg_class c "
 						  "LEFT JOIN pg_depend d ON "
 						  "(c.relkind = '%c' AND "
@@ -6815,7 +6830,8 @@ getTables(Archive *fout, int *numTables)
 						  "NULL AS changed_acl, "
 						  "NULL AS partkeydef, "
 						  "false AS ispartition, "
-						  "NULL AS partbound "
+						  "NULL AS partbound, "
+						  "false AS isivm "
 						  "FROM pg_class c "
 						  "LEFT JOIN pg_depend d ON "
 						  "(c.relkind = '%c' AND "
@@ -6887,6 +6903,7 @@ getTables(Archive *fout, int *numTables)
 	i_ispartition = PQfnumber(res, "ispartition");
 	i_partbound = PQfnumber(res, "partbound");
 	i_amname = PQfnumber(res, "amname");
+	i_isivm = PQfnumber(res, "isivm");
 
 	if (dopt->lockWaitTimeout)
 	{
@@ -7000,6 +7017,9 @@ getTables(Archive *fout, int *numTables)
 		/* foreign server */
 		tblinfo[i].foreign_server = atooid(PQgetvalue(res, i, i_foreignserver));
 
+		/* Incremental view maintenance information */
+		tblinfo[i].isivm = (strcmp(PQgetvalue(res, i, i_isivm), "t") == 0);
+
 		/*
 		 * Read-lock target tables to make sure they aren't DROPPED or altered
 		 * in schema before we get around to dumping them.
@@ -15990,9 +16010,11 @@ dumpTableSchema(Archive *fout, const TableInfo *tbinfo)
 			binary_upgrade_set_pg_class_oids(fout, q,
 											 tbinfo->dobj.catId.oid, false);
 
-		appendPQExpBuffer(q, "CREATE %s%s %s",
+		appendPQExpBuffer(q, "CREATE %s%s%s %s",
 						  tbinfo->relpersistence == RELPERSISTENCE_UNLOGGED ?
 						  "UNLOGGED " : "",
+						  tbinfo->relkind == RELKIND_MATVIEW && tbinfo->isivm ?
+						  "INCREMENTAL " : "",
 						  reltypename,
 						  qualrelname);
 
diff --git a/src/bin/pg_dump/pg_dump.h b/src/bin/pg_dump/pg_dump.h
index f5e170e0db..ae8f24bb78 100644
--- a/src/bin/pg_dump/pg_dump.h
+++ b/src/bin/pg_dump/pg_dump.h
@@ -298,6 +298,7 @@ typedef struct _tableInfo
 	bool		dummy_view;		/* view's real definition must be postponed */
 	bool		postponed_def;	/* matview must be postponed into post-data */
 	bool		ispartition;	/* is table a partition? */
+	bool		isivm;			/* is incrementally maintainable materialized view? */
 
 	/*
 	 * These fields are computed only if we decide the table is interesting
diff --git a/src/bin/pg_dump/t/002_pg_dump.pl b/src/bin/pg_dump/t/002_pg_dump.pl
index c5d8915be8..9d1776a506 100644
--- a/src/bin/pg_dump/t/002_pg_dump.pl
+++ b/src/bin/pg_dump/t/002_pg_dump.pl
@@ -2160,6 +2160,21 @@ my %tests = (
 		  { exclude_dump_test_schema => 1, no_toast_compression => 1, },
 	},
 
+	'CREATE MATERIALIZED VIEW matview_ivm' => {
+		create_order => 21,
+		create_sql   => 'CREATE INCREMENTAL MATERIALIZED VIEW dump_test.matview_ivm (col1) AS
+					   SELECT col1 FROM dump_test.test_table;',
+		regexp => qr/^
+			\QCREATE INCREMENTAL MATERIALIZED VIEW dump_test.matview_ivm AS\E
+			\n\s+\QSELECT test_table.col1\E
+			\n\s+\QFROM dump_test.test_table\E
+			\n\s+\QWITH NO DATA;\E
+			/xm,
+		like =>
+		  { %full_runs, %dump_test_schema_runs, section_pre_data => 1, },
+		unlike => { exclude_dump_test_schema => 1, },
+	},
+
 	'CREATE POLICY p1 ON test_table' => {
 		create_order => 22,
 		create_sql   => 'CREATE POLICY p1 ON dump_test.test_table
-- 
2.17.1


--Multipart=_Mon__2_Aug_2021_15_28_34_+0900_wlHCjIpnD/FrGAKu
Content-Type: text/x-diff;
 name="v23-0006-Add-Incremental-View-Maintenance-support-to-psql.patch"
Content-Disposition: attachment;
 filename="v23-0006-Add-Incremental-View-Maintenance-support-to-psql.patch"
Content-Transfer-Encoding: 7bit



^ permalink  raw  reply  [nested|flat] 101+ messages in thread

* [PATCH v24 05/15] Add Incremental View Maintenance support to pg_dump
@ 2020-11-11 08:01  Yugo Nagata <[email protected]>
  0 siblings, 0 replies; 101+ messages in thread

From: Yugo Nagata @ 2020-11-11 08:01 UTC (permalink / raw)

Support CREATE INCREMENTAL MATERIALIZED VIEW syntax.
---
 src/bin/pg_dump/pg_dump.c        | 42 ++++++++++++++++++++++++--------
 src/bin/pg_dump/pg_dump.h        |  1 +
 src/bin/pg_dump/t/002_pg_dump.pl | 15 ++++++++++++
 3 files changed, 48 insertions(+), 10 deletions(-)

diff --git a/src/bin/pg_dump/pg_dump.c b/src/bin/pg_dump/pg_dump.c
index a485fb2d07..4e3836af7c 100644
--- a/src/bin/pg_dump/pg_dump.c
+++ b/src/bin/pg_dump/pg_dump.c
@@ -6267,6 +6267,7 @@ getTables(Archive *fout, int *numTables)
 	int			i_ispartition;
 	int			i_partbound;
 	int			i_amname;
+	int			i_isivm;
 
 	/*
 	 * Find all the tables and table-like objects.
@@ -6298,6 +6299,7 @@ getTables(Archive *fout, int *numTables)
 		char	   *ispartition = "false";
 		char	   *partbound = "NULL";
 		char	   *relhasoids = "c.relhasoids";
+		char	   *isivm = "false";
 
 		PQExpBuffer acl_subquery = createPQExpBuffer();
 		PQExpBuffer racl_subquery = createPQExpBuffer();
@@ -6325,6 +6327,10 @@ getTables(Archive *fout, int *numTables)
 		if (fout->remoteVersion >= 120000)
 			relhasoids = "'f'::bool";
 
+		/* The information about incremental view maintenance */
+		if (fout->remoteVersion >= 150000)
+			isivm = "c.relisivm";
+
 		/*
 		 * Left join to pick up dependency info linking sequences to their
 		 * owning column, if any (note this dependency is AUTO as of 8.2)
@@ -6383,7 +6389,8 @@ getTables(Archive *fout, int *numTables)
 						  "AS changed_acl, "
 						  "%s AS partkeydef, "
 						  "%s AS ispartition, "
-						  "%s AS partbound "
+						  "%s AS partbound, "
+						  "%s AS isivm "
 						  "FROM pg_class c "
 						  "LEFT JOIN pg_depend d ON "
 						  "(c.relkind = '%c' AND "
@@ -6412,6 +6419,7 @@ getTables(Archive *fout, int *numTables)
 						  partkeydef,
 						  ispartition,
 						  partbound,
+						  isivm,
 						  RELKIND_SEQUENCE,
 						  RELKIND_PARTITIONED_TABLE,
 						  RELKIND_RELATION, RELKIND_SEQUENCE,
@@ -6465,7 +6473,8 @@ getTables(Archive *fout, int *numTables)
 						  "NULL AS changed_acl, "
 						  "NULL AS partkeydef, "
 						  "false AS ispartition, "
-						  "NULL AS partbound "
+						  "NULL AS partbound, "
+						  "false AS isivm "
 						  "FROM pg_class c "
 						  "LEFT JOIN pg_depend d ON "
 						  "(c.relkind = '%c' AND "
@@ -6518,7 +6527,8 @@ getTables(Archive *fout, int *numTables)
 						  "NULL AS changed_acl, "
 						  "NULL AS partkeydef, "
 						  "false AS ispartition, "
-						  "NULL AS partbound "
+						  "NULL AS partbound, "
+						  "false AS isivm "
 						  "FROM pg_class c "
 						  "LEFT JOIN pg_depend d ON "
 						  "(c.relkind = '%c' AND "
@@ -6571,7 +6581,8 @@ getTables(Archive *fout, int *numTables)
 						  "NULL AS changed_acl, "
 						  "NULL AS partkeydef, "
 						  "false AS ispartition, "
-						  "NULL AS partbound "
+						  "NULL AS partbound, "
+						  "false AS isivm "
 						  "FROM pg_class c "
 						  "LEFT JOIN pg_depend d ON "
 						  "(c.relkind = '%c' AND "
@@ -6622,7 +6633,8 @@ getTables(Archive *fout, int *numTables)
 						  "NULL AS changed_acl, "
 						  "NULL AS partkeydef, "
 						  "false AS ispartition, "
-						  "NULL AS partbound "
+						  "NULL AS partbound, "
+						  "false AS isivm "
 						  "FROM pg_class c "
 						  "LEFT JOIN pg_depend d ON "
 						  "(c.relkind = '%c' AND "
@@ -6671,7 +6683,8 @@ getTables(Archive *fout, int *numTables)
 						  "NULL AS changed_acl, "
 						  "NULL AS partkeydef, "
 						  "false AS ispartition, "
-						  "NULL AS partbound "
+						  "NULL AS partbound, "
+						  "false AS isivm "
 						  "FROM pg_class c "
 						  "LEFT JOIN pg_depend d ON "
 						  "(c.relkind = '%c' AND "
@@ -6719,7 +6732,8 @@ getTables(Archive *fout, int *numTables)
 						  "NULL AS changed_acl, "
 						  "NULL AS partkeydef, "
 						  "false AS ispartition, "
-						  "NULL AS partbound "
+						  "NULL AS partbound, "
+						  "false AS isivm "
 						  "FROM pg_class c "
 						  "LEFT JOIN pg_depend d ON "
 						  "(c.relkind = '%c' AND "
@@ -6767,7 +6781,8 @@ getTables(Archive *fout, int *numTables)
 						  "NULL AS changed_acl, "
 						  "NULL AS partkeydef, "
 						  "false AS ispartition, "
-						  "NULL AS partbound "
+						  "NULL AS partbound, "
+						  "false AS isivm "
 						  "FROM pg_class c "
 						  "LEFT JOIN pg_depend d ON "
 						  "(c.relkind = '%c' AND "
@@ -6814,7 +6829,8 @@ getTables(Archive *fout, int *numTables)
 						  "NULL AS changed_acl, "
 						  "NULL AS partkeydef, "
 						  "false AS ispartition, "
-						  "NULL AS partbound "
+						  "NULL AS partbound, "
+						  "false AS isivm "
 						  "FROM pg_class c "
 						  "LEFT JOIN pg_depend d ON "
 						  "(c.relkind = '%c' AND "
@@ -6886,6 +6902,7 @@ getTables(Archive *fout, int *numTables)
 	i_ispartition = PQfnumber(res, "ispartition");
 	i_partbound = PQfnumber(res, "partbound");
 	i_amname = PQfnumber(res, "amname");
+	i_isivm = PQfnumber(res, "isivm");
 
 	if (dopt->lockWaitTimeout)
 	{
@@ -6999,6 +7016,9 @@ getTables(Archive *fout, int *numTables)
 		/* foreign server */
 		tblinfo[i].foreign_server = atooid(PQgetvalue(res, i, i_foreignserver));
 
+		/* Incremental view maintenance information */
+		tblinfo[i].isivm = (strcmp(PQgetvalue(res, i, i_isivm), "t") == 0);
+
 		/*
 		 * Read-lock target tables to make sure they aren't DROPPED or altered
 		 * in schema before we get around to dumping them.
@@ -16014,9 +16034,11 @@ dumpTableSchema(Archive *fout, const TableInfo *tbinfo)
 			binary_upgrade_set_pg_class_oids(fout, q,
 											 tbinfo->dobj.catId.oid, false);
 
-		appendPQExpBuffer(q, "CREATE %s%s %s",
+		appendPQExpBuffer(q, "CREATE %s%s%s %s",
 						  tbinfo->relpersistence == RELPERSISTENCE_UNLOGGED ?
 						  "UNLOGGED " : "",
+						  tbinfo->relkind == RELKIND_MATVIEW && tbinfo->isivm ?
+						  "INCREMENTAL " : "",
 						  reltypename,
 						  qualrelname);
 
diff --git a/src/bin/pg_dump/pg_dump.h b/src/bin/pg_dump/pg_dump.h
index 29af845ece..c271782817 100644
--- a/src/bin/pg_dump/pg_dump.h
+++ b/src/bin/pg_dump/pg_dump.h
@@ -300,6 +300,7 @@ typedef struct _tableInfo
 	bool		dummy_view;		/* view's real definition must be postponed */
 	bool		postponed_def;	/* matview must be postponed into post-data */
 	bool		ispartition;	/* is table a partition? */
+	bool		isivm;			/* is incrementally maintainable materialized view? */
 
 	/*
 	 * These fields are computed only if we decide the table is interesting
diff --git a/src/bin/pg_dump/t/002_pg_dump.pl b/src/bin/pg_dump/t/002_pg_dump.pl
index c61d95e817..fb20699c8b 100644
--- a/src/bin/pg_dump/t/002_pg_dump.pl
+++ b/src/bin/pg_dump/t/002_pg_dump.pl
@@ -2161,6 +2161,21 @@ my %tests = (
 		  { exclude_dump_test_schema => 1, no_toast_compression => 1, },
 	},
 
+	'CREATE MATERIALIZED VIEW matview_ivm' => {
+		create_order => 21,
+		create_sql   => 'CREATE INCREMENTAL MATERIALIZED VIEW dump_test.matview_ivm (col1) AS
+					   SELECT col1 FROM dump_test.test_table;',
+		regexp => qr/^
+			\QCREATE INCREMENTAL MATERIALIZED VIEW dump_test.matview_ivm AS\E
+			\n\s+\QSELECT test_table.col1\E
+			\n\s+\QFROM dump_test.test_table\E
+			\n\s+\QWITH NO DATA;\E
+			/xm,
+		like =>
+		  { %full_runs, %dump_test_schema_runs, section_pre_data => 1, },
+		unlike => { exclude_dump_test_schema => 1, },
+	},
+
 	'CREATE POLICY p1 ON test_table' => {
 		create_order => 22,
 		create_sql   => 'CREATE POLICY p1 ON dump_test.test_table
-- 
2.17.1


--Multipart=_Thu__23_Sep_2021_04_57_30_+0900_b5pmgR1N8oMaMz.U
Content-Type: text/x-diff;
 name="v24-0006-Add-Incremental-View-Maintenance-support-to-psql.patch"
Content-Disposition: attachment;
 filename="v24-0006-Add-Incremental-View-Maintenance-support-to-psql.patch"
Content-Transfer-Encoding: 7bit



^ permalink  raw  reply  [nested|flat] 101+ messages in thread

* [PATCH v24 05/15] Add Incremental View Maintenance support to pg_dump
@ 2020-11-11 08:01  Yugo Nagata <[email protected]>
  0 siblings, 0 replies; 101+ messages in thread

From: Yugo Nagata @ 2020-11-11 08:01 UTC (permalink / raw)

Support CREATE INCREMENTAL MATERIALIZED VIEW syntax.
---
 src/bin/pg_dump/pg_dump.c        | 20 +++++++++++++++++---
 src/bin/pg_dump/pg_dump.h        |  1 +
 src/bin/pg_dump/t/002_pg_dump.pl | 15 +++++++++++++++
 3 files changed, 33 insertions(+), 3 deletions(-)

diff --git a/src/bin/pg_dump/pg_dump.c b/src/bin/pg_dump/pg_dump.c
index d1842edde0..d44361a47b 100644
--- a/src/bin/pg_dump/pg_dump.c
+++ b/src/bin/pg_dump/pg_dump.c
@@ -6393,6 +6393,7 @@ getTables(Archive *fout, int *numTables)
 	int			i_partkeydef;
 	int			i_ispartition;
 	int			i_partbound;
+	int			i_isivm;
 
 	/*
 	 * Find all the tables and table-like objects.
@@ -6596,12 +6597,19 @@ getTables(Archive *fout, int *numTables)
 		appendPQExpBufferStr(query,
 							 "pg_get_partkeydef(c.oid) AS partkeydef, "
 							 "c.relispartition AS ispartition, "
-							 "pg_get_expr(c.relpartbound, c.oid) AS partbound ");
+							 "pg_get_expr(c.relpartbound, c.oid) AS partbound, ");
 	else
 		appendPQExpBufferStr(query,
 							 "NULL AS partkeydef, "
 							 "false AS ispartition, "
-							 "NULL AS partbound ");
+							 "NULL AS partbound, ");
+
+	if (fout->remoteVersion >= 150000)
+		appendPQExpBufferStr(query,
+							 "c.relisivm AS isivm ");
+	else
+		appendPQExpBufferStr(query,
+							 "false AS isivm ");
 
 	/*
 	 * Left join to pg_depend to pick up dependency info linking sequences to
@@ -6719,6 +6727,8 @@ getTables(Archive *fout, int *numTables)
 	i_partkeydef = PQfnumber(res, "partkeydef");
 	i_ispartition = PQfnumber(res, "ispartition");
 	i_partbound = PQfnumber(res, "partbound");
+	i_isivm = PQfnumber(res, "isivm");
+
 
 	if (dopt->lockWaitTimeout)
 	{
@@ -6796,6 +6806,8 @@ getTables(Archive *fout, int *numTables)
 		tblinfo[i].partkeydef = pg_strdup(PQgetvalue(res, i, i_partkeydef));
 		tblinfo[i].ispartition = (strcmp(PQgetvalue(res, i, i_ispartition), "t") == 0);
 		tblinfo[i].partbound = pg_strdup(PQgetvalue(res, i, i_partbound));
+		tblinfo[i].isivm = (strcmp(PQgetvalue(res, i, i_isivm), "t") == 0);
+
 
 		/* other fields were zeroed above */
 
@@ -15868,9 +15880,11 @@ dumpTableSchema(Archive *fout, const TableInfo *tbinfo)
 			binary_upgrade_set_pg_class_oids(fout, q,
 											 tbinfo->dobj.catId.oid, false);
 
-		appendPQExpBuffer(q, "CREATE %s%s %s",
+		appendPQExpBuffer(q, "CREATE %s%s%s %s",
 						  tbinfo->relpersistence == RELPERSISTENCE_UNLOGGED ?
 						  "UNLOGGED " : "",
+						  tbinfo->relkind == RELKIND_MATVIEW && tbinfo->isivm ?
+						  "INCREMENTAL " : "",
 						  reltypename,
 						  qualrelname);
 
diff --git a/src/bin/pg_dump/pg_dump.h b/src/bin/pg_dump/pg_dump.h
index f9af14b793..c4e226831c 100644
--- a/src/bin/pg_dump/pg_dump.h
+++ b/src/bin/pg_dump/pg_dump.h
@@ -301,6 +301,7 @@ typedef struct _tableInfo
 	bool		dummy_view;		/* view's real definition must be postponed */
 	bool		postponed_def;	/* matview must be postponed into post-data */
 	bool		ispartition;	/* is table a partition? */
+	bool		isivm;			/* is incrementally maintainable materialized view? */
 
 	/*
 	 * These fields are computed only if we decide the table is interesting
diff --git a/src/bin/pg_dump/t/002_pg_dump.pl b/src/bin/pg_dump/t/002_pg_dump.pl
index d293f52b05..80efbcc7bc 100644
--- a/src/bin/pg_dump/t/002_pg_dump.pl
+++ b/src/bin/pg_dump/t/002_pg_dump.pl
@@ -2180,6 +2180,21 @@ my %tests = (
 		  { exclude_dump_test_schema => 1, no_toast_compression => 1, },
 	},
 
+	'CREATE MATERIALIZED VIEW matview_ivm' => {
+		create_order => 21,
+		create_sql   => 'CREATE INCREMENTAL MATERIALIZED VIEW dump_test.matview_ivm (col1) AS
+					   SELECT col1 FROM dump_test.test_table;',
+		regexp => qr/^
+			\QCREATE INCREMENTAL MATERIALIZED VIEW dump_test.matview_ivm AS\E
+			\n\s+\QSELECT test_table.col1\E
+			\n\s+\QFROM dump_test.test_table\E
+			\n\s+\QWITH NO DATA;\E
+			/xm,
+		like =>
+		  { %full_runs, %dump_test_schema_runs, section_pre_data => 1, },
+		unlike => { exclude_dump_test_schema => 1, },
+	},
+
 	'CREATE POLICY p1 ON test_table' => {
 		create_order => 22,
 		create_sql   => 'CREATE POLICY p1 ON dump_test.test_table
-- 
2.17.1


--Multipart=_Fri__29_Oct_2021_18_16_28_+0900_jlYRKjywLqhZ7oyk
Content-Type: text/x-diff;
 name="v24-0006-Add-Incremental-View-Maintenance-support-to-psql.patch"
Content-Disposition: attachment;
 filename="v24-0006-Add-Incremental-View-Maintenance-support-to-psql.patch"
Content-Transfer-Encoding: 7bit



^ permalink  raw  reply  [nested|flat] 101+ messages in thread

* [PATCH v26 05/10] Add Incremental View Maintenance support to pg_dump
@ 2020-11-11 08:01  Yugo Nagata <[email protected]>
  0 siblings, 0 replies; 101+ messages in thread

From: Yugo Nagata @ 2020-11-11 08:01 UTC (permalink / raw)

Support CREATE INCREMENTAL MATERIALIZED VIEW syntax.
---
 src/bin/pg_dump/pg_dump.c        | 18 +++++++++++++++---
 src/bin/pg_dump/pg_dump.h        |  1 +
 src/bin/pg_dump/t/002_pg_dump.pl | 15 +++++++++++++++
 3 files changed, 31 insertions(+), 3 deletions(-)

diff --git a/src/bin/pg_dump/pg_dump.c b/src/bin/pg_dump/pg_dump.c
index 4dd24b8c89..42bcd5509b 100644
--- a/src/bin/pg_dump/pg_dump.c
+++ b/src/bin/pg_dump/pg_dump.c
@@ -6032,6 +6032,7 @@ getTables(Archive *fout, int *numTables)
 	int			i_relacl;
 	int			i_acldefault;
 	int			i_ispartition;
+	int			i_isivm;
 
 	/*
 	 * Find all the tables and table-like objects.
@@ -6134,10 +6135,17 @@ getTables(Archive *fout, int *numTables)
 
 	if (fout->remoteVersion >= 100000)
 		appendPQExpBufferStr(query,
-							 "c.relispartition AS ispartition ");
+							 "c.relispartition AS ispartition, ");
 	else
 		appendPQExpBufferStr(query,
-							 "false AS ispartition ");
+							 "false AS ispartition, ");
+
+	if (fout->remoteVersion >= 150000)
+		appendPQExpBufferStr(query,
+							 "c.relisivm AS isivm ");
+	else
+		appendPQExpBufferStr(query,
+							 "false AS isivm ");
 
 	/*
 	 * Left join to pg_depend to pick up dependency info linking sequences to
@@ -6246,6 +6254,7 @@ getTables(Archive *fout, int *numTables)
 	i_relacl = PQfnumber(res, "relacl");
 	i_acldefault = PQfnumber(res, "acldefault");
 	i_ispartition = PQfnumber(res, "ispartition");
+	i_isivm = PQfnumber(res, "isivm");
 
 	if (dopt->lockWaitTimeout)
 	{
@@ -6323,6 +6332,7 @@ getTables(Archive *fout, int *numTables)
 			tblinfo[i].amname = pg_strdup(PQgetvalue(res, i, i_amname));
 		tblinfo[i].is_identity_sequence = (strcmp(PQgetvalue(res, i, i_is_identity_sequence), "t") == 0);
 		tblinfo[i].ispartition = (strcmp(PQgetvalue(res, i, i_ispartition), "t") == 0);
+		tblinfo[i].isivm = (strcmp(PQgetvalue(res, i, i_isivm), "t") == 0);
 
 		/* other fields were zeroed above */
 
@@ -15058,9 +15068,11 @@ dumpTableSchema(Archive *fout, const TableInfo *tbinfo)
 			binary_upgrade_set_pg_class_oids(fout, q,
 											 tbinfo->dobj.catId.oid, false);
 
-		appendPQExpBuffer(q, "CREATE %s%s %s",
+		appendPQExpBuffer(q, "CREATE %s%s%s %s",
 						  tbinfo->relpersistence == RELPERSISTENCE_UNLOGGED ?
 						  "UNLOGGED " : "",
+						  tbinfo->relkind == RELKIND_MATVIEW && tbinfo->isivm ?
+						  "INCREMENTAL " : "",
 						  reltypename,
 						  qualrelname);
 
diff --git a/src/bin/pg_dump/pg_dump.h b/src/bin/pg_dump/pg_dump.h
index 772dc0cf7a..756f54360c 100644
--- a/src/bin/pg_dump/pg_dump.h
+++ b/src/bin/pg_dump/pg_dump.h
@@ -318,6 +318,7 @@ typedef struct _tableInfo
 	bool		dummy_view;		/* view's real definition must be postponed */
 	bool		postponed_def;	/* matview must be postponed into post-data */
 	bool		ispartition;	/* is table a partition? */
+	bool		isivm;			/* is incrementally maintainable materialized view? */
 
 	/*
 	 * These fields are computed only if we decide the table is interesting
diff --git a/src/bin/pg_dump/t/002_pg_dump.pl b/src/bin/pg_dump/t/002_pg_dump.pl
index 3e55ff26f8..f2b29cc0a1 100644
--- a/src/bin/pg_dump/t/002_pg_dump.pl
+++ b/src/bin/pg_dump/t/002_pg_dump.pl
@@ -2233,6 +2233,21 @@ my %tests = (
 		  { exclude_dump_test_schema => 1, no_toast_compression => 1, },
 	},
 
+	'CREATE MATERIALIZED VIEW matview_ivm' => {
+		create_order => 21,
+		create_sql   => 'CREATE INCREMENTAL MATERIALIZED VIEW dump_test.matview_ivm (col1) AS
+					   SELECT col1 FROM dump_test.test_table;',
+		regexp => qr/^
+			\QCREATE INCREMENTAL MATERIALIZED VIEW dump_test.matview_ivm AS\E
+			\n\s+\QSELECT test_table.col1\E
+			\n\s+\QFROM dump_test.test_table\E
+			\n\s+\QWITH NO DATA;\E
+			/xm,
+		like =>
+		  { %full_runs, %dump_test_schema_runs, section_pre_data => 1, },
+		unlike => { exclude_dump_test_schema => 1, },
+	},
+
 	'CREATE POLICY p1 ON test_table' => {
 		create_order => 22,
 		create_sql   => 'CREATE POLICY p1 ON dump_test.test_table
-- 
2.17.1


--Multipart=_Mon__14_Mar_2022_19_12_17_+0900_E9HVp8j5QFkIIek.
Content-Type: text/x-diff;
 name="v26-0004-Allow-to-prolong-life-span-of-transition-tables-.patch"
Content-Disposition: attachment;
 filename="v26-0004-Allow-to-prolong-life-span-of-transition-tables-.patch"
Content-Transfer-Encoding: 7bit



^ permalink  raw  reply  [nested|flat] 101+ messages in thread

* [PATCH v25 05/15] Add Incremental View Maintenance support to pg_dump
@ 2020-11-11 08:01  Yugo Nagata <[email protected]>
  0 siblings, 0 replies; 101+ messages in thread

From: Yugo Nagata @ 2020-11-11 08:01 UTC (permalink / raw)

Support CREATE INCREMENTAL MATERIALIZED VIEW syntax.
---
 src/bin/pg_dump/pg_dump.c        | 18 +++++++++++++++---
 src/bin/pg_dump/pg_dump.h        |  1 +
 src/bin/pg_dump/t/002_pg_dump.pl | 15 +++++++++++++++
 3 files changed, 31 insertions(+), 3 deletions(-)

diff --git a/src/bin/pg_dump/pg_dump.c b/src/bin/pg_dump/pg_dump.c
index e3ddf19959..99cdca23a6 100644
--- a/src/bin/pg_dump/pg_dump.c
+++ b/src/bin/pg_dump/pg_dump.c
@@ -5979,6 +5979,7 @@ getTables(Archive *fout, int *numTables)
 	int			i_relacl;
 	int			i_acldefault;
 	int			i_ispartition;
+	int			i_isivm;
 
 	/*
 	 * Find all the tables and table-like objects.
@@ -6081,10 +6082,17 @@ getTables(Archive *fout, int *numTables)
 
 	if (fout->remoteVersion >= 100000)
 		appendPQExpBufferStr(query,
-							 "c.relispartition AS ispartition ");
+							 "c.relispartition AS ispartition, ");
 	else
 		appendPQExpBufferStr(query,
-							 "false AS ispartition ");
+							 "false AS ispartition, ");
+
+	if (fout->remoteVersion >= 150000)
+		appendPQExpBufferStr(query,
+							 "c.relisivm AS isivm ");
+	else
+		appendPQExpBufferStr(query,
+							 "false AS isivm ");
 
 	/*
 	 * Left join to pg_depend to pick up dependency info linking sequences to
@@ -6193,6 +6201,7 @@ getTables(Archive *fout, int *numTables)
 	i_relacl = PQfnumber(res, "relacl");
 	i_acldefault = PQfnumber(res, "acldefault");
 	i_ispartition = PQfnumber(res, "ispartition");
+	i_isivm = PQfnumber(res, "isivm");
 
 	if (dopt->lockWaitTimeout)
 	{
@@ -6270,6 +6279,7 @@ getTables(Archive *fout, int *numTables)
 			tblinfo[i].amname = pg_strdup(PQgetvalue(res, i, i_amname));
 		tblinfo[i].is_identity_sequence = (strcmp(PQgetvalue(res, i, i_is_identity_sequence), "t") == 0);
 		tblinfo[i].ispartition = (strcmp(PQgetvalue(res, i, i_ispartition), "t") == 0);
+		tblinfo[i].isivm = (strcmp(PQgetvalue(res, i, i_isivm), "t") == 0);
 
 		/* other fields were zeroed above */
 
@@ -14997,9 +15007,11 @@ dumpTableSchema(Archive *fout, const TableInfo *tbinfo)
 			binary_upgrade_set_pg_class_oids(fout, q,
 											 tbinfo->dobj.catId.oid, false);
 
-		appendPQExpBuffer(q, "CREATE %s%s %s",
+		appendPQExpBuffer(q, "CREATE %s%s%s %s",
 						  tbinfo->relpersistence == RELPERSISTENCE_UNLOGGED ?
 						  "UNLOGGED " : "",
+						  tbinfo->relkind == RELKIND_MATVIEW && tbinfo->isivm ?
+						  "INCREMENTAL " : "",
 						  reltypename,
 						  qualrelname);
 
diff --git a/src/bin/pg_dump/pg_dump.h b/src/bin/pg_dump/pg_dump.h
index 066a129ee5..7e80748d53 100644
--- a/src/bin/pg_dump/pg_dump.h
+++ b/src/bin/pg_dump/pg_dump.h
@@ -318,6 +318,7 @@ typedef struct _tableInfo
 	bool		dummy_view;		/* view's real definition must be postponed */
 	bool		postponed_def;	/* matview must be postponed into post-data */
 	bool		ispartition;	/* is table a partition? */
+	bool		isivm;			/* is incrementally maintainable materialized view? */
 
 	/*
 	 * These fields are computed only if we decide the table is interesting
diff --git a/src/bin/pg_dump/t/002_pg_dump.pl b/src/bin/pg_dump/t/002_pg_dump.pl
index 39fa1952e7..5fc70c30c1 100644
--- a/src/bin/pg_dump/t/002_pg_dump.pl
+++ b/src/bin/pg_dump/t/002_pg_dump.pl
@@ -2232,6 +2232,21 @@ my %tests = (
 		  { exclude_dump_test_schema => 1, no_toast_compression => 1, },
 	},
 
+	'CREATE MATERIALIZED VIEW matview_ivm' => {
+		create_order => 21,
+		create_sql   => 'CREATE INCREMENTAL MATERIALIZED VIEW dump_test.matview_ivm (col1) AS
+					   SELECT col1 FROM dump_test.test_table;',
+		regexp => qr/^
+			\QCREATE INCREMENTAL MATERIALIZED VIEW dump_test.matview_ivm AS\E
+			\n\s+\QSELECT test_table.col1\E
+			\n\s+\QFROM dump_test.test_table\E
+			\n\s+\QWITH NO DATA;\E
+			/xm,
+		like =>
+		  { %full_runs, %dump_test_schema_runs, section_pre_data => 1, },
+		unlike => { exclude_dump_test_schema => 1, },
+	},
+
 	'CREATE POLICY p1 ON test_table' => {
 		create_order => 22,
 		create_sql   => 'CREATE POLICY p1 ON dump_test.test_table
-- 
2.17.1


--Multipart=_Fri__4_Feb_2022_01_48_06_+0900_N8BNZpfOR27sWrgY
Content-Type: text/x-diff;
 name="v25-0004-Allow-to-prolong-life-span-of-transition-tables-.patch"
Content-Disposition: attachment;
 filename="v25-0004-Allow-to-prolong-life-span-of-transition-tables-.patch"
Content-Transfer-Encoding: 7bit



^ permalink  raw  reply  [nested|flat] 101+ messages in thread

* [PATCH v29 04/11] Add Incremental View Maintenance support to pg_dump
@ 2020-11-11 08:01  Yugo Nagata <[email protected]>
  0 siblings, 0 replies; 101+ messages in thread

From: Yugo Nagata @ 2020-11-11 08:01 UTC (permalink / raw)

Support CREATE INCREMENTAL MATERIALIZED VIEW syntax.
---
 src/bin/pg_dump/pg_dump.c        | 18 +++++++++++++++---
 src/bin/pg_dump/pg_dump.h        |  1 +
 src/bin/pg_dump/t/002_pg_dump.pl | 15 +++++++++++++++
 3 files changed, 31 insertions(+), 3 deletions(-)

diff --git a/src/bin/pg_dump/pg_dump.c b/src/bin/pg_dump/pg_dump.c
index 65f64c282d..013ead7655 100644
--- a/src/bin/pg_dump/pg_dump.c
+++ b/src/bin/pg_dump/pg_dump.c
@@ -6354,6 +6354,7 @@ getTables(Archive *fout, int *numTables)
 	int			i_relacl;
 	int			i_acldefault;
 	int			i_ispartition;
+	int			i_isivm;
 
 	/*
 	 * Find all the tables and table-like objects.
@@ -6456,10 +6457,17 @@ getTables(Archive *fout, int *numTables)
 
 	if (fout->remoteVersion >= 100000)
 		appendPQExpBufferStr(query,
-							 "c.relispartition AS ispartition ");
+							 "c.relispartition AS ispartition, ");
 	else
 		appendPQExpBufferStr(query,
-							 "false AS ispartition ");
+							 "false AS ispartition, ");
+
+	if (fout->remoteVersion >= 170000)
+		appendPQExpBufferStr(query,
+							 "c.relisivm AS isivm ");
+	else
+		appendPQExpBufferStr(query,
+							 "false AS isivm ");
 
 	/*
 	 * Left join to pg_depend to pick up dependency info linking sequences to
@@ -6568,6 +6576,7 @@ getTables(Archive *fout, int *numTables)
 	i_relacl = PQfnumber(res, "relacl");
 	i_acldefault = PQfnumber(res, "acldefault");
 	i_ispartition = PQfnumber(res, "ispartition");
+	i_isivm = PQfnumber(res, "isivm");
 
 	if (dopt->lockWaitTimeout)
 	{
@@ -6647,6 +6656,7 @@ getTables(Archive *fout, int *numTables)
 			tblinfo[i].amname = pg_strdup(PQgetvalue(res, i, i_amname));
 		tblinfo[i].is_identity_sequence = (strcmp(PQgetvalue(res, i, i_is_identity_sequence), "t") == 0);
 		tblinfo[i].ispartition = (strcmp(PQgetvalue(res, i, i_ispartition), "t") == 0);
+		tblinfo[i].isivm = (strcmp(PQgetvalue(res, i, i_isivm), "t") == 0);
 
 		/* other fields were zeroed above */
 
@@ -15737,9 +15747,11 @@ dumpTableSchema(Archive *fout, const TableInfo *tbinfo)
 			binary_upgrade_set_pg_class_oids(fout, q,
 											 tbinfo->dobj.catId.oid, false);
 
-		appendPQExpBuffer(q, "CREATE %s%s %s",
+		appendPQExpBuffer(q, "CREATE %s%s%s %s",
 						  tbinfo->relpersistence == RELPERSISTENCE_UNLOGGED ?
 						  "UNLOGGED " : "",
+						  tbinfo->relkind == RELKIND_MATVIEW && tbinfo->isivm ?
+						  "INCREMENTAL " : "",
 						  reltypename,
 						  qualrelname);
 
diff --git a/src/bin/pg_dump/pg_dump.h b/src/bin/pg_dump/pg_dump.h
index 9036b13f6a..3705891d25 100644
--- a/src/bin/pg_dump/pg_dump.h
+++ b/src/bin/pg_dump/pg_dump.h
@@ -323,6 +323,7 @@ typedef struct _tableInfo
 
 	int			numParents;		/* number of (immediate) parent tables */
 	struct _tableInfo **parents;	/* TableInfos of immediate parents */
+	bool		isivm;			/* is incrementally maintainable materialized view? */
 
 	/*
 	 * These fields are computed only if we decide the table is interesting
diff --git a/src/bin/pg_dump/t/002_pg_dump.pl b/src/bin/pg_dump/t/002_pg_dump.pl
index 0758fe5ea0..fb2f31e191 100644
--- a/src/bin/pg_dump/t/002_pg_dump.pl
+++ b/src/bin/pg_dump/t/002_pg_dump.pl
@@ -2799,6 +2799,21 @@ my %tests = (
 		},
 	},
 
+	'CREATE MATERIALIZED VIEW matview_ivm' => {
+		create_order => 21,
+		create_sql   => 'CREATE INCREMENTAL MATERIALIZED VIEW dump_test.matview_ivm (col1) AS
+					   SELECT col1 FROM dump_test.test_table;',
+		regexp => qr/^
+			\QCREATE INCREMENTAL MATERIALIZED VIEW dump_test.matview_ivm AS\E
+			\n\s+\QSELECT test_table.col1\E
+			\n\s+\QFROM dump_test.test_table\E
+			\n\s+\QWITH NO DATA;\E
+			/xm,
+		like =>
+		  { %full_runs, %dump_test_schema_runs, section_pre_data => 1, },
+		unlike => { exclude_dump_test_schema => 1, },
+	},
+
 	'CREATE POLICY p1 ON test_table' => {
 		create_order => 22,
 		create_sql => 'CREATE POLICY p1 ON dump_test.test_table
-- 
2.25.1


--Multipart=_Mon__28_Aug_2023_11_52_52_+0900_hj6L5h176QaSGtg7
Content-Type: text/x-diff;
 name="v29-0005-Add-Incremental-View-Maintenance-support-to-psql.patch"
Content-Disposition: attachment;
 filename="v29-0005-Add-Incremental-View-Maintenance-support-to-psql.patch"
Content-Transfer-Encoding: 7bit



^ permalink  raw  reply  [nested|flat] 101+ messages in thread

* [PATCH v27 4/9] Add Incremental View Maintenance support to pg_dump
@ 2020-11-11 08:01  Yugo Nagata <[email protected]>
  0 siblings, 0 replies; 101+ messages in thread

From: Yugo Nagata @ 2020-11-11 08:01 UTC (permalink / raw)

Support CREATE INCREMENTAL MATERIALIZED VIEW syntax.
---
 src/bin/pg_dump/pg_dump.c        | 18 +++++++++++++++---
 src/bin/pg_dump/pg_dump.h        |  1 +
 src/bin/pg_dump/t/002_pg_dump.pl | 15 +++++++++++++++
 3 files changed, 31 insertions(+), 3 deletions(-)

diff --git a/src/bin/pg_dump/pg_dump.c b/src/bin/pg_dump/pg_dump.c
index 969e2a7a46..6340b3e2b7 100644
--- a/src/bin/pg_dump/pg_dump.c
+++ b/src/bin/pg_dump/pg_dump.c
@@ -6089,6 +6089,7 @@ getTables(Archive *fout, int *numTables)
 	int			i_relacl;
 	int			i_acldefault;
 	int			i_ispartition;
+	int			i_isivm;
 
 	/*
 	 * Find all the tables and table-like objects.
@@ -6191,10 +6192,17 @@ getTables(Archive *fout, int *numTables)
 
 	if (fout->remoteVersion >= 100000)
 		appendPQExpBufferStr(query,
-							 "c.relispartition AS ispartition ");
+							 "c.relispartition AS ispartition, ");
 	else
 		appendPQExpBufferStr(query,
-							 "false AS ispartition ");
+							 "false AS ispartition, ");
+
+	if (fout->remoteVersion >= 150000)
+		appendPQExpBufferStr(query,
+							 "c.relisivm AS isivm ");
+	else
+		appendPQExpBufferStr(query,
+							 "false AS isivm ");
 
 	/*
 	 * Left join to pg_depend to pick up dependency info linking sequences to
@@ -6303,6 +6311,7 @@ getTables(Archive *fout, int *numTables)
 	i_relacl = PQfnumber(res, "relacl");
 	i_acldefault = PQfnumber(res, "acldefault");
 	i_ispartition = PQfnumber(res, "ispartition");
+	i_isivm = PQfnumber(res, "isivm");
 
 	if (dopt->lockWaitTimeout)
 	{
@@ -6380,6 +6389,7 @@ getTables(Archive *fout, int *numTables)
 			tblinfo[i].amname = pg_strdup(PQgetvalue(res, i, i_amname));
 		tblinfo[i].is_identity_sequence = (strcmp(PQgetvalue(res, i, i_is_identity_sequence), "t") == 0);
 		tblinfo[i].ispartition = (strcmp(PQgetvalue(res, i, i_ispartition), "t") == 0);
+		tblinfo[i].isivm = (strcmp(PQgetvalue(res, i, i_isivm), "t") == 0);
 
 		/* other fields were zeroed above */
 
@@ -15115,9 +15125,11 @@ dumpTableSchema(Archive *fout, const TableInfo *tbinfo)
 			binary_upgrade_set_pg_class_oids(fout, q,
 											 tbinfo->dobj.catId.oid, false);
 
-		appendPQExpBuffer(q, "CREATE %s%s %s",
+		appendPQExpBuffer(q, "CREATE %s%s%s %s",
 						  tbinfo->relpersistence == RELPERSISTENCE_UNLOGGED ?
 						  "UNLOGGED " : "",
+						  tbinfo->relkind == RELKIND_MATVIEW && tbinfo->isivm ?
+						  "INCREMENTAL " : "",
 						  reltypename,
 						  qualrelname);
 
diff --git a/src/bin/pg_dump/pg_dump.h b/src/bin/pg_dump/pg_dump.h
index 1d21c2906f..0b798ad5de 100644
--- a/src/bin/pg_dump/pg_dump.h
+++ b/src/bin/pg_dump/pg_dump.h
@@ -318,6 +318,7 @@ typedef struct _tableInfo
 	bool		dummy_view;		/* view's real definition must be postponed */
 	bool		postponed_def;	/* matview must be postponed into post-data */
 	bool		ispartition;	/* is table a partition? */
+	bool		isivm;			/* is incrementally maintainable materialized view? */
 
 	/*
 	 * These fields are computed only if we decide the table is interesting
diff --git a/src/bin/pg_dump/t/002_pg_dump.pl b/src/bin/pg_dump/t/002_pg_dump.pl
index c65c92bfb0..3655727472 100644
--- a/src/bin/pg_dump/t/002_pg_dump.pl
+++ b/src/bin/pg_dump/t/002_pg_dump.pl
@@ -2295,6 +2295,21 @@ my %tests = (
 		  { exclude_dump_test_schema => 1, no_toast_compression => 1, },
 	},
 
+	'CREATE MATERIALIZED VIEW matview_ivm' => {
+		create_order => 21,
+		create_sql   => 'CREATE INCREMENTAL MATERIALIZED VIEW dump_test.matview_ivm (col1) AS
+					   SELECT col1 FROM dump_test.test_table;',
+		regexp => qr/^
+			\QCREATE INCREMENTAL MATERIALIZED VIEW dump_test.matview_ivm AS\E
+			\n\s+\QSELECT test_table.col1\E
+			\n\s+\QFROM dump_test.test_table\E
+			\n\s+\QWITH NO DATA;\E
+			/xm,
+		like =>
+		  { %full_runs, %dump_test_schema_runs, section_pre_data => 1, },
+		unlike => { exclude_dump_test_schema => 1, },
+	},
+
 	'CREATE POLICY p1 ON test_table' => {
 		create_order => 22,
 		create_sql   => 'CREATE POLICY p1 ON dump_test.test_table
-- 
2.17.1


--Multipart=_Fri__22_Apr_2022_14_58_01_+0900_MN3L/o2YUVF2g4zw
Content-Type: text/x-diff;
 name="v27-0005-Add-Incremental-View-Maintenance-support-to-psql.patch"
Content-Disposition: attachment;
 filename="v27-0005-Add-Incremental-View-Maintenance-support-to-psql.patch"
Content-Transfer-Encoding: 7bit



^ permalink  raw  reply  [nested|flat] 101+ messages in thread

* [PATCH v29 04/11] Add Incremental View Maintenance support to pg_dump
@ 2020-11-11 08:01  Yugo Nagata <[email protected]>
  0 siblings, 0 replies; 101+ messages in thread

From: Yugo Nagata @ 2020-11-11 08:01 UTC (permalink / raw)

Support CREATE INCREMENTAL MATERIALIZED VIEW syntax.
---
 src/bin/pg_dump/pg_dump.c        | 18 +++++++++++++++---
 src/bin/pg_dump/pg_dump.h        |  2 ++
 src/bin/pg_dump/t/002_pg_dump.pl | 18 ++++++++++++++++++
 3 files changed, 35 insertions(+), 3 deletions(-)

diff --git a/src/bin/pg_dump/pg_dump.c b/src/bin/pg_dump/pg_dump.c
index 65f64c282d..013ead7655 100644
--- a/src/bin/pg_dump/pg_dump.c
+++ b/src/bin/pg_dump/pg_dump.c
@@ -6354,6 +6354,7 @@ getTables(Archive *fout, int *numTables)
 	int			i_relacl;
 	int			i_acldefault;
 	int			i_ispartition;
+	int			i_isivm;
 
 	/*
 	 * Find all the tables and table-like objects.
@@ -6456,10 +6457,17 @@ getTables(Archive *fout, int *numTables)
 
 	if (fout->remoteVersion >= 100000)
 		appendPQExpBufferStr(query,
-							 "c.relispartition AS ispartition ");
+							 "c.relispartition AS ispartition, ");
 	else
 		appendPQExpBufferStr(query,
-							 "false AS ispartition ");
+							 "false AS ispartition, ");
+
+	if (fout->remoteVersion >= 170000)
+		appendPQExpBufferStr(query,
+							 "c.relisivm AS isivm ");
+	else
+		appendPQExpBufferStr(query,
+							 "false AS isivm ");
 
 	/*
 	 * Left join to pg_depend to pick up dependency info linking sequences to
@@ -6568,6 +6576,7 @@ getTables(Archive *fout, int *numTables)
 	i_relacl = PQfnumber(res, "relacl");
 	i_acldefault = PQfnumber(res, "acldefault");
 	i_ispartition = PQfnumber(res, "ispartition");
+	i_isivm = PQfnumber(res, "isivm");
 
 	if (dopt->lockWaitTimeout)
 	{
@@ -6647,6 +6656,7 @@ getTables(Archive *fout, int *numTables)
 			tblinfo[i].amname = pg_strdup(PQgetvalue(res, i, i_amname));
 		tblinfo[i].is_identity_sequence = (strcmp(PQgetvalue(res, i, i_is_identity_sequence), "t") == 0);
 		tblinfo[i].ispartition = (strcmp(PQgetvalue(res, i, i_ispartition), "t") == 0);
+		tblinfo[i].isivm = (strcmp(PQgetvalue(res, i, i_isivm), "t") == 0);
 
 		/* other fields were zeroed above */
 
@@ -15737,9 +15747,11 @@ dumpTableSchema(Archive *fout, const TableInfo *tbinfo)
 			binary_upgrade_set_pg_class_oids(fout, q,
 											 tbinfo->dobj.catId.oid, false);
 
-		appendPQExpBuffer(q, "CREATE %s%s %s",
+		appendPQExpBuffer(q, "CREATE %s%s%s %s",
 						  tbinfo->relpersistence == RELPERSISTENCE_UNLOGGED ?
 						  "UNLOGGED " : "",
+						  tbinfo->relkind == RELKIND_MATVIEW && tbinfo->isivm ?
+						  "INCREMENTAL " : "",
 						  reltypename,
 						  qualrelname);
 
diff --git a/src/bin/pg_dump/pg_dump.h b/src/bin/pg_dump/pg_dump.h
index 9036b13f6a..71ea246abd 100644
--- a/src/bin/pg_dump/pg_dump.h
+++ b/src/bin/pg_dump/pg_dump.h
@@ -324,6 +324,8 @@ typedef struct _tableInfo
 	int			numParents;		/* number of (immediate) parent tables */
 	struct _tableInfo **parents;	/* TableInfos of immediate parents */
 
+	bool		isivm;			/* is incrementally maintainable materialized view? */
+
 	/*
 	 * These fields are computed only if we decide the table is interesting
 	 * (it's either a table to dump, or a direct parent of a dumpable table).
diff --git a/src/bin/pg_dump/t/002_pg_dump.pl b/src/bin/pg_dump/t/002_pg_dump.pl
index 0758fe5ea0..f83c317268 100644
--- a/src/bin/pg_dump/t/002_pg_dump.pl
+++ b/src/bin/pg_dump/t/002_pg_dump.pl
@@ -2799,6 +2799,24 @@ my %tests = (
 		},
 	},
 
+	'CREATE MATERIALIZED VIEW matview_ivm' => {
+		create_order => 21,
+		create_sql   => 'CREATE INCREMENTAL MATERIALIZED VIEW dump_test.matview_ivm (col1) AS
+					   SELECT col1 FROM dump_test.test_table;',
+		regexp => qr/^
+			\QCREATE INCREMENTAL MATERIALIZED VIEW dump_test.matview_ivm AS\E
+			\n\s+\QSELECT col1\E
+			\n\s+\QFROM dump_test.test_table\E
+			\n\s+\QWITH NO DATA;\E
+			/xm,
+		like =>
+		  { %full_runs, %dump_test_schema_runs, section_pre_data => 1, },
+		unlike => {
+			exclude_dump_test_schema => 1,
+			only_dump_measurement => 1,
+		},
+	},
+
 	'CREATE POLICY p1 ON test_table' => {
 		create_order => 22,
 		create_sql => 'CREATE POLICY p1 ON dump_test.test_table
-- 
2.25.1


--Multipart=_Mon__28_Aug_2023_16_05_30_+0900_b1OvQD_3A3ZMTGvj
Content-Type: text/x-diff;
 name="v29-0005-Add-Incremental-View-Maintenance-support-to-psql.patch"
Content-Disposition: attachment;
 filename="v29-0005-Add-Incremental-View-Maintenance-support-to-psql.patch"
Content-Transfer-Encoding: 7bit



^ permalink  raw  reply  [nested|flat] 101+ messages in thread

* [PATCH v27 4/9] Add Incremental View Maintenance support to pg_dump
@ 2020-11-11 08:01  Yugo Nagata <[email protected]>
  0 siblings, 0 replies; 101+ messages in thread

From: Yugo Nagata @ 2020-11-11 08:01 UTC (permalink / raw)

Support CREATE INCREMENTAL MATERIALIZED VIEW syntax.
---
 src/bin/pg_dump/pg_dump.c        | 18 +++++++++++++++---
 src/bin/pg_dump/pg_dump.h        |  1 +
 src/bin/pg_dump/t/002_pg_dump.pl | 15 +++++++++++++++
 3 files changed, 31 insertions(+), 3 deletions(-)

diff --git a/src/bin/pg_dump/pg_dump.c b/src/bin/pg_dump/pg_dump.c
index 969e2a7a46..3c764076d2 100644
--- a/src/bin/pg_dump/pg_dump.c
+++ b/src/bin/pg_dump/pg_dump.c
@@ -6089,6 +6089,7 @@ getTables(Archive *fout, int *numTables)
 	int			i_relacl;
 	int			i_acldefault;
 	int			i_ispartition;
+	int			i_isivm;
 
 	/*
 	 * Find all the tables and table-like objects.
@@ -6191,10 +6192,17 @@ getTables(Archive *fout, int *numTables)
 
 	if (fout->remoteVersion >= 100000)
 		appendPQExpBufferStr(query,
-							 "c.relispartition AS ispartition ");
+							 "c.relispartition AS ispartition, ");
 	else
 		appendPQExpBufferStr(query,
-							 "false AS ispartition ");
+							 "false AS ispartition, ");
+
+	if (fout->remoteVersion >= 160000)
+		appendPQExpBufferStr(query,
+							 "c.relisivm AS isivm ");
+	else
+		appendPQExpBufferStr(query,
+							 "false AS isivm ");
 
 	/*
 	 * Left join to pg_depend to pick up dependency info linking sequences to
@@ -6303,6 +6311,7 @@ getTables(Archive *fout, int *numTables)
 	i_relacl = PQfnumber(res, "relacl");
 	i_acldefault = PQfnumber(res, "acldefault");
 	i_ispartition = PQfnumber(res, "ispartition");
+	i_isivm = PQfnumber(res, "isivm");
 
 	if (dopt->lockWaitTimeout)
 	{
@@ -6380,6 +6389,7 @@ getTables(Archive *fout, int *numTables)
 			tblinfo[i].amname = pg_strdup(PQgetvalue(res, i, i_amname));
 		tblinfo[i].is_identity_sequence = (strcmp(PQgetvalue(res, i, i_is_identity_sequence), "t") == 0);
 		tblinfo[i].ispartition = (strcmp(PQgetvalue(res, i, i_ispartition), "t") == 0);
+		tblinfo[i].isivm = (strcmp(PQgetvalue(res, i, i_isivm), "t") == 0);
 
 		/* other fields were zeroed above */
 
@@ -15115,9 +15125,11 @@ dumpTableSchema(Archive *fout, const TableInfo *tbinfo)
 			binary_upgrade_set_pg_class_oids(fout, q,
 											 tbinfo->dobj.catId.oid, false);
 
-		appendPQExpBuffer(q, "CREATE %s%s %s",
+		appendPQExpBuffer(q, "CREATE %s%s%s %s",
 						  tbinfo->relpersistence == RELPERSISTENCE_UNLOGGED ?
 						  "UNLOGGED " : "",
+						  tbinfo->relkind == RELKIND_MATVIEW && tbinfo->isivm ?
+						  "INCREMENTAL " : "",
 						  reltypename,
 						  qualrelname);
 
diff --git a/src/bin/pg_dump/pg_dump.h b/src/bin/pg_dump/pg_dump.h
index 1d21c2906f..0b798ad5de 100644
--- a/src/bin/pg_dump/pg_dump.h
+++ b/src/bin/pg_dump/pg_dump.h
@@ -318,6 +318,7 @@ typedef struct _tableInfo
 	bool		dummy_view;		/* view's real definition must be postponed */
 	bool		postponed_def;	/* matview must be postponed into post-data */
 	bool		ispartition;	/* is table a partition? */
+	bool		isivm;			/* is incrementally maintainable materialized view? */
 
 	/*
 	 * These fields are computed only if we decide the table is interesting
diff --git a/src/bin/pg_dump/t/002_pg_dump.pl b/src/bin/pg_dump/t/002_pg_dump.pl
index c65c92bfb0..3655727472 100644
--- a/src/bin/pg_dump/t/002_pg_dump.pl
+++ b/src/bin/pg_dump/t/002_pg_dump.pl
@@ -2295,6 +2295,21 @@ my %tests = (
 		  { exclude_dump_test_schema => 1, no_toast_compression => 1, },
 	},
 
+	'CREATE MATERIALIZED VIEW matview_ivm' => {
+		create_order => 21,
+		create_sql   => 'CREATE INCREMENTAL MATERIALIZED VIEW dump_test.matview_ivm (col1) AS
+					   SELECT col1 FROM dump_test.test_table;',
+		regexp => qr/^
+			\QCREATE INCREMENTAL MATERIALIZED VIEW dump_test.matview_ivm AS\E
+			\n\s+\QSELECT test_table.col1\E
+			\n\s+\QFROM dump_test.test_table\E
+			\n\s+\QWITH NO DATA;\E
+			/xm,
+		like =>
+		  { %full_runs, %dump_test_schema_runs, section_pre_data => 1, },
+		unlike => { exclude_dump_test_schema => 1, },
+	},
+
 	'CREATE POLICY p1 ON test_table' => {
 		create_order => 22,
 		create_sql   => 'CREATE POLICY p1 ON dump_test.test_table
-- 
2.17.1


--Multipart=_Fri__22_Apr_2022_11_29_39_+0900_ZOAC7UMt5e8j1Nvx
Content-Type: text/x-diff;
 name="v27-0005-Add-Incremental-View-Maintenance-support-to-psql.patch"
Content-Disposition: attachment;
 filename="v27-0005-Add-Incremental-View-Maintenance-support-to-psql.patch"
Content-Transfer-Encoding: 7bit



^ permalink  raw  reply  [nested|flat] 101+ messages in thread

* [PATCH v37 04/11] Add Incremental View Maintenance support to pg_dump
@ 2020-11-11 08:01  Yugo Nagata <[email protected]>
  0 siblings, 0 replies; 101+ messages in thread

From: Yugo Nagata @ 2020-11-11 08:01 UTC (permalink / raw)

Support CREATE INCREMENTAL MATERIALIZED VIEW syntax.
---
 src/bin/pg_dump/pg_dump.c        | 18 +++++++++++++++---
 src/bin/pg_dump/pg_dump.h        |  2 ++
 src/bin/pg_dump/t/002_pg_dump.pl | 18 ++++++++++++++++++
 3 files changed, 35 insertions(+), 3 deletions(-)

diff --git a/src/bin/pg_dump/pg_dump.c b/src/bin/pg_dump/pg_dump.c
index d56dcc701ce..b1d37675f66 100644
--- a/src/bin/pg_dump/pg_dump.c
+++ b/src/bin/pg_dump/pg_dump.c
@@ -7323,6 +7323,7 @@ getTables(Archive *fout, int *numTables)
 	int			i_relacl;
 	int			i_acldefault;
 	int			i_ispartition;
+	int			i_isivm;
 
 	/*
 	 * Find all the tables and table-like objects.
@@ -7432,10 +7433,17 @@ getTables(Archive *fout, int *numTables)
 
 	if (fout->remoteVersion >= 100000)
 		appendPQExpBufferStr(query,
-							 "c.relispartition AS ispartition ");
+							 "c.relispartition AS ispartition, ");
 	else
 		appendPQExpBufferStr(query,
-							 "false AS ispartition ");
+							 "false AS ispartition, ");
+
+	if (fout->remoteVersion >= 180000)
+		appendPQExpBufferStr(query,
+							 "c.relisivm AS isivm ");
+	else
+		appendPQExpBufferStr(query,
+							 "false AS isivm ");
 
 	/*
 	 * Left join to pg_depend to pick up dependency info linking sequences to
@@ -7548,6 +7556,7 @@ getTables(Archive *fout, int *numTables)
 	i_relacl = PQfnumber(res, "relacl");
 	i_acldefault = PQfnumber(res, "acldefault");
 	i_ispartition = PQfnumber(res, "ispartition");
+	i_isivm = PQfnumber(res, "isivm");
 
 	if (dopt->lockWaitTimeout)
 	{
@@ -7630,6 +7639,7 @@ getTables(Archive *fout, int *numTables)
 			tblinfo[i].amname = pg_strdup(PQgetvalue(res, i, i_amname));
 		tblinfo[i].is_identity_sequence = (strcmp(PQgetvalue(res, i, i_is_identity_sequence), "t") == 0);
 		tblinfo[i].ispartition = (strcmp(PQgetvalue(res, i, i_ispartition), "t") == 0);
+		tblinfo[i].isivm = (strcmp(PQgetvalue(res, i, i_isivm), "t") == 0);
 
 		/* other fields were zeroed above */
 
@@ -17452,10 +17462,12 @@ dumpTableSchema(Archive *fout, const TableInfo *tbinfo)
 		 * PostgreSQL 18 has disabled UNLOGGED for partitioned tables, so
 		 * ignore it when dumping if it was set in this case.
 		 */
-		appendPQExpBuffer(q, "CREATE %s%s %s",
+		appendPQExpBuffer(q, "CREATE %s%s%s %s",
 						  (tbinfo->relpersistence == RELPERSISTENCE_UNLOGGED &&
 						   tbinfo->relkind != RELKIND_PARTITIONED_TABLE) ?
 						  "UNLOGGED " : "",
+						  tbinfo->relkind == RELKIND_MATVIEW && tbinfo->isivm ?
+						  "INCREMENTAL " : "",
 						  reltypename,
 						  qualrelname);
 
diff --git a/src/bin/pg_dump/pg_dump.h b/src/bin/pg_dump/pg_dump.h
index 5a6726d8b12..4408c504323 100644
--- a/src/bin/pg_dump/pg_dump.h
+++ b/src/bin/pg_dump/pg_dump.h
@@ -347,6 +347,8 @@ typedef struct _tableInfo
 	int			numParents;		/* number of (immediate) parent tables */
 	struct _tableInfo **parents;	/* TableInfos of immediate parents */
 
+	bool		isivm;			/* is incrementally maintainable materialized view? */
+
 	/*
 	 * These fields are computed only if we decide the table is interesting
 	 * (it's either a table to dump, or a direct parent of a dumpable table).
diff --git a/src/bin/pg_dump/t/002_pg_dump.pl b/src/bin/pg_dump/t/002_pg_dump.pl
index 3ee9fda50e4..7c38d3023f0 100644
--- a/src/bin/pg_dump/t/002_pg_dump.pl
+++ b/src/bin/pg_dump/t/002_pg_dump.pl
@@ -2992,6 +2992,24 @@ my %tests = (
 		},
 	},
 
+	'CREATE MATERIALIZED VIEW matview_ivm' => {
+		create_order => 21,
+		create_sql   => 'CREATE INCREMENTAL MATERIALIZED VIEW dump_test.matview_ivm (col1) AS
+					   SELECT col1 FROM dump_test.test_table;',
+		regexp => qr/^
+			\QCREATE INCREMENTAL MATERIALIZED VIEW dump_test.matview_ivm AS\E
+			\n\s+\QSELECT col1\E
+			\n\s+\QFROM dump_test.test_table\E
+			\n\s+\QWITH NO DATA;\E
+			/xm,
+		like =>
+		  { %full_runs, %dump_test_schema_runs, section_pre_data => 1, },
+		unlike => {
+			exclude_dump_test_schema => 1,
+			only_dump_measurement => 1,
+		},
+	},
+
 	'CREATE POLICY p1 ON test_table' => {
 		create_order => 22,
 		create_sql => 'CREATE POLICY p1 ON dump_test.test_table
-- 
2.43.0


--Multipart=_Fri__29_May_2026_23_14_17_+0900_Te0o73X2VqYK57Gd
Content-Type: text/x-diff;
 name="v37-0003-Allow-to-prolong-life-span-of-transition-tables-.patch"
Content-Disposition: attachment;
 filename="v37-0003-Allow-to-prolong-life-span-of-transition-tables-.patch"
Content-Transfer-Encoding: 7bit



^ permalink  raw  reply  [nested|flat] 101+ messages in thread

* [PATCH v32 04/11] Add Incremental View Maintenance support to pg_dump
@ 2020-11-11 08:01  Yugo Nagata <[email protected]>
  0 siblings, 0 replies; 101+ messages in thread

From: Yugo Nagata @ 2020-11-11 08:01 UTC (permalink / raw)

Support CREATE INCREMENTAL MATERIALIZED VIEW syntax.
---
 src/bin/pg_dump/pg_dump.c        | 18 +++++++++++++++---
 src/bin/pg_dump/pg_dump.h        |  2 ++
 src/bin/pg_dump/t/002_pg_dump.pl | 18 ++++++++++++++++++
 3 files changed, 35 insertions(+), 3 deletions(-)

diff --git a/src/bin/pg_dump/pg_dump.c b/src/bin/pg_dump/pg_dump.c
index b1c4c3ec7f..92a8cbf244 100644
--- a/src/bin/pg_dump/pg_dump.c
+++ b/src/bin/pg_dump/pg_dump.c
@@ -6677,6 +6677,7 @@ getTables(Archive *fout, int *numTables)
 	int			i_relacl;
 	int			i_acldefault;
 	int			i_ispartition;
+	int			i_isivm;
 
 	/*
 	 * Find all the tables and table-like objects.
@@ -6779,10 +6780,17 @@ getTables(Archive *fout, int *numTables)
 
 	if (fout->remoteVersion >= 100000)
 		appendPQExpBufferStr(query,
-							 "c.relispartition AS ispartition ");
+							 "c.relispartition AS ispartition, ");
 	else
 		appendPQExpBufferStr(query,
-							 "false AS ispartition ");
+							 "false AS ispartition, ");
+
+	if (fout->remoteVersion >= 170000)
+		appendPQExpBufferStr(query,
+							 "c.relisivm AS isivm ");
+	else
+		appendPQExpBufferStr(query,
+							 "false AS isivm ");
 
 	/*
 	 * Left join to pg_depend to pick up dependency info linking sequences to
@@ -6891,6 +6899,7 @@ getTables(Archive *fout, int *numTables)
 	i_relacl = PQfnumber(res, "relacl");
 	i_acldefault = PQfnumber(res, "acldefault");
 	i_ispartition = PQfnumber(res, "ispartition");
+	i_isivm = PQfnumber(res, "isivm");
 
 	if (dopt->lockWaitTimeout)
 	{
@@ -6970,6 +6979,7 @@ getTables(Archive *fout, int *numTables)
 			tblinfo[i].amname = pg_strdup(PQgetvalue(res, i, i_amname));
 		tblinfo[i].is_identity_sequence = (strcmp(PQgetvalue(res, i, i_is_identity_sequence), "t") == 0);
 		tblinfo[i].ispartition = (strcmp(PQgetvalue(res, i, i_ispartition), "t") == 0);
+		tblinfo[i].isivm = (strcmp(PQgetvalue(res, i, i_isivm), "t") == 0);
 
 		/* other fields were zeroed above */
 
@@ -16023,9 +16033,11 @@ dumpTableSchema(Archive *fout, const TableInfo *tbinfo)
 			binary_upgrade_set_pg_class_oids(fout, q,
 											 tbinfo->dobj.catId.oid, false);
 
-		appendPQExpBuffer(q, "CREATE %s%s %s",
+		appendPQExpBuffer(q, "CREATE %s%s%s %s",
 						  tbinfo->relpersistence == RELPERSISTENCE_UNLOGGED ?
 						  "UNLOGGED " : "",
+						  tbinfo->relkind == RELKIND_MATVIEW && tbinfo->isivm ?
+						  "INCREMENTAL " : "",
 						  reltypename,
 						  qualrelname);
 
diff --git a/src/bin/pg_dump/pg_dump.h b/src/bin/pg_dump/pg_dump.h
index 9bc93520b4..4e240f8832 100644
--- a/src/bin/pg_dump/pg_dump.h
+++ b/src/bin/pg_dump/pg_dump.h
@@ -325,6 +325,8 @@ typedef struct _tableInfo
 	int			numParents;		/* number of (immediate) parent tables */
 	struct _tableInfo **parents;	/* TableInfos of immediate parents */
 
+	bool		isivm;			/* is incrementally maintainable materialized view? */
+
 	/*
 	 * These fields are computed only if we decide the table is interesting
 	 * (it's either a table to dump, or a direct parent of a dumpable table).
diff --git a/src/bin/pg_dump/t/002_pg_dump.pl b/src/bin/pg_dump/t/002_pg_dump.pl
index f0410ce6a1..a119ec8db1 100644
--- a/src/bin/pg_dump/t/002_pg_dump.pl
+++ b/src/bin/pg_dump/t/002_pg_dump.pl
@@ -2832,6 +2832,24 @@ my %tests = (
 		},
 	},
 
+	'CREATE MATERIALIZED VIEW matview_ivm' => {
+		create_order => 21,
+		create_sql   => 'CREATE INCREMENTAL MATERIALIZED VIEW dump_test.matview_ivm (col1) AS
+					   SELECT col1 FROM dump_test.test_table;',
+		regexp => qr/^
+			\QCREATE INCREMENTAL MATERIALIZED VIEW dump_test.matview_ivm AS\E
+			\n\s+\QSELECT col1\E
+			\n\s+\QFROM dump_test.test_table\E
+			\n\s+\QWITH NO DATA;\E
+			/xm,
+		like =>
+		  { %full_runs, %dump_test_schema_runs, section_pre_data => 1, },
+		unlike => {
+			exclude_dump_test_schema => 1,
+			only_dump_measurement => 1,
+		},
+	},
+
 	'CREATE POLICY p1 ON test_table' => {
 		create_order => 22,
 		create_sql => 'CREATE POLICY p1 ON dump_test.test_table
-- 
2.25.1


--Multipart=_Sun__31_Mar_2024_22_59_31_+0900_msknEviJj08_wgqO
Content-Type: text/x-diff;
 name="v32-0005-Add-Incremental-View-Maintenance-support-to-psql.patch"
Content-Disposition: attachment;
 filename="v32-0005-Add-Incremental-View-Maintenance-support-to-psql.patch"
Content-Transfer-Encoding: 7bit



^ permalink  raw  reply  [nested|flat] 101+ messages in thread

* [PATCH v38 04/11] Add Incremental View Maintenance support to pg_dump
@ 2020-11-11 08:01  Yugo Nagata <[email protected]>
  0 siblings, 0 replies; 101+ messages in thread

From: Yugo Nagata @ 2020-11-11 08:01 UTC (permalink / raw)

Support CREATE INCREMENTAL MATERIALIZED VIEW syntax.
---
 src/bin/pg_dump/pg_dump.c        | 18 +++++++++++++++---
 src/bin/pg_dump/pg_dump.h        |  2 ++
 src/bin/pg_dump/t/002_pg_dump.pl | 18 ++++++++++++++++++
 3 files changed, 35 insertions(+), 3 deletions(-)

diff --git a/src/bin/pg_dump/pg_dump.c b/src/bin/pg_dump/pg_dump.c
index c56437d6057..f7420e0db41 100644
--- a/src/bin/pg_dump/pg_dump.c
+++ b/src/bin/pg_dump/pg_dump.c
@@ -7323,6 +7323,7 @@ getTables(Archive *fout, int *numTables)
 	int			i_relacl;
 	int			i_acldefault;
 	int			i_ispartition;
+	int			i_isivm;
 
 	/*
 	 * Find all the tables and table-like objects.
@@ -7432,10 +7433,17 @@ getTables(Archive *fout, int *numTables)
 
 	if (fout->remoteVersion >= 100000)
 		appendPQExpBufferStr(query,
-							 "c.relispartition AS ispartition ");
+							 "c.relispartition AS ispartition, ");
 	else
 		appendPQExpBufferStr(query,
-							 "false AS ispartition ");
+							 "false AS ispartition, ");
+
+	if (fout->remoteVersion >= 200000)
+		appendPQExpBufferStr(query,
+							 "c.relisivm AS isivm ");
+	else
+		appendPQExpBufferStr(query,
+							 "false AS isivm ");
 
 	/*
 	 * Left join to pg_depend to pick up dependency info linking sequences to
@@ -7548,6 +7556,7 @@ getTables(Archive *fout, int *numTables)
 	i_relacl = PQfnumber(res, "relacl");
 	i_acldefault = PQfnumber(res, "acldefault");
 	i_ispartition = PQfnumber(res, "ispartition");
+	i_isivm = PQfnumber(res, "isivm");
 
 	if (dopt->lockWaitTimeout)
 	{
@@ -7630,6 +7639,7 @@ getTables(Archive *fout, int *numTables)
 			tblinfo[i].amname = pg_strdup(PQgetvalue(res, i, i_amname));
 		tblinfo[i].is_identity_sequence = (strcmp(PQgetvalue(res, i, i_is_identity_sequence), "t") == 0);
 		tblinfo[i].ispartition = (strcmp(PQgetvalue(res, i, i_ispartition), "t") == 0);
+		tblinfo[i].isivm = (strcmp(PQgetvalue(res, i, i_isivm), "t") == 0);
 
 		/* other fields were zeroed above */
 
@@ -17452,10 +17462,12 @@ dumpTableSchema(Archive *fout, const TableInfo *tbinfo)
 		 * PostgreSQL 18 has disabled UNLOGGED for partitioned tables, so
 		 * ignore it when dumping if it was set in this case.
 		 */
-		appendPQExpBuffer(q, "CREATE %s%s %s",
+		appendPQExpBuffer(q, "CREATE %s%s%s %s",
 						  (tbinfo->relpersistence == RELPERSISTENCE_UNLOGGED &&
 						   tbinfo->relkind != RELKIND_PARTITIONED_TABLE) ?
 						  "UNLOGGED " : "",
+						  tbinfo->relkind == RELKIND_MATVIEW && tbinfo->isivm ?
+						  "INCREMENTAL " : "",
 						  reltypename,
 						  qualrelname);
 
diff --git a/src/bin/pg_dump/pg_dump.h b/src/bin/pg_dump/pg_dump.h
index 5a6726d8b12..4408c504323 100644
--- a/src/bin/pg_dump/pg_dump.h
+++ b/src/bin/pg_dump/pg_dump.h
@@ -347,6 +347,8 @@ typedef struct _tableInfo
 	int			numParents;		/* number of (immediate) parent tables */
 	struct _tableInfo **parents;	/* TableInfos of immediate parents */
 
+	bool		isivm;			/* is incrementally maintainable materialized view? */
+
 	/*
 	 * These fields are computed only if we decide the table is interesting
 	 * (it's either a table to dump, or a direct parent of a dumpable table).
diff --git a/src/bin/pg_dump/t/002_pg_dump.pl b/src/bin/pg_dump/t/002_pg_dump.pl
index 9258948b583..8abde57e4f3 100644
--- a/src/bin/pg_dump/t/002_pg_dump.pl
+++ b/src/bin/pg_dump/t/002_pg_dump.pl
@@ -3033,6 +3033,24 @@ my %tests = (
 		},
 	},
 
+	'CREATE MATERIALIZED VIEW matview_ivm' => {
+		create_order => 21,
+		create_sql   => 'CREATE INCREMENTAL MATERIALIZED VIEW dump_test.matview_ivm (col1) AS
+					   SELECT col1 FROM dump_test.test_table;',
+		regexp => qr/^
+			\QCREATE INCREMENTAL MATERIALIZED VIEW dump_test.matview_ivm AS\E
+			\n\s+\QSELECT col1\E
+			\n\s+\QFROM dump_test.test_table\E
+			\n\s+\QWITH NO DATA;\E
+			/xm,
+		like =>
+		  { %full_runs, %dump_test_schema_runs, section_pre_data => 1, },
+		unlike => {
+			exclude_dump_test_schema => 1,
+			only_dump_measurement => 1,
+		},
+	},
+
 	'CREATE POLICY p1 ON test_table' => {
 		create_order => 22,
 		create_sql => 'CREATE POLICY p1 ON dump_test.test_table
-- 
2.43.0


--Multipart=_Wed__1_Jul_2026_00_04_01_+0900_OVSy2WWK_9aByzDJ
Content-Type: text/x-diff;
 name="v38-0003-Allow-to-prolong-life-span-of-transition-tables-.patch"
Content-Disposition: attachment;
 filename="v38-0003-Allow-to-prolong-life-span-of-transition-tables-.patch"
Content-Transfer-Encoding: 7bit



^ permalink  raw  reply  [nested|flat] 101+ messages in thread

* [PATCH v31 04/11] Add Incremental View Maintenance support to pg_dump
@ 2020-11-11 08:01  Yugo Nagata <[email protected]>
  0 siblings, 0 replies; 101+ messages in thread

From: Yugo Nagata @ 2020-11-11 08:01 UTC (permalink / raw)

Support CREATE INCREMENTAL MATERIALIZED VIEW syntax.
---
 src/bin/pg_dump/pg_dump.c        | 18 +++++++++++++++---
 src/bin/pg_dump/pg_dump.h        |  2 ++
 src/bin/pg_dump/t/002_pg_dump.pl | 18 ++++++++++++++++++
 3 files changed, 35 insertions(+), 3 deletions(-)

diff --git a/src/bin/pg_dump/pg_dump.c b/src/bin/pg_dump/pg_dump.c
index b1c4c3ec7f..92a8cbf244 100644
--- a/src/bin/pg_dump/pg_dump.c
+++ b/src/bin/pg_dump/pg_dump.c
@@ -6677,6 +6677,7 @@ getTables(Archive *fout, int *numTables)
 	int			i_relacl;
 	int			i_acldefault;
 	int			i_ispartition;
+	int			i_isivm;
 
 	/*
 	 * Find all the tables and table-like objects.
@@ -6779,10 +6780,17 @@ getTables(Archive *fout, int *numTables)
 
 	if (fout->remoteVersion >= 100000)
 		appendPQExpBufferStr(query,
-							 "c.relispartition AS ispartition ");
+							 "c.relispartition AS ispartition, ");
 	else
 		appendPQExpBufferStr(query,
-							 "false AS ispartition ");
+							 "false AS ispartition, ");
+
+	if (fout->remoteVersion >= 170000)
+		appendPQExpBufferStr(query,
+							 "c.relisivm AS isivm ");
+	else
+		appendPQExpBufferStr(query,
+							 "false AS isivm ");
 
 	/*
 	 * Left join to pg_depend to pick up dependency info linking sequences to
@@ -6891,6 +6899,7 @@ getTables(Archive *fout, int *numTables)
 	i_relacl = PQfnumber(res, "relacl");
 	i_acldefault = PQfnumber(res, "acldefault");
 	i_ispartition = PQfnumber(res, "ispartition");
+	i_isivm = PQfnumber(res, "isivm");
 
 	if (dopt->lockWaitTimeout)
 	{
@@ -6970,6 +6979,7 @@ getTables(Archive *fout, int *numTables)
 			tblinfo[i].amname = pg_strdup(PQgetvalue(res, i, i_amname));
 		tblinfo[i].is_identity_sequence = (strcmp(PQgetvalue(res, i, i_is_identity_sequence), "t") == 0);
 		tblinfo[i].ispartition = (strcmp(PQgetvalue(res, i, i_ispartition), "t") == 0);
+		tblinfo[i].isivm = (strcmp(PQgetvalue(res, i, i_isivm), "t") == 0);
 
 		/* other fields were zeroed above */
 
@@ -16023,9 +16033,11 @@ dumpTableSchema(Archive *fout, const TableInfo *tbinfo)
 			binary_upgrade_set_pg_class_oids(fout, q,
 											 tbinfo->dobj.catId.oid, false);
 
-		appendPQExpBuffer(q, "CREATE %s%s %s",
+		appendPQExpBuffer(q, "CREATE %s%s%s %s",
 						  tbinfo->relpersistence == RELPERSISTENCE_UNLOGGED ?
 						  "UNLOGGED " : "",
+						  tbinfo->relkind == RELKIND_MATVIEW && tbinfo->isivm ?
+						  "INCREMENTAL " : "",
 						  reltypename,
 						  qualrelname);
 
diff --git a/src/bin/pg_dump/pg_dump.h b/src/bin/pg_dump/pg_dump.h
index 9bc93520b4..4e240f8832 100644
--- a/src/bin/pg_dump/pg_dump.h
+++ b/src/bin/pg_dump/pg_dump.h
@@ -325,6 +325,8 @@ typedef struct _tableInfo
 	int			numParents;		/* number of (immediate) parent tables */
 	struct _tableInfo **parents;	/* TableInfos of immediate parents */
 
+	bool		isivm;			/* is incrementally maintainable materialized view? */
+
 	/*
 	 * These fields are computed only if we decide the table is interesting
 	 * (it's either a table to dump, or a direct parent of a dumpable table).
diff --git a/src/bin/pg_dump/t/002_pg_dump.pl b/src/bin/pg_dump/t/002_pg_dump.pl
index f0410ce6a1..a119ec8db1 100644
--- a/src/bin/pg_dump/t/002_pg_dump.pl
+++ b/src/bin/pg_dump/t/002_pg_dump.pl
@@ -2832,6 +2832,24 @@ my %tests = (
 		},
 	},
 
+	'CREATE MATERIALIZED VIEW matview_ivm' => {
+		create_order => 21,
+		create_sql   => 'CREATE INCREMENTAL MATERIALIZED VIEW dump_test.matview_ivm (col1) AS
+					   SELECT col1 FROM dump_test.test_table;',
+		regexp => qr/^
+			\QCREATE INCREMENTAL MATERIALIZED VIEW dump_test.matview_ivm AS\E
+			\n\s+\QSELECT col1\E
+			\n\s+\QFROM dump_test.test_table\E
+			\n\s+\QWITH NO DATA;\E
+			/xm,
+		like =>
+		  { %full_runs, %dump_test_schema_runs, section_pre_data => 1, },
+		unlike => {
+			exclude_dump_test_schema => 1,
+			only_dump_measurement => 1,
+		},
+	},
+
 	'CREATE POLICY p1 ON test_table' => {
 		create_order => 22,
 		create_sql => 'CREATE POLICY p1 ON dump_test.test_table
-- 
2.25.1


--Multipart=_Fri__29_Mar_2024_23_47_00_+0900_KGpmmDOIs1266Ib1
Content-Type: text/x-diff;
 name="v31-0005-Add-Incremental-View-Maintenance-support-to-psql.patch"
Content-Disposition: attachment;
 filename="v31-0005-Add-Incremental-View-Maintenance-support-to-psql.patch"
Content-Transfer-Encoding: 7bit



^ permalink  raw  reply  [nested|flat] 101+ messages in thread

* [PATCH v39 4/8] Add Incremental View Maintenance support to pg_dump
@ 2020-11-11 08:01  Yugo Nagata <[email protected]>
  0 siblings, 0 replies; 101+ messages in thread

From: Yugo Nagata @ 2020-11-11 08:01 UTC (permalink / raw)

Support CREATE INCREMENTAL MATERIALIZED VIEW syntax.
---
 src/bin/pg_dump/pg_dump.c        | 14 +++++++++++++-
 src/bin/pg_dump/pg_dump.h        |  2 ++
 src/bin/pg_dump/t/002_pg_dump.pl | 18 ++++++++++++++++++
 3 files changed, 33 insertions(+), 1 deletion(-)

diff --git a/src/bin/pg_dump/pg_dump.c b/src/bin/pg_dump/pg_dump.c
index f67daf85911..9a5f65659e3 100644
--- a/src/bin/pg_dump/pg_dump.c
+++ b/src/bin/pg_dump/pg_dump.c
@@ -7196,6 +7196,7 @@ getTables(Archive *fout, int *numTables)
 	int			i_relacl;
 	int			i_acldefault;
 	int			i_ispartition;
+	int			i_isivm;
 
 	/*
 	 * Find all the tables and table-like objects.
@@ -7277,6 +7278,13 @@ getTables(Archive *fout, int *numTables)
 	appendPQExpBufferStr(query,
 						 "c.relispartition AS ispartition ");
 
+	if (fout->remoteVersion >= 200000)
+		appendPQExpBufferStr(query,
+							 "c.relisivm AS isivm ");
+	else
+		appendPQExpBufferStr(query,
+							 "false AS isivm ");
+
 	/*
 	 * Left join to pg_depend to pick up dependency info linking sequences to
 	 * their owning column, if any (note this dependency is AUTO except for
@@ -7387,6 +7395,7 @@ getTables(Archive *fout, int *numTables)
 	i_relacl = PQfnumber(res, "relacl");
 	i_acldefault = PQfnumber(res, "acldefault");
 	i_ispartition = PQfnumber(res, "ispartition");
+	i_isivm = PQfnumber(res, "isivm");
 
 	if (dopt->lockWaitTimeout)
 	{
@@ -7469,6 +7478,7 @@ getTables(Archive *fout, int *numTables)
 			tblinfo[i].amname = pg_strdup(PQgetvalue(res, i, i_amname));
 		tblinfo[i].is_identity_sequence = (strcmp(PQgetvalue(res, i, i_is_identity_sequence), "t") == 0);
 		tblinfo[i].ispartition = (strcmp(PQgetvalue(res, i, i_ispartition), "t") == 0);
+		tblinfo[i].isivm = (strcmp(PQgetvalue(res, i, i_isivm), "t") == 0);
 
 		/* other fields were zeroed above */
 
@@ -17202,10 +17212,12 @@ dumpTableSchema(Archive *fout, const TableInfo *tbinfo)
 		 * PostgreSQL 18 has disabled UNLOGGED for partitioned tables, so
 		 * ignore it when dumping if it was set in this case.
 		 */
-		appendPQExpBuffer(q, "CREATE %s%s %s",
+		appendPQExpBuffer(q, "CREATE %s%s%s %s",
 						  (tbinfo->relpersistence == RELPERSISTENCE_UNLOGGED &&
 						   tbinfo->relkind != RELKIND_PARTITIONED_TABLE) ?
 						  "UNLOGGED " : "",
+						  tbinfo->relkind == RELKIND_MATVIEW && tbinfo->isivm ?
+						  "INCREMENTAL " : "",
 						  reltypename,
 						  qualrelname);
 
diff --git a/src/bin/pg_dump/pg_dump.h b/src/bin/pg_dump/pg_dump.h
index 5a6726d8b12..4408c504323 100644
--- a/src/bin/pg_dump/pg_dump.h
+++ b/src/bin/pg_dump/pg_dump.h
@@ -347,6 +347,8 @@ typedef struct _tableInfo
 	int			numParents;		/* number of (immediate) parent tables */
 	struct _tableInfo **parents;	/* TableInfos of immediate parents */
 
+	bool		isivm;			/* is incrementally maintainable materialized view? */
+
 	/*
 	 * These fields are computed only if we decide the table is interesting
 	 * (it's either a table to dump, or a direct parent of a dumpable table).
diff --git a/src/bin/pg_dump/t/002_pg_dump.pl b/src/bin/pg_dump/t/002_pg_dump.pl
index 9258948b583..8abde57e4f3 100644
--- a/src/bin/pg_dump/t/002_pg_dump.pl
+++ b/src/bin/pg_dump/t/002_pg_dump.pl
@@ -3033,6 +3033,24 @@ my %tests = (
 		},
 	},
 
+	'CREATE MATERIALIZED VIEW matview_ivm' => {
+		create_order => 21,
+		create_sql   => 'CREATE INCREMENTAL MATERIALIZED VIEW dump_test.matview_ivm (col1) AS
+					   SELECT col1 FROM dump_test.test_table;',
+		regexp => qr/^
+			\QCREATE INCREMENTAL MATERIALIZED VIEW dump_test.matview_ivm AS\E
+			\n\s+\QSELECT col1\E
+			\n\s+\QFROM dump_test.test_table\E
+			\n\s+\QWITH NO DATA;\E
+			/xm,
+		like =>
+		  { %full_runs, %dump_test_schema_runs, section_pre_data => 1, },
+		unlike => {
+			exclude_dump_test_schema => 1,
+			only_dump_measurement => 1,
+		},
+	},
+
 	'CREATE POLICY p1 ON test_table' => {
 		create_order => 22,
 		create_sql => 'CREATE POLICY p1 ON dump_test.test_table
-- 
2.43.0


--Multipart=_Fri__3_Jul_2026_19_11_16_+0900_CskxSIu_iGcDMEyM
Content-Type: text/x-diff;
 name="v39-0003-Allow-to-prolong-life-span-of-transition-tables-.patch"
Content-Disposition: attachment;
 filename="v39-0003-Allow-to-prolong-life-span-of-transition-tables-.patch"
Content-Transfer-Encoding: 7bit



^ permalink  raw  reply  [nested|flat] 101+ messages in thread

* [PATCH v29 04/11] Add Incremental View Maintenance support to pg_dump
@ 2020-11-11 08:01  Yugo Nagata <[email protected]>
  0 siblings, 0 replies; 101+ messages in thread

From: Yugo Nagata @ 2020-11-11 08:01 UTC (permalink / raw)

Support CREATE INCREMENTAL MATERIALIZED VIEW syntax.
---
 src/bin/pg_dump/pg_dump.c        | 18 +++++++++++++++---
 src/bin/pg_dump/pg_dump.h        |  1 +
 src/bin/pg_dump/t/002_pg_dump.pl | 15 +++++++++++++++
 3 files changed, 31 insertions(+), 3 deletions(-)

diff --git a/src/bin/pg_dump/pg_dump.c b/src/bin/pg_dump/pg_dump.c
index 65f64c282d..013ead7655 100644
--- a/src/bin/pg_dump/pg_dump.c
+++ b/src/bin/pg_dump/pg_dump.c
@@ -6354,6 +6354,7 @@ getTables(Archive *fout, int *numTables)
 	int			i_relacl;
 	int			i_acldefault;
 	int			i_ispartition;
+	int			i_isivm;
 
 	/*
 	 * Find all the tables and table-like objects.
@@ -6456,10 +6457,17 @@ getTables(Archive *fout, int *numTables)
 
 	if (fout->remoteVersion >= 100000)
 		appendPQExpBufferStr(query,
-							 "c.relispartition AS ispartition ");
+							 "c.relispartition AS ispartition, ");
 	else
 		appendPQExpBufferStr(query,
-							 "false AS ispartition ");
+							 "false AS ispartition, ");
+
+	if (fout->remoteVersion >= 170000)
+		appendPQExpBufferStr(query,
+							 "c.relisivm AS isivm ");
+	else
+		appendPQExpBufferStr(query,
+							 "false AS isivm ");
 
 	/*
 	 * Left join to pg_depend to pick up dependency info linking sequences to
@@ -6568,6 +6576,7 @@ getTables(Archive *fout, int *numTables)
 	i_relacl = PQfnumber(res, "relacl");
 	i_acldefault = PQfnumber(res, "acldefault");
 	i_ispartition = PQfnumber(res, "ispartition");
+	i_isivm = PQfnumber(res, "isivm");
 
 	if (dopt->lockWaitTimeout)
 	{
@@ -6647,6 +6656,7 @@ getTables(Archive *fout, int *numTables)
 			tblinfo[i].amname = pg_strdup(PQgetvalue(res, i, i_amname));
 		tblinfo[i].is_identity_sequence = (strcmp(PQgetvalue(res, i, i_is_identity_sequence), "t") == 0);
 		tblinfo[i].ispartition = (strcmp(PQgetvalue(res, i, i_ispartition), "t") == 0);
+		tblinfo[i].isivm = (strcmp(PQgetvalue(res, i, i_isivm), "t") == 0);
 
 		/* other fields were zeroed above */
 
@@ -15737,9 +15747,11 @@ dumpTableSchema(Archive *fout, const TableInfo *tbinfo)
 			binary_upgrade_set_pg_class_oids(fout, q,
 											 tbinfo->dobj.catId.oid, false);
 
-		appendPQExpBuffer(q, "CREATE %s%s %s",
+		appendPQExpBuffer(q, "CREATE %s%s%s %s",
 						  tbinfo->relpersistence == RELPERSISTENCE_UNLOGGED ?
 						  "UNLOGGED " : "",
+						  tbinfo->relkind == RELKIND_MATVIEW && tbinfo->isivm ?
+						  "INCREMENTAL " : "",
 						  reltypename,
 						  qualrelname);
 
diff --git a/src/bin/pg_dump/pg_dump.h b/src/bin/pg_dump/pg_dump.h
index 9036b13f6a..3705891d25 100644
--- a/src/bin/pg_dump/pg_dump.h
+++ b/src/bin/pg_dump/pg_dump.h
@@ -323,6 +323,7 @@ typedef struct _tableInfo
 
 	int			numParents;		/* number of (immediate) parent tables */
 	struct _tableInfo **parents;	/* TableInfos of immediate parents */
+	bool		isivm;			/* is incrementally maintainable materialized view? */
 
 	/*
 	 * These fields are computed only if we decide the table is interesting
diff --git a/src/bin/pg_dump/t/002_pg_dump.pl b/src/bin/pg_dump/t/002_pg_dump.pl
index 0758fe5ea0..fb2f31e191 100644
--- a/src/bin/pg_dump/t/002_pg_dump.pl
+++ b/src/bin/pg_dump/t/002_pg_dump.pl
@@ -2799,6 +2799,21 @@ my %tests = (
 		},
 	},
 
+	'CREATE MATERIALIZED VIEW matview_ivm' => {
+		create_order => 21,
+		create_sql   => 'CREATE INCREMENTAL MATERIALIZED VIEW dump_test.matview_ivm (col1) AS
+					   SELECT col1 FROM dump_test.test_table;',
+		regexp => qr/^
+			\QCREATE INCREMENTAL MATERIALIZED VIEW dump_test.matview_ivm AS\E
+			\n\s+\QSELECT test_table.col1\E
+			\n\s+\QFROM dump_test.test_table\E
+			\n\s+\QWITH NO DATA;\E
+			/xm,
+		like =>
+		  { %full_runs, %dump_test_schema_runs, section_pre_data => 1, },
+		unlike => { exclude_dump_test_schema => 1, },
+	},
+
 	'CREATE POLICY p1 ON test_table' => {
 		create_order => 22,
 		create_sql => 'CREATE POLICY p1 ON dump_test.test_table
-- 
2.25.1


--Multipart=_Mon__28_Aug_2023_11_52_52_+0900_hj6L5h176QaSGtg7
Content-Type: text/x-diff;
 name="v29-0005-Add-Incremental-View-Maintenance-support-to-psql.patch"
Content-Disposition: attachment;
 filename="v29-0005-Add-Incremental-View-Maintenance-support-to-psql.patch"
Content-Transfer-Encoding: 7bit



^ permalink  raw  reply  [nested|flat] 101+ messages in thread

* [PATCH v30 04/11] Add Incremental View Maintenance support to pg_dump
@ 2020-11-11 08:01  Yugo Nagata <[email protected]>
  0 siblings, 0 replies; 101+ messages in thread

From: Yugo Nagata @ 2020-11-11 08:01 UTC (permalink / raw)

Support CREATE INCREMENTAL MATERIALIZED VIEW syntax.
---
 src/bin/pg_dump/pg_dump.c        | 18 +++++++++++++++---
 src/bin/pg_dump/pg_dump.h        |  2 ++
 src/bin/pg_dump/t/002_pg_dump.pl | 18 ++++++++++++++++++
 3 files changed, 35 insertions(+), 3 deletions(-)

diff --git a/src/bin/pg_dump/pg_dump.c b/src/bin/pg_dump/pg_dump.c
index 2225a12718..009958fdd4 100644
--- a/src/bin/pg_dump/pg_dump.c
+++ b/src/bin/pg_dump/pg_dump.c
@@ -6648,6 +6648,7 @@ getTables(Archive *fout, int *numTables)
 	int			i_relacl;
 	int			i_acldefault;
 	int			i_ispartition;
+	int			i_isivm;
 
 	/*
 	 * Find all the tables and table-like objects.
@@ -6750,10 +6751,17 @@ getTables(Archive *fout, int *numTables)
 
 	if (fout->remoteVersion >= 100000)
 		appendPQExpBufferStr(query,
-							 "c.relispartition AS ispartition ");
+							 "c.relispartition AS ispartition, ");
 	else
 		appendPQExpBufferStr(query,
-							 "false AS ispartition ");
+							 "false AS ispartition, ");
+
+	if (fout->remoteVersion >= 170000)
+		appendPQExpBufferStr(query,
+							 "c.relisivm AS isivm ");
+	else
+		appendPQExpBufferStr(query,
+							 "false AS isivm ");
 
 	/*
 	 * Left join to pg_depend to pick up dependency info linking sequences to
@@ -6862,6 +6870,7 @@ getTables(Archive *fout, int *numTables)
 	i_relacl = PQfnumber(res, "relacl");
 	i_acldefault = PQfnumber(res, "acldefault");
 	i_ispartition = PQfnumber(res, "ispartition");
+	i_isivm = PQfnumber(res, "isivm");
 
 	if (dopt->lockWaitTimeout)
 	{
@@ -6941,6 +6950,7 @@ getTables(Archive *fout, int *numTables)
 			tblinfo[i].amname = pg_strdup(PQgetvalue(res, i, i_amname));
 		tblinfo[i].is_identity_sequence = (strcmp(PQgetvalue(res, i, i_is_identity_sequence), "t") == 0);
 		tblinfo[i].ispartition = (strcmp(PQgetvalue(res, i, i_ispartition), "t") == 0);
+		tblinfo[i].isivm = (strcmp(PQgetvalue(res, i, i_isivm), "t") == 0);
 
 		/* other fields were zeroed above */
 
@@ -15977,9 +15987,11 @@ dumpTableSchema(Archive *fout, const TableInfo *tbinfo)
 			binary_upgrade_set_pg_class_oids(fout, q,
 											 tbinfo->dobj.catId.oid, false);
 
-		appendPQExpBuffer(q, "CREATE %s%s %s",
+		appendPQExpBuffer(q, "CREATE %s%s%s %s",
 						  tbinfo->relpersistence == RELPERSISTENCE_UNLOGGED ?
 						  "UNLOGGED " : "",
+						  tbinfo->relkind == RELKIND_MATVIEW && tbinfo->isivm ?
+						  "INCREMENTAL " : "",
 						  reltypename,
 						  qualrelname);
 
diff --git a/src/bin/pg_dump/pg_dump.h b/src/bin/pg_dump/pg_dump.h
index 77db42e354..7f05cbaec6 100644
--- a/src/bin/pg_dump/pg_dump.h
+++ b/src/bin/pg_dump/pg_dump.h
@@ -325,6 +325,8 @@ typedef struct _tableInfo
 	int			numParents;		/* number of (immediate) parent tables */
 	struct _tableInfo **parents;	/* TableInfos of immediate parents */
 
+	bool		isivm;			/* is incrementally maintainable materialized view? */
+
 	/*
 	 * These fields are computed only if we decide the table is interesting
 	 * (it's either a table to dump, or a direct parent of a dumpable table).
diff --git a/src/bin/pg_dump/t/002_pg_dump.pl b/src/bin/pg_dump/t/002_pg_dump.pl
index 00b5092713..fff9419347 100644
--- a/src/bin/pg_dump/t/002_pg_dump.pl
+++ b/src/bin/pg_dump/t/002_pg_dump.pl
@@ -2832,6 +2832,24 @@ my %tests = (
 		},
 	},
 
+	'CREATE MATERIALIZED VIEW matview_ivm' => {
+		create_order => 21,
+		create_sql   => 'CREATE INCREMENTAL MATERIALIZED VIEW dump_test.matview_ivm (col1) AS
+					   SELECT col1 FROM dump_test.test_table;',
+		regexp => qr/^
+			\QCREATE INCREMENTAL MATERIALIZED VIEW dump_test.matview_ivm AS\E
+			\n\s+\QSELECT col1\E
+			\n\s+\QFROM dump_test.test_table\E
+			\n\s+\QWITH NO DATA;\E
+			/xm,
+		like =>
+		  { %full_runs, %dump_test_schema_runs, section_pre_data => 1, },
+		unlike => {
+			exclude_dump_test_schema => 1,
+			only_dump_measurement => 1,
+		},
+	},
+
 	'CREATE POLICY p1 ON test_table' => {
 		create_order => 22,
 		create_sql => 'CREATE POLICY p1 ON dump_test.test_table
-- 
2.25.1


--Multipart=_Mon__4_Mar_2024_11_58_46_+0900_UaponF/qQhQrVCFt
Content-Type: text/x-diff;
 name="v30-0005-Add-Incremental-View-Maintenance-support-to-psql.patch"
Content-Disposition: attachment;
 filename="v30-0005-Add-Incremental-View-Maintenance-support-to-psql.patch"
Content-Transfer-Encoding: 7bit



^ permalink  raw  reply  [nested|flat] 101+ messages in thread

* [PATCH v29 04/11] Add Incremental View Maintenance support to pg_dump
@ 2020-11-11 08:01  Yugo Nagata <[email protected]>
  0 siblings, 0 replies; 101+ messages in thread

From: Yugo Nagata @ 2020-11-11 08:01 UTC (permalink / raw)

Support CREATE INCREMENTAL MATERIALIZED VIEW syntax.
---
 src/bin/pg_dump/pg_dump.c        | 18 +++++++++++++++---
 src/bin/pg_dump/pg_dump.h        |  2 ++
 src/bin/pg_dump/t/002_pg_dump.pl | 18 ++++++++++++++++++
 3 files changed, 35 insertions(+), 3 deletions(-)

diff --git a/src/bin/pg_dump/pg_dump.c b/src/bin/pg_dump/pg_dump.c
index 65f64c282d..013ead7655 100644
--- a/src/bin/pg_dump/pg_dump.c
+++ b/src/bin/pg_dump/pg_dump.c
@@ -6354,6 +6354,7 @@ getTables(Archive *fout, int *numTables)
 	int			i_relacl;
 	int			i_acldefault;
 	int			i_ispartition;
+	int			i_isivm;
 
 	/*
 	 * Find all the tables and table-like objects.
@@ -6456,10 +6457,17 @@ getTables(Archive *fout, int *numTables)
 
 	if (fout->remoteVersion >= 100000)
 		appendPQExpBufferStr(query,
-							 "c.relispartition AS ispartition ");
+							 "c.relispartition AS ispartition, ");
 	else
 		appendPQExpBufferStr(query,
-							 "false AS ispartition ");
+							 "false AS ispartition, ");
+
+	if (fout->remoteVersion >= 170000)
+		appendPQExpBufferStr(query,
+							 "c.relisivm AS isivm ");
+	else
+		appendPQExpBufferStr(query,
+							 "false AS isivm ");
 
 	/*
 	 * Left join to pg_depend to pick up dependency info linking sequences to
@@ -6568,6 +6576,7 @@ getTables(Archive *fout, int *numTables)
 	i_relacl = PQfnumber(res, "relacl");
 	i_acldefault = PQfnumber(res, "acldefault");
 	i_ispartition = PQfnumber(res, "ispartition");
+	i_isivm = PQfnumber(res, "isivm");
 
 	if (dopt->lockWaitTimeout)
 	{
@@ -6647,6 +6656,7 @@ getTables(Archive *fout, int *numTables)
 			tblinfo[i].amname = pg_strdup(PQgetvalue(res, i, i_amname));
 		tblinfo[i].is_identity_sequence = (strcmp(PQgetvalue(res, i, i_is_identity_sequence), "t") == 0);
 		tblinfo[i].ispartition = (strcmp(PQgetvalue(res, i, i_ispartition), "t") == 0);
+		tblinfo[i].isivm = (strcmp(PQgetvalue(res, i, i_isivm), "t") == 0);
 
 		/* other fields were zeroed above */
 
@@ -15737,9 +15747,11 @@ dumpTableSchema(Archive *fout, const TableInfo *tbinfo)
 			binary_upgrade_set_pg_class_oids(fout, q,
 											 tbinfo->dobj.catId.oid, false);
 
-		appendPQExpBuffer(q, "CREATE %s%s %s",
+		appendPQExpBuffer(q, "CREATE %s%s%s %s",
 						  tbinfo->relpersistence == RELPERSISTENCE_UNLOGGED ?
 						  "UNLOGGED " : "",
+						  tbinfo->relkind == RELKIND_MATVIEW && tbinfo->isivm ?
+						  "INCREMENTAL " : "",
 						  reltypename,
 						  qualrelname);
 
diff --git a/src/bin/pg_dump/pg_dump.h b/src/bin/pg_dump/pg_dump.h
index 9036b13f6a..71ea246abd 100644
--- a/src/bin/pg_dump/pg_dump.h
+++ b/src/bin/pg_dump/pg_dump.h
@@ -324,6 +324,8 @@ typedef struct _tableInfo
 	int			numParents;		/* number of (immediate) parent tables */
 	struct _tableInfo **parents;	/* TableInfos of immediate parents */
 
+	bool		isivm;			/* is incrementally maintainable materialized view? */
+
 	/*
 	 * These fields are computed only if we decide the table is interesting
 	 * (it's either a table to dump, or a direct parent of a dumpable table).
diff --git a/src/bin/pg_dump/t/002_pg_dump.pl b/src/bin/pg_dump/t/002_pg_dump.pl
index 0758fe5ea0..f83c317268 100644
--- a/src/bin/pg_dump/t/002_pg_dump.pl
+++ b/src/bin/pg_dump/t/002_pg_dump.pl
@@ -2799,6 +2799,24 @@ my %tests = (
 		},
 	},
 
+	'CREATE MATERIALIZED VIEW matview_ivm' => {
+		create_order => 21,
+		create_sql   => 'CREATE INCREMENTAL MATERIALIZED VIEW dump_test.matview_ivm (col1) AS
+					   SELECT col1 FROM dump_test.test_table;',
+		regexp => qr/^
+			\QCREATE INCREMENTAL MATERIALIZED VIEW dump_test.matview_ivm AS\E
+			\n\s+\QSELECT col1\E
+			\n\s+\QFROM dump_test.test_table\E
+			\n\s+\QWITH NO DATA;\E
+			/xm,
+		like =>
+		  { %full_runs, %dump_test_schema_runs, section_pre_data => 1, },
+		unlike => {
+			exclude_dump_test_schema => 1,
+			only_dump_measurement => 1,
+		},
+	},
+
 	'CREATE POLICY p1 ON test_table' => {
 		create_order => 22,
 		create_sql => 'CREATE POLICY p1 ON dump_test.test_table
-- 
2.25.1


--Multipart=_Mon__28_Aug_2023_16_05_30_+0900_b1OvQD_3A3ZMTGvj
Content-Type: text/x-diff;
 name="v29-0005-Add-Incremental-View-Maintenance-support-to-psql.patch"
Content-Disposition: attachment;
 filename="v29-0005-Add-Incremental-View-Maintenance-support-to-psql.patch"
Content-Transfer-Encoding: 7bit



^ permalink  raw  reply  [nested|flat] 101+ messages in thread

* [PATCH v26 07/10] Add Incremental View Maintenance support
@ 2020-12-22 09:40  Yugo Nagata <[email protected]>
  0 siblings, 0 replies; 101+ messages in thread

From: Yugo Nagata @ 2020-12-22 09:40 UTC (permalink / raw)

In this implementation, AFTER triggers are used to collect
tuplestores containing transition table contents. When multiple tables
are changed, multiple AFTER triggers are invoked, then the final AFTER
trigger performs actual update of the matview. In addition, BEFORE
triggers are also used to handle global information for view
maintenance. To calculate view deltas, we need both pre-state and
post-state of base tables. Post-update states are available in AFTER
trigger, and pre-update states can be calculated by filtering inserted
tuples using cmin/xmin system columns, and append deleted tuples which
are contained in an old transition table.

This patch also allows self-join, simultaneous updates of more than
one base table, and multiple updates of the same base table.

Incrementally Maintainable Materialized Views (IMMV) can contain
duplicated tuples. Also, DISTINCT clause is supported. When IMMV is
created with DISTINCT, multiplicity of tuples is counted and stored
in  "__ivm_count__" column, which is a hidden column of IMMV.
The value in __ivm_count__ is updated when IMMV is maintained
incrementally. A tuple in IMMV can be removed if and only if the
count becomes zero.
---
 src/backend/access/transam/xact.c   |    5 +
 src/backend/commands/createas.c     |  746 +++++++++++++
 src/backend/commands/indexcmds.c    |   40 +
 src/backend/commands/matview.c      | 1555 ++++++++++++++++++++++++++-
 src/backend/commands/tablecmds.c    |    9 +
 src/backend/nodes/copyfuncs.c       |    1 +
 src/backend/nodes/equalfuncs.c      |    1 +
 src/backend/nodes/outfuncs.c        |    1 +
 src/backend/nodes/readfuncs.c       |    1 +
 src/backend/parser/parse_relation.c |   18 +-
 src/backend/rewrite/rewriteDefine.c |    3 +-
 src/include/catalog/pg_proc.dat     |    8 +
 src/include/commands/createas.h     |    6 +
 src/include/commands/matview.h      |    8 +
 src/include/nodes/parsenodes.h      |    2 +
 15 files changed, 2364 insertions(+), 40 deletions(-)

diff --git a/src/backend/access/transam/xact.c b/src/backend/access/transam/xact.c
index 8964ddf3eb..5d9ab6b1f9 100644
--- a/src/backend/access/transam/xact.c
+++ b/src/backend/access/transam/xact.c
@@ -36,6 +36,7 @@
 #include "catalog/pg_enum.h"
 #include "catalog/storage.h"
 #include "commands/async.h"
+#include "commands/matview.h"
 #include "commands/tablecmds.h"
 #include "commands/trigger.h"
 #include "common/pg_prng.h"
@@ -2777,6 +2778,7 @@ AbortTransaction(void)
 	AtAbort_Notify();
 	AtEOXact_RelationMap(false, is_parallel_worker);
 	AtAbort_Twophase();
+	AtAbort_IVM();
 
 	/*
 	 * Advertise the fact that we aborted in pg_xact (assuming that we got as
@@ -5017,6 +5019,9 @@ AbortSubTransaction(void)
 	AbortBufferIO();
 	UnlockBuffers();
 
+	/* Clean up hash entries for incremental view maintenance */
+	AtAbort_IVM();
+
 	/* Reset WAL record construction state */
 	XLogResetInsertion();
 
diff --git a/src/backend/commands/createas.c b/src/backend/commands/createas.c
index 9abbb6b555..1fbcede7aa 100644
--- a/src/backend/commands/createas.c
+++ b/src/backend/commands/createas.c
@@ -32,24 +32,41 @@
 #include "access/xact.h"
 #include "access/xlog.h"
 #include "catalog/namespace.h"
+#include "catalog/index.h"
+#include "catalog/pg_constraint.h"
+#include "catalog/pg_inherits.h"
+#include "catalog/pg_trigger.h"
+#include "catalog/pg_type.h"
 #include "catalog/toasting.h"
 #include "commands/createas.h"
+#include "commands/defrem.h"
 #include "commands/matview.h"
 #include "commands/prepare.h"
 #include "commands/tablecmds.h"
+#include "commands/tablespace.h"
+#include "commands/trigger.h"
 #include "commands/view.h"
 #include "miscadmin.h"
+#include "optimizer/clauses.h"
+#include "optimizer/optimizer.h"
 #include "nodes/makefuncs.h"
 #include "nodes/nodeFuncs.h"
+#include "parser/parser.h"
+#include "parser/parsetree.h"
 #include "parser/parse_clause.h"
+#include "parser/parse_func.h"
+#include "parser/parse_type.h"
 #include "rewrite/rewriteHandler.h"
+#include "rewrite/rewriteManip.h"
 #include "storage/smgr.h"
 #include "tcop/tcopprot.h"
 #include "utils/builtins.h"
+#include "utils/fmgroids.h"
 #include "utils/lsyscache.h"
 #include "utils/rel.h"
 #include "utils/rls.h"
 #include "utils/snapmgr.h"
+#include "utils/syscache.h"
 
 typedef struct
 {
@@ -73,6 +90,13 @@ static bool intorel_receive(TupleTableSlot *slot, DestReceiver *self);
 static void intorel_shutdown(DestReceiver *self);
 static void intorel_destroy(DestReceiver *self);
 
+static void CreateIvmTriggersOnBaseTablesRecurse(Query *qry, Node *node, Oid matviewOid,
+									 Relids *relids, bool ex_lock);
+static void CreateIvmTrigger(Oid relOid, Oid viewOid, int16 type, int16 timing, bool ex_lock);
+static void check_ivm_restriction(Node *node);
+static bool check_ivm_restriction_walker(Node *node, void *context);
+static Bitmapset *get_primary_key_attnos_from_query(Query *qry, List **constraintList, bool is_create);
+static Bitmapset *get_primary_key_attnos_from_query(Query *query, List **constraintList, bool is_create);
 
 /*
  * create_ctas_internal
@@ -108,6 +132,8 @@ create_ctas_internal(List *attrList, IntoClause *into)
 	create->oncommit = into->onCommit;
 	create->tablespacename = into->tableSpaceName;
 	create->if_not_exists = false;
+	/* Using Materialized view only */
+	create->ivm = into->ivm;
 	create->accessMethod = into->accessMethod;
 
 	/*
@@ -282,6 +308,21 @@ ExecCreateTableAs(ParseState *pstate, CreateTableAsStmt *stmt,
 		save_nestlevel = NewGUCNestLevel();
 	}
 
+	if (is_matview && into->ivm)
+	{
+		/* check if the query is supported in IMMV definition */
+		if (contain_mutable_functions((Node *) query))
+			ereport(ERROR,
+					(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+					 errmsg("mutable function is not supported on incrementally maintainable materialized view"),
+					 errhint("functions must be marked IMMUTABLE")));
+
+		check_ivm_restriction((Node *) query);
+
+		/* For IMMV, we need to rewrite matview query */
+		query = rewriteQueryForIMMV(query, into->colNames);
+	}
+
 	if (into->skipData)
 	{
 		/*
@@ -358,11 +399,74 @@ ExecCreateTableAs(ParseState *pstate, CreateTableAsStmt *stmt,
 
 		/* Restore userid and security context */
 		SetUserIdAndSecContext(save_userid, save_sec_context);
+
+		if (into->ivm)
+		{
+			Oid matviewOid = address.objectId;
+			Relation matviewRel = table_open(matviewOid, NoLock);
+
+			/*
+			 * Mark relisivm field, if it's a matview and into->ivm is true.
+			 */
+			SetMatViewIVMState(matviewRel, true);
+
+			if (!into->skipData)
+			{
+				/* Create an index on incremental maintainable materialized view, if possible */
+				CreateIndexOnIMMV((Query *) into->viewQuery, matviewRel, true);
+
+				/* Create triggers on incremental maintainable materialized view */
+				CreateIvmTriggersOnBaseTables((Query *) into->viewQuery, matviewOid, true);
+			}
+			table_close(matviewRel, NoLock);
+		}
 	}
 
 	return address;
 }
 
+/*
+ * rewriteQueryForIMMV -- rewrite view definition query for IMMV
+ *
+ * count(*) is added for counting distinct tuples in views.
+ */
+Query *
+rewriteQueryForIMMV(Query *query, List *colNames)
+{
+	Query *rewritten;
+
+	TargetEntry *tle;
+	Node *node;
+	ParseState *pstate = make_parsestate(NULL);
+	FuncCall *fn;
+
+	rewritten = copyObject(query);
+	pstate->p_expr_kind = EXPR_KIND_SELECT_TARGET;
+
+	/*
+	 * Convert DISTINCT to GROUP BY and add count(*) for counting distinct
+	 * tuples in views.
+	 */
+	if (rewritten->distinctClause)
+	{
+		rewritten->groupClause = transformDistinctClause(NULL, &rewritten->targetList, rewritten->sortClause, false);
+
+		fn = makeFuncCall(list_make1(makeString("count")), NIL, COERCE_EXPLICIT_CALL, -1);
+		fn->agg_star = true;
+
+		node = ParseFuncOrColumn(pstate, fn->funcname, NIL, NULL, fn, false, -1);
+
+		tle = makeTargetEntry((Expr *) node,
+								list_length(rewritten->targetList) + 1,
+								pstrdup("__ivm_count__"),
+								false);
+		rewritten->targetList = lappend(rewritten->targetList, tle);
+		rewritten->hasAggs = true;
+	}
+
+	return rewritten;
+}
+
 /*
  * GetIntoRelEFlags --- compute executor flags needed for CREATE TABLE AS
  *
@@ -623,3 +727,645 @@ intorel_destroy(DestReceiver *self)
 {
 	pfree(self);
 }
+
+/*
+ * CreateIvmTriggersOnBaseTables -- create IVM triggers on all base tables
+ */
+void
+CreateIvmTriggersOnBaseTables(Query *qry, Oid matviewOid, bool is_create)
+{
+	Relids	relids = NULL;
+	bool	ex_lock = false;
+	Index	first_rtindex = is_create ? 1 : PRS2_NEW_VARNO + 1;
+	RangeTblEntry *rte;
+
+	/* Immediately return if we don't have any base tables. */
+	if (list_length(qry->rtable) < first_rtindex)
+		return;
+
+	/*
+	 * If the view has more than one base tables, we need an exclusive lock
+	 * on the view so that the view would be maintained serially to avoid
+	 * the inconsistency that occurs when two base tables are modified in
+	 * concurrent transactions. However, if the view has only one table,
+	 * we can use a weaker lock.
+	 *
+	 * The type of lock should be determined here, because if we check the
+	 * view definition at maintenance time, we need to acquire a weaker lock,
+	 * and upgrading the lock level after this increases probability of
+	 * deadlock.
+	 */
+
+	rte = list_nth(qry->rtable, first_rtindex - 1);
+	if (list_length(qry->rtable) > first_rtindex ||
+		rte->rtekind != RTE_RELATION)
+		ex_lock = true;
+
+	CreateIvmTriggersOnBaseTablesRecurse(qry, (Node *)qry, matviewOid, &relids, ex_lock);
+
+	bms_free(relids);
+}
+
+static void
+CreateIvmTriggersOnBaseTablesRecurse(Query *qry, Node *node, Oid matviewOid,
+									 Relids *relids, bool ex_lock)
+{
+	if (node == NULL)
+		return;
+
+	/* This can recurse, so check for excessive recursion */
+	check_stack_depth();
+
+	switch (nodeTag(node))
+	{
+		case T_Query:
+			{
+				Query *query = (Query *) node;
+
+				CreateIvmTriggersOnBaseTablesRecurse(qry, (Node *)query->jointree, matviewOid, relids, ex_lock);
+			}
+			break;
+
+		case T_RangeTblRef:
+			{
+				int			rti = ((RangeTblRef *) node)->rtindex;
+				RangeTblEntry *rte = rt_fetch(rti, qry->rtable);
+
+				if (rte->rtekind == RTE_RELATION && !bms_is_member(rte->relid, *relids))
+				{
+					CreateIvmTrigger(rte->relid, matviewOid, TRIGGER_TYPE_INSERT, TRIGGER_TYPE_BEFORE, ex_lock);
+					CreateIvmTrigger(rte->relid, matviewOid, TRIGGER_TYPE_DELETE, TRIGGER_TYPE_BEFORE, ex_lock);
+					CreateIvmTrigger(rte->relid, matviewOid, TRIGGER_TYPE_UPDATE, TRIGGER_TYPE_BEFORE, ex_lock);
+					CreateIvmTrigger(rte->relid, matviewOid, TRIGGER_TYPE_INSERT, TRIGGER_TYPE_AFTER, ex_lock);
+					CreateIvmTrigger(rte->relid, matviewOid, TRIGGER_TYPE_DELETE, TRIGGER_TYPE_AFTER, ex_lock);
+					CreateIvmTrigger(rte->relid, matviewOid, TRIGGER_TYPE_UPDATE, TRIGGER_TYPE_AFTER, ex_lock);
+
+					*relids = bms_add_member(*relids, rte->relid);
+				}
+			}
+			break;
+
+		case T_FromExpr:
+			{
+				FromExpr   *f = (FromExpr *) node;
+				ListCell   *l;
+
+				foreach(l, f->fromlist)
+					CreateIvmTriggersOnBaseTablesRecurse(qry, lfirst(l), matviewOid, relids, ex_lock);
+			}
+			break;
+
+		case T_JoinExpr:
+			{
+				JoinExpr   *j = (JoinExpr *) node;
+
+				CreateIvmTriggersOnBaseTablesRecurse(qry, j->larg, matviewOid, relids, ex_lock);
+				CreateIvmTriggersOnBaseTablesRecurse(qry, j->rarg, matviewOid, relids, ex_lock);
+			}
+			break;
+
+		default:
+			elog(ERROR, "unrecognized node type: %d", (int) nodeTag(node));
+	}
+}
+
+/*
+ * CreateIvmTrigger -- create IVM trigger on a base table
+ */
+static void
+CreateIvmTrigger(Oid relOid, Oid viewOid, int16 type, int16 timing, bool ex_lock)
+{
+	ObjectAddress	refaddr;
+	ObjectAddress	address;
+	CreateTrigStmt *ivm_trigger;
+	List *transitionRels = NIL;
+
+	Assert(timing == TRIGGER_TYPE_BEFORE || timing == TRIGGER_TYPE_AFTER);
+
+	refaddr.classId = RelationRelationId;
+	refaddr.objectId = viewOid;
+	refaddr.objectSubId = 0;
+
+	ivm_trigger = makeNode(CreateTrigStmt);
+	ivm_trigger->relation = NULL;
+	ivm_trigger->row = false;
+
+	ivm_trigger->timing = timing;
+	ivm_trigger->events = type;
+
+	switch (type)
+	{
+		case TRIGGER_TYPE_INSERT:
+			ivm_trigger->trigname = (timing == TRIGGER_TYPE_BEFORE ? "IVM_trigger_ins_before" : "IVM_trigger_ins_after");
+			break;
+		case TRIGGER_TYPE_DELETE:
+			ivm_trigger->trigname = (timing == TRIGGER_TYPE_BEFORE ? "IVM_trigger_del_before" : "IVM_trigger_del_after");
+			break;
+		case TRIGGER_TYPE_UPDATE:
+			ivm_trigger->trigname = (timing == TRIGGER_TYPE_BEFORE ? "IVM_trigger_upd_before" : "IVM_trigger_upd_after");
+			break;
+		default:
+			elog(ERROR, "unsupported trigger type");
+	}
+
+	if (timing == TRIGGER_TYPE_AFTER)
+	{
+		if (type == TRIGGER_TYPE_INSERT || type == TRIGGER_TYPE_UPDATE)
+		{
+			TriggerTransition *n = makeNode(TriggerTransition);
+			n->name = "__ivm_newtable";
+			n->isNew = true;
+			n->isTable = true;
+
+			transitionRels = lappend(transitionRels, n);
+		}
+		if (type == TRIGGER_TYPE_DELETE || type == TRIGGER_TYPE_UPDATE)
+		{
+			TriggerTransition *n = makeNode(TriggerTransition);
+			n->name = "__ivm_oldtable";
+			n->isNew = false;
+			n->isTable = true;
+
+			transitionRels = lappend(transitionRels, n);
+		}
+	}
+
+	ivm_trigger->funcname =
+		(timing == TRIGGER_TYPE_BEFORE ? SystemFuncName("IVM_immediate_before") : SystemFuncName("IVM_immediate_maintenance"));
+
+	ivm_trigger->columns = NIL;
+	ivm_trigger->transitionRels = transitionRels;
+	ivm_trigger->whenClause = NULL;
+	ivm_trigger->isconstraint = false;
+	ivm_trigger->deferrable = false;
+	ivm_trigger->initdeferred = false;
+	ivm_trigger->constrrel = NULL;
+	ivm_trigger->args = list_make2(
+		makeString(DatumGetPointer(DirectFunctionCall1(oidout, ObjectIdGetDatum(viewOid)))),
+		makeString(DatumGetPointer(DirectFunctionCall1(boolout, BoolGetDatum(ex_lock))))
+		);
+
+	address = CreateTrigger(ivm_trigger, NULL, relOid, InvalidOid, InvalidOid,
+						 InvalidOid, InvalidOid, InvalidOid, NULL, true, false);
+
+	recordDependencyOn(&address, &refaddr, DEPENDENCY_IMMV);
+
+	/* Make changes-so-far visible */
+	CommandCounterIncrement();
+}
+
+/*
+ * check_ivm_restriction --- look for specify nodes in the query tree
+ */
+static void
+check_ivm_restriction(Node *node)
+{
+	check_ivm_restriction_walker(node, NULL);
+}
+
+static bool
+check_ivm_restriction_walker(Node *node, void *context)
+{
+	if (node == NULL)
+		return false;
+
+	/*
+	 * We currently don't support Sub-Query.
+	 */
+	if (IsA(node, SubPlan) || IsA(node, SubLink))
+		ereport(ERROR,
+				(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+				 errmsg("subquery is not supported on incrementally maintainable materialized view")));
+
+	/* This can recurse, so check for excessive recursion */
+	check_stack_depth();
+
+	switch (nodeTag(node))
+	{
+		case T_Query:
+			{
+				Query *qry = (Query *)node;
+				ListCell   *lc;
+				List       *vars;
+
+				/* if contained CTE, return error */
+				if (qry->cteList != NIL)
+					ereport(ERROR,
+							(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+							 errmsg("CTE is not supported on incrementally maintainable materialized view")));
+				if (qry->havingQual != NULL)
+					ereport(ERROR,
+							(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+							 errmsg(" HAVING clause is not supported on incrementally maintainable materialized view")));
+				if (qry->sortClause != NIL)	/* There is a possibility that we don't need to return an error */
+					ereport(ERROR,
+							(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+							 errmsg("ORDER BY clause is not supported on incrementally maintainable materialized view")));
+				if (qry->limitOffset != NULL || qry->limitCount != NULL)
+					ereport(ERROR,
+							(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+							 errmsg("LIMIT/OFFSET clause is not supported on incrementally maintainable materialized view")));
+				if (qry->hasDistinctOn)
+					ereport(ERROR,
+							(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+							 errmsg("DISTINCT ON is not supported on incrementally maintainable materialized view")));
+				if (qry->hasWindowFuncs)
+					ereport(ERROR,
+							(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+							 errmsg("window functions are not supported on incrementally maintainable materialized view")));
+				if (qry->groupingSets != NIL)
+					ereport(ERROR,
+							(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+							 errmsg("GROUPING SETS, ROLLUP, or CUBE clauses is not supported on incrementally maintainable materialized view")));
+				if (qry->setOperations != NULL)
+					ereport(ERROR,
+							(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+							 errmsg("UNION/INTERSECT/EXCEPT statements are not supported on incrementally maintainable materialized view")));
+				if (list_length(qry->targetList) == 0)
+					ereport(ERROR,
+							(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+							 errmsg("empty target list is not supported on incrementally maintainable materialized view")));
+				if (qry->rowMarks != NIL)
+					ereport(ERROR,
+							(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+							 errmsg("FOR UPDATE/SHARE clause is not supported on incrementally maintainable materialized view")));
+
+				/* system column restrictions */
+				vars = pull_vars_of_level((Node *) qry, 0);
+				foreach(lc, vars)
+				{
+					if (IsA(lfirst(lc), Var))
+					{
+						Var *var = (Var *) lfirst(lc);
+						/* if system column, return error */
+						if (var->varattno < 0)
+							ereport(ERROR,
+									(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+									 errmsg("system column is not supported on incrementally maintainable materialized view")));
+					}
+				}
+
+				/* restrictions for rtable */
+				foreach(lc, qry->rtable)
+				{
+					RangeTblEntry *rte = (RangeTblEntry *) lfirst(lc);
+
+					if (rte->subquery)
+						ereport(ERROR,
+								(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+								 errmsg("subquery is not supported on incrementally maintainable materialized view")));
+
+					if (rte->tablesample != NULL)
+						ereport(ERROR,
+								(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+								 errmsg("TABLESAMPLE clause is not supported on incrementally maintainable materialized view")));
+
+					if (rte->relkind == RELKIND_PARTITIONED_TABLE)
+						ereport(ERROR,
+								(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+								 errmsg("partitioned table is not supported on incrementally maintainable materialized view")));
+
+					if (rte->relkind == RELKIND_RELATION && has_superclass(rte->relid))
+						ereport(ERROR,
+								(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+								 errmsg("partitions is not supported on incrementally maintainable materialized view")));
+
+					if (rte->relkind == RELKIND_RELATION && find_inheritance_children(rte->relid, NoLock) != NIL)
+						ereport(ERROR,
+								(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+								 errmsg("inheritance parent is not supported on incrementally maintainable materialized view")));
+
+					if (rte->relkind == RELKIND_FOREIGN_TABLE)
+						ereport(ERROR,
+								(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+								 errmsg("foreign table is not supported on incrementally maintainable materialized view")));
+
+					if (rte->relkind == RELKIND_VIEW ||
+						rte->relkind == RELKIND_MATVIEW)
+						ereport(ERROR,
+								(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+								 errmsg("VIEW or MATERIALIZED VIEW is not supported on incrementally maintainable materialized view")));
+
+					if (rte->rtekind == RTE_VALUES)
+						ereport(ERROR,
+								(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+								 errmsg("VALUES is not supported on incrementally maintainable materialized view")));
+
+				}
+
+				query_tree_walker(qry, check_ivm_restriction_walker, NULL, QTW_IGNORE_RANGE_TABLE);
+
+				break;
+			}
+		case T_TargetEntry:
+			{
+				TargetEntry *tle = (TargetEntry *)node;
+				if (isIvmName(tle->resname))
+						ereport(ERROR,
+								(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+								 errmsg("column name %s is not supported on incrementally maintainable materialized view", tle->resname)));
+
+				expression_tree_walker(node, check_ivm_restriction_walker, NULL);
+				break;
+			}
+		case T_JoinExpr:
+			{
+				JoinExpr *joinexpr = (JoinExpr *)node;
+
+				if (joinexpr->jointype > JOIN_INNER)
+						ereport(ERROR,
+								(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+								 errmsg("OUTER JOIN is not supported on incrementally maintainable materialized view")));
+
+				expression_tree_walker(node, check_ivm_restriction_walker, NULL);
+			}
+			break;
+		default:
+			expression_tree_walker(node, check_ivm_restriction_walker, (void *) context);
+			break;
+	}
+	return false;
+}
+
+/*
+ * CreateIndexOnIMMV
+ *
+ * Create a unique index on incremental maintainable materialized view.
+ * If the view definition query has a GROUP BY clause, the index is created
+ * on the columns of GROUP BY expressions. Otherwise, if the view contains
+ * all primary key attritubes of its base tables in the target list, the index
+ * is created on these attritubes. In other cases, no index is created.
+ */
+void
+CreateIndexOnIMMV(Query *query, Relation matviewRel, bool is_create)
+{
+	ListCell *lc;
+	IndexStmt  *index;
+	ObjectAddress address;
+	List *constraintList = NIL;
+	char		idxname[NAMEDATALEN];
+	List	   *indexoidlist = RelationGetIndexList(matviewRel);
+	ListCell   *indexoidscan;
+
+	snprintf(idxname, sizeof(idxname), "%s_index", RelationGetRelationName(matviewRel));
+
+	index = makeNode(IndexStmt);
+
+	/*
+	 * We consider null values not distinct to make sure that views with DISTINCT
+	 * or GROUP BY don't contain multiple NULL rows when NULL is inserted to
+	 * a base table concurrently.
+	 */
+	index->nulls_not_distinct = true;
+
+	index->unique = true;
+	index->primary = false;
+	index->isconstraint = false;
+	index->deferrable = false;
+	index->initdeferred = false;
+	index->idxname = idxname;
+	index->relation =
+		makeRangeVar(get_namespace_name(RelationGetNamespace(matviewRel)),
+					 pstrdup(RelationGetRelationName(matviewRel)),
+					 -1);
+	index->accessMethod = DEFAULT_INDEX_TYPE;
+	index->options = NIL;
+	index->tableSpace = get_tablespace_name(matviewRel->rd_rel->reltablespace);
+	index->whereClause = NULL;
+	index->indexParams = NIL;
+	index->indexIncludingParams = NIL;
+	index->excludeOpNames = NIL;
+	index->idxcomment = NULL;
+	index->indexOid = InvalidOid;
+	index->oldNode = InvalidOid;
+	index->oldCreateSubid = InvalidSubTransactionId;
+	index->oldFirstRelfilenodeSubid = InvalidSubTransactionId;
+	index->transformed = true;
+	index->concurrent = false;
+	index->if_not_exists = false;
+
+	if (query->distinctClause)
+	{
+		/* create unique constraint on all columns */
+		foreach(lc, query->targetList)
+		{
+			TargetEntry *tle = (TargetEntry *) lfirst(lc);
+			Form_pg_attribute attr = TupleDescAttr(matviewRel->rd_att, tle->resno - 1);
+			IndexElem  *iparam;
+
+			iparam = makeNode(IndexElem);
+			iparam->name = pstrdup(NameStr(attr->attname));
+			iparam->expr = NULL;
+			iparam->indexcolname = NULL;
+			iparam->collation = NIL;
+			iparam->opclass = NIL;
+			iparam->opclassopts = NIL;
+			iparam->ordering = SORTBY_DEFAULT;
+			iparam->nulls_ordering = SORTBY_NULLS_DEFAULT;
+			index->indexParams = lappend(index->indexParams, iparam);
+		}
+	}
+	else
+	{
+		Bitmapset *key_attnos;
+
+		/* create index on the base tables' primary key columns */
+		key_attnos = get_primary_key_attnos_from_query(query, &constraintList, is_create);
+		if (key_attnos)
+		{
+			foreach(lc, query->targetList)
+			{
+				TargetEntry *tle = (TargetEntry *) lfirst(lc);
+				Form_pg_attribute attr = TupleDescAttr(matviewRel->rd_att, tle->resno - 1);
+
+				if (bms_is_member(tle->resno - FirstLowInvalidHeapAttributeNumber, key_attnos))
+				{
+					IndexElem  *iparam;
+
+					iparam = makeNode(IndexElem);
+					iparam->name = pstrdup(NameStr(attr->attname));
+					iparam->expr = NULL;
+					iparam->indexcolname = NULL;
+					iparam->collation = NIL;
+					iparam->opclass = NIL;
+					iparam->opclassopts = NIL;
+					iparam->ordering = SORTBY_DEFAULT;
+					iparam->nulls_ordering = SORTBY_NULLS_DEFAULT;
+					index->indexParams = lappend(index->indexParams, iparam);
+				}
+			}
+		}
+		else
+		{
+			/* create no index, just notice that an appropriate index is necessary for efficient IVM */
+			ereport(NOTICE,
+					(errmsg("could not create an index on materialized view \"%s\" automatically",
+							RelationGetRelationName(matviewRel)),
+					 errdetail("This target list does not have all the primary key columns, "
+							   "or this view does not contain DISTINCT clause."),
+					 errhint("Create an index on the materialized view for efficient incremental maintenance.")));
+			return;
+		}
+	}
+
+	/* If we have a compatible index, we don't need to create another. */
+	foreach(indexoidscan, indexoidlist)
+	{
+		Oid			indexoid = lfirst_oid(indexoidscan);
+		Relation	indexRel;
+		bool		hasCompatibleIndex = false;
+
+		indexRel = index_open(indexoid, AccessShareLock);
+
+		if (CheckIndexCompatible(indexRel->rd_id,
+								index->accessMethod,
+								index->indexParams,
+								index->excludeOpNames))
+			hasCompatibleIndex = true;
+
+		index_close(indexRel, AccessShareLock);
+
+		if (hasCompatibleIndex)
+			return;
+	}
+
+	address = DefineIndex(RelationGetRelid(matviewRel),
+						  index,
+						  InvalidOid,
+						  InvalidOid,
+						  InvalidOid,
+						  false, true, false, false, true);
+
+	ereport(NOTICE,
+			(errmsg("created index \"%s\" on materialized view \"%s\"",
+					idxname, RelationGetRelationName(matviewRel))));
+
+	/*
+	 * Make dependencies so that the index is dropped if any base tables's
+	 * primary key is dropped.
+	 */
+	foreach(lc, constraintList)
+	{
+		Oid constraintOid = lfirst_oid(lc);
+		ObjectAddress	refaddr;
+
+		refaddr.classId = ConstraintRelationId;
+		refaddr.objectId = constraintOid;
+		refaddr.objectSubId = 0;
+
+		recordDependencyOn(&address, &refaddr, DEPENDENCY_NORMAL);
+	}
+}
+
+
+/*
+ * get_primary_key_attnos_from_query
+ *
+ * Identify the columns in base tables' primary keys in the target list.
+ *
+ * Returns a Bitmapset of the column attnos of the primary key's columns of
+ * tables that used in the query.  The attnos are offset by
+ * FirstLowInvalidHeapAttributeNumber as same as get_primary_key_attnos.
+ *
+ * If any table has no primary key or any primary key's columns is not in
+ * the target list, return NULL.  We also return NULL if any pkey constraint
+ * is deferrable.
+ *
+ * constraintList is set to a list of the OIDs of the pkey constraints.
+ */
+static Bitmapset *
+get_primary_key_attnos_from_query(Query *query, List **constraintList, bool is_create)
+{
+	List *key_attnos_list = NIL;
+	ListCell *lc;
+	int i;
+	Bitmapset *keys = NULL;
+	Relids	rels_in_from;
+	PlannerInfo root;
+
+
+	/*
+	 * Collect primary key attributes from all tables used in query. The key attributes
+	 * sets for each table are stored in key_attnos_list in order by RTE index.
+	 */
+	i = 1;
+	foreach(lc, query->rtable)
+	{
+		RangeTblEntry *r = (RangeTblEntry*) lfirst(lc);
+		Bitmapset *key_attnos;
+		bool	has_pkey = true;
+		Index	first_rtindex = is_create ? 1 : PRS2_NEW_VARNO + 1;
+
+		/* skip NEW/OLD entries */
+		if (i >= first_rtindex)
+		{
+			/* for tables, call get_primary_key_attnos */
+			if (r->rtekind == RTE_RELATION)
+			{
+				Oid constraintOid;
+				key_attnos = get_primary_key_attnos(r->relid, false, &constraintOid);
+				*constraintList = lappend_oid(*constraintList, constraintOid);
+				has_pkey = (key_attnos != NULL);
+			}
+			/* for other RTEs, store NULL into key_attnos_list */
+			else
+				key_attnos = NULL;
+		}
+		else
+			key_attnos = NULL;
+
+		/*
+		 * If any table or subquery has no primary key or its pkey constraint is deferrable,
+		 * we cannot get key attributes for this query, so return NULL.
+		 */
+		if (!has_pkey)
+			return NULL;
+
+		key_attnos_list = lappend(key_attnos_list, key_attnos);
+		i++;
+	}
+
+	/* Collect key attributes appearing in the target list */
+	i = 1;
+	foreach(lc, query->targetList)
+	{
+		TargetEntry *tle = (TargetEntry *) flatten_join_alias_vars(query, lfirst(lc));
+
+		if (IsA(tle->expr, Var))
+		{
+			Var *var = (Var*) tle->expr;
+			Bitmapset *attnos = list_nth(key_attnos_list, var->varno - 1);
+
+			/* check if this attribute is from a base table's primary key */
+			if (bms_is_member(var->varattno - FirstLowInvalidHeapAttributeNumber, attnos))
+			{
+				/*
+				 * Remove found key attributes from key_attnos_list, and add this
+				 * to the result list.
+				 */
+				bms_del_member(attnos, var->varattno - FirstLowInvalidHeapAttributeNumber);
+				keys = bms_add_member(keys, i - FirstLowInvalidHeapAttributeNumber);
+			}
+		}
+		i++;
+	}
+
+	/* Collect relations appearing in the FROM clause */
+	rels_in_from = pull_varnos_of_level(&root, (Node *)query->jointree, 0);
+
+	/*
+	 * Check if all key attributes of relations in FROM are appearing in the target
+	 * list.  If an attribute remains in key_attnos_list in spite of the table is used
+	 * in FROM clause, the target is missing this key attribute, so we return NULL.
+	 */
+	i = 1;
+	foreach(lc, key_attnos_list)
+	{
+		Bitmapset *bms = (Bitmapset *)lfirst(lc);
+		if (!bms_is_empty(bms) && bms_is_member(i, rels_in_from))
+			return NULL;
+		i++;
+	}
+
+	return keys;
+}
diff --git a/src/backend/commands/indexcmds.c b/src/backend/commands/indexcmds.c
index cd30f15eba..a94b8ffd7d 100644
--- a/src/backend/commands/indexcmds.c
+++ b/src/backend/commands/indexcmds.c
@@ -36,6 +36,7 @@
 #include "commands/dbcommands.h"
 #include "commands/defrem.h"
 #include "commands/event_trigger.h"
+#include "commands/matview.h"
 #include "commands/progress.h"
 #include "commands/tablecmds.h"
 #include "commands/tablespace.h"
@@ -1055,6 +1056,45 @@ DefineIndex(Oid relationId,
 	safe_index = indexInfo->ii_Expressions == NIL &&
 		indexInfo->ii_Predicate == NIL;
 
+	/*
+	 * We disallow unique indexes on IVM columns of IMMVs.
+	 */
+	if (RelationIsIVM(rel) && stmt->unique)
+	{
+		for (i = 0; i < indexInfo->ii_NumIndexKeyAttrs; i++)
+		{
+			AttrNumber	attno = indexInfo->ii_IndexAttrNumbers[i];
+			if (attno > 0)
+			{
+				char *name = NameStr(TupleDescAttr(rel->rd_att, attno - 1)->attname);
+				if (name && isIvmName(name))
+					ereport(ERROR,
+							(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+							 errmsg("unique index creation on IVM columns is not supported")));
+			}
+		}
+
+		if (indexInfo->ii_Expressions)
+		{
+			Bitmapset  *indexattrs = NULL;
+			int			varno = -1;
+
+			pull_varattnos((Node *) indexInfo->ii_Expressions, 1, &indexattrs);
+
+			while ((varno = bms_next_member(indexattrs, varno)) >= 0)
+			{
+				int attno = varno + FirstLowInvalidHeapAttributeNumber;
+				char *name = NameStr(TupleDescAttr(rel->rd_att, attno - 1)->attname);
+				if (name && isIvmName(name))
+					ereport(ERROR,
+							(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+							 errmsg("unique index creation on IVM columns is not supported")));
+			}
+
+		}
+	}
+
+
 	/*
 	 * Report index creation if appropriate (delay this till after most of the
 	 * error checks)
diff --git a/src/backend/commands/matview.c b/src/backend/commands/matview.c
index 05e7b60059..29cf18360e 100644
--- a/src/backend/commands/matview.c
+++ b/src/backend/commands/matview.c
@@ -25,26 +25,47 @@
 #include "catalog/indexing.h"
 #include "catalog/namespace.h"
 #include "catalog/pg_am.h"
+#include "catalog/pg_collation.h"
+#include "catalog/pg_depend.h"
+#include "catalog/pg_type.h"
 #include "catalog/pg_opclass.h"
 #include "catalog/pg_operator.h"
 #include "commands/cluster.h"
+#include "commands/defrem.h"
 #include "commands/matview.h"
 #include "commands/tablecmds.h"
 #include "commands/tablespace.h"
+#include "commands/createas.h"
 #include "executor/executor.h"
 #include "executor/spi.h"
+#include "executor/tstoreReceiver.h"
 #include "miscadmin.h"
+#include "nodes/makefuncs.h"
+#include "nodes/nodeFuncs.h"
+#include "optimizer/optimizer.h"
+#include "parser/analyze.h"
+#include "parser/parser.h"
+#include "parser/parsetree.h"
+#include "parser/parse_clause.h"
+#include "parser/parse_coerce.h"
+#include "parser/parse_collate.h"
+#include "parser/parse_func.h"
 #include "parser/parse_relation.h"
+#include "parser/parse_type.h"
 #include "pgstat.h"
 #include "rewrite/rewriteHandler.h"
+#include "rewrite/rewriteManip.h"
+#include "rewrite/rowsecurity.h"
 #include "storage/lmgr.h"
 #include "storage/smgr.h"
 #include "tcop/tcopprot.h"
 #include "utils/builtins.h"
+#include "utils/fmgroids.h"
 #include "utils/lsyscache.h"
 #include "utils/rel.h"
 #include "utils/snapmgr.h"
 #include "utils/syscache.h"
+#include "utils/typcache.h"
 
 
 typedef struct
@@ -58,6 +79,50 @@ typedef struct
 	BulkInsertState bistate;	/* bulk insert state */
 } DR_transientrel;
 
+#define MV_INIT_QUERYHASHSIZE	16
+
+/*
+ * MV_TriggerHashEntry
+ *
+ * Hash entry for base tables on which IVM trigger is invoked
+ */
+typedef struct MV_TriggerHashEntry
+{
+	Oid	matview_id;			/* OID of the materialized view */
+	int	before_trig_count;	/* count of before triggers invoked */
+	int	after_trig_count;	/* count of after triggers invoked */
+
+	TransactionId	xid;	/* Transaction id before the first table is modified*/
+	CommandId		cid;	/* Command id before the first table is modified */
+
+	List   *tables;		/* List of MV_TriggerTable */
+	bool	has_old;	/* tuples are deleted from any table? */
+	bool	has_new;	/* tuples are inserted into any table? */
+} MV_TriggerHashEntry;
+
+/*
+ * MV_TriggerTable
+ *
+ * IVM related data for tables on which the trigger is invoked.
+ */
+typedef struct MV_TriggerTable
+{
+	Oid		table_id;			/* OID of the modified table */
+	List   *old_tuplestores;	/* tuplestores for deleted tuples */
+	List   *new_tuplestores;	/* tuplestores for inserted tuples */
+	List   *old_rtes;			/* RTEs of ENRs for old_tuplestores*/
+	List   *new_rtes;			/* RTEs of ENRs for new_tuplestores */
+
+	List   *rte_indexes;		/* List of RTE index of the modified table */
+	RangeTblEntry *original_rte;	/* the original RTE saved before rewriting query */
+} MV_TriggerTable;
+
+static HTAB *mv_trigger_info = NULL;
+
+/* ENR name for materialized view delta */
+#define NEW_DELTA_ENRNAME "new_delta"
+#define OLD_DELTA_ENRNAME "old_delta"
+
 static int	matview_maintenance_depth = 0;
 
 static void transientrel_startup(DestReceiver *self, int operation, TupleDesc typeinfo);
@@ -65,7 +130,9 @@ static bool transientrel_receive(TupleTableSlot *slot, DestReceiver *self);
 static void transientrel_shutdown(DestReceiver *self);
 static void transientrel_destroy(DestReceiver *self);
 static uint64 refresh_matview_datafill(DestReceiver *dest, Query *query,
-									   const char *queryString);
+						 QueryEnvironment *queryEnv,
+						 TupleDesc *resultTupleDesc,
+						 const char *queryString);
 static char *make_temptable_name_n(char *tempname, int n);
 static void refresh_by_match_merge(Oid matviewOid, Oid tempOid, Oid relowner,
 								   int save_sec_context);
@@ -73,6 +140,45 @@ static void refresh_by_heap_swap(Oid matviewOid, Oid OIDNewHeap, char relpersist
 static bool is_usable_unique_index(Relation indexRel);
 static void OpenMatViewIncrementalMaintenance(void);
 static void CloseMatViewIncrementalMaintenance(void);
+static Query *get_matview_query(Relation matviewRel);
+
+static Query *rewrite_query_for_preupdate_state(Query *query, List *tables,
+								  TransactionId xid, CommandId cid,
+								  ParseState *pstate);
+static void register_delta_ENRs(ParseState *pstate, Query *query, List *tables);
+static char *make_delta_enr_name(const char *prefix, Oid relid, int count);
+static RangeTblEntry *get_prestate_rte(RangeTblEntry *rte, MV_TriggerTable *table,
+				 TransactionId xid, CommandId cid,
+				 QueryEnvironment *queryEnv);
+static RangeTblEntry *union_ENRs(RangeTblEntry *rte, Oid relid, List *enr_rtes, const char *prefix,
+		   QueryEnvironment *queryEnv);
+static Query *rewrite_query_for_distinct(Query *query, ParseState *pstate);
+
+static void calc_delta(MV_TriggerTable *table, int rte_index, Query *query,
+			DestReceiver *dest_old, DestReceiver *dest_new,
+			TupleDesc *tupdesc_old, TupleDesc *tupdesc_new,
+			QueryEnvironment *queryEnv);
+static Query *rewrite_query_for_postupdate_state(Query *query, MV_TriggerTable *table, int rte_index);
+
+static void apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *new_tuplestores,
+			TupleDesc tupdesc_old, TupleDesc tupdesc_new,
+			Query *query, bool use_count, char *count_colname);
+static void apply_old_delta(const char *matviewname, const char *deltaname_old,
+				List *keys);
+static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old,
+				List *keys, const char *count_colname);
+static void apply_new_delta(const char *matviewname, const char *deltaname_new,
+				StringInfo target_list);
+static void apply_new_delta_with_count(const char *matviewname, const char* deltaname_new,
+				List *keys, StringInfo target_list, const char* count_colname);
+static char *get_matching_condition_string(List *keys);
+static void generate_equal(StringInfo querybuf, Oid opttype,
+			   const char *leftop, const char *rightop);
+
+static void mv_InitHashTables(void);
+static void clean_up_IVM_hash_entry(MV_TriggerHashEntry *entry);
+
+static List *get_securityQuals(Oid relId, int rt_index, Query *query);
 
 /*
  * SetMatViewPopulatedState
@@ -114,6 +220,46 @@ SetMatViewPopulatedState(Relation relation, bool newstate)
 	CommandCounterIncrement();
 }
 
+/*
+ * SetMatViewIVMState
+ *		Mark a materialized view as IVM, or not.
+ *
+ * NOTE: caller must be holding an appropriate lock on the relation.
+ */
+void
+SetMatViewIVMState(Relation relation, bool newstate)
+{
+	Relation	pgrel;
+	HeapTuple	tuple;
+
+	Assert(relation->rd_rel->relkind == RELKIND_MATVIEW);
+
+	/*
+	 * Update relation's pg_class entry.  Crucial side-effect: other backends
+	 * (and this one too!) are sent SI message to make them rebuild relcache
+	 * entries.
+	 */
+	pgrel = table_open(RelationRelationId, RowExclusiveLock);
+	tuple = SearchSysCacheCopy1(RELOID,
+								ObjectIdGetDatum(RelationGetRelid(relation)));
+	if (!HeapTupleIsValid(tuple))
+		elog(ERROR, "cache lookup failed for relation %u",
+			 RelationGetRelid(relation));
+
+	((Form_pg_class) GETSTRUCT(tuple))->relisivm = newstate;
+
+	CatalogTupleUpdate(pgrel, &tuple->t_self, tuple);
+
+	heap_freetuple(tuple);
+	table_close(pgrel, RowExclusiveLock);
+
+	/*
+	 * Advance command counter to make the updated pg_class row locally
+	 * visible.
+	 */
+	CommandCounterIncrement();
+}
+
 /*
  * ExecRefreshMatView -- execute a REFRESH MATERIALIZED VIEW command
  *
@@ -140,9 +286,8 @@ ExecRefreshMatView(RefreshMatViewStmt *stmt, const char *queryString,
 {
 	Oid			matviewOid;
 	Relation	matviewRel;
-	RewriteRule *rule;
-	List	   *actions;
 	Query	   *dataQuery;
+	Query	   *viewQuery;
 	Oid			tableSpace;
 	Oid			relowner;
 	Oid			OIDNewHeap;
@@ -155,6 +300,7 @@ ExecRefreshMatView(RefreshMatViewStmt *stmt, const char *queryString,
 	int			save_sec_context;
 	int			save_nestlevel;
 	ObjectAddress address;
+	bool oldPopulated;
 
 	/* Determine strength of lock needed. */
 	concurrent = stmt->concurrent;
@@ -167,6 +313,7 @@ ExecRefreshMatView(RefreshMatViewStmt *stmt, const char *queryString,
 										  lockmode, 0,
 										  RangeVarCallbackOwnsTable, NULL);
 	matviewRel = table_open(matviewOid, NoLock);
+	oldPopulated = RelationIsPopulated(matviewRel);
 
 	/* Make sure it is a materialized view. */
 	if (matviewRel->rd_rel->relkind != RELKIND_MATVIEW)
@@ -188,32 +335,14 @@ ExecRefreshMatView(RefreshMatViewStmt *stmt, const char *queryString,
 				 errmsg("%s and %s options cannot be used together",
 						"CONCURRENTLY", "WITH NO DATA")));
 
-	/*
-	 * Check that everything is correct for a refresh. Problems at this point
-	 * are internal errors, so elog is sufficient.
-	 */
-	if (matviewRel->rd_rel->relhasrules == false ||
-		matviewRel->rd_rules->numLocks < 1)
-		elog(ERROR,
-			 "materialized view \"%s\" is missing rewrite information",
-			 RelationGetRelationName(matviewRel));
-
-	if (matviewRel->rd_rules->numLocks > 1)
-		elog(ERROR,
-			 "materialized view \"%s\" has too many rules",
-			 RelationGetRelationName(matviewRel));
 
-	rule = matviewRel->rd_rules->rules[0];
-	if (rule->event != CMD_SELECT || !(rule->isInstead))
-		elog(ERROR,
-			 "the rule for materialized view \"%s\" is not a SELECT INSTEAD OF rule",
-			 RelationGetRelationName(matviewRel));
+	viewQuery = get_matview_query(matviewRel);
 
-	actions = rule->actions;
-	if (list_length(actions) != 1)
-		elog(ERROR,
-			 "the rule for materialized view \"%s\" is not a single action",
-			 RelationGetRelationName(matviewRel));
+	/* For IMMV, we need to rewrite matview query */
+	if (!stmt->skipData && RelationIsIVM(matviewRel))
+		dataQuery = rewriteQueryForIMMV(viewQuery,NIL);
+	else
+		dataQuery = viewQuery;
 
 	/*
 	 * Check that there is a unique index with no WHERE clause on one or more
@@ -248,12 +377,6 @@ ExecRefreshMatView(RefreshMatViewStmt *stmt, const char *queryString,
 					 errhint("Create a unique index with no WHERE clause on one or more columns of the materialized view.")));
 	}
 
-	/*
-	 * The stored query was rewritten at the time of the MV definition, but
-	 * has not been scribbled on by the planner.
-	 */
-	dataQuery = linitial_node(Query, actions);
-
 	/*
 	 * Check for active uses of the relation in the current transaction, such
 	 * as open scans.
@@ -294,6 +417,52 @@ ExecRefreshMatView(RefreshMatViewStmt *stmt, const char *queryString,
 		relpersistence = matviewRel->rd_rel->relpersistence;
 	}
 
+	/* delete immv triggers */
+	if (RelationIsIVM(matviewRel) && stmt->skipData )
+	{
+		/* use deleted trigger */
+		Relation	depRel;
+		ScanKeyData key;
+		SysScanDesc scan;
+		HeapTuple	tup;
+		ObjectAddresses *immv_triggers;
+
+		immv_triggers = new_object_addresses();
+
+		/*
+		 * We save some cycles by opening pg_depend just once and passing the
+		 * Relation pointer down to all the recursive deletion steps.
+		 */
+		depRel = table_open(DependRelationId, RowExclusiveLock);
+
+		ScanKeyInit(&key,
+					Anum_pg_depend_refobjid,
+					BTEqualStrategyNumber, F_OIDEQ,
+					ObjectIdGetDatum(matviewOid));
+
+		scan = systable_beginscan(depRel, DependReferenceIndexId, true,
+								  NULL, 1, &key);
+		while ((tup = systable_getnext(scan)) != NULL)
+		{
+			ObjectAddress obj;
+			Form_pg_depend foundDep = (Form_pg_depend) GETSTRUCT(tup);
+
+			if (foundDep->deptype == DEPENDENCY_IMMV)
+			{
+				obj.classId = foundDep->classid;
+				obj.objectId = foundDep->objid;
+				obj.objectSubId = foundDep->refobjsubid;
+				add_exact_object_address(&obj, immv_triggers);
+			}
+		}
+		systable_endscan(scan);
+
+		performMultipleDeletions(immv_triggers, DROP_RESTRICT, PERFORM_DELETION_INTERNAL);
+
+		table_close(depRel, RowExclusiveLock);
+		free_object_addresses(immv_triggers);
+	}
+
 	/*
 	 * Create the transient table that will receive the regenerated data. Lock
 	 * it against access by any other process until commit (by which time it
@@ -313,7 +482,7 @@ ExecRefreshMatView(RefreshMatViewStmt *stmt, const char *queryString,
 
 	/* Generate the data, if wanted. */
 	if (!stmt->skipData)
-		processed = refresh_matview_datafill(dest, dataQuery, queryString);
+		processed = refresh_matview_datafill(dest, dataQuery, NULL, NULL, queryString);
 
 	/* Make the matview match the newly generated data. */
 	if (concurrent)
@@ -348,6 +517,12 @@ ExecRefreshMatView(RefreshMatViewStmt *stmt, const char *queryString,
 			pgstat_count_heap_insert(matviewRel, processed);
 	}
 
+	if (!stmt->skipData && RelationIsIVM(matviewRel) && !oldPopulated)
+	{
+		CreateIndexOnIMMV(viewQuery, matviewRel, false);
+		CreateIvmTriggersOnBaseTables(viewQuery, matviewOid, false);
+	}
+
 	table_close(matviewRel, NoLock);
 
 	/* Roll back any GUC changes */
@@ -382,6 +557,8 @@ ExecRefreshMatView(RefreshMatViewStmt *stmt, const char *queryString,
  */
 static uint64
 refresh_matview_datafill(DestReceiver *dest, Query *query,
+						 QueryEnvironment *queryEnv,
+						 TupleDesc *resultTupleDesc,
 						 const char *queryString)
 {
 	List	   *rewritten;
@@ -418,7 +595,7 @@ refresh_matview_datafill(DestReceiver *dest, Query *query,
 	/* Create a QueryDesc, redirecting output to our tuple receiver */
 	queryDesc = CreateQueryDesc(plan, queryString,
 								GetActiveSnapshot(), InvalidSnapshot,
-								dest, NULL, NULL, 0);
+								dest, NULL, queryEnv ? queryEnv: NULL, 0);
 
 	/* call ExecutorStart to prepare the plan for execution */
 	ExecutorStart(queryDesc, 0);
@@ -428,6 +605,9 @@ refresh_matview_datafill(DestReceiver *dest, Query *query,
 
 	processed = queryDesc->estate->es_processed;
 
+	if (resultTupleDesc)
+		*resultTupleDesc = CreateTupleDescCopy(queryDesc->tupDesc);
+
 	/* and clean up */
 	ExecutorFinish(queryDesc);
 	ExecutorEnd(queryDesc);
@@ -942,3 +1122,1308 @@ CloseMatViewIncrementalMaintenance(void)
 	matview_maintenance_depth--;
 	Assert(matview_maintenance_depth >= 0);
 }
+
+/*
+ * get_matview_query - get the Query from a matview's _RETURN rule.
+ */
+static Query *
+get_matview_query(Relation matviewRel)
+{
+	RewriteRule *rule;
+	List * actions;
+
+	/*
+	 * Check that everything is correct for a refresh. Problems at this point
+	 * are internal errors, so elog is sufficient.
+	 */
+	if (matviewRel->rd_rel->relhasrules == false ||
+		matviewRel->rd_rules->numLocks < 1)
+		elog(ERROR,
+			 "materialized view \"%s\" is missing rewrite information",
+			 RelationGetRelationName(matviewRel));
+
+	if (matviewRel->rd_rules->numLocks > 1)
+		elog(ERROR,
+			 "materialized view \"%s\" has too many rules",
+			 RelationGetRelationName(matviewRel));
+
+	rule = matviewRel->rd_rules->rules[0];
+	if (rule->event != CMD_SELECT || !(rule->isInstead))
+		elog(ERROR,
+			 "the rule for materialized view \"%s\" is not a SELECT INSTEAD OF rule",
+			 RelationGetRelationName(matviewRel));
+
+	actions = rule->actions;
+	if (list_length(actions) != 1)
+		elog(ERROR,
+			 "the rule for materialized view \"%s\" is not a single action",
+			 RelationGetRelationName(matviewRel));
+
+	/*
+	 * The stored query was rewritten at the time of the MV definition, but
+	 * has not been scribbled on by the planner.
+	 */
+	return linitial_node(Query, actions);
+}
+
+
+/* ----------------------------------------------------
+ *		Incremental View Maintenance routines
+ * ---------------------------------------------------
+ */
+
+/*
+ * IVM_immediate_before
+ *
+ * IVM trigger function invoked before base table is modified. If this is
+ * invoked firstly in the same statement, we save the transaction id and the
+ * command id at that time.
+ */
+Datum
+IVM_immediate_before(PG_FUNCTION_ARGS)
+{
+	TriggerData *trigdata = (TriggerData *) fcinfo->context;
+	char	   *matviewOid_text = trigdata->tg_trigger->tgargs[0];
+	char	   *ex_lock_text = trigdata->tg_trigger->tgargs[1];
+	Oid			matviewOid;
+	MV_TriggerHashEntry *entry;
+	bool	found;
+	bool	ex_lock;
+
+	matviewOid = DatumGetObjectId(DirectFunctionCall1(oidin, CStringGetDatum(matviewOid_text)));
+	ex_lock = DatumGetBool(DirectFunctionCall1(boolin, CStringGetDatum(ex_lock_text)));
+
+	/* If the view has more than one tables, we have to use an exclusive lock. */
+	if (ex_lock)
+	{
+		/*
+		 * Wait for concurrent transactions which update this materialized view at
+		 * READ COMMITED. This is needed to see changes committed in other
+		 * transactions. No wait and raise an error at REPEATABLE READ or
+		 * SERIALIZABLE to prevent update anomalies of matviews.
+		 * XXX: dead-lock is possible here.
+		 */
+		if (!IsolationUsesXactSnapshot())
+			LockRelationOid(matviewOid, ExclusiveLock);
+		else if (!ConditionalLockRelationOid(matviewOid, ExclusiveLock))
+		{
+			/* try to throw error by name; relation could be deleted... */
+			char	   *relname = get_rel_name(matviewOid);
+
+			if (!relname)
+				ereport(ERROR,
+						(errcode(ERRCODE_LOCK_NOT_AVAILABLE),
+						errmsg("could not obtain lock on materialized view during incremental maintenance")));
+
+			ereport(ERROR,
+					(errcode(ERRCODE_LOCK_NOT_AVAILABLE),
+					errmsg("could not obtain lock on materialized view \"%s\" during incremental maintenance",
+							relname)));
+		}
+	}
+	else
+		LockRelationOid(matviewOid, RowExclusiveLock);
+
+	/*
+	 * On the first call initialize the hashtable
+	 */
+	if (!mv_trigger_info)
+		mv_InitHashTables();
+
+	entry = (MV_TriggerHashEntry *) hash_search(mv_trigger_info,
+											  (void *) &matviewOid,
+											  HASH_ENTER, &found);
+
+	/* On the first BEFORE to update the view, initialize trigger data */
+	if (!found)
+	{
+		Snapshot snapshot = GetActiveSnapshot();
+
+		entry->matview_id = matviewOid;
+		entry->before_trig_count = 0;
+		entry->after_trig_count = 0;
+		entry->xid = GetCurrentTransactionId();
+		entry->cid = snapshot->curcid;
+		entry->tables = NIL;
+		entry->has_old = false;
+		entry->has_new = false;
+	}
+
+	entry->before_trig_count++;
+
+	return PointerGetDatum(NULL);
+}
+
+/*
+ * IVM_immediate_before
+ *
+ * IVM trigger function invoked after base table is modified.
+ * For each table, tuplestores of transition tables are collected.
+ * and after the last modification
+ */
+Datum
+IVM_immediate_maintenance(PG_FUNCTION_ARGS)
+{
+	TriggerData *trigdata = (TriggerData *) fcinfo->context;
+	Relation	rel;
+	Oid			relid;
+	Oid			matviewOid;
+	Query	   *query;
+	Query	   *rewritten = NULL;
+	char	   *matviewOid_text = trigdata->tg_trigger->tgargs[0];
+	Relation	matviewRel;
+	int old_depth = matview_maintenance_depth;
+
+	Oid			relowner;
+	Tuplestorestate *old_tuplestore = NULL;
+	Tuplestorestate *new_tuplestore = NULL;
+	DestReceiver *dest_new = NULL, *dest_old = NULL;
+	Oid			save_userid;
+	int			save_sec_context;
+	int			save_nestlevel;
+
+	MV_TriggerHashEntry *entry;
+	MV_TriggerTable		*table;
+	bool	found;
+
+	ParseState		 *pstate;
+	QueryEnvironment *queryEnv = create_queryEnv();
+	MemoryContext	oldcxt;
+	ListCell   *lc;
+	int			i;
+
+
+	/* Create a ParseState for rewriting the view definition query */
+	pstate = make_parsestate(NULL);
+	pstate->p_queryEnv = queryEnv;
+	pstate->p_expr_kind = EXPR_KIND_SELECT_TARGET;
+
+	rel = trigdata->tg_relation;
+	relid = rel->rd_id;
+
+	matviewOid = DatumGetObjectId(DirectFunctionCall1(oidin, CStringGetDatum(matviewOid_text)));
+
+	/*
+	 * On the first call initialize the hashtable
+	 */
+	if (!mv_trigger_info)
+		mv_InitHashTables();
+
+	/* get the entry for this materialized view */
+	entry = (MV_TriggerHashEntry *) hash_search(mv_trigger_info,
+											  (void *) &matviewOid,
+											  HASH_FIND, &found);
+	Assert (found && entry != NULL);
+	entry->after_trig_count++;
+
+	/* search the entry for the modified table and create new entry if not found */
+	found = false;
+	foreach(lc, entry->tables)
+	{
+		table = (MV_TriggerTable *) lfirst(lc);
+		if (table->table_id == relid)
+		{
+			found = true;
+			break;
+		}
+	}
+	if (!found)
+	{
+		oldcxt = MemoryContextSwitchTo(TopTransactionContext);
+
+		table = (MV_TriggerTable *) palloc0(sizeof(MV_TriggerTable));
+		table->table_id = relid;
+		table->old_tuplestores = NIL;
+		table->new_tuplestores = NIL;
+		table->old_rtes = NIL;
+		table->new_rtes = NIL;
+		table->rte_indexes = NIL;
+		entry->tables = lappend(entry->tables, table);
+
+		MemoryContextSwitchTo(oldcxt);
+	}
+
+	/* Save the transition tables and make a request to not free immediately */
+	if (trigdata->tg_oldtable)
+	{
+		oldcxt = MemoryContextSwitchTo(TopTransactionContext);
+		table->old_tuplestores = lappend(table->old_tuplestores, trigdata->tg_oldtable);
+		entry->has_old = true;
+		MemoryContextSwitchTo(oldcxt);
+	}
+	if (trigdata->tg_newtable)
+	{
+		oldcxt = MemoryContextSwitchTo(TopTransactionContext);
+		table->new_tuplestores = lappend(table->new_tuplestores, trigdata->tg_newtable);
+		entry->has_new = true;
+		MemoryContextSwitchTo(oldcxt);
+	}
+	if (entry->has_new || entry->has_old)
+	{
+		CmdType cmd;
+
+		if (TRIGGER_FIRED_BY_INSERT(trigdata->tg_event))
+			cmd = CMD_INSERT;
+		else if (TRIGGER_FIRED_BY_DELETE(trigdata->tg_event))
+			cmd = CMD_DELETE;
+		else if (TRIGGER_FIRED_BY_UPDATE(trigdata->tg_event))
+			cmd = CMD_UPDATE;
+		else
+			elog(ERROR,"unsupported trigger type");
+
+		/* Prolong lifespan of transition tables to the end of the last AFTER trigger */
+		SetTransitionTablePreserved(relid, cmd);
+	}
+
+
+	/* If this is not the last AFTER trigger call, immediately exit. */
+	Assert (entry->before_trig_count >= entry->after_trig_count);
+	if (entry->before_trig_count != entry->after_trig_count)
+		return PointerGetDatum(NULL);
+
+	/*
+	 * If this is the last AFTER trigger call, continue and update the view.
+	 */
+
+	/*
+	 * Advance command counter to make the updated base table row locally
+	 * visible.
+	 */
+	CommandCounterIncrement();
+
+	matviewRel = table_open(matviewOid, NoLock);
+
+	/* get view query*/
+	query = get_matview_query(matviewRel);
+
+	/* Make sure it is a materialized view. */
+	Assert(matviewRel->rd_rel->relkind == RELKIND_MATVIEW);
+
+	/*
+	 * Get and push the latast snapshot to see any changes which is committed
+	 * during waiting in other transactions at READ COMMITTED level.
+	 */
+	PushActiveSnapshot(GetTransactionSnapshot());
+
+	/*
+	 * Check for active uses of the relation in the current transaction, such
+	 * as open scans.
+	 *
+	 * NB: We count on this to protect us against problems with refreshing the
+	 * data using TABLE_INSERT_FROZEN.
+	 */
+	CheckTableNotInUse(matviewRel, "refresh a materialized view incrementally");
+
+	/*
+	 * Switch to the owner's userid, so that any functions are run as that
+	 * user.  Also arrange to make GUC variable changes local to this command.
+	 * We will switch modes when we are about to execute user code.
+	 */
+	relowner = matviewRel->rd_rel->relowner;
+	GetUserIdAndSecContext(&save_userid, &save_sec_context);
+	SetUserIdAndSecContext(relowner,
+						   save_sec_context | SECURITY_RESTRICTED_OPERATION);
+	save_nestlevel = NewGUCNestLevel();
+
+	/*
+	 * rewrite query for calculating deltas
+	 */
+
+	rewritten = copyObject(query);
+
+	/* Replace resnames in a target list with materialized view's attnames */
+	i = 0;
+	foreach (lc, rewritten->targetList)
+	{
+		TargetEntry *tle = (TargetEntry *) lfirst(lc);
+		Form_pg_attribute attr = TupleDescAttr(matviewRel->rd_att, i);
+		char *resname = NameStr(attr->attname);
+
+		tle->resname = pstrdup(resname);
+		i++;
+	}
+
+	/* Set all tables in the query to pre-update state */
+	rewritten = rewrite_query_for_preupdate_state(rewritten, entry->tables,
+												  entry->xid, entry->cid,
+												  pstate);
+	/* Rewrite for DISTINCT clause */
+	rewritten = rewrite_query_for_distinct(rewritten, pstate);
+
+	/* Create tuplestores to store view deltas */
+	if (entry->has_old)
+	{
+		oldcxt = MemoryContextSwitchTo(TopTransactionContext);
+
+		old_tuplestore = tuplestore_begin_heap(false, false, work_mem);
+		dest_old = CreateDestReceiver(DestTuplestore);
+		SetTuplestoreDestReceiverParams(dest_old,
+									old_tuplestore,
+									TopTransactionContext,
+									false,
+									NULL,
+									NULL);
+
+		MemoryContextSwitchTo(oldcxt);
+	}
+	if (entry->has_new)
+	{
+		oldcxt = MemoryContextSwitchTo(TopTransactionContext);
+
+		new_tuplestore = tuplestore_begin_heap(false, false, work_mem);
+		dest_new = CreateDestReceiver(DestTuplestore);
+		SetTuplestoreDestReceiverParams(dest_new,
+									new_tuplestore,
+									TopTransactionContext,
+									false,
+									NULL,
+									NULL);
+		MemoryContextSwitchTo(oldcxt);
+	}
+
+	/* for all modified tables */
+	foreach(lc, entry->tables)
+	{
+		ListCell *lc2;
+
+		table = (MV_TriggerTable *) lfirst(lc);
+
+		/* loop for self-join */
+		foreach(lc2, table->rte_indexes)
+		{
+			int	rte_index = lfirst_int(lc2);
+			TupleDesc		tupdesc_old;
+			TupleDesc		tupdesc_new;
+			bool	use_count = false;
+			char   *count_colname = NULL;
+
+			count_colname = pstrdup("__ivm_count__");
+
+			if (query->distinctClause)
+				use_count = true;
+
+			/* calculate delta tables */
+			calc_delta(table, rte_index, rewritten, dest_old, dest_new,
+					   &tupdesc_old, &tupdesc_new, queryEnv);
+
+			/* Set the table in the query to post-update state */
+			rewritten = rewrite_query_for_postupdate_state(rewritten, table, rte_index);
+
+			PG_TRY();
+			{
+				/* apply the delta tables to the materialized view */
+				apply_delta(matviewOid, old_tuplestore, new_tuplestore,
+							tupdesc_old, tupdesc_new, query, use_count,
+							count_colname);
+			}
+			PG_CATCH();
+			{
+				matview_maintenance_depth = old_depth;
+				PG_RE_THROW();
+			}
+			PG_END_TRY();
+
+			/* clear view delta tuplestores */
+			if (old_tuplestore)
+				tuplestore_clear(old_tuplestore);
+			if (new_tuplestore)
+				tuplestore_clear(new_tuplestore);
+		}
+	}
+
+	/* Clean up hash entry and delete tuplestores */
+	clean_up_IVM_hash_entry(entry);
+	if (old_tuplestore)
+	{
+		dest_old->rDestroy(dest_old);
+		tuplestore_end(old_tuplestore);
+	}
+	if (new_tuplestore)
+	{
+		dest_new->rDestroy(dest_new);
+		tuplestore_end(new_tuplestore);
+	}
+
+	/* Pop the original snapshot. */
+	PopActiveSnapshot();
+
+	table_close(matviewRel, NoLock);
+
+	/* Roll back any GUC changes */
+	AtEOXact_GUC(false, save_nestlevel);
+
+	/* Restore userid and security context */
+	SetUserIdAndSecContext(save_userid, save_sec_context);
+
+	return PointerGetDatum(NULL);
+}
+
+/*
+ * rewrite_query_for_preupdate_state
+ *
+ * Rewrite the query so that base tables' RTEs will represent "pre-update"
+ * state of tables. This is necessary to calculate view delta after multiple
+ * tables are modified. xid and cid are the transaction id and command id
+ * before the first table was modified.
+ */
+static Query*
+rewrite_query_for_preupdate_state(Query *query, List *tables,
+								  TransactionId xid, CommandId cid,
+								  ParseState *pstate)
+{
+	ListCell *lc;
+	int num_rte = list_length(query->rtable);
+	int i;
+
+
+	/* register delta ENRs */
+	register_delta_ENRs(pstate, query, tables);
+
+	/* XXX: Is necessary? Is this right timing? */
+	AcquireRewriteLocks(query, true, false);
+
+	i = 1;
+	foreach(lc, query->rtable)
+	{
+		RangeTblEntry *r = (RangeTblEntry*) lfirst(lc);
+
+		ListCell *lc2;
+		foreach(lc2, tables)
+		{
+			MV_TriggerTable *table = (MV_TriggerTable *) lfirst(lc2);
+			/*
+			 * if the modified table is found then replace the original RTE with
+			 * "pre-state" RTE and append its index to the list.
+			 */
+			if (r->relid == table->table_id)
+			{
+				lfirst(lc) = get_prestate_rte(r, table, xid, cid, pstate->p_queryEnv);
+				table->rte_indexes = lappend_int(table->rte_indexes, i);
+				break;
+			}
+		}
+
+		/* finish the loop if we processed all RTE included in the original query */
+		if (i++ >= num_rte)
+			break;
+	}
+
+	return query;
+}
+
+/*
+ * register_delta_ENRs
+ *
+ * For all modified tables, make ENRs for their transition tables
+ * and register them to the queryEnv. ENR's RTEs are also appended
+ * into the list in query tree.
+ */
+static void
+register_delta_ENRs(ParseState *pstate, Query *query, List *tables)
+{
+	QueryEnvironment *queryEnv = pstate->p_queryEnv;
+	ListCell *lc;
+	RangeTblEntry	*rte;
+
+	foreach(lc, tables)
+	{
+		MV_TriggerTable *table = (MV_TriggerTable *) lfirst(lc);
+		ListCell *lc2;
+		int count;
+
+		count = 0;
+		foreach(lc2, table->old_tuplestores)
+		{
+			Tuplestorestate *oldtable = (Tuplestorestate *) lfirst(lc2);
+			EphemeralNamedRelation enr =
+				palloc(sizeof(EphemeralNamedRelationData));
+			ParseNamespaceItem *nsitem;
+
+			enr->md.name = make_delta_enr_name("old", table->table_id, count);
+			enr->md.reliddesc = table->table_id;
+			enr->md.tupdesc = NULL;
+			enr->md.enrtype = ENR_NAMED_TUPLESTORE;
+			enr->md.enrtuples = tuplestore_tuple_count(oldtable);
+			enr->reldata = oldtable;
+			register_ENR(queryEnv, enr);
+
+			nsitem = addRangeTableEntryForENR(pstate, makeRangeVar(NULL, enr->md.name, -1), true);
+			rte = nsitem->p_rte;
+			/* if base table has RLS, set security condition to enr */
+			rte->securityQuals = get_securityQuals(table->table_id, list_length(query->rtable) + 1, query);
+
+			query->rtable = lappend(query->rtable, rte);
+			table->old_rtes = lappend(table->old_rtes, rte);
+
+			count++;
+		}
+
+		count = 0;
+		foreach(lc2, table->new_tuplestores)
+		{
+			Tuplestorestate *newtable = (Tuplestorestate *) lfirst(lc2);
+			EphemeralNamedRelation enr =
+				palloc(sizeof(EphemeralNamedRelationData));
+			ParseNamespaceItem *nsitem;
+
+			enr->md.name = make_delta_enr_name("new", table->table_id, count);
+			enr->md.reliddesc = table->table_id;
+			enr->md.tupdesc = NULL;
+			enr->md.enrtype = ENR_NAMED_TUPLESTORE;
+			enr->md.enrtuples = tuplestore_tuple_count(newtable);
+			enr->reldata = newtable;
+			register_ENR(queryEnv, enr);
+
+			nsitem = addRangeTableEntryForENR(pstate, makeRangeVar(NULL, enr->md.name, -1), true);
+			rte = nsitem->p_rte;
+			/* if base table has RLS, set security condition to enr*/
+			rte->securityQuals = get_securityQuals(table->table_id, list_length(query->rtable) + 1, query);
+
+			query->rtable = lappend(query->rtable, rte);
+			table->new_rtes = lappend(table->new_rtes, rte);
+
+			count++;
+		}
+	}
+}
+
+/*
+ * get_prestate_rte
+ *
+ * Rewrite RTE of the modified table to a subquery which represents
+ * "pre-state" table. The original RTE is saved in table->rte_original.
+ */
+static RangeTblEntry*
+get_prestate_rte(RangeTblEntry *rte, MV_TriggerTable *table,
+				 TransactionId xid, CommandId cid,
+				 QueryEnvironment *queryEnv)
+{
+	StringInfoData str;
+	RawStmt *raw;
+	Query *sub;
+	Relation rel;
+	ParseState *pstate;
+	char *relname;
+	int i;
+
+	pstate = make_parsestate(NULL);
+	pstate->p_queryEnv = queryEnv;
+	pstate->p_expr_kind = EXPR_KIND_SELECT_TARGET;
+
+	/*
+	 * We can use NoLock here since AcquireRewriteLocks should
+	 * have locked the rel already.
+	 */
+	rel = table_open(table->table_id, NoLock);
+	relname = quote_qualified_identifier(
+					get_namespace_name(RelationGetNamespace(rel)),
+									   RelationGetRelationName(rel));
+	table_close(rel, NoLock);
+
+	initStringInfo(&str);
+	appendStringInfo(&str,
+		"SELECT t.* FROM %s t"
+		" WHERE (age(t.xmin) - age(%u::text::xid) > 0) OR"
+		" (t.xmin = %u AND t.cmin::text::int < %u)",
+			relname, xid, xid, cid);
+
+	for (i = 0; i < list_length(table->old_tuplestores); i++)
+	{
+		appendStringInfo(&str, " UNION ALL ");
+		appendStringInfo(&str," SELECT * FROM %s",
+			make_delta_enr_name("old", table->table_id, i));
+	}
+
+	raw = (RawStmt*)linitial(raw_parser(str.data, RAW_PARSE_DEFAULT));
+	sub = transformStmt(pstate, raw->stmt);
+
+	/* If this query has setOperations, RTEs in rtables has a subquery which contains ENR */
+	if (sub->setOperations != NULL)
+	{
+		ListCell *lc;
+
+		/* add securityQuals for tuplestores */
+		foreach (lc, sub->rtable)
+		{
+			RangeTblEntry *rte;
+			RangeTblEntry *sub_rte;
+
+			rte = (RangeTblEntry *)lfirst(lc);
+			Assert(rte->subquery != NULL);
+
+			sub_rte = (RangeTblEntry *)linitial(rte->subquery->rtable);
+			if (sub_rte->rtekind == RTE_NAMEDTUPLESTORE)
+				/* rt_index is always 1, bacause subquery has enr_rte only */
+				sub_rte->securityQuals = get_securityQuals(sub_rte->relid, 1, sub);
+		}
+	}
+
+	/* save the original RTE */
+	table->original_rte = copyObject(rte);
+
+	rte->rtekind = RTE_SUBQUERY;
+	rte->subquery = sub;
+	rte->security_barrier = false;
+	/* Clear fields that should not be set in a subquery RTE */
+	rte->relid = InvalidOid;
+	rte->relkind = 0;
+	rte->rellockmode = 0;
+	rte->tablesample = NULL;
+	rte->inh = false;			/* must not be set for a subquery */
+
+	rte->requiredPerms = 0;		/* no permission check on subquery itself */
+	rte->checkAsUser = InvalidOid;
+	rte->selectedCols = NULL;
+	rte->insertedCols = NULL;
+	rte->updatedCols = NULL;
+	rte->extraUpdatedCols = NULL;
+
+	return rte;
+}
+
+/*
+ * make_delta_enr_name
+ *
+ * Make a name for ENR of a transition table from the base table's oid.
+ * prefix will be "new" or "old" depending on its transition table kind..
+ */
+static char*
+make_delta_enr_name(const char *prefix, Oid relid, int count)
+{
+	char buf[NAMEDATALEN];
+	char *name;
+
+	snprintf(buf, NAMEDATALEN, "__ivm_%s_%u_%u", prefix, relid, count);
+	name = pstrdup(buf);
+
+	return name;
+}
+
+/*
+ * union_ENRs
+ *
+ * Make a single table delta by unionning all transition tables of the modified table
+ * whose RTE is specified by
+ */
+static RangeTblEntry*
+union_ENRs(RangeTblEntry *rte, Oid relid, List *enr_rtes, const char *prefix,
+		   QueryEnvironment *queryEnv)
+{
+	StringInfoData str;
+	ParseState	*pstate;
+	RawStmt *raw;
+	Query *sub;
+	int	i;
+	RangeTblEntry *enr_rte;
+
+	/* Create a ParseState for rewriting the view definition query */
+	pstate = make_parsestate(NULL);
+	pstate->p_queryEnv = queryEnv;
+	pstate->p_expr_kind = EXPR_KIND_SELECT_TARGET;
+
+	initStringInfo(&str);
+
+	for (i = 0; i < list_length(enr_rtes); i++)
+	{
+		if (i > 0)
+			appendStringInfo(&str, " UNION ALL ");
+
+		appendStringInfo(&str,
+			" SELECT * FROM %s",
+			make_delta_enr_name(prefix, relid, i));
+	}
+
+	raw = (RawStmt*)linitial(raw_parser(str.data, RAW_PARSE_DEFAULT));
+	sub = transformStmt(pstate, raw->stmt);
+
+	rte->rtekind = RTE_SUBQUERY;
+	rte->subquery = sub;
+	rte->security_barrier = false;
+	/* Clear fields that should not be set in a subquery RTE */
+	rte->relid = InvalidOid;
+	rte->relkind = 0;
+	rte->rellockmode = 0;
+	rte->tablesample = NULL;
+	rte->inh = false;			/* must not be set for a subquery */
+
+	rte->requiredPerms = 0;		/* no permission check on subquery itself */
+	rte->checkAsUser = InvalidOid;
+	rte->selectedCols = NULL;
+	rte->insertedCols = NULL;
+	rte->updatedCols = NULL;
+	rte->extraUpdatedCols = NULL;
+	/* if base table has RLS, set security condition to enr*/
+	enr_rte = (RangeTblEntry *)linitial(sub->rtable);
+	/* rt_index is always 1, bacause subquery has enr_rte only */
+	enr_rte->securityQuals = get_securityQuals(relid, 1, sub);
+
+	return rte;
+}
+
+/*
+ * rewrite_query_for_distinct
+ *
+ * Rewrite query for counting DISTINCT clause.
+ */
+static Query *
+rewrite_query_for_distinct(Query *query, ParseState *pstate)
+{
+	TargetEntry *tle_count;
+	FuncCall *fn;
+	Node *node;
+
+	/* Add count(*) for counting distinct tuples in views */
+	fn = makeFuncCall(list_make1(makeString("count")), NIL, COERCE_EXPLICIT_CALL, -1);
+	fn->agg_star = true;
+	if (!query->groupClause && !query->hasAggs)
+		query->groupClause = transformDistinctClause(NULL, &query->targetList, query->sortClause, false);
+
+	node = ParseFuncOrColumn(pstate, fn->funcname, NIL, NULL, fn, false, -1);
+
+	tle_count = makeTargetEntry((Expr *) node,
+								list_length(query->targetList) + 1,
+								pstrdup("__ivm_count__"),
+								false);
+	query->targetList = lappend(query->targetList, tle_count);
+	query->hasAggs = true;
+
+	return query;
+}
+
+/*
+ * calc_delta
+ *
+ * Calculate view deltas generated under the modification of a table specified
+ * by the RTE index.
+ */
+static void
+calc_delta(MV_TriggerTable *table, int rte_index, Query *query,
+			DestReceiver *dest_old, DestReceiver *dest_new,
+			TupleDesc *tupdesc_old, TupleDesc *tupdesc_new,
+			QueryEnvironment *queryEnv)
+{
+	ListCell *lc = list_nth_cell(query->rtable, rte_index - 1);
+	RangeTblEntry *rte = (RangeTblEntry *) lfirst(lc);
+
+	/* Generate old delta */
+	if (list_length(table->old_rtes) > 0)
+	{
+		/* Replace the modified table with the old delta table and calculate the old view delta. */
+		lfirst(lc) = union_ENRs(rte, table->table_id, table->old_rtes, "old", queryEnv);
+		refresh_matview_datafill(dest_old, query, queryEnv, tupdesc_old, "");
+	}
+
+	/* Generate new delta */
+	if (list_length(table->new_rtes) > 0)
+	{
+		/* Replace the modified table with the new delta table and calculate the new view delta*/
+		lfirst(lc) = union_ENRs(rte, table->table_id, table->new_rtes, "new", queryEnv);
+		refresh_matview_datafill(dest_new, query, queryEnv, tupdesc_new, "");
+	}
+}
+
+/*
+ * rewrite_query_for_postupdate_state
+ *
+ * Rewrite the query so that the specified base table's RTEs will represent
+ * "post-update" state of tables. This is called after the view delta
+ * calculation due to changes on this table finishes.
+ */
+static Query*
+rewrite_query_for_postupdate_state(Query *query, MV_TriggerTable *table, int rte_index)
+{
+	ListCell *lc = list_nth_cell(query->rtable, rte_index - 1);
+
+	/* Retore the original RTE */
+	lfirst(lc) = table->original_rte;
+
+	return query;
+}
+
+/*
+ * apply_delta
+ *
+ * Apply deltas to the materialized view. In outer join cases, this requires
+ * the view maintenance graph.
+ */
+static void
+apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *new_tuplestores,
+			TupleDesc tupdesc_old, TupleDesc tupdesc_new,
+			Query *query, bool use_count, char *count_colname)
+{
+	StringInfoData querybuf;
+	StringInfoData target_list_buf;
+	Relation	matviewRel;
+	char	   *matviewname;
+	ListCell	*lc;
+	int			i;
+	List	   *keys = NIL;
+
+
+	/*
+	 * get names of the materialized view and delta tables
+	 */
+
+	matviewRel = table_open(matviewOid, NoLock);
+	matviewname = quote_qualified_identifier(get_namespace_name(RelationGetNamespace(matviewRel)),
+											 RelationGetRelationName(matviewRel));
+
+	/*
+	 * Build parts of the maintenance queries
+	 */
+
+	initStringInfo(&querybuf);
+	initStringInfo(&target_list_buf);
+
+	/* build string of target list */
+	for (i = 0; i < matviewRel->rd_att->natts; i++)
+	{
+		Form_pg_attribute attr = TupleDescAttr(matviewRel->rd_att, i);
+		char   *resname = NameStr(attr->attname);
+
+		if (i != 0)
+			appendStringInfo(&target_list_buf, ", ");
+		appendStringInfo(&target_list_buf, "%s", quote_qualified_identifier(NULL, resname));
+	}
+
+	i = 0;
+	foreach (lc, query->targetList)
+	{
+		TargetEntry *tle = (TargetEntry *) lfirst(lc);
+		Form_pg_attribute attr = TupleDescAttr(matviewRel->rd_att, i);
+		char *resname = NameStr(attr->attname);
+
+		i++;
+
+		if (tle->resjunk)
+			continue;
+
+		keys = lappend(keys, resname);
+	}
+
+	/* Start maintaining the materialized view. */
+	OpenMatViewIncrementalMaintenance();
+
+	/* Open SPI context. */
+	if (SPI_connect() != SPI_OK_CONNECT)
+		elog(ERROR, "SPI_connect failed");
+
+	/* For tuple deletion */
+	if (old_tuplestores && tuplestore_tuple_count(old_tuplestores) > 0)
+	{
+		EphemeralNamedRelation enr = palloc(sizeof(EphemeralNamedRelationData));
+		int				rc;
+
+		/* convert tuplestores to ENR, and register for SPI */
+		enr->md.name = pstrdup(OLD_DELTA_ENRNAME);
+		enr->md.reliddesc = InvalidOid;
+		enr->md.tupdesc = tupdesc_old;
+		enr->md.enrtype = ENR_NAMED_TUPLESTORE;
+		enr->md.enrtuples = tuplestore_tuple_count(old_tuplestores);
+		enr->reldata = old_tuplestores;
+
+		rc = SPI_register_relation(enr);
+		if (rc != SPI_OK_REL_REGISTER)
+			elog(ERROR, "SPI_register failed");
+
+		if (use_count)
+			/* apply old delta and get rows to be recalculated */
+			apply_old_delta_with_count(matviewname, OLD_DELTA_ENRNAME,
+									   keys, count_colname);
+		else
+			apply_old_delta(matviewname, OLD_DELTA_ENRNAME, keys);
+
+	}
+	/* For tuple insertion */
+	if (new_tuplestores && tuplestore_tuple_count(new_tuplestores) > 0)
+	{
+		EphemeralNamedRelation enr = palloc(sizeof(EphemeralNamedRelationData));
+		int rc;
+
+		/* convert tuplestores to ENR, and register for SPI */
+		enr->md.name = pstrdup(NEW_DELTA_ENRNAME);
+		enr->md.reliddesc = InvalidOid;
+		enr->md.tupdesc = tupdesc_new;;
+		enr->md.enrtype = ENR_NAMED_TUPLESTORE;
+		enr->md.enrtuples = tuplestore_tuple_count(new_tuplestores);
+		enr->reldata = new_tuplestores;
+
+		rc = SPI_register_relation(enr);
+		if (rc != SPI_OK_REL_REGISTER)
+			elog(ERROR, "SPI_register failed");
+
+		/* apply new delta */
+		if (use_count)
+			apply_new_delta_with_count(matviewname, NEW_DELTA_ENRNAME,
+								keys, &target_list_buf, count_colname);
+		else
+			apply_new_delta(matviewname, NEW_DELTA_ENRNAME, &target_list_buf);
+	}
+
+	/* We're done maintaining the materialized view. */
+	CloseMatViewIncrementalMaintenance();
+
+	table_close(matviewRel, NoLock);
+
+	/* Close SPI context. */
+	if (SPI_finish() != SPI_OK_FINISH)
+		elog(ERROR, "SPI_finish failed");
+}
+
+/*
+ * apply_old_delta_with_count
+ *
+ * Execute a query for applying a delta table given by deltname_old
+ * which contains tuples to be deleted from to a materialized view given by
+ * matviewname.  This is used when counting is required, that is, the view
+ * has aggregate or distinct.
+ */
+static void
+apply_old_delta_with_count(const char *matviewname, const char *deltaname_old,
+				List *keys, const char *count_colname)
+{
+	StringInfoData	querybuf;
+	char   *match_cond;
+
+	/* build WHERE condition for searching tuples to be deleted */
+	match_cond = get_matching_condition_string(keys);
+
+	/* Search for matching tuples from the view and update or delete if found. */
+	initStringInfo(&querybuf);
+	appendStringInfo(&querybuf,
+					"WITH t AS ("			/* collecting tid of target tuples in the view */
+						"SELECT diff.%s, "			/* count column */
+								"(diff.%s OPERATOR(pg_catalog.=) mv.%s) AS for_dlt, "
+								"mv.ctid "
+						"FROM %s AS mv, %s AS diff "
+						"WHERE %s"					/* tuple matching condition */
+					"), updt AS ("			/* update a tuple if this is not to be deleted */
+						"UPDATE %s AS mv SET %s = mv.%s OPERATOR(pg_catalog.-) t.%s "
+						"FROM t WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND NOT for_dlt "
+					"), dlt AS ("			/* delete a tuple if this is to be deleted */
+						"DELETE FROM %s AS mv USING t "
+						"WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt"
+					")",
+					count_colname,
+					count_colname, count_colname,
+					matviewname, deltaname_old,
+					match_cond,
+					matviewname, count_colname, count_colname, count_colname,
+					matviewname);
+
+	if (SPI_exec(querybuf.data, 0) != SPI_OK_DELETE)
+		elog(ERROR, "SPI_exec failed: %s", querybuf.data);
+}
+
+/*
+ * apply_old_delta
+ *
+ * Execute a query for applying a delta table given by deltname_old
+ * which contains tuples to be deleted from to a materialized view given by
+ * matviewname.  This is used when counting is not required.
+ */
+static void
+apply_old_delta(const char *matviewname, const char *deltaname_old,
+				List *keys)
+{
+	StringInfoData	querybuf;
+	StringInfoData	keysbuf;
+	char   *match_cond;
+	ListCell *lc;
+
+	/* build WHERE condition for searching tuples to be deleted */
+	match_cond = get_matching_condition_string(keys);
+
+	/* build string of keys list */
+	initStringInfo(&keysbuf);
+	foreach (lc, keys)
+	{
+		Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc);
+		char   *resname = NameStr(attr->attname);
+		appendStringInfo(&keysbuf, "%s", quote_qualified_identifier("mv", resname));
+		if (lnext(keys, lc))
+			appendStringInfo(&keysbuf, ", ");
+	}
+
+	/* Search for matching tuples from the view and update or delete if found. */
+	initStringInfo(&querybuf);
+	appendStringInfo(&querybuf,
+	"DELETE FROM %s WHERE ctid IN ("
+		"SELECT tid FROM (SELECT row_number() over (partition by %s) AS \"__ivm_row_number__\","
+								  "mv.ctid AS tid,"
+								  "diff.\"__ivm_count__\""
+						 "FROM %s AS mv, %s AS diff "
+						 "WHERE %s) v "
+					"WHERE v.\"__ivm_row_number__\" OPERATOR(pg_catalog.<=) v.\"__ivm_count__\")",
+					matviewname,
+					keysbuf.data,
+					matviewname, deltaname_old,
+					match_cond);
+
+	if (SPI_exec(querybuf.data, 0) != SPI_OK_DELETE)
+		elog(ERROR, "SPI_exec failed: %s", querybuf.data);
+}
+
+/*
+ * apply_new_delta_with_count
+ *
+ * Execute a query for applying a delta table given by deltname_new
+ * which contains tuples to be inserted into a materialized view given by
+ * matviewname.  This is used when counting is required, that is, the view
+ * has aggregate or distinct. Also, when a table in EXISTS sub queries
+ * is modified.
+ */
+static void
+apply_new_delta_with_count(const char *matviewname, const char* deltaname_new,
+				List *keys, StringInfo target_list, const char* count_colname)
+{
+	StringInfoData	querybuf;
+	StringInfoData	returning_keys;
+	ListCell	*lc;
+	char	*match_cond = "";
+
+	/* build WHERE condition for searching tuples to be updated */
+	match_cond = get_matching_condition_string(keys);
+
+	/* build string of keys list */
+	initStringInfo(&returning_keys);
+	if (keys)
+	{
+		foreach (lc, keys)
+		{
+			Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc);
+			char   *resname = NameStr(attr->attname);
+			appendStringInfo(&returning_keys, "%s", quote_qualified_identifier("mv", resname));
+			if (lnext(keys, lc))
+				appendStringInfo(&returning_keys, ", ");
+		}
+	}
+	else
+		appendStringInfo(&returning_keys, "NULL");
+
+	/* Search for matching tuples from the view and update if found or insert if not. */
+	initStringInfo(&querybuf);
+	appendStringInfo(&querybuf,
+					"WITH updt AS ("		/* update a tuple if this exists in the view */
+						"UPDATE %s AS mv SET %s = mv.%s OPERATOR(pg_catalog.+) diff.%s "
+						"FROM %s AS diff "
+						"WHERE %s "					/* tuple matching condition */
+						"RETURNING %s"				/* returning keys of updated tuples */
+					") INSERT INTO %s (%s)"	/* insert a new tuple if this doesn't existw */
+						"SELECT %s FROM %s AS diff "
+						"WHERE NOT EXISTS (SELECT 1 FROM updt AS mv WHERE %s);",
+					matviewname, count_colname, count_colname, count_colname,
+					deltaname_new,
+					match_cond,
+					returning_keys.data,
+					matviewname, target_list->data,
+					target_list->data, deltaname_new,
+					match_cond);
+
+	if (SPI_exec(querybuf.data, 0) != SPI_OK_INSERT)
+		elog(ERROR, "SPI_exec failed: %s", querybuf.data);
+}
+
+/*
+ * apply_new_delta
+ *
+ * Execute a query for applying a delta table given by deltname_new
+ * which contains tuples to be inserted into a materialized view given by
+ * matviewname.  This is used when counting is not required.
+ */
+static void
+apply_new_delta(const char *matviewname, const char *deltaname_new,
+				StringInfo target_list)
+{
+	StringInfoData	querybuf;
+
+	/* Search for matching tuples from the view and update or delete if found. */
+	initStringInfo(&querybuf);
+	appendStringInfo(&querybuf,
+					"INSERT INTO %s (%s) SELECT %s FROM ("
+						"SELECT diff.*, generate_series(1, diff.\"__ivm_count__\") "
+						"FROM %s AS diff) AS v",
+					matviewname, target_list->data, target_list->data,
+					deltaname_new);
+
+	if (SPI_exec(querybuf.data, 0) != SPI_OK_INSERT)
+		elog(ERROR, "SPI_exec failed: %s", querybuf.data);
+}
+
+/*
+ * get_matching_condition_string
+ *
+ * Build a predicate string for looking for a tuple with given keys.
+ */
+static char *
+get_matching_condition_string(List *keys)
+{
+	StringInfoData match_cond;
+	ListCell	*lc;
+
+	/* If there is no key columns, the condition is always true. */
+	if (keys == NIL)
+		return "true";
+
+	initStringInfo(&match_cond);
+	foreach (lc, keys)
+	{
+		Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc);
+		char   *resname = NameStr(attr->attname);
+		char   *mv_resname = quote_qualified_identifier("mv", resname);
+		char   *diff_resname = quote_qualified_identifier("diff", resname);
+		Oid		typid = attr->atttypid;
+
+		/* Considering NULL values, we can not use simple = operator. */
+		appendStringInfo(&match_cond, "(");
+		generate_equal(&match_cond, typid, mv_resname, diff_resname);
+		appendStringInfo(&match_cond, " OR (%s IS NULL AND %s IS NULL))",
+						 mv_resname, diff_resname);
+
+		if (lnext(keys, lc))
+			appendStringInfo(&match_cond, " AND ");
+	}
+
+	return match_cond.data;
+}
+
+/*
+ * generate_equals
+ *
+ * Generate an equality clause using given operands' default equality
+ * operator.
+ */
+static void
+generate_equal(StringInfo querybuf, Oid opttype,
+			   const char *leftop, const char *rightop)
+{
+	TypeCacheEntry *typentry;
+
+	typentry = lookup_type_cache(opttype, TYPECACHE_EQ_OPR);
+	if (!OidIsValid(typentry->eq_opr))
+		ereport(ERROR,
+				(errcode(ERRCODE_UNDEFINED_FUNCTION),
+				 errmsg("could not identify an equality operator for type %s",
+						format_type_be(opttype))));
+
+	generate_operator_clause(querybuf,
+							 leftop, opttype,
+							 typentry->eq_opr,
+							 rightop, opttype);
+}
+
+/*
+ * mv_InitHashTables
+ */
+static void
+mv_InitHashTables(void)
+{
+	HASHCTL		ctl;
+
+	memset(&ctl, 0, sizeof(ctl));
+	ctl.keysize = sizeof(Oid);
+	ctl.entrysize = sizeof(MV_TriggerHashEntry);
+	mv_trigger_info = hash_create("MV trigger info",
+								 MV_INIT_QUERYHASHSIZE,
+								 &ctl, HASH_ELEM | HASH_BLOBS);
+}
+
+/*
+ * AtAbort_IVM
+ *
+ * Clean up hash entries for all materialized views. This is called at
+ * transaction abort.
+ */
+void
+AtAbort_IVM()
+{
+	HASH_SEQ_STATUS seq;
+	MV_TriggerHashEntry *entry;
+
+	if (mv_trigger_info)
+	{
+		hash_seq_init(&seq, mv_trigger_info);
+		while ((entry = hash_seq_search(&seq)) != NULL)
+			clean_up_IVM_hash_entry(entry);
+	}
+}
+
+/*
+ * clean_up_IVM_hash_entry
+ *
+ * Clean up tuple stores and hash entries for a materialized view after its
+ * maintenance finished.
+ */
+static void
+clean_up_IVM_hash_entry(MV_TriggerHashEntry *entry)
+{
+	bool found;
+	ListCell *lc;
+
+	foreach(lc, entry->tables)
+	{
+		MV_TriggerTable *table = (MV_TriggerTable *) lfirst(lc);
+
+		list_free(table->old_tuplestores);
+		list_free(table->new_tuplestores);
+	}
+	list_free(entry->tables);
+
+	hash_search(mv_trigger_info, (void *) &entry->matview_id, HASH_REMOVE, &found);
+}
+
+/*
+ * isIvmName
+ *
+ * Check if this is a IVM hidden column from the name.
+ */
+bool
+isIvmName(const char *s)
+{
+	if (s)
+		return (strncmp(s, "__ivm_", 6) == 0);
+	return false;
+}
+
+/*
+ * get_securityQuals
+ *
+ * Get row security policy on a relation.
+ * This is used by IVM for copying RLS from base table to enr.
+ */
+static List *
+get_securityQuals(Oid relId, int rt_index, Query *query)
+{
+	ParseState *pstate;
+	Relation rel;
+	ParseNamespaceItem *nsitem;
+	RangeTblEntry *rte;
+	List *securityQuals;
+	List *withCheckOptions;
+	bool  hasRowSecurity;
+	bool  hasSubLinks;
+
+	securityQuals = NIL;
+	pstate = make_parsestate(NULL);
+
+	rel = table_open(relId, NoLock);
+	nsitem = addRangeTableEntryForRelation(pstate, rel, AccessShareLock, NULL, false, false);
+	rte = nsitem->p_rte;
+
+	get_row_security_policies(query, rte, rt_index,
+							  &securityQuals, &withCheckOptions,
+							  &hasRowSecurity, &hasSubLinks);
+
+	/*
+	 * Make sure the query is marked correctly if row level security
+	 * applies, or if the new quals had sublinks.
+	 */
+	if (hasRowSecurity)
+		query->hasRowSecurity = true;
+	if (hasSubLinks)
+		query->hasSubLinks = true;
+
+	table_close(rel, NoLock);
+
+	return securityQuals;
+}
diff --git a/src/backend/commands/tablecmds.c b/src/backend/commands/tablecmds.c
index dc5872f988..571f5c4cb9 100644
--- a/src/backend/commands/tablecmds.c
+++ b/src/backend/commands/tablecmds.c
@@ -51,6 +51,7 @@
 #include "commands/cluster.h"
 #include "commands/comment.h"
 #include "commands/defrem.h"
+#include "commands/matview.h"
 #include "commands/event_trigger.h"
 #include "commands/policy.h"
 #include "commands/sequence.h"
@@ -3415,6 +3416,14 @@ renameatt_internal(Oid myrelid,
 	targetrelation = relation_open(myrelid, AccessExclusiveLock);
 	renameatt_check(myrelid, RelationGetForm(targetrelation), recursing);
 
+	/*
+	 * Don't rename IVM columns.
+	 */
+	if (RelationIsIVM(targetrelation) && isIvmName(oldattname))
+		ereport(ERROR,
+				(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+				 errmsg("IVM column can not be renamed")));
+
 	/*
 	 * if the 'recurse' flag is set then we are supposed to rename this
 	 * attribute in all classes that inherit from 'relname' (as well as in
diff --git a/src/backend/nodes/copyfuncs.c b/src/backend/nodes/copyfuncs.c
index eb28657791..504ae3546e 100644
--- a/src/backend/nodes/copyfuncs.c
+++ b/src/backend/nodes/copyfuncs.c
@@ -2464,6 +2464,7 @@ _copyRangeTblEntry(const RangeTblEntry *from)
 	COPY_SCALAR_FIELD(relkind);
 	COPY_SCALAR_FIELD(rellockmode);
 	COPY_NODE_FIELD(tablesample);
+	COPY_SCALAR_FIELD(relisivm);
 	COPY_NODE_FIELD(subquery);
 	COPY_SCALAR_FIELD(security_barrier);
 	COPY_SCALAR_FIELD(jointype);
diff --git a/src/backend/nodes/equalfuncs.c b/src/backend/nodes/equalfuncs.c
index 521a87a8ea..56431f5aee 100644
--- a/src/backend/nodes/equalfuncs.c
+++ b/src/backend/nodes/equalfuncs.c
@@ -2776,6 +2776,7 @@ _equalRangeTblEntry(const RangeTblEntry *a, const RangeTblEntry *b)
 	COMPARE_SCALAR_FIELD(relkind);
 	COMPARE_SCALAR_FIELD(rellockmode);
 	COMPARE_NODE_FIELD(tablesample);
+	COMPARE_SCALAR_FIELD(relisivm);
 	COMPARE_NODE_FIELD(subquery);
 	COMPARE_SCALAR_FIELD(security_barrier);
 	COMPARE_SCALAR_FIELD(jointype);
diff --git a/src/backend/nodes/outfuncs.c b/src/backend/nodes/outfuncs.c
index 801c41b978..8cc0b93213 100644
--- a/src/backend/nodes/outfuncs.c
+++ b/src/backend/nodes/outfuncs.c
@@ -3259,6 +3259,7 @@ _outRangeTblEntry(StringInfo str, const RangeTblEntry *node)
 			WRITE_CHAR_FIELD(relkind);
 			WRITE_INT_FIELD(rellockmode);
 			WRITE_NODE_FIELD(tablesample);
+			WRITE_BOOL_FIELD(relisivm);
 			break;
 		case RTE_SUBQUERY:
 			WRITE_NODE_FIELD(subquery);
diff --git a/src/backend/nodes/readfuncs.c b/src/backend/nodes/readfuncs.c
index cc6dcb7220..37dff1ec27 100644
--- a/src/backend/nodes/readfuncs.c
+++ b/src/backend/nodes/readfuncs.c
@@ -1441,6 +1441,7 @@ _readRangeTblEntry(void)
 			READ_CHAR_FIELD(relkind);
 			READ_INT_FIELD(rellockmode);
 			READ_NODE_FIELD(tablesample);
+			READ_BOOL_FIELD(relisivm);
 			break;
 		case RTE_SUBQUERY:
 			READ_NODE_FIELD(subquery);
diff --git a/src/backend/parser/parse_relation.c b/src/backend/parser/parse_relation.c
index cb9e177b5e..dcfd1f3fc0 100644
--- a/src/backend/parser/parse_relation.c
+++ b/src/backend/parser/parse_relation.c
@@ -36,6 +36,7 @@
 #include "utils/rel.h"
 #include "utils/syscache.h"
 #include "utils/varlena.h"
+#include "commands/matview.h"
 
 
 /*
@@ -79,7 +80,7 @@ static void expandTupleDesc(TupleDesc tupdesc, Alias *eref,
 							int count, int offset,
 							int rtindex, int sublevels_up,
 							int location, bool include_dropped,
-							List **colnames, List **colvars);
+							List **colnames, List **colvars, bool is_ivm);
 static int	specialAttNum(const char *attname);
 static bool isQueryUsingTempRelation_walker(Node *node, void *context);
 
@@ -1433,6 +1434,7 @@ addRangeTableEntry(ParseState *pstate,
 	rte->relid = RelationGetRelid(rel);
 	rte->relkind = rel->rd_rel->relkind;
 	rte->rellockmode = lockmode;
+	rte->relisivm = rel->rd_rel->relisivm;
 
 	/*
 	 * Build the list of effective column names using user-supplied aliases
@@ -1521,6 +1523,7 @@ addRangeTableEntryForRelation(ParseState *pstate,
 	rte->relid = RelationGetRelid(rel);
 	rte->relkind = rel->rd_rel->relkind;
 	rte->rellockmode = lockmode;
+	rte->relisivm = rel->rd_rel->relisivm;
 
 	/*
 	 * Build the list of effective column names using user-supplied aliases
@@ -2676,7 +2679,7 @@ expandRTE(RangeTblEntry *rte, int rtindex, int sublevels_up,
 						expandTupleDesc(tupdesc, rte->eref,
 										rtfunc->funccolcount, atts_done,
 										rtindex, sublevels_up, location,
-										include_dropped, colnames, colvars);
+										include_dropped, colnames, colvars, false);
 					}
 					else if (functypclass == TYPEFUNC_SCALAR)
 					{
@@ -2944,7 +2947,7 @@ expandRelation(Oid relid, Alias *eref, int rtindex, int sublevels_up,
 	expandTupleDesc(rel->rd_att, eref, rel->rd_att->natts, 0,
 					rtindex, sublevels_up,
 					location, include_dropped,
-					colnames, colvars);
+					colnames, colvars, RelationIsIVM(rel));
 	relation_close(rel, AccessShareLock);
 }
 
@@ -2961,7 +2964,7 @@ static void
 expandTupleDesc(TupleDesc tupdesc, Alias *eref, int count, int offset,
 				int rtindex, int sublevels_up,
 				int location, bool include_dropped,
-				List **colnames, List **colvars)
+				List **colnames, List **colvars, bool is_ivm)
 {
 	ListCell   *aliascell;
 	int			varattno;
@@ -2974,6 +2977,9 @@ expandTupleDesc(TupleDesc tupdesc, Alias *eref, int count, int offset,
 	{
 		Form_pg_attribute attr = TupleDescAttr(tupdesc, varattno);
 
+		if (is_ivm && isIvmName(NameStr(attr->attname)) && !MatViewIncrementalMaintenanceIsEnabled())
+			continue;
+
 		if (attr->attisdropped)
 		{
 			if (include_dropped)
@@ -3127,6 +3133,10 @@ expandNSItemAttrs(ParseState *pstate, ParseNamespaceItem *nsitem,
 		Var		   *varnode = (Var *) lfirst(var);
 		TargetEntry *te;
 
+		/* if transform * into columnlist with IMMV, remove IVM columns */
+		if (rte->relisivm && isIvmName(label) && !MatViewIncrementalMaintenanceIsEnabled())
+			continue;
+
 		te = makeTargetEntry((Expr *) varnode,
 							 (AttrNumber) pstate->p_next_resno++,
 							 label,
diff --git a/src/backend/rewrite/rewriteDefine.c b/src/backend/rewrite/rewriteDefine.c
index 185bf5fbff..d8a8b66196 100644
--- a/src/backend/rewrite/rewriteDefine.c
+++ b/src/backend/rewrite/rewriteDefine.c
@@ -776,7 +776,8 @@ checkRuleResultList(List *targetList, TupleDesc resultDesc, bool isSelect,
 														attr->atttypmod))));
 	}
 
-	if (i != resultDesc->natts)
+	/* No check for materialized views since this could have special columns for IVM */
+	if ((!isSelect || requireColumnNameMatch) && i != resultDesc->natts)
 		ereport(ERROR,
 				(errcode(ERRCODE_INVALID_OBJECT_DEFINITION),
 				 isSelect ?
diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat
index d8e8715ed1..2929a6872e 100644
--- a/src/include/catalog/pg_proc.dat
+++ b/src/include/catalog/pg_proc.dat
@@ -11747,4 +11747,12 @@
   prorettype => 'bytea', proargtypes => 'pg_brin_minmax_multi_summary',
   prosrc => 'brin_minmax_multi_summary_send' },
 
+# IVM
+{ oid => '786', descr => 'ivm trigger (before)',
+  proname => 'IVM_immediate_before', provolatile => 'v', prorettype => 'trigger',
+  proargtypes => '', prosrc => 'IVM_immediate_before' },
+{ oid => '787', descr => 'ivm trigger (after)',
+  proname => 'IVM_immediate_maintenance', provolatile => 'v', prorettype => 'trigger',
+  proargtypes => '', prosrc => 'IVM_immediate_maintenance' },
+
 ]
diff --git a/src/include/commands/createas.h b/src/include/commands/createas.h
index 54a38491fb..c369b3ba5e 100644
--- a/src/include/commands/createas.h
+++ b/src/include/commands/createas.h
@@ -16,6 +16,7 @@
 
 #include "catalog/objectaddress.h"
 #include "nodes/params.h"
+#include "nodes/pathnodes.h"
 #include "parser/parse_node.h"
 #include "tcop/dest.h"
 #include "utils/queryenvironment.h"
@@ -25,6 +26,11 @@ extern ObjectAddress ExecCreateTableAs(ParseState *pstate, CreateTableAsStmt *st
 									   ParamListInfo params, QueryEnvironment *queryEnv,
 									   QueryCompletion *qc);
 
+extern void CreateIvmTriggersOnBaseTables(Query *qry, Oid matviewOid, bool is_create);
+extern void CreateIndexOnIMMV(Query *query, Relation matviewRel, bool is_create);
+
+extern Query *rewriteQueryForIMMV(Query *query, List *colNames);
+
 extern int	GetIntoRelEFlags(IntoClause *intoClause);
 
 extern DestReceiver *CreateIntoRelDestReceiver(IntoClause *intoClause);
diff --git a/src/include/commands/matview.h b/src/include/commands/matview.h
index a067da39d2..ec479db513 100644
--- a/src/include/commands/matview.h
+++ b/src/include/commands/matview.h
@@ -15,6 +15,7 @@
 #define MATVIEW_H
 
 #include "catalog/objectaddress.h"
+#include "fmgr.h"
 #include "nodes/params.h"
 #include "nodes/parsenodes.h"
 #include "tcop/dest.h"
@@ -23,6 +24,8 @@
 
 extern void SetMatViewPopulatedState(Relation relation, bool newstate);
 
+extern void SetMatViewIVMState(Relation relation, bool newstate);
+
 extern ObjectAddress ExecRefreshMatView(RefreshMatViewStmt *stmt, const char *queryString,
 										ParamListInfo params, QueryCompletion *qc);
 
@@ -30,4 +33,9 @@ extern DestReceiver *CreateTransientRelDestReceiver(Oid oid);
 
 extern bool MatViewIncrementalMaintenanceIsEnabled(void);
 
+extern Datum IVM_immediate_before(PG_FUNCTION_ARGS);
+extern Datum IVM_immediate_maintenance(PG_FUNCTION_ARGS);
+extern void AtAbort_IVM(void);
+extern bool isIvmName(const char *s);
+
 #endif							/* MATVIEW_H */
diff --git a/src/include/nodes/parsenodes.h b/src/include/nodes/parsenodes.h
index 1617702d9d..3aa2d9f61c 100644
--- a/src/include/nodes/parsenodes.h
+++ b/src/include/nodes/parsenodes.h
@@ -1036,6 +1036,7 @@ typedef struct RangeTblEntry
 	char		relkind;		/* relation kind (see pg_class.relkind) */
 	int			rellockmode;	/* lock level that query requires on the rel */
 	struct TableSampleClause *tablesample;	/* sampling info, or NULL */
+	bool		relisivm;
 
 	/*
 	 * Fields valid for a subquery RTE (else NULL):
@@ -2195,6 +2196,7 @@ typedef struct CreateStmt
 	char	   *tablespacename; /* table space to use, or NULL */
 	char	   *accessMethod;	/* table access method */
 	bool		if_not_exists;	/* just do nothing if it already exists? */
+	bool		ivm;			/* incremental view maintenance is used by materialized view */
 } CreateStmt;
 
 /* ----------
-- 
2.17.1


--Multipart=_Mon__14_Mar_2022_19_12_17_+0900_E9HVp8j5QFkIIek.
Content-Type: text/x-diff;
 name="v26-0006-Add-Incremental-View-Maintenance-support-to-psql.patch"
Content-Disposition: attachment;
 filename="v26-0006-Add-Incremental-View-Maintenance-support-to-psql.patch"
Content-Transfer-Encoding: 7bit



^ permalink  raw  reply  [nested|flat] 101+ messages in thread

* [PATCH v25 07/15] Add Incremental View Maintenance support
@ 2020-12-22 09:40  Yugo Nagata <[email protected]>
  0 siblings, 0 replies; 101+ messages in thread

From: Yugo Nagata @ 2020-12-22 09:40 UTC (permalink / raw)

In this implementation, AFTER triggers are used to collect
tuplestores containing transition table contents. When multiple tables
are changed, multiple AFTER triggers are invoked, then the final AFTER
trigger performs actual update of the matview. In addition, BEFORE
triggers are also used to handle global information for view
maintenance. To calculate view deltas, we need both pre-state and
post-state of base tables. Post-update states are available in AFTER
trigger, and pre-update states can be calculated by filtering inserted
tuples using cmin/xmin system columns, and append deleted tuples which
are contained in an old transition table.

This patch also allows self-join, simultaneous updates of more than
one base table, and multiple updates of the same base table.

Incrementally Maintainable Materialized Views (IMMV) can contain
duplicated tuples. Also, DISTINCT clause is supported. When IMMV is
created with DISTINCT, multiplicity of tuples is counted and stored
in  "__ivm_count__" column, which is a hidden column of IMMV.
The value in __ivm_count__ is updated when IMMV is maintained
incrementally. A tuple in IMMV can be removed if and only if the
count becomes zero.
---
 src/backend/access/transam/xact.c   |    5 +
 src/backend/commands/createas.c     |  736 +++++++++++++
 src/backend/commands/indexcmds.c    |   40 +
 src/backend/commands/matview.c      | 1555 ++++++++++++++++++++++++++-
 src/backend/commands/tablecmds.c    |    9 +
 src/backend/nodes/copyfuncs.c       |    1 +
 src/backend/nodes/equalfuncs.c      |    1 +
 src/backend/nodes/outfuncs.c        |    1 +
 src/backend/nodes/readfuncs.c       |    1 +
 src/backend/parser/parse_relation.c |   18 +-
 src/backend/rewrite/rewriteDefine.c |    3 +-
 src/include/catalog/pg_proc.dat     |    8 +
 src/include/commands/createas.h     |    6 +
 src/include/commands/matview.h      |    8 +
 src/include/nodes/parsenodes.h      |    2 +
 15 files changed, 2354 insertions(+), 40 deletions(-)

diff --git a/src/backend/access/transam/xact.c b/src/backend/access/transam/xact.c
index c9516e03fa..06b012b21f 100644
--- a/src/backend/access/transam/xact.c
+++ b/src/backend/access/transam/xact.c
@@ -35,6 +35,7 @@
 #include "catalog/pg_enum.h"
 #include "catalog/storage.h"
 #include "commands/async.h"
+#include "commands/matview.h"
 #include "commands/tablecmds.h"
 #include "commands/trigger.h"
 #include "common/pg_prng.h"
@@ -2776,6 +2777,7 @@ AbortTransaction(void)
 	AtAbort_Notify();
 	AtEOXact_RelationMap(false, is_parallel_worker);
 	AtAbort_Twophase();
+	AtAbort_IVM();
 
 	/*
 	 * Advertise the fact that we aborted in pg_xact (assuming that we got as
@@ -5020,6 +5022,9 @@ AbortSubTransaction(void)
 	AbortBufferIO();
 	UnlockBuffers();
 
+	/* Clean up hash entries for incremental view maintenance */
+	AtAbort_IVM();
+
 	/* Reset WAL record construction state */
 	XLogResetInsertion();
 
diff --git a/src/backend/commands/createas.c b/src/backend/commands/createas.c
index 9abbb6b555..4b73965e56 100644
--- a/src/backend/commands/createas.c
+++ b/src/backend/commands/createas.c
@@ -32,24 +32,41 @@
 #include "access/xact.h"
 #include "access/xlog.h"
 #include "catalog/namespace.h"
+#include "catalog/index.h"
+#include "catalog/pg_constraint.h"
+#include "catalog/pg_inherits.h"
+#include "catalog/pg_trigger.h"
+#include "catalog/pg_type.h"
 #include "catalog/toasting.h"
 #include "commands/createas.h"
+#include "commands/defrem.h"
 #include "commands/matview.h"
 #include "commands/prepare.h"
 #include "commands/tablecmds.h"
+#include "commands/tablespace.h"
+#include "commands/trigger.h"
 #include "commands/view.h"
 #include "miscadmin.h"
+#include "optimizer/clauses.h"
+#include "optimizer/optimizer.h"
 #include "nodes/makefuncs.h"
 #include "nodes/nodeFuncs.h"
+#include "parser/parser.h"
+#include "parser/parsetree.h"
 #include "parser/parse_clause.h"
+#include "parser/parse_func.h"
+#include "parser/parse_type.h"
 #include "rewrite/rewriteHandler.h"
+#include "rewrite/rewriteManip.h"
 #include "storage/smgr.h"
 #include "tcop/tcopprot.h"
 #include "utils/builtins.h"
+#include "utils/fmgroids.h"
 #include "utils/lsyscache.h"
 #include "utils/rel.h"
 #include "utils/rls.h"
 #include "utils/snapmgr.h"
+#include "utils/syscache.h"
 
 typedef struct
 {
@@ -73,6 +90,12 @@ static bool intorel_receive(TupleTableSlot *slot, DestReceiver *self);
 static void intorel_shutdown(DestReceiver *self);
 static void intorel_destroy(DestReceiver *self);
 
+static void CreateIvmTriggersOnBaseTablesRecurse(Query *qry, Node *node, Oid matviewOid,
+									 Relids *relids, bool ex_lock);
+static void CreateIvmTrigger(Oid relOid, Oid viewOid, int16 type, int16 timing, bool ex_lock);
+static void check_ivm_restriction(Node *node);
+static bool check_ivm_restriction_walker(Node *node, void *context);
+static Bitmapset *get_primary_key_attnos_from_query(Query *qry, List **constraintList);
 
 /*
  * create_ctas_internal
@@ -108,6 +131,8 @@ create_ctas_internal(List *attrList, IntoClause *into)
 	create->oncommit = into->onCommit;
 	create->tablespacename = into->tableSpaceName;
 	create->if_not_exists = false;
+	/* Using Materialized view only */
+	create->ivm = into->ivm;
 	create->accessMethod = into->accessMethod;
 
 	/*
@@ -238,6 +263,7 @@ ExecCreateTableAs(ParseState *pstate, CreateTableAsStmt *stmt,
 	List	   *rewritten;
 	PlannedStmt *plan;
 	QueryDesc  *queryDesc;
+	Query	   *query_immv = NULL;
 
 	/* Check if the relation exists or not */
 	if (CreateTableAsRelExists(stmt))
@@ -282,6 +308,22 @@ ExecCreateTableAs(ParseState *pstate, CreateTableAsStmt *stmt,
 		save_nestlevel = NewGUCNestLevel();
 	}
 
+	if (is_matview && into->ivm)
+	{
+		/* check if the query is supported in IMMV definition */
+		if (contain_mutable_functions((Node *) query))
+			ereport(ERROR,
+					(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+					 errmsg("mutable function is not supported on incrementally maintainable materialized view"),
+					 errhint("functions must be marked IMMUTABLE")));
+
+		check_ivm_restriction((Node *) query);
+
+		/* For IMMV, we need to rewrite matview query */
+		query = rewriteQueryForIMMV(query, into->colNames);
+		query_immv = copyObject(query);
+	}
+
 	if (into->skipData)
 	{
 		/*
@@ -358,11 +400,75 @@ ExecCreateTableAs(ParseState *pstate, CreateTableAsStmt *stmt,
 
 		/* Restore userid and security context */
 		SetUserIdAndSecContext(save_userid, save_sec_context);
+
+		if (into->ivm)
+		{
+			Oid matviewOid = address.objectId;
+			Relation matviewRel = table_open(matviewOid, NoLock);
+
+			/*
+			 * Mark relisivm field, if it's a matview and into->ivm is true.
+			 */
+			SetMatViewIVMState(matviewRel, true);
+
+			if (!into->skipData)
+			{
+				/* Create an index on incremental maintainable materialized view, if possible */
+				CreateIndexOnIMMV((Query *) into->viewQuery, matviewRel);
+
+				/* Create triggers on incremental maintainable materialized view */
+				Assert(query_immv != NULL);
+				CreateIvmTriggersOnBaseTables(query_immv, matviewOid, true);
+			}
+			table_close(matviewRel, NoLock);
+		}
 	}
 
 	return address;
 }
 
+/*
+ * rewriteQueryForIMMV -- rewrite view definition query for IMMV
+ *
+ * count(*) is added for counting distinct tuples in views.
+ */
+Query *
+rewriteQueryForIMMV(Query *query, List *colNames)
+{
+	Query *rewritten;
+
+	TargetEntry *tle;
+	Node *node;
+	ParseState *pstate = make_parsestate(NULL);
+	FuncCall *fn;
+
+	rewritten = copyObject(query);
+	pstate->p_expr_kind = EXPR_KIND_SELECT_TARGET;
+
+	/*
+	 * Convert DISTINCT to GROUP BY and add count(*) for counting distinct
+	 * tuples in views.
+	 */
+	if (rewritten->distinctClause)
+	{
+		rewritten->groupClause = transformDistinctClause(NULL, &rewritten->targetList, rewritten->sortClause, false);
+
+		fn = makeFuncCall(list_make1(makeString("count")), NIL, COERCE_EXPLICIT_CALL, -1);
+		fn->agg_star = true;
+
+		node = ParseFuncOrColumn(pstate, fn->funcname, NIL, NULL, fn, false, -1);
+
+		tle = makeTargetEntry((Expr *) node,
+								list_length(rewritten->targetList) + 1,
+								pstrdup("__ivm_count__"),
+								false);
+		rewritten->targetList = lappend(rewritten->targetList, tle);
+		rewritten->hasAggs = true;
+	}
+
+	return rewritten;
+}
+
 /*
  * GetIntoRelEFlags --- compute executor flags needed for CREATE TABLE AS
  *
@@ -623,3 +729,633 @@ intorel_destroy(DestReceiver *self)
 {
 	pfree(self);
 }
+
+/*
+ * CreateIvmTriggersOnBaseTables -- create IVM triggers on all base tables
+ */
+void
+CreateIvmTriggersOnBaseTables(Query *qry, Oid matviewOid, bool is_create)
+{
+	Relids	relids = NULL;
+	bool	ex_lock = false;
+	Index	first_rtindex = is_create ? 1 : PRS2_NEW_VARNO + 1;
+	RangeTblEntry *rte;
+
+	/* Immediately return if we don't have any base tables. */
+	if (list_length(qry->rtable) < first_rtindex)
+		return;
+
+	/*
+	 * If the view has more than one base tables, we need an exclusive lock
+	 * on the view so that the view would be maintained serially to avoid
+	 * the inconsistency that occurs when two base tables are modified in
+	 * concurrent transactions. However, if the view has only one table,
+	 * we can use a weaker lock.
+	 *
+	 * The type of lock should be determined here, because if we check the
+	 * view definition at maintenance time, we need to acquire a weaker lock,
+	 * and upgrading the lock level after this increases probability of
+	 * deadlock.
+	 */
+
+	rte = list_nth(qry->rtable, first_rtindex - 1);
+	if (list_length(qry->rtable) > first_rtindex ||
+		rte->rtekind != RTE_RELATION)
+		ex_lock = true;
+
+	CreateIvmTriggersOnBaseTablesRecurse(qry, (Node *)qry, matviewOid, &relids, ex_lock);
+
+	bms_free(relids);
+}
+
+static void
+CreateIvmTriggersOnBaseTablesRecurse(Query *qry, Node *node, Oid matviewOid,
+									 Relids *relids, bool ex_lock)
+{
+	if (node == NULL)
+		return;
+
+	/* This can recurse, so check for excessive recursion */
+	check_stack_depth();
+
+	switch (nodeTag(node))
+	{
+		case T_Query:
+			{
+				Query *query = (Query *) node;
+
+				CreateIvmTriggersOnBaseTablesRecurse(qry, (Node *)query->jointree, matviewOid, relids, ex_lock);
+			}
+			break;
+
+		case T_RangeTblRef:
+			{
+				int			rti = ((RangeTblRef *) node)->rtindex;
+				RangeTblEntry *rte = rt_fetch(rti, qry->rtable);
+
+				if (rte->rtekind == RTE_RELATION && !bms_is_member(rte->relid, *relids))
+				{
+					CreateIvmTrigger(rte->relid, matviewOid, TRIGGER_TYPE_INSERT, TRIGGER_TYPE_BEFORE, ex_lock);
+					CreateIvmTrigger(rte->relid, matviewOid, TRIGGER_TYPE_DELETE, TRIGGER_TYPE_BEFORE, ex_lock);
+					CreateIvmTrigger(rte->relid, matviewOid, TRIGGER_TYPE_UPDATE, TRIGGER_TYPE_BEFORE, ex_lock);
+					CreateIvmTrigger(rte->relid, matviewOid, TRIGGER_TYPE_INSERT, TRIGGER_TYPE_AFTER, ex_lock);
+					CreateIvmTrigger(rte->relid, matviewOid, TRIGGER_TYPE_DELETE, TRIGGER_TYPE_AFTER, ex_lock);
+					CreateIvmTrigger(rte->relid, matviewOid, TRIGGER_TYPE_UPDATE, TRIGGER_TYPE_AFTER, ex_lock);
+
+					*relids = bms_add_member(*relids, rte->relid);
+				}
+			}
+			break;
+
+		case T_FromExpr:
+			{
+				FromExpr   *f = (FromExpr *) node;
+				ListCell   *l;
+
+				foreach(l, f->fromlist)
+					CreateIvmTriggersOnBaseTablesRecurse(qry, lfirst(l), matviewOid, relids, ex_lock);
+			}
+			break;
+
+		case T_JoinExpr:
+			{
+				JoinExpr   *j = (JoinExpr *) node;
+
+				CreateIvmTriggersOnBaseTablesRecurse(qry, j->larg, matviewOid, relids, ex_lock);
+				CreateIvmTriggersOnBaseTablesRecurse(qry, j->rarg, matviewOid, relids, ex_lock);
+			}
+			break;
+
+		default:
+			elog(ERROR, "unrecognized node type: %d", (int) nodeTag(node));
+	}
+}
+
+/*
+ * CreateIvmTrigger -- create IVM trigger on a base table
+ */
+static void
+CreateIvmTrigger(Oid relOid, Oid viewOid, int16 type, int16 timing, bool ex_lock)
+{
+	ObjectAddress	refaddr;
+	ObjectAddress	address;
+	CreateTrigStmt *ivm_trigger;
+	List *transitionRels = NIL;
+
+	Assert(timing == TRIGGER_TYPE_BEFORE || timing == TRIGGER_TYPE_AFTER);
+
+	refaddr.classId = RelationRelationId;
+	refaddr.objectId = viewOid;
+	refaddr.objectSubId = 0;
+
+	ivm_trigger = makeNode(CreateTrigStmt);
+	ivm_trigger->relation = NULL;
+	ivm_trigger->row = false;
+
+	ivm_trigger->timing = timing;
+	ivm_trigger->events = type;
+
+	switch (type)
+	{
+		case TRIGGER_TYPE_INSERT:
+			ivm_trigger->trigname = (timing == TRIGGER_TYPE_BEFORE ? "IVM_trigger_ins_before" : "IVM_trigger_ins_after");
+			break;
+		case TRIGGER_TYPE_DELETE:
+			ivm_trigger->trigname = (timing == TRIGGER_TYPE_BEFORE ? "IVM_trigger_del_before" : "IVM_trigger_del_after");
+			break;
+		case TRIGGER_TYPE_UPDATE:
+			ivm_trigger->trigname = (timing == TRIGGER_TYPE_BEFORE ? "IVM_trigger_upd_before" : "IVM_trigger_upd_after");
+			break;
+		default:
+			elog(ERROR, "unsupported trigger type");
+	}
+
+	if (timing == TRIGGER_TYPE_AFTER)
+	{
+		if (type == TRIGGER_TYPE_INSERT || type == TRIGGER_TYPE_UPDATE)
+		{
+			TriggerTransition *n = makeNode(TriggerTransition);
+			n->name = "__ivm_newtable";
+			n->isNew = true;
+			n->isTable = true;
+
+			transitionRels = lappend(transitionRels, n);
+		}
+		if (type == TRIGGER_TYPE_DELETE || type == TRIGGER_TYPE_UPDATE)
+		{
+			TriggerTransition *n = makeNode(TriggerTransition);
+			n->name = "__ivm_oldtable";
+			n->isNew = false;
+			n->isTable = true;
+
+			transitionRels = lappend(transitionRels, n);
+		}
+	}
+
+	ivm_trigger->funcname =
+		(timing == TRIGGER_TYPE_BEFORE ? SystemFuncName("IVM_immediate_before") : SystemFuncName("IVM_immediate_maintenance"));
+
+	ivm_trigger->columns = NIL;
+	ivm_trigger->transitionRels = transitionRels;
+	ivm_trigger->whenClause = NULL;
+	ivm_trigger->isconstraint = false;
+	ivm_trigger->deferrable = false;
+	ivm_trigger->initdeferred = false;
+	ivm_trigger->constrrel = NULL;
+	ivm_trigger->args = list_make2(
+		makeString(DatumGetPointer(DirectFunctionCall1(oidout, ObjectIdGetDatum(viewOid)))),
+		makeString(DatumGetPointer(DirectFunctionCall1(boolout, BoolGetDatum(ex_lock))))
+		);
+
+	address = CreateTrigger(ivm_trigger, NULL, relOid, InvalidOid, InvalidOid,
+						 InvalidOid, InvalidOid, InvalidOid, NULL, true, false);
+
+	recordDependencyOn(&address, &refaddr, DEPENDENCY_IMMV);
+
+	/* Make changes-so-far visible */
+	CommandCounterIncrement();
+}
+
+/*
+ * check_ivm_restriction --- look for specify nodes in the query tree
+ */
+static void
+check_ivm_restriction(Node *node)
+{
+	check_ivm_restriction_walker(node, NULL);
+}
+
+static bool
+check_ivm_restriction_walker(Node *node, void *context)
+{
+	if (node == NULL)
+		return false;
+
+	/*
+	 * We currently don't support Sub-Query.
+	 */
+	if (IsA(node, SubPlan) || IsA(node, SubLink))
+		ereport(ERROR,
+				(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+				 errmsg("subquery is not supported on incrementally maintainable materialized view")));
+
+	/* This can recurse, so check for excessive recursion */
+	check_stack_depth();
+
+	switch (nodeTag(node))
+	{
+		case T_Query:
+			{
+				Query *qry = (Query *)node;
+				ListCell   *lc;
+				List       *vars;
+
+				/* if contained CTE, return error */
+				if (qry->cteList != NIL)
+					ereport(ERROR,
+							(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+							 errmsg("CTE is not supported on incrementally maintainable materialized view")));
+				if (qry->havingQual != NULL)
+					ereport(ERROR,
+							(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+							 errmsg(" HAVING clause is not supported on incrementally maintainable materialized view")));
+				if (qry->sortClause != NIL)	/* There is a possibility that we don't need to return an error */
+					ereport(ERROR,
+							(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+							 errmsg("ORDER BY clause is not supported on incrementally maintainable materialized view")));
+				if (qry->limitOffset != NULL || qry->limitCount != NULL)
+					ereport(ERROR,
+							(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+							 errmsg("LIMIT/OFFSET clause is not supported on incrementally maintainable materialized view")));
+				if (qry->hasDistinctOn)
+					ereport(ERROR,
+							(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+							 errmsg("DISTINCT ON is not supported on incrementally maintainable materialized view")));
+				if (qry->hasWindowFuncs)
+					ereport(ERROR,
+							(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+							 errmsg("window functions are not supported on incrementally maintainable materialized view")));
+				if (qry->groupingSets != NIL)
+					ereport(ERROR,
+							(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+							 errmsg("GROUPING SETS, ROLLUP, or CUBE clauses is not supported on incrementally maintainable materialized view")));
+				if (qry->setOperations != NULL)
+					ereport(ERROR,
+							(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+							 errmsg("UNION/INTERSECT/EXCEPT statements are not supported on incrementally maintainable materialized view")));
+				if (list_length(qry->targetList) == 0)
+					ereport(ERROR,
+							(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+							 errmsg("empty target list is not supported on incrementally maintainable materialized view")));
+				if (qry->rowMarks != NIL)
+					ereport(ERROR,
+							(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+							 errmsg("FOR UPDATE/SHARE clause is not supported on incrementally maintainable materialized view")));
+
+				/* system column restrictions */
+				vars = pull_vars_of_level((Node *) qry, 0);
+				foreach(lc, vars)
+				{
+					if (IsA(lfirst(lc), Var))
+					{
+						Var *var = (Var *) lfirst(lc);
+						/* if system column, return error */
+						if (var->varattno < 0)
+							ereport(ERROR,
+									(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+									 errmsg("system column is not supported on incrementally maintainable materialized view")));
+					}
+				}
+
+				/* restrictions for rtable */
+				foreach(lc, qry->rtable)
+				{
+					RangeTblEntry *rte = (RangeTblEntry *) lfirst(lc);
+
+					if (rte->subquery)
+						ereport(ERROR,
+								(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+								 errmsg("subquery is not supported on incrementally maintainable materialized view")));
+
+					if (rte->tablesample != NULL)
+						ereport(ERROR,
+								(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+								 errmsg("TABLESAMPLE clause is not supported on incrementally maintainable materialized view")));
+
+					if (rte->relkind == RELKIND_PARTITIONED_TABLE)
+						ereport(ERROR,
+								(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+								 errmsg("partitioned table is not supported on incrementally maintainable materialized view")));
+
+					if (rte->relkind == RELKIND_RELATION && has_superclass(rte->relid))
+						ereport(ERROR,
+								(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+								 errmsg("partitions is not supported on incrementally maintainable materialized view")));
+
+					if (rte->relkind == RELKIND_RELATION && find_inheritance_children(rte->relid, NoLock) != NIL)
+						ereport(ERROR,
+								(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+								 errmsg("inheritance parent is not supported on incrementally maintainable materialized view")));
+
+					if (rte->relkind == RELKIND_FOREIGN_TABLE)
+						ereport(ERROR,
+								(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+								 errmsg("foreign table is not supported on incrementally maintainable materialized view")));
+
+					if (rte->relkind == RELKIND_VIEW ||
+						rte->relkind == RELKIND_MATVIEW)
+						ereport(ERROR,
+								(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+								 errmsg("VIEW or MATERIALIZED VIEW is not supported on incrementally maintainable materialized view")));
+
+					if (rte->rtekind == RTE_VALUES)
+						ereport(ERROR,
+								(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+								 errmsg("VALUES is not supported on incrementally maintainable materialized view")));
+
+				}
+
+				query_tree_walker(qry, check_ivm_restriction_walker, NULL, QTW_IGNORE_RANGE_TABLE);
+
+				break;
+			}
+		case T_TargetEntry:
+			{
+				TargetEntry *tle = (TargetEntry *)node;
+				if (isIvmName(tle->resname))
+						ereport(ERROR,
+								(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+								 errmsg("column name %s is not supported on incrementally maintainable materialized view", tle->resname)));
+
+				expression_tree_walker(node, check_ivm_restriction_walker, NULL);
+				break;
+			}
+		case T_JoinExpr:
+			{
+				JoinExpr *joinexpr = (JoinExpr *)node;
+
+				if (joinexpr->jointype > JOIN_INNER)
+						ereport(ERROR,
+								(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+								 errmsg("OUTER JOIN is not supported on incrementally maintainable materialized view")));
+
+				expression_tree_walker(node, check_ivm_restriction_walker, NULL);
+			}
+			break;
+			expression_tree_walker(node, check_ivm_restriction_walker, NULL);
+			break;
+	}
+	return false;
+}
+
+/*
+ * CreateIndexOnIMMV
+ *
+ * Create a unique index on incremental maintainable materialized view.
+ * If the view definition query has a GROUP BY clause, the index is created
+ * on the columns of GROUP BY expressions. Otherwise, if the view contains
+ * all primary key attritubes of its base tables in the target list, the index
+ * is created on these attritubes. In other cases, no index is created.
+ */
+void
+CreateIndexOnIMMV(Query *query, Relation matviewRel)
+{
+	Query *qry = (Query *) copyObject(query);
+	ListCell *lc;
+	IndexStmt  *index;
+	ObjectAddress address;
+	List *constraintList = NIL;
+	char		idxname[NAMEDATALEN];
+	List	   *indexoidlist = RelationGetIndexList(matviewRel);
+	ListCell   *indexoidscan;
+
+	snprintf(idxname, sizeof(idxname), "%s_index", RelationGetRelationName(matviewRel));
+
+	index = makeNode(IndexStmt);
+
+	index->unique = true;
+	index->primary = false;
+	index->isconstraint = false;
+	index->deferrable = false;
+	index->initdeferred = false;
+	index->idxname = idxname;
+	index->relation =
+		makeRangeVar(get_namespace_name(RelationGetNamespace(matviewRel)),
+					 pstrdup(RelationGetRelationName(matviewRel)),
+					 -1);
+	index->accessMethod = DEFAULT_INDEX_TYPE;
+	index->options = NIL;
+	index->tableSpace = get_tablespace_name(matviewRel->rd_rel->reltablespace);
+	index->whereClause = NULL;
+	index->indexParams = NIL;
+	index->indexIncludingParams = NIL;
+	index->excludeOpNames = NIL;
+	index->idxcomment = NULL;
+	index->indexOid = InvalidOid;
+	index->oldNode = InvalidOid;
+	index->oldCreateSubid = InvalidSubTransactionId;
+	index->oldFirstRelfilenodeSubid = InvalidSubTransactionId;
+	index->transformed = true;
+	index->concurrent = false;
+	index->if_not_exists = false;
+
+	if (qry->distinctClause)
+	{
+		/* create unique constraint on all columns */
+		foreach(lc, qry->targetList)
+		{
+			TargetEntry *tle = (TargetEntry *) lfirst(lc);
+			Form_pg_attribute attr = TupleDescAttr(matviewRel->rd_att, tle->resno - 1);
+			IndexElem  *iparam;
+
+			iparam = makeNode(IndexElem);
+			iparam->name = pstrdup(NameStr(attr->attname));
+			iparam->expr = NULL;
+			iparam->indexcolname = NULL;
+			iparam->collation = NIL;
+			iparam->opclass = NIL;
+			iparam->opclassopts = NIL;
+			iparam->ordering = SORTBY_DEFAULT;
+			iparam->nulls_ordering = SORTBY_NULLS_DEFAULT;
+			index->indexParams = lappend(index->indexParams, iparam);
+		}
+	}
+	else
+	{
+		Bitmapset *key_attnos;
+
+		/* create index on the base tables' primary key columns */
+		key_attnos = get_primary_key_attnos_from_query(qry, &constraintList);
+		if (key_attnos)
+		{
+			foreach(lc, qry->targetList)
+			{
+				TargetEntry *tle = (TargetEntry *) lfirst(lc);
+				Form_pg_attribute attr = TupleDescAttr(matviewRel->rd_att, tle->resno - 1);
+
+				if (bms_is_member(tle->resno - FirstLowInvalidHeapAttributeNumber, key_attnos))
+				{
+					IndexElem  *iparam;
+
+					iparam = makeNode(IndexElem);
+					iparam->name = pstrdup(NameStr(attr->attname));
+					iparam->expr = NULL;
+					iparam->indexcolname = NULL;
+					iparam->collation = NIL;
+					iparam->opclass = NIL;
+					iparam->opclassopts = NIL;
+					iparam->ordering = SORTBY_DEFAULT;
+					iparam->nulls_ordering = SORTBY_NULLS_DEFAULT;
+					index->indexParams = lappend(index->indexParams, iparam);
+				}
+			}
+
+		}
+		else
+		{
+			/* create no index, just notice that an appropriate index is necessary for efficient IVM */
+			ereport(NOTICE,
+					(errmsg("could not create an index on materialized view \"%s\" automatically",
+							RelationGetRelationName(matviewRel)),
+					 errdetail("This target list does not have all the primary key columns, "
+							   "or this view does not contain DISTINCT clause."),
+					 errhint("Create an index on the materialized view for efficient incremental maintenance.")));
+			return;
+		}
+	}
+
+
+	/* If we have a compatible index, we don't need to create another. */
+	foreach(indexoidscan, indexoidlist)
+	{
+		Oid			indexoid = lfirst_oid(indexoidscan);
+		Relation	indexRel;
+		bool		hasCompatibleIndex = false;
+
+		indexRel = index_open(indexoid, AccessShareLock);
+
+		if (CheckIndexCompatible(indexRel->rd_id,
+								index->accessMethod,
+								index->indexParams,
+								index->excludeOpNames))
+			hasCompatibleIndex = true;
+
+		index_close(indexRel, AccessShareLock);
+
+		if (hasCompatibleIndex)
+			return;
+	}
+
+	address = DefineIndex(RelationGetRelid(matviewRel),
+						  index,
+						  InvalidOid,
+						  InvalidOid,
+						  InvalidOid,
+						  false, true, false, false, true);
+
+	ereport(NOTICE,
+			(errmsg("created index \"%s\" on materialized view \"%s\"",
+					idxname, RelationGetRelationName(matviewRel))));
+
+
+	/*
+	 * Make dependencies so that the index is dropped if any base tables's
+	 * primary key is dropped.
+	 */
+	foreach(lc, constraintList)
+	{
+		Oid constraintOid = lfirst_oid(lc);
+		ObjectAddress	refaddr;
+
+		refaddr.classId = ConstraintRelationId;
+		refaddr.objectId = constraintOid;
+		refaddr.objectSubId = 0;
+
+		recordDependencyOn(&address, &refaddr, DEPENDENCY_NORMAL);
+	}
+}
+
+
+/*
+ * get_primary_key_attnos_from_query
+ *
+ * Identify the columns in base tables' primary keys in the target list.
+ *
+ * Returns a Bitmapset of the column attnos of the primary key's columns of
+ * tables that used in the query.  The attnos are offset by
+ * FirstLowInvalidHeapAttributeNumber as same as get_primary_key_attnos.
+ *
+ * If any table has no primary key or any primary key's columns is not in
+ * the target list, return NULL.  We also return NULL if any pkey constraint
+ * is deferrable.
+ *
+ * constraintList is set to a list of the OIDs of the pkey constraints.
+ */
+static Bitmapset *
+get_primary_key_attnos_from_query(Query *query, List **constraintList)
+{
+	List *key_attnos_list = NIL;
+	ListCell *lc;
+	int i;
+	Bitmapset *keys = NULL;
+	Relids	rels_in_from;
+	PlannerInfo root;
+
+
+	/*
+	 * Collect primary key attributes from all tables used in query. The key attributes
+	 * sets for each table are stored in key_attnos_list in order by RTE index.
+	 */
+	i = 1;
+	foreach(lc, query->rtable)
+	{
+		RangeTblEntry *r = (RangeTblEntry*) lfirst(lc);
+		Bitmapset *key_attnos;
+		bool	has_pkey = true;
+
+		/* for tables, call get_primary_key_attnos */
+		if (r->rtekind == RTE_RELATION)
+		{
+			Oid constraintOid;
+			key_attnos = get_primary_key_attnos(r->relid, false, &constraintOid);
+			*constraintList = lappend_oid(*constraintList, constraintOid);
+			has_pkey = (key_attnos != NULL);
+		}
+		/* for other RTEs, store NULL into key_attnos_list */
+		else
+			key_attnos = NULL;
+
+		/*
+		 * If any table or subquery has no primary key or its pkey constraint is deferrable,
+		 * we cannot get key attributes for this query, so return NULL.
+		 */
+		if (!has_pkey)
+			return NULL;
+
+		key_attnos_list = lappend(key_attnos_list, key_attnos);
+	}
+
+	/* Collect key attributes appearing in the target list */
+	i = 1;
+	foreach(lc, query->targetList)
+	{
+		TargetEntry *tle = (TargetEntry *) flatten_join_alias_vars(query, lfirst(lc));
+
+		if (IsA(tle->expr, Var))
+		{
+			Var *var = (Var*) tle->expr;
+			Bitmapset *attnos = list_nth(key_attnos_list, var->varno - 1);
+
+			/* check if this attribute is from a base table's primary key */
+			if (bms_is_member(var->varattno - FirstLowInvalidHeapAttributeNumber, attnos))
+			{
+				/*
+				 * Remove found key attributes from key_attnos_list, and add this
+				 * to the result list.
+				 */
+				bms_del_member(attnos, var->varattno - FirstLowInvalidHeapAttributeNumber);
+				keys = bms_add_member(keys, i - FirstLowInvalidHeapAttributeNumber);
+			}
+		}
+		i++;
+	}
+
+	/* Collect relations appearing in the FROM clause */
+	rels_in_from = pull_varnos_of_level(&root, (Node *)query->jointree, 0);
+
+	/*
+	 * Check if all key attributes of relations in FROM are appearing in the target
+	 * list.  If an attribute remains in key_attnos_list in spite of the table is used
+	 * in FROM clause, the target is missing this key attribute, so we return NULL.
+	 */
+	i = 1;
+	foreach(lc, key_attnos_list)
+	{
+		Bitmapset *bms = (Bitmapset *)lfirst(lc);
+		if (!bms_is_empty(bms) && bms_is_member(i, rels_in_from))
+			return NULL;
+		i++;
+	}
+
+	return keys;
+}
diff --git a/src/backend/commands/indexcmds.c b/src/backend/commands/indexcmds.c
index 42aacc8f0a..dfa4408d1c 100644
--- a/src/backend/commands/indexcmds.c
+++ b/src/backend/commands/indexcmds.c
@@ -36,6 +36,7 @@
 #include "commands/dbcommands.h"
 #include "commands/defrem.h"
 #include "commands/event_trigger.h"
+#include "commands/matview.h"
 #include "commands/progress.h"
 #include "commands/tablecmds.h"
 #include "commands/tablespace.h"
@@ -1054,6 +1055,45 @@ DefineIndex(Oid relationId,
 	safe_index = indexInfo->ii_Expressions == NIL &&
 		indexInfo->ii_Predicate == NIL;
 
+	/*
+	 * We disallow unique indexes on IVM columns of IMMVs.
+	 */
+	if (RelationIsIVM(rel) && stmt->unique)
+	{
+		for (i = 0; i < indexInfo->ii_NumIndexKeyAttrs; i++)
+		{
+			AttrNumber	attno = indexInfo->ii_IndexAttrNumbers[i];
+			if (attno > 0)
+			{
+				char *name = NameStr(TupleDescAttr(rel->rd_att, attno - 1)->attname);
+				if (name && isIvmName(name))
+					ereport(ERROR,
+							(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+							 errmsg("unique index creation on IVM columns is not supported")));
+			}
+		}
+
+		if (indexInfo->ii_Expressions)
+		{
+			Bitmapset  *indexattrs = NULL;
+			int			varno = -1;
+
+			pull_varattnos((Node *) indexInfo->ii_Expressions, 1, &indexattrs);
+
+			while ((varno = bms_next_member(indexattrs, varno)) >= 0)
+			{
+				int attno = varno + FirstLowInvalidHeapAttributeNumber;
+				char *name = NameStr(TupleDescAttr(rel->rd_att, attno - 1)->attname);
+				if (name && isIvmName(name))
+					ereport(ERROR,
+							(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+							 errmsg("unique index creation on IVM columns is not supported")));
+			}
+
+		}
+	}
+
+
 	/*
 	 * Report index creation if appropriate (delay this till after most of the
 	 * error checks)
diff --git a/src/backend/commands/matview.c b/src/backend/commands/matview.c
index 05e7b60059..943de5dfba 100644
--- a/src/backend/commands/matview.c
+++ b/src/backend/commands/matview.c
@@ -25,26 +25,47 @@
 #include "catalog/indexing.h"
 #include "catalog/namespace.h"
 #include "catalog/pg_am.h"
+#include "catalog/pg_collation.h"
+#include "catalog/pg_depend.h"
+#include "catalog/pg_type.h"
 #include "catalog/pg_opclass.h"
 #include "catalog/pg_operator.h"
 #include "commands/cluster.h"
+#include "commands/defrem.h"
 #include "commands/matview.h"
 #include "commands/tablecmds.h"
 #include "commands/tablespace.h"
+#include "commands/createas.h"
 #include "executor/executor.h"
 #include "executor/spi.h"
+#include "executor/tstoreReceiver.h"
 #include "miscadmin.h"
+#include "nodes/makefuncs.h"
+#include "nodes/nodeFuncs.h"
+#include "optimizer/optimizer.h"
+#include "parser/analyze.h"
+#include "parser/parser.h"
+#include "parser/parsetree.h"
+#include "parser/parse_clause.h"
+#include "parser/parse_coerce.h"
+#include "parser/parse_collate.h"
+#include "parser/parse_func.h"
 #include "parser/parse_relation.h"
+#include "parser/parse_type.h"
 #include "pgstat.h"
 #include "rewrite/rewriteHandler.h"
+#include "rewrite/rewriteManip.h"
+#include "rewrite/rowsecurity.h"
 #include "storage/lmgr.h"
 #include "storage/smgr.h"
 #include "tcop/tcopprot.h"
 #include "utils/builtins.h"
+#include "utils/fmgroids.h"
 #include "utils/lsyscache.h"
 #include "utils/rel.h"
 #include "utils/snapmgr.h"
 #include "utils/syscache.h"
+#include "utils/typcache.h"
 
 
 typedef struct
@@ -58,6 +79,50 @@ typedef struct
 	BulkInsertState bistate;	/* bulk insert state */
 } DR_transientrel;
 
+#define MV_INIT_QUERYHASHSIZE	16
+
+/*
+ * MV_TriggerHashEntry
+ *
+ * Hash entry for base tables on which IVM trigger is invoked
+ */
+typedef struct MV_TriggerHashEntry
+{
+	Oid	matview_id;			/* OID of the materialized view */
+	int	before_trig_count;	/* count of before triggers invoked */
+	int	after_trig_count;	/* count of after triggers invoked */
+
+	TransactionId	xid;	/* Transaction id before the first table is modified*/
+	CommandId		cid;	/* Command id before the first table is modified */
+
+	List   *tables;		/* List of MV_TriggerTable */
+	bool	has_old;	/* tuples are deleted from any table? */
+	bool	has_new;	/* tuples are inserted into any table? */
+} MV_TriggerHashEntry;
+
+/*
+ * MV_TriggerTable
+ *
+ * IVM related data for tables on which the trigger is invoked.
+ */
+typedef struct MV_TriggerTable
+{
+	Oid		table_id;			/* OID of the modified table */
+	List   *old_tuplestores;	/* tuplestores for deleted tuples */
+	List   *new_tuplestores;	/* tuplestores for inserted tuples */
+	List   *old_rtes;			/* RTEs of ENRs for old_tuplestores*/
+	List   *new_rtes;			/* RTEs of ENRs for new_tuplestores */
+
+	List   *rte_indexes;		/* List of RTE index of the modified table */
+	RangeTblEntry *original_rte;	/* the original RTE saved before rewriting query */
+} MV_TriggerTable;
+
+static HTAB *mv_trigger_info = NULL;
+
+/* ENR name for materialized view delta */
+#define NEW_DELTA_ENRNAME "new_delta"
+#define OLD_DELTA_ENRNAME "old_delta"
+
 static int	matview_maintenance_depth = 0;
 
 static void transientrel_startup(DestReceiver *self, int operation, TupleDesc typeinfo);
@@ -65,7 +130,9 @@ static bool transientrel_receive(TupleTableSlot *slot, DestReceiver *self);
 static void transientrel_shutdown(DestReceiver *self);
 static void transientrel_destroy(DestReceiver *self);
 static uint64 refresh_matview_datafill(DestReceiver *dest, Query *query,
-									   const char *queryString);
+						 QueryEnvironment *queryEnv,
+						 TupleDesc *resultTupleDesc,
+						 const char *queryString);
 static char *make_temptable_name_n(char *tempname, int n);
 static void refresh_by_match_merge(Oid matviewOid, Oid tempOid, Oid relowner,
 								   int save_sec_context);
@@ -73,6 +140,45 @@ static void refresh_by_heap_swap(Oid matviewOid, Oid OIDNewHeap, char relpersist
 static bool is_usable_unique_index(Relation indexRel);
 static void OpenMatViewIncrementalMaintenance(void);
 static void CloseMatViewIncrementalMaintenance(void);
+static Query *get_matview_query(Relation matviewRel);
+
+static Query *rewrite_query_for_preupdate_state(Query *query, List *tables,
+								  TransactionId xid, CommandId cid,
+								  ParseState *pstate);
+static void register_delta_ENRs(ParseState *pstate, Query *query, List *tables);
+static char *make_delta_enr_name(const char *prefix, Oid relid, int count);
+static RangeTblEntry *get_prestate_rte(RangeTblEntry *rte, MV_TriggerTable *table,
+				 TransactionId xid, CommandId cid,
+				 QueryEnvironment *queryEnv);
+static RangeTblEntry *union_ENRs(RangeTblEntry *rte, Oid relid, List *enr_rtes, const char *prefix,
+		   QueryEnvironment *queryEnv);
+static Query *rewrite_query_for_distinct(Query *query, ParseState *pstate);
+
+static void calc_delta(MV_TriggerTable *table, int rte_index, Query *query,
+			DestReceiver *dest_old, DestReceiver *dest_new,
+			TupleDesc *tupdesc_old, TupleDesc *tupdesc_new,
+			QueryEnvironment *queryEnv);
+static Query *rewrite_query_for_postupdate_state(Query *query, MV_TriggerTable *table, int rte_index);
+
+static void apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *new_tuplestores,
+			TupleDesc tupdesc_old, TupleDesc tupdesc_new,
+			Query *query, bool use_count, char *count_colname);
+static void apply_old_delta(const char *matviewname, const char *deltaname_old,
+				List *keys);
+static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old,
+				List *keys, const char *count_colname);
+static void apply_new_delta(const char *matviewname, const char *deltaname_new,
+				StringInfo target_list);
+static void apply_new_delta_with_count(const char *matviewname, const char* deltaname_new,
+				List *keys, StringInfo target_list, const char* count_colname);
+static char *get_matching_condition_string(List *keys);
+static void generate_equal(StringInfo querybuf, Oid opttype,
+			   const char *leftop, const char *rightop);
+
+static void mv_InitHashTables(void);
+static void clean_up_IVM_hash_entry(MV_TriggerHashEntry *entry);
+
+static List *get_securityQuals(Oid relId, int rt_index, Query *query);
 
 /*
  * SetMatViewPopulatedState
@@ -114,6 +220,46 @@ SetMatViewPopulatedState(Relation relation, bool newstate)
 	CommandCounterIncrement();
 }
 
+/*
+ * SetMatViewIVMState
+ *		Mark a materialized view as IVM, or not.
+ *
+ * NOTE: caller must be holding an appropriate lock on the relation.
+ */
+void
+SetMatViewIVMState(Relation relation, bool newstate)
+{
+	Relation	pgrel;
+	HeapTuple	tuple;
+
+	Assert(relation->rd_rel->relkind == RELKIND_MATVIEW);
+
+	/*
+	 * Update relation's pg_class entry.  Crucial side-effect: other backends
+	 * (and this one too!) are sent SI message to make them rebuild relcache
+	 * entries.
+	 */
+	pgrel = table_open(RelationRelationId, RowExclusiveLock);
+	tuple = SearchSysCacheCopy1(RELOID,
+								ObjectIdGetDatum(RelationGetRelid(relation)));
+	if (!HeapTupleIsValid(tuple))
+		elog(ERROR, "cache lookup failed for relation %u",
+			 RelationGetRelid(relation));
+
+	((Form_pg_class) GETSTRUCT(tuple))->relisivm = newstate;
+
+	CatalogTupleUpdate(pgrel, &tuple->t_self, tuple);
+
+	heap_freetuple(tuple);
+	table_close(pgrel, RowExclusiveLock);
+
+	/*
+	 * Advance command counter to make the updated pg_class row locally
+	 * visible.
+	 */
+	CommandCounterIncrement();
+}
+
 /*
  * ExecRefreshMatView -- execute a REFRESH MATERIALIZED VIEW command
  *
@@ -140,9 +286,8 @@ ExecRefreshMatView(RefreshMatViewStmt *stmt, const char *queryString,
 {
 	Oid			matviewOid;
 	Relation	matviewRel;
-	RewriteRule *rule;
-	List	   *actions;
 	Query	   *dataQuery;
+	Query	   *viewQuery;
 	Oid			tableSpace;
 	Oid			relowner;
 	Oid			OIDNewHeap;
@@ -155,6 +300,7 @@ ExecRefreshMatView(RefreshMatViewStmt *stmt, const char *queryString,
 	int			save_sec_context;
 	int			save_nestlevel;
 	ObjectAddress address;
+	bool oldPopulated;
 
 	/* Determine strength of lock needed. */
 	concurrent = stmt->concurrent;
@@ -167,6 +313,7 @@ ExecRefreshMatView(RefreshMatViewStmt *stmt, const char *queryString,
 										  lockmode, 0,
 										  RangeVarCallbackOwnsTable, NULL);
 	matviewRel = table_open(matviewOid, NoLock);
+	oldPopulated = RelationIsPopulated(matviewRel);
 
 	/* Make sure it is a materialized view. */
 	if (matviewRel->rd_rel->relkind != RELKIND_MATVIEW)
@@ -188,32 +335,14 @@ ExecRefreshMatView(RefreshMatViewStmt *stmt, const char *queryString,
 				 errmsg("%s and %s options cannot be used together",
 						"CONCURRENTLY", "WITH NO DATA")));
 
-	/*
-	 * Check that everything is correct for a refresh. Problems at this point
-	 * are internal errors, so elog is sufficient.
-	 */
-	if (matviewRel->rd_rel->relhasrules == false ||
-		matviewRel->rd_rules->numLocks < 1)
-		elog(ERROR,
-			 "materialized view \"%s\" is missing rewrite information",
-			 RelationGetRelationName(matviewRel));
-
-	if (matviewRel->rd_rules->numLocks > 1)
-		elog(ERROR,
-			 "materialized view \"%s\" has too many rules",
-			 RelationGetRelationName(matviewRel));
 
-	rule = matviewRel->rd_rules->rules[0];
-	if (rule->event != CMD_SELECT || !(rule->isInstead))
-		elog(ERROR,
-			 "the rule for materialized view \"%s\" is not a SELECT INSTEAD OF rule",
-			 RelationGetRelationName(matviewRel));
+	viewQuery = get_matview_query(matviewRel);
 
-	actions = rule->actions;
-	if (list_length(actions) != 1)
-		elog(ERROR,
-			 "the rule for materialized view \"%s\" is not a single action",
-			 RelationGetRelationName(matviewRel));
+	/* For IMMV, we need to rewrite matview query */
+	if (!stmt->skipData && RelationIsIVM(matviewRel))
+		dataQuery = rewriteQueryForIMMV(viewQuery,NIL);
+	else
+		dataQuery = viewQuery;
 
 	/*
 	 * Check that there is a unique index with no WHERE clause on one or more
@@ -248,12 +377,6 @@ ExecRefreshMatView(RefreshMatViewStmt *stmt, const char *queryString,
 					 errhint("Create a unique index with no WHERE clause on one or more columns of the materialized view.")));
 	}
 
-	/*
-	 * The stored query was rewritten at the time of the MV definition, but
-	 * has not been scribbled on by the planner.
-	 */
-	dataQuery = linitial_node(Query, actions);
-
 	/*
 	 * Check for active uses of the relation in the current transaction, such
 	 * as open scans.
@@ -294,6 +417,52 @@ ExecRefreshMatView(RefreshMatViewStmt *stmt, const char *queryString,
 		relpersistence = matviewRel->rd_rel->relpersistence;
 	}
 
+	/* delete immv triggers */
+	if (RelationIsIVM(matviewRel) && stmt->skipData )
+	{
+		/* use deleted trigger */
+		Relation	depRel;
+		ScanKeyData key;
+		SysScanDesc scan;
+		HeapTuple	tup;
+		ObjectAddresses *immv_triggers;
+
+		immv_triggers = new_object_addresses();
+
+		/*
+		 * We save some cycles by opening pg_depend just once and passing the
+		 * Relation pointer down to all the recursive deletion steps.
+		 */
+		depRel = table_open(DependRelationId, RowExclusiveLock);
+
+		ScanKeyInit(&key,
+					Anum_pg_depend_refobjid,
+					BTEqualStrategyNumber, F_OIDEQ,
+					ObjectIdGetDatum(matviewOid));
+
+		scan = systable_beginscan(depRel, DependReferenceIndexId, true,
+								  NULL, 1, &key);
+		while ((tup = systable_getnext(scan)) != NULL)
+		{
+			ObjectAddress obj;
+			Form_pg_depend foundDep = (Form_pg_depend) GETSTRUCT(tup);
+
+			if (foundDep->deptype == DEPENDENCY_IMMV)
+			{
+				obj.classId = foundDep->classid;
+				obj.objectId = foundDep->objid;
+				obj.objectSubId = foundDep->refobjsubid;
+				add_exact_object_address(&obj, immv_triggers);
+			}
+		}
+		systable_endscan(scan);
+
+		performMultipleDeletions(immv_triggers, DROP_RESTRICT, PERFORM_DELETION_INTERNAL);
+
+		table_close(depRel, RowExclusiveLock);
+		free_object_addresses(immv_triggers);
+	}
+
 	/*
 	 * Create the transient table that will receive the regenerated data. Lock
 	 * it against access by any other process until commit (by which time it
@@ -313,7 +482,7 @@ ExecRefreshMatView(RefreshMatViewStmt *stmt, const char *queryString,
 
 	/* Generate the data, if wanted. */
 	if (!stmt->skipData)
-		processed = refresh_matview_datafill(dest, dataQuery, queryString);
+		processed = refresh_matview_datafill(dest, dataQuery, NULL, NULL, queryString);
 
 	/* Make the matview match the newly generated data. */
 	if (concurrent)
@@ -348,6 +517,12 @@ ExecRefreshMatView(RefreshMatViewStmt *stmt, const char *queryString,
 			pgstat_count_heap_insert(matviewRel, processed);
 	}
 
+	if (!stmt->skipData && RelationIsIVM(matviewRel) && !oldPopulated)
+	{
+		CreateIndexOnIMMV(viewQuery, matviewRel);
+		CreateIvmTriggersOnBaseTables(dataQuery, matviewOid, false);
+	}
+
 	table_close(matviewRel, NoLock);
 
 	/* Roll back any GUC changes */
@@ -382,6 +557,8 @@ ExecRefreshMatView(RefreshMatViewStmt *stmt, const char *queryString,
  */
 static uint64
 refresh_matview_datafill(DestReceiver *dest, Query *query,
+						 QueryEnvironment *queryEnv,
+						 TupleDesc *resultTupleDesc,
 						 const char *queryString)
 {
 	List	   *rewritten;
@@ -418,7 +595,7 @@ refresh_matview_datafill(DestReceiver *dest, Query *query,
 	/* Create a QueryDesc, redirecting output to our tuple receiver */
 	queryDesc = CreateQueryDesc(plan, queryString,
 								GetActiveSnapshot(), InvalidSnapshot,
-								dest, NULL, NULL, 0);
+								dest, NULL, queryEnv ? queryEnv: NULL, 0);
 
 	/* call ExecutorStart to prepare the plan for execution */
 	ExecutorStart(queryDesc, 0);
@@ -428,6 +605,9 @@ refresh_matview_datafill(DestReceiver *dest, Query *query,
 
 	processed = queryDesc->estate->es_processed;
 
+	if (resultTupleDesc)
+		*resultTupleDesc = CreateTupleDescCopy(queryDesc->tupDesc);
+
 	/* and clean up */
 	ExecutorFinish(queryDesc);
 	ExecutorEnd(queryDesc);
@@ -942,3 +1122,1308 @@ CloseMatViewIncrementalMaintenance(void)
 	matview_maintenance_depth--;
 	Assert(matview_maintenance_depth >= 0);
 }
+
+/*
+ * get_matview_query - get the Query from a matview's _RETURN rule.
+ */
+static Query *
+get_matview_query(Relation matviewRel)
+{
+	RewriteRule *rule;
+	List * actions;
+
+	/*
+	 * Check that everything is correct for a refresh. Problems at this point
+	 * are internal errors, so elog is sufficient.
+	 */
+	if (matviewRel->rd_rel->relhasrules == false ||
+		matviewRel->rd_rules->numLocks < 1)
+		elog(ERROR,
+			 "materialized view \"%s\" is missing rewrite information",
+			 RelationGetRelationName(matviewRel));
+
+	if (matviewRel->rd_rules->numLocks > 1)
+		elog(ERROR,
+			 "materialized view \"%s\" has too many rules",
+			 RelationGetRelationName(matviewRel));
+
+	rule = matviewRel->rd_rules->rules[0];
+	if (rule->event != CMD_SELECT || !(rule->isInstead))
+		elog(ERROR,
+			 "the rule for materialized view \"%s\" is not a SELECT INSTEAD OF rule",
+			 RelationGetRelationName(matviewRel));
+
+	actions = rule->actions;
+	if (list_length(actions) != 1)
+		elog(ERROR,
+			 "the rule for materialized view \"%s\" is not a single action",
+			 RelationGetRelationName(matviewRel));
+
+	/*
+	 * The stored query was rewritten at the time of the MV definition, but
+	 * has not been scribbled on by the planner.
+	 */
+	return linitial_node(Query, actions);
+}
+
+
+/* ----------------------------------------------------
+ *		Incremental View Maintenance routines
+ * ---------------------------------------------------
+ */
+
+/*
+ * IVM_immediate_before
+ *
+ * IVM trigger function invoked before base table is modified. If this is
+ * invoked firstly in the same statement, we save the transaction id and the
+ * command id at that time.
+ */
+Datum
+IVM_immediate_before(PG_FUNCTION_ARGS)
+{
+	TriggerData *trigdata = (TriggerData *) fcinfo->context;
+	char	   *matviewOid_text = trigdata->tg_trigger->tgargs[0];
+	char	   *ex_lock_text = trigdata->tg_trigger->tgargs[1];
+	Oid			matviewOid;
+	MV_TriggerHashEntry *entry;
+	bool	found;
+	bool	ex_lock;
+
+	matviewOid = DatumGetObjectId(DirectFunctionCall1(oidin, CStringGetDatum(matviewOid_text)));
+	ex_lock = DatumGetBool(DirectFunctionCall1(boolin, CStringGetDatum(ex_lock_text)));
+
+	/* If the view has more than one tables, we have to use an exclusive lock. */
+	if (ex_lock)
+	{
+		/*
+		 * Wait for concurrent transactions which update this materialized view at
+		 * READ COMMITED. This is needed to see changes committed in other
+		 * transactions. No wait and raise an error at REPEATABLE READ or
+		 * SERIALIZABLE to prevent update anomalies of matviews.
+		 * XXX: dead-lock is possible here.
+		 */
+		if (!IsolationUsesXactSnapshot())
+			LockRelationOid(matviewOid, ExclusiveLock);
+		else if (!ConditionalLockRelationOid(matviewOid, ExclusiveLock))
+		{
+			/* try to throw error by name; relation could be deleted... */
+			char	   *relname = get_rel_name(matviewOid);
+
+			if (!relname)
+				ereport(ERROR,
+						(errcode(ERRCODE_LOCK_NOT_AVAILABLE),
+						errmsg("could not obtain lock on materialized view during incremental maintenance")));
+
+			ereport(ERROR,
+					(errcode(ERRCODE_LOCK_NOT_AVAILABLE),
+					errmsg("could not obtain lock on materialized view \"%s\" during incremental maintenance",
+							relname)));
+		}
+	}
+	else
+		LockRelationOid(matviewOid, RowExclusiveLock);
+
+	/*
+	 * On the first call initialize the hashtable
+	 */
+	if (!mv_trigger_info)
+		mv_InitHashTables();
+
+	entry = (MV_TriggerHashEntry *) hash_search(mv_trigger_info,
+											  (void *) &matviewOid,
+											  HASH_ENTER, &found);
+
+	/* On the first BEFORE to update the view, initialize trigger data */
+	if (!found)
+	{
+		Snapshot snapshot = GetActiveSnapshot();
+
+		entry->matview_id = matviewOid;
+		entry->before_trig_count = 0;
+		entry->after_trig_count = 0;
+		entry->xid = GetCurrentTransactionId();
+		entry->cid = snapshot->curcid;
+		entry->tables = NIL;
+		entry->has_old = false;
+		entry->has_new = false;
+	}
+
+	entry->before_trig_count++;
+
+	return PointerGetDatum(NULL);
+}
+
+/*
+ * IVM_immediate_before
+ *
+ * IVM trigger function invoked after base table is modified.
+ * For each table, tuplestores of transition tables are collected.
+ * and after the last modification
+ */
+Datum
+IVM_immediate_maintenance(PG_FUNCTION_ARGS)
+{
+	TriggerData *trigdata = (TriggerData *) fcinfo->context;
+	Relation	rel;
+	Oid			relid;
+	Oid			matviewOid;
+	Query	   *query;
+	Query	   *rewritten = NULL;
+	char	   *matviewOid_text = trigdata->tg_trigger->tgargs[0];
+	Relation	matviewRel;
+	int old_depth = matview_maintenance_depth;
+
+	Oid			relowner;
+	Tuplestorestate *old_tuplestore = NULL;
+	Tuplestorestate *new_tuplestore = NULL;
+	DestReceiver *dest_new = NULL, *dest_old = NULL;
+	Oid			save_userid;
+	int			save_sec_context;
+	int			save_nestlevel;
+
+	MV_TriggerHashEntry *entry;
+	MV_TriggerTable		*table;
+	bool	found;
+
+	ParseState		 *pstate;
+	QueryEnvironment *queryEnv = create_queryEnv();
+	MemoryContext	oldcxt;
+	ListCell   *lc;
+	int			i;
+
+
+	/* Create a ParseState for rewriting the view definition query */
+	pstate = make_parsestate(NULL);
+	pstate->p_queryEnv = queryEnv;
+	pstate->p_expr_kind = EXPR_KIND_SELECT_TARGET;
+
+	rel = trigdata->tg_relation;
+	relid = rel->rd_id;
+
+	matviewOid = DatumGetObjectId(DirectFunctionCall1(oidin, CStringGetDatum(matviewOid_text)));
+
+	/*
+	 * On the first call initialize the hashtable
+	 */
+	if (!mv_trigger_info)
+		mv_InitHashTables();
+
+	/* get the entry for this materialized view */
+	entry = (MV_TriggerHashEntry *) hash_search(mv_trigger_info,
+											  (void *) &matviewOid,
+											  HASH_FIND, &found);
+	Assert (found && entry != NULL);
+	entry->after_trig_count++;
+
+	/* search the entry for the modified table and create new entry if not found */
+	found = false;
+	foreach(lc, entry->tables)
+	{
+		table = (MV_TriggerTable *) lfirst(lc);
+		if (table->table_id == relid)
+		{
+			found = true;
+			break;
+		}
+	}
+	if (!found)
+	{
+		oldcxt = MemoryContextSwitchTo(TopTransactionContext);
+
+		table = (MV_TriggerTable *) palloc0(sizeof(MV_TriggerTable));
+		table->table_id = relid;
+		table->old_tuplestores = NIL;
+		table->new_tuplestores = NIL;
+		table->old_rtes = NIL;
+		table->new_rtes = NIL;
+		table->rte_indexes = NIL;
+		entry->tables = lappend(entry->tables, table);
+
+		MemoryContextSwitchTo(oldcxt);
+	}
+
+	/* Save the transition tables and make a request to not free immediately */
+	if (trigdata->tg_oldtable)
+	{
+		oldcxt = MemoryContextSwitchTo(TopTransactionContext);
+		table->old_tuplestores = lappend(table->old_tuplestores, trigdata->tg_oldtable);
+		entry->has_old = true;
+		MemoryContextSwitchTo(oldcxt);
+	}
+	if (trigdata->tg_newtable)
+	{
+		oldcxt = MemoryContextSwitchTo(TopTransactionContext);
+		table->new_tuplestores = lappend(table->new_tuplestores, trigdata->tg_newtable);
+		entry->has_new = true;
+		MemoryContextSwitchTo(oldcxt);
+	}
+	if (entry->has_new || entry->has_old)
+	{
+		CmdType cmd;
+
+		if (TRIGGER_FIRED_BY_INSERT(trigdata->tg_event))
+			cmd = CMD_INSERT;
+		else if (TRIGGER_FIRED_BY_DELETE(trigdata->tg_event))
+			cmd = CMD_DELETE;
+		else if (TRIGGER_FIRED_BY_UPDATE(trigdata->tg_event))
+			cmd = CMD_UPDATE;
+		else
+			elog(ERROR,"unsupported trigger type");
+
+		/* Prolong lifespan of transition tables to the end of the last AFTER trigger */
+		SetTransitionTablePreserved(relid, cmd);
+	}
+
+
+	/* If this is not the last AFTER trigger call, immediately exit. */
+	Assert (entry->before_trig_count >= entry->after_trig_count);
+	if (entry->before_trig_count != entry->after_trig_count)
+		return PointerGetDatum(NULL);
+
+	/*
+	 * If this is the last AFTER trigger call, continue and update the view.
+	 */
+
+	/*
+	 * Advance command counter to make the updated base table row locally
+	 * visible.
+	 */
+	CommandCounterIncrement();
+
+	matviewRel = table_open(matviewOid, NoLock);
+
+	/* get view query*/
+	query = get_matview_query(matviewRel);
+
+	/* Make sure it is a materialized view. */
+	Assert(matviewRel->rd_rel->relkind == RELKIND_MATVIEW);
+
+	/*
+	 * Get and push the latast snapshot to see any changes which is committed
+	 * during waiting in other transactions at READ COMMITTED level.
+	 */
+	PushActiveSnapshot(GetTransactionSnapshot());
+
+	/*
+	 * Check for active uses of the relation in the current transaction, such
+	 * as open scans.
+	 *
+	 * NB: We count on this to protect us against problems with refreshing the
+	 * data using TABLE_INSERT_FROZEN.
+	 */
+	CheckTableNotInUse(matviewRel, "refresh a materialized view incrementally");
+
+	/*
+	 * Switch to the owner's userid, so that any functions are run as that
+	 * user.  Also arrange to make GUC variable changes local to this command.
+	 * We will switch modes when we are about to execute user code.
+	 */
+	relowner = matviewRel->rd_rel->relowner;
+	GetUserIdAndSecContext(&save_userid, &save_sec_context);
+	SetUserIdAndSecContext(relowner,
+						   save_sec_context | SECURITY_RESTRICTED_OPERATION);
+	save_nestlevel = NewGUCNestLevel();
+
+	/*
+	 * rewrite query for calculating deltas
+	 */
+
+	rewritten = copyObject(query);
+
+	/* Replace resnames in a target list with materialized view's attnames */
+	i = 0;
+	foreach (lc, rewritten->targetList)
+	{
+		TargetEntry *tle = (TargetEntry *) lfirst(lc);
+		Form_pg_attribute attr = TupleDescAttr(matviewRel->rd_att, i);
+		char *resname = NameStr(attr->attname);
+
+		tle->resname = pstrdup(resname);
+		i++;
+	}
+
+	/* Set all tables in the query to pre-update state */
+	rewritten = rewrite_query_for_preupdate_state(rewritten, entry->tables,
+												  entry->xid, entry->cid,
+												  pstate);
+	/* Rewrite for DISTINCT clause */
+	rewritten = rewrite_query_for_distinct(rewritten, pstate);
+
+	/* Create tuplestores to store view deltas */
+	if (entry->has_old)
+	{
+		oldcxt = MemoryContextSwitchTo(TopTransactionContext);
+
+		old_tuplestore = tuplestore_begin_heap(false, false, work_mem);
+		dest_old = CreateDestReceiver(DestTuplestore);
+		SetTuplestoreDestReceiverParams(dest_old,
+									old_tuplestore,
+									TopTransactionContext,
+									false,
+									NULL,
+									NULL);
+
+		MemoryContextSwitchTo(oldcxt);
+	}
+	if (entry->has_new)
+	{
+		oldcxt = MemoryContextSwitchTo(TopTransactionContext);
+
+		new_tuplestore = tuplestore_begin_heap(false, false, work_mem);
+		dest_new = CreateDestReceiver(DestTuplestore);
+		SetTuplestoreDestReceiverParams(dest_new,
+									new_tuplestore,
+									TopTransactionContext,
+									false,
+									NULL,
+									NULL);
+		MemoryContextSwitchTo(oldcxt);
+	}
+
+	/* for all modified tables */
+	foreach(lc, entry->tables)
+	{
+		ListCell *lc2;
+
+		table = (MV_TriggerTable *) lfirst(lc);
+
+		/* loop for self-join */
+		foreach(lc2, table->rte_indexes)
+		{
+			int	rte_index = lfirst_int(lc2);
+			TupleDesc		tupdesc_old;
+			TupleDesc		tupdesc_new;
+			bool	use_count = false;
+			char   *count_colname = NULL;
+
+			count_colname = pstrdup("__ivm_count__");
+
+			if (query->distinctClause)
+				use_count = true;
+
+			/* calculate delta tables */
+			calc_delta(table, rte_index, rewritten, dest_old, dest_new,
+					   &tupdesc_old, &tupdesc_new, queryEnv);
+
+			/* Set the table in the query to post-update state */
+			rewritten = rewrite_query_for_postupdate_state(rewritten, table, rte_index);
+
+			PG_TRY();
+			{
+				/* apply the delta tables to the materialized view */
+				apply_delta(matviewOid, old_tuplestore, new_tuplestore,
+							tupdesc_old, tupdesc_new, query, use_count,
+							count_colname);
+			}
+			PG_CATCH();
+			{
+				matview_maintenance_depth = old_depth;
+				PG_RE_THROW();
+			}
+			PG_END_TRY();
+
+			/* clear view delta tuplestores */
+			if (old_tuplestore)
+				tuplestore_clear(old_tuplestore);
+			if (new_tuplestore)
+				tuplestore_clear(new_tuplestore);
+		}
+	}
+
+	/* Clean up hash entry and delete tuplestores */
+	clean_up_IVM_hash_entry(entry);
+	if (old_tuplestore)
+	{
+		dest_old->rDestroy(dest_old);
+		tuplestore_end(old_tuplestore);
+	}
+	if (new_tuplestore)
+	{
+		dest_new->rDestroy(dest_new);
+		tuplestore_end(new_tuplestore);
+	}
+
+	/* Pop the original snapshot. */
+	PopActiveSnapshot();
+
+	table_close(matviewRel, NoLock);
+
+	/* Roll back any GUC changes */
+	AtEOXact_GUC(false, save_nestlevel);
+
+	/* Restore userid and security context */
+	SetUserIdAndSecContext(save_userid, save_sec_context);
+
+	return PointerGetDatum(NULL);
+}
+
+/*
+ * rewrite_query_for_preupdate_state
+ *
+ * Rewrite the query so that base tables' RTEs will represent "pre-update"
+ * state of tables. This is necessary to calculate view delta after multiple
+ * tables are modified. xid and cid are the transaction id and command id
+ * before the first table was modified.
+ */
+static Query*
+rewrite_query_for_preupdate_state(Query *query, List *tables,
+								  TransactionId xid, CommandId cid,
+								  ParseState *pstate)
+{
+	ListCell *lc;
+	int num_rte = list_length(query->rtable);
+	int i;
+
+
+	/* register delta ENRs */
+	register_delta_ENRs(pstate, query, tables);
+
+	/* XXX: Is necessary? Is this right timing? */
+	AcquireRewriteLocks(query, true, false);
+
+	i = 1;
+	foreach(lc, query->rtable)
+	{
+		RangeTblEntry *r = (RangeTblEntry*) lfirst(lc);
+
+		ListCell *lc2;
+		foreach(lc2, tables)
+		{
+			MV_TriggerTable *table = (MV_TriggerTable *) lfirst(lc2);
+			/*
+			 * if the modified table is found then replace the original RTE with
+			 * "pre-state" RTE and append its index to the list.
+			 */
+			if (r->relid == table->table_id)
+			{
+				lfirst(lc) = get_prestate_rte(r, table, xid, cid, pstate->p_queryEnv);
+				table->rte_indexes = lappend_int(table->rte_indexes, i);
+				break;
+			}
+		}
+
+		/* finish the loop if we processed all RTE included in the original query */
+		if (i++ >= num_rte)
+			break;
+	}
+
+	return query;
+}
+
+/*
+ * register_delta_ENRs
+ *
+ * For all modified tables, make ENRs for their transition tables
+ * and register them to the queryEnv. ENR's RTEs are also appended
+ * into the list in query tree.
+ */
+static void
+register_delta_ENRs(ParseState *pstate, Query *query, List *tables)
+{
+	QueryEnvironment *queryEnv = pstate->p_queryEnv;
+	ListCell *lc;
+	RangeTblEntry	*rte;
+
+	foreach(lc, tables)
+	{
+		MV_TriggerTable *table = (MV_TriggerTable *) lfirst(lc);
+		ListCell *lc2;
+		int count;
+
+		count = 0;
+		foreach(lc2, table->old_tuplestores)
+		{
+			Tuplestorestate *oldtable = (Tuplestorestate *) lfirst(lc2);
+			EphemeralNamedRelation enr =
+				palloc(sizeof(EphemeralNamedRelationData));
+			ParseNamespaceItem *nsitem;
+
+			enr->md.name = make_delta_enr_name("old", table->table_id, count);
+			enr->md.reliddesc = table->table_id;
+			enr->md.tupdesc = NULL;
+			enr->md.enrtype = ENR_NAMED_TUPLESTORE;
+			enr->md.enrtuples = tuplestore_tuple_count(oldtable);
+			enr->reldata = oldtable;
+			register_ENR(queryEnv, enr);
+
+			nsitem = addRangeTableEntryForENR(pstate, makeRangeVar(NULL, enr->md.name, -1), true);
+			rte = nsitem->p_rte;
+			/* if base table has RLS, set security condition to enr */
+			rte->securityQuals = get_securityQuals(table->table_id, list_length(query->rtable) + 1, query);
+
+			query->rtable = lappend(query->rtable, rte);
+			table->old_rtes = lappend(table->old_rtes, rte);
+
+			count++;
+		}
+
+		count = 0;
+		foreach(lc2, table->new_tuplestores)
+		{
+			Tuplestorestate *newtable = (Tuplestorestate *) lfirst(lc2);
+			EphemeralNamedRelation enr =
+				palloc(sizeof(EphemeralNamedRelationData));
+			ParseNamespaceItem *nsitem;
+
+			enr->md.name = make_delta_enr_name("new", table->table_id, count);
+			enr->md.reliddesc = table->table_id;
+			enr->md.tupdesc = NULL;
+			enr->md.enrtype = ENR_NAMED_TUPLESTORE;
+			enr->md.enrtuples = tuplestore_tuple_count(newtable);
+			enr->reldata = newtable;
+			register_ENR(queryEnv, enr);
+
+			nsitem = addRangeTableEntryForENR(pstate, makeRangeVar(NULL, enr->md.name, -1), true);
+			rte = nsitem->p_rte;
+			/* if base table has RLS, set security condition to enr*/
+			rte->securityQuals = get_securityQuals(table->table_id, list_length(query->rtable) + 1, query);
+
+			query->rtable = lappend(query->rtable, rte);
+			table->new_rtes = lappend(table->new_rtes, rte);
+
+			count++;
+		}
+	}
+}
+
+/*
+ * get_prestate_rte
+ *
+ * Rewrite RTE of the modified table to a subquery which represents
+ * "pre-state" table. The original RTE is saved in table->rte_original.
+ */
+static RangeTblEntry*
+get_prestate_rte(RangeTblEntry *rte, MV_TriggerTable *table,
+				 TransactionId xid, CommandId cid,
+				 QueryEnvironment *queryEnv)
+{
+	StringInfoData str;
+	RawStmt *raw;
+	Query *sub;
+	Relation rel;
+	ParseState *pstate;
+	char *relname;
+	int i;
+
+	pstate = make_parsestate(NULL);
+	pstate->p_queryEnv = queryEnv;
+	pstate->p_expr_kind = EXPR_KIND_SELECT_TARGET;
+
+	/*
+	 * We can use NoLock here since AcquireRewriteLocks should
+	 * have locked the rel already.
+	 */
+	rel = table_open(table->table_id, NoLock);
+	relname = quote_qualified_identifier(
+					get_namespace_name(RelationGetNamespace(rel)),
+									   RelationGetRelationName(rel));
+	table_close(rel, NoLock);
+
+	initStringInfo(&str);
+	appendStringInfo(&str,
+		"SELECT t.* FROM %s t"
+		" WHERE (age(t.xmin) - age(%u::text::xid) > 0) OR"
+		" (t.xmin = %u AND t.cmin::text::int < %u)",
+			relname, xid, xid, cid);
+
+	for (i = 0; i < list_length(table->old_tuplestores); i++)
+	{
+		appendStringInfo(&str, " UNION ALL ");
+		appendStringInfo(&str," SELECT * FROM %s",
+			make_delta_enr_name("old", table->table_id, i));
+	}
+
+	raw = (RawStmt*)linitial(raw_parser(str.data, RAW_PARSE_DEFAULT));
+	sub = transformStmt(pstate, raw->stmt);
+
+	/* If this query has setOperations, RTEs in rtables has a subquery which contains ENR */
+	if (sub->setOperations != NULL)
+	{
+		ListCell *lc;
+
+		/* add securityQuals for tuplestores */
+		foreach (lc, sub->rtable)
+		{
+			RangeTblEntry *rte;
+			RangeTblEntry *sub_rte;
+
+			rte = (RangeTblEntry *)lfirst(lc);
+			Assert(rte->subquery != NULL);
+
+			sub_rte = (RangeTblEntry *)linitial(rte->subquery->rtable);
+			if (sub_rte->rtekind == RTE_NAMEDTUPLESTORE)
+				/* rt_index is always 1, bacause subquery has enr_rte only */
+				sub_rte->securityQuals = get_securityQuals(sub_rte->relid, 1, sub);
+		}
+	}
+
+	/* save the original RTE */
+	table->original_rte = copyObject(rte);
+
+	rte->rtekind = RTE_SUBQUERY;
+	rte->subquery = sub;
+	rte->security_barrier = false;
+	/* Clear fields that should not be set in a subquery RTE */
+	rte->relid = InvalidOid;
+	rte->relkind = 0;
+	rte->rellockmode = 0;
+	rte->tablesample = NULL;
+	rte->inh = false;			/* must not be set for a subquery */
+
+	rte->requiredPerms = 0;		/* no permission check on subquery itself */
+	rte->checkAsUser = InvalidOid;
+	rte->selectedCols = NULL;
+	rte->insertedCols = NULL;
+	rte->updatedCols = NULL;
+	rte->extraUpdatedCols = NULL;
+
+	return rte;
+}
+
+/*
+ * make_delta_enr_name
+ *
+ * Make a name for ENR of a transition table from the base table's oid.
+ * prefix will be "new" or "old" depending on its transition table kind..
+ */
+static char*
+make_delta_enr_name(const char *prefix, Oid relid, int count)
+{
+	char buf[NAMEDATALEN];
+	char *name;
+
+	snprintf(buf, NAMEDATALEN, "__ivm_%s_%u_%u", prefix, relid, count);
+	name = pstrdup(buf);
+
+	return name;
+}
+
+/*
+ * union_ENRs
+ *
+ * Make a single table delta by unionning all transition tables of the modified table
+ * whose RTE is specified by
+ */
+static RangeTblEntry*
+union_ENRs(RangeTblEntry *rte, Oid relid, List *enr_rtes, const char *prefix,
+		   QueryEnvironment *queryEnv)
+{
+	StringInfoData str;
+	ParseState	*pstate;
+	RawStmt *raw;
+	Query *sub;
+	int	i;
+	RangeTblEntry *enr_rte;
+
+	/* Create a ParseState for rewriting the view definition query */
+	pstate = make_parsestate(NULL);
+	pstate->p_queryEnv = queryEnv;
+	pstate->p_expr_kind = EXPR_KIND_SELECT_TARGET;
+
+	initStringInfo(&str);
+
+	for (i = 0; i < list_length(enr_rtes); i++)
+	{
+		if (i > 0)
+			appendStringInfo(&str, " UNION ALL ");
+
+		appendStringInfo(&str,
+			" SELECT * FROM %s",
+			make_delta_enr_name(prefix, relid, i));
+	}
+
+	raw = (RawStmt*)linitial(raw_parser(str.data, RAW_PARSE_DEFAULT));
+	sub = transformStmt(pstate, raw->stmt);
+
+	rte->rtekind = RTE_SUBQUERY;
+	rte->subquery = sub;
+	rte->security_barrier = false;
+	/* Clear fields that should not be set in a subquery RTE */
+	rte->relid = InvalidOid;
+	rte->relkind = 0;
+	rte->rellockmode = 0;
+	rte->tablesample = NULL;
+	rte->inh = false;			/* must not be set for a subquery */
+
+	rte->requiredPerms = 0;		/* no permission check on subquery itself */
+	rte->checkAsUser = InvalidOid;
+	rte->selectedCols = NULL;
+	rte->insertedCols = NULL;
+	rte->updatedCols = NULL;
+	rte->extraUpdatedCols = NULL;
+	/* if base table has RLS, set security condition to enr*/
+	enr_rte = (RangeTblEntry *)linitial(sub->rtable);
+	/* rt_index is always 1, bacause subquery has enr_rte only */
+	enr_rte->securityQuals = get_securityQuals(relid, 1, sub);
+
+	return rte;
+}
+
+/*
+ * rewrite_query_for_distinct
+ *
+ * Rewrite query for counting DISTINCT clause.
+ */
+static Query *
+rewrite_query_for_distinct(Query *query, ParseState *pstate)
+{
+	TargetEntry *tle_count;
+	FuncCall *fn;
+	Node *node;
+
+	/* Add count(*) for counting distinct tuples in views */
+	fn = makeFuncCall(list_make1(makeString("count")), NIL, COERCE_EXPLICIT_CALL, -1);
+	fn->agg_star = true;
+	if (!query->groupClause && !query->hasAggs)
+		query->groupClause = transformDistinctClause(NULL, &query->targetList, query->sortClause, false);
+
+	node = ParseFuncOrColumn(pstate, fn->funcname, NIL, NULL, fn, false, -1);
+
+	tle_count = makeTargetEntry((Expr *) node,
+								list_length(query->targetList) + 1,
+								pstrdup("__ivm_count__"),
+								false);
+	query->targetList = lappend(query->targetList, tle_count);
+	query->hasAggs = true;
+
+	return query;
+}
+
+/*
+ * calc_delta
+ *
+ * Calculate view deltas generated under the modification of a table specified
+ * by the RTE index.
+ */
+static void
+calc_delta(MV_TriggerTable *table, int rte_index, Query *query,
+			DestReceiver *dest_old, DestReceiver *dest_new,
+			TupleDesc *tupdesc_old, TupleDesc *tupdesc_new,
+			QueryEnvironment *queryEnv)
+{
+	ListCell *lc = list_nth_cell(query->rtable, rte_index - 1);
+	RangeTblEntry *rte = (RangeTblEntry *) lfirst(lc);
+
+	/* Generate old delta */
+	if (list_length(table->old_rtes) > 0)
+	{
+		/* Replace the modified table with the old delta table and calculate the old view delta. */
+		lfirst(lc) = union_ENRs(rte, table->table_id, table->old_rtes, "old", queryEnv);
+		refresh_matview_datafill(dest_old, query, queryEnv, tupdesc_old, "");
+	}
+
+	/* Generate new delta */
+	if (list_length(table->new_rtes) > 0)
+	{
+		/* Replace the modified table with the new delta table and calculate the new view delta*/
+		lfirst(lc) = union_ENRs(rte, table->table_id, table->new_rtes, "new", queryEnv);
+		refresh_matview_datafill(dest_new, query, queryEnv, tupdesc_new, "");
+	}
+}
+
+/*
+ * rewrite_query_for_postupdate_state
+ *
+ * Rewrite the query so that the specified base table's RTEs will represent
+ * "post-update" state of tables. This is called after the view delta
+ * calculation due to changes on this table finishes.
+ */
+static Query*
+rewrite_query_for_postupdate_state(Query *query, MV_TriggerTable *table, int rte_index)
+{
+	ListCell *lc = list_nth_cell(query->rtable, rte_index - 1);
+
+	/* Retore the original RTE */
+	lfirst(lc) = table->original_rte;
+
+	return query;
+}
+
+/*
+ * apply_delta
+ *
+ * Apply deltas to the materialized view. In outer join cases, this requires
+ * the view maintenance graph.
+ */
+static void
+apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *new_tuplestores,
+			TupleDesc tupdesc_old, TupleDesc tupdesc_new,
+			Query *query, bool use_count, char *count_colname)
+{
+	StringInfoData querybuf;
+	StringInfoData target_list_buf;
+	Relation	matviewRel;
+	char	   *matviewname;
+	ListCell	*lc;
+	int			i;
+	List	   *keys = NIL;
+
+
+	/*
+	 * get names of the materialized view and delta tables
+	 */
+
+	matviewRel = table_open(matviewOid, NoLock);
+	matviewname = quote_qualified_identifier(get_namespace_name(RelationGetNamespace(matviewRel)),
+											 RelationGetRelationName(matviewRel));
+
+	/*
+	 * Build parts of the maintenance queries
+	 */
+
+	initStringInfo(&querybuf);
+	initStringInfo(&target_list_buf);
+
+	/* build string of target list */
+	for (i = 0; i < matviewRel->rd_att->natts; i++)
+	{
+		Form_pg_attribute attr = TupleDescAttr(matviewRel->rd_att, i);
+		char   *resname = NameStr(attr->attname);
+
+		if (i != 0)
+			appendStringInfo(&target_list_buf, ", ");
+		appendStringInfo(&target_list_buf, "%s", quote_qualified_identifier(NULL, resname));
+	}
+
+	i = 0;
+	foreach (lc, query->targetList)
+	{
+		TargetEntry *tle = (TargetEntry *) lfirst(lc);
+		Form_pg_attribute attr = TupleDescAttr(matviewRel->rd_att, i);
+		char *resname = NameStr(attr->attname);
+
+		i++;
+
+		if (tle->resjunk)
+			continue;
+
+		keys = lappend(keys, resname);
+	}
+
+	/* Start maintaining the materialized view. */
+	OpenMatViewIncrementalMaintenance();
+
+	/* Open SPI context. */
+	if (SPI_connect() != SPI_OK_CONNECT)
+		elog(ERROR, "SPI_connect failed");
+
+	/* For tuple deletion */
+	if (old_tuplestores && tuplestore_tuple_count(old_tuplestores) > 0)
+	{
+		EphemeralNamedRelation enr = palloc(sizeof(EphemeralNamedRelationData));
+		int				rc;
+
+		/* convert tuplestores to ENR, and register for SPI */
+		enr->md.name = pstrdup(OLD_DELTA_ENRNAME);
+		enr->md.reliddesc = InvalidOid;
+		enr->md.tupdesc = tupdesc_old;
+		enr->md.enrtype = ENR_NAMED_TUPLESTORE;
+		enr->md.enrtuples = tuplestore_tuple_count(old_tuplestores);
+		enr->reldata = old_tuplestores;
+
+		rc = SPI_register_relation(enr);
+		if (rc != SPI_OK_REL_REGISTER)
+			elog(ERROR, "SPI_register failed");
+
+		if (use_count)
+			/* apply old delta and get rows to be recalculated */
+			apply_old_delta_with_count(matviewname, OLD_DELTA_ENRNAME,
+									   keys, count_colname);
+		else
+			apply_old_delta(matviewname, OLD_DELTA_ENRNAME, keys);
+
+	}
+	/* For tuple insertion */
+	if (new_tuplestores && tuplestore_tuple_count(new_tuplestores) > 0)
+	{
+		EphemeralNamedRelation enr = palloc(sizeof(EphemeralNamedRelationData));
+		int rc;
+
+		/* convert tuplestores to ENR, and register for SPI */
+		enr->md.name = pstrdup(NEW_DELTA_ENRNAME);
+		enr->md.reliddesc = InvalidOid;
+		enr->md.tupdesc = tupdesc_new;;
+		enr->md.enrtype = ENR_NAMED_TUPLESTORE;
+		enr->md.enrtuples = tuplestore_tuple_count(new_tuplestores);
+		enr->reldata = new_tuplestores;
+
+		rc = SPI_register_relation(enr);
+		if (rc != SPI_OK_REL_REGISTER)
+			elog(ERROR, "SPI_register failed");
+
+		/* apply new delta */
+		if (use_count)
+			apply_new_delta_with_count(matviewname, NEW_DELTA_ENRNAME,
+								keys, &target_list_buf, count_colname);
+		else
+			apply_new_delta(matviewname, NEW_DELTA_ENRNAME, &target_list_buf);
+	}
+
+	/* We're done maintaining the materialized view. */
+	CloseMatViewIncrementalMaintenance();
+
+	table_close(matviewRel, NoLock);
+
+	/* Close SPI context. */
+	if (SPI_finish() != SPI_OK_FINISH)
+		elog(ERROR, "SPI_finish failed");
+}
+
+/*
+ * apply_old_delta_with_count
+ *
+ * Execute a query for applying a delta table given by deltname_old
+ * which contains tuples to be deleted from to a materialized view given by
+ * matviewname.  This is used when counting is required, that is, the view
+ * has aggregate or distinct.
+ */
+static void
+apply_old_delta_with_count(const char *matviewname, const char *deltaname_old,
+				List *keys, const char *count_colname)
+{
+	StringInfoData	querybuf;
+	char   *match_cond;
+
+	/* build WHERE condition for searching tuples to be deleted */
+	match_cond = get_matching_condition_string(keys);
+
+	/* Search for matching tuples from the view and update or delete if found. */
+	initStringInfo(&querybuf);
+	appendStringInfo(&querybuf,
+					"WITH t AS ("			/* collecting tid of target tuples in the view */
+						"SELECT diff.%s, "			/* count column */
+								"(diff.%s OPERATOR(pg_catalog.=) mv.%s) AS for_dlt, "
+								"mv.ctid "
+						"FROM %s AS mv, %s AS diff "
+						"WHERE %s"					/* tuple matching condition */
+					"), updt AS ("			/* update a tuple if this is not to be deleted */
+						"UPDATE %s AS mv SET %s = mv.%s OPERATOR(pg_catalog.-) t.%s "
+						"FROM t WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND NOT for_dlt "
+					"), dlt AS ("			/* delete a tuple if this is to be deleted */
+						"DELETE FROM %s AS mv USING t "
+						"WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt"
+					")",
+					count_colname,
+					count_colname, count_colname,
+					matviewname, deltaname_old,
+					match_cond,
+					matviewname, count_colname, count_colname, count_colname,
+					matviewname);
+
+	if (SPI_exec(querybuf.data, 0) != SPI_OK_DELETE)
+		elog(ERROR, "SPI_exec failed: %s", querybuf.data);
+}
+
+/*
+ * apply_old_delta
+ *
+ * Execute a query for applying a delta table given by deltname_old
+ * which contains tuples to be deleted from to a materialized view given by
+ * matviewname.  This is used when counting is not required.
+ */
+static void
+apply_old_delta(const char *matviewname, const char *deltaname_old,
+				List *keys)
+{
+	StringInfoData	querybuf;
+	StringInfoData	keysbuf;
+	char   *match_cond;
+	ListCell *lc;
+
+	/* build WHERE condition for searching tuples to be deleted */
+	match_cond = get_matching_condition_string(keys);
+
+	/* build string of keys list */
+	initStringInfo(&keysbuf);
+	foreach (lc, keys)
+	{
+		Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc);
+		char   *resname = NameStr(attr->attname);
+		appendStringInfo(&keysbuf, "%s", quote_qualified_identifier("mv", resname));
+		if (lnext(keys, lc))
+			appendStringInfo(&keysbuf, ", ");
+	}
+
+	/* Search for matching tuples from the view and update or delete if found. */
+	initStringInfo(&querybuf);
+	appendStringInfo(&querybuf,
+	"DELETE FROM %s WHERE ctid IN ("
+		"SELECT tid FROM (SELECT row_number() over (partition by %s) AS \"__ivm_row_number__\","
+								  "mv.ctid AS tid,"
+								  "diff.\"__ivm_count__\""
+						 "FROM %s AS mv, %s AS diff "
+						 "WHERE %s) v "
+					"WHERE v.\"__ivm_row_number__\" OPERATOR(pg_catalog.<=) v.\"__ivm_count__\")",
+					matviewname,
+					keysbuf.data,
+					matviewname, deltaname_old,
+					match_cond);
+
+	if (SPI_exec(querybuf.data, 0) != SPI_OK_DELETE)
+		elog(ERROR, "SPI_exec failed: %s", querybuf.data);
+}
+
+/*
+ * apply_new_delta_with_count
+ *
+ * Execute a query for applying a delta table given by deltname_new
+ * which contains tuples to be inserted into a materialized view given by
+ * matviewname.  This is used when counting is required, that is, the view
+ * has aggregate or distinct. Also, when a table in EXISTS sub queries
+ * is modified.
+ */
+static void
+apply_new_delta_with_count(const char *matviewname, const char* deltaname_new,
+				List *keys, StringInfo target_list, const char* count_colname)
+{
+	StringInfoData	querybuf;
+	StringInfoData	returning_keys;
+	ListCell	*lc;
+	char	*match_cond = "";
+
+	/* build WHERE condition for searching tuples to be updated */
+	match_cond = get_matching_condition_string(keys);
+
+	/* build string of keys list */
+	initStringInfo(&returning_keys);
+	if (keys)
+	{
+		foreach (lc, keys)
+		{
+			Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc);
+			char   *resname = NameStr(attr->attname);
+			appendStringInfo(&returning_keys, "%s", quote_qualified_identifier("mv", resname));
+			if (lnext(keys, lc))
+				appendStringInfo(&returning_keys, ", ");
+		}
+	}
+	else
+		appendStringInfo(&returning_keys, "NULL");
+
+	/* Search for matching tuples from the view and update if found or insert if not. */
+	initStringInfo(&querybuf);
+	appendStringInfo(&querybuf,
+					"WITH updt AS ("		/* update a tuple if this exists in the view */
+						"UPDATE %s AS mv SET %s = mv.%s OPERATOR(pg_catalog.+) diff.%s "
+						"FROM %s AS diff "
+						"WHERE %s "					/* tuple matching condition */
+						"RETURNING %s"				/* returning keys of updated tuples */
+					") INSERT INTO %s (%s)"	/* insert a new tuple if this doesn't existw */
+						"SELECT %s FROM %s AS diff "
+						"WHERE NOT EXISTS (SELECT 1 FROM updt AS mv WHERE %s);",
+					matviewname, count_colname, count_colname, count_colname,
+					deltaname_new,
+					match_cond,
+					returning_keys.data,
+					matviewname, target_list->data,
+					target_list->data, deltaname_new,
+					match_cond);
+
+	if (SPI_exec(querybuf.data, 0) != SPI_OK_INSERT)
+		elog(ERROR, "SPI_exec failed: %s", querybuf.data);
+}
+
+/*
+ * apply_new_delta
+ *
+ * Execute a query for applying a delta table given by deltname_new
+ * which contains tuples to be inserted into a materialized view given by
+ * matviewname.  This is used when counting is not required.
+ */
+static void
+apply_new_delta(const char *matviewname, const char *deltaname_new,
+				StringInfo target_list)
+{
+	StringInfoData	querybuf;
+
+	/* Search for matching tuples from the view and update or delete if found. */
+	initStringInfo(&querybuf);
+	appendStringInfo(&querybuf,
+					"INSERT INTO %s (%s) SELECT %s FROM ("
+						"SELECT diff.*, generate_series(1, diff.\"__ivm_count__\") "
+						"FROM %s AS diff) AS v",
+					matviewname, target_list->data, target_list->data,
+					deltaname_new);
+
+	if (SPI_exec(querybuf.data, 0) != SPI_OK_INSERT)
+		elog(ERROR, "SPI_exec failed: %s", querybuf.data);
+}
+
+/*
+ * get_matching_condition_string
+ *
+ * Build a predicate string for looking for a tuple with given keys.
+ */
+static char *
+get_matching_condition_string(List *keys)
+{
+	StringInfoData match_cond;
+	ListCell	*lc;
+
+	/* If there is no key columns, the condition is always true. */
+	if (keys == NIL)
+		return "true";
+
+	initStringInfo(&match_cond);
+	foreach (lc, keys)
+	{
+		Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc);
+		char   *resname = NameStr(attr->attname);
+		char   *mv_resname = quote_qualified_identifier("mv", resname);
+		char   *diff_resname = quote_qualified_identifier("diff", resname);
+		Oid		typid = attr->atttypid;
+
+		/* Considering NULL values, we can not use simple = operator. */
+		appendStringInfo(&match_cond, "(");
+		generate_equal(&match_cond, typid, mv_resname, diff_resname);
+		appendStringInfo(&match_cond, " OR (%s IS NULL AND %s IS NULL))",
+						 mv_resname, diff_resname);
+
+		if (lnext(keys, lc))
+			appendStringInfo(&match_cond, " AND ");
+	}
+
+	return match_cond.data;
+}
+
+/*
+ * generate_equals
+ *
+ * Generate an equality clause using given operands' default equality
+ * operator.
+ */
+static void
+generate_equal(StringInfo querybuf, Oid opttype,
+			   const char *leftop, const char *rightop)
+{
+	TypeCacheEntry *typentry;
+
+	typentry = lookup_type_cache(opttype, TYPECACHE_EQ_OPR);
+	if (!OidIsValid(typentry->eq_opr))
+		ereport(ERROR,
+				(errcode(ERRCODE_UNDEFINED_FUNCTION),
+				 errmsg("could not identify an equality operator for type %s",
+						format_type_be(opttype))));
+
+	generate_operator_clause(querybuf,
+							 leftop, opttype,
+							 typentry->eq_opr,
+							 rightop, opttype);
+}
+
+/*
+ * mv_InitHashTables
+ */
+static void
+mv_InitHashTables(void)
+{
+	HASHCTL		ctl;
+
+	memset(&ctl, 0, sizeof(ctl));
+	ctl.keysize = sizeof(Oid);
+	ctl.entrysize = sizeof(MV_TriggerHashEntry);
+	mv_trigger_info = hash_create("MV trigger info",
+								 MV_INIT_QUERYHASHSIZE,
+								 &ctl, HASH_ELEM | HASH_BLOBS);
+}
+
+/*
+ * AtAbort_IVM
+ *
+ * Clean up hash entries for all materialized views. This is called at
+ * transaction abort.
+ */
+void
+AtAbort_IVM()
+{
+	HASH_SEQ_STATUS seq;
+	MV_TriggerHashEntry *entry;
+
+	if (mv_trigger_info)
+	{
+		hash_seq_init(&seq, mv_trigger_info);
+		while ((entry = hash_seq_search(&seq)) != NULL)
+			clean_up_IVM_hash_entry(entry);
+	}
+}
+
+/*
+ * clean_up_IVM_hash_entry
+ *
+ * Clean up tuple stores and hash entries for a materialized view after its
+ * maintenance finished.
+ */
+static void
+clean_up_IVM_hash_entry(MV_TriggerHashEntry *entry)
+{
+	bool found;
+	ListCell *lc;
+
+	foreach(lc, entry->tables)
+	{
+		MV_TriggerTable *table = (MV_TriggerTable *) lfirst(lc);
+
+		list_free(table->old_tuplestores);
+		list_free(table->new_tuplestores);
+	}
+	list_free(entry->tables);
+
+	hash_search(mv_trigger_info, (void *) &entry->matview_id, HASH_REMOVE, &found);
+}
+
+/*
+ * isIvmName
+ *
+ * Check if this is a IVM hidden column from the name.
+ */
+bool
+isIvmName(const char *s)
+{
+	if (s)
+		return (strncmp(s, "__ivm_", 6) == 0);
+	return false;
+}
+
+/*
+ * get_securityQuals
+ *
+ * Get row security policy on a relation.
+ * This is used by IVM for copying RLS from base table to enr.
+ */
+static List *
+get_securityQuals(Oid relId, int rt_index, Query *query)
+{
+	ParseState *pstate;
+	Relation rel;
+	ParseNamespaceItem *nsitem;
+	RangeTblEntry *rte;
+	List *securityQuals;
+	List *withCheckOptions;
+	bool  hasRowSecurity;
+	bool  hasSubLinks;
+
+	securityQuals = NIL;
+	pstate = make_parsestate(NULL);
+
+	rel = table_open(relId, NoLock);
+	nsitem = addRangeTableEntryForRelation(pstate, rel, AccessShareLock, NULL, false, false);
+	rte = nsitem->p_rte;
+
+	get_row_security_policies(query, rte, rt_index,
+							  &securityQuals, &withCheckOptions,
+							  &hasRowSecurity, &hasSubLinks);
+
+	/*
+	 * Make sure the query is marked correctly if row level security
+	 * applies, or if the new quals had sublinks.
+	 */
+	if (hasRowSecurity)
+		query->hasRowSecurity = true;
+	if (hasSubLinks)
+		query->hasSubLinks = true;
+
+	table_close(rel, NoLock);
+
+	return securityQuals;
+}
diff --git a/src/backend/commands/tablecmds.c b/src/backend/commands/tablecmds.c
index 3e83f375b5..c64539b20d 100644
--- a/src/backend/commands/tablecmds.c
+++ b/src/backend/commands/tablecmds.c
@@ -51,6 +51,7 @@
 #include "commands/cluster.h"
 #include "commands/comment.h"
 #include "commands/defrem.h"
+#include "commands/matview.h"
 #include "commands/event_trigger.h"
 #include "commands/policy.h"
 #include "commands/sequence.h"
@@ -3415,6 +3416,14 @@ renameatt_internal(Oid myrelid,
 	targetrelation = relation_open(myrelid, AccessExclusiveLock);
 	renameatt_check(myrelid, RelationGetForm(targetrelation), recursing);
 
+	/*
+	 * Don't rename IVM columns.
+	 */
+	if (RelationIsIVM(targetrelation) && isIvmName(oldattname))
+		ereport(ERROR,
+				(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+				 errmsg("IVM column can not be renamed")));
+
 	/*
 	 * if the 'recurse' flag is set then we are supposed to rename this
 	 * attribute in all classes that inherit from 'relname' (as well as in
diff --git a/src/backend/nodes/copyfuncs.c b/src/backend/nodes/copyfuncs.c
index 80268ac059..158652734f 100644
--- a/src/backend/nodes/copyfuncs.c
+++ b/src/backend/nodes/copyfuncs.c
@@ -2464,6 +2464,7 @@ _copyRangeTblEntry(const RangeTblEntry *from)
 	COPY_SCALAR_FIELD(relkind);
 	COPY_SCALAR_FIELD(rellockmode);
 	COPY_NODE_FIELD(tablesample);
+	COPY_SCALAR_FIELD(relisivm);
 	COPY_NODE_FIELD(subquery);
 	COPY_SCALAR_FIELD(security_barrier);
 	COPY_SCALAR_FIELD(jointype);
diff --git a/src/backend/nodes/equalfuncs.c b/src/backend/nodes/equalfuncs.c
index 572560b4a2..5a320c28a0 100644
--- a/src/backend/nodes/equalfuncs.c
+++ b/src/backend/nodes/equalfuncs.c
@@ -2765,6 +2765,7 @@ _equalRangeTblEntry(const RangeTblEntry *a, const RangeTblEntry *b)
 	COMPARE_SCALAR_FIELD(relkind);
 	COMPARE_SCALAR_FIELD(rellockmode);
 	COMPARE_NODE_FIELD(tablesample);
+	COMPARE_SCALAR_FIELD(relisivm);
 	COMPARE_NODE_FIELD(subquery);
 	COMPARE_SCALAR_FIELD(security_barrier);
 	COMPARE_SCALAR_FIELD(jointype);
diff --git a/src/backend/nodes/outfuncs.c b/src/backend/nodes/outfuncs.c
index 8ec4059cc0..300d488824 100644
--- a/src/backend/nodes/outfuncs.c
+++ b/src/backend/nodes/outfuncs.c
@@ -3258,6 +3258,7 @@ _outRangeTblEntry(StringInfo str, const RangeTblEntry *node)
 			WRITE_CHAR_FIELD(relkind);
 			WRITE_INT_FIELD(rellockmode);
 			WRITE_NODE_FIELD(tablesample);
+			WRITE_BOOL_FIELD(relisivm);
 			break;
 		case RTE_SUBQUERY:
 			WRITE_NODE_FIELD(subquery);
diff --git a/src/backend/nodes/readfuncs.c b/src/backend/nodes/readfuncs.c
index cc6dcb7220..37dff1ec27 100644
--- a/src/backend/nodes/readfuncs.c
+++ b/src/backend/nodes/readfuncs.c
@@ -1441,6 +1441,7 @@ _readRangeTblEntry(void)
 			READ_CHAR_FIELD(relkind);
 			READ_INT_FIELD(rellockmode);
 			READ_NODE_FIELD(tablesample);
+			READ_BOOL_FIELD(relisivm);
 			break;
 		case RTE_SUBQUERY:
 			READ_NODE_FIELD(subquery);
diff --git a/src/backend/parser/parse_relation.c b/src/backend/parser/parse_relation.c
index cb9e177b5e..dcfd1f3fc0 100644
--- a/src/backend/parser/parse_relation.c
+++ b/src/backend/parser/parse_relation.c
@@ -36,6 +36,7 @@
 #include "utils/rel.h"
 #include "utils/syscache.h"
 #include "utils/varlena.h"
+#include "commands/matview.h"
 
 
 /*
@@ -79,7 +80,7 @@ static void expandTupleDesc(TupleDesc tupdesc, Alias *eref,
 							int count, int offset,
 							int rtindex, int sublevels_up,
 							int location, bool include_dropped,
-							List **colnames, List **colvars);
+							List **colnames, List **colvars, bool is_ivm);
 static int	specialAttNum(const char *attname);
 static bool isQueryUsingTempRelation_walker(Node *node, void *context);
 
@@ -1433,6 +1434,7 @@ addRangeTableEntry(ParseState *pstate,
 	rte->relid = RelationGetRelid(rel);
 	rte->relkind = rel->rd_rel->relkind;
 	rte->rellockmode = lockmode;
+	rte->relisivm = rel->rd_rel->relisivm;
 
 	/*
 	 * Build the list of effective column names using user-supplied aliases
@@ -1521,6 +1523,7 @@ addRangeTableEntryForRelation(ParseState *pstate,
 	rte->relid = RelationGetRelid(rel);
 	rte->relkind = rel->rd_rel->relkind;
 	rte->rellockmode = lockmode;
+	rte->relisivm = rel->rd_rel->relisivm;
 
 	/*
 	 * Build the list of effective column names using user-supplied aliases
@@ -2676,7 +2679,7 @@ expandRTE(RangeTblEntry *rte, int rtindex, int sublevels_up,
 						expandTupleDesc(tupdesc, rte->eref,
 										rtfunc->funccolcount, atts_done,
 										rtindex, sublevels_up, location,
-										include_dropped, colnames, colvars);
+										include_dropped, colnames, colvars, false);
 					}
 					else if (functypclass == TYPEFUNC_SCALAR)
 					{
@@ -2944,7 +2947,7 @@ expandRelation(Oid relid, Alias *eref, int rtindex, int sublevels_up,
 	expandTupleDesc(rel->rd_att, eref, rel->rd_att->natts, 0,
 					rtindex, sublevels_up,
 					location, include_dropped,
-					colnames, colvars);
+					colnames, colvars, RelationIsIVM(rel));
 	relation_close(rel, AccessShareLock);
 }
 
@@ -2961,7 +2964,7 @@ static void
 expandTupleDesc(TupleDesc tupdesc, Alias *eref, int count, int offset,
 				int rtindex, int sublevels_up,
 				int location, bool include_dropped,
-				List **colnames, List **colvars)
+				List **colnames, List **colvars, bool is_ivm)
 {
 	ListCell   *aliascell;
 	int			varattno;
@@ -2974,6 +2977,9 @@ expandTupleDesc(TupleDesc tupdesc, Alias *eref, int count, int offset,
 	{
 		Form_pg_attribute attr = TupleDescAttr(tupdesc, varattno);
 
+		if (is_ivm && isIvmName(NameStr(attr->attname)) && !MatViewIncrementalMaintenanceIsEnabled())
+			continue;
+
 		if (attr->attisdropped)
 		{
 			if (include_dropped)
@@ -3127,6 +3133,10 @@ expandNSItemAttrs(ParseState *pstate, ParseNamespaceItem *nsitem,
 		Var		   *varnode = (Var *) lfirst(var);
 		TargetEntry *te;
 
+		/* if transform * into columnlist with IMMV, remove IVM columns */
+		if (rte->relisivm && isIvmName(label) && !MatViewIncrementalMaintenanceIsEnabled())
+			continue;
+
 		te = makeTargetEntry((Expr *) varnode,
 							 (AttrNumber) pstate->p_next_resno++,
 							 label,
diff --git a/src/backend/rewrite/rewriteDefine.c b/src/backend/rewrite/rewriteDefine.c
index 185bf5fbff..d8a8b66196 100644
--- a/src/backend/rewrite/rewriteDefine.c
+++ b/src/backend/rewrite/rewriteDefine.c
@@ -776,7 +776,8 @@ checkRuleResultList(List *targetList, TupleDesc resultDesc, bool isSelect,
 														attr->atttypmod))));
 	}
 
-	if (i != resultDesc->natts)
+	/* No check for materialized views since this could have special columns for IVM */
+	if ((!isSelect || requireColumnNameMatch) && i != resultDesc->natts)
 		ereport(ERROR,
 				(errcode(ERRCODE_INVALID_OBJECT_DEFINITION),
 				 isSelect ?
diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat
index 7024dbe10a..a37602d45f 100644
--- a/src/include/catalog/pg_proc.dat
+++ b/src/include/catalog/pg_proc.dat
@@ -11736,4 +11736,12 @@
   prorettype => 'bytea', proargtypes => 'pg_brin_minmax_multi_summary',
   prosrc => 'brin_minmax_multi_summary_send' },
 
+# IVM
+{ oid => '786', descr => 'ivm trigger (before)',
+  proname => 'IVM_immediate_before', provolatile => 'v', prorettype => 'trigger',
+  proargtypes => '', prosrc => 'IVM_immediate_before' },
+{ oid => '787', descr => 'ivm trigger (after)',
+  proname => 'IVM_immediate_maintenance', provolatile => 'v', prorettype => 'trigger',
+  proargtypes => '', prosrc => 'IVM_immediate_maintenance' },
+
 ]
diff --git a/src/include/commands/createas.h b/src/include/commands/createas.h
index 54a38491fb..bcea9782d3 100644
--- a/src/include/commands/createas.h
+++ b/src/include/commands/createas.h
@@ -16,6 +16,7 @@
 
 #include "catalog/objectaddress.h"
 #include "nodes/params.h"
+#include "nodes/pathnodes.h"
 #include "parser/parse_node.h"
 #include "tcop/dest.h"
 #include "utils/queryenvironment.h"
@@ -25,6 +26,11 @@ extern ObjectAddress ExecCreateTableAs(ParseState *pstate, CreateTableAsStmt *st
 									   ParamListInfo params, QueryEnvironment *queryEnv,
 									   QueryCompletion *qc);
 
+extern void CreateIvmTriggersOnBaseTables(Query *qry, Oid matviewOid, bool is_create);
+extern void CreateIndexOnIMMV(Query *query, Relation matviewRel);
+
+extern Query *rewriteQueryForIMMV(Query *query, List *colNames);
+
 extern int	GetIntoRelEFlags(IntoClause *intoClause);
 
 extern DestReceiver *CreateIntoRelDestReceiver(IntoClause *intoClause);
diff --git a/src/include/commands/matview.h b/src/include/commands/matview.h
index a067da39d2..ec479db513 100644
--- a/src/include/commands/matview.h
+++ b/src/include/commands/matview.h
@@ -15,6 +15,7 @@
 #define MATVIEW_H
 
 #include "catalog/objectaddress.h"
+#include "fmgr.h"
 #include "nodes/params.h"
 #include "nodes/parsenodes.h"
 #include "tcop/dest.h"
@@ -23,6 +24,8 @@
 
 extern void SetMatViewPopulatedState(Relation relation, bool newstate);
 
+extern void SetMatViewIVMState(Relation relation, bool newstate);
+
 extern ObjectAddress ExecRefreshMatView(RefreshMatViewStmt *stmt, const char *queryString,
 										ParamListInfo params, QueryCompletion *qc);
 
@@ -30,4 +33,9 @@ extern DestReceiver *CreateTransientRelDestReceiver(Oid oid);
 
 extern bool MatViewIncrementalMaintenanceIsEnabled(void);
 
+extern Datum IVM_immediate_before(PG_FUNCTION_ARGS);
+extern Datum IVM_immediate_maintenance(PG_FUNCTION_ARGS);
+extern void AtAbort_IVM(void);
+extern bool isIvmName(const char *s);
+
 #endif							/* MATVIEW_H */
diff --git a/src/include/nodes/parsenodes.h b/src/include/nodes/parsenodes.h
index 3e9bdc781f..b0e8a396cc 100644
--- a/src/include/nodes/parsenodes.h
+++ b/src/include/nodes/parsenodes.h
@@ -1036,6 +1036,7 @@ typedef struct RangeTblEntry
 	char		relkind;		/* relation kind (see pg_class.relkind) */
 	int			rellockmode;	/* lock level that query requires on the rel */
 	struct TableSampleClause *tablesample;	/* sampling info, or NULL */
+	bool		relisivm;
 
 	/*
 	 * Fields valid for a subquery RTE (else NULL):
@@ -2195,6 +2196,7 @@ typedef struct CreateStmt
 	char	   *tablespacename; /* table space to use, or NULL */
 	char	   *accessMethod;	/* table access method */
 	bool		if_not_exists;	/* just do nothing if it already exists? */
+	bool		ivm;			/* incremental view maintenance is used by materialized view */
 } CreateStmt;
 
 /* ----------
-- 
2.17.1


--Multipart=_Fri__4_Feb_2022_01_48_06_+0900_N8BNZpfOR27sWrgY
Content-Type: text/x-diff;
 name="v25-0006-Add-Incremental-View-Maintenance-support-to-psql.patch"
Content-Disposition: attachment;
 filename="v25-0006-Add-Incremental-View-Maintenance-support-to-psql.patch"
Content-Transfer-Encoding: 7bit



^ permalink  raw  reply  [nested|flat] 101+ messages in thread

* [PATCH v24 07/15] Add Incremental View Maintenance support
@ 2020-12-22 09:40  Yugo Nagata <[email protected]>
  0 siblings, 0 replies; 101+ messages in thread

From: Yugo Nagata @ 2020-12-22 09:40 UTC (permalink / raw)

In this implementation, AFTER triggers are used to collect
tuplestores containing transition table contents. When multiple tables
are changed, multiple AFTER triggers are invoked, then the final AFTER
trigger performs actual update of the matview. In addition, BEFORE
triggers are also used to handle global information for view
maintenance. To calculate view deltas, we need both pre-state and
post-state of base tables. Post-update states are available in AFTER
trigger, and pre-update states can be calculated by filtering inserted
tuples using cmin/xmin system columns, and append deleted tuples which
are contained in an old transition table.

This patch also allows self-join, simultaneous updates of more than
one base table, and multiple updates of the same base table.

Incrementally Maintainable Materialized Views (IMMV) can contain
duplicated tuples. Also, DISTINCT clause is supported. When IMMV is
created with DISTINCT, multiplicity of tuples is counted and stored
in  "__ivm_count__" column, which is a hidden column of IMMV.
The value in __ivm_count__ is updated when IMMV is maintained
incrementally. A tuple in IMMV can be removed if and only if the
count becomes zero.
---
 src/backend/access/transam/xact.c   |    5 +
 src/backend/commands/createas.c     |  713 ++++++++++++
 src/backend/commands/indexcmds.c    |   40 +
 src/backend/commands/matview.c      | 1549 ++++++++++++++++++++++++++-
 src/backend/commands/tablecmds.c    |    9 +
 src/backend/nodes/copyfuncs.c       |    1 +
 src/backend/nodes/equalfuncs.c      |    1 +
 src/backend/nodes/outfuncs.c        |    1 +
 src/backend/nodes/readfuncs.c       |    1 +
 src/backend/parser/parse_relation.c |   18 +-
 src/backend/rewrite/rewriteDefine.c |    3 +-
 src/include/catalog/pg_proc.dat     |    8 +
 src/include/commands/createas.h     |    5 +
 src/include/commands/matview.h      |    8 +
 src/include/nodes/parsenodes.h      |    2 +
 15 files changed, 2324 insertions(+), 40 deletions(-)

diff --git a/src/backend/access/transam/xact.c b/src/backend/access/transam/xact.c
index ca6f6d57d3..b67bdc240a 100644
--- a/src/backend/access/transam/xact.c
+++ b/src/backend/access/transam/xact.c
@@ -35,6 +35,7 @@
 #include "catalog/pg_enum.h"
 #include "catalog/storage.h"
 #include "commands/async.h"
+#include "commands/matview.h"
 #include "commands/tablecmds.h"
 #include "commands/trigger.h"
 #include "executor/spi.h"
@@ -2725,6 +2726,7 @@ AbortTransaction(void)
 	AtAbort_Notify();
 	AtEOXact_RelationMap(false, is_parallel_worker);
 	AtAbort_Twophase();
+	AtAbort_IVM();
 
 	/*
 	 * Advertise the fact that we aborted in pg_xact (assuming that we got as
@@ -4969,6 +4971,9 @@ AbortSubTransaction(void)
 	AbortBufferIO();
 	UnlockBuffers();
 
+	/* Clean up hash entries for incremental view maintenance */
+	AtAbort_IVM();
+
 	/* Reset WAL record construction state */
 	XLogResetInsertion();
 
diff --git a/src/backend/commands/createas.c b/src/backend/commands/createas.c
index 0982851715..91888891bf 100644
--- a/src/backend/commands/createas.c
+++ b/src/backend/commands/createas.c
@@ -32,24 +32,41 @@
 #include "access/xact.h"
 #include "access/xlog.h"
 #include "catalog/namespace.h"
+#include "catalog/index.h"
+#include "catalog/pg_constraint.h"
+#include "catalog/pg_inherits.h"
+#include "catalog/pg_trigger.h"
+#include "catalog/pg_type.h"
 #include "catalog/toasting.h"
 #include "commands/createas.h"
+#include "commands/defrem.h"
 #include "commands/matview.h"
 #include "commands/prepare.h"
 #include "commands/tablecmds.h"
+#include "commands/tablespace.h"
+#include "commands/trigger.h"
 #include "commands/view.h"
 #include "miscadmin.h"
+#include "optimizer/clauses.h"
+#include "optimizer/optimizer.h"
 #include "nodes/makefuncs.h"
 #include "nodes/nodeFuncs.h"
+#include "parser/parser.h"
+#include "parser/parsetree.h"
 #include "parser/parse_clause.h"
+#include "parser/parse_func.h"
+#include "parser/parse_type.h"
 #include "rewrite/rewriteHandler.h"
+#include "rewrite/rewriteManip.h"
 #include "storage/smgr.h"
 #include "tcop/tcopprot.h"
 #include "utils/builtins.h"
+#include "utils/fmgroids.h"
 #include "utils/lsyscache.h"
 #include "utils/rel.h"
 #include "utils/rls.h"
 #include "utils/snapmgr.h"
+#include "utils/syscache.h"
 
 typedef struct
 {
@@ -73,6 +90,13 @@ static bool intorel_receive(TupleTableSlot *slot, DestReceiver *self);
 static void intorel_shutdown(DestReceiver *self);
 static void intorel_destroy(DestReceiver *self);
 
+static void CreateIvmTriggersOnBaseTablesRecurse(Query *qry, Node *node, Oid matviewOid,
+									 Relids *relids, bool ex_lock);
+static void CreateIvmTrigger(Oid relOid, Oid viewOid, int16 type, int16 timing, bool ex_lock);
+static void check_ivm_restriction(Node *node);
+static bool check_ivm_restriction_walker(Node *node, void *context);
+static void CreateIndexOnIMMV(Query *query, Relation matviewRel);
+static Bitmapset *get_primary_key_attnos_from_query(Query *qry, List **constraintList);
 
 /*
  * create_ctas_internal
@@ -108,6 +132,8 @@ create_ctas_internal(List *attrList, IntoClause *into)
 	create->oncommit = into->onCommit;
 	create->tablespacename = into->tableSpaceName;
 	create->if_not_exists = false;
+	/* Using Materialized view only */
+	create->ivm = into->ivm;
 	create->accessMethod = into->accessMethod;
 
 	/*
@@ -238,6 +264,7 @@ ExecCreateTableAs(ParseState *pstate, CreateTableAsStmt *stmt,
 	List	   *rewritten;
 	PlannedStmt *plan;
 	QueryDesc  *queryDesc;
+	Query	   *query_immv = NULL;
 
 	/* Check if the relation exists or not */
 	if (CreateTableAsRelExists(stmt))
@@ -282,6 +309,22 @@ ExecCreateTableAs(ParseState *pstate, CreateTableAsStmt *stmt,
 		save_nestlevel = NewGUCNestLevel();
 	}
 
+	if (is_matview && into->ivm)
+	{
+		/* check if the query is supported in IMMV definition */
+		if (contain_mutable_functions((Node *) query))
+			ereport(ERROR,
+					(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+					 errmsg("mutable function is not supported on incrementally maintainable materialized view"),
+					 errhint("functions must be marked IMMUTABLE")));
+
+		check_ivm_restriction((Node *) query);
+
+		/* For IMMV, we need to rewrite matview query */
+		query = rewriteQueryForIMMV(query, into->colNames);
+		query_immv = copyObject(query);
+	}
+
 	if (into->skipData)
 	{
 		/*
@@ -358,11 +401,75 @@ ExecCreateTableAs(ParseState *pstate, CreateTableAsStmt *stmt,
 
 		/* Restore userid and security context */
 		SetUserIdAndSecContext(save_userid, save_sec_context);
+
+		if (into->ivm)
+		{
+			Oid matviewOid = address.objectId;
+			Relation matviewRel = table_open(matviewOid, NoLock);
+
+			/*
+			 * Mark relisivm field, if it's a matview and into->ivm is true.
+			 */
+			SetMatViewIVMState(matviewRel, true);
+
+			/* Create an index on incremental maintainable materialized view, if possible */
+			CreateIndexOnIMMV((Query *) into->viewQuery, matviewRel);
+
+			/* Create triggers on incremental maintainable materialized view */
+			if (!into->skipData)
+			{
+				Assert(query_immv != NULL);
+				CreateIvmTriggersOnBaseTables(query_immv, matviewOid, true);
+			}
+			table_close(matviewRel, NoLock);
+		}
 	}
 
 	return address;
 }
 
+/*
+ * rewriteQueryForIMMV -- rewrite view definition query for IMMV
+ *
+ * count(*) is added for counting distinct tuples in views.
+ */
+Query *
+rewriteQueryForIMMV(Query *query, List *colNames)
+{
+	Query *rewritten;
+
+	TargetEntry *tle;
+	Node *node;
+	ParseState *pstate = make_parsestate(NULL);
+	FuncCall *fn;
+
+	rewritten = copyObject(query);
+	pstate->p_expr_kind = EXPR_KIND_SELECT_TARGET;
+
+	/*
+	 * Convert DISTINCT to GROUP BY and add count(*) for counting distinct
+	 * tuples in views.
+	 */
+	if (rewritten->distinctClause)
+	{
+		rewritten->groupClause = transformDistinctClause(NULL, &rewritten->targetList, rewritten->sortClause, false);
+
+		fn = makeFuncCall(list_make1(makeString("count")), NIL, COERCE_EXPLICIT_CALL, -1);
+		fn->agg_star = true;
+
+		node = ParseFuncOrColumn(pstate, fn->funcname, NIL, NULL, fn, false, -1);
+
+		tle = makeTargetEntry((Expr *) node,
+								list_length(rewritten->targetList) + 1,
+								pstrdup("__ivm_count__"),
+								false);
+		rewritten->targetList = lappend(rewritten->targetList, tle);
+		rewritten->hasAggs = true;
+	}
+
+	return rewritten;
+}
+
 /*
  * GetIntoRelEFlags --- compute executor flags needed for CREATE TABLE AS
  *
@@ -623,3 +730,609 @@ intorel_destroy(DestReceiver *self)
 {
 	pfree(self);
 }
+
+/*
+ * CreateIvmTriggersOnBaseTables -- create IVM triggers on all base tables
+ */
+void
+CreateIvmTriggersOnBaseTables(Query *qry, Oid matviewOid, bool is_create)
+{
+	Relids	relids = NULL;
+	bool	ex_lock = false;
+	Index	first_rtindex = is_create ? 1 : PRS2_NEW_VARNO + 1;
+	RangeTblEntry *rte;
+
+	/* Immediately return if we don't have any base tables. */
+	if (list_length(qry->rtable) < first_rtindex)
+		return;
+
+	/*
+	 * If the view has more than one base tables, we need an exclusive lock
+	 * on the view so that the view would be maintained serially to avoid
+	 * the inconsistency that occurs when two base tables are modified in
+	 * concurrent transactions. However, if the view has only one table,
+	 * we can use a weaker lock.
+	 *
+	 * The type of lock should be determined here, because if we check the
+	 * view definition at maintenance time, we need to acquire a weaker lock,
+	 * and upgrading the lock level after this increases probability of
+	 * deadlock.
+	 */
+
+	rte = list_nth(qry->rtable, first_rtindex - 1);
+	if (list_length(qry->rtable) > first_rtindex ||
+		rte->rtekind != RTE_RELATION)
+		ex_lock = true;
+
+	CreateIvmTriggersOnBaseTablesRecurse(qry, (Node *)qry, matviewOid, &relids, ex_lock);
+
+	bms_free(relids);
+}
+
+static void
+CreateIvmTriggersOnBaseTablesRecurse(Query *qry, Node *node, Oid matviewOid,
+									 Relids *relids, bool ex_lock)
+{
+	if (node == NULL)
+		return;
+
+	/* This can recurse, so check for excessive recursion */
+	check_stack_depth();
+
+	switch (nodeTag(node))
+	{
+		case T_Query:
+			{
+				Query *query = (Query *) node;
+
+				CreateIvmTriggersOnBaseTablesRecurse(qry, (Node *)query->jointree, matviewOid, relids, ex_lock);
+			}
+			break;
+
+		case T_RangeTblRef:
+			{
+				int			rti = ((RangeTblRef *) node)->rtindex;
+				RangeTblEntry *rte = rt_fetch(rti, qry->rtable);
+
+				if (rte->rtekind == RTE_RELATION && !bms_is_member(rte->relid, *relids))
+				{
+					CreateIvmTrigger(rte->relid, matviewOid, TRIGGER_TYPE_INSERT, TRIGGER_TYPE_BEFORE, ex_lock);
+					CreateIvmTrigger(rte->relid, matviewOid, TRIGGER_TYPE_DELETE, TRIGGER_TYPE_BEFORE, ex_lock);
+					CreateIvmTrigger(rte->relid, matviewOid, TRIGGER_TYPE_UPDATE, TRIGGER_TYPE_BEFORE, ex_lock);
+					CreateIvmTrigger(rte->relid, matviewOid, TRIGGER_TYPE_INSERT, TRIGGER_TYPE_AFTER, ex_lock);
+					CreateIvmTrigger(rte->relid, matviewOid, TRIGGER_TYPE_DELETE, TRIGGER_TYPE_AFTER, ex_lock);
+					CreateIvmTrigger(rte->relid, matviewOid, TRIGGER_TYPE_UPDATE, TRIGGER_TYPE_AFTER, ex_lock);
+
+					*relids = bms_add_member(*relids, rte->relid);
+				}
+			}
+			break;
+
+		case T_FromExpr:
+			{
+				FromExpr   *f = (FromExpr *) node;
+				ListCell   *l;
+
+				foreach(l, f->fromlist)
+					CreateIvmTriggersOnBaseTablesRecurse(qry, lfirst(l), matviewOid, relids, ex_lock);
+			}
+			break;
+
+		case T_JoinExpr:
+			{
+				JoinExpr   *j = (JoinExpr *) node;
+
+				CreateIvmTriggersOnBaseTablesRecurse(qry, j->larg, matviewOid, relids, ex_lock);
+				CreateIvmTriggersOnBaseTablesRecurse(qry, j->rarg, matviewOid, relids, ex_lock);
+			}
+			break;
+
+		default:
+			elog(ERROR, "unrecognized node type: %d", (int) nodeTag(node));
+	}
+}
+
+/*
+ * CreateIvmTrigger -- create IVM trigger on a base table
+ */
+static void
+CreateIvmTrigger(Oid relOid, Oid viewOid, int16 type, int16 timing, bool ex_lock)
+{
+	ObjectAddress	refaddr;
+	ObjectAddress	address;
+	CreateTrigStmt *ivm_trigger;
+	List *transitionRels = NIL;
+
+	Assert(timing == TRIGGER_TYPE_BEFORE || timing == TRIGGER_TYPE_AFTER);
+
+	refaddr.classId = RelationRelationId;
+	refaddr.objectId = viewOid;
+	refaddr.objectSubId = 0;
+
+	ivm_trigger = makeNode(CreateTrigStmt);
+	ivm_trigger->relation = NULL;
+	ivm_trigger->row = false;
+
+	ivm_trigger->timing = timing;
+	ivm_trigger->events = type;
+
+	switch (type)
+	{
+		case TRIGGER_TYPE_INSERT:
+			ivm_trigger->trigname = (timing == TRIGGER_TYPE_BEFORE ? "IVM_trigger_ins_before" : "IVM_trigger_ins_after");
+			break;
+		case TRIGGER_TYPE_DELETE:
+			ivm_trigger->trigname = (timing == TRIGGER_TYPE_BEFORE ? "IVM_trigger_del_before" : "IVM_trigger_del_after");
+			break;
+		case TRIGGER_TYPE_UPDATE:
+			ivm_trigger->trigname = (timing == TRIGGER_TYPE_BEFORE ? "IVM_trigger_upd_before" : "IVM_trigger_upd_after");
+			break;
+		default:
+			elog(ERROR, "unsupported trigger type");
+	}
+
+	if (timing == TRIGGER_TYPE_AFTER)
+	{
+		if (type == TRIGGER_TYPE_INSERT || type == TRIGGER_TYPE_UPDATE)
+		{
+			TriggerTransition *n = makeNode(TriggerTransition);
+			n->name = "__ivm_newtable";
+			n->isNew = true;
+			n->isTable = true;
+
+			transitionRels = lappend(transitionRels, n);
+		}
+		if (type == TRIGGER_TYPE_DELETE || type == TRIGGER_TYPE_UPDATE)
+		{
+			TriggerTransition *n = makeNode(TriggerTransition);
+			n->name = "__ivm_oldtable";
+			n->isNew = false;
+			n->isTable = true;
+
+			transitionRels = lappend(transitionRels, n);
+		}
+	}
+
+	ivm_trigger->funcname =
+		(timing == TRIGGER_TYPE_BEFORE ? SystemFuncName("IVM_immediate_before") : SystemFuncName("IVM_immediate_maintenance"));
+
+	ivm_trigger->columns = NIL;
+	ivm_trigger->transitionRels = transitionRels;
+	ivm_trigger->whenClause = NULL;
+	ivm_trigger->isconstraint = false;
+	ivm_trigger->deferrable = false;
+	ivm_trigger->initdeferred = false;
+	ivm_trigger->constrrel = NULL;
+	ivm_trigger->args = list_make2(
+		makeString(DatumGetPointer(DirectFunctionCall1(oidout, ObjectIdGetDatum(viewOid)))),
+		makeString(DatumGetPointer(DirectFunctionCall1(boolout, BoolGetDatum(ex_lock))))
+		);
+
+	address = CreateTrigger(ivm_trigger, NULL, relOid, InvalidOid, InvalidOid,
+						 InvalidOid, InvalidOid, InvalidOid, NULL, true, false);
+
+	recordDependencyOn(&address, &refaddr, DEPENDENCY_IMMV);
+
+	/* Make changes-so-far visible */
+	CommandCounterIncrement();
+}
+
+/*
+ * check_ivm_restriction --- look for specify nodes in the query tree
+ */
+static void
+check_ivm_restriction(Node *node)
+{
+	check_ivm_restriction_walker(node, NULL);
+}
+
+static bool
+check_ivm_restriction_walker(Node *node, void *context)
+{
+	if (node == NULL)
+		return false;
+
+	/*
+	 * We currently don't support Sub-Query.
+	 */
+	if (IsA(node, SubPlan) || IsA(node, SubLink))
+		ereport(ERROR,
+				(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+				 errmsg("subquery is not supported on incrementally maintainable materialized view")));
+
+	/* This can recurse, so check for excessive recursion */
+	check_stack_depth();
+
+	switch (nodeTag(node))
+	{
+		case T_Query:
+			{
+				Query *qry = (Query *)node;
+				ListCell   *lc;
+				List       *vars;
+
+				/* if contained CTE, return error */
+				if (qry->cteList != NIL)
+					ereport(ERROR,
+							(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+							 errmsg("CTE is not supported on incrementally maintainable materialized view")));
+				if (qry->havingQual != NULL)
+					ereport(ERROR,
+							(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+							 errmsg(" HAVING clause is not supported on incrementally maintainable materialized view")));
+				if (qry->sortClause != NIL)	/* There is a possibility that we don't need to return an error */
+					ereport(ERROR,
+							(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+							 errmsg("ORDER BY clause is not supported on incrementally maintainable materialized view")));
+				if (qry->limitOffset != NULL || qry->limitCount != NULL)
+					ereport(ERROR,
+							(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+							 errmsg("LIMIT/OFFSET clause is not supported on incrementally maintainable materialized view")));
+				if (qry->hasDistinctOn)
+					ereport(ERROR,
+							(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+							 errmsg("DISTINCT ON is not supported on incrementally maintainable materialized view")));
+				if (qry->hasWindowFuncs)
+					ereport(ERROR,
+							(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+							 errmsg("window functions are not supported on incrementally maintainable materialized view")));
+				if (qry->groupingSets != NIL)
+					ereport(ERROR,
+							(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+							 errmsg("GROUPING SETS, ROLLUP, or CUBE clauses is not supported on incrementally maintainable materialized view")));
+				if (qry->setOperations != NULL)
+					ereport(ERROR,
+							(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+							 errmsg("UNION/INTERSECT/EXCEPT statements are not supported on incrementally maintainable materialized view")));
+				if (list_length(qry->targetList) == 0)
+					ereport(ERROR,
+							(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+							 errmsg("empty target list is not supported on incrementally maintainable materialized view")));
+				if (qry->rowMarks != NIL)
+					ereport(ERROR,
+							(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+							 errmsg("FOR UPDATE/SHARE clause is not supported on incrementally maintainable materialized view")));
+
+				/* system column restrictions */
+				vars = pull_vars_of_level((Node *) qry, 0);
+				foreach(lc, vars)
+				{
+					if (IsA(lfirst(lc), Var))
+					{
+						Var *var = (Var *) lfirst(lc);
+						/* if system column, return error */
+						if (var->varattno < 0)
+							ereport(ERROR,
+									(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+									 errmsg("system column is not supported on incrementally maintainable materialized view")));
+					}
+				}
+
+				/* restrictions for rtable */
+				foreach(lc, qry->rtable)
+				{
+					RangeTblEntry *rte = (RangeTblEntry *) lfirst(lc);
+
+					if (rte->subquery)
+						ereport(ERROR,
+								(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+								 errmsg("subquery is not supported on incrementally maintainable materialized view")));
+
+					if (rte->tablesample != NULL)
+						ereport(ERROR,
+								(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+								 errmsg("TABLESAMPLE clause is not supported on incrementally maintainable materialized view")));
+
+					if (rte->relkind == RELKIND_PARTITIONED_TABLE)
+						ereport(ERROR,
+								(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+								 errmsg("partitioned table is not supported on incrementally maintainable materialized view")));
+
+					if (rte->relkind == RELKIND_RELATION && has_superclass(rte->relid))
+						ereport(ERROR,
+								(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+								 errmsg("partitions is not supported on incrementally maintainable materialized view")));
+
+					if (rte->relkind == RELKIND_RELATION && find_inheritance_children(rte->relid, NoLock) != NIL)
+						ereport(ERROR,
+								(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+								 errmsg("inheritance parent is not supported on incrementally maintainable materialized view")));
+
+					if (rte->relkind == RELKIND_FOREIGN_TABLE)
+						ereport(ERROR,
+								(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+								 errmsg("foreign table is not supported on incrementally maintainable materialized view")));
+
+					if (rte->relkind == RELKIND_VIEW ||
+						rte->relkind == RELKIND_MATVIEW)
+						ereport(ERROR,
+								(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+								 errmsg("VIEW or MATERIALIZED VIEW is not supported on incrementally maintainable materialized view")));
+
+					if (rte->rtekind == RTE_VALUES)
+						ereport(ERROR,
+								(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+								 errmsg("VALUES is not supported on incrementally maintainable materialized view")));
+
+				}
+
+				query_tree_walker(qry, check_ivm_restriction_walker, NULL, QTW_IGNORE_RANGE_TABLE);
+
+				break;
+			}
+		case T_TargetEntry:
+			{
+				TargetEntry *tle = (TargetEntry *)node;
+				if (isIvmName(tle->resname))
+						ereport(ERROR,
+								(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+								 errmsg("column name %s is not supported on incrementally maintainable materialized view", tle->resname)));
+
+				expression_tree_walker(node, check_ivm_restriction_walker, NULL);
+				break;
+			}
+		case T_JoinExpr:
+			{
+				JoinExpr *joinexpr = (JoinExpr *)node;
+
+				if (joinexpr->jointype > JOIN_INNER)
+						ereport(ERROR,
+								(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+								 errmsg("OUTER JOIN is not supported on incrementally maintainable materialized view")));
+
+				expression_tree_walker(node, check_ivm_restriction_walker, NULL);
+			}
+			break;
+			expression_tree_walker(node, check_ivm_restriction_walker, NULL);
+			break;
+	}
+	return false;
+}
+
+/*
+ * CreateIndexOnIMMV
+ *
+ * Create a unique index on incremental maintainable materialized view.
+ * If the view definition query has a GROUP BY clause, the index is created
+ * on the columns of GROUP BY expressions. Otherwise, if the view contains
+ * all primary key attritubes of its base tables in the target list, the index
+ * is created on these attritubes. In other cases, no index is created.
+ */
+static void
+CreateIndexOnIMMV(Query *query, Relation matviewRel)
+{
+	Query *qry = (Query *) copyObject(query);
+	ListCell *lc;
+	IndexStmt  *index;
+	ObjectAddress address;
+	List *constraintList = NIL;
+	char		idxname[NAMEDATALEN];
+
+	snprintf(idxname, sizeof(idxname), "%s_index", RelationGetRelationName(matviewRel));
+
+	index = makeNode(IndexStmt);
+
+	index->unique = true;
+	index->primary = false;
+	index->isconstraint = false;
+	index->deferrable = false;
+	index->initdeferred = false;
+	index->idxname = idxname;
+	index->relation =
+		makeRangeVar(get_namespace_name(RelationGetNamespace(matviewRel)),
+					 pstrdup(RelationGetRelationName(matviewRel)),
+					 -1);
+	index->accessMethod = DEFAULT_INDEX_TYPE;
+	index->options = NIL;
+	index->tableSpace = get_tablespace_name(matviewRel->rd_rel->reltablespace);
+	index->whereClause = NULL;
+	index->indexParams = NIL;
+	index->indexIncludingParams = NIL;
+	index->excludeOpNames = NIL;
+	index->idxcomment = NULL;
+	index->indexOid = InvalidOid;
+	index->oldNode = InvalidOid;
+	index->oldCreateSubid = InvalidSubTransactionId;
+	index->oldFirstRelfilenodeSubid = InvalidSubTransactionId;
+	index->transformed = true;
+	index->concurrent = false;
+	index->if_not_exists = false;
+
+	if (qry->distinctClause)
+	{
+		/* create unique constraint on all columns */
+		foreach(lc, qry->targetList)
+		{
+			TargetEntry *tle = (TargetEntry *) lfirst(lc);
+			Form_pg_attribute attr = TupleDescAttr(matviewRel->rd_att, tle->resno - 1);
+			IndexElem  *iparam;
+
+			iparam = makeNode(IndexElem);
+			iparam->name = pstrdup(NameStr(attr->attname));
+			iparam->expr = NULL;
+			iparam->indexcolname = NULL;
+			iparam->collation = NIL;
+			iparam->opclass = NIL;
+			iparam->opclassopts = NIL;
+			iparam->ordering = SORTBY_DEFAULT;
+			iparam->nulls_ordering = SORTBY_NULLS_DEFAULT;
+			index->indexParams = lappend(index->indexParams, iparam);
+		}
+	}
+	else
+	{
+		Bitmapset *key_attnos;
+
+		/* create index on the base tables' primary key columns */
+		key_attnos = get_primary_key_attnos_from_query(qry, &constraintList);
+		if (key_attnos)
+		{
+			foreach(lc, qry->targetList)
+			{
+				TargetEntry *tle = (TargetEntry *) lfirst(lc);
+				Form_pg_attribute attr = TupleDescAttr(matviewRel->rd_att, tle->resno - 1);
+
+				if (bms_is_member(tle->resno - FirstLowInvalidHeapAttributeNumber, key_attnos))
+				{
+					IndexElem  *iparam;
+
+					iparam = makeNode(IndexElem);
+					iparam->name = pstrdup(NameStr(attr->attname));
+					iparam->expr = NULL;
+					iparam->indexcolname = NULL;
+					iparam->collation = NIL;
+					iparam->opclass = NIL;
+					iparam->opclassopts = NIL;
+					iparam->ordering = SORTBY_DEFAULT;
+					iparam->nulls_ordering = SORTBY_NULLS_DEFAULT;
+					index->indexParams = lappend(index->indexParams, iparam);
+				}
+			}
+
+		}
+		else
+		{
+			/* create no index, just notice that an appropriate index is necessary for efficient IVM */
+			ereport(NOTICE,
+					(errmsg("could not create an index on materialized view \"%s\" automatically",
+							RelationGetRelationName(matviewRel)),
+					 errdetail("This target list does not have all the primary key columns, "
+							   "or this view does not contain DISTINCT clause."),
+					 errhint("Create an index on the materialized view for efficient incremental maintenance.")));
+			return;
+		}
+	}
+
+	address = DefineIndex(RelationGetRelid(matviewRel),
+						  index,
+						  InvalidOid,
+						  InvalidOid,
+						  InvalidOid,
+						  false, true, false, false, true);
+
+	ereport(NOTICE,
+			(errmsg("created index \"%s\" on materialized view \"%s\"",
+					idxname, RelationGetRelationName(matviewRel))));
+
+
+	/*
+	 * Make dependencies so that the index is dropped if any base tables's
+	 * primary key is dropped.
+	 */
+	foreach(lc, constraintList)
+	{
+		Oid constraintOid = lfirst_oid(lc);
+		ObjectAddress	refaddr;
+
+		refaddr.classId = ConstraintRelationId;
+		refaddr.objectId = constraintOid;
+		refaddr.objectSubId = 0;
+
+		recordDependencyOn(&address, &refaddr, DEPENDENCY_NORMAL);
+	}
+}
+
+
+/*
+ * get_primary_key_attnos_from_query
+ *
+ * Identify the columns in base tables' primary keys in the target list.
+ *
+ * Returns a Bitmapset of the column attnos of the primary key's columns of
+ * tables that used in the query.  The attnos are offset by
+ * FirstLowInvalidHeapAttributeNumber as same as get_primary_key_attnos.
+ *
+ * If any table has no primary key or any primary key's columns is not in
+ * the target list, return NULL.  We also return NULL if any pkey constraint
+ * is deferrable.
+ *
+ * constraintList is set to a list of the OIDs of the pkey constraints.
+ */
+static Bitmapset *
+get_primary_key_attnos_from_query(Query *query, List **constraintList)
+{
+	List *key_attnos_list = NIL;
+	ListCell *lc;
+	int i;
+	Bitmapset *keys = NULL;
+	Relids	rels_in_from;
+	PlannerInfo root;
+
+
+	/*
+	 * Collect primary key attributes from all tables used in query. The key attributes
+	 * sets for each table are stored in key_attnos_list in order by RTE index.
+	 */
+	i = 1;
+	foreach(lc, query->rtable)
+	{
+		RangeTblEntry *r = (RangeTblEntry*) lfirst(lc);
+		Bitmapset *key_attnos;
+		bool	has_pkey = true;
+
+		/* for tables, call get_primary_key_attnos */
+		if (r->rtekind == RTE_RELATION)
+		{
+			Oid constraintOid;
+			key_attnos = get_primary_key_attnos(r->relid, false, &constraintOid);
+			*constraintList = lappend_oid(*constraintList, constraintOid);
+			has_pkey = (key_attnos != NULL);
+		}
+		/* for other RTEs, store NULL into key_attnos_list */
+		else
+			key_attnos = NULL;
+
+		/*
+		 * If any table or subquery has no primary key or its pkey constraint is deferrable,
+		 * we cannot get key attributes for this query, so return NULL.
+		 */
+		if (!has_pkey)
+			return NULL;
+
+		key_attnos_list = lappend(key_attnos_list, key_attnos);
+	}
+
+	/* Collect key attributes appearing in the target list */
+	i = 1;
+	foreach(lc, query->targetList)
+	{
+		TargetEntry *tle = (TargetEntry *) flatten_join_alias_vars(query, lfirst(lc));
+
+		if (IsA(tle->expr, Var))
+		{
+			Var *var = (Var*) tle->expr;
+			Bitmapset *attnos = list_nth(key_attnos_list, var->varno - 1);
+
+			/* check if this attribute is from a base table's primary key */
+			if (bms_is_member(var->varattno - FirstLowInvalidHeapAttributeNumber, attnos))
+			{
+				/*
+				 * Remove found key attributes from key_attnos_list, and add this
+				 * to the result list.
+				 */
+				bms_del_member(attnos, var->varattno - FirstLowInvalidHeapAttributeNumber);
+				keys = bms_add_member(keys, i - FirstLowInvalidHeapAttributeNumber);
+			}
+		}
+		i++;
+	}
+
+	/* Collect relations appearing in the FROM clause */
+	rels_in_from = pull_varnos_of_level(&root, (Node *)query->jointree, 0);
+
+	/*
+	 * Check if all key attributes of relations in FROM are appearing in the target
+	 * list.  If an attribute remains in key_attnos_list in spite of the table is used
+	 * in FROM clause, the target is missing this key attribute, so we return NULL.
+	 */
+	i = 1;
+	foreach(lc, key_attnos_list)
+	{
+		Bitmapset *bms = (Bitmapset *)lfirst(lc);
+		if (!bms_is_empty(bms) && bms_is_member(i, rels_in_from))
+			return NULL;
+		i++;
+	}
+
+	return keys;
+}
diff --git a/src/backend/commands/indexcmds.c b/src/backend/commands/indexcmds.c
index c14ca27c5e..5581c21298 100644
--- a/src/backend/commands/indexcmds.c
+++ b/src/backend/commands/indexcmds.c
@@ -36,6 +36,7 @@
 #include "commands/dbcommands.h"
 #include "commands/defrem.h"
 #include "commands/event_trigger.h"
+#include "commands/matview.h"
 #include "commands/progress.h"
 #include "commands/tablecmds.h"
 #include "commands/tablespace.h"
@@ -1054,6 +1055,45 @@ DefineIndex(Oid relationId,
 	safe_index = indexInfo->ii_Expressions == NIL &&
 		indexInfo->ii_Predicate == NIL;
 
+	/*
+	 * We disallow unique indexes on IVM columns of IMMVs.
+	 */
+	if (RelationIsIVM(rel) && stmt->unique)
+	{
+		for (i = 0; i < indexInfo->ii_NumIndexKeyAttrs; i++)
+		{
+			AttrNumber	attno = indexInfo->ii_IndexAttrNumbers[i];
+			if (attno > 0)
+			{
+				char *name = NameStr(TupleDescAttr(rel->rd_att, attno - 1)->attname);
+				if (name && isIvmName(name))
+					ereport(ERROR,
+							(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+							 errmsg("unique index creation on IVM columns is not supported")));
+			}
+		}
+
+		if (indexInfo->ii_Expressions)
+		{
+			Bitmapset  *indexattrs = NULL;
+			int			varno = -1;
+
+			pull_varattnos((Node *) indexInfo->ii_Expressions, 1, &indexattrs);
+
+			while ((varno = bms_next_member(indexattrs, varno)) >= 0)
+			{
+				int attno = varno + FirstLowInvalidHeapAttributeNumber;
+				char *name = NameStr(TupleDescAttr(rel->rd_att, attno - 1)->attname);
+				if (name && isIvmName(name))
+					ereport(ERROR,
+							(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+							 errmsg("unique index creation on IVM columns is not supported")));
+			}
+
+		}
+	}
+
+
 	/*
 	 * Report index creation if appropriate (delay this till after most of the
 	 * error checks)
diff --git a/src/backend/commands/matview.c b/src/backend/commands/matview.c
index fbbf769a87..a27d23434d 100644
--- a/src/backend/commands/matview.c
+++ b/src/backend/commands/matview.c
@@ -25,26 +25,47 @@
 #include "catalog/indexing.h"
 #include "catalog/namespace.h"
 #include "catalog/pg_am.h"
+#include "catalog/pg_collation.h"
+#include "catalog/pg_depend.h"
+#include "catalog/pg_type.h"
 #include "catalog/pg_opclass.h"
 #include "catalog/pg_operator.h"
 #include "commands/cluster.h"
+#include "commands/defrem.h"
 #include "commands/matview.h"
 #include "commands/tablecmds.h"
 #include "commands/tablespace.h"
+#include "commands/createas.h"
 #include "executor/executor.h"
 #include "executor/spi.h"
+#include "executor/tstoreReceiver.h"
 #include "miscadmin.h"
+#include "nodes/makefuncs.h"
+#include "nodes/nodeFuncs.h"
+#include "optimizer/optimizer.h"
+#include "parser/analyze.h"
+#include "parser/parser.h"
+#include "parser/parsetree.h"
+#include "parser/parse_clause.h"
+#include "parser/parse_coerce.h"
+#include "parser/parse_collate.h"
+#include "parser/parse_func.h"
 #include "parser/parse_relation.h"
+#include "parser/parse_type.h"
 #include "pgstat.h"
 #include "rewrite/rewriteHandler.h"
+#include "rewrite/rewriteManip.h"
+#include "rewrite/rowsecurity.h"
 #include "storage/lmgr.h"
 #include "storage/smgr.h"
 #include "tcop/tcopprot.h"
 #include "utils/builtins.h"
+#include "utils/fmgroids.h"
 #include "utils/lsyscache.h"
 #include "utils/rel.h"
 #include "utils/snapmgr.h"
 #include "utils/syscache.h"
+#include "utils/typcache.h"
 
 
 typedef struct
@@ -58,6 +79,50 @@ typedef struct
 	BulkInsertState bistate;	/* bulk insert state */
 } DR_transientrel;
 
+#define MV_INIT_QUERYHASHSIZE	16
+
+/*
+ * MV_TriggerHashEntry
+ *
+ * Hash entry for base tables on which IVM trigger is invoked
+ */
+typedef struct MV_TriggerHashEntry
+{
+	Oid	matview_id;			/* OID of the materialized view */
+	int	before_trig_count;	/* count of before triggers invoked */
+	int	after_trig_count;	/* count of after triggers invoked */
+
+	TransactionId	xid;	/* Transaction id before the first table is modified*/
+	CommandId		cid;	/* Command id before the first table is modified */
+
+	List   *tables;		/* List of MV_TriggerTable */
+	bool	has_old;	/* tuples are deleted from any table? */
+	bool	has_new;	/* tuples are inserted into any table? */
+} MV_TriggerHashEntry;
+
+/*
+ * MV_TriggerTable
+ *
+ * IVM related data for tables on which the trigger is invoked.
+ */
+typedef struct MV_TriggerTable
+{
+	Oid		table_id;			/* OID of the modified table */
+	List   *old_tuplestores;	/* tuplestores for deleted tuples */
+	List   *new_tuplestores;	/* tuplestores for inserted tuples */
+	List   *old_rtes;			/* RTEs of ENRs for old_tuplestores*/
+	List   *new_rtes;			/* RTEs of ENRs for new_tuplestores */
+
+	List   *rte_indexes;		/* List of RTE index of the modified table */
+	RangeTblEntry *original_rte;	/* the original RTE saved before rewriting query */
+} MV_TriggerTable;
+
+static HTAB *mv_trigger_info = NULL;
+
+/* ENR name for materialized view delta */
+#define NEW_DELTA_ENRNAME "new_delta"
+#define OLD_DELTA_ENRNAME "old_delta"
+
 static int	matview_maintenance_depth = 0;
 
 static void transientrel_startup(DestReceiver *self, int operation, TupleDesc typeinfo);
@@ -65,7 +130,9 @@ static bool transientrel_receive(TupleTableSlot *slot, DestReceiver *self);
 static void transientrel_shutdown(DestReceiver *self);
 static void transientrel_destroy(DestReceiver *self);
 static uint64 refresh_matview_datafill(DestReceiver *dest, Query *query,
-									   const char *queryString);
+						 QueryEnvironment *queryEnv,
+						 TupleDesc *resultTupleDesc,
+						 const char *queryString);
 static char *make_temptable_name_n(char *tempname, int n);
 static void refresh_by_match_merge(Oid matviewOid, Oid tempOid, Oid relowner,
 								   int save_sec_context);
@@ -73,6 +140,45 @@ static void refresh_by_heap_swap(Oid matviewOid, Oid OIDNewHeap, char relpersist
 static bool is_usable_unique_index(Relation indexRel);
 static void OpenMatViewIncrementalMaintenance(void);
 static void CloseMatViewIncrementalMaintenance(void);
+static Query *get_matview_query(Relation matviewRel);
+
+static Query *rewrite_query_for_preupdate_state(Query *query, List *tables,
+								  TransactionId xid, CommandId cid,
+								  ParseState *pstate);
+static void register_delta_ENRs(ParseState *pstate, Query *query, List *tables);
+static char *make_delta_enr_name(const char *prefix, Oid relid, int count);
+static RangeTblEntry *get_prestate_rte(RangeTblEntry *rte, MV_TriggerTable *table,
+				 TransactionId xid, CommandId cid,
+				 QueryEnvironment *queryEnv);
+static RangeTblEntry *union_ENRs(RangeTblEntry *rte, Oid relid, List *enr_rtes, const char *prefix,
+		   QueryEnvironment *queryEnv);
+static Query *rewrite_query_for_distinct(Query *query, ParseState *pstate);
+
+static void calc_delta(MV_TriggerTable *table, int rte_index, Query *query,
+			DestReceiver *dest_old, DestReceiver *dest_new,
+			TupleDesc *tupdesc_old, TupleDesc *tupdesc_new,
+			QueryEnvironment *queryEnv);
+static Query *rewrite_query_for_postupdate_state(Query *query, MV_TriggerTable *table, int rte_index);
+
+static void apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *new_tuplestores,
+			TupleDesc tupdesc_old, TupleDesc tupdesc_new,
+			Query *query, bool use_count, char *count_colname);
+static void apply_old_delta(const char *matviewname, const char *deltaname_old,
+				List *keys);
+static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old,
+				List *keys, const char *count_colname);
+static void apply_new_delta(const char *matviewname, const char *deltaname_new,
+				StringInfo target_list);
+static void apply_new_delta_with_count(const char *matviewname, const char* deltaname_new,
+				List *keys, StringInfo target_list, const char* count_colname);
+static char *get_matching_condition_string(List *keys);
+static void generate_equal(StringInfo querybuf, Oid opttype,
+			   const char *leftop, const char *rightop);
+
+static void mv_InitHashTables(void);
+static void clean_up_IVM_hash_entry(MV_TriggerHashEntry *entry);
+
+static List *get_securityQuals(Oid relId, int rt_index, Query *query);
 
 /*
  * SetMatViewPopulatedState
@@ -114,6 +220,46 @@ SetMatViewPopulatedState(Relation relation, bool newstate)
 	CommandCounterIncrement();
 }
 
+/*
+ * SetMatViewIVMState
+ *		Mark a materialized view as IVM, or not.
+ *
+ * NOTE: caller must be holding an appropriate lock on the relation.
+ */
+void
+SetMatViewIVMState(Relation relation, bool newstate)
+{
+	Relation	pgrel;
+	HeapTuple	tuple;
+
+	Assert(relation->rd_rel->relkind == RELKIND_MATVIEW);
+
+	/*
+	 * Update relation's pg_class entry.  Crucial side-effect: other backends
+	 * (and this one too!) are sent SI message to make them rebuild relcache
+	 * entries.
+	 */
+	pgrel = table_open(RelationRelationId, RowExclusiveLock);
+	tuple = SearchSysCacheCopy1(RELOID,
+								ObjectIdGetDatum(RelationGetRelid(relation)));
+	if (!HeapTupleIsValid(tuple))
+		elog(ERROR, "cache lookup failed for relation %u",
+			 RelationGetRelid(relation));
+
+	((Form_pg_class) GETSTRUCT(tuple))->relisivm = newstate;
+
+	CatalogTupleUpdate(pgrel, &tuple->t_self, tuple);
+
+	heap_freetuple(tuple);
+	table_close(pgrel, RowExclusiveLock);
+
+	/*
+	 * Advance command counter to make the updated pg_class row locally
+	 * visible.
+	 */
+	CommandCounterIncrement();
+}
+
 /*
  * ExecRefreshMatView -- execute a REFRESH MATERIALIZED VIEW command
  *
@@ -140,8 +286,6 @@ ExecRefreshMatView(RefreshMatViewStmt *stmt, const char *queryString,
 {
 	Oid			matviewOid;
 	Relation	matviewRel;
-	RewriteRule *rule;
-	List	   *actions;
 	Query	   *dataQuery;
 	Oid			tableSpace;
 	Oid			relowner;
@@ -155,6 +299,7 @@ ExecRefreshMatView(RefreshMatViewStmt *stmt, const char *queryString,
 	int			save_sec_context;
 	int			save_nestlevel;
 	ObjectAddress address;
+	bool oldPopulated;
 
 	/* Determine strength of lock needed. */
 	concurrent = stmt->concurrent;
@@ -167,6 +312,7 @@ ExecRefreshMatView(RefreshMatViewStmt *stmt, const char *queryString,
 										  lockmode, 0,
 										  RangeVarCallbackOwnsTable, NULL);
 	matviewRel = table_open(matviewOid, NoLock);
+	oldPopulated = RelationIsPopulated(matviewRel);
 
 	/* Make sure it is a materialized view. */
 	if (matviewRel->rd_rel->relkind != RELKIND_MATVIEW)
@@ -188,32 +334,12 @@ ExecRefreshMatView(RefreshMatViewStmt *stmt, const char *queryString,
 				 errmsg("%s and %s options cannot be used together",
 						"CONCURRENTLY", "WITH NO DATA")));
 
-	/*
-	 * Check that everything is correct for a refresh. Problems at this point
-	 * are internal errors, so elog is sufficient.
-	 */
-	if (matviewRel->rd_rel->relhasrules == false ||
-		matviewRel->rd_rules->numLocks < 1)
-		elog(ERROR,
-			 "materialized view \"%s\" is missing rewrite information",
-			 RelationGetRelationName(matviewRel));
-
-	if (matviewRel->rd_rules->numLocks > 1)
-		elog(ERROR,
-			 "materialized view \"%s\" has too many rules",
-			 RelationGetRelationName(matviewRel));
 
-	rule = matviewRel->rd_rules->rules[0];
-	if (rule->event != CMD_SELECT || !(rule->isInstead))
-		elog(ERROR,
-			 "the rule for materialized view \"%s\" is not a SELECT INSTEAD OF rule",
-			 RelationGetRelationName(matviewRel));
+	dataQuery = get_matview_query(matviewRel);
 
-	actions = rule->actions;
-	if (list_length(actions) != 1)
-		elog(ERROR,
-			 "the rule for materialized view \"%s\" is not a single action",
-			 RelationGetRelationName(matviewRel));
+	/* For IMMV, we need to rewrite matview query */
+	if (!stmt->skipData && RelationIsIVM(matviewRel))
+		dataQuery = rewriteQueryForIMMV(dataQuery,NIL);
 
 	/*
 	 * Check that there is a unique index with no WHERE clause on one or more
@@ -248,12 +374,6 @@ ExecRefreshMatView(RefreshMatViewStmt *stmt, const char *queryString,
 					 errhint("Create a unique index with no WHERE clause on one or more columns of the materialized view.")));
 	}
 
-	/*
-	 * The stored query was rewritten at the time of the MV definition, but
-	 * has not been scribbled on by the planner.
-	 */
-	dataQuery = linitial_node(Query, actions);
-
 	/*
 	 * Check for active uses of the relation in the current transaction, such
 	 * as open scans.
@@ -294,6 +414,52 @@ ExecRefreshMatView(RefreshMatViewStmt *stmt, const char *queryString,
 		relpersistence = matviewRel->rd_rel->relpersistence;
 	}
 
+	/* delete immv triggers */
+	if (RelationIsIVM(matviewRel) && stmt->skipData )
+	{
+		/* use deleted trigger */
+		Relation	depRel;
+		ScanKeyData key;
+		SysScanDesc scan;
+		HeapTuple	tup;
+		ObjectAddresses *immv_triggers;
+
+		immv_triggers = new_object_addresses();
+
+		/*
+		 * We save some cycles by opening pg_depend just once and passing the
+		 * Relation pointer down to all the recursive deletion steps.
+		 */
+		depRel = table_open(DependRelationId, RowExclusiveLock);
+
+		ScanKeyInit(&key,
+					Anum_pg_depend_refobjid,
+					BTEqualStrategyNumber, F_OIDEQ,
+					ObjectIdGetDatum(matviewOid));
+
+		scan = systable_beginscan(depRel, DependReferenceIndexId, true,
+								  NULL, 1, &key);
+		while ((tup = systable_getnext(scan)) != NULL)
+		{
+			ObjectAddress obj;
+			Form_pg_depend foundDep = (Form_pg_depend) GETSTRUCT(tup);
+
+			if (foundDep->deptype == DEPENDENCY_IMMV)
+			{
+				obj.classId = foundDep->classid;
+				obj.objectId = foundDep->objid;
+				obj.objectSubId = foundDep->refobjsubid;
+				add_exact_object_address(&obj, immv_triggers);
+			}
+		}
+		systable_endscan(scan);
+
+		performMultipleDeletions(immv_triggers, DROP_RESTRICT, PERFORM_DELETION_INTERNAL);
+
+		table_close(depRel, RowExclusiveLock);
+		free_object_addresses(immv_triggers);
+	}
+
 	/*
 	 * Create the transient table that will receive the regenerated data. Lock
 	 * it against access by any other process until commit (by which time it
@@ -313,7 +479,7 @@ ExecRefreshMatView(RefreshMatViewStmt *stmt, const char *queryString,
 
 	/* Generate the data, if wanted. */
 	if (!stmt->skipData)
-		processed = refresh_matview_datafill(dest, dataQuery, queryString);
+		processed = refresh_matview_datafill(dest, dataQuery, NULL, NULL, queryString);
 
 	/* Make the matview match the newly generated data. */
 	if (concurrent)
@@ -348,6 +514,9 @@ ExecRefreshMatView(RefreshMatViewStmt *stmt, const char *queryString,
 			pgstat_count_heap_insert(matviewRel, processed);
 	}
 
+	if (!stmt->skipData && RelationIsIVM(matviewRel) && !oldPopulated)
+		CreateIvmTriggersOnBaseTables(dataQuery, matviewOid, false);
+
 	table_close(matviewRel, NoLock);
 
 	/* Roll back any GUC changes */
@@ -382,6 +551,8 @@ ExecRefreshMatView(RefreshMatViewStmt *stmt, const char *queryString,
  */
 static uint64
 refresh_matview_datafill(DestReceiver *dest, Query *query,
+						 QueryEnvironment *queryEnv,
+						 TupleDesc *resultTupleDesc,
 						 const char *queryString)
 {
 	List	   *rewritten;
@@ -418,7 +589,7 @@ refresh_matview_datafill(DestReceiver *dest, Query *query,
 	/* Create a QueryDesc, redirecting output to our tuple receiver */
 	queryDesc = CreateQueryDesc(plan, queryString,
 								GetActiveSnapshot(), InvalidSnapshot,
-								dest, NULL, NULL, 0);
+								dest, NULL, queryEnv ? queryEnv: NULL, 0);
 
 	/* call ExecutorStart to prepare the plan for execution */
 	ExecutorStart(queryDesc, 0);
@@ -428,6 +599,9 @@ refresh_matview_datafill(DestReceiver *dest, Query *query,
 
 	processed = queryDesc->estate->es_processed;
 
+	if (resultTupleDesc)
+		*resultTupleDesc = CreateTupleDescCopy(queryDesc->tupDesc);
+
 	/* and clean up */
 	ExecutorFinish(queryDesc);
 	ExecutorEnd(queryDesc);
@@ -942,3 +1116,1308 @@ CloseMatViewIncrementalMaintenance(void)
 	matview_maintenance_depth--;
 	Assert(matview_maintenance_depth >= 0);
 }
+
+/*
+ * get_matview_query - get the Query from a matview's _RETURN rule.
+ */
+static Query *
+get_matview_query(Relation matviewRel)
+{
+	RewriteRule *rule;
+	List * actions;
+
+	/*
+	 * Check that everything is correct for a refresh. Problems at this point
+	 * are internal errors, so elog is sufficient.
+	 */
+	if (matviewRel->rd_rel->relhasrules == false ||
+		matviewRel->rd_rules->numLocks < 1)
+		elog(ERROR,
+			 "materialized view \"%s\" is missing rewrite information",
+			 RelationGetRelationName(matviewRel));
+
+	if (matviewRel->rd_rules->numLocks > 1)
+		elog(ERROR,
+			 "materialized view \"%s\" has too many rules",
+			 RelationGetRelationName(matviewRel));
+
+	rule = matviewRel->rd_rules->rules[0];
+	if (rule->event != CMD_SELECT || !(rule->isInstead))
+		elog(ERROR,
+			 "the rule for materialized view \"%s\" is not a SELECT INSTEAD OF rule",
+			 RelationGetRelationName(matviewRel));
+
+	actions = rule->actions;
+	if (list_length(actions) != 1)
+		elog(ERROR,
+			 "the rule for materialized view \"%s\" is not a single action",
+			 RelationGetRelationName(matviewRel));
+
+	/*
+	 * The stored query was rewritten at the time of the MV definition, but
+	 * has not been scribbled on by the planner.
+	 */
+	return linitial_node(Query, actions);
+}
+
+
+/* ----------------------------------------------------
+ *		Incremental View Maintenance routines
+ * ---------------------------------------------------
+ */
+
+/*
+ * IVM_immediate_before
+ *
+ * IVM trigger function invoked before base table is modified. If this is
+ * invoked firstly in the same statement, we save the transaction id and the
+ * command id at that time.
+ */
+Datum
+IVM_immediate_before(PG_FUNCTION_ARGS)
+{
+	TriggerData *trigdata = (TriggerData *) fcinfo->context;
+	char	   *matviewOid_text = trigdata->tg_trigger->tgargs[0];
+	char	   *ex_lock_text = trigdata->tg_trigger->tgargs[1];
+	Oid			matviewOid;
+	MV_TriggerHashEntry *entry;
+	bool	found;
+	bool	ex_lock;
+
+	matviewOid = DatumGetObjectId(DirectFunctionCall1(oidin, CStringGetDatum(matviewOid_text)));
+	ex_lock = DatumGetBool(DirectFunctionCall1(boolin, CStringGetDatum(ex_lock_text)));
+
+	/* If the view has more than one tables, we have to use an exclusive lock. */
+	if (ex_lock)
+	{
+		/*
+		 * Wait for concurrent transactions which update this materialized view at
+		 * READ COMMITED. This is needed to see changes committed in other
+		 * transactions. No wait and raise an error at REPEATABLE READ or
+		 * SERIALIZABLE to prevent update anomalies of matviews.
+		 * XXX: dead-lock is possible here.
+		 */
+		if (!IsolationUsesXactSnapshot())
+			LockRelationOid(matviewOid, ExclusiveLock);
+		else if (!ConditionalLockRelationOid(matviewOid, ExclusiveLock))
+		{
+			/* try to throw error by name; relation could be deleted... */
+			char	   *relname = get_rel_name(matviewOid);
+
+			if (!relname)
+				ereport(ERROR,
+						(errcode(ERRCODE_LOCK_NOT_AVAILABLE),
+						errmsg("could not obtain lock on materialized view during incremental maintenance")));
+
+			ereport(ERROR,
+					(errcode(ERRCODE_LOCK_NOT_AVAILABLE),
+					errmsg("could not obtain lock on materialized view \"%s\" during incremental maintenance",
+							relname)));
+		}
+	}
+	else
+		LockRelationOid(matviewOid, RowExclusiveLock);
+
+	/*
+	 * On the first call initialize the hashtable
+	 */
+	if (!mv_trigger_info)
+		mv_InitHashTables();
+
+	entry = (MV_TriggerHashEntry *) hash_search(mv_trigger_info,
+											  (void *) &matviewOid,
+											  HASH_ENTER, &found);
+
+	/* On the first BEFORE to update the view, initialize trigger data */
+	if (!found)
+	{
+		Snapshot snapshot = GetActiveSnapshot();
+
+		entry->matview_id = matviewOid;
+		entry->before_trig_count = 0;
+		entry->after_trig_count = 0;
+		entry->xid = GetCurrentTransactionId();
+		entry->cid = snapshot->curcid;
+		entry->tables = NIL;
+		entry->has_old = false;
+		entry->has_new = false;
+	}
+
+	entry->before_trig_count++;
+
+	return PointerGetDatum(NULL);
+}
+
+/*
+ * IVM_immediate_before
+ *
+ * IVM trigger function invoked after base table is modified.
+ * For each table, tuplestores of transition tables are collected.
+ * and after the last modification
+ */
+Datum
+IVM_immediate_maintenance(PG_FUNCTION_ARGS)
+{
+	TriggerData *trigdata = (TriggerData *) fcinfo->context;
+	Relation	rel;
+	Oid			relid;
+	Oid			matviewOid;
+	Query	   *query;
+	Query	   *rewritten = NULL;
+	char	   *matviewOid_text = trigdata->tg_trigger->tgargs[0];
+	Relation	matviewRel;
+	int old_depth = matview_maintenance_depth;
+
+	Oid			relowner;
+	Tuplestorestate *old_tuplestore = NULL;
+	Tuplestorestate *new_tuplestore = NULL;
+	DestReceiver *dest_new = NULL, *dest_old = NULL;
+	Oid			save_userid;
+	int			save_sec_context;
+	int			save_nestlevel;
+
+	MV_TriggerHashEntry *entry;
+	MV_TriggerTable		*table;
+	bool	found;
+
+	ParseState		 *pstate;
+	QueryEnvironment *queryEnv = create_queryEnv();
+	MemoryContext	oldcxt;
+	ListCell   *lc;
+	int			i;
+
+
+	/* Create a ParseState for rewriting the view definition query */
+	pstate = make_parsestate(NULL);
+	pstate->p_queryEnv = queryEnv;
+	pstate->p_expr_kind = EXPR_KIND_SELECT_TARGET;
+
+	rel = trigdata->tg_relation;
+	relid = rel->rd_id;
+
+	matviewOid = DatumGetObjectId(DirectFunctionCall1(oidin, CStringGetDatum(matviewOid_text)));
+
+	/*
+	 * On the first call initialize the hashtable
+	 */
+	if (!mv_trigger_info)
+		mv_InitHashTables();
+
+	/* get the entry for this materialized view */
+	entry = (MV_TriggerHashEntry *) hash_search(mv_trigger_info,
+											  (void *) &matviewOid,
+											  HASH_FIND, &found);
+	Assert (found && entry != NULL);
+	entry->after_trig_count++;
+
+	/* search the entry for the modified table and create new entry if not found */
+	found = false;
+	foreach(lc, entry->tables)
+	{
+		table = (MV_TriggerTable *) lfirst(lc);
+		if (table->table_id == relid)
+		{
+			found = true;
+			break;
+		}
+	}
+	if (!found)
+	{
+		oldcxt = MemoryContextSwitchTo(TopTransactionContext);
+
+		table = (MV_TriggerTable *) palloc0(sizeof(MV_TriggerTable));
+		table->table_id = relid;
+		table->old_tuplestores = NIL;
+		table->new_tuplestores = NIL;
+		table->old_rtes = NIL;
+		table->new_rtes = NIL;
+		table->rte_indexes = NIL;
+		entry->tables = lappend(entry->tables, table);
+
+		MemoryContextSwitchTo(oldcxt);
+	}
+
+	/* Save the transition tables and make a request to not free immediately */
+	if (trigdata->tg_oldtable)
+	{
+		oldcxt = MemoryContextSwitchTo(TopTransactionContext);
+		table->old_tuplestores = lappend(table->old_tuplestores, trigdata->tg_oldtable);
+		entry->has_old = true;
+		MemoryContextSwitchTo(oldcxt);
+	}
+	if (trigdata->tg_newtable)
+	{
+		oldcxt = MemoryContextSwitchTo(TopTransactionContext);
+		table->new_tuplestores = lappend(table->new_tuplestores, trigdata->tg_newtable);
+		entry->has_new = true;
+		MemoryContextSwitchTo(oldcxt);
+	}
+	if (entry->has_new || entry->has_old)
+	{
+		CmdType cmd;
+
+		if (TRIGGER_FIRED_BY_INSERT(trigdata->tg_event))
+			cmd = CMD_INSERT;
+		else if (TRIGGER_FIRED_BY_DELETE(trigdata->tg_event))
+			cmd = CMD_DELETE;
+		else if (TRIGGER_FIRED_BY_UPDATE(trigdata->tg_event))
+			cmd = CMD_UPDATE;
+		else
+			elog(ERROR,"unsupported trigger type");
+
+		/* Prolong lifespan of transition tables to the end of the last AFTER trigger */
+		SetTransitionTablePreserved(relid, cmd);
+	}
+
+
+	/* If this is not the last AFTER trigger call, immediately exit. */
+	Assert (entry->before_trig_count >= entry->after_trig_count);
+	if (entry->before_trig_count != entry->after_trig_count)
+		return PointerGetDatum(NULL);
+
+	/*
+	 * If this is the last AFTER trigger call, continue and update the view.
+	 */
+
+	/*
+	 * Advance command counter to make the updated base table row locally
+	 * visible.
+	 */
+	CommandCounterIncrement();
+
+	matviewRel = table_open(matviewOid, NoLock);
+
+	/* get view query*/
+	query = get_matview_query(matviewRel);
+
+	/* Make sure it is a materialized view. */
+	Assert(matviewRel->rd_rel->relkind == RELKIND_MATVIEW);
+
+	/*
+	 * Get and push the latast snapshot to see any changes which is committed
+	 * during waiting in other transactions at READ COMMITTED level.
+	 */
+	PushActiveSnapshot(GetTransactionSnapshot());
+
+	/*
+	 * Check for active uses of the relation in the current transaction, such
+	 * as open scans.
+	 *
+	 * NB: We count on this to protect us against problems with refreshing the
+	 * data using TABLE_INSERT_FROZEN.
+	 */
+	CheckTableNotInUse(matviewRel, "refresh a materialized view incrementally");
+
+	/*
+	 * Switch to the owner's userid, so that any functions are run as that
+	 * user.  Also arrange to make GUC variable changes local to this command.
+	 * We will switch modes when we are about to execute user code.
+	 */
+	relowner = matviewRel->rd_rel->relowner;
+	GetUserIdAndSecContext(&save_userid, &save_sec_context);
+	SetUserIdAndSecContext(relowner,
+						   save_sec_context | SECURITY_RESTRICTED_OPERATION);
+	save_nestlevel = NewGUCNestLevel();
+
+	/*
+	 * rewrite query for calculating deltas
+	 */
+
+	rewritten = copyObject(query);
+
+	/* Replace resnames in a target list with materialized view's attnames */
+	i = 0;
+	foreach (lc, rewritten->targetList)
+	{
+		TargetEntry *tle = (TargetEntry *) lfirst(lc);
+		Form_pg_attribute attr = TupleDescAttr(matviewRel->rd_att, i);
+		char *resname = NameStr(attr->attname);
+
+		tle->resname = pstrdup(resname);
+		i++;
+	}
+
+	/* Set all tables in the query to pre-update state */
+	rewritten = rewrite_query_for_preupdate_state(rewritten, entry->tables,
+												  entry->xid, entry->cid,
+												  pstate);
+	/* Rewrite for DISTINCT clause */
+	rewritten = rewrite_query_for_distinct(rewritten, pstate);
+
+	/* Create tuplestores to store view deltas */
+	if (entry->has_old)
+	{
+		oldcxt = MemoryContextSwitchTo(TopTransactionContext);
+
+		old_tuplestore = tuplestore_begin_heap(false, false, work_mem);
+		dest_old = CreateDestReceiver(DestTuplestore);
+		SetTuplestoreDestReceiverParams(dest_old,
+									old_tuplestore,
+									TopTransactionContext,
+									false,
+									NULL,
+									NULL);
+
+		MemoryContextSwitchTo(oldcxt);
+	}
+	if (entry->has_new)
+	{
+		oldcxt = MemoryContextSwitchTo(TopTransactionContext);
+
+		new_tuplestore = tuplestore_begin_heap(false, false, work_mem);
+		dest_new = CreateDestReceiver(DestTuplestore);
+		SetTuplestoreDestReceiverParams(dest_new,
+									new_tuplestore,
+									TopTransactionContext,
+									false,
+									NULL,
+									NULL);
+		MemoryContextSwitchTo(oldcxt);
+	}
+
+	/* for all modified tables */
+	foreach(lc, entry->tables)
+	{
+		ListCell *lc2;
+
+		table = (MV_TriggerTable *) lfirst(lc);
+
+		/* loop for self-join */
+		foreach(lc2, table->rte_indexes)
+		{
+			int	rte_index = lfirst_int(lc2);
+			TupleDesc		tupdesc_old;
+			TupleDesc		tupdesc_new;
+			bool	use_count = false;
+			char   *count_colname = NULL;
+
+			count_colname = pstrdup("__ivm_count__");
+
+			if (query->distinctClause)
+				use_count = true;
+
+			/* calculate delta tables */
+			calc_delta(table, rte_index, rewritten, dest_old, dest_new,
+					   &tupdesc_old, &tupdesc_new, queryEnv);
+
+			/* Set the table in the query to post-update state */
+			rewritten = rewrite_query_for_postupdate_state(rewritten, table, rte_index);
+
+			PG_TRY();
+			{
+				/* apply the delta tables to the materialized view */
+				apply_delta(matviewOid, old_tuplestore, new_tuplestore,
+							tupdesc_old, tupdesc_new, query, use_count,
+							count_colname);
+			}
+			PG_CATCH();
+			{
+				matview_maintenance_depth = old_depth;
+				PG_RE_THROW();
+			}
+			PG_END_TRY();
+
+			/* clear view delta tuplestores */
+			if (old_tuplestore)
+				tuplestore_clear(old_tuplestore);
+			if (new_tuplestore)
+				tuplestore_clear(new_tuplestore);
+		}
+	}
+
+	/* Clean up hash entry and delete tuplestores */
+	clean_up_IVM_hash_entry(entry);
+	if (old_tuplestore)
+	{
+		dest_old->rDestroy(dest_old);
+		tuplestore_end(old_tuplestore);
+	}
+	if (new_tuplestore)
+	{
+		dest_new->rDestroy(dest_new);
+		tuplestore_end(new_tuplestore);
+	}
+
+	/* Pop the original snapshot. */
+	PopActiveSnapshot();
+
+	table_close(matviewRel, NoLock);
+
+	/* Roll back any GUC changes */
+	AtEOXact_GUC(false, save_nestlevel);
+
+	/* Restore userid and security context */
+	SetUserIdAndSecContext(save_userid, save_sec_context);
+
+	return PointerGetDatum(NULL);
+}
+
+/*
+ * rewrite_query_for_preupdate_state
+ *
+ * Rewrite the query so that base tables' RTEs will represent "pre-update"
+ * state of tables. This is necessary to calculate view delta after multiple
+ * tables are modified. xid and cid are the transaction id and command id
+ * before the first table was modified.
+ */
+static Query*
+rewrite_query_for_preupdate_state(Query *query, List *tables,
+								  TransactionId xid, CommandId cid,
+								  ParseState *pstate)
+{
+	ListCell *lc;
+	int num_rte = list_length(query->rtable);
+	int i;
+
+
+	/* register delta ENRs */
+	register_delta_ENRs(pstate, query, tables);
+
+	/* XXX: Is necessary? Is this right timing? */
+	AcquireRewriteLocks(query, true, false);
+
+	i = 1;
+	foreach(lc, query->rtable)
+	{
+		RangeTblEntry *r = (RangeTblEntry*) lfirst(lc);
+
+		ListCell *lc2;
+		foreach(lc2, tables)
+		{
+			MV_TriggerTable *table = (MV_TriggerTable *) lfirst(lc2);
+			/*
+			 * if the modified table is found then replace the original RTE with
+			 * "pre-state" RTE and append its index to the list.
+			 */
+			if (r->relid == table->table_id)
+			{
+				lfirst(lc) = get_prestate_rte(r, table, xid, cid, pstate->p_queryEnv);
+				table->rte_indexes = lappend_int(table->rte_indexes, i);
+				break;
+			}
+		}
+
+		/* finish the loop if we processed all RTE included in the original query */
+		if (i++ >= num_rte)
+			break;
+	}
+
+	return query;
+}
+
+/*
+ * register_delta_ENRs
+ *
+ * For all modified tables, make ENRs for their transition tables
+ * and register them to the queryEnv. ENR's RTEs are also appended
+ * into the list in query tree.
+ */
+static void
+register_delta_ENRs(ParseState *pstate, Query *query, List *tables)
+{
+	QueryEnvironment *queryEnv = pstate->p_queryEnv;
+	ListCell *lc;
+	RangeTblEntry	*rte;
+
+	foreach(lc, tables)
+	{
+		MV_TriggerTable *table = (MV_TriggerTable *) lfirst(lc);
+		ListCell *lc2;
+		int count;
+
+		count = 0;
+		foreach(lc2, table->old_tuplestores)
+		{
+			Tuplestorestate *oldtable = (Tuplestorestate *) lfirst(lc2);
+			EphemeralNamedRelation enr =
+				palloc(sizeof(EphemeralNamedRelationData));
+			ParseNamespaceItem *nsitem;
+
+			enr->md.name = make_delta_enr_name("old", table->table_id, count);
+			enr->md.reliddesc = table->table_id;
+			enr->md.tupdesc = NULL;
+			enr->md.enrtype = ENR_NAMED_TUPLESTORE;
+			enr->md.enrtuples = tuplestore_tuple_count(oldtable);
+			enr->reldata = oldtable;
+			register_ENR(queryEnv, enr);
+
+			nsitem = addRangeTableEntryForENR(pstate, makeRangeVar(NULL, enr->md.name, -1), true);
+			rte = nsitem->p_rte;
+			/* if base table has RLS, set security condition to enr */
+			rte->securityQuals = get_securityQuals(table->table_id, list_length(query->rtable) + 1, query);
+
+			query->rtable = lappend(query->rtable, rte);
+			table->old_rtes = lappend(table->old_rtes, rte);
+
+			count++;
+		}
+
+		count = 0;
+		foreach(lc2, table->new_tuplestores)
+		{
+			Tuplestorestate *newtable = (Tuplestorestate *) lfirst(lc2);
+			EphemeralNamedRelation enr =
+				palloc(sizeof(EphemeralNamedRelationData));
+			ParseNamespaceItem *nsitem;
+
+			enr->md.name = make_delta_enr_name("new", table->table_id, count);
+			enr->md.reliddesc = table->table_id;
+			enr->md.tupdesc = NULL;
+			enr->md.enrtype = ENR_NAMED_TUPLESTORE;
+			enr->md.enrtuples = tuplestore_tuple_count(newtable);
+			enr->reldata = newtable;
+			register_ENR(queryEnv, enr);
+
+			nsitem = addRangeTableEntryForENR(pstate, makeRangeVar(NULL, enr->md.name, -1), true);
+			rte = nsitem->p_rte;
+			/* if base table has RLS, set security condition to enr*/
+			rte->securityQuals = get_securityQuals(table->table_id, list_length(query->rtable) + 1, query);
+
+			query->rtable = lappend(query->rtable, rte);
+			table->new_rtes = lappend(table->new_rtes, rte);
+
+			count++;
+		}
+	}
+}
+
+/*
+ * get_prestate_rte
+ *
+ * Rewrite RTE of the modified table to a subquery which represents
+ * "pre-state" table. The original RTE is saved in table->rte_original.
+ */
+static RangeTblEntry*
+get_prestate_rte(RangeTblEntry *rte, MV_TriggerTable *table,
+				 TransactionId xid, CommandId cid,
+				 QueryEnvironment *queryEnv)
+{
+	StringInfoData str;
+	RawStmt *raw;
+	Query *sub;
+	Relation rel;
+	ParseState *pstate;
+	char *relname;
+	int i;
+
+	pstate = make_parsestate(NULL);
+	pstate->p_queryEnv = queryEnv;
+	pstate->p_expr_kind = EXPR_KIND_SELECT_TARGET;
+
+	/*
+	 * We can use NoLock here since AcquireRewriteLocks should
+	 * have locked the rel already.
+	 */
+	rel = table_open(table->table_id, NoLock);
+	relname = quote_qualified_identifier(
+					get_namespace_name(RelationGetNamespace(rel)),
+									   RelationGetRelationName(rel));
+	table_close(rel, NoLock);
+
+	initStringInfo(&str);
+	appendStringInfo(&str,
+		"SELECT t.* FROM %s t"
+		" WHERE (age(t.xmin) - age(%u::text::xid) > 0) OR"
+		" (t.xmin = %u AND t.cmin::text::int < %u)",
+			relname, xid, xid, cid);
+
+	for (i = 0; i < list_length(table->old_tuplestores); i++)
+	{
+		appendStringInfo(&str, " UNION ALL ");
+		appendStringInfo(&str," SELECT * FROM %s",
+			make_delta_enr_name("old", table->table_id, i));
+	}
+
+	raw = (RawStmt*)linitial(raw_parser(str.data, RAW_PARSE_DEFAULT));
+	sub = transformStmt(pstate, raw->stmt);
+
+	/* If this query has setOperations, RTEs in rtables has a subquery which contains ENR */
+	if (sub->setOperations != NULL)
+	{
+		ListCell *lc;
+
+		/* add securityQuals for tuplestores */
+		foreach (lc, sub->rtable)
+		{
+			RangeTblEntry *rte;
+			RangeTblEntry *sub_rte;
+
+			rte = (RangeTblEntry *)lfirst(lc);
+			Assert(rte->subquery != NULL);
+
+			sub_rte = (RangeTblEntry *)linitial(rte->subquery->rtable);
+			if (sub_rte->rtekind == RTE_NAMEDTUPLESTORE)
+				/* rt_index is always 1, bacause subquery has enr_rte only */
+				sub_rte->securityQuals = get_securityQuals(sub_rte->relid, 1, sub);
+		}
+	}
+
+	/* save the original RTE */
+	table->original_rte = copyObject(rte);
+
+	rte->rtekind = RTE_SUBQUERY;
+	rte->subquery = sub;
+	rte->security_barrier = false;
+	/* Clear fields that should not be set in a subquery RTE */
+	rte->relid = InvalidOid;
+	rte->relkind = 0;
+	rte->rellockmode = 0;
+	rte->tablesample = NULL;
+	rte->inh = false;			/* must not be set for a subquery */
+
+	rte->requiredPerms = 0;		/* no permission check on subquery itself */
+	rte->checkAsUser = InvalidOid;
+	rte->selectedCols = NULL;
+	rte->insertedCols = NULL;
+	rte->updatedCols = NULL;
+	rte->extraUpdatedCols = NULL;
+
+	return rte;
+}
+
+/*
+ * make_delta_enr_name
+ *
+ * Make a name for ENR of a transition table from the base table's oid.
+ * prefix will be "new" or "old" depending on its transition table kind..
+ */
+static char*
+make_delta_enr_name(const char *prefix, Oid relid, int count)
+{
+	char buf[NAMEDATALEN];
+	char *name;
+
+	snprintf(buf, NAMEDATALEN, "__ivm_%s_%u_%u", prefix, relid, count);
+	name = pstrdup(buf);
+
+	return name;
+}
+
+/*
+ * union_ENRs
+ *
+ * Make a single table delta by unionning all transition tables of the modified table
+ * whose RTE is specified by
+ */
+static RangeTblEntry*
+union_ENRs(RangeTblEntry *rte, Oid relid, List *enr_rtes, const char *prefix,
+		   QueryEnvironment *queryEnv)
+{
+	StringInfoData str;
+	ParseState	*pstate;
+	RawStmt *raw;
+	Query *sub;
+	int	i;
+	RangeTblEntry *enr_rte;
+
+	/* Create a ParseState for rewriting the view definition query */
+	pstate = make_parsestate(NULL);
+	pstate->p_queryEnv = queryEnv;
+	pstate->p_expr_kind = EXPR_KIND_SELECT_TARGET;
+
+	initStringInfo(&str);
+
+	for (i = 0; i < list_length(enr_rtes); i++)
+	{
+		if (i > 0)
+			appendStringInfo(&str, " UNION ALL ");
+
+		appendStringInfo(&str,
+			" SELECT * FROM %s",
+			make_delta_enr_name(prefix, relid, i));
+	}
+
+	raw = (RawStmt*)linitial(raw_parser(str.data, RAW_PARSE_DEFAULT));
+	sub = transformStmt(pstate, raw->stmt);
+
+	rte->rtekind = RTE_SUBQUERY;
+	rte->subquery = sub;
+	rte->security_barrier = false;
+	/* Clear fields that should not be set in a subquery RTE */
+	rte->relid = InvalidOid;
+	rte->relkind = 0;
+	rte->rellockmode = 0;
+	rte->tablesample = NULL;
+	rte->inh = false;			/* must not be set for a subquery */
+
+	rte->requiredPerms = 0;		/* no permission check on subquery itself */
+	rte->checkAsUser = InvalidOid;
+	rte->selectedCols = NULL;
+	rte->insertedCols = NULL;
+	rte->updatedCols = NULL;
+	rte->extraUpdatedCols = NULL;
+	/* if base table has RLS, set security condition to enr*/
+	enr_rte = (RangeTblEntry *)linitial(sub->rtable);
+	/* rt_index is always 1, bacause subquery has enr_rte only */
+	enr_rte->securityQuals = get_securityQuals(relid, 1, sub);
+
+	return rte;
+}
+
+/*
+ * rewrite_query_for_distinct
+ *
+ * Rewrite query for counting DISTINCT clause.
+ */
+static Query *
+rewrite_query_for_distinct(Query *query, ParseState *pstate)
+{
+	TargetEntry *tle_count;
+	FuncCall *fn;
+	Node *node;
+
+	/* Add count(*) for counting distinct tuples in views */
+	fn = makeFuncCall(list_make1(makeString("count")), NIL, COERCE_EXPLICIT_CALL, -1);
+	fn->agg_star = true;
+	if (!query->groupClause && !query->hasAggs)
+		query->groupClause = transformDistinctClause(NULL, &query->targetList, query->sortClause, false);
+
+	node = ParseFuncOrColumn(pstate, fn->funcname, NIL, NULL, fn, false, -1);
+
+	tle_count = makeTargetEntry((Expr *) node,
+								list_length(query->targetList) + 1,
+								pstrdup("__ivm_count__"),
+								false);
+	query->targetList = lappend(query->targetList, tle_count);
+	query->hasAggs = true;
+
+	return query;
+}
+
+/*
+ * calc_delta
+ *
+ * Calculate view deltas generated under the modification of a table specified
+ * by the RTE index.
+ */
+static void
+calc_delta(MV_TriggerTable *table, int rte_index, Query *query,
+			DestReceiver *dest_old, DestReceiver *dest_new,
+			TupleDesc *tupdesc_old, TupleDesc *tupdesc_new,
+			QueryEnvironment *queryEnv)
+{
+	ListCell *lc = list_nth_cell(query->rtable, rte_index - 1);
+	RangeTblEntry *rte = (RangeTblEntry *) lfirst(lc);
+
+	/* Generate old delta */
+	if (list_length(table->old_rtes) > 0)
+	{
+		/* Replace the modified table with the old delta table and calculate the old view delta. */
+		lfirst(lc) = union_ENRs(rte, table->table_id, table->old_rtes, "old", queryEnv);
+		refresh_matview_datafill(dest_old, query, queryEnv, tupdesc_old, "");
+	}
+
+	/* Generate new delta */
+	if (list_length(table->new_rtes) > 0)
+	{
+		/* Replace the modified table with the new delta table and calculate the new view delta*/
+		lfirst(lc) = union_ENRs(rte, table->table_id, table->new_rtes, "new", queryEnv);
+		refresh_matview_datafill(dest_new, query, queryEnv, tupdesc_new, "");
+	}
+}
+
+/*
+ * rewrite_query_for_postupdate_state
+ *
+ * Rewrite the query so that the specified base table's RTEs will represent
+ * "post-update" state of tables. This is called after the view delta
+ * calculation due to changes on this table finishes.
+ */
+static Query*
+rewrite_query_for_postupdate_state(Query *query, MV_TriggerTable *table, int rte_index)
+{
+	ListCell *lc = list_nth_cell(query->rtable, rte_index - 1);
+
+	/* Retore the original RTE */
+	lfirst(lc) = table->original_rte;
+
+	return query;
+}
+
+/*
+ * apply_delta
+ *
+ * Apply deltas to the materialized view. In outer join cases, this requires
+ * the view maintenance graph.
+ */
+static void
+apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *new_tuplestores,
+			TupleDesc tupdesc_old, TupleDesc tupdesc_new,
+			Query *query, bool use_count, char *count_colname)
+{
+	StringInfoData querybuf;
+	StringInfoData target_list_buf;
+	Relation	matviewRel;
+	char	   *matviewname;
+	ListCell	*lc;
+	int			i;
+	List	   *keys = NIL;
+
+
+	/*
+	 * get names of the materialized view and delta tables
+	 */
+
+	matviewRel = table_open(matviewOid, NoLock);
+	matviewname = quote_qualified_identifier(get_namespace_name(RelationGetNamespace(matviewRel)),
+											 RelationGetRelationName(matviewRel));
+
+	/*
+	 * Build parts of the maintenance queries
+	 */
+
+	initStringInfo(&querybuf);
+	initStringInfo(&target_list_buf);
+
+	/* build string of target list */
+	for (i = 0; i < matviewRel->rd_att->natts; i++)
+	{
+		Form_pg_attribute attr = TupleDescAttr(matviewRel->rd_att, i);
+		char   *resname = NameStr(attr->attname);
+
+		if (i != 0)
+			appendStringInfo(&target_list_buf, ", ");
+		appendStringInfo(&target_list_buf, "%s", quote_qualified_identifier(NULL, resname));
+	}
+
+	i = 0;
+	foreach (lc, query->targetList)
+	{
+		TargetEntry *tle = (TargetEntry *) lfirst(lc);
+		Form_pg_attribute attr = TupleDescAttr(matviewRel->rd_att, i);
+		char *resname = NameStr(attr->attname);
+
+		i++;
+
+		if (tle->resjunk)
+			continue;
+
+		keys = lappend(keys, resname);
+	}
+
+	/* Start maintaining the materialized view. */
+	OpenMatViewIncrementalMaintenance();
+
+	/* Open SPI context. */
+	if (SPI_connect() != SPI_OK_CONNECT)
+		elog(ERROR, "SPI_connect failed");
+
+	/* For tuple deletion */
+	if (old_tuplestores && tuplestore_tuple_count(old_tuplestores) > 0)
+	{
+		EphemeralNamedRelation enr = palloc(sizeof(EphemeralNamedRelationData));
+		int				rc;
+
+		/* convert tuplestores to ENR, and register for SPI */
+		enr->md.name = pstrdup(OLD_DELTA_ENRNAME);
+		enr->md.reliddesc = InvalidOid;
+		enr->md.tupdesc = tupdesc_old;
+		enr->md.enrtype = ENR_NAMED_TUPLESTORE;
+		enr->md.enrtuples = tuplestore_tuple_count(old_tuplestores);
+		enr->reldata = old_tuplestores;
+
+		rc = SPI_register_relation(enr);
+		if (rc != SPI_OK_REL_REGISTER)
+			elog(ERROR, "SPI_register failed");
+
+		if (use_count)
+			/* apply old delta and get rows to be recalculated */
+			apply_old_delta_with_count(matviewname, OLD_DELTA_ENRNAME,
+									   keys, count_colname);
+		else
+			apply_old_delta(matviewname, OLD_DELTA_ENRNAME, keys);
+
+	}
+	/* For tuple insertion */
+	if (new_tuplestores && tuplestore_tuple_count(new_tuplestores) > 0)
+	{
+		EphemeralNamedRelation enr = palloc(sizeof(EphemeralNamedRelationData));
+		int rc;
+
+		/* convert tuplestores to ENR, and register for SPI */
+		enr->md.name = pstrdup(NEW_DELTA_ENRNAME);
+		enr->md.reliddesc = InvalidOid;
+		enr->md.tupdesc = tupdesc_new;;
+		enr->md.enrtype = ENR_NAMED_TUPLESTORE;
+		enr->md.enrtuples = tuplestore_tuple_count(new_tuplestores);
+		enr->reldata = new_tuplestores;
+
+		rc = SPI_register_relation(enr);
+		if (rc != SPI_OK_REL_REGISTER)
+			elog(ERROR, "SPI_register failed");
+
+		/* apply new delta */
+		if (use_count)
+			apply_new_delta_with_count(matviewname, NEW_DELTA_ENRNAME,
+								keys, &target_list_buf, count_colname);
+		else
+			apply_new_delta(matviewname, NEW_DELTA_ENRNAME, &target_list_buf);
+	}
+
+	/* We're done maintaining the materialized view. */
+	CloseMatViewIncrementalMaintenance();
+
+	table_close(matviewRel, NoLock);
+
+	/* Close SPI context. */
+	if (SPI_finish() != SPI_OK_FINISH)
+		elog(ERROR, "SPI_finish failed");
+}
+
+/*
+ * apply_old_delta_with_count
+ *
+ * Execute a query for applying a delta table given by deltname_old
+ * which contains tuples to be deleted from to a materialized view given by
+ * matviewname.  This is used when counting is required, that is, the view
+ * has aggregate or distinct.
+ */
+static void
+apply_old_delta_with_count(const char *matviewname, const char *deltaname_old,
+				List *keys, const char *count_colname)
+{
+	StringInfoData	querybuf;
+	char   *match_cond;
+
+	/* build WHERE condition for searching tuples to be deleted */
+	match_cond = get_matching_condition_string(keys);
+
+	/* Search for matching tuples from the view and update or delete if found. */
+	initStringInfo(&querybuf);
+	appendStringInfo(&querybuf,
+					"WITH t AS ("			/* collecting tid of target tuples in the view */
+						"SELECT diff.%s, "			/* count column */
+								"(diff.%s OPERATOR(pg_catalog.=) mv.%s) AS for_dlt, "
+								"mv.ctid "
+						"FROM %s AS mv, %s AS diff "
+						"WHERE %s"					/* tuple matching condition */
+					"), updt AS ("			/* update a tuple if this is not to be deleted */
+						"UPDATE %s AS mv SET %s = mv.%s OPERATOR(pg_catalog.-) t.%s "
+						"FROM t WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND NOT for_dlt "
+					"), dlt AS ("			/* delete a tuple if this is to be deleted */
+						"DELETE FROM %s AS mv USING t "
+						"WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt"
+					")",
+					count_colname,
+					count_colname, count_colname,
+					matviewname, deltaname_old,
+					match_cond,
+					matviewname, count_colname, count_colname, count_colname,
+					matviewname);
+
+	if (SPI_exec(querybuf.data, 0) != SPI_OK_DELETE)
+		elog(ERROR, "SPI_exec failed: %s", querybuf.data);
+}
+
+/*
+ * apply_old_delta
+ *
+ * Execute a query for applying a delta table given by deltname_old
+ * which contains tuples to be deleted from to a materialized view given by
+ * matviewname.  This is used when counting is not required.
+ */
+static void
+apply_old_delta(const char *matviewname, const char *deltaname_old,
+				List *keys)
+{
+	StringInfoData	querybuf;
+	StringInfoData	keysbuf;
+	char   *match_cond;
+	ListCell *lc;
+
+	/* build WHERE condition for searching tuples to be deleted */
+	match_cond = get_matching_condition_string(keys);
+
+	/* build string of keys list */
+	initStringInfo(&keysbuf);
+	foreach (lc, keys)
+	{
+		Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc);
+		char   *resname = NameStr(attr->attname);
+		appendStringInfo(&keysbuf, "%s", quote_qualified_identifier("mv", resname));
+		if (lnext(keys, lc))
+			appendStringInfo(&keysbuf, ", ");
+	}
+
+	/* Search for matching tuples from the view and update or delete if found. */
+	initStringInfo(&querybuf);
+	appendStringInfo(&querybuf,
+	"DELETE FROM %s WHERE ctid IN ("
+		"SELECT tid FROM (SELECT row_number() over (partition by %s) AS \"__ivm_row_number__\","
+								  "mv.ctid AS tid,"
+								  "diff.\"__ivm_count__\""
+						 "FROM %s AS mv, %s AS diff "
+						 "WHERE %s) v "
+					"WHERE v.\"__ivm_row_number__\" OPERATOR(pg_catalog.<=) v.\"__ivm_count__\")",
+					matviewname,
+					keysbuf.data,
+					matviewname, deltaname_old,
+					match_cond);
+
+	if (SPI_exec(querybuf.data, 0) != SPI_OK_DELETE)
+		elog(ERROR, "SPI_exec failed: %s", querybuf.data);
+}
+
+/*
+ * apply_new_delta_with_count
+ *
+ * Execute a query for applying a delta table given by deltname_new
+ * which contains tuples to be inserted into a materialized view given by
+ * matviewname.  This is used when counting is required, that is, the view
+ * has aggregate or distinct. Also, when a table in EXISTS sub queries
+ * is modified.
+ */
+static void
+apply_new_delta_with_count(const char *matviewname, const char* deltaname_new,
+				List *keys, StringInfo target_list, const char* count_colname)
+{
+	StringInfoData	querybuf;
+	StringInfoData	returning_keys;
+	ListCell	*lc;
+	char	*match_cond = "";
+
+	/* build WHERE condition for searching tuples to be updated */
+	match_cond = get_matching_condition_string(keys);
+
+	/* build string of keys list */
+	initStringInfo(&returning_keys);
+	if (keys)
+	{
+		foreach (lc, keys)
+		{
+			Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc);
+			char   *resname = NameStr(attr->attname);
+			appendStringInfo(&returning_keys, "%s", quote_qualified_identifier("mv", resname));
+			if (lnext(keys, lc))
+				appendStringInfo(&returning_keys, ", ");
+		}
+	}
+	else
+		appendStringInfo(&returning_keys, "NULL");
+
+	/* Search for matching tuples from the view and update if found or insert if not. */
+	initStringInfo(&querybuf);
+	appendStringInfo(&querybuf,
+					"WITH updt AS ("		/* update a tuple if this exists in the view */
+						"UPDATE %s AS mv SET %s = mv.%s OPERATOR(pg_catalog.+) diff.%s "
+						"FROM %s AS diff "
+						"WHERE %s "					/* tuple matching condition */
+						"RETURNING %s"				/* returning keys of updated tuples */
+					") INSERT INTO %s (%s)"	/* insert a new tuple if this doesn't existw */
+						"SELECT %s FROM %s AS diff "
+						"WHERE NOT EXISTS (SELECT 1 FROM updt AS mv WHERE %s);",
+					matviewname, count_colname, count_colname, count_colname,
+					deltaname_new,
+					match_cond,
+					returning_keys.data,
+					matviewname, target_list->data,
+					target_list->data, deltaname_new,
+					match_cond);
+
+	if (SPI_exec(querybuf.data, 0) != SPI_OK_INSERT)
+		elog(ERROR, "SPI_exec failed: %s", querybuf.data);
+}
+
+/*
+ * apply_new_delta
+ *
+ * Execute a query for applying a delta table given by deltname_new
+ * which contains tuples to be inserted into a materialized view given by
+ * matviewname.  This is used when counting is not required.
+ */
+static void
+apply_new_delta(const char *matviewname, const char *deltaname_new,
+				StringInfo target_list)
+{
+	StringInfoData	querybuf;
+
+	/* Search for matching tuples from the view and update or delete if found. */
+	initStringInfo(&querybuf);
+	appendStringInfo(&querybuf,
+					"INSERT INTO %s (%s) SELECT %s FROM ("
+						"SELECT diff.*, generate_series(1, diff.\"__ivm_count__\") "
+						"FROM %s AS diff) AS v",
+					matviewname, target_list->data, target_list->data,
+					deltaname_new);
+
+	if (SPI_exec(querybuf.data, 0) != SPI_OK_INSERT)
+		elog(ERROR, "SPI_exec failed: %s", querybuf.data);
+}
+
+/*
+ * get_matching_condition_string
+ *
+ * Build a predicate string for looking for a tuple with given keys.
+ */
+static char *
+get_matching_condition_string(List *keys)
+{
+	StringInfoData match_cond;
+	ListCell	*lc;
+
+	/* If there is no key columns, the condition is always true. */
+	if (keys == NIL)
+		return "true";
+
+	initStringInfo(&match_cond);
+	foreach (lc, keys)
+	{
+		Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc);
+		char   *resname = NameStr(attr->attname);
+		char   *mv_resname = quote_qualified_identifier("mv", resname);
+		char   *diff_resname = quote_qualified_identifier("diff", resname);
+		Oid		typid = attr->atttypid;
+
+		/* Considering NULL values, we can not use simple = operator. */
+		appendStringInfo(&match_cond, "(");
+		generate_equal(&match_cond, typid, mv_resname, diff_resname);
+		appendStringInfo(&match_cond, " OR (%s IS NULL AND %s IS NULL))",
+						 mv_resname, diff_resname);
+
+		if (lnext(keys, lc))
+			appendStringInfo(&match_cond, " AND ");
+	}
+
+	return match_cond.data;
+}
+
+/*
+ * generate_equals
+ *
+ * Generate an equality clause using given operands' default equality
+ * operator.
+ */
+static void
+generate_equal(StringInfo querybuf, Oid opttype,
+			   const char *leftop, const char *rightop)
+{
+	TypeCacheEntry *typentry;
+
+	typentry = lookup_type_cache(opttype, TYPECACHE_EQ_OPR);
+	if (!OidIsValid(typentry->eq_opr))
+		ereport(ERROR,
+				(errcode(ERRCODE_UNDEFINED_FUNCTION),
+				 errmsg("could not identify an equality operator for type %s",
+						format_type_be(opttype))));
+
+	generate_operator_clause(querybuf,
+							 leftop, opttype,
+							 typentry->eq_opr,
+							 rightop, opttype);
+}
+
+/*
+ * mv_InitHashTables
+ */
+static void
+mv_InitHashTables(void)
+{
+	HASHCTL		ctl;
+
+	memset(&ctl, 0, sizeof(ctl));
+	ctl.keysize = sizeof(Oid);
+	ctl.entrysize = sizeof(MV_TriggerHashEntry);
+	mv_trigger_info = hash_create("MV trigger info",
+								 MV_INIT_QUERYHASHSIZE,
+								 &ctl, HASH_ELEM | HASH_BLOBS);
+}
+
+/*
+ * AtAbort_IVM
+ *
+ * Clean up hash entries for all materialized views. This is called at
+ * transaction abort.
+ */
+void
+AtAbort_IVM()
+{
+	HASH_SEQ_STATUS seq;
+	MV_TriggerHashEntry *entry;
+
+	if (mv_trigger_info)
+	{
+		hash_seq_init(&seq, mv_trigger_info);
+		while ((entry = hash_seq_search(&seq)) != NULL)
+			clean_up_IVM_hash_entry(entry);
+	}
+}
+
+/*
+ * clean_up_IVM_hash_entry
+ *
+ * Clean up tuple stores and hash entries for a materialized view after its
+ * maintenance finished.
+ */
+static void
+clean_up_IVM_hash_entry(MV_TriggerHashEntry *entry)
+{
+	bool found;
+	ListCell *lc;
+
+	foreach(lc, entry->tables)
+	{
+		MV_TriggerTable *table = (MV_TriggerTable *) lfirst(lc);
+
+		list_free(table->old_tuplestores);
+		list_free(table->new_tuplestores);
+	}
+	list_free(entry->tables);
+
+	hash_search(mv_trigger_info, (void *) &entry->matview_id, HASH_REMOVE, &found);
+}
+
+/*
+ * isIvmName
+ *
+ * Check if this is a IVM hidden column from the name.
+ */
+bool
+isIvmName(const char *s)
+{
+	if (s)
+		return (strncmp(s, "__ivm_", 6) == 0);
+	return false;
+}
+
+/*
+ * get_securityQuals
+ *
+ * Get row security policy on a relation.
+ * This is used by IVM for copying RLS from base table to enr.
+ */
+static List *
+get_securityQuals(Oid relId, int rt_index, Query *query)
+{
+	ParseState *pstate;
+	Relation rel;
+	ParseNamespaceItem *nsitem;
+	RangeTblEntry *rte;
+	List *securityQuals;
+	List *withCheckOptions;
+	bool  hasRowSecurity;
+	bool  hasSubLinks;
+
+	securityQuals = NIL;
+	pstate = make_parsestate(NULL);
+
+	rel = table_open(relId, NoLock);
+	nsitem = addRangeTableEntryForRelation(pstate, rel, AccessShareLock, NULL, false, false);
+	rte = nsitem->p_rte;
+
+	get_row_security_policies(query, rte, rt_index,
+							  &securityQuals, &withCheckOptions,
+							  &hasRowSecurity, &hasSubLinks);
+
+	/*
+	 * Make sure the query is marked correctly if row level security
+	 * applies, or if the new quals had sublinks.
+	 */
+	if (hasRowSecurity)
+		query->hasRowSecurity = true;
+	if (hasSubLinks)
+		query->hasSubLinks = true;
+
+	table_close(rel, NoLock);
+
+	return securityQuals;
+}
diff --git a/src/backend/commands/tablecmds.c b/src/backend/commands/tablecmds.c
index 857cc5ce6e..a5652f93ed 100644
--- a/src/backend/commands/tablecmds.c
+++ b/src/backend/commands/tablecmds.c
@@ -50,6 +50,7 @@
 #include "commands/cluster.h"
 #include "commands/comment.h"
 #include "commands/defrem.h"
+#include "commands/matview.h"
 #include "commands/event_trigger.h"
 #include "commands/policy.h"
 #include "commands/sequence.h"
@@ -3394,6 +3395,14 @@ renameatt_internal(Oid myrelid,
 	targetrelation = relation_open(myrelid, AccessExclusiveLock);
 	renameatt_check(myrelid, RelationGetForm(targetrelation), recursing);
 
+	/*
+	 * Don't rename IVM columns.
+	 */
+	if (RelationIsIVM(targetrelation) && isIvmName(oldattname))
+		ereport(ERROR,
+				(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+				 errmsg("IVM column can not be renamed")));
+
 	/*
 	 * if the 'recurse' flag is set then we are supposed to rename this
 	 * attribute in all classes that inherit from 'relname' (as well as in
diff --git a/src/backend/nodes/copyfuncs.c b/src/backend/nodes/copyfuncs.c
index 5769a10586..51bd4ffce5 100644
--- a/src/backend/nodes/copyfuncs.c
+++ b/src/backend/nodes/copyfuncs.c
@@ -2460,6 +2460,7 @@ _copyRangeTblEntry(const RangeTblEntry *from)
 	COPY_SCALAR_FIELD(relkind);
 	COPY_SCALAR_FIELD(rellockmode);
 	COPY_NODE_FIELD(tablesample);
+	COPY_SCALAR_FIELD(relisivm);
 	COPY_NODE_FIELD(subquery);
 	COPY_SCALAR_FIELD(security_barrier);
 	COPY_SCALAR_FIELD(jointype);
diff --git a/src/backend/nodes/equalfuncs.c b/src/backend/nodes/equalfuncs.c
index 80497dc240..6df5d21b55 100644
--- a/src/backend/nodes/equalfuncs.c
+++ b/src/backend/nodes/equalfuncs.c
@@ -2764,6 +2764,7 @@ _equalRangeTblEntry(const RangeTblEntry *a, const RangeTblEntry *b)
 	COMPARE_SCALAR_FIELD(relkind);
 	COMPARE_SCALAR_FIELD(rellockmode);
 	COMPARE_NODE_FIELD(tablesample);
+	COMPARE_SCALAR_FIELD(relisivm);
 	COMPARE_NODE_FIELD(subquery);
 	COMPARE_SCALAR_FIELD(security_barrier);
 	COMPARE_SCALAR_FIELD(jointype);
diff --git a/src/backend/nodes/outfuncs.c b/src/backend/nodes/outfuncs.c
index f6166f7859..8133850e98 100644
--- a/src/backend/nodes/outfuncs.c
+++ b/src/backend/nodes/outfuncs.c
@@ -3253,6 +3253,7 @@ _outRangeTblEntry(StringInfo str, const RangeTblEntry *node)
 			WRITE_CHAR_FIELD(relkind);
 			WRITE_INT_FIELD(rellockmode);
 			WRITE_NODE_FIELD(tablesample);
+			WRITE_BOOL_FIELD(relisivm);
 			break;
 		case RTE_SUBQUERY:
 			WRITE_NODE_FIELD(subquery);
diff --git a/src/backend/nodes/readfuncs.c b/src/backend/nodes/readfuncs.c
index 1e55a58f69..96fa85758f 100644
--- a/src/backend/nodes/readfuncs.c
+++ b/src/backend/nodes/readfuncs.c
@@ -1443,6 +1443,7 @@ _readRangeTblEntry(void)
 			READ_CHAR_FIELD(relkind);
 			READ_INT_FIELD(rellockmode);
 			READ_NODE_FIELD(tablesample);
+			READ_BOOL_FIELD(relisivm);
 			break;
 		case RTE_SUBQUERY:
 			READ_NODE_FIELD(subquery);
diff --git a/src/backend/parser/parse_relation.c b/src/backend/parser/parse_relation.c
index c5c3f26ecf..4a52035371 100644
--- a/src/backend/parser/parse_relation.c
+++ b/src/backend/parser/parse_relation.c
@@ -36,6 +36,7 @@
 #include "utils/rel.h"
 #include "utils/syscache.h"
 #include "utils/varlena.h"
+#include "commands/matview.h"
 
 
 /*
@@ -79,7 +80,7 @@ static void expandTupleDesc(TupleDesc tupdesc, Alias *eref,
 							int count, int offset,
 							int rtindex, int sublevels_up,
 							int location, bool include_dropped,
-							List **colnames, List **colvars);
+							List **colnames, List **colvars, bool is_ivm);
 static int	specialAttNum(const char *attname);
 static bool isQueryUsingTempRelation_walker(Node *node, void *context);
 
@@ -1433,6 +1434,7 @@ addRangeTableEntry(ParseState *pstate,
 	rte->relid = RelationGetRelid(rel);
 	rte->relkind = rel->rd_rel->relkind;
 	rte->rellockmode = lockmode;
+	rte->relisivm = rel->rd_rel->relisivm;
 
 	/*
 	 * Build the list of effective column names using user-supplied aliases
@@ -1521,6 +1523,7 @@ addRangeTableEntryForRelation(ParseState *pstate,
 	rte->relid = RelationGetRelid(rel);
 	rte->relkind = rel->rd_rel->relkind;
 	rte->rellockmode = lockmode;
+	rte->relisivm = rel->rd_rel->relisivm;
 
 	/*
 	 * Build the list of effective column names using user-supplied aliases
@@ -2676,7 +2679,7 @@ expandRTE(RangeTblEntry *rte, int rtindex, int sublevels_up,
 						expandTupleDesc(tupdesc, rte->eref,
 										rtfunc->funccolcount, atts_done,
 										rtindex, sublevels_up, location,
-										include_dropped, colnames, colvars);
+										include_dropped, colnames, colvars, false);
 					}
 					else if (functypclass == TYPEFUNC_SCALAR)
 					{
@@ -2944,7 +2947,7 @@ expandRelation(Oid relid, Alias *eref, int rtindex, int sublevels_up,
 	expandTupleDesc(rel->rd_att, eref, rel->rd_att->natts, 0,
 					rtindex, sublevels_up,
 					location, include_dropped,
-					colnames, colvars);
+					colnames, colvars, RelationIsIVM(rel));
 	relation_close(rel, AccessShareLock);
 }
 
@@ -2961,7 +2964,7 @@ static void
 expandTupleDesc(TupleDesc tupdesc, Alias *eref, int count, int offset,
 				int rtindex, int sublevels_up,
 				int location, bool include_dropped,
-				List **colnames, List **colvars)
+				List **colnames, List **colvars, bool is_ivm)
 {
 	ListCell   *aliascell;
 	int			varattno;
@@ -2974,6 +2977,9 @@ expandTupleDesc(TupleDesc tupdesc, Alias *eref, int count, int offset,
 	{
 		Form_pg_attribute attr = TupleDescAttr(tupdesc, varattno);
 
+		if (is_ivm && isIvmName(NameStr(attr->attname)) && !MatViewIncrementalMaintenanceIsEnabled())
+			continue;
+
 		if (attr->attisdropped)
 		{
 			if (include_dropped)
@@ -3127,6 +3133,10 @@ expandNSItemAttrs(ParseState *pstate, ParseNamespaceItem *nsitem,
 		Var		   *varnode = (Var *) lfirst(var);
 		TargetEntry *te;
 
+		/* if transform * into columnlist with IMMV, remove IVM columns */
+		if (rte->relisivm && isIvmName(label) && !MatViewIncrementalMaintenanceIsEnabled())
+			continue;
+
 		te = makeTargetEntry((Expr *) varnode,
 							 (AttrNumber) pstate->p_next_resno++,
 							 label,
diff --git a/src/backend/rewrite/rewriteDefine.c b/src/backend/rewrite/rewriteDefine.c
index 6589345ac4..02f33d404b 100644
--- a/src/backend/rewrite/rewriteDefine.c
+++ b/src/backend/rewrite/rewriteDefine.c
@@ -776,7 +776,8 @@ checkRuleResultList(List *targetList, TupleDesc resultDesc, bool isSelect,
 														attr->atttypmod))));
 	}
 
-	if (i != resultDesc->natts)
+	/* No check for materialized views since this could have special columns for IVM */
+	if ((!isSelect || requireColumnNameMatch) && i != resultDesc->natts)
 		ereport(ERROR,
 				(errcode(ERRCODE_INVALID_OBJECT_DEFINITION),
 				 isSelect ?
diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat
index d068d6532e..4845e71898 100644
--- a/src/include/catalog/pg_proc.dat
+++ b/src/include/catalog/pg_proc.dat
@@ -11689,4 +11689,12 @@
   prorettype => 'bytea', proargtypes => 'pg_brin_minmax_multi_summary',
   prosrc => 'brin_minmax_multi_summary_send' },
 
+# IVM
+{ oid => '786', descr => 'ivm trigger (before)',
+  proname => 'IVM_immediate_before', provolatile => 'v', prorettype => 'trigger',
+  proargtypes => '', prosrc => 'IVM_immediate_before' },
+{ oid => '787', descr => 'ivm trigger (after)',
+  proname => 'IVM_immediate_maintenance', provolatile => 'v', prorettype => 'trigger',
+  proargtypes => '', prosrc => 'IVM_immediate_maintenance' },
+
 ]
diff --git a/src/include/commands/createas.h b/src/include/commands/createas.h
index ad5054d116..a57ce463e1 100644
--- a/src/include/commands/createas.h
+++ b/src/include/commands/createas.h
@@ -16,6 +16,7 @@
 
 #include "catalog/objectaddress.h"
 #include "nodes/params.h"
+#include "nodes/pathnodes.h"
 #include "parser/parse_node.h"
 #include "tcop/dest.h"
 #include "utils/queryenvironment.h"
@@ -25,6 +26,10 @@ extern ObjectAddress ExecCreateTableAs(ParseState *pstate, CreateTableAsStmt *st
 									   ParamListInfo params, QueryEnvironment *queryEnv,
 									   QueryCompletion *qc);
 
+extern void CreateIvmTriggersOnBaseTables(Query *qry, Oid matviewOid, bool is_create);
+
+extern Query *rewriteQueryForIMMV(Query *query, List *colNames);
+
 extern int	GetIntoRelEFlags(IntoClause *intoClause);
 
 extern DestReceiver *CreateIntoRelDestReceiver(IntoClause *intoClause);
diff --git a/src/include/commands/matview.h b/src/include/commands/matview.h
index 214b1c1df6..13a5722f17 100644
--- a/src/include/commands/matview.h
+++ b/src/include/commands/matview.h
@@ -15,6 +15,7 @@
 #define MATVIEW_H
 
 #include "catalog/objectaddress.h"
+#include "fmgr.h"
 #include "nodes/params.h"
 #include "nodes/parsenodes.h"
 #include "tcop/dest.h"
@@ -23,6 +24,8 @@
 
 extern void SetMatViewPopulatedState(Relation relation, bool newstate);
 
+extern void SetMatViewIVMState(Relation relation, bool newstate);
+
 extern ObjectAddress ExecRefreshMatView(RefreshMatViewStmt *stmt, const char *queryString,
 										ParamListInfo params, QueryCompletion *qc);
 
@@ -30,4 +33,9 @@ extern DestReceiver *CreateTransientRelDestReceiver(Oid oid);
 
 extern bool MatViewIncrementalMaintenanceIsEnabled(void);
 
+extern Datum IVM_immediate_before(PG_FUNCTION_ARGS);
+extern Datum IVM_immediate_maintenance(PG_FUNCTION_ARGS);
+extern void AtAbort_IVM(void);
+extern bool isIvmName(const char *s);
+
 #endif							/* MATVIEW_H */
diff --git a/src/include/nodes/parsenodes.h b/src/include/nodes/parsenodes.h
index 49123e28a4..526ae434af 100644
--- a/src/include/nodes/parsenodes.h
+++ b/src/include/nodes/parsenodes.h
@@ -1035,6 +1035,7 @@ typedef struct RangeTblEntry
 	char		relkind;		/* relation kind (see pg_class.relkind) */
 	int			rellockmode;	/* lock level that query requires on the rel */
 	struct TableSampleClause *tablesample;	/* sampling info, or NULL */
+	bool		relisivm;
 
 	/*
 	 * Fields valid for a subquery RTE (else NULL):
@@ -2194,6 +2195,7 @@ typedef struct CreateStmt
 	char	   *tablespacename; /* table space to use, or NULL */
 	char	   *accessMethod;	/* table access method */
 	bool		if_not_exists;	/* just do nothing if it already exists? */
+	bool		ivm;			/* incremental view maintenance is used by materialized view */
 } CreateStmt;
 
 /* ----------
-- 
2.17.1


--Multipart=_Fri__29_Oct_2021_18_16_28_+0900_jlYRKjywLqhZ7oyk
Content-Type: text/x-diff;
 name="v24-0008-Add-aggregates-support-in-IVM.patch"
Content-Disposition: attachment;
 filename="v24-0008-Add-aggregates-support-in-IVM.patch"
Content-Transfer-Encoding: quoted-printable



^ permalink  raw  reply  [nested|flat] 101+ messages in thread

* [PATCH v24 07/15] Add Incremental View Maintenance support
@ 2020-12-22 09:40  Yugo Nagata <[email protected]>
  0 siblings, 0 replies; 101+ messages in thread

From: Yugo Nagata @ 2020-12-22 09:40 UTC (permalink / raw)

In this implementation, AFTER triggers are used to collect
tuplestores containing transition table contents. When multiple tables
are changed, multiple AFTER triggers are invoked, then the final AFTER
trigger performs actual update of the matview. In addition, BEFORE
triggers are also used to handle global information for view
maintenance. To calculate view deltas, we need both pre-state and
post-state of base tables. Post-update states are available in AFTER
trigger, and pre-update states can be calculated by filtering inserted
tuples using cmin/xmin system columns, and append deleted tuples which
are contained in an old transition table.

This patch also allows self-join, simultaneous updates of more than
one base table, and multiple updates of the same base table.

Incrementally Maintainable Materialized Views (IMMV) can contain
duplicated tuples. Also, DISTINCT clause is supported. When IMMV is
created with DISTINCT, multiplicity of tuples is counted and stored
in  "__ivm_count__" column, which is a hidden column of IMMV.
The value in __ivm_count__ is updated when IMMV is maintained
incrementally. A tuple in IMMV can be removed if and only if the
count becomes zero.
---
 src/backend/access/transam/xact.c   |    5 +
 src/backend/commands/createas.c     |  713 ++++++++++++
 src/backend/commands/indexcmds.c    |   40 +
 src/backend/commands/matview.c      | 1549 ++++++++++++++++++++++++++-
 src/backend/commands/tablecmds.c    |    9 +
 src/backend/nodes/copyfuncs.c       |    1 +
 src/backend/nodes/equalfuncs.c      |    1 +
 src/backend/nodes/outfuncs.c        |    1 +
 src/backend/nodes/readfuncs.c       |    1 +
 src/backend/parser/parse_relation.c |   18 +-
 src/backend/rewrite/rewriteDefine.c |    3 +-
 src/include/catalog/pg_proc.dat     |    8 +
 src/include/commands/createas.h     |    5 +
 src/include/commands/matview.h      |    8 +
 src/include/nodes/parsenodes.h      |    2 +
 15 files changed, 2324 insertions(+), 40 deletions(-)

diff --git a/src/backend/access/transam/xact.c b/src/backend/access/transam/xact.c
index 6597ec45a9..f971727255 100644
--- a/src/backend/access/transam/xact.c
+++ b/src/backend/access/transam/xact.c
@@ -35,6 +35,7 @@
 #include "catalog/pg_enum.h"
 #include "catalog/storage.h"
 #include "commands/async.h"
+#include "commands/matview.h"
 #include "commands/tablecmds.h"
 #include "commands/trigger.h"
 #include "executor/spi.h"
@@ -2715,6 +2716,7 @@ AbortTransaction(void)
 	AtAbort_Notify();
 	AtEOXact_RelationMap(false, is_parallel_worker);
 	AtAbort_Twophase();
+	AtAbort_IVM();
 
 	/*
 	 * Advertise the fact that we aborted in pg_xact (assuming that we got as
@@ -4958,6 +4960,9 @@ AbortSubTransaction(void)
 	AbortBufferIO();
 	UnlockBuffers();
 
+	/* Clean up hash entries for incremental view maintenance */
+	AtAbort_IVM();
+
 	/* Reset WAL record construction state */
 	XLogResetInsertion();
 
diff --git a/src/backend/commands/createas.c b/src/backend/commands/createas.c
index 0982851715..91888891bf 100644
--- a/src/backend/commands/createas.c
+++ b/src/backend/commands/createas.c
@@ -32,24 +32,41 @@
 #include "access/xact.h"
 #include "access/xlog.h"
 #include "catalog/namespace.h"
+#include "catalog/index.h"
+#include "catalog/pg_constraint.h"
+#include "catalog/pg_inherits.h"
+#include "catalog/pg_trigger.h"
+#include "catalog/pg_type.h"
 #include "catalog/toasting.h"
 #include "commands/createas.h"
+#include "commands/defrem.h"
 #include "commands/matview.h"
 #include "commands/prepare.h"
 #include "commands/tablecmds.h"
+#include "commands/tablespace.h"
+#include "commands/trigger.h"
 #include "commands/view.h"
 #include "miscadmin.h"
+#include "optimizer/clauses.h"
+#include "optimizer/optimizer.h"
 #include "nodes/makefuncs.h"
 #include "nodes/nodeFuncs.h"
+#include "parser/parser.h"
+#include "parser/parsetree.h"
 #include "parser/parse_clause.h"
+#include "parser/parse_func.h"
+#include "parser/parse_type.h"
 #include "rewrite/rewriteHandler.h"
+#include "rewrite/rewriteManip.h"
 #include "storage/smgr.h"
 #include "tcop/tcopprot.h"
 #include "utils/builtins.h"
+#include "utils/fmgroids.h"
 #include "utils/lsyscache.h"
 #include "utils/rel.h"
 #include "utils/rls.h"
 #include "utils/snapmgr.h"
+#include "utils/syscache.h"
 
 typedef struct
 {
@@ -73,6 +90,13 @@ static bool intorel_receive(TupleTableSlot *slot, DestReceiver *self);
 static void intorel_shutdown(DestReceiver *self);
 static void intorel_destroy(DestReceiver *self);
 
+static void CreateIvmTriggersOnBaseTablesRecurse(Query *qry, Node *node, Oid matviewOid,
+									 Relids *relids, bool ex_lock);
+static void CreateIvmTrigger(Oid relOid, Oid viewOid, int16 type, int16 timing, bool ex_lock);
+static void check_ivm_restriction(Node *node);
+static bool check_ivm_restriction_walker(Node *node, void *context);
+static void CreateIndexOnIMMV(Query *query, Relation matviewRel);
+static Bitmapset *get_primary_key_attnos_from_query(Query *qry, List **constraintList);
 
 /*
  * create_ctas_internal
@@ -108,6 +132,8 @@ create_ctas_internal(List *attrList, IntoClause *into)
 	create->oncommit = into->onCommit;
 	create->tablespacename = into->tableSpaceName;
 	create->if_not_exists = false;
+	/* Using Materialized view only */
+	create->ivm = into->ivm;
 	create->accessMethod = into->accessMethod;
 
 	/*
@@ -238,6 +264,7 @@ ExecCreateTableAs(ParseState *pstate, CreateTableAsStmt *stmt,
 	List	   *rewritten;
 	PlannedStmt *plan;
 	QueryDesc  *queryDesc;
+	Query	   *query_immv = NULL;
 
 	/* Check if the relation exists or not */
 	if (CreateTableAsRelExists(stmt))
@@ -282,6 +309,22 @@ ExecCreateTableAs(ParseState *pstate, CreateTableAsStmt *stmt,
 		save_nestlevel = NewGUCNestLevel();
 	}
 
+	if (is_matview && into->ivm)
+	{
+		/* check if the query is supported in IMMV definition */
+		if (contain_mutable_functions((Node *) query))
+			ereport(ERROR,
+					(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+					 errmsg("mutable function is not supported on incrementally maintainable materialized view"),
+					 errhint("functions must be marked IMMUTABLE")));
+
+		check_ivm_restriction((Node *) query);
+
+		/* For IMMV, we need to rewrite matview query */
+		query = rewriteQueryForIMMV(query, into->colNames);
+		query_immv = copyObject(query);
+	}
+
 	if (into->skipData)
 	{
 		/*
@@ -358,11 +401,75 @@ ExecCreateTableAs(ParseState *pstate, CreateTableAsStmt *stmt,
 
 		/* Restore userid and security context */
 		SetUserIdAndSecContext(save_userid, save_sec_context);
+
+		if (into->ivm)
+		{
+			Oid matviewOid = address.objectId;
+			Relation matviewRel = table_open(matviewOid, NoLock);
+
+			/*
+			 * Mark relisivm field, if it's a matview and into->ivm is true.
+			 */
+			SetMatViewIVMState(matviewRel, true);
+
+			/* Create an index on incremental maintainable materialized view, if possible */
+			CreateIndexOnIMMV((Query *) into->viewQuery, matviewRel);
+
+			/* Create triggers on incremental maintainable materialized view */
+			if (!into->skipData)
+			{
+				Assert(query_immv != NULL);
+				CreateIvmTriggersOnBaseTables(query_immv, matviewOid, true);
+			}
+			table_close(matviewRel, NoLock);
+		}
 	}
 
 	return address;
 }
 
+/*
+ * rewriteQueryForIMMV -- rewrite view definition query for IMMV
+ *
+ * count(*) is added for counting distinct tuples in views.
+ */
+Query *
+rewriteQueryForIMMV(Query *query, List *colNames)
+{
+	Query *rewritten;
+
+	TargetEntry *tle;
+	Node *node;
+	ParseState *pstate = make_parsestate(NULL);
+	FuncCall *fn;
+
+	rewritten = copyObject(query);
+	pstate->p_expr_kind = EXPR_KIND_SELECT_TARGET;
+
+	/*
+	 * Convert DISTINCT to GROUP BY and add count(*) for counting distinct
+	 * tuples in views.
+	 */
+	if (rewritten->distinctClause)
+	{
+		rewritten->groupClause = transformDistinctClause(NULL, &rewritten->targetList, rewritten->sortClause, false);
+
+		fn = makeFuncCall(list_make1(makeString("count")), NIL, COERCE_EXPLICIT_CALL, -1);
+		fn->agg_star = true;
+
+		node = ParseFuncOrColumn(pstate, fn->funcname, NIL, NULL, fn, false, -1);
+
+		tle = makeTargetEntry((Expr *) node,
+								list_length(rewritten->targetList) + 1,
+								pstrdup("__ivm_count__"),
+								false);
+		rewritten->targetList = lappend(rewritten->targetList, tle);
+		rewritten->hasAggs = true;
+	}
+
+	return rewritten;
+}
+
 /*
  * GetIntoRelEFlags --- compute executor flags needed for CREATE TABLE AS
  *
@@ -623,3 +730,609 @@ intorel_destroy(DestReceiver *self)
 {
 	pfree(self);
 }
+
+/*
+ * CreateIvmTriggersOnBaseTables -- create IVM triggers on all base tables
+ */
+void
+CreateIvmTriggersOnBaseTables(Query *qry, Oid matviewOid, bool is_create)
+{
+	Relids	relids = NULL;
+	bool	ex_lock = false;
+	Index	first_rtindex = is_create ? 1 : PRS2_NEW_VARNO + 1;
+	RangeTblEntry *rte;
+
+	/* Immediately return if we don't have any base tables. */
+	if (list_length(qry->rtable) < first_rtindex)
+		return;
+
+	/*
+	 * If the view has more than one base tables, we need an exclusive lock
+	 * on the view so that the view would be maintained serially to avoid
+	 * the inconsistency that occurs when two base tables are modified in
+	 * concurrent transactions. However, if the view has only one table,
+	 * we can use a weaker lock.
+	 *
+	 * The type of lock should be determined here, because if we check the
+	 * view definition at maintenance time, we need to acquire a weaker lock,
+	 * and upgrading the lock level after this increases probability of
+	 * deadlock.
+	 */
+
+	rte = list_nth(qry->rtable, first_rtindex - 1);
+	if (list_length(qry->rtable) > first_rtindex ||
+		rte->rtekind != RTE_RELATION)
+		ex_lock = true;
+
+	CreateIvmTriggersOnBaseTablesRecurse(qry, (Node *)qry, matviewOid, &relids, ex_lock);
+
+	bms_free(relids);
+}
+
+static void
+CreateIvmTriggersOnBaseTablesRecurse(Query *qry, Node *node, Oid matviewOid,
+									 Relids *relids, bool ex_lock)
+{
+	if (node == NULL)
+		return;
+
+	/* This can recurse, so check for excessive recursion */
+	check_stack_depth();
+
+	switch (nodeTag(node))
+	{
+		case T_Query:
+			{
+				Query *query = (Query *) node;
+
+				CreateIvmTriggersOnBaseTablesRecurse(qry, (Node *)query->jointree, matviewOid, relids, ex_lock);
+			}
+			break;
+
+		case T_RangeTblRef:
+			{
+				int			rti = ((RangeTblRef *) node)->rtindex;
+				RangeTblEntry *rte = rt_fetch(rti, qry->rtable);
+
+				if (rte->rtekind == RTE_RELATION && !bms_is_member(rte->relid, *relids))
+				{
+					CreateIvmTrigger(rte->relid, matviewOid, TRIGGER_TYPE_INSERT, TRIGGER_TYPE_BEFORE, ex_lock);
+					CreateIvmTrigger(rte->relid, matviewOid, TRIGGER_TYPE_DELETE, TRIGGER_TYPE_BEFORE, ex_lock);
+					CreateIvmTrigger(rte->relid, matviewOid, TRIGGER_TYPE_UPDATE, TRIGGER_TYPE_BEFORE, ex_lock);
+					CreateIvmTrigger(rte->relid, matviewOid, TRIGGER_TYPE_INSERT, TRIGGER_TYPE_AFTER, ex_lock);
+					CreateIvmTrigger(rte->relid, matviewOid, TRIGGER_TYPE_DELETE, TRIGGER_TYPE_AFTER, ex_lock);
+					CreateIvmTrigger(rte->relid, matviewOid, TRIGGER_TYPE_UPDATE, TRIGGER_TYPE_AFTER, ex_lock);
+
+					*relids = bms_add_member(*relids, rte->relid);
+				}
+			}
+			break;
+
+		case T_FromExpr:
+			{
+				FromExpr   *f = (FromExpr *) node;
+				ListCell   *l;
+
+				foreach(l, f->fromlist)
+					CreateIvmTriggersOnBaseTablesRecurse(qry, lfirst(l), matviewOid, relids, ex_lock);
+			}
+			break;
+
+		case T_JoinExpr:
+			{
+				JoinExpr   *j = (JoinExpr *) node;
+
+				CreateIvmTriggersOnBaseTablesRecurse(qry, j->larg, matviewOid, relids, ex_lock);
+				CreateIvmTriggersOnBaseTablesRecurse(qry, j->rarg, matviewOid, relids, ex_lock);
+			}
+			break;
+
+		default:
+			elog(ERROR, "unrecognized node type: %d", (int) nodeTag(node));
+	}
+}
+
+/*
+ * CreateIvmTrigger -- create IVM trigger on a base table
+ */
+static void
+CreateIvmTrigger(Oid relOid, Oid viewOid, int16 type, int16 timing, bool ex_lock)
+{
+	ObjectAddress	refaddr;
+	ObjectAddress	address;
+	CreateTrigStmt *ivm_trigger;
+	List *transitionRels = NIL;
+
+	Assert(timing == TRIGGER_TYPE_BEFORE || timing == TRIGGER_TYPE_AFTER);
+
+	refaddr.classId = RelationRelationId;
+	refaddr.objectId = viewOid;
+	refaddr.objectSubId = 0;
+
+	ivm_trigger = makeNode(CreateTrigStmt);
+	ivm_trigger->relation = NULL;
+	ivm_trigger->row = false;
+
+	ivm_trigger->timing = timing;
+	ivm_trigger->events = type;
+
+	switch (type)
+	{
+		case TRIGGER_TYPE_INSERT:
+			ivm_trigger->trigname = (timing == TRIGGER_TYPE_BEFORE ? "IVM_trigger_ins_before" : "IVM_trigger_ins_after");
+			break;
+		case TRIGGER_TYPE_DELETE:
+			ivm_trigger->trigname = (timing == TRIGGER_TYPE_BEFORE ? "IVM_trigger_del_before" : "IVM_trigger_del_after");
+			break;
+		case TRIGGER_TYPE_UPDATE:
+			ivm_trigger->trigname = (timing == TRIGGER_TYPE_BEFORE ? "IVM_trigger_upd_before" : "IVM_trigger_upd_after");
+			break;
+		default:
+			elog(ERROR, "unsupported trigger type");
+	}
+
+	if (timing == TRIGGER_TYPE_AFTER)
+	{
+		if (type == TRIGGER_TYPE_INSERT || type == TRIGGER_TYPE_UPDATE)
+		{
+			TriggerTransition *n = makeNode(TriggerTransition);
+			n->name = "__ivm_newtable";
+			n->isNew = true;
+			n->isTable = true;
+
+			transitionRels = lappend(transitionRels, n);
+		}
+		if (type == TRIGGER_TYPE_DELETE || type == TRIGGER_TYPE_UPDATE)
+		{
+			TriggerTransition *n = makeNode(TriggerTransition);
+			n->name = "__ivm_oldtable";
+			n->isNew = false;
+			n->isTable = true;
+
+			transitionRels = lappend(transitionRels, n);
+		}
+	}
+
+	ivm_trigger->funcname =
+		(timing == TRIGGER_TYPE_BEFORE ? SystemFuncName("IVM_immediate_before") : SystemFuncName("IVM_immediate_maintenance"));
+
+	ivm_trigger->columns = NIL;
+	ivm_trigger->transitionRels = transitionRels;
+	ivm_trigger->whenClause = NULL;
+	ivm_trigger->isconstraint = false;
+	ivm_trigger->deferrable = false;
+	ivm_trigger->initdeferred = false;
+	ivm_trigger->constrrel = NULL;
+	ivm_trigger->args = list_make2(
+		makeString(DatumGetPointer(DirectFunctionCall1(oidout, ObjectIdGetDatum(viewOid)))),
+		makeString(DatumGetPointer(DirectFunctionCall1(boolout, BoolGetDatum(ex_lock))))
+		);
+
+	address = CreateTrigger(ivm_trigger, NULL, relOid, InvalidOid, InvalidOid,
+						 InvalidOid, InvalidOid, InvalidOid, NULL, true, false);
+
+	recordDependencyOn(&address, &refaddr, DEPENDENCY_IMMV);
+
+	/* Make changes-so-far visible */
+	CommandCounterIncrement();
+}
+
+/*
+ * check_ivm_restriction --- look for specify nodes in the query tree
+ */
+static void
+check_ivm_restriction(Node *node)
+{
+	check_ivm_restriction_walker(node, NULL);
+}
+
+static bool
+check_ivm_restriction_walker(Node *node, void *context)
+{
+	if (node == NULL)
+		return false;
+
+	/*
+	 * We currently don't support Sub-Query.
+	 */
+	if (IsA(node, SubPlan) || IsA(node, SubLink))
+		ereport(ERROR,
+				(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+				 errmsg("subquery is not supported on incrementally maintainable materialized view")));
+
+	/* This can recurse, so check for excessive recursion */
+	check_stack_depth();
+
+	switch (nodeTag(node))
+	{
+		case T_Query:
+			{
+				Query *qry = (Query *)node;
+				ListCell   *lc;
+				List       *vars;
+
+				/* if contained CTE, return error */
+				if (qry->cteList != NIL)
+					ereport(ERROR,
+							(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+							 errmsg("CTE is not supported on incrementally maintainable materialized view")));
+				if (qry->havingQual != NULL)
+					ereport(ERROR,
+							(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+							 errmsg(" HAVING clause is not supported on incrementally maintainable materialized view")));
+				if (qry->sortClause != NIL)	/* There is a possibility that we don't need to return an error */
+					ereport(ERROR,
+							(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+							 errmsg("ORDER BY clause is not supported on incrementally maintainable materialized view")));
+				if (qry->limitOffset != NULL || qry->limitCount != NULL)
+					ereport(ERROR,
+							(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+							 errmsg("LIMIT/OFFSET clause is not supported on incrementally maintainable materialized view")));
+				if (qry->hasDistinctOn)
+					ereport(ERROR,
+							(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+							 errmsg("DISTINCT ON is not supported on incrementally maintainable materialized view")));
+				if (qry->hasWindowFuncs)
+					ereport(ERROR,
+							(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+							 errmsg("window functions are not supported on incrementally maintainable materialized view")));
+				if (qry->groupingSets != NIL)
+					ereport(ERROR,
+							(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+							 errmsg("GROUPING SETS, ROLLUP, or CUBE clauses is not supported on incrementally maintainable materialized view")));
+				if (qry->setOperations != NULL)
+					ereport(ERROR,
+							(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+							 errmsg("UNION/INTERSECT/EXCEPT statements are not supported on incrementally maintainable materialized view")));
+				if (list_length(qry->targetList) == 0)
+					ereport(ERROR,
+							(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+							 errmsg("empty target list is not supported on incrementally maintainable materialized view")));
+				if (qry->rowMarks != NIL)
+					ereport(ERROR,
+							(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+							 errmsg("FOR UPDATE/SHARE clause is not supported on incrementally maintainable materialized view")));
+
+				/* system column restrictions */
+				vars = pull_vars_of_level((Node *) qry, 0);
+				foreach(lc, vars)
+				{
+					if (IsA(lfirst(lc), Var))
+					{
+						Var *var = (Var *) lfirst(lc);
+						/* if system column, return error */
+						if (var->varattno < 0)
+							ereport(ERROR,
+									(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+									 errmsg("system column is not supported on incrementally maintainable materialized view")));
+					}
+				}
+
+				/* restrictions for rtable */
+				foreach(lc, qry->rtable)
+				{
+					RangeTblEntry *rte = (RangeTblEntry *) lfirst(lc);
+
+					if (rte->subquery)
+						ereport(ERROR,
+								(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+								 errmsg("subquery is not supported on incrementally maintainable materialized view")));
+
+					if (rte->tablesample != NULL)
+						ereport(ERROR,
+								(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+								 errmsg("TABLESAMPLE clause is not supported on incrementally maintainable materialized view")));
+
+					if (rte->relkind == RELKIND_PARTITIONED_TABLE)
+						ereport(ERROR,
+								(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+								 errmsg("partitioned table is not supported on incrementally maintainable materialized view")));
+
+					if (rte->relkind == RELKIND_RELATION && has_superclass(rte->relid))
+						ereport(ERROR,
+								(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+								 errmsg("partitions is not supported on incrementally maintainable materialized view")));
+
+					if (rte->relkind == RELKIND_RELATION && find_inheritance_children(rte->relid, NoLock) != NIL)
+						ereport(ERROR,
+								(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+								 errmsg("inheritance parent is not supported on incrementally maintainable materialized view")));
+
+					if (rte->relkind == RELKIND_FOREIGN_TABLE)
+						ereport(ERROR,
+								(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+								 errmsg("foreign table is not supported on incrementally maintainable materialized view")));
+
+					if (rte->relkind == RELKIND_VIEW ||
+						rte->relkind == RELKIND_MATVIEW)
+						ereport(ERROR,
+								(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+								 errmsg("VIEW or MATERIALIZED VIEW is not supported on incrementally maintainable materialized view")));
+
+					if (rte->rtekind == RTE_VALUES)
+						ereport(ERROR,
+								(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+								 errmsg("VALUES is not supported on incrementally maintainable materialized view")));
+
+				}
+
+				query_tree_walker(qry, check_ivm_restriction_walker, NULL, QTW_IGNORE_RANGE_TABLE);
+
+				break;
+			}
+		case T_TargetEntry:
+			{
+				TargetEntry *tle = (TargetEntry *)node;
+				if (isIvmName(tle->resname))
+						ereport(ERROR,
+								(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+								 errmsg("column name %s is not supported on incrementally maintainable materialized view", tle->resname)));
+
+				expression_tree_walker(node, check_ivm_restriction_walker, NULL);
+				break;
+			}
+		case T_JoinExpr:
+			{
+				JoinExpr *joinexpr = (JoinExpr *)node;
+
+				if (joinexpr->jointype > JOIN_INNER)
+						ereport(ERROR,
+								(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+								 errmsg("OUTER JOIN is not supported on incrementally maintainable materialized view")));
+
+				expression_tree_walker(node, check_ivm_restriction_walker, NULL);
+			}
+			break;
+			expression_tree_walker(node, check_ivm_restriction_walker, NULL);
+			break;
+	}
+	return false;
+}
+
+/*
+ * CreateIndexOnIMMV
+ *
+ * Create a unique index on incremental maintainable materialized view.
+ * If the view definition query has a GROUP BY clause, the index is created
+ * on the columns of GROUP BY expressions. Otherwise, if the view contains
+ * all primary key attritubes of its base tables in the target list, the index
+ * is created on these attritubes. In other cases, no index is created.
+ */
+static void
+CreateIndexOnIMMV(Query *query, Relation matviewRel)
+{
+	Query *qry = (Query *) copyObject(query);
+	ListCell *lc;
+	IndexStmt  *index;
+	ObjectAddress address;
+	List *constraintList = NIL;
+	char		idxname[NAMEDATALEN];
+
+	snprintf(idxname, sizeof(idxname), "%s_index", RelationGetRelationName(matviewRel));
+
+	index = makeNode(IndexStmt);
+
+	index->unique = true;
+	index->primary = false;
+	index->isconstraint = false;
+	index->deferrable = false;
+	index->initdeferred = false;
+	index->idxname = idxname;
+	index->relation =
+		makeRangeVar(get_namespace_name(RelationGetNamespace(matviewRel)),
+					 pstrdup(RelationGetRelationName(matviewRel)),
+					 -1);
+	index->accessMethod = DEFAULT_INDEX_TYPE;
+	index->options = NIL;
+	index->tableSpace = get_tablespace_name(matviewRel->rd_rel->reltablespace);
+	index->whereClause = NULL;
+	index->indexParams = NIL;
+	index->indexIncludingParams = NIL;
+	index->excludeOpNames = NIL;
+	index->idxcomment = NULL;
+	index->indexOid = InvalidOid;
+	index->oldNode = InvalidOid;
+	index->oldCreateSubid = InvalidSubTransactionId;
+	index->oldFirstRelfilenodeSubid = InvalidSubTransactionId;
+	index->transformed = true;
+	index->concurrent = false;
+	index->if_not_exists = false;
+
+	if (qry->distinctClause)
+	{
+		/* create unique constraint on all columns */
+		foreach(lc, qry->targetList)
+		{
+			TargetEntry *tle = (TargetEntry *) lfirst(lc);
+			Form_pg_attribute attr = TupleDescAttr(matviewRel->rd_att, tle->resno - 1);
+			IndexElem  *iparam;
+
+			iparam = makeNode(IndexElem);
+			iparam->name = pstrdup(NameStr(attr->attname));
+			iparam->expr = NULL;
+			iparam->indexcolname = NULL;
+			iparam->collation = NIL;
+			iparam->opclass = NIL;
+			iparam->opclassopts = NIL;
+			iparam->ordering = SORTBY_DEFAULT;
+			iparam->nulls_ordering = SORTBY_NULLS_DEFAULT;
+			index->indexParams = lappend(index->indexParams, iparam);
+		}
+	}
+	else
+	{
+		Bitmapset *key_attnos;
+
+		/* create index on the base tables' primary key columns */
+		key_attnos = get_primary_key_attnos_from_query(qry, &constraintList);
+		if (key_attnos)
+		{
+			foreach(lc, qry->targetList)
+			{
+				TargetEntry *tle = (TargetEntry *) lfirst(lc);
+				Form_pg_attribute attr = TupleDescAttr(matviewRel->rd_att, tle->resno - 1);
+
+				if (bms_is_member(tle->resno - FirstLowInvalidHeapAttributeNumber, key_attnos))
+				{
+					IndexElem  *iparam;
+
+					iparam = makeNode(IndexElem);
+					iparam->name = pstrdup(NameStr(attr->attname));
+					iparam->expr = NULL;
+					iparam->indexcolname = NULL;
+					iparam->collation = NIL;
+					iparam->opclass = NIL;
+					iparam->opclassopts = NIL;
+					iparam->ordering = SORTBY_DEFAULT;
+					iparam->nulls_ordering = SORTBY_NULLS_DEFAULT;
+					index->indexParams = lappend(index->indexParams, iparam);
+				}
+			}
+
+		}
+		else
+		{
+			/* create no index, just notice that an appropriate index is necessary for efficient IVM */
+			ereport(NOTICE,
+					(errmsg("could not create an index on materialized view \"%s\" automatically",
+							RelationGetRelationName(matviewRel)),
+					 errdetail("This target list does not have all the primary key columns, "
+							   "or this view does not contain DISTINCT clause."),
+					 errhint("Create an index on the materialized view for efficient incremental maintenance.")));
+			return;
+		}
+	}
+
+	address = DefineIndex(RelationGetRelid(matviewRel),
+						  index,
+						  InvalidOid,
+						  InvalidOid,
+						  InvalidOid,
+						  false, true, false, false, true);
+
+	ereport(NOTICE,
+			(errmsg("created index \"%s\" on materialized view \"%s\"",
+					idxname, RelationGetRelationName(matviewRel))));
+
+
+	/*
+	 * Make dependencies so that the index is dropped if any base tables's
+	 * primary key is dropped.
+	 */
+	foreach(lc, constraintList)
+	{
+		Oid constraintOid = lfirst_oid(lc);
+		ObjectAddress	refaddr;
+
+		refaddr.classId = ConstraintRelationId;
+		refaddr.objectId = constraintOid;
+		refaddr.objectSubId = 0;
+
+		recordDependencyOn(&address, &refaddr, DEPENDENCY_NORMAL);
+	}
+}
+
+
+/*
+ * get_primary_key_attnos_from_query
+ *
+ * Identify the columns in base tables' primary keys in the target list.
+ *
+ * Returns a Bitmapset of the column attnos of the primary key's columns of
+ * tables that used in the query.  The attnos are offset by
+ * FirstLowInvalidHeapAttributeNumber as same as get_primary_key_attnos.
+ *
+ * If any table has no primary key or any primary key's columns is not in
+ * the target list, return NULL.  We also return NULL if any pkey constraint
+ * is deferrable.
+ *
+ * constraintList is set to a list of the OIDs of the pkey constraints.
+ */
+static Bitmapset *
+get_primary_key_attnos_from_query(Query *query, List **constraintList)
+{
+	List *key_attnos_list = NIL;
+	ListCell *lc;
+	int i;
+	Bitmapset *keys = NULL;
+	Relids	rels_in_from;
+	PlannerInfo root;
+
+
+	/*
+	 * Collect primary key attributes from all tables used in query. The key attributes
+	 * sets for each table are stored in key_attnos_list in order by RTE index.
+	 */
+	i = 1;
+	foreach(lc, query->rtable)
+	{
+		RangeTblEntry *r = (RangeTblEntry*) lfirst(lc);
+		Bitmapset *key_attnos;
+		bool	has_pkey = true;
+
+		/* for tables, call get_primary_key_attnos */
+		if (r->rtekind == RTE_RELATION)
+		{
+			Oid constraintOid;
+			key_attnos = get_primary_key_attnos(r->relid, false, &constraintOid);
+			*constraintList = lappend_oid(*constraintList, constraintOid);
+			has_pkey = (key_attnos != NULL);
+		}
+		/* for other RTEs, store NULL into key_attnos_list */
+		else
+			key_attnos = NULL;
+
+		/*
+		 * If any table or subquery has no primary key or its pkey constraint is deferrable,
+		 * we cannot get key attributes for this query, so return NULL.
+		 */
+		if (!has_pkey)
+			return NULL;
+
+		key_attnos_list = lappend(key_attnos_list, key_attnos);
+	}
+
+	/* Collect key attributes appearing in the target list */
+	i = 1;
+	foreach(lc, query->targetList)
+	{
+		TargetEntry *tle = (TargetEntry *) flatten_join_alias_vars(query, lfirst(lc));
+
+		if (IsA(tle->expr, Var))
+		{
+			Var *var = (Var*) tle->expr;
+			Bitmapset *attnos = list_nth(key_attnos_list, var->varno - 1);
+
+			/* check if this attribute is from a base table's primary key */
+			if (bms_is_member(var->varattno - FirstLowInvalidHeapAttributeNumber, attnos))
+			{
+				/*
+				 * Remove found key attributes from key_attnos_list, and add this
+				 * to the result list.
+				 */
+				bms_del_member(attnos, var->varattno - FirstLowInvalidHeapAttributeNumber);
+				keys = bms_add_member(keys, i - FirstLowInvalidHeapAttributeNumber);
+			}
+		}
+		i++;
+	}
+
+	/* Collect relations appearing in the FROM clause */
+	rels_in_from = pull_varnos_of_level(&root, (Node *)query->jointree, 0);
+
+	/*
+	 * Check if all key attributes of relations in FROM are appearing in the target
+	 * list.  If an attribute remains in key_attnos_list in spite of the table is used
+	 * in FROM clause, the target is missing this key attribute, so we return NULL.
+	 */
+	i = 1;
+	foreach(lc, key_attnos_list)
+	{
+		Bitmapset *bms = (Bitmapset *)lfirst(lc);
+		if (!bms_is_empty(bms) && bms_is_member(i, rels_in_from))
+			return NULL;
+		i++;
+	}
+
+	return keys;
+}
diff --git a/src/backend/commands/indexcmds.c b/src/backend/commands/indexcmds.c
index c14ca27c5e..5581c21298 100644
--- a/src/backend/commands/indexcmds.c
+++ b/src/backend/commands/indexcmds.c
@@ -36,6 +36,7 @@
 #include "commands/dbcommands.h"
 #include "commands/defrem.h"
 #include "commands/event_trigger.h"
+#include "commands/matview.h"
 #include "commands/progress.h"
 #include "commands/tablecmds.h"
 #include "commands/tablespace.h"
@@ -1054,6 +1055,45 @@ DefineIndex(Oid relationId,
 	safe_index = indexInfo->ii_Expressions == NIL &&
 		indexInfo->ii_Predicate == NIL;
 
+	/*
+	 * We disallow unique indexes on IVM columns of IMMVs.
+	 */
+	if (RelationIsIVM(rel) && stmt->unique)
+	{
+		for (i = 0; i < indexInfo->ii_NumIndexKeyAttrs; i++)
+		{
+			AttrNumber	attno = indexInfo->ii_IndexAttrNumbers[i];
+			if (attno > 0)
+			{
+				char *name = NameStr(TupleDescAttr(rel->rd_att, attno - 1)->attname);
+				if (name && isIvmName(name))
+					ereport(ERROR,
+							(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+							 errmsg("unique index creation on IVM columns is not supported")));
+			}
+		}
+
+		if (indexInfo->ii_Expressions)
+		{
+			Bitmapset  *indexattrs = NULL;
+			int			varno = -1;
+
+			pull_varattnos((Node *) indexInfo->ii_Expressions, 1, &indexattrs);
+
+			while ((varno = bms_next_member(indexattrs, varno)) >= 0)
+			{
+				int attno = varno + FirstLowInvalidHeapAttributeNumber;
+				char *name = NameStr(TupleDescAttr(rel->rd_att, attno - 1)->attname);
+				if (name && isIvmName(name))
+					ereport(ERROR,
+							(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+							 errmsg("unique index creation on IVM columns is not supported")));
+			}
+
+		}
+	}
+
+
 	/*
 	 * Report index creation if appropriate (delay this till after most of the
 	 * error checks)
diff --git a/src/backend/commands/matview.c b/src/backend/commands/matview.c
index 512b00bc65..70e35e5a63 100644
--- a/src/backend/commands/matview.c
+++ b/src/backend/commands/matview.c
@@ -25,26 +25,47 @@
 #include "catalog/indexing.h"
 #include "catalog/namespace.h"
 #include "catalog/pg_am.h"
+#include "catalog/pg_collation.h"
+#include "catalog/pg_depend.h"
+#include "catalog/pg_type.h"
 #include "catalog/pg_opclass.h"
 #include "catalog/pg_operator.h"
 #include "commands/cluster.h"
+#include "commands/defrem.h"
 #include "commands/matview.h"
 #include "commands/tablecmds.h"
 #include "commands/tablespace.h"
+#include "commands/createas.h"
 #include "executor/executor.h"
 #include "executor/spi.h"
+#include "executor/tstoreReceiver.h"
 #include "miscadmin.h"
+#include "nodes/makefuncs.h"
+#include "nodes/nodeFuncs.h"
+#include "optimizer/optimizer.h"
+#include "parser/analyze.h"
+#include "parser/parser.h"
+#include "parser/parsetree.h"
+#include "parser/parse_clause.h"
+#include "parser/parse_coerce.h"
+#include "parser/parse_collate.h"
+#include "parser/parse_func.h"
 #include "parser/parse_relation.h"
+#include "parser/parse_type.h"
 #include "pgstat.h"
 #include "rewrite/rewriteHandler.h"
+#include "rewrite/rewriteManip.h"
+#include "rewrite/rowsecurity.h"
 #include "storage/lmgr.h"
 #include "storage/smgr.h"
 #include "tcop/tcopprot.h"
 #include "utils/builtins.h"
+#include "utils/fmgroids.h"
 #include "utils/lsyscache.h"
 #include "utils/rel.h"
 #include "utils/snapmgr.h"
 #include "utils/syscache.h"
+#include "utils/typcache.h"
 
 
 typedef struct
@@ -58,6 +79,50 @@ typedef struct
 	BulkInsertState bistate;	/* bulk insert state */
 } DR_transientrel;
 
+#define MV_INIT_QUERYHASHSIZE	16
+
+/*
+ * MV_TriggerHashEntry
+ *
+ * Hash entry for base tables on which IVM trigger is invoked
+ */
+typedef struct MV_TriggerHashEntry
+{
+	Oid	matview_id;			/* OID of the materialized view */
+	int	before_trig_count;	/* count of before triggers invoked */
+	int	after_trig_count;	/* count of after triggers invoked */
+
+	TransactionId	xid;	/* Transaction id before the first table is modified*/
+	CommandId		cid;	/* Command id before the first table is modified */
+
+	List   *tables;		/* List of MV_TriggerTable */
+	bool	has_old;	/* tuples are deleted from any table? */
+	bool	has_new;	/* tuples are inserted into any table? */
+} MV_TriggerHashEntry;
+
+/*
+ * MV_TriggerTable
+ *
+ * IVM related data for tables on which the trigger is invoked.
+ */
+typedef struct MV_TriggerTable
+{
+	Oid		table_id;			/* OID of the modified table */
+	List   *old_tuplestores;	/* tuplestores for deleted tuples */
+	List   *new_tuplestores;	/* tuplestores for inserted tuples */
+	List   *old_rtes;			/* RTEs of ENRs for old_tuplestores*/
+	List   *new_rtes;			/* RTEs of ENRs for new_tuplestores */
+
+	List   *rte_indexes;		/* List of RTE index of the modified table */
+	RangeTblEntry *original_rte;	/* the original RTE saved before rewriting query */
+} MV_TriggerTable;
+
+static HTAB *mv_trigger_info = NULL;
+
+/* ENR name for materialized view delta */
+#define NEW_DELTA_ENRNAME "new_delta"
+#define OLD_DELTA_ENRNAME "old_delta"
+
 static int	matview_maintenance_depth = 0;
 
 static void transientrel_startup(DestReceiver *self, int operation, TupleDesc typeinfo);
@@ -65,7 +130,9 @@ static bool transientrel_receive(TupleTableSlot *slot, DestReceiver *self);
 static void transientrel_shutdown(DestReceiver *self);
 static void transientrel_destroy(DestReceiver *self);
 static uint64 refresh_matview_datafill(DestReceiver *dest, Query *query,
-									   const char *queryString);
+						 QueryEnvironment *queryEnv,
+						 TupleDesc *resultTupleDesc,
+						 const char *queryString);
 static char *make_temptable_name_n(char *tempname, int n);
 static void refresh_by_match_merge(Oid matviewOid, Oid tempOid, Oid relowner,
 								   int save_sec_context);
@@ -73,6 +140,45 @@ static void refresh_by_heap_swap(Oid matviewOid, Oid OIDNewHeap, char relpersist
 static bool is_usable_unique_index(Relation indexRel);
 static void OpenMatViewIncrementalMaintenance(void);
 static void CloseMatViewIncrementalMaintenance(void);
+static Query *get_matview_query(Relation matviewRel);
+
+static Query *rewrite_query_for_preupdate_state(Query *query, List *tables,
+								  TransactionId xid, CommandId cid,
+								  ParseState *pstate);
+static void register_delta_ENRs(ParseState *pstate, Query *query, List *tables);
+static char *make_delta_enr_name(const char *prefix, Oid relid, int count);
+static RangeTblEntry *get_prestate_rte(RangeTblEntry *rte, MV_TriggerTable *table,
+				 TransactionId xid, CommandId cid,
+				 QueryEnvironment *queryEnv);
+static RangeTblEntry *union_ENRs(RangeTblEntry *rte, Oid relid, List *enr_rtes, const char *prefix,
+		   QueryEnvironment *queryEnv);
+static Query *rewrite_query_for_distinct(Query *query, ParseState *pstate);
+
+static void calc_delta(MV_TriggerTable *table, int rte_index, Query *query,
+			DestReceiver *dest_old, DestReceiver *dest_new,
+			TupleDesc *tupdesc_old, TupleDesc *tupdesc_new,
+			QueryEnvironment *queryEnv);
+static Query *rewrite_query_for_postupdate_state(Query *query, MV_TriggerTable *table, int rte_index);
+
+static void apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *new_tuplestores,
+			TupleDesc tupdesc_old, TupleDesc tupdesc_new,
+			Query *query, bool use_count, char *count_colname);
+static void apply_old_delta(const char *matviewname, const char *deltaname_old,
+				List *keys);
+static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old,
+				List *keys, const char *count_colname);
+static void apply_new_delta(const char *matviewname, const char *deltaname_new,
+				StringInfo target_list);
+static void apply_new_delta_with_count(const char *matviewname, const char* deltaname_new,
+				List *keys, StringInfo target_list, const char* count_colname);
+static char *get_matching_condition_string(List *keys);
+static void generate_equal(StringInfo querybuf, Oid opttype,
+			   const char *leftop, const char *rightop);
+
+static void mv_InitHashTables(void);
+static void clean_up_IVM_hash_entry(MV_TriggerHashEntry *entry);
+
+static List *get_securityQuals(Oid relId, int rt_index, Query *query);
 
 /*
  * SetMatViewPopulatedState
@@ -114,6 +220,46 @@ SetMatViewPopulatedState(Relation relation, bool newstate)
 	CommandCounterIncrement();
 }
 
+/*
+ * SetMatViewIVMState
+ *		Mark a materialized view as IVM, or not.
+ *
+ * NOTE: caller must be holding an appropriate lock on the relation.
+ */
+void
+SetMatViewIVMState(Relation relation, bool newstate)
+{
+	Relation	pgrel;
+	HeapTuple	tuple;
+
+	Assert(relation->rd_rel->relkind == RELKIND_MATVIEW);
+
+	/*
+	 * Update relation's pg_class entry.  Crucial side-effect: other backends
+	 * (and this one too!) are sent SI message to make them rebuild relcache
+	 * entries.
+	 */
+	pgrel = table_open(RelationRelationId, RowExclusiveLock);
+	tuple = SearchSysCacheCopy1(RELOID,
+								ObjectIdGetDatum(RelationGetRelid(relation)));
+	if (!HeapTupleIsValid(tuple))
+		elog(ERROR, "cache lookup failed for relation %u",
+			 RelationGetRelid(relation));
+
+	((Form_pg_class) GETSTRUCT(tuple))->relisivm = newstate;
+
+	CatalogTupleUpdate(pgrel, &tuple->t_self, tuple);
+
+	heap_freetuple(tuple);
+	table_close(pgrel, RowExclusiveLock);
+
+	/*
+	 * Advance command counter to make the updated pg_class row locally
+	 * visible.
+	 */
+	CommandCounterIncrement();
+}
+
 /*
  * ExecRefreshMatView -- execute a REFRESH MATERIALIZED VIEW command
  *
@@ -140,8 +286,6 @@ ExecRefreshMatView(RefreshMatViewStmt *stmt, const char *queryString,
 {
 	Oid			matviewOid;
 	Relation	matviewRel;
-	RewriteRule *rule;
-	List	   *actions;
 	Query	   *dataQuery;
 	Oid			tableSpace;
 	Oid			relowner;
@@ -155,6 +299,7 @@ ExecRefreshMatView(RefreshMatViewStmt *stmt, const char *queryString,
 	int			save_sec_context;
 	int			save_nestlevel;
 	ObjectAddress address;
+	bool oldPopulated;
 
 	/* Determine strength of lock needed. */
 	concurrent = stmt->concurrent;
@@ -167,6 +312,7 @@ ExecRefreshMatView(RefreshMatViewStmt *stmt, const char *queryString,
 										  lockmode, 0,
 										  RangeVarCallbackOwnsTable, NULL);
 	matviewRel = table_open(matviewOid, NoLock);
+	oldPopulated = RelationIsPopulated(matviewRel);
 
 	/* Make sure it is a materialized view. */
 	if (matviewRel->rd_rel->relkind != RELKIND_MATVIEW)
@@ -187,32 +333,12 @@ ExecRefreshMatView(RefreshMatViewStmt *stmt, const char *queryString,
 				(errcode(ERRCODE_SYNTAX_ERROR),
 				 errmsg("CONCURRENTLY and WITH NO DATA options cannot be used together")));
 
-	/*
-	 * Check that everything is correct for a refresh. Problems at this point
-	 * are internal errors, so elog is sufficient.
-	 */
-	if (matviewRel->rd_rel->relhasrules == false ||
-		matviewRel->rd_rules->numLocks < 1)
-		elog(ERROR,
-			 "materialized view \"%s\" is missing rewrite information",
-			 RelationGetRelationName(matviewRel));
-
-	if (matviewRel->rd_rules->numLocks > 1)
-		elog(ERROR,
-			 "materialized view \"%s\" has too many rules",
-			 RelationGetRelationName(matviewRel));
 
-	rule = matviewRel->rd_rules->rules[0];
-	if (rule->event != CMD_SELECT || !(rule->isInstead))
-		elog(ERROR,
-			 "the rule for materialized view \"%s\" is not a SELECT INSTEAD OF rule",
-			 RelationGetRelationName(matviewRel));
+	dataQuery = get_matview_query(matviewRel);
 
-	actions = rule->actions;
-	if (list_length(actions) != 1)
-		elog(ERROR,
-			 "the rule for materialized view \"%s\" is not a single action",
-			 RelationGetRelationName(matviewRel));
+	/* For IMMV, we need to rewrite matview query */
+	if (!stmt->skipData && RelationIsIVM(matviewRel))
+		dataQuery = rewriteQueryForIMMV(dataQuery,NIL);
 
 	/*
 	 * Check that there is a unique index with no WHERE clause on one or more
@@ -247,12 +373,6 @@ ExecRefreshMatView(RefreshMatViewStmt *stmt, const char *queryString,
 					 errhint("Create a unique index with no WHERE clause on one or more columns of the materialized view.")));
 	}
 
-	/*
-	 * The stored query was rewritten at the time of the MV definition, but
-	 * has not been scribbled on by the planner.
-	 */
-	dataQuery = linitial_node(Query, actions);
-
 	/*
 	 * Check for active uses of the relation in the current transaction, such
 	 * as open scans.
@@ -293,6 +413,52 @@ ExecRefreshMatView(RefreshMatViewStmt *stmt, const char *queryString,
 		relpersistence = matviewRel->rd_rel->relpersistence;
 	}
 
+	/* delete immv triggers */
+	if (RelationIsIVM(matviewRel) && stmt->skipData )
+	{
+		/* use deleted trigger */
+		Relation	depRel;
+		ScanKeyData key;
+		SysScanDesc scan;
+		HeapTuple	tup;
+		ObjectAddresses *immv_triggers;
+
+		immv_triggers = new_object_addresses();
+
+		/*
+		 * We save some cycles by opening pg_depend just once and passing the
+		 * Relation pointer down to all the recursive deletion steps.
+		 */
+		depRel = table_open(DependRelationId, RowExclusiveLock);
+
+		ScanKeyInit(&key,
+					Anum_pg_depend_refobjid,
+					BTEqualStrategyNumber, F_OIDEQ,
+					ObjectIdGetDatum(matviewOid));
+
+		scan = systable_beginscan(depRel, DependReferenceIndexId, true,
+								  NULL, 1, &key);
+		while ((tup = systable_getnext(scan)) != NULL)
+		{
+			ObjectAddress obj;
+			Form_pg_depend foundDep = (Form_pg_depend) GETSTRUCT(tup);
+
+			if (foundDep->deptype == DEPENDENCY_IMMV)
+			{
+				obj.classId = foundDep->classid;
+				obj.objectId = foundDep->objid;
+				obj.objectSubId = foundDep->refobjsubid;
+				add_exact_object_address(&obj, immv_triggers);
+			}
+		}
+		systable_endscan(scan);
+
+		performMultipleDeletions(immv_triggers, DROP_RESTRICT, PERFORM_DELETION_INTERNAL);
+
+		table_close(depRel, RowExclusiveLock);
+		free_object_addresses(immv_triggers);
+	}
+
 	/*
 	 * Create the transient table that will receive the regenerated data. Lock
 	 * it against access by any other process until commit (by which time it
@@ -312,7 +478,7 @@ ExecRefreshMatView(RefreshMatViewStmt *stmt, const char *queryString,
 
 	/* Generate the data, if wanted. */
 	if (!stmt->skipData)
-		processed = refresh_matview_datafill(dest, dataQuery, queryString);
+		processed = refresh_matview_datafill(dest, dataQuery, NULL, NULL, queryString);
 
 	/* Make the matview match the newly generated data. */
 	if (concurrent)
@@ -347,6 +513,9 @@ ExecRefreshMatView(RefreshMatViewStmt *stmt, const char *queryString,
 			pgstat_count_heap_insert(matviewRel, processed);
 	}
 
+	if (!stmt->skipData && RelationIsIVM(matviewRel) && !oldPopulated)
+		CreateIvmTriggersOnBaseTables(dataQuery, matviewOid, false);
+
 	table_close(matviewRel, NoLock);
 
 	/* Roll back any GUC changes */
@@ -381,6 +550,8 @@ ExecRefreshMatView(RefreshMatViewStmt *stmt, const char *queryString,
  */
 static uint64
 refresh_matview_datafill(DestReceiver *dest, Query *query,
+						 QueryEnvironment *queryEnv,
+						 TupleDesc *resultTupleDesc,
 						 const char *queryString)
 {
 	List	   *rewritten;
@@ -417,7 +588,7 @@ refresh_matview_datafill(DestReceiver *dest, Query *query,
 	/* Create a QueryDesc, redirecting output to our tuple receiver */
 	queryDesc = CreateQueryDesc(plan, queryString,
 								GetActiveSnapshot(), InvalidSnapshot,
-								dest, NULL, NULL, 0);
+								dest, NULL, queryEnv ? queryEnv: NULL, 0);
 
 	/* call ExecutorStart to prepare the plan for execution */
 	ExecutorStart(queryDesc, 0);
@@ -427,6 +598,9 @@ refresh_matview_datafill(DestReceiver *dest, Query *query,
 
 	processed = queryDesc->estate->es_processed;
 
+	if (resultTupleDesc)
+		*resultTupleDesc = CreateTupleDescCopy(queryDesc->tupDesc);
+
 	/* and clean up */
 	ExecutorFinish(queryDesc);
 	ExecutorEnd(queryDesc);
@@ -941,3 +1115,1308 @@ CloseMatViewIncrementalMaintenance(void)
 	matview_maintenance_depth--;
 	Assert(matview_maintenance_depth >= 0);
 }
+
+/*
+ * get_matview_query - get the Query from a matview's _RETURN rule.
+ */
+static Query *
+get_matview_query(Relation matviewRel)
+{
+	RewriteRule *rule;
+	List * actions;
+
+	/*
+	 * Check that everything is correct for a refresh. Problems at this point
+	 * are internal errors, so elog is sufficient.
+	 */
+	if (matviewRel->rd_rel->relhasrules == false ||
+		matviewRel->rd_rules->numLocks < 1)
+		elog(ERROR,
+			 "materialized view \"%s\" is missing rewrite information",
+			 RelationGetRelationName(matviewRel));
+
+	if (matviewRel->rd_rules->numLocks > 1)
+		elog(ERROR,
+			 "materialized view \"%s\" has too many rules",
+			 RelationGetRelationName(matviewRel));
+
+	rule = matviewRel->rd_rules->rules[0];
+	if (rule->event != CMD_SELECT || !(rule->isInstead))
+		elog(ERROR,
+			 "the rule for materialized view \"%s\" is not a SELECT INSTEAD OF rule",
+			 RelationGetRelationName(matviewRel));
+
+	actions = rule->actions;
+	if (list_length(actions) != 1)
+		elog(ERROR,
+			 "the rule for materialized view \"%s\" is not a single action",
+			 RelationGetRelationName(matviewRel));
+
+	/*
+	 * The stored query was rewritten at the time of the MV definition, but
+	 * has not been scribbled on by the planner.
+	 */
+	return linitial_node(Query, actions);
+}
+
+
+/* ----------------------------------------------------
+ *		Incremental View Maintenance routines
+ * ---------------------------------------------------
+ */
+
+/*
+ * IVM_immediate_before
+ *
+ * IVM trigger function invoked before base table is modified. If this is
+ * invoked firstly in the same statement, we save the transaction id and the
+ * command id at that time.
+ */
+Datum
+IVM_immediate_before(PG_FUNCTION_ARGS)
+{
+	TriggerData *trigdata = (TriggerData *) fcinfo->context;
+	char	   *matviewOid_text = trigdata->tg_trigger->tgargs[0];
+	char	   *ex_lock_text = trigdata->tg_trigger->tgargs[1];
+	Oid			matviewOid;
+	MV_TriggerHashEntry *entry;
+	bool	found;
+	bool	ex_lock;
+
+	matviewOid = DatumGetObjectId(DirectFunctionCall1(oidin, CStringGetDatum(matviewOid_text)));
+	ex_lock = DatumGetBool(DirectFunctionCall1(boolin, CStringGetDatum(ex_lock_text)));
+
+	/* If the view has more than one tables, we have to use an exclusive lock. */
+	if (ex_lock)
+	{
+		/*
+		 * Wait for concurrent transactions which update this materialized view at
+		 * READ COMMITED. This is needed to see changes committed in other
+		 * transactions. No wait and raise an error at REPEATABLE READ or
+		 * SERIALIZABLE to prevent update anomalies of matviews.
+		 * XXX: dead-lock is possible here.
+		 */
+		if (!IsolationUsesXactSnapshot())
+			LockRelationOid(matviewOid, ExclusiveLock);
+		else if (!ConditionalLockRelationOid(matviewOid, ExclusiveLock))
+		{
+			/* try to throw error by name; relation could be deleted... */
+			char	   *relname = get_rel_name(matviewOid);
+
+			if (!relname)
+				ereport(ERROR,
+						(errcode(ERRCODE_LOCK_NOT_AVAILABLE),
+						errmsg("could not obtain lock on materialized view during incremental maintenance")));
+
+			ereport(ERROR,
+					(errcode(ERRCODE_LOCK_NOT_AVAILABLE),
+					errmsg("could not obtain lock on materialized view \"%s\" during incremental maintenance",
+							relname)));
+		}
+	}
+	else
+		LockRelationOid(matviewOid, RowExclusiveLock);
+
+	/*
+	 * On the first call initialize the hashtable
+	 */
+	if (!mv_trigger_info)
+		mv_InitHashTables();
+
+	entry = (MV_TriggerHashEntry *) hash_search(mv_trigger_info,
+											  (void *) &matviewOid,
+											  HASH_ENTER, &found);
+
+	/* On the first BEFORE to update the view, initialize trigger data */
+	if (!found)
+	{
+		Snapshot snapshot = GetActiveSnapshot();
+
+		entry->matview_id = matviewOid;
+		entry->before_trig_count = 0;
+		entry->after_trig_count = 0;
+		entry->xid = GetCurrentTransactionId();
+		entry->cid = snapshot->curcid;
+		entry->tables = NIL;
+		entry->has_old = false;
+		entry->has_new = false;
+	}
+
+	entry->before_trig_count++;
+
+	return PointerGetDatum(NULL);
+}
+
+/*
+ * IVM_immediate_before
+ *
+ * IVM trigger function invoked after base table is modified.
+ * For each table, tuplestores of transition tables are collected.
+ * and after the last modification
+ */
+Datum
+IVM_immediate_maintenance(PG_FUNCTION_ARGS)
+{
+	TriggerData *trigdata = (TriggerData *) fcinfo->context;
+	Relation	rel;
+	Oid			relid;
+	Oid			matviewOid;
+	Query	   *query;
+	Query	   *rewritten = NULL;
+	char	   *matviewOid_text = trigdata->tg_trigger->tgargs[0];
+	Relation	matviewRel;
+	int old_depth = matview_maintenance_depth;
+
+	Oid			relowner;
+	Tuplestorestate *old_tuplestore = NULL;
+	Tuplestorestate *new_tuplestore = NULL;
+	DestReceiver *dest_new = NULL, *dest_old = NULL;
+	Oid			save_userid;
+	int			save_sec_context;
+	int			save_nestlevel;
+
+	MV_TriggerHashEntry *entry;
+	MV_TriggerTable		*table;
+	bool	found;
+
+	ParseState		 *pstate;
+	QueryEnvironment *queryEnv = create_queryEnv();
+	MemoryContext	oldcxt;
+	ListCell   *lc;
+	int			i;
+
+
+	/* Create a ParseState for rewriting the view definition query */
+	pstate = make_parsestate(NULL);
+	pstate->p_queryEnv = queryEnv;
+	pstate->p_expr_kind = EXPR_KIND_SELECT_TARGET;
+
+	rel = trigdata->tg_relation;
+	relid = rel->rd_id;
+
+	matviewOid = DatumGetObjectId(DirectFunctionCall1(oidin, CStringGetDatum(matviewOid_text)));
+
+	/*
+	 * On the first call initialize the hashtable
+	 */
+	if (!mv_trigger_info)
+		mv_InitHashTables();
+
+	/* get the entry for this materialized view */
+	entry = (MV_TriggerHashEntry *) hash_search(mv_trigger_info,
+											  (void *) &matviewOid,
+											  HASH_FIND, &found);
+	Assert (found && entry != NULL);
+	entry->after_trig_count++;
+
+	/* search the entry for the modified table and create new entry if not found */
+	found = false;
+	foreach(lc, entry->tables)
+	{
+		table = (MV_TriggerTable *) lfirst(lc);
+		if (table->table_id == relid)
+		{
+			found = true;
+			break;
+		}
+	}
+	if (!found)
+	{
+		oldcxt = MemoryContextSwitchTo(TopTransactionContext);
+
+		table = (MV_TriggerTable *) palloc0(sizeof(MV_TriggerTable));
+		table->table_id = relid;
+		table->old_tuplestores = NIL;
+		table->new_tuplestores = NIL;
+		table->old_rtes = NIL;
+		table->new_rtes = NIL;
+		table->rte_indexes = NIL;
+		entry->tables = lappend(entry->tables, table);
+
+		MemoryContextSwitchTo(oldcxt);
+	}
+
+	/* Save the transition tables and make a request to not free immediately */
+	if (trigdata->tg_oldtable)
+	{
+		oldcxt = MemoryContextSwitchTo(TopTransactionContext);
+		table->old_tuplestores = lappend(table->old_tuplestores, trigdata->tg_oldtable);
+		entry->has_old = true;
+		MemoryContextSwitchTo(oldcxt);
+	}
+	if (trigdata->tg_newtable)
+	{
+		oldcxt = MemoryContextSwitchTo(TopTransactionContext);
+		table->new_tuplestores = lappend(table->new_tuplestores, trigdata->tg_newtable);
+		entry->has_new = true;
+		MemoryContextSwitchTo(oldcxt);
+	}
+	if (entry->has_new || entry->has_old)
+	{
+		CmdType cmd;
+
+		if (TRIGGER_FIRED_BY_INSERT(trigdata->tg_event))
+			cmd = CMD_INSERT;
+		else if (TRIGGER_FIRED_BY_DELETE(trigdata->tg_event))
+			cmd = CMD_DELETE;
+		else if (TRIGGER_FIRED_BY_UPDATE(trigdata->tg_event))
+			cmd = CMD_UPDATE;
+		else
+			elog(ERROR,"unsupported trigger type");
+
+		/* Prolong lifespan of transition tables to the end of the last AFTER trigger */
+		SetTransitionTablePreserved(relid, cmd);
+	}
+
+
+	/* If this is not the last AFTER trigger call, immediately exit. */
+	Assert (entry->before_trig_count >= entry->after_trig_count);
+	if (entry->before_trig_count != entry->after_trig_count)
+		return PointerGetDatum(NULL);
+
+	/*
+	 * If this is the last AFTER trigger call, continue and update the view.
+	 */
+
+	/*
+	 * Advance command counter to make the updated base table row locally
+	 * visible.
+	 */
+	CommandCounterIncrement();
+
+	matviewRel = table_open(matviewOid, NoLock);
+
+	/* get view query*/
+	query = get_matview_query(matviewRel);
+
+	/* Make sure it is a materialized view. */
+	Assert(matviewRel->rd_rel->relkind == RELKIND_MATVIEW);
+
+	/*
+	 * Get and push the latast snapshot to see any changes which is committed
+	 * during waiting in other transactions at READ COMMITTED level.
+	 */
+	PushActiveSnapshot(GetTransactionSnapshot());
+
+	/*
+	 * Check for active uses of the relation in the current transaction, such
+	 * as open scans.
+	 *
+	 * NB: We count on this to protect us against problems with refreshing the
+	 * data using TABLE_INSERT_FROZEN.
+	 */
+	CheckTableNotInUse(matviewRel, "refresh a materialized view incrementally");
+
+	/*
+	 * Switch to the owner's userid, so that any functions are run as that
+	 * user.  Also arrange to make GUC variable changes local to this command.
+	 * We will switch modes when we are about to execute user code.
+	 */
+	relowner = matviewRel->rd_rel->relowner;
+	GetUserIdAndSecContext(&save_userid, &save_sec_context);
+	SetUserIdAndSecContext(relowner,
+						   save_sec_context | SECURITY_RESTRICTED_OPERATION);
+	save_nestlevel = NewGUCNestLevel();
+
+	/*
+	 * rewrite query for calculating deltas
+	 */
+
+	rewritten = copyObject(query);
+
+	/* Replace resnames in a target list with materialized view's attnames */
+	i = 0;
+	foreach (lc, rewritten->targetList)
+	{
+		TargetEntry *tle = (TargetEntry *) lfirst(lc);
+		Form_pg_attribute attr = TupleDescAttr(matviewRel->rd_att, i);
+		char *resname = NameStr(attr->attname);
+
+		tle->resname = pstrdup(resname);
+		i++;
+	}
+
+	/* Set all tables in the query to pre-update state */
+	rewritten = rewrite_query_for_preupdate_state(rewritten, entry->tables,
+												  entry->xid, entry->cid,
+												  pstate);
+	/* Rewrite for DISTINCT clause */
+	rewritten = rewrite_query_for_distinct(rewritten, pstate);
+
+	/* Create tuplestores to store view deltas */
+	if (entry->has_old)
+	{
+		oldcxt = MemoryContextSwitchTo(TopTransactionContext);
+
+		old_tuplestore = tuplestore_begin_heap(false, false, work_mem);
+		dest_old = CreateDestReceiver(DestTuplestore);
+		SetTuplestoreDestReceiverParams(dest_old,
+									old_tuplestore,
+									TopTransactionContext,
+									false,
+									NULL,
+									NULL);
+
+		MemoryContextSwitchTo(oldcxt);
+	}
+	if (entry->has_new)
+	{
+		oldcxt = MemoryContextSwitchTo(TopTransactionContext);
+
+		new_tuplestore = tuplestore_begin_heap(false, false, work_mem);
+		dest_new = CreateDestReceiver(DestTuplestore);
+		SetTuplestoreDestReceiverParams(dest_new,
+									new_tuplestore,
+									TopTransactionContext,
+									false,
+									NULL,
+									NULL);
+		MemoryContextSwitchTo(oldcxt);
+	}
+
+	/* for all modified tables */
+	foreach(lc, entry->tables)
+	{
+		ListCell *lc2;
+
+		table = (MV_TriggerTable *) lfirst(lc);
+
+		/* loop for self-join */
+		foreach(lc2, table->rte_indexes)
+		{
+			int	rte_index = lfirst_int(lc2);
+			TupleDesc		tupdesc_old;
+			TupleDesc		tupdesc_new;
+			bool	use_count = false;
+			char   *count_colname = NULL;
+
+			count_colname = pstrdup("__ivm_count__");
+
+			if (query->distinctClause)
+				use_count = true;
+
+			/* calculate delta tables */
+			calc_delta(table, rte_index, rewritten, dest_old, dest_new,
+					   &tupdesc_old, &tupdesc_new, queryEnv);
+
+			/* Set the table in the query to post-update state */
+			rewritten = rewrite_query_for_postupdate_state(rewritten, table, rte_index);
+
+			PG_TRY();
+			{
+				/* apply the delta tables to the materialized view */
+				apply_delta(matviewOid, old_tuplestore, new_tuplestore,
+							tupdesc_old, tupdesc_new, query, use_count,
+							count_colname);
+			}
+			PG_CATCH();
+			{
+				matview_maintenance_depth = old_depth;
+				PG_RE_THROW();
+			}
+			PG_END_TRY();
+
+			/* clear view delta tuplestores */
+			if (old_tuplestore)
+				tuplestore_clear(old_tuplestore);
+			if (new_tuplestore)
+				tuplestore_clear(new_tuplestore);
+		}
+	}
+
+	/* Clean up hash entry and delete tuplestores */
+	clean_up_IVM_hash_entry(entry);
+	if (old_tuplestore)
+	{
+		dest_old->rDestroy(dest_old);
+		tuplestore_end(old_tuplestore);
+	}
+	if (new_tuplestore)
+	{
+		dest_new->rDestroy(dest_new);
+		tuplestore_end(new_tuplestore);
+	}
+
+	/* Pop the original snapshot. */
+	PopActiveSnapshot();
+
+	table_close(matviewRel, NoLock);
+
+	/* Roll back any GUC changes */
+	AtEOXact_GUC(false, save_nestlevel);
+
+	/* Restore userid and security context */
+	SetUserIdAndSecContext(save_userid, save_sec_context);
+
+	return PointerGetDatum(NULL);
+}
+
+/*
+ * rewrite_query_for_preupdate_state
+ *
+ * Rewrite the query so that base tables' RTEs will represent "pre-update"
+ * state of tables. This is necessary to calculate view delta after multiple
+ * tables are modified. xid and cid are the transaction id and command id
+ * before the first table was modified.
+ */
+static Query*
+rewrite_query_for_preupdate_state(Query *query, List *tables,
+								  TransactionId xid, CommandId cid,
+								  ParseState *pstate)
+{
+	ListCell *lc;
+	int num_rte = list_length(query->rtable);
+	int i;
+
+
+	/* register delta ENRs */
+	register_delta_ENRs(pstate, query, tables);
+
+	/* XXX: Is necessary? Is this right timing? */
+	AcquireRewriteLocks(query, true, false);
+
+	i = 1;
+	foreach(lc, query->rtable)
+	{
+		RangeTblEntry *r = (RangeTblEntry*) lfirst(lc);
+
+		ListCell *lc2;
+		foreach(lc2, tables)
+		{
+			MV_TriggerTable *table = (MV_TriggerTable *) lfirst(lc2);
+			/*
+			 * if the modified table is found then replace the original RTE with
+			 * "pre-state" RTE and append its index to the list.
+			 */
+			if (r->relid == table->table_id)
+			{
+				lfirst(lc) = get_prestate_rte(r, table, xid, cid, pstate->p_queryEnv);
+				table->rte_indexes = lappend_int(table->rte_indexes, i);
+				break;
+			}
+		}
+
+		/* finish the loop if we processed all RTE included in the original query */
+		if (i++ >= num_rte)
+			break;
+	}
+
+	return query;
+}
+
+/*
+ * register_delta_ENRs
+ *
+ * For all modified tables, make ENRs for their transition tables
+ * and register them to the queryEnv. ENR's RTEs are also appended
+ * into the list in query tree.
+ */
+static void
+register_delta_ENRs(ParseState *pstate, Query *query, List *tables)
+{
+	QueryEnvironment *queryEnv = pstate->p_queryEnv;
+	ListCell *lc;
+	RangeTblEntry	*rte;
+
+	foreach(lc, tables)
+	{
+		MV_TriggerTable *table = (MV_TriggerTable *) lfirst(lc);
+		ListCell *lc2;
+		int count;
+
+		count = 0;
+		foreach(lc2, table->old_tuplestores)
+		{
+			Tuplestorestate *oldtable = (Tuplestorestate *) lfirst(lc2);
+			EphemeralNamedRelation enr =
+				palloc(sizeof(EphemeralNamedRelationData));
+			ParseNamespaceItem *nsitem;
+
+			enr->md.name = make_delta_enr_name("old", table->table_id, count);
+			enr->md.reliddesc = table->table_id;
+			enr->md.tupdesc = NULL;
+			enr->md.enrtype = ENR_NAMED_TUPLESTORE;
+			enr->md.enrtuples = tuplestore_tuple_count(oldtable);
+			enr->reldata = oldtable;
+			register_ENR(queryEnv, enr);
+
+			nsitem = addRangeTableEntryForENR(pstate, makeRangeVar(NULL, enr->md.name, -1), true);
+			rte = nsitem->p_rte;
+			/* if base table has RLS, set security condition to enr */
+			rte->securityQuals = get_securityQuals(table->table_id, list_length(query->rtable) + 1, query);
+
+			query->rtable = lappend(query->rtable, rte);
+			table->old_rtes = lappend(table->old_rtes, rte);
+
+			count++;
+		}
+
+		count = 0;
+		foreach(lc2, table->new_tuplestores)
+		{
+			Tuplestorestate *newtable = (Tuplestorestate *) lfirst(lc2);
+			EphemeralNamedRelation enr =
+				palloc(sizeof(EphemeralNamedRelationData));
+			ParseNamespaceItem *nsitem;
+
+			enr->md.name = make_delta_enr_name("new", table->table_id, count);
+			enr->md.reliddesc = table->table_id;
+			enr->md.tupdesc = NULL;
+			enr->md.enrtype = ENR_NAMED_TUPLESTORE;
+			enr->md.enrtuples = tuplestore_tuple_count(newtable);
+			enr->reldata = newtable;
+			register_ENR(queryEnv, enr);
+
+			nsitem = addRangeTableEntryForENR(pstate, makeRangeVar(NULL, enr->md.name, -1), true);
+			rte = nsitem->p_rte;
+			/* if base table has RLS, set security condition to enr*/
+			rte->securityQuals = get_securityQuals(table->table_id, list_length(query->rtable) + 1, query);
+
+			query->rtable = lappend(query->rtable, rte);
+			table->new_rtes = lappend(table->new_rtes, rte);
+
+			count++;
+		}
+	}
+}
+
+/*
+ * get_prestate_rte
+ *
+ * Rewrite RTE of the modified table to a subquery which represents
+ * "pre-state" table. The original RTE is saved in table->rte_original.
+ */
+static RangeTblEntry*
+get_prestate_rte(RangeTblEntry *rte, MV_TriggerTable *table,
+				 TransactionId xid, CommandId cid,
+				 QueryEnvironment *queryEnv)
+{
+	StringInfoData str;
+	RawStmt *raw;
+	Query *sub;
+	Relation rel;
+	ParseState *pstate;
+	char *relname;
+	int i;
+
+	pstate = make_parsestate(NULL);
+	pstate->p_queryEnv = queryEnv;
+	pstate->p_expr_kind = EXPR_KIND_SELECT_TARGET;
+
+	/*
+	 * We can use NoLock here since AcquireRewriteLocks should
+	 * have locked the rel already.
+	 */
+	rel = table_open(table->table_id, NoLock);
+	relname = quote_qualified_identifier(
+					get_namespace_name(RelationGetNamespace(rel)),
+									   RelationGetRelationName(rel));
+	table_close(rel, NoLock);
+
+	initStringInfo(&str);
+	appendStringInfo(&str,
+		"SELECT t.* FROM %s t"
+		" WHERE (age(t.xmin) - age(%u::text::xid) > 0) OR"
+		" (t.xmin = %u AND t.cmin::text::int < %u)",
+			relname, xid, xid, cid);
+
+	for (i = 0; i < list_length(table->old_tuplestores); i++)
+	{
+		appendStringInfo(&str, " UNION ALL ");
+		appendStringInfo(&str," SELECT * FROM %s",
+			make_delta_enr_name("old", table->table_id, i));
+	}
+
+	raw = (RawStmt*)linitial(raw_parser(str.data, RAW_PARSE_DEFAULT));
+	sub = transformStmt(pstate, raw->stmt);
+
+	/* If this query has setOperations, RTEs in rtables has a subquery which contains ENR */
+	if (sub->setOperations != NULL)
+	{
+		ListCell *lc;
+
+		/* add securityQuals for tuplestores */
+		foreach (lc, sub->rtable)
+		{
+			RangeTblEntry *rte;
+			RangeTblEntry *sub_rte;
+
+			rte = (RangeTblEntry *)lfirst(lc);
+			Assert(rte->subquery != NULL);
+
+			sub_rte = (RangeTblEntry *)linitial(rte->subquery->rtable);
+			if (sub_rte->rtekind == RTE_NAMEDTUPLESTORE)
+				/* rt_index is always 1, bacause subquery has enr_rte only */
+				sub_rte->securityQuals = get_securityQuals(sub_rte->relid, 1, sub);
+		}
+	}
+
+	/* save the original RTE */
+	table->original_rte = copyObject(rte);
+
+	rte->rtekind = RTE_SUBQUERY;
+	rte->subquery = sub;
+	rte->security_barrier = false;
+	/* Clear fields that should not be set in a subquery RTE */
+	rte->relid = InvalidOid;
+	rte->relkind = 0;
+	rte->rellockmode = 0;
+	rte->tablesample = NULL;
+	rte->inh = false;			/* must not be set for a subquery */
+
+	rte->requiredPerms = 0;		/* no permission check on subquery itself */
+	rte->checkAsUser = InvalidOid;
+	rte->selectedCols = NULL;
+	rte->insertedCols = NULL;
+	rte->updatedCols = NULL;
+	rte->extraUpdatedCols = NULL;
+
+	return rte;
+}
+
+/*
+ * make_delta_enr_name
+ *
+ * Make a name for ENR of a transition table from the base table's oid.
+ * prefix will be "new" or "old" depending on its transition table kind..
+ */
+static char*
+make_delta_enr_name(const char *prefix, Oid relid, int count)
+{
+	char buf[NAMEDATALEN];
+	char *name;
+
+	snprintf(buf, NAMEDATALEN, "__ivm_%s_%u_%u", prefix, relid, count);
+	name = pstrdup(buf);
+
+	return name;
+}
+
+/*
+ * union_ENRs
+ *
+ * Make a single table delta by unionning all transition tables of the modified table
+ * whose RTE is specified by
+ */
+static RangeTblEntry*
+union_ENRs(RangeTblEntry *rte, Oid relid, List *enr_rtes, const char *prefix,
+		   QueryEnvironment *queryEnv)
+{
+	StringInfoData str;
+	ParseState	*pstate;
+	RawStmt *raw;
+	Query *sub;
+	int	i;
+	RangeTblEntry *enr_rte;
+
+	/* Create a ParseState for rewriting the view definition query */
+	pstate = make_parsestate(NULL);
+	pstate->p_queryEnv = queryEnv;
+	pstate->p_expr_kind = EXPR_KIND_SELECT_TARGET;
+
+	initStringInfo(&str);
+
+	for (i = 0; i < list_length(enr_rtes); i++)
+	{
+		if (i > 0)
+			appendStringInfo(&str, " UNION ALL ");
+
+		appendStringInfo(&str,
+			" SELECT * FROM %s",
+			make_delta_enr_name(prefix, relid, i));
+	}
+
+	raw = (RawStmt*)linitial(raw_parser(str.data, RAW_PARSE_DEFAULT));
+	sub = transformStmt(pstate, raw->stmt);
+
+	rte->rtekind = RTE_SUBQUERY;
+	rte->subquery = sub;
+	rte->security_barrier = false;
+	/* Clear fields that should not be set in a subquery RTE */
+	rte->relid = InvalidOid;
+	rte->relkind = 0;
+	rte->rellockmode = 0;
+	rte->tablesample = NULL;
+	rte->inh = false;			/* must not be set for a subquery */
+
+	rte->requiredPerms = 0;		/* no permission check on subquery itself */
+	rte->checkAsUser = InvalidOid;
+	rte->selectedCols = NULL;
+	rte->insertedCols = NULL;
+	rte->updatedCols = NULL;
+	rte->extraUpdatedCols = NULL;
+	/* if base table has RLS, set security condition to enr*/
+	enr_rte = (RangeTblEntry *)linitial(sub->rtable);
+	/* rt_index is always 1, bacause subquery has enr_rte only */
+	enr_rte->securityQuals = get_securityQuals(relid, 1, sub);
+
+	return rte;
+}
+
+/*
+ * rewrite_query_for_distinct
+ *
+ * Rewrite query for counting DISTINCT clause.
+ */
+static Query *
+rewrite_query_for_distinct(Query *query, ParseState *pstate)
+{
+	TargetEntry *tle_count;
+	FuncCall *fn;
+	Node *node;
+
+	/* Add count(*) for counting distinct tuples in views */
+	fn = makeFuncCall(list_make1(makeString("count")), NIL, COERCE_EXPLICIT_CALL, -1);
+	fn->agg_star = true;
+	if (!query->groupClause && !query->hasAggs)
+		query->groupClause = transformDistinctClause(NULL, &query->targetList, query->sortClause, false);
+
+	node = ParseFuncOrColumn(pstate, fn->funcname, NIL, NULL, fn, false, -1);
+
+	tle_count = makeTargetEntry((Expr *) node,
+								list_length(query->targetList) + 1,
+								pstrdup("__ivm_count__"),
+								false);
+	query->targetList = lappend(query->targetList, tle_count);
+	query->hasAggs = true;
+
+	return query;
+}
+
+/*
+ * calc_delta
+ *
+ * Calculate view deltas generated under the modification of a table specified
+ * by the RTE index.
+ */
+static void
+calc_delta(MV_TriggerTable *table, int rte_index, Query *query,
+			DestReceiver *dest_old, DestReceiver *dest_new,
+			TupleDesc *tupdesc_old, TupleDesc *tupdesc_new,
+			QueryEnvironment *queryEnv)
+{
+	ListCell *lc = list_nth_cell(query->rtable, rte_index - 1);
+	RangeTblEntry *rte = (RangeTblEntry *) lfirst(lc);
+
+	/* Generate old delta */
+	if (list_length(table->old_rtes) > 0)
+	{
+		/* Replace the modified table with the old delta table and calculate the old view delta. */
+		lfirst(lc) = union_ENRs(rte, table->table_id, table->old_rtes, "old", queryEnv);
+		refresh_matview_datafill(dest_old, query, queryEnv, tupdesc_old, "");
+	}
+
+	/* Generate new delta */
+	if (list_length(table->new_rtes) > 0)
+	{
+		/* Replace the modified table with the new delta table and calculate the new view delta*/
+		lfirst(lc) = union_ENRs(rte, table->table_id, table->new_rtes, "new", queryEnv);
+		refresh_matview_datafill(dest_new, query, queryEnv, tupdesc_new, "");
+	}
+}
+
+/*
+ * rewrite_query_for_postupdate_state
+ *
+ * Rewrite the query so that the specified base table's RTEs will represent
+ * "post-update" state of tables. This is called after the view delta
+ * calculation due to changes on this table finishes.
+ */
+static Query*
+rewrite_query_for_postupdate_state(Query *query, MV_TriggerTable *table, int rte_index)
+{
+	ListCell *lc = list_nth_cell(query->rtable, rte_index - 1);
+
+	/* Retore the original RTE */
+	lfirst(lc) = table->original_rte;
+
+	return query;
+}
+
+/*
+ * apply_delta
+ *
+ * Apply deltas to the materialized view. In outer join cases, this requires
+ * the view maintenance graph.
+ */
+static void
+apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *new_tuplestores,
+			TupleDesc tupdesc_old, TupleDesc tupdesc_new,
+			Query *query, bool use_count, char *count_colname)
+{
+	StringInfoData querybuf;
+	StringInfoData target_list_buf;
+	Relation	matviewRel;
+	char	   *matviewname;
+	ListCell	*lc;
+	int			i;
+	List	   *keys = NIL;
+
+
+	/*
+	 * get names of the materialized view and delta tables
+	 */
+
+	matviewRel = table_open(matviewOid, NoLock);
+	matviewname = quote_qualified_identifier(get_namespace_name(RelationGetNamespace(matviewRel)),
+											 RelationGetRelationName(matviewRel));
+
+	/*
+	 * Build parts of the maintenance queries
+	 */
+
+	initStringInfo(&querybuf);
+	initStringInfo(&target_list_buf);
+
+	/* build string of target list */
+	for (i = 0; i < matviewRel->rd_att->natts; i++)
+	{
+		Form_pg_attribute attr = TupleDescAttr(matviewRel->rd_att, i);
+		char   *resname = NameStr(attr->attname);
+
+		if (i != 0)
+			appendStringInfo(&target_list_buf, ", ");
+		appendStringInfo(&target_list_buf, "%s", quote_qualified_identifier(NULL, resname));
+	}
+
+	i = 0;
+	foreach (lc, query->targetList)
+	{
+		TargetEntry *tle = (TargetEntry *) lfirst(lc);
+		Form_pg_attribute attr = TupleDescAttr(matviewRel->rd_att, i);
+		char *resname = NameStr(attr->attname);
+
+		i++;
+
+		if (tle->resjunk)
+			continue;
+
+		keys = lappend(keys, resname);
+	}
+
+	/* Start maintaining the materialized view. */
+	OpenMatViewIncrementalMaintenance();
+
+	/* Open SPI context. */
+	if (SPI_connect() != SPI_OK_CONNECT)
+		elog(ERROR, "SPI_connect failed");
+
+	/* For tuple deletion */
+	if (old_tuplestores && tuplestore_tuple_count(old_tuplestores) > 0)
+	{
+		EphemeralNamedRelation enr = palloc(sizeof(EphemeralNamedRelationData));
+		int				rc;
+
+		/* convert tuplestores to ENR, and register for SPI */
+		enr->md.name = pstrdup(OLD_DELTA_ENRNAME);
+		enr->md.reliddesc = InvalidOid;
+		enr->md.tupdesc = tupdesc_old;
+		enr->md.enrtype = ENR_NAMED_TUPLESTORE;
+		enr->md.enrtuples = tuplestore_tuple_count(old_tuplestores);
+		enr->reldata = old_tuplestores;
+
+		rc = SPI_register_relation(enr);
+		if (rc != SPI_OK_REL_REGISTER)
+			elog(ERROR, "SPI_register failed");
+
+		if (use_count)
+			/* apply old delta and get rows to be recalculated */
+			apply_old_delta_with_count(matviewname, OLD_DELTA_ENRNAME,
+									   keys, count_colname);
+		else
+			apply_old_delta(matviewname, OLD_DELTA_ENRNAME, keys);
+
+	}
+	/* For tuple insertion */
+	if (new_tuplestores && tuplestore_tuple_count(new_tuplestores) > 0)
+	{
+		EphemeralNamedRelation enr = palloc(sizeof(EphemeralNamedRelationData));
+		int rc;
+
+		/* convert tuplestores to ENR, and register for SPI */
+		enr->md.name = pstrdup(NEW_DELTA_ENRNAME);
+		enr->md.reliddesc = InvalidOid;
+		enr->md.tupdesc = tupdesc_new;;
+		enr->md.enrtype = ENR_NAMED_TUPLESTORE;
+		enr->md.enrtuples = tuplestore_tuple_count(new_tuplestores);
+		enr->reldata = new_tuplestores;
+
+		rc = SPI_register_relation(enr);
+		if (rc != SPI_OK_REL_REGISTER)
+			elog(ERROR, "SPI_register failed");
+
+		/* apply new delta */
+		if (use_count)
+			apply_new_delta_with_count(matviewname, NEW_DELTA_ENRNAME,
+								keys, &target_list_buf, count_colname);
+		else
+			apply_new_delta(matviewname, NEW_DELTA_ENRNAME, &target_list_buf);
+	}
+
+	/* We're done maintaining the materialized view. */
+	CloseMatViewIncrementalMaintenance();
+
+	table_close(matviewRel, NoLock);
+
+	/* Close SPI context. */
+	if (SPI_finish() != SPI_OK_FINISH)
+		elog(ERROR, "SPI_finish failed");
+}
+
+/*
+ * apply_old_delta_with_count
+ *
+ * Execute a query for applying a delta table given by deltname_old
+ * which contains tuples to be deleted from to a materialized view given by
+ * matviewname.  This is used when counting is required, that is, the view
+ * has aggregate or distinct.
+ */
+static void
+apply_old_delta_with_count(const char *matviewname, const char *deltaname_old,
+				List *keys, const char *count_colname)
+{
+	StringInfoData	querybuf;
+	char   *match_cond;
+
+	/* build WHERE condition for searching tuples to be deleted */
+	match_cond = get_matching_condition_string(keys);
+
+	/* Search for matching tuples from the view and update or delete if found. */
+	initStringInfo(&querybuf);
+	appendStringInfo(&querybuf,
+					"WITH t AS ("			/* collecting tid of target tuples in the view */
+						"SELECT diff.%s, "			/* count column */
+								"(diff.%s OPERATOR(pg_catalog.=) mv.%s) AS for_dlt, "
+								"mv.ctid "
+						"FROM %s AS mv, %s AS diff "
+						"WHERE %s"					/* tuple matching condition */
+					"), updt AS ("			/* update a tuple if this is not to be deleted */
+						"UPDATE %s AS mv SET %s = mv.%s OPERATOR(pg_catalog.-) t.%s "
+						"FROM t WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND NOT for_dlt "
+					"), dlt AS ("			/* delete a tuple if this is to be deleted */
+						"DELETE FROM %s AS mv USING t "
+						"WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt"
+					")",
+					count_colname,
+					count_colname, count_colname,
+					matviewname, deltaname_old,
+					match_cond,
+					matviewname, count_colname, count_colname, count_colname,
+					matviewname);
+
+	if (SPI_exec(querybuf.data, 0) != SPI_OK_DELETE)
+		elog(ERROR, "SPI_exec failed: %s", querybuf.data);
+}
+
+/*
+ * apply_old_delta
+ *
+ * Execute a query for applying a delta table given by deltname_old
+ * which contains tuples to be deleted from to a materialized view given by
+ * matviewname.  This is used when counting is not required.
+ */
+static void
+apply_old_delta(const char *matviewname, const char *deltaname_old,
+				List *keys)
+{
+	StringInfoData	querybuf;
+	StringInfoData	keysbuf;
+	char   *match_cond;
+	ListCell *lc;
+
+	/* build WHERE condition for searching tuples to be deleted */
+	match_cond = get_matching_condition_string(keys);
+
+	/* build string of keys list */
+	initStringInfo(&keysbuf);
+	foreach (lc, keys)
+	{
+		Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc);
+		char   *resname = NameStr(attr->attname);
+		appendStringInfo(&keysbuf, "%s", quote_qualified_identifier("mv", resname));
+		if (lnext(keys, lc))
+			appendStringInfo(&keysbuf, ", ");
+	}
+
+	/* Search for matching tuples from the view and update or delete if found. */
+	initStringInfo(&querybuf);
+	appendStringInfo(&querybuf,
+	"DELETE FROM %s WHERE ctid IN ("
+		"SELECT tid FROM (SELECT row_number() over (partition by %s) AS \"__ivm_row_number__\","
+								  "mv.ctid AS tid,"
+								  "diff.\"__ivm_count__\""
+						 "FROM %s AS mv, %s AS diff "
+						 "WHERE %s) v "
+					"WHERE v.\"__ivm_row_number__\" OPERATOR(pg_catalog.<=) v.\"__ivm_count__\")",
+					matviewname,
+					keysbuf.data,
+					matviewname, deltaname_old,
+					match_cond);
+
+	if (SPI_exec(querybuf.data, 0) != SPI_OK_DELETE)
+		elog(ERROR, "SPI_exec failed: %s", querybuf.data);
+}
+
+/*
+ * apply_new_delta_with_count
+ *
+ * Execute a query for applying a delta table given by deltname_new
+ * which contains tuples to be inserted into a materialized view given by
+ * matviewname.  This is used when counting is required, that is, the view
+ * has aggregate or distinct. Also, when a table in EXISTS sub queries
+ * is modified.
+ */
+static void
+apply_new_delta_with_count(const char *matviewname, const char* deltaname_new,
+				List *keys, StringInfo target_list, const char* count_colname)
+{
+	StringInfoData	querybuf;
+	StringInfoData	returning_keys;
+	ListCell	*lc;
+	char	*match_cond = "";
+
+	/* build WHERE condition for searching tuples to be updated */
+	match_cond = get_matching_condition_string(keys);
+
+	/* build string of keys list */
+	initStringInfo(&returning_keys);
+	if (keys)
+	{
+		foreach (lc, keys)
+		{
+			Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc);
+			char   *resname = NameStr(attr->attname);
+			appendStringInfo(&returning_keys, "%s", quote_qualified_identifier("mv", resname));
+			if (lnext(keys, lc))
+				appendStringInfo(&returning_keys, ", ");
+		}
+	}
+	else
+		appendStringInfo(&returning_keys, "NULL");
+
+	/* Search for matching tuples from the view and update if found or insert if not. */
+	initStringInfo(&querybuf);
+	appendStringInfo(&querybuf,
+					"WITH updt AS ("		/* update a tuple if this exists in the view */
+						"UPDATE %s AS mv SET %s = mv.%s OPERATOR(pg_catalog.+) diff.%s "
+						"FROM %s AS diff "
+						"WHERE %s "					/* tuple matching condition */
+						"RETURNING %s"				/* returning keys of updated tuples */
+					") INSERT INTO %s (%s)"	/* insert a new tuple if this doesn't existw */
+						"SELECT %s FROM %s AS diff "
+						"WHERE NOT EXISTS (SELECT 1 FROM updt AS mv WHERE %s);",
+					matviewname, count_colname, count_colname, count_colname,
+					deltaname_new,
+					match_cond,
+					returning_keys.data,
+					matviewname, target_list->data,
+					target_list->data, deltaname_new,
+					match_cond);
+
+	if (SPI_exec(querybuf.data, 0) != SPI_OK_INSERT)
+		elog(ERROR, "SPI_exec failed: %s", querybuf.data);
+}
+
+/*
+ * apply_new_delta
+ *
+ * Execute a query for applying a delta table given by deltname_new
+ * which contains tuples to be inserted into a materialized view given by
+ * matviewname.  This is used when counting is not required.
+ */
+static void
+apply_new_delta(const char *matviewname, const char *deltaname_new,
+				StringInfo target_list)
+{
+	StringInfoData	querybuf;
+
+	/* Search for matching tuples from the view and update or delete if found. */
+	initStringInfo(&querybuf);
+	appendStringInfo(&querybuf,
+					"INSERT INTO %s (%s) SELECT %s FROM ("
+						"SELECT diff.*, generate_series(1, diff.\"__ivm_count__\") "
+						"FROM %s AS diff) AS v",
+					matviewname, target_list->data, target_list->data,
+					deltaname_new);
+
+	if (SPI_exec(querybuf.data, 0) != SPI_OK_INSERT)
+		elog(ERROR, "SPI_exec failed: %s", querybuf.data);
+}
+
+/*
+ * get_matching_condition_string
+ *
+ * Build a predicate string for looking for a tuple with given keys.
+ */
+static char *
+get_matching_condition_string(List *keys)
+{
+	StringInfoData match_cond;
+	ListCell	*lc;
+
+	/* If there is no key columns, the condition is always true. */
+	if (keys == NIL)
+		return "true";
+
+	initStringInfo(&match_cond);
+	foreach (lc, keys)
+	{
+		Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc);
+		char   *resname = NameStr(attr->attname);
+		char   *mv_resname = quote_qualified_identifier("mv", resname);
+		char   *diff_resname = quote_qualified_identifier("diff", resname);
+		Oid		typid = attr->atttypid;
+
+		/* Considering NULL values, we can not use simple = operator. */
+		appendStringInfo(&match_cond, "(");
+		generate_equal(&match_cond, typid, mv_resname, diff_resname);
+		appendStringInfo(&match_cond, " OR (%s IS NULL AND %s IS NULL))",
+						 mv_resname, diff_resname);
+
+		if (lnext(keys, lc))
+			appendStringInfo(&match_cond, " AND ");
+	}
+
+	return match_cond.data;
+}
+
+/*
+ * generate_equals
+ *
+ * Generate an equality clause using given operands' default equality
+ * operator.
+ */
+static void
+generate_equal(StringInfo querybuf, Oid opttype,
+			   const char *leftop, const char *rightop)
+{
+	TypeCacheEntry *typentry;
+
+	typentry = lookup_type_cache(opttype, TYPECACHE_EQ_OPR);
+	if (!OidIsValid(typentry->eq_opr))
+		ereport(ERROR,
+				(errcode(ERRCODE_UNDEFINED_FUNCTION),
+				 errmsg("could not identify an equality operator for type %s",
+						format_type_be(opttype))));
+
+	generate_operator_clause(querybuf,
+							 leftop, opttype,
+							 typentry->eq_opr,
+							 rightop, opttype);
+}
+
+/*
+ * mv_InitHashTables
+ */
+static void
+mv_InitHashTables(void)
+{
+	HASHCTL		ctl;
+
+	memset(&ctl, 0, sizeof(ctl));
+	ctl.keysize = sizeof(Oid);
+	ctl.entrysize = sizeof(MV_TriggerHashEntry);
+	mv_trigger_info = hash_create("MV trigger info",
+								 MV_INIT_QUERYHASHSIZE,
+								 &ctl, HASH_ELEM | HASH_BLOBS);
+}
+
+/*
+ * AtAbort_IVM
+ *
+ * Clean up hash entries for all materialized views. This is called at
+ * transaction abort.
+ */
+void
+AtAbort_IVM()
+{
+	HASH_SEQ_STATUS seq;
+	MV_TriggerHashEntry *entry;
+
+	if (mv_trigger_info)
+	{
+		hash_seq_init(&seq, mv_trigger_info);
+		while ((entry = hash_seq_search(&seq)) != NULL)
+			clean_up_IVM_hash_entry(entry);
+	}
+}
+
+/*
+ * clean_up_IVM_hash_entry
+ *
+ * Clean up tuple stores and hash entries for a materialized view after its
+ * maintenance finished.
+ */
+static void
+clean_up_IVM_hash_entry(MV_TriggerHashEntry *entry)
+{
+	bool found;
+	ListCell *lc;
+
+	foreach(lc, entry->tables)
+	{
+		MV_TriggerTable *table = (MV_TriggerTable *) lfirst(lc);
+
+		list_free(table->old_tuplestores);
+		list_free(table->new_tuplestores);
+	}
+	list_free(entry->tables);
+
+	hash_search(mv_trigger_info, (void *) &entry->matview_id, HASH_REMOVE, &found);
+}
+
+/*
+ * isIvmName
+ *
+ * Check if this is a IVM hidden column from the name.
+ */
+bool
+isIvmName(const char *s)
+{
+	if (s)
+		return (strncmp(s, "__ivm_", 6) == 0);
+	return false;
+}
+
+/*
+ * get_securityQuals
+ *
+ * Get row security policy on a relation.
+ * This is used by IVM for copying RLS from base table to enr.
+ */
+static List *
+get_securityQuals(Oid relId, int rt_index, Query *query)
+{
+	ParseState *pstate;
+	Relation rel;
+	ParseNamespaceItem *nsitem;
+	RangeTblEntry *rte;
+	List *securityQuals;
+	List *withCheckOptions;
+	bool  hasRowSecurity;
+	bool  hasSubLinks;
+
+	securityQuals = NIL;
+	pstate = make_parsestate(NULL);
+
+	rel = table_open(relId, NoLock);
+	nsitem = addRangeTableEntryForRelation(pstate, rel, AccessShareLock, NULL, false, false);
+	rte = nsitem->p_rte;
+
+	get_row_security_policies(query, rte, rt_index,
+							  &securityQuals, &withCheckOptions,
+							  &hasRowSecurity, &hasSubLinks);
+
+	/*
+	 * Make sure the query is marked correctly if row level security
+	 * applies, or if the new quals had sublinks.
+	 */
+	if (hasRowSecurity)
+		query->hasRowSecurity = true;
+	if (hasSubLinks)
+		query->hasSubLinks = true;
+
+	table_close(rel, NoLock);
+
+	return securityQuals;
+}
diff --git a/src/backend/commands/tablecmds.c b/src/backend/commands/tablecmds.c
index dbee6ae199..a91a0e9ca1 100644
--- a/src/backend/commands/tablecmds.c
+++ b/src/backend/commands/tablecmds.c
@@ -50,6 +50,7 @@
 #include "commands/cluster.h"
 #include "commands/comment.h"
 #include "commands/defrem.h"
+#include "commands/matview.h"
 #include "commands/event_trigger.h"
 #include "commands/policy.h"
 #include "commands/sequence.h"
@@ -3394,6 +3395,14 @@ renameatt_internal(Oid myrelid,
 	targetrelation = relation_open(myrelid, AccessExclusiveLock);
 	renameatt_check(myrelid, RelationGetForm(targetrelation), recursing);
 
+	/*
+	 * Don't rename IVM columns.
+	 */
+	if (RelationIsIVM(targetrelation) && isIvmName(oldattname))
+		ereport(ERROR,
+				(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+				 errmsg("IVM column can not be renamed")));
+
 	/*
 	 * if the 'recurse' flag is set then we are supposed to rename this
 	 * attribute in all classes that inherit from 'relname' (as well as in
diff --git a/src/backend/nodes/copyfuncs.c b/src/backend/nodes/copyfuncs.c
index 17be377aa7..5235f2169e 100644
--- a/src/backend/nodes/copyfuncs.c
+++ b/src/backend/nodes/copyfuncs.c
@@ -2460,6 +2460,7 @@ _copyRangeTblEntry(const RangeTblEntry *from)
 	COPY_SCALAR_FIELD(relkind);
 	COPY_SCALAR_FIELD(rellockmode);
 	COPY_NODE_FIELD(tablesample);
+	COPY_SCALAR_FIELD(relisivm);
 	COPY_NODE_FIELD(subquery);
 	COPY_SCALAR_FIELD(security_barrier);
 	COPY_SCALAR_FIELD(jointype);
diff --git a/src/backend/nodes/equalfuncs.c b/src/backend/nodes/equalfuncs.c
index ed74a5022c..c60a5f9bee 100644
--- a/src/backend/nodes/equalfuncs.c
+++ b/src/backend/nodes/equalfuncs.c
@@ -2744,6 +2744,7 @@ _equalRangeTblEntry(const RangeTblEntry *a, const RangeTblEntry *b)
 	COMPARE_SCALAR_FIELD(relkind);
 	COMPARE_SCALAR_FIELD(rellockmode);
 	COMPARE_NODE_FIELD(tablesample);
+	COMPARE_SCALAR_FIELD(relisivm);
 	COMPARE_NODE_FIELD(subquery);
 	COMPARE_SCALAR_FIELD(security_barrier);
 	COMPARE_SCALAR_FIELD(jointype);
diff --git a/src/backend/nodes/outfuncs.c b/src/backend/nodes/outfuncs.c
index f6166f7859..8133850e98 100644
--- a/src/backend/nodes/outfuncs.c
+++ b/src/backend/nodes/outfuncs.c
@@ -3253,6 +3253,7 @@ _outRangeTblEntry(StringInfo str, const RangeTblEntry *node)
 			WRITE_CHAR_FIELD(relkind);
 			WRITE_INT_FIELD(rellockmode);
 			WRITE_NODE_FIELD(tablesample);
+			WRITE_BOOL_FIELD(relisivm);
 			break;
 		case RTE_SUBQUERY:
 			WRITE_NODE_FIELD(subquery);
diff --git a/src/backend/nodes/readfuncs.c b/src/backend/nodes/readfuncs.c
index 1e55a58f69..96fa85758f 100644
--- a/src/backend/nodes/readfuncs.c
+++ b/src/backend/nodes/readfuncs.c
@@ -1443,6 +1443,7 @@ _readRangeTblEntry(void)
 			READ_CHAR_FIELD(relkind);
 			READ_INT_FIELD(rellockmode);
 			READ_NODE_FIELD(tablesample);
+			READ_BOOL_FIELD(relisivm);
 			break;
 		case RTE_SUBQUERY:
 			READ_NODE_FIELD(subquery);
diff --git a/src/backend/parser/parse_relation.c b/src/backend/parser/parse_relation.c
index c5c3f26ecf..4a52035371 100644
--- a/src/backend/parser/parse_relation.c
+++ b/src/backend/parser/parse_relation.c
@@ -36,6 +36,7 @@
 #include "utils/rel.h"
 #include "utils/syscache.h"
 #include "utils/varlena.h"
+#include "commands/matview.h"
 
 
 /*
@@ -79,7 +80,7 @@ static void expandTupleDesc(TupleDesc tupdesc, Alias *eref,
 							int count, int offset,
 							int rtindex, int sublevels_up,
 							int location, bool include_dropped,
-							List **colnames, List **colvars);
+							List **colnames, List **colvars, bool is_ivm);
 static int	specialAttNum(const char *attname);
 static bool isQueryUsingTempRelation_walker(Node *node, void *context);
 
@@ -1433,6 +1434,7 @@ addRangeTableEntry(ParseState *pstate,
 	rte->relid = RelationGetRelid(rel);
 	rte->relkind = rel->rd_rel->relkind;
 	rte->rellockmode = lockmode;
+	rte->relisivm = rel->rd_rel->relisivm;
 
 	/*
 	 * Build the list of effective column names using user-supplied aliases
@@ -1521,6 +1523,7 @@ addRangeTableEntryForRelation(ParseState *pstate,
 	rte->relid = RelationGetRelid(rel);
 	rte->relkind = rel->rd_rel->relkind;
 	rte->rellockmode = lockmode;
+	rte->relisivm = rel->rd_rel->relisivm;
 
 	/*
 	 * Build the list of effective column names using user-supplied aliases
@@ -2676,7 +2679,7 @@ expandRTE(RangeTblEntry *rte, int rtindex, int sublevels_up,
 						expandTupleDesc(tupdesc, rte->eref,
 										rtfunc->funccolcount, atts_done,
 										rtindex, sublevels_up, location,
-										include_dropped, colnames, colvars);
+										include_dropped, colnames, colvars, false);
 					}
 					else if (functypclass == TYPEFUNC_SCALAR)
 					{
@@ -2944,7 +2947,7 @@ expandRelation(Oid relid, Alias *eref, int rtindex, int sublevels_up,
 	expandTupleDesc(rel->rd_att, eref, rel->rd_att->natts, 0,
 					rtindex, sublevels_up,
 					location, include_dropped,
-					colnames, colvars);
+					colnames, colvars, RelationIsIVM(rel));
 	relation_close(rel, AccessShareLock);
 }
 
@@ -2961,7 +2964,7 @@ static void
 expandTupleDesc(TupleDesc tupdesc, Alias *eref, int count, int offset,
 				int rtindex, int sublevels_up,
 				int location, bool include_dropped,
-				List **colnames, List **colvars)
+				List **colnames, List **colvars, bool is_ivm)
 {
 	ListCell   *aliascell;
 	int			varattno;
@@ -2974,6 +2977,9 @@ expandTupleDesc(TupleDesc tupdesc, Alias *eref, int count, int offset,
 	{
 		Form_pg_attribute attr = TupleDescAttr(tupdesc, varattno);
 
+		if (is_ivm && isIvmName(NameStr(attr->attname)) && !MatViewIncrementalMaintenanceIsEnabled())
+			continue;
+
 		if (attr->attisdropped)
 		{
 			if (include_dropped)
@@ -3127,6 +3133,10 @@ expandNSItemAttrs(ParseState *pstate, ParseNamespaceItem *nsitem,
 		Var		   *varnode = (Var *) lfirst(var);
 		TargetEntry *te;
 
+		/* if transform * into columnlist with IMMV, remove IVM columns */
+		if (rte->relisivm && isIvmName(label) && !MatViewIncrementalMaintenanceIsEnabled())
+			continue;
+
 		te = makeTargetEntry((Expr *) varnode,
 							 (AttrNumber) pstate->p_next_resno++,
 							 label,
diff --git a/src/backend/rewrite/rewriteDefine.c b/src/backend/rewrite/rewriteDefine.c
index 6589345ac4..02f33d404b 100644
--- a/src/backend/rewrite/rewriteDefine.c
+++ b/src/backend/rewrite/rewriteDefine.c
@@ -776,7 +776,8 @@ checkRuleResultList(List *targetList, TupleDesc resultDesc, bool isSelect,
 														attr->atttypmod))));
 	}
 
-	if (i != resultDesc->natts)
+	/* No check for materialized views since this could have special columns for IVM */
+	if ((!isSelect || requireColumnNameMatch) && i != resultDesc->natts)
 		ereport(ERROR,
 				(errcode(ERRCODE_INVALID_OBJECT_DEFINITION),
 				 isSelect ?
diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat
index d068d6532e..4845e71898 100644
--- a/src/include/catalog/pg_proc.dat
+++ b/src/include/catalog/pg_proc.dat
@@ -11689,4 +11689,12 @@
   prorettype => 'bytea', proargtypes => 'pg_brin_minmax_multi_summary',
   prosrc => 'brin_minmax_multi_summary_send' },
 
+# IVM
+{ oid => '786', descr => 'ivm trigger (before)',
+  proname => 'IVM_immediate_before', provolatile => 'v', prorettype => 'trigger',
+  proargtypes => '', prosrc => 'IVM_immediate_before' },
+{ oid => '787', descr => 'ivm trigger (after)',
+  proname => 'IVM_immediate_maintenance', provolatile => 'v', prorettype => 'trigger',
+  proargtypes => '', prosrc => 'IVM_immediate_maintenance' },
+
 ]
diff --git a/src/include/commands/createas.h b/src/include/commands/createas.h
index ad5054d116..a57ce463e1 100644
--- a/src/include/commands/createas.h
+++ b/src/include/commands/createas.h
@@ -16,6 +16,7 @@
 
 #include "catalog/objectaddress.h"
 #include "nodes/params.h"
+#include "nodes/pathnodes.h"
 #include "parser/parse_node.h"
 #include "tcop/dest.h"
 #include "utils/queryenvironment.h"
@@ -25,6 +26,10 @@ extern ObjectAddress ExecCreateTableAs(ParseState *pstate, CreateTableAsStmt *st
 									   ParamListInfo params, QueryEnvironment *queryEnv,
 									   QueryCompletion *qc);
 
+extern void CreateIvmTriggersOnBaseTables(Query *qry, Oid matviewOid, bool is_create);
+
+extern Query *rewriteQueryForIMMV(Query *query, List *colNames);
+
 extern int	GetIntoRelEFlags(IntoClause *intoClause);
 
 extern DestReceiver *CreateIntoRelDestReceiver(IntoClause *intoClause);
diff --git a/src/include/commands/matview.h b/src/include/commands/matview.h
index 214b1c1df6..13a5722f17 100644
--- a/src/include/commands/matview.h
+++ b/src/include/commands/matview.h
@@ -15,6 +15,7 @@
 #define MATVIEW_H
 
 #include "catalog/objectaddress.h"
+#include "fmgr.h"
 #include "nodes/params.h"
 #include "nodes/parsenodes.h"
 #include "tcop/dest.h"
@@ -23,6 +24,8 @@
 
 extern void SetMatViewPopulatedState(Relation relation, bool newstate);
 
+extern void SetMatViewIVMState(Relation relation, bool newstate);
+
 extern ObjectAddress ExecRefreshMatView(RefreshMatViewStmt *stmt, const char *queryString,
 										ParamListInfo params, QueryCompletion *qc);
 
@@ -30,4 +33,9 @@ extern DestReceiver *CreateTransientRelDestReceiver(Oid oid);
 
 extern bool MatViewIncrementalMaintenanceIsEnabled(void);
 
+extern Datum IVM_immediate_before(PG_FUNCTION_ARGS);
+extern Datum IVM_immediate_maintenance(PG_FUNCTION_ARGS);
+extern void AtAbort_IVM(void);
+extern bool isIvmName(const char *s);
+
 #endif							/* MATVIEW_H */
diff --git a/src/include/nodes/parsenodes.h b/src/include/nodes/parsenodes.h
index 3138877553..e7d3b00971 100644
--- a/src/include/nodes/parsenodes.h
+++ b/src/include/nodes/parsenodes.h
@@ -1035,6 +1035,7 @@ typedef struct RangeTblEntry
 	char		relkind;		/* relation kind (see pg_class.relkind) */
 	int			rellockmode;	/* lock level that query requires on the rel */
 	struct TableSampleClause *tablesample;	/* sampling info, or NULL */
+	bool		relisivm;
 
 	/*
 	 * Fields valid for a subquery RTE (else NULL):
@@ -2193,6 +2194,7 @@ typedef struct CreateStmt
 	char	   *tablespacename; /* table space to use, or NULL */
 	char	   *accessMethod;	/* table access method */
 	bool		if_not_exists;	/* just do nothing if it already exists? */
+	bool		ivm;			/* incremental view maintenance is used by materialized view */
 } CreateStmt;
 
 /* ----------
-- 
2.17.1


--Multipart=_Thu__23_Sep_2021_04_57_30_+0900_b5pmgR1N8oMaMz.U
Content-Type: text/x-diff;
 name="v24-0008-Add-aggregates-support-in-IVM.patch"
Content-Disposition: attachment;
 filename="v24-0008-Add-aggregates-support-in-IVM.patch"
Content-Transfer-Encoding: quoted-printable



^ permalink  raw  reply  [nested|flat] 101+ messages in thread

* [PATCH v23 07/15] Add Incremental View Maintenance support
@ 2020-12-22 09:40  Yugo Nagata <[email protected]>
  0 siblings, 0 replies; 101+ messages in thread

From: Yugo Nagata @ 2020-12-22 09:40 UTC (permalink / raw)

In this implementation, AFTER triggers are used to collecting
tuplestores containing transition table contents. When multiple tables
are changed, multiple AFTER triggers are invoked, then the final AFTER
trigger performs actual update of the matview. In addition, BEFORE
triggers are also used to handle global information for view
maintenance. To calculate view deltas, we need both pre-state and
post-state of base tables. Post-update states are available in AFTER
trigger, and pre-update states can be calculated by filtering inserted
tuples using cmin/xmin system columns, and append deleted tuples which
are contained in a old transition table.

This patch also allows self-join, simultaneous updates of more than
one base tables, and multiple updates of the same base table.

DISTINCT and tuple duplicates in views are supported. When IMMV is
created with DISTINCT, multiplicity of tuples is counted and stored
in  "__ivm_count__" column, which is a hidden column of IMMV.
The value in__ivm_count__ is updated when IMMV is maintained
incrementally. A tuple in IMMV can be removed if and only if the
count becomes zero.
---
 src/backend/access/transam/xact.c   |    5 +
 src/backend/commands/createas.c     |  697 ++++++++++++
 src/backend/commands/indexcmds.c    |   40 +
 src/backend/commands/matview.c      | 1549 ++++++++++++++++++++++++++-
 src/backend/commands/tablecmds.c    |    9 +
 src/backend/nodes/copyfuncs.c       |    1 +
 src/backend/nodes/equalfuncs.c      |    1 +
 src/backend/nodes/outfuncs.c        |    1 +
 src/backend/nodes/readfuncs.c       |    1 +
 src/backend/parser/parse_relation.c |   18 +-
 src/backend/rewrite/rewriteDefine.c |    3 +-
 src/include/catalog/pg_proc.dat     |    8 +
 src/include/commands/createas.h     |    5 +
 src/include/commands/matview.h      |    8 +
 src/include/nodes/parsenodes.h      |    2 +
 15 files changed, 2308 insertions(+), 40 deletions(-)

diff --git a/src/backend/access/transam/xact.c b/src/backend/access/transam/xact.c
index 441445927e..d67a8bc906 100644
--- a/src/backend/access/transam/xact.c
+++ b/src/backend/access/transam/xact.c
@@ -35,6 +35,7 @@
 #include "catalog/pg_enum.h"
 #include "catalog/storage.h"
 #include "commands/async.h"
+#include "commands/matview.h"
 #include "commands/tablecmds.h"
 #include "commands/trigger.h"
 #include "executor/spi.h"
@@ -2705,6 +2706,7 @@ AbortTransaction(void)
 	AtAbort_Notify();
 	AtEOXact_RelationMap(false, is_parallel_worker);
 	AtAbort_Twophase();
+	AtAbort_IVM();
 
 	/*
 	 * Advertise the fact that we aborted in pg_xact (assuming that we got as
@@ -4948,6 +4950,9 @@ AbortSubTransaction(void)
 	AbortBufferIO();
 	UnlockBuffers();
 
+	/* Clean up hash entries for incremental view maintenance */
+	AtAbort_IVM();
+
 	/* Reset WAL record construction state */
 	XLogResetInsertion();
 
diff --git a/src/backend/commands/createas.c b/src/backend/commands/createas.c
index 0982851715..3fc2af1c4a 100644
--- a/src/backend/commands/createas.c
+++ b/src/backend/commands/createas.c
@@ -32,24 +32,41 @@
 #include "access/xact.h"
 #include "access/xlog.h"
 #include "catalog/namespace.h"
+#include "catalog/index.h"
+#include "catalog/pg_constraint.h"
+#include "catalog/pg_inherits.h"
+#include "catalog/pg_trigger.h"
+#include "catalog/pg_type.h"
 #include "catalog/toasting.h"
 #include "commands/createas.h"
+#include "commands/defrem.h"
 #include "commands/matview.h"
 #include "commands/prepare.h"
 #include "commands/tablecmds.h"
+#include "commands/tablespace.h"
+#include "commands/trigger.h"
 #include "commands/view.h"
 #include "miscadmin.h"
+#include "optimizer/clauses.h"
+#include "optimizer/optimizer.h"
 #include "nodes/makefuncs.h"
 #include "nodes/nodeFuncs.h"
+#include "parser/parser.h"
+#include "parser/parsetree.h"
 #include "parser/parse_clause.h"
+#include "parser/parse_func.h"
+#include "parser/parse_type.h"
 #include "rewrite/rewriteHandler.h"
+#include "rewrite/rewriteManip.h"
 #include "storage/smgr.h"
 #include "tcop/tcopprot.h"
 #include "utils/builtins.h"
+#include "utils/fmgroids.h"
 #include "utils/lsyscache.h"
 #include "utils/rel.h"
 #include "utils/rls.h"
 #include "utils/snapmgr.h"
+#include "utils/syscache.h"
 
 typedef struct
 {
@@ -73,6 +90,12 @@ static bool intorel_receive(TupleTableSlot *slot, DestReceiver *self);
 static void intorel_shutdown(DestReceiver *self);
 static void intorel_destroy(DestReceiver *self);
 
+static void CreateIvmTriggersOnBaseTables_recurse(Query *qry, Node *node, Oid matviewOid, Relids *relids, bool ex_lock);
+static void CreateIvmTrigger(Oid relOid, Oid viewOid, int16 type, int16 timing, bool ex_lock);
+static void check_ivm_restriction(Node *node);
+static bool check_ivm_restriction_walker(Node *node, void *context);
+static void CreateIndexOnIMMV(Query *query, Relation matviewRel);
+static Bitmapset *get_primary_key_attnos_from_query(Query *qry, List **constraintList);
 
 /*
  * create_ctas_internal
@@ -108,6 +131,8 @@ create_ctas_internal(List *attrList, IntoClause *into)
 	create->oncommit = into->onCommit;
 	create->tablespacename = into->tableSpaceName;
 	create->if_not_exists = false;
+	/* Using Materialized view only */
+	create->ivm = into->ivm;
 	create->accessMethod = into->accessMethod;
 
 	/*
@@ -238,6 +263,7 @@ ExecCreateTableAs(ParseState *pstate, CreateTableAsStmt *stmt,
 	List	   *rewritten;
 	PlannedStmt *plan;
 	QueryDesc  *queryDesc;
+	Query	   *query_immv = NULL;
 
 	/* Check if the relation exists or not */
 	if (CreateTableAsRelExists(stmt))
@@ -282,6 +308,22 @@ ExecCreateTableAs(ParseState *pstate, CreateTableAsStmt *stmt,
 		save_nestlevel = NewGUCNestLevel();
 	}
 
+	if (is_matview && into->ivm)
+	{
+		/* check if the query is supported in IMMV definition */
+		if (contain_mutable_functions((Node *) query))
+			ereport(ERROR,
+					(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+					 errmsg("mutable function is not supported on incrementally maintainable materialized view"),
+					 errhint("functions must be marked IMMUTABLE")));
+
+		check_ivm_restriction((Node *) query);
+
+		/* For IMMV, we need to rewrite matview query */
+		query = rewriteQueryForIMMV(query, into->colNames);
+		query_immv = copyObject(query);
+	}
+
 	if (into->skipData)
 	{
 		/*
@@ -358,11 +400,74 @@ ExecCreateTableAs(ParseState *pstate, CreateTableAsStmt *stmt,
 
 		/* Restore userid and security context */
 		SetUserIdAndSecContext(save_userid, save_sec_context);
+
+		if (into->ivm)
+		{
+			Oid matviewOid = address.objectId;
+			Relation matviewRel = table_open(matviewOid, NoLock);
+
+			/*
+			 * Mark relisivm field, if it's a matview and into->ivm is true.
+			 */
+			SetMatViewIVMState(matviewRel, true);
+
+			/* Create an index on incremental maintainable materialized view, if possible */
+			CreateIndexOnIMMV((Query *) into->viewQuery, matviewRel);
+
+			/* Create triggers on incremental maintainable materialized view */
+			if (!into->skipData)
+			{
+				Assert(query_immv != NULL);
+				CreateIvmTriggersOnBaseTables(query_immv, matviewOid, true);
+			}
+			table_close(matviewRel, NoLock);
+		}
 	}
 
 	return address;
 }
 
+/*
+ * rewriteQueryForIMMV -- rewrite view definition query for IMMV
+ *
+ * count(*) is added for counting distinct tuples in views.
+ */
+Query *
+rewriteQueryForIMMV(Query *query, List *colNames)
+{
+	Query *rewritten;
+
+	TargetEntry *tle;
+	Node *node;
+	ParseState *pstate = make_parsestate(NULL);
+	FuncCall *fn;
+
+	rewritten = copyObject(query);
+	pstate->p_expr_kind = EXPR_KIND_SELECT_TARGET;
+
+	/* Convert DISTINCT to GROUP BY.  count(*) will be added afterward. */
+	if (rewritten->distinctClause)
+		rewritten->groupClause = transformDistinctClause(NULL, &rewritten->targetList, rewritten->sortClause, false);
+
+	/* Add count(*) for counting distinct tuples in views */
+	if (rewritten->distinctClause)
+	{
+		fn = makeFuncCall(list_make1(makeString("count")), NIL, COERCE_EXPLICIT_CALL, -1);
+		fn->agg_star = true;
+
+		node = ParseFuncOrColumn(pstate, fn->funcname, NIL, NULL, fn, false, -1);
+
+		tle = makeTargetEntry((Expr *) node,
+								list_length(rewritten->targetList) + 1,
+								pstrdup("__ivm_count__"),
+								false);
+		rewritten->targetList = lappend(rewritten->targetList, tle);
+		rewritten->hasAggs = true;
+	}
+
+	return rewritten;
+}
+
 /*
  * GetIntoRelEFlags --- compute executor flags needed for CREATE TABLE AS
  *
@@ -623,3 +728,595 @@ intorel_destroy(DestReceiver *self)
 {
 	pfree(self);
 }
+
+/*
+ * CreateIvmTriggersOnBaseTables -- create IVM triggers on all base tables
+ */
+void
+CreateIvmTriggersOnBaseTables(Query *qry, Oid matviewOid, bool is_create)
+{
+	Relids	relids = NULL;
+	bool	ex_lock = false;
+	Index	first_rtindex = is_create ? 1 : PRS2_NEW_VARNO + 1;
+	RangeTblEntry *rte;
+
+	/* Immediately return if we don't have any base tables. */
+	if (list_length(qry->rtable) < first_rtindex)
+		return;
+
+	/*
+	 * If the view has more than one base tables, we need an exclusive lock
+	 * on the view so that the view would be maintained serially to avoid
+	 * the inconsistency that occurs when two base tables are modified in
+	 * concurrent transactions. However, if the view has only one table,
+	 * we can use a weaker lock.
+	 *
+	 * The type of lock should be determined here, because if we check the
+	 * view definition at maintenance time, we need to acquire a weaker lock,
+	 * and upgrading the lock level after this increases probability of
+	 * deadlock.
+	 */
+
+	rte = list_nth(qry->rtable, first_rtindex - 1);
+	if (list_length(qry->rtable) > first_rtindex ||
+		rte->rtekind != RTE_RELATION)
+		ex_lock = true;
+
+	CreateIvmTriggersOnBaseTables_recurse(qry, (Node *)qry, matviewOid, &relids, ex_lock);
+
+	bms_free(relids);
+}
+
+static void
+CreateIvmTriggersOnBaseTables_recurse(Query *qry, Node *node, Oid matviewOid, Relids *relids, bool ex_lock)
+{
+	/* This can recurse, so check for excessive recursion */
+	check_stack_depth();
+
+	if (node == NULL)
+		return;
+
+	switch (nodeTag(node))
+	{
+		case T_Query:
+			{
+				Query *query = (Query *) node;
+
+				CreateIvmTriggersOnBaseTables_recurse(qry, (Node *)query->jointree, matviewOid, relids, ex_lock);
+			}
+			break;
+
+		case T_RangeTblRef:
+			{
+				int			rti = ((RangeTblRef *) node)->rtindex;
+				RangeTblEntry *rte = rt_fetch(rti, qry->rtable);
+
+				if (rte->rtekind == RTE_RELATION)
+				{
+					if (!bms_is_member(rte->relid, *relids))
+					{
+						CreateIvmTrigger(rte->relid, matviewOid, TRIGGER_TYPE_INSERT, TRIGGER_TYPE_BEFORE, ex_lock);
+						CreateIvmTrigger(rte->relid, matviewOid, TRIGGER_TYPE_DELETE, TRIGGER_TYPE_BEFORE, ex_lock);
+						CreateIvmTrigger(rte->relid, matviewOid, TRIGGER_TYPE_UPDATE, TRIGGER_TYPE_BEFORE, ex_lock);
+						CreateIvmTrigger(rte->relid, matviewOid, TRIGGER_TYPE_INSERT, TRIGGER_TYPE_AFTER, ex_lock);
+						CreateIvmTrigger(rte->relid, matviewOid, TRIGGER_TYPE_DELETE, TRIGGER_TYPE_AFTER, ex_lock);
+						CreateIvmTrigger(rte->relid, matviewOid, TRIGGER_TYPE_UPDATE, TRIGGER_TYPE_AFTER, ex_lock);
+
+						*relids = bms_add_member(*relids, rte->relid);
+					}
+				}
+			}
+			break;
+
+		case T_FromExpr:
+			{
+				FromExpr   *f = (FromExpr *) node;
+				ListCell   *l;
+
+				foreach(l, f->fromlist)
+					CreateIvmTriggersOnBaseTables_recurse(qry, lfirst(l), matviewOid, relids, ex_lock);
+			}
+			break;
+
+		case T_JoinExpr:
+			{
+				JoinExpr   *j = (JoinExpr *) node;
+
+				CreateIvmTriggersOnBaseTables_recurse(qry, j->larg, matviewOid, relids, ex_lock);
+				CreateIvmTriggersOnBaseTables_recurse(qry, j->rarg, matviewOid, relids, ex_lock);
+			}
+			break;
+
+		default:
+			elog(ERROR, "unrecognized node type: %d", (int) nodeTag(node));
+	}
+}
+
+/*
+ * CreateIvmTrigger -- create IVM trigger on a base table
+ */
+static void
+CreateIvmTrigger(Oid relOid, Oid viewOid, int16 type, int16 timing, bool ex_lock)
+{
+	ObjectAddress	refaddr;
+	ObjectAddress	address;
+	CreateTrigStmt *ivm_trigger;
+	List *transitionRels = NIL;
+
+	Assert(timing == TRIGGER_TYPE_BEFORE || timing == TRIGGER_TYPE_AFTER);
+
+	refaddr.classId = RelationRelationId;
+	refaddr.objectId = viewOid;
+	refaddr.objectSubId = 0;
+
+	ivm_trigger = makeNode(CreateTrigStmt);
+	ivm_trigger->relation = NULL;
+	ivm_trigger->row = false;
+
+	ivm_trigger->timing = timing;
+	ivm_trigger->events = type;
+
+	switch (type)
+	{
+		case TRIGGER_TYPE_INSERT:
+			ivm_trigger->trigname = (timing == TRIGGER_TYPE_BEFORE ? "IVM_trigger_ins_before" : "IVM_trigger_ins_after");
+			break;
+		case TRIGGER_TYPE_DELETE:
+			ivm_trigger->trigname = (timing == TRIGGER_TYPE_BEFORE ? "IVM_trigger_del_before" : "IVM_trigger_del_after");
+			break;
+		case TRIGGER_TYPE_UPDATE:
+			ivm_trigger->trigname = (timing == TRIGGER_TYPE_BEFORE ? "IVM_trigger_upd_before" : "IVM_trigger_upd_after");
+			break;
+		default:
+			elog(ERROR, "unsupported trigger type");
+	}
+
+	if (timing == TRIGGER_TYPE_AFTER)
+	{
+		if (type == TRIGGER_TYPE_INSERT || type == TRIGGER_TYPE_UPDATE)
+		{
+			TriggerTransition *n = makeNode(TriggerTransition);
+			n->name = "__ivm_newtable";
+			n->isNew = true;
+			n->isTable = true;
+
+			transitionRels = lappend(transitionRels, n);
+		}
+		if (type == TRIGGER_TYPE_DELETE || type == TRIGGER_TYPE_UPDATE)
+		{
+			TriggerTransition *n = makeNode(TriggerTransition);
+			n->name = "__ivm_oldtable";
+			n->isNew = false;
+			n->isTable = true;
+
+			transitionRels = lappend(transitionRels, n);
+		}
+	}
+
+	ivm_trigger->funcname =
+		(timing == TRIGGER_TYPE_BEFORE ? SystemFuncName("IVM_immediate_before") : SystemFuncName("IVM_immediate_maintenance"));
+
+	ivm_trigger->columns = NIL;
+	ivm_trigger->transitionRels = transitionRels;
+	ivm_trigger->whenClause = NULL;
+	ivm_trigger->isconstraint = false;
+	ivm_trigger->deferrable = false;
+	ivm_trigger->initdeferred = false;
+	ivm_trigger->constrrel = NULL;
+	ivm_trigger->args = list_make2(
+		makeString(DatumGetPointer(DirectFunctionCall1(oidout, ObjectIdGetDatum(viewOid)))),
+		makeString(DatumGetPointer(DirectFunctionCall1(boolout, BoolGetDatum(ex_lock))))
+		);
+
+	address = CreateTrigger(ivm_trigger, NULL, relOid, InvalidOid, InvalidOid,
+						 InvalidOid, InvalidOid, InvalidOid, NULL, true, false);
+
+	recordDependencyOn(&address, &refaddr, DEPENDENCY_IMMV);
+
+	/* Make changes-so-far visible */
+	CommandCounterIncrement();
+}
+
+/*
+ * check_ivm_restriction --- look for specify nodes in the query tree
+ */
+static void
+check_ivm_restriction(Node *node)
+{
+	check_ivm_restriction_walker(node, NULL);
+}
+
+static bool
+check_ivm_restriction_walker(Node *node, void *context)
+{
+	/* This can recurse, so check for excessive recursion */
+	check_stack_depth();
+
+	if (node == NULL)
+		return false;
+
+	/*
+	 * We currently don't support Sub-Query.
+	 */
+	if (IsA(node, SubPlan) || IsA(node, SubLink))
+		ereport(ERROR,
+				(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+				 errmsg("subquery is not supported on incrementally maintainable materialized view")));
+
+	switch (nodeTag(node))
+	{
+		case T_Query:
+			{
+				Query *qry = (Query *)node;
+				ListCell   *lc;
+				List       *vars;
+
+				/* if contained CTE, return error */
+				if (qry->cteList != NIL)
+					ereport(ERROR,
+							(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+							 errmsg("CTE is not supported on incrementally maintainable materialized view")));
+				if (qry->havingQual != NULL)
+					ereport(ERROR,
+							(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+							 errmsg(" HAVING clause is not supported on incrementally maintainable materialized view")));
+				if (qry->sortClause != NIL)	/* There is a possibility that we don't need to return an error */
+					ereport(ERROR,
+							(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+							 errmsg("ORDER BY clause is not supported on incrementally maintainable materialized view")));
+				if (qry->limitOffset != NULL || qry->limitCount != NULL)
+					ereport(ERROR,
+							(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+							 errmsg("LIMIT/OFFSET clause is not supported on incrementally maintainable materialized view")));
+				if (qry->hasDistinctOn)
+					ereport(ERROR,
+							(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+							 errmsg("DISTINCT ON is not supported on incrementally maintainable materialized view")));
+				if (qry->hasWindowFuncs)
+					ereport(ERROR,
+							(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+							 errmsg("window functions are not supported on incrementally maintainable materialized view")));
+				if (qry->groupingSets != NIL)
+					ereport(ERROR,
+							(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+							 errmsg("GROUPING SETS, ROLLUP, or CUBE clauses is not supported on incrementally maintainable materialized view")));
+				if (qry->setOperations != NULL)
+					ereport(ERROR,
+							(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+							 errmsg("UNION/INTERSECT/EXCEPT statements are not supported on incrementally maintainable materialized view")));
+				if (list_length(qry->targetList) == 0)
+					ereport(ERROR,
+							(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+							 errmsg("empty target list is not supported on incrementally maintainable materialized view")));
+				if (qry->rowMarks != NIL)
+					ereport(ERROR,
+							(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+							 errmsg("FOR UPDATE/SHARE clause is not supported on incrementally maintainable materialized view")));
+
+				/* system column restrictions */
+				vars = pull_vars_of_level((Node *) qry, 0);
+				foreach(lc, vars)
+				{
+					if (IsA(lfirst(lc), Var))
+					{
+						Var *var = (Var *) lfirst(lc);
+						/* if system column, return error */
+						if (var->varattno < 0)
+							ereport(ERROR,
+									(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+									 errmsg("system column is not supported on incrementally maintainable materialized view")));
+					}
+				}
+
+				/* restrictions for rtable */
+				foreach(lc, qry->rtable)
+				{
+					RangeTblEntry *rte = (RangeTblEntry *) lfirst(lc);
+
+					if (rte->subquery)
+						ereport(ERROR,
+								(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+								 errmsg("subquery is not supported on incrementally maintainable materialized view")));
+
+					if (rte->tablesample != NULL)
+						ereport(ERROR,
+								(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+								 errmsg("TABLESAMPLE clause is not supported on incrementally maintainable materialized view")));
+
+					if (rte->relkind == RELKIND_RELATION && find_inheritance_children(rte->relid, NoLock) != NIL)
+						ereport(ERROR,
+								(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+								 errmsg("inheritance parent is not supported on incrementally maintainable materialized view")));
+
+					if (rte->relkind == RELKIND_VIEW ||
+						rte->relkind == RELKIND_MATVIEW)
+						ereport(ERROR,
+								(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+								 errmsg("VIEW or MATERIALIZED VIEW is not supported on incrementally maintainable materialized view")));
+
+					if (rte->rtekind == RTE_VALUES)
+						ereport(ERROR,
+								(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+								 errmsg("VALUES is not supported on incrementally maintainable materialized view")));
+
+				}
+
+				query_tree_walker(qry, check_ivm_restriction_walker, NULL, QTW_IGNORE_RANGE_TABLE);
+
+				break;
+			}
+		case T_TargetEntry:
+			{
+				TargetEntry *tle = (TargetEntry *)node;
+				if (isIvmName(tle->resname))
+						ereport(ERROR,
+								(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+								 errmsg("column name %s is not supported on incrementally maintainable materialized view", tle->resname)));
+
+				expression_tree_walker(node, check_ivm_restriction_walker, NULL);
+				break;
+			}
+		case T_JoinExpr:
+			{
+				JoinExpr *joinexpr = (JoinExpr *)node;
+
+				if (joinexpr->jointype > JOIN_INNER)
+						ereport(ERROR,
+								(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+								 errmsg("OUTER JOIN is not supported on incrementally maintainable materialized view")));
+
+				expression_tree_walker(node, check_ivm_restriction_walker, NULL);
+			}
+			break;
+			expression_tree_walker(node, check_ivm_restriction_walker, NULL);
+			break;
+	}
+	return false;
+}
+
+/*
+ * CreateindexOnIMMV
+ *
+ * Create a unique index on incremental maintainable materialized view.
+ * If the view definition query has a GROUP BY clause, the index is created
+ * on the columns of GROUP BY expressions. Otherwise, if the view contains
+ * all primary key attritubes of its base tables in the target list, the index
+ * is created on these attritubes. In other cases, no index is created.
+ */
+static void
+CreateIndexOnIMMV(Query *query, Relation matviewRel)
+{
+	Query *qry = (Query *) copyObject(query);
+	ListCell *lc;
+	IndexStmt  *index;
+	ObjectAddress address;
+	List *constraintList = NIL;
+	char		idxname[NAMEDATALEN];
+
+	snprintf(idxname, sizeof(idxname), "%s_index", RelationGetRelationName(matviewRel));
+
+	index = makeNode(IndexStmt);
+
+	index->unique = true;
+	index->primary = false;
+	index->isconstraint = false;
+	index->deferrable = false;
+	index->initdeferred = false;
+	index->idxname = idxname;
+	index->relation =
+		makeRangeVar(get_namespace_name(RelationGetNamespace(matviewRel)),
+					 pstrdup(RelationGetRelationName(matviewRel)),
+					 -1);
+	index->accessMethod = DEFAULT_INDEX_TYPE;
+	index->options = NIL;
+	index->tableSpace = get_tablespace_name(matviewRel->rd_rel->reltablespace);
+	index->whereClause = NULL;
+	index->indexParams = NIL;
+	index->indexIncludingParams = NIL;
+	index->excludeOpNames = NIL;
+	index->idxcomment = NULL;
+	index->indexOid = InvalidOid;
+	index->oldNode = InvalidOid;
+	index->oldCreateSubid = InvalidSubTransactionId;
+	index->oldFirstRelfilenodeSubid = InvalidSubTransactionId;
+	index->transformed = true;
+	index->concurrent = false;
+	index->if_not_exists = false;
+
+	if (qry->distinctClause)
+	{
+		/* create unique constraint on all columns */
+		index->isconstraint = true;
+		foreach(lc, qry->targetList)
+		{
+			TargetEntry *tle = (TargetEntry *) lfirst(lc);
+			Form_pg_attribute attr = TupleDescAttr(matviewRel->rd_att, tle->resno - 1);
+			IndexElem  *iparam;
+
+			iparam = makeNode(IndexElem);
+			iparam->name = pstrdup(NameStr(attr->attname));
+			iparam->expr = NULL;
+			iparam->indexcolname = NULL;
+			iparam->collation = NIL;
+			iparam->opclass = NIL;
+			iparam->opclassopts = NIL;
+			iparam->ordering = SORTBY_DEFAULT;
+			iparam->nulls_ordering = SORTBY_NULLS_DEFAULT;
+			index->indexParams = lappend(index->indexParams, iparam);
+		}
+	}
+	else
+	{
+		Bitmapset *key_attnos;
+
+		/* create index on the base tables' primary key columns */
+		key_attnos = get_primary_key_attnos_from_query(qry, &constraintList);
+		if (key_attnos)
+		{
+			foreach(lc, qry->targetList)
+			{
+				TargetEntry *tle = (TargetEntry *) lfirst(lc);
+				Form_pg_attribute attr = TupleDescAttr(matviewRel->rd_att, tle->resno - 1);
+
+				if (bms_is_member(tle->resno - FirstLowInvalidHeapAttributeNumber, key_attnos))
+				{
+					IndexElem  *iparam;
+
+					iparam = makeNode(IndexElem);
+					iparam->name = pstrdup(NameStr(attr->attname));
+					iparam->expr = NULL;
+					iparam->indexcolname = NULL;
+					iparam->collation = NIL;
+					iparam->opclass = NIL;
+					iparam->opclassopts = NIL;
+					iparam->ordering = SORTBY_DEFAULT;
+					iparam->nulls_ordering = SORTBY_NULLS_DEFAULT;
+					index->indexParams = lappend(index->indexParams, iparam);
+				}
+			}
+
+		}
+		else
+		{
+			/* create no index, just notice that an appropriate index is necessary for efficient, IVM */
+			ereport(NOTICE,
+					(errmsg("could not create an index on materialized view \"%s\" automatically",
+							RelationGetRelationName(matviewRel)),
+					errhint("Create an index on the materialized view for efficient incremental maintenance.")));
+			return;
+		}
+	}
+
+	address = DefineIndex(RelationGetRelid(matviewRel),
+						  index,
+						  InvalidOid,
+						  InvalidOid,
+						  InvalidOid,
+						  false, true, false, false, true);
+
+	ereport(NOTICE,
+			(errmsg("created index \"%s\" on materialized view \"%s\"",
+					idxname, RelationGetRelationName(matviewRel))));
+
+
+	/*
+	 * Make dependencies so that the index is dropped if any base tables's
+	 * primary key is dropped.
+	 */
+	foreach(lc, constraintList)
+	{
+		Oid constraintOid = lfirst_oid(lc);
+		ObjectAddress	refaddr;
+
+		refaddr.classId = ConstraintRelationId;
+		refaddr.objectId = constraintOid;
+		refaddr.objectSubId = 0;
+
+		recordDependencyOn(&address, &refaddr, DEPENDENCY_NORMAL);
+	}
+}
+
+
+/*
+ * get_primary_key_attnos_from_query
+ *
+ * Identify the columns in base tables' primary keys in the target list.
+ *
+ * Returns a Bitmapset of the column attnos of the primary key's columns of
+ * tables that used in the query.  The attnos are offset by
+ * FirstLowInvalidHeapAttributeNumber as same as get_primary_key_attnos.
+ *
+ * If any table has no primary key or any primary key's columns is not in
+ * the target list, return NULL.  We also return NULL if any pkey constraint
+ * is deferrable.
+ *
+ * constraintList is set to a list of the OIDs of the pkey constraints.
+ */
+static Bitmapset *
+get_primary_key_attnos_from_query(Query *query, List **constraintList)
+{
+	List *key_attnos_list = NIL;
+	ListCell *lc;
+	int i;
+	Bitmapset *keys = NULL;
+	Relids	rels_in_from;
+	PlannerInfo root;
+
+
+	/*
+	 * Collect primary key attributes from all tables used in query. The key attributes
+	 * sets for each table are stored in key_attnos_list in order by RTE index.
+	 */
+	i = 1;
+	foreach(lc, query->rtable)
+	{
+		RangeTblEntry *r = (RangeTblEntry*) lfirst(lc);
+		Bitmapset *key_attnos;
+		bool	has_pkey = true;
+
+		/* for tables, call get_primary_key_attnos */
+		if (r->rtekind == RTE_RELATION)
+		{
+			Oid constraintOid;
+			key_attnos = get_primary_key_attnos(r->relid, false, &constraintOid);
+			*constraintList = lappend_oid(*constraintList, constraintOid);
+			has_pkey = (key_attnos != NULL);
+		}
+		/* for other RTEs, store NULL into key_attnos_list */
+		else
+			key_attnos = NULL;
+
+		/*
+		 * If any table or subquery has no primary key or its pkey constraint is deferrable,
+		 * we cannot get key attributes for this query, so return NULL.
+		 */
+		if (!has_pkey)
+			return NULL;
+
+		key_attnos_list = lappend(key_attnos_list, key_attnos);
+	}
+
+	/* Collect key attributes appearing in the target list */
+	i = 1;
+	foreach(lc, query->targetList)
+	{
+		TargetEntry *tle = (TargetEntry *) flatten_join_alias_vars(query, lfirst(lc));
+
+		if (IsA(tle->expr, Var))
+		{
+			Var *var = (Var*) tle->expr;
+			Bitmapset *attnos = list_nth(key_attnos_list, var->varno - 1);
+
+			/* check if this attribute is from a base table's primary key */
+			if (bms_is_member(var->varattno - FirstLowInvalidHeapAttributeNumber, attnos))
+			{
+				/*
+				 * Remove found key attributes from key_attnos_list, and add this
+				 * to the result list.
+				 */
+				bms_del_member(attnos, var->varattno - FirstLowInvalidHeapAttributeNumber);
+				keys = bms_add_member(keys, i - FirstLowInvalidHeapAttributeNumber);
+			}
+		}
+		i++;
+	}
+
+	/* Collect relations appearing in the FROM clause */
+	rels_in_from = pull_varnos_of_level(&root, (Node *)query->jointree, 0);
+
+	/*
+	 * Check if all key attributes of relations in FROM are appearing in the target
+	 * list.  If an attribute remains in key_attnos_list in spite of the table is used
+	 * in FROM clause, the target is missing this key attribute, so we return NULL.
+	 */
+	i = 1;
+	foreach(lc, key_attnos_list)
+	{
+		Bitmapset *bms = (Bitmapset *)lfirst(lc);
+		if (!bms_is_empty(bms) && bms_is_member(i, rels_in_from))
+			return NULL;
+		i++;
+	}
+
+	return keys;
+}
diff --git a/src/backend/commands/indexcmds.c b/src/backend/commands/indexcmds.c
index c14ca27c5e..5581c21298 100644
--- a/src/backend/commands/indexcmds.c
+++ b/src/backend/commands/indexcmds.c
@@ -36,6 +36,7 @@
 #include "commands/dbcommands.h"
 #include "commands/defrem.h"
 #include "commands/event_trigger.h"
+#include "commands/matview.h"
 #include "commands/progress.h"
 #include "commands/tablecmds.h"
 #include "commands/tablespace.h"
@@ -1054,6 +1055,45 @@ DefineIndex(Oid relationId,
 	safe_index = indexInfo->ii_Expressions == NIL &&
 		indexInfo->ii_Predicate == NIL;
 
+	/*
+	 * We disallow unique indexes on IVM columns of IMMVs.
+	 */
+	if (RelationIsIVM(rel) && stmt->unique)
+	{
+		for (i = 0; i < indexInfo->ii_NumIndexKeyAttrs; i++)
+		{
+			AttrNumber	attno = indexInfo->ii_IndexAttrNumbers[i];
+			if (attno > 0)
+			{
+				char *name = NameStr(TupleDescAttr(rel->rd_att, attno - 1)->attname);
+				if (name && isIvmName(name))
+					ereport(ERROR,
+							(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+							 errmsg("unique index creation on IVM columns is not supported")));
+			}
+		}
+
+		if (indexInfo->ii_Expressions)
+		{
+			Bitmapset  *indexattrs = NULL;
+			int			varno = -1;
+
+			pull_varattnos((Node *) indexInfo->ii_Expressions, 1, &indexattrs);
+
+			while ((varno = bms_next_member(indexattrs, varno)) >= 0)
+			{
+				int attno = varno + FirstLowInvalidHeapAttributeNumber;
+				char *name = NameStr(TupleDescAttr(rel->rd_att, attno - 1)->attname);
+				if (name && isIvmName(name))
+					ereport(ERROR,
+							(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+							 errmsg("unique index creation on IVM columns is not supported")));
+			}
+
+		}
+	}
+
+
 	/*
 	 * Report index creation if appropriate (delay this till after most of the
 	 * error checks)
diff --git a/src/backend/commands/matview.c b/src/backend/commands/matview.c
index 25bbd8a5c1..f1f46e2e14 100644
--- a/src/backend/commands/matview.c
+++ b/src/backend/commands/matview.c
@@ -25,26 +25,47 @@
 #include "catalog/indexing.h"
 #include "catalog/namespace.h"
 #include "catalog/pg_am.h"
+#include "catalog/pg_collation.h"
+#include "catalog/pg_depend.h"
+#include "catalog/pg_type.h"
 #include "catalog/pg_opclass.h"
 #include "catalog/pg_operator.h"
 #include "commands/cluster.h"
+#include "commands/defrem.h"
 #include "commands/matview.h"
 #include "commands/tablecmds.h"
 #include "commands/tablespace.h"
+#include "commands/createas.h"
 #include "executor/executor.h"
 #include "executor/spi.h"
+#include "executor/tstoreReceiver.h"
 #include "miscadmin.h"
+#include "nodes/makefuncs.h"
+#include "nodes/nodeFuncs.h"
+#include "optimizer/optimizer.h"
+#include "parser/analyze.h"
+#include "parser/parser.h"
+#include "parser/parsetree.h"
+#include "parser/parse_clause.h"
+#include "parser/parse_coerce.h"
+#include "parser/parse_collate.h"
+#include "parser/parse_func.h"
 #include "parser/parse_relation.h"
+#include "parser/parse_type.h"
 #include "pgstat.h"
 #include "rewrite/rewriteHandler.h"
+#include "rewrite/rewriteManip.h"
+#include "rewrite/rowsecurity.h"
 #include "storage/lmgr.h"
 #include "storage/smgr.h"
 #include "tcop/tcopprot.h"
 #include "utils/builtins.h"
+#include "utils/fmgroids.h"
 #include "utils/lsyscache.h"
 #include "utils/rel.h"
 #include "utils/snapmgr.h"
 #include "utils/syscache.h"
+#include "utils/typcache.h"
 
 
 typedef struct
@@ -58,6 +79,50 @@ typedef struct
 	BulkInsertState bistate;	/* bulk insert state */
 } DR_transientrel;
 
+#define MV_INIT_QUERYHASHSIZE	16
+
+/*
+ * MV_TriggerHashEntry
+ *
+ * Hash entry for base tables on which IVM trigger is invoked
+ */
+typedef struct MV_TriggerHashEntry
+{
+	Oid	matview_id;			/* OID of the materialized view */
+	int	before_trig_count;	/* count of before triggers invoked */
+	int	after_trig_count;	/* count of after triggers invoked */
+
+	TransactionId	xid;	/* Transaction id before the first table is modified*/
+	CommandId		cid;	/* Command id before the first table is modified */
+
+	List   *tables;		/* List of MV_TriggerTable */
+	bool	has_old;	/* tuples are deleted from any table? */
+	bool	has_new;	/* tuples are inserted into any table? */
+} MV_TriggerHashEntry;
+
+/*
+ * MV_TriggerTable
+ *
+ * IVM related data for tables on which the trigger is invoked.
+ */
+typedef struct MV_TriggerTable
+{
+	Oid		table_id;			/* OID of the modified table */
+	List   *old_tuplestores;	/* tuplestores for deleted tuples */
+	List   *new_tuplestores;	/* tuplestores for inserted tuples */
+	List   *old_rtes;			/* RTEs of ENRs for old_tuplestores*/
+	List   *new_rtes;			/* RTEs of ENRs for new_tuplestores */
+
+	List   *rte_indexes;		/* List of RTE index of the modified table */
+	RangeTblEntry *original_rte;	/* the original RTE saved before rewriting query */
+} MV_TriggerTable;
+
+static HTAB *mv_trigger_info = NULL;
+
+/* ENR name for materialized view delta */
+#define NEW_DELTA_ENRNAME "new_delta"
+#define OLD_DELTA_ENRNAME "old_delta"
+
 static int	matview_maintenance_depth = 0;
 
 static void transientrel_startup(DestReceiver *self, int operation, TupleDesc typeinfo);
@@ -65,7 +130,9 @@ static bool transientrel_receive(TupleTableSlot *slot, DestReceiver *self);
 static void transientrel_shutdown(DestReceiver *self);
 static void transientrel_destroy(DestReceiver *self);
 static uint64 refresh_matview_datafill(DestReceiver *dest, Query *query,
-									   const char *queryString);
+						 QueryEnvironment *queryEnv,
+						 TupleDesc *resultTupleDesc,
+						 const char *queryString);
 static char *make_temptable_name_n(char *tempname, int n);
 static void refresh_by_match_merge(Oid matviewOid, Oid tempOid, Oid relowner,
 								   int save_sec_context);
@@ -73,6 +140,45 @@ static void refresh_by_heap_swap(Oid matviewOid, Oid OIDNewHeap, char relpersist
 static bool is_usable_unique_index(Relation indexRel);
 static void OpenMatViewIncrementalMaintenance(void);
 static void CloseMatViewIncrementalMaintenance(void);
+static Query *get_matview_query(Relation matviewRel);
+
+static Query *rewrite_query_for_preupdate_state(Query *query, List *tables,
+								  TransactionId xid, CommandId cid,
+								  ParseState *pstate);
+static void register_delta_ENRs(ParseState *pstate, Query *query, List *tables);
+static char *make_delta_enr_name(const char *prefix, Oid relid, int count);
+static RangeTblEntry *get_prestate_rte(RangeTblEntry *rte, MV_TriggerTable *table,
+				 TransactionId xid, CommandId cid,
+				 QueryEnvironment *queryEnv);
+static RangeTblEntry *union_ENRs(RangeTblEntry *rte, Oid relid, List *enr_rtes, const char *prefix,
+		   QueryEnvironment *queryEnv);
+static Query *rewrite_query_for_distinct(Query *query, ParseState *pstate);
+
+static void calc_delta(MV_TriggerTable *table, int rte_index, Query *query,
+			DestReceiver *dest_old, DestReceiver *dest_new,
+			TupleDesc *tupdesc_old, TupleDesc *tupdesc_new,
+			QueryEnvironment *queryEnv);
+static Query *rewrite_query_for_postupdate_state(Query *query, MV_TriggerTable *table, int rte_index);
+
+static void apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *new_tuplestores,
+			TupleDesc tupdesc_old, TupleDesc tupdesc_new,
+			Query *query, bool use_count, char *count_colname);
+static void apply_old_delta(const char *matviewname, const char *deltaname_old,
+				List *keys);
+static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old,
+				List *keys, const char *count_colname);
+static void apply_new_delta(const char *matviewname, const char *deltaname_new,
+				StringInfo target_list);
+static void apply_new_delta_with_count(const char *matviewname, const char* deltaname_new,
+				List *keys, StringInfo target_list, const char* count_colname);
+static char *get_matching_condition_string(List *keys);
+static void generate_equal(StringInfo querybuf, Oid opttype,
+			   const char *leftop, const char *rightop);
+
+static void mv_InitHashTables(void);
+static void clean_up_IVM_hash_entry(MV_TriggerHashEntry *entry);
+
+static List *get_securityQuals(Oid relId, int rt_index, Query *query);
 
 /*
  * SetMatViewPopulatedState
@@ -114,6 +220,46 @@ SetMatViewPopulatedState(Relation relation, bool newstate)
 	CommandCounterIncrement();
 }
 
+/*
+ * SetMatViewIVMState
+ *		Mark a materialized view as IVM, or not.
+ *
+ * NOTE: caller must be holding an appropriate lock on the relation.
+ */
+void
+SetMatViewIVMState(Relation relation, bool newstate)
+{
+	Relation	pgrel;
+	HeapTuple	tuple;
+
+	Assert(relation->rd_rel->relkind == RELKIND_MATVIEW);
+
+	/*
+	 * Update relation's pg_class entry.  Crucial side-effect: other backends
+	 * (and this one too!) are sent SI message to make them rebuild relcache
+	 * entries.
+	 */
+	pgrel = table_open(RelationRelationId, RowExclusiveLock);
+	tuple = SearchSysCacheCopy1(RELOID,
+								ObjectIdGetDatum(RelationGetRelid(relation)));
+	if (!HeapTupleIsValid(tuple))
+		elog(ERROR, "cache lookup failed for relation %u",
+			 RelationGetRelid(relation));
+
+	((Form_pg_class) GETSTRUCT(tuple))->relisivm = newstate;
+
+	CatalogTupleUpdate(pgrel, &tuple->t_self, tuple);
+
+	heap_freetuple(tuple);
+	table_close(pgrel, RowExclusiveLock);
+
+	/*
+	 * Advance command counter to make the updated pg_class row locally
+	 * visible.
+	 */
+	CommandCounterIncrement();
+}
+
 /*
  * ExecRefreshMatView -- execute a REFRESH MATERIALIZED VIEW command
  *
@@ -140,8 +286,6 @@ ExecRefreshMatView(RefreshMatViewStmt *stmt, const char *queryString,
 {
 	Oid			matviewOid;
 	Relation	matviewRel;
-	RewriteRule *rule;
-	List	   *actions;
 	Query	   *dataQuery;
 	Oid			tableSpace;
 	Oid			relowner;
@@ -155,6 +299,7 @@ ExecRefreshMatView(RefreshMatViewStmt *stmt, const char *queryString,
 	int			save_sec_context;
 	int			save_nestlevel;
 	ObjectAddress address;
+	bool oldPopulated;
 
 	/* Determine strength of lock needed. */
 	concurrent = stmt->concurrent;
@@ -167,6 +312,7 @@ ExecRefreshMatView(RefreshMatViewStmt *stmt, const char *queryString,
 										  lockmode, 0,
 										  RangeVarCallbackOwnsTable, NULL);
 	matviewRel = table_open(matviewOid, NoLock);
+	oldPopulated = RelationIsPopulated(matviewRel);
 
 	/* Make sure it is a materialized view. */
 	if (matviewRel->rd_rel->relkind != RELKIND_MATVIEW)
@@ -187,32 +333,12 @@ ExecRefreshMatView(RefreshMatViewStmt *stmt, const char *queryString,
 				(errcode(ERRCODE_SYNTAX_ERROR),
 				 errmsg("CONCURRENTLY and WITH NO DATA options cannot be used together")));
 
-	/*
-	 * Check that everything is correct for a refresh. Problems at this point
-	 * are internal errors, so elog is sufficient.
-	 */
-	if (matviewRel->rd_rel->relhasrules == false ||
-		matviewRel->rd_rules->numLocks < 1)
-		elog(ERROR,
-			 "materialized view \"%s\" is missing rewrite information",
-			 RelationGetRelationName(matviewRel));
-
-	if (matviewRel->rd_rules->numLocks > 1)
-		elog(ERROR,
-			 "materialized view \"%s\" has too many rules",
-			 RelationGetRelationName(matviewRel));
 
-	rule = matviewRel->rd_rules->rules[0];
-	if (rule->event != CMD_SELECT || !(rule->isInstead))
-		elog(ERROR,
-			 "the rule for materialized view \"%s\" is not a SELECT INSTEAD OF rule",
-			 RelationGetRelationName(matviewRel));
+	dataQuery = get_matview_query(matviewRel);
 
-	actions = rule->actions;
-	if (list_length(actions) != 1)
-		elog(ERROR,
-			 "the rule for materialized view \"%s\" is not a single action",
-			 RelationGetRelationName(matviewRel));
+	/* For IMMV, we need to rewrite matview query */
+	if (!stmt->skipData && RelationIsIVM(matviewRel))
+		dataQuery = rewriteQueryForIMMV(dataQuery,NIL);
 
 	/*
 	 * Check that there is a unique index with no WHERE clause on one or more
@@ -247,12 +373,6 @@ ExecRefreshMatView(RefreshMatViewStmt *stmt, const char *queryString,
 					 errhint("Create a unique index with no WHERE clause on one or more columns of the materialized view.")));
 	}
 
-	/*
-	 * The stored query was rewritten at the time of the MV definition, but
-	 * has not been scribbled on by the planner.
-	 */
-	dataQuery = linitial_node(Query, actions);
-
 	/*
 	 * Check for active uses of the relation in the current transaction, such
 	 * as open scans.
@@ -293,6 +413,52 @@ ExecRefreshMatView(RefreshMatViewStmt *stmt, const char *queryString,
 		relpersistence = matviewRel->rd_rel->relpersistence;
 	}
 
+	/* delete immv triggers */
+	if (RelationIsIVM(matviewRel) && stmt->skipData )
+	{
+		/* use deleted trigger */
+		Relation	depRel;
+		ScanKeyData key;
+		SysScanDesc scan;
+		HeapTuple	tup;
+		ObjectAddresses *immv_triggers;
+
+		immv_triggers = new_object_addresses();
+
+		/*
+		 * We save some cycles by opening pg_depend just once and passing the
+		 * Relation pointer down to all the recursive deletion steps.
+		 */
+		depRel = table_open(DependRelationId, RowExclusiveLock);
+
+		ScanKeyInit(&key,
+					Anum_pg_depend_refobjid,
+					BTEqualStrategyNumber, F_OIDEQ,
+					ObjectIdGetDatum(matviewOid));
+
+		scan = systable_beginscan(depRel, DependReferenceIndexId, true,
+								  NULL, 1, &key);
+		while ((tup = systable_getnext(scan)) != NULL)
+		{
+			ObjectAddress obj;
+			Form_pg_depend foundDep = (Form_pg_depend) GETSTRUCT(tup);
+
+			if (foundDep->deptype == DEPENDENCY_IMMV)
+			{
+				obj.classId = foundDep->classid;
+				obj.objectId = foundDep->objid;
+				obj.objectSubId = foundDep->refobjsubid;
+				add_exact_object_address(&obj, immv_triggers);
+			}
+		}
+		systable_endscan(scan);
+
+		performMultipleDeletions(immv_triggers, DROP_RESTRICT, PERFORM_DELETION_INTERNAL);
+
+		table_close(depRel, RowExclusiveLock);
+		free_object_addresses(immv_triggers);
+	}
+
 	/*
 	 * Create the transient table that will receive the regenerated data. Lock
 	 * it against access by any other process until commit (by which time it
@@ -311,7 +477,7 @@ ExecRefreshMatView(RefreshMatViewStmt *stmt, const char *queryString,
 
 	/* Generate the data, if wanted. */
 	if (!stmt->skipData)
-		processed = refresh_matview_datafill(dest, dataQuery, queryString);
+		processed = refresh_matview_datafill(dest, dataQuery, NULL, NULL, queryString);
 
 	/* Make the matview match the newly generated data. */
 	if (concurrent)
@@ -346,6 +512,9 @@ ExecRefreshMatView(RefreshMatViewStmt *stmt, const char *queryString,
 			pgstat_count_heap_insert(matviewRel, processed);
 	}
 
+	if (!stmt->skipData && RelationIsIVM(matviewRel) && !oldPopulated)
+		CreateIvmTriggersOnBaseTables(dataQuery, matviewOid, false);
+
 	table_close(matviewRel, NoLock);
 
 	/* Roll back any GUC changes */
@@ -380,6 +549,8 @@ ExecRefreshMatView(RefreshMatViewStmt *stmt, const char *queryString,
  */
 static uint64
 refresh_matview_datafill(DestReceiver *dest, Query *query,
+						 QueryEnvironment *queryEnv,
+						 TupleDesc *resultTupleDesc,
 						 const char *queryString)
 {
 	List	   *rewritten;
@@ -416,7 +587,7 @@ refresh_matview_datafill(DestReceiver *dest, Query *query,
 	/* Create a QueryDesc, redirecting output to our tuple receiver */
 	queryDesc = CreateQueryDesc(plan, queryString,
 								GetActiveSnapshot(), InvalidSnapshot,
-								dest, NULL, NULL, 0);
+								dest, NULL, queryEnv ? queryEnv: NULL, 0);
 
 	/* call ExecutorStart to prepare the plan for execution */
 	ExecutorStart(queryDesc, 0);
@@ -426,6 +597,9 @@ refresh_matview_datafill(DestReceiver *dest, Query *query,
 
 	processed = queryDesc->estate->es_processed;
 
+	if (resultTupleDesc)
+		*resultTupleDesc = CreateTupleDescCopy(queryDesc->tupDesc);
+
 	/* and clean up */
 	ExecutorFinish(queryDesc);
 	ExecutorEnd(queryDesc);
@@ -933,3 +1107,1308 @@ CloseMatViewIncrementalMaintenance(void)
 	matview_maintenance_depth--;
 	Assert(matview_maintenance_depth >= 0);
 }
+
+/*
+ * get_matview_query - get the Query from a matview's _RETURN rule.
+ */
+static Query *
+get_matview_query(Relation matviewRel)
+{
+	RewriteRule *rule;
+	List * actions;
+
+	/*
+	 * Check that everything is correct for a refresh. Problems at this point
+	 * are internal errors, so elog is sufficient.
+	 */
+	if (matviewRel->rd_rel->relhasrules == false ||
+		matviewRel->rd_rules->numLocks < 1)
+		elog(ERROR,
+			 "materialized view \"%s\" is missing rewrite information",
+			 RelationGetRelationName(matviewRel));
+
+	if (matviewRel->rd_rules->numLocks > 1)
+		elog(ERROR,
+			 "materialized view \"%s\" has too many rules",
+			 RelationGetRelationName(matviewRel));
+
+	rule = matviewRel->rd_rules->rules[0];
+	if (rule->event != CMD_SELECT || !(rule->isInstead))
+		elog(ERROR,
+			 "the rule for materialized view \"%s\" is not a SELECT INSTEAD OF rule",
+			 RelationGetRelationName(matviewRel));
+
+	actions = rule->actions;
+	if (list_length(actions) != 1)
+		elog(ERROR,
+			 "the rule for materialized view \"%s\" is not a single action",
+			 RelationGetRelationName(matviewRel));
+
+	/*
+	 * The stored query was rewritten at the time of the MV definition, but
+	 * has not been scribbled on by the planner.
+	 */
+	return linitial_node(Query, actions);
+}
+
+
+/* ----------------------------------------------------
+ *		Incremental View Maintenance routines
+ * ---------------------------------------------------
+ */
+
+/*
+ * IVM_immediate_before
+ *
+ * IVM trigger function invoked before base table is modified. If this is
+ * invoked firstly in the same statement, we save the transaction id and the
+ * command id at that time.
+ */
+Datum
+IVM_immediate_before(PG_FUNCTION_ARGS)
+{
+	TriggerData *trigdata = (TriggerData *) fcinfo->context;
+	char	   *matviewOid_text = trigdata->tg_trigger->tgargs[0];
+	char	   *ex_lock_text = trigdata->tg_trigger->tgargs[1];
+	Oid			matviewOid;
+	MV_TriggerHashEntry *entry;
+	bool	found;
+	bool	ex_lock;
+
+	matviewOid = DatumGetObjectId(DirectFunctionCall1(oidin, CStringGetDatum(matviewOid_text)));
+	ex_lock = DatumGetBool(DirectFunctionCall1(boolin, CStringGetDatum(ex_lock_text)));
+
+	/* If the view has more than one tables, we have to use an exclusive lock. */
+	if (ex_lock)
+	{
+		/*
+		 * Wait for concurrent transactions which update this materialized view at
+		 * READ COMMITED. This is needed to see changes committed in other
+		 * transactions. No wait and raise an error at REPEATABLE READ or
+		 * SERIALIZABLE to prevent update anomalies of matviews.
+		 * XXX: dead-lock is possible here.
+		 */
+		if (!IsolationUsesXactSnapshot())
+			LockRelationOid(matviewOid, ExclusiveLock);
+		else if (!ConditionalLockRelationOid(matviewOid, ExclusiveLock))
+		{
+			/* try to throw error by name; relation could be deleted... */
+			char	   *relname = get_rel_name(matviewOid);
+
+			if (!relname)
+				ereport(ERROR,
+						(errcode(ERRCODE_LOCK_NOT_AVAILABLE),
+						errmsg("could not obtain lock on materialized view during incremental maintenance")));
+
+			ereport(ERROR,
+					(errcode(ERRCODE_LOCK_NOT_AVAILABLE),
+					errmsg("could not obtain lock on materialized view \"%s\" during incremental maintenance",
+							relname)));
+		}
+	}
+	else
+		LockRelationOid(matviewOid, RowExclusiveLock);
+
+	/*
+	 * On the first call initialize the hashtable
+	 */
+	if (!mv_trigger_info)
+		mv_InitHashTables();
+
+	entry = (MV_TriggerHashEntry *) hash_search(mv_trigger_info,
+											  (void *) &matviewOid,
+											  HASH_ENTER, &found);
+
+	/* On the first BEFORE to update the view, initialize trigger data */
+	if (!found)
+	{
+		Snapshot snapshot = GetActiveSnapshot();
+
+		entry->matview_id = matviewOid;
+		entry->before_trig_count = 0;
+		entry->after_trig_count = 0;
+		entry->xid = GetCurrentTransactionId();
+		entry->cid = snapshot->curcid;
+		entry->tables = NIL;
+		entry->has_old = false;
+		entry->has_new = false;
+	}
+
+	entry->before_trig_count++;
+
+	return PointerGetDatum(NULL);
+}
+
+/*
+ * IVM_immediate_before
+ *
+ * IVM trigger function invoked after base table is modified.
+ * For each table, tuplestores of transition tables are collected.
+ * and after the last modification
+ */
+Datum
+IVM_immediate_maintenance(PG_FUNCTION_ARGS)
+{
+	TriggerData *trigdata = (TriggerData *) fcinfo->context;
+	Relation	rel;
+	Oid			relid;
+	Oid			matviewOid;
+	Query	   *query;
+	Query	   *rewritten = NULL;
+	char	   *matviewOid_text = trigdata->tg_trigger->tgargs[0];
+	Relation	matviewRel;
+	int old_depth = matview_maintenance_depth;
+
+	Oid			relowner;
+	Tuplestorestate *old_tuplestore = NULL;
+	Tuplestorestate *new_tuplestore = NULL;
+	DestReceiver *dest_new = NULL, *dest_old = NULL;
+	Oid			save_userid;
+	int			save_sec_context;
+	int			save_nestlevel;
+
+	MV_TriggerHashEntry *entry;
+	MV_TriggerTable		*table;
+	bool	found;
+
+	ParseState		 *pstate;
+	QueryEnvironment *queryEnv = create_queryEnv();
+	MemoryContext	oldcxt;
+	ListCell   *lc;
+	int			i;
+
+
+	/* Create a ParseState for rewriting the view definition query */
+	pstate = make_parsestate(NULL);
+	pstate->p_queryEnv = queryEnv;
+	pstate->p_expr_kind = EXPR_KIND_SELECT_TARGET;
+
+	rel = trigdata->tg_relation;
+	relid = rel->rd_id;
+
+	matviewOid = DatumGetObjectId(DirectFunctionCall1(oidin, CStringGetDatum(matviewOid_text)));
+
+	/*
+	 * On the first call initialize the hashtable
+	 */
+	if (!mv_trigger_info)
+		mv_InitHashTables();
+
+	/* get the entry for this materialized view */
+	entry = (MV_TriggerHashEntry *) hash_search(mv_trigger_info,
+											  (void *) &matviewOid,
+											  HASH_FIND, &found);
+	Assert (found && entry != NULL);
+	entry->after_trig_count++;
+
+	/* search the entry for the modified table and create new entry if not found */
+	found = false;
+	foreach(lc, entry->tables)
+	{
+		table = (MV_TriggerTable *) lfirst(lc);
+		if (table->table_id == relid)
+		{
+			found = true;
+			break;
+		}
+	}
+	if (!found)
+	{
+		oldcxt = MemoryContextSwitchTo(TopTransactionContext);
+
+		table = (MV_TriggerTable *) palloc0(sizeof(MV_TriggerTable));
+		table->table_id = relid;
+		table->old_tuplestores = NIL;
+		table->new_tuplestores = NIL;
+		table->old_rtes = NIL;
+		table->new_rtes = NIL;
+		table->rte_indexes = NIL;
+		entry->tables = lappend(entry->tables, table);
+
+		MemoryContextSwitchTo(oldcxt);
+	}
+
+	/* Save the transition tables and make a request to not free immediately */
+	if (trigdata->tg_oldtable)
+	{
+		oldcxt = MemoryContextSwitchTo(TopTransactionContext);
+		table->old_tuplestores = lappend(table->old_tuplestores, trigdata->tg_oldtable);
+		entry->has_old = true;
+		MemoryContextSwitchTo(oldcxt);
+	}
+	if (trigdata->tg_newtable)
+	{
+		oldcxt = MemoryContextSwitchTo(TopTransactionContext);
+		table->new_tuplestores = lappend(table->new_tuplestores, trigdata->tg_newtable);
+		entry->has_new = true;
+		MemoryContextSwitchTo(oldcxt);
+	}
+	if (entry->has_new || entry->has_old)
+	{
+		CmdType cmd;
+
+		if (TRIGGER_FIRED_BY_INSERT(trigdata->tg_event))
+			cmd = CMD_INSERT;
+		else if (TRIGGER_FIRED_BY_DELETE(trigdata->tg_event))
+			cmd = CMD_DELETE;
+		else if (TRIGGER_FIRED_BY_UPDATE(trigdata->tg_event))
+			cmd = CMD_UPDATE;
+		else
+			elog(ERROR,"unsupported trigger type");
+
+		/* Prolong lifespan of transition tables to the end of the last AFTER trigger */
+		SetTransitionTablePreserved(relid, cmd);
+	}
+
+
+	/* If this is not the last AFTER trigger call, immediately exit. */
+	Assert (entry->before_trig_count >= entry->after_trig_count);
+	if (entry->before_trig_count != entry->after_trig_count)
+		return PointerGetDatum(NULL);
+
+	/*
+	 * If this is the last AFTER trigger call, continue and update the view.
+	 */
+
+	/*
+	 * Advance command counter to make the updated base table row locally
+	 * visible.
+	 */
+	CommandCounterIncrement();
+
+	matviewRel = table_open(matviewOid, NoLock);
+
+	/* get view query*/
+	query = get_matview_query(matviewRel);
+
+	/* Make sure it is a materialized view. */
+	Assert(matviewRel->rd_rel->relkind == RELKIND_MATVIEW);
+
+	/*
+	 * Get and push the latast snapshot to see any changes which is committed
+	 * during waiting in other transactions at READ COMMITTED level.
+	 */
+	PushActiveSnapshot(GetTransactionSnapshot());
+
+	/*
+	 * Check for active uses of the relation in the current transaction, such
+	 * as open scans.
+	 *
+	 * NB: We count on this to protect us against problems with refreshing the
+	 * data using TABLE_INSERT_FROZEN.
+	 */
+	CheckTableNotInUse(matviewRel, "refresh a materialized view incrementally");
+
+	/*
+	 * Switch to the owner's userid, so that any functions are run as that
+	 * user.  Also arrange to make GUC variable changes local to this command.
+	 * We will switch modes when we are about to execute user code.
+	 */
+	relowner = matviewRel->rd_rel->relowner;
+	GetUserIdAndSecContext(&save_userid, &save_sec_context);
+	SetUserIdAndSecContext(relowner,
+						   save_sec_context | SECURITY_RESTRICTED_OPERATION);
+	save_nestlevel = NewGUCNestLevel();
+
+	/*
+	 * rewrite query for calculating deltas
+	 */
+
+	rewritten = copyObject(query);
+
+	/* Replace resnames in a target list with materialized view's attnames */
+	i = 0;
+	foreach (lc, rewritten->targetList)
+	{
+		TargetEntry *tle = (TargetEntry *) lfirst(lc);
+		Form_pg_attribute attr = TupleDescAttr(matviewRel->rd_att, i);
+		char *resname = NameStr(attr->attname);
+
+		tle->resname = pstrdup(resname);
+		i++;
+	}
+
+	/* Set all tables in the query to pre-update state */
+	rewritten = rewrite_query_for_preupdate_state(rewritten, entry->tables,
+												  entry->xid, entry->cid,
+												  pstate);
+	/* Rewrite for DISTINCT clause */
+	rewritten = rewrite_query_for_distinct(rewritten, pstate);
+
+	/* Create tuplestores to store view deltas */
+	if (entry->has_old)
+	{
+		oldcxt = MemoryContextSwitchTo(TopTransactionContext);
+
+		old_tuplestore = tuplestore_begin_heap(false, false, work_mem);
+		dest_old = CreateDestReceiver(DestTuplestore);
+		SetTuplestoreDestReceiverParams(dest_old,
+									old_tuplestore,
+									TopTransactionContext,
+									false,
+									NULL,
+									NULL);
+
+		MemoryContextSwitchTo(oldcxt);
+	}
+	if (entry->has_new)
+	{
+		oldcxt = MemoryContextSwitchTo(TopTransactionContext);
+
+		new_tuplestore = tuplestore_begin_heap(false, false, work_mem);
+		dest_new = CreateDestReceiver(DestTuplestore);
+		SetTuplestoreDestReceiverParams(dest_new,
+									new_tuplestore,
+									TopTransactionContext,
+									false,
+									NULL,
+									NULL);
+		MemoryContextSwitchTo(oldcxt);
+	}
+
+	/* for all modified tables */
+	foreach(lc, entry->tables)
+	{
+		ListCell *lc2;
+
+		table = (MV_TriggerTable *) lfirst(lc);
+
+		/* loop for self-join */
+		foreach(lc2, table->rte_indexes)
+		{
+			int	rte_index = lfirst_int(lc2);
+			TupleDesc		tupdesc_old;
+			TupleDesc		tupdesc_new;
+			bool	use_count = false;
+			char   *count_colname = NULL;
+
+			count_colname = pstrdup("__ivm_count__");
+
+			if (query->distinctClause)
+				use_count = true;
+
+			/* calculate delta tables */
+			calc_delta(table, rte_index, rewritten, dest_old, dest_new,
+					   &tupdesc_old, &tupdesc_new, queryEnv);
+
+			/* Set the table in the query to post-update state */
+			rewritten = rewrite_query_for_postupdate_state(rewritten, table, rte_index);
+
+			PG_TRY();
+			{
+				/* apply the delta tables to the materialized view */
+				apply_delta(matviewOid, old_tuplestore, new_tuplestore,
+							tupdesc_old, tupdesc_new, query, use_count,
+							count_colname);
+			}
+			PG_CATCH();
+			{
+				matview_maintenance_depth = old_depth;
+				PG_RE_THROW();
+			}
+			PG_END_TRY();
+
+			/* clear view delta tuplestores */
+			if (old_tuplestore)
+				tuplestore_clear(old_tuplestore);
+			if (new_tuplestore)
+				tuplestore_clear(new_tuplestore);
+		}
+	}
+
+	/* Clean up hash entry and delete tuplestores */
+	clean_up_IVM_hash_entry(entry);
+	if (old_tuplestore)
+	{
+		dest_old->rDestroy(dest_old);
+		tuplestore_end(old_tuplestore);
+	}
+	if (new_tuplestore)
+	{
+		dest_new->rDestroy(dest_new);
+		tuplestore_end(new_tuplestore);
+	}
+
+	/* Pop the original snapshot. */
+	PopActiveSnapshot();
+
+	table_close(matviewRel, NoLock);
+
+	/* Roll back any GUC changes */
+	AtEOXact_GUC(false, save_nestlevel);
+
+	/* Restore userid and security context */
+	SetUserIdAndSecContext(save_userid, save_sec_context);
+
+	return PointerGetDatum(NULL);
+}
+
+/*
+ * rewrite_query_for_preupdate_state
+ *
+ * Rewrite the query so that base tables' RTEs will represent "pre-update"
+ * state of tables. This is necessary to calculate view delta after multiple
+ * tables are modified. xid and cid are the transaction id and command id
+ * before the first table was modified.
+ */
+static Query*
+rewrite_query_for_preupdate_state(Query *query, List *tables,
+								  TransactionId xid, CommandId cid,
+								  ParseState *pstate)
+{
+	ListCell *lc;
+	int num_rte = list_length(query->rtable);
+	int i;
+
+
+	/* register delta ENRs */
+	register_delta_ENRs(pstate, query, tables);
+
+	/* XXX: Is necessary? Is this right timing? */
+	AcquireRewriteLocks(query, true, false);
+
+	i = 1;
+	foreach(lc, query->rtable)
+	{
+		RangeTblEntry *r = (RangeTblEntry*) lfirst(lc);
+
+		ListCell *lc2;
+		foreach(lc2, tables)
+		{
+			MV_TriggerTable *table = (MV_TriggerTable *) lfirst(lc2);
+			/*
+			 * if the modified table is found then replace the original RTE with
+			 * "pre-state" RTE and append its index to the list.
+			 */
+			if (r->relid == table->table_id)
+			{
+				lfirst(lc) = get_prestate_rte(r, table, xid, cid, pstate->p_queryEnv);
+				table->rte_indexes = lappend_int(table->rte_indexes, i);
+				break;
+			}
+		}
+
+		/* finish the loop if we processed all RTE included in the original query */
+		if (i++ >= num_rte)
+			break;
+	}
+
+	return query;
+}
+
+/*
+ * register_delta_ENRs
+ *
+ * For all modified tables, make ENRs for their transition tables
+ * and register them to the queryEnv. ENR's RTEs are also appended
+ * into the list in query tree.
+ */
+static void
+register_delta_ENRs(ParseState *pstate, Query *query, List *tables)
+{
+	QueryEnvironment *queryEnv = pstate->p_queryEnv;
+	ListCell *lc;
+	RangeTblEntry	*rte;
+
+	foreach(lc, tables)
+	{
+		MV_TriggerTable *table = (MV_TriggerTable *) lfirst(lc);
+		ListCell *lc2;
+		int count;
+
+		count = 0;
+		foreach(lc2, table->old_tuplestores)
+		{
+			Tuplestorestate *oldtable = (Tuplestorestate *) lfirst(lc2);
+			EphemeralNamedRelation enr =
+				palloc(sizeof(EphemeralNamedRelationData));
+			ParseNamespaceItem *nsitem;
+
+			enr->md.name = make_delta_enr_name("old", table->table_id, count);
+			enr->md.reliddesc = table->table_id;
+			enr->md.tupdesc = NULL;
+			enr->md.enrtype = ENR_NAMED_TUPLESTORE;
+			enr->md.enrtuples = tuplestore_tuple_count(oldtable);
+			enr->reldata = oldtable;
+			register_ENR(queryEnv, enr);
+
+			nsitem = addRangeTableEntryForENR(pstate, makeRangeVar(NULL, enr->md.name, -1), true);
+			rte = nsitem->p_rte;
+			/* if base table has RLS, set security condition to enr */
+			rte->securityQuals = get_securityQuals(table->table_id, list_length(query->rtable) + 1, query);
+
+			query->rtable = lappend(query->rtable, rte);
+			table->old_rtes = lappend(table->old_rtes, rte);
+
+			count++;
+		}
+
+		count = 0;
+		foreach(lc2, table->new_tuplestores)
+		{
+			Tuplestorestate *newtable = (Tuplestorestate *) lfirst(lc2);
+			EphemeralNamedRelation enr =
+				palloc(sizeof(EphemeralNamedRelationData));
+			ParseNamespaceItem *nsitem;
+
+			enr->md.name = make_delta_enr_name("new", table->table_id, count);
+			enr->md.reliddesc = table->table_id;
+			enr->md.tupdesc = NULL;
+			enr->md.enrtype = ENR_NAMED_TUPLESTORE;
+			enr->md.enrtuples = tuplestore_tuple_count(newtable);
+			enr->reldata = newtable;
+			register_ENR(queryEnv, enr);
+
+			nsitem = addRangeTableEntryForENR(pstate, makeRangeVar(NULL, enr->md.name, -1), true);
+			rte = nsitem->p_rte;
+			/* if base table has RLS, set security condition to enr*/
+			rte->securityQuals = get_securityQuals(table->table_id, list_length(query->rtable) + 1, query);
+
+			query->rtable = lappend(query->rtable, rte);
+			table->new_rtes = lappend(table->new_rtes, rte);
+
+			count++;
+		}
+	}
+}
+
+/*
+ * get_prestate_rte
+ *
+ * Rewrite RTE of the modified table to a subquery which represents
+ * "pre-state" table. The original RTE is saved in table->rte_original.
+ */
+static RangeTblEntry*
+get_prestate_rte(RangeTblEntry *rte, MV_TriggerTable *table,
+				 TransactionId xid, CommandId cid,
+				 QueryEnvironment *queryEnv)
+{
+	StringInfoData str;
+	RawStmt *raw;
+	Query *sub;
+	Relation rel;
+	ParseState *pstate;
+	char *relname;
+	int i;
+
+	pstate = make_parsestate(NULL);
+	pstate->p_queryEnv = queryEnv;
+	pstate->p_expr_kind = EXPR_KIND_SELECT_TARGET;
+
+	/*
+	 * We can use NoLock here since AcquireRewriteLocks should
+	 * have locked the rel already.
+	 */
+	rel = table_open(table->table_id, NoLock);
+	relname = quote_qualified_identifier(
+					get_namespace_name(RelationGetNamespace(rel)),
+									   RelationGetRelationName(rel));
+	table_close(rel, NoLock);
+
+	initStringInfo(&str);
+	appendStringInfo(&str,
+		"SELECT t.* FROM %s t"
+		" WHERE (age(t.xmin) - age(%u::text::xid) > 0) OR"
+		" (t.xmin = %u AND t.cmin::text::int < %u)",
+			relname, xid, xid, cid);
+
+	for (i = 0; i < list_length(table->old_tuplestores); i++)
+	{
+		appendStringInfo(&str, " UNION ALL ");
+		appendStringInfo(&str," SELECT * FROM %s",
+			make_delta_enr_name("old", table->table_id, i));
+	}
+
+	raw = (RawStmt*)linitial(raw_parser(str.data, RAW_PARSE_DEFAULT));
+	sub = transformStmt(pstate, raw->stmt);
+
+	/* If this query has setOperations, RTEs in rtables has a subquery which contains ENR */
+	if (sub->setOperations != NULL)
+	{
+		ListCell *lc;
+
+		/* add securityQuals for tuplestores */
+		foreach (lc, sub->rtable)
+		{
+			RangeTblEntry *rte;
+			RangeTblEntry *sub_rte;
+
+			rte = (RangeTblEntry *)lfirst(lc);
+			Assert(rte->subquery != NULL);
+
+			sub_rte = (RangeTblEntry *)linitial(rte->subquery->rtable);
+			if (sub_rte->rtekind == RTE_NAMEDTUPLESTORE)
+				/* rt_index is always 1, bacause subquery has enr_rte only */
+				sub_rte->securityQuals = get_securityQuals(sub_rte->relid, 1, sub);
+		}
+	}
+
+	/* save the original RTE */
+	table->original_rte = copyObject(rte);
+
+	rte->rtekind = RTE_SUBQUERY;
+	rte->subquery = sub;
+	rte->security_barrier = false;
+	/* Clear fields that should not be set in a subquery RTE */
+	rte->relid = InvalidOid;
+	rte->relkind = 0;
+	rte->rellockmode = 0;
+	rte->tablesample = NULL;
+	rte->inh = false;			/* must not be set for a subquery */
+
+	rte->requiredPerms = 0;		/* no permission check on subquery itself */
+	rte->checkAsUser = InvalidOid;
+	rte->selectedCols = NULL;
+	rte->insertedCols = NULL;
+	rte->updatedCols = NULL;
+	rte->extraUpdatedCols = NULL;
+
+	return rte;
+}
+
+/*
+ * make_delta_enr_name
+ *
+ * Make a name for ENR of a transition table from the base table's oid.
+ * prefix will be "new" or "old" depending on its transition table kind..
+ */
+static char*
+make_delta_enr_name(const char *prefix, Oid relid, int count)
+{
+	char buf[NAMEDATALEN];
+	char *name;
+
+	snprintf(buf, NAMEDATALEN, "__ivm_%s_%u_%u", prefix, relid, count);
+	name = pstrdup(buf);
+
+	return name;
+}
+
+/*
+ * union_ENRs
+ *
+ * Make a single table delta by unionning all transition tables of the modified table
+ * whose RTE is specified by
+ */
+static RangeTblEntry*
+union_ENRs(RangeTblEntry *rte, Oid relid, List *enr_rtes, const char *prefix,
+		   QueryEnvironment *queryEnv)
+{
+	StringInfoData str;
+	ParseState	*pstate;
+	RawStmt *raw;
+	Query *sub;
+	int	i;
+	RangeTblEntry *enr_rte;
+
+	/* Create a ParseState for rewriting the view definition query */
+	pstate = make_parsestate(NULL);
+	pstate->p_queryEnv = queryEnv;
+	pstate->p_expr_kind = EXPR_KIND_SELECT_TARGET;
+
+	initStringInfo(&str);
+
+	for (i = 0; i < list_length(enr_rtes); i++)
+	{
+		if (i > 0)
+			appendStringInfo(&str, " UNION ALL ");
+
+		appendStringInfo(&str,
+			" SELECT * FROM %s",
+			make_delta_enr_name(prefix, relid, i));
+	}
+
+	raw = (RawStmt*)linitial(raw_parser(str.data, RAW_PARSE_DEFAULT));
+	sub = transformStmt(pstate, raw->stmt);
+
+	rte->rtekind = RTE_SUBQUERY;
+	rte->subquery = sub;
+	rte->security_barrier = false;
+	/* Clear fields that should not be set in a subquery RTE */
+	rte->relid = InvalidOid;
+	rte->relkind = 0;
+	rte->rellockmode = 0;
+	rte->tablesample = NULL;
+	rte->inh = false;			/* must not be set for a subquery */
+
+	rte->requiredPerms = 0;		/* no permission check on subquery itself */
+	rte->checkAsUser = InvalidOid;
+	rte->selectedCols = NULL;
+	rte->insertedCols = NULL;
+	rte->updatedCols = NULL;
+	rte->extraUpdatedCols = NULL;
+	/* if base table has RLS, set security condition to enr*/
+	enr_rte = (RangeTblEntry *)linitial(sub->rtable);
+	/* rt_index is always 1, bacause subquery has enr_rte only */
+	enr_rte->securityQuals = get_securityQuals(relid, 1, sub);
+
+	return rte;
+}
+
+/*
+ * rewrite_query_for_distinct
+ *
+ * Rewrite query for counting DISTINCT clause.
+ */
+static Query *
+rewrite_query_for_distinct(Query *query, ParseState *pstate)
+{
+	TargetEntry *tle_count;
+	FuncCall *fn;
+	Node *node;
+
+	/* Add count(*) for counting distinct tuples in views */
+	fn = makeFuncCall(list_make1(makeString("count")), NIL, COERCE_EXPLICIT_CALL, -1);
+	fn->agg_star = true;
+	if (!query->groupClause && !query->hasAggs)
+		query->groupClause = transformDistinctClause(NULL, &query->targetList, query->sortClause, false);
+
+	node = ParseFuncOrColumn(pstate, fn->funcname, NIL, NULL, fn, false, -1);
+
+	tle_count = makeTargetEntry((Expr *) node,
+								list_length(query->targetList) + 1,
+								pstrdup("__ivm_count__"),
+								false);
+	query->targetList = lappend(query->targetList, tle_count);
+	query->hasAggs = true;
+
+	return query;
+}
+
+/*
+ * calc_delta
+ *
+ * Calculate view deltas generated under the modification of a table specified
+ * by the RTE index.
+ */
+static void
+calc_delta(MV_TriggerTable *table, int rte_index, Query *query,
+			DestReceiver *dest_old, DestReceiver *dest_new,
+			TupleDesc *tupdesc_old, TupleDesc *tupdesc_new,
+			QueryEnvironment *queryEnv)
+{
+	ListCell *lc = list_nth_cell(query->rtable, rte_index - 1);
+	RangeTblEntry *rte = (RangeTblEntry *) lfirst(lc);
+
+	/* Generate old delta */
+	if (list_length(table->old_rtes) > 0)
+	{
+		/* Replace the modified table with the old delta table and calculate the old view delta. */
+		lfirst(lc) = union_ENRs(rte, table->table_id, table->old_rtes, "old", queryEnv);
+		refresh_matview_datafill(dest_old, query, queryEnv, tupdesc_old, "");
+	}
+
+	/* Generate new delta */
+	if (list_length(table->new_rtes) > 0)
+	{
+		/* Replace the modified table with the new delta table and calculate the new view delta*/
+		lfirst(lc) = union_ENRs(rte, table->table_id, table->new_rtes, "new", queryEnv);
+		refresh_matview_datafill(dest_new, query, queryEnv, tupdesc_new, "");
+	}
+}
+
+/*
+ * rewrite_query_for_postupdate_state
+ *
+ * Rewrite the query so that the specified base table's RTEs will represent
+ * "post-update" state of tables. This is called after the view delta
+ * calculation due to changes on this table finishes.
+ */
+static Query*
+rewrite_query_for_postupdate_state(Query *query, MV_TriggerTable *table, int rte_index)
+{
+	ListCell *lc = list_nth_cell(query->rtable, rte_index - 1);
+
+	/* Retore the original RTE */
+	lfirst(lc) = table->original_rte;
+
+	return query;
+}
+
+/*
+ * apply_delta
+ *
+ * Apply deltas to the materialized view. In outer join cases, this requires
+ * the view maintenance graph.
+ */
+static void
+apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *new_tuplestores,
+			TupleDesc tupdesc_old, TupleDesc tupdesc_new,
+			Query *query, bool use_count, char *count_colname)
+{
+	StringInfoData querybuf;
+	StringInfoData target_list_buf;
+	Relation	matviewRel;
+	char	   *matviewname;
+	ListCell	*lc;
+	int			i;
+	List	   *keys = NIL;
+
+
+	/*
+	 * get names of the materialized view and delta tables
+	 */
+
+	matviewRel = table_open(matviewOid, NoLock);
+	matviewname = quote_qualified_identifier(get_namespace_name(RelationGetNamespace(matviewRel)),
+											 RelationGetRelationName(matviewRel));
+
+	/*
+	 * Build parts of the maintenance queries
+	 */
+
+	initStringInfo(&querybuf);
+	initStringInfo(&target_list_buf);
+
+	/* build string of target list */
+	for (i = 0; i < matviewRel->rd_att->natts; i++)
+	{
+		Form_pg_attribute attr = TupleDescAttr(matviewRel->rd_att, i);
+		char   *resname = NameStr(attr->attname);
+
+		if (i != 0)
+			appendStringInfo(&target_list_buf, ", ");
+		appendStringInfo(&target_list_buf, "%s", quote_qualified_identifier(NULL, resname));
+	}
+
+	i = 0;
+	foreach (lc, query->targetList)
+	{
+		TargetEntry *tle = (TargetEntry *) lfirst(lc);
+		Form_pg_attribute attr = TupleDescAttr(matviewRel->rd_att, i);
+		char *resname = NameStr(attr->attname);
+
+		i++;
+
+		if (tle->resjunk)
+			continue;
+
+		keys = lappend(keys, resname);
+	}
+
+	/* Start maintaining the materialized view. */
+	OpenMatViewIncrementalMaintenance();
+
+	/* Open SPI context. */
+	if (SPI_connect() != SPI_OK_CONNECT)
+		elog(ERROR, "SPI_connect failed");
+
+	/* For tuple deletion */
+	if (old_tuplestores && tuplestore_tuple_count(old_tuplestores) > 0)
+	{
+		EphemeralNamedRelation enr = palloc(sizeof(EphemeralNamedRelationData));
+		int				rc;
+
+		/* convert tuplestores to ENR, and register for SPI */
+		enr->md.name = pstrdup(OLD_DELTA_ENRNAME);
+		enr->md.reliddesc = InvalidOid;
+		enr->md.tupdesc = tupdesc_old;
+		enr->md.enrtype = ENR_NAMED_TUPLESTORE;
+		enr->md.enrtuples = tuplestore_tuple_count(old_tuplestores);
+		enr->reldata = old_tuplestores;
+
+		rc = SPI_register_relation(enr);
+		if (rc != SPI_OK_REL_REGISTER)
+			elog(ERROR, "SPI_register failed");
+
+		if (use_count)
+			/* apply old delta and get rows to be recalculated */
+			apply_old_delta_with_count(matviewname, OLD_DELTA_ENRNAME,
+									   keys, count_colname);
+		else
+			apply_old_delta(matviewname, OLD_DELTA_ENRNAME, keys);
+
+	}
+	/* For tuple insertion */
+	if (new_tuplestores && tuplestore_tuple_count(new_tuplestores) > 0)
+	{
+		EphemeralNamedRelation enr = palloc(sizeof(EphemeralNamedRelationData));
+		int rc;
+
+		/* convert tuplestores to ENR, and register for SPI */
+		enr->md.name = pstrdup(NEW_DELTA_ENRNAME);
+		enr->md.reliddesc = InvalidOid;
+		enr->md.tupdesc = tupdesc_new;;
+		enr->md.enrtype = ENR_NAMED_TUPLESTORE;
+		enr->md.enrtuples = tuplestore_tuple_count(new_tuplestores);
+		enr->reldata = new_tuplestores;
+
+		rc = SPI_register_relation(enr);
+		if (rc != SPI_OK_REL_REGISTER)
+			elog(ERROR, "SPI_register failed");
+
+		/* apply new delta */
+		if (use_count)
+			apply_new_delta_with_count(matviewname, NEW_DELTA_ENRNAME,
+								keys, &target_list_buf, count_colname);
+		else
+			apply_new_delta(matviewname, NEW_DELTA_ENRNAME, &target_list_buf);
+	}
+
+	/* We're done maintaining the materialized view. */
+	CloseMatViewIncrementalMaintenance();
+
+	table_close(matviewRel, NoLock);
+
+	/* Close SPI context. */
+	if (SPI_finish() != SPI_OK_FINISH)
+		elog(ERROR, "SPI_finish failed");
+}
+
+/*
+ * apply_old_delta_with_count
+ *
+ * Execute a query for applying a delta table given by deltname_old
+ * which contains tuples to be deleted from to a materialized view given by
+ * matviewname.  This is used when counting is required, that is, the view
+ * has aggregate or distinct.
+ */
+static void
+apply_old_delta_with_count(const char *matviewname, const char *deltaname_old,
+				List *keys, const char *count_colname)
+{
+	StringInfoData	querybuf;
+	char   *match_cond;
+
+	/* build WHERE condition for searching tuples to be deleted */
+	match_cond = get_matching_condition_string(keys);
+
+	/* Search for matching tuples from the view and update or delete if found. */
+	initStringInfo(&querybuf);
+	appendStringInfo(&querybuf,
+					"WITH t AS ("			/* collecting tid of target tuples in the view */
+						"SELECT diff.%s, "			/* count column */
+								"(diff.%s OPERATOR(pg_catalog.=) mv.%s) AS for_dlt, "
+								"mv.ctid "
+						"FROM %s AS mv, %s AS diff "
+						"WHERE %s"					/* tuple matching condition */
+					"), updt AS ("			/* update a tuple if this is not to be deleted */
+						"UPDATE %s AS mv SET %s = mv.%s OPERATOR(pg_catalog.-) t.%s "
+						"FROM t WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND NOT for_dlt "
+					"), dlt AS ("			/* delete a tuple if this is to be deleted */
+						"DELETE FROM %s AS mv USING t "
+						"WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt"
+					")",
+					count_colname,
+					count_colname, count_colname,
+					matviewname, deltaname_old,
+					match_cond,
+					matviewname, count_colname, count_colname, count_colname,
+					matviewname);
+
+	if (SPI_exec(querybuf.data, 0) != SPI_OK_DELETE)
+		elog(ERROR, "SPI_exec failed: %s", querybuf.data);
+}
+
+/*
+ * apply_old_delta
+ *
+ * Execute a query for applying a delta table given by deltname_old
+ * which contains tuples to be deleted from to a materialized view given by
+ * matviewname.  This is used when counting is not required.
+ */
+static void
+apply_old_delta(const char *matviewname, const char *deltaname_old,
+				List *keys)
+{
+	StringInfoData	querybuf;
+	StringInfoData	keysbuf;
+	char   *match_cond;
+	ListCell *lc;
+
+	/* build WHERE condition for searching tuples to be deleted */
+	match_cond = get_matching_condition_string(keys);
+
+	/* build string of keys list */
+	initStringInfo(&keysbuf);
+	foreach (lc, keys)
+	{
+		Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc);
+		char   *resname = NameStr(attr->attname);
+		appendStringInfo(&keysbuf, "%s", quote_qualified_identifier("mv", resname));
+		if (lnext(keys, lc))
+			appendStringInfo(&keysbuf, ", ");
+	}
+
+	/* Search for matching tuples from the view and update or delete if found. */
+	initStringInfo(&querybuf);
+	appendStringInfo(&querybuf,
+	"DELETE FROM %s WHERE ctid IN ("
+		"SELECT tid FROM (SELECT row_number() over (partition by %s) AS \"__ivm_row_number__\","
+								  "mv.ctid AS tid,"
+								  "diff.\"__ivm_count__\""
+						 "FROM %s AS mv, %s AS diff "
+						 "WHERE %s) v "
+					"WHERE v.\"__ivm_row_number__\" OPERATOR(pg_catalog.<=) v.\"__ivm_count__\")",
+					matviewname,
+					keysbuf.data,
+					matviewname, deltaname_old,
+					match_cond);
+
+	if (SPI_exec(querybuf.data, 0) != SPI_OK_DELETE)
+		elog(ERROR, "SPI_exec failed: %s", querybuf.data);
+}
+
+/*
+ * apply_new_delta_with_count
+ *
+ * Execute a query for applying a delta table given by deltname_new
+ * which contains tuples to be inserted into a materialized view given by
+ * matviewname.  This is used when counting is required, that is, the view
+ * has aggregate or distinct. Also, when a table in EXISTS sub queries
+ * is modified.
+ */
+static void
+apply_new_delta_with_count(const char *matviewname, const char* deltaname_new,
+				List *keys, StringInfo target_list, const char* count_colname)
+{
+	StringInfoData	querybuf;
+	StringInfoData	returning_keys;
+	ListCell	*lc;
+	char	*match_cond = "";
+
+	/* build WHERE condition for searching tuples to be updated */
+	match_cond = get_matching_condition_string(keys);
+
+	/* build string of keys list */
+	initStringInfo(&returning_keys);
+	if (keys)
+	{
+		foreach (lc, keys)
+		{
+			Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc);
+			char   *resname = NameStr(attr->attname);
+			appendStringInfo(&returning_keys, "%s", quote_qualified_identifier("mv", resname));
+			if (lnext(keys, lc))
+				appendStringInfo(&returning_keys, ", ");
+		}
+	}
+	else
+		appendStringInfo(&returning_keys, "NULL");
+
+	/* Search for matching tuples from the view and update if found or insert if not. */
+	initStringInfo(&querybuf);
+	appendStringInfo(&querybuf,
+					"WITH updt AS ("		/* update a tuple if this exists in the view */
+						"UPDATE %s AS mv SET %s = mv.%s OPERATOR(pg_catalog.+) diff.%s "
+						"FROM %s AS diff "
+						"WHERE %s "					/* tuple matching condition */
+						"RETURNING %s"				/* returning keys of updated tuples */
+					") INSERT INTO %s (%s)"	/* insert a new tuple if this doesn't existw */
+						"SELECT %s FROM %s AS diff "
+						"WHERE NOT EXISTS (SELECT 1 FROM updt AS mv WHERE %s);",
+					matviewname, count_colname, count_colname, count_colname,
+					deltaname_new,
+					match_cond,
+					returning_keys.data,
+					matviewname, target_list->data,
+					target_list->data, deltaname_new,
+					match_cond);
+
+	if (SPI_exec(querybuf.data, 0) != SPI_OK_INSERT)
+		elog(ERROR, "SPI_exec failed: %s", querybuf.data);
+}
+
+/*
+ * apply_new_delta
+ *
+ * Execute a query for applying a delta table given by deltname_new
+ * which contains tuples to be inserted into a materialized view given by
+ * matviewname.  This is used when counting is not required.
+ */
+static void
+apply_new_delta(const char *matviewname, const char *deltaname_new,
+				StringInfo target_list)
+{
+	StringInfoData	querybuf;
+
+	/* Search for matching tuples from the view and update or delete if found. */
+	initStringInfo(&querybuf);
+	appendStringInfo(&querybuf,
+					"INSERT INTO %s (%s) SELECT %s FROM ("
+						"SELECT diff.*, generate_series(1, diff.\"__ivm_count__\") "
+						"FROM %s AS diff) AS v",
+					matviewname, target_list->data, target_list->data,
+					deltaname_new);
+
+	if (SPI_exec(querybuf.data, 0) != SPI_OK_INSERT)
+		elog(ERROR, "SPI_exec failed: %s", querybuf.data);
+}
+
+/*
+ * get_matching_condition_string
+ *
+ * Build a predicate string for looking for a tuple with given keys.
+ */
+static char *
+get_matching_condition_string(List *keys)
+{
+	StringInfoData match_cond;
+	ListCell	*lc;
+
+	/* If there is no key columns, the condition is always true. */
+	if (keys == NIL)
+		return "true";
+
+	initStringInfo(&match_cond);
+	foreach (lc, keys)
+	{
+		Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc);
+		char   *resname = NameStr(attr->attname);
+		char   *mv_resname = quote_qualified_identifier("mv", resname);
+		char   *diff_resname = quote_qualified_identifier("diff", resname);
+		Oid		typid = attr->atttypid;
+
+		/* Considering NULL values, we can not use simple = operator. */
+		appendStringInfo(&match_cond, "(");
+		generate_equal(&match_cond, typid, mv_resname, diff_resname);
+		appendStringInfo(&match_cond, " OR (%s IS NULL AND %s IS NULL))",
+						 mv_resname, diff_resname);
+
+		if (lnext(keys, lc))
+			appendStringInfo(&match_cond, " AND ");
+	}
+
+	return match_cond.data;
+}
+
+/*
+ * generate_equals
+ *
+ * Generate an equality clause using given operands' default equality
+ * operator.
+ */
+static void
+generate_equal(StringInfo querybuf, Oid opttype,
+			   const char *leftop, const char *rightop)
+{
+	TypeCacheEntry *typentry;
+
+	typentry = lookup_type_cache(opttype, TYPECACHE_EQ_OPR);
+	if (!OidIsValid(typentry->eq_opr))
+		ereport(ERROR,
+				(errcode(ERRCODE_UNDEFINED_FUNCTION),
+				 errmsg("could not identify an equality operator for type %s",
+						format_type_be(opttype))));
+
+	generate_operator_clause(querybuf,
+							 leftop, opttype,
+							 typentry->eq_opr,
+							 rightop, opttype);
+}
+
+/*
+ * mv_InitHashTables
+ */
+static void
+mv_InitHashTables(void)
+{
+	HASHCTL		ctl;
+
+	memset(&ctl, 0, sizeof(ctl));
+	ctl.keysize = sizeof(Oid);
+	ctl.entrysize = sizeof(MV_TriggerHashEntry);
+	mv_trigger_info = hash_create("MV trigger info",
+								 MV_INIT_QUERYHASHSIZE,
+								 &ctl, HASH_ELEM | HASH_BLOBS);
+}
+
+/*
+ * AtAbort_IVM
+ *
+ * Clean up hash entries for all materialized views. This is called at
+ * transaction abort.
+ */
+void
+AtAbort_IVM()
+{
+	HASH_SEQ_STATUS seq;
+	MV_TriggerHashEntry *entry;
+
+	if (mv_trigger_info)
+	{
+		hash_seq_init(&seq, mv_trigger_info);
+		while ((entry = hash_seq_search(&seq)) != NULL)
+			clean_up_IVM_hash_entry(entry);
+	}
+}
+
+/*
+ * clean_up_IVM_hash_entry
+ *
+ * Clean up tuple stores and hash entries for a materialized view after its
+ * maintenance finished.
+ */
+static void
+clean_up_IVM_hash_entry(MV_TriggerHashEntry *entry)
+{
+	bool found;
+	ListCell *lc;
+
+	foreach(lc, entry->tables)
+	{
+		MV_TriggerTable *table = (MV_TriggerTable *) lfirst(lc);
+
+		list_free(table->old_tuplestores);
+		list_free(table->new_tuplestores);
+	}
+	list_free(entry->tables);
+
+	hash_search(mv_trigger_info, (void *) &entry->matview_id, HASH_REMOVE, &found);
+}
+
+/*
+ * isIvmName
+ *
+ * Check if this is a IVM hidden column from the name.
+ */
+bool
+isIvmName(const char *s)
+{
+	if (s)
+		return (strncmp(s, "__ivm_", 6) == 0);
+	return false;
+}
+
+/*
+ * get_securityQuals
+ *
+ * Get row security policy on a relation.
+ * This is used by IVM for copying RLS from base table to enr.
+ */
+static List *
+get_securityQuals(Oid relId, int rt_index, Query *query)
+{
+	ParseState *pstate;
+	Relation rel;
+	ParseNamespaceItem *nsitem;
+	RangeTblEntry *rte;
+	List *securityQuals;
+	List *withCheckOptions;
+	bool  hasRowSecurity;
+	bool  hasSubLinks;
+
+	securityQuals = NIL;
+	pstate = make_parsestate(NULL);
+
+	rel = table_open(relId, NoLock);
+	nsitem = addRangeTableEntryForRelation(pstate, rel, AccessShareLock, NULL, false, false);
+	rte = nsitem->p_rte;
+
+	get_row_security_policies(query, rte, rt_index,
+							  &securityQuals, &withCheckOptions,
+							  &hasRowSecurity, &hasSubLinks);
+
+	/*
+	 * Make sure the query is marked correctly if row level security
+	 * applies, or if the new quals had sublinks.
+	 */
+	if (hasRowSecurity)
+		query->hasRowSecurity = true;
+	if (hasSubLinks)
+		query->hasSubLinks = true;
+
+	table_close(rel, NoLock);
+
+	return securityQuals;
+}
diff --git a/src/backend/commands/tablecmds.c b/src/backend/commands/tablecmds.c
index a16e749506..9aad4792e5 100644
--- a/src/backend/commands/tablecmds.c
+++ b/src/backend/commands/tablecmds.c
@@ -50,6 +50,7 @@
 #include "commands/cluster.h"
 #include "commands/comment.h"
 #include "commands/defrem.h"
+#include "commands/matview.h"
 #include "commands/event_trigger.h"
 #include "commands/policy.h"
 #include "commands/sequence.h"
@@ -3437,6 +3438,14 @@ renameatt_internal(Oid myrelid,
 	targetrelation = relation_open(myrelid, AccessExclusiveLock);
 	renameatt_check(myrelid, RelationGetForm(targetrelation), recursing);
 
+	/*
+	 * Don't rename IVM columns.
+	 */
+	if (RelationIsIVM(targetrelation) && isIvmName(oldattname))
+		ereport(ERROR,
+				(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+				 errmsg("IVM column can not be renamed")));
+
 	/*
 	 * if the 'recurse' flag is set then we are supposed to rename this
 	 * attribute in all classes that inherit from 'relname' (as well as in
diff --git a/src/backend/nodes/copyfuncs.c b/src/backend/nodes/copyfuncs.c
index 29020c908e..afda022a60 100644
--- a/src/backend/nodes/copyfuncs.c
+++ b/src/backend/nodes/copyfuncs.c
@@ -2467,6 +2467,7 @@ _copyRangeTblEntry(const RangeTblEntry *from)
 	COPY_SCALAR_FIELD(relkind);
 	COPY_SCALAR_FIELD(rellockmode);
 	COPY_NODE_FIELD(tablesample);
+	COPY_SCALAR_FIELD(relisivm);
 	COPY_NODE_FIELD(subquery);
 	COPY_SCALAR_FIELD(security_barrier);
 	COPY_SCALAR_FIELD(jointype);
diff --git a/src/backend/nodes/equalfuncs.c b/src/backend/nodes/equalfuncs.c
index 8a1762000c..32345b7f41 100644
--- a/src/backend/nodes/equalfuncs.c
+++ b/src/backend/nodes/equalfuncs.c
@@ -2730,6 +2730,7 @@ _equalRangeTblEntry(const RangeTblEntry *a, const RangeTblEntry *b)
 	COMPARE_SCALAR_FIELD(relkind);
 	COMPARE_SCALAR_FIELD(rellockmode);
 	COMPARE_NODE_FIELD(tablesample);
+	COMPARE_SCALAR_FIELD(relisivm);
 	COMPARE_NODE_FIELD(subquery);
 	COMPARE_SCALAR_FIELD(security_barrier);
 	COMPARE_SCALAR_FIELD(jointype);
diff --git a/src/backend/nodes/outfuncs.c b/src/backend/nodes/outfuncs.c
index 48202d2232..fd87a6153a 100644
--- a/src/backend/nodes/outfuncs.c
+++ b/src/backend/nodes/outfuncs.c
@@ -3251,6 +3251,7 @@ _outRangeTblEntry(StringInfo str, const RangeTblEntry *node)
 			WRITE_CHAR_FIELD(relkind);
 			WRITE_INT_FIELD(rellockmode);
 			WRITE_NODE_FIELD(tablesample);
+			WRITE_BOOL_FIELD(relisivm);
 			break;
 		case RTE_SUBQUERY:
 			WRITE_NODE_FIELD(subquery);
diff --git a/src/backend/nodes/readfuncs.c b/src/backend/nodes/readfuncs.c
index 77d082d8b4..cd85f6910a 100644
--- a/src/backend/nodes/readfuncs.c
+++ b/src/backend/nodes/readfuncs.c
@@ -1442,6 +1442,7 @@ _readRangeTblEntry(void)
 			READ_CHAR_FIELD(relkind);
 			READ_INT_FIELD(rellockmode);
 			READ_NODE_FIELD(tablesample);
+			READ_BOOL_FIELD(relisivm);
 			break;
 		case RTE_SUBQUERY:
 			READ_NODE_FIELD(subquery);
diff --git a/src/backend/parser/parse_relation.c b/src/backend/parser/parse_relation.c
index 7465919044..5246c78ff8 100644
--- a/src/backend/parser/parse_relation.c
+++ b/src/backend/parser/parse_relation.c
@@ -36,6 +36,7 @@
 #include "utils/rel.h"
 #include "utils/syscache.h"
 #include "utils/varlena.h"
+#include "commands/matview.h"
 
 
 /*
@@ -79,7 +80,7 @@ static void expandTupleDesc(TupleDesc tupdesc, Alias *eref,
 							int count, int offset,
 							int rtindex, int sublevels_up,
 							int location, bool include_dropped,
-							List **colnames, List **colvars);
+							List **colnames, List **colvars, bool is_ivm);
 static int	specialAttNum(const char *attname);
 static bool isQueryUsingTempRelation_walker(Node *node, void *context);
 
@@ -1433,6 +1434,7 @@ addRangeTableEntry(ParseState *pstate,
 	rte->relid = RelationGetRelid(rel);
 	rte->relkind = rel->rd_rel->relkind;
 	rte->rellockmode = lockmode;
+	rte->relisivm = rel->rd_rel->relisivm;
 
 	/*
 	 * Build the list of effective column names using user-supplied aliases
@@ -1521,6 +1523,7 @@ addRangeTableEntryForRelation(ParseState *pstate,
 	rte->relid = RelationGetRelid(rel);
 	rte->relkind = rel->rd_rel->relkind;
 	rte->rellockmode = lockmode;
+	rte->relisivm = rel->rd_rel->relisivm;
 
 	/*
 	 * Build the list of effective column names using user-supplied aliases
@@ -2676,7 +2679,7 @@ expandRTE(RangeTblEntry *rte, int rtindex, int sublevels_up,
 						expandTupleDesc(tupdesc, rte->eref,
 										rtfunc->funccolcount, atts_done,
 										rtindex, sublevels_up, location,
-										include_dropped, colnames, colvars);
+										include_dropped, colnames, colvars, false);
 					}
 					else if (functypclass == TYPEFUNC_SCALAR)
 					{
@@ -2944,7 +2947,7 @@ expandRelation(Oid relid, Alias *eref, int rtindex, int sublevels_up,
 	expandTupleDesc(rel->rd_att, eref, rel->rd_att->natts, 0,
 					rtindex, sublevels_up,
 					location, include_dropped,
-					colnames, colvars);
+					colnames, colvars, RelationIsIVM(rel));
 	relation_close(rel, AccessShareLock);
 }
 
@@ -2961,7 +2964,7 @@ static void
 expandTupleDesc(TupleDesc tupdesc, Alias *eref, int count, int offset,
 				int rtindex, int sublevels_up,
 				int location, bool include_dropped,
-				List **colnames, List **colvars)
+				List **colnames, List **colvars, bool is_ivm)
 {
 	ListCell   *aliascell;
 	int			varattno;
@@ -2974,6 +2977,9 @@ expandTupleDesc(TupleDesc tupdesc, Alias *eref, int count, int offset,
 	{
 		Form_pg_attribute attr = TupleDescAttr(tupdesc, varattno);
 
+		if (is_ivm && isIvmName(NameStr(attr->attname)) && !MatViewIncrementalMaintenanceIsEnabled())
+			continue;
+
 		if (attr->attisdropped)
 		{
 			if (include_dropped)
@@ -3127,6 +3133,10 @@ expandNSItemAttrs(ParseState *pstate, ParseNamespaceItem *nsitem,
 		Var		   *varnode = (Var *) lfirst(var);
 		TargetEntry *te;
 
+		/* if transform * into columnlist with IMMV, remove IVM columns */
+		if (rte->relisivm && isIvmName(label) && !MatViewIncrementalMaintenanceIsEnabled())
+			continue;
+
 		te = makeTargetEntry((Expr *) varnode,
 							 (AttrNumber) pstate->p_next_resno++,
 							 label,
diff --git a/src/backend/rewrite/rewriteDefine.c b/src/backend/rewrite/rewriteDefine.c
index 6589345ac4..02f33d404b 100644
--- a/src/backend/rewrite/rewriteDefine.c
+++ b/src/backend/rewrite/rewriteDefine.c
@@ -776,7 +776,8 @@ checkRuleResultList(List *targetList, TupleDesc resultDesc, bool isSelect,
 														attr->atttypmod))));
 	}
 
-	if (i != resultDesc->natts)
+	/* No check for materialized views since this could have special columns for IVM */
+	if ((!isSelect || requireColumnNameMatch) && i != resultDesc->natts)
 		ereport(ERROR,
 				(errcode(ERRCODE_INVALID_OBJECT_DEFINITION),
 				 isSelect ?
diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat
index 8cd0252082..c2841ab604 100644
--- a/src/include/catalog/pg_proc.dat
+++ b/src/include/catalog/pg_proc.dat
@@ -11625,4 +11625,12 @@
   prorettype => 'bytea', proargtypes => 'pg_brin_minmax_multi_summary',
   prosrc => 'brin_minmax_multi_summary_send' },
 
+# IVM
+{ oid => '786', descr => 'ivm trigger (before)',
+  proname => 'IVM_immediate_before', provolatile => 'v', prorettype => 'trigger',
+  proargtypes => '', prosrc => 'IVM_immediate_before' },
+{ oid => '787', descr => 'ivm trigger (after)',
+  proname => 'IVM_immediate_maintenance', provolatile => 'v', prorettype => 'trigger',
+  proargtypes => '', prosrc => 'IVM_immediate_maintenance' },
+
 ]
diff --git a/src/include/commands/createas.h b/src/include/commands/createas.h
index ad5054d116..a57ce463e1 100644
--- a/src/include/commands/createas.h
+++ b/src/include/commands/createas.h
@@ -16,6 +16,7 @@
 
 #include "catalog/objectaddress.h"
 #include "nodes/params.h"
+#include "nodes/pathnodes.h"
 #include "parser/parse_node.h"
 #include "tcop/dest.h"
 #include "utils/queryenvironment.h"
@@ -25,6 +26,10 @@ extern ObjectAddress ExecCreateTableAs(ParseState *pstate, CreateTableAsStmt *st
 									   ParamListInfo params, QueryEnvironment *queryEnv,
 									   QueryCompletion *qc);
 
+extern void CreateIvmTriggersOnBaseTables(Query *qry, Oid matviewOid, bool is_create);
+
+extern Query *rewriteQueryForIMMV(Query *query, List *colNames);
+
 extern int	GetIntoRelEFlags(IntoClause *intoClause);
 
 extern DestReceiver *CreateIntoRelDestReceiver(IntoClause *intoClause);
diff --git a/src/include/commands/matview.h b/src/include/commands/matview.h
index 214b1c1df6..13a5722f17 100644
--- a/src/include/commands/matview.h
+++ b/src/include/commands/matview.h
@@ -15,6 +15,7 @@
 #define MATVIEW_H
 
 #include "catalog/objectaddress.h"
+#include "fmgr.h"
 #include "nodes/params.h"
 #include "nodes/parsenodes.h"
 #include "tcop/dest.h"
@@ -23,6 +24,8 @@
 
 extern void SetMatViewPopulatedState(Relation relation, bool newstate);
 
+extern void SetMatViewIVMState(Relation relation, bool newstate);
+
 extern ObjectAddress ExecRefreshMatView(RefreshMatViewStmt *stmt, const char *queryString,
 										ParamListInfo params, QueryCompletion *qc);
 
@@ -30,4 +33,9 @@ extern DestReceiver *CreateTransientRelDestReceiver(Oid oid);
 
 extern bool MatViewIncrementalMaintenanceIsEnabled(void);
 
+extern Datum IVM_immediate_before(PG_FUNCTION_ARGS);
+extern Datum IVM_immediate_maintenance(PG_FUNCTION_ARGS);
+extern void AtAbort_IVM(void);
+extern bool isIvmName(const char *s);
+
 #endif							/* MATVIEW_H */
diff --git a/src/include/nodes/parsenodes.h b/src/include/nodes/parsenodes.h
index 947660a4b0..d10ce8780b 100644
--- a/src/include/nodes/parsenodes.h
+++ b/src/include/nodes/parsenodes.h
@@ -1023,6 +1023,7 @@ typedef struct RangeTblEntry
 	char		relkind;		/* relation kind (see pg_class.relkind) */
 	int			rellockmode;	/* lock level that query requires on the rel */
 	struct TableSampleClause *tablesample;	/* sampling info, or NULL */
+	bool		relisivm;
 
 	/*
 	 * Fields valid for a subquery RTE (else NULL):
@@ -2180,6 +2181,7 @@ typedef struct CreateStmt
 	char	   *tablespacename; /* table space to use, or NULL */
 	char	   *accessMethod;	/* table access method */
 	bool		if_not_exists;	/* just do nothing if it already exists? */
+	bool		ivm;			/* incremental view maintenance is used by materialized view */
 } CreateStmt;
 
 /* ----------
-- 
2.17.1


--Multipart=_Mon__2_Aug_2021_15_28_34_+0900_wlHCjIpnD/FrGAKu
Content-Type: text/x-diff;
 name="v23-0008-Add-aggregates-support-in-IVM.patch"
Content-Disposition: attachment;
 filename="v23-0008-Add-aggregates-support-in-IVM.patch"
Content-Transfer-Encoding: quoted-printable



^ permalink  raw  reply  [nested|flat] 101+ messages in thread

* [PATCH v27 6/9] Add Incremental View Maintenance support
@ 2022-04-21 02:58  Yugo Nagata <[email protected]>
  0 siblings, 0 replies; 101+ messages in thread

From: Yugo Nagata @ 2022-04-21 02:58 UTC (permalink / raw)

In this implementation, AFTER triggers are used to collect
tuplestores containing transition table contents. When multiple tables
are changed, multiple AFTER triggers are invoked, then the final AFTER
trigger performs actual update of the matview. In addition, BEFORE
triggers are also used to handle global information for view
maintenance. To calculate view deltas, we need both pre-state and
post-state of base tables. Post-update states are available in AFTER
trigger, and pre-update states can be calculated by filtering inserted
tuples using cmin/xmin system columns, and append deleted tuples which
are contained in an old transition table.

This patch also allows self-join, simultaneous updates of more than
one base table, and multiple updates of the same base table.

Incrementally Maintainable Materialized Views (IMMV) can contain
duplicated tuples. Also, DISTINCT clause is supported. When IMMV is
created with DISTINCT, multiplicity of tuples is counted and stored
in  "__ivm_count__" column, which is a hidden column of IMMV.
The value in __ivm_count__ is updated when IMMV is maintained
incrementally. A tuple in IMMV can be removed if and only if the
count becomes zero.
---
 src/backend/access/transam/xact.c   |    5 +
 src/backend/commands/createas.c     |  751 +++++++++++++
 src/backend/commands/indexcmds.c    |   40 +
 src/backend/commands/matview.c      | 1577 ++++++++++++++++++++++++++-
 src/backend/commands/tablecmds.c    |    9 +
 src/backend/nodes/copyfuncs.c       |    1 +
 src/backend/nodes/equalfuncs.c      |    1 +
 src/backend/nodes/outfuncs.c        |    1 +
 src/backend/nodes/readfuncs.c       |    1 +
 src/backend/parser/parse_relation.c |   18 +-
 src/backend/rewrite/rewriteDefine.c |    3 +-
 src/include/catalog/pg_proc.dat     |    8 +
 src/include/commands/createas.h     |    6 +
 src/include/commands/matview.h      |    8 +
 src/include/nodes/parsenodes.h      |    2 +
 15 files changed, 2391 insertions(+), 40 deletions(-)

diff --git a/src/backend/access/transam/xact.c b/src/backend/access/transam/xact.c
index 53f3e7fd1a..0377f5a88b 100644
--- a/src/backend/access/transam/xact.c
+++ b/src/backend/access/transam/xact.c
@@ -36,6 +36,7 @@
 #include "catalog/pg_enum.h"
 #include "catalog/storage.h"
 #include "commands/async.h"
+#include "commands/matview.h"
 #include "commands/tablecmds.h"
 #include "commands/trigger.h"
 #include "common/pg_prng.h"
@@ -2792,6 +2793,7 @@ AbortTransaction(void)
 	AtAbort_Notify();
 	AtEOXact_RelationMap(false, is_parallel_worker);
 	AtAbort_Twophase();
+	AtAbort_IVM();
 
 	/*
 	 * Advertise the fact that we aborted in pg_xact (assuming that we got as
@@ -5032,6 +5034,9 @@ AbortSubTransaction(void)
 	AbortBufferIO();
 	UnlockBuffers();
 
+	/* Clean up hash entries for incremental view maintenance */
+	AtAbort_IVM();
+
 	/* Reset WAL record construction state */
 	XLogResetInsertion();
 
diff --git a/src/backend/commands/createas.c b/src/backend/commands/createas.c
index 9abbb6b555..1224a3b075 100644
--- a/src/backend/commands/createas.c
+++ b/src/backend/commands/createas.c
@@ -32,24 +32,41 @@
 #include "access/xact.h"
 #include "access/xlog.h"
 #include "catalog/namespace.h"
+#include "catalog/index.h"
+#include "catalog/pg_constraint.h"
+#include "catalog/pg_inherits.h"
+#include "catalog/pg_trigger.h"
+#include "catalog/pg_type.h"
 #include "catalog/toasting.h"
 #include "commands/createas.h"
+#include "commands/defrem.h"
 #include "commands/matview.h"
 #include "commands/prepare.h"
 #include "commands/tablecmds.h"
+#include "commands/tablespace.h"
+#include "commands/trigger.h"
 #include "commands/view.h"
 #include "miscadmin.h"
+#include "optimizer/clauses.h"
+#include "optimizer/optimizer.h"
 #include "nodes/makefuncs.h"
 #include "nodes/nodeFuncs.h"
+#include "parser/parser.h"
+#include "parser/parsetree.h"
 #include "parser/parse_clause.h"
+#include "parser/parse_func.h"
+#include "parser/parse_type.h"
 #include "rewrite/rewriteHandler.h"
+#include "rewrite/rewriteManip.h"
 #include "storage/smgr.h"
 #include "tcop/tcopprot.h"
 #include "utils/builtins.h"
+#include "utils/fmgroids.h"
 #include "utils/lsyscache.h"
 #include "utils/rel.h"
 #include "utils/rls.h"
 #include "utils/snapmgr.h"
+#include "utils/syscache.h"
 
 typedef struct
 {
@@ -73,6 +90,13 @@ static bool intorel_receive(TupleTableSlot *slot, DestReceiver *self);
 static void intorel_shutdown(DestReceiver *self);
 static void intorel_destroy(DestReceiver *self);
 
+static void CreateIvmTriggersOnBaseTablesRecurse(Query *qry, Node *node, Oid matviewOid,
+									 Relids *relids, bool ex_lock);
+static void CreateIvmTrigger(Oid relOid, Oid viewOid, int16 type, int16 timing, bool ex_lock);
+static void check_ivm_restriction(Node *node);
+static bool check_ivm_restriction_walker(Node *node, void *context);
+static Bitmapset *get_primary_key_attnos_from_query(Query *qry, List **constraintList, bool is_create);
+static Bitmapset *get_primary_key_attnos_from_query(Query *query, List **constraintList, bool is_create);
 
 /*
  * create_ctas_internal
@@ -108,6 +132,8 @@ create_ctas_internal(List *attrList, IntoClause *into)
 	create->oncommit = into->onCommit;
 	create->tablespacename = into->tableSpaceName;
 	create->if_not_exists = false;
+	/* Using Materialized view only */
+	create->ivm = into->ivm;
 	create->accessMethod = into->accessMethod;
 
 	/*
@@ -282,6 +308,21 @@ ExecCreateTableAs(ParseState *pstate, CreateTableAsStmt *stmt,
 		save_nestlevel = NewGUCNestLevel();
 	}
 
+	if (is_matview && into->ivm)
+	{
+		/* check if the query is supported in IMMV definition */
+		if (contain_mutable_functions((Node *) query))
+			ereport(ERROR,
+					(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+					 errmsg("mutable function is not supported on incrementally maintainable materialized view"),
+					 errhint("functions must be marked IMMUTABLE")));
+
+		check_ivm_restriction((Node *) query);
+
+		/* For IMMV, we need to rewrite matview query */
+		query = rewriteQueryForIMMV(query, into->colNames);
+	}
+
 	if (into->skipData)
 	{
 		/*
@@ -358,11 +399,74 @@ ExecCreateTableAs(ParseState *pstate, CreateTableAsStmt *stmt,
 
 		/* Restore userid and security context */
 		SetUserIdAndSecContext(save_userid, save_sec_context);
+
+		if (into->ivm)
+		{
+			Oid matviewOid = address.objectId;
+			Relation matviewRel = table_open(matviewOid, NoLock);
+
+			/*
+			 * Mark relisivm field, if it's a matview and into->ivm is true.
+			 */
+			SetMatViewIVMState(matviewRel, true);
+
+			if (!into->skipData)
+			{
+				/* Create an index on incremental maintainable materialized view, if possible */
+				CreateIndexOnIMMV((Query *) into->viewQuery, matviewRel, true);
+
+				/* Create triggers on incremental maintainable materialized view */
+				CreateIvmTriggersOnBaseTables((Query *) into->viewQuery, matviewOid, true);
+			}
+			table_close(matviewRel, NoLock);
+		}
 	}
 
 	return address;
 }
 
+/*
+ * rewriteQueryForIMMV -- rewrite view definition query for IMMV
+ *
+ * count(*) is added for counting distinct tuples in views.
+ */
+Query *
+rewriteQueryForIMMV(Query *query, List *colNames)
+{
+	Query *rewritten;
+
+	TargetEntry *tle;
+	Node *node;
+	ParseState *pstate = make_parsestate(NULL);
+	FuncCall *fn;
+
+	rewritten = copyObject(query);
+	pstate->p_expr_kind = EXPR_KIND_SELECT_TARGET;
+
+	/*
+	 * Convert DISTINCT to GROUP BY and add count(*) for counting distinct
+	 * tuples in views.
+	 */
+	if (rewritten->distinctClause)
+	{
+		rewritten->groupClause = transformDistinctClause(NULL, &rewritten->targetList, rewritten->sortClause, false);
+
+		fn = makeFuncCall(list_make1(makeString("count")), NIL, COERCE_EXPLICIT_CALL, -1);
+		fn->agg_star = true;
+
+		node = ParseFuncOrColumn(pstate, fn->funcname, NIL, NULL, fn, false, -1);
+
+		tle = makeTargetEntry((Expr *) node,
+								list_length(rewritten->targetList) + 1,
+								pstrdup("__ivm_count__"),
+								false);
+		rewritten->targetList = lappend(rewritten->targetList, tle);
+		rewritten->hasAggs = true;
+	}
+
+	return rewritten;
+}
+
 /*
  * GetIntoRelEFlags --- compute executor flags needed for CREATE TABLE AS
  *
@@ -623,3 +727,650 @@ intorel_destroy(DestReceiver *self)
 {
 	pfree(self);
 }
+
+/*
+ * CreateIvmTriggersOnBaseTables -- create IVM triggers on all base tables
+ */
+void
+CreateIvmTriggersOnBaseTables(Query *qry, Oid matviewOid, bool is_create)
+{
+	Relids	relids = NULL;
+	bool	ex_lock = false;
+	Index	first_rtindex = is_create ? 1 : PRS2_NEW_VARNO + 1;
+	RangeTblEntry *rte;
+
+	/* Immediately return if we don't have any base tables. */
+	if (list_length(qry->rtable) < first_rtindex)
+		return;
+
+	/*
+	 * If the view has more than one base tables, we need an exclusive lock
+	 * on the view so that the view would be maintained serially to avoid
+	 * the inconsistency that occurs when two base tables are modified in
+	 * concurrent transactions. However, if the view has only one table,
+	 * we can use a weaker lock.
+	 *
+	 * The type of lock should be determined here, because if we check the
+	 * view definition at maintenance time, we need to acquire a weaker lock,
+	 * and upgrading the lock level after this increases probability of
+	 * deadlock.
+	 */
+
+	rte = list_nth(qry->rtable, first_rtindex - 1);
+	if (list_length(qry->rtable) > first_rtindex ||
+		rte->rtekind != RTE_RELATION)
+		ex_lock = true;
+
+	CreateIvmTriggersOnBaseTablesRecurse(qry, (Node *)qry, matviewOid, &relids, ex_lock);
+
+	bms_free(relids);
+}
+
+static void
+CreateIvmTriggersOnBaseTablesRecurse(Query *qry, Node *node, Oid matviewOid,
+									 Relids *relids, bool ex_lock)
+{
+	if (node == NULL)
+		return;
+
+	/* This can recurse, so check for excessive recursion */
+	check_stack_depth();
+
+	switch (nodeTag(node))
+	{
+		case T_Query:
+			{
+				Query *query = (Query *) node;
+
+				CreateIvmTriggersOnBaseTablesRecurse(qry, (Node *)query->jointree, matviewOid, relids, ex_lock);
+			}
+			break;
+
+		case T_RangeTblRef:
+			{
+				int			rti = ((RangeTblRef *) node)->rtindex;
+				RangeTblEntry *rte = rt_fetch(rti, qry->rtable);
+
+				if (rte->rtekind == RTE_RELATION && !bms_is_member(rte->relid, *relids))
+				{
+					CreateIvmTrigger(rte->relid, matviewOid, TRIGGER_TYPE_INSERT, TRIGGER_TYPE_BEFORE, ex_lock);
+					CreateIvmTrigger(rte->relid, matviewOid, TRIGGER_TYPE_DELETE, TRIGGER_TYPE_BEFORE, ex_lock);
+					CreateIvmTrigger(rte->relid, matviewOid, TRIGGER_TYPE_UPDATE, TRIGGER_TYPE_BEFORE, ex_lock);
+					CreateIvmTrigger(rte->relid, matviewOid, TRIGGER_TYPE_INSERT, TRIGGER_TYPE_AFTER, ex_lock);
+					CreateIvmTrigger(rte->relid, matviewOid, TRIGGER_TYPE_DELETE, TRIGGER_TYPE_AFTER, ex_lock);
+					CreateIvmTrigger(rte->relid, matviewOid, TRIGGER_TYPE_UPDATE, TRIGGER_TYPE_AFTER, ex_lock);
+
+					*relids = bms_add_member(*relids, rte->relid);
+				}
+			}
+			break;
+
+		case T_FromExpr:
+			{
+				FromExpr   *f = (FromExpr *) node;
+				ListCell   *l;
+
+				foreach(l, f->fromlist)
+					CreateIvmTriggersOnBaseTablesRecurse(qry, lfirst(l), matviewOid, relids, ex_lock);
+			}
+			break;
+
+		case T_JoinExpr:
+			{
+				JoinExpr   *j = (JoinExpr *) node;
+
+				CreateIvmTriggersOnBaseTablesRecurse(qry, j->larg, matviewOid, relids, ex_lock);
+				CreateIvmTriggersOnBaseTablesRecurse(qry, j->rarg, matviewOid, relids, ex_lock);
+			}
+			break;
+
+		default:
+			elog(ERROR, "unrecognized node type: %d", (int) nodeTag(node));
+	}
+}
+
+/*
+ * CreateIvmTrigger -- create IVM trigger on a base table
+ */
+static void
+CreateIvmTrigger(Oid relOid, Oid viewOid, int16 type, int16 timing, bool ex_lock)
+{
+	ObjectAddress	refaddr;
+	ObjectAddress	address;
+	CreateTrigStmt *ivm_trigger;
+	List *transitionRels = NIL;
+
+	Assert(timing == TRIGGER_TYPE_BEFORE || timing == TRIGGER_TYPE_AFTER);
+
+	refaddr.classId = RelationRelationId;
+	refaddr.objectId = viewOid;
+	refaddr.objectSubId = 0;
+
+	ivm_trigger = makeNode(CreateTrigStmt);
+	ivm_trigger->relation = NULL;
+	ivm_trigger->row = false;
+
+	ivm_trigger->timing = timing;
+	ivm_trigger->events = type;
+
+	switch (type)
+	{
+		case TRIGGER_TYPE_INSERT:
+			ivm_trigger->trigname = (timing == TRIGGER_TYPE_BEFORE ? "IVM_trigger_ins_before" : "IVM_trigger_ins_after");
+			break;
+		case TRIGGER_TYPE_DELETE:
+			ivm_trigger->trigname = (timing == TRIGGER_TYPE_BEFORE ? "IVM_trigger_del_before" : "IVM_trigger_del_after");
+			break;
+		case TRIGGER_TYPE_UPDATE:
+			ivm_trigger->trigname = (timing == TRIGGER_TYPE_BEFORE ? "IVM_trigger_upd_before" : "IVM_trigger_upd_after");
+			break;
+		default:
+			elog(ERROR, "unsupported trigger type");
+	}
+
+	if (timing == TRIGGER_TYPE_AFTER)
+	{
+		if (type == TRIGGER_TYPE_INSERT || type == TRIGGER_TYPE_UPDATE)
+		{
+			TriggerTransition *n = makeNode(TriggerTransition);
+			n->name = "__ivm_newtable";
+			n->isNew = true;
+			n->isTable = true;
+
+			transitionRels = lappend(transitionRels, n);
+		}
+		if (type == TRIGGER_TYPE_DELETE || type == TRIGGER_TYPE_UPDATE)
+		{
+			TriggerTransition *n = makeNode(TriggerTransition);
+			n->name = "__ivm_oldtable";
+			n->isNew = false;
+			n->isTable = true;
+
+			transitionRels = lappend(transitionRels, n);
+		}
+	}
+
+	ivm_trigger->funcname =
+		(timing == TRIGGER_TYPE_BEFORE ? SystemFuncName("IVM_immediate_before") : SystemFuncName("IVM_immediate_maintenance"));
+
+	ivm_trigger->columns = NIL;
+	ivm_trigger->transitionRels = transitionRels;
+	ivm_trigger->whenClause = NULL;
+	ivm_trigger->isconstraint = false;
+	ivm_trigger->deferrable = false;
+	ivm_trigger->initdeferred = false;
+	ivm_trigger->constrrel = NULL;
+	ivm_trigger->args = list_make2(
+		makeString(DatumGetPointer(DirectFunctionCall1(oidout, ObjectIdGetDatum(viewOid)))),
+		makeString(DatumGetPointer(DirectFunctionCall1(boolout, BoolGetDatum(ex_lock))))
+		);
+
+	address = CreateTrigger(ivm_trigger, NULL, relOid, InvalidOid, InvalidOid,
+						 InvalidOid, InvalidOid, InvalidOid, NULL, true, false);
+
+	recordDependencyOn(&address, &refaddr, DEPENDENCY_AUTO);
+
+	/* Make changes-so-far visible */
+	CommandCounterIncrement();
+}
+
+/*
+ * check_ivm_restriction --- look for specify nodes in the query tree
+ */
+static void
+check_ivm_restriction(Node *node)
+{
+	check_ivm_restriction_walker(node, NULL);
+}
+
+static bool
+check_ivm_restriction_walker(Node *node, void *context)
+{
+	if (node == NULL)
+		return false;
+
+	/*
+	 * We currently don't support Sub-Query.
+	 */
+	if (IsA(node, SubPlan) || IsA(node, SubLink))
+		ereport(ERROR,
+				(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+				 errmsg("subquery is not supported on incrementally maintainable materialized view")));
+
+	/* This can recurse, so check for excessive recursion */
+	check_stack_depth();
+
+	switch (nodeTag(node))
+	{
+		case T_Query:
+			{
+				Query *qry = (Query *)node;
+				ListCell   *lc;
+				List       *vars;
+
+				/* if contained CTE, return error */
+				if (qry->cteList != NIL)
+					ereport(ERROR,
+							(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+							 errmsg("CTE is not supported on incrementally maintainable materialized view")));
+				if (qry->havingQual != NULL)
+					ereport(ERROR,
+							(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+							 errmsg(" HAVING clause is not supported on incrementally maintainable materialized view")));
+				if (qry->sortClause != NIL)	/* There is a possibility that we don't need to return an error */
+					ereport(ERROR,
+							(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+							 errmsg("ORDER BY clause is not supported on incrementally maintainable materialized view")));
+				if (qry->limitOffset != NULL || qry->limitCount != NULL)
+					ereport(ERROR,
+							(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+							 errmsg("LIMIT/OFFSET clause is not supported on incrementally maintainable materialized view")));
+				if (qry->hasDistinctOn)
+					ereport(ERROR,
+							(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+							 errmsg("DISTINCT ON is not supported on incrementally maintainable materialized view")));
+				if (qry->hasWindowFuncs)
+					ereport(ERROR,
+							(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+							 errmsg("window functions are not supported on incrementally maintainable materialized view")));
+				if (qry->groupingSets != NIL)
+					ereport(ERROR,
+							(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+							 errmsg("GROUPING SETS, ROLLUP, or CUBE clauses is not supported on incrementally maintainable materialized view")));
+				if (qry->setOperations != NULL)
+					ereport(ERROR,
+							(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+							 errmsg("UNION/INTERSECT/EXCEPT statements are not supported on incrementally maintainable materialized view")));
+				if (list_length(qry->targetList) == 0)
+					ereport(ERROR,
+							(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+							 errmsg("empty target list is not supported on incrementally maintainable materialized view")));
+				if (qry->rowMarks != NIL)
+					ereport(ERROR,
+							(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+							 errmsg("FOR UPDATE/SHARE clause is not supported on incrementally maintainable materialized view")));
+
+				/* system column restrictions */
+				vars = pull_vars_of_level((Node *) qry, 0);
+				foreach(lc, vars)
+				{
+					if (IsA(lfirst(lc), Var))
+					{
+						Var *var = (Var *) lfirst(lc);
+						/* if system column, return error */
+						if (var->varattno < 0)
+							ereport(ERROR,
+									(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+									 errmsg("system column is not supported on incrementally maintainable materialized view")));
+					}
+				}
+
+				/* restrictions for rtable */
+				foreach(lc, qry->rtable)
+				{
+					RangeTblEntry *rte = (RangeTblEntry *) lfirst(lc);
+
+					if (rte->subquery)
+						ereport(ERROR,
+								(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+								 errmsg("subquery is not supported on incrementally maintainable materialized view")));
+
+					if (rte->tablesample != NULL)
+						ereport(ERROR,
+								(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+								 errmsg("TABLESAMPLE clause is not supported on incrementally maintainable materialized view")));
+
+					if (rte->relkind == RELKIND_PARTITIONED_TABLE)
+						ereport(ERROR,
+								(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+								 errmsg("partitioned table is not supported on incrementally maintainable materialized view")));
+
+					if (rte->relkind == RELKIND_RELATION && has_superclass(rte->relid))
+						ereport(ERROR,
+								(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+								 errmsg("partitions is not supported on incrementally maintainable materialized view")));
+
+					if (rte->relkind == RELKIND_RELATION && find_inheritance_children(rte->relid, NoLock) != NIL)
+						ereport(ERROR,
+								(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+								 errmsg("inheritance parent is not supported on incrementally maintainable materialized view")));
+
+					if (rte->relkind == RELKIND_FOREIGN_TABLE)
+						ereport(ERROR,
+								(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+								 errmsg("foreign table is not supported on incrementally maintainable materialized view")));
+
+					if (rte->relkind == RELKIND_VIEW ||
+						rte->relkind == RELKIND_MATVIEW)
+						ereport(ERROR,
+								(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+								 errmsg("VIEW or MATERIALIZED VIEW is not supported on incrementally maintainable materialized view")));
+
+					if (rte->rtekind == RTE_VALUES)
+						ereport(ERROR,
+								(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+								 errmsg("VALUES is not supported on incrementally maintainable materialized view")));
+
+				}
+
+				query_tree_walker(qry, check_ivm_restriction_walker, NULL, QTW_IGNORE_RANGE_TABLE);
+
+				break;
+			}
+		case T_TargetEntry:
+			{
+				TargetEntry *tle = (TargetEntry *)node;
+				if (isIvmName(tle->resname))
+						ereport(ERROR,
+								(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+								 errmsg("column name %s is not supported on incrementally maintainable materialized view", tle->resname)));
+
+				expression_tree_walker(node, check_ivm_restriction_walker, NULL);
+				break;
+			}
+		case T_JoinExpr:
+			{
+				JoinExpr *joinexpr = (JoinExpr *)node;
+
+				if (joinexpr->jointype > JOIN_INNER)
+						ereport(ERROR,
+								(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+								 errmsg("OUTER JOIN is not supported on incrementally maintainable materialized view")));
+
+				expression_tree_walker(node, check_ivm_restriction_walker, NULL);
+			}
+			break;
+		case T_Aggref:
+			ereport(ERROR,
+					(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+					 errmsg("aggregate function is not supported on incrementally maintainable materialized view")));
+			break;
+		default:
+			expression_tree_walker(node, check_ivm_restriction_walker, (void *) context);
+			break;
+	}
+	return false;
+}
+
+/*
+ * CreateIndexOnIMMV
+ *
+ * Create a unique index on incremental maintainable materialized view.
+ * If the view definition query has a GROUP BY clause, the index is created
+ * on the columns of GROUP BY expressions. Otherwise, if the view contains
+ * all primary key attritubes of its base tables in the target list, the index
+ * is created on these attritubes. In other cases, no index is created.
+ */
+void
+CreateIndexOnIMMV(Query *query, Relation matviewRel, bool is_create)
+{
+	ListCell *lc;
+	IndexStmt  *index;
+	ObjectAddress address;
+	List *constraintList = NIL;
+	char		idxname[NAMEDATALEN];
+	List	   *indexoidlist = RelationGetIndexList(matviewRel);
+	ListCell   *indexoidscan;
+
+	snprintf(idxname, sizeof(idxname), "%s_index", RelationGetRelationName(matviewRel));
+
+	index = makeNode(IndexStmt);
+
+	/*
+	 * We consider null values not distinct to make sure that views with DISTINCT
+	 * or GROUP BY don't contain multiple NULL rows when NULL is inserted to
+	 * a base table concurrently.
+	 */
+	index->nulls_not_distinct = true;
+
+	index->unique = true;
+	index->primary = false;
+	index->isconstraint = false;
+	index->deferrable = false;
+	index->initdeferred = false;
+	index->idxname = idxname;
+	index->relation =
+		makeRangeVar(get_namespace_name(RelationGetNamespace(matviewRel)),
+					 pstrdup(RelationGetRelationName(matviewRel)),
+					 -1);
+	index->accessMethod = DEFAULT_INDEX_TYPE;
+	index->options = NIL;
+	index->tableSpace = get_tablespace_name(matviewRel->rd_rel->reltablespace);
+	index->whereClause = NULL;
+	index->indexParams = NIL;
+	index->indexIncludingParams = NIL;
+	index->excludeOpNames = NIL;
+	index->idxcomment = NULL;
+	index->indexOid = InvalidOid;
+	index->oldNode = InvalidOid;
+	index->oldCreateSubid = InvalidSubTransactionId;
+	index->oldFirstRelfilenodeSubid = InvalidSubTransactionId;
+	index->transformed = true;
+	index->concurrent = false;
+	index->if_not_exists = false;
+
+	if (query->distinctClause)
+	{
+		/* create unique constraint on all columns */
+		foreach(lc, query->targetList)
+		{
+			TargetEntry *tle = (TargetEntry *) lfirst(lc);
+			Form_pg_attribute attr = TupleDescAttr(matviewRel->rd_att, tle->resno - 1);
+			IndexElem  *iparam;
+
+			iparam = makeNode(IndexElem);
+			iparam->name = pstrdup(NameStr(attr->attname));
+			iparam->expr = NULL;
+			iparam->indexcolname = NULL;
+			iparam->collation = NIL;
+			iparam->opclass = NIL;
+			iparam->opclassopts = NIL;
+			iparam->ordering = SORTBY_DEFAULT;
+			iparam->nulls_ordering = SORTBY_NULLS_DEFAULT;
+			index->indexParams = lappend(index->indexParams, iparam);
+		}
+	}
+	else
+	{
+		Bitmapset *key_attnos;
+
+		/* create index on the base tables' primary key columns */
+		key_attnos = get_primary_key_attnos_from_query(query, &constraintList, is_create);
+		if (key_attnos)
+		{
+			foreach(lc, query->targetList)
+			{
+				TargetEntry *tle = (TargetEntry *) lfirst(lc);
+				Form_pg_attribute attr = TupleDescAttr(matviewRel->rd_att, tle->resno - 1);
+
+				if (bms_is_member(tle->resno - FirstLowInvalidHeapAttributeNumber, key_attnos))
+				{
+					IndexElem  *iparam;
+
+					iparam = makeNode(IndexElem);
+					iparam->name = pstrdup(NameStr(attr->attname));
+					iparam->expr = NULL;
+					iparam->indexcolname = NULL;
+					iparam->collation = NIL;
+					iparam->opclass = NIL;
+					iparam->opclassopts = NIL;
+					iparam->ordering = SORTBY_DEFAULT;
+					iparam->nulls_ordering = SORTBY_NULLS_DEFAULT;
+					index->indexParams = lappend(index->indexParams, iparam);
+				}
+			}
+		}
+		else
+		{
+			/* create no index, just notice that an appropriate index is necessary for efficient IVM */
+			ereport(NOTICE,
+					(errmsg("could not create an index on materialized view \"%s\" automatically",
+							RelationGetRelationName(matviewRel)),
+					 errdetail("This target list does not have all the primary key columns, "
+							   "or this view does not contain DISTINCT clause."),
+					 errhint("Create an index on the materialized view for efficient incremental maintenance.")));
+			return;
+		}
+	}
+
+	/* If we have a compatible index, we don't need to create another. */
+	foreach(indexoidscan, indexoidlist)
+	{
+		Oid			indexoid = lfirst_oid(indexoidscan);
+		Relation	indexRel;
+		bool		hasCompatibleIndex = false;
+
+		indexRel = index_open(indexoid, AccessShareLock);
+
+		if (CheckIndexCompatible(indexRel->rd_id,
+								index->accessMethod,
+								index->indexParams,
+								index->excludeOpNames))
+			hasCompatibleIndex = true;
+
+		index_close(indexRel, AccessShareLock);
+
+		if (hasCompatibleIndex)
+			return;
+	}
+
+	address = DefineIndex(RelationGetRelid(matviewRel),
+						  index,
+						  InvalidOid,
+						  InvalidOid,
+						  InvalidOid,
+						  false, true, false, false, true);
+
+	ereport(NOTICE,
+			(errmsg("created index \"%s\" on materialized view \"%s\"",
+					idxname, RelationGetRelationName(matviewRel))));
+
+	/*
+	 * Make dependencies so that the index is dropped if any base tables's
+	 * primary key is dropped.
+	 */
+	foreach(lc, constraintList)
+	{
+		Oid constraintOid = lfirst_oid(lc);
+		ObjectAddress	refaddr;
+
+		refaddr.classId = ConstraintRelationId;
+		refaddr.objectId = constraintOid;
+		refaddr.objectSubId = 0;
+
+		recordDependencyOn(&address, &refaddr, DEPENDENCY_NORMAL);
+	}
+}
+
+
+/*
+ * get_primary_key_attnos_from_query
+ *
+ * Identify the columns in base tables' primary keys in the target list.
+ *
+ * Returns a Bitmapset of the column attnos of the primary key's columns of
+ * tables that used in the query.  The attnos are offset by
+ * FirstLowInvalidHeapAttributeNumber as same as get_primary_key_attnos.
+ *
+ * If any table has no primary key or any primary key's columns is not in
+ * the target list, return NULL.  We also return NULL if any pkey constraint
+ * is deferrable.
+ *
+ * constraintList is set to a list of the OIDs of the pkey constraints.
+ */
+static Bitmapset *
+get_primary_key_attnos_from_query(Query *query, List **constraintList, bool is_create)
+{
+	List *key_attnos_list = NIL;
+	ListCell *lc;
+	int i;
+	Bitmapset *keys = NULL;
+	Relids	rels_in_from;
+	PlannerInfo root;
+
+
+	/*
+	 * Collect primary key attributes from all tables used in query. The key attributes
+	 * sets for each table are stored in key_attnos_list in order by RTE index.
+	 */
+	i = 1;
+	foreach(lc, query->rtable)
+	{
+		RangeTblEntry *r = (RangeTblEntry*) lfirst(lc);
+		Bitmapset *key_attnos;
+		bool	has_pkey = true;
+		Index	first_rtindex = is_create ? 1 : PRS2_NEW_VARNO + 1;
+
+		/* skip NEW/OLD entries */
+		if (i >= first_rtindex)
+		{
+			/* for tables, call get_primary_key_attnos */
+			if (r->rtekind == RTE_RELATION)
+			{
+				Oid constraintOid;
+				key_attnos = get_primary_key_attnos(r->relid, false, &constraintOid);
+				*constraintList = lappend_oid(*constraintList, constraintOid);
+				has_pkey = (key_attnos != NULL);
+			}
+			/* for other RTEs, store NULL into key_attnos_list */
+			else
+				key_attnos = NULL;
+		}
+		else
+			key_attnos = NULL;
+
+		/*
+		 * If any table or subquery has no primary key or its pkey constraint is deferrable,
+		 * we cannot get key attributes for this query, so return NULL.
+		 */
+		if (!has_pkey)
+			return NULL;
+
+		key_attnos_list = lappend(key_attnos_list, key_attnos);
+		i++;
+	}
+
+	/* Collect key attributes appearing in the target list */
+	i = 1;
+	foreach(lc, query->targetList)
+	{
+		TargetEntry *tle = (TargetEntry *) flatten_join_alias_vars(query, lfirst(lc));
+
+		if (IsA(tle->expr, Var))
+		{
+			Var *var = (Var*) tle->expr;
+			Bitmapset *attnos = list_nth(key_attnos_list, var->varno - 1);
+
+			/* check if this attribute is from a base table's primary key */
+			if (bms_is_member(var->varattno - FirstLowInvalidHeapAttributeNumber, attnos))
+			{
+				/*
+				 * Remove found key attributes from key_attnos_list, and add this
+				 * to the result list.
+				 */
+				bms_del_member(attnos, var->varattno - FirstLowInvalidHeapAttributeNumber);
+				keys = bms_add_member(keys, i - FirstLowInvalidHeapAttributeNumber);
+			}
+		}
+		i++;
+	}
+
+	/* Collect relations appearing in the FROM clause */
+	rels_in_from = pull_varnos_of_level(&root, (Node *)query->jointree, 0);
+
+	/*
+	 * Check if all key attributes of relations in FROM are appearing in the target
+	 * list.  If an attribute remains in key_attnos_list in spite of the table is used
+	 * in FROM clause, the target is missing this key attribute, so we return NULL.
+	 */
+	i = 1;
+	foreach(lc, key_attnos_list)
+	{
+		Bitmapset *bms = (Bitmapset *)lfirst(lc);
+		if (!bms_is_empty(bms) && bms_is_member(i, rels_in_from))
+			return NULL;
+		i++;
+	}
+
+	return keys;
+}
diff --git a/src/backend/commands/indexcmds.c b/src/backend/commands/indexcmds.c
index cd30f15eba..a94b8ffd7d 100644
--- a/src/backend/commands/indexcmds.c
+++ b/src/backend/commands/indexcmds.c
@@ -36,6 +36,7 @@
 #include "commands/dbcommands.h"
 #include "commands/defrem.h"
 #include "commands/event_trigger.h"
+#include "commands/matview.h"
 #include "commands/progress.h"
 #include "commands/tablecmds.h"
 #include "commands/tablespace.h"
@@ -1055,6 +1056,45 @@ DefineIndex(Oid relationId,
 	safe_index = indexInfo->ii_Expressions == NIL &&
 		indexInfo->ii_Predicate == NIL;
 
+	/*
+	 * We disallow unique indexes on IVM columns of IMMVs.
+	 */
+	if (RelationIsIVM(rel) && stmt->unique)
+	{
+		for (i = 0; i < indexInfo->ii_NumIndexKeyAttrs; i++)
+		{
+			AttrNumber	attno = indexInfo->ii_IndexAttrNumbers[i];
+			if (attno > 0)
+			{
+				char *name = NameStr(TupleDescAttr(rel->rd_att, attno - 1)->attname);
+				if (name && isIvmName(name))
+					ereport(ERROR,
+							(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+							 errmsg("unique index creation on IVM columns is not supported")));
+			}
+		}
+
+		if (indexInfo->ii_Expressions)
+		{
+			Bitmapset  *indexattrs = NULL;
+			int			varno = -1;
+
+			pull_varattnos((Node *) indexInfo->ii_Expressions, 1, &indexattrs);
+
+			while ((varno = bms_next_member(indexattrs, varno)) >= 0)
+			{
+				int attno = varno + FirstLowInvalidHeapAttributeNumber;
+				char *name = NameStr(TupleDescAttr(rel->rd_att, attno - 1)->attname);
+				if (name && isIvmName(name))
+					ereport(ERROR,
+							(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+							 errmsg("unique index creation on IVM columns is not supported")));
+			}
+
+		}
+	}
+
+
 	/*
 	 * Report index creation if appropriate (delay this till after most of the
 	 * error checks)
diff --git a/src/backend/commands/matview.c b/src/backend/commands/matview.c
index 9ab248d25e..cb713328a0 100644
--- a/src/backend/commands/matview.c
+++ b/src/backend/commands/matview.c
@@ -25,26 +25,48 @@
 #include "catalog/indexing.h"
 #include "catalog/namespace.h"
 #include "catalog/pg_am.h"
+#include "catalog/pg_collation.h"
+#include "catalog/pg_depend.h"
+#include "catalog/pg_trigger.h"
+#include "catalog/pg_type.h"
 #include "catalog/pg_opclass.h"
 #include "catalog/pg_operator.h"
 #include "commands/cluster.h"
+#include "commands/defrem.h"
 #include "commands/matview.h"
 #include "commands/tablecmds.h"
 #include "commands/tablespace.h"
+#include "commands/createas.h"
 #include "executor/executor.h"
 #include "executor/spi.h"
+#include "executor/tstoreReceiver.h"
 #include "miscadmin.h"
+#include "nodes/makefuncs.h"
+#include "nodes/nodeFuncs.h"
+#include "optimizer/optimizer.h"
+#include "parser/analyze.h"
+#include "parser/parser.h"
+#include "parser/parsetree.h"
+#include "parser/parse_clause.h"
+#include "parser/parse_coerce.h"
+#include "parser/parse_collate.h"
+#include "parser/parse_func.h"
 #include "parser/parse_relation.h"
+#include "parser/parse_type.h"
 #include "pgstat.h"
 #include "rewrite/rewriteHandler.h"
+#include "rewrite/rewriteManip.h"
+#include "rewrite/rowsecurity.h"
 #include "storage/lmgr.h"
 #include "storage/smgr.h"
 #include "tcop/tcopprot.h"
 #include "utils/builtins.h"
+#include "utils/fmgroids.h"
 #include "utils/lsyscache.h"
 #include "utils/rel.h"
 #include "utils/snapmgr.h"
 #include "utils/syscache.h"
+#include "utils/typcache.h"
 
 
 typedef struct
@@ -58,6 +80,50 @@ typedef struct
 	BulkInsertState bistate;	/* bulk insert state */
 } DR_transientrel;
 
+#define MV_INIT_QUERYHASHSIZE	16
+
+/*
+ * MV_TriggerHashEntry
+ *
+ * Hash entry for base tables on which IVM trigger is invoked
+ */
+typedef struct MV_TriggerHashEntry
+{
+	Oid	matview_id;			/* OID of the materialized view */
+	int	before_trig_count;	/* count of before triggers invoked */
+	int	after_trig_count;	/* count of after triggers invoked */
+
+	TransactionId	xid;	/* Transaction id before the first table is modified*/
+	CommandId		cid;	/* Command id before the first table is modified */
+
+	List   *tables;		/* List of MV_TriggerTable */
+	bool	has_old;	/* tuples are deleted from any table? */
+	bool	has_new;	/* tuples are inserted into any table? */
+} MV_TriggerHashEntry;
+
+/*
+ * MV_TriggerTable
+ *
+ * IVM related data for tables on which the trigger is invoked.
+ */
+typedef struct MV_TriggerTable
+{
+	Oid		table_id;			/* OID of the modified table */
+	List   *old_tuplestores;	/* tuplestores for deleted tuples */
+	List   *new_tuplestores;	/* tuplestores for inserted tuples */
+	List   *old_rtes;			/* RTEs of ENRs for old_tuplestores*/
+	List   *new_rtes;			/* RTEs of ENRs for new_tuplestores */
+
+	List   *rte_indexes;		/* List of RTE index of the modified table */
+	RangeTblEntry *original_rte;	/* the original RTE saved before rewriting query */
+} MV_TriggerTable;
+
+static HTAB *mv_trigger_info = NULL;
+
+/* ENR name for materialized view delta */
+#define NEW_DELTA_ENRNAME "new_delta"
+#define OLD_DELTA_ENRNAME "old_delta"
+
 static int	matview_maintenance_depth = 0;
 
 static void transientrel_startup(DestReceiver *self, int operation, TupleDesc typeinfo);
@@ -65,7 +131,9 @@ static bool transientrel_receive(TupleTableSlot *slot, DestReceiver *self);
 static void transientrel_shutdown(DestReceiver *self);
 static void transientrel_destroy(DestReceiver *self);
 static uint64 refresh_matview_datafill(DestReceiver *dest, Query *query,
-									   const char *queryString);
+						 QueryEnvironment *queryEnv,
+						 TupleDesc *resultTupleDesc,
+						 const char *queryString);
 static char *make_temptable_name_n(char *tempname, int n);
 static void refresh_by_match_merge(Oid matviewOid, Oid tempOid, Oid relowner,
 								   int save_sec_context);
@@ -73,6 +141,45 @@ static void refresh_by_heap_swap(Oid matviewOid, Oid OIDNewHeap, char relpersist
 static bool is_usable_unique_index(Relation indexRel);
 static void OpenMatViewIncrementalMaintenance(void);
 static void CloseMatViewIncrementalMaintenance(void);
+static Query *get_matview_query(Relation matviewRel);
+
+static Query *rewrite_query_for_preupdate_state(Query *query, List *tables,
+								  TransactionId xid, CommandId cid,
+								  ParseState *pstate);
+static void register_delta_ENRs(ParseState *pstate, Query *query, List *tables);
+static char *make_delta_enr_name(const char *prefix, Oid relid, int count);
+static RangeTblEntry *get_prestate_rte(RangeTblEntry *rte, MV_TriggerTable *table,
+				 TransactionId xid, CommandId cid,
+				 QueryEnvironment *queryEnv);
+static RangeTblEntry *union_ENRs(RangeTblEntry *rte, Oid relid, List *enr_rtes, const char *prefix,
+		   QueryEnvironment *queryEnv);
+static Query *rewrite_query_for_distinct(Query *query, ParseState *pstate);
+
+static void calc_delta(MV_TriggerTable *table, int rte_index, Query *query,
+			DestReceiver *dest_old, DestReceiver *dest_new,
+			TupleDesc *tupdesc_old, TupleDesc *tupdesc_new,
+			QueryEnvironment *queryEnv);
+static Query *rewrite_query_for_postupdate_state(Query *query, MV_TriggerTable *table, int rte_index);
+
+static void apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *new_tuplestores,
+			TupleDesc tupdesc_old, TupleDesc tupdesc_new,
+			Query *query, bool use_count, char *count_colname);
+static void apply_old_delta(const char *matviewname, const char *deltaname_old,
+				List *keys);
+static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old,
+				List *keys, const char *count_colname);
+static void apply_new_delta(const char *matviewname, const char *deltaname_new,
+				StringInfo target_list);
+static void apply_new_delta_with_count(const char *matviewname, const char* deltaname_new,
+				List *keys, StringInfo target_list, const char* count_colname);
+static char *get_matching_condition_string(List *keys);
+static void generate_equal(StringInfo querybuf, Oid opttype,
+			   const char *leftop, const char *rightop);
+
+static void mv_InitHashTables(void);
+static void clean_up_IVM_hash_entry(MV_TriggerHashEntry *entry);
+
+static List *get_securityQuals(Oid relId, int rt_index, Query *query);
 
 /*
  * SetMatViewPopulatedState
@@ -114,6 +221,46 @@ SetMatViewPopulatedState(Relation relation, bool newstate)
 	CommandCounterIncrement();
 }
 
+/*
+ * SetMatViewIVMState
+ *		Mark a materialized view as IVM, or not.
+ *
+ * NOTE: caller must be holding an appropriate lock on the relation.
+ */
+void
+SetMatViewIVMState(Relation relation, bool newstate)
+{
+	Relation	pgrel;
+	HeapTuple	tuple;
+
+	Assert(relation->rd_rel->relkind == RELKIND_MATVIEW);
+
+	/*
+	 * Update relation's pg_class entry.  Crucial side-effect: other backends
+	 * (and this one too!) are sent SI message to make them rebuild relcache
+	 * entries.
+	 */
+	pgrel = table_open(RelationRelationId, RowExclusiveLock);
+	tuple = SearchSysCacheCopy1(RELOID,
+								ObjectIdGetDatum(RelationGetRelid(relation)));
+	if (!HeapTupleIsValid(tuple))
+		elog(ERROR, "cache lookup failed for relation %u",
+			 RelationGetRelid(relation));
+
+	((Form_pg_class) GETSTRUCT(tuple))->relisivm = newstate;
+
+	CatalogTupleUpdate(pgrel, &tuple->t_self, tuple);
+
+	heap_freetuple(tuple);
+	table_close(pgrel, RowExclusiveLock);
+
+	/*
+	 * Advance command counter to make the updated pg_class row locally
+	 * visible.
+	 */
+	CommandCounterIncrement();
+}
+
 /*
  * ExecRefreshMatView -- execute a REFRESH MATERIALIZED VIEW command
  *
@@ -140,9 +287,8 @@ ExecRefreshMatView(RefreshMatViewStmt *stmt, const char *queryString,
 {
 	Oid			matviewOid;
 	Relation	matviewRel;
-	RewriteRule *rule;
-	List	   *actions;
 	Query	   *dataQuery;
+	Query	   *viewQuery;
 	Oid			tableSpace;
 	Oid			relowner;
 	Oid			OIDNewHeap;
@@ -155,6 +301,7 @@ ExecRefreshMatView(RefreshMatViewStmt *stmt, const char *queryString,
 	int			save_sec_context;
 	int			save_nestlevel;
 	ObjectAddress address;
+	bool oldPopulated;
 
 	/* Determine strength of lock needed. */
 	concurrent = stmt->concurrent;
@@ -167,6 +314,7 @@ ExecRefreshMatView(RefreshMatViewStmt *stmt, const char *queryString,
 										  lockmode, 0,
 										  RangeVarCallbackOwnsTable, NULL);
 	matviewRel = table_open(matviewOid, NoLock);
+	oldPopulated = RelationIsPopulated(matviewRel);
 
 	/* Make sure it is a materialized view. */
 	if (matviewRel->rd_rel->relkind != RELKIND_MATVIEW)
@@ -188,32 +336,14 @@ ExecRefreshMatView(RefreshMatViewStmt *stmt, const char *queryString,
 				 errmsg("%s and %s options cannot be used together",
 						"CONCURRENTLY", "WITH NO DATA")));
 
-	/*
-	 * Check that everything is correct for a refresh. Problems at this point
-	 * are internal errors, so elog is sufficient.
-	 */
-	if (matviewRel->rd_rel->relhasrules == false ||
-		matviewRel->rd_rules->numLocks < 1)
-		elog(ERROR,
-			 "materialized view \"%s\" is missing rewrite information",
-			 RelationGetRelationName(matviewRel));
-
-	if (matviewRel->rd_rules->numLocks > 1)
-		elog(ERROR,
-			 "materialized view \"%s\" has too many rules",
-			 RelationGetRelationName(matviewRel));
 
-	rule = matviewRel->rd_rules->rules[0];
-	if (rule->event != CMD_SELECT || !(rule->isInstead))
-		elog(ERROR,
-			 "the rule for materialized view \"%s\" is not a SELECT INSTEAD OF rule",
-			 RelationGetRelationName(matviewRel));
+	viewQuery = get_matview_query(matviewRel);
 
-	actions = rule->actions;
-	if (list_length(actions) != 1)
-		elog(ERROR,
-			 "the rule for materialized view \"%s\" is not a single action",
-			 RelationGetRelationName(matviewRel));
+	/* For IMMV, we need to rewrite matview query */
+	if (!stmt->skipData && RelationIsIVM(matviewRel))
+		dataQuery = rewriteQueryForIMMV(viewQuery,NIL);
+	else
+		dataQuery = viewQuery;
 
 	/*
 	 * Check that there is a unique index with no WHERE clause on one or more
@@ -248,12 +378,6 @@ ExecRefreshMatView(RefreshMatViewStmt *stmt, const char *queryString,
 					 errhint("Create a unique index with no WHERE clause on one or more columns of the materialized view.")));
 	}
 
-	/*
-	 * The stored query was rewritten at the time of the MV definition, but
-	 * has not been scribbled on by the planner.
-	 */
-	dataQuery = linitial_node(Query, actions);
-
 	/*
 	 * Check for active uses of the relation in the current transaction, such
 	 * as open scans.
@@ -294,6 +418,74 @@ ExecRefreshMatView(RefreshMatViewStmt *stmt, const char *queryString,
 		relpersistence = matviewRel->rd_rel->relpersistence;
 	}
 
+	/* delete IMMV triggers. */
+	if (RelationIsIVM(matviewRel) && stmt->skipData )
+	{
+		Relation	tgRel;
+		Relation	depRel;
+		ScanKeyData key;
+		SysScanDesc scan;
+		HeapTuple	tup;
+		ObjectAddresses *immv_triggers;
+
+		immv_triggers = new_object_addresses();
+
+		tgRel = table_open(TriggerRelationId, RowExclusiveLock);
+		depRel = table_open(DependRelationId, RowExclusiveLock);
+
+		/* search triggers that depends on IMMV. */
+		ScanKeyInit(&key,
+					Anum_pg_depend_refobjid,
+					BTEqualStrategyNumber, F_OIDEQ,
+					ObjectIdGetDatum(matviewOid));
+		scan = systable_beginscan(depRel, DependReferenceIndexId, true,
+								  NULL, 1, &key);
+		while ((tup = systable_getnext(scan)) != NULL)
+		{
+			ObjectAddress obj;
+			Form_pg_depend foundDep = (Form_pg_depend) GETSTRUCT(tup);
+
+			if (foundDep->classid == TriggerRelationId)
+			{
+				HeapTuple	tgtup;
+				ScanKeyData tgkey[1];
+				SysScanDesc tgscan;
+				Form_pg_trigger tgform;
+
+				/* Find the trigger name. */
+				ScanKeyInit(&tgkey[0],
+							Anum_pg_trigger_oid,
+							BTEqualStrategyNumber, F_OIDEQ,
+							ObjectIdGetDatum(foundDep->objid));
+
+				tgscan = systable_beginscan(tgRel, TriggerOidIndexId, true,
+											NULL, 1, tgkey);
+				tgtup = systable_getnext(tgscan);
+				if (!HeapTupleIsValid(tgtup))
+					elog(ERROR, "could not find tuple for immv trigger %u", foundDep->objid);
+
+				tgform = (Form_pg_trigger) GETSTRUCT(tgtup);
+
+				/* If trigger is created by IMMV, delete it. */
+				if (strncmp(NameStr(tgform->tgname), "IVM_trigger_", 12) == 0)
+				{
+					obj.classId = foundDep->classid;
+					obj.objectId = foundDep->objid;
+					obj.objectSubId = foundDep->refobjsubid;
+					add_exact_object_address(&obj, immv_triggers);
+				}
+				systable_endscan(tgscan);
+			}
+		}
+		systable_endscan(scan);
+
+		performMultipleDeletions(immv_triggers, DROP_RESTRICT, PERFORM_DELETION_INTERNAL);
+
+		table_close(depRel, RowExclusiveLock);
+		table_close(tgRel, RowExclusiveLock);
+		free_object_addresses(immv_triggers);
+	}
+
 	/*
 	 * Create the transient table that will receive the regenerated data. Lock
 	 * it against access by any other process until commit (by which time it
@@ -313,7 +505,7 @@ ExecRefreshMatView(RefreshMatViewStmt *stmt, const char *queryString,
 
 	/* Generate the data, if wanted. */
 	if (!stmt->skipData)
-		processed = refresh_matview_datafill(dest, dataQuery, queryString);
+		processed = refresh_matview_datafill(dest, dataQuery, NULL, NULL, queryString);
 
 	/* Make the matview match the newly generated data. */
 	if (concurrent)
@@ -348,6 +540,12 @@ ExecRefreshMatView(RefreshMatViewStmt *stmt, const char *queryString,
 			pgstat_count_heap_insert(matviewRel, processed);
 	}
 
+	if (!stmt->skipData && RelationIsIVM(matviewRel) && !oldPopulated)
+	{
+		CreateIndexOnIMMV(viewQuery, matviewRel, false);
+		CreateIvmTriggersOnBaseTables(viewQuery, matviewOid, false);
+	}
+
 	table_close(matviewRel, NoLock);
 
 	/* Roll back any GUC changes */
@@ -382,6 +580,8 @@ ExecRefreshMatView(RefreshMatViewStmt *stmt, const char *queryString,
  */
 static uint64
 refresh_matview_datafill(DestReceiver *dest, Query *query,
+						 QueryEnvironment *queryEnv,
+						 TupleDesc *resultTupleDesc,
 						 const char *queryString)
 {
 	List	   *rewritten;
@@ -418,7 +618,7 @@ refresh_matview_datafill(DestReceiver *dest, Query *query,
 	/* Create a QueryDesc, redirecting output to our tuple receiver */
 	queryDesc = CreateQueryDesc(plan, queryString,
 								GetActiveSnapshot(), InvalidSnapshot,
-								dest, NULL, NULL, 0);
+								dest, NULL, queryEnv ? queryEnv: NULL, 0);
 
 	/* call ExecutorStart to prepare the plan for execution */
 	ExecutorStart(queryDesc, 0);
@@ -428,6 +628,9 @@ refresh_matview_datafill(DestReceiver *dest, Query *query,
 
 	processed = queryDesc->estate->es_processed;
 
+	if (resultTupleDesc)
+		*resultTupleDesc = CreateTupleDescCopy(queryDesc->tupDesc);
+
 	/* and clean up */
 	ExecutorFinish(queryDesc);
 	ExecutorEnd(queryDesc);
@@ -942,3 +1145,1307 @@ CloseMatViewIncrementalMaintenance(void)
 	matview_maintenance_depth--;
 	Assert(matview_maintenance_depth >= 0);
 }
+
+/*
+ * get_matview_query - get the Query from a matview's _RETURN rule.
+ */
+static Query *
+get_matview_query(Relation matviewRel)
+{
+	RewriteRule *rule;
+	List * actions;
+
+	/*
+	 * Check that everything is correct for a refresh. Problems at this point
+	 * are internal errors, so elog is sufficient.
+	 */
+	if (matviewRel->rd_rel->relhasrules == false ||
+		matviewRel->rd_rules->numLocks < 1)
+		elog(ERROR,
+			 "materialized view \"%s\" is missing rewrite information",
+			 RelationGetRelationName(matviewRel));
+
+	if (matviewRel->rd_rules->numLocks > 1)
+		elog(ERROR,
+			 "materialized view \"%s\" has too many rules",
+			 RelationGetRelationName(matviewRel));
+
+	rule = matviewRel->rd_rules->rules[0];
+	if (rule->event != CMD_SELECT || !(rule->isInstead))
+		elog(ERROR,
+			 "the rule for materialized view \"%s\" is not a SELECT INSTEAD OF rule",
+			 RelationGetRelationName(matviewRel));
+
+	actions = rule->actions;
+	if (list_length(actions) != 1)
+		elog(ERROR,
+			 "the rule for materialized view \"%s\" is not a single action",
+			 RelationGetRelationName(matviewRel));
+
+	/*
+	 * The stored query was rewritten at the time of the MV definition, but
+	 * has not been scribbled on by the planner.
+	 */
+	return linitial_node(Query, actions);
+}
+
+
+/* ----------------------------------------------------
+ *		Incremental View Maintenance routines
+ * ---------------------------------------------------
+ */
+
+/*
+ * IVM_immediate_before
+ *
+ * IVM trigger function invoked before base table is modified. If this is
+ * invoked firstly in the same statement, we save the transaction id and the
+ * command id at that time.
+ */
+Datum
+IVM_immediate_before(PG_FUNCTION_ARGS)
+{
+	TriggerData *trigdata = (TriggerData *) fcinfo->context;
+	char	   *matviewOid_text = trigdata->tg_trigger->tgargs[0];
+	char	   *ex_lock_text = trigdata->tg_trigger->tgargs[1];
+	Oid			matviewOid;
+	MV_TriggerHashEntry *entry;
+	bool	found;
+	bool	ex_lock;
+
+	matviewOid = DatumGetObjectId(DirectFunctionCall1(oidin, CStringGetDatum(matviewOid_text)));
+	ex_lock = DatumGetBool(DirectFunctionCall1(boolin, CStringGetDatum(ex_lock_text)));
+
+	/* If the view has more than one tables, we have to use an exclusive lock. */
+	if (ex_lock)
+	{
+		/*
+		 * Wait for concurrent transactions which update this materialized view at
+		 * READ COMMITED. This is needed to see changes committed in other
+		 * transactions. No wait and raise an error at REPEATABLE READ or
+		 * SERIALIZABLE to prevent update anomalies of matviews.
+		 * XXX: dead-lock is possible here.
+		 */
+		if (!IsolationUsesXactSnapshot())
+			LockRelationOid(matviewOid, ExclusiveLock);
+		else if (!ConditionalLockRelationOid(matviewOid, ExclusiveLock))
+		{
+			/* try to throw error by name; relation could be deleted... */
+			char	   *relname = get_rel_name(matviewOid);
+
+			if (!relname)
+				ereport(ERROR,
+						(errcode(ERRCODE_LOCK_NOT_AVAILABLE),
+						errmsg("could not obtain lock on materialized view during incremental maintenance")));
+
+			ereport(ERROR,
+					(errcode(ERRCODE_LOCK_NOT_AVAILABLE),
+					errmsg("could not obtain lock on materialized view \"%s\" during incremental maintenance",
+							relname)));
+		}
+	}
+	else
+		LockRelationOid(matviewOid, RowExclusiveLock);
+
+	/*
+	 * On the first call initialize the hashtable
+	 */
+	if (!mv_trigger_info)
+		mv_InitHashTables();
+
+	entry = (MV_TriggerHashEntry *) hash_search(mv_trigger_info,
+											  (void *) &matviewOid,
+											  HASH_ENTER, &found);
+
+	/* On the first BEFORE to update the view, initialize trigger data */
+	if (!found)
+	{
+		Snapshot snapshot = GetActiveSnapshot();
+
+		entry->matview_id = matviewOid;
+		entry->before_trig_count = 0;
+		entry->after_trig_count = 0;
+		entry->xid = GetCurrentTransactionId();
+		entry->cid = snapshot->curcid;
+		entry->tables = NIL;
+		entry->has_old = false;
+		entry->has_new = false;
+	}
+
+	entry->before_trig_count++;
+
+	return PointerGetDatum(NULL);
+}
+
+/*
+ * IVM_immediate_before
+ *
+ * IVM trigger function invoked after base table is modified.
+ * For each table, tuplestores of transition tables are collected.
+ * and after the last modification
+ */
+Datum
+IVM_immediate_maintenance(PG_FUNCTION_ARGS)
+{
+	TriggerData *trigdata = (TriggerData *) fcinfo->context;
+	Relation	rel;
+	Oid			relid;
+	Oid			matviewOid;
+	Query	   *query;
+	Query	   *rewritten = NULL;
+	char	   *matviewOid_text = trigdata->tg_trigger->tgargs[0];
+	Relation	matviewRel;
+	int old_depth = matview_maintenance_depth;
+
+	Oid			relowner;
+	Tuplestorestate *old_tuplestore = NULL;
+	Tuplestorestate *new_tuplestore = NULL;
+	DestReceiver *dest_new = NULL, *dest_old = NULL;
+	Oid			save_userid;
+	int			save_sec_context;
+	int			save_nestlevel;
+
+	MV_TriggerHashEntry *entry;
+	MV_TriggerTable		*table;
+	bool	found;
+
+	ParseState		 *pstate;
+	QueryEnvironment *queryEnv = create_queryEnv();
+	MemoryContext	oldcxt;
+	ListCell   *lc;
+	int			i;
+
+
+	/* Create a ParseState for rewriting the view definition query */
+	pstate = make_parsestate(NULL);
+	pstate->p_queryEnv = queryEnv;
+	pstate->p_expr_kind = EXPR_KIND_SELECT_TARGET;
+
+	rel = trigdata->tg_relation;
+	relid = rel->rd_id;
+
+	matviewOid = DatumGetObjectId(DirectFunctionCall1(oidin, CStringGetDatum(matviewOid_text)));
+
+	/*
+	 * On the first call initialize the hashtable
+	 */
+	if (!mv_trigger_info)
+		mv_InitHashTables();
+
+	/* get the entry for this materialized view */
+	entry = (MV_TriggerHashEntry *) hash_search(mv_trigger_info,
+											  (void *) &matviewOid,
+											  HASH_FIND, &found);
+	Assert (found && entry != NULL);
+	entry->after_trig_count++;
+
+	/* search the entry for the modified table and create new entry if not found */
+	found = false;
+	foreach(lc, entry->tables)
+	{
+		table = (MV_TriggerTable *) lfirst(lc);
+		if (table->table_id == relid)
+		{
+			found = true;
+			break;
+		}
+	}
+	if (!found)
+	{
+		oldcxt = MemoryContextSwitchTo(TopTransactionContext);
+
+		table = (MV_TriggerTable *) palloc0(sizeof(MV_TriggerTable));
+		table->table_id = relid;
+		table->old_tuplestores = NIL;
+		table->new_tuplestores = NIL;
+		table->old_rtes = NIL;
+		table->new_rtes = NIL;
+		table->rte_indexes = NIL;
+		entry->tables = lappend(entry->tables, table);
+
+		MemoryContextSwitchTo(oldcxt);
+	}
+
+	/* Save the transition tables and make a request to not free immediately */
+	if (trigdata->tg_oldtable)
+	{
+		oldcxt = MemoryContextSwitchTo(TopTransactionContext);
+		table->old_tuplestores = lappend(table->old_tuplestores, trigdata->tg_oldtable);
+		entry->has_old = true;
+		MemoryContextSwitchTo(oldcxt);
+	}
+	if (trigdata->tg_newtable)
+	{
+		oldcxt = MemoryContextSwitchTo(TopTransactionContext);
+		table->new_tuplestores = lappend(table->new_tuplestores, trigdata->tg_newtable);
+		entry->has_new = true;
+		MemoryContextSwitchTo(oldcxt);
+	}
+	if (entry->has_new || entry->has_old)
+	{
+		CmdType cmd;
+
+		if (TRIGGER_FIRED_BY_INSERT(trigdata->tg_event))
+			cmd = CMD_INSERT;
+		else if (TRIGGER_FIRED_BY_DELETE(trigdata->tg_event))
+			cmd = CMD_DELETE;
+		else if (TRIGGER_FIRED_BY_UPDATE(trigdata->tg_event))
+			cmd = CMD_UPDATE;
+		else
+			elog(ERROR,"unsupported trigger type");
+
+		/* Prolong lifespan of transition tables to the end of the last AFTER trigger */
+		SetTransitionTablePreserved(relid, cmd);
+	}
+
+
+	/* If this is not the last AFTER trigger call, immediately exit. */
+	Assert (entry->before_trig_count >= entry->after_trig_count);
+	if (entry->before_trig_count != entry->after_trig_count)
+		return PointerGetDatum(NULL);
+
+	/*
+	 * If this is the last AFTER trigger call, continue and update the view.
+	 */
+
+	/*
+	 * Advance command counter to make the updated base table row locally
+	 * visible.
+	 */
+	CommandCounterIncrement();
+
+	matviewRel = table_open(matviewOid, NoLock);
+
+	/* get view query*/
+	query = get_matview_query(matviewRel);
+
+	/* Make sure it is a materialized view. */
+	Assert(matviewRel->rd_rel->relkind == RELKIND_MATVIEW);
+
+	/*
+	 * Get and push the latast snapshot to see any changes which is committed
+	 * during waiting in other transactions at READ COMMITTED level.
+	 */
+	PushActiveSnapshot(GetTransactionSnapshot());
+
+	/*
+	 * Check for active uses of the relation in the current transaction, such
+	 * as open scans.
+	 *
+	 * NB: We count on this to protect us against problems with refreshing the
+	 * data using TABLE_INSERT_FROZEN.
+	 */
+	CheckTableNotInUse(matviewRel, "refresh a materialized view incrementally");
+
+	/*
+	 * Switch to the owner's userid, so that any functions are run as that
+	 * user.  Also arrange to make GUC variable changes local to this command.
+	 * We will switch modes when we are about to execute user code.
+	 */
+	relowner = matviewRel->rd_rel->relowner;
+	GetUserIdAndSecContext(&save_userid, &save_sec_context);
+	SetUserIdAndSecContext(relowner,
+						   save_sec_context | SECURITY_RESTRICTED_OPERATION);
+	save_nestlevel = NewGUCNestLevel();
+
+	/*
+	 * rewrite query for calculating deltas
+	 */
+
+	rewritten = copyObject(query);
+
+	/* Replace resnames in a target list with materialized view's attnames */
+	i = 0;
+	foreach (lc, rewritten->targetList)
+	{
+		TargetEntry *tle = (TargetEntry *) lfirst(lc);
+		Form_pg_attribute attr = TupleDescAttr(matviewRel->rd_att, i);
+		char *resname = NameStr(attr->attname);
+
+		tle->resname = pstrdup(resname);
+		i++;
+	}
+
+	/* Set all tables in the query to pre-update state */
+	rewritten = rewrite_query_for_preupdate_state(rewritten, entry->tables,
+												  entry->xid, entry->cid,
+												  pstate);
+	/* Rewrite for DISTINCT clause */
+	rewritten = rewrite_query_for_distinct(rewritten, pstate);
+
+	/* Create tuplestores to store view deltas */
+	if (entry->has_old)
+	{
+		oldcxt = MemoryContextSwitchTo(TopTransactionContext);
+
+		old_tuplestore = tuplestore_begin_heap(false, false, work_mem);
+		dest_old = CreateDestReceiver(DestTuplestore);
+		SetTuplestoreDestReceiverParams(dest_old,
+									old_tuplestore,
+									TopTransactionContext,
+									false,
+									NULL,
+									NULL);
+
+		MemoryContextSwitchTo(oldcxt);
+	}
+	if (entry->has_new)
+	{
+		oldcxt = MemoryContextSwitchTo(TopTransactionContext);
+
+		new_tuplestore = tuplestore_begin_heap(false, false, work_mem);
+		dest_new = CreateDestReceiver(DestTuplestore);
+		SetTuplestoreDestReceiverParams(dest_new,
+									new_tuplestore,
+									TopTransactionContext,
+									false,
+									NULL,
+									NULL);
+		MemoryContextSwitchTo(oldcxt);
+	}
+
+	/* for all modified tables */
+	foreach(lc, entry->tables)
+	{
+		ListCell *lc2;
+
+		table = (MV_TriggerTable *) lfirst(lc);
+
+		/* loop for self-join */
+		foreach(lc2, table->rte_indexes)
+		{
+			int	rte_index = lfirst_int(lc2);
+			TupleDesc		tupdesc_old;
+			TupleDesc		tupdesc_new;
+			bool	use_count = false;
+			char   *count_colname = NULL;
+
+			count_colname = pstrdup("__ivm_count__");
+
+			if (query->distinctClause)
+				use_count = true;
+
+			/* calculate delta tables */
+			calc_delta(table, rte_index, rewritten, dest_old, dest_new,
+					   &tupdesc_old, &tupdesc_new, queryEnv);
+
+			/* Set the table in the query to post-update state */
+			rewritten = rewrite_query_for_postupdate_state(rewritten, table, rte_index);
+
+			PG_TRY();
+			{
+				/* apply the delta tables to the materialized view */
+				apply_delta(matviewOid, old_tuplestore, new_tuplestore,
+							tupdesc_old, tupdesc_new, query, use_count,
+							count_colname);
+			}
+			PG_CATCH();
+			{
+				matview_maintenance_depth = old_depth;
+				PG_RE_THROW();
+			}
+			PG_END_TRY();
+
+			/* clear view delta tuplestores */
+			if (old_tuplestore)
+				tuplestore_clear(old_tuplestore);
+			if (new_tuplestore)
+				tuplestore_clear(new_tuplestore);
+		}
+	}
+
+	/* Clean up hash entry and delete tuplestores */
+	clean_up_IVM_hash_entry(entry);
+	if (old_tuplestore)
+	{
+		dest_old->rDestroy(dest_old);
+		tuplestore_end(old_tuplestore);
+	}
+	if (new_tuplestore)
+	{
+		dest_new->rDestroy(dest_new);
+		tuplestore_end(new_tuplestore);
+	}
+
+	/* Pop the original snapshot. */
+	PopActiveSnapshot();
+
+	table_close(matviewRel, NoLock);
+
+	/* Roll back any GUC changes */
+	AtEOXact_GUC(false, save_nestlevel);
+
+	/* Restore userid and security context */
+	SetUserIdAndSecContext(save_userid, save_sec_context);
+
+	return PointerGetDatum(NULL);
+}
+
+/*
+ * rewrite_query_for_preupdate_state
+ *
+ * Rewrite the query so that base tables' RTEs will represent "pre-update"
+ * state of tables. This is necessary to calculate view delta after multiple
+ * tables are modified. xid and cid are the transaction id and command id
+ * before the first table was modified.
+ */
+static Query*
+rewrite_query_for_preupdate_state(Query *query, List *tables,
+								  TransactionId xid, CommandId cid,
+								  ParseState *pstate)
+{
+	ListCell *lc;
+	int num_rte = list_length(query->rtable);
+	int i;
+
+
+	/* register delta ENRs */
+	register_delta_ENRs(pstate, query, tables);
+
+	/* XXX: Is necessary? Is this right timing? */
+	AcquireRewriteLocks(query, true, false);
+
+	i = 1;
+	foreach(lc, query->rtable)
+	{
+		RangeTblEntry *r = (RangeTblEntry*) lfirst(lc);
+
+		ListCell *lc2;
+		foreach(lc2, tables)
+		{
+			MV_TriggerTable *table = (MV_TriggerTable *) lfirst(lc2);
+			/*
+			 * if the modified table is found then replace the original RTE with
+			 * "pre-state" RTE and append its index to the list.
+			 */
+			if (r->relid == table->table_id)
+			{
+				lfirst(lc) = get_prestate_rte(r, table, xid, cid, pstate->p_queryEnv);
+				table->rte_indexes = lappend_int(table->rte_indexes, i);
+				break;
+			}
+		}
+
+		/* finish the loop if we processed all RTE included in the original query */
+		if (i++ >= num_rte)
+			break;
+	}
+
+	return query;
+}
+
+/*
+ * register_delta_ENRs
+ *
+ * For all modified tables, make ENRs for their transition tables
+ * and register them to the queryEnv. ENR's RTEs are also appended
+ * into the list in query tree.
+ */
+static void
+register_delta_ENRs(ParseState *pstate, Query *query, List *tables)
+{
+	QueryEnvironment *queryEnv = pstate->p_queryEnv;
+	ListCell *lc;
+	RangeTblEntry	*rte;
+
+	foreach(lc, tables)
+	{
+		MV_TriggerTable *table = (MV_TriggerTable *) lfirst(lc);
+		ListCell *lc2;
+		int count;
+
+		count = 0;
+		foreach(lc2, table->old_tuplestores)
+		{
+			Tuplestorestate *oldtable = (Tuplestorestate *) lfirst(lc2);
+			EphemeralNamedRelation enr =
+				palloc(sizeof(EphemeralNamedRelationData));
+			ParseNamespaceItem *nsitem;
+
+			enr->md.name = make_delta_enr_name("old", table->table_id, count);
+			enr->md.reliddesc = table->table_id;
+			enr->md.tupdesc = NULL;
+			enr->md.enrtype = ENR_NAMED_TUPLESTORE;
+			enr->md.enrtuples = tuplestore_tuple_count(oldtable);
+			enr->reldata = oldtable;
+			register_ENR(queryEnv, enr);
+
+			nsitem = addRangeTableEntryForENR(pstate, makeRangeVar(NULL, enr->md.name, -1), true);
+			rte = nsitem->p_rte;
+			/* if base table has RLS, set security condition to enr */
+			rte->securityQuals = get_securityQuals(table->table_id, list_length(query->rtable) + 1, query);
+
+			query->rtable = lappend(query->rtable, rte);
+			table->old_rtes = lappend(table->old_rtes, rte);
+
+			count++;
+		}
+
+		count = 0;
+		foreach(lc2, table->new_tuplestores)
+		{
+			Tuplestorestate *newtable = (Tuplestorestate *) lfirst(lc2);
+			EphemeralNamedRelation enr =
+				palloc(sizeof(EphemeralNamedRelationData));
+			ParseNamespaceItem *nsitem;
+
+			enr->md.name = make_delta_enr_name("new", table->table_id, count);
+			enr->md.reliddesc = table->table_id;
+			enr->md.tupdesc = NULL;
+			enr->md.enrtype = ENR_NAMED_TUPLESTORE;
+			enr->md.enrtuples = tuplestore_tuple_count(newtable);
+			enr->reldata = newtable;
+			register_ENR(queryEnv, enr);
+
+			nsitem = addRangeTableEntryForENR(pstate, makeRangeVar(NULL, enr->md.name, -1), true);
+			rte = nsitem->p_rte;
+			/* if base table has RLS, set security condition to enr*/
+			rte->securityQuals = get_securityQuals(table->table_id, list_length(query->rtable) + 1, query);
+
+			query->rtable = lappend(query->rtable, rte);
+			table->new_rtes = lappend(table->new_rtes, rte);
+
+			count++;
+		}
+	}
+}
+
+/*
+ * get_prestate_rte
+ *
+ * Rewrite RTE of the modified table to a subquery which represents
+ * "pre-state" table. The original RTE is saved in table->rte_original.
+ */
+static RangeTblEntry*
+get_prestate_rte(RangeTblEntry *rte, MV_TriggerTable *table,
+				 TransactionId xid, CommandId cid,
+				 QueryEnvironment *queryEnv)
+{
+	StringInfoData str;
+	RawStmt *raw;
+	Query *sub;
+	Relation rel;
+	ParseState *pstate;
+	char *relname;
+	int i;
+
+	pstate = make_parsestate(NULL);
+	pstate->p_queryEnv = queryEnv;
+	pstate->p_expr_kind = EXPR_KIND_SELECT_TARGET;
+
+	/*
+	 * We can use NoLock here since AcquireRewriteLocks should
+	 * have locked the rel already.
+	 */
+	rel = table_open(table->table_id, NoLock);
+	relname = quote_qualified_identifier(
+					get_namespace_name(RelationGetNamespace(rel)),
+									   RelationGetRelationName(rel));
+	table_close(rel, NoLock);
+
+	initStringInfo(&str);
+	appendStringInfo(&str,
+		"SELECT t.* FROM %s t"
+		" WHERE (age(t.xmin) - age(%u::text::xid) > 0) OR"
+		" (t.xmin = %u AND t.cmin::text::int < %u)",
+			relname, xid, xid, cid);
+
+	for (i = 0; i < list_length(table->old_tuplestores); i++)
+	{
+		appendStringInfo(&str, " UNION ALL ");
+		appendStringInfo(&str," SELECT * FROM %s",
+			make_delta_enr_name("old", table->table_id, i));
+	}
+
+	raw = (RawStmt*)linitial(raw_parser(str.data, RAW_PARSE_DEFAULT));
+	sub = transformStmt(pstate, raw->stmt);
+
+	/* If this query has setOperations, RTEs in rtables has a subquery which contains ENR */
+	if (sub->setOperations != NULL)
+	{
+		ListCell *lc;
+
+		/* add securityQuals for tuplestores */
+		foreach (lc, sub->rtable)
+		{
+			RangeTblEntry *rte;
+			RangeTblEntry *sub_rte;
+
+			rte = (RangeTblEntry *)lfirst(lc);
+			Assert(rte->subquery != NULL);
+
+			sub_rte = (RangeTblEntry *)linitial(rte->subquery->rtable);
+			if (sub_rte->rtekind == RTE_NAMEDTUPLESTORE)
+				/* rt_index is always 1, bacause subquery has enr_rte only */
+				sub_rte->securityQuals = get_securityQuals(sub_rte->relid, 1, sub);
+		}
+	}
+
+	/* save the original RTE */
+	table->original_rte = copyObject(rte);
+
+	rte->rtekind = RTE_SUBQUERY;
+	rte->subquery = sub;
+	rte->security_barrier = false;
+	/* Clear fields that should not be set in a subquery RTE */
+	rte->relid = InvalidOid;
+	rte->relkind = 0;
+	rte->rellockmode = 0;
+	rte->tablesample = NULL;
+	rte->inh = false;			/* must not be set for a subquery */
+
+	rte->requiredPerms = 0;		/* no permission check on subquery itself */
+	rte->checkAsUser = InvalidOid;
+	rte->selectedCols = NULL;
+	rte->insertedCols = NULL;
+	rte->updatedCols = NULL;
+	rte->extraUpdatedCols = NULL;
+
+	return rte;
+}
+
+/*
+ * make_delta_enr_name
+ *
+ * Make a name for ENR of a transition table from the base table's oid.
+ * prefix will be "new" or "old" depending on its transition table kind..
+ */
+static char*
+make_delta_enr_name(const char *prefix, Oid relid, int count)
+{
+	char buf[NAMEDATALEN];
+	char *name;
+
+	snprintf(buf, NAMEDATALEN, "__ivm_%s_%u_%u", prefix, relid, count);
+	name = pstrdup(buf);
+
+	return name;
+}
+
+/*
+ * union_ENRs
+ *
+ * Make a single table delta by unionning all transition tables of the modified table
+ * whose RTE is specified by
+ */
+static RangeTblEntry*
+union_ENRs(RangeTblEntry *rte, Oid relid, List *enr_rtes, const char *prefix,
+		   QueryEnvironment *queryEnv)
+{
+	StringInfoData str;
+	ParseState	*pstate;
+	RawStmt *raw;
+	Query *sub;
+	int	i;
+	RangeTblEntry *enr_rte;
+
+	/* Create a ParseState for rewriting the view definition query */
+	pstate = make_parsestate(NULL);
+	pstate->p_queryEnv = queryEnv;
+	pstate->p_expr_kind = EXPR_KIND_SELECT_TARGET;
+
+	initStringInfo(&str);
+
+	for (i = 0; i < list_length(enr_rtes); i++)
+	{
+		if (i > 0)
+			appendStringInfo(&str, " UNION ALL ");
+
+		appendStringInfo(&str,
+			" SELECT * FROM %s",
+			make_delta_enr_name(prefix, relid, i));
+	}
+
+	raw = (RawStmt*)linitial(raw_parser(str.data, RAW_PARSE_DEFAULT));
+	sub = transformStmt(pstate, raw->stmt);
+
+	rte->rtekind = RTE_SUBQUERY;
+	rte->subquery = sub;
+	rte->security_barrier = false;
+	/* Clear fields that should not be set in a subquery RTE */
+	rte->relid = InvalidOid;
+	rte->relkind = 0;
+	rte->rellockmode = 0;
+	rte->tablesample = NULL;
+	rte->inh = false;			/* must not be set for a subquery */
+
+	rte->requiredPerms = 0;		/* no permission check on subquery itself */
+	rte->checkAsUser = InvalidOid;
+	rte->selectedCols = NULL;
+	rte->insertedCols = NULL;
+	rte->updatedCols = NULL;
+	rte->extraUpdatedCols = NULL;
+	/* if base table has RLS, set security condition to enr*/
+	enr_rte = (RangeTblEntry *)linitial(sub->rtable);
+	/* rt_index is always 1, bacause subquery has enr_rte only */
+	enr_rte->securityQuals = get_securityQuals(relid, 1, sub);
+
+	return rte;
+}
+
+/*
+ * rewrite_query_for_distinct
+ *
+ * Rewrite query for counting DISTINCT clause.
+ */
+static Query *
+rewrite_query_for_distinct(Query *query, ParseState *pstate)
+{
+	TargetEntry *tle_count;
+	FuncCall *fn;
+	Node *node;
+
+	/* Add count(*) for counting distinct tuples in views */
+	fn = makeFuncCall(list_make1(makeString("count")), NIL, COERCE_EXPLICIT_CALL, -1);
+	fn->agg_star = true;
+	if (!query->groupClause && !query->hasAggs)
+		query->groupClause = transformDistinctClause(NULL, &query->targetList, query->sortClause, false);
+
+	node = ParseFuncOrColumn(pstate, fn->funcname, NIL, NULL, fn, false, -1);
+
+	tle_count = makeTargetEntry((Expr *) node,
+								list_length(query->targetList) + 1,
+								pstrdup("__ivm_count__"),
+								false);
+	query->targetList = lappend(query->targetList, tle_count);
+	query->hasAggs = true;
+
+	return query;
+}
+
+/*
+ * calc_delta
+ *
+ * Calculate view deltas generated under the modification of a table specified
+ * by the RTE index.
+ */
+static void
+calc_delta(MV_TriggerTable *table, int rte_index, Query *query,
+			DestReceiver *dest_old, DestReceiver *dest_new,
+			TupleDesc *tupdesc_old, TupleDesc *tupdesc_new,
+			QueryEnvironment *queryEnv)
+{
+	ListCell *lc = list_nth_cell(query->rtable, rte_index - 1);
+	RangeTblEntry *rte = (RangeTblEntry *) lfirst(lc);
+
+	/* Generate old delta */
+	if (list_length(table->old_rtes) > 0)
+	{
+		/* Replace the modified table with the old delta table and calculate the old view delta. */
+		lfirst(lc) = union_ENRs(rte, table->table_id, table->old_rtes, "old", queryEnv);
+		refresh_matview_datafill(dest_old, query, queryEnv, tupdesc_old, "");
+	}
+
+	/* Generate new delta */
+	if (list_length(table->new_rtes) > 0)
+	{
+		/* Replace the modified table with the new delta table and calculate the new view delta*/
+		lfirst(lc) = union_ENRs(rte, table->table_id, table->new_rtes, "new", queryEnv);
+		refresh_matview_datafill(dest_new, query, queryEnv, tupdesc_new, "");
+	}
+}
+
+/*
+ * rewrite_query_for_postupdate_state
+ *
+ * Rewrite the query so that the specified base table's RTEs will represent
+ * "post-update" state of tables. This is called after the view delta
+ * calculation due to changes on this table finishes.
+ */
+static Query*
+rewrite_query_for_postupdate_state(Query *query, MV_TriggerTable *table, int rte_index)
+{
+	ListCell *lc = list_nth_cell(query->rtable, rte_index - 1);
+
+	/* Retore the original RTE */
+	lfirst(lc) = table->original_rte;
+
+	return query;
+}
+
+/*
+ * apply_delta
+ *
+ * Apply deltas to the materialized view. In outer join cases, this requires
+ * the view maintenance graph.
+ */
+static void
+apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *new_tuplestores,
+			TupleDesc tupdesc_old, TupleDesc tupdesc_new,
+			Query *query, bool use_count, char *count_colname)
+{
+	StringInfoData querybuf;
+	StringInfoData target_list_buf;
+	Relation	matviewRel;
+	char	   *matviewname;
+	ListCell	*lc;
+	int			i;
+	List	   *keys = NIL;
+
+
+	/*
+	 * get names of the materialized view and delta tables
+	 */
+
+	matviewRel = table_open(matviewOid, NoLock);
+	matviewname = quote_qualified_identifier(get_namespace_name(RelationGetNamespace(matviewRel)),
+											 RelationGetRelationName(matviewRel));
+
+	/*
+	 * Build parts of the maintenance queries
+	 */
+
+	initStringInfo(&querybuf);
+	initStringInfo(&target_list_buf);
+
+	/* build string of target list */
+	for (i = 0; i < matviewRel->rd_att->natts; i++)
+	{
+		Form_pg_attribute attr = TupleDescAttr(matviewRel->rd_att, i);
+		char   *resname = NameStr(attr->attname);
+
+		if (i != 0)
+			appendStringInfo(&target_list_buf, ", ");
+		appendStringInfo(&target_list_buf, "%s", quote_qualified_identifier(NULL, resname));
+	}
+
+	i = 0;
+	foreach (lc, query->targetList)
+	{
+		TargetEntry *tle = (TargetEntry *) lfirst(lc);
+		Form_pg_attribute attr = TupleDescAttr(matviewRel->rd_att, i);
+
+		i++;
+
+		if (tle->resjunk)
+			continue;
+
+		keys = lappend(keys, attr);
+	}
+
+	/* Start maintaining the materialized view. */
+	OpenMatViewIncrementalMaintenance();
+
+	/* Open SPI context. */
+	if (SPI_connect() != SPI_OK_CONNECT)
+		elog(ERROR, "SPI_connect failed");
+
+	/* For tuple deletion */
+	if (old_tuplestores && tuplestore_tuple_count(old_tuplestores) > 0)
+	{
+		EphemeralNamedRelation enr = palloc(sizeof(EphemeralNamedRelationData));
+		int				rc;
+
+		/* convert tuplestores to ENR, and register for SPI */
+		enr->md.name = pstrdup(OLD_DELTA_ENRNAME);
+		enr->md.reliddesc = InvalidOid;
+		enr->md.tupdesc = tupdesc_old;
+		enr->md.enrtype = ENR_NAMED_TUPLESTORE;
+		enr->md.enrtuples = tuplestore_tuple_count(old_tuplestores);
+		enr->reldata = old_tuplestores;
+
+		rc = SPI_register_relation(enr);
+		if (rc != SPI_OK_REL_REGISTER)
+			elog(ERROR, "SPI_register failed");
+
+		if (use_count)
+			/* apply old delta and get rows to be recalculated */
+			apply_old_delta_with_count(matviewname, OLD_DELTA_ENRNAME,
+									   keys, count_colname);
+		else
+			apply_old_delta(matviewname, OLD_DELTA_ENRNAME, keys);
+
+	}
+	/* For tuple insertion */
+	if (new_tuplestores && tuplestore_tuple_count(new_tuplestores) > 0)
+	{
+		EphemeralNamedRelation enr = palloc(sizeof(EphemeralNamedRelationData));
+		int rc;
+
+		/* convert tuplestores to ENR, and register for SPI */
+		enr->md.name = pstrdup(NEW_DELTA_ENRNAME);
+		enr->md.reliddesc = InvalidOid;
+		enr->md.tupdesc = tupdesc_new;;
+		enr->md.enrtype = ENR_NAMED_TUPLESTORE;
+		enr->md.enrtuples = tuplestore_tuple_count(new_tuplestores);
+		enr->reldata = new_tuplestores;
+
+		rc = SPI_register_relation(enr);
+		if (rc != SPI_OK_REL_REGISTER)
+			elog(ERROR, "SPI_register failed");
+
+		/* apply new delta */
+		if (use_count)
+			apply_new_delta_with_count(matviewname, NEW_DELTA_ENRNAME,
+								keys, &target_list_buf, count_colname);
+		else
+			apply_new_delta(matviewname, NEW_DELTA_ENRNAME, &target_list_buf);
+	}
+
+	/* We're done maintaining the materialized view. */
+	CloseMatViewIncrementalMaintenance();
+
+	table_close(matviewRel, NoLock);
+
+	/* Close SPI context. */
+	if (SPI_finish() != SPI_OK_FINISH)
+		elog(ERROR, "SPI_finish failed");
+}
+
+/*
+ * apply_old_delta_with_count
+ *
+ * Execute a query for applying a delta table given by deltname_old
+ * which contains tuples to be deleted from to a materialized view given by
+ * matviewname.  This is used when counting is required, that is, the view
+ * has aggregate or distinct.
+ */
+static void
+apply_old_delta_with_count(const char *matviewname, const char *deltaname_old,
+				List *keys, const char *count_colname)
+{
+	StringInfoData	querybuf;
+	char   *match_cond;
+
+	/* build WHERE condition for searching tuples to be deleted */
+	match_cond = get_matching_condition_string(keys);
+
+	/* Search for matching tuples from the view and update or delete if found. */
+	initStringInfo(&querybuf);
+	appendStringInfo(&querybuf,
+					"WITH t AS ("			/* collecting tid of target tuples in the view */
+						"SELECT diff.%s, "			/* count column */
+								"(diff.%s OPERATOR(pg_catalog.=) mv.%s) AS for_dlt, "
+								"mv.ctid "
+						"FROM %s AS mv, %s AS diff "
+						"WHERE %s"					/* tuple matching condition */
+					"), updt AS ("			/* update a tuple if this is not to be deleted */
+						"UPDATE %s AS mv SET %s = mv.%s OPERATOR(pg_catalog.-) t.%s "
+						"FROM t WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND NOT for_dlt "
+					")"
+					/* delete a tuple if this is to be deleted */
+					"DELETE FROM %s AS mv USING t "
+					"WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt",
+					count_colname,
+					count_colname, count_colname,
+					matviewname, deltaname_old,
+					match_cond,
+					matviewname, count_colname, count_colname, count_colname,
+					matviewname);
+
+	if (SPI_exec(querybuf.data, 0) != SPI_OK_DELETE)
+		elog(ERROR, "SPI_exec failed: %s", querybuf.data);
+}
+
+/*
+ * apply_old_delta
+ *
+ * Execute a query for applying a delta table given by deltname_old
+ * which contains tuples to be deleted from to a materialized view given by
+ * matviewname.  This is used when counting is not required.
+ */
+static void
+apply_old_delta(const char *matviewname, const char *deltaname_old,
+				List *keys)
+{
+	StringInfoData	querybuf;
+	StringInfoData	keysbuf;
+	char   *match_cond;
+	ListCell *lc;
+
+	/* build WHERE condition for searching tuples to be deleted */
+	match_cond = get_matching_condition_string(keys);
+
+	/* build string of keys list */
+	initStringInfo(&keysbuf);
+	foreach (lc, keys)
+	{
+		Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc);
+		char   *resname = NameStr(attr->attname);
+		appendStringInfo(&keysbuf, "%s", quote_qualified_identifier("mv", resname));
+		if (lnext(keys, lc))
+			appendStringInfo(&keysbuf, ", ");
+	}
+
+	/* Search for matching tuples from the view and update or delete if found. */
+	initStringInfo(&querybuf);
+	appendStringInfo(&querybuf,
+	"DELETE FROM %s WHERE ctid IN ("
+		"SELECT tid FROM (SELECT row_number() over (partition by %s) AS \"__ivm_row_number__\","
+								  "mv.ctid AS tid,"
+								  "diff.\"__ivm_count__\""
+						 "FROM %s AS mv, %s AS diff "
+						 "WHERE %s) v "
+					"WHERE v.\"__ivm_row_number__\" OPERATOR(pg_catalog.<=) v.\"__ivm_count__\")",
+					matviewname,
+					keysbuf.data,
+					matviewname, deltaname_old,
+					match_cond);
+
+	if (SPI_exec(querybuf.data, 0) != SPI_OK_DELETE)
+		elog(ERROR, "SPI_exec failed: %s", querybuf.data);
+}
+
+/*
+ * apply_new_delta_with_count
+ *
+ * Execute a query for applying a delta table given by deltname_new
+ * which contains tuples to be inserted into a materialized view given by
+ * matviewname.  This is used when counting is required, that is, the view
+ * has aggregate or distinct. Also, when a table in EXISTS sub queries
+ * is modified.
+ */
+static void
+apply_new_delta_with_count(const char *matviewname, const char* deltaname_new,
+				List *keys, StringInfo target_list, const char* count_colname)
+{
+	StringInfoData	querybuf;
+	StringInfoData	returning_keys;
+	ListCell	*lc;
+	char	*match_cond = "";
+
+	/* build WHERE condition for searching tuples to be updated */
+	match_cond = get_matching_condition_string(keys);
+
+	/* build string of keys list */
+	initStringInfo(&returning_keys);
+	if (keys)
+	{
+		foreach (lc, keys)
+		{
+			Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc);
+			char   *resname = NameStr(attr->attname);
+			appendStringInfo(&returning_keys, "%s", quote_qualified_identifier("mv", resname));
+			if (lnext(keys, lc))
+				appendStringInfo(&returning_keys, ", ");
+		}
+	}
+	else
+		appendStringInfo(&returning_keys, "NULL");
+
+	/* Search for matching tuples from the view and update if found or insert if not. */
+	initStringInfo(&querybuf);
+	appendStringInfo(&querybuf,
+					"WITH updt AS ("		/* update a tuple if this exists in the view */
+						"UPDATE %s AS mv SET %s = mv.%s OPERATOR(pg_catalog.+) diff.%s "
+						"FROM %s AS diff "
+						"WHERE %s "					/* tuple matching condition */
+						"RETURNING %s"				/* returning keys of updated tuples */
+					") INSERT INTO %s (%s)"	/* insert a new tuple if this doesn't existw */
+						"SELECT %s FROM %s AS diff "
+						"WHERE NOT EXISTS (SELECT 1 FROM updt AS mv WHERE %s);",
+					matviewname, count_colname, count_colname, count_colname,
+					deltaname_new,
+					match_cond,
+					returning_keys.data,
+					matviewname, target_list->data,
+					target_list->data, deltaname_new,
+					match_cond);
+
+	if (SPI_exec(querybuf.data, 0) != SPI_OK_INSERT)
+		elog(ERROR, "SPI_exec failed: %s", querybuf.data);
+}
+
+/*
+ * apply_new_delta
+ *
+ * Execute a query for applying a delta table given by deltname_new
+ * which contains tuples to be inserted into a materialized view given by
+ * matviewname.  This is used when counting is not required.
+ */
+static void
+apply_new_delta(const char *matviewname, const char *deltaname_new,
+				StringInfo target_list)
+{
+	StringInfoData	querybuf;
+
+	/* Search for matching tuples from the view and update or delete if found. */
+	initStringInfo(&querybuf);
+	appendStringInfo(&querybuf,
+					"INSERT INTO %s (%s) SELECT %s FROM ("
+						"SELECT diff.*, generate_series(1, diff.\"__ivm_count__\") "
+						"FROM %s AS diff) AS v",
+					matviewname, target_list->data, target_list->data,
+					deltaname_new);
+
+	if (SPI_exec(querybuf.data, 0) != SPI_OK_INSERT)
+		elog(ERROR, "SPI_exec failed: %s", querybuf.data);
+}
+
+/*
+ * get_matching_condition_string
+ *
+ * Build a predicate string for looking for a tuple with given keys.
+ */
+static char *
+get_matching_condition_string(List *keys)
+{
+	StringInfoData match_cond;
+	ListCell	*lc;
+
+	/* If there is no key columns, the condition is always true. */
+	if (keys == NIL)
+		return "true";
+
+	initStringInfo(&match_cond);
+	foreach (lc, keys)
+	{
+		Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc);
+		char   *resname = NameStr(attr->attname);
+		char   *mv_resname = quote_qualified_identifier("mv", resname);
+		char   *diff_resname = quote_qualified_identifier("diff", resname);
+		Oid		typid = attr->atttypid;
+
+		/* Considering NULL values, we can not use simple = operator. */
+		appendStringInfo(&match_cond, "(");
+		generate_equal(&match_cond, typid, mv_resname, diff_resname);
+		appendStringInfo(&match_cond, " OR (%s IS NULL AND %s IS NULL))",
+						 mv_resname, diff_resname);
+
+		if (lnext(keys, lc))
+			appendStringInfo(&match_cond, " AND ");
+	}
+
+	return match_cond.data;
+}
+
+/*
+ * generate_equals
+ *
+ * Generate an equality clause using given operands' default equality
+ * operator.
+ */
+static void
+generate_equal(StringInfo querybuf, Oid opttype,
+			   const char *leftop, const char *rightop)
+{
+	TypeCacheEntry *typentry;
+
+	typentry = lookup_type_cache(opttype, TYPECACHE_EQ_OPR);
+	if (!OidIsValid(typentry->eq_opr))
+		ereport(ERROR,
+				(errcode(ERRCODE_UNDEFINED_FUNCTION),
+				 errmsg("could not identify an equality operator for type %s",
+						format_type_be(opttype))));
+
+	generate_operator_clause(querybuf,
+							 leftop, opttype,
+							 typentry->eq_opr,
+							 rightop, opttype);
+}
+
+/*
+ * mv_InitHashTables
+ */
+static void
+mv_InitHashTables(void)
+{
+	HASHCTL		ctl;
+
+	memset(&ctl, 0, sizeof(ctl));
+	ctl.keysize = sizeof(Oid);
+	ctl.entrysize = sizeof(MV_TriggerHashEntry);
+	mv_trigger_info = hash_create("MV trigger info",
+								 MV_INIT_QUERYHASHSIZE,
+								 &ctl, HASH_ELEM | HASH_BLOBS);
+}
+
+/*
+ * AtAbort_IVM
+ *
+ * Clean up hash entries for all materialized views. This is called at
+ * transaction abort.
+ */
+void
+AtAbort_IVM()
+{
+	HASH_SEQ_STATUS seq;
+	MV_TriggerHashEntry *entry;
+
+	if (mv_trigger_info)
+	{
+		hash_seq_init(&seq, mv_trigger_info);
+		while ((entry = hash_seq_search(&seq)) != NULL)
+			clean_up_IVM_hash_entry(entry);
+	}
+}
+
+/*
+ * clean_up_IVM_hash_entry
+ *
+ * Clean up tuple stores and hash entries for a materialized view after its
+ * maintenance finished.
+ */
+static void
+clean_up_IVM_hash_entry(MV_TriggerHashEntry *entry)
+{
+	bool found;
+	ListCell *lc;
+
+	foreach(lc, entry->tables)
+	{
+		MV_TriggerTable *table = (MV_TriggerTable *) lfirst(lc);
+
+		list_free(table->old_tuplestores);
+		list_free(table->new_tuplestores);
+	}
+	list_free(entry->tables);
+
+	hash_search(mv_trigger_info, (void *) &entry->matview_id, HASH_REMOVE, &found);
+}
+
+/*
+ * isIvmName
+ *
+ * Check if this is a IVM hidden column from the name.
+ */
+bool
+isIvmName(const char *s)
+{
+	if (s)
+		return (strncmp(s, "__ivm_", 6) == 0);
+	return false;
+}
+
+/*
+ * get_securityQuals
+ *
+ * Get row security policy on a relation.
+ * This is used by IVM for copying RLS from base table to enr.
+ */
+static List *
+get_securityQuals(Oid relId, int rt_index, Query *query)
+{
+	ParseState *pstate;
+	Relation rel;
+	ParseNamespaceItem *nsitem;
+	RangeTblEntry *rte;
+	List *securityQuals;
+	List *withCheckOptions;
+	bool  hasRowSecurity;
+	bool  hasSubLinks;
+
+	securityQuals = NIL;
+	pstate = make_parsestate(NULL);
+
+	rel = table_open(relId, NoLock);
+	nsitem = addRangeTableEntryForRelation(pstate, rel, AccessShareLock, NULL, false, false);
+	rte = nsitem->p_rte;
+
+	get_row_security_policies(query, rte, rt_index,
+							  &securityQuals, &withCheckOptions,
+							  &hasRowSecurity, &hasSubLinks);
+
+	/*
+	 * Make sure the query is marked correctly if row level security
+	 * applies, or if the new quals had sublinks.
+	 */
+	if (hasRowSecurity)
+		query->hasRowSecurity = true;
+	if (hasSubLinks)
+		query->hasSubLinks = true;
+
+	table_close(rel, NoLock);
+
+	return securityQuals;
+}
diff --git a/src/backend/commands/tablecmds.c b/src/backend/commands/tablecmds.c
index 2cd8546d47..1c85df888e 100644
--- a/src/backend/commands/tablecmds.c
+++ b/src/backend/commands/tablecmds.c
@@ -52,6 +52,7 @@
 #include "commands/cluster.h"
 #include "commands/comment.h"
 #include "commands/defrem.h"
+#include "commands/matview.h"
 #include "commands/event_trigger.h"
 #include "commands/policy.h"
 #include "commands/sequence.h"
@@ -3441,6 +3442,14 @@ renameatt_internal(Oid myrelid,
 	targetrelation = relation_open(myrelid, AccessExclusiveLock);
 	renameatt_check(myrelid, RelationGetForm(targetrelation), recursing);
 
+	/*
+	 * Don't rename IVM columns.
+	 */
+	if (RelationIsIVM(targetrelation) && isIvmName(oldattname))
+		ereport(ERROR,
+				(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+				 errmsg("IVM column can not be renamed")));
+
 	/*
 	 * if the 'recurse' flag is set then we are supposed to rename this
 	 * attribute in all classes that inherit from 'relname' (as well as in
diff --git a/src/backend/nodes/copyfuncs.c b/src/backend/nodes/copyfuncs.c
index 0490bce664..4afc8f5826 100644
--- a/src/backend/nodes/copyfuncs.c
+++ b/src/backend/nodes/copyfuncs.c
@@ -2949,6 +2949,7 @@ _copyRangeTblEntry(const RangeTblEntry *from)
 	COPY_SCALAR_FIELD(relkind);
 	COPY_SCALAR_FIELD(rellockmode);
 	COPY_NODE_FIELD(tablesample);
+	COPY_SCALAR_FIELD(relisivm);
 	COPY_NODE_FIELD(subquery);
 	COPY_SCALAR_FIELD(security_barrier);
 	COPY_SCALAR_FIELD(jointype);
diff --git a/src/backend/nodes/equalfuncs.c b/src/backend/nodes/equalfuncs.c
index 55f41263ee..08d7805b7c 100644
--- a/src/backend/nodes/equalfuncs.c
+++ b/src/backend/nodes/equalfuncs.c
@@ -3131,6 +3131,7 @@ _equalRangeTblEntry(const RangeTblEntry *a, const RangeTblEntry *b)
 	COMPARE_SCALAR_FIELD(relkind);
 	COMPARE_SCALAR_FIELD(rellockmode);
 	COMPARE_NODE_FIELD(tablesample);
+	COMPARE_SCALAR_FIELD(relisivm);
 	COMPARE_NODE_FIELD(subquery);
 	COMPARE_SCALAR_FIELD(security_barrier);
 	COMPARE_SCALAR_FIELD(jointype);
diff --git a/src/backend/nodes/outfuncs.c b/src/backend/nodes/outfuncs.c
index cfd3ce68b4..e5a9467e99 100644
--- a/src/backend/nodes/outfuncs.c
+++ b/src/backend/nodes/outfuncs.c
@@ -3436,6 +3436,7 @@ _outRangeTblEntry(StringInfo str, const RangeTblEntry *node)
 			WRITE_CHAR_FIELD(relkind);
 			WRITE_INT_FIELD(rellockmode);
 			WRITE_NODE_FIELD(tablesample);
+			WRITE_BOOL_FIELD(relisivm);
 			break;
 		case RTE_SUBQUERY:
 			WRITE_NODE_FIELD(subquery);
diff --git a/src/backend/nodes/readfuncs.c b/src/backend/nodes/readfuncs.c
index 5165fb3b93..50cc852c32 100644
--- a/src/backend/nodes/readfuncs.c
+++ b/src/backend/nodes/readfuncs.c
@@ -1669,6 +1669,7 @@ _readRangeTblEntry(void)
 			READ_CHAR_FIELD(relkind);
 			READ_INT_FIELD(rellockmode);
 			READ_NODE_FIELD(tablesample);
+			READ_BOOL_FIELD(relisivm);
 			break;
 		case RTE_SUBQUERY:
 			READ_NODE_FIELD(subquery);
diff --git a/src/backend/parser/parse_relation.c b/src/backend/parser/parse_relation.c
index 5448cb01fa..b08c742678 100644
--- a/src/backend/parser/parse_relation.c
+++ b/src/backend/parser/parse_relation.c
@@ -36,6 +36,7 @@
 #include "utils/rel.h"
 #include "utils/syscache.h"
 #include "utils/varlena.h"
+#include "commands/matview.h"
 
 
 /*
@@ -79,7 +80,7 @@ static void expandTupleDesc(TupleDesc tupdesc, Alias *eref,
 							int count, int offset,
 							int rtindex, int sublevels_up,
 							int location, bool include_dropped,
-							List **colnames, List **colvars);
+							List **colnames, List **colvars, bool is_ivm);
 static int	specialAttNum(const char *attname);
 static bool isQueryUsingTempRelation_walker(Node *node, void *context);
 
@@ -1444,6 +1445,7 @@ addRangeTableEntry(ParseState *pstate,
 	rte->relid = RelationGetRelid(rel);
 	rte->relkind = rel->rd_rel->relkind;
 	rte->rellockmode = lockmode;
+	rte->relisivm = rel->rd_rel->relisivm;
 
 	/*
 	 * Build the list of effective column names using user-supplied aliases
@@ -1532,6 +1534,7 @@ addRangeTableEntryForRelation(ParseState *pstate,
 	rte->relid = RelationGetRelid(rel);
 	rte->relkind = rel->rd_rel->relkind;
 	rte->rellockmode = lockmode;
+	rte->relisivm = rel->rd_rel->relisivm;
 
 	/*
 	 * Build the list of effective column names using user-supplied aliases
@@ -2688,7 +2691,7 @@ expandRTE(RangeTblEntry *rte, int rtindex, int sublevels_up,
 						expandTupleDesc(tupdesc, rte->eref,
 										rtfunc->funccolcount, atts_done,
 										rtindex, sublevels_up, location,
-										include_dropped, colnames, colvars);
+										include_dropped, colnames, colvars, false);
 					}
 					else if (functypclass == TYPEFUNC_SCALAR)
 					{
@@ -2956,7 +2959,7 @@ expandRelation(Oid relid, Alias *eref, int rtindex, int sublevels_up,
 	expandTupleDesc(rel->rd_att, eref, rel->rd_att->natts, 0,
 					rtindex, sublevels_up,
 					location, include_dropped,
-					colnames, colvars);
+					colnames, colvars, RelationIsIVM(rel));
 	relation_close(rel, AccessShareLock);
 }
 
@@ -2973,7 +2976,7 @@ static void
 expandTupleDesc(TupleDesc tupdesc, Alias *eref, int count, int offset,
 				int rtindex, int sublevels_up,
 				int location, bool include_dropped,
-				List **colnames, List **colvars)
+				List **colnames, List **colvars, bool is_ivm)
 {
 	ListCell   *aliascell;
 	int			varattno;
@@ -2986,6 +2989,9 @@ expandTupleDesc(TupleDesc tupdesc, Alias *eref, int count, int offset,
 	{
 		Form_pg_attribute attr = TupleDescAttr(tupdesc, varattno);
 
+		if (is_ivm && isIvmName(NameStr(attr->attname)) && !MatViewIncrementalMaintenanceIsEnabled())
+			continue;
+
 		if (attr->attisdropped)
 		{
 			if (include_dropped)
@@ -3140,6 +3146,10 @@ expandNSItemAttrs(ParseState *pstate, ParseNamespaceItem *nsitem,
 		Var		   *varnode = (Var *) lfirst(var);
 		TargetEntry *te;
 
+		/* if transform * into columnlist with IMMV, remove IVM columns */
+		if (rte->relisivm && isIvmName(label) && !MatViewIncrementalMaintenanceIsEnabled())
+			continue;
+
 		te = makeTargetEntry((Expr *) varnode,
 							 (AttrNumber) pstate->p_next_resno++,
 							 label,
diff --git a/src/backend/rewrite/rewriteDefine.c b/src/backend/rewrite/rewriteDefine.c
index 185bf5fbff..d8a8b66196 100644
--- a/src/backend/rewrite/rewriteDefine.c
+++ b/src/backend/rewrite/rewriteDefine.c
@@ -776,7 +776,8 @@ checkRuleResultList(List *targetList, TupleDesc resultDesc, bool isSelect,
 														attr->atttypmod))));
 	}
 
-	if (i != resultDesc->natts)
+	/* No check for materialized views since this could have special columns for IVM */
+	if ((!isSelect || requireColumnNameMatch) && i != resultDesc->natts)
 		ereport(ERROR,
 				(errcode(ERRCODE_INVALID_OBJECT_DEFINITION),
 				 isSelect ?
diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat
index 6d378ff785..7d88a84682 100644
--- a/src/include/catalog/pg_proc.dat
+++ b/src/include/catalog/pg_proc.dat
@@ -11882,4 +11882,12 @@
   prorettype => 'bytea', proargtypes => 'pg_brin_minmax_multi_summary',
   prosrc => 'brin_minmax_multi_summary_send' },
 
+# IVM
+{ oid => '786', descr => 'ivm trigger (before)',
+  proname => 'IVM_immediate_before', provolatile => 'v', prorettype => 'trigger',
+  proargtypes => '', prosrc => 'IVM_immediate_before' },
+{ oid => '787', descr => 'ivm trigger (after)',
+  proname => 'IVM_immediate_maintenance', provolatile => 'v', prorettype => 'trigger',
+  proargtypes => '', prosrc => 'IVM_immediate_maintenance' },
+
 ]
diff --git a/src/include/commands/createas.h b/src/include/commands/createas.h
index 54a38491fb..c369b3ba5e 100644
--- a/src/include/commands/createas.h
+++ b/src/include/commands/createas.h
@@ -16,6 +16,7 @@
 
 #include "catalog/objectaddress.h"
 #include "nodes/params.h"
+#include "nodes/pathnodes.h"
 #include "parser/parse_node.h"
 #include "tcop/dest.h"
 #include "utils/queryenvironment.h"
@@ -25,6 +26,11 @@ extern ObjectAddress ExecCreateTableAs(ParseState *pstate, CreateTableAsStmt *st
 									   ParamListInfo params, QueryEnvironment *queryEnv,
 									   QueryCompletion *qc);
 
+extern void CreateIvmTriggersOnBaseTables(Query *qry, Oid matviewOid, bool is_create);
+extern void CreateIndexOnIMMV(Query *query, Relation matviewRel, bool is_create);
+
+extern Query *rewriteQueryForIMMV(Query *query, List *colNames);
+
 extern int	GetIntoRelEFlags(IntoClause *intoClause);
 
 extern DestReceiver *CreateIntoRelDestReceiver(IntoClause *intoClause);
diff --git a/src/include/commands/matview.h b/src/include/commands/matview.h
index a067da39d2..ec479db513 100644
--- a/src/include/commands/matview.h
+++ b/src/include/commands/matview.h
@@ -15,6 +15,7 @@
 #define MATVIEW_H
 
 #include "catalog/objectaddress.h"
+#include "fmgr.h"
 #include "nodes/params.h"
 #include "nodes/parsenodes.h"
 #include "tcop/dest.h"
@@ -23,6 +24,8 @@
 
 extern void SetMatViewPopulatedState(Relation relation, bool newstate);
 
+extern void SetMatViewIVMState(Relation relation, bool newstate);
+
 extern ObjectAddress ExecRefreshMatView(RefreshMatViewStmt *stmt, const char *queryString,
 										ParamListInfo params, QueryCompletion *qc);
 
@@ -30,4 +33,9 @@ extern DestReceiver *CreateTransientRelDestReceiver(Oid oid);
 
 extern bool MatViewIncrementalMaintenanceIsEnabled(void);
 
+extern Datum IVM_immediate_before(PG_FUNCTION_ARGS);
+extern Datum IVM_immediate_maintenance(PG_FUNCTION_ARGS);
+extern void AtAbort_IVM(void);
+extern bool isIvmName(const char *s);
+
 #endif							/* MATVIEW_H */
diff --git a/src/include/nodes/parsenodes.h b/src/include/nodes/parsenodes.h
index da02658c81..d1a754936b 100644
--- a/src/include/nodes/parsenodes.h
+++ b/src/include/nodes/parsenodes.h
@@ -1042,6 +1042,7 @@ typedef struct RangeTblEntry
 	char		relkind;		/* relation kind (see pg_class.relkind) */
 	int			rellockmode;	/* lock level that query requires on the rel */
 	struct TableSampleClause *tablesample;	/* sampling info, or NULL */
+	bool		relisivm;
 
 	/*
 	 * Fields valid for a subquery RTE (else NULL):
@@ -2545,6 +2546,7 @@ typedef struct CreateStmt
 	char	   *tablespacename; /* table space to use, or NULL */
 	char	   *accessMethod;	/* table access method */
 	bool		if_not_exists;	/* just do nothing if it already exists? */
+	bool		ivm;			/* incremental view maintenance is used by materialized view */
 } CreateStmt;
 
 /* ----------
-- 
2.17.1


--Multipart=_Fri__22_Apr_2022_11_29_39_+0900_ZOAC7UMt5e8j1Nvx
Content-Type: text/x-diff;
 name="v27-0007-Add-aggregates-support-in-IVM.patch"
Content-Disposition: attachment;
 filename="v27-0007-Add-aggregates-support-in-IVM.patch"
Content-Transfer-Encoding: quoted-printable



^ permalink  raw  reply  [nested|flat] 101+ messages in thread

* [PATCH v27 6/9] Add Incremental View Maintenance support
@ 2022-04-21 02:58  Yugo Nagata <[email protected]>
  0 siblings, 0 replies; 101+ messages in thread

From: Yugo Nagata @ 2022-04-21 02:58 UTC (permalink / raw)

In this implementation, AFTER triggers are used to collect
tuplestores containing transition table contents. When multiple tables
are changed, multiple AFTER triggers are invoked, then the final AFTER
trigger performs actual update of the matview. In addition, BEFORE
triggers are also used to handle global information for view
maintenance. To calculate view deltas, we need both pre-state and
post-state of base tables. Post-update states are available in AFTER
trigger, and pre-update states can be calculated by filtering inserted
tuples using cmin/xmin system columns, and append deleted tuples which
are contained in an old transition table.

This patch also allows self-join, simultaneous updates of more than
one base table, and multiple updates of the same base table.

Incrementally Maintainable Materialized Views (IMMV) can contain
duplicated tuples. Also, DISTINCT clause is supported. When IMMV is
created with DISTINCT, multiplicity of tuples is counted and stored
in  "__ivm_count__" column, which is a hidden column of IMMV.
The value in __ivm_count__ is updated when IMMV is maintained
incrementally. A tuple in IMMV can be removed if and only if the
count becomes zero.
---
 src/backend/access/transam/xact.c   |    5 +
 src/backend/commands/createas.c     |  751 +++++++++++++
 src/backend/commands/indexcmds.c    |   40 +
 src/backend/commands/matview.c      | 1577 ++++++++++++++++++++++++++-
 src/backend/commands/tablecmds.c    |    9 +
 src/backend/nodes/copyfuncs.c       |    1 +
 src/backend/nodes/equalfuncs.c      |    1 +
 src/backend/nodes/outfuncs.c        |    1 +
 src/backend/nodes/readfuncs.c       |    1 +
 src/backend/parser/parse_relation.c |   18 +-
 src/backend/rewrite/rewriteDefine.c |    3 +-
 src/include/catalog/pg_proc.dat     |    8 +
 src/include/commands/createas.h     |    6 +
 src/include/commands/matview.h      |    8 +
 src/include/nodes/parsenodes.h      |    2 +
 15 files changed, 2391 insertions(+), 40 deletions(-)

diff --git a/src/backend/access/transam/xact.c b/src/backend/access/transam/xact.c
index 53f3e7fd1a..0377f5a88b 100644
--- a/src/backend/access/transam/xact.c
+++ b/src/backend/access/transam/xact.c
@@ -36,6 +36,7 @@
 #include "catalog/pg_enum.h"
 #include "catalog/storage.h"
 #include "commands/async.h"
+#include "commands/matview.h"
 #include "commands/tablecmds.h"
 #include "commands/trigger.h"
 #include "common/pg_prng.h"
@@ -2792,6 +2793,7 @@ AbortTransaction(void)
 	AtAbort_Notify();
 	AtEOXact_RelationMap(false, is_parallel_worker);
 	AtAbort_Twophase();
+	AtAbort_IVM();
 
 	/*
 	 * Advertise the fact that we aborted in pg_xact (assuming that we got as
@@ -5032,6 +5034,9 @@ AbortSubTransaction(void)
 	AbortBufferIO();
 	UnlockBuffers();
 
+	/* Clean up hash entries for incremental view maintenance */
+	AtAbort_IVM();
+
 	/* Reset WAL record construction state */
 	XLogResetInsertion();
 
diff --git a/src/backend/commands/createas.c b/src/backend/commands/createas.c
index 9abbb6b555..1224a3b075 100644
--- a/src/backend/commands/createas.c
+++ b/src/backend/commands/createas.c
@@ -32,24 +32,41 @@
 #include "access/xact.h"
 #include "access/xlog.h"
 #include "catalog/namespace.h"
+#include "catalog/index.h"
+#include "catalog/pg_constraint.h"
+#include "catalog/pg_inherits.h"
+#include "catalog/pg_trigger.h"
+#include "catalog/pg_type.h"
 #include "catalog/toasting.h"
 #include "commands/createas.h"
+#include "commands/defrem.h"
 #include "commands/matview.h"
 #include "commands/prepare.h"
 #include "commands/tablecmds.h"
+#include "commands/tablespace.h"
+#include "commands/trigger.h"
 #include "commands/view.h"
 #include "miscadmin.h"
+#include "optimizer/clauses.h"
+#include "optimizer/optimizer.h"
 #include "nodes/makefuncs.h"
 #include "nodes/nodeFuncs.h"
+#include "parser/parser.h"
+#include "parser/parsetree.h"
 #include "parser/parse_clause.h"
+#include "parser/parse_func.h"
+#include "parser/parse_type.h"
 #include "rewrite/rewriteHandler.h"
+#include "rewrite/rewriteManip.h"
 #include "storage/smgr.h"
 #include "tcop/tcopprot.h"
 #include "utils/builtins.h"
+#include "utils/fmgroids.h"
 #include "utils/lsyscache.h"
 #include "utils/rel.h"
 #include "utils/rls.h"
 #include "utils/snapmgr.h"
+#include "utils/syscache.h"
 
 typedef struct
 {
@@ -73,6 +90,13 @@ static bool intorel_receive(TupleTableSlot *slot, DestReceiver *self);
 static void intorel_shutdown(DestReceiver *self);
 static void intorel_destroy(DestReceiver *self);
 
+static void CreateIvmTriggersOnBaseTablesRecurse(Query *qry, Node *node, Oid matviewOid,
+									 Relids *relids, bool ex_lock);
+static void CreateIvmTrigger(Oid relOid, Oid viewOid, int16 type, int16 timing, bool ex_lock);
+static void check_ivm_restriction(Node *node);
+static bool check_ivm_restriction_walker(Node *node, void *context);
+static Bitmapset *get_primary_key_attnos_from_query(Query *qry, List **constraintList, bool is_create);
+static Bitmapset *get_primary_key_attnos_from_query(Query *query, List **constraintList, bool is_create);
 
 /*
  * create_ctas_internal
@@ -108,6 +132,8 @@ create_ctas_internal(List *attrList, IntoClause *into)
 	create->oncommit = into->onCommit;
 	create->tablespacename = into->tableSpaceName;
 	create->if_not_exists = false;
+	/* Using Materialized view only */
+	create->ivm = into->ivm;
 	create->accessMethod = into->accessMethod;
 
 	/*
@@ -282,6 +308,21 @@ ExecCreateTableAs(ParseState *pstate, CreateTableAsStmt *stmt,
 		save_nestlevel = NewGUCNestLevel();
 	}
 
+	if (is_matview && into->ivm)
+	{
+		/* check if the query is supported in IMMV definition */
+		if (contain_mutable_functions((Node *) query))
+			ereport(ERROR,
+					(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+					 errmsg("mutable function is not supported on incrementally maintainable materialized view"),
+					 errhint("functions must be marked IMMUTABLE")));
+
+		check_ivm_restriction((Node *) query);
+
+		/* For IMMV, we need to rewrite matview query */
+		query = rewriteQueryForIMMV(query, into->colNames);
+	}
+
 	if (into->skipData)
 	{
 		/*
@@ -358,11 +399,74 @@ ExecCreateTableAs(ParseState *pstate, CreateTableAsStmt *stmt,
 
 		/* Restore userid and security context */
 		SetUserIdAndSecContext(save_userid, save_sec_context);
+
+		if (into->ivm)
+		{
+			Oid matviewOid = address.objectId;
+			Relation matviewRel = table_open(matviewOid, NoLock);
+
+			/*
+			 * Mark relisivm field, if it's a matview and into->ivm is true.
+			 */
+			SetMatViewIVMState(matviewRel, true);
+
+			if (!into->skipData)
+			{
+				/* Create an index on incremental maintainable materialized view, if possible */
+				CreateIndexOnIMMV((Query *) into->viewQuery, matviewRel, true);
+
+				/* Create triggers on incremental maintainable materialized view */
+				CreateIvmTriggersOnBaseTables((Query *) into->viewQuery, matviewOid, true);
+			}
+			table_close(matviewRel, NoLock);
+		}
 	}
 
 	return address;
 }
 
+/*
+ * rewriteQueryForIMMV -- rewrite view definition query for IMMV
+ *
+ * count(*) is added for counting distinct tuples in views.
+ */
+Query *
+rewriteQueryForIMMV(Query *query, List *colNames)
+{
+	Query *rewritten;
+
+	TargetEntry *tle;
+	Node *node;
+	ParseState *pstate = make_parsestate(NULL);
+	FuncCall *fn;
+
+	rewritten = copyObject(query);
+	pstate->p_expr_kind = EXPR_KIND_SELECT_TARGET;
+
+	/*
+	 * Convert DISTINCT to GROUP BY and add count(*) for counting distinct
+	 * tuples in views.
+	 */
+	if (rewritten->distinctClause)
+	{
+		rewritten->groupClause = transformDistinctClause(NULL, &rewritten->targetList, rewritten->sortClause, false);
+
+		fn = makeFuncCall(list_make1(makeString("count")), NIL, COERCE_EXPLICIT_CALL, -1);
+		fn->agg_star = true;
+
+		node = ParseFuncOrColumn(pstate, fn->funcname, NIL, NULL, fn, false, -1);
+
+		tle = makeTargetEntry((Expr *) node,
+								list_length(rewritten->targetList) + 1,
+								pstrdup("__ivm_count__"),
+								false);
+		rewritten->targetList = lappend(rewritten->targetList, tle);
+		rewritten->hasAggs = true;
+	}
+
+	return rewritten;
+}
+
 /*
  * GetIntoRelEFlags --- compute executor flags needed for CREATE TABLE AS
  *
@@ -623,3 +727,650 @@ intorel_destroy(DestReceiver *self)
 {
 	pfree(self);
 }
+
+/*
+ * CreateIvmTriggersOnBaseTables -- create IVM triggers on all base tables
+ */
+void
+CreateIvmTriggersOnBaseTables(Query *qry, Oid matviewOid, bool is_create)
+{
+	Relids	relids = NULL;
+	bool	ex_lock = false;
+	Index	first_rtindex = is_create ? 1 : PRS2_NEW_VARNO + 1;
+	RangeTblEntry *rte;
+
+	/* Immediately return if we don't have any base tables. */
+	if (list_length(qry->rtable) < first_rtindex)
+		return;
+
+	/*
+	 * If the view has more than one base tables, we need an exclusive lock
+	 * on the view so that the view would be maintained serially to avoid
+	 * the inconsistency that occurs when two base tables are modified in
+	 * concurrent transactions. However, if the view has only one table,
+	 * we can use a weaker lock.
+	 *
+	 * The type of lock should be determined here, because if we check the
+	 * view definition at maintenance time, we need to acquire a weaker lock,
+	 * and upgrading the lock level after this increases probability of
+	 * deadlock.
+	 */
+
+	rte = list_nth(qry->rtable, first_rtindex - 1);
+	if (list_length(qry->rtable) > first_rtindex ||
+		rte->rtekind != RTE_RELATION)
+		ex_lock = true;
+
+	CreateIvmTriggersOnBaseTablesRecurse(qry, (Node *)qry, matviewOid, &relids, ex_lock);
+
+	bms_free(relids);
+}
+
+static void
+CreateIvmTriggersOnBaseTablesRecurse(Query *qry, Node *node, Oid matviewOid,
+									 Relids *relids, bool ex_lock)
+{
+	if (node == NULL)
+		return;
+
+	/* This can recurse, so check for excessive recursion */
+	check_stack_depth();
+
+	switch (nodeTag(node))
+	{
+		case T_Query:
+			{
+				Query *query = (Query *) node;
+
+				CreateIvmTriggersOnBaseTablesRecurse(qry, (Node *)query->jointree, matviewOid, relids, ex_lock);
+			}
+			break;
+
+		case T_RangeTblRef:
+			{
+				int			rti = ((RangeTblRef *) node)->rtindex;
+				RangeTblEntry *rte = rt_fetch(rti, qry->rtable);
+
+				if (rte->rtekind == RTE_RELATION && !bms_is_member(rte->relid, *relids))
+				{
+					CreateIvmTrigger(rte->relid, matviewOid, TRIGGER_TYPE_INSERT, TRIGGER_TYPE_BEFORE, ex_lock);
+					CreateIvmTrigger(rte->relid, matviewOid, TRIGGER_TYPE_DELETE, TRIGGER_TYPE_BEFORE, ex_lock);
+					CreateIvmTrigger(rte->relid, matviewOid, TRIGGER_TYPE_UPDATE, TRIGGER_TYPE_BEFORE, ex_lock);
+					CreateIvmTrigger(rte->relid, matviewOid, TRIGGER_TYPE_INSERT, TRIGGER_TYPE_AFTER, ex_lock);
+					CreateIvmTrigger(rte->relid, matviewOid, TRIGGER_TYPE_DELETE, TRIGGER_TYPE_AFTER, ex_lock);
+					CreateIvmTrigger(rte->relid, matviewOid, TRIGGER_TYPE_UPDATE, TRIGGER_TYPE_AFTER, ex_lock);
+
+					*relids = bms_add_member(*relids, rte->relid);
+				}
+			}
+			break;
+
+		case T_FromExpr:
+			{
+				FromExpr   *f = (FromExpr *) node;
+				ListCell   *l;
+
+				foreach(l, f->fromlist)
+					CreateIvmTriggersOnBaseTablesRecurse(qry, lfirst(l), matviewOid, relids, ex_lock);
+			}
+			break;
+
+		case T_JoinExpr:
+			{
+				JoinExpr   *j = (JoinExpr *) node;
+
+				CreateIvmTriggersOnBaseTablesRecurse(qry, j->larg, matviewOid, relids, ex_lock);
+				CreateIvmTriggersOnBaseTablesRecurse(qry, j->rarg, matviewOid, relids, ex_lock);
+			}
+			break;
+
+		default:
+			elog(ERROR, "unrecognized node type: %d", (int) nodeTag(node));
+	}
+}
+
+/*
+ * CreateIvmTrigger -- create IVM trigger on a base table
+ */
+static void
+CreateIvmTrigger(Oid relOid, Oid viewOid, int16 type, int16 timing, bool ex_lock)
+{
+	ObjectAddress	refaddr;
+	ObjectAddress	address;
+	CreateTrigStmt *ivm_trigger;
+	List *transitionRels = NIL;
+
+	Assert(timing == TRIGGER_TYPE_BEFORE || timing == TRIGGER_TYPE_AFTER);
+
+	refaddr.classId = RelationRelationId;
+	refaddr.objectId = viewOid;
+	refaddr.objectSubId = 0;
+
+	ivm_trigger = makeNode(CreateTrigStmt);
+	ivm_trigger->relation = NULL;
+	ivm_trigger->row = false;
+
+	ivm_trigger->timing = timing;
+	ivm_trigger->events = type;
+
+	switch (type)
+	{
+		case TRIGGER_TYPE_INSERT:
+			ivm_trigger->trigname = (timing == TRIGGER_TYPE_BEFORE ? "IVM_trigger_ins_before" : "IVM_trigger_ins_after");
+			break;
+		case TRIGGER_TYPE_DELETE:
+			ivm_trigger->trigname = (timing == TRIGGER_TYPE_BEFORE ? "IVM_trigger_del_before" : "IVM_trigger_del_after");
+			break;
+		case TRIGGER_TYPE_UPDATE:
+			ivm_trigger->trigname = (timing == TRIGGER_TYPE_BEFORE ? "IVM_trigger_upd_before" : "IVM_trigger_upd_after");
+			break;
+		default:
+			elog(ERROR, "unsupported trigger type");
+	}
+
+	if (timing == TRIGGER_TYPE_AFTER)
+	{
+		if (type == TRIGGER_TYPE_INSERT || type == TRIGGER_TYPE_UPDATE)
+		{
+			TriggerTransition *n = makeNode(TriggerTransition);
+			n->name = "__ivm_newtable";
+			n->isNew = true;
+			n->isTable = true;
+
+			transitionRels = lappend(transitionRels, n);
+		}
+		if (type == TRIGGER_TYPE_DELETE || type == TRIGGER_TYPE_UPDATE)
+		{
+			TriggerTransition *n = makeNode(TriggerTransition);
+			n->name = "__ivm_oldtable";
+			n->isNew = false;
+			n->isTable = true;
+
+			transitionRels = lappend(transitionRels, n);
+		}
+	}
+
+	ivm_trigger->funcname =
+		(timing == TRIGGER_TYPE_BEFORE ? SystemFuncName("IVM_immediate_before") : SystemFuncName("IVM_immediate_maintenance"));
+
+	ivm_trigger->columns = NIL;
+	ivm_trigger->transitionRels = transitionRels;
+	ivm_trigger->whenClause = NULL;
+	ivm_trigger->isconstraint = false;
+	ivm_trigger->deferrable = false;
+	ivm_trigger->initdeferred = false;
+	ivm_trigger->constrrel = NULL;
+	ivm_trigger->args = list_make2(
+		makeString(DatumGetPointer(DirectFunctionCall1(oidout, ObjectIdGetDatum(viewOid)))),
+		makeString(DatumGetPointer(DirectFunctionCall1(boolout, BoolGetDatum(ex_lock))))
+		);
+
+	address = CreateTrigger(ivm_trigger, NULL, relOid, InvalidOid, InvalidOid,
+						 InvalidOid, InvalidOid, InvalidOid, NULL, true, false);
+
+	recordDependencyOn(&address, &refaddr, DEPENDENCY_AUTO);
+
+	/* Make changes-so-far visible */
+	CommandCounterIncrement();
+}
+
+/*
+ * check_ivm_restriction --- look for specify nodes in the query tree
+ */
+static void
+check_ivm_restriction(Node *node)
+{
+	check_ivm_restriction_walker(node, NULL);
+}
+
+static bool
+check_ivm_restriction_walker(Node *node, void *context)
+{
+	if (node == NULL)
+		return false;
+
+	/*
+	 * We currently don't support Sub-Query.
+	 */
+	if (IsA(node, SubPlan) || IsA(node, SubLink))
+		ereport(ERROR,
+				(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+				 errmsg("subquery is not supported on incrementally maintainable materialized view")));
+
+	/* This can recurse, so check for excessive recursion */
+	check_stack_depth();
+
+	switch (nodeTag(node))
+	{
+		case T_Query:
+			{
+				Query *qry = (Query *)node;
+				ListCell   *lc;
+				List       *vars;
+
+				/* if contained CTE, return error */
+				if (qry->cteList != NIL)
+					ereport(ERROR,
+							(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+							 errmsg("CTE is not supported on incrementally maintainable materialized view")));
+				if (qry->havingQual != NULL)
+					ereport(ERROR,
+							(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+							 errmsg(" HAVING clause is not supported on incrementally maintainable materialized view")));
+				if (qry->sortClause != NIL)	/* There is a possibility that we don't need to return an error */
+					ereport(ERROR,
+							(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+							 errmsg("ORDER BY clause is not supported on incrementally maintainable materialized view")));
+				if (qry->limitOffset != NULL || qry->limitCount != NULL)
+					ereport(ERROR,
+							(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+							 errmsg("LIMIT/OFFSET clause is not supported on incrementally maintainable materialized view")));
+				if (qry->hasDistinctOn)
+					ereport(ERROR,
+							(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+							 errmsg("DISTINCT ON is not supported on incrementally maintainable materialized view")));
+				if (qry->hasWindowFuncs)
+					ereport(ERROR,
+							(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+							 errmsg("window functions are not supported on incrementally maintainable materialized view")));
+				if (qry->groupingSets != NIL)
+					ereport(ERROR,
+							(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+							 errmsg("GROUPING SETS, ROLLUP, or CUBE clauses is not supported on incrementally maintainable materialized view")));
+				if (qry->setOperations != NULL)
+					ereport(ERROR,
+							(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+							 errmsg("UNION/INTERSECT/EXCEPT statements are not supported on incrementally maintainable materialized view")));
+				if (list_length(qry->targetList) == 0)
+					ereport(ERROR,
+							(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+							 errmsg("empty target list is not supported on incrementally maintainable materialized view")));
+				if (qry->rowMarks != NIL)
+					ereport(ERROR,
+							(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+							 errmsg("FOR UPDATE/SHARE clause is not supported on incrementally maintainable materialized view")));
+
+				/* system column restrictions */
+				vars = pull_vars_of_level((Node *) qry, 0);
+				foreach(lc, vars)
+				{
+					if (IsA(lfirst(lc), Var))
+					{
+						Var *var = (Var *) lfirst(lc);
+						/* if system column, return error */
+						if (var->varattno < 0)
+							ereport(ERROR,
+									(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+									 errmsg("system column is not supported on incrementally maintainable materialized view")));
+					}
+				}
+
+				/* restrictions for rtable */
+				foreach(lc, qry->rtable)
+				{
+					RangeTblEntry *rte = (RangeTblEntry *) lfirst(lc);
+
+					if (rte->subquery)
+						ereport(ERROR,
+								(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+								 errmsg("subquery is not supported on incrementally maintainable materialized view")));
+
+					if (rte->tablesample != NULL)
+						ereport(ERROR,
+								(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+								 errmsg("TABLESAMPLE clause is not supported on incrementally maintainable materialized view")));
+
+					if (rte->relkind == RELKIND_PARTITIONED_TABLE)
+						ereport(ERROR,
+								(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+								 errmsg("partitioned table is not supported on incrementally maintainable materialized view")));
+
+					if (rte->relkind == RELKIND_RELATION && has_superclass(rte->relid))
+						ereport(ERROR,
+								(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+								 errmsg("partitions is not supported on incrementally maintainable materialized view")));
+
+					if (rte->relkind == RELKIND_RELATION && find_inheritance_children(rte->relid, NoLock) != NIL)
+						ereport(ERROR,
+								(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+								 errmsg("inheritance parent is not supported on incrementally maintainable materialized view")));
+
+					if (rte->relkind == RELKIND_FOREIGN_TABLE)
+						ereport(ERROR,
+								(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+								 errmsg("foreign table is not supported on incrementally maintainable materialized view")));
+
+					if (rte->relkind == RELKIND_VIEW ||
+						rte->relkind == RELKIND_MATVIEW)
+						ereport(ERROR,
+								(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+								 errmsg("VIEW or MATERIALIZED VIEW is not supported on incrementally maintainable materialized view")));
+
+					if (rte->rtekind == RTE_VALUES)
+						ereport(ERROR,
+								(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+								 errmsg("VALUES is not supported on incrementally maintainable materialized view")));
+
+				}
+
+				query_tree_walker(qry, check_ivm_restriction_walker, NULL, QTW_IGNORE_RANGE_TABLE);
+
+				break;
+			}
+		case T_TargetEntry:
+			{
+				TargetEntry *tle = (TargetEntry *)node;
+				if (isIvmName(tle->resname))
+						ereport(ERROR,
+								(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+								 errmsg("column name %s is not supported on incrementally maintainable materialized view", tle->resname)));
+
+				expression_tree_walker(node, check_ivm_restriction_walker, NULL);
+				break;
+			}
+		case T_JoinExpr:
+			{
+				JoinExpr *joinexpr = (JoinExpr *)node;
+
+				if (joinexpr->jointype > JOIN_INNER)
+						ereport(ERROR,
+								(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+								 errmsg("OUTER JOIN is not supported on incrementally maintainable materialized view")));
+
+				expression_tree_walker(node, check_ivm_restriction_walker, NULL);
+			}
+			break;
+		case T_Aggref:
+			ereport(ERROR,
+					(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+					 errmsg("aggregate function is not supported on incrementally maintainable materialized view")));
+			break;
+		default:
+			expression_tree_walker(node, check_ivm_restriction_walker, (void *) context);
+			break;
+	}
+	return false;
+}
+
+/*
+ * CreateIndexOnIMMV
+ *
+ * Create a unique index on incremental maintainable materialized view.
+ * If the view definition query has a GROUP BY clause, the index is created
+ * on the columns of GROUP BY expressions. Otherwise, if the view contains
+ * all primary key attritubes of its base tables in the target list, the index
+ * is created on these attritubes. In other cases, no index is created.
+ */
+void
+CreateIndexOnIMMV(Query *query, Relation matviewRel, bool is_create)
+{
+	ListCell *lc;
+	IndexStmt  *index;
+	ObjectAddress address;
+	List *constraintList = NIL;
+	char		idxname[NAMEDATALEN];
+	List	   *indexoidlist = RelationGetIndexList(matviewRel);
+	ListCell   *indexoidscan;
+
+	snprintf(idxname, sizeof(idxname), "%s_index", RelationGetRelationName(matviewRel));
+
+	index = makeNode(IndexStmt);
+
+	/*
+	 * We consider null values not distinct to make sure that views with DISTINCT
+	 * or GROUP BY don't contain multiple NULL rows when NULL is inserted to
+	 * a base table concurrently.
+	 */
+	index->nulls_not_distinct = true;
+
+	index->unique = true;
+	index->primary = false;
+	index->isconstraint = false;
+	index->deferrable = false;
+	index->initdeferred = false;
+	index->idxname = idxname;
+	index->relation =
+		makeRangeVar(get_namespace_name(RelationGetNamespace(matviewRel)),
+					 pstrdup(RelationGetRelationName(matviewRel)),
+					 -1);
+	index->accessMethod = DEFAULT_INDEX_TYPE;
+	index->options = NIL;
+	index->tableSpace = get_tablespace_name(matviewRel->rd_rel->reltablespace);
+	index->whereClause = NULL;
+	index->indexParams = NIL;
+	index->indexIncludingParams = NIL;
+	index->excludeOpNames = NIL;
+	index->idxcomment = NULL;
+	index->indexOid = InvalidOid;
+	index->oldNode = InvalidOid;
+	index->oldCreateSubid = InvalidSubTransactionId;
+	index->oldFirstRelfilenodeSubid = InvalidSubTransactionId;
+	index->transformed = true;
+	index->concurrent = false;
+	index->if_not_exists = false;
+
+	if (query->distinctClause)
+	{
+		/* create unique constraint on all columns */
+		foreach(lc, query->targetList)
+		{
+			TargetEntry *tle = (TargetEntry *) lfirst(lc);
+			Form_pg_attribute attr = TupleDescAttr(matviewRel->rd_att, tle->resno - 1);
+			IndexElem  *iparam;
+
+			iparam = makeNode(IndexElem);
+			iparam->name = pstrdup(NameStr(attr->attname));
+			iparam->expr = NULL;
+			iparam->indexcolname = NULL;
+			iparam->collation = NIL;
+			iparam->opclass = NIL;
+			iparam->opclassopts = NIL;
+			iparam->ordering = SORTBY_DEFAULT;
+			iparam->nulls_ordering = SORTBY_NULLS_DEFAULT;
+			index->indexParams = lappend(index->indexParams, iparam);
+		}
+	}
+	else
+	{
+		Bitmapset *key_attnos;
+
+		/* create index on the base tables' primary key columns */
+		key_attnos = get_primary_key_attnos_from_query(query, &constraintList, is_create);
+		if (key_attnos)
+		{
+			foreach(lc, query->targetList)
+			{
+				TargetEntry *tle = (TargetEntry *) lfirst(lc);
+				Form_pg_attribute attr = TupleDescAttr(matviewRel->rd_att, tle->resno - 1);
+
+				if (bms_is_member(tle->resno - FirstLowInvalidHeapAttributeNumber, key_attnos))
+				{
+					IndexElem  *iparam;
+
+					iparam = makeNode(IndexElem);
+					iparam->name = pstrdup(NameStr(attr->attname));
+					iparam->expr = NULL;
+					iparam->indexcolname = NULL;
+					iparam->collation = NIL;
+					iparam->opclass = NIL;
+					iparam->opclassopts = NIL;
+					iparam->ordering = SORTBY_DEFAULT;
+					iparam->nulls_ordering = SORTBY_NULLS_DEFAULT;
+					index->indexParams = lappend(index->indexParams, iparam);
+				}
+			}
+		}
+		else
+		{
+			/* create no index, just notice that an appropriate index is necessary for efficient IVM */
+			ereport(NOTICE,
+					(errmsg("could not create an index on materialized view \"%s\" automatically",
+							RelationGetRelationName(matviewRel)),
+					 errdetail("This target list does not have all the primary key columns, "
+							   "or this view does not contain DISTINCT clause."),
+					 errhint("Create an index on the materialized view for efficient incremental maintenance.")));
+			return;
+		}
+	}
+
+	/* If we have a compatible index, we don't need to create another. */
+	foreach(indexoidscan, indexoidlist)
+	{
+		Oid			indexoid = lfirst_oid(indexoidscan);
+		Relation	indexRel;
+		bool		hasCompatibleIndex = false;
+
+		indexRel = index_open(indexoid, AccessShareLock);
+
+		if (CheckIndexCompatible(indexRel->rd_id,
+								index->accessMethod,
+								index->indexParams,
+								index->excludeOpNames))
+			hasCompatibleIndex = true;
+
+		index_close(indexRel, AccessShareLock);
+
+		if (hasCompatibleIndex)
+			return;
+	}
+
+	address = DefineIndex(RelationGetRelid(matviewRel),
+						  index,
+						  InvalidOid,
+						  InvalidOid,
+						  InvalidOid,
+						  false, true, false, false, true);
+
+	ereport(NOTICE,
+			(errmsg("created index \"%s\" on materialized view \"%s\"",
+					idxname, RelationGetRelationName(matviewRel))));
+
+	/*
+	 * Make dependencies so that the index is dropped if any base tables's
+	 * primary key is dropped.
+	 */
+	foreach(lc, constraintList)
+	{
+		Oid constraintOid = lfirst_oid(lc);
+		ObjectAddress	refaddr;
+
+		refaddr.classId = ConstraintRelationId;
+		refaddr.objectId = constraintOid;
+		refaddr.objectSubId = 0;
+
+		recordDependencyOn(&address, &refaddr, DEPENDENCY_NORMAL);
+	}
+}
+
+
+/*
+ * get_primary_key_attnos_from_query
+ *
+ * Identify the columns in base tables' primary keys in the target list.
+ *
+ * Returns a Bitmapset of the column attnos of the primary key's columns of
+ * tables that used in the query.  The attnos are offset by
+ * FirstLowInvalidHeapAttributeNumber as same as get_primary_key_attnos.
+ *
+ * If any table has no primary key or any primary key's columns is not in
+ * the target list, return NULL.  We also return NULL if any pkey constraint
+ * is deferrable.
+ *
+ * constraintList is set to a list of the OIDs of the pkey constraints.
+ */
+static Bitmapset *
+get_primary_key_attnos_from_query(Query *query, List **constraintList, bool is_create)
+{
+	List *key_attnos_list = NIL;
+	ListCell *lc;
+	int i;
+	Bitmapset *keys = NULL;
+	Relids	rels_in_from;
+	PlannerInfo root;
+
+
+	/*
+	 * Collect primary key attributes from all tables used in query. The key attributes
+	 * sets for each table are stored in key_attnos_list in order by RTE index.
+	 */
+	i = 1;
+	foreach(lc, query->rtable)
+	{
+		RangeTblEntry *r = (RangeTblEntry*) lfirst(lc);
+		Bitmapset *key_attnos;
+		bool	has_pkey = true;
+		Index	first_rtindex = is_create ? 1 : PRS2_NEW_VARNO + 1;
+
+		/* skip NEW/OLD entries */
+		if (i >= first_rtindex)
+		{
+			/* for tables, call get_primary_key_attnos */
+			if (r->rtekind == RTE_RELATION)
+			{
+				Oid constraintOid;
+				key_attnos = get_primary_key_attnos(r->relid, false, &constraintOid);
+				*constraintList = lappend_oid(*constraintList, constraintOid);
+				has_pkey = (key_attnos != NULL);
+			}
+			/* for other RTEs, store NULL into key_attnos_list */
+			else
+				key_attnos = NULL;
+		}
+		else
+			key_attnos = NULL;
+
+		/*
+		 * If any table or subquery has no primary key or its pkey constraint is deferrable,
+		 * we cannot get key attributes for this query, so return NULL.
+		 */
+		if (!has_pkey)
+			return NULL;
+
+		key_attnos_list = lappend(key_attnos_list, key_attnos);
+		i++;
+	}
+
+	/* Collect key attributes appearing in the target list */
+	i = 1;
+	foreach(lc, query->targetList)
+	{
+		TargetEntry *tle = (TargetEntry *) flatten_join_alias_vars(query, lfirst(lc));
+
+		if (IsA(tle->expr, Var))
+		{
+			Var *var = (Var*) tle->expr;
+			Bitmapset *attnos = list_nth(key_attnos_list, var->varno - 1);
+
+			/* check if this attribute is from a base table's primary key */
+			if (bms_is_member(var->varattno - FirstLowInvalidHeapAttributeNumber, attnos))
+			{
+				/*
+				 * Remove found key attributes from key_attnos_list, and add this
+				 * to the result list.
+				 */
+				bms_del_member(attnos, var->varattno - FirstLowInvalidHeapAttributeNumber);
+				keys = bms_add_member(keys, i - FirstLowInvalidHeapAttributeNumber);
+			}
+		}
+		i++;
+	}
+
+	/* Collect relations appearing in the FROM clause */
+	rels_in_from = pull_varnos_of_level(&root, (Node *)query->jointree, 0);
+
+	/*
+	 * Check if all key attributes of relations in FROM are appearing in the target
+	 * list.  If an attribute remains in key_attnos_list in spite of the table is used
+	 * in FROM clause, the target is missing this key attribute, so we return NULL.
+	 */
+	i = 1;
+	foreach(lc, key_attnos_list)
+	{
+		Bitmapset *bms = (Bitmapset *)lfirst(lc);
+		if (!bms_is_empty(bms) && bms_is_member(i, rels_in_from))
+			return NULL;
+		i++;
+	}
+
+	return keys;
+}
diff --git a/src/backend/commands/indexcmds.c b/src/backend/commands/indexcmds.c
index cd30f15eba..a94b8ffd7d 100644
--- a/src/backend/commands/indexcmds.c
+++ b/src/backend/commands/indexcmds.c
@@ -36,6 +36,7 @@
 #include "commands/dbcommands.h"
 #include "commands/defrem.h"
 #include "commands/event_trigger.h"
+#include "commands/matview.h"
 #include "commands/progress.h"
 #include "commands/tablecmds.h"
 #include "commands/tablespace.h"
@@ -1055,6 +1056,45 @@ DefineIndex(Oid relationId,
 	safe_index = indexInfo->ii_Expressions == NIL &&
 		indexInfo->ii_Predicate == NIL;
 
+	/*
+	 * We disallow unique indexes on IVM columns of IMMVs.
+	 */
+	if (RelationIsIVM(rel) && stmt->unique)
+	{
+		for (i = 0; i < indexInfo->ii_NumIndexKeyAttrs; i++)
+		{
+			AttrNumber	attno = indexInfo->ii_IndexAttrNumbers[i];
+			if (attno > 0)
+			{
+				char *name = NameStr(TupleDescAttr(rel->rd_att, attno - 1)->attname);
+				if (name && isIvmName(name))
+					ereport(ERROR,
+							(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+							 errmsg("unique index creation on IVM columns is not supported")));
+			}
+		}
+
+		if (indexInfo->ii_Expressions)
+		{
+			Bitmapset  *indexattrs = NULL;
+			int			varno = -1;
+
+			pull_varattnos((Node *) indexInfo->ii_Expressions, 1, &indexattrs);
+
+			while ((varno = bms_next_member(indexattrs, varno)) >= 0)
+			{
+				int attno = varno + FirstLowInvalidHeapAttributeNumber;
+				char *name = NameStr(TupleDescAttr(rel->rd_att, attno - 1)->attname);
+				if (name && isIvmName(name))
+					ereport(ERROR,
+							(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+							 errmsg("unique index creation on IVM columns is not supported")));
+			}
+
+		}
+	}
+
+
 	/*
 	 * Report index creation if appropriate (delay this till after most of the
 	 * error checks)
diff --git a/src/backend/commands/matview.c b/src/backend/commands/matview.c
index 9ab248d25e..cb713328a0 100644
--- a/src/backend/commands/matview.c
+++ b/src/backend/commands/matview.c
@@ -25,26 +25,48 @@
 #include "catalog/indexing.h"
 #include "catalog/namespace.h"
 #include "catalog/pg_am.h"
+#include "catalog/pg_collation.h"
+#include "catalog/pg_depend.h"
+#include "catalog/pg_trigger.h"
+#include "catalog/pg_type.h"
 #include "catalog/pg_opclass.h"
 #include "catalog/pg_operator.h"
 #include "commands/cluster.h"
+#include "commands/defrem.h"
 #include "commands/matview.h"
 #include "commands/tablecmds.h"
 #include "commands/tablespace.h"
+#include "commands/createas.h"
 #include "executor/executor.h"
 #include "executor/spi.h"
+#include "executor/tstoreReceiver.h"
 #include "miscadmin.h"
+#include "nodes/makefuncs.h"
+#include "nodes/nodeFuncs.h"
+#include "optimizer/optimizer.h"
+#include "parser/analyze.h"
+#include "parser/parser.h"
+#include "parser/parsetree.h"
+#include "parser/parse_clause.h"
+#include "parser/parse_coerce.h"
+#include "parser/parse_collate.h"
+#include "parser/parse_func.h"
 #include "parser/parse_relation.h"
+#include "parser/parse_type.h"
 #include "pgstat.h"
 #include "rewrite/rewriteHandler.h"
+#include "rewrite/rewriteManip.h"
+#include "rewrite/rowsecurity.h"
 #include "storage/lmgr.h"
 #include "storage/smgr.h"
 #include "tcop/tcopprot.h"
 #include "utils/builtins.h"
+#include "utils/fmgroids.h"
 #include "utils/lsyscache.h"
 #include "utils/rel.h"
 #include "utils/snapmgr.h"
 #include "utils/syscache.h"
+#include "utils/typcache.h"
 
 
 typedef struct
@@ -58,6 +80,50 @@ typedef struct
 	BulkInsertState bistate;	/* bulk insert state */
 } DR_transientrel;
 
+#define MV_INIT_QUERYHASHSIZE	16
+
+/*
+ * MV_TriggerHashEntry
+ *
+ * Hash entry for base tables on which IVM trigger is invoked
+ */
+typedef struct MV_TriggerHashEntry
+{
+	Oid	matview_id;			/* OID of the materialized view */
+	int	before_trig_count;	/* count of before triggers invoked */
+	int	after_trig_count;	/* count of after triggers invoked */
+
+	TransactionId	xid;	/* Transaction id before the first table is modified*/
+	CommandId		cid;	/* Command id before the first table is modified */
+
+	List   *tables;		/* List of MV_TriggerTable */
+	bool	has_old;	/* tuples are deleted from any table? */
+	bool	has_new;	/* tuples are inserted into any table? */
+} MV_TriggerHashEntry;
+
+/*
+ * MV_TriggerTable
+ *
+ * IVM related data for tables on which the trigger is invoked.
+ */
+typedef struct MV_TriggerTable
+{
+	Oid		table_id;			/* OID of the modified table */
+	List   *old_tuplestores;	/* tuplestores for deleted tuples */
+	List   *new_tuplestores;	/* tuplestores for inserted tuples */
+	List   *old_rtes;			/* RTEs of ENRs for old_tuplestores*/
+	List   *new_rtes;			/* RTEs of ENRs for new_tuplestores */
+
+	List   *rte_indexes;		/* List of RTE index of the modified table */
+	RangeTblEntry *original_rte;	/* the original RTE saved before rewriting query */
+} MV_TriggerTable;
+
+static HTAB *mv_trigger_info = NULL;
+
+/* ENR name for materialized view delta */
+#define NEW_DELTA_ENRNAME "new_delta"
+#define OLD_DELTA_ENRNAME "old_delta"
+
 static int	matview_maintenance_depth = 0;
 
 static void transientrel_startup(DestReceiver *self, int operation, TupleDesc typeinfo);
@@ -65,7 +131,9 @@ static bool transientrel_receive(TupleTableSlot *slot, DestReceiver *self);
 static void transientrel_shutdown(DestReceiver *self);
 static void transientrel_destroy(DestReceiver *self);
 static uint64 refresh_matview_datafill(DestReceiver *dest, Query *query,
-									   const char *queryString);
+						 QueryEnvironment *queryEnv,
+						 TupleDesc *resultTupleDesc,
+						 const char *queryString);
 static char *make_temptable_name_n(char *tempname, int n);
 static void refresh_by_match_merge(Oid matviewOid, Oid tempOid, Oid relowner,
 								   int save_sec_context);
@@ -73,6 +141,45 @@ static void refresh_by_heap_swap(Oid matviewOid, Oid OIDNewHeap, char relpersist
 static bool is_usable_unique_index(Relation indexRel);
 static void OpenMatViewIncrementalMaintenance(void);
 static void CloseMatViewIncrementalMaintenance(void);
+static Query *get_matview_query(Relation matviewRel);
+
+static Query *rewrite_query_for_preupdate_state(Query *query, List *tables,
+								  TransactionId xid, CommandId cid,
+								  ParseState *pstate);
+static void register_delta_ENRs(ParseState *pstate, Query *query, List *tables);
+static char *make_delta_enr_name(const char *prefix, Oid relid, int count);
+static RangeTblEntry *get_prestate_rte(RangeTblEntry *rte, MV_TriggerTable *table,
+				 TransactionId xid, CommandId cid,
+				 QueryEnvironment *queryEnv);
+static RangeTblEntry *union_ENRs(RangeTblEntry *rte, Oid relid, List *enr_rtes, const char *prefix,
+		   QueryEnvironment *queryEnv);
+static Query *rewrite_query_for_distinct(Query *query, ParseState *pstate);
+
+static void calc_delta(MV_TriggerTable *table, int rte_index, Query *query,
+			DestReceiver *dest_old, DestReceiver *dest_new,
+			TupleDesc *tupdesc_old, TupleDesc *tupdesc_new,
+			QueryEnvironment *queryEnv);
+static Query *rewrite_query_for_postupdate_state(Query *query, MV_TriggerTable *table, int rte_index);
+
+static void apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *new_tuplestores,
+			TupleDesc tupdesc_old, TupleDesc tupdesc_new,
+			Query *query, bool use_count, char *count_colname);
+static void apply_old_delta(const char *matviewname, const char *deltaname_old,
+				List *keys);
+static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old,
+				List *keys, const char *count_colname);
+static void apply_new_delta(const char *matviewname, const char *deltaname_new,
+				StringInfo target_list);
+static void apply_new_delta_with_count(const char *matviewname, const char* deltaname_new,
+				List *keys, StringInfo target_list, const char* count_colname);
+static char *get_matching_condition_string(List *keys);
+static void generate_equal(StringInfo querybuf, Oid opttype,
+			   const char *leftop, const char *rightop);
+
+static void mv_InitHashTables(void);
+static void clean_up_IVM_hash_entry(MV_TriggerHashEntry *entry);
+
+static List *get_securityQuals(Oid relId, int rt_index, Query *query);
 
 /*
  * SetMatViewPopulatedState
@@ -114,6 +221,46 @@ SetMatViewPopulatedState(Relation relation, bool newstate)
 	CommandCounterIncrement();
 }
 
+/*
+ * SetMatViewIVMState
+ *		Mark a materialized view as IVM, or not.
+ *
+ * NOTE: caller must be holding an appropriate lock on the relation.
+ */
+void
+SetMatViewIVMState(Relation relation, bool newstate)
+{
+	Relation	pgrel;
+	HeapTuple	tuple;
+
+	Assert(relation->rd_rel->relkind == RELKIND_MATVIEW);
+
+	/*
+	 * Update relation's pg_class entry.  Crucial side-effect: other backends
+	 * (and this one too!) are sent SI message to make them rebuild relcache
+	 * entries.
+	 */
+	pgrel = table_open(RelationRelationId, RowExclusiveLock);
+	tuple = SearchSysCacheCopy1(RELOID,
+								ObjectIdGetDatum(RelationGetRelid(relation)));
+	if (!HeapTupleIsValid(tuple))
+		elog(ERROR, "cache lookup failed for relation %u",
+			 RelationGetRelid(relation));
+
+	((Form_pg_class) GETSTRUCT(tuple))->relisivm = newstate;
+
+	CatalogTupleUpdate(pgrel, &tuple->t_self, tuple);
+
+	heap_freetuple(tuple);
+	table_close(pgrel, RowExclusiveLock);
+
+	/*
+	 * Advance command counter to make the updated pg_class row locally
+	 * visible.
+	 */
+	CommandCounterIncrement();
+}
+
 /*
  * ExecRefreshMatView -- execute a REFRESH MATERIALIZED VIEW command
  *
@@ -140,9 +287,8 @@ ExecRefreshMatView(RefreshMatViewStmt *stmt, const char *queryString,
 {
 	Oid			matviewOid;
 	Relation	matviewRel;
-	RewriteRule *rule;
-	List	   *actions;
 	Query	   *dataQuery;
+	Query	   *viewQuery;
 	Oid			tableSpace;
 	Oid			relowner;
 	Oid			OIDNewHeap;
@@ -155,6 +301,7 @@ ExecRefreshMatView(RefreshMatViewStmt *stmt, const char *queryString,
 	int			save_sec_context;
 	int			save_nestlevel;
 	ObjectAddress address;
+	bool oldPopulated;
 
 	/* Determine strength of lock needed. */
 	concurrent = stmt->concurrent;
@@ -167,6 +314,7 @@ ExecRefreshMatView(RefreshMatViewStmt *stmt, const char *queryString,
 										  lockmode, 0,
 										  RangeVarCallbackOwnsTable, NULL);
 	matviewRel = table_open(matviewOid, NoLock);
+	oldPopulated = RelationIsPopulated(matviewRel);
 
 	/* Make sure it is a materialized view. */
 	if (matviewRel->rd_rel->relkind != RELKIND_MATVIEW)
@@ -188,32 +336,14 @@ ExecRefreshMatView(RefreshMatViewStmt *stmt, const char *queryString,
 				 errmsg("%s and %s options cannot be used together",
 						"CONCURRENTLY", "WITH NO DATA")));
 
-	/*
-	 * Check that everything is correct for a refresh. Problems at this point
-	 * are internal errors, so elog is sufficient.
-	 */
-	if (matviewRel->rd_rel->relhasrules == false ||
-		matviewRel->rd_rules->numLocks < 1)
-		elog(ERROR,
-			 "materialized view \"%s\" is missing rewrite information",
-			 RelationGetRelationName(matviewRel));
-
-	if (matviewRel->rd_rules->numLocks > 1)
-		elog(ERROR,
-			 "materialized view \"%s\" has too many rules",
-			 RelationGetRelationName(matviewRel));
 
-	rule = matviewRel->rd_rules->rules[0];
-	if (rule->event != CMD_SELECT || !(rule->isInstead))
-		elog(ERROR,
-			 "the rule for materialized view \"%s\" is not a SELECT INSTEAD OF rule",
-			 RelationGetRelationName(matviewRel));
+	viewQuery = get_matview_query(matviewRel);
 
-	actions = rule->actions;
-	if (list_length(actions) != 1)
-		elog(ERROR,
-			 "the rule for materialized view \"%s\" is not a single action",
-			 RelationGetRelationName(matviewRel));
+	/* For IMMV, we need to rewrite matview query */
+	if (!stmt->skipData && RelationIsIVM(matviewRel))
+		dataQuery = rewriteQueryForIMMV(viewQuery,NIL);
+	else
+		dataQuery = viewQuery;
 
 	/*
 	 * Check that there is a unique index with no WHERE clause on one or more
@@ -248,12 +378,6 @@ ExecRefreshMatView(RefreshMatViewStmt *stmt, const char *queryString,
 					 errhint("Create a unique index with no WHERE clause on one or more columns of the materialized view.")));
 	}
 
-	/*
-	 * The stored query was rewritten at the time of the MV definition, but
-	 * has not been scribbled on by the planner.
-	 */
-	dataQuery = linitial_node(Query, actions);
-
 	/*
 	 * Check for active uses of the relation in the current transaction, such
 	 * as open scans.
@@ -294,6 +418,74 @@ ExecRefreshMatView(RefreshMatViewStmt *stmt, const char *queryString,
 		relpersistence = matviewRel->rd_rel->relpersistence;
 	}
 
+	/* delete IMMV triggers. */
+	if (RelationIsIVM(matviewRel) && stmt->skipData )
+	{
+		Relation	tgRel;
+		Relation	depRel;
+		ScanKeyData key;
+		SysScanDesc scan;
+		HeapTuple	tup;
+		ObjectAddresses *immv_triggers;
+
+		immv_triggers = new_object_addresses();
+
+		tgRel = table_open(TriggerRelationId, RowExclusiveLock);
+		depRel = table_open(DependRelationId, RowExclusiveLock);
+
+		/* search triggers that depends on IMMV. */
+		ScanKeyInit(&key,
+					Anum_pg_depend_refobjid,
+					BTEqualStrategyNumber, F_OIDEQ,
+					ObjectIdGetDatum(matviewOid));
+		scan = systable_beginscan(depRel, DependReferenceIndexId, true,
+								  NULL, 1, &key);
+		while ((tup = systable_getnext(scan)) != NULL)
+		{
+			ObjectAddress obj;
+			Form_pg_depend foundDep = (Form_pg_depend) GETSTRUCT(tup);
+
+			if (foundDep->classid == TriggerRelationId)
+			{
+				HeapTuple	tgtup;
+				ScanKeyData tgkey[1];
+				SysScanDesc tgscan;
+				Form_pg_trigger tgform;
+
+				/* Find the trigger name. */
+				ScanKeyInit(&tgkey[0],
+							Anum_pg_trigger_oid,
+							BTEqualStrategyNumber, F_OIDEQ,
+							ObjectIdGetDatum(foundDep->objid));
+
+				tgscan = systable_beginscan(tgRel, TriggerOidIndexId, true,
+											NULL, 1, tgkey);
+				tgtup = systable_getnext(tgscan);
+				if (!HeapTupleIsValid(tgtup))
+					elog(ERROR, "could not find tuple for immv trigger %u", foundDep->objid);
+
+				tgform = (Form_pg_trigger) GETSTRUCT(tgtup);
+
+				/* If trigger is created by IMMV, delete it. */
+				if (strncmp(NameStr(tgform->tgname), "IVM_trigger_", 12) == 0)
+				{
+					obj.classId = foundDep->classid;
+					obj.objectId = foundDep->objid;
+					obj.objectSubId = foundDep->refobjsubid;
+					add_exact_object_address(&obj, immv_triggers);
+				}
+				systable_endscan(tgscan);
+			}
+		}
+		systable_endscan(scan);
+
+		performMultipleDeletions(immv_triggers, DROP_RESTRICT, PERFORM_DELETION_INTERNAL);
+
+		table_close(depRel, RowExclusiveLock);
+		table_close(tgRel, RowExclusiveLock);
+		free_object_addresses(immv_triggers);
+	}
+
 	/*
 	 * Create the transient table that will receive the regenerated data. Lock
 	 * it against access by any other process until commit (by which time it
@@ -313,7 +505,7 @@ ExecRefreshMatView(RefreshMatViewStmt *stmt, const char *queryString,
 
 	/* Generate the data, if wanted. */
 	if (!stmt->skipData)
-		processed = refresh_matview_datafill(dest, dataQuery, queryString);
+		processed = refresh_matview_datafill(dest, dataQuery, NULL, NULL, queryString);
 
 	/* Make the matview match the newly generated data. */
 	if (concurrent)
@@ -348,6 +540,12 @@ ExecRefreshMatView(RefreshMatViewStmt *stmt, const char *queryString,
 			pgstat_count_heap_insert(matviewRel, processed);
 	}
 
+	if (!stmt->skipData && RelationIsIVM(matviewRel) && !oldPopulated)
+	{
+		CreateIndexOnIMMV(viewQuery, matviewRel, false);
+		CreateIvmTriggersOnBaseTables(viewQuery, matviewOid, false);
+	}
+
 	table_close(matviewRel, NoLock);
 
 	/* Roll back any GUC changes */
@@ -382,6 +580,8 @@ ExecRefreshMatView(RefreshMatViewStmt *stmt, const char *queryString,
  */
 static uint64
 refresh_matview_datafill(DestReceiver *dest, Query *query,
+						 QueryEnvironment *queryEnv,
+						 TupleDesc *resultTupleDesc,
 						 const char *queryString)
 {
 	List	   *rewritten;
@@ -418,7 +618,7 @@ refresh_matview_datafill(DestReceiver *dest, Query *query,
 	/* Create a QueryDesc, redirecting output to our tuple receiver */
 	queryDesc = CreateQueryDesc(plan, queryString,
 								GetActiveSnapshot(), InvalidSnapshot,
-								dest, NULL, NULL, 0);
+								dest, NULL, queryEnv ? queryEnv: NULL, 0);
 
 	/* call ExecutorStart to prepare the plan for execution */
 	ExecutorStart(queryDesc, 0);
@@ -428,6 +628,9 @@ refresh_matview_datafill(DestReceiver *dest, Query *query,
 
 	processed = queryDesc->estate->es_processed;
 
+	if (resultTupleDesc)
+		*resultTupleDesc = CreateTupleDescCopy(queryDesc->tupDesc);
+
 	/* and clean up */
 	ExecutorFinish(queryDesc);
 	ExecutorEnd(queryDesc);
@@ -942,3 +1145,1307 @@ CloseMatViewIncrementalMaintenance(void)
 	matview_maintenance_depth--;
 	Assert(matview_maintenance_depth >= 0);
 }
+
+/*
+ * get_matview_query - get the Query from a matview's _RETURN rule.
+ */
+static Query *
+get_matview_query(Relation matviewRel)
+{
+	RewriteRule *rule;
+	List * actions;
+
+	/*
+	 * Check that everything is correct for a refresh. Problems at this point
+	 * are internal errors, so elog is sufficient.
+	 */
+	if (matviewRel->rd_rel->relhasrules == false ||
+		matviewRel->rd_rules->numLocks < 1)
+		elog(ERROR,
+			 "materialized view \"%s\" is missing rewrite information",
+			 RelationGetRelationName(matviewRel));
+
+	if (matviewRel->rd_rules->numLocks > 1)
+		elog(ERROR,
+			 "materialized view \"%s\" has too many rules",
+			 RelationGetRelationName(matviewRel));
+
+	rule = matviewRel->rd_rules->rules[0];
+	if (rule->event != CMD_SELECT || !(rule->isInstead))
+		elog(ERROR,
+			 "the rule for materialized view \"%s\" is not a SELECT INSTEAD OF rule",
+			 RelationGetRelationName(matviewRel));
+
+	actions = rule->actions;
+	if (list_length(actions) != 1)
+		elog(ERROR,
+			 "the rule for materialized view \"%s\" is not a single action",
+			 RelationGetRelationName(matviewRel));
+
+	/*
+	 * The stored query was rewritten at the time of the MV definition, but
+	 * has not been scribbled on by the planner.
+	 */
+	return linitial_node(Query, actions);
+}
+
+
+/* ----------------------------------------------------
+ *		Incremental View Maintenance routines
+ * ---------------------------------------------------
+ */
+
+/*
+ * IVM_immediate_before
+ *
+ * IVM trigger function invoked before base table is modified. If this is
+ * invoked firstly in the same statement, we save the transaction id and the
+ * command id at that time.
+ */
+Datum
+IVM_immediate_before(PG_FUNCTION_ARGS)
+{
+	TriggerData *trigdata = (TriggerData *) fcinfo->context;
+	char	   *matviewOid_text = trigdata->tg_trigger->tgargs[0];
+	char	   *ex_lock_text = trigdata->tg_trigger->tgargs[1];
+	Oid			matviewOid;
+	MV_TriggerHashEntry *entry;
+	bool	found;
+	bool	ex_lock;
+
+	matviewOid = DatumGetObjectId(DirectFunctionCall1(oidin, CStringGetDatum(matviewOid_text)));
+	ex_lock = DatumGetBool(DirectFunctionCall1(boolin, CStringGetDatum(ex_lock_text)));
+
+	/* If the view has more than one tables, we have to use an exclusive lock. */
+	if (ex_lock)
+	{
+		/*
+		 * Wait for concurrent transactions which update this materialized view at
+		 * READ COMMITED. This is needed to see changes committed in other
+		 * transactions. No wait and raise an error at REPEATABLE READ or
+		 * SERIALIZABLE to prevent update anomalies of matviews.
+		 * XXX: dead-lock is possible here.
+		 */
+		if (!IsolationUsesXactSnapshot())
+			LockRelationOid(matviewOid, ExclusiveLock);
+		else if (!ConditionalLockRelationOid(matviewOid, ExclusiveLock))
+		{
+			/* try to throw error by name; relation could be deleted... */
+			char	   *relname = get_rel_name(matviewOid);
+
+			if (!relname)
+				ereport(ERROR,
+						(errcode(ERRCODE_LOCK_NOT_AVAILABLE),
+						errmsg("could not obtain lock on materialized view during incremental maintenance")));
+
+			ereport(ERROR,
+					(errcode(ERRCODE_LOCK_NOT_AVAILABLE),
+					errmsg("could not obtain lock on materialized view \"%s\" during incremental maintenance",
+							relname)));
+		}
+	}
+	else
+		LockRelationOid(matviewOid, RowExclusiveLock);
+
+	/*
+	 * On the first call initialize the hashtable
+	 */
+	if (!mv_trigger_info)
+		mv_InitHashTables();
+
+	entry = (MV_TriggerHashEntry *) hash_search(mv_trigger_info,
+											  (void *) &matviewOid,
+											  HASH_ENTER, &found);
+
+	/* On the first BEFORE to update the view, initialize trigger data */
+	if (!found)
+	{
+		Snapshot snapshot = GetActiveSnapshot();
+
+		entry->matview_id = matviewOid;
+		entry->before_trig_count = 0;
+		entry->after_trig_count = 0;
+		entry->xid = GetCurrentTransactionId();
+		entry->cid = snapshot->curcid;
+		entry->tables = NIL;
+		entry->has_old = false;
+		entry->has_new = false;
+	}
+
+	entry->before_trig_count++;
+
+	return PointerGetDatum(NULL);
+}
+
+/*
+ * IVM_immediate_before
+ *
+ * IVM trigger function invoked after base table is modified.
+ * For each table, tuplestores of transition tables are collected.
+ * and after the last modification
+ */
+Datum
+IVM_immediate_maintenance(PG_FUNCTION_ARGS)
+{
+	TriggerData *trigdata = (TriggerData *) fcinfo->context;
+	Relation	rel;
+	Oid			relid;
+	Oid			matviewOid;
+	Query	   *query;
+	Query	   *rewritten = NULL;
+	char	   *matviewOid_text = trigdata->tg_trigger->tgargs[0];
+	Relation	matviewRel;
+	int old_depth = matview_maintenance_depth;
+
+	Oid			relowner;
+	Tuplestorestate *old_tuplestore = NULL;
+	Tuplestorestate *new_tuplestore = NULL;
+	DestReceiver *dest_new = NULL, *dest_old = NULL;
+	Oid			save_userid;
+	int			save_sec_context;
+	int			save_nestlevel;
+
+	MV_TriggerHashEntry *entry;
+	MV_TriggerTable		*table;
+	bool	found;
+
+	ParseState		 *pstate;
+	QueryEnvironment *queryEnv = create_queryEnv();
+	MemoryContext	oldcxt;
+	ListCell   *lc;
+	int			i;
+
+
+	/* Create a ParseState for rewriting the view definition query */
+	pstate = make_parsestate(NULL);
+	pstate->p_queryEnv = queryEnv;
+	pstate->p_expr_kind = EXPR_KIND_SELECT_TARGET;
+
+	rel = trigdata->tg_relation;
+	relid = rel->rd_id;
+
+	matviewOid = DatumGetObjectId(DirectFunctionCall1(oidin, CStringGetDatum(matviewOid_text)));
+
+	/*
+	 * On the first call initialize the hashtable
+	 */
+	if (!mv_trigger_info)
+		mv_InitHashTables();
+
+	/* get the entry for this materialized view */
+	entry = (MV_TriggerHashEntry *) hash_search(mv_trigger_info,
+											  (void *) &matviewOid,
+											  HASH_FIND, &found);
+	Assert (found && entry != NULL);
+	entry->after_trig_count++;
+
+	/* search the entry for the modified table and create new entry if not found */
+	found = false;
+	foreach(lc, entry->tables)
+	{
+		table = (MV_TriggerTable *) lfirst(lc);
+		if (table->table_id == relid)
+		{
+			found = true;
+			break;
+		}
+	}
+	if (!found)
+	{
+		oldcxt = MemoryContextSwitchTo(TopTransactionContext);
+
+		table = (MV_TriggerTable *) palloc0(sizeof(MV_TriggerTable));
+		table->table_id = relid;
+		table->old_tuplestores = NIL;
+		table->new_tuplestores = NIL;
+		table->old_rtes = NIL;
+		table->new_rtes = NIL;
+		table->rte_indexes = NIL;
+		entry->tables = lappend(entry->tables, table);
+
+		MemoryContextSwitchTo(oldcxt);
+	}
+
+	/* Save the transition tables and make a request to not free immediately */
+	if (trigdata->tg_oldtable)
+	{
+		oldcxt = MemoryContextSwitchTo(TopTransactionContext);
+		table->old_tuplestores = lappend(table->old_tuplestores, trigdata->tg_oldtable);
+		entry->has_old = true;
+		MemoryContextSwitchTo(oldcxt);
+	}
+	if (trigdata->tg_newtable)
+	{
+		oldcxt = MemoryContextSwitchTo(TopTransactionContext);
+		table->new_tuplestores = lappend(table->new_tuplestores, trigdata->tg_newtable);
+		entry->has_new = true;
+		MemoryContextSwitchTo(oldcxt);
+	}
+	if (entry->has_new || entry->has_old)
+	{
+		CmdType cmd;
+
+		if (TRIGGER_FIRED_BY_INSERT(trigdata->tg_event))
+			cmd = CMD_INSERT;
+		else if (TRIGGER_FIRED_BY_DELETE(trigdata->tg_event))
+			cmd = CMD_DELETE;
+		else if (TRIGGER_FIRED_BY_UPDATE(trigdata->tg_event))
+			cmd = CMD_UPDATE;
+		else
+			elog(ERROR,"unsupported trigger type");
+
+		/* Prolong lifespan of transition tables to the end of the last AFTER trigger */
+		SetTransitionTablePreserved(relid, cmd);
+	}
+
+
+	/* If this is not the last AFTER trigger call, immediately exit. */
+	Assert (entry->before_trig_count >= entry->after_trig_count);
+	if (entry->before_trig_count != entry->after_trig_count)
+		return PointerGetDatum(NULL);
+
+	/*
+	 * If this is the last AFTER trigger call, continue and update the view.
+	 */
+
+	/*
+	 * Advance command counter to make the updated base table row locally
+	 * visible.
+	 */
+	CommandCounterIncrement();
+
+	matviewRel = table_open(matviewOid, NoLock);
+
+	/* get view query*/
+	query = get_matview_query(matviewRel);
+
+	/* Make sure it is a materialized view. */
+	Assert(matviewRel->rd_rel->relkind == RELKIND_MATVIEW);
+
+	/*
+	 * Get and push the latast snapshot to see any changes which is committed
+	 * during waiting in other transactions at READ COMMITTED level.
+	 */
+	PushActiveSnapshot(GetTransactionSnapshot());
+
+	/*
+	 * Check for active uses of the relation in the current transaction, such
+	 * as open scans.
+	 *
+	 * NB: We count on this to protect us against problems with refreshing the
+	 * data using TABLE_INSERT_FROZEN.
+	 */
+	CheckTableNotInUse(matviewRel, "refresh a materialized view incrementally");
+
+	/*
+	 * Switch to the owner's userid, so that any functions are run as that
+	 * user.  Also arrange to make GUC variable changes local to this command.
+	 * We will switch modes when we are about to execute user code.
+	 */
+	relowner = matviewRel->rd_rel->relowner;
+	GetUserIdAndSecContext(&save_userid, &save_sec_context);
+	SetUserIdAndSecContext(relowner,
+						   save_sec_context | SECURITY_RESTRICTED_OPERATION);
+	save_nestlevel = NewGUCNestLevel();
+
+	/*
+	 * rewrite query for calculating deltas
+	 */
+
+	rewritten = copyObject(query);
+
+	/* Replace resnames in a target list with materialized view's attnames */
+	i = 0;
+	foreach (lc, rewritten->targetList)
+	{
+		TargetEntry *tle = (TargetEntry *) lfirst(lc);
+		Form_pg_attribute attr = TupleDescAttr(matviewRel->rd_att, i);
+		char *resname = NameStr(attr->attname);
+
+		tle->resname = pstrdup(resname);
+		i++;
+	}
+
+	/* Set all tables in the query to pre-update state */
+	rewritten = rewrite_query_for_preupdate_state(rewritten, entry->tables,
+												  entry->xid, entry->cid,
+												  pstate);
+	/* Rewrite for DISTINCT clause */
+	rewritten = rewrite_query_for_distinct(rewritten, pstate);
+
+	/* Create tuplestores to store view deltas */
+	if (entry->has_old)
+	{
+		oldcxt = MemoryContextSwitchTo(TopTransactionContext);
+
+		old_tuplestore = tuplestore_begin_heap(false, false, work_mem);
+		dest_old = CreateDestReceiver(DestTuplestore);
+		SetTuplestoreDestReceiverParams(dest_old,
+									old_tuplestore,
+									TopTransactionContext,
+									false,
+									NULL,
+									NULL);
+
+		MemoryContextSwitchTo(oldcxt);
+	}
+	if (entry->has_new)
+	{
+		oldcxt = MemoryContextSwitchTo(TopTransactionContext);
+
+		new_tuplestore = tuplestore_begin_heap(false, false, work_mem);
+		dest_new = CreateDestReceiver(DestTuplestore);
+		SetTuplestoreDestReceiverParams(dest_new,
+									new_tuplestore,
+									TopTransactionContext,
+									false,
+									NULL,
+									NULL);
+		MemoryContextSwitchTo(oldcxt);
+	}
+
+	/* for all modified tables */
+	foreach(lc, entry->tables)
+	{
+		ListCell *lc2;
+
+		table = (MV_TriggerTable *) lfirst(lc);
+
+		/* loop for self-join */
+		foreach(lc2, table->rte_indexes)
+		{
+			int	rte_index = lfirst_int(lc2);
+			TupleDesc		tupdesc_old;
+			TupleDesc		tupdesc_new;
+			bool	use_count = false;
+			char   *count_colname = NULL;
+
+			count_colname = pstrdup("__ivm_count__");
+
+			if (query->distinctClause)
+				use_count = true;
+
+			/* calculate delta tables */
+			calc_delta(table, rte_index, rewritten, dest_old, dest_new,
+					   &tupdesc_old, &tupdesc_new, queryEnv);
+
+			/* Set the table in the query to post-update state */
+			rewritten = rewrite_query_for_postupdate_state(rewritten, table, rte_index);
+
+			PG_TRY();
+			{
+				/* apply the delta tables to the materialized view */
+				apply_delta(matviewOid, old_tuplestore, new_tuplestore,
+							tupdesc_old, tupdesc_new, query, use_count,
+							count_colname);
+			}
+			PG_CATCH();
+			{
+				matview_maintenance_depth = old_depth;
+				PG_RE_THROW();
+			}
+			PG_END_TRY();
+
+			/* clear view delta tuplestores */
+			if (old_tuplestore)
+				tuplestore_clear(old_tuplestore);
+			if (new_tuplestore)
+				tuplestore_clear(new_tuplestore);
+		}
+	}
+
+	/* Clean up hash entry and delete tuplestores */
+	clean_up_IVM_hash_entry(entry);
+	if (old_tuplestore)
+	{
+		dest_old->rDestroy(dest_old);
+		tuplestore_end(old_tuplestore);
+	}
+	if (new_tuplestore)
+	{
+		dest_new->rDestroy(dest_new);
+		tuplestore_end(new_tuplestore);
+	}
+
+	/* Pop the original snapshot. */
+	PopActiveSnapshot();
+
+	table_close(matviewRel, NoLock);
+
+	/* Roll back any GUC changes */
+	AtEOXact_GUC(false, save_nestlevel);
+
+	/* Restore userid and security context */
+	SetUserIdAndSecContext(save_userid, save_sec_context);
+
+	return PointerGetDatum(NULL);
+}
+
+/*
+ * rewrite_query_for_preupdate_state
+ *
+ * Rewrite the query so that base tables' RTEs will represent "pre-update"
+ * state of tables. This is necessary to calculate view delta after multiple
+ * tables are modified. xid and cid are the transaction id and command id
+ * before the first table was modified.
+ */
+static Query*
+rewrite_query_for_preupdate_state(Query *query, List *tables,
+								  TransactionId xid, CommandId cid,
+								  ParseState *pstate)
+{
+	ListCell *lc;
+	int num_rte = list_length(query->rtable);
+	int i;
+
+
+	/* register delta ENRs */
+	register_delta_ENRs(pstate, query, tables);
+
+	/* XXX: Is necessary? Is this right timing? */
+	AcquireRewriteLocks(query, true, false);
+
+	i = 1;
+	foreach(lc, query->rtable)
+	{
+		RangeTblEntry *r = (RangeTblEntry*) lfirst(lc);
+
+		ListCell *lc2;
+		foreach(lc2, tables)
+		{
+			MV_TriggerTable *table = (MV_TriggerTable *) lfirst(lc2);
+			/*
+			 * if the modified table is found then replace the original RTE with
+			 * "pre-state" RTE and append its index to the list.
+			 */
+			if (r->relid == table->table_id)
+			{
+				lfirst(lc) = get_prestate_rte(r, table, xid, cid, pstate->p_queryEnv);
+				table->rte_indexes = lappend_int(table->rte_indexes, i);
+				break;
+			}
+		}
+
+		/* finish the loop if we processed all RTE included in the original query */
+		if (i++ >= num_rte)
+			break;
+	}
+
+	return query;
+}
+
+/*
+ * register_delta_ENRs
+ *
+ * For all modified tables, make ENRs for their transition tables
+ * and register them to the queryEnv. ENR's RTEs are also appended
+ * into the list in query tree.
+ */
+static void
+register_delta_ENRs(ParseState *pstate, Query *query, List *tables)
+{
+	QueryEnvironment *queryEnv = pstate->p_queryEnv;
+	ListCell *lc;
+	RangeTblEntry	*rte;
+
+	foreach(lc, tables)
+	{
+		MV_TriggerTable *table = (MV_TriggerTable *) lfirst(lc);
+		ListCell *lc2;
+		int count;
+
+		count = 0;
+		foreach(lc2, table->old_tuplestores)
+		{
+			Tuplestorestate *oldtable = (Tuplestorestate *) lfirst(lc2);
+			EphemeralNamedRelation enr =
+				palloc(sizeof(EphemeralNamedRelationData));
+			ParseNamespaceItem *nsitem;
+
+			enr->md.name = make_delta_enr_name("old", table->table_id, count);
+			enr->md.reliddesc = table->table_id;
+			enr->md.tupdesc = NULL;
+			enr->md.enrtype = ENR_NAMED_TUPLESTORE;
+			enr->md.enrtuples = tuplestore_tuple_count(oldtable);
+			enr->reldata = oldtable;
+			register_ENR(queryEnv, enr);
+
+			nsitem = addRangeTableEntryForENR(pstate, makeRangeVar(NULL, enr->md.name, -1), true);
+			rte = nsitem->p_rte;
+			/* if base table has RLS, set security condition to enr */
+			rte->securityQuals = get_securityQuals(table->table_id, list_length(query->rtable) + 1, query);
+
+			query->rtable = lappend(query->rtable, rte);
+			table->old_rtes = lappend(table->old_rtes, rte);
+
+			count++;
+		}
+
+		count = 0;
+		foreach(lc2, table->new_tuplestores)
+		{
+			Tuplestorestate *newtable = (Tuplestorestate *) lfirst(lc2);
+			EphemeralNamedRelation enr =
+				palloc(sizeof(EphemeralNamedRelationData));
+			ParseNamespaceItem *nsitem;
+
+			enr->md.name = make_delta_enr_name("new", table->table_id, count);
+			enr->md.reliddesc = table->table_id;
+			enr->md.tupdesc = NULL;
+			enr->md.enrtype = ENR_NAMED_TUPLESTORE;
+			enr->md.enrtuples = tuplestore_tuple_count(newtable);
+			enr->reldata = newtable;
+			register_ENR(queryEnv, enr);
+
+			nsitem = addRangeTableEntryForENR(pstate, makeRangeVar(NULL, enr->md.name, -1), true);
+			rte = nsitem->p_rte;
+			/* if base table has RLS, set security condition to enr*/
+			rte->securityQuals = get_securityQuals(table->table_id, list_length(query->rtable) + 1, query);
+
+			query->rtable = lappend(query->rtable, rte);
+			table->new_rtes = lappend(table->new_rtes, rte);
+
+			count++;
+		}
+	}
+}
+
+/*
+ * get_prestate_rte
+ *
+ * Rewrite RTE of the modified table to a subquery which represents
+ * "pre-state" table. The original RTE is saved in table->rte_original.
+ */
+static RangeTblEntry*
+get_prestate_rte(RangeTblEntry *rte, MV_TriggerTable *table,
+				 TransactionId xid, CommandId cid,
+				 QueryEnvironment *queryEnv)
+{
+	StringInfoData str;
+	RawStmt *raw;
+	Query *sub;
+	Relation rel;
+	ParseState *pstate;
+	char *relname;
+	int i;
+
+	pstate = make_parsestate(NULL);
+	pstate->p_queryEnv = queryEnv;
+	pstate->p_expr_kind = EXPR_KIND_SELECT_TARGET;
+
+	/*
+	 * We can use NoLock here since AcquireRewriteLocks should
+	 * have locked the rel already.
+	 */
+	rel = table_open(table->table_id, NoLock);
+	relname = quote_qualified_identifier(
+					get_namespace_name(RelationGetNamespace(rel)),
+									   RelationGetRelationName(rel));
+	table_close(rel, NoLock);
+
+	initStringInfo(&str);
+	appendStringInfo(&str,
+		"SELECT t.* FROM %s t"
+		" WHERE (age(t.xmin) - age(%u::text::xid) > 0) OR"
+		" (t.xmin = %u AND t.cmin::text::int < %u)",
+			relname, xid, xid, cid);
+
+	for (i = 0; i < list_length(table->old_tuplestores); i++)
+	{
+		appendStringInfo(&str, " UNION ALL ");
+		appendStringInfo(&str," SELECT * FROM %s",
+			make_delta_enr_name("old", table->table_id, i));
+	}
+
+	raw = (RawStmt*)linitial(raw_parser(str.data, RAW_PARSE_DEFAULT));
+	sub = transformStmt(pstate, raw->stmt);
+
+	/* If this query has setOperations, RTEs in rtables has a subquery which contains ENR */
+	if (sub->setOperations != NULL)
+	{
+		ListCell *lc;
+
+		/* add securityQuals for tuplestores */
+		foreach (lc, sub->rtable)
+		{
+			RangeTblEntry *rte;
+			RangeTblEntry *sub_rte;
+
+			rte = (RangeTblEntry *)lfirst(lc);
+			Assert(rte->subquery != NULL);
+
+			sub_rte = (RangeTblEntry *)linitial(rte->subquery->rtable);
+			if (sub_rte->rtekind == RTE_NAMEDTUPLESTORE)
+				/* rt_index is always 1, bacause subquery has enr_rte only */
+				sub_rte->securityQuals = get_securityQuals(sub_rte->relid, 1, sub);
+		}
+	}
+
+	/* save the original RTE */
+	table->original_rte = copyObject(rte);
+
+	rte->rtekind = RTE_SUBQUERY;
+	rte->subquery = sub;
+	rte->security_barrier = false;
+	/* Clear fields that should not be set in a subquery RTE */
+	rte->relid = InvalidOid;
+	rte->relkind = 0;
+	rte->rellockmode = 0;
+	rte->tablesample = NULL;
+	rte->inh = false;			/* must not be set for a subquery */
+
+	rte->requiredPerms = 0;		/* no permission check on subquery itself */
+	rte->checkAsUser = InvalidOid;
+	rte->selectedCols = NULL;
+	rte->insertedCols = NULL;
+	rte->updatedCols = NULL;
+	rte->extraUpdatedCols = NULL;
+
+	return rte;
+}
+
+/*
+ * make_delta_enr_name
+ *
+ * Make a name for ENR of a transition table from the base table's oid.
+ * prefix will be "new" or "old" depending on its transition table kind..
+ */
+static char*
+make_delta_enr_name(const char *prefix, Oid relid, int count)
+{
+	char buf[NAMEDATALEN];
+	char *name;
+
+	snprintf(buf, NAMEDATALEN, "__ivm_%s_%u_%u", prefix, relid, count);
+	name = pstrdup(buf);
+
+	return name;
+}
+
+/*
+ * union_ENRs
+ *
+ * Make a single table delta by unionning all transition tables of the modified table
+ * whose RTE is specified by
+ */
+static RangeTblEntry*
+union_ENRs(RangeTblEntry *rte, Oid relid, List *enr_rtes, const char *prefix,
+		   QueryEnvironment *queryEnv)
+{
+	StringInfoData str;
+	ParseState	*pstate;
+	RawStmt *raw;
+	Query *sub;
+	int	i;
+	RangeTblEntry *enr_rte;
+
+	/* Create a ParseState for rewriting the view definition query */
+	pstate = make_parsestate(NULL);
+	pstate->p_queryEnv = queryEnv;
+	pstate->p_expr_kind = EXPR_KIND_SELECT_TARGET;
+
+	initStringInfo(&str);
+
+	for (i = 0; i < list_length(enr_rtes); i++)
+	{
+		if (i > 0)
+			appendStringInfo(&str, " UNION ALL ");
+
+		appendStringInfo(&str,
+			" SELECT * FROM %s",
+			make_delta_enr_name(prefix, relid, i));
+	}
+
+	raw = (RawStmt*)linitial(raw_parser(str.data, RAW_PARSE_DEFAULT));
+	sub = transformStmt(pstate, raw->stmt);
+
+	rte->rtekind = RTE_SUBQUERY;
+	rte->subquery = sub;
+	rte->security_barrier = false;
+	/* Clear fields that should not be set in a subquery RTE */
+	rte->relid = InvalidOid;
+	rte->relkind = 0;
+	rte->rellockmode = 0;
+	rte->tablesample = NULL;
+	rte->inh = false;			/* must not be set for a subquery */
+
+	rte->requiredPerms = 0;		/* no permission check on subquery itself */
+	rte->checkAsUser = InvalidOid;
+	rte->selectedCols = NULL;
+	rte->insertedCols = NULL;
+	rte->updatedCols = NULL;
+	rte->extraUpdatedCols = NULL;
+	/* if base table has RLS, set security condition to enr*/
+	enr_rte = (RangeTblEntry *)linitial(sub->rtable);
+	/* rt_index is always 1, bacause subquery has enr_rte only */
+	enr_rte->securityQuals = get_securityQuals(relid, 1, sub);
+
+	return rte;
+}
+
+/*
+ * rewrite_query_for_distinct
+ *
+ * Rewrite query for counting DISTINCT clause.
+ */
+static Query *
+rewrite_query_for_distinct(Query *query, ParseState *pstate)
+{
+	TargetEntry *tle_count;
+	FuncCall *fn;
+	Node *node;
+
+	/* Add count(*) for counting distinct tuples in views */
+	fn = makeFuncCall(list_make1(makeString("count")), NIL, COERCE_EXPLICIT_CALL, -1);
+	fn->agg_star = true;
+	if (!query->groupClause && !query->hasAggs)
+		query->groupClause = transformDistinctClause(NULL, &query->targetList, query->sortClause, false);
+
+	node = ParseFuncOrColumn(pstate, fn->funcname, NIL, NULL, fn, false, -1);
+
+	tle_count = makeTargetEntry((Expr *) node,
+								list_length(query->targetList) + 1,
+								pstrdup("__ivm_count__"),
+								false);
+	query->targetList = lappend(query->targetList, tle_count);
+	query->hasAggs = true;
+
+	return query;
+}
+
+/*
+ * calc_delta
+ *
+ * Calculate view deltas generated under the modification of a table specified
+ * by the RTE index.
+ */
+static void
+calc_delta(MV_TriggerTable *table, int rte_index, Query *query,
+			DestReceiver *dest_old, DestReceiver *dest_new,
+			TupleDesc *tupdesc_old, TupleDesc *tupdesc_new,
+			QueryEnvironment *queryEnv)
+{
+	ListCell *lc = list_nth_cell(query->rtable, rte_index - 1);
+	RangeTblEntry *rte = (RangeTblEntry *) lfirst(lc);
+
+	/* Generate old delta */
+	if (list_length(table->old_rtes) > 0)
+	{
+		/* Replace the modified table with the old delta table and calculate the old view delta. */
+		lfirst(lc) = union_ENRs(rte, table->table_id, table->old_rtes, "old", queryEnv);
+		refresh_matview_datafill(dest_old, query, queryEnv, tupdesc_old, "");
+	}
+
+	/* Generate new delta */
+	if (list_length(table->new_rtes) > 0)
+	{
+		/* Replace the modified table with the new delta table and calculate the new view delta*/
+		lfirst(lc) = union_ENRs(rte, table->table_id, table->new_rtes, "new", queryEnv);
+		refresh_matview_datafill(dest_new, query, queryEnv, tupdesc_new, "");
+	}
+}
+
+/*
+ * rewrite_query_for_postupdate_state
+ *
+ * Rewrite the query so that the specified base table's RTEs will represent
+ * "post-update" state of tables. This is called after the view delta
+ * calculation due to changes on this table finishes.
+ */
+static Query*
+rewrite_query_for_postupdate_state(Query *query, MV_TriggerTable *table, int rte_index)
+{
+	ListCell *lc = list_nth_cell(query->rtable, rte_index - 1);
+
+	/* Retore the original RTE */
+	lfirst(lc) = table->original_rte;
+
+	return query;
+}
+
+/*
+ * apply_delta
+ *
+ * Apply deltas to the materialized view. In outer join cases, this requires
+ * the view maintenance graph.
+ */
+static void
+apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *new_tuplestores,
+			TupleDesc tupdesc_old, TupleDesc tupdesc_new,
+			Query *query, bool use_count, char *count_colname)
+{
+	StringInfoData querybuf;
+	StringInfoData target_list_buf;
+	Relation	matviewRel;
+	char	   *matviewname;
+	ListCell	*lc;
+	int			i;
+	List	   *keys = NIL;
+
+
+	/*
+	 * get names of the materialized view and delta tables
+	 */
+
+	matviewRel = table_open(matviewOid, NoLock);
+	matviewname = quote_qualified_identifier(get_namespace_name(RelationGetNamespace(matviewRel)),
+											 RelationGetRelationName(matviewRel));
+
+	/*
+	 * Build parts of the maintenance queries
+	 */
+
+	initStringInfo(&querybuf);
+	initStringInfo(&target_list_buf);
+
+	/* build string of target list */
+	for (i = 0; i < matviewRel->rd_att->natts; i++)
+	{
+		Form_pg_attribute attr = TupleDescAttr(matviewRel->rd_att, i);
+		char   *resname = NameStr(attr->attname);
+
+		if (i != 0)
+			appendStringInfo(&target_list_buf, ", ");
+		appendStringInfo(&target_list_buf, "%s", quote_qualified_identifier(NULL, resname));
+	}
+
+	i = 0;
+	foreach (lc, query->targetList)
+	{
+		TargetEntry *tle = (TargetEntry *) lfirst(lc);
+		Form_pg_attribute attr = TupleDescAttr(matviewRel->rd_att, i);
+
+		i++;
+
+		if (tle->resjunk)
+			continue;
+
+		keys = lappend(keys, attr);
+	}
+
+	/* Start maintaining the materialized view. */
+	OpenMatViewIncrementalMaintenance();
+
+	/* Open SPI context. */
+	if (SPI_connect() != SPI_OK_CONNECT)
+		elog(ERROR, "SPI_connect failed");
+
+	/* For tuple deletion */
+	if (old_tuplestores && tuplestore_tuple_count(old_tuplestores) > 0)
+	{
+		EphemeralNamedRelation enr = palloc(sizeof(EphemeralNamedRelationData));
+		int				rc;
+
+		/* convert tuplestores to ENR, and register for SPI */
+		enr->md.name = pstrdup(OLD_DELTA_ENRNAME);
+		enr->md.reliddesc = InvalidOid;
+		enr->md.tupdesc = tupdesc_old;
+		enr->md.enrtype = ENR_NAMED_TUPLESTORE;
+		enr->md.enrtuples = tuplestore_tuple_count(old_tuplestores);
+		enr->reldata = old_tuplestores;
+
+		rc = SPI_register_relation(enr);
+		if (rc != SPI_OK_REL_REGISTER)
+			elog(ERROR, "SPI_register failed");
+
+		if (use_count)
+			/* apply old delta and get rows to be recalculated */
+			apply_old_delta_with_count(matviewname, OLD_DELTA_ENRNAME,
+									   keys, count_colname);
+		else
+			apply_old_delta(matviewname, OLD_DELTA_ENRNAME, keys);
+
+	}
+	/* For tuple insertion */
+	if (new_tuplestores && tuplestore_tuple_count(new_tuplestores) > 0)
+	{
+		EphemeralNamedRelation enr = palloc(sizeof(EphemeralNamedRelationData));
+		int rc;
+
+		/* convert tuplestores to ENR, and register for SPI */
+		enr->md.name = pstrdup(NEW_DELTA_ENRNAME);
+		enr->md.reliddesc = InvalidOid;
+		enr->md.tupdesc = tupdesc_new;;
+		enr->md.enrtype = ENR_NAMED_TUPLESTORE;
+		enr->md.enrtuples = tuplestore_tuple_count(new_tuplestores);
+		enr->reldata = new_tuplestores;
+
+		rc = SPI_register_relation(enr);
+		if (rc != SPI_OK_REL_REGISTER)
+			elog(ERROR, "SPI_register failed");
+
+		/* apply new delta */
+		if (use_count)
+			apply_new_delta_with_count(matviewname, NEW_DELTA_ENRNAME,
+								keys, &target_list_buf, count_colname);
+		else
+			apply_new_delta(matviewname, NEW_DELTA_ENRNAME, &target_list_buf);
+	}
+
+	/* We're done maintaining the materialized view. */
+	CloseMatViewIncrementalMaintenance();
+
+	table_close(matviewRel, NoLock);
+
+	/* Close SPI context. */
+	if (SPI_finish() != SPI_OK_FINISH)
+		elog(ERROR, "SPI_finish failed");
+}
+
+/*
+ * apply_old_delta_with_count
+ *
+ * Execute a query for applying a delta table given by deltname_old
+ * which contains tuples to be deleted from to a materialized view given by
+ * matviewname.  This is used when counting is required, that is, the view
+ * has aggregate or distinct.
+ */
+static void
+apply_old_delta_with_count(const char *matviewname, const char *deltaname_old,
+				List *keys, const char *count_colname)
+{
+	StringInfoData	querybuf;
+	char   *match_cond;
+
+	/* build WHERE condition for searching tuples to be deleted */
+	match_cond = get_matching_condition_string(keys);
+
+	/* Search for matching tuples from the view and update or delete if found. */
+	initStringInfo(&querybuf);
+	appendStringInfo(&querybuf,
+					"WITH t AS ("			/* collecting tid of target tuples in the view */
+						"SELECT diff.%s, "			/* count column */
+								"(diff.%s OPERATOR(pg_catalog.=) mv.%s) AS for_dlt, "
+								"mv.ctid "
+						"FROM %s AS mv, %s AS diff "
+						"WHERE %s"					/* tuple matching condition */
+					"), updt AS ("			/* update a tuple if this is not to be deleted */
+						"UPDATE %s AS mv SET %s = mv.%s OPERATOR(pg_catalog.-) t.%s "
+						"FROM t WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND NOT for_dlt "
+					")"
+					/* delete a tuple if this is to be deleted */
+					"DELETE FROM %s AS mv USING t "
+					"WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt",
+					count_colname,
+					count_colname, count_colname,
+					matviewname, deltaname_old,
+					match_cond,
+					matviewname, count_colname, count_colname, count_colname,
+					matviewname);
+
+	if (SPI_exec(querybuf.data, 0) != SPI_OK_DELETE)
+		elog(ERROR, "SPI_exec failed: %s", querybuf.data);
+}
+
+/*
+ * apply_old_delta
+ *
+ * Execute a query for applying a delta table given by deltname_old
+ * which contains tuples to be deleted from to a materialized view given by
+ * matviewname.  This is used when counting is not required.
+ */
+static void
+apply_old_delta(const char *matviewname, const char *deltaname_old,
+				List *keys)
+{
+	StringInfoData	querybuf;
+	StringInfoData	keysbuf;
+	char   *match_cond;
+	ListCell *lc;
+
+	/* build WHERE condition for searching tuples to be deleted */
+	match_cond = get_matching_condition_string(keys);
+
+	/* build string of keys list */
+	initStringInfo(&keysbuf);
+	foreach (lc, keys)
+	{
+		Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc);
+		char   *resname = NameStr(attr->attname);
+		appendStringInfo(&keysbuf, "%s", quote_qualified_identifier("mv", resname));
+		if (lnext(keys, lc))
+			appendStringInfo(&keysbuf, ", ");
+	}
+
+	/* Search for matching tuples from the view and update or delete if found. */
+	initStringInfo(&querybuf);
+	appendStringInfo(&querybuf,
+	"DELETE FROM %s WHERE ctid IN ("
+		"SELECT tid FROM (SELECT row_number() over (partition by %s) AS \"__ivm_row_number__\","
+								  "mv.ctid AS tid,"
+								  "diff.\"__ivm_count__\""
+						 "FROM %s AS mv, %s AS diff "
+						 "WHERE %s) v "
+					"WHERE v.\"__ivm_row_number__\" OPERATOR(pg_catalog.<=) v.\"__ivm_count__\")",
+					matviewname,
+					keysbuf.data,
+					matviewname, deltaname_old,
+					match_cond);
+
+	if (SPI_exec(querybuf.data, 0) != SPI_OK_DELETE)
+		elog(ERROR, "SPI_exec failed: %s", querybuf.data);
+}
+
+/*
+ * apply_new_delta_with_count
+ *
+ * Execute a query for applying a delta table given by deltname_new
+ * which contains tuples to be inserted into a materialized view given by
+ * matviewname.  This is used when counting is required, that is, the view
+ * has aggregate or distinct. Also, when a table in EXISTS sub queries
+ * is modified.
+ */
+static void
+apply_new_delta_with_count(const char *matviewname, const char* deltaname_new,
+				List *keys, StringInfo target_list, const char* count_colname)
+{
+	StringInfoData	querybuf;
+	StringInfoData	returning_keys;
+	ListCell	*lc;
+	char	*match_cond = "";
+
+	/* build WHERE condition for searching tuples to be updated */
+	match_cond = get_matching_condition_string(keys);
+
+	/* build string of keys list */
+	initStringInfo(&returning_keys);
+	if (keys)
+	{
+		foreach (lc, keys)
+		{
+			Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc);
+			char   *resname = NameStr(attr->attname);
+			appendStringInfo(&returning_keys, "%s", quote_qualified_identifier("mv", resname));
+			if (lnext(keys, lc))
+				appendStringInfo(&returning_keys, ", ");
+		}
+	}
+	else
+		appendStringInfo(&returning_keys, "NULL");
+
+	/* Search for matching tuples from the view and update if found or insert if not. */
+	initStringInfo(&querybuf);
+	appendStringInfo(&querybuf,
+					"WITH updt AS ("		/* update a tuple if this exists in the view */
+						"UPDATE %s AS mv SET %s = mv.%s OPERATOR(pg_catalog.+) diff.%s "
+						"FROM %s AS diff "
+						"WHERE %s "					/* tuple matching condition */
+						"RETURNING %s"				/* returning keys of updated tuples */
+					") INSERT INTO %s (%s)"	/* insert a new tuple if this doesn't existw */
+						"SELECT %s FROM %s AS diff "
+						"WHERE NOT EXISTS (SELECT 1 FROM updt AS mv WHERE %s);",
+					matviewname, count_colname, count_colname, count_colname,
+					deltaname_new,
+					match_cond,
+					returning_keys.data,
+					matviewname, target_list->data,
+					target_list->data, deltaname_new,
+					match_cond);
+
+	if (SPI_exec(querybuf.data, 0) != SPI_OK_INSERT)
+		elog(ERROR, "SPI_exec failed: %s", querybuf.data);
+}
+
+/*
+ * apply_new_delta
+ *
+ * Execute a query for applying a delta table given by deltname_new
+ * which contains tuples to be inserted into a materialized view given by
+ * matviewname.  This is used when counting is not required.
+ */
+static void
+apply_new_delta(const char *matviewname, const char *deltaname_new,
+				StringInfo target_list)
+{
+	StringInfoData	querybuf;
+
+	/* Search for matching tuples from the view and update or delete if found. */
+	initStringInfo(&querybuf);
+	appendStringInfo(&querybuf,
+					"INSERT INTO %s (%s) SELECT %s FROM ("
+						"SELECT diff.*, generate_series(1, diff.\"__ivm_count__\") "
+						"FROM %s AS diff) AS v",
+					matviewname, target_list->data, target_list->data,
+					deltaname_new);
+
+	if (SPI_exec(querybuf.data, 0) != SPI_OK_INSERT)
+		elog(ERROR, "SPI_exec failed: %s", querybuf.data);
+}
+
+/*
+ * get_matching_condition_string
+ *
+ * Build a predicate string for looking for a tuple with given keys.
+ */
+static char *
+get_matching_condition_string(List *keys)
+{
+	StringInfoData match_cond;
+	ListCell	*lc;
+
+	/* If there is no key columns, the condition is always true. */
+	if (keys == NIL)
+		return "true";
+
+	initStringInfo(&match_cond);
+	foreach (lc, keys)
+	{
+		Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc);
+		char   *resname = NameStr(attr->attname);
+		char   *mv_resname = quote_qualified_identifier("mv", resname);
+		char   *diff_resname = quote_qualified_identifier("diff", resname);
+		Oid		typid = attr->atttypid;
+
+		/* Considering NULL values, we can not use simple = operator. */
+		appendStringInfo(&match_cond, "(");
+		generate_equal(&match_cond, typid, mv_resname, diff_resname);
+		appendStringInfo(&match_cond, " OR (%s IS NULL AND %s IS NULL))",
+						 mv_resname, diff_resname);
+
+		if (lnext(keys, lc))
+			appendStringInfo(&match_cond, " AND ");
+	}
+
+	return match_cond.data;
+}
+
+/*
+ * generate_equals
+ *
+ * Generate an equality clause using given operands' default equality
+ * operator.
+ */
+static void
+generate_equal(StringInfo querybuf, Oid opttype,
+			   const char *leftop, const char *rightop)
+{
+	TypeCacheEntry *typentry;
+
+	typentry = lookup_type_cache(opttype, TYPECACHE_EQ_OPR);
+	if (!OidIsValid(typentry->eq_opr))
+		ereport(ERROR,
+				(errcode(ERRCODE_UNDEFINED_FUNCTION),
+				 errmsg("could not identify an equality operator for type %s",
+						format_type_be(opttype))));
+
+	generate_operator_clause(querybuf,
+							 leftop, opttype,
+							 typentry->eq_opr,
+							 rightop, opttype);
+}
+
+/*
+ * mv_InitHashTables
+ */
+static void
+mv_InitHashTables(void)
+{
+	HASHCTL		ctl;
+
+	memset(&ctl, 0, sizeof(ctl));
+	ctl.keysize = sizeof(Oid);
+	ctl.entrysize = sizeof(MV_TriggerHashEntry);
+	mv_trigger_info = hash_create("MV trigger info",
+								 MV_INIT_QUERYHASHSIZE,
+								 &ctl, HASH_ELEM | HASH_BLOBS);
+}
+
+/*
+ * AtAbort_IVM
+ *
+ * Clean up hash entries for all materialized views. This is called at
+ * transaction abort.
+ */
+void
+AtAbort_IVM()
+{
+	HASH_SEQ_STATUS seq;
+	MV_TriggerHashEntry *entry;
+
+	if (mv_trigger_info)
+	{
+		hash_seq_init(&seq, mv_trigger_info);
+		while ((entry = hash_seq_search(&seq)) != NULL)
+			clean_up_IVM_hash_entry(entry);
+	}
+}
+
+/*
+ * clean_up_IVM_hash_entry
+ *
+ * Clean up tuple stores and hash entries for a materialized view after its
+ * maintenance finished.
+ */
+static void
+clean_up_IVM_hash_entry(MV_TriggerHashEntry *entry)
+{
+	bool found;
+	ListCell *lc;
+
+	foreach(lc, entry->tables)
+	{
+		MV_TriggerTable *table = (MV_TriggerTable *) lfirst(lc);
+
+		list_free(table->old_tuplestores);
+		list_free(table->new_tuplestores);
+	}
+	list_free(entry->tables);
+
+	hash_search(mv_trigger_info, (void *) &entry->matview_id, HASH_REMOVE, &found);
+}
+
+/*
+ * isIvmName
+ *
+ * Check if this is a IVM hidden column from the name.
+ */
+bool
+isIvmName(const char *s)
+{
+	if (s)
+		return (strncmp(s, "__ivm_", 6) == 0);
+	return false;
+}
+
+/*
+ * get_securityQuals
+ *
+ * Get row security policy on a relation.
+ * This is used by IVM for copying RLS from base table to enr.
+ */
+static List *
+get_securityQuals(Oid relId, int rt_index, Query *query)
+{
+	ParseState *pstate;
+	Relation rel;
+	ParseNamespaceItem *nsitem;
+	RangeTblEntry *rte;
+	List *securityQuals;
+	List *withCheckOptions;
+	bool  hasRowSecurity;
+	bool  hasSubLinks;
+
+	securityQuals = NIL;
+	pstate = make_parsestate(NULL);
+
+	rel = table_open(relId, NoLock);
+	nsitem = addRangeTableEntryForRelation(pstate, rel, AccessShareLock, NULL, false, false);
+	rte = nsitem->p_rte;
+
+	get_row_security_policies(query, rte, rt_index,
+							  &securityQuals, &withCheckOptions,
+							  &hasRowSecurity, &hasSubLinks);
+
+	/*
+	 * Make sure the query is marked correctly if row level security
+	 * applies, or if the new quals had sublinks.
+	 */
+	if (hasRowSecurity)
+		query->hasRowSecurity = true;
+	if (hasSubLinks)
+		query->hasSubLinks = true;
+
+	table_close(rel, NoLock);
+
+	return securityQuals;
+}
diff --git a/src/backend/commands/tablecmds.c b/src/backend/commands/tablecmds.c
index 2cd8546d47..1c85df888e 100644
--- a/src/backend/commands/tablecmds.c
+++ b/src/backend/commands/tablecmds.c
@@ -52,6 +52,7 @@
 #include "commands/cluster.h"
 #include "commands/comment.h"
 #include "commands/defrem.h"
+#include "commands/matview.h"
 #include "commands/event_trigger.h"
 #include "commands/policy.h"
 #include "commands/sequence.h"
@@ -3441,6 +3442,14 @@ renameatt_internal(Oid myrelid,
 	targetrelation = relation_open(myrelid, AccessExclusiveLock);
 	renameatt_check(myrelid, RelationGetForm(targetrelation), recursing);
 
+	/*
+	 * Don't rename IVM columns.
+	 */
+	if (RelationIsIVM(targetrelation) && isIvmName(oldattname))
+		ereport(ERROR,
+				(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+				 errmsg("IVM column can not be renamed")));
+
 	/*
 	 * if the 'recurse' flag is set then we are supposed to rename this
 	 * attribute in all classes that inherit from 'relname' (as well as in
diff --git a/src/backend/nodes/copyfuncs.c b/src/backend/nodes/copyfuncs.c
index 0490bce664..4afc8f5826 100644
--- a/src/backend/nodes/copyfuncs.c
+++ b/src/backend/nodes/copyfuncs.c
@@ -2949,6 +2949,7 @@ _copyRangeTblEntry(const RangeTblEntry *from)
 	COPY_SCALAR_FIELD(relkind);
 	COPY_SCALAR_FIELD(rellockmode);
 	COPY_NODE_FIELD(tablesample);
+	COPY_SCALAR_FIELD(relisivm);
 	COPY_NODE_FIELD(subquery);
 	COPY_SCALAR_FIELD(security_barrier);
 	COPY_SCALAR_FIELD(jointype);
diff --git a/src/backend/nodes/equalfuncs.c b/src/backend/nodes/equalfuncs.c
index 55f41263ee..08d7805b7c 100644
--- a/src/backend/nodes/equalfuncs.c
+++ b/src/backend/nodes/equalfuncs.c
@@ -3131,6 +3131,7 @@ _equalRangeTblEntry(const RangeTblEntry *a, const RangeTblEntry *b)
 	COMPARE_SCALAR_FIELD(relkind);
 	COMPARE_SCALAR_FIELD(rellockmode);
 	COMPARE_NODE_FIELD(tablesample);
+	COMPARE_SCALAR_FIELD(relisivm);
 	COMPARE_NODE_FIELD(subquery);
 	COMPARE_SCALAR_FIELD(security_barrier);
 	COMPARE_SCALAR_FIELD(jointype);
diff --git a/src/backend/nodes/outfuncs.c b/src/backend/nodes/outfuncs.c
index cfd3ce68b4..e5a9467e99 100644
--- a/src/backend/nodes/outfuncs.c
+++ b/src/backend/nodes/outfuncs.c
@@ -3436,6 +3436,7 @@ _outRangeTblEntry(StringInfo str, const RangeTblEntry *node)
 			WRITE_CHAR_FIELD(relkind);
 			WRITE_INT_FIELD(rellockmode);
 			WRITE_NODE_FIELD(tablesample);
+			WRITE_BOOL_FIELD(relisivm);
 			break;
 		case RTE_SUBQUERY:
 			WRITE_NODE_FIELD(subquery);
diff --git a/src/backend/nodes/readfuncs.c b/src/backend/nodes/readfuncs.c
index 5165fb3b93..50cc852c32 100644
--- a/src/backend/nodes/readfuncs.c
+++ b/src/backend/nodes/readfuncs.c
@@ -1669,6 +1669,7 @@ _readRangeTblEntry(void)
 			READ_CHAR_FIELD(relkind);
 			READ_INT_FIELD(rellockmode);
 			READ_NODE_FIELD(tablesample);
+			READ_BOOL_FIELD(relisivm);
 			break;
 		case RTE_SUBQUERY:
 			READ_NODE_FIELD(subquery);
diff --git a/src/backend/parser/parse_relation.c b/src/backend/parser/parse_relation.c
index 5448cb01fa..b08c742678 100644
--- a/src/backend/parser/parse_relation.c
+++ b/src/backend/parser/parse_relation.c
@@ -36,6 +36,7 @@
 #include "utils/rel.h"
 #include "utils/syscache.h"
 #include "utils/varlena.h"
+#include "commands/matview.h"
 
 
 /*
@@ -79,7 +80,7 @@ static void expandTupleDesc(TupleDesc tupdesc, Alias *eref,
 							int count, int offset,
 							int rtindex, int sublevels_up,
 							int location, bool include_dropped,
-							List **colnames, List **colvars);
+							List **colnames, List **colvars, bool is_ivm);
 static int	specialAttNum(const char *attname);
 static bool isQueryUsingTempRelation_walker(Node *node, void *context);
 
@@ -1444,6 +1445,7 @@ addRangeTableEntry(ParseState *pstate,
 	rte->relid = RelationGetRelid(rel);
 	rte->relkind = rel->rd_rel->relkind;
 	rte->rellockmode = lockmode;
+	rte->relisivm = rel->rd_rel->relisivm;
 
 	/*
 	 * Build the list of effective column names using user-supplied aliases
@@ -1532,6 +1534,7 @@ addRangeTableEntryForRelation(ParseState *pstate,
 	rte->relid = RelationGetRelid(rel);
 	rte->relkind = rel->rd_rel->relkind;
 	rte->rellockmode = lockmode;
+	rte->relisivm = rel->rd_rel->relisivm;
 
 	/*
 	 * Build the list of effective column names using user-supplied aliases
@@ -2688,7 +2691,7 @@ expandRTE(RangeTblEntry *rte, int rtindex, int sublevels_up,
 						expandTupleDesc(tupdesc, rte->eref,
 										rtfunc->funccolcount, atts_done,
 										rtindex, sublevels_up, location,
-										include_dropped, colnames, colvars);
+										include_dropped, colnames, colvars, false);
 					}
 					else if (functypclass == TYPEFUNC_SCALAR)
 					{
@@ -2956,7 +2959,7 @@ expandRelation(Oid relid, Alias *eref, int rtindex, int sublevels_up,
 	expandTupleDesc(rel->rd_att, eref, rel->rd_att->natts, 0,
 					rtindex, sublevels_up,
 					location, include_dropped,
-					colnames, colvars);
+					colnames, colvars, RelationIsIVM(rel));
 	relation_close(rel, AccessShareLock);
 }
 
@@ -2973,7 +2976,7 @@ static void
 expandTupleDesc(TupleDesc tupdesc, Alias *eref, int count, int offset,
 				int rtindex, int sublevels_up,
 				int location, bool include_dropped,
-				List **colnames, List **colvars)
+				List **colnames, List **colvars, bool is_ivm)
 {
 	ListCell   *aliascell;
 	int			varattno;
@@ -2986,6 +2989,9 @@ expandTupleDesc(TupleDesc tupdesc, Alias *eref, int count, int offset,
 	{
 		Form_pg_attribute attr = TupleDescAttr(tupdesc, varattno);
 
+		if (is_ivm && isIvmName(NameStr(attr->attname)) && !MatViewIncrementalMaintenanceIsEnabled())
+			continue;
+
 		if (attr->attisdropped)
 		{
 			if (include_dropped)
@@ -3140,6 +3146,10 @@ expandNSItemAttrs(ParseState *pstate, ParseNamespaceItem *nsitem,
 		Var		   *varnode = (Var *) lfirst(var);
 		TargetEntry *te;
 
+		/* if transform * into columnlist with IMMV, remove IVM columns */
+		if (rte->relisivm && isIvmName(label) && !MatViewIncrementalMaintenanceIsEnabled())
+			continue;
+
 		te = makeTargetEntry((Expr *) varnode,
 							 (AttrNumber) pstate->p_next_resno++,
 							 label,
diff --git a/src/backend/rewrite/rewriteDefine.c b/src/backend/rewrite/rewriteDefine.c
index 185bf5fbff..d8a8b66196 100644
--- a/src/backend/rewrite/rewriteDefine.c
+++ b/src/backend/rewrite/rewriteDefine.c
@@ -776,7 +776,8 @@ checkRuleResultList(List *targetList, TupleDesc resultDesc, bool isSelect,
 														attr->atttypmod))));
 	}
 
-	if (i != resultDesc->natts)
+	/* No check for materialized views since this could have special columns for IVM */
+	if ((!isSelect || requireColumnNameMatch) && i != resultDesc->natts)
 		ereport(ERROR,
 				(errcode(ERRCODE_INVALID_OBJECT_DEFINITION),
 				 isSelect ?
diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat
index 6d378ff785..7d88a84682 100644
--- a/src/include/catalog/pg_proc.dat
+++ b/src/include/catalog/pg_proc.dat
@@ -11882,4 +11882,12 @@
   prorettype => 'bytea', proargtypes => 'pg_brin_minmax_multi_summary',
   prosrc => 'brin_minmax_multi_summary_send' },
 
+# IVM
+{ oid => '786', descr => 'ivm trigger (before)',
+  proname => 'IVM_immediate_before', provolatile => 'v', prorettype => 'trigger',
+  proargtypes => '', prosrc => 'IVM_immediate_before' },
+{ oid => '787', descr => 'ivm trigger (after)',
+  proname => 'IVM_immediate_maintenance', provolatile => 'v', prorettype => 'trigger',
+  proargtypes => '', prosrc => 'IVM_immediate_maintenance' },
+
 ]
diff --git a/src/include/commands/createas.h b/src/include/commands/createas.h
index 54a38491fb..c369b3ba5e 100644
--- a/src/include/commands/createas.h
+++ b/src/include/commands/createas.h
@@ -16,6 +16,7 @@
 
 #include "catalog/objectaddress.h"
 #include "nodes/params.h"
+#include "nodes/pathnodes.h"
 #include "parser/parse_node.h"
 #include "tcop/dest.h"
 #include "utils/queryenvironment.h"
@@ -25,6 +26,11 @@ extern ObjectAddress ExecCreateTableAs(ParseState *pstate, CreateTableAsStmt *st
 									   ParamListInfo params, QueryEnvironment *queryEnv,
 									   QueryCompletion *qc);
 
+extern void CreateIvmTriggersOnBaseTables(Query *qry, Oid matviewOid, bool is_create);
+extern void CreateIndexOnIMMV(Query *query, Relation matviewRel, bool is_create);
+
+extern Query *rewriteQueryForIMMV(Query *query, List *colNames);
+
 extern int	GetIntoRelEFlags(IntoClause *intoClause);
 
 extern DestReceiver *CreateIntoRelDestReceiver(IntoClause *intoClause);
diff --git a/src/include/commands/matview.h b/src/include/commands/matview.h
index a067da39d2..ec479db513 100644
--- a/src/include/commands/matview.h
+++ b/src/include/commands/matview.h
@@ -15,6 +15,7 @@
 #define MATVIEW_H
 
 #include "catalog/objectaddress.h"
+#include "fmgr.h"
 #include "nodes/params.h"
 #include "nodes/parsenodes.h"
 #include "tcop/dest.h"
@@ -23,6 +24,8 @@
 
 extern void SetMatViewPopulatedState(Relation relation, bool newstate);
 
+extern void SetMatViewIVMState(Relation relation, bool newstate);
+
 extern ObjectAddress ExecRefreshMatView(RefreshMatViewStmt *stmt, const char *queryString,
 										ParamListInfo params, QueryCompletion *qc);
 
@@ -30,4 +33,9 @@ extern DestReceiver *CreateTransientRelDestReceiver(Oid oid);
 
 extern bool MatViewIncrementalMaintenanceIsEnabled(void);
 
+extern Datum IVM_immediate_before(PG_FUNCTION_ARGS);
+extern Datum IVM_immediate_maintenance(PG_FUNCTION_ARGS);
+extern void AtAbort_IVM(void);
+extern bool isIvmName(const char *s);
+
 #endif							/* MATVIEW_H */
diff --git a/src/include/nodes/parsenodes.h b/src/include/nodes/parsenodes.h
index da02658c81..d1a754936b 100644
--- a/src/include/nodes/parsenodes.h
+++ b/src/include/nodes/parsenodes.h
@@ -1042,6 +1042,7 @@ typedef struct RangeTblEntry
 	char		relkind;		/* relation kind (see pg_class.relkind) */
 	int			rellockmode;	/* lock level that query requires on the rel */
 	struct TableSampleClause *tablesample;	/* sampling info, or NULL */
+	bool		relisivm;
 
 	/*
 	 * Fields valid for a subquery RTE (else NULL):
@@ -2545,6 +2546,7 @@ typedef struct CreateStmt
 	char	   *tablespacename; /* table space to use, or NULL */
 	char	   *accessMethod;	/* table access method */
 	bool		if_not_exists;	/* just do nothing if it already exists? */
+	bool		ivm;			/* incremental view maintenance is used by materialized view */
 } CreateStmt;
 
 /* ----------
-- 
2.17.1


--Multipart=_Fri__22_Apr_2022_14_58_01_+0900_MN3L/o2YUVF2g4zw
Content-Type: text/x-diff;
 name="v27-0007-Add-aggregates-support-in-IVM.patch"
Content-Disposition: attachment;
 filename="v27-0007-Add-aggregates-support-in-IVM.patch"
Content-Transfer-Encoding: quoted-printable



^ permalink  raw  reply  [nested|flat] 101+ messages in thread

* [PATCH v29 06/11] Add Incremental View Maintenance support
@ 2023-05-31 09:59  Yugo Nagata <[email protected]>
  0 siblings, 0 replies; 101+ messages in thread

From: Yugo Nagata @ 2023-05-31 09:59 UTC (permalink / raw)

In this implementation, AFTER triggers are used to collect
tuplestores containing transition table contents. When multiple tables
are changed, multiple AFTER triggers are invoked, then the final AFTER
trigger performs actual update of the matview. In addition, BEFORE
triggers are also used to handle global information for view
maintenance.

To calculate view deltas, we need both pre-state and post-state of base
tables. Post-update states are available in AFTER trigger, and pre-update
states can be calculated by removing inserted tuples and appending deleted
tuples. Insterted tuples are filtered using the snapshot taken before
table modiication, and deleted tuples are contained in the old transition
table.

Incrementally Maintainable Materialized Views (IMMV) can contain
duplicated tuples.

This patch also allows self-join, simultaneous updates of more than
one base table, and multiple updates of the same base table.
---
 src/backend/access/transam/xact.c |    5 +
 src/backend/commands/createas.c   |  680 +++++++++++++
 src/backend/commands/matview.c    | 1466 ++++++++++++++++++++++++++++-
 src/include/catalog/pg_proc.dat   |   10 +
 src/include/commands/createas.h   |    4 +
 src/include/commands/matview.h    |    9 +
 6 files changed, 2139 insertions(+), 35 deletions(-)

diff --git a/src/backend/access/transam/xact.c b/src/backend/access/transam/xact.c
index 8daaa535ed..cd280bdffd 100644
--- a/src/backend/access/transam/xact.c
+++ b/src/backend/access/transam/xact.c
@@ -36,6 +36,7 @@
 #include "catalog/pg_enum.h"
 #include "catalog/storage.h"
 #include "commands/async.h"
+#include "commands/matview.h"
 #include "commands/tablecmds.h"
 #include "commands/trigger.h"
 #include "common/pg_prng.h"
@@ -2803,6 +2804,7 @@ AbortTransaction(void)
 	AtAbort_Notify();
 	AtEOXact_RelationMap(false, is_parallel_worker);
 	AtAbort_Twophase();
+	AtAbort_IVM();
 
 	/*
 	 * Advertise the fact that we aborted in pg_xact (assuming that we got as
@@ -5080,6 +5082,9 @@ AbortSubTransaction(void)
 	pgstat_progress_end_command();
 	UnlockBuffers();
 
+	/* Clean up hash entries for incremental view maintenance */
+	AtAbort_IVM();
+
 	/* Reset WAL record construction state */
 	XLogResetInsertion();
 
diff --git a/src/backend/commands/createas.c b/src/backend/commands/createas.c
index e91920ca14..415f110516 100644
--- a/src/backend/commands/createas.c
+++ b/src/backend/commands/createas.c
@@ -32,15 +32,26 @@
 #include "access/xact.h"
 #include "access/xlog.h"
 #include "catalog/namespace.h"
+#include "catalog/index.h"
+#include "catalog/pg_constraint.h"
+#include "catalog/pg_inherits.h"
+#include "catalog/pg_trigger.h"
 #include "catalog/toasting.h"
 #include "commands/createas.h"
+#include "commands/defrem.h"
 #include "commands/matview.h"
 #include "commands/prepare.h"
 #include "commands/tablecmds.h"
+#include "commands/tablespace.h"
+#include "commands/trigger.h"
 #include "commands/view.h"
 #include "miscadmin.h"
+#include "optimizer/optimizer.h"
+#include "optimizer/prep.h"
 #include "nodes/makefuncs.h"
 #include "nodes/nodeFuncs.h"
+#include "parser/parser.h"
+#include "parser/parsetree.h"
 #include "parser/parse_clause.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/smgr.h"
@@ -73,6 +84,12 @@ static bool intorel_receive(TupleTableSlot *slot, DestReceiver *self);
 static void intorel_shutdown(DestReceiver *self);
 static void intorel_destroy(DestReceiver *self);
 
+static void CreateIvmTriggersOnBaseTablesRecurse(Query *qry, Node *node, Oid matviewOid,
+									 Relids *relids, bool ex_lock);
+static void CreateIvmTrigger(Oid relOid, Oid viewOid, int16 type, int16 timing, bool ex_lock);
+static void check_ivm_restriction(Node *node);
+static bool check_ivm_restriction_walker(Node *node, void *context);
+static Bitmapset *get_primary_key_attnos_from_query(Query *query, List **constraintList);
 
 /*
  * create_ctas_internal
@@ -282,6 +299,18 @@ ExecCreateTableAs(ParseState *pstate, CreateTableAsStmt *stmt,
 		save_nestlevel = NewGUCNestLevel();
 	}
 
+	if (is_matview && into->ivm)
+	{
+		/* check if the query is supported in IMMV definition */
+		if (contain_mutable_functions((Node *) query))
+			ereport(ERROR,
+					(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+					 errmsg("mutable function is not supported on incrementally maintainable materialized view"),
+					 errhint("functions must be marked IMMUTABLE")));
+
+		check_ivm_restriction((Node *) query);
+	}
+
 	if (into->skipData)
 	{
 		/*
@@ -358,6 +387,27 @@ ExecCreateTableAs(ParseState *pstate, CreateTableAsStmt *stmt,
 
 		/* Restore userid and security context */
 		SetUserIdAndSecContext(save_userid, save_sec_context);
+
+		if (into->ivm)
+		{
+			Oid matviewOid = address.objectId;
+			Relation matviewRel = table_open(matviewOid, NoLock);
+
+			/*
+			 * Mark relisivm field, if it's a matview and into->ivm is true.
+			 */
+			SetMatViewIVMState(matviewRel, true);
+
+			if (!into->skipData)
+			{
+				/* Create an index on incremental maintainable materialized view, if possible */
+				CreateIndexOnIMMV((Query *) into->viewQuery, matviewRel);
+
+				/* Create triggers on incremental maintainable materialized view */
+				CreateIvmTriggersOnBaseTables((Query *) into->viewQuery, matviewOid);
+			}
+			table_close(matviewRel, NoLock);
+		}
 	}
 
 	return address;
@@ -635,3 +685,633 @@ intorel_destroy(DestReceiver *self)
 {
 	pfree(self);
 }
+
+/*
+ * CreateIvmTriggersOnBaseTables -- create IVM triggers on all base tables
+ */
+void
+CreateIvmTriggersOnBaseTables(Query *qry, Oid matviewOid)
+{
+	Relids	relids = NULL;
+	bool	ex_lock = false;
+	RangeTblEntry *rte;
+
+	/* Immediately return if we don't have any base tables. */
+	if (list_length(qry->rtable) < 1)
+		return;
+
+	/*
+	 * If the view has more than one base tables, we need an exclusive lock
+	 * on the view so that the view would be maintained serially to avoid
+	 * the inconsistency that occurs when two base tables are modified in
+	 * concurrent transactions. However, if the view has only one table,
+	 * we can use a weaker lock.
+	 *
+	 * The type of lock should be determined here, because if we check the
+	 * view definition at maintenance time, we need to acquire a weaker lock,
+	 * and upgrading the lock level after this increases probability of
+	 * deadlock.
+	 */
+
+	rte = list_nth(qry->rtable, 0);
+	if (list_length(qry->rtable) > 1 || rte->rtekind != RTE_RELATION)
+		ex_lock = true;
+
+	CreateIvmTriggersOnBaseTablesRecurse(qry, (Node *)qry, matviewOid, &relids, ex_lock);
+
+	bms_free(relids);
+}
+
+static void
+CreateIvmTriggersOnBaseTablesRecurse(Query *qry, Node *node, Oid matviewOid,
+									 Relids *relids, bool ex_lock)
+{
+	if (node == NULL)
+		return;
+
+	/* This can recurse, so check for excessive recursion */
+	check_stack_depth();
+
+	switch (nodeTag(node))
+	{
+		case T_Query:
+			{
+				Query *query = (Query *) node;
+
+				CreateIvmTriggersOnBaseTablesRecurse(qry, (Node *)query->jointree, matviewOid, relids, ex_lock);
+			}
+			break;
+
+		case T_RangeTblRef:
+			{
+				int			rti = ((RangeTblRef *) node)->rtindex;
+				RangeTblEntry *rte = rt_fetch(rti, qry->rtable);
+
+				if (rte->rtekind == RTE_RELATION && !bms_is_member(rte->relid, *relids))
+				{
+					CreateIvmTrigger(rte->relid, matviewOid, TRIGGER_TYPE_INSERT, TRIGGER_TYPE_BEFORE, ex_lock);
+					CreateIvmTrigger(rte->relid, matviewOid, TRIGGER_TYPE_DELETE, TRIGGER_TYPE_BEFORE, ex_lock);
+					CreateIvmTrigger(rte->relid, matviewOid, TRIGGER_TYPE_UPDATE, TRIGGER_TYPE_BEFORE, ex_lock);
+					CreateIvmTrigger(rte->relid, matviewOid, TRIGGER_TYPE_TRUNCATE, TRIGGER_TYPE_BEFORE, true);
+					CreateIvmTrigger(rte->relid, matviewOid, TRIGGER_TYPE_INSERT, TRIGGER_TYPE_AFTER, ex_lock);
+					CreateIvmTrigger(rte->relid, matviewOid, TRIGGER_TYPE_DELETE, TRIGGER_TYPE_AFTER, ex_lock);
+					CreateIvmTrigger(rte->relid, matviewOid, TRIGGER_TYPE_UPDATE, TRIGGER_TYPE_AFTER, ex_lock);
+					CreateIvmTrigger(rte->relid, matviewOid, TRIGGER_TYPE_TRUNCATE, TRIGGER_TYPE_AFTER, true);
+
+					*relids = bms_add_member(*relids, rte->relid);
+				}
+			}
+			break;
+
+		case T_FromExpr:
+			{
+				FromExpr   *f = (FromExpr *) node;
+				ListCell   *l;
+
+				foreach(l, f->fromlist)
+					CreateIvmTriggersOnBaseTablesRecurse(qry, lfirst(l), matviewOid, relids, ex_lock);
+			}
+			break;
+
+		case T_JoinExpr:
+			{
+				JoinExpr   *j = (JoinExpr *) node;
+
+				CreateIvmTriggersOnBaseTablesRecurse(qry, j->larg, matviewOid, relids, ex_lock);
+				CreateIvmTriggersOnBaseTablesRecurse(qry, j->rarg, matviewOid, relids, ex_lock);
+			}
+			break;
+
+		default:
+			elog(ERROR, "unrecognized node type: %d", (int) nodeTag(node));
+	}
+}
+
+/*
+ * CreateIvmTrigger -- create IVM trigger on a base table
+ */
+static void
+CreateIvmTrigger(Oid relOid, Oid viewOid, int16 type, int16 timing, bool ex_lock)
+{
+	ObjectAddress	refaddr;
+	ObjectAddress	address;
+	CreateTrigStmt *ivm_trigger;
+	List *transitionRels = NIL;
+
+	Assert(timing == TRIGGER_TYPE_BEFORE || timing == TRIGGER_TYPE_AFTER);
+
+	refaddr.classId = RelationRelationId;
+	refaddr.objectId = viewOid;
+	refaddr.objectSubId = 0;
+
+	ivm_trigger = makeNode(CreateTrigStmt);
+	ivm_trigger->relation = NULL;
+	ivm_trigger->row = false;
+
+	ivm_trigger->timing = timing;
+	ivm_trigger->events = type;
+
+	switch (type)
+	{
+		case TRIGGER_TYPE_INSERT:
+			ivm_trigger->trigname = (timing == TRIGGER_TYPE_BEFORE ? "IVM_trigger_ins_before" : "IVM_trigger_ins_after");
+			break;
+		case TRIGGER_TYPE_DELETE:
+			ivm_trigger->trigname = (timing == TRIGGER_TYPE_BEFORE ? "IVM_trigger_del_before" : "IVM_trigger_del_after");
+			break;
+		case TRIGGER_TYPE_UPDATE:
+			ivm_trigger->trigname = (timing == TRIGGER_TYPE_BEFORE ? "IVM_trigger_upd_before" : "IVM_trigger_upd_after");
+			break;
+		case TRIGGER_TYPE_TRUNCATE:
+			ivm_trigger->trigname = (timing == TRIGGER_TYPE_BEFORE ? "IVM_trigger_truncate_before" : "IVM_trigger_truncate_after");
+			break;
+		default:
+			elog(ERROR, "unsupported trigger type");
+	}
+
+	if (timing == TRIGGER_TYPE_AFTER)
+	{
+		if (type == TRIGGER_TYPE_INSERT || type == TRIGGER_TYPE_UPDATE)
+		{
+			TriggerTransition *n = makeNode(TriggerTransition);
+			n->name = "__ivm_newtable";
+			n->isNew = true;
+			n->isTable = true;
+
+			transitionRels = lappend(transitionRels, n);
+		}
+		if (type == TRIGGER_TYPE_DELETE || type == TRIGGER_TYPE_UPDATE)
+		{
+			TriggerTransition *n = makeNode(TriggerTransition);
+			n->name = "__ivm_oldtable";
+			n->isNew = false;
+			n->isTable = true;
+
+			transitionRels = lappend(transitionRels, n);
+		}
+	}
+
+	/*
+	 * XXX: When using DELETE or UPDATE, we must use exclusive lock for now
+	 * because apply_old_delta(_with_count) uses ctid to identify the tuple
+	 * to be deleted/deleted, but doesn't work in concurrent situations.
+	 *
+	 * If the view doesn't have aggregate, distinct, or tuple duplicate,
+	 * then it would work even in concurrent situations. However, we don't have
+	 * any way to guarantee the view has a unique key before opening the IMMV
+	 * at the maintenance time because users may drop the unique index.
+	 */
+
+	if (type == TRIGGER_TYPE_DELETE || type == TRIGGER_TYPE_UPDATE)
+		ex_lock = true;
+
+	ivm_trigger->funcname =
+		(timing == TRIGGER_TYPE_BEFORE ? SystemFuncName("IVM_immediate_before") : SystemFuncName("IVM_immediate_maintenance"));
+
+	ivm_trigger->columns = NIL;
+	ivm_trigger->transitionRels = transitionRels;
+	ivm_trigger->whenClause = NULL;
+	ivm_trigger->isconstraint = false;
+	ivm_trigger->deferrable = false;
+	ivm_trigger->initdeferred = false;
+	ivm_trigger->constrrel = NULL;
+	ivm_trigger->args = list_make2(
+		makeString(DatumGetPointer(DirectFunctionCall1(oidout, ObjectIdGetDatum(viewOid)))),
+		makeString(DatumGetPointer(DirectFunctionCall1(boolout, BoolGetDatum(ex_lock))))
+		);
+
+	address = CreateTrigger(ivm_trigger, NULL, relOid, InvalidOid, InvalidOid,
+						 InvalidOid, InvalidOid, InvalidOid, NULL, true, false);
+
+	recordDependencyOn(&address, &refaddr, DEPENDENCY_AUTO);
+
+	/* Make changes-so-far visible */
+	CommandCounterIncrement();
+}
+
+/*
+ * check_ivm_restriction --- look for specify nodes in the query tree
+ */
+static void
+check_ivm_restriction(Node *node)
+{
+	check_ivm_restriction_walker(node, NULL);
+}
+
+static bool
+check_ivm_restriction_walker(Node *node, void *context)
+{
+	if (node == NULL)
+		return false;
+
+	/*
+	 * We currently don't support Sub-Query.
+	 */
+	if (IsA(node, SubPlan) || IsA(node, SubLink))
+		ereport(ERROR,
+				(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+				 errmsg("subquery is not supported on incrementally maintainable materialized view")));
+
+	/* This can recurse, so check for excessive recursion */
+	check_stack_depth();
+
+	switch (nodeTag(node))
+	{
+		case T_Query:
+			{
+				Query *qry = (Query *)node;
+				ListCell   *lc;
+				List       *vars;
+
+				/* if contained CTE, return error */
+				if (qry->cteList != NIL)
+					ereport(ERROR,
+							(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+							 errmsg("CTE is not supported on incrementally maintainable materialized view")));
+				if (qry->havingQual != NULL)
+					ereport(ERROR,
+							(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+							 errmsg(" HAVING clause is not supported on incrementally maintainable materialized view")));
+				if (qry->sortClause != NIL)	/* There is a possibility that we don't need to return an error */
+					ereport(ERROR,
+							(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+							 errmsg("ORDER BY clause is not supported on incrementally maintainable materialized view")));
+				if (qry->limitOffset != NULL || qry->limitCount != NULL)
+					ereport(ERROR,
+							(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+							 errmsg("LIMIT/OFFSET clause is not supported on incrementally maintainable materialized view")));
+				if (qry->distinctClause)
+					ereport(ERROR,
+							(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+							 errmsg("DISTINCT is not supported on incrementally maintainable materialized view")));
+				if (qry->hasDistinctOn)
+					ereport(ERROR,
+							(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+							 errmsg("DISTINCT ON is not supported on incrementally maintainable materialized view")));
+				if (qry->hasWindowFuncs)
+					ereport(ERROR,
+							(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+							 errmsg("window functions are not supported on incrementally maintainable materialized view")));
+				if (qry->groupingSets != NIL)
+					ereport(ERROR,
+							(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+							 errmsg("GROUPING SETS, ROLLUP, or CUBE clauses is not supported on incrementally maintainable materialized view")));
+				if (qry->setOperations != NULL)
+					ereport(ERROR,
+							(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+							 errmsg("UNION/INTERSECT/EXCEPT statements are not supported on incrementally maintainable materialized view")));
+				if (list_length(qry->targetList) == 0)
+					ereport(ERROR,
+							(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+							 errmsg("empty target list is not supported on incrementally maintainable materialized view")));
+				if (qry->rowMarks != NIL)
+					ereport(ERROR,
+							(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+							 errmsg("FOR UPDATE/SHARE clause is not supported on incrementally maintainable materialized view")));
+
+				/* system column restrictions */
+				vars = pull_vars_of_level((Node *) qry, 0);
+				foreach(lc, vars)
+				{
+					if (IsA(lfirst(lc), Var))
+					{
+						Var *var = (Var *) lfirst(lc);
+						/* if system column, return error */
+						if (var->varattno < 0)
+							ereport(ERROR,
+									(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+									 errmsg("system column is not supported on incrementally maintainable materialized view")));
+					}
+				}
+
+				/* restrictions for rtable */
+				foreach(lc, qry->rtable)
+				{
+					RangeTblEntry *rte = (RangeTblEntry *) lfirst(lc);
+
+					if (rte->subquery)
+						ereport(ERROR,
+								(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+								 errmsg("subquery is not supported on incrementally maintainable materialized view")));
+
+					if (rte->tablesample != NULL)
+						ereport(ERROR,
+								(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+								 errmsg("TABLESAMPLE clause is not supported on incrementally maintainable materialized view")));
+
+					if (rte->relkind == RELKIND_PARTITIONED_TABLE)
+						ereport(ERROR,
+								(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+								 errmsg("partitioned table is not supported on incrementally maintainable materialized view")));
+
+					if (rte->relkind == RELKIND_RELATION && has_superclass(rte->relid))
+						ereport(ERROR,
+								(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+								 errmsg("partitions is not supported on incrementally maintainable materialized view")));
+
+					if (rte->relkind == RELKIND_RELATION && find_inheritance_children(rte->relid, NoLock) != NIL)
+						ereport(ERROR,
+								(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+								 errmsg("inheritance parent is not supported on incrementally maintainable materialized view")));
+
+					if (rte->relkind == RELKIND_FOREIGN_TABLE)
+						ereport(ERROR,
+								(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+								 errmsg("foreign table is not supported on incrementally maintainable materialized view")));
+
+					if (rte->relkind == RELKIND_VIEW ||
+						rte->relkind == RELKIND_MATVIEW)
+						ereport(ERROR,
+								(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+								 errmsg("VIEW or MATERIALIZED VIEW is not supported on incrementally maintainable materialized view")));
+
+					if (rte->rtekind == RTE_VALUES)
+						ereport(ERROR,
+								(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+								 errmsg("VALUES is not supported on incrementally maintainable materialized view")));
+
+				}
+
+				query_tree_walker(qry, check_ivm_restriction_walker, NULL, QTW_IGNORE_RANGE_TABLE);
+
+				break;
+			}
+		case T_TargetEntry:
+			{
+				TargetEntry *tle = (TargetEntry *)node;
+				if (isIvmName(tle->resname))
+						ereport(ERROR,
+								(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+								 errmsg("column name %s is not supported on incrementally maintainable materialized view", tle->resname)));
+
+				expression_tree_walker(node, check_ivm_restriction_walker, NULL);
+				break;
+			}
+		case T_JoinExpr:
+			{
+				JoinExpr *joinexpr = (JoinExpr *)node;
+
+				if (joinexpr->jointype > JOIN_INNER)
+						ereport(ERROR,
+								(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+								 errmsg("OUTER JOIN is not supported on incrementally maintainable materialized view")));
+
+				expression_tree_walker(node, check_ivm_restriction_walker, NULL);
+			}
+			break;
+		case T_Aggref:
+			ereport(ERROR,
+					(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+					 errmsg("aggregate function is not supported on incrementally maintainable materialized view")));
+			break;
+		default:
+			expression_tree_walker(node, check_ivm_restriction_walker, (void *) context);
+			break;
+	}
+	return false;
+}
+
+/*
+ * CreateIndexOnIMMV
+ *
+ * Create a unique index on incremental maintainable materialized view.
+ * If the view definition query has a GROUP BY clause, the index is created
+ * on the columns of GROUP BY expressions. Otherwise, if the view contains
+ * all primary key attritubes of its base tables in the target list, the index
+ * is created on these attritubes. In other cases, no index is created.
+ */
+void
+CreateIndexOnIMMV(Query *query, Relation matviewRel)
+{
+	ListCell *lc;
+	IndexStmt  *index;
+	ObjectAddress address;
+	List *constraintList = NIL;
+	char		idxname[NAMEDATALEN];
+	List	   *indexoidlist = RelationGetIndexList(matviewRel);
+	ListCell   *indexoidscan;
+	Bitmapset *key_attnos;
+
+	snprintf(idxname, sizeof(idxname), "%s_index", RelationGetRelationName(matviewRel));
+
+	index = makeNode(IndexStmt);
+
+	index->unique = true;
+	index->primary = false;
+	index->isconstraint = false;
+	index->deferrable = false;
+	index->initdeferred = false;
+	index->idxname = idxname;
+	index->relation =
+		makeRangeVar(get_namespace_name(RelationGetNamespace(matviewRel)),
+					 pstrdup(RelationGetRelationName(matviewRel)),
+					 -1);
+	index->accessMethod = DEFAULT_INDEX_TYPE;
+	index->options = NIL;
+	index->tableSpace = get_tablespace_name(matviewRel->rd_rel->reltablespace);
+	index->whereClause = NULL;
+	index->indexParams = NIL;
+	index->indexIncludingParams = NIL;
+	index->excludeOpNames = NIL;
+	index->idxcomment = NULL;
+	index->indexOid = InvalidOid;
+	index->oldNumber = InvalidRelFileNumber;
+	index->oldCreateSubid = InvalidSubTransactionId;
+	index->oldFirstRelfilelocatorSubid = InvalidSubTransactionId;
+	index->transformed = true;
+	index->concurrent = false;
+	index->if_not_exists = false;
+
+	/* create index on the base tables' primary key columns */
+	key_attnos = get_primary_key_attnos_from_query(query, &constraintList);
+	if (key_attnos)
+	{
+		foreach(lc, query->targetList)
+		{
+			TargetEntry *tle = (TargetEntry *) lfirst(lc);
+			Form_pg_attribute attr = TupleDescAttr(matviewRel->rd_att, tle->resno - 1);
+
+			if (bms_is_member(tle->resno - FirstLowInvalidHeapAttributeNumber, key_attnos))
+			{
+				IndexElem  *iparam;
+
+				iparam = makeNode(IndexElem);
+				iparam->name = pstrdup(NameStr(attr->attname));
+				iparam->expr = NULL;
+				iparam->indexcolname = NULL;
+				iparam->collation = NIL;
+				iparam->opclass = NIL;
+				iparam->opclassopts = NIL;
+				iparam->ordering = SORTBY_DEFAULT;
+				iparam->nulls_ordering = SORTBY_NULLS_DEFAULT;
+				index->indexParams = lappend(index->indexParams, iparam);
+			}
+		}
+	}
+	else
+	{
+		/* create no index, just notice that an appropriate index is necessary for efficient IVM */
+		ereport(NOTICE,
+				(errmsg("could not create an index on materialized view \"%s\" automatically",
+						RelationGetRelationName(matviewRel)),
+				 errdetail("This target list does not have all the primary key columns. "),
+				 errhint("Create an index on the materialized view for efficient incremental maintenance.")));
+		return;
+	}
+
+	/* If we have a compatible index, we don't need to create another. */
+	foreach(indexoidscan, indexoidlist)
+	{
+		Oid			indexoid = lfirst_oid(indexoidscan);
+		Relation	indexRel;
+		bool		hasCompatibleIndex = false;
+
+		indexRel = index_open(indexoid, AccessShareLock);
+
+		if (CheckIndexCompatible(indexRel->rd_id,
+								index->accessMethod,
+								index->indexParams,
+								index->excludeOpNames))
+			hasCompatibleIndex = true;
+
+		index_close(indexRel, AccessShareLock);
+
+		if (hasCompatibleIndex)
+			return;
+	}
+
+	address = DefineIndex(RelationGetRelid(matviewRel),
+						  index,
+						  InvalidOid,
+						  InvalidOid,
+						  InvalidOid,
+						  -1,
+						  false, true, false, false, true);
+
+	ereport(NOTICE,
+			(errmsg("created index \"%s\" on materialized view \"%s\"",
+					idxname, RelationGetRelationName(matviewRel))));
+
+	/*
+	 * Make dependencies so that the index is dropped if any base tables's
+	 * primary key is dropped.
+	 */
+	foreach(lc, constraintList)
+	{
+		Oid constraintOid = lfirst_oid(lc);
+		ObjectAddress	refaddr;
+
+		refaddr.classId = ConstraintRelationId;
+		refaddr.objectId = constraintOid;
+		refaddr.objectSubId = 0;
+
+		recordDependencyOn(&address, &refaddr, DEPENDENCY_NORMAL);
+	}
+}
+
+
+/*
+ * get_primary_key_attnos_from_query
+ *
+ * Identify the columns in base tables' primary keys in the target list.
+ *
+ * Returns a Bitmapset of the column attnos of the primary key's columns of
+ * tables that used in the query.  The attnos are offset by
+ * FirstLowInvalidHeapAttributeNumber as same as get_primary_key_attnos.
+ *
+ * If any table has no primary key or any primary key's columns is not in
+ * the target list, return NULL.  We also return NULL if any pkey constraint
+ * is deferrable.
+ *
+ * constraintList is set to a list of the OIDs of the pkey constraints.
+ */
+static Bitmapset *
+get_primary_key_attnos_from_query(Query *query, List **constraintList)
+{
+	List *key_attnos_list = NIL;
+	ListCell *lc;
+	int i;
+	Bitmapset *keys = NULL;
+	Relids	rels_in_from;
+
+	/*
+	 * Collect primary key attributes from all tables used in query. The key attributes
+	 * sets for each table are stored in key_attnos_list in order by RTE index.
+	 */
+	foreach(lc, query->rtable)
+	{
+		RangeTblEntry *r = (RangeTblEntry*) lfirst(lc);
+		Bitmapset *key_attnos;
+		bool	has_pkey = true;
+
+		/* for tables, call get_primary_key_attnos */
+		if (r->rtekind == RTE_RELATION)
+		{
+			Oid constraintOid;
+			key_attnos = get_primary_key_attnos(r->relid, false, &constraintOid);
+			*constraintList = lappend_oid(*constraintList, constraintOid);
+			has_pkey = (key_attnos != NULL);
+		}
+		/* for other RTEs, store NULL into key_attnos_list */
+		else
+			key_attnos = NULL;
+
+		/*
+		 * If any table or subquery has no primary key or its pkey constraint is deferrable,
+		 * we cannot get key attributes for this query, so return NULL.
+		 */
+		if (!has_pkey)
+			return NULL;
+
+		key_attnos_list = lappend(key_attnos_list, key_attnos);
+	}
+
+	/* Collect key attributes appearing in the target list */
+	i = 1;
+	foreach(lc, query->targetList)
+	{
+		TargetEntry *tle = (TargetEntry *) flatten_join_alias_vars(NULL, query, lfirst(lc));
+
+		if (IsA(tle->expr, Var))
+		{
+			Var *var = (Var*) tle->expr;
+			Bitmapset *key_attnos = list_nth(key_attnos_list, var->varno - 1);
+
+			/* check if this attribute is from a base table's primary key */
+			if (bms_is_member(var->varattno - FirstLowInvalidHeapAttributeNumber, key_attnos))
+			{
+				/*
+				 * Remove found key attributes from key_attnos_list, and add this
+				 * to the result list.
+				 */
+				key_attnos = bms_del_member(key_attnos, var->varattno - FirstLowInvalidHeapAttributeNumber);
+				if (bms_is_empty(key_attnos))
+				{
+					key_attnos_list = list_delete_nth_cell(key_attnos_list, var->varno - 1);
+					key_attnos_list = list_insert_nth(key_attnos_list, var->varno - 1, NULL);
+				}
+				keys = bms_add_member(keys, i - FirstLowInvalidHeapAttributeNumber);
+			}
+		}
+		i++;
+	}
+
+	/* Collect RTE indexes of relations appearing in the FROM clause */
+	rels_in_from = get_relids_in_jointree((Node *) query->jointree, false, false);
+
+	/*
+	 * Check if all key attributes of relations in FROM are appearing in the target
+	 * list.  If an attribute remains in key_attnos_list in spite of the table is used
+	 * in FROM clause, the target is missing this key attribute, so we return NULL.
+	 */
+	i = 1;
+	foreach(lc, key_attnos_list)
+	{
+		Bitmapset *bms = (Bitmapset *)lfirst(lc);
+		if (!bms_is_empty(bms) && bms_is_member(i, rels_in_from))
+			return NULL;
+		i++;
+	}
+
+	return keys;
+}
diff --git a/src/backend/commands/matview.c b/src/backend/commands/matview.c
index ac2e74fa3f..39305f3c49 100644
--- a/src/backend/commands/matview.c
+++ b/src/backend/commands/matview.c
@@ -25,26 +25,37 @@
 #include "catalog/indexing.h"
 #include "catalog/namespace.h"
 #include "catalog/pg_am.h"
+#include "catalog/pg_depend.h"
+#include "catalog/pg_trigger.h"
 #include "catalog/pg_opclass.h"
 #include "catalog/pg_operator.h"
 #include "commands/cluster.h"
 #include "commands/matview.h"
 #include "commands/tablecmds.h"
 #include "commands/tablespace.h"
+#include "commands/createas.h"
 #include "executor/executor.h"
 #include "executor/spi.h"
+#include "executor/tstoreReceiver.h"
 #include "miscadmin.h"
+#include "nodes/makefuncs.h"
+#include "parser/analyze.h"
+#include "parser/parse_clause.h"
+#include "parser/parse_func.h"
 #include "parser/parse_relation.h"
 #include "pgstat.h"
 #include "rewrite/rewriteHandler.h"
+#include "rewrite/rowsecurity.h"
 #include "storage/lmgr.h"
 #include "storage/smgr.h"
 #include "tcop/tcopprot.h"
 #include "utils/builtins.h"
+#include "utils/fmgroids.h"
 #include "utils/lsyscache.h"
 #include "utils/rel.h"
 #include "utils/snapmgr.h"
 #include "utils/syscache.h"
+#include "utils/typcache.h"
 
 
 typedef struct
@@ -58,6 +69,52 @@ typedef struct
 	BulkInsertState bistate;	/* bulk insert state */
 } DR_transientrel;
 
+#define MV_INIT_QUERYHASHSIZE	16
+
+/*
+ * MV_TriggerHashEntry
+ *
+ * Hash entry for base tables on which IVM trigger is invoked
+ */
+typedef struct MV_TriggerHashEntry
+{
+	Oid	matview_id;			/* OID of the materialized view */
+	int	before_trig_count;	/* count of before triggers invoked */
+	int	after_trig_count;	/* count of after triggers invoked */
+
+	Snapshot	snapshot;	/* Snapshot just before table change */
+
+	List   *tables;		/* List of MV_TriggerTable */
+	bool	has_old;	/* tuples are deleted from any table? */
+	bool	has_new;	/* tuples are inserted into any table? */
+} MV_TriggerHashEntry;
+
+/*
+ * MV_TriggerTable
+ *
+ * IVM related data for tables on which the trigger is invoked.
+ */
+typedef struct MV_TriggerTable
+{
+	Oid		table_id;			/* OID of the modified table */
+	List   *old_tuplestores;	/* tuplestores for deleted tuples */
+	List   *new_tuplestores;	/* tuplestores for inserted tuples */
+
+	List   *rte_indexes;		/* List of RTE index of the modified table */
+	RangeTblEntry *original_rte;	/* the original RTE saved before rewriting query */
+
+	Relation	rel;			/* relation of the modified table */
+	TupleTableSlot *slot;		/* for checking visibility in the pre-state table */
+} MV_TriggerTable;
+
+static HTAB *mv_trigger_info = NULL;
+
+static bool in_delta_calculation = false;
+
+/* ENR name for materialized view delta */
+#define NEW_DELTA_ENRNAME "new_delta"
+#define OLD_DELTA_ENRNAME "old_delta"
+
 static int	matview_maintenance_depth = 0;
 
 static void transientrel_startup(DestReceiver *self, int operation, TupleDesc typeinfo);
@@ -65,7 +122,9 @@ static bool transientrel_receive(TupleTableSlot *slot, DestReceiver *self);
 static void transientrel_shutdown(DestReceiver *self);
 static void transientrel_destroy(DestReceiver *self);
 static uint64 refresh_matview_datafill(DestReceiver *dest, Query *query,
-									   const char *queryString);
+						 QueryEnvironment *queryEnv,
+						 TupleDesc *resultTupleDesc,
+						 const char *queryString);
 static char *make_temptable_name_n(char *tempname, int n);
 static void refresh_by_match_merge(Oid matviewOid, Oid tempOid, Oid relowner,
 								   int save_sec_context);
@@ -73,6 +132,37 @@ static void refresh_by_heap_swap(Oid matviewOid, Oid OIDNewHeap, char relpersist
 static bool is_usable_unique_index(Relation indexRel);
 static void OpenMatViewIncrementalMaintenance(void);
 static void CloseMatViewIncrementalMaintenance(void);
+static Query *get_matview_query(Relation matviewRel);
+
+static Query *rewrite_query_for_preupdate_state(Query *query, List *tables,
+								  ParseState *pstate, Oid matviewid);
+static void register_delta_ENRs(ParseState *pstate, Query *query, List *tables);
+static char *make_delta_enr_name(const char *prefix, Oid relid, int count);
+static RangeTblEntry *get_prestate_rte(RangeTblEntry *rte, MV_TriggerTable *table,
+				 QueryEnvironment *queryEnv, Oid matviewid);
+static RangeTblEntry *replace_rte_with_delta(RangeTblEntry *rte, MV_TriggerTable *table, bool is_new,
+		   QueryEnvironment *queryEnv);
+static Query *rewrite_query_for_counting(Query *query, ParseState *pstate);
+
+static void calc_delta(MV_TriggerTable *table, int rte_index, Query *query,
+			DestReceiver *dest_old, DestReceiver *dest_new,
+			TupleDesc *tupdesc_old, TupleDesc *tupdesc_new,
+			QueryEnvironment *queryEnv);
+static Query *rewrite_query_for_postupdate_state(Query *query, MV_TriggerTable *table, int rte_index);
+
+static void apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *new_tuplestores,
+			TupleDesc tupdesc_old, TupleDesc tupdesc_new,
+			Query *query);
+static void apply_old_delta(const char *matviewname, const char *deltaname_old,
+				List *keys);
+static void apply_new_delta(const char *matviewname, const char *deltaname_new,
+				StringInfo target_list);
+static char *get_matching_condition_string(List *keys);
+static void generate_equal(StringInfo querybuf, Oid opttype,
+			   const char *leftop, const char *rightop);
+
+static void mv_InitHashTables(void);
+static void clean_up_IVM_hash_entry(MV_TriggerHashEntry *entry, bool is_abort);
 
 /*
  * SetMatViewPopulatedState
@@ -114,6 +204,46 @@ SetMatViewPopulatedState(Relation relation, bool newstate)
 	CommandCounterIncrement();
 }
 
+/*
+ * SetMatViewIVMState
+ *		Mark a materialized view as IVM, or not.
+ *
+ * NOTE: caller must be holding an appropriate lock on the relation.
+ */
+void
+SetMatViewIVMState(Relation relation, bool newstate)
+{
+	Relation	pgrel;
+	HeapTuple	tuple;
+
+	Assert(relation->rd_rel->relkind == RELKIND_MATVIEW);
+
+	/*
+	 * Update relation's pg_class entry.  Crucial side-effect: other backends
+	 * (and this one too!) are sent SI message to make them rebuild relcache
+	 * entries.
+	 */
+	pgrel = table_open(RelationRelationId, RowExclusiveLock);
+	tuple = SearchSysCacheCopy1(RELOID,
+								ObjectIdGetDatum(RelationGetRelid(relation)));
+	if (!HeapTupleIsValid(tuple))
+		elog(ERROR, "cache lookup failed for relation %u",
+			 RelationGetRelid(relation));
+
+	((Form_pg_class) GETSTRUCT(tuple))->relisivm = newstate;
+
+	CatalogTupleUpdate(pgrel, &tuple->t_self, tuple);
+
+	heap_freetuple(tuple);
+	table_close(pgrel, RowExclusiveLock);
+
+	/*
+	 * Advance command counter to make the updated pg_class row locally
+	 * visible.
+	 */
+	CommandCounterIncrement();
+}
+
 /*
  * ExecRefreshMatView -- execute a REFRESH MATERIALIZED VIEW command
  *
@@ -140,8 +270,6 @@ ExecRefreshMatView(RefreshMatViewStmt *stmt, const char *queryString,
 {
 	Oid			matviewOid;
 	Relation	matviewRel;
-	RewriteRule *rule;
-	List	   *actions;
 	Query	   *dataQuery;
 	Oid			tableSpace;
 	Oid			relowner;
@@ -155,6 +283,7 @@ ExecRefreshMatView(RefreshMatViewStmt *stmt, const char *queryString,
 	int			save_sec_context;
 	int			save_nestlevel;
 	ObjectAddress address;
+	bool oldPopulated;
 
 	/* Determine strength of lock needed. */
 	concurrent = stmt->concurrent;
@@ -178,6 +307,7 @@ ExecRefreshMatView(RefreshMatViewStmt *stmt, const char *queryString,
 	SetUserIdAndSecContext(relowner,
 						   save_sec_context | SECURITY_RESTRICTED_OPERATION);
 	save_nestlevel = NewGUCNestLevel();
+	oldPopulated = RelationIsPopulated(matviewRel);
 
 	/* Make sure it is a materialized view. */
 	if (matviewRel->rd_rel->relkind != RELKIND_MATVIEW)
@@ -199,32 +329,9 @@ ExecRefreshMatView(RefreshMatViewStmt *stmt, const char *queryString,
 				 errmsg("%s and %s options cannot be used together",
 						"CONCURRENTLY", "WITH NO DATA")));
 
-	/*
-	 * Check that everything is correct for a refresh. Problems at this point
-	 * are internal errors, so elog is sufficient.
-	 */
-	if (matviewRel->rd_rel->relhasrules == false ||
-		matviewRel->rd_rules->numLocks < 1)
-		elog(ERROR,
-			 "materialized view \"%s\" is missing rewrite information",
-			 RelationGetRelationName(matviewRel));
-
-	if (matviewRel->rd_rules->numLocks > 1)
-		elog(ERROR,
-			 "materialized view \"%s\" has too many rules",
-			 RelationGetRelationName(matviewRel));
 
-	rule = matviewRel->rd_rules->rules[0];
-	if (rule->event != CMD_SELECT || !(rule->isInstead))
-		elog(ERROR,
-			 "the rule for materialized view \"%s\" is not a SELECT INSTEAD OF rule",
-			 RelationGetRelationName(matviewRel));
+	dataQuery = get_matview_query(matviewRel);
 
-	actions = rule->actions;
-	if (list_length(actions) != 1)
-		elog(ERROR,
-			 "the rule for materialized view \"%s\" is not a single action",
-			 RelationGetRelationName(matviewRel));
 
 	/*
 	 * Check that there is a unique index with no WHERE clause on one or more
@@ -259,12 +366,6 @@ ExecRefreshMatView(RefreshMatViewStmt *stmt, const char *queryString,
 					 errhint("Create a unique index with no WHERE clause on one or more columns of the materialized view.")));
 	}
 
-	/*
-	 * The stored query was rewritten at the time of the MV definition, but
-	 * has not been scribbled on by the planner.
-	 */
-	dataQuery = linitial_node(Query, actions);
-
 	/*
 	 * Check for active uses of the relation in the current transaction, such
 	 * as open scans.
@@ -292,6 +393,74 @@ ExecRefreshMatView(RefreshMatViewStmt *stmt, const char *queryString,
 		relpersistence = matviewRel->rd_rel->relpersistence;
 	}
 
+	/* delete IMMV triggers. */
+	if (RelationIsIVM(matviewRel) && stmt->skipData )
+	{
+		Relation	tgRel;
+		Relation	depRel;
+		ScanKeyData key;
+		SysScanDesc scan;
+		HeapTuple	tup;
+		ObjectAddresses *immv_triggers;
+
+		immv_triggers = new_object_addresses();
+
+		tgRel = table_open(TriggerRelationId, RowExclusiveLock);
+		depRel = table_open(DependRelationId, RowExclusiveLock);
+
+		/* search triggers that depends on IMMV. */
+		ScanKeyInit(&key,
+					Anum_pg_depend_refobjid,
+					BTEqualStrategyNumber, F_OIDEQ,
+					ObjectIdGetDatum(matviewOid));
+		scan = systable_beginscan(depRel, DependReferenceIndexId, true,
+								  NULL, 1, &key);
+		while ((tup = systable_getnext(scan)) != NULL)
+		{
+			ObjectAddress obj;
+			Form_pg_depend foundDep = (Form_pg_depend) GETSTRUCT(tup);
+
+			if (foundDep->classid == TriggerRelationId)
+			{
+				HeapTuple	tgtup;
+				ScanKeyData tgkey[1];
+				SysScanDesc tgscan;
+				Form_pg_trigger tgform;
+
+				/* Find the trigger name. */
+				ScanKeyInit(&tgkey[0],
+							Anum_pg_trigger_oid,
+							BTEqualStrategyNumber, F_OIDEQ,
+							ObjectIdGetDatum(foundDep->objid));
+
+				tgscan = systable_beginscan(tgRel, TriggerOidIndexId, true,
+											NULL, 1, tgkey);
+				tgtup = systable_getnext(tgscan);
+				if (!HeapTupleIsValid(tgtup))
+					elog(ERROR, "could not find tuple for immv trigger %u", foundDep->objid);
+
+				tgform = (Form_pg_trigger) GETSTRUCT(tgtup);
+
+				/* If trigger is created by IMMV, delete it. */
+				if (strncmp(NameStr(tgform->tgname), "IVM_trigger_", 12) == 0)
+				{
+					obj.classId = foundDep->classid;
+					obj.objectId = foundDep->objid;
+					obj.objectSubId = foundDep->refobjsubid;
+					add_exact_object_address(&obj, immv_triggers);
+				}
+				systable_endscan(tgscan);
+			}
+		}
+		systable_endscan(scan);
+
+		performMultipleDeletions(immv_triggers, DROP_RESTRICT, PERFORM_DELETION_INTERNAL);
+
+		table_close(depRel, RowExclusiveLock);
+		table_close(tgRel, RowExclusiveLock);
+		free_object_addresses(immv_triggers);
+	}
+
 	/*
 	 * Create the transient table that will receive the regenerated data. Lock
 	 * it against access by any other process until commit (by which time it
@@ -305,7 +474,7 @@ ExecRefreshMatView(RefreshMatViewStmt *stmt, const char *queryString,
 
 	/* Generate the data, if wanted. */
 	if (!stmt->skipData)
-		processed = refresh_matview_datafill(dest, dataQuery, queryString);
+		processed = refresh_matview_datafill(dest, dataQuery, NULL, NULL, queryString);
 
 	/* Make the matview match the newly generated data. */
 	if (concurrent)
@@ -340,6 +509,12 @@ ExecRefreshMatView(RefreshMatViewStmt *stmt, const char *queryString,
 			pgstat_count_heap_insert(matviewRel, processed);
 	}
 
+	if (!stmt->skipData && RelationIsIVM(matviewRel) && !oldPopulated)
+	{
+		CreateIndexOnIMMV(dataQuery, matviewRel);
+		CreateIvmTriggersOnBaseTables(dataQuery, matviewOid);
+	}
+
 	table_close(matviewRel, NoLock);
 
 	/* Roll back any GUC changes */
@@ -374,6 +549,8 @@ ExecRefreshMatView(RefreshMatViewStmt *stmt, const char *queryString,
  */
 static uint64
 refresh_matview_datafill(DestReceiver *dest, Query *query,
+						 QueryEnvironment *queryEnv,
+						 TupleDesc *resultTupleDesc,
 						 const char *queryString)
 {
 	List	   *rewritten;
@@ -410,7 +587,7 @@ refresh_matview_datafill(DestReceiver *dest, Query *query,
 	/* Create a QueryDesc, redirecting output to our tuple receiver */
 	queryDesc = CreateQueryDesc(plan, queryString,
 								GetActiveSnapshot(), InvalidSnapshot,
-								dest, NULL, NULL, 0);
+								dest, NULL, queryEnv ? queryEnv: NULL, 0);
 
 	/* call ExecutorStart to prepare the plan for execution */
 	ExecutorStart(queryDesc, 0);
@@ -420,6 +597,9 @@ refresh_matview_datafill(DestReceiver *dest, Query *query,
 
 	processed = queryDesc->estate->es_processed;
 
+	if (resultTupleDesc)
+		*resultTupleDesc = CreateTupleDescCopy(queryDesc->tupDesc);
+
 	/* and clean up */
 	ExecutorFinish(queryDesc);
 	ExecutorEnd(queryDesc);
@@ -931,3 +1111,1219 @@ CloseMatViewIncrementalMaintenance(void)
 	matview_maintenance_depth--;
 	Assert(matview_maintenance_depth >= 0);
 }
+
+/*
+ * get_matview_query - get the Query from a matview's _RETURN rule.
+ */
+static Query *
+get_matview_query(Relation matviewRel)
+{
+	RewriteRule *rule;
+	List * actions;
+
+	/*
+	 * Check that everything is correct for a refresh. Problems at this point
+	 * are internal errors, so elog is sufficient.
+	 */
+	if (matviewRel->rd_rel->relhasrules == false ||
+		matviewRel->rd_rules->numLocks < 1)
+		elog(ERROR,
+			 "materialized view \"%s\" is missing rewrite information",
+			 RelationGetRelationName(matviewRel));
+
+	if (matviewRel->rd_rules->numLocks > 1)
+		elog(ERROR,
+			 "materialized view \"%s\" has too many rules",
+			 RelationGetRelationName(matviewRel));
+
+	rule = matviewRel->rd_rules->rules[0];
+	if (rule->event != CMD_SELECT || !(rule->isInstead))
+		elog(ERROR,
+			 "the rule for materialized view \"%s\" is not a SELECT INSTEAD OF rule",
+			 RelationGetRelationName(matviewRel));
+
+	actions = rule->actions;
+	if (list_length(actions) != 1)
+		elog(ERROR,
+			 "the rule for materialized view \"%s\" is not a single action",
+			 RelationGetRelationName(matviewRel));
+
+	/*
+	 * The stored query was rewritten at the time of the MV definition, but
+	 * has not been scribbled on by the planner.
+	 */
+	return linitial_node(Query, actions);
+}
+
+
+/* ----------------------------------------------------
+ *		Incremental View Maintenance routines
+ * ---------------------------------------------------
+ */
+
+/*
+ * IVM_immediate_before
+ *
+ * IVM trigger function invoked before base table is modified. If this is
+ * invoked firstly in the same statement, we save the transaction id and the
+ * command id at that time.
+ */
+Datum
+IVM_immediate_before(PG_FUNCTION_ARGS)
+{
+	TriggerData *trigdata = (TriggerData *) fcinfo->context;
+	char	   *matviewOid_text = trigdata->tg_trigger->tgargs[0];
+	char	   *ex_lock_text = trigdata->tg_trigger->tgargs[1];
+	Oid			matviewOid;
+	MV_TriggerHashEntry *entry;
+	bool	found;
+	bool	ex_lock;
+
+	matviewOid = DatumGetObjectId(DirectFunctionCall1(oidin, CStringGetDatum(matviewOid_text)));
+	ex_lock = DatumGetBool(DirectFunctionCall1(boolin, CStringGetDatum(ex_lock_text)));
+
+	/* If the view has more than one tables, we have to use an exclusive lock. */
+	if (ex_lock)
+	{
+		/*
+		 * Wait for concurrent transactions which update this materialized view at
+		 * READ COMMITED. This is needed to see changes committed in other
+		 * transactions. No wait and raise an error at REPEATABLE READ or
+		 * SERIALIZABLE to prevent update anomalies of matviews.
+		 * XXX: dead-lock is possible here.
+		 */
+		if (!IsolationUsesXactSnapshot())
+			LockRelationOid(matviewOid, ExclusiveLock);
+		else if (!ConditionalLockRelationOid(matviewOid, ExclusiveLock))
+		{
+			/* try to throw error by name; relation could be deleted... */
+			char	   *relname = get_rel_name(matviewOid);
+
+			if (!relname)
+				ereport(ERROR,
+						(errcode(ERRCODE_LOCK_NOT_AVAILABLE),
+						errmsg("could not obtain lock on materialized view during incremental maintenance")));
+
+			ereport(ERROR,
+					(errcode(ERRCODE_LOCK_NOT_AVAILABLE),
+					errmsg("could not obtain lock on materialized view \"%s\" during incremental maintenance",
+							relname)));
+		}
+	}
+	else
+		LockRelationOid(matviewOid, RowExclusiveLock);
+
+	/*
+	 * On the first call initialize the hashtable
+	 */
+	if (!mv_trigger_info)
+		mv_InitHashTables();
+
+	entry = (MV_TriggerHashEntry *) hash_search(mv_trigger_info,
+											  (void *) &matviewOid,
+											  HASH_ENTER, &found);
+
+	/* On the first BEFORE to update the view, initialize trigger data */
+	if (!found)
+	{
+		/*
+		 * Get a snapshot just before the table was modified for checking
+		 * tuple visibility in the pre-update state of the table.
+		 */
+		Snapshot snapshot = GetActiveSnapshot();
+
+		entry->matview_id = matviewOid;
+		entry->before_trig_count = 0;
+		entry->after_trig_count = 0;
+		entry->snapshot = RegisterSnapshot(snapshot);
+		entry->tables = NIL;
+		entry->has_old = false;
+		entry->has_new = false;
+	}
+
+	entry->before_trig_count++;
+
+	return PointerGetDatum(NULL);
+}
+
+/*
+ * IVM_immediate_maintenance
+ *
+ * IVM trigger function invoked after base table is modified.
+ * For each table, tuplestores of transition tables are collected.
+ * and after the last modification
+ */
+Datum
+IVM_immediate_maintenance(PG_FUNCTION_ARGS)
+{
+	TriggerData *trigdata = (TriggerData *) fcinfo->context;
+	Relation	rel;
+	Oid			relid;
+	Oid			matviewOid;
+	Query	   *query;
+	Query	   *rewritten = NULL;
+	char	   *matviewOid_text = trigdata->tg_trigger->tgargs[0];
+	Relation	matviewRel;
+	int old_depth = matview_maintenance_depth;
+
+	Oid			relowner;
+	Tuplestorestate *old_tuplestore = NULL;
+	Tuplestorestate *new_tuplestore = NULL;
+	DestReceiver *dest_new = NULL, *dest_old = NULL;
+	Oid			save_userid;
+	int			save_sec_context;
+	int			save_nestlevel;
+
+	MV_TriggerHashEntry *entry;
+	MV_TriggerTable		*table;
+	bool	found;
+
+	ParseState		 *pstate;
+	QueryEnvironment *queryEnv = create_queryEnv();
+	MemoryContext	oldcxt;
+	ListCell   *lc;
+	int			i;
+
+
+	/* Create a ParseState for rewriting the view definition query */
+	pstate = make_parsestate(NULL);
+	pstate->p_queryEnv = queryEnv;
+	pstate->p_expr_kind = EXPR_KIND_SELECT_TARGET;
+
+	rel = trigdata->tg_relation;
+	relid = rel->rd_id;
+
+	matviewOid = DatumGetObjectId(DirectFunctionCall1(oidin, CStringGetDatum(matviewOid_text)));
+
+	/*
+	 * On the first call initialize the hashtable
+	 */
+	if (!mv_trigger_info)
+		mv_InitHashTables();
+
+	/* get the entry for this materialized view */
+	entry = (MV_TriggerHashEntry *) hash_search(mv_trigger_info,
+											  (void *) &matviewOid,
+											  HASH_FIND, &found);
+	Assert (found && entry != NULL);
+	entry->after_trig_count++;
+
+	/* search the entry for the modified table and create new entry if not found */
+	found = false;
+	foreach(lc, entry->tables)
+	{
+		table = (MV_TriggerTable *) lfirst(lc);
+		if (table->table_id == relid)
+		{
+			found = true;
+			break;
+		}
+	}
+	if (!found)
+	{
+		oldcxt = MemoryContextSwitchTo(TopTransactionContext);
+
+		table = (MV_TriggerTable *) palloc0(sizeof(MV_TriggerTable));
+		table->table_id = relid;
+		table->old_tuplestores = NIL;
+		table->new_tuplestores = NIL;
+		table->rte_indexes = NIL;
+		table->slot = MakeSingleTupleTableSlot(RelationGetDescr(rel), table_slot_callbacks(rel));
+		table->rel = table_open(RelationGetRelid(rel), NoLock);
+		entry->tables = lappend(entry->tables, table);
+
+		MemoryContextSwitchTo(oldcxt);
+	}
+
+	/* Save the transition tables and make a request to not free immediately */
+	if (trigdata->tg_oldtable)
+	{
+		oldcxt = MemoryContextSwitchTo(TopTransactionContext);
+		table->old_tuplestores = lappend(table->old_tuplestores, trigdata->tg_oldtable);
+		entry->has_old = true;
+		MemoryContextSwitchTo(oldcxt);
+	}
+	if (trigdata->tg_newtable)
+	{
+		oldcxt = MemoryContextSwitchTo(TopTransactionContext);
+		table->new_tuplestores = lappend(table->new_tuplestores, trigdata->tg_newtable);
+		entry->has_new = true;
+		MemoryContextSwitchTo(oldcxt);
+	}
+	if (entry->has_new || entry->has_old)
+	{
+		CmdType cmd;
+
+		if (TRIGGER_FIRED_BY_INSERT(trigdata->tg_event))
+			cmd = CMD_INSERT;
+		else if (TRIGGER_FIRED_BY_DELETE(trigdata->tg_event))
+			cmd = CMD_DELETE;
+		else if (TRIGGER_FIRED_BY_UPDATE(trigdata->tg_event))
+			cmd = CMD_UPDATE;
+		else
+			elog(ERROR,"unsupported trigger type");
+
+		/* Prolong lifespan of transition tables to the end of the last AFTER trigger */
+		SetTransitionTablePreserved(relid, cmd);
+	}
+
+
+	/* If this is not the last AFTER trigger call, immediately exit. */
+	Assert (entry->before_trig_count >= entry->after_trig_count);
+	if (entry->before_trig_count != entry->after_trig_count)
+		return PointerGetDatum(NULL);
+
+	/*
+	 * If this is the last AFTER trigger call, continue and update the view.
+	 */
+
+	/*
+	 * Advance command counter to make the updated base table row locally
+	 * visible.
+	 */
+	CommandCounterIncrement();
+
+	matviewRel = table_open(matviewOid, NoLock);
+
+	/* Make sure it is a materialized view. */
+	Assert(matviewRel->rd_rel->relkind == RELKIND_MATVIEW);
+
+	/*
+	 * Get and push the latast snapshot to see any changes which is committed
+	 * during waiting in other transactions at READ COMMITTED level.
+	 */
+	PushActiveSnapshot(GetTransactionSnapshot());
+
+	/*
+	 * Check for active uses of the relation in the current transaction, such
+	 * as open scans.
+	 *
+	 * NB: We count on this to protect us against problems with refreshing the
+	 * data using TABLE_INSERT_FROZEN.
+	 */
+	CheckTableNotInUse(matviewRel, "refresh a materialized view incrementally");
+
+	/*
+	 * Switch to the owner's userid, so that any functions are run as that
+	 * user.  Also arrange to make GUC variable changes local to this command.
+	 * We will switch modes when we are about to execute user code.
+	 */
+	relowner = matviewRel->rd_rel->relowner;
+	GetUserIdAndSecContext(&save_userid, &save_sec_context);
+	SetUserIdAndSecContext(relowner,
+						   save_sec_context | SECURITY_RESTRICTED_OPERATION);
+	save_nestlevel = NewGUCNestLevel();
+
+	/* get view query*/
+	query = get_matview_query(matviewRel);
+
+	/*
+	 * When a base table is truncated, the view content will be empty if the
+	 * view definition query does not contain an aggregate without a GROUP clause.
+	 * Therefore, such views can be truncated.
+	 */
+	if (TRIGGER_FIRED_BY_TRUNCATE(trigdata->tg_event))
+	{
+		ExecuteTruncateGuts(list_make1(matviewRel), list_make1_oid(matviewOid),
+							NIL, DROP_RESTRICT, false, false);
+
+		/* Clean up hash entry and delete tuplestores */
+		clean_up_IVM_hash_entry(entry, false);
+
+		/* Pop the original snapshot. */
+		PopActiveSnapshot();
+
+		table_close(matviewRel, NoLock);
+
+		/* Roll back any GUC changes */
+		AtEOXact_GUC(false, save_nestlevel);
+
+		/* Restore userid and security context */
+		SetUserIdAndSecContext(save_userid, save_sec_context);
+
+		return PointerGetDatum(NULL);
+	}
+
+	/*
+	 * rewrite query for calculating deltas
+	 */
+
+	rewritten = copyObject(query);
+
+	/* Replace resnames in a target list with materialized view's attnames */
+	i = 0;
+	foreach (lc, rewritten->targetList)
+	{
+		TargetEntry *tle = (TargetEntry *) lfirst(lc);
+		Form_pg_attribute attr = TupleDescAttr(matviewRel->rd_att, i);
+		char *resname = NameStr(attr->attname);
+
+		tle->resname = pstrdup(resname);
+		i++;
+	}
+
+	/* Set all tables in the query to pre-update state */
+	rewritten = rewrite_query_for_preupdate_state(rewritten, entry->tables,
+												  pstate, matviewOid);
+	/* Rewrite for counting duplicated tuples */
+	rewritten = rewrite_query_for_counting(rewritten, pstate);
+
+	/* Create tuplestores to store view deltas */
+	if (entry->has_old)
+	{
+		oldcxt = MemoryContextSwitchTo(TopTransactionContext);
+
+		old_tuplestore = tuplestore_begin_heap(false, false, work_mem);
+		dest_old = CreateDestReceiver(DestTuplestore);
+		SetTuplestoreDestReceiverParams(dest_old,
+									old_tuplestore,
+									TopTransactionContext,
+									false,
+									NULL,
+									NULL);
+
+		MemoryContextSwitchTo(oldcxt);
+	}
+	if (entry->has_new)
+	{
+		oldcxt = MemoryContextSwitchTo(TopTransactionContext);
+
+		new_tuplestore = tuplestore_begin_heap(false, false, work_mem);
+		dest_new = CreateDestReceiver(DestTuplestore);
+		SetTuplestoreDestReceiverParams(dest_new,
+									new_tuplestore,
+									TopTransactionContext,
+									false,
+									NULL,
+									NULL);
+		MemoryContextSwitchTo(oldcxt);
+	}
+
+	/* for all modified tables */
+	foreach(lc, entry->tables)
+	{
+		ListCell *lc2;
+
+		table = (MV_TriggerTable *) lfirst(lc);
+
+		/* loop for self-join */
+		foreach(lc2, table->rte_indexes)
+		{
+			int	rte_index = lfirst_int(lc2);
+			TupleDesc		tupdesc_old;
+			TupleDesc		tupdesc_new;
+
+			/* calculate delta tables */
+			calc_delta(table, rte_index, rewritten, dest_old, dest_new,
+					   &tupdesc_old, &tupdesc_new, queryEnv);
+
+			/* Set the table in the query to post-update state */
+			rewritten = rewrite_query_for_postupdate_state(rewritten, table, rte_index);
+
+			PG_TRY();
+			{
+				/* apply the delta tables to the materialized view */
+				apply_delta(matviewOid, old_tuplestore, new_tuplestore,
+							tupdesc_old, tupdesc_new, query);
+			}
+			PG_CATCH();
+			{
+				matview_maintenance_depth = old_depth;
+				PG_RE_THROW();
+			}
+			PG_END_TRY();
+
+			/* clear view delta tuplestores */
+			if (old_tuplestore)
+				tuplestore_clear(old_tuplestore);
+			if (new_tuplestore)
+				tuplestore_clear(new_tuplestore);
+		}
+	}
+
+	/* Clean up hash entry and delete tuplestores */
+	clean_up_IVM_hash_entry(entry, false);
+	if (old_tuplestore)
+	{
+		dest_old->rDestroy(dest_old);
+		tuplestore_end(old_tuplestore);
+	}
+	if (new_tuplestore)
+	{
+		dest_new->rDestroy(dest_new);
+		tuplestore_end(new_tuplestore);
+	}
+
+	/* Pop the original snapshot. */
+	PopActiveSnapshot();
+
+	table_close(matviewRel, NoLock);
+
+	/* Roll back any GUC changes */
+	AtEOXact_GUC(false, save_nestlevel);
+
+	/* Restore userid and security context */
+	SetUserIdAndSecContext(save_userid, save_sec_context);
+
+	return PointerGetDatum(NULL);
+}
+
+/*
+ * rewrite_query_for_preupdate_state
+ *
+ * Rewrite the query so that base tables' RTEs will represent "pre-update"
+ * state of tables. This is necessary to calculate view delta after multiple
+ * tables are modified.
+ */
+static Query*
+rewrite_query_for_preupdate_state(Query *query, List *tables,
+								  ParseState *pstate, Oid matviewid)
+{
+	ListCell *lc;
+	int num_rte = list_length(query->rtable);
+	int i;
+
+
+	/* register delta ENRs */
+	register_delta_ENRs(pstate, query, tables);
+
+	/* XXX: Is necessary? Is this right timing? */
+	AcquireRewriteLocks(query, true, false);
+
+	i = 1;
+	foreach(lc, query->rtable)
+	{
+		RangeTblEntry *r = (RangeTblEntry*) lfirst(lc);
+
+		ListCell *lc2;
+		foreach(lc2, tables)
+		{
+			MV_TriggerTable *table = (MV_TriggerTable *) lfirst(lc2);
+			/*
+			 * if the modified table is found then replace the original RTE with
+			 * "pre-state" RTE and append its index to the list.
+			 */
+			if (r->relid == table->table_id)
+			{
+				List *securityQuals;
+				List *withCheckOptions;
+				bool  hasRowSecurity;
+				bool  hasSubLinks;
+
+				RangeTblEntry *rte_pre = get_prestate_rte(r, table, pstate->p_queryEnv, matviewid);
+
+				/*
+				 * Set a row security poslicies of the modified table to the subquery RTE which
+				 * represents the pre-update state of the table.
+				 */
+				get_row_security_policies(query, table->original_rte, i,
+										  &securityQuals, &withCheckOptions,
+										  &hasRowSecurity, &hasSubLinks);
+
+				if (hasRowSecurity)
+				{
+					query->hasRowSecurity = true;
+					rte_pre->security_barrier = true;
+				}
+				if (hasSubLinks)
+					query->hasSubLinks = true;
+
+				rte_pre->securityQuals = securityQuals;
+				lfirst(lc) = rte_pre;
+
+				table->rte_indexes = lappend_int(table->rte_indexes, i);
+				break;
+			}
+		}
+
+		/* finish the loop if we processed all RTE included in the original query */
+		if (i++ >= num_rte)
+			break;
+	}
+
+	return query;
+}
+
+/*
+ * register_delta_ENRs
+ *
+ * For all modified tables, make ENRs for their transition tables
+ * and register them to the queryEnv. ENR's RTEs are also appended
+ * into the list in query tree.
+ */
+static void
+register_delta_ENRs(ParseState *pstate, Query *query, List *tables)
+{
+	QueryEnvironment *queryEnv = pstate->p_queryEnv;
+	ListCell *lc;
+	RangeTblEntry	*rte;
+
+	foreach(lc, tables)
+	{
+		MV_TriggerTable *table = (MV_TriggerTable *) lfirst(lc);
+		ListCell *lc2;
+		int count;
+
+		count = 0;
+		foreach(lc2, table->old_tuplestores)
+		{
+			Tuplestorestate *oldtable = (Tuplestorestate *) lfirst(lc2);
+			EphemeralNamedRelation enr =
+				palloc(sizeof(EphemeralNamedRelationData));
+			ParseNamespaceItem *nsitem;
+
+			enr->md.name = make_delta_enr_name("old", table->table_id, count);
+			enr->md.reliddesc = table->table_id;
+			enr->md.tupdesc = NULL;
+			enr->md.enrtype = ENR_NAMED_TUPLESTORE;
+			enr->md.enrtuples = tuplestore_tuple_count(oldtable);
+			enr->reldata = oldtable;
+			register_ENR(queryEnv, enr);
+
+			nsitem = addRangeTableEntryForENR(pstate, makeRangeVar(NULL, enr->md.name, -1), true);
+			rte = nsitem->p_rte;
+
+			query->rtable = lappend(query->rtable, rte);
+
+			count++;
+		}
+
+		count = 0;
+		foreach(lc2, table->new_tuplestores)
+		{
+			Tuplestorestate *newtable = (Tuplestorestate *) lfirst(lc2);
+			EphemeralNamedRelation enr =
+				palloc(sizeof(EphemeralNamedRelationData));
+			ParseNamespaceItem *nsitem;
+
+			enr->md.name = make_delta_enr_name("new", table->table_id, count);
+			enr->md.reliddesc = table->table_id;
+			enr->md.tupdesc = NULL;
+			enr->md.enrtype = ENR_NAMED_TUPLESTORE;
+			enr->md.enrtuples = tuplestore_tuple_count(newtable);
+			enr->reldata = newtable;
+			register_ENR(queryEnv, enr);
+
+			nsitem = addRangeTableEntryForENR(pstate, makeRangeVar(NULL, enr->md.name, -1), true);
+			rte = nsitem->p_rte;
+
+			query->rtable = lappend(query->rtable, rte);
+
+			count++;
+		}
+	}
+}
+
+#define DatumGetItemPointer(X)	 ((ItemPointer) DatumGetPointer(X))
+#define PG_GETARG_ITEMPOINTER(n) DatumGetItemPointer(PG_GETARG_DATUM(n))
+
+/*
+ * ivm_visible_in_prestate
+ *
+ * Check visibility of a tuple specified by the tableoid and item pointer
+ * using the snapshot taken just before the table was modified.
+ */
+Datum
+ivm_visible_in_prestate(PG_FUNCTION_ARGS)
+{
+	Oid			tableoid = PG_GETARG_OID(0);
+	ItemPointer itemPtr = PG_GETARG_ITEMPOINTER(1);
+	Oid			matviewOid = PG_GETARG_OID(2);
+	MV_TriggerHashEntry *entry;
+	MV_TriggerTable		*table = NULL;
+	ListCell   *lc;
+	bool	found;
+	bool	result;
+
+	if (!in_delta_calculation)
+		ereport(ERROR,
+				(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+				 errmsg("ivm_visible_in_prestate can be called only in delta calculation")));
+
+	entry = (MV_TriggerHashEntry *) hash_search(mv_trigger_info,
+											  (void *) &matviewOid,
+											  HASH_FIND, &found);
+	Assert (found && entry != NULL);
+
+	foreach(lc, entry->tables)
+	{
+		table = (MV_TriggerTable *) lfirst(lc);
+		if (table->table_id == tableoid)
+			break;
+	}
+
+	Assert (table != NULL);
+
+	result = table_tuple_fetch_row_version(table->rel, itemPtr, entry->snapshot, table->slot);
+
+	PG_RETURN_BOOL(result);
+}
+
+/*
+ * get_prestate_rte
+ *
+ * Rewrite RTE of the modified table to a subquery which represents
+ * "pre-state" table. The original RTE is saved in table->rte_original.
+ */
+static RangeTblEntry*
+get_prestate_rte(RangeTblEntry *rte, MV_TriggerTable *table,
+				 QueryEnvironment *queryEnv, Oid matviewid)
+{
+	StringInfoData str;
+	RawStmt *raw;
+	Query *subquery;
+	Relation rel;
+	ParseState *pstate;
+	char *relname;
+	int i;
+
+	pstate = make_parsestate(NULL);
+	pstate->p_queryEnv = queryEnv;
+	pstate->p_expr_kind = EXPR_KIND_SELECT_TARGET;
+
+	/*
+	 * We can use NoLock here since AcquireRewriteLocks should
+	 * have locked the relation already.
+	 */
+	rel = table_open(table->table_id, NoLock);
+	relname = quote_qualified_identifier(
+					get_namespace_name(RelationGetNamespace(rel)),
+									   RelationGetRelationName(rel));
+	table_close(rel, NoLock);
+
+	/*
+	 * Filtering inserted row using the snapshot taken before the table
+	 * is modified. ctid is required for maintaining outer join views.
+	 */
+	initStringInfo(&str);
+	appendStringInfo(&str,
+		"SELECT t.* FROM %s t"
+		" WHERE pg_catalog.ivm_visible_in_prestate(t.tableoid, t.ctid ,%d::pg_catalog.oid)",
+			relname, matviewid);
+
+	/*
+	 * Append deleted rows contained in old transition tables.
+	 */
+	for (i = 0; i < list_length(table->old_tuplestores); i++)
+	{
+		appendStringInfo(&str, " UNION ALL ");
+		appendStringInfo(&str," SELECT * FROM %s",
+			make_delta_enr_name("old", table->table_id, i));
+	}
+
+	/* Get a subquery representing pre-state of the table */
+	raw = (RawStmt*)linitial(raw_parser(str.data, RAW_PARSE_DEFAULT));
+	subquery = transformStmt(pstate, raw->stmt);
+
+	/* save the original RTE */
+	table->original_rte = copyObject(rte);
+
+	rte->rtekind = RTE_SUBQUERY;
+	rte->subquery = subquery;
+	rte->security_barrier = false;
+
+	/* Clear fields that should not be set in a subquery RTE */
+	rte->relid = InvalidOid;
+	rte->relkind = 0;
+	rte->rellockmode = 0;
+	rte->tablesample = NULL;
+	rte->perminfoindex = 0;         /* no permission checking for this RTE */
+	rte->inh = false;			/* must not be set for a subquery */
+
+	return rte;
+}
+
+/*
+ * make_delta_enr_name
+ *
+ * Make a name for ENR of a transition table from the base table's oid.
+ * prefix will be "new" or "old" depending on its transition table kind..
+ */
+static char*
+make_delta_enr_name(const char *prefix, Oid relid, int count)
+{
+	char buf[NAMEDATALEN];
+	char *name;
+
+	snprintf(buf, NAMEDATALEN, "__ivm_%s_%u_%u", prefix, relid, count);
+	name = pstrdup(buf);
+
+	return name;
+}
+
+/*
+ * replace_rte_with_delta
+ *
+ * Replace RTE of the modified table with a single table delta that combine its
+ * all transition tables.
+ */
+static RangeTblEntry*
+replace_rte_with_delta(RangeTblEntry *rte, MV_TriggerTable *table, bool is_new,
+					   QueryEnvironment *queryEnv)
+{
+	Oid relid = table->table_id;
+	StringInfoData str;
+	ParseState	*pstate;
+	RawStmt *raw;
+	Query *sub;
+	int		num_tuplestores = list_length(is_new ? table->new_tuplestores : table->old_tuplestores);
+	int		i;
+
+	/* the previous RTE must be a subquery which represents "pre-state" table */
+	Assert(rte->rtekind == RTE_SUBQUERY);
+
+	/* Create a ParseState for rewriting the view definition query */
+	pstate = make_parsestate(NULL);
+	pstate->p_queryEnv = queryEnv;
+	pstate->p_expr_kind = EXPR_KIND_SELECT_TARGET;
+
+	initStringInfo(&str);
+
+	for (i = 0; i < num_tuplestores; i++)
+	{
+		if (i > 0)
+			appendStringInfo(&str, " UNION ALL ");
+
+		appendStringInfo(&str,
+			" SELECT * FROM %s",
+			make_delta_enr_name(is_new ? "new" : "old", relid, i));
+	}
+
+	raw = (RawStmt*)linitial(raw_parser(str.data, RAW_PARSE_DEFAULT));
+	sub = transformStmt(pstate, raw->stmt);
+
+	/*
+	 * Update the subquery so that it represent the combined transition
+	 * table.  Note that we leave the security_barrier and securityQuals
+	 * fields so that the subquery relation can be protected by the RLS
+	 * policy as same as the modified table.
+	 */
+	rte->rtekind = RTE_SUBQUERY;
+	rte->subquery = sub;
+
+	return rte;
+}
+
+/*
+ * rewrite_query_for_counting
+ *
+ * Rewrite query for counting duplicated tuples.
+ */
+static Query *
+rewrite_query_for_counting(Query *query, ParseState *pstate)
+{
+	TargetEntry *tle_count;
+	FuncCall *fn;
+	Node *node;
+
+	/* Add count(*) for counting distinct tuples in views */
+	fn = makeFuncCall(SystemFuncName("count"), NIL, COERCE_EXPLICIT_CALL, -1);
+	fn->agg_star = true;
+	if (!query->groupClause && !query->hasAggs)
+		query->groupClause = transformDistinctClause(NULL, &query->targetList, query->sortClause, false);
+
+	node = ParseFuncOrColumn(pstate, fn->funcname, NIL, NULL, fn, false, -1);
+
+	tle_count = makeTargetEntry((Expr *) node,
+								list_length(query->targetList) + 1,
+								pstrdup("__ivm_count__"),
+								false);
+	query->targetList = lappend(query->targetList, tle_count);
+	query->hasAggs = true;
+
+	return query;
+}
+
+/*
+ * calc_delta
+ *
+ * Calculate view deltas generated under the modification of a table specified
+ * by the RTE index.
+ */
+static void
+calc_delta(MV_TriggerTable *table, int rte_index, Query *query,
+			DestReceiver *dest_old, DestReceiver *dest_new,
+			TupleDesc *tupdesc_old, TupleDesc *tupdesc_new,
+			QueryEnvironment *queryEnv)
+{
+	ListCell *lc = list_nth_cell(query->rtable, rte_index - 1);
+	RangeTblEntry *rte = (RangeTblEntry *) lfirst(lc);
+
+	in_delta_calculation = true;
+
+	/* Generate old delta */
+	if (list_length(table->old_tuplestores) > 0)
+	{
+		/* Replace the modified table with the old delta table and calculate the old view delta. */
+		replace_rte_with_delta(rte, table, false, queryEnv);
+		refresh_matview_datafill(dest_old, query, queryEnv, tupdesc_old, "");
+	}
+
+	/* Generate new delta */
+	if (list_length(table->new_tuplestores) > 0)
+	{
+		/* Replace the modified table with the new delta table and calculate the new view delta*/
+		replace_rte_with_delta(rte, table, true, queryEnv);
+		refresh_matview_datafill(dest_new, query, queryEnv, tupdesc_new, "");
+	}
+
+	in_delta_calculation = false;
+}
+
+/*
+ * rewrite_query_for_postupdate_state
+ *
+ * Rewrite the query so that the specified base table's RTEs will represent
+ * "post-update" state of tables. This is called after the view delta
+ * calculation due to changes on this table finishes.
+ */
+static Query*
+rewrite_query_for_postupdate_state(Query *query, MV_TriggerTable *table, int rte_index)
+{
+	ListCell *lc = list_nth_cell(query->rtable, rte_index - 1);
+
+	/* Retore the original RTE */
+	lfirst(lc) = table->original_rte;
+
+	return query;
+}
+
+/*
+ * apply_delta
+ *
+ * Apply deltas to the materialized view. In outer join cases, this requires
+ * the view maintenance graph.
+ */
+static void
+apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *new_tuplestores,
+			TupleDesc tupdesc_old, TupleDesc tupdesc_new,
+			Query *query)
+{
+	StringInfoData querybuf;
+	StringInfoData target_list_buf;
+	Relation	matviewRel;
+	char	   *matviewname;
+	ListCell	*lc;
+	int			i;
+	List	   *keys = NIL;
+
+
+	/*
+	 * get names of the materialized view and delta tables
+	 */
+
+	matviewRel = table_open(matviewOid, NoLock);
+	matviewname = quote_qualified_identifier(get_namespace_name(RelationGetNamespace(matviewRel)),
+											 RelationGetRelationName(matviewRel));
+
+	/*
+	 * Build parts of the maintenance queries
+	 */
+
+	initStringInfo(&querybuf);
+	initStringInfo(&target_list_buf);
+
+	/* build string of target list */
+	for (i = 0; i < matviewRel->rd_att->natts; i++)
+	{
+		Form_pg_attribute attr = TupleDescAttr(matviewRel->rd_att, i);
+		char   *resname = NameStr(attr->attname);
+
+		if (i != 0)
+			appendStringInfo(&target_list_buf, ", ");
+		appendStringInfo(&target_list_buf, "%s", quote_qualified_identifier(NULL, resname));
+	}
+
+	i = 0;
+	foreach (lc, query->targetList)
+	{
+		TargetEntry *tle = (TargetEntry *) lfirst(lc);
+		Form_pg_attribute attr = TupleDescAttr(matviewRel->rd_att, i);
+
+		i++;
+
+		if (tle->resjunk)
+			continue;
+
+		keys = lappend(keys, attr);
+	}
+
+	/* Start maintaining the materialized view. */
+	OpenMatViewIncrementalMaintenance();
+
+	/* Open SPI context. */
+	if (SPI_connect() != SPI_OK_CONNECT)
+		elog(ERROR, "SPI_connect failed");
+
+	/* For tuple deletion */
+	if (old_tuplestores && tuplestore_tuple_count(old_tuplestores) > 0)
+	{
+		EphemeralNamedRelation enr = palloc(sizeof(EphemeralNamedRelationData));
+		int				rc;
+
+		/* convert tuplestores to ENR, and register for SPI */
+		enr->md.name = pstrdup(OLD_DELTA_ENRNAME);
+		enr->md.reliddesc = InvalidOid;
+		enr->md.tupdesc = tupdesc_old;
+		enr->md.enrtype = ENR_NAMED_TUPLESTORE;
+		enr->md.enrtuples = tuplestore_tuple_count(old_tuplestores);
+		enr->reldata = old_tuplestores;
+
+		rc = SPI_register_relation(enr);
+		if (rc != SPI_OK_REL_REGISTER)
+			elog(ERROR, "SPI_register failed");
+
+		apply_old_delta(matviewname, OLD_DELTA_ENRNAME, keys);
+
+	}
+	/* For tuple insertion */
+	if (new_tuplestores && tuplestore_tuple_count(new_tuplestores) > 0)
+	{
+		EphemeralNamedRelation enr = palloc(sizeof(EphemeralNamedRelationData));
+		int rc;
+
+		/* convert tuplestores to ENR, and register for SPI */
+		enr->md.name = pstrdup(NEW_DELTA_ENRNAME);
+		enr->md.reliddesc = InvalidOid;
+		enr->md.tupdesc = tupdesc_new;;
+		enr->md.enrtype = ENR_NAMED_TUPLESTORE;
+		enr->md.enrtuples = tuplestore_tuple_count(new_tuplestores);
+		enr->reldata = new_tuplestores;
+
+		rc = SPI_register_relation(enr);
+		if (rc != SPI_OK_REL_REGISTER)
+			elog(ERROR, "SPI_register failed");
+
+		/* apply new delta */
+		apply_new_delta(matviewname, NEW_DELTA_ENRNAME, &target_list_buf);
+	}
+
+	/* We're done maintaining the materialized view. */
+	CloseMatViewIncrementalMaintenance();
+
+	table_close(matviewRel, NoLock);
+
+	/* Close SPI context. */
+	if (SPI_finish() != SPI_OK_FINISH)
+		elog(ERROR, "SPI_finish failed");
+}
+
+/*
+ * apply_old_delta
+ *
+ * Execute a query for applying a delta table given by deltname_old
+ * which contains tuples to be deleted from to a materialized view given by
+ * matviewname.  This is used when counting is not required.
+ */
+static void
+apply_old_delta(const char *matviewname, const char *deltaname_old,
+				List *keys)
+{
+	StringInfoData	querybuf;
+	StringInfoData	keysbuf;
+	char   *match_cond;
+	ListCell *lc;
+
+	/* build WHERE condition for searching tuples to be deleted */
+	match_cond = get_matching_condition_string(keys);
+
+	/* build string of keys list */
+	initStringInfo(&keysbuf);
+	foreach (lc, keys)
+	{
+		Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc);
+		char   *resname = NameStr(attr->attname);
+		appendStringInfo(&keysbuf, "%s", quote_qualified_identifier("mv", resname));
+		if (lnext(keys, lc))
+			appendStringInfo(&keysbuf, ", ");
+	}
+
+	/* Search for matching tuples from the view and update or delete if found. */
+	initStringInfo(&querybuf);
+	appendStringInfo(&querybuf,
+	"DELETE FROM %s WHERE ctid IN ("
+		"SELECT tid FROM (SELECT pg_catalog.row_number() over (partition by %s) AS \"__ivm_row_number__\","
+								  "mv.ctid AS tid,"
+								  "diff.\"__ivm_count__\""
+						 "FROM %s AS mv, %s AS diff "
+						 "WHERE %s) v "
+					"WHERE v.\"__ivm_row_number__\" OPERATOR(pg_catalog.<=) v.\"__ivm_count__\")",
+					matviewname,
+					keysbuf.data,
+					matviewname, deltaname_old,
+					match_cond);
+
+	if (SPI_exec(querybuf.data, 0) != SPI_OK_DELETE)
+		elog(ERROR, "SPI_exec failed: %s", querybuf.data);
+}
+
+/*
+ * apply_new_delta
+ *
+ * Execute a query for applying a delta table given by deltname_new
+ * which contains tuples to be inserted into a materialized view given by
+ * matviewname.  This is used when counting is not required.
+ */
+static void
+apply_new_delta(const char *matviewname, const char *deltaname_new,
+				StringInfo target_list)
+{
+	StringInfoData	querybuf;
+
+	/* Search for matching tuples from the view and update or delete if found. */
+	initStringInfo(&querybuf);
+	appendStringInfo(&querybuf,
+					"INSERT INTO %s (%s) SELECT %s FROM ("
+						"SELECT diff.*, pg_catalog.generate_series(1, diff.\"__ivm_count__\")"
+							" AS __ivm_generate_series__ "
+						"FROM %s AS diff) AS v",
+					matviewname, target_list->data, target_list->data,
+					deltaname_new);
+
+	if (SPI_exec(querybuf.data, 0) != SPI_OK_INSERT)
+		elog(ERROR, "SPI_exec failed: %s", querybuf.data);
+}
+
+/*
+ * get_matching_condition_string
+ *
+ * Build a predicate string for looking for a tuple with given keys.
+ */
+static char *
+get_matching_condition_string(List *keys)
+{
+	StringInfoData match_cond;
+	ListCell	*lc;
+
+	/* If there is no key columns, the condition is always true. */
+	if (keys == NIL)
+		return "true";
+
+	initStringInfo(&match_cond);
+	foreach (lc, keys)
+	{
+		Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc);
+		char   *resname = NameStr(attr->attname);
+		char   *mv_resname = quote_qualified_identifier("mv", resname);
+		char   *diff_resname = quote_qualified_identifier("diff", resname);
+		Oid		typid = attr->atttypid;
+
+		/* Considering NULL values, we can not use simple = operator. */
+		appendStringInfo(&match_cond, "(");
+		generate_equal(&match_cond, typid, mv_resname, diff_resname);
+		appendStringInfo(&match_cond, " OR (%s IS NULL AND %s IS NULL))",
+						 mv_resname, diff_resname);
+
+		if (lnext(keys, lc))
+			appendStringInfo(&match_cond, " AND ");
+	}
+
+	return match_cond.data;
+}
+
+/*
+ * generate_equals
+ *
+ * Generate an equality clause using given operands' default equality
+ * operator.
+ */
+static void
+generate_equal(StringInfo querybuf, Oid opttype,
+			   const char *leftop, const char *rightop)
+{
+	TypeCacheEntry *typentry;
+
+	typentry = lookup_type_cache(opttype, TYPECACHE_EQ_OPR);
+	if (!OidIsValid(typentry->eq_opr))
+		ereport(ERROR,
+				(errcode(ERRCODE_UNDEFINED_FUNCTION),
+				 errmsg("could not identify an equality operator for type %s",
+						format_type_be_qualified(opttype))));
+
+	generate_operator_clause(querybuf,
+							 leftop, opttype,
+							 typentry->eq_opr,
+							 rightop, opttype);
+}
+
+/*
+ * mv_InitHashTables
+ */
+static void
+mv_InitHashTables(void)
+{
+	HASHCTL		ctl;
+
+	memset(&ctl, 0, sizeof(ctl));
+	ctl.keysize = sizeof(Oid);
+	ctl.entrysize = sizeof(MV_TriggerHashEntry);
+	mv_trigger_info = hash_create("MV trigger info",
+								 MV_INIT_QUERYHASHSIZE,
+								 &ctl, HASH_ELEM | HASH_BLOBS);
+}
+
+/*
+ * AtAbort_IVM
+ *
+ * Clean up hash entries for all materialized views. This is called at
+ * transaction abort.
+ */
+void
+AtAbort_IVM()
+{
+	HASH_SEQ_STATUS seq;
+	MV_TriggerHashEntry *entry;
+
+	if (mv_trigger_info)
+	{
+		hash_seq_init(&seq, mv_trigger_info);
+		while ((entry = hash_seq_search(&seq)) != NULL)
+			clean_up_IVM_hash_entry(entry, true);
+	}
+	in_delta_calculation = false;
+}
+
+/*
+ * clean_up_IVM_hash_entry
+ *
+ * Clean up tuple stores and hash entries for a materialized view after its
+ * maintenance finished.
+ */
+static void
+clean_up_IVM_hash_entry(MV_TriggerHashEntry *entry, bool is_abort)
+{
+	bool found;
+	ListCell *lc;
+
+	foreach(lc, entry->tables)
+	{
+		MV_TriggerTable *table = (MV_TriggerTable *) lfirst(lc);
+
+		list_free(table->old_tuplestores);
+		list_free(table->new_tuplestores);
+		if (!is_abort)
+		{
+			ExecDropSingleTupleTableSlot(table->slot);
+			table_close(table->rel, NoLock);
+		}
+	}
+	list_free(entry->tables);
+
+	if (!is_abort)
+		UnregisterSnapshot(entry->snapshot);
+
+	hash_search(mv_trigger_info, (void *) &entry->matview_id, HASH_REMOVE, &found);
+}
+
+/*
+ * isIvmName
+ *
+ * Check if this is a IVM hidden column from the name.
+ */
+bool
+isIvmName(const char *s)
+{
+	if (s)
+		return (strncmp(s, "__ivm_", 6) == 0);
+	return false;
+}
diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat
index 9805bc6118..f6896d77b4 100644
--- a/src/include/catalog/pg_proc.dat
+++ b/src/include/catalog/pg_proc.dat
@@ -12062,4 +12062,14 @@
   proname => 'any_value_transfn', prorettype => 'anyelement',
   proargtypes => 'anyelement anyelement', prosrc => 'any_value_transfn' },
 
+# IVM
+{ oid => '786', descr => 'ivm trigger (before)',
+  proname => 'IVM_immediate_before', provolatile => 'v', prorettype => 'trigger',
+  proargtypes => '', prosrc => 'IVM_immediate_before' },
+{ oid => '787', descr => 'ivm trigger (after)',
+  proname => 'IVM_immediate_maintenance', provolatile => 'v', prorettype => 'trigger',
+  proargtypes => '', prosrc => 'IVM_immediate_maintenance' },
+{ oid => '788', descr => 'ivm filetring ',
+  proname => 'ivm_visible_in_prestate', provolatile => 's', prorettype => 'bool',
+  proargtypes => 'oid tid oid', prosrc => 'ivm_visible_in_prestate' },
 ]
diff --git a/src/include/commands/createas.h b/src/include/commands/createas.h
index 3647f96f73..09a64fa2e5 100644
--- a/src/include/commands/createas.h
+++ b/src/include/commands/createas.h
@@ -16,6 +16,7 @@
 
 #include "catalog/objectaddress.h"
 #include "nodes/params.h"
+#include "nodes/pathnodes.h"
 #include "parser/parse_node.h"
 #include "tcop/dest.h"
 #include "utils/queryenvironment.h"
@@ -25,6 +26,9 @@ extern ObjectAddress ExecCreateTableAs(ParseState *pstate, CreateTableAsStmt *st
 									   ParamListInfo params, QueryEnvironment *queryEnv,
 									   QueryCompletion *qc);
 
+extern void CreateIvmTriggersOnBaseTables(Query *qry, Oid matviewOid);
+extern void CreateIndexOnIMMV(Query *query, Relation matviewRel);
+
 extern int	GetIntoRelEFlags(IntoClause *intoClause);
 
 extern DestReceiver *CreateIntoRelDestReceiver(IntoClause *intoClause);
diff --git a/src/include/commands/matview.h b/src/include/commands/matview.h
index 9eaa6212a1..504b83a446 100644
--- a/src/include/commands/matview.h
+++ b/src/include/commands/matview.h
@@ -15,6 +15,7 @@
 #define MATVIEW_H
 
 #include "catalog/objectaddress.h"
+#include "fmgr.h"
 #include "nodes/params.h"
 #include "nodes/parsenodes.h"
 #include "tcop/dest.h"
@@ -23,6 +24,8 @@
 
 extern void SetMatViewPopulatedState(Relation relation, bool newstate);
 
+extern void SetMatViewIVMState(Relation relation, bool newstate);
+
 extern ObjectAddress ExecRefreshMatView(RefreshMatViewStmt *stmt, const char *queryString,
 										ParamListInfo params, QueryCompletion *qc);
 
@@ -30,4 +33,10 @@ extern DestReceiver *CreateTransientRelDestReceiver(Oid transientoid);
 
 extern bool MatViewIncrementalMaintenanceIsEnabled(void);
 
+extern Datum IVM_immediate_before(PG_FUNCTION_ARGS);
+extern Datum IVM_immediate_maintenance(PG_FUNCTION_ARGS);
+extern Datum IVM_visible_in_prestate(PG_FUNCTION_ARGS);
+extern void AtAbort_IVM(void);
+extern bool isIvmName(const char *s);
+
 #endif							/* MATVIEW_H */
-- 
2.25.1


--Multipart=_Mon__28_Aug_2023_11_52_52_+0900_hj6L5h176QaSGtg7
Content-Type: text/x-diff;
 name="v29-0007-Add-DISTINCT-support-for-IVM.patch"
Content-Disposition: attachment;
 filename="v29-0007-Add-DISTINCT-support-for-IVM.patch"
Content-Transfer-Encoding: 7bit



^ permalink  raw  reply  [nested|flat] 101+ messages in thread

* [PATCH v30 06/11] Add Incremental View Maintenance support
@ 2023-05-31 09:59  Yugo Nagata <[email protected]>
  0 siblings, 0 replies; 101+ messages in thread

From: Yugo Nagata @ 2023-05-31 09:59 UTC (permalink / raw)

In this implementation, AFTER triggers are used to collect
tuplestores containing transition table contents. When multiple tables
are changed, multiple AFTER triggers are invoked, then the final AFTER
trigger performs actual update of the matview. In addition, BEFORE
triggers are also used to handle global information for view
maintenance.

To calculate view deltas, we need both pre-state and post-state of base
tables. Post-update states are available in AFTER trigger, and pre-update
states can be calculated by removing inserted tuples and appending deleted
tuples. Insterted tuples are filtered using the snapshot taken before
table modiication, and deleted tuples are contained in the old transition
table.

Incrementally Maintainable Materialized Views (IMMV) can contain
duplicated tuples.

This patch also allows self-join, simultaneous updates of more than
one base table, and multiple updates of the same base table.
---
 src/backend/access/transam/xact.c |    5 +
 src/backend/commands/createas.c   |  681 ++++++++++++++
 src/backend/commands/matview.c    | 1466 ++++++++++++++++++++++++++++-
 src/include/catalog/pg_proc.dat   |   10 +
 src/include/commands/createas.h   |    4 +
 src/include/commands/matview.h    |    9 +
 6 files changed, 2140 insertions(+), 35 deletions(-)

diff --git a/src/backend/access/transam/xact.c b/src/backend/access/transam/xact.c
index 70ab6e27a1..0de7ab6abe 100644
--- a/src/backend/access/transam/xact.c
+++ b/src/backend/access/transam/xact.c
@@ -36,6 +36,7 @@
 #include "catalog/pg_enum.h"
 #include "catalog/storage.h"
 #include "commands/async.h"
+#include "commands/matview.h"
 #include "commands/tablecmds.h"
 #include "commands/trigger.h"
 #include "common/pg_prng.h"
@@ -2819,6 +2820,7 @@ AbortTransaction(void)
 	AtAbort_Notify();
 	AtEOXact_RelationMap(false, is_parallel_worker);
 	AtAbort_Twophase();
+	AtAbort_IVM();
 
 	/*
 	 * Advertise the fact that we aborted in pg_xact (assuming that we got as
@@ -5097,6 +5099,9 @@ AbortSubTransaction(void)
 	pgstat_progress_end_command();
 	UnlockBuffers();
 
+	/* Clean up hash entries for incremental view maintenance */
+	AtAbort_IVM();
+
 	/* Reset WAL record construction state */
 	XLogResetInsertion();
 
diff --git a/src/backend/commands/createas.c b/src/backend/commands/createas.c
index 16a2fe65e6..08262100ea 100644
--- a/src/backend/commands/createas.c
+++ b/src/backend/commands/createas.c
@@ -32,15 +32,26 @@
 #include "access/xact.h"
 #include "access/xlog.h"
 #include "catalog/namespace.h"
+#include "catalog/index.h"
+#include "catalog/pg_constraint.h"
+#include "catalog/pg_inherits.h"
+#include "catalog/pg_trigger.h"
 #include "catalog/toasting.h"
 #include "commands/createas.h"
+#include "commands/defrem.h"
 #include "commands/matview.h"
 #include "commands/prepare.h"
 #include "commands/tablecmds.h"
+#include "commands/tablespace.h"
+#include "commands/trigger.h"
 #include "commands/view.h"
 #include "miscadmin.h"
+#include "optimizer/optimizer.h"
+#include "optimizer/prep.h"
 #include "nodes/makefuncs.h"
 #include "nodes/nodeFuncs.h"
+#include "parser/parser.h"
+#include "parser/parsetree.h"
 #include "parser/parse_clause.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/smgr.h"
@@ -73,6 +84,12 @@ static bool intorel_receive(TupleTableSlot *slot, DestReceiver *self);
 static void intorel_shutdown(DestReceiver *self);
 static void intorel_destroy(DestReceiver *self);
 
+static void CreateIvmTriggersOnBaseTablesRecurse(Query *qry, Node *node, Oid matviewOid,
+									 Relids *relids, bool ex_lock);
+static void CreateIvmTrigger(Oid relOid, Oid viewOid, int16 type, int16 timing, bool ex_lock);
+static void check_ivm_restriction(Node *node);
+static bool check_ivm_restriction_walker(Node *node, void *context);
+static Bitmapset *get_primary_key_attnos_from_query(Query *query, List **constraintList);
 
 /*
  * create_ctas_internal
@@ -282,6 +299,18 @@ ExecCreateTableAs(ParseState *pstate, CreateTableAsStmt *stmt,
 		save_nestlevel = NewGUCNestLevel();
 	}
 
+	if (is_matview && into->ivm)
+	{
+		/* check if the query is supported in IMMV definition */
+		if (contain_mutable_functions((Node *) query))
+			ereport(ERROR,
+					(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+					 errmsg("mutable function is not supported on incrementally maintainable materialized view"),
+					 errhint("functions must be marked IMMUTABLE")));
+
+		check_ivm_restriction((Node *) query);
+	}
+
 	if (into->skipData)
 	{
 		/*
@@ -358,6 +387,27 @@ ExecCreateTableAs(ParseState *pstate, CreateTableAsStmt *stmt,
 
 		/* Restore userid and security context */
 		SetUserIdAndSecContext(save_userid, save_sec_context);
+
+		if (into->ivm)
+		{
+			Oid matviewOid = address.objectId;
+			Relation matviewRel = table_open(matviewOid, NoLock);
+
+			/*
+			 * Mark relisivm field, if it's a matview and into->ivm is true.
+			 */
+			SetMatViewIVMState(matviewRel, true);
+
+			if (!into->skipData)
+			{
+				/* Create an index on incremental maintainable materialized view, if possible */
+				CreateIndexOnIMMV((Query *) into->viewQuery, matviewRel);
+
+				/* Create triggers on incremental maintainable materialized view */
+				CreateIvmTriggersOnBaseTables((Query *) into->viewQuery, matviewOid);
+			}
+			table_close(matviewRel, NoLock);
+		}
 	}
 
 	return address;
@@ -635,3 +685,634 @@ intorel_destroy(DestReceiver *self)
 {
 	pfree(self);
 }
+
+/*
+ * CreateIvmTriggersOnBaseTables -- create IVM triggers on all base tables
+ */
+void
+CreateIvmTriggersOnBaseTables(Query *qry, Oid matviewOid)
+{
+	Relids	relids = NULL;
+	bool	ex_lock = false;
+	RangeTblEntry *rte;
+
+	/* Immediately return if we don't have any base tables. */
+	if (list_length(qry->rtable) < 1)
+		return;
+
+	/*
+	 * If the view has more than one base tables, we need an exclusive lock
+	 * on the view so that the view would be maintained serially to avoid
+	 * the inconsistency that occurs when two base tables are modified in
+	 * concurrent transactions. However, if the view has only one table,
+	 * we can use a weaker lock.
+	 *
+	 * The type of lock should be determined here, because if we check the
+	 * view definition at maintenance time, we need to acquire a weaker lock,
+	 * and upgrading the lock level after this increases probability of
+	 * deadlock.
+	 */
+
+	rte = list_nth(qry->rtable, 0);
+	if (list_length(qry->rtable) > 1 || rte->rtekind != RTE_RELATION)
+		ex_lock = true;
+
+	CreateIvmTriggersOnBaseTablesRecurse(qry, (Node *)qry, matviewOid, &relids, ex_lock);
+
+	bms_free(relids);
+}
+
+static void
+CreateIvmTriggersOnBaseTablesRecurse(Query *qry, Node *node, Oid matviewOid,
+									 Relids *relids, bool ex_lock)
+{
+	if (node == NULL)
+		return;
+
+	/* This can recurse, so check for excessive recursion */
+	check_stack_depth();
+
+	switch (nodeTag(node))
+	{
+		case T_Query:
+			{
+				Query *query = (Query *) node;
+
+				CreateIvmTriggersOnBaseTablesRecurse(qry, (Node *)query->jointree, matviewOid, relids, ex_lock);
+			}
+			break;
+
+		case T_RangeTblRef:
+			{
+				int			rti = ((RangeTblRef *) node)->rtindex;
+				RangeTblEntry *rte = rt_fetch(rti, qry->rtable);
+
+				if (rte->rtekind == RTE_RELATION && !bms_is_member(rte->relid, *relids))
+				{
+					CreateIvmTrigger(rte->relid, matviewOid, TRIGGER_TYPE_INSERT, TRIGGER_TYPE_BEFORE, ex_lock);
+					CreateIvmTrigger(rte->relid, matviewOid, TRIGGER_TYPE_DELETE, TRIGGER_TYPE_BEFORE, ex_lock);
+					CreateIvmTrigger(rte->relid, matviewOid, TRIGGER_TYPE_UPDATE, TRIGGER_TYPE_BEFORE, ex_lock);
+					CreateIvmTrigger(rte->relid, matviewOid, TRIGGER_TYPE_TRUNCATE, TRIGGER_TYPE_BEFORE, true);
+					CreateIvmTrigger(rte->relid, matviewOid, TRIGGER_TYPE_INSERT, TRIGGER_TYPE_AFTER, ex_lock);
+					CreateIvmTrigger(rte->relid, matviewOid, TRIGGER_TYPE_DELETE, TRIGGER_TYPE_AFTER, ex_lock);
+					CreateIvmTrigger(rte->relid, matviewOid, TRIGGER_TYPE_UPDATE, TRIGGER_TYPE_AFTER, ex_lock);
+					CreateIvmTrigger(rte->relid, matviewOid, TRIGGER_TYPE_TRUNCATE, TRIGGER_TYPE_AFTER, true);
+
+					*relids = bms_add_member(*relids, rte->relid);
+				}
+			}
+			break;
+
+		case T_FromExpr:
+			{
+				FromExpr   *f = (FromExpr *) node;
+				ListCell   *l;
+
+				foreach(l, f->fromlist)
+					CreateIvmTriggersOnBaseTablesRecurse(qry, lfirst(l), matviewOid, relids, ex_lock);
+			}
+			break;
+
+		case T_JoinExpr:
+			{
+				JoinExpr   *j = (JoinExpr *) node;
+
+				CreateIvmTriggersOnBaseTablesRecurse(qry, j->larg, matviewOid, relids, ex_lock);
+				CreateIvmTriggersOnBaseTablesRecurse(qry, j->rarg, matviewOid, relids, ex_lock);
+			}
+			break;
+
+		default:
+			elog(ERROR, "unrecognized node type: %d", (int) nodeTag(node));
+	}
+}
+
+/*
+ * CreateIvmTrigger -- create IVM trigger on a base table
+ */
+static void
+CreateIvmTrigger(Oid relOid, Oid viewOid, int16 type, int16 timing, bool ex_lock)
+{
+	ObjectAddress	refaddr;
+	ObjectAddress	address;
+	CreateTrigStmt *ivm_trigger;
+	List *transitionRels = NIL;
+
+	Assert(timing == TRIGGER_TYPE_BEFORE || timing == TRIGGER_TYPE_AFTER);
+
+	refaddr.classId = RelationRelationId;
+	refaddr.objectId = viewOid;
+	refaddr.objectSubId = 0;
+
+	ivm_trigger = makeNode(CreateTrigStmt);
+	ivm_trigger->relation = NULL;
+	ivm_trigger->row = false;
+
+	ivm_trigger->timing = timing;
+	ivm_trigger->events = type;
+
+	switch (type)
+	{
+		case TRIGGER_TYPE_INSERT:
+			ivm_trigger->trigname = (timing == TRIGGER_TYPE_BEFORE ? "IVM_trigger_ins_before" : "IVM_trigger_ins_after");
+			break;
+		case TRIGGER_TYPE_DELETE:
+			ivm_trigger->trigname = (timing == TRIGGER_TYPE_BEFORE ? "IVM_trigger_del_before" : "IVM_trigger_del_after");
+			break;
+		case TRIGGER_TYPE_UPDATE:
+			ivm_trigger->trigname = (timing == TRIGGER_TYPE_BEFORE ? "IVM_trigger_upd_before" : "IVM_trigger_upd_after");
+			break;
+		case TRIGGER_TYPE_TRUNCATE:
+			ivm_trigger->trigname = (timing == TRIGGER_TYPE_BEFORE ? "IVM_trigger_truncate_before" : "IVM_trigger_truncate_after");
+			break;
+		default:
+			elog(ERROR, "unsupported trigger type");
+	}
+
+	if (timing == TRIGGER_TYPE_AFTER)
+	{
+		if (type == TRIGGER_TYPE_INSERT || type == TRIGGER_TYPE_UPDATE)
+		{
+			TriggerTransition *n = makeNode(TriggerTransition);
+			n->name = "__ivm_newtable";
+			n->isNew = true;
+			n->isTable = true;
+
+			transitionRels = lappend(transitionRels, n);
+		}
+		if (type == TRIGGER_TYPE_DELETE || type == TRIGGER_TYPE_UPDATE)
+		{
+			TriggerTransition *n = makeNode(TriggerTransition);
+			n->name = "__ivm_oldtable";
+			n->isNew = false;
+			n->isTable = true;
+
+			transitionRels = lappend(transitionRels, n);
+		}
+	}
+
+	/*
+	 * XXX: When using DELETE or UPDATE, we must use exclusive lock for now
+	 * because apply_old_delta(_with_count) uses ctid to identify the tuple
+	 * to be deleted/deleted, but doesn't work in concurrent situations.
+	 *
+	 * If the view doesn't have aggregate, distinct, or tuple duplicate,
+	 * then it would work even in concurrent situations. However, we don't have
+	 * any way to guarantee the view has a unique key before opening the IMMV
+	 * at the maintenance time because users may drop the unique index.
+	 */
+
+	if (type == TRIGGER_TYPE_DELETE || type == TRIGGER_TYPE_UPDATE)
+		ex_lock = true;
+
+	ivm_trigger->funcname =
+		(timing == TRIGGER_TYPE_BEFORE ? SystemFuncName("IVM_immediate_before") : SystemFuncName("IVM_immediate_maintenance"));
+
+	ivm_trigger->columns = NIL;
+	ivm_trigger->transitionRels = transitionRels;
+	ivm_trigger->whenClause = NULL;
+	ivm_trigger->isconstraint = false;
+	ivm_trigger->deferrable = false;
+	ivm_trigger->initdeferred = false;
+	ivm_trigger->constrrel = NULL;
+	ivm_trigger->args = list_make2(
+		makeString(DatumGetPointer(DirectFunctionCall1(oidout, ObjectIdGetDatum(viewOid)))),
+		makeString(DatumGetPointer(DirectFunctionCall1(boolout, BoolGetDatum(ex_lock))))
+		);
+
+	address = CreateTrigger(ivm_trigger, NULL, relOid, InvalidOid, InvalidOid,
+						 InvalidOid, InvalidOid, InvalidOid, NULL, true, false);
+
+	recordDependencyOn(&address, &refaddr, DEPENDENCY_AUTO);
+
+	/* Make changes-so-far visible */
+	CommandCounterIncrement();
+}
+
+/*
+ * check_ivm_restriction --- look for specify nodes in the query tree
+ */
+static void
+check_ivm_restriction(Node *node)
+{
+	check_ivm_restriction_walker(node, NULL);
+}
+
+static bool
+check_ivm_restriction_walker(Node *node, void *context)
+{
+	if (node == NULL)
+		return false;
+
+	/*
+	 * We currently don't support Sub-Query.
+	 */
+	if (IsA(node, SubPlan) || IsA(node, SubLink))
+		ereport(ERROR,
+				(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+				 errmsg("subquery is not supported on incrementally maintainable materialized view")));
+
+	/* This can recurse, so check for excessive recursion */
+	check_stack_depth();
+
+	switch (nodeTag(node))
+	{
+		case T_Query:
+			{
+				Query *qry = (Query *)node;
+				ListCell   *lc;
+				List       *vars;
+
+				/* if contained CTE, return error */
+				if (qry->cteList != NIL)
+					ereport(ERROR,
+							(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+							 errmsg("CTE is not supported on incrementally maintainable materialized view")));
+				if (qry->havingQual != NULL)
+					ereport(ERROR,
+							(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+							 errmsg(" HAVING clause is not supported on incrementally maintainable materialized view")));
+				if (qry->sortClause != NIL)	/* There is a possibility that we don't need to return an error */
+					ereport(ERROR,
+							(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+							 errmsg("ORDER BY clause is not supported on incrementally maintainable materialized view")));
+				if (qry->limitOffset != NULL || qry->limitCount != NULL)
+					ereport(ERROR,
+							(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+							 errmsg("LIMIT/OFFSET clause is not supported on incrementally maintainable materialized view")));
+				if (qry->distinctClause)
+					ereport(ERROR,
+							(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+							 errmsg("DISTINCT is not supported on incrementally maintainable materialized view")));
+				if (qry->hasDistinctOn)
+					ereport(ERROR,
+							(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+							 errmsg("DISTINCT ON is not supported on incrementally maintainable materialized view")));
+				if (qry->hasWindowFuncs)
+					ereport(ERROR,
+							(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+							 errmsg("window functions are not supported on incrementally maintainable materialized view")));
+				if (qry->groupingSets != NIL)
+					ereport(ERROR,
+							(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+							 errmsg("GROUPING SETS, ROLLUP, or CUBE clauses is not supported on incrementally maintainable materialized view")));
+				if (qry->setOperations != NULL)
+					ereport(ERROR,
+							(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+							 errmsg("UNION/INTERSECT/EXCEPT statements are not supported on incrementally maintainable materialized view")));
+				if (list_length(qry->targetList) == 0)
+					ereport(ERROR,
+							(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+							 errmsg("empty target list is not supported on incrementally maintainable materialized view")));
+				if (qry->rowMarks != NIL)
+					ereport(ERROR,
+							(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+							 errmsg("FOR UPDATE/SHARE clause is not supported on incrementally maintainable materialized view")));
+
+				/* system column restrictions */
+				vars = pull_vars_of_level((Node *) qry, 0);
+				foreach(lc, vars)
+				{
+					if (IsA(lfirst(lc), Var))
+					{
+						Var *var = (Var *) lfirst(lc);
+						/* if system column, return error */
+						if (var->varattno < 0)
+							ereport(ERROR,
+									(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+									 errmsg("system column is not supported on incrementally maintainable materialized view")));
+					}
+				}
+
+				/* restrictions for rtable */
+				foreach(lc, qry->rtable)
+				{
+					RangeTblEntry *rte = (RangeTblEntry *) lfirst(lc);
+
+					if (rte->subquery)
+						ereport(ERROR,
+								(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+								 errmsg("subquery is not supported on incrementally maintainable materialized view")));
+
+					if (rte->tablesample != NULL)
+						ereport(ERROR,
+								(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+								 errmsg("TABLESAMPLE clause is not supported on incrementally maintainable materialized view")));
+
+					if (rte->relkind == RELKIND_PARTITIONED_TABLE)
+						ereport(ERROR,
+								(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+								 errmsg("partitioned table is not supported on incrementally maintainable materialized view")));
+
+					if (rte->relkind == RELKIND_RELATION && has_superclass(rte->relid))
+						ereport(ERROR,
+								(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+								 errmsg("partitions is not supported on incrementally maintainable materialized view")));
+
+					if (rte->relkind == RELKIND_RELATION && find_inheritance_children(rte->relid, NoLock) != NIL)
+						ereport(ERROR,
+								(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+								 errmsg("inheritance parent is not supported on incrementally maintainable materialized view")));
+
+					if (rte->relkind == RELKIND_FOREIGN_TABLE)
+						ereport(ERROR,
+								(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+								 errmsg("foreign table is not supported on incrementally maintainable materialized view")));
+
+					if (rte->relkind == RELKIND_VIEW ||
+						rte->relkind == RELKIND_MATVIEW)
+						ereport(ERROR,
+								(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+								 errmsg("VIEW or MATERIALIZED VIEW is not supported on incrementally maintainable materialized view")));
+
+					if (rte->rtekind == RTE_VALUES)
+						ereport(ERROR,
+								(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+								 errmsg("VALUES is not supported on incrementally maintainable materialized view")));
+
+				}
+
+				query_tree_walker(qry, check_ivm_restriction_walker, NULL, QTW_IGNORE_RANGE_TABLE);
+
+				break;
+			}
+		case T_TargetEntry:
+			{
+				TargetEntry *tle = (TargetEntry *)node;
+				if (isIvmName(tle->resname))
+						ereport(ERROR,
+								(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+								 errmsg("column name %s is not supported on incrementally maintainable materialized view", tle->resname)));
+
+				expression_tree_walker(node, check_ivm_restriction_walker, NULL);
+				break;
+			}
+		case T_JoinExpr:
+			{
+				JoinExpr *joinexpr = (JoinExpr *)node;
+
+				if (joinexpr->jointype > JOIN_INNER)
+						ereport(ERROR,
+								(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+								 errmsg("OUTER JOIN is not supported on incrementally maintainable materialized view")));
+
+				expression_tree_walker(node, check_ivm_restriction_walker, NULL);
+			}
+			break;
+		case T_Aggref:
+			ereport(ERROR,
+					(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+					 errmsg("aggregate function is not supported on incrementally maintainable materialized view")));
+			break;
+		default:
+			expression_tree_walker(node, check_ivm_restriction_walker, (void *) context);
+			break;
+	}
+	return false;
+}
+
+/*
+ * CreateIndexOnIMMV
+ *
+ * Create a unique index on incremental maintainable materialized view.
+ * If the view definition query has a GROUP BY clause, the index is created
+ * on the columns of GROUP BY expressions. Otherwise, if the view contains
+ * all primary key attritubes of its base tables in the target list, the index
+ * is created on these attritubes. In other cases, no index is created.
+ */
+void
+CreateIndexOnIMMV(Query *query, Relation matviewRel)
+{
+	ListCell *lc;
+	IndexStmt  *index;
+	ObjectAddress address;
+	List *constraintList = NIL;
+	char		idxname[NAMEDATALEN];
+	List	   *indexoidlist = RelationGetIndexList(matviewRel);
+	ListCell   *indexoidscan;
+	Bitmapset *key_attnos;
+
+	snprintf(idxname, sizeof(idxname), "%s_index", RelationGetRelationName(matviewRel));
+
+	index = makeNode(IndexStmt);
+
+	index->unique = true;
+	index->primary = false;
+	index->isconstraint = false;
+	index->deferrable = false;
+	index->initdeferred = false;
+	index->idxname = idxname;
+	index->relation =
+		makeRangeVar(get_namespace_name(RelationGetNamespace(matviewRel)),
+					 pstrdup(RelationGetRelationName(matviewRel)),
+					 -1);
+	index->accessMethod = DEFAULT_INDEX_TYPE;
+	index->options = NIL;
+	index->tableSpace = get_tablespace_name(matviewRel->rd_rel->reltablespace);
+	index->whereClause = NULL;
+	index->indexParams = NIL;
+	index->indexIncludingParams = NIL;
+	index->excludeOpNames = NIL;
+	index->idxcomment = NULL;
+	index->indexOid = InvalidOid;
+	index->oldNumber = InvalidRelFileNumber;
+	index->oldCreateSubid = InvalidSubTransactionId;
+	index->oldFirstRelfilelocatorSubid = InvalidSubTransactionId;
+	index->transformed = true;
+	index->concurrent = false;
+	index->if_not_exists = false;
+
+	/* create index on the base tables' primary key columns */
+	key_attnos = get_primary_key_attnos_from_query(query, &constraintList);
+	if (key_attnos)
+	{
+		foreach(lc, query->targetList)
+		{
+			TargetEntry *tle = (TargetEntry *) lfirst(lc);
+			Form_pg_attribute attr = TupleDescAttr(matviewRel->rd_att, tle->resno - 1);
+
+			if (bms_is_member(tle->resno - FirstLowInvalidHeapAttributeNumber, key_attnos))
+			{
+				IndexElem  *iparam;
+
+				iparam = makeNode(IndexElem);
+				iparam->name = pstrdup(NameStr(attr->attname));
+				iparam->expr = NULL;
+				iparam->indexcolname = NULL;
+				iparam->collation = NIL;
+				iparam->opclass = NIL;
+				iparam->opclassopts = NIL;
+				iparam->ordering = SORTBY_DEFAULT;
+				iparam->nulls_ordering = SORTBY_NULLS_DEFAULT;
+				index->indexParams = lappend(index->indexParams, iparam);
+			}
+		}
+	}
+	else
+	{
+		/* create no index, just notice that an appropriate index is necessary for efficient IVM */
+		ereport(NOTICE,
+				(errmsg("could not create an index on materialized view \"%s\" automatically",
+						RelationGetRelationName(matviewRel)),
+				 errdetail("This target list does not have all the primary key columns. "),
+				 errhint("Create an index on the materialized view for efficient incremental maintenance.")));
+		return;
+	}
+
+	/* If we have a compatible index, we don't need to create another. */
+	foreach(indexoidscan, indexoidlist)
+	{
+		Oid			indexoid = lfirst_oid(indexoidscan);
+		Relation	indexRel;
+		bool		hasCompatibleIndex = false;
+
+		indexRel = index_open(indexoid, AccessShareLock);
+
+		if (CheckIndexCompatible(indexRel->rd_id,
+								index->accessMethod,
+								index->indexParams,
+								index->excludeOpNames,
+								false))
+			hasCompatibleIndex = true;
+
+		index_close(indexRel, AccessShareLock);
+
+		if (hasCompatibleIndex)
+			return;
+	}
+
+	address = DefineIndex(RelationGetRelid(matviewRel),
+						  index,
+						  InvalidOid,
+						  InvalidOid,
+						  InvalidOid,
+						  -1,
+						  false, true, false, false, true);
+
+	ereport(NOTICE,
+			(errmsg("created index \"%s\" on materialized view \"%s\"",
+					idxname, RelationGetRelationName(matviewRel))));
+
+	/*
+	 * Make dependencies so that the index is dropped if any base tables's
+	 * primary key is dropped.
+	 */
+	foreach(lc, constraintList)
+	{
+		Oid constraintOid = lfirst_oid(lc);
+		ObjectAddress	refaddr;
+
+		refaddr.classId = ConstraintRelationId;
+		refaddr.objectId = constraintOid;
+		refaddr.objectSubId = 0;
+
+		recordDependencyOn(&address, &refaddr, DEPENDENCY_NORMAL);
+	}
+}
+
+
+/*
+ * get_primary_key_attnos_from_query
+ *
+ * Identify the columns in base tables' primary keys in the target list.
+ *
+ * Returns a Bitmapset of the column attnos of the primary key's columns of
+ * tables that used in the query.  The attnos are offset by
+ * FirstLowInvalidHeapAttributeNumber as same as get_primary_key_attnos.
+ *
+ * If any table has no primary key or any primary key's columns is not in
+ * the target list, return NULL.  We also return NULL if any pkey constraint
+ * is deferrable.
+ *
+ * constraintList is set to a list of the OIDs of the pkey constraints.
+ */
+static Bitmapset *
+get_primary_key_attnos_from_query(Query *query, List **constraintList)
+{
+	List *key_attnos_list = NIL;
+	ListCell *lc;
+	int i;
+	Bitmapset *keys = NULL;
+	Relids	rels_in_from;
+
+	/*
+	 * Collect primary key attributes from all tables used in query. The key attributes
+	 * sets for each table are stored in key_attnos_list in order by RTE index.
+	 */
+	foreach(lc, query->rtable)
+	{
+		RangeTblEntry *r = (RangeTblEntry*) lfirst(lc);
+		Bitmapset *key_attnos;
+		bool	has_pkey = true;
+
+		/* for tables, call get_primary_key_attnos */
+		if (r->rtekind == RTE_RELATION)
+		{
+			Oid constraintOid;
+			key_attnos = get_primary_key_attnos(r->relid, false, &constraintOid);
+			*constraintList = lappend_oid(*constraintList, constraintOid);
+			has_pkey = (key_attnos != NULL);
+		}
+		/* for other RTEs, store NULL into key_attnos_list */
+		else
+			key_attnos = NULL;
+
+		/*
+		 * If any table or subquery has no primary key or its pkey constraint is deferrable,
+		 * we cannot get key attributes for this query, so return NULL.
+		 */
+		if (!has_pkey)
+			return NULL;
+
+		key_attnos_list = lappend(key_attnos_list, key_attnos);
+	}
+
+	/* Collect key attributes appearing in the target list */
+	i = 1;
+	foreach(lc, query->targetList)
+	{
+		TargetEntry *tle = (TargetEntry *) flatten_join_alias_vars(NULL, query, lfirst(lc));
+
+		if (IsA(tle->expr, Var))
+		{
+			Var *var = (Var*) tle->expr;
+			Bitmapset *key_attnos = list_nth(key_attnos_list, var->varno - 1);
+
+			/* check if this attribute is from a base table's primary key */
+			if (bms_is_member(var->varattno - FirstLowInvalidHeapAttributeNumber, key_attnos))
+			{
+				/*
+				 * Remove found key attributes from key_attnos_list, and add this
+				 * to the result list.
+				 */
+				key_attnos = bms_del_member(key_attnos, var->varattno - FirstLowInvalidHeapAttributeNumber);
+				if (bms_is_empty(key_attnos))
+				{
+					key_attnos_list = list_delete_nth_cell(key_attnos_list, var->varno - 1);
+					key_attnos_list = list_insert_nth(key_attnos_list, var->varno - 1, NULL);
+				}
+				keys = bms_add_member(keys, i - FirstLowInvalidHeapAttributeNumber);
+			}
+		}
+		i++;
+	}
+
+	/* Collect RTE indexes of relations appearing in the FROM clause */
+	rels_in_from = get_relids_in_jointree((Node *) query->jointree, false, false);
+
+	/*
+	 * Check if all key attributes of relations in FROM are appearing in the target
+	 * list.  If an attribute remains in key_attnos_list in spite of the table is used
+	 * in FROM clause, the target is missing this key attribute, so we return NULL.
+	 */
+	i = 1;
+	foreach(lc, key_attnos_list)
+	{
+		Bitmapset *bms = (Bitmapset *)lfirst(lc);
+		if (!bms_is_empty(bms) && bms_is_member(i, rels_in_from))
+			return NULL;
+		i++;
+	}
+
+	return keys;
+}
diff --git a/src/backend/commands/matview.c b/src/backend/commands/matview.c
index 59920ced83..a821992a37 100644
--- a/src/backend/commands/matview.c
+++ b/src/backend/commands/matview.c
@@ -25,26 +25,37 @@
 #include "catalog/indexing.h"
 #include "catalog/namespace.h"
 #include "catalog/pg_am.h"
+#include "catalog/pg_depend.h"
+#include "catalog/pg_trigger.h"
 #include "catalog/pg_opclass.h"
 #include "catalog/pg_operator.h"
 #include "commands/cluster.h"
 #include "commands/matview.h"
 #include "commands/tablecmds.h"
 #include "commands/tablespace.h"
+#include "commands/createas.h"
 #include "executor/executor.h"
 #include "executor/spi.h"
+#include "executor/tstoreReceiver.h"
 #include "miscadmin.h"
+#include "nodes/makefuncs.h"
+#include "parser/analyze.h"
+#include "parser/parse_clause.h"
+#include "parser/parse_func.h"
 #include "parser/parse_relation.h"
 #include "pgstat.h"
 #include "rewrite/rewriteHandler.h"
+#include "rewrite/rowsecurity.h"
 #include "storage/lmgr.h"
 #include "storage/smgr.h"
 #include "tcop/tcopprot.h"
 #include "utils/builtins.h"
+#include "utils/fmgroids.h"
 #include "utils/lsyscache.h"
 #include "utils/rel.h"
 #include "utils/snapmgr.h"
 #include "utils/syscache.h"
+#include "utils/typcache.h"
 
 
 typedef struct
@@ -58,6 +69,52 @@ typedef struct
 	BulkInsertState bistate;	/* bulk insert state */
 } DR_transientrel;
 
+#define MV_INIT_QUERYHASHSIZE	16
+
+/*
+ * MV_TriggerHashEntry
+ *
+ * Hash entry for base tables on which IVM trigger is invoked
+ */
+typedef struct MV_TriggerHashEntry
+{
+	Oid	matview_id;			/* OID of the materialized view */
+	int	before_trig_count;	/* count of before triggers invoked */
+	int	after_trig_count;	/* count of after triggers invoked */
+
+	Snapshot	snapshot;	/* Snapshot just before table change */
+
+	List   *tables;		/* List of MV_TriggerTable */
+	bool	has_old;	/* tuples are deleted from any table? */
+	bool	has_new;	/* tuples are inserted into any table? */
+} MV_TriggerHashEntry;
+
+/*
+ * MV_TriggerTable
+ *
+ * IVM related data for tables on which the trigger is invoked.
+ */
+typedef struct MV_TriggerTable
+{
+	Oid		table_id;			/* OID of the modified table */
+	List   *old_tuplestores;	/* tuplestores for deleted tuples */
+	List   *new_tuplestores;	/* tuplestores for inserted tuples */
+
+	List   *rte_indexes;		/* List of RTE index of the modified table */
+	RangeTblEntry *original_rte;	/* the original RTE saved before rewriting query */
+
+	Relation	rel;			/* relation of the modified table */
+	TupleTableSlot *slot;		/* for checking visibility in the pre-state table */
+} MV_TriggerTable;
+
+static HTAB *mv_trigger_info = NULL;
+
+static bool in_delta_calculation = false;
+
+/* ENR name for materialized view delta */
+#define NEW_DELTA_ENRNAME "new_delta"
+#define OLD_DELTA_ENRNAME "old_delta"
+
 static int	matview_maintenance_depth = 0;
 
 static void transientrel_startup(DestReceiver *self, int operation, TupleDesc typeinfo);
@@ -65,7 +122,9 @@ static bool transientrel_receive(TupleTableSlot *slot, DestReceiver *self);
 static void transientrel_shutdown(DestReceiver *self);
 static void transientrel_destroy(DestReceiver *self);
 static uint64 refresh_matview_datafill(DestReceiver *dest, Query *query,
-									   const char *queryString);
+						 QueryEnvironment *queryEnv,
+						 TupleDesc *resultTupleDesc,
+						 const char *queryString);
 static char *make_temptable_name_n(char *tempname, int n);
 static void refresh_by_match_merge(Oid matviewOid, Oid tempOid, Oid relowner,
 								   int save_sec_context);
@@ -73,6 +132,37 @@ static void refresh_by_heap_swap(Oid matviewOid, Oid OIDNewHeap, char relpersist
 static bool is_usable_unique_index(Relation indexRel);
 static void OpenMatViewIncrementalMaintenance(void);
 static void CloseMatViewIncrementalMaintenance(void);
+static Query *get_matview_query(Relation matviewRel);
+
+static Query *rewrite_query_for_preupdate_state(Query *query, List *tables,
+								  ParseState *pstate, Oid matviewid);
+static void register_delta_ENRs(ParseState *pstate, Query *query, List *tables);
+static char *make_delta_enr_name(const char *prefix, Oid relid, int count);
+static RangeTblEntry *get_prestate_rte(RangeTblEntry *rte, MV_TriggerTable *table,
+				 QueryEnvironment *queryEnv, Oid matviewid);
+static RangeTblEntry *replace_rte_with_delta(RangeTblEntry *rte, MV_TriggerTable *table, bool is_new,
+		   QueryEnvironment *queryEnv);
+static Query *rewrite_query_for_counting(Query *query, ParseState *pstate);
+
+static void calc_delta(MV_TriggerTable *table, int rte_index, Query *query,
+			DestReceiver *dest_old, DestReceiver *dest_new,
+			TupleDesc *tupdesc_old, TupleDesc *tupdesc_new,
+			QueryEnvironment *queryEnv);
+static Query *rewrite_query_for_postupdate_state(Query *query, MV_TriggerTable *table, int rte_index);
+
+static void apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *new_tuplestores,
+			TupleDesc tupdesc_old, TupleDesc tupdesc_new,
+			Query *query);
+static void apply_old_delta(const char *matviewname, const char *deltaname_old,
+				List *keys);
+static void apply_new_delta(const char *matviewname, const char *deltaname_new,
+				StringInfo target_list);
+static char *get_matching_condition_string(List *keys);
+static void generate_equal(StringInfo querybuf, Oid opttype,
+			   const char *leftop, const char *rightop);
+
+static void mv_InitHashTables(void);
+static void clean_up_IVM_hash_entry(MV_TriggerHashEntry *entry, bool is_abort);
 
 /*
  * SetMatViewPopulatedState
@@ -114,6 +204,46 @@ SetMatViewPopulatedState(Relation relation, bool newstate)
 	CommandCounterIncrement();
 }
 
+/*
+ * SetMatViewIVMState
+ *		Mark a materialized view as IVM, or not.
+ *
+ * NOTE: caller must be holding an appropriate lock on the relation.
+ */
+void
+SetMatViewIVMState(Relation relation, bool newstate)
+{
+	Relation	pgrel;
+	HeapTuple	tuple;
+
+	Assert(relation->rd_rel->relkind == RELKIND_MATVIEW);
+
+	/*
+	 * Update relation's pg_class entry.  Crucial side-effect: other backends
+	 * (and this one too!) are sent SI message to make them rebuild relcache
+	 * entries.
+	 */
+	pgrel = table_open(RelationRelationId, RowExclusiveLock);
+	tuple = SearchSysCacheCopy1(RELOID,
+								ObjectIdGetDatum(RelationGetRelid(relation)));
+	if (!HeapTupleIsValid(tuple))
+		elog(ERROR, "cache lookup failed for relation %u",
+			 RelationGetRelid(relation));
+
+	((Form_pg_class) GETSTRUCT(tuple))->relisivm = newstate;
+
+	CatalogTupleUpdate(pgrel, &tuple->t_self, tuple);
+
+	heap_freetuple(tuple);
+	table_close(pgrel, RowExclusiveLock);
+
+	/*
+	 * Advance command counter to make the updated pg_class row locally
+	 * visible.
+	 */
+	CommandCounterIncrement();
+}
+
 /*
  * ExecRefreshMatView -- execute a REFRESH MATERIALIZED VIEW command
  *
@@ -140,8 +270,6 @@ ExecRefreshMatView(RefreshMatViewStmt *stmt, const char *queryString,
 {
 	Oid			matviewOid;
 	Relation	matviewRel;
-	RewriteRule *rule;
-	List	   *actions;
 	Query	   *dataQuery;
 	Oid			tableSpace;
 	Oid			relowner;
@@ -155,6 +283,7 @@ ExecRefreshMatView(RefreshMatViewStmt *stmt, const char *queryString,
 	int			save_sec_context;
 	int			save_nestlevel;
 	ObjectAddress address;
+	bool oldPopulated;
 
 	/* Determine strength of lock needed. */
 	concurrent = stmt->concurrent;
@@ -178,6 +307,7 @@ ExecRefreshMatView(RefreshMatViewStmt *stmt, const char *queryString,
 	SetUserIdAndSecContext(relowner,
 						   save_sec_context | SECURITY_RESTRICTED_OPERATION);
 	save_nestlevel = NewGUCNestLevel();
+	oldPopulated = RelationIsPopulated(matviewRel);
 
 	/* Make sure it is a materialized view. */
 	if (matviewRel->rd_rel->relkind != RELKIND_MATVIEW)
@@ -199,32 +329,9 @@ ExecRefreshMatView(RefreshMatViewStmt *stmt, const char *queryString,
 				 errmsg("%s and %s options cannot be used together",
 						"CONCURRENTLY", "WITH NO DATA")));
 
-	/*
-	 * Check that everything is correct for a refresh. Problems at this point
-	 * are internal errors, so elog is sufficient.
-	 */
-	if (matviewRel->rd_rel->relhasrules == false ||
-		matviewRel->rd_rules->numLocks < 1)
-		elog(ERROR,
-			 "materialized view \"%s\" is missing rewrite information",
-			 RelationGetRelationName(matviewRel));
-
-	if (matviewRel->rd_rules->numLocks > 1)
-		elog(ERROR,
-			 "materialized view \"%s\" has too many rules",
-			 RelationGetRelationName(matviewRel));
 
-	rule = matviewRel->rd_rules->rules[0];
-	if (rule->event != CMD_SELECT || !(rule->isInstead))
-		elog(ERROR,
-			 "the rule for materialized view \"%s\" is not a SELECT INSTEAD OF rule",
-			 RelationGetRelationName(matviewRel));
+	dataQuery = get_matview_query(matviewRel);
 
-	actions = rule->actions;
-	if (list_length(actions) != 1)
-		elog(ERROR,
-			 "the rule for materialized view \"%s\" is not a single action",
-			 RelationGetRelationName(matviewRel));
 
 	/*
 	 * Check that there is a unique index with no WHERE clause on one or more
@@ -259,12 +366,6 @@ ExecRefreshMatView(RefreshMatViewStmt *stmt, const char *queryString,
 					 errhint("Create a unique index with no WHERE clause on one or more columns of the materialized view.")));
 	}
 
-	/*
-	 * The stored query was rewritten at the time of the MV definition, but
-	 * has not been scribbled on by the planner.
-	 */
-	dataQuery = linitial_node(Query, actions);
-
 	/*
 	 * Check for active uses of the relation in the current transaction, such
 	 * as open scans.
@@ -292,6 +393,74 @@ ExecRefreshMatView(RefreshMatViewStmt *stmt, const char *queryString,
 		relpersistence = matviewRel->rd_rel->relpersistence;
 	}
 
+	/* delete IMMV triggers. */
+	if (RelationIsIVM(matviewRel) && stmt->skipData )
+	{
+		Relation	tgRel;
+		Relation	depRel;
+		ScanKeyData key;
+		SysScanDesc scan;
+		HeapTuple	tup;
+		ObjectAddresses *immv_triggers;
+
+		immv_triggers = new_object_addresses();
+
+		tgRel = table_open(TriggerRelationId, RowExclusiveLock);
+		depRel = table_open(DependRelationId, RowExclusiveLock);
+
+		/* search triggers that depends on IMMV. */
+		ScanKeyInit(&key,
+					Anum_pg_depend_refobjid,
+					BTEqualStrategyNumber, F_OIDEQ,
+					ObjectIdGetDatum(matviewOid));
+		scan = systable_beginscan(depRel, DependReferenceIndexId, true,
+								  NULL, 1, &key);
+		while ((tup = systable_getnext(scan)) != NULL)
+		{
+			ObjectAddress obj;
+			Form_pg_depend foundDep = (Form_pg_depend) GETSTRUCT(tup);
+
+			if (foundDep->classid == TriggerRelationId)
+			{
+				HeapTuple	tgtup;
+				ScanKeyData tgkey[1];
+				SysScanDesc tgscan;
+				Form_pg_trigger tgform;
+
+				/* Find the trigger name. */
+				ScanKeyInit(&tgkey[0],
+							Anum_pg_trigger_oid,
+							BTEqualStrategyNumber, F_OIDEQ,
+							ObjectIdGetDatum(foundDep->objid));
+
+				tgscan = systable_beginscan(tgRel, TriggerOidIndexId, true,
+											NULL, 1, tgkey);
+				tgtup = systable_getnext(tgscan);
+				if (!HeapTupleIsValid(tgtup))
+					elog(ERROR, "could not find tuple for immv trigger %u", foundDep->objid);
+
+				tgform = (Form_pg_trigger) GETSTRUCT(tgtup);
+
+				/* If trigger is created by IMMV, delete it. */
+				if (strncmp(NameStr(tgform->tgname), "IVM_trigger_", 12) == 0)
+				{
+					obj.classId = foundDep->classid;
+					obj.objectId = foundDep->objid;
+					obj.objectSubId = foundDep->refobjsubid;
+					add_exact_object_address(&obj, immv_triggers);
+				}
+				systable_endscan(tgscan);
+			}
+		}
+		systable_endscan(scan);
+
+		performMultipleDeletions(immv_triggers, DROP_RESTRICT, PERFORM_DELETION_INTERNAL);
+
+		table_close(depRel, RowExclusiveLock);
+		table_close(tgRel, RowExclusiveLock);
+		free_object_addresses(immv_triggers);
+	}
+
 	/*
 	 * Create the transient table that will receive the regenerated data. Lock
 	 * it against access by any other process until commit (by which time it
@@ -305,7 +474,7 @@ ExecRefreshMatView(RefreshMatViewStmt *stmt, const char *queryString,
 
 	/* Generate the data, if wanted. */
 	if (!stmt->skipData)
-		processed = refresh_matview_datafill(dest, dataQuery, queryString);
+		processed = refresh_matview_datafill(dest, dataQuery, NULL, NULL, queryString);
 
 	/* Make the matview match the newly generated data. */
 	if (concurrent)
@@ -340,6 +509,12 @@ ExecRefreshMatView(RefreshMatViewStmt *stmt, const char *queryString,
 			pgstat_count_heap_insert(matviewRel, processed);
 	}
 
+	if (!stmt->skipData && RelationIsIVM(matviewRel) && !oldPopulated)
+	{
+		CreateIndexOnIMMV(dataQuery, matviewRel);
+		CreateIvmTriggersOnBaseTables(dataQuery, matviewOid);
+	}
+
 	table_close(matviewRel, NoLock);
 
 	/* Roll back any GUC changes */
@@ -374,6 +549,8 @@ ExecRefreshMatView(RefreshMatViewStmt *stmt, const char *queryString,
  */
 static uint64
 refresh_matview_datafill(DestReceiver *dest, Query *query,
+						 QueryEnvironment *queryEnv,
+						 TupleDesc *resultTupleDesc,
 						 const char *queryString)
 {
 	List	   *rewritten;
@@ -410,7 +587,7 @@ refresh_matview_datafill(DestReceiver *dest, Query *query,
 	/* Create a QueryDesc, redirecting output to our tuple receiver */
 	queryDesc = CreateQueryDesc(plan, queryString,
 								GetActiveSnapshot(), InvalidSnapshot,
-								dest, NULL, NULL, 0);
+								dest, NULL, queryEnv ? queryEnv: NULL, 0);
 
 	/* call ExecutorStart to prepare the plan for execution */
 	ExecutorStart(queryDesc, 0);
@@ -420,6 +597,9 @@ refresh_matview_datafill(DestReceiver *dest, Query *query,
 
 	processed = queryDesc->estate->es_processed;
 
+	if (resultTupleDesc)
+		*resultTupleDesc = CreateTupleDescCopy(queryDesc->tupDesc);
+
 	/* and clean up */
 	ExecutorFinish(queryDesc);
 	ExecutorEnd(queryDesc);
@@ -953,3 +1133,1219 @@ CloseMatViewIncrementalMaintenance(void)
 	matview_maintenance_depth--;
 	Assert(matview_maintenance_depth >= 0);
 }
+
+/*
+ * get_matview_query - get the Query from a matview's _RETURN rule.
+ */
+static Query *
+get_matview_query(Relation matviewRel)
+{
+	RewriteRule *rule;
+	List * actions;
+
+	/*
+	 * Check that everything is correct for a refresh. Problems at this point
+	 * are internal errors, so elog is sufficient.
+	 */
+	if (matviewRel->rd_rel->relhasrules == false ||
+		matviewRel->rd_rules->numLocks < 1)
+		elog(ERROR,
+			 "materialized view \"%s\" is missing rewrite information",
+			 RelationGetRelationName(matviewRel));
+
+	if (matviewRel->rd_rules->numLocks > 1)
+		elog(ERROR,
+			 "materialized view \"%s\" has too many rules",
+			 RelationGetRelationName(matviewRel));
+
+	rule = matviewRel->rd_rules->rules[0];
+	if (rule->event != CMD_SELECT || !(rule->isInstead))
+		elog(ERROR,
+			 "the rule for materialized view \"%s\" is not a SELECT INSTEAD OF rule",
+			 RelationGetRelationName(matviewRel));
+
+	actions = rule->actions;
+	if (list_length(actions) != 1)
+		elog(ERROR,
+			 "the rule for materialized view \"%s\" is not a single action",
+			 RelationGetRelationName(matviewRel));
+
+	/*
+	 * The stored query was rewritten at the time of the MV definition, but
+	 * has not been scribbled on by the planner.
+	 */
+	return linitial_node(Query, actions);
+}
+
+
+/* ----------------------------------------------------
+ *		Incremental View Maintenance routines
+ * ---------------------------------------------------
+ */
+
+/*
+ * IVM_immediate_before
+ *
+ * IVM trigger function invoked before base table is modified. If this is
+ * invoked firstly in the same statement, we save the transaction id and the
+ * command id at that time.
+ */
+Datum
+IVM_immediate_before(PG_FUNCTION_ARGS)
+{
+	TriggerData *trigdata = (TriggerData *) fcinfo->context;
+	char	   *matviewOid_text = trigdata->tg_trigger->tgargs[0];
+	char	   *ex_lock_text = trigdata->tg_trigger->tgargs[1];
+	Oid			matviewOid;
+	MV_TriggerHashEntry *entry;
+	bool	found;
+	bool	ex_lock;
+
+	matviewOid = DatumGetObjectId(DirectFunctionCall1(oidin, CStringGetDatum(matviewOid_text)));
+	ex_lock = DatumGetBool(DirectFunctionCall1(boolin, CStringGetDatum(ex_lock_text)));
+
+	/* If the view has more than one tables, we have to use an exclusive lock. */
+	if (ex_lock)
+	{
+		/*
+		 * Wait for concurrent transactions which update this materialized view at
+		 * READ COMMITED. This is needed to see changes committed in other
+		 * transactions. No wait and raise an error at REPEATABLE READ or
+		 * SERIALIZABLE to prevent update anomalies of matviews.
+		 * XXX: dead-lock is possible here.
+		 */
+		if (!IsolationUsesXactSnapshot())
+			LockRelationOid(matviewOid, ExclusiveLock);
+		else if (!ConditionalLockRelationOid(matviewOid, ExclusiveLock))
+		{
+			/* try to throw error by name; relation could be deleted... */
+			char	   *relname = get_rel_name(matviewOid);
+
+			if (!relname)
+				ereport(ERROR,
+						(errcode(ERRCODE_LOCK_NOT_AVAILABLE),
+						errmsg("could not obtain lock on materialized view during incremental maintenance")));
+
+			ereport(ERROR,
+					(errcode(ERRCODE_LOCK_NOT_AVAILABLE),
+					errmsg("could not obtain lock on materialized view \"%s\" during incremental maintenance",
+							relname)));
+		}
+	}
+	else
+		LockRelationOid(matviewOid, RowExclusiveLock);
+
+	/*
+	 * On the first call initialize the hashtable
+	 */
+	if (!mv_trigger_info)
+		mv_InitHashTables();
+
+	entry = (MV_TriggerHashEntry *) hash_search(mv_trigger_info,
+											  (void *) &matviewOid,
+											  HASH_ENTER, &found);
+
+	/* On the first BEFORE to update the view, initialize trigger data */
+	if (!found)
+	{
+		/*
+		 * Get a snapshot just before the table was modified for checking
+		 * tuple visibility in the pre-update state of the table.
+		 */
+		Snapshot snapshot = GetActiveSnapshot();
+
+		entry->matview_id = matviewOid;
+		entry->before_trig_count = 0;
+		entry->after_trig_count = 0;
+		entry->snapshot = RegisterSnapshot(snapshot);
+		entry->tables = NIL;
+		entry->has_old = false;
+		entry->has_new = false;
+	}
+
+	entry->before_trig_count++;
+
+	return PointerGetDatum(NULL);
+}
+
+/*
+ * IVM_immediate_maintenance
+ *
+ * IVM trigger function invoked after base table is modified.
+ * For each table, tuplestores of transition tables are collected.
+ * and after the last modification
+ */
+Datum
+IVM_immediate_maintenance(PG_FUNCTION_ARGS)
+{
+	TriggerData *trigdata = (TriggerData *) fcinfo->context;
+	Relation	rel;
+	Oid			relid;
+	Oid			matviewOid;
+	Query	   *query;
+	Query	   *rewritten = NULL;
+	char	   *matviewOid_text = trigdata->tg_trigger->tgargs[0];
+	Relation	matviewRel;
+	int old_depth = matview_maintenance_depth;
+
+	Oid			relowner;
+	Tuplestorestate *old_tuplestore = NULL;
+	Tuplestorestate *new_tuplestore = NULL;
+	DestReceiver *dest_new = NULL, *dest_old = NULL;
+	Oid			save_userid;
+	int			save_sec_context;
+	int			save_nestlevel;
+
+	MV_TriggerHashEntry *entry;
+	MV_TriggerTable		*table;
+	bool	found;
+
+	ParseState		 *pstate;
+	QueryEnvironment *queryEnv = create_queryEnv();
+	MemoryContext	oldcxt;
+	ListCell   *lc;
+	int			i;
+
+
+	/* Create a ParseState for rewriting the view definition query */
+	pstate = make_parsestate(NULL);
+	pstate->p_queryEnv = queryEnv;
+	pstate->p_expr_kind = EXPR_KIND_SELECT_TARGET;
+
+	rel = trigdata->tg_relation;
+	relid = rel->rd_id;
+
+	matviewOid = DatumGetObjectId(DirectFunctionCall1(oidin, CStringGetDatum(matviewOid_text)));
+
+	/*
+	 * On the first call initialize the hashtable
+	 */
+	if (!mv_trigger_info)
+		mv_InitHashTables();
+
+	/* get the entry for this materialized view */
+	entry = (MV_TriggerHashEntry *) hash_search(mv_trigger_info,
+											  (void *) &matviewOid,
+											  HASH_FIND, &found);
+	Assert (found && entry != NULL);
+	entry->after_trig_count++;
+
+	/* search the entry for the modified table and create new entry if not found */
+	found = false;
+	foreach(lc, entry->tables)
+	{
+		table = (MV_TriggerTable *) lfirst(lc);
+		if (table->table_id == relid)
+		{
+			found = true;
+			break;
+		}
+	}
+	if (!found)
+	{
+		oldcxt = MemoryContextSwitchTo(TopTransactionContext);
+
+		table = (MV_TriggerTable *) palloc0(sizeof(MV_TriggerTable));
+		table->table_id = relid;
+		table->old_tuplestores = NIL;
+		table->new_tuplestores = NIL;
+		table->rte_indexes = NIL;
+		table->slot = MakeSingleTupleTableSlot(RelationGetDescr(rel), table_slot_callbacks(rel));
+		table->rel = table_open(RelationGetRelid(rel), NoLock);
+		entry->tables = lappend(entry->tables, table);
+
+		MemoryContextSwitchTo(oldcxt);
+	}
+
+	/* Save the transition tables and make a request to not free immediately */
+	if (trigdata->tg_oldtable)
+	{
+		oldcxt = MemoryContextSwitchTo(TopTransactionContext);
+		table->old_tuplestores = lappend(table->old_tuplestores, trigdata->tg_oldtable);
+		entry->has_old = true;
+		MemoryContextSwitchTo(oldcxt);
+	}
+	if (trigdata->tg_newtable)
+	{
+		oldcxt = MemoryContextSwitchTo(TopTransactionContext);
+		table->new_tuplestores = lappend(table->new_tuplestores, trigdata->tg_newtable);
+		entry->has_new = true;
+		MemoryContextSwitchTo(oldcxt);
+	}
+	if (entry->has_new || entry->has_old)
+	{
+		CmdType cmd;
+
+		if (TRIGGER_FIRED_BY_INSERT(trigdata->tg_event))
+			cmd = CMD_INSERT;
+		else if (TRIGGER_FIRED_BY_DELETE(trigdata->tg_event))
+			cmd = CMD_DELETE;
+		else if (TRIGGER_FIRED_BY_UPDATE(trigdata->tg_event))
+			cmd = CMD_UPDATE;
+		else
+			elog(ERROR,"unsupported trigger type");
+
+		/* Prolong lifespan of transition tables to the end of the last AFTER trigger */
+		SetTransitionTablePreserved(relid, cmd);
+	}
+
+
+	/* If this is not the last AFTER trigger call, immediately exit. */
+	Assert (entry->before_trig_count >= entry->after_trig_count);
+	if (entry->before_trig_count != entry->after_trig_count)
+		return PointerGetDatum(NULL);
+
+	/*
+	 * If this is the last AFTER trigger call, continue and update the view.
+	 */
+
+	/*
+	 * Advance command counter to make the updated base table row locally
+	 * visible.
+	 */
+	CommandCounterIncrement();
+
+	matviewRel = table_open(matviewOid, NoLock);
+
+	/* Make sure it is a materialized view. */
+	Assert(matviewRel->rd_rel->relkind == RELKIND_MATVIEW);
+
+	/*
+	 * Get and push the latast snapshot to see any changes which is committed
+	 * during waiting in other transactions at READ COMMITTED level.
+	 */
+	PushActiveSnapshot(GetTransactionSnapshot());
+
+	/*
+	 * Check for active uses of the relation in the current transaction, such
+	 * as open scans.
+	 *
+	 * NB: We count on this to protect us against problems with refreshing the
+	 * data using TABLE_INSERT_FROZEN.
+	 */
+	CheckTableNotInUse(matviewRel, "refresh a materialized view incrementally");
+
+	/*
+	 * Switch to the owner's userid, so that any functions are run as that
+	 * user.  Also arrange to make GUC variable changes local to this command.
+	 * We will switch modes when we are about to execute user code.
+	 */
+	relowner = matviewRel->rd_rel->relowner;
+	GetUserIdAndSecContext(&save_userid, &save_sec_context);
+	SetUserIdAndSecContext(relowner,
+						   save_sec_context | SECURITY_RESTRICTED_OPERATION);
+	save_nestlevel = NewGUCNestLevel();
+
+	/* get view query*/
+	query = get_matview_query(matviewRel);
+
+	/*
+	 * When a base table is truncated, the view content will be empty if the
+	 * view definition query does not contain an aggregate without a GROUP clause.
+	 * Therefore, such views can be truncated.
+	 */
+	if (TRIGGER_FIRED_BY_TRUNCATE(trigdata->tg_event))
+	{
+		ExecuteTruncateGuts(list_make1(matviewRel), list_make1_oid(matviewOid),
+							NIL, DROP_RESTRICT, false, false);
+
+		/* Clean up hash entry and delete tuplestores */
+		clean_up_IVM_hash_entry(entry, false);
+
+		/* Pop the original snapshot. */
+		PopActiveSnapshot();
+
+		table_close(matviewRel, NoLock);
+
+		/* Roll back any GUC changes */
+		AtEOXact_GUC(false, save_nestlevel);
+
+		/* Restore userid and security context */
+		SetUserIdAndSecContext(save_userid, save_sec_context);
+
+		return PointerGetDatum(NULL);
+	}
+
+	/*
+	 * rewrite query for calculating deltas
+	 */
+
+	rewritten = copyObject(query);
+
+	/* Replace resnames in a target list with materialized view's attnames */
+	i = 0;
+	foreach (lc, rewritten->targetList)
+	{
+		TargetEntry *tle = (TargetEntry *) lfirst(lc);
+		Form_pg_attribute attr = TupleDescAttr(matviewRel->rd_att, i);
+		char *resname = NameStr(attr->attname);
+
+		tle->resname = pstrdup(resname);
+		i++;
+	}
+
+	/* Set all tables in the query to pre-update state */
+	rewritten = rewrite_query_for_preupdate_state(rewritten, entry->tables,
+												  pstate, matviewOid);
+	/* Rewrite for counting duplicated tuples */
+	rewritten = rewrite_query_for_counting(rewritten, pstate);
+
+	/* Create tuplestores to store view deltas */
+	if (entry->has_old)
+	{
+		oldcxt = MemoryContextSwitchTo(TopTransactionContext);
+
+		old_tuplestore = tuplestore_begin_heap(false, false, work_mem);
+		dest_old = CreateDestReceiver(DestTuplestore);
+		SetTuplestoreDestReceiverParams(dest_old,
+									old_tuplestore,
+									TopTransactionContext,
+									false,
+									NULL,
+									NULL);
+
+		MemoryContextSwitchTo(oldcxt);
+	}
+	if (entry->has_new)
+	{
+		oldcxt = MemoryContextSwitchTo(TopTransactionContext);
+
+		new_tuplestore = tuplestore_begin_heap(false, false, work_mem);
+		dest_new = CreateDestReceiver(DestTuplestore);
+		SetTuplestoreDestReceiverParams(dest_new,
+									new_tuplestore,
+									TopTransactionContext,
+									false,
+									NULL,
+									NULL);
+		MemoryContextSwitchTo(oldcxt);
+	}
+
+	/* for all modified tables */
+	foreach(lc, entry->tables)
+	{
+		ListCell *lc2;
+
+		table = (MV_TriggerTable *) lfirst(lc);
+
+		/* loop for self-join */
+		foreach(lc2, table->rte_indexes)
+		{
+			int	rte_index = lfirst_int(lc2);
+			TupleDesc		tupdesc_old;
+			TupleDesc		tupdesc_new;
+
+			/* calculate delta tables */
+			calc_delta(table, rte_index, rewritten, dest_old, dest_new,
+					   &tupdesc_old, &tupdesc_new, queryEnv);
+
+			/* Set the table in the query to post-update state */
+			rewritten = rewrite_query_for_postupdate_state(rewritten, table, rte_index);
+
+			PG_TRY();
+			{
+				/* apply the delta tables to the materialized view */
+				apply_delta(matviewOid, old_tuplestore, new_tuplestore,
+							tupdesc_old, tupdesc_new, query);
+			}
+			PG_CATCH();
+			{
+				matview_maintenance_depth = old_depth;
+				PG_RE_THROW();
+			}
+			PG_END_TRY();
+
+			/* clear view delta tuplestores */
+			if (old_tuplestore)
+				tuplestore_clear(old_tuplestore);
+			if (new_tuplestore)
+				tuplestore_clear(new_tuplestore);
+		}
+	}
+
+	/* Clean up hash entry and delete tuplestores */
+	clean_up_IVM_hash_entry(entry, false);
+	if (old_tuplestore)
+	{
+		dest_old->rDestroy(dest_old);
+		tuplestore_end(old_tuplestore);
+	}
+	if (new_tuplestore)
+	{
+		dest_new->rDestroy(dest_new);
+		tuplestore_end(new_tuplestore);
+	}
+
+	/* Pop the original snapshot. */
+	PopActiveSnapshot();
+
+	table_close(matviewRel, NoLock);
+
+	/* Roll back any GUC changes */
+	AtEOXact_GUC(false, save_nestlevel);
+
+	/* Restore userid and security context */
+	SetUserIdAndSecContext(save_userid, save_sec_context);
+
+	return PointerGetDatum(NULL);
+}
+
+/*
+ * rewrite_query_for_preupdate_state
+ *
+ * Rewrite the query so that base tables' RTEs will represent "pre-update"
+ * state of tables. This is necessary to calculate view delta after multiple
+ * tables are modified.
+ */
+static Query*
+rewrite_query_for_preupdate_state(Query *query, List *tables,
+								  ParseState *pstate, Oid matviewid)
+{
+	ListCell *lc;
+	int num_rte = list_length(query->rtable);
+	int i;
+
+
+	/* register delta ENRs */
+	register_delta_ENRs(pstate, query, tables);
+
+	/* XXX: Is necessary? Is this right timing? */
+	AcquireRewriteLocks(query, true, false);
+
+	i = 1;
+	foreach(lc, query->rtable)
+	{
+		RangeTblEntry *r = (RangeTblEntry*) lfirst(lc);
+
+		ListCell *lc2;
+		foreach(lc2, tables)
+		{
+			MV_TriggerTable *table = (MV_TriggerTable *) lfirst(lc2);
+			/*
+			 * if the modified table is found then replace the original RTE with
+			 * "pre-state" RTE and append its index to the list.
+			 */
+			if (r->relid == table->table_id)
+			{
+				List *securityQuals;
+				List *withCheckOptions;
+				bool  hasRowSecurity;
+				bool  hasSubLinks;
+
+				RangeTblEntry *rte_pre = get_prestate_rte(r, table, pstate->p_queryEnv, matviewid);
+
+				/*
+				 * Set a row security poslicies of the modified table to the subquery RTE which
+				 * represents the pre-update state of the table.
+				 */
+				get_row_security_policies(query, table->original_rte, i,
+										  &securityQuals, &withCheckOptions,
+										  &hasRowSecurity, &hasSubLinks);
+
+				if (hasRowSecurity)
+				{
+					query->hasRowSecurity = true;
+					rte_pre->security_barrier = true;
+				}
+				if (hasSubLinks)
+					query->hasSubLinks = true;
+
+				rte_pre->securityQuals = securityQuals;
+				lfirst(lc) = rte_pre;
+
+				table->rte_indexes = lappend_int(table->rte_indexes, i);
+				break;
+			}
+		}
+
+		/* finish the loop if we processed all RTE included in the original query */
+		if (i++ >= num_rte)
+			break;
+	}
+
+	return query;
+}
+
+/*
+ * register_delta_ENRs
+ *
+ * For all modified tables, make ENRs for their transition tables
+ * and register them to the queryEnv. ENR's RTEs are also appended
+ * into the list in query tree.
+ */
+static void
+register_delta_ENRs(ParseState *pstate, Query *query, List *tables)
+{
+	QueryEnvironment *queryEnv = pstate->p_queryEnv;
+	ListCell *lc;
+	RangeTblEntry	*rte;
+
+	foreach(lc, tables)
+	{
+		MV_TriggerTable *table = (MV_TriggerTable *) lfirst(lc);
+		ListCell *lc2;
+		int count;
+
+		count = 0;
+		foreach(lc2, table->old_tuplestores)
+		{
+			Tuplestorestate *oldtable = (Tuplestorestate *) lfirst(lc2);
+			EphemeralNamedRelation enr =
+				palloc(sizeof(EphemeralNamedRelationData));
+			ParseNamespaceItem *nsitem;
+
+			enr->md.name = make_delta_enr_name("old", table->table_id, count);
+			enr->md.reliddesc = table->table_id;
+			enr->md.tupdesc = NULL;
+			enr->md.enrtype = ENR_NAMED_TUPLESTORE;
+			enr->md.enrtuples = tuplestore_tuple_count(oldtable);
+			enr->reldata = oldtable;
+			register_ENR(queryEnv, enr);
+
+			nsitem = addRangeTableEntryForENR(pstate, makeRangeVar(NULL, enr->md.name, -1), true);
+			rte = nsitem->p_rte;
+
+			query->rtable = lappend(query->rtable, rte);
+
+			count++;
+		}
+
+		count = 0;
+		foreach(lc2, table->new_tuplestores)
+		{
+			Tuplestorestate *newtable = (Tuplestorestate *) lfirst(lc2);
+			EphemeralNamedRelation enr =
+				palloc(sizeof(EphemeralNamedRelationData));
+			ParseNamespaceItem *nsitem;
+
+			enr->md.name = make_delta_enr_name("new", table->table_id, count);
+			enr->md.reliddesc = table->table_id;
+			enr->md.tupdesc = NULL;
+			enr->md.enrtype = ENR_NAMED_TUPLESTORE;
+			enr->md.enrtuples = tuplestore_tuple_count(newtable);
+			enr->reldata = newtable;
+			register_ENR(queryEnv, enr);
+
+			nsitem = addRangeTableEntryForENR(pstate, makeRangeVar(NULL, enr->md.name, -1), true);
+			rte = nsitem->p_rte;
+
+			query->rtable = lappend(query->rtable, rte);
+
+			count++;
+		}
+	}
+}
+
+#define DatumGetItemPointer(X)	 ((ItemPointer) DatumGetPointer(X))
+#define PG_GETARG_ITEMPOINTER(n) DatumGetItemPointer(PG_GETARG_DATUM(n))
+
+/*
+ * ivm_visible_in_prestate
+ *
+ * Check visibility of a tuple specified by the tableoid and item pointer
+ * using the snapshot taken just before the table was modified.
+ */
+Datum
+ivm_visible_in_prestate(PG_FUNCTION_ARGS)
+{
+	Oid			tableoid = PG_GETARG_OID(0);
+	ItemPointer itemPtr = PG_GETARG_ITEMPOINTER(1);
+	Oid			matviewOid = PG_GETARG_OID(2);
+	MV_TriggerHashEntry *entry;
+	MV_TriggerTable		*table = NULL;
+	ListCell   *lc;
+	bool	found;
+	bool	result;
+
+	if (!in_delta_calculation)
+		ereport(ERROR,
+				(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+				 errmsg("ivm_visible_in_prestate can be called only in delta calculation")));
+
+	entry = (MV_TriggerHashEntry *) hash_search(mv_trigger_info,
+											  (void *) &matviewOid,
+											  HASH_FIND, &found);
+	Assert (found && entry != NULL);
+
+	foreach(lc, entry->tables)
+	{
+		table = (MV_TriggerTable *) lfirst(lc);
+		if (table->table_id == tableoid)
+			break;
+	}
+
+	Assert (table != NULL);
+
+	result = table_tuple_fetch_row_version(table->rel, itemPtr, entry->snapshot, table->slot);
+
+	PG_RETURN_BOOL(result);
+}
+
+/*
+ * get_prestate_rte
+ *
+ * Rewrite RTE of the modified table to a subquery which represents
+ * "pre-state" table. The original RTE is saved in table->rte_original.
+ */
+static RangeTblEntry*
+get_prestate_rte(RangeTblEntry *rte, MV_TriggerTable *table,
+				 QueryEnvironment *queryEnv, Oid matviewid)
+{
+	StringInfoData str;
+	RawStmt *raw;
+	Query *subquery;
+	Relation rel;
+	ParseState *pstate;
+	char *relname;
+	int i;
+
+	pstate = make_parsestate(NULL);
+	pstate->p_queryEnv = queryEnv;
+	pstate->p_expr_kind = EXPR_KIND_SELECT_TARGET;
+
+	/*
+	 * We can use NoLock here since AcquireRewriteLocks should
+	 * have locked the relation already.
+	 */
+	rel = table_open(table->table_id, NoLock);
+	relname = quote_qualified_identifier(
+					get_namespace_name(RelationGetNamespace(rel)),
+									   RelationGetRelationName(rel));
+	table_close(rel, NoLock);
+
+	/*
+	 * Filtering inserted row using the snapshot taken before the table
+	 * is modified. ctid is required for maintaining outer join views.
+	 */
+	initStringInfo(&str);
+	appendStringInfo(&str,
+		"SELECT t.* FROM %s t"
+		" WHERE pg_catalog.ivm_visible_in_prestate(t.tableoid, t.ctid ,%d::pg_catalog.oid)",
+			relname, matviewid);
+
+	/*
+	 * Append deleted rows contained in old transition tables.
+	 */
+	for (i = 0; i < list_length(table->old_tuplestores); i++)
+	{
+		appendStringInfo(&str, " UNION ALL ");
+		appendStringInfo(&str," SELECT * FROM %s",
+			make_delta_enr_name("old", table->table_id, i));
+	}
+
+	/* Get a subquery representing pre-state of the table */
+	raw = (RawStmt*)linitial(raw_parser(str.data, RAW_PARSE_DEFAULT));
+	subquery = transformStmt(pstate, raw->stmt);
+
+	/* save the original RTE */
+	table->original_rte = copyObject(rte);
+
+	rte->rtekind = RTE_SUBQUERY;
+	rte->subquery = subquery;
+	rte->security_barrier = false;
+
+	/* Clear fields that should not be set in a subquery RTE */
+	rte->relid = InvalidOid;
+	rte->relkind = 0;
+	rte->rellockmode = 0;
+	rte->tablesample = NULL;
+	rte->perminfoindex = 0;         /* no permission checking for this RTE */
+	rte->inh = false;			/* must not be set for a subquery */
+
+	return rte;
+}
+
+/*
+ * make_delta_enr_name
+ *
+ * Make a name for ENR of a transition table from the base table's oid.
+ * prefix will be "new" or "old" depending on its transition table kind..
+ */
+static char*
+make_delta_enr_name(const char *prefix, Oid relid, int count)
+{
+	char buf[NAMEDATALEN];
+	char *name;
+
+	snprintf(buf, NAMEDATALEN, "__ivm_%s_%u_%u", prefix, relid, count);
+	name = pstrdup(buf);
+
+	return name;
+}
+
+/*
+ * replace_rte_with_delta
+ *
+ * Replace RTE of the modified table with a single table delta that combine its
+ * all transition tables.
+ */
+static RangeTblEntry*
+replace_rte_with_delta(RangeTblEntry *rte, MV_TriggerTable *table, bool is_new,
+					   QueryEnvironment *queryEnv)
+{
+	Oid relid = table->table_id;
+	StringInfoData str;
+	ParseState	*pstate;
+	RawStmt *raw;
+	Query *sub;
+	int		num_tuplestores = list_length(is_new ? table->new_tuplestores : table->old_tuplestores);
+	int		i;
+
+	/* the previous RTE must be a subquery which represents "pre-state" table */
+	Assert(rte->rtekind == RTE_SUBQUERY);
+
+	/* Create a ParseState for rewriting the view definition query */
+	pstate = make_parsestate(NULL);
+	pstate->p_queryEnv = queryEnv;
+	pstate->p_expr_kind = EXPR_KIND_SELECT_TARGET;
+
+	initStringInfo(&str);
+
+	for (i = 0; i < num_tuplestores; i++)
+	{
+		if (i > 0)
+			appendStringInfo(&str, " UNION ALL ");
+
+		appendStringInfo(&str,
+			" SELECT * FROM %s",
+			make_delta_enr_name(is_new ? "new" : "old", relid, i));
+	}
+
+	raw = (RawStmt*)linitial(raw_parser(str.data, RAW_PARSE_DEFAULT));
+	sub = transformStmt(pstate, raw->stmt);
+
+	/*
+	 * Update the subquery so that it represent the combined transition
+	 * table.  Note that we leave the security_barrier and securityQuals
+	 * fields so that the subquery relation can be protected by the RLS
+	 * policy as same as the modified table.
+	 */
+	rte->rtekind = RTE_SUBQUERY;
+	rte->subquery = sub;
+
+	return rte;
+}
+
+/*
+ * rewrite_query_for_counting
+ *
+ * Rewrite query for counting duplicated tuples.
+ */
+static Query *
+rewrite_query_for_counting(Query *query, ParseState *pstate)
+{
+	TargetEntry *tle_count;
+	FuncCall *fn;
+	Node *node;
+
+	/* Add count(*) for counting distinct tuples in views */
+	fn = makeFuncCall(SystemFuncName("count"), NIL, COERCE_EXPLICIT_CALL, -1);
+	fn->agg_star = true;
+	if (!query->groupClause && !query->hasAggs)
+		query->groupClause = transformDistinctClause(NULL, &query->targetList, query->sortClause, false);
+
+	node = ParseFuncOrColumn(pstate, fn->funcname, NIL, NULL, fn, false, -1);
+
+	tle_count = makeTargetEntry((Expr *) node,
+								list_length(query->targetList) + 1,
+								pstrdup("__ivm_count__"),
+								false);
+	query->targetList = lappend(query->targetList, tle_count);
+	query->hasAggs = true;
+
+	return query;
+}
+
+/*
+ * calc_delta
+ *
+ * Calculate view deltas generated under the modification of a table specified
+ * by the RTE index.
+ */
+static void
+calc_delta(MV_TriggerTable *table, int rte_index, Query *query,
+			DestReceiver *dest_old, DestReceiver *dest_new,
+			TupleDesc *tupdesc_old, TupleDesc *tupdesc_new,
+			QueryEnvironment *queryEnv)
+{
+	ListCell *lc = list_nth_cell(query->rtable, rte_index - 1);
+	RangeTblEntry *rte = (RangeTblEntry *) lfirst(lc);
+
+	in_delta_calculation = true;
+
+	/* Generate old delta */
+	if (list_length(table->old_tuplestores) > 0)
+	{
+		/* Replace the modified table with the old delta table and calculate the old view delta. */
+		replace_rte_with_delta(rte, table, false, queryEnv);
+		refresh_matview_datafill(dest_old, query, queryEnv, tupdesc_old, "");
+	}
+
+	/* Generate new delta */
+	if (list_length(table->new_tuplestores) > 0)
+	{
+		/* Replace the modified table with the new delta table and calculate the new view delta*/
+		replace_rte_with_delta(rte, table, true, queryEnv);
+		refresh_matview_datafill(dest_new, query, queryEnv, tupdesc_new, "");
+	}
+
+	in_delta_calculation = false;
+}
+
+/*
+ * rewrite_query_for_postupdate_state
+ *
+ * Rewrite the query so that the specified base table's RTEs will represent
+ * "post-update" state of tables. This is called after the view delta
+ * calculation due to changes on this table finishes.
+ */
+static Query*
+rewrite_query_for_postupdate_state(Query *query, MV_TriggerTable *table, int rte_index)
+{
+	ListCell *lc = list_nth_cell(query->rtable, rte_index - 1);
+
+	/* Retore the original RTE */
+	lfirst(lc) = table->original_rte;
+
+	return query;
+}
+
+/*
+ * apply_delta
+ *
+ * Apply deltas to the materialized view. In outer join cases, this requires
+ * the view maintenance graph.
+ */
+static void
+apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *new_tuplestores,
+			TupleDesc tupdesc_old, TupleDesc tupdesc_new,
+			Query *query)
+{
+	StringInfoData querybuf;
+	StringInfoData target_list_buf;
+	Relation	matviewRel;
+	char	   *matviewname;
+	ListCell	*lc;
+	int			i;
+	List	   *keys = NIL;
+
+
+	/*
+	 * get names of the materialized view and delta tables
+	 */
+
+	matviewRel = table_open(matviewOid, NoLock);
+	matviewname = quote_qualified_identifier(get_namespace_name(RelationGetNamespace(matviewRel)),
+											 RelationGetRelationName(matviewRel));
+
+	/*
+	 * Build parts of the maintenance queries
+	 */
+
+	initStringInfo(&querybuf);
+	initStringInfo(&target_list_buf);
+
+	/* build string of target list */
+	for (i = 0; i < matviewRel->rd_att->natts; i++)
+	{
+		Form_pg_attribute attr = TupleDescAttr(matviewRel->rd_att, i);
+		char   *resname = NameStr(attr->attname);
+
+		if (i != 0)
+			appendStringInfo(&target_list_buf, ", ");
+		appendStringInfo(&target_list_buf, "%s", quote_qualified_identifier(NULL, resname));
+	}
+
+	i = 0;
+	foreach (lc, query->targetList)
+	{
+		TargetEntry *tle = (TargetEntry *) lfirst(lc);
+		Form_pg_attribute attr = TupleDescAttr(matviewRel->rd_att, i);
+
+		i++;
+
+		if (tle->resjunk)
+			continue;
+
+		keys = lappend(keys, attr);
+	}
+
+	/* Start maintaining the materialized view. */
+	OpenMatViewIncrementalMaintenance();
+
+	/* Open SPI context. */
+	if (SPI_connect() != SPI_OK_CONNECT)
+		elog(ERROR, "SPI_connect failed");
+
+	/* For tuple deletion */
+	if (old_tuplestores && tuplestore_tuple_count(old_tuplestores) > 0)
+	{
+		EphemeralNamedRelation enr = palloc(sizeof(EphemeralNamedRelationData));
+		int				rc;
+
+		/* convert tuplestores to ENR, and register for SPI */
+		enr->md.name = pstrdup(OLD_DELTA_ENRNAME);
+		enr->md.reliddesc = InvalidOid;
+		enr->md.tupdesc = tupdesc_old;
+		enr->md.enrtype = ENR_NAMED_TUPLESTORE;
+		enr->md.enrtuples = tuplestore_tuple_count(old_tuplestores);
+		enr->reldata = old_tuplestores;
+
+		rc = SPI_register_relation(enr);
+		if (rc != SPI_OK_REL_REGISTER)
+			elog(ERROR, "SPI_register failed");
+
+		apply_old_delta(matviewname, OLD_DELTA_ENRNAME, keys);
+
+	}
+	/* For tuple insertion */
+	if (new_tuplestores && tuplestore_tuple_count(new_tuplestores) > 0)
+	{
+		EphemeralNamedRelation enr = palloc(sizeof(EphemeralNamedRelationData));
+		int rc;
+
+		/* convert tuplestores to ENR, and register for SPI */
+		enr->md.name = pstrdup(NEW_DELTA_ENRNAME);
+		enr->md.reliddesc = InvalidOid;
+		enr->md.tupdesc = tupdesc_new;;
+		enr->md.enrtype = ENR_NAMED_TUPLESTORE;
+		enr->md.enrtuples = tuplestore_tuple_count(new_tuplestores);
+		enr->reldata = new_tuplestores;
+
+		rc = SPI_register_relation(enr);
+		if (rc != SPI_OK_REL_REGISTER)
+			elog(ERROR, "SPI_register failed");
+
+		/* apply new delta */
+		apply_new_delta(matviewname, NEW_DELTA_ENRNAME, &target_list_buf);
+	}
+
+	/* We're done maintaining the materialized view. */
+	CloseMatViewIncrementalMaintenance();
+
+	table_close(matviewRel, NoLock);
+
+	/* Close SPI context. */
+	if (SPI_finish() != SPI_OK_FINISH)
+		elog(ERROR, "SPI_finish failed");
+}
+
+/*
+ * apply_old_delta
+ *
+ * Execute a query for applying a delta table given by deltname_old
+ * which contains tuples to be deleted from to a materialized view given by
+ * matviewname.  This is used when counting is not required.
+ */
+static void
+apply_old_delta(const char *matviewname, const char *deltaname_old,
+				List *keys)
+{
+	StringInfoData	querybuf;
+	StringInfoData	keysbuf;
+	char   *match_cond;
+	ListCell *lc;
+
+	/* build WHERE condition for searching tuples to be deleted */
+	match_cond = get_matching_condition_string(keys);
+
+	/* build string of keys list */
+	initStringInfo(&keysbuf);
+	foreach (lc, keys)
+	{
+		Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc);
+		char   *resname = NameStr(attr->attname);
+		appendStringInfo(&keysbuf, "%s", quote_qualified_identifier("mv", resname));
+		if (lnext(keys, lc))
+			appendStringInfo(&keysbuf, ", ");
+	}
+
+	/* Search for matching tuples from the view and update or delete if found. */
+	initStringInfo(&querybuf);
+	appendStringInfo(&querybuf,
+	"DELETE FROM %s WHERE ctid IN ("
+		"SELECT tid FROM (SELECT pg_catalog.row_number() over (partition by %s) AS \"__ivm_row_number__\","
+								  "mv.ctid AS tid,"
+								  "diff.\"__ivm_count__\""
+						 "FROM %s AS mv, %s AS diff "
+						 "WHERE %s) v "
+					"WHERE v.\"__ivm_row_number__\" OPERATOR(pg_catalog.<=) v.\"__ivm_count__\")",
+					matviewname,
+					keysbuf.data,
+					matviewname, deltaname_old,
+					match_cond);
+
+	if (SPI_exec(querybuf.data, 0) != SPI_OK_DELETE)
+		elog(ERROR, "SPI_exec failed: %s", querybuf.data);
+}
+
+/*
+ * apply_new_delta
+ *
+ * Execute a query for applying a delta table given by deltname_new
+ * which contains tuples to be inserted into a materialized view given by
+ * matviewname.  This is used when counting is not required.
+ */
+static void
+apply_new_delta(const char *matviewname, const char *deltaname_new,
+				StringInfo target_list)
+{
+	StringInfoData	querybuf;
+
+	/* Search for matching tuples from the view and update or delete if found. */
+	initStringInfo(&querybuf);
+	appendStringInfo(&querybuf,
+					"INSERT INTO %s (%s) SELECT %s FROM ("
+						"SELECT diff.*, pg_catalog.generate_series(1, diff.\"__ivm_count__\")"
+							" AS __ivm_generate_series__ "
+						"FROM %s AS diff) AS v",
+					matviewname, target_list->data, target_list->data,
+					deltaname_new);
+
+	if (SPI_exec(querybuf.data, 0) != SPI_OK_INSERT)
+		elog(ERROR, "SPI_exec failed: %s", querybuf.data);
+}
+
+/*
+ * get_matching_condition_string
+ *
+ * Build a predicate string for looking for a tuple with given keys.
+ */
+static char *
+get_matching_condition_string(List *keys)
+{
+	StringInfoData match_cond;
+	ListCell	*lc;
+
+	/* If there is no key columns, the condition is always true. */
+	if (keys == NIL)
+		return "true";
+
+	initStringInfo(&match_cond);
+	foreach (lc, keys)
+	{
+		Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc);
+		char   *resname = NameStr(attr->attname);
+		char   *mv_resname = quote_qualified_identifier("mv", resname);
+		char   *diff_resname = quote_qualified_identifier("diff", resname);
+		Oid		typid = attr->atttypid;
+
+		/* Considering NULL values, we can not use simple = operator. */
+		appendStringInfo(&match_cond, "(");
+		generate_equal(&match_cond, typid, mv_resname, diff_resname);
+		appendStringInfo(&match_cond, " OR (%s IS NULL AND %s IS NULL))",
+						 mv_resname, diff_resname);
+
+		if (lnext(keys, lc))
+			appendStringInfo(&match_cond, " AND ");
+	}
+
+	return match_cond.data;
+}
+
+/*
+ * generate_equals
+ *
+ * Generate an equality clause using given operands' default equality
+ * operator.
+ */
+static void
+generate_equal(StringInfo querybuf, Oid opttype,
+			   const char *leftop, const char *rightop)
+{
+	TypeCacheEntry *typentry;
+
+	typentry = lookup_type_cache(opttype, TYPECACHE_EQ_OPR);
+	if (!OidIsValid(typentry->eq_opr))
+		ereport(ERROR,
+				(errcode(ERRCODE_UNDEFINED_FUNCTION),
+				 errmsg("could not identify an equality operator for type %s",
+						format_type_be_qualified(opttype))));
+
+	generate_operator_clause(querybuf,
+							 leftop, opttype,
+							 typentry->eq_opr,
+							 rightop, opttype);
+}
+
+/*
+ * mv_InitHashTables
+ */
+static void
+mv_InitHashTables(void)
+{
+	HASHCTL		ctl;
+
+	memset(&ctl, 0, sizeof(ctl));
+	ctl.keysize = sizeof(Oid);
+	ctl.entrysize = sizeof(MV_TriggerHashEntry);
+	mv_trigger_info = hash_create("MV trigger info",
+								 MV_INIT_QUERYHASHSIZE,
+								 &ctl, HASH_ELEM | HASH_BLOBS);
+}
+
+/*
+ * AtAbort_IVM
+ *
+ * Clean up hash entries for all materialized views. This is called at
+ * transaction abort.
+ */
+void
+AtAbort_IVM()
+{
+	HASH_SEQ_STATUS seq;
+	MV_TriggerHashEntry *entry;
+
+	if (mv_trigger_info)
+	{
+		hash_seq_init(&seq, mv_trigger_info);
+		while ((entry = hash_seq_search(&seq)) != NULL)
+			clean_up_IVM_hash_entry(entry, true);
+	}
+	in_delta_calculation = false;
+}
+
+/*
+ * clean_up_IVM_hash_entry
+ *
+ * Clean up tuple stores and hash entries for a materialized view after its
+ * maintenance finished.
+ */
+static void
+clean_up_IVM_hash_entry(MV_TriggerHashEntry *entry, bool is_abort)
+{
+	bool found;
+	ListCell *lc;
+
+	foreach(lc, entry->tables)
+	{
+		MV_TriggerTable *table = (MV_TriggerTable *) lfirst(lc);
+
+		list_free(table->old_tuplestores);
+		list_free(table->new_tuplestores);
+		if (!is_abort)
+		{
+			ExecDropSingleTupleTableSlot(table->slot);
+			table_close(table->rel, NoLock);
+		}
+	}
+	list_free(entry->tables);
+
+	if (!is_abort)
+		UnregisterSnapshot(entry->snapshot);
+
+	hash_search(mv_trigger_info, (void *) &entry->matview_id, HASH_REMOVE, &found);
+}
+
+/*
+ * isIvmName
+ *
+ * Check if this is a IVM hidden column from the name.
+ */
+bool
+isIvmName(const char *s)
+{
+	if (s)
+		return (strncmp(s, "__ivm_", 6) == 0);
+	return false;
+}
diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat
index 9c120fc2b7..e111f11bf5 100644
--- a/src/include/catalog/pg_proc.dat
+++ b/src/include/catalog/pg_proc.dat
@@ -12174,4 +12174,14 @@
   proargtypes => 'int2',
   prosrc => 'gist_stratnum_identity' },
 
+# IVM
+{ oid => '786', descr => 'ivm trigger (before)',
+  proname => 'IVM_immediate_before', provolatile => 'v', prorettype => 'trigger',
+  proargtypes => '', prosrc => 'IVM_immediate_before' },
+{ oid => '787', descr => 'ivm trigger (after)',
+  proname => 'IVM_immediate_maintenance', provolatile => 'v', prorettype => 'trigger',
+  proargtypes => '', prosrc => 'IVM_immediate_maintenance' },
+{ oid => '788', descr => 'ivm filetring ',
+  proname => 'ivm_visible_in_prestate', provolatile => 's', prorettype => 'bool',
+  proargtypes => 'oid tid oid', prosrc => 'ivm_visible_in_prestate' },
 ]
diff --git a/src/include/commands/createas.h b/src/include/commands/createas.h
index 94678e3834..396ad1bb4c 100644
--- a/src/include/commands/createas.h
+++ b/src/include/commands/createas.h
@@ -16,6 +16,7 @@
 
 #include "catalog/objectaddress.h"
 #include "nodes/params.h"
+#include "nodes/pathnodes.h"
 #include "parser/parse_node.h"
 #include "tcop/dest.h"
 #include "utils/queryenvironment.h"
@@ -25,6 +26,9 @@ extern ObjectAddress ExecCreateTableAs(ParseState *pstate, CreateTableAsStmt *st
 									   ParamListInfo params, QueryEnvironment *queryEnv,
 									   QueryCompletion *qc);
 
+extern void CreateIvmTriggersOnBaseTables(Query *qry, Oid matviewOid);
+extern void CreateIndexOnIMMV(Query *query, Relation matviewRel);
+
 extern int	GetIntoRelEFlags(IntoClause *intoClause);
 
 extern DestReceiver *CreateIntoRelDestReceiver(IntoClause *intoClause);
diff --git a/src/include/commands/matview.h b/src/include/commands/matview.h
index 817b2ba0b6..3257e1adff 100644
--- a/src/include/commands/matview.h
+++ b/src/include/commands/matview.h
@@ -15,6 +15,7 @@
 #define MATVIEW_H
 
 #include "catalog/objectaddress.h"
+#include "fmgr.h"
 #include "nodes/params.h"
 #include "nodes/parsenodes.h"
 #include "tcop/dest.h"
@@ -23,6 +24,8 @@
 
 extern void SetMatViewPopulatedState(Relation relation, bool newstate);
 
+extern void SetMatViewIVMState(Relation relation, bool newstate);
+
 extern ObjectAddress ExecRefreshMatView(RefreshMatViewStmt *stmt, const char *queryString,
 										ParamListInfo params, QueryCompletion *qc);
 
@@ -30,4 +33,10 @@ extern DestReceiver *CreateTransientRelDestReceiver(Oid transientoid);
 
 extern bool MatViewIncrementalMaintenanceIsEnabled(void);
 
+extern Datum IVM_immediate_before(PG_FUNCTION_ARGS);
+extern Datum IVM_immediate_maintenance(PG_FUNCTION_ARGS);
+extern Datum IVM_visible_in_prestate(PG_FUNCTION_ARGS);
+extern void AtAbort_IVM(void);
+extern bool isIvmName(const char *s);
+
 #endif							/* MATVIEW_H */
-- 
2.25.1


--Multipart=_Mon__4_Mar_2024_11_58_46_+0900_UaponF/qQhQrVCFt
Content-Type: text/x-diff;
 name="v30-0007-Add-DISTINCT-support-for-IVM.patch"
Content-Disposition: attachment;
 filename="v30-0007-Add-DISTINCT-support-for-IVM.patch"
Content-Transfer-Encoding: 7bit



^ permalink  raw  reply  [nested|flat] 101+ messages in thread

* [PATCH v28 06/11] Add Incremental View Maintenance support
@ 2023-05-31 09:59  Yugo Nagata <[email protected]>
  0 siblings, 0 replies; 101+ messages in thread

From: Yugo Nagata @ 2023-05-31 09:59 UTC (permalink / raw)

In this implementation, AFTER triggers are used to collect
tuplestores containing transition table contents. When multiple tables
are changed, multiple AFTER triggers are invoked, then the final AFTER
trigger performs actual update of the matview. In addition, BEFORE
triggers are also used to handle global information for view
maintenance.

To calculate view deltas, we need both pre-state and post-state of base
tables. Post-update states are available in AFTER trigger, and pre-update
states can be calculated by removing inserted tuples and appending deleted
tuples. Insterted tuples are filtered using the snapshot taken before
table modiication, and deleted tuples are contained in the old transition
table.

Incrementally Maintainable Materialized Views (IMMV) can contain
duplicated tuples.

This patch also allows self-join, simultaneous updates of more than
one base table, and multiple updates of the same base table.
---
 src/backend/access/transam/xact.c |    5 +
 src/backend/commands/createas.c   |  680 +++++++++++++
 src/backend/commands/matview.c    | 1466 ++++++++++++++++++++++++++++-
 src/include/catalog/pg_proc.dat   |   10 +
 src/include/commands/createas.h   |    4 +
 src/include/commands/matview.h    |    9 +
 6 files changed, 2139 insertions(+), 35 deletions(-)

diff --git a/src/backend/access/transam/xact.c b/src/backend/access/transam/xact.c
index 8daaa535ed..cd280bdffd 100644
--- a/src/backend/access/transam/xact.c
+++ b/src/backend/access/transam/xact.c
@@ -36,6 +36,7 @@
 #include "catalog/pg_enum.h"
 #include "catalog/storage.h"
 #include "commands/async.h"
+#include "commands/matview.h"
 #include "commands/tablecmds.h"
 #include "commands/trigger.h"
 #include "common/pg_prng.h"
@@ -2803,6 +2804,7 @@ AbortTransaction(void)
 	AtAbort_Notify();
 	AtEOXact_RelationMap(false, is_parallel_worker);
 	AtAbort_Twophase();
+	AtAbort_IVM();
 
 	/*
 	 * Advertise the fact that we aborted in pg_xact (assuming that we got as
@@ -5080,6 +5082,9 @@ AbortSubTransaction(void)
 	pgstat_progress_end_command();
 	UnlockBuffers();
 
+	/* Clean up hash entries for incremental view maintenance */
+	AtAbort_IVM();
+
 	/* Reset WAL record construction state */
 	XLogResetInsertion();
 
diff --git a/src/backend/commands/createas.c b/src/backend/commands/createas.c
index e91920ca14..415f110516 100644
--- a/src/backend/commands/createas.c
+++ b/src/backend/commands/createas.c
@@ -32,15 +32,26 @@
 #include "access/xact.h"
 #include "access/xlog.h"
 #include "catalog/namespace.h"
+#include "catalog/index.h"
+#include "catalog/pg_constraint.h"
+#include "catalog/pg_inherits.h"
+#include "catalog/pg_trigger.h"
 #include "catalog/toasting.h"
 #include "commands/createas.h"
+#include "commands/defrem.h"
 #include "commands/matview.h"
 #include "commands/prepare.h"
 #include "commands/tablecmds.h"
+#include "commands/tablespace.h"
+#include "commands/trigger.h"
 #include "commands/view.h"
 #include "miscadmin.h"
+#include "optimizer/optimizer.h"
+#include "optimizer/prep.h"
 #include "nodes/makefuncs.h"
 #include "nodes/nodeFuncs.h"
+#include "parser/parser.h"
+#include "parser/parsetree.h"
 #include "parser/parse_clause.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/smgr.h"
@@ -73,6 +84,12 @@ static bool intorel_receive(TupleTableSlot *slot, DestReceiver *self);
 static void intorel_shutdown(DestReceiver *self);
 static void intorel_destroy(DestReceiver *self);
 
+static void CreateIvmTriggersOnBaseTablesRecurse(Query *qry, Node *node, Oid matviewOid,
+									 Relids *relids, bool ex_lock);
+static void CreateIvmTrigger(Oid relOid, Oid viewOid, int16 type, int16 timing, bool ex_lock);
+static void check_ivm_restriction(Node *node);
+static bool check_ivm_restriction_walker(Node *node, void *context);
+static Bitmapset *get_primary_key_attnos_from_query(Query *query, List **constraintList);
 
 /*
  * create_ctas_internal
@@ -282,6 +299,18 @@ ExecCreateTableAs(ParseState *pstate, CreateTableAsStmt *stmt,
 		save_nestlevel = NewGUCNestLevel();
 	}
 
+	if (is_matview && into->ivm)
+	{
+		/* check if the query is supported in IMMV definition */
+		if (contain_mutable_functions((Node *) query))
+			ereport(ERROR,
+					(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+					 errmsg("mutable function is not supported on incrementally maintainable materialized view"),
+					 errhint("functions must be marked IMMUTABLE")));
+
+		check_ivm_restriction((Node *) query);
+	}
+
 	if (into->skipData)
 	{
 		/*
@@ -358,6 +387,27 @@ ExecCreateTableAs(ParseState *pstate, CreateTableAsStmt *stmt,
 
 		/* Restore userid and security context */
 		SetUserIdAndSecContext(save_userid, save_sec_context);
+
+		if (into->ivm)
+		{
+			Oid matviewOid = address.objectId;
+			Relation matviewRel = table_open(matviewOid, NoLock);
+
+			/*
+			 * Mark relisivm field, if it's a matview and into->ivm is true.
+			 */
+			SetMatViewIVMState(matviewRel, true);
+
+			if (!into->skipData)
+			{
+				/* Create an index on incremental maintainable materialized view, if possible */
+				CreateIndexOnIMMV((Query *) into->viewQuery, matviewRel);
+
+				/* Create triggers on incremental maintainable materialized view */
+				CreateIvmTriggersOnBaseTables((Query *) into->viewQuery, matviewOid);
+			}
+			table_close(matviewRel, NoLock);
+		}
 	}
 
 	return address;
@@ -635,3 +685,633 @@ intorel_destroy(DestReceiver *self)
 {
 	pfree(self);
 }
+
+/*
+ * CreateIvmTriggersOnBaseTables -- create IVM triggers on all base tables
+ */
+void
+CreateIvmTriggersOnBaseTables(Query *qry, Oid matviewOid)
+{
+	Relids	relids = NULL;
+	bool	ex_lock = false;
+	RangeTblEntry *rte;
+
+	/* Immediately return if we don't have any base tables. */
+	if (list_length(qry->rtable) < 1)
+		return;
+
+	/*
+	 * If the view has more than one base tables, we need an exclusive lock
+	 * on the view so that the view would be maintained serially to avoid
+	 * the inconsistency that occurs when two base tables are modified in
+	 * concurrent transactions. However, if the view has only one table,
+	 * we can use a weaker lock.
+	 *
+	 * The type of lock should be determined here, because if we check the
+	 * view definition at maintenance time, we need to acquire a weaker lock,
+	 * and upgrading the lock level after this increases probability of
+	 * deadlock.
+	 */
+
+	rte = list_nth(qry->rtable, 0);
+	if (list_length(qry->rtable) > 1 || rte->rtekind != RTE_RELATION)
+		ex_lock = true;
+
+	CreateIvmTriggersOnBaseTablesRecurse(qry, (Node *)qry, matviewOid, &relids, ex_lock);
+
+	bms_free(relids);
+}
+
+static void
+CreateIvmTriggersOnBaseTablesRecurse(Query *qry, Node *node, Oid matviewOid,
+									 Relids *relids, bool ex_lock)
+{
+	if (node == NULL)
+		return;
+
+	/* This can recurse, so check for excessive recursion */
+	check_stack_depth();
+
+	switch (nodeTag(node))
+	{
+		case T_Query:
+			{
+				Query *query = (Query *) node;
+
+				CreateIvmTriggersOnBaseTablesRecurse(qry, (Node *)query->jointree, matviewOid, relids, ex_lock);
+			}
+			break;
+
+		case T_RangeTblRef:
+			{
+				int			rti = ((RangeTblRef *) node)->rtindex;
+				RangeTblEntry *rte = rt_fetch(rti, qry->rtable);
+
+				if (rte->rtekind == RTE_RELATION && !bms_is_member(rte->relid, *relids))
+				{
+					CreateIvmTrigger(rte->relid, matviewOid, TRIGGER_TYPE_INSERT, TRIGGER_TYPE_BEFORE, ex_lock);
+					CreateIvmTrigger(rte->relid, matviewOid, TRIGGER_TYPE_DELETE, TRIGGER_TYPE_BEFORE, ex_lock);
+					CreateIvmTrigger(rte->relid, matviewOid, TRIGGER_TYPE_UPDATE, TRIGGER_TYPE_BEFORE, ex_lock);
+					CreateIvmTrigger(rte->relid, matviewOid, TRIGGER_TYPE_TRUNCATE, TRIGGER_TYPE_BEFORE, true);
+					CreateIvmTrigger(rte->relid, matviewOid, TRIGGER_TYPE_INSERT, TRIGGER_TYPE_AFTER, ex_lock);
+					CreateIvmTrigger(rte->relid, matviewOid, TRIGGER_TYPE_DELETE, TRIGGER_TYPE_AFTER, ex_lock);
+					CreateIvmTrigger(rte->relid, matviewOid, TRIGGER_TYPE_UPDATE, TRIGGER_TYPE_AFTER, ex_lock);
+					CreateIvmTrigger(rte->relid, matviewOid, TRIGGER_TYPE_TRUNCATE, TRIGGER_TYPE_AFTER, true);
+
+					*relids = bms_add_member(*relids, rte->relid);
+				}
+			}
+			break;
+
+		case T_FromExpr:
+			{
+				FromExpr   *f = (FromExpr *) node;
+				ListCell   *l;
+
+				foreach(l, f->fromlist)
+					CreateIvmTriggersOnBaseTablesRecurse(qry, lfirst(l), matviewOid, relids, ex_lock);
+			}
+			break;
+
+		case T_JoinExpr:
+			{
+				JoinExpr   *j = (JoinExpr *) node;
+
+				CreateIvmTriggersOnBaseTablesRecurse(qry, j->larg, matviewOid, relids, ex_lock);
+				CreateIvmTriggersOnBaseTablesRecurse(qry, j->rarg, matviewOid, relids, ex_lock);
+			}
+			break;
+
+		default:
+			elog(ERROR, "unrecognized node type: %d", (int) nodeTag(node));
+	}
+}
+
+/*
+ * CreateIvmTrigger -- create IVM trigger on a base table
+ */
+static void
+CreateIvmTrigger(Oid relOid, Oid viewOid, int16 type, int16 timing, bool ex_lock)
+{
+	ObjectAddress	refaddr;
+	ObjectAddress	address;
+	CreateTrigStmt *ivm_trigger;
+	List *transitionRels = NIL;
+
+	Assert(timing == TRIGGER_TYPE_BEFORE || timing == TRIGGER_TYPE_AFTER);
+
+	refaddr.classId = RelationRelationId;
+	refaddr.objectId = viewOid;
+	refaddr.objectSubId = 0;
+
+	ivm_trigger = makeNode(CreateTrigStmt);
+	ivm_trigger->relation = NULL;
+	ivm_trigger->row = false;
+
+	ivm_trigger->timing = timing;
+	ivm_trigger->events = type;
+
+	switch (type)
+	{
+		case TRIGGER_TYPE_INSERT:
+			ivm_trigger->trigname = (timing == TRIGGER_TYPE_BEFORE ? "IVM_trigger_ins_before" : "IVM_trigger_ins_after");
+			break;
+		case TRIGGER_TYPE_DELETE:
+			ivm_trigger->trigname = (timing == TRIGGER_TYPE_BEFORE ? "IVM_trigger_del_before" : "IVM_trigger_del_after");
+			break;
+		case TRIGGER_TYPE_UPDATE:
+			ivm_trigger->trigname = (timing == TRIGGER_TYPE_BEFORE ? "IVM_trigger_upd_before" : "IVM_trigger_upd_after");
+			break;
+		case TRIGGER_TYPE_TRUNCATE:
+			ivm_trigger->trigname = (timing == TRIGGER_TYPE_BEFORE ? "IVM_trigger_truncate_before" : "IVM_trigger_truncate_after");
+			break;
+		default:
+			elog(ERROR, "unsupported trigger type");
+	}
+
+	if (timing == TRIGGER_TYPE_AFTER)
+	{
+		if (type == TRIGGER_TYPE_INSERT || type == TRIGGER_TYPE_UPDATE)
+		{
+			TriggerTransition *n = makeNode(TriggerTransition);
+			n->name = "__ivm_newtable";
+			n->isNew = true;
+			n->isTable = true;
+
+			transitionRels = lappend(transitionRels, n);
+		}
+		if (type == TRIGGER_TYPE_DELETE || type == TRIGGER_TYPE_UPDATE)
+		{
+			TriggerTransition *n = makeNode(TriggerTransition);
+			n->name = "__ivm_oldtable";
+			n->isNew = false;
+			n->isTable = true;
+
+			transitionRels = lappend(transitionRels, n);
+		}
+	}
+
+	/*
+	 * XXX: When using DELETE or UPDATE, we must use exclusive lock for now
+	 * because apply_old_delta(_with_count) uses ctid to identify the tuple
+	 * to be deleted/deleted, but doesn't work in concurrent situations.
+	 *
+	 * If the view doesn't have aggregate, distinct, or tuple duplicate,
+	 * then it would work even in concurrent situations. However, we don't have
+	 * any way to guarantee the view has a unique key before opening the IMMV
+	 * at the maintenance time because users may drop the unique index.
+	 */
+
+	if (type == TRIGGER_TYPE_DELETE || type == TRIGGER_TYPE_UPDATE)
+		ex_lock = true;
+
+	ivm_trigger->funcname =
+		(timing == TRIGGER_TYPE_BEFORE ? SystemFuncName("IVM_immediate_before") : SystemFuncName("IVM_immediate_maintenance"));
+
+	ivm_trigger->columns = NIL;
+	ivm_trigger->transitionRels = transitionRels;
+	ivm_trigger->whenClause = NULL;
+	ivm_trigger->isconstraint = false;
+	ivm_trigger->deferrable = false;
+	ivm_trigger->initdeferred = false;
+	ivm_trigger->constrrel = NULL;
+	ivm_trigger->args = list_make2(
+		makeString(DatumGetPointer(DirectFunctionCall1(oidout, ObjectIdGetDatum(viewOid)))),
+		makeString(DatumGetPointer(DirectFunctionCall1(boolout, BoolGetDatum(ex_lock))))
+		);
+
+	address = CreateTrigger(ivm_trigger, NULL, relOid, InvalidOid, InvalidOid,
+						 InvalidOid, InvalidOid, InvalidOid, NULL, true, false);
+
+	recordDependencyOn(&address, &refaddr, DEPENDENCY_AUTO);
+
+	/* Make changes-so-far visible */
+	CommandCounterIncrement();
+}
+
+/*
+ * check_ivm_restriction --- look for specify nodes in the query tree
+ */
+static void
+check_ivm_restriction(Node *node)
+{
+	check_ivm_restriction_walker(node, NULL);
+}
+
+static bool
+check_ivm_restriction_walker(Node *node, void *context)
+{
+	if (node == NULL)
+		return false;
+
+	/*
+	 * We currently don't support Sub-Query.
+	 */
+	if (IsA(node, SubPlan) || IsA(node, SubLink))
+		ereport(ERROR,
+				(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+				 errmsg("subquery is not supported on incrementally maintainable materialized view")));
+
+	/* This can recurse, so check for excessive recursion */
+	check_stack_depth();
+
+	switch (nodeTag(node))
+	{
+		case T_Query:
+			{
+				Query *qry = (Query *)node;
+				ListCell   *lc;
+				List       *vars;
+
+				/* if contained CTE, return error */
+				if (qry->cteList != NIL)
+					ereport(ERROR,
+							(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+							 errmsg("CTE is not supported on incrementally maintainable materialized view")));
+				if (qry->havingQual != NULL)
+					ereport(ERROR,
+							(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+							 errmsg(" HAVING clause is not supported on incrementally maintainable materialized view")));
+				if (qry->sortClause != NIL)	/* There is a possibility that we don't need to return an error */
+					ereport(ERROR,
+							(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+							 errmsg("ORDER BY clause is not supported on incrementally maintainable materialized view")));
+				if (qry->limitOffset != NULL || qry->limitCount != NULL)
+					ereport(ERROR,
+							(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+							 errmsg("LIMIT/OFFSET clause is not supported on incrementally maintainable materialized view")));
+				if (qry->distinctClause)
+					ereport(ERROR,
+							(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+							 errmsg("DISTINCT is not supported on incrementally maintainable materialized view")));
+				if (qry->hasDistinctOn)
+					ereport(ERROR,
+							(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+							 errmsg("DISTINCT ON is not supported on incrementally maintainable materialized view")));
+				if (qry->hasWindowFuncs)
+					ereport(ERROR,
+							(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+							 errmsg("window functions are not supported on incrementally maintainable materialized view")));
+				if (qry->groupingSets != NIL)
+					ereport(ERROR,
+							(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+							 errmsg("GROUPING SETS, ROLLUP, or CUBE clauses is not supported on incrementally maintainable materialized view")));
+				if (qry->setOperations != NULL)
+					ereport(ERROR,
+							(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+							 errmsg("UNION/INTERSECT/EXCEPT statements are not supported on incrementally maintainable materialized view")));
+				if (list_length(qry->targetList) == 0)
+					ereport(ERROR,
+							(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+							 errmsg("empty target list is not supported on incrementally maintainable materialized view")));
+				if (qry->rowMarks != NIL)
+					ereport(ERROR,
+							(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+							 errmsg("FOR UPDATE/SHARE clause is not supported on incrementally maintainable materialized view")));
+
+				/* system column restrictions */
+				vars = pull_vars_of_level((Node *) qry, 0);
+				foreach(lc, vars)
+				{
+					if (IsA(lfirst(lc), Var))
+					{
+						Var *var = (Var *) lfirst(lc);
+						/* if system column, return error */
+						if (var->varattno < 0)
+							ereport(ERROR,
+									(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+									 errmsg("system column is not supported on incrementally maintainable materialized view")));
+					}
+				}
+
+				/* restrictions for rtable */
+				foreach(lc, qry->rtable)
+				{
+					RangeTblEntry *rte = (RangeTblEntry *) lfirst(lc);
+
+					if (rte->subquery)
+						ereport(ERROR,
+								(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+								 errmsg("subquery is not supported on incrementally maintainable materialized view")));
+
+					if (rte->tablesample != NULL)
+						ereport(ERROR,
+								(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+								 errmsg("TABLESAMPLE clause is not supported on incrementally maintainable materialized view")));
+
+					if (rte->relkind == RELKIND_PARTITIONED_TABLE)
+						ereport(ERROR,
+								(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+								 errmsg("partitioned table is not supported on incrementally maintainable materialized view")));
+
+					if (rte->relkind == RELKIND_RELATION && has_superclass(rte->relid))
+						ereport(ERROR,
+								(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+								 errmsg("partitions is not supported on incrementally maintainable materialized view")));
+
+					if (rte->relkind == RELKIND_RELATION && find_inheritance_children(rte->relid, NoLock) != NIL)
+						ereport(ERROR,
+								(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+								 errmsg("inheritance parent is not supported on incrementally maintainable materialized view")));
+
+					if (rte->relkind == RELKIND_FOREIGN_TABLE)
+						ereport(ERROR,
+								(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+								 errmsg("foreign table is not supported on incrementally maintainable materialized view")));
+
+					if (rte->relkind == RELKIND_VIEW ||
+						rte->relkind == RELKIND_MATVIEW)
+						ereport(ERROR,
+								(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+								 errmsg("VIEW or MATERIALIZED VIEW is not supported on incrementally maintainable materialized view")));
+
+					if (rte->rtekind == RTE_VALUES)
+						ereport(ERROR,
+								(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+								 errmsg("VALUES is not supported on incrementally maintainable materialized view")));
+
+				}
+
+				query_tree_walker(qry, check_ivm_restriction_walker, NULL, QTW_IGNORE_RANGE_TABLE);
+
+				break;
+			}
+		case T_TargetEntry:
+			{
+				TargetEntry *tle = (TargetEntry *)node;
+				if (isIvmName(tle->resname))
+						ereport(ERROR,
+								(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+								 errmsg("column name %s is not supported on incrementally maintainable materialized view", tle->resname)));
+
+				expression_tree_walker(node, check_ivm_restriction_walker, NULL);
+				break;
+			}
+		case T_JoinExpr:
+			{
+				JoinExpr *joinexpr = (JoinExpr *)node;
+
+				if (joinexpr->jointype > JOIN_INNER)
+						ereport(ERROR,
+								(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+								 errmsg("OUTER JOIN is not supported on incrementally maintainable materialized view")));
+
+				expression_tree_walker(node, check_ivm_restriction_walker, NULL);
+			}
+			break;
+		case T_Aggref:
+			ereport(ERROR,
+					(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+					 errmsg("aggregate function is not supported on incrementally maintainable materialized view")));
+			break;
+		default:
+			expression_tree_walker(node, check_ivm_restriction_walker, (void *) context);
+			break;
+	}
+	return false;
+}
+
+/*
+ * CreateIndexOnIMMV
+ *
+ * Create a unique index on incremental maintainable materialized view.
+ * If the view definition query has a GROUP BY clause, the index is created
+ * on the columns of GROUP BY expressions. Otherwise, if the view contains
+ * all primary key attritubes of its base tables in the target list, the index
+ * is created on these attritubes. In other cases, no index is created.
+ */
+void
+CreateIndexOnIMMV(Query *query, Relation matviewRel)
+{
+	ListCell *lc;
+	IndexStmt  *index;
+	ObjectAddress address;
+	List *constraintList = NIL;
+	char		idxname[NAMEDATALEN];
+	List	   *indexoidlist = RelationGetIndexList(matviewRel);
+	ListCell   *indexoidscan;
+	Bitmapset *key_attnos;
+
+	snprintf(idxname, sizeof(idxname), "%s_index", RelationGetRelationName(matviewRel));
+
+	index = makeNode(IndexStmt);
+
+	index->unique = true;
+	index->primary = false;
+	index->isconstraint = false;
+	index->deferrable = false;
+	index->initdeferred = false;
+	index->idxname = idxname;
+	index->relation =
+		makeRangeVar(get_namespace_name(RelationGetNamespace(matviewRel)),
+					 pstrdup(RelationGetRelationName(matviewRel)),
+					 -1);
+	index->accessMethod = DEFAULT_INDEX_TYPE;
+	index->options = NIL;
+	index->tableSpace = get_tablespace_name(matviewRel->rd_rel->reltablespace);
+	index->whereClause = NULL;
+	index->indexParams = NIL;
+	index->indexIncludingParams = NIL;
+	index->excludeOpNames = NIL;
+	index->idxcomment = NULL;
+	index->indexOid = InvalidOid;
+	index->oldNumber = InvalidRelFileNumber;
+	index->oldCreateSubid = InvalidSubTransactionId;
+	index->oldFirstRelfilelocatorSubid = InvalidSubTransactionId;
+	index->transformed = true;
+	index->concurrent = false;
+	index->if_not_exists = false;
+
+	/* create index on the base tables' primary key columns */
+	key_attnos = get_primary_key_attnos_from_query(query, &constraintList);
+	if (key_attnos)
+	{
+		foreach(lc, query->targetList)
+		{
+			TargetEntry *tle = (TargetEntry *) lfirst(lc);
+			Form_pg_attribute attr = TupleDescAttr(matviewRel->rd_att, tle->resno - 1);
+
+			if (bms_is_member(tle->resno - FirstLowInvalidHeapAttributeNumber, key_attnos))
+			{
+				IndexElem  *iparam;
+
+				iparam = makeNode(IndexElem);
+				iparam->name = pstrdup(NameStr(attr->attname));
+				iparam->expr = NULL;
+				iparam->indexcolname = NULL;
+				iparam->collation = NIL;
+				iparam->opclass = NIL;
+				iparam->opclassopts = NIL;
+				iparam->ordering = SORTBY_DEFAULT;
+				iparam->nulls_ordering = SORTBY_NULLS_DEFAULT;
+				index->indexParams = lappend(index->indexParams, iparam);
+			}
+		}
+	}
+	else
+	{
+		/* create no index, just notice that an appropriate index is necessary for efficient IVM */
+		ereport(NOTICE,
+				(errmsg("could not create an index on materialized view \"%s\" automatically",
+						RelationGetRelationName(matviewRel)),
+				 errdetail("This target list does not have all the primary key columns. "),
+				 errhint("Create an index on the materialized view for efficient incremental maintenance.")));
+		return;
+	}
+
+	/* If we have a compatible index, we don't need to create another. */
+	foreach(indexoidscan, indexoidlist)
+	{
+		Oid			indexoid = lfirst_oid(indexoidscan);
+		Relation	indexRel;
+		bool		hasCompatibleIndex = false;
+
+		indexRel = index_open(indexoid, AccessShareLock);
+
+		if (CheckIndexCompatible(indexRel->rd_id,
+								index->accessMethod,
+								index->indexParams,
+								index->excludeOpNames))
+			hasCompatibleIndex = true;
+
+		index_close(indexRel, AccessShareLock);
+
+		if (hasCompatibleIndex)
+			return;
+	}
+
+	address = DefineIndex(RelationGetRelid(matviewRel),
+						  index,
+						  InvalidOid,
+						  InvalidOid,
+						  InvalidOid,
+						  -1,
+						  false, true, false, false, true);
+
+	ereport(NOTICE,
+			(errmsg("created index \"%s\" on materialized view \"%s\"",
+					idxname, RelationGetRelationName(matviewRel))));
+
+	/*
+	 * Make dependencies so that the index is dropped if any base tables's
+	 * primary key is dropped.
+	 */
+	foreach(lc, constraintList)
+	{
+		Oid constraintOid = lfirst_oid(lc);
+		ObjectAddress	refaddr;
+
+		refaddr.classId = ConstraintRelationId;
+		refaddr.objectId = constraintOid;
+		refaddr.objectSubId = 0;
+
+		recordDependencyOn(&address, &refaddr, DEPENDENCY_NORMAL);
+	}
+}
+
+
+/*
+ * get_primary_key_attnos_from_query
+ *
+ * Identify the columns in base tables' primary keys in the target list.
+ *
+ * Returns a Bitmapset of the column attnos of the primary key's columns of
+ * tables that used in the query.  The attnos are offset by
+ * FirstLowInvalidHeapAttributeNumber as same as get_primary_key_attnos.
+ *
+ * If any table has no primary key or any primary key's columns is not in
+ * the target list, return NULL.  We also return NULL if any pkey constraint
+ * is deferrable.
+ *
+ * constraintList is set to a list of the OIDs of the pkey constraints.
+ */
+static Bitmapset *
+get_primary_key_attnos_from_query(Query *query, List **constraintList)
+{
+	List *key_attnos_list = NIL;
+	ListCell *lc;
+	int i;
+	Bitmapset *keys = NULL;
+	Relids	rels_in_from;
+
+	/*
+	 * Collect primary key attributes from all tables used in query. The key attributes
+	 * sets for each table are stored in key_attnos_list in order by RTE index.
+	 */
+	foreach(lc, query->rtable)
+	{
+		RangeTblEntry *r = (RangeTblEntry*) lfirst(lc);
+		Bitmapset *key_attnos;
+		bool	has_pkey = true;
+
+		/* for tables, call get_primary_key_attnos */
+		if (r->rtekind == RTE_RELATION)
+		{
+			Oid constraintOid;
+			key_attnos = get_primary_key_attnos(r->relid, false, &constraintOid);
+			*constraintList = lappend_oid(*constraintList, constraintOid);
+			has_pkey = (key_attnos != NULL);
+		}
+		/* for other RTEs, store NULL into key_attnos_list */
+		else
+			key_attnos = NULL;
+
+		/*
+		 * If any table or subquery has no primary key or its pkey constraint is deferrable,
+		 * we cannot get key attributes for this query, so return NULL.
+		 */
+		if (!has_pkey)
+			return NULL;
+
+		key_attnos_list = lappend(key_attnos_list, key_attnos);
+	}
+
+	/* Collect key attributes appearing in the target list */
+	i = 1;
+	foreach(lc, query->targetList)
+	{
+		TargetEntry *tle = (TargetEntry *) flatten_join_alias_vars(NULL, query, lfirst(lc));
+
+		if (IsA(tle->expr, Var))
+		{
+			Var *var = (Var*) tle->expr;
+			Bitmapset *key_attnos = list_nth(key_attnos_list, var->varno - 1);
+
+			/* check if this attribute is from a base table's primary key */
+			if (bms_is_member(var->varattno - FirstLowInvalidHeapAttributeNumber, key_attnos))
+			{
+				/*
+				 * Remove found key attributes from key_attnos_list, and add this
+				 * to the result list.
+				 */
+				key_attnos = bms_del_member(key_attnos, var->varattno - FirstLowInvalidHeapAttributeNumber);
+				if (bms_is_empty(key_attnos))
+				{
+					key_attnos_list = list_delete_nth_cell(key_attnos_list, var->varno - 1);
+					key_attnos_list = list_insert_nth(key_attnos_list, var->varno - 1, NULL);
+				}
+				keys = bms_add_member(keys, i - FirstLowInvalidHeapAttributeNumber);
+			}
+		}
+		i++;
+	}
+
+	/* Collect RTE indexes of relations appearing in the FROM clause */
+	rels_in_from = get_relids_in_jointree((Node *) query->jointree, false, false);
+
+	/*
+	 * Check if all key attributes of relations in FROM are appearing in the target
+	 * list.  If an attribute remains in key_attnos_list in spite of the table is used
+	 * in FROM clause, the target is missing this key attribute, so we return NULL.
+	 */
+	i = 1;
+	foreach(lc, key_attnos_list)
+	{
+		Bitmapset *bms = (Bitmapset *)lfirst(lc);
+		if (!bms_is_empty(bms) && bms_is_member(i, rels_in_from))
+			return NULL;
+		i++;
+	}
+
+	return keys;
+}
diff --git a/src/backend/commands/matview.c b/src/backend/commands/matview.c
index f9a3bdfc3a..fd9d0d99ae 100644
--- a/src/backend/commands/matview.c
+++ b/src/backend/commands/matview.c
@@ -25,26 +25,37 @@
 #include "catalog/indexing.h"
 #include "catalog/namespace.h"
 #include "catalog/pg_am.h"
+#include "catalog/pg_depend.h"
+#include "catalog/pg_trigger.h"
 #include "catalog/pg_opclass.h"
 #include "catalog/pg_operator.h"
 #include "commands/cluster.h"
 #include "commands/matview.h"
 #include "commands/tablecmds.h"
 #include "commands/tablespace.h"
+#include "commands/createas.h"
 #include "executor/executor.h"
 #include "executor/spi.h"
+#include "executor/tstoreReceiver.h"
 #include "miscadmin.h"
+#include "nodes/makefuncs.h"
+#include "parser/analyze.h"
+#include "parser/parse_clause.h"
+#include "parser/parse_func.h"
 #include "parser/parse_relation.h"
 #include "pgstat.h"
 #include "rewrite/rewriteHandler.h"
+#include "rewrite/rowsecurity.h"
 #include "storage/lmgr.h"
 #include "storage/smgr.h"
 #include "tcop/tcopprot.h"
 #include "utils/builtins.h"
+#include "utils/fmgroids.h"
 #include "utils/lsyscache.h"
 #include "utils/rel.h"
 #include "utils/snapmgr.h"
 #include "utils/syscache.h"
+#include "utils/typcache.h"
 
 
 typedef struct
@@ -58,6 +69,52 @@ typedef struct
 	BulkInsertState bistate;	/* bulk insert state */
 } DR_transientrel;
 
+#define MV_INIT_QUERYHASHSIZE	16
+
+/*
+ * MV_TriggerHashEntry
+ *
+ * Hash entry for base tables on which IVM trigger is invoked
+ */
+typedef struct MV_TriggerHashEntry
+{
+	Oid	matview_id;			/* OID of the materialized view */
+	int	before_trig_count;	/* count of before triggers invoked */
+	int	after_trig_count;	/* count of after triggers invoked */
+
+	Snapshot	snapshot;	/* Snapshot just before table change */
+
+	List   *tables;		/* List of MV_TriggerTable */
+	bool	has_old;	/* tuples are deleted from any table? */
+	bool	has_new;	/* tuples are inserted into any table? */
+} MV_TriggerHashEntry;
+
+/*
+ * MV_TriggerTable
+ *
+ * IVM related data for tables on which the trigger is invoked.
+ */
+typedef struct MV_TriggerTable
+{
+	Oid		table_id;			/* OID of the modified table */
+	List   *old_tuplestores;	/* tuplestores for deleted tuples */
+	List   *new_tuplestores;	/* tuplestores for inserted tuples */
+
+	List   *rte_indexes;		/* List of RTE index of the modified table */
+	RangeTblEntry *original_rte;	/* the original RTE saved before rewriting query */
+
+	Relation	rel;			/* relation of the modified table */
+	TupleTableSlot *slot;		/* for checking visibility in the pre-state table */
+} MV_TriggerTable;
+
+static HTAB *mv_trigger_info = NULL;
+
+static bool in_delta_calculation = false;
+
+/* ENR name for materialized view delta */
+#define NEW_DELTA_ENRNAME "new_delta"
+#define OLD_DELTA_ENRNAME "old_delta"
+
 static int	matview_maintenance_depth = 0;
 
 static void transientrel_startup(DestReceiver *self, int operation, TupleDesc typeinfo);
@@ -65,7 +122,9 @@ static bool transientrel_receive(TupleTableSlot *slot, DestReceiver *self);
 static void transientrel_shutdown(DestReceiver *self);
 static void transientrel_destroy(DestReceiver *self);
 static uint64 refresh_matview_datafill(DestReceiver *dest, Query *query,
-									   const char *queryString);
+						 QueryEnvironment *queryEnv,
+						 TupleDesc *resultTupleDesc,
+						 const char *queryString);
 static char *make_temptable_name_n(char *tempname, int n);
 static void refresh_by_match_merge(Oid matviewOid, Oid tempOid, Oid relowner,
 								   int save_sec_context);
@@ -73,6 +132,37 @@ static void refresh_by_heap_swap(Oid matviewOid, Oid OIDNewHeap, char relpersist
 static bool is_usable_unique_index(Relation indexRel);
 static void OpenMatViewIncrementalMaintenance(void);
 static void CloseMatViewIncrementalMaintenance(void);
+static Query *get_matview_query(Relation matviewRel);
+
+static Query *rewrite_query_for_preupdate_state(Query *query, List *tables,
+								  ParseState *pstate, Oid matviewid);
+static void register_delta_ENRs(ParseState *pstate, Query *query, List *tables);
+static char *make_delta_enr_name(const char *prefix, Oid relid, int count);
+static RangeTblEntry *get_prestate_rte(RangeTblEntry *rte, MV_TriggerTable *table,
+				 QueryEnvironment *queryEnv, Oid matviewid);
+static RangeTblEntry *replace_rte_with_delta(RangeTblEntry *rte, MV_TriggerTable *table, bool is_new,
+		   QueryEnvironment *queryEnv);
+static Query *rewrite_query_for_counting(Query *query, ParseState *pstate);
+
+static void calc_delta(MV_TriggerTable *table, int rte_index, Query *query,
+			DestReceiver *dest_old, DestReceiver *dest_new,
+			TupleDesc *tupdesc_old, TupleDesc *tupdesc_new,
+			QueryEnvironment *queryEnv);
+static Query *rewrite_query_for_postupdate_state(Query *query, MV_TriggerTable *table, int rte_index);
+
+static void apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *new_tuplestores,
+			TupleDesc tupdesc_old, TupleDesc tupdesc_new,
+			Query *query);
+static void apply_old_delta(const char *matviewname, const char *deltaname_old,
+				List *keys);
+static void apply_new_delta(const char *matviewname, const char *deltaname_new,
+				StringInfo target_list);
+static char *get_matching_condition_string(List *keys);
+static void generate_equal(StringInfo querybuf, Oid opttype,
+			   const char *leftop, const char *rightop);
+
+static void mv_InitHashTables(void);
+static void clean_up_IVM_hash_entry(MV_TriggerHashEntry *entry, bool is_abort);
 
 /*
  * SetMatViewPopulatedState
@@ -114,6 +204,46 @@ SetMatViewPopulatedState(Relation relation, bool newstate)
 	CommandCounterIncrement();
 }
 
+/*
+ * SetMatViewIVMState
+ *		Mark a materialized view as IVM, or not.
+ *
+ * NOTE: caller must be holding an appropriate lock on the relation.
+ */
+void
+SetMatViewIVMState(Relation relation, bool newstate)
+{
+	Relation	pgrel;
+	HeapTuple	tuple;
+
+	Assert(relation->rd_rel->relkind == RELKIND_MATVIEW);
+
+	/*
+	 * Update relation's pg_class entry.  Crucial side-effect: other backends
+	 * (and this one too!) are sent SI message to make them rebuild relcache
+	 * entries.
+	 */
+	pgrel = table_open(RelationRelationId, RowExclusiveLock);
+	tuple = SearchSysCacheCopy1(RELOID,
+								ObjectIdGetDatum(RelationGetRelid(relation)));
+	if (!HeapTupleIsValid(tuple))
+		elog(ERROR, "cache lookup failed for relation %u",
+			 RelationGetRelid(relation));
+
+	((Form_pg_class) GETSTRUCT(tuple))->relisivm = newstate;
+
+	CatalogTupleUpdate(pgrel, &tuple->t_self, tuple);
+
+	heap_freetuple(tuple);
+	table_close(pgrel, RowExclusiveLock);
+
+	/*
+	 * Advance command counter to make the updated pg_class row locally
+	 * visible.
+	 */
+	CommandCounterIncrement();
+}
+
 /*
  * ExecRefreshMatView -- execute a REFRESH MATERIALIZED VIEW command
  *
@@ -140,8 +270,6 @@ ExecRefreshMatView(RefreshMatViewStmt *stmt, const char *queryString,
 {
 	Oid			matviewOid;
 	Relation	matviewRel;
-	RewriteRule *rule;
-	List	   *actions;
 	Query	   *dataQuery;
 	Oid			tableSpace;
 	Oid			relowner;
@@ -155,6 +283,7 @@ ExecRefreshMatView(RefreshMatViewStmt *stmt, const char *queryString,
 	int			save_sec_context;
 	int			save_nestlevel;
 	ObjectAddress address;
+	bool oldPopulated;
 
 	/* Determine strength of lock needed. */
 	concurrent = stmt->concurrent;
@@ -179,6 +308,7 @@ ExecRefreshMatView(RefreshMatViewStmt *stmt, const char *queryString,
 	SetUserIdAndSecContext(relowner,
 						   save_sec_context | SECURITY_RESTRICTED_OPERATION);
 	save_nestlevel = NewGUCNestLevel();
+	oldPopulated = RelationIsPopulated(matviewRel);
 
 	/* Make sure it is a materialized view. */
 	if (matviewRel->rd_rel->relkind != RELKIND_MATVIEW)
@@ -200,32 +330,9 @@ ExecRefreshMatView(RefreshMatViewStmt *stmt, const char *queryString,
 				 errmsg("%s and %s options cannot be used together",
 						"CONCURRENTLY", "WITH NO DATA")));
 
-	/*
-	 * Check that everything is correct for a refresh. Problems at this point
-	 * are internal errors, so elog is sufficient.
-	 */
-	if (matviewRel->rd_rel->relhasrules == false ||
-		matviewRel->rd_rules->numLocks < 1)
-		elog(ERROR,
-			 "materialized view \"%s\" is missing rewrite information",
-			 RelationGetRelationName(matviewRel));
-
-	if (matviewRel->rd_rules->numLocks > 1)
-		elog(ERROR,
-			 "materialized view \"%s\" has too many rules",
-			 RelationGetRelationName(matviewRel));
 
-	rule = matviewRel->rd_rules->rules[0];
-	if (rule->event != CMD_SELECT || !(rule->isInstead))
-		elog(ERROR,
-			 "the rule for materialized view \"%s\" is not a SELECT INSTEAD OF rule",
-			 RelationGetRelationName(matviewRel));
+	dataQuery = get_matview_query(matviewRel);
 
-	actions = rule->actions;
-	if (list_length(actions) != 1)
-		elog(ERROR,
-			 "the rule for materialized view \"%s\" is not a single action",
-			 RelationGetRelationName(matviewRel));
 
 	/*
 	 * Check that there is a unique index with no WHERE clause on one or more
@@ -260,12 +367,6 @@ ExecRefreshMatView(RefreshMatViewStmt *stmt, const char *queryString,
 					 errhint("Create a unique index with no WHERE clause on one or more columns of the materialized view.")));
 	}
 
-	/*
-	 * The stored query was rewritten at the time of the MV definition, but
-	 * has not been scribbled on by the planner.
-	 */
-	dataQuery = linitial_node(Query, actions);
-
 	/*
 	 * Check for active uses of the relation in the current transaction, such
 	 * as open scans.
@@ -293,6 +394,74 @@ ExecRefreshMatView(RefreshMatViewStmt *stmt, const char *queryString,
 		relpersistence = matviewRel->rd_rel->relpersistence;
 	}
 
+	/* delete IMMV triggers. */
+	if (RelationIsIVM(matviewRel) && stmt->skipData )
+	{
+		Relation	tgRel;
+		Relation	depRel;
+		ScanKeyData key;
+		SysScanDesc scan;
+		HeapTuple	tup;
+		ObjectAddresses *immv_triggers;
+
+		immv_triggers = new_object_addresses();
+
+		tgRel = table_open(TriggerRelationId, RowExclusiveLock);
+		depRel = table_open(DependRelationId, RowExclusiveLock);
+
+		/* search triggers that depends on IMMV. */
+		ScanKeyInit(&key,
+					Anum_pg_depend_refobjid,
+					BTEqualStrategyNumber, F_OIDEQ,
+					ObjectIdGetDatum(matviewOid));
+		scan = systable_beginscan(depRel, DependReferenceIndexId, true,
+								  NULL, 1, &key);
+		while ((tup = systable_getnext(scan)) != NULL)
+		{
+			ObjectAddress obj;
+			Form_pg_depend foundDep = (Form_pg_depend) GETSTRUCT(tup);
+
+			if (foundDep->classid == TriggerRelationId)
+			{
+				HeapTuple	tgtup;
+				ScanKeyData tgkey[1];
+				SysScanDesc tgscan;
+				Form_pg_trigger tgform;
+
+				/* Find the trigger name. */
+				ScanKeyInit(&tgkey[0],
+							Anum_pg_trigger_oid,
+							BTEqualStrategyNumber, F_OIDEQ,
+							ObjectIdGetDatum(foundDep->objid));
+
+				tgscan = systable_beginscan(tgRel, TriggerOidIndexId, true,
+											NULL, 1, tgkey);
+				tgtup = systable_getnext(tgscan);
+				if (!HeapTupleIsValid(tgtup))
+					elog(ERROR, "could not find tuple for immv trigger %u", foundDep->objid);
+
+				tgform = (Form_pg_trigger) GETSTRUCT(tgtup);
+
+				/* If trigger is created by IMMV, delete it. */
+				if (strncmp(NameStr(tgform->tgname), "IVM_trigger_", 12) == 0)
+				{
+					obj.classId = foundDep->classid;
+					obj.objectId = foundDep->objid;
+					obj.objectSubId = foundDep->refobjsubid;
+					add_exact_object_address(&obj, immv_triggers);
+				}
+				systable_endscan(tgscan);
+			}
+		}
+		systable_endscan(scan);
+
+		performMultipleDeletions(immv_triggers, DROP_RESTRICT, PERFORM_DELETION_INTERNAL);
+
+		table_close(depRel, RowExclusiveLock);
+		table_close(tgRel, RowExclusiveLock);
+		free_object_addresses(immv_triggers);
+	}
+
 	/*
 	 * Create the transient table that will receive the regenerated data. Lock
 	 * it against access by any other process until commit (by which time it
@@ -306,7 +475,7 @@ ExecRefreshMatView(RefreshMatViewStmt *stmt, const char *queryString,
 
 	/* Generate the data, if wanted. */
 	if (!stmt->skipData)
-		processed = refresh_matview_datafill(dest, dataQuery, queryString);
+		processed = refresh_matview_datafill(dest, dataQuery, NULL, NULL, queryString);
 
 	/* Make the matview match the newly generated data. */
 	if (concurrent)
@@ -341,6 +510,12 @@ ExecRefreshMatView(RefreshMatViewStmt *stmt, const char *queryString,
 			pgstat_count_heap_insert(matviewRel, processed);
 	}
 
+	if (!stmt->skipData && RelationIsIVM(matviewRel) && !oldPopulated)
+	{
+		CreateIndexOnIMMV(dataQuery, matviewRel);
+		CreateIvmTriggersOnBaseTables(dataQuery, matviewOid);
+	}
+
 	table_close(matviewRel, NoLock);
 
 	/* Roll back any GUC changes */
@@ -375,6 +550,8 @@ ExecRefreshMatView(RefreshMatViewStmt *stmt, const char *queryString,
  */
 static uint64
 refresh_matview_datafill(DestReceiver *dest, Query *query,
+						 QueryEnvironment *queryEnv,
+						 TupleDesc *resultTupleDesc,
 						 const char *queryString)
 {
 	List	   *rewritten;
@@ -411,7 +588,7 @@ refresh_matview_datafill(DestReceiver *dest, Query *query,
 	/* Create a QueryDesc, redirecting output to our tuple receiver */
 	queryDesc = CreateQueryDesc(plan, queryString,
 								GetActiveSnapshot(), InvalidSnapshot,
-								dest, NULL, NULL, 0);
+								dest, NULL, queryEnv ? queryEnv: NULL, 0);
 
 	/* call ExecutorStart to prepare the plan for execution */
 	ExecutorStart(queryDesc, 0);
@@ -421,6 +598,9 @@ refresh_matview_datafill(DestReceiver *dest, Query *query,
 
 	processed = queryDesc->estate->es_processed;
 
+	if (resultTupleDesc)
+		*resultTupleDesc = CreateTupleDescCopy(queryDesc->tupDesc);
+
 	/* and clean up */
 	ExecutorFinish(queryDesc);
 	ExecutorEnd(queryDesc);
@@ -932,3 +1112,1219 @@ CloseMatViewIncrementalMaintenance(void)
 	matview_maintenance_depth--;
 	Assert(matview_maintenance_depth >= 0);
 }
+
+/*
+ * get_matview_query - get the Query from a matview's _RETURN rule.
+ */
+static Query *
+get_matview_query(Relation matviewRel)
+{
+	RewriteRule *rule;
+	List * actions;
+
+	/*
+	 * Check that everything is correct for a refresh. Problems at this point
+	 * are internal errors, so elog is sufficient.
+	 */
+	if (matviewRel->rd_rel->relhasrules == false ||
+		matviewRel->rd_rules->numLocks < 1)
+		elog(ERROR,
+			 "materialized view \"%s\" is missing rewrite information",
+			 RelationGetRelationName(matviewRel));
+
+	if (matviewRel->rd_rules->numLocks > 1)
+		elog(ERROR,
+			 "materialized view \"%s\" has too many rules",
+			 RelationGetRelationName(matviewRel));
+
+	rule = matviewRel->rd_rules->rules[0];
+	if (rule->event != CMD_SELECT || !(rule->isInstead))
+		elog(ERROR,
+			 "the rule for materialized view \"%s\" is not a SELECT INSTEAD OF rule",
+			 RelationGetRelationName(matviewRel));
+
+	actions = rule->actions;
+	if (list_length(actions) != 1)
+		elog(ERROR,
+			 "the rule for materialized view \"%s\" is not a single action",
+			 RelationGetRelationName(matviewRel));
+
+	/*
+	 * The stored query was rewritten at the time of the MV definition, but
+	 * has not been scribbled on by the planner.
+	 */
+	return linitial_node(Query, actions);
+}
+
+
+/* ----------------------------------------------------
+ *		Incremental View Maintenance routines
+ * ---------------------------------------------------
+ */
+
+/*
+ * IVM_immediate_before
+ *
+ * IVM trigger function invoked before base table is modified. If this is
+ * invoked firstly in the same statement, we save the transaction id and the
+ * command id at that time.
+ */
+Datum
+IVM_immediate_before(PG_FUNCTION_ARGS)
+{
+	TriggerData *trigdata = (TriggerData *) fcinfo->context;
+	char	   *matviewOid_text = trigdata->tg_trigger->tgargs[0];
+	char	   *ex_lock_text = trigdata->tg_trigger->tgargs[1];
+	Oid			matviewOid;
+	MV_TriggerHashEntry *entry;
+	bool	found;
+	bool	ex_lock;
+
+	matviewOid = DatumGetObjectId(DirectFunctionCall1(oidin, CStringGetDatum(matviewOid_text)));
+	ex_lock = DatumGetBool(DirectFunctionCall1(boolin, CStringGetDatum(ex_lock_text)));
+
+	/* If the view has more than one tables, we have to use an exclusive lock. */
+	if (ex_lock)
+	{
+		/*
+		 * Wait for concurrent transactions which update this materialized view at
+		 * READ COMMITED. This is needed to see changes committed in other
+		 * transactions. No wait and raise an error at REPEATABLE READ or
+		 * SERIALIZABLE to prevent update anomalies of matviews.
+		 * XXX: dead-lock is possible here.
+		 */
+		if (!IsolationUsesXactSnapshot())
+			LockRelationOid(matviewOid, ExclusiveLock);
+		else if (!ConditionalLockRelationOid(matviewOid, ExclusiveLock))
+		{
+			/* try to throw error by name; relation could be deleted... */
+			char	   *relname = get_rel_name(matviewOid);
+
+			if (!relname)
+				ereport(ERROR,
+						(errcode(ERRCODE_LOCK_NOT_AVAILABLE),
+						errmsg("could not obtain lock on materialized view during incremental maintenance")));
+
+			ereport(ERROR,
+					(errcode(ERRCODE_LOCK_NOT_AVAILABLE),
+					errmsg("could not obtain lock on materialized view \"%s\" during incremental maintenance",
+							relname)));
+		}
+	}
+	else
+		LockRelationOid(matviewOid, RowExclusiveLock);
+
+	/*
+	 * On the first call initialize the hashtable
+	 */
+	if (!mv_trigger_info)
+		mv_InitHashTables();
+
+	entry = (MV_TriggerHashEntry *) hash_search(mv_trigger_info,
+											  (void *) &matviewOid,
+											  HASH_ENTER, &found);
+
+	/* On the first BEFORE to update the view, initialize trigger data */
+	if (!found)
+	{
+		/*
+		 * Get a snapshot just before the table was modified for checking
+		 * tuple visibility in the pre-update state of the table.
+		 */
+		Snapshot snapshot = GetActiveSnapshot();
+
+		entry->matview_id = matviewOid;
+		entry->before_trig_count = 0;
+		entry->after_trig_count = 0;
+		entry->snapshot = RegisterSnapshot(snapshot);
+		entry->tables = NIL;
+		entry->has_old = false;
+		entry->has_new = false;
+	}
+
+	entry->before_trig_count++;
+
+	return PointerGetDatum(NULL);
+}
+
+/*
+ * IVM_immediate_maintenance
+ *
+ * IVM trigger function invoked after base table is modified.
+ * For each table, tuplestores of transition tables are collected.
+ * and after the last modification
+ */
+Datum
+IVM_immediate_maintenance(PG_FUNCTION_ARGS)
+{
+	TriggerData *trigdata = (TriggerData *) fcinfo->context;
+	Relation	rel;
+	Oid			relid;
+	Oid			matviewOid;
+	Query	   *query;
+	Query	   *rewritten = NULL;
+	char	   *matviewOid_text = trigdata->tg_trigger->tgargs[0];
+	Relation	matviewRel;
+	int old_depth = matview_maintenance_depth;
+
+	Oid			relowner;
+	Tuplestorestate *old_tuplestore = NULL;
+	Tuplestorestate *new_tuplestore = NULL;
+	DestReceiver *dest_new = NULL, *dest_old = NULL;
+	Oid			save_userid;
+	int			save_sec_context;
+	int			save_nestlevel;
+
+	MV_TriggerHashEntry *entry;
+	MV_TriggerTable		*table;
+	bool	found;
+
+	ParseState		 *pstate;
+	QueryEnvironment *queryEnv = create_queryEnv();
+	MemoryContext	oldcxt;
+	ListCell   *lc;
+	int			i;
+
+
+	/* Create a ParseState for rewriting the view definition query */
+	pstate = make_parsestate(NULL);
+	pstate->p_queryEnv = queryEnv;
+	pstate->p_expr_kind = EXPR_KIND_SELECT_TARGET;
+
+	rel = trigdata->tg_relation;
+	relid = rel->rd_id;
+
+	matviewOid = DatumGetObjectId(DirectFunctionCall1(oidin, CStringGetDatum(matviewOid_text)));
+
+	/*
+	 * On the first call initialize the hashtable
+	 */
+	if (!mv_trigger_info)
+		mv_InitHashTables();
+
+	/* get the entry for this materialized view */
+	entry = (MV_TriggerHashEntry *) hash_search(mv_trigger_info,
+											  (void *) &matviewOid,
+											  HASH_FIND, &found);
+	Assert (found && entry != NULL);
+	entry->after_trig_count++;
+
+	/* search the entry for the modified table and create new entry if not found */
+	found = false;
+	foreach(lc, entry->tables)
+	{
+		table = (MV_TriggerTable *) lfirst(lc);
+		if (table->table_id == relid)
+		{
+			found = true;
+			break;
+		}
+	}
+	if (!found)
+	{
+		oldcxt = MemoryContextSwitchTo(TopTransactionContext);
+
+		table = (MV_TriggerTable *) palloc0(sizeof(MV_TriggerTable));
+		table->table_id = relid;
+		table->old_tuplestores = NIL;
+		table->new_tuplestores = NIL;
+		table->rte_indexes = NIL;
+		table->slot = MakeSingleTupleTableSlot(RelationGetDescr(rel), table_slot_callbacks(rel));
+		table->rel = table_open(RelationGetRelid(rel), NoLock);
+		entry->tables = lappend(entry->tables, table);
+
+		MemoryContextSwitchTo(oldcxt);
+	}
+
+	/* Save the transition tables and make a request to not free immediately */
+	if (trigdata->tg_oldtable)
+	{
+		oldcxt = MemoryContextSwitchTo(TopTransactionContext);
+		table->old_tuplestores = lappend(table->old_tuplestores, trigdata->tg_oldtable);
+		entry->has_old = true;
+		MemoryContextSwitchTo(oldcxt);
+	}
+	if (trigdata->tg_newtable)
+	{
+		oldcxt = MemoryContextSwitchTo(TopTransactionContext);
+		table->new_tuplestores = lappend(table->new_tuplestores, trigdata->tg_newtable);
+		entry->has_new = true;
+		MemoryContextSwitchTo(oldcxt);
+	}
+	if (entry->has_new || entry->has_old)
+	{
+		CmdType cmd;
+
+		if (TRIGGER_FIRED_BY_INSERT(trigdata->tg_event))
+			cmd = CMD_INSERT;
+		else if (TRIGGER_FIRED_BY_DELETE(trigdata->tg_event))
+			cmd = CMD_DELETE;
+		else if (TRIGGER_FIRED_BY_UPDATE(trigdata->tg_event))
+			cmd = CMD_UPDATE;
+		else
+			elog(ERROR,"unsupported trigger type");
+
+		/* Prolong lifespan of transition tables to the end of the last AFTER trigger */
+		SetTransitionTablePreserved(relid, cmd);
+	}
+
+
+	/* If this is not the last AFTER trigger call, immediately exit. */
+	Assert (entry->before_trig_count >= entry->after_trig_count);
+	if (entry->before_trig_count != entry->after_trig_count)
+		return PointerGetDatum(NULL);
+
+	/*
+	 * If this is the last AFTER trigger call, continue and update the view.
+	 */
+
+	/*
+	 * Advance command counter to make the updated base table row locally
+	 * visible.
+	 */
+	CommandCounterIncrement();
+
+	matviewRel = table_open(matviewOid, NoLock);
+
+	/* Make sure it is a materialized view. */
+	Assert(matviewRel->rd_rel->relkind == RELKIND_MATVIEW);
+
+	/*
+	 * Get and push the latast snapshot to see any changes which is committed
+	 * during waiting in other transactions at READ COMMITTED level.
+	 */
+	PushActiveSnapshot(GetTransactionSnapshot());
+
+	/*
+	 * Check for active uses of the relation in the current transaction, such
+	 * as open scans.
+	 *
+	 * NB: We count on this to protect us against problems with refreshing the
+	 * data using TABLE_INSERT_FROZEN.
+	 */
+	CheckTableNotInUse(matviewRel, "refresh a materialized view incrementally");
+
+	/*
+	 * Switch to the owner's userid, so that any functions are run as that
+	 * user.  Also arrange to make GUC variable changes local to this command.
+	 * We will switch modes when we are about to execute user code.
+	 */
+	relowner = matviewRel->rd_rel->relowner;
+	GetUserIdAndSecContext(&save_userid, &save_sec_context);
+	SetUserIdAndSecContext(relowner,
+						   save_sec_context | SECURITY_RESTRICTED_OPERATION);
+	save_nestlevel = NewGUCNestLevel();
+
+	/* get view query*/
+	query = get_matview_query(matviewRel);
+
+	/*
+	 * When a base table is truncated, the view content will be empty if the
+	 * view definition query does not contain an aggregate without a GROUP clause.
+	 * Therefore, such views can be truncated.
+	 */
+	if (TRIGGER_FIRED_BY_TRUNCATE(trigdata->tg_event))
+	{
+		ExecuteTruncateGuts(list_make1(matviewRel), list_make1_oid(matviewOid),
+							NIL, DROP_RESTRICT, false, false);
+
+		/* Clean up hash entry and delete tuplestores */
+		clean_up_IVM_hash_entry(entry, false);
+
+		/* Pop the original snapshot. */
+		PopActiveSnapshot();
+
+		table_close(matviewRel, NoLock);
+
+		/* Roll back any GUC changes */
+		AtEOXact_GUC(false, save_nestlevel);
+
+		/* Restore userid and security context */
+		SetUserIdAndSecContext(save_userid, save_sec_context);
+
+		return PointerGetDatum(NULL);
+	}
+
+	/*
+	 * rewrite query for calculating deltas
+	 */
+
+	rewritten = copyObject(query);
+
+	/* Replace resnames in a target list with materialized view's attnames */
+	i = 0;
+	foreach (lc, rewritten->targetList)
+	{
+		TargetEntry *tle = (TargetEntry *) lfirst(lc);
+		Form_pg_attribute attr = TupleDescAttr(matviewRel->rd_att, i);
+		char *resname = NameStr(attr->attname);
+
+		tle->resname = pstrdup(resname);
+		i++;
+	}
+
+	/* Set all tables in the query to pre-update state */
+	rewritten = rewrite_query_for_preupdate_state(rewritten, entry->tables,
+												  pstate, matviewOid);
+	/* Rewrite for counting duplicated tuples */
+	rewritten = rewrite_query_for_counting(rewritten, pstate);
+
+	/* Create tuplestores to store view deltas */
+	if (entry->has_old)
+	{
+		oldcxt = MemoryContextSwitchTo(TopTransactionContext);
+
+		old_tuplestore = tuplestore_begin_heap(false, false, work_mem);
+		dest_old = CreateDestReceiver(DestTuplestore);
+		SetTuplestoreDestReceiverParams(dest_old,
+									old_tuplestore,
+									TopTransactionContext,
+									false,
+									NULL,
+									NULL);
+
+		MemoryContextSwitchTo(oldcxt);
+	}
+	if (entry->has_new)
+	{
+		oldcxt = MemoryContextSwitchTo(TopTransactionContext);
+
+		new_tuplestore = tuplestore_begin_heap(false, false, work_mem);
+		dest_new = CreateDestReceiver(DestTuplestore);
+		SetTuplestoreDestReceiverParams(dest_new,
+									new_tuplestore,
+									TopTransactionContext,
+									false,
+									NULL,
+									NULL);
+		MemoryContextSwitchTo(oldcxt);
+	}
+
+	/* for all modified tables */
+	foreach(lc, entry->tables)
+	{
+		ListCell *lc2;
+
+		table = (MV_TriggerTable *) lfirst(lc);
+
+		/* loop for self-join */
+		foreach(lc2, table->rte_indexes)
+		{
+			int	rte_index = lfirst_int(lc2);
+			TupleDesc		tupdesc_old;
+			TupleDesc		tupdesc_new;
+
+			/* calculate delta tables */
+			calc_delta(table, rte_index, rewritten, dest_old, dest_new,
+					   &tupdesc_old, &tupdesc_new, queryEnv);
+
+			/* Set the table in the query to post-update state */
+			rewritten = rewrite_query_for_postupdate_state(rewritten, table, rte_index);
+
+			PG_TRY();
+			{
+				/* apply the delta tables to the materialized view */
+				apply_delta(matviewOid, old_tuplestore, new_tuplestore,
+							tupdesc_old, tupdesc_new, query);
+			}
+			PG_CATCH();
+			{
+				matview_maintenance_depth = old_depth;
+				PG_RE_THROW();
+			}
+			PG_END_TRY();
+
+			/* clear view delta tuplestores */
+			if (old_tuplestore)
+				tuplestore_clear(old_tuplestore);
+			if (new_tuplestore)
+				tuplestore_clear(new_tuplestore);
+		}
+	}
+
+	/* Clean up hash entry and delete tuplestores */
+	clean_up_IVM_hash_entry(entry, false);
+	if (old_tuplestore)
+	{
+		dest_old->rDestroy(dest_old);
+		tuplestore_end(old_tuplestore);
+	}
+	if (new_tuplestore)
+	{
+		dest_new->rDestroy(dest_new);
+		tuplestore_end(new_tuplestore);
+	}
+
+	/* Pop the original snapshot. */
+	PopActiveSnapshot();
+
+	table_close(matviewRel, NoLock);
+
+	/* Roll back any GUC changes */
+	AtEOXact_GUC(false, save_nestlevel);
+
+	/* Restore userid and security context */
+	SetUserIdAndSecContext(save_userid, save_sec_context);
+
+	return PointerGetDatum(NULL);
+}
+
+/*
+ * rewrite_query_for_preupdate_state
+ *
+ * Rewrite the query so that base tables' RTEs will represent "pre-update"
+ * state of tables. This is necessary to calculate view delta after multiple
+ * tables are modified.
+ */
+static Query*
+rewrite_query_for_preupdate_state(Query *query, List *tables,
+								  ParseState *pstate, Oid matviewid)
+{
+	ListCell *lc;
+	int num_rte = list_length(query->rtable);
+	int i;
+
+
+	/* register delta ENRs */
+	register_delta_ENRs(pstate, query, tables);
+
+	/* XXX: Is necessary? Is this right timing? */
+	AcquireRewriteLocks(query, true, false);
+
+	i = 1;
+	foreach(lc, query->rtable)
+	{
+		RangeTblEntry *r = (RangeTblEntry*) lfirst(lc);
+
+		ListCell *lc2;
+		foreach(lc2, tables)
+		{
+			MV_TriggerTable *table = (MV_TriggerTable *) lfirst(lc2);
+			/*
+			 * if the modified table is found then replace the original RTE with
+			 * "pre-state" RTE and append its index to the list.
+			 */
+			if (r->relid == table->table_id)
+			{
+				List *securityQuals;
+				List *withCheckOptions;
+				bool  hasRowSecurity;
+				bool  hasSubLinks;
+
+				RangeTblEntry *rte_pre = get_prestate_rte(r, table, pstate->p_queryEnv, matviewid);
+
+				/*
+				 * Set a row security poslicies of the modified table to the subquery RTE which
+				 * represents the pre-update state of the table.
+				 */
+				get_row_security_policies(query, table->original_rte, i,
+										  &securityQuals, &withCheckOptions,
+										  &hasRowSecurity, &hasSubLinks);
+
+				if (hasRowSecurity)
+				{
+					query->hasRowSecurity = true;
+					rte_pre->security_barrier = true;
+				}
+				if (hasSubLinks)
+					query->hasSubLinks = true;
+
+				rte_pre->securityQuals = securityQuals;
+				lfirst(lc) = rte_pre;
+
+				table->rte_indexes = lappend_int(table->rte_indexes, i);
+				break;
+			}
+		}
+
+		/* finish the loop if we processed all RTE included in the original query */
+		if (i++ >= num_rte)
+			break;
+	}
+
+	return query;
+}
+
+/*
+ * register_delta_ENRs
+ *
+ * For all modified tables, make ENRs for their transition tables
+ * and register them to the queryEnv. ENR's RTEs are also appended
+ * into the list in query tree.
+ */
+static void
+register_delta_ENRs(ParseState *pstate, Query *query, List *tables)
+{
+	QueryEnvironment *queryEnv = pstate->p_queryEnv;
+	ListCell *lc;
+	RangeTblEntry	*rte;
+
+	foreach(lc, tables)
+	{
+		MV_TriggerTable *table = (MV_TriggerTable *) lfirst(lc);
+		ListCell *lc2;
+		int count;
+
+		count = 0;
+		foreach(lc2, table->old_tuplestores)
+		{
+			Tuplestorestate *oldtable = (Tuplestorestate *) lfirst(lc2);
+			EphemeralNamedRelation enr =
+				palloc(sizeof(EphemeralNamedRelationData));
+			ParseNamespaceItem *nsitem;
+
+			enr->md.name = make_delta_enr_name("old", table->table_id, count);
+			enr->md.reliddesc = table->table_id;
+			enr->md.tupdesc = NULL;
+			enr->md.enrtype = ENR_NAMED_TUPLESTORE;
+			enr->md.enrtuples = tuplestore_tuple_count(oldtable);
+			enr->reldata = oldtable;
+			register_ENR(queryEnv, enr);
+
+			nsitem = addRangeTableEntryForENR(pstate, makeRangeVar(NULL, enr->md.name, -1), true);
+			rte = nsitem->p_rte;
+
+			query->rtable = lappend(query->rtable, rte);
+
+			count++;
+		}
+
+		count = 0;
+		foreach(lc2, table->new_tuplestores)
+		{
+			Tuplestorestate *newtable = (Tuplestorestate *) lfirst(lc2);
+			EphemeralNamedRelation enr =
+				palloc(sizeof(EphemeralNamedRelationData));
+			ParseNamespaceItem *nsitem;
+
+			enr->md.name = make_delta_enr_name("new", table->table_id, count);
+			enr->md.reliddesc = table->table_id;
+			enr->md.tupdesc = NULL;
+			enr->md.enrtype = ENR_NAMED_TUPLESTORE;
+			enr->md.enrtuples = tuplestore_tuple_count(newtable);
+			enr->reldata = newtable;
+			register_ENR(queryEnv, enr);
+
+			nsitem = addRangeTableEntryForENR(pstate, makeRangeVar(NULL, enr->md.name, -1), true);
+			rte = nsitem->p_rte;
+
+			query->rtable = lappend(query->rtable, rte);
+
+			count++;
+		}
+	}
+}
+
+#define DatumGetItemPointer(X)	 ((ItemPointer) DatumGetPointer(X))
+#define PG_GETARG_ITEMPOINTER(n) DatumGetItemPointer(PG_GETARG_DATUM(n))
+
+/*
+ * ivm_visible_in_prestate
+ *
+ * Check visibility of a tuple specified by the tableoid and item pointer
+ * using the snapshot taken just before the table was modified.
+ */
+Datum
+ivm_visible_in_prestate(PG_FUNCTION_ARGS)
+{
+	Oid			tableoid = PG_GETARG_OID(0);
+	ItemPointer itemPtr = PG_GETARG_ITEMPOINTER(1);
+	Oid			matviewOid = PG_GETARG_OID(2);
+	MV_TriggerHashEntry *entry;
+	MV_TriggerTable		*table = NULL;
+	ListCell   *lc;
+	bool	found;
+	bool	result;
+
+	if (!in_delta_calculation)
+		ereport(ERROR,
+				(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+				 errmsg("ivm_visible_in_prestate can be called only in delta calculation")));
+
+	entry = (MV_TriggerHashEntry *) hash_search(mv_trigger_info,
+											  (void *) &matviewOid,
+											  HASH_FIND, &found);
+	Assert (found && entry != NULL);
+
+	foreach(lc, entry->tables)
+	{
+		table = (MV_TriggerTable *) lfirst(lc);
+		if (table->table_id == tableoid)
+			break;
+	}
+
+	Assert (table != NULL);
+
+	result = table_tuple_fetch_row_version(table->rel, itemPtr, entry->snapshot, table->slot);
+
+	PG_RETURN_BOOL(result);
+}
+
+/*
+ * get_prestate_rte
+ *
+ * Rewrite RTE of the modified table to a subquery which represents
+ * "pre-state" table. The original RTE is saved in table->rte_original.
+ */
+static RangeTblEntry*
+get_prestate_rte(RangeTblEntry *rte, MV_TriggerTable *table,
+				 QueryEnvironment *queryEnv, Oid matviewid)
+{
+	StringInfoData str;
+	RawStmt *raw;
+	Query *subquery;
+	Relation rel;
+	ParseState *pstate;
+	char *relname;
+	int i;
+
+	pstate = make_parsestate(NULL);
+	pstate->p_queryEnv = queryEnv;
+	pstate->p_expr_kind = EXPR_KIND_SELECT_TARGET;
+
+	/*
+	 * We can use NoLock here since AcquireRewriteLocks should
+	 * have locked the relation already.
+	 */
+	rel = table_open(table->table_id, NoLock);
+	relname = quote_qualified_identifier(
+					get_namespace_name(RelationGetNamespace(rel)),
+									   RelationGetRelationName(rel));
+	table_close(rel, NoLock);
+
+	/*
+	 * Filtering inserted row using the snapshot taken before the table
+	 * is modified. ctid is required for maintaining outer join views.
+	 */
+	initStringInfo(&str);
+	appendStringInfo(&str,
+		"SELECT t.* FROM %s t"
+		" WHERE pg_catalog.ivm_visible_in_prestate(t.tableoid, t.ctid ,%d::pg_catalog.oid)",
+			relname, matviewid);
+
+	/*
+	 * Append deleted rows contained in old transition tables.
+	 */
+	for (i = 0; i < list_length(table->old_tuplestores); i++)
+	{
+		appendStringInfo(&str, " UNION ALL ");
+		appendStringInfo(&str," SELECT * FROM %s",
+			make_delta_enr_name("old", table->table_id, i));
+	}
+
+	/* Get a subquery representing pre-state of the table */
+	raw = (RawStmt*)linitial(raw_parser(str.data, RAW_PARSE_DEFAULT));
+	subquery = transformStmt(pstate, raw->stmt);
+
+	/* save the original RTE */
+	table->original_rte = copyObject(rte);
+
+	rte->rtekind = RTE_SUBQUERY;
+	rte->subquery = subquery;
+	rte->security_barrier = false;
+
+	/* Clear fields that should not be set in a subquery RTE */
+	rte->relid = InvalidOid;
+	rte->relkind = 0;
+	rte->rellockmode = 0;
+	rte->tablesample = NULL;
+	rte->perminfoindex = 0;         /* no permission checking for this RTE */
+	rte->inh = false;			/* must not be set for a subquery */
+
+	return rte;
+}
+
+/*
+ * make_delta_enr_name
+ *
+ * Make a name for ENR of a transition table from the base table's oid.
+ * prefix will be "new" or "old" depending on its transition table kind..
+ */
+static char*
+make_delta_enr_name(const char *prefix, Oid relid, int count)
+{
+	char buf[NAMEDATALEN];
+	char *name;
+
+	snprintf(buf, NAMEDATALEN, "__ivm_%s_%u_%u", prefix, relid, count);
+	name = pstrdup(buf);
+
+	return name;
+}
+
+/*
+ * replace_rte_with_delta
+ *
+ * Replace RTE of the modified table with a single table delta that combine its
+ * all transition tables.
+ */
+static RangeTblEntry*
+replace_rte_with_delta(RangeTblEntry *rte, MV_TriggerTable *table, bool is_new,
+					   QueryEnvironment *queryEnv)
+{
+	Oid relid = table->table_id;
+	StringInfoData str;
+	ParseState	*pstate;
+	RawStmt *raw;
+	Query *sub;
+	int		num_tuplestores = list_length(is_new ? table->new_tuplestores : table->old_tuplestores);
+	int		i;
+
+	/* the previous RTE must be a subquery which represents "pre-state" table */
+	Assert(rte->rtekind == RTE_SUBQUERY);
+
+	/* Create a ParseState for rewriting the view definition query */
+	pstate = make_parsestate(NULL);
+	pstate->p_queryEnv = queryEnv;
+	pstate->p_expr_kind = EXPR_KIND_SELECT_TARGET;
+
+	initStringInfo(&str);
+
+	for (i = 0; i < num_tuplestores; i++)
+	{
+		if (i > 0)
+			appendStringInfo(&str, " UNION ALL ");
+
+		appendStringInfo(&str,
+			" SELECT * FROM %s",
+			make_delta_enr_name(is_new ? "new" : "old", relid, i));
+	}
+
+	raw = (RawStmt*)linitial(raw_parser(str.data, RAW_PARSE_DEFAULT));
+	sub = transformStmt(pstate, raw->stmt);
+
+	/*
+	 * Update the subquery so that it represent the combined transition
+	 * table.  Note that we leave the security_barrier and securityQuals
+	 * fields so that the subquery relation can be protected by the RLS
+	 * policy as same as the modified table.
+	 */
+	rte->rtekind = RTE_SUBQUERY;
+	rte->subquery = sub;
+
+	return rte;
+}
+
+/*
+ * rewrite_query_for_counting
+ *
+ * Rewrite query for counting duplicated tuples.
+ */
+static Query *
+rewrite_query_for_counting(Query *query, ParseState *pstate)
+{
+	TargetEntry *tle_count;
+	FuncCall *fn;
+	Node *node;
+
+	/* Add count(*) for counting distinct tuples in views */
+	fn = makeFuncCall(SystemFuncName("count"), NIL, COERCE_EXPLICIT_CALL, -1);
+	fn->agg_star = true;
+	if (!query->groupClause && !query->hasAggs)
+		query->groupClause = transformDistinctClause(NULL, &query->targetList, query->sortClause, false);
+
+	node = ParseFuncOrColumn(pstate, fn->funcname, NIL, NULL, fn, false, -1);
+
+	tle_count = makeTargetEntry((Expr *) node,
+								list_length(query->targetList) + 1,
+								pstrdup("__ivm_count__"),
+								false);
+	query->targetList = lappend(query->targetList, tle_count);
+	query->hasAggs = true;
+
+	return query;
+}
+
+/*
+ * calc_delta
+ *
+ * Calculate view deltas generated under the modification of a table specified
+ * by the RTE index.
+ */
+static void
+calc_delta(MV_TriggerTable *table, int rte_index, Query *query,
+			DestReceiver *dest_old, DestReceiver *dest_new,
+			TupleDesc *tupdesc_old, TupleDesc *tupdesc_new,
+			QueryEnvironment *queryEnv)
+{
+	ListCell *lc = list_nth_cell(query->rtable, rte_index - 1);
+	RangeTblEntry *rte = (RangeTblEntry *) lfirst(lc);
+
+	in_delta_calculation = true;
+
+	/* Generate old delta */
+	if (list_length(table->old_tuplestores) > 0)
+	{
+		/* Replace the modified table with the old delta table and calculate the old view delta. */
+		replace_rte_with_delta(rte, table, false, queryEnv);
+		refresh_matview_datafill(dest_old, query, queryEnv, tupdesc_old, "");
+	}
+
+	/* Generate new delta */
+	if (list_length(table->new_tuplestores) > 0)
+	{
+		/* Replace the modified table with the new delta table and calculate the new view delta*/
+		replace_rte_with_delta(rte, table, true, queryEnv);
+		refresh_matview_datafill(dest_new, query, queryEnv, tupdesc_new, "");
+	}
+
+	in_delta_calculation = false;
+}
+
+/*
+ * rewrite_query_for_postupdate_state
+ *
+ * Rewrite the query so that the specified base table's RTEs will represent
+ * "post-update" state of tables. This is called after the view delta
+ * calculation due to changes on this table finishes.
+ */
+static Query*
+rewrite_query_for_postupdate_state(Query *query, MV_TriggerTable *table, int rte_index)
+{
+	ListCell *lc = list_nth_cell(query->rtable, rte_index - 1);
+
+	/* Retore the original RTE */
+	lfirst(lc) = table->original_rte;
+
+	return query;
+}
+
+/*
+ * apply_delta
+ *
+ * Apply deltas to the materialized view. In outer join cases, this requires
+ * the view maintenance graph.
+ */
+static void
+apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *new_tuplestores,
+			TupleDesc tupdesc_old, TupleDesc tupdesc_new,
+			Query *query)
+{
+	StringInfoData querybuf;
+	StringInfoData target_list_buf;
+	Relation	matviewRel;
+	char	   *matviewname;
+	ListCell	*lc;
+	int			i;
+	List	   *keys = NIL;
+
+
+	/*
+	 * get names of the materialized view and delta tables
+	 */
+
+	matviewRel = table_open(matviewOid, NoLock);
+	matviewname = quote_qualified_identifier(get_namespace_name(RelationGetNamespace(matviewRel)),
+											 RelationGetRelationName(matviewRel));
+
+	/*
+	 * Build parts of the maintenance queries
+	 */
+
+	initStringInfo(&querybuf);
+	initStringInfo(&target_list_buf);
+
+	/* build string of target list */
+	for (i = 0; i < matviewRel->rd_att->natts; i++)
+	{
+		Form_pg_attribute attr = TupleDescAttr(matviewRel->rd_att, i);
+		char   *resname = NameStr(attr->attname);
+
+		if (i != 0)
+			appendStringInfo(&target_list_buf, ", ");
+		appendStringInfo(&target_list_buf, "%s", quote_qualified_identifier(NULL, resname));
+	}
+
+	i = 0;
+	foreach (lc, query->targetList)
+	{
+		TargetEntry *tle = (TargetEntry *) lfirst(lc);
+		Form_pg_attribute attr = TupleDescAttr(matviewRel->rd_att, i);
+
+		i++;
+
+		if (tle->resjunk)
+			continue;
+
+		keys = lappend(keys, attr);
+	}
+
+	/* Start maintaining the materialized view. */
+	OpenMatViewIncrementalMaintenance();
+
+	/* Open SPI context. */
+	if (SPI_connect() != SPI_OK_CONNECT)
+		elog(ERROR, "SPI_connect failed");
+
+	/* For tuple deletion */
+	if (old_tuplestores && tuplestore_tuple_count(old_tuplestores) > 0)
+	{
+		EphemeralNamedRelation enr = palloc(sizeof(EphemeralNamedRelationData));
+		int				rc;
+
+		/* convert tuplestores to ENR, and register for SPI */
+		enr->md.name = pstrdup(OLD_DELTA_ENRNAME);
+		enr->md.reliddesc = InvalidOid;
+		enr->md.tupdesc = tupdesc_old;
+		enr->md.enrtype = ENR_NAMED_TUPLESTORE;
+		enr->md.enrtuples = tuplestore_tuple_count(old_tuplestores);
+		enr->reldata = old_tuplestores;
+
+		rc = SPI_register_relation(enr);
+		if (rc != SPI_OK_REL_REGISTER)
+			elog(ERROR, "SPI_register failed");
+
+		apply_old_delta(matviewname, OLD_DELTA_ENRNAME, keys);
+
+	}
+	/* For tuple insertion */
+	if (new_tuplestores && tuplestore_tuple_count(new_tuplestores) > 0)
+	{
+		EphemeralNamedRelation enr = palloc(sizeof(EphemeralNamedRelationData));
+		int rc;
+
+		/* convert tuplestores to ENR, and register for SPI */
+		enr->md.name = pstrdup(NEW_DELTA_ENRNAME);
+		enr->md.reliddesc = InvalidOid;
+		enr->md.tupdesc = tupdesc_new;;
+		enr->md.enrtype = ENR_NAMED_TUPLESTORE;
+		enr->md.enrtuples = tuplestore_tuple_count(new_tuplestores);
+		enr->reldata = new_tuplestores;
+
+		rc = SPI_register_relation(enr);
+		if (rc != SPI_OK_REL_REGISTER)
+			elog(ERROR, "SPI_register failed");
+
+		/* apply new delta */
+		apply_new_delta(matviewname, NEW_DELTA_ENRNAME, &target_list_buf);
+	}
+
+	/* We're done maintaining the materialized view. */
+	CloseMatViewIncrementalMaintenance();
+
+	table_close(matviewRel, NoLock);
+
+	/* Close SPI context. */
+	if (SPI_finish() != SPI_OK_FINISH)
+		elog(ERROR, "SPI_finish failed");
+}
+
+/*
+ * apply_old_delta
+ *
+ * Execute a query for applying a delta table given by deltname_old
+ * which contains tuples to be deleted from to a materialized view given by
+ * matviewname.  This is used when counting is not required.
+ */
+static void
+apply_old_delta(const char *matviewname, const char *deltaname_old,
+				List *keys)
+{
+	StringInfoData	querybuf;
+	StringInfoData	keysbuf;
+	char   *match_cond;
+	ListCell *lc;
+
+	/* build WHERE condition for searching tuples to be deleted */
+	match_cond = get_matching_condition_string(keys);
+
+	/* build string of keys list */
+	initStringInfo(&keysbuf);
+	foreach (lc, keys)
+	{
+		Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc);
+		char   *resname = NameStr(attr->attname);
+		appendStringInfo(&keysbuf, "%s", quote_qualified_identifier("mv", resname));
+		if (lnext(keys, lc))
+			appendStringInfo(&keysbuf, ", ");
+	}
+
+	/* Search for matching tuples from the view and update or delete if found. */
+	initStringInfo(&querybuf);
+	appendStringInfo(&querybuf,
+	"DELETE FROM %s WHERE ctid IN ("
+		"SELECT tid FROM (SELECT pg_catalog.row_number() over (partition by %s) AS \"__ivm_row_number__\","
+								  "mv.ctid AS tid,"
+								  "diff.\"__ivm_count__\""
+						 "FROM %s AS mv, %s AS diff "
+						 "WHERE %s) v "
+					"WHERE v.\"__ivm_row_number__\" OPERATOR(pg_catalog.<=) v.\"__ivm_count__\")",
+					matviewname,
+					keysbuf.data,
+					matviewname, deltaname_old,
+					match_cond);
+
+	if (SPI_exec(querybuf.data, 0) != SPI_OK_DELETE)
+		elog(ERROR, "SPI_exec failed: %s", querybuf.data);
+}
+
+/*
+ * apply_new_delta
+ *
+ * Execute a query for applying a delta table given by deltname_new
+ * which contains tuples to be inserted into a materialized view given by
+ * matviewname.  This is used when counting is not required.
+ */
+static void
+apply_new_delta(const char *matviewname, const char *deltaname_new,
+				StringInfo target_list)
+{
+	StringInfoData	querybuf;
+
+	/* Search for matching tuples from the view and update or delete if found. */
+	initStringInfo(&querybuf);
+	appendStringInfo(&querybuf,
+					"INSERT INTO %s (%s) SELECT %s FROM ("
+						"SELECT diff.*, pg_catalog.generate_series(1, diff.\"__ivm_count__\")"
+							" AS __ivm_generate_series__ "
+						"FROM %s AS diff) AS v",
+					matviewname, target_list->data, target_list->data,
+					deltaname_new);
+
+	if (SPI_exec(querybuf.data, 0) != SPI_OK_INSERT)
+		elog(ERROR, "SPI_exec failed: %s", querybuf.data);
+}
+
+/*
+ * get_matching_condition_string
+ *
+ * Build a predicate string for looking for a tuple with given keys.
+ */
+static char *
+get_matching_condition_string(List *keys)
+{
+	StringInfoData match_cond;
+	ListCell	*lc;
+
+	/* If there is no key columns, the condition is always true. */
+	if (keys == NIL)
+		return "true";
+
+	initStringInfo(&match_cond);
+	foreach (lc, keys)
+	{
+		Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc);
+		char   *resname = NameStr(attr->attname);
+		char   *mv_resname = quote_qualified_identifier("mv", resname);
+		char   *diff_resname = quote_qualified_identifier("diff", resname);
+		Oid		typid = attr->atttypid;
+
+		/* Considering NULL values, we can not use simple = operator. */
+		appendStringInfo(&match_cond, "(");
+		generate_equal(&match_cond, typid, mv_resname, diff_resname);
+		appendStringInfo(&match_cond, " OR (%s IS NULL AND %s IS NULL))",
+						 mv_resname, diff_resname);
+
+		if (lnext(keys, lc))
+			appendStringInfo(&match_cond, " AND ");
+	}
+
+	return match_cond.data;
+}
+
+/*
+ * generate_equals
+ *
+ * Generate an equality clause using given operands' default equality
+ * operator.
+ */
+static void
+generate_equal(StringInfo querybuf, Oid opttype,
+			   const char *leftop, const char *rightop)
+{
+	TypeCacheEntry *typentry;
+
+	typentry = lookup_type_cache(opttype, TYPECACHE_EQ_OPR);
+	if (!OidIsValid(typentry->eq_opr))
+		ereport(ERROR,
+				(errcode(ERRCODE_UNDEFINED_FUNCTION),
+				 errmsg("could not identify an equality operator for type %s",
+						format_type_be_qualified(opttype))));
+
+	generate_operator_clause(querybuf,
+							 leftop, opttype,
+							 typentry->eq_opr,
+							 rightop, opttype);
+}
+
+/*
+ * mv_InitHashTables
+ */
+static void
+mv_InitHashTables(void)
+{
+	HASHCTL		ctl;
+
+	memset(&ctl, 0, sizeof(ctl));
+	ctl.keysize = sizeof(Oid);
+	ctl.entrysize = sizeof(MV_TriggerHashEntry);
+	mv_trigger_info = hash_create("MV trigger info",
+								 MV_INIT_QUERYHASHSIZE,
+								 &ctl, HASH_ELEM | HASH_BLOBS);
+}
+
+/*
+ * AtAbort_IVM
+ *
+ * Clean up hash entries for all materialized views. This is called at
+ * transaction abort.
+ */
+void
+AtAbort_IVM()
+{
+	HASH_SEQ_STATUS seq;
+	MV_TriggerHashEntry *entry;
+
+	if (mv_trigger_info)
+	{
+		hash_seq_init(&seq, mv_trigger_info);
+		while ((entry = hash_seq_search(&seq)) != NULL)
+			clean_up_IVM_hash_entry(entry, true);
+	}
+	in_delta_calculation = false;
+}
+
+/*
+ * clean_up_IVM_hash_entry
+ *
+ * Clean up tuple stores and hash entries for a materialized view after its
+ * maintenance finished.
+ */
+static void
+clean_up_IVM_hash_entry(MV_TriggerHashEntry *entry, bool is_abort)
+{
+	bool found;
+	ListCell *lc;
+
+	foreach(lc, entry->tables)
+	{
+		MV_TriggerTable *table = (MV_TriggerTable *) lfirst(lc);
+
+		list_free(table->old_tuplestores);
+		list_free(table->new_tuplestores);
+		if (!is_abort)
+		{
+			ExecDropSingleTupleTableSlot(table->slot);
+			table_close(table->rel, NoLock);
+		}
+	}
+	list_free(entry->tables);
+
+	if (!is_abort)
+		UnregisterSnapshot(entry->snapshot);
+
+	hash_search(mv_trigger_info, (void *) &entry->matview_id, HASH_REMOVE, &found);
+}
+
+/*
+ * isIvmName
+ *
+ * Check if this is a IVM hidden column from the name.
+ */
+bool
+isIvmName(const char *s)
+{
+	if (s)
+		return (strncmp(s, "__ivm_", 6) == 0);
+	return false;
+}
diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat
index 6996073989..1cca12e049 100644
--- a/src/include/catalog/pg_proc.dat
+++ b/src/include/catalog/pg_proc.dat
@@ -12043,4 +12043,14 @@
   proname => 'any_value_transfn', prorettype => 'anyelement',
   proargtypes => 'anyelement anyelement', prosrc => 'any_value_transfn' },
 
+# IVM
+{ oid => '786', descr => 'ivm trigger (before)',
+  proname => 'IVM_immediate_before', provolatile => 'v', prorettype => 'trigger',
+  proargtypes => '', prosrc => 'IVM_immediate_before' },
+{ oid => '787', descr => 'ivm trigger (after)',
+  proname => 'IVM_immediate_maintenance', provolatile => 'v', prorettype => 'trigger',
+  proargtypes => '', prosrc => 'IVM_immediate_maintenance' },
+{ oid => '788', descr => 'ivm filetring ',
+  proname => 'ivm_visible_in_prestate', provolatile => 's', prorettype => 'bool',
+  proargtypes => 'oid tid oid', prosrc => 'ivm_visible_in_prestate' },
 ]
diff --git a/src/include/commands/createas.h b/src/include/commands/createas.h
index 3647f96f73..09a64fa2e5 100644
--- a/src/include/commands/createas.h
+++ b/src/include/commands/createas.h
@@ -16,6 +16,7 @@
 
 #include "catalog/objectaddress.h"
 #include "nodes/params.h"
+#include "nodes/pathnodes.h"
 #include "parser/parse_node.h"
 #include "tcop/dest.h"
 #include "utils/queryenvironment.h"
@@ -25,6 +26,9 @@ extern ObjectAddress ExecCreateTableAs(ParseState *pstate, CreateTableAsStmt *st
 									   ParamListInfo params, QueryEnvironment *queryEnv,
 									   QueryCompletion *qc);
 
+extern void CreateIvmTriggersOnBaseTables(Query *qry, Oid matviewOid);
+extern void CreateIndexOnIMMV(Query *query, Relation matviewRel);
+
 extern int	GetIntoRelEFlags(IntoClause *intoClause);
 
 extern DestReceiver *CreateIntoRelDestReceiver(IntoClause *intoClause);
diff --git a/src/include/commands/matview.h b/src/include/commands/matview.h
index 9eaa6212a1..504b83a446 100644
--- a/src/include/commands/matview.h
+++ b/src/include/commands/matview.h
@@ -15,6 +15,7 @@
 #define MATVIEW_H
 
 #include "catalog/objectaddress.h"
+#include "fmgr.h"
 #include "nodes/params.h"
 #include "nodes/parsenodes.h"
 #include "tcop/dest.h"
@@ -23,6 +24,8 @@
 
 extern void SetMatViewPopulatedState(Relation relation, bool newstate);
 
+extern void SetMatViewIVMState(Relation relation, bool newstate);
+
 extern ObjectAddress ExecRefreshMatView(RefreshMatViewStmt *stmt, const char *queryString,
 										ParamListInfo params, QueryCompletion *qc);
 
@@ -30,4 +33,10 @@ extern DestReceiver *CreateTransientRelDestReceiver(Oid transientoid);
 
 extern bool MatViewIncrementalMaintenanceIsEnabled(void);
 
+extern Datum IVM_immediate_before(PG_FUNCTION_ARGS);
+extern Datum IVM_immediate_maintenance(PG_FUNCTION_ARGS);
+extern Datum IVM_visible_in_prestate(PG_FUNCTION_ARGS);
+extern void AtAbort_IVM(void);
+extern bool isIvmName(const char *s);
+
 #endif							/* MATVIEW_H */
-- 
2.25.1


--Multipart=_Thu__1_Jun_2023_23_59_09_+0900_/G5+8nG46.f1T42K
Content-Type: text/x-diff;
 name="v28-0007-Add-DISTINCT-support-for-IVM.patch"
Content-Disposition: attachment;
 filename="v28-0007-Add-DISTINCT-support-for-IVM.patch"
Content-Transfer-Encoding: 7bit



^ permalink  raw  reply  [nested|flat] 101+ messages in thread

* [PATCH v30 06/11] Add Incremental View Maintenance support
@ 2023-05-31 09:59  Yugo Nagata <[email protected]>
  0 siblings, 0 replies; 101+ messages in thread

From: Yugo Nagata @ 2023-05-31 09:59 UTC (permalink / raw)

In this implementation, AFTER triggers are used to collect
tuplestores containing transition table contents. When multiple tables
are changed, multiple AFTER triggers are invoked, then the final AFTER
trigger performs actual update of the matview. In addition, BEFORE
triggers are also used to handle global information for view
maintenance.

To calculate view deltas, we need both pre-state and post-state of base
tables. Post-update states are available in AFTER trigger, and pre-update
states can be calculated by removing inserted tuples and appending deleted
tuples. Insterted tuples are filtered using the snapshot taken before
table modiication, and deleted tuples are contained in the old transition
table.

Incrementally Maintainable Materialized Views (IMMV) can contain
duplicated tuples.

This patch also allows self-join, simultaneous updates of more than
one base table, and multiple updates of the same base table.
---
 src/backend/access/transam/xact.c |    5 +
 src/backend/commands/createas.c   |  681 ++++++++++++++
 src/backend/commands/matview.c    | 1466 ++++++++++++++++++++++++++++-
 src/include/catalog/pg_proc.dat   |   10 +
 src/include/commands/createas.h   |    4 +
 src/include/commands/matview.h    |    9 +
 6 files changed, 2140 insertions(+), 35 deletions(-)

diff --git a/src/backend/access/transam/xact.c b/src/backend/access/transam/xact.c
index 70ab6e27a1..0de7ab6abe 100644
--- a/src/backend/access/transam/xact.c
+++ b/src/backend/access/transam/xact.c
@@ -36,6 +36,7 @@
 #include "catalog/pg_enum.h"
 #include "catalog/storage.h"
 #include "commands/async.h"
+#include "commands/matview.h"
 #include "commands/tablecmds.h"
 #include "commands/trigger.h"
 #include "common/pg_prng.h"
@@ -2819,6 +2820,7 @@ AbortTransaction(void)
 	AtAbort_Notify();
 	AtEOXact_RelationMap(false, is_parallel_worker);
 	AtAbort_Twophase();
+	AtAbort_IVM();
 
 	/*
 	 * Advertise the fact that we aborted in pg_xact (assuming that we got as
@@ -5097,6 +5099,9 @@ AbortSubTransaction(void)
 	pgstat_progress_end_command();
 	UnlockBuffers();
 
+	/* Clean up hash entries for incremental view maintenance */
+	AtAbort_IVM();
+
 	/* Reset WAL record construction state */
 	XLogResetInsertion();
 
diff --git a/src/backend/commands/createas.c b/src/backend/commands/createas.c
index 16a2fe65e6..08262100ea 100644
--- a/src/backend/commands/createas.c
+++ b/src/backend/commands/createas.c
@@ -32,15 +32,26 @@
 #include "access/xact.h"
 #include "access/xlog.h"
 #include "catalog/namespace.h"
+#include "catalog/index.h"
+#include "catalog/pg_constraint.h"
+#include "catalog/pg_inherits.h"
+#include "catalog/pg_trigger.h"
 #include "catalog/toasting.h"
 #include "commands/createas.h"
+#include "commands/defrem.h"
 #include "commands/matview.h"
 #include "commands/prepare.h"
 #include "commands/tablecmds.h"
+#include "commands/tablespace.h"
+#include "commands/trigger.h"
 #include "commands/view.h"
 #include "miscadmin.h"
+#include "optimizer/optimizer.h"
+#include "optimizer/prep.h"
 #include "nodes/makefuncs.h"
 #include "nodes/nodeFuncs.h"
+#include "parser/parser.h"
+#include "parser/parsetree.h"
 #include "parser/parse_clause.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/smgr.h"
@@ -73,6 +84,12 @@ static bool intorel_receive(TupleTableSlot *slot, DestReceiver *self);
 static void intorel_shutdown(DestReceiver *self);
 static void intorel_destroy(DestReceiver *self);
 
+static void CreateIvmTriggersOnBaseTablesRecurse(Query *qry, Node *node, Oid matviewOid,
+									 Relids *relids, bool ex_lock);
+static void CreateIvmTrigger(Oid relOid, Oid viewOid, int16 type, int16 timing, bool ex_lock);
+static void check_ivm_restriction(Node *node);
+static bool check_ivm_restriction_walker(Node *node, void *context);
+static Bitmapset *get_primary_key_attnos_from_query(Query *query, List **constraintList);
 
 /*
  * create_ctas_internal
@@ -282,6 +299,18 @@ ExecCreateTableAs(ParseState *pstate, CreateTableAsStmt *stmt,
 		save_nestlevel = NewGUCNestLevel();
 	}
 
+	if (is_matview && into->ivm)
+	{
+		/* check if the query is supported in IMMV definition */
+		if (contain_mutable_functions((Node *) query))
+			ereport(ERROR,
+					(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+					 errmsg("mutable function is not supported on incrementally maintainable materialized view"),
+					 errhint("functions must be marked IMMUTABLE")));
+
+		check_ivm_restriction((Node *) query);
+	}
+
 	if (into->skipData)
 	{
 		/*
@@ -358,6 +387,27 @@ ExecCreateTableAs(ParseState *pstate, CreateTableAsStmt *stmt,
 
 		/* Restore userid and security context */
 		SetUserIdAndSecContext(save_userid, save_sec_context);
+
+		if (into->ivm)
+		{
+			Oid matviewOid = address.objectId;
+			Relation matviewRel = table_open(matviewOid, NoLock);
+
+			/*
+			 * Mark relisivm field, if it's a matview and into->ivm is true.
+			 */
+			SetMatViewIVMState(matviewRel, true);
+
+			if (!into->skipData)
+			{
+				/* Create an index on incremental maintainable materialized view, if possible */
+				CreateIndexOnIMMV((Query *) into->viewQuery, matviewRel);
+
+				/* Create triggers on incremental maintainable materialized view */
+				CreateIvmTriggersOnBaseTables((Query *) into->viewQuery, matviewOid);
+			}
+			table_close(matviewRel, NoLock);
+		}
 	}
 
 	return address;
@@ -635,3 +685,634 @@ intorel_destroy(DestReceiver *self)
 {
 	pfree(self);
 }
+
+/*
+ * CreateIvmTriggersOnBaseTables -- create IVM triggers on all base tables
+ */
+void
+CreateIvmTriggersOnBaseTables(Query *qry, Oid matviewOid)
+{
+	Relids	relids = NULL;
+	bool	ex_lock = false;
+	RangeTblEntry *rte;
+
+	/* Immediately return if we don't have any base tables. */
+	if (list_length(qry->rtable) < 1)
+		return;
+
+	/*
+	 * If the view has more than one base tables, we need an exclusive lock
+	 * on the view so that the view would be maintained serially to avoid
+	 * the inconsistency that occurs when two base tables are modified in
+	 * concurrent transactions. However, if the view has only one table,
+	 * we can use a weaker lock.
+	 *
+	 * The type of lock should be determined here, because if we check the
+	 * view definition at maintenance time, we need to acquire a weaker lock,
+	 * and upgrading the lock level after this increases probability of
+	 * deadlock.
+	 */
+
+	rte = list_nth(qry->rtable, 0);
+	if (list_length(qry->rtable) > 1 || rte->rtekind != RTE_RELATION)
+		ex_lock = true;
+
+	CreateIvmTriggersOnBaseTablesRecurse(qry, (Node *)qry, matviewOid, &relids, ex_lock);
+
+	bms_free(relids);
+}
+
+static void
+CreateIvmTriggersOnBaseTablesRecurse(Query *qry, Node *node, Oid matviewOid,
+									 Relids *relids, bool ex_lock)
+{
+	if (node == NULL)
+		return;
+
+	/* This can recurse, so check for excessive recursion */
+	check_stack_depth();
+
+	switch (nodeTag(node))
+	{
+		case T_Query:
+			{
+				Query *query = (Query *) node;
+
+				CreateIvmTriggersOnBaseTablesRecurse(qry, (Node *)query->jointree, matviewOid, relids, ex_lock);
+			}
+			break;
+
+		case T_RangeTblRef:
+			{
+				int			rti = ((RangeTblRef *) node)->rtindex;
+				RangeTblEntry *rte = rt_fetch(rti, qry->rtable);
+
+				if (rte->rtekind == RTE_RELATION && !bms_is_member(rte->relid, *relids))
+				{
+					CreateIvmTrigger(rte->relid, matviewOid, TRIGGER_TYPE_INSERT, TRIGGER_TYPE_BEFORE, ex_lock);
+					CreateIvmTrigger(rte->relid, matviewOid, TRIGGER_TYPE_DELETE, TRIGGER_TYPE_BEFORE, ex_lock);
+					CreateIvmTrigger(rte->relid, matviewOid, TRIGGER_TYPE_UPDATE, TRIGGER_TYPE_BEFORE, ex_lock);
+					CreateIvmTrigger(rte->relid, matviewOid, TRIGGER_TYPE_TRUNCATE, TRIGGER_TYPE_BEFORE, true);
+					CreateIvmTrigger(rte->relid, matviewOid, TRIGGER_TYPE_INSERT, TRIGGER_TYPE_AFTER, ex_lock);
+					CreateIvmTrigger(rte->relid, matviewOid, TRIGGER_TYPE_DELETE, TRIGGER_TYPE_AFTER, ex_lock);
+					CreateIvmTrigger(rte->relid, matviewOid, TRIGGER_TYPE_UPDATE, TRIGGER_TYPE_AFTER, ex_lock);
+					CreateIvmTrigger(rte->relid, matviewOid, TRIGGER_TYPE_TRUNCATE, TRIGGER_TYPE_AFTER, true);
+
+					*relids = bms_add_member(*relids, rte->relid);
+				}
+			}
+			break;
+
+		case T_FromExpr:
+			{
+				FromExpr   *f = (FromExpr *) node;
+				ListCell   *l;
+
+				foreach(l, f->fromlist)
+					CreateIvmTriggersOnBaseTablesRecurse(qry, lfirst(l), matviewOid, relids, ex_lock);
+			}
+			break;
+
+		case T_JoinExpr:
+			{
+				JoinExpr   *j = (JoinExpr *) node;
+
+				CreateIvmTriggersOnBaseTablesRecurse(qry, j->larg, matviewOid, relids, ex_lock);
+				CreateIvmTriggersOnBaseTablesRecurse(qry, j->rarg, matviewOid, relids, ex_lock);
+			}
+			break;
+
+		default:
+			elog(ERROR, "unrecognized node type: %d", (int) nodeTag(node));
+	}
+}
+
+/*
+ * CreateIvmTrigger -- create IVM trigger on a base table
+ */
+static void
+CreateIvmTrigger(Oid relOid, Oid viewOid, int16 type, int16 timing, bool ex_lock)
+{
+	ObjectAddress	refaddr;
+	ObjectAddress	address;
+	CreateTrigStmt *ivm_trigger;
+	List *transitionRels = NIL;
+
+	Assert(timing == TRIGGER_TYPE_BEFORE || timing == TRIGGER_TYPE_AFTER);
+
+	refaddr.classId = RelationRelationId;
+	refaddr.objectId = viewOid;
+	refaddr.objectSubId = 0;
+
+	ivm_trigger = makeNode(CreateTrigStmt);
+	ivm_trigger->relation = NULL;
+	ivm_trigger->row = false;
+
+	ivm_trigger->timing = timing;
+	ivm_trigger->events = type;
+
+	switch (type)
+	{
+		case TRIGGER_TYPE_INSERT:
+			ivm_trigger->trigname = (timing == TRIGGER_TYPE_BEFORE ? "IVM_trigger_ins_before" : "IVM_trigger_ins_after");
+			break;
+		case TRIGGER_TYPE_DELETE:
+			ivm_trigger->trigname = (timing == TRIGGER_TYPE_BEFORE ? "IVM_trigger_del_before" : "IVM_trigger_del_after");
+			break;
+		case TRIGGER_TYPE_UPDATE:
+			ivm_trigger->trigname = (timing == TRIGGER_TYPE_BEFORE ? "IVM_trigger_upd_before" : "IVM_trigger_upd_after");
+			break;
+		case TRIGGER_TYPE_TRUNCATE:
+			ivm_trigger->trigname = (timing == TRIGGER_TYPE_BEFORE ? "IVM_trigger_truncate_before" : "IVM_trigger_truncate_after");
+			break;
+		default:
+			elog(ERROR, "unsupported trigger type");
+	}
+
+	if (timing == TRIGGER_TYPE_AFTER)
+	{
+		if (type == TRIGGER_TYPE_INSERT || type == TRIGGER_TYPE_UPDATE)
+		{
+			TriggerTransition *n = makeNode(TriggerTransition);
+			n->name = "__ivm_newtable";
+			n->isNew = true;
+			n->isTable = true;
+
+			transitionRels = lappend(transitionRels, n);
+		}
+		if (type == TRIGGER_TYPE_DELETE || type == TRIGGER_TYPE_UPDATE)
+		{
+			TriggerTransition *n = makeNode(TriggerTransition);
+			n->name = "__ivm_oldtable";
+			n->isNew = false;
+			n->isTable = true;
+
+			transitionRels = lappend(transitionRels, n);
+		}
+	}
+
+	/*
+	 * XXX: When using DELETE or UPDATE, we must use exclusive lock for now
+	 * because apply_old_delta(_with_count) uses ctid to identify the tuple
+	 * to be deleted/deleted, but doesn't work in concurrent situations.
+	 *
+	 * If the view doesn't have aggregate, distinct, or tuple duplicate,
+	 * then it would work even in concurrent situations. However, we don't have
+	 * any way to guarantee the view has a unique key before opening the IMMV
+	 * at the maintenance time because users may drop the unique index.
+	 */
+
+	if (type == TRIGGER_TYPE_DELETE || type == TRIGGER_TYPE_UPDATE)
+		ex_lock = true;
+
+	ivm_trigger->funcname =
+		(timing == TRIGGER_TYPE_BEFORE ? SystemFuncName("IVM_immediate_before") : SystemFuncName("IVM_immediate_maintenance"));
+
+	ivm_trigger->columns = NIL;
+	ivm_trigger->transitionRels = transitionRels;
+	ivm_trigger->whenClause = NULL;
+	ivm_trigger->isconstraint = false;
+	ivm_trigger->deferrable = false;
+	ivm_trigger->initdeferred = false;
+	ivm_trigger->constrrel = NULL;
+	ivm_trigger->args = list_make2(
+		makeString(DatumGetPointer(DirectFunctionCall1(oidout, ObjectIdGetDatum(viewOid)))),
+		makeString(DatumGetPointer(DirectFunctionCall1(boolout, BoolGetDatum(ex_lock))))
+		);
+
+	address = CreateTrigger(ivm_trigger, NULL, relOid, InvalidOid, InvalidOid,
+						 InvalidOid, InvalidOid, InvalidOid, NULL, true, false);
+
+	recordDependencyOn(&address, &refaddr, DEPENDENCY_AUTO);
+
+	/* Make changes-so-far visible */
+	CommandCounterIncrement();
+}
+
+/*
+ * check_ivm_restriction --- look for specify nodes in the query tree
+ */
+static void
+check_ivm_restriction(Node *node)
+{
+	check_ivm_restriction_walker(node, NULL);
+}
+
+static bool
+check_ivm_restriction_walker(Node *node, void *context)
+{
+	if (node == NULL)
+		return false;
+
+	/*
+	 * We currently don't support Sub-Query.
+	 */
+	if (IsA(node, SubPlan) || IsA(node, SubLink))
+		ereport(ERROR,
+				(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+				 errmsg("subquery is not supported on incrementally maintainable materialized view")));
+
+	/* This can recurse, so check for excessive recursion */
+	check_stack_depth();
+
+	switch (nodeTag(node))
+	{
+		case T_Query:
+			{
+				Query *qry = (Query *)node;
+				ListCell   *lc;
+				List       *vars;
+
+				/* if contained CTE, return error */
+				if (qry->cteList != NIL)
+					ereport(ERROR,
+							(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+							 errmsg("CTE is not supported on incrementally maintainable materialized view")));
+				if (qry->havingQual != NULL)
+					ereport(ERROR,
+							(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+							 errmsg(" HAVING clause is not supported on incrementally maintainable materialized view")));
+				if (qry->sortClause != NIL)	/* There is a possibility that we don't need to return an error */
+					ereport(ERROR,
+							(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+							 errmsg("ORDER BY clause is not supported on incrementally maintainable materialized view")));
+				if (qry->limitOffset != NULL || qry->limitCount != NULL)
+					ereport(ERROR,
+							(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+							 errmsg("LIMIT/OFFSET clause is not supported on incrementally maintainable materialized view")));
+				if (qry->distinctClause)
+					ereport(ERROR,
+							(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+							 errmsg("DISTINCT is not supported on incrementally maintainable materialized view")));
+				if (qry->hasDistinctOn)
+					ereport(ERROR,
+							(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+							 errmsg("DISTINCT ON is not supported on incrementally maintainable materialized view")));
+				if (qry->hasWindowFuncs)
+					ereport(ERROR,
+							(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+							 errmsg("window functions are not supported on incrementally maintainable materialized view")));
+				if (qry->groupingSets != NIL)
+					ereport(ERROR,
+							(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+							 errmsg("GROUPING SETS, ROLLUP, or CUBE clauses is not supported on incrementally maintainable materialized view")));
+				if (qry->setOperations != NULL)
+					ereport(ERROR,
+							(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+							 errmsg("UNION/INTERSECT/EXCEPT statements are not supported on incrementally maintainable materialized view")));
+				if (list_length(qry->targetList) == 0)
+					ereport(ERROR,
+							(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+							 errmsg("empty target list is not supported on incrementally maintainable materialized view")));
+				if (qry->rowMarks != NIL)
+					ereport(ERROR,
+							(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+							 errmsg("FOR UPDATE/SHARE clause is not supported on incrementally maintainable materialized view")));
+
+				/* system column restrictions */
+				vars = pull_vars_of_level((Node *) qry, 0);
+				foreach(lc, vars)
+				{
+					if (IsA(lfirst(lc), Var))
+					{
+						Var *var = (Var *) lfirst(lc);
+						/* if system column, return error */
+						if (var->varattno < 0)
+							ereport(ERROR,
+									(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+									 errmsg("system column is not supported on incrementally maintainable materialized view")));
+					}
+				}
+
+				/* restrictions for rtable */
+				foreach(lc, qry->rtable)
+				{
+					RangeTblEntry *rte = (RangeTblEntry *) lfirst(lc);
+
+					if (rte->subquery)
+						ereport(ERROR,
+								(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+								 errmsg("subquery is not supported on incrementally maintainable materialized view")));
+
+					if (rte->tablesample != NULL)
+						ereport(ERROR,
+								(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+								 errmsg("TABLESAMPLE clause is not supported on incrementally maintainable materialized view")));
+
+					if (rte->relkind == RELKIND_PARTITIONED_TABLE)
+						ereport(ERROR,
+								(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+								 errmsg("partitioned table is not supported on incrementally maintainable materialized view")));
+
+					if (rte->relkind == RELKIND_RELATION && has_superclass(rte->relid))
+						ereport(ERROR,
+								(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+								 errmsg("partitions is not supported on incrementally maintainable materialized view")));
+
+					if (rte->relkind == RELKIND_RELATION && find_inheritance_children(rte->relid, NoLock) != NIL)
+						ereport(ERROR,
+								(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+								 errmsg("inheritance parent is not supported on incrementally maintainable materialized view")));
+
+					if (rte->relkind == RELKIND_FOREIGN_TABLE)
+						ereport(ERROR,
+								(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+								 errmsg("foreign table is not supported on incrementally maintainable materialized view")));
+
+					if (rte->relkind == RELKIND_VIEW ||
+						rte->relkind == RELKIND_MATVIEW)
+						ereport(ERROR,
+								(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+								 errmsg("VIEW or MATERIALIZED VIEW is not supported on incrementally maintainable materialized view")));
+
+					if (rte->rtekind == RTE_VALUES)
+						ereport(ERROR,
+								(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+								 errmsg("VALUES is not supported on incrementally maintainable materialized view")));
+
+				}
+
+				query_tree_walker(qry, check_ivm_restriction_walker, NULL, QTW_IGNORE_RANGE_TABLE);
+
+				break;
+			}
+		case T_TargetEntry:
+			{
+				TargetEntry *tle = (TargetEntry *)node;
+				if (isIvmName(tle->resname))
+						ereport(ERROR,
+								(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+								 errmsg("column name %s is not supported on incrementally maintainable materialized view", tle->resname)));
+
+				expression_tree_walker(node, check_ivm_restriction_walker, NULL);
+				break;
+			}
+		case T_JoinExpr:
+			{
+				JoinExpr *joinexpr = (JoinExpr *)node;
+
+				if (joinexpr->jointype > JOIN_INNER)
+						ereport(ERROR,
+								(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+								 errmsg("OUTER JOIN is not supported on incrementally maintainable materialized view")));
+
+				expression_tree_walker(node, check_ivm_restriction_walker, NULL);
+			}
+			break;
+		case T_Aggref:
+			ereport(ERROR,
+					(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+					 errmsg("aggregate function is not supported on incrementally maintainable materialized view")));
+			break;
+		default:
+			expression_tree_walker(node, check_ivm_restriction_walker, (void *) context);
+			break;
+	}
+	return false;
+}
+
+/*
+ * CreateIndexOnIMMV
+ *
+ * Create a unique index on incremental maintainable materialized view.
+ * If the view definition query has a GROUP BY clause, the index is created
+ * on the columns of GROUP BY expressions. Otherwise, if the view contains
+ * all primary key attritubes of its base tables in the target list, the index
+ * is created on these attritubes. In other cases, no index is created.
+ */
+void
+CreateIndexOnIMMV(Query *query, Relation matviewRel)
+{
+	ListCell *lc;
+	IndexStmt  *index;
+	ObjectAddress address;
+	List *constraintList = NIL;
+	char		idxname[NAMEDATALEN];
+	List	   *indexoidlist = RelationGetIndexList(matviewRel);
+	ListCell   *indexoidscan;
+	Bitmapset *key_attnos;
+
+	snprintf(idxname, sizeof(idxname), "%s_index", RelationGetRelationName(matviewRel));
+
+	index = makeNode(IndexStmt);
+
+	index->unique = true;
+	index->primary = false;
+	index->isconstraint = false;
+	index->deferrable = false;
+	index->initdeferred = false;
+	index->idxname = idxname;
+	index->relation =
+		makeRangeVar(get_namespace_name(RelationGetNamespace(matviewRel)),
+					 pstrdup(RelationGetRelationName(matviewRel)),
+					 -1);
+	index->accessMethod = DEFAULT_INDEX_TYPE;
+	index->options = NIL;
+	index->tableSpace = get_tablespace_name(matviewRel->rd_rel->reltablespace);
+	index->whereClause = NULL;
+	index->indexParams = NIL;
+	index->indexIncludingParams = NIL;
+	index->excludeOpNames = NIL;
+	index->idxcomment = NULL;
+	index->indexOid = InvalidOid;
+	index->oldNumber = InvalidRelFileNumber;
+	index->oldCreateSubid = InvalidSubTransactionId;
+	index->oldFirstRelfilelocatorSubid = InvalidSubTransactionId;
+	index->transformed = true;
+	index->concurrent = false;
+	index->if_not_exists = false;
+
+	/* create index on the base tables' primary key columns */
+	key_attnos = get_primary_key_attnos_from_query(query, &constraintList);
+	if (key_attnos)
+	{
+		foreach(lc, query->targetList)
+		{
+			TargetEntry *tle = (TargetEntry *) lfirst(lc);
+			Form_pg_attribute attr = TupleDescAttr(matviewRel->rd_att, tle->resno - 1);
+
+			if (bms_is_member(tle->resno - FirstLowInvalidHeapAttributeNumber, key_attnos))
+			{
+				IndexElem  *iparam;
+
+				iparam = makeNode(IndexElem);
+				iparam->name = pstrdup(NameStr(attr->attname));
+				iparam->expr = NULL;
+				iparam->indexcolname = NULL;
+				iparam->collation = NIL;
+				iparam->opclass = NIL;
+				iparam->opclassopts = NIL;
+				iparam->ordering = SORTBY_DEFAULT;
+				iparam->nulls_ordering = SORTBY_NULLS_DEFAULT;
+				index->indexParams = lappend(index->indexParams, iparam);
+			}
+		}
+	}
+	else
+	{
+		/* create no index, just notice that an appropriate index is necessary for efficient IVM */
+		ereport(NOTICE,
+				(errmsg("could not create an index on materialized view \"%s\" automatically",
+						RelationGetRelationName(matviewRel)),
+				 errdetail("This target list does not have all the primary key columns. "),
+				 errhint("Create an index on the materialized view for efficient incremental maintenance.")));
+		return;
+	}
+
+	/* If we have a compatible index, we don't need to create another. */
+	foreach(indexoidscan, indexoidlist)
+	{
+		Oid			indexoid = lfirst_oid(indexoidscan);
+		Relation	indexRel;
+		bool		hasCompatibleIndex = false;
+
+		indexRel = index_open(indexoid, AccessShareLock);
+
+		if (CheckIndexCompatible(indexRel->rd_id,
+								index->accessMethod,
+								index->indexParams,
+								index->excludeOpNames,
+								false))
+			hasCompatibleIndex = true;
+
+		index_close(indexRel, AccessShareLock);
+
+		if (hasCompatibleIndex)
+			return;
+	}
+
+	address = DefineIndex(RelationGetRelid(matviewRel),
+						  index,
+						  InvalidOid,
+						  InvalidOid,
+						  InvalidOid,
+						  -1,
+						  false, true, false, false, true);
+
+	ereport(NOTICE,
+			(errmsg("created index \"%s\" on materialized view \"%s\"",
+					idxname, RelationGetRelationName(matviewRel))));
+
+	/*
+	 * Make dependencies so that the index is dropped if any base tables's
+	 * primary key is dropped.
+	 */
+	foreach(lc, constraintList)
+	{
+		Oid constraintOid = lfirst_oid(lc);
+		ObjectAddress	refaddr;
+
+		refaddr.classId = ConstraintRelationId;
+		refaddr.objectId = constraintOid;
+		refaddr.objectSubId = 0;
+
+		recordDependencyOn(&address, &refaddr, DEPENDENCY_NORMAL);
+	}
+}
+
+
+/*
+ * get_primary_key_attnos_from_query
+ *
+ * Identify the columns in base tables' primary keys in the target list.
+ *
+ * Returns a Bitmapset of the column attnos of the primary key's columns of
+ * tables that used in the query.  The attnos are offset by
+ * FirstLowInvalidHeapAttributeNumber as same as get_primary_key_attnos.
+ *
+ * If any table has no primary key or any primary key's columns is not in
+ * the target list, return NULL.  We also return NULL if any pkey constraint
+ * is deferrable.
+ *
+ * constraintList is set to a list of the OIDs of the pkey constraints.
+ */
+static Bitmapset *
+get_primary_key_attnos_from_query(Query *query, List **constraintList)
+{
+	List *key_attnos_list = NIL;
+	ListCell *lc;
+	int i;
+	Bitmapset *keys = NULL;
+	Relids	rels_in_from;
+
+	/*
+	 * Collect primary key attributes from all tables used in query. The key attributes
+	 * sets for each table are stored in key_attnos_list in order by RTE index.
+	 */
+	foreach(lc, query->rtable)
+	{
+		RangeTblEntry *r = (RangeTblEntry*) lfirst(lc);
+		Bitmapset *key_attnos;
+		bool	has_pkey = true;
+
+		/* for tables, call get_primary_key_attnos */
+		if (r->rtekind == RTE_RELATION)
+		{
+			Oid constraintOid;
+			key_attnos = get_primary_key_attnos(r->relid, false, &constraintOid);
+			*constraintList = lappend_oid(*constraintList, constraintOid);
+			has_pkey = (key_attnos != NULL);
+		}
+		/* for other RTEs, store NULL into key_attnos_list */
+		else
+			key_attnos = NULL;
+
+		/*
+		 * If any table or subquery has no primary key or its pkey constraint is deferrable,
+		 * we cannot get key attributes for this query, so return NULL.
+		 */
+		if (!has_pkey)
+			return NULL;
+
+		key_attnos_list = lappend(key_attnos_list, key_attnos);
+	}
+
+	/* Collect key attributes appearing in the target list */
+	i = 1;
+	foreach(lc, query->targetList)
+	{
+		TargetEntry *tle = (TargetEntry *) flatten_join_alias_vars(NULL, query, lfirst(lc));
+
+		if (IsA(tle->expr, Var))
+		{
+			Var *var = (Var*) tle->expr;
+			Bitmapset *key_attnos = list_nth(key_attnos_list, var->varno - 1);
+
+			/* check if this attribute is from a base table's primary key */
+			if (bms_is_member(var->varattno - FirstLowInvalidHeapAttributeNumber, key_attnos))
+			{
+				/*
+				 * Remove found key attributes from key_attnos_list, and add this
+				 * to the result list.
+				 */
+				key_attnos = bms_del_member(key_attnos, var->varattno - FirstLowInvalidHeapAttributeNumber);
+				if (bms_is_empty(key_attnos))
+				{
+					key_attnos_list = list_delete_nth_cell(key_attnos_list, var->varno - 1);
+					key_attnos_list = list_insert_nth(key_attnos_list, var->varno - 1, NULL);
+				}
+				keys = bms_add_member(keys, i - FirstLowInvalidHeapAttributeNumber);
+			}
+		}
+		i++;
+	}
+
+	/* Collect RTE indexes of relations appearing in the FROM clause */
+	rels_in_from = get_relids_in_jointree((Node *) query->jointree, false, false);
+
+	/*
+	 * Check if all key attributes of relations in FROM are appearing in the target
+	 * list.  If an attribute remains in key_attnos_list in spite of the table is used
+	 * in FROM clause, the target is missing this key attribute, so we return NULL.
+	 */
+	i = 1;
+	foreach(lc, key_attnos_list)
+	{
+		Bitmapset *bms = (Bitmapset *)lfirst(lc);
+		if (!bms_is_empty(bms) && bms_is_member(i, rels_in_from))
+			return NULL;
+		i++;
+	}
+
+	return keys;
+}
diff --git a/src/backend/commands/matview.c b/src/backend/commands/matview.c
index 59920ced83..a821992a37 100644
--- a/src/backend/commands/matview.c
+++ b/src/backend/commands/matview.c
@@ -25,26 +25,37 @@
 #include "catalog/indexing.h"
 #include "catalog/namespace.h"
 #include "catalog/pg_am.h"
+#include "catalog/pg_depend.h"
+#include "catalog/pg_trigger.h"
 #include "catalog/pg_opclass.h"
 #include "catalog/pg_operator.h"
 #include "commands/cluster.h"
 #include "commands/matview.h"
 #include "commands/tablecmds.h"
 #include "commands/tablespace.h"
+#include "commands/createas.h"
 #include "executor/executor.h"
 #include "executor/spi.h"
+#include "executor/tstoreReceiver.h"
 #include "miscadmin.h"
+#include "nodes/makefuncs.h"
+#include "parser/analyze.h"
+#include "parser/parse_clause.h"
+#include "parser/parse_func.h"
 #include "parser/parse_relation.h"
 #include "pgstat.h"
 #include "rewrite/rewriteHandler.h"
+#include "rewrite/rowsecurity.h"
 #include "storage/lmgr.h"
 #include "storage/smgr.h"
 #include "tcop/tcopprot.h"
 #include "utils/builtins.h"
+#include "utils/fmgroids.h"
 #include "utils/lsyscache.h"
 #include "utils/rel.h"
 #include "utils/snapmgr.h"
 #include "utils/syscache.h"
+#include "utils/typcache.h"
 
 
 typedef struct
@@ -58,6 +69,52 @@ typedef struct
 	BulkInsertState bistate;	/* bulk insert state */
 } DR_transientrel;
 
+#define MV_INIT_QUERYHASHSIZE	16
+
+/*
+ * MV_TriggerHashEntry
+ *
+ * Hash entry for base tables on which IVM trigger is invoked
+ */
+typedef struct MV_TriggerHashEntry
+{
+	Oid	matview_id;			/* OID of the materialized view */
+	int	before_trig_count;	/* count of before triggers invoked */
+	int	after_trig_count;	/* count of after triggers invoked */
+
+	Snapshot	snapshot;	/* Snapshot just before table change */
+
+	List   *tables;		/* List of MV_TriggerTable */
+	bool	has_old;	/* tuples are deleted from any table? */
+	bool	has_new;	/* tuples are inserted into any table? */
+} MV_TriggerHashEntry;
+
+/*
+ * MV_TriggerTable
+ *
+ * IVM related data for tables on which the trigger is invoked.
+ */
+typedef struct MV_TriggerTable
+{
+	Oid		table_id;			/* OID of the modified table */
+	List   *old_tuplestores;	/* tuplestores for deleted tuples */
+	List   *new_tuplestores;	/* tuplestores for inserted tuples */
+
+	List   *rte_indexes;		/* List of RTE index of the modified table */
+	RangeTblEntry *original_rte;	/* the original RTE saved before rewriting query */
+
+	Relation	rel;			/* relation of the modified table */
+	TupleTableSlot *slot;		/* for checking visibility in the pre-state table */
+} MV_TriggerTable;
+
+static HTAB *mv_trigger_info = NULL;
+
+static bool in_delta_calculation = false;
+
+/* ENR name for materialized view delta */
+#define NEW_DELTA_ENRNAME "new_delta"
+#define OLD_DELTA_ENRNAME "old_delta"
+
 static int	matview_maintenance_depth = 0;
 
 static void transientrel_startup(DestReceiver *self, int operation, TupleDesc typeinfo);
@@ -65,7 +122,9 @@ static bool transientrel_receive(TupleTableSlot *slot, DestReceiver *self);
 static void transientrel_shutdown(DestReceiver *self);
 static void transientrel_destroy(DestReceiver *self);
 static uint64 refresh_matview_datafill(DestReceiver *dest, Query *query,
-									   const char *queryString);
+						 QueryEnvironment *queryEnv,
+						 TupleDesc *resultTupleDesc,
+						 const char *queryString);
 static char *make_temptable_name_n(char *tempname, int n);
 static void refresh_by_match_merge(Oid matviewOid, Oid tempOid, Oid relowner,
 								   int save_sec_context);
@@ -73,6 +132,37 @@ static void refresh_by_heap_swap(Oid matviewOid, Oid OIDNewHeap, char relpersist
 static bool is_usable_unique_index(Relation indexRel);
 static void OpenMatViewIncrementalMaintenance(void);
 static void CloseMatViewIncrementalMaintenance(void);
+static Query *get_matview_query(Relation matviewRel);
+
+static Query *rewrite_query_for_preupdate_state(Query *query, List *tables,
+								  ParseState *pstate, Oid matviewid);
+static void register_delta_ENRs(ParseState *pstate, Query *query, List *tables);
+static char *make_delta_enr_name(const char *prefix, Oid relid, int count);
+static RangeTblEntry *get_prestate_rte(RangeTblEntry *rte, MV_TriggerTable *table,
+				 QueryEnvironment *queryEnv, Oid matviewid);
+static RangeTblEntry *replace_rte_with_delta(RangeTblEntry *rte, MV_TriggerTable *table, bool is_new,
+		   QueryEnvironment *queryEnv);
+static Query *rewrite_query_for_counting(Query *query, ParseState *pstate);
+
+static void calc_delta(MV_TriggerTable *table, int rte_index, Query *query,
+			DestReceiver *dest_old, DestReceiver *dest_new,
+			TupleDesc *tupdesc_old, TupleDesc *tupdesc_new,
+			QueryEnvironment *queryEnv);
+static Query *rewrite_query_for_postupdate_state(Query *query, MV_TriggerTable *table, int rte_index);
+
+static void apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *new_tuplestores,
+			TupleDesc tupdesc_old, TupleDesc tupdesc_new,
+			Query *query);
+static void apply_old_delta(const char *matviewname, const char *deltaname_old,
+				List *keys);
+static void apply_new_delta(const char *matviewname, const char *deltaname_new,
+				StringInfo target_list);
+static char *get_matching_condition_string(List *keys);
+static void generate_equal(StringInfo querybuf, Oid opttype,
+			   const char *leftop, const char *rightop);
+
+static void mv_InitHashTables(void);
+static void clean_up_IVM_hash_entry(MV_TriggerHashEntry *entry, bool is_abort);
 
 /*
  * SetMatViewPopulatedState
@@ -114,6 +204,46 @@ SetMatViewPopulatedState(Relation relation, bool newstate)
 	CommandCounterIncrement();
 }
 
+/*
+ * SetMatViewIVMState
+ *		Mark a materialized view as IVM, or not.
+ *
+ * NOTE: caller must be holding an appropriate lock on the relation.
+ */
+void
+SetMatViewIVMState(Relation relation, bool newstate)
+{
+	Relation	pgrel;
+	HeapTuple	tuple;
+
+	Assert(relation->rd_rel->relkind == RELKIND_MATVIEW);
+
+	/*
+	 * Update relation's pg_class entry.  Crucial side-effect: other backends
+	 * (and this one too!) are sent SI message to make them rebuild relcache
+	 * entries.
+	 */
+	pgrel = table_open(RelationRelationId, RowExclusiveLock);
+	tuple = SearchSysCacheCopy1(RELOID,
+								ObjectIdGetDatum(RelationGetRelid(relation)));
+	if (!HeapTupleIsValid(tuple))
+		elog(ERROR, "cache lookup failed for relation %u",
+			 RelationGetRelid(relation));
+
+	((Form_pg_class) GETSTRUCT(tuple))->relisivm = newstate;
+
+	CatalogTupleUpdate(pgrel, &tuple->t_self, tuple);
+
+	heap_freetuple(tuple);
+	table_close(pgrel, RowExclusiveLock);
+
+	/*
+	 * Advance command counter to make the updated pg_class row locally
+	 * visible.
+	 */
+	CommandCounterIncrement();
+}
+
 /*
  * ExecRefreshMatView -- execute a REFRESH MATERIALIZED VIEW command
  *
@@ -140,8 +270,6 @@ ExecRefreshMatView(RefreshMatViewStmt *stmt, const char *queryString,
 {
 	Oid			matviewOid;
 	Relation	matviewRel;
-	RewriteRule *rule;
-	List	   *actions;
 	Query	   *dataQuery;
 	Oid			tableSpace;
 	Oid			relowner;
@@ -155,6 +283,7 @@ ExecRefreshMatView(RefreshMatViewStmt *stmt, const char *queryString,
 	int			save_sec_context;
 	int			save_nestlevel;
 	ObjectAddress address;
+	bool oldPopulated;
 
 	/* Determine strength of lock needed. */
 	concurrent = stmt->concurrent;
@@ -178,6 +307,7 @@ ExecRefreshMatView(RefreshMatViewStmt *stmt, const char *queryString,
 	SetUserIdAndSecContext(relowner,
 						   save_sec_context | SECURITY_RESTRICTED_OPERATION);
 	save_nestlevel = NewGUCNestLevel();
+	oldPopulated = RelationIsPopulated(matviewRel);
 
 	/* Make sure it is a materialized view. */
 	if (matviewRel->rd_rel->relkind != RELKIND_MATVIEW)
@@ -199,32 +329,9 @@ ExecRefreshMatView(RefreshMatViewStmt *stmt, const char *queryString,
 				 errmsg("%s and %s options cannot be used together",
 						"CONCURRENTLY", "WITH NO DATA")));
 
-	/*
-	 * Check that everything is correct for a refresh. Problems at this point
-	 * are internal errors, so elog is sufficient.
-	 */
-	if (matviewRel->rd_rel->relhasrules == false ||
-		matviewRel->rd_rules->numLocks < 1)
-		elog(ERROR,
-			 "materialized view \"%s\" is missing rewrite information",
-			 RelationGetRelationName(matviewRel));
-
-	if (matviewRel->rd_rules->numLocks > 1)
-		elog(ERROR,
-			 "materialized view \"%s\" has too many rules",
-			 RelationGetRelationName(matviewRel));
 
-	rule = matviewRel->rd_rules->rules[0];
-	if (rule->event != CMD_SELECT || !(rule->isInstead))
-		elog(ERROR,
-			 "the rule for materialized view \"%s\" is not a SELECT INSTEAD OF rule",
-			 RelationGetRelationName(matviewRel));
+	dataQuery = get_matview_query(matviewRel);
 
-	actions = rule->actions;
-	if (list_length(actions) != 1)
-		elog(ERROR,
-			 "the rule for materialized view \"%s\" is not a single action",
-			 RelationGetRelationName(matviewRel));
 
 	/*
 	 * Check that there is a unique index with no WHERE clause on one or more
@@ -259,12 +366,6 @@ ExecRefreshMatView(RefreshMatViewStmt *stmt, const char *queryString,
 					 errhint("Create a unique index with no WHERE clause on one or more columns of the materialized view.")));
 	}
 
-	/*
-	 * The stored query was rewritten at the time of the MV definition, but
-	 * has not been scribbled on by the planner.
-	 */
-	dataQuery = linitial_node(Query, actions);
-
 	/*
 	 * Check for active uses of the relation in the current transaction, such
 	 * as open scans.
@@ -292,6 +393,74 @@ ExecRefreshMatView(RefreshMatViewStmt *stmt, const char *queryString,
 		relpersistence = matviewRel->rd_rel->relpersistence;
 	}
 
+	/* delete IMMV triggers. */
+	if (RelationIsIVM(matviewRel) && stmt->skipData )
+	{
+		Relation	tgRel;
+		Relation	depRel;
+		ScanKeyData key;
+		SysScanDesc scan;
+		HeapTuple	tup;
+		ObjectAddresses *immv_triggers;
+
+		immv_triggers = new_object_addresses();
+
+		tgRel = table_open(TriggerRelationId, RowExclusiveLock);
+		depRel = table_open(DependRelationId, RowExclusiveLock);
+
+		/* search triggers that depends on IMMV. */
+		ScanKeyInit(&key,
+					Anum_pg_depend_refobjid,
+					BTEqualStrategyNumber, F_OIDEQ,
+					ObjectIdGetDatum(matviewOid));
+		scan = systable_beginscan(depRel, DependReferenceIndexId, true,
+								  NULL, 1, &key);
+		while ((tup = systable_getnext(scan)) != NULL)
+		{
+			ObjectAddress obj;
+			Form_pg_depend foundDep = (Form_pg_depend) GETSTRUCT(tup);
+
+			if (foundDep->classid == TriggerRelationId)
+			{
+				HeapTuple	tgtup;
+				ScanKeyData tgkey[1];
+				SysScanDesc tgscan;
+				Form_pg_trigger tgform;
+
+				/* Find the trigger name. */
+				ScanKeyInit(&tgkey[0],
+							Anum_pg_trigger_oid,
+							BTEqualStrategyNumber, F_OIDEQ,
+							ObjectIdGetDatum(foundDep->objid));
+
+				tgscan = systable_beginscan(tgRel, TriggerOidIndexId, true,
+											NULL, 1, tgkey);
+				tgtup = systable_getnext(tgscan);
+				if (!HeapTupleIsValid(tgtup))
+					elog(ERROR, "could not find tuple for immv trigger %u", foundDep->objid);
+
+				tgform = (Form_pg_trigger) GETSTRUCT(tgtup);
+
+				/* If trigger is created by IMMV, delete it. */
+				if (strncmp(NameStr(tgform->tgname), "IVM_trigger_", 12) == 0)
+				{
+					obj.classId = foundDep->classid;
+					obj.objectId = foundDep->objid;
+					obj.objectSubId = foundDep->refobjsubid;
+					add_exact_object_address(&obj, immv_triggers);
+				}
+				systable_endscan(tgscan);
+			}
+		}
+		systable_endscan(scan);
+
+		performMultipleDeletions(immv_triggers, DROP_RESTRICT, PERFORM_DELETION_INTERNAL);
+
+		table_close(depRel, RowExclusiveLock);
+		table_close(tgRel, RowExclusiveLock);
+		free_object_addresses(immv_triggers);
+	}
+
 	/*
 	 * Create the transient table that will receive the regenerated data. Lock
 	 * it against access by any other process until commit (by which time it
@@ -305,7 +474,7 @@ ExecRefreshMatView(RefreshMatViewStmt *stmt, const char *queryString,
 
 	/* Generate the data, if wanted. */
 	if (!stmt->skipData)
-		processed = refresh_matview_datafill(dest, dataQuery, queryString);
+		processed = refresh_matview_datafill(dest, dataQuery, NULL, NULL, queryString);
 
 	/* Make the matview match the newly generated data. */
 	if (concurrent)
@@ -340,6 +509,12 @@ ExecRefreshMatView(RefreshMatViewStmt *stmt, const char *queryString,
 			pgstat_count_heap_insert(matviewRel, processed);
 	}
 
+	if (!stmt->skipData && RelationIsIVM(matviewRel) && !oldPopulated)
+	{
+		CreateIndexOnIMMV(dataQuery, matviewRel);
+		CreateIvmTriggersOnBaseTables(dataQuery, matviewOid);
+	}
+
 	table_close(matviewRel, NoLock);
 
 	/* Roll back any GUC changes */
@@ -374,6 +549,8 @@ ExecRefreshMatView(RefreshMatViewStmt *stmt, const char *queryString,
  */
 static uint64
 refresh_matview_datafill(DestReceiver *dest, Query *query,
+						 QueryEnvironment *queryEnv,
+						 TupleDesc *resultTupleDesc,
 						 const char *queryString)
 {
 	List	   *rewritten;
@@ -410,7 +587,7 @@ refresh_matview_datafill(DestReceiver *dest, Query *query,
 	/* Create a QueryDesc, redirecting output to our tuple receiver */
 	queryDesc = CreateQueryDesc(plan, queryString,
 								GetActiveSnapshot(), InvalidSnapshot,
-								dest, NULL, NULL, 0);
+								dest, NULL, queryEnv ? queryEnv: NULL, 0);
 
 	/* call ExecutorStart to prepare the plan for execution */
 	ExecutorStart(queryDesc, 0);
@@ -420,6 +597,9 @@ refresh_matview_datafill(DestReceiver *dest, Query *query,
 
 	processed = queryDesc->estate->es_processed;
 
+	if (resultTupleDesc)
+		*resultTupleDesc = CreateTupleDescCopy(queryDesc->tupDesc);
+
 	/* and clean up */
 	ExecutorFinish(queryDesc);
 	ExecutorEnd(queryDesc);
@@ -953,3 +1133,1219 @@ CloseMatViewIncrementalMaintenance(void)
 	matview_maintenance_depth--;
 	Assert(matview_maintenance_depth >= 0);
 }
+
+/*
+ * get_matview_query - get the Query from a matview's _RETURN rule.
+ */
+static Query *
+get_matview_query(Relation matviewRel)
+{
+	RewriteRule *rule;
+	List * actions;
+
+	/*
+	 * Check that everything is correct for a refresh. Problems at this point
+	 * are internal errors, so elog is sufficient.
+	 */
+	if (matviewRel->rd_rel->relhasrules == false ||
+		matviewRel->rd_rules->numLocks < 1)
+		elog(ERROR,
+			 "materialized view \"%s\" is missing rewrite information",
+			 RelationGetRelationName(matviewRel));
+
+	if (matviewRel->rd_rules->numLocks > 1)
+		elog(ERROR,
+			 "materialized view \"%s\" has too many rules",
+			 RelationGetRelationName(matviewRel));
+
+	rule = matviewRel->rd_rules->rules[0];
+	if (rule->event != CMD_SELECT || !(rule->isInstead))
+		elog(ERROR,
+			 "the rule for materialized view \"%s\" is not a SELECT INSTEAD OF rule",
+			 RelationGetRelationName(matviewRel));
+
+	actions = rule->actions;
+	if (list_length(actions) != 1)
+		elog(ERROR,
+			 "the rule for materialized view \"%s\" is not a single action",
+			 RelationGetRelationName(matviewRel));
+
+	/*
+	 * The stored query was rewritten at the time of the MV definition, but
+	 * has not been scribbled on by the planner.
+	 */
+	return linitial_node(Query, actions);
+}
+
+
+/* ----------------------------------------------------
+ *		Incremental View Maintenance routines
+ * ---------------------------------------------------
+ */
+
+/*
+ * IVM_immediate_before
+ *
+ * IVM trigger function invoked before base table is modified. If this is
+ * invoked firstly in the same statement, we save the transaction id and the
+ * command id at that time.
+ */
+Datum
+IVM_immediate_before(PG_FUNCTION_ARGS)
+{
+	TriggerData *trigdata = (TriggerData *) fcinfo->context;
+	char	   *matviewOid_text = trigdata->tg_trigger->tgargs[0];
+	char	   *ex_lock_text = trigdata->tg_trigger->tgargs[1];
+	Oid			matviewOid;
+	MV_TriggerHashEntry *entry;
+	bool	found;
+	bool	ex_lock;
+
+	matviewOid = DatumGetObjectId(DirectFunctionCall1(oidin, CStringGetDatum(matviewOid_text)));
+	ex_lock = DatumGetBool(DirectFunctionCall1(boolin, CStringGetDatum(ex_lock_text)));
+
+	/* If the view has more than one tables, we have to use an exclusive lock. */
+	if (ex_lock)
+	{
+		/*
+		 * Wait for concurrent transactions which update this materialized view at
+		 * READ COMMITED. This is needed to see changes committed in other
+		 * transactions. No wait and raise an error at REPEATABLE READ or
+		 * SERIALIZABLE to prevent update anomalies of matviews.
+		 * XXX: dead-lock is possible here.
+		 */
+		if (!IsolationUsesXactSnapshot())
+			LockRelationOid(matviewOid, ExclusiveLock);
+		else if (!ConditionalLockRelationOid(matviewOid, ExclusiveLock))
+		{
+			/* try to throw error by name; relation could be deleted... */
+			char	   *relname = get_rel_name(matviewOid);
+
+			if (!relname)
+				ereport(ERROR,
+						(errcode(ERRCODE_LOCK_NOT_AVAILABLE),
+						errmsg("could not obtain lock on materialized view during incremental maintenance")));
+
+			ereport(ERROR,
+					(errcode(ERRCODE_LOCK_NOT_AVAILABLE),
+					errmsg("could not obtain lock on materialized view \"%s\" during incremental maintenance",
+							relname)));
+		}
+	}
+	else
+		LockRelationOid(matviewOid, RowExclusiveLock);
+
+	/*
+	 * On the first call initialize the hashtable
+	 */
+	if (!mv_trigger_info)
+		mv_InitHashTables();
+
+	entry = (MV_TriggerHashEntry *) hash_search(mv_trigger_info,
+											  (void *) &matviewOid,
+											  HASH_ENTER, &found);
+
+	/* On the first BEFORE to update the view, initialize trigger data */
+	if (!found)
+	{
+		/*
+		 * Get a snapshot just before the table was modified for checking
+		 * tuple visibility in the pre-update state of the table.
+		 */
+		Snapshot snapshot = GetActiveSnapshot();
+
+		entry->matview_id = matviewOid;
+		entry->before_trig_count = 0;
+		entry->after_trig_count = 0;
+		entry->snapshot = RegisterSnapshot(snapshot);
+		entry->tables = NIL;
+		entry->has_old = false;
+		entry->has_new = false;
+	}
+
+	entry->before_trig_count++;
+
+	return PointerGetDatum(NULL);
+}
+
+/*
+ * IVM_immediate_maintenance
+ *
+ * IVM trigger function invoked after base table is modified.
+ * For each table, tuplestores of transition tables are collected.
+ * and after the last modification
+ */
+Datum
+IVM_immediate_maintenance(PG_FUNCTION_ARGS)
+{
+	TriggerData *trigdata = (TriggerData *) fcinfo->context;
+	Relation	rel;
+	Oid			relid;
+	Oid			matviewOid;
+	Query	   *query;
+	Query	   *rewritten = NULL;
+	char	   *matviewOid_text = trigdata->tg_trigger->tgargs[0];
+	Relation	matviewRel;
+	int old_depth = matview_maintenance_depth;
+
+	Oid			relowner;
+	Tuplestorestate *old_tuplestore = NULL;
+	Tuplestorestate *new_tuplestore = NULL;
+	DestReceiver *dest_new = NULL, *dest_old = NULL;
+	Oid			save_userid;
+	int			save_sec_context;
+	int			save_nestlevel;
+
+	MV_TriggerHashEntry *entry;
+	MV_TriggerTable		*table;
+	bool	found;
+
+	ParseState		 *pstate;
+	QueryEnvironment *queryEnv = create_queryEnv();
+	MemoryContext	oldcxt;
+	ListCell   *lc;
+	int			i;
+
+
+	/* Create a ParseState for rewriting the view definition query */
+	pstate = make_parsestate(NULL);
+	pstate->p_queryEnv = queryEnv;
+	pstate->p_expr_kind = EXPR_KIND_SELECT_TARGET;
+
+	rel = trigdata->tg_relation;
+	relid = rel->rd_id;
+
+	matviewOid = DatumGetObjectId(DirectFunctionCall1(oidin, CStringGetDatum(matviewOid_text)));
+
+	/*
+	 * On the first call initialize the hashtable
+	 */
+	if (!mv_trigger_info)
+		mv_InitHashTables();
+
+	/* get the entry for this materialized view */
+	entry = (MV_TriggerHashEntry *) hash_search(mv_trigger_info,
+											  (void *) &matviewOid,
+											  HASH_FIND, &found);
+	Assert (found && entry != NULL);
+	entry->after_trig_count++;
+
+	/* search the entry for the modified table and create new entry if not found */
+	found = false;
+	foreach(lc, entry->tables)
+	{
+		table = (MV_TriggerTable *) lfirst(lc);
+		if (table->table_id == relid)
+		{
+			found = true;
+			break;
+		}
+	}
+	if (!found)
+	{
+		oldcxt = MemoryContextSwitchTo(TopTransactionContext);
+
+		table = (MV_TriggerTable *) palloc0(sizeof(MV_TriggerTable));
+		table->table_id = relid;
+		table->old_tuplestores = NIL;
+		table->new_tuplestores = NIL;
+		table->rte_indexes = NIL;
+		table->slot = MakeSingleTupleTableSlot(RelationGetDescr(rel), table_slot_callbacks(rel));
+		table->rel = table_open(RelationGetRelid(rel), NoLock);
+		entry->tables = lappend(entry->tables, table);
+
+		MemoryContextSwitchTo(oldcxt);
+	}
+
+	/* Save the transition tables and make a request to not free immediately */
+	if (trigdata->tg_oldtable)
+	{
+		oldcxt = MemoryContextSwitchTo(TopTransactionContext);
+		table->old_tuplestores = lappend(table->old_tuplestores, trigdata->tg_oldtable);
+		entry->has_old = true;
+		MemoryContextSwitchTo(oldcxt);
+	}
+	if (trigdata->tg_newtable)
+	{
+		oldcxt = MemoryContextSwitchTo(TopTransactionContext);
+		table->new_tuplestores = lappend(table->new_tuplestores, trigdata->tg_newtable);
+		entry->has_new = true;
+		MemoryContextSwitchTo(oldcxt);
+	}
+	if (entry->has_new || entry->has_old)
+	{
+		CmdType cmd;
+
+		if (TRIGGER_FIRED_BY_INSERT(trigdata->tg_event))
+			cmd = CMD_INSERT;
+		else if (TRIGGER_FIRED_BY_DELETE(trigdata->tg_event))
+			cmd = CMD_DELETE;
+		else if (TRIGGER_FIRED_BY_UPDATE(trigdata->tg_event))
+			cmd = CMD_UPDATE;
+		else
+			elog(ERROR,"unsupported trigger type");
+
+		/* Prolong lifespan of transition tables to the end of the last AFTER trigger */
+		SetTransitionTablePreserved(relid, cmd);
+	}
+
+
+	/* If this is not the last AFTER trigger call, immediately exit. */
+	Assert (entry->before_trig_count >= entry->after_trig_count);
+	if (entry->before_trig_count != entry->after_trig_count)
+		return PointerGetDatum(NULL);
+
+	/*
+	 * If this is the last AFTER trigger call, continue and update the view.
+	 */
+
+	/*
+	 * Advance command counter to make the updated base table row locally
+	 * visible.
+	 */
+	CommandCounterIncrement();
+
+	matviewRel = table_open(matviewOid, NoLock);
+
+	/* Make sure it is a materialized view. */
+	Assert(matviewRel->rd_rel->relkind == RELKIND_MATVIEW);
+
+	/*
+	 * Get and push the latast snapshot to see any changes which is committed
+	 * during waiting in other transactions at READ COMMITTED level.
+	 */
+	PushActiveSnapshot(GetTransactionSnapshot());
+
+	/*
+	 * Check for active uses of the relation in the current transaction, such
+	 * as open scans.
+	 *
+	 * NB: We count on this to protect us against problems with refreshing the
+	 * data using TABLE_INSERT_FROZEN.
+	 */
+	CheckTableNotInUse(matviewRel, "refresh a materialized view incrementally");
+
+	/*
+	 * Switch to the owner's userid, so that any functions are run as that
+	 * user.  Also arrange to make GUC variable changes local to this command.
+	 * We will switch modes when we are about to execute user code.
+	 */
+	relowner = matviewRel->rd_rel->relowner;
+	GetUserIdAndSecContext(&save_userid, &save_sec_context);
+	SetUserIdAndSecContext(relowner,
+						   save_sec_context | SECURITY_RESTRICTED_OPERATION);
+	save_nestlevel = NewGUCNestLevel();
+
+	/* get view query*/
+	query = get_matview_query(matviewRel);
+
+	/*
+	 * When a base table is truncated, the view content will be empty if the
+	 * view definition query does not contain an aggregate without a GROUP clause.
+	 * Therefore, such views can be truncated.
+	 */
+	if (TRIGGER_FIRED_BY_TRUNCATE(trigdata->tg_event))
+	{
+		ExecuteTruncateGuts(list_make1(matviewRel), list_make1_oid(matviewOid),
+							NIL, DROP_RESTRICT, false, false);
+
+		/* Clean up hash entry and delete tuplestores */
+		clean_up_IVM_hash_entry(entry, false);
+
+		/* Pop the original snapshot. */
+		PopActiveSnapshot();
+
+		table_close(matviewRel, NoLock);
+
+		/* Roll back any GUC changes */
+		AtEOXact_GUC(false, save_nestlevel);
+
+		/* Restore userid and security context */
+		SetUserIdAndSecContext(save_userid, save_sec_context);
+
+		return PointerGetDatum(NULL);
+	}
+
+	/*
+	 * rewrite query for calculating deltas
+	 */
+
+	rewritten = copyObject(query);
+
+	/* Replace resnames in a target list with materialized view's attnames */
+	i = 0;
+	foreach (lc, rewritten->targetList)
+	{
+		TargetEntry *tle = (TargetEntry *) lfirst(lc);
+		Form_pg_attribute attr = TupleDescAttr(matviewRel->rd_att, i);
+		char *resname = NameStr(attr->attname);
+
+		tle->resname = pstrdup(resname);
+		i++;
+	}
+
+	/* Set all tables in the query to pre-update state */
+	rewritten = rewrite_query_for_preupdate_state(rewritten, entry->tables,
+												  pstate, matviewOid);
+	/* Rewrite for counting duplicated tuples */
+	rewritten = rewrite_query_for_counting(rewritten, pstate);
+
+	/* Create tuplestores to store view deltas */
+	if (entry->has_old)
+	{
+		oldcxt = MemoryContextSwitchTo(TopTransactionContext);
+
+		old_tuplestore = tuplestore_begin_heap(false, false, work_mem);
+		dest_old = CreateDestReceiver(DestTuplestore);
+		SetTuplestoreDestReceiverParams(dest_old,
+									old_tuplestore,
+									TopTransactionContext,
+									false,
+									NULL,
+									NULL);
+
+		MemoryContextSwitchTo(oldcxt);
+	}
+	if (entry->has_new)
+	{
+		oldcxt = MemoryContextSwitchTo(TopTransactionContext);
+
+		new_tuplestore = tuplestore_begin_heap(false, false, work_mem);
+		dest_new = CreateDestReceiver(DestTuplestore);
+		SetTuplestoreDestReceiverParams(dest_new,
+									new_tuplestore,
+									TopTransactionContext,
+									false,
+									NULL,
+									NULL);
+		MemoryContextSwitchTo(oldcxt);
+	}
+
+	/* for all modified tables */
+	foreach(lc, entry->tables)
+	{
+		ListCell *lc2;
+
+		table = (MV_TriggerTable *) lfirst(lc);
+
+		/* loop for self-join */
+		foreach(lc2, table->rte_indexes)
+		{
+			int	rte_index = lfirst_int(lc2);
+			TupleDesc		tupdesc_old;
+			TupleDesc		tupdesc_new;
+
+			/* calculate delta tables */
+			calc_delta(table, rte_index, rewritten, dest_old, dest_new,
+					   &tupdesc_old, &tupdesc_new, queryEnv);
+
+			/* Set the table in the query to post-update state */
+			rewritten = rewrite_query_for_postupdate_state(rewritten, table, rte_index);
+
+			PG_TRY();
+			{
+				/* apply the delta tables to the materialized view */
+				apply_delta(matviewOid, old_tuplestore, new_tuplestore,
+							tupdesc_old, tupdesc_new, query);
+			}
+			PG_CATCH();
+			{
+				matview_maintenance_depth = old_depth;
+				PG_RE_THROW();
+			}
+			PG_END_TRY();
+
+			/* clear view delta tuplestores */
+			if (old_tuplestore)
+				tuplestore_clear(old_tuplestore);
+			if (new_tuplestore)
+				tuplestore_clear(new_tuplestore);
+		}
+	}
+
+	/* Clean up hash entry and delete tuplestores */
+	clean_up_IVM_hash_entry(entry, false);
+	if (old_tuplestore)
+	{
+		dest_old->rDestroy(dest_old);
+		tuplestore_end(old_tuplestore);
+	}
+	if (new_tuplestore)
+	{
+		dest_new->rDestroy(dest_new);
+		tuplestore_end(new_tuplestore);
+	}
+
+	/* Pop the original snapshot. */
+	PopActiveSnapshot();
+
+	table_close(matviewRel, NoLock);
+
+	/* Roll back any GUC changes */
+	AtEOXact_GUC(false, save_nestlevel);
+
+	/* Restore userid and security context */
+	SetUserIdAndSecContext(save_userid, save_sec_context);
+
+	return PointerGetDatum(NULL);
+}
+
+/*
+ * rewrite_query_for_preupdate_state
+ *
+ * Rewrite the query so that base tables' RTEs will represent "pre-update"
+ * state of tables. This is necessary to calculate view delta after multiple
+ * tables are modified.
+ */
+static Query*
+rewrite_query_for_preupdate_state(Query *query, List *tables,
+								  ParseState *pstate, Oid matviewid)
+{
+	ListCell *lc;
+	int num_rte = list_length(query->rtable);
+	int i;
+
+
+	/* register delta ENRs */
+	register_delta_ENRs(pstate, query, tables);
+
+	/* XXX: Is necessary? Is this right timing? */
+	AcquireRewriteLocks(query, true, false);
+
+	i = 1;
+	foreach(lc, query->rtable)
+	{
+		RangeTblEntry *r = (RangeTblEntry*) lfirst(lc);
+
+		ListCell *lc2;
+		foreach(lc2, tables)
+		{
+			MV_TriggerTable *table = (MV_TriggerTable *) lfirst(lc2);
+			/*
+			 * if the modified table is found then replace the original RTE with
+			 * "pre-state" RTE and append its index to the list.
+			 */
+			if (r->relid == table->table_id)
+			{
+				List *securityQuals;
+				List *withCheckOptions;
+				bool  hasRowSecurity;
+				bool  hasSubLinks;
+
+				RangeTblEntry *rte_pre = get_prestate_rte(r, table, pstate->p_queryEnv, matviewid);
+
+				/*
+				 * Set a row security poslicies of the modified table to the subquery RTE which
+				 * represents the pre-update state of the table.
+				 */
+				get_row_security_policies(query, table->original_rte, i,
+										  &securityQuals, &withCheckOptions,
+										  &hasRowSecurity, &hasSubLinks);
+
+				if (hasRowSecurity)
+				{
+					query->hasRowSecurity = true;
+					rte_pre->security_barrier = true;
+				}
+				if (hasSubLinks)
+					query->hasSubLinks = true;
+
+				rte_pre->securityQuals = securityQuals;
+				lfirst(lc) = rte_pre;
+
+				table->rte_indexes = lappend_int(table->rte_indexes, i);
+				break;
+			}
+		}
+
+		/* finish the loop if we processed all RTE included in the original query */
+		if (i++ >= num_rte)
+			break;
+	}
+
+	return query;
+}
+
+/*
+ * register_delta_ENRs
+ *
+ * For all modified tables, make ENRs for their transition tables
+ * and register them to the queryEnv. ENR's RTEs are also appended
+ * into the list in query tree.
+ */
+static void
+register_delta_ENRs(ParseState *pstate, Query *query, List *tables)
+{
+	QueryEnvironment *queryEnv = pstate->p_queryEnv;
+	ListCell *lc;
+	RangeTblEntry	*rte;
+
+	foreach(lc, tables)
+	{
+		MV_TriggerTable *table = (MV_TriggerTable *) lfirst(lc);
+		ListCell *lc2;
+		int count;
+
+		count = 0;
+		foreach(lc2, table->old_tuplestores)
+		{
+			Tuplestorestate *oldtable = (Tuplestorestate *) lfirst(lc2);
+			EphemeralNamedRelation enr =
+				palloc(sizeof(EphemeralNamedRelationData));
+			ParseNamespaceItem *nsitem;
+
+			enr->md.name = make_delta_enr_name("old", table->table_id, count);
+			enr->md.reliddesc = table->table_id;
+			enr->md.tupdesc = NULL;
+			enr->md.enrtype = ENR_NAMED_TUPLESTORE;
+			enr->md.enrtuples = tuplestore_tuple_count(oldtable);
+			enr->reldata = oldtable;
+			register_ENR(queryEnv, enr);
+
+			nsitem = addRangeTableEntryForENR(pstate, makeRangeVar(NULL, enr->md.name, -1), true);
+			rte = nsitem->p_rte;
+
+			query->rtable = lappend(query->rtable, rte);
+
+			count++;
+		}
+
+		count = 0;
+		foreach(lc2, table->new_tuplestores)
+		{
+			Tuplestorestate *newtable = (Tuplestorestate *) lfirst(lc2);
+			EphemeralNamedRelation enr =
+				palloc(sizeof(EphemeralNamedRelationData));
+			ParseNamespaceItem *nsitem;
+
+			enr->md.name = make_delta_enr_name("new", table->table_id, count);
+			enr->md.reliddesc = table->table_id;
+			enr->md.tupdesc = NULL;
+			enr->md.enrtype = ENR_NAMED_TUPLESTORE;
+			enr->md.enrtuples = tuplestore_tuple_count(newtable);
+			enr->reldata = newtable;
+			register_ENR(queryEnv, enr);
+
+			nsitem = addRangeTableEntryForENR(pstate, makeRangeVar(NULL, enr->md.name, -1), true);
+			rte = nsitem->p_rte;
+
+			query->rtable = lappend(query->rtable, rte);
+
+			count++;
+		}
+	}
+}
+
+#define DatumGetItemPointer(X)	 ((ItemPointer) DatumGetPointer(X))
+#define PG_GETARG_ITEMPOINTER(n) DatumGetItemPointer(PG_GETARG_DATUM(n))
+
+/*
+ * ivm_visible_in_prestate
+ *
+ * Check visibility of a tuple specified by the tableoid and item pointer
+ * using the snapshot taken just before the table was modified.
+ */
+Datum
+ivm_visible_in_prestate(PG_FUNCTION_ARGS)
+{
+	Oid			tableoid = PG_GETARG_OID(0);
+	ItemPointer itemPtr = PG_GETARG_ITEMPOINTER(1);
+	Oid			matviewOid = PG_GETARG_OID(2);
+	MV_TriggerHashEntry *entry;
+	MV_TriggerTable		*table = NULL;
+	ListCell   *lc;
+	bool	found;
+	bool	result;
+
+	if (!in_delta_calculation)
+		ereport(ERROR,
+				(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+				 errmsg("ivm_visible_in_prestate can be called only in delta calculation")));
+
+	entry = (MV_TriggerHashEntry *) hash_search(mv_trigger_info,
+											  (void *) &matviewOid,
+											  HASH_FIND, &found);
+	Assert (found && entry != NULL);
+
+	foreach(lc, entry->tables)
+	{
+		table = (MV_TriggerTable *) lfirst(lc);
+		if (table->table_id == tableoid)
+			break;
+	}
+
+	Assert (table != NULL);
+
+	result = table_tuple_fetch_row_version(table->rel, itemPtr, entry->snapshot, table->slot);
+
+	PG_RETURN_BOOL(result);
+}
+
+/*
+ * get_prestate_rte
+ *
+ * Rewrite RTE of the modified table to a subquery which represents
+ * "pre-state" table. The original RTE is saved in table->rte_original.
+ */
+static RangeTblEntry*
+get_prestate_rte(RangeTblEntry *rte, MV_TriggerTable *table,
+				 QueryEnvironment *queryEnv, Oid matviewid)
+{
+	StringInfoData str;
+	RawStmt *raw;
+	Query *subquery;
+	Relation rel;
+	ParseState *pstate;
+	char *relname;
+	int i;
+
+	pstate = make_parsestate(NULL);
+	pstate->p_queryEnv = queryEnv;
+	pstate->p_expr_kind = EXPR_KIND_SELECT_TARGET;
+
+	/*
+	 * We can use NoLock here since AcquireRewriteLocks should
+	 * have locked the relation already.
+	 */
+	rel = table_open(table->table_id, NoLock);
+	relname = quote_qualified_identifier(
+					get_namespace_name(RelationGetNamespace(rel)),
+									   RelationGetRelationName(rel));
+	table_close(rel, NoLock);
+
+	/*
+	 * Filtering inserted row using the snapshot taken before the table
+	 * is modified. ctid is required for maintaining outer join views.
+	 */
+	initStringInfo(&str);
+	appendStringInfo(&str,
+		"SELECT t.* FROM %s t"
+		" WHERE pg_catalog.ivm_visible_in_prestate(t.tableoid, t.ctid ,%d::pg_catalog.oid)",
+			relname, matviewid);
+
+	/*
+	 * Append deleted rows contained in old transition tables.
+	 */
+	for (i = 0; i < list_length(table->old_tuplestores); i++)
+	{
+		appendStringInfo(&str, " UNION ALL ");
+		appendStringInfo(&str," SELECT * FROM %s",
+			make_delta_enr_name("old", table->table_id, i));
+	}
+
+	/* Get a subquery representing pre-state of the table */
+	raw = (RawStmt*)linitial(raw_parser(str.data, RAW_PARSE_DEFAULT));
+	subquery = transformStmt(pstate, raw->stmt);
+
+	/* save the original RTE */
+	table->original_rte = copyObject(rte);
+
+	rte->rtekind = RTE_SUBQUERY;
+	rte->subquery = subquery;
+	rte->security_barrier = false;
+
+	/* Clear fields that should not be set in a subquery RTE */
+	rte->relid = InvalidOid;
+	rte->relkind = 0;
+	rte->rellockmode = 0;
+	rte->tablesample = NULL;
+	rte->perminfoindex = 0;         /* no permission checking for this RTE */
+	rte->inh = false;			/* must not be set for a subquery */
+
+	return rte;
+}
+
+/*
+ * make_delta_enr_name
+ *
+ * Make a name for ENR of a transition table from the base table's oid.
+ * prefix will be "new" or "old" depending on its transition table kind..
+ */
+static char*
+make_delta_enr_name(const char *prefix, Oid relid, int count)
+{
+	char buf[NAMEDATALEN];
+	char *name;
+
+	snprintf(buf, NAMEDATALEN, "__ivm_%s_%u_%u", prefix, relid, count);
+	name = pstrdup(buf);
+
+	return name;
+}
+
+/*
+ * replace_rte_with_delta
+ *
+ * Replace RTE of the modified table with a single table delta that combine its
+ * all transition tables.
+ */
+static RangeTblEntry*
+replace_rte_with_delta(RangeTblEntry *rte, MV_TriggerTable *table, bool is_new,
+					   QueryEnvironment *queryEnv)
+{
+	Oid relid = table->table_id;
+	StringInfoData str;
+	ParseState	*pstate;
+	RawStmt *raw;
+	Query *sub;
+	int		num_tuplestores = list_length(is_new ? table->new_tuplestores : table->old_tuplestores);
+	int		i;
+
+	/* the previous RTE must be a subquery which represents "pre-state" table */
+	Assert(rte->rtekind == RTE_SUBQUERY);
+
+	/* Create a ParseState for rewriting the view definition query */
+	pstate = make_parsestate(NULL);
+	pstate->p_queryEnv = queryEnv;
+	pstate->p_expr_kind = EXPR_KIND_SELECT_TARGET;
+
+	initStringInfo(&str);
+
+	for (i = 0; i < num_tuplestores; i++)
+	{
+		if (i > 0)
+			appendStringInfo(&str, " UNION ALL ");
+
+		appendStringInfo(&str,
+			" SELECT * FROM %s",
+			make_delta_enr_name(is_new ? "new" : "old", relid, i));
+	}
+
+	raw = (RawStmt*)linitial(raw_parser(str.data, RAW_PARSE_DEFAULT));
+	sub = transformStmt(pstate, raw->stmt);
+
+	/*
+	 * Update the subquery so that it represent the combined transition
+	 * table.  Note that we leave the security_barrier and securityQuals
+	 * fields so that the subquery relation can be protected by the RLS
+	 * policy as same as the modified table.
+	 */
+	rte->rtekind = RTE_SUBQUERY;
+	rte->subquery = sub;
+
+	return rte;
+}
+
+/*
+ * rewrite_query_for_counting
+ *
+ * Rewrite query for counting duplicated tuples.
+ */
+static Query *
+rewrite_query_for_counting(Query *query, ParseState *pstate)
+{
+	TargetEntry *tle_count;
+	FuncCall *fn;
+	Node *node;
+
+	/* Add count(*) for counting distinct tuples in views */
+	fn = makeFuncCall(SystemFuncName("count"), NIL, COERCE_EXPLICIT_CALL, -1);
+	fn->agg_star = true;
+	if (!query->groupClause && !query->hasAggs)
+		query->groupClause = transformDistinctClause(NULL, &query->targetList, query->sortClause, false);
+
+	node = ParseFuncOrColumn(pstate, fn->funcname, NIL, NULL, fn, false, -1);
+
+	tle_count = makeTargetEntry((Expr *) node,
+								list_length(query->targetList) + 1,
+								pstrdup("__ivm_count__"),
+								false);
+	query->targetList = lappend(query->targetList, tle_count);
+	query->hasAggs = true;
+
+	return query;
+}
+
+/*
+ * calc_delta
+ *
+ * Calculate view deltas generated under the modification of a table specified
+ * by the RTE index.
+ */
+static void
+calc_delta(MV_TriggerTable *table, int rte_index, Query *query,
+			DestReceiver *dest_old, DestReceiver *dest_new,
+			TupleDesc *tupdesc_old, TupleDesc *tupdesc_new,
+			QueryEnvironment *queryEnv)
+{
+	ListCell *lc = list_nth_cell(query->rtable, rte_index - 1);
+	RangeTblEntry *rte = (RangeTblEntry *) lfirst(lc);
+
+	in_delta_calculation = true;
+
+	/* Generate old delta */
+	if (list_length(table->old_tuplestores) > 0)
+	{
+		/* Replace the modified table with the old delta table and calculate the old view delta. */
+		replace_rte_with_delta(rte, table, false, queryEnv);
+		refresh_matview_datafill(dest_old, query, queryEnv, tupdesc_old, "");
+	}
+
+	/* Generate new delta */
+	if (list_length(table->new_tuplestores) > 0)
+	{
+		/* Replace the modified table with the new delta table and calculate the new view delta*/
+		replace_rte_with_delta(rte, table, true, queryEnv);
+		refresh_matview_datafill(dest_new, query, queryEnv, tupdesc_new, "");
+	}
+
+	in_delta_calculation = false;
+}
+
+/*
+ * rewrite_query_for_postupdate_state
+ *
+ * Rewrite the query so that the specified base table's RTEs will represent
+ * "post-update" state of tables. This is called after the view delta
+ * calculation due to changes on this table finishes.
+ */
+static Query*
+rewrite_query_for_postupdate_state(Query *query, MV_TriggerTable *table, int rte_index)
+{
+	ListCell *lc = list_nth_cell(query->rtable, rte_index - 1);
+
+	/* Retore the original RTE */
+	lfirst(lc) = table->original_rte;
+
+	return query;
+}
+
+/*
+ * apply_delta
+ *
+ * Apply deltas to the materialized view. In outer join cases, this requires
+ * the view maintenance graph.
+ */
+static void
+apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *new_tuplestores,
+			TupleDesc tupdesc_old, TupleDesc tupdesc_new,
+			Query *query)
+{
+	StringInfoData querybuf;
+	StringInfoData target_list_buf;
+	Relation	matviewRel;
+	char	   *matviewname;
+	ListCell	*lc;
+	int			i;
+	List	   *keys = NIL;
+
+
+	/*
+	 * get names of the materialized view and delta tables
+	 */
+
+	matviewRel = table_open(matviewOid, NoLock);
+	matviewname = quote_qualified_identifier(get_namespace_name(RelationGetNamespace(matviewRel)),
+											 RelationGetRelationName(matviewRel));
+
+	/*
+	 * Build parts of the maintenance queries
+	 */
+
+	initStringInfo(&querybuf);
+	initStringInfo(&target_list_buf);
+
+	/* build string of target list */
+	for (i = 0; i < matviewRel->rd_att->natts; i++)
+	{
+		Form_pg_attribute attr = TupleDescAttr(matviewRel->rd_att, i);
+		char   *resname = NameStr(attr->attname);
+
+		if (i != 0)
+			appendStringInfo(&target_list_buf, ", ");
+		appendStringInfo(&target_list_buf, "%s", quote_qualified_identifier(NULL, resname));
+	}
+
+	i = 0;
+	foreach (lc, query->targetList)
+	{
+		TargetEntry *tle = (TargetEntry *) lfirst(lc);
+		Form_pg_attribute attr = TupleDescAttr(matviewRel->rd_att, i);
+
+		i++;
+
+		if (tle->resjunk)
+			continue;
+
+		keys = lappend(keys, attr);
+	}
+
+	/* Start maintaining the materialized view. */
+	OpenMatViewIncrementalMaintenance();
+
+	/* Open SPI context. */
+	if (SPI_connect() != SPI_OK_CONNECT)
+		elog(ERROR, "SPI_connect failed");
+
+	/* For tuple deletion */
+	if (old_tuplestores && tuplestore_tuple_count(old_tuplestores) > 0)
+	{
+		EphemeralNamedRelation enr = palloc(sizeof(EphemeralNamedRelationData));
+		int				rc;
+
+		/* convert tuplestores to ENR, and register for SPI */
+		enr->md.name = pstrdup(OLD_DELTA_ENRNAME);
+		enr->md.reliddesc = InvalidOid;
+		enr->md.tupdesc = tupdesc_old;
+		enr->md.enrtype = ENR_NAMED_TUPLESTORE;
+		enr->md.enrtuples = tuplestore_tuple_count(old_tuplestores);
+		enr->reldata = old_tuplestores;
+
+		rc = SPI_register_relation(enr);
+		if (rc != SPI_OK_REL_REGISTER)
+			elog(ERROR, "SPI_register failed");
+
+		apply_old_delta(matviewname, OLD_DELTA_ENRNAME, keys);
+
+	}
+	/* For tuple insertion */
+	if (new_tuplestores && tuplestore_tuple_count(new_tuplestores) > 0)
+	{
+		EphemeralNamedRelation enr = palloc(sizeof(EphemeralNamedRelationData));
+		int rc;
+
+		/* convert tuplestores to ENR, and register for SPI */
+		enr->md.name = pstrdup(NEW_DELTA_ENRNAME);
+		enr->md.reliddesc = InvalidOid;
+		enr->md.tupdesc = tupdesc_new;;
+		enr->md.enrtype = ENR_NAMED_TUPLESTORE;
+		enr->md.enrtuples = tuplestore_tuple_count(new_tuplestores);
+		enr->reldata = new_tuplestores;
+
+		rc = SPI_register_relation(enr);
+		if (rc != SPI_OK_REL_REGISTER)
+			elog(ERROR, "SPI_register failed");
+
+		/* apply new delta */
+		apply_new_delta(matviewname, NEW_DELTA_ENRNAME, &target_list_buf);
+	}
+
+	/* We're done maintaining the materialized view. */
+	CloseMatViewIncrementalMaintenance();
+
+	table_close(matviewRel, NoLock);
+
+	/* Close SPI context. */
+	if (SPI_finish() != SPI_OK_FINISH)
+		elog(ERROR, "SPI_finish failed");
+}
+
+/*
+ * apply_old_delta
+ *
+ * Execute a query for applying a delta table given by deltname_old
+ * which contains tuples to be deleted from to a materialized view given by
+ * matviewname.  This is used when counting is not required.
+ */
+static void
+apply_old_delta(const char *matviewname, const char *deltaname_old,
+				List *keys)
+{
+	StringInfoData	querybuf;
+	StringInfoData	keysbuf;
+	char   *match_cond;
+	ListCell *lc;
+
+	/* build WHERE condition for searching tuples to be deleted */
+	match_cond = get_matching_condition_string(keys);
+
+	/* build string of keys list */
+	initStringInfo(&keysbuf);
+	foreach (lc, keys)
+	{
+		Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc);
+		char   *resname = NameStr(attr->attname);
+		appendStringInfo(&keysbuf, "%s", quote_qualified_identifier("mv", resname));
+		if (lnext(keys, lc))
+			appendStringInfo(&keysbuf, ", ");
+	}
+
+	/* Search for matching tuples from the view and update or delete if found. */
+	initStringInfo(&querybuf);
+	appendStringInfo(&querybuf,
+	"DELETE FROM %s WHERE ctid IN ("
+		"SELECT tid FROM (SELECT pg_catalog.row_number() over (partition by %s) AS \"__ivm_row_number__\","
+								  "mv.ctid AS tid,"
+								  "diff.\"__ivm_count__\""
+						 "FROM %s AS mv, %s AS diff "
+						 "WHERE %s) v "
+					"WHERE v.\"__ivm_row_number__\" OPERATOR(pg_catalog.<=) v.\"__ivm_count__\")",
+					matviewname,
+					keysbuf.data,
+					matviewname, deltaname_old,
+					match_cond);
+
+	if (SPI_exec(querybuf.data, 0) != SPI_OK_DELETE)
+		elog(ERROR, "SPI_exec failed: %s", querybuf.data);
+}
+
+/*
+ * apply_new_delta
+ *
+ * Execute a query for applying a delta table given by deltname_new
+ * which contains tuples to be inserted into a materialized view given by
+ * matviewname.  This is used when counting is not required.
+ */
+static void
+apply_new_delta(const char *matviewname, const char *deltaname_new,
+				StringInfo target_list)
+{
+	StringInfoData	querybuf;
+
+	/* Search for matching tuples from the view and update or delete if found. */
+	initStringInfo(&querybuf);
+	appendStringInfo(&querybuf,
+					"INSERT INTO %s (%s) SELECT %s FROM ("
+						"SELECT diff.*, pg_catalog.generate_series(1, diff.\"__ivm_count__\")"
+							" AS __ivm_generate_series__ "
+						"FROM %s AS diff) AS v",
+					matviewname, target_list->data, target_list->data,
+					deltaname_new);
+
+	if (SPI_exec(querybuf.data, 0) != SPI_OK_INSERT)
+		elog(ERROR, "SPI_exec failed: %s", querybuf.data);
+}
+
+/*
+ * get_matching_condition_string
+ *
+ * Build a predicate string for looking for a tuple with given keys.
+ */
+static char *
+get_matching_condition_string(List *keys)
+{
+	StringInfoData match_cond;
+	ListCell	*lc;
+
+	/* If there is no key columns, the condition is always true. */
+	if (keys == NIL)
+		return "true";
+
+	initStringInfo(&match_cond);
+	foreach (lc, keys)
+	{
+		Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc);
+		char   *resname = NameStr(attr->attname);
+		char   *mv_resname = quote_qualified_identifier("mv", resname);
+		char   *diff_resname = quote_qualified_identifier("diff", resname);
+		Oid		typid = attr->atttypid;
+
+		/* Considering NULL values, we can not use simple = operator. */
+		appendStringInfo(&match_cond, "(");
+		generate_equal(&match_cond, typid, mv_resname, diff_resname);
+		appendStringInfo(&match_cond, " OR (%s IS NULL AND %s IS NULL))",
+						 mv_resname, diff_resname);
+
+		if (lnext(keys, lc))
+			appendStringInfo(&match_cond, " AND ");
+	}
+
+	return match_cond.data;
+}
+
+/*
+ * generate_equals
+ *
+ * Generate an equality clause using given operands' default equality
+ * operator.
+ */
+static void
+generate_equal(StringInfo querybuf, Oid opttype,
+			   const char *leftop, const char *rightop)
+{
+	TypeCacheEntry *typentry;
+
+	typentry = lookup_type_cache(opttype, TYPECACHE_EQ_OPR);
+	if (!OidIsValid(typentry->eq_opr))
+		ereport(ERROR,
+				(errcode(ERRCODE_UNDEFINED_FUNCTION),
+				 errmsg("could not identify an equality operator for type %s",
+						format_type_be_qualified(opttype))));
+
+	generate_operator_clause(querybuf,
+							 leftop, opttype,
+							 typentry->eq_opr,
+							 rightop, opttype);
+}
+
+/*
+ * mv_InitHashTables
+ */
+static void
+mv_InitHashTables(void)
+{
+	HASHCTL		ctl;
+
+	memset(&ctl, 0, sizeof(ctl));
+	ctl.keysize = sizeof(Oid);
+	ctl.entrysize = sizeof(MV_TriggerHashEntry);
+	mv_trigger_info = hash_create("MV trigger info",
+								 MV_INIT_QUERYHASHSIZE,
+								 &ctl, HASH_ELEM | HASH_BLOBS);
+}
+
+/*
+ * AtAbort_IVM
+ *
+ * Clean up hash entries for all materialized views. This is called at
+ * transaction abort.
+ */
+void
+AtAbort_IVM()
+{
+	HASH_SEQ_STATUS seq;
+	MV_TriggerHashEntry *entry;
+
+	if (mv_trigger_info)
+	{
+		hash_seq_init(&seq, mv_trigger_info);
+		while ((entry = hash_seq_search(&seq)) != NULL)
+			clean_up_IVM_hash_entry(entry, true);
+	}
+	in_delta_calculation = false;
+}
+
+/*
+ * clean_up_IVM_hash_entry
+ *
+ * Clean up tuple stores and hash entries for a materialized view after its
+ * maintenance finished.
+ */
+static void
+clean_up_IVM_hash_entry(MV_TriggerHashEntry *entry, bool is_abort)
+{
+	bool found;
+	ListCell *lc;
+
+	foreach(lc, entry->tables)
+	{
+		MV_TriggerTable *table = (MV_TriggerTable *) lfirst(lc);
+
+		list_free(table->old_tuplestores);
+		list_free(table->new_tuplestores);
+		if (!is_abort)
+		{
+			ExecDropSingleTupleTableSlot(table->slot);
+			table_close(table->rel, NoLock);
+		}
+	}
+	list_free(entry->tables);
+
+	if (!is_abort)
+		UnregisterSnapshot(entry->snapshot);
+
+	hash_search(mv_trigger_info, (void *) &entry->matview_id, HASH_REMOVE, &found);
+}
+
+/*
+ * isIvmName
+ *
+ * Check if this is a IVM hidden column from the name.
+ */
+bool
+isIvmName(const char *s)
+{
+	if (s)
+		return (strncmp(s, "__ivm_", 6) == 0);
+	return false;
+}
diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat
index 9c120fc2b7..e111f11bf5 100644
--- a/src/include/catalog/pg_proc.dat
+++ b/src/include/catalog/pg_proc.dat
@@ -12174,4 +12174,14 @@
   proargtypes => 'int2',
   prosrc => 'gist_stratnum_identity' },
 
+# IVM
+{ oid => '786', descr => 'ivm trigger (before)',
+  proname => 'IVM_immediate_before', provolatile => 'v', prorettype => 'trigger',
+  proargtypes => '', prosrc => 'IVM_immediate_before' },
+{ oid => '787', descr => 'ivm trigger (after)',
+  proname => 'IVM_immediate_maintenance', provolatile => 'v', prorettype => 'trigger',
+  proargtypes => '', prosrc => 'IVM_immediate_maintenance' },
+{ oid => '788', descr => 'ivm filetring ',
+  proname => 'ivm_visible_in_prestate', provolatile => 's', prorettype => 'bool',
+  proargtypes => 'oid tid oid', prosrc => 'ivm_visible_in_prestate' },
 ]
diff --git a/src/include/commands/createas.h b/src/include/commands/createas.h
index 94678e3834..396ad1bb4c 100644
--- a/src/include/commands/createas.h
+++ b/src/include/commands/createas.h
@@ -16,6 +16,7 @@
 
 #include "catalog/objectaddress.h"
 #include "nodes/params.h"
+#include "nodes/pathnodes.h"
 #include "parser/parse_node.h"
 #include "tcop/dest.h"
 #include "utils/queryenvironment.h"
@@ -25,6 +26,9 @@ extern ObjectAddress ExecCreateTableAs(ParseState *pstate, CreateTableAsStmt *st
 									   ParamListInfo params, QueryEnvironment *queryEnv,
 									   QueryCompletion *qc);
 
+extern void CreateIvmTriggersOnBaseTables(Query *qry, Oid matviewOid);
+extern void CreateIndexOnIMMV(Query *query, Relation matviewRel);
+
 extern int	GetIntoRelEFlags(IntoClause *intoClause);
 
 extern DestReceiver *CreateIntoRelDestReceiver(IntoClause *intoClause);
diff --git a/src/include/commands/matview.h b/src/include/commands/matview.h
index 817b2ba0b6..3257e1adff 100644
--- a/src/include/commands/matview.h
+++ b/src/include/commands/matview.h
@@ -15,6 +15,7 @@
 #define MATVIEW_H
 
 #include "catalog/objectaddress.h"
+#include "fmgr.h"
 #include "nodes/params.h"
 #include "nodes/parsenodes.h"
 #include "tcop/dest.h"
@@ -23,6 +24,8 @@
 
 extern void SetMatViewPopulatedState(Relation relation, bool newstate);
 
+extern void SetMatViewIVMState(Relation relation, bool newstate);
+
 extern ObjectAddress ExecRefreshMatView(RefreshMatViewStmt *stmt, const char *queryString,
 										ParamListInfo params, QueryCompletion *qc);
 
@@ -30,4 +33,10 @@ extern DestReceiver *CreateTransientRelDestReceiver(Oid transientoid);
 
 extern bool MatViewIncrementalMaintenanceIsEnabled(void);
 
+extern Datum IVM_immediate_before(PG_FUNCTION_ARGS);
+extern Datum IVM_immediate_maintenance(PG_FUNCTION_ARGS);
+extern Datum IVM_visible_in_prestate(PG_FUNCTION_ARGS);
+extern void AtAbort_IVM(void);
+extern bool isIvmName(const char *s);
+
 #endif							/* MATVIEW_H */
-- 
2.25.1


--Multipart=_Mon__4_Mar_2024_11_58_46_+0900_UaponF/qQhQrVCFt
Content-Type: text/x-diff;
 name="v30-0007-Add-DISTINCT-support-for-IVM.patch"
Content-Disposition: attachment;
 filename="v30-0007-Add-DISTINCT-support-for-IVM.patch"
Content-Transfer-Encoding: 7bit



^ permalink  raw  reply  [nested|flat] 101+ messages in thread

* [PATCH v31 06/11] Add Incremental View Maintenance support
@ 2023-05-31 09:59  Yugo Nagata <[email protected]>
  0 siblings, 0 replies; 101+ messages in thread

From: Yugo Nagata @ 2023-05-31 09:59 UTC (permalink / raw)

In this implementation, AFTER triggers are used to collect
tuplestores containing transition table contents. When multiple tables
are changed, multiple AFTER triggers are invoked, then the final AFTER
trigger performs actual update of the matview. In addition, BEFORE
triggers are also used to handle global information for view
maintenance.

To calculate view deltas, we need both pre-state and post-state of base
tables. Post-update states are available in AFTER trigger, and pre-update
states can be calculated by removing inserted tuples and appending deleted
tuples. Insterted tuples are filtered using the snapshot taken before
table modiication, and deleted tuples are contained in the old transition
table.

Incrementally Maintainable Materialized Views (IMMV) can contain
duplicated tuples.

This patch also allows self-join, simultaneous updates of more than
one base table, and multiple updates of the same base table.
---
 src/backend/access/transam/xact.c |    5 +
 src/backend/commands/createas.c   |  682 ++++++++++++++
 src/backend/commands/matview.c    | 1468 ++++++++++++++++++++++++++++-
 src/include/catalog/pg_proc.dat   |   10 +
 src/include/commands/createas.h   |    4 +
 src/include/commands/matview.h    |    9 +
 6 files changed, 2143 insertions(+), 35 deletions(-)

diff --git a/src/backend/access/transam/xact.c b/src/backend/access/transam/xact.c
index df5a67e4c3..a2d5404912 100644
--- a/src/backend/access/transam/xact.c
+++ b/src/backend/access/transam/xact.c
@@ -36,6 +36,7 @@
 #include "catalog/pg_enum.h"
 #include "catalog/storage.h"
 #include "commands/async.h"
+#include "commands/matview.h"
 #include "commands/tablecmds.h"
 #include "commands/trigger.h"
 #include "common/pg_prng.h"
@@ -2860,6 +2861,7 @@ AbortTransaction(void)
 	AtAbort_Notify();
 	AtEOXact_RelationMap(false, is_parallel_worker);
 	AtAbort_Twophase();
+	AtAbort_IVM();
 
 	/*
 	 * Advertise the fact that we aborted in pg_xact (assuming that we got as
@@ -5198,6 +5200,9 @@ AbortSubTransaction(void)
 	pgstat_progress_end_command();
 	UnlockBuffers();
 
+	/* Clean up hash entries for incremental view maintenance */
+	AtAbort_IVM();
+
 	/* Reset WAL record construction state */
 	XLogResetInsertion();
 
diff --git a/src/backend/commands/createas.c b/src/backend/commands/createas.c
index 62050f4dc5..04a5ee9e37 100644
--- a/src/backend/commands/createas.c
+++ b/src/backend/commands/createas.c
@@ -29,15 +29,27 @@
 #include "access/tableam.h"
 #include "access/xact.h"
 #include "catalog/namespace.h"
+#include "catalog/index.h"
+#include "catalog/pg_constraint.h"
+#include "catalog/pg_inherits.h"
+#include "catalog/pg_trigger.h"
 #include "catalog/toasting.h"
 #include "commands/createas.h"
+#include "commands/defrem.h"
 #include "commands/matview.h"
 #include "commands/prepare.h"
 #include "commands/tablecmds.h"
+#include "commands/tablespace.h"
+#include "commands/trigger.h"
 #include "commands/view.h"
 #include "miscadmin.h"
+#include "optimizer/optimizer.h"
+#include "optimizer/prep.h"
 #include "nodes/makefuncs.h"
 #include "nodes/nodeFuncs.h"
+#include "parser/parser.h"
+#include "parser/parsetree.h"
+#include "parser/parse_clause.h"
 #include "rewrite/rewriteHandler.h"
 #include "tcop/tcopprot.h"
 #include "utils/builtins.h"
@@ -68,6 +80,12 @@ static bool intorel_receive(TupleTableSlot *slot, DestReceiver *self);
 static void intorel_shutdown(DestReceiver *self);
 static void intorel_destroy(DestReceiver *self);
 
+static void CreateIvmTriggersOnBaseTablesRecurse(Query *qry, Node *node, Oid matviewOid,
+									 Relids *relids, bool ex_lock);
+static void CreateIvmTrigger(Oid relOid, Oid viewOid, int16 type, int16 timing, bool ex_lock);
+static void check_ivm_restriction(Node *node);
+static bool check_ivm_restriction_walker(Node *node, void *context);
+static Bitmapset *get_primary_key_attnos_from_query(Query *query, List **constraintList);
 
 /*
  * create_ctas_internal
@@ -277,6 +295,18 @@ ExecCreateTableAs(ParseState *pstate, CreateTableAsStmt *stmt,
 		save_nestlevel = NewGUCNestLevel();
 	}
 
+	if (is_matview && into->ivm)
+	{
+		/* check if the query is supported in IMMV definition */
+		if (contain_mutable_functions((Node *) query))
+			ereport(ERROR,
+					(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+					 errmsg("mutable function is not supported on incrementally maintainable materialized view"),
+					 errhint("functions must be marked IMMUTABLE")));
+
+		check_ivm_restriction((Node *) query);
+	}
+
 	if (into->skipData)
 	{
 		/*
@@ -353,6 +383,27 @@ ExecCreateTableAs(ParseState *pstate, CreateTableAsStmt *stmt,
 
 		/* Restore userid and security context */
 		SetUserIdAndSecContext(save_userid, save_sec_context);
+
+		if (into->ivm)
+		{
+			Oid matviewOid = address.objectId;
+			Relation matviewRel = table_open(matviewOid, NoLock);
+
+			/*
+			 * Mark relisivm field, if it's a matview and into->ivm is true.
+			 */
+			SetMatViewIVMState(matviewRel, true);
+
+			if (!into->skipData)
+			{
+				/* Create an index on incremental maintainable materialized view, if possible */
+				CreateIndexOnIMMV((Query *) into->viewQuery, matviewRel);
+
+				/* Create triggers on incremental maintainable materialized view */
+				CreateIvmTriggersOnBaseTables((Query *) into->viewQuery, matviewOid);
+			}
+			table_close(matviewRel, NoLock);
+		}
 	}
 
 	return address;
@@ -630,3 +681,634 @@ intorel_destroy(DestReceiver *self)
 {
 	pfree(self);
 }
+
+/*
+ * CreateIvmTriggersOnBaseTables -- create IVM triggers on all base tables
+ */
+void
+CreateIvmTriggersOnBaseTables(Query *qry, Oid matviewOid)
+{
+	Relids	relids = NULL;
+	bool	ex_lock = false;
+	RangeTblEntry *rte;
+
+	/* Immediately return if we don't have any base tables. */
+	if (list_length(qry->rtable) < 1)
+		return;
+
+	/*
+	 * If the view has more than one base tables, we need an exclusive lock
+	 * on the view so that the view would be maintained serially to avoid
+	 * the inconsistency that occurs when two base tables are modified in
+	 * concurrent transactions. However, if the view has only one table,
+	 * we can use a weaker lock.
+	 *
+	 * The type of lock should be determined here, because if we check the
+	 * view definition at maintenance time, we need to acquire a weaker lock,
+	 * and upgrading the lock level after this increases probability of
+	 * deadlock.
+	 */
+
+	rte = list_nth(qry->rtable, 0);
+	if (list_length(qry->rtable) > 1 || rte->rtekind != RTE_RELATION)
+		ex_lock = true;
+
+	CreateIvmTriggersOnBaseTablesRecurse(qry, (Node *)qry, matviewOid, &relids, ex_lock);
+
+	bms_free(relids);
+}
+
+static void
+CreateIvmTriggersOnBaseTablesRecurse(Query *qry, Node *node, Oid matviewOid,
+									 Relids *relids, bool ex_lock)
+{
+	if (node == NULL)
+		return;
+
+	/* This can recurse, so check for excessive recursion */
+	check_stack_depth();
+
+	switch (nodeTag(node))
+	{
+		case T_Query:
+			{
+				Query *query = (Query *) node;
+
+				CreateIvmTriggersOnBaseTablesRecurse(qry, (Node *)query->jointree, matviewOid, relids, ex_lock);
+			}
+			break;
+
+		case T_RangeTblRef:
+			{
+				int			rti = ((RangeTblRef *) node)->rtindex;
+				RangeTblEntry *rte = rt_fetch(rti, qry->rtable);
+
+				if (rte->rtekind == RTE_RELATION && !bms_is_member(rte->relid, *relids))
+				{
+					CreateIvmTrigger(rte->relid, matviewOid, TRIGGER_TYPE_INSERT, TRIGGER_TYPE_BEFORE, ex_lock);
+					CreateIvmTrigger(rte->relid, matviewOid, TRIGGER_TYPE_DELETE, TRIGGER_TYPE_BEFORE, ex_lock);
+					CreateIvmTrigger(rte->relid, matviewOid, TRIGGER_TYPE_UPDATE, TRIGGER_TYPE_BEFORE, ex_lock);
+					CreateIvmTrigger(rte->relid, matviewOid, TRIGGER_TYPE_TRUNCATE, TRIGGER_TYPE_BEFORE, true);
+					CreateIvmTrigger(rte->relid, matviewOid, TRIGGER_TYPE_INSERT, TRIGGER_TYPE_AFTER, ex_lock);
+					CreateIvmTrigger(rte->relid, matviewOid, TRIGGER_TYPE_DELETE, TRIGGER_TYPE_AFTER, ex_lock);
+					CreateIvmTrigger(rte->relid, matviewOid, TRIGGER_TYPE_UPDATE, TRIGGER_TYPE_AFTER, ex_lock);
+					CreateIvmTrigger(rte->relid, matviewOid, TRIGGER_TYPE_TRUNCATE, TRIGGER_TYPE_AFTER, true);
+
+					*relids = bms_add_member(*relids, rte->relid);
+				}
+			}
+			break;
+
+		case T_FromExpr:
+			{
+				FromExpr   *f = (FromExpr *) node;
+				ListCell   *l;
+
+				foreach(l, f->fromlist)
+					CreateIvmTriggersOnBaseTablesRecurse(qry, lfirst(l), matviewOid, relids, ex_lock);
+			}
+			break;
+
+		case T_JoinExpr:
+			{
+				JoinExpr   *j = (JoinExpr *) node;
+
+				CreateIvmTriggersOnBaseTablesRecurse(qry, j->larg, matviewOid, relids, ex_lock);
+				CreateIvmTriggersOnBaseTablesRecurse(qry, j->rarg, matviewOid, relids, ex_lock);
+			}
+			break;
+
+		default:
+			elog(ERROR, "unrecognized node type: %d", (int) nodeTag(node));
+	}
+}
+
+/*
+ * CreateIvmTrigger -- create IVM trigger on a base table
+ */
+static void
+CreateIvmTrigger(Oid relOid, Oid viewOid, int16 type, int16 timing, bool ex_lock)
+{
+	ObjectAddress	refaddr;
+	ObjectAddress	address;
+	CreateTrigStmt *ivm_trigger;
+	List *transitionRels = NIL;
+
+	Assert(timing == TRIGGER_TYPE_BEFORE || timing == TRIGGER_TYPE_AFTER);
+
+	refaddr.classId = RelationRelationId;
+	refaddr.objectId = viewOid;
+	refaddr.objectSubId = 0;
+
+	ivm_trigger = makeNode(CreateTrigStmt);
+	ivm_trigger->relation = NULL;
+	ivm_trigger->row = false;
+
+	ivm_trigger->timing = timing;
+	ivm_trigger->events = type;
+
+	switch (type)
+	{
+		case TRIGGER_TYPE_INSERT:
+			ivm_trigger->trigname = (timing == TRIGGER_TYPE_BEFORE ? "IVM_trigger_ins_before" : "IVM_trigger_ins_after");
+			break;
+		case TRIGGER_TYPE_DELETE:
+			ivm_trigger->trigname = (timing == TRIGGER_TYPE_BEFORE ? "IVM_trigger_del_before" : "IVM_trigger_del_after");
+			break;
+		case TRIGGER_TYPE_UPDATE:
+			ivm_trigger->trigname = (timing == TRIGGER_TYPE_BEFORE ? "IVM_trigger_upd_before" : "IVM_trigger_upd_after");
+			break;
+		case TRIGGER_TYPE_TRUNCATE:
+			ivm_trigger->trigname = (timing == TRIGGER_TYPE_BEFORE ? "IVM_trigger_truncate_before" : "IVM_trigger_truncate_after");
+			break;
+		default:
+			elog(ERROR, "unsupported trigger type");
+	}
+
+	if (timing == TRIGGER_TYPE_AFTER)
+	{
+		if (type == TRIGGER_TYPE_INSERT || type == TRIGGER_TYPE_UPDATE)
+		{
+			TriggerTransition *n = makeNode(TriggerTransition);
+			n->name = "__ivm_newtable";
+			n->isNew = true;
+			n->isTable = true;
+
+			transitionRels = lappend(transitionRels, n);
+		}
+		if (type == TRIGGER_TYPE_DELETE || type == TRIGGER_TYPE_UPDATE)
+		{
+			TriggerTransition *n = makeNode(TriggerTransition);
+			n->name = "__ivm_oldtable";
+			n->isNew = false;
+			n->isTable = true;
+
+			transitionRels = lappend(transitionRels, n);
+		}
+	}
+
+	/*
+	 * XXX: When using DELETE or UPDATE, we must use exclusive lock for now
+	 * because apply_old_delta(_with_count) uses ctid to identify the tuple
+	 * to be deleted/deleted, but doesn't work in concurrent situations.
+	 *
+	 * If the view doesn't have aggregate, distinct, or tuple duplicate,
+	 * then it would work even in concurrent situations. However, we don't have
+	 * any way to guarantee the view has a unique key before opening the IMMV
+	 * at the maintenance time because users may drop the unique index.
+	 */
+
+	if (type == TRIGGER_TYPE_DELETE || type == TRIGGER_TYPE_UPDATE)
+		ex_lock = true;
+
+	ivm_trigger->funcname =
+		(timing == TRIGGER_TYPE_BEFORE ? SystemFuncName("IVM_immediate_before") : SystemFuncName("IVM_immediate_maintenance"));
+
+	ivm_trigger->columns = NIL;
+	ivm_trigger->transitionRels = transitionRels;
+	ivm_trigger->whenClause = NULL;
+	ivm_trigger->isconstraint = false;
+	ivm_trigger->deferrable = false;
+	ivm_trigger->initdeferred = false;
+	ivm_trigger->constrrel = NULL;
+	ivm_trigger->args = list_make2(
+		makeString(DatumGetPointer(DirectFunctionCall1(oidout, ObjectIdGetDatum(viewOid)))),
+		makeString(DatumGetPointer(DirectFunctionCall1(boolout, BoolGetDatum(ex_lock))))
+		);
+
+	address = CreateTrigger(ivm_trigger, NULL, relOid, InvalidOid, InvalidOid,
+						 InvalidOid, InvalidOid, InvalidOid, NULL, true, false);
+
+	recordDependencyOn(&address, &refaddr, DEPENDENCY_AUTO);
+
+	/* Make changes-so-far visible */
+	CommandCounterIncrement();
+}
+
+/*
+ * check_ivm_restriction --- look for specify nodes in the query tree
+ */
+static void
+check_ivm_restriction(Node *node)
+{
+	check_ivm_restriction_walker(node, NULL);
+}
+
+static bool
+check_ivm_restriction_walker(Node *node, void *context)
+{
+	if (node == NULL)
+		return false;
+
+	/*
+	 * We currently don't support Sub-Query.
+	 */
+	if (IsA(node, SubPlan) || IsA(node, SubLink))
+		ereport(ERROR,
+				(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+				 errmsg("subquery is not supported on incrementally maintainable materialized view")));
+
+	/* This can recurse, so check for excessive recursion */
+	check_stack_depth();
+
+	switch (nodeTag(node))
+	{
+		case T_Query:
+			{
+				Query *qry = (Query *)node;
+				ListCell   *lc;
+				List       *vars;
+
+				/* if contained CTE, return error */
+				if (qry->cteList != NIL)
+					ereport(ERROR,
+							(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+							 errmsg("CTE is not supported on incrementally maintainable materialized view")));
+				if (qry->havingQual != NULL)
+					ereport(ERROR,
+							(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+							 errmsg(" HAVING clause is not supported on incrementally maintainable materialized view")));
+				if (qry->sortClause != NIL)	/* There is a possibility that we don't need to return an error */
+					ereport(ERROR,
+							(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+							 errmsg("ORDER BY clause is not supported on incrementally maintainable materialized view")));
+				if (qry->limitOffset != NULL || qry->limitCount != NULL)
+					ereport(ERROR,
+							(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+							 errmsg("LIMIT/OFFSET clause is not supported on incrementally maintainable materialized view")));
+				if (qry->distinctClause)
+					ereport(ERROR,
+							(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+							 errmsg("DISTINCT is not supported on incrementally maintainable materialized view")));
+				if (qry->hasDistinctOn)
+					ereport(ERROR,
+							(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+							 errmsg("DISTINCT ON is not supported on incrementally maintainable materialized view")));
+				if (qry->hasWindowFuncs)
+					ereport(ERROR,
+							(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+							 errmsg("window functions are not supported on incrementally maintainable materialized view")));
+				if (qry->groupingSets != NIL)
+					ereport(ERROR,
+							(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+							 errmsg("GROUPING SETS, ROLLUP, or CUBE clauses is not supported on incrementally maintainable materialized view")));
+				if (qry->setOperations != NULL)
+					ereport(ERROR,
+							(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+							 errmsg("UNION/INTERSECT/EXCEPT statements are not supported on incrementally maintainable materialized view")));
+				if (list_length(qry->targetList) == 0)
+					ereport(ERROR,
+							(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+							 errmsg("empty target list is not supported on incrementally maintainable materialized view")));
+				if (qry->rowMarks != NIL)
+					ereport(ERROR,
+							(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+							 errmsg("FOR UPDATE/SHARE clause is not supported on incrementally maintainable materialized view")));
+
+				/* system column restrictions */
+				vars = pull_vars_of_level((Node *) qry, 0);
+				foreach(lc, vars)
+				{
+					if (IsA(lfirst(lc), Var))
+					{
+						Var *var = (Var *) lfirst(lc);
+						/* if system column, return error */
+						if (var->varattno < 0)
+							ereport(ERROR,
+									(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+									 errmsg("system column is not supported on incrementally maintainable materialized view")));
+					}
+				}
+
+				/* restrictions for rtable */
+				foreach(lc, qry->rtable)
+				{
+					RangeTblEntry *rte = (RangeTblEntry *) lfirst(lc);
+
+					if (rte->subquery)
+						ereport(ERROR,
+								(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+								 errmsg("subquery is not supported on incrementally maintainable materialized view")));
+
+					if (rte->tablesample != NULL)
+						ereport(ERROR,
+								(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+								 errmsg("TABLESAMPLE clause is not supported on incrementally maintainable materialized view")));
+
+					if (rte->relkind == RELKIND_PARTITIONED_TABLE)
+						ereport(ERROR,
+								(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+								 errmsg("partitioned table is not supported on incrementally maintainable materialized view")));
+
+					if (rte->relkind == RELKIND_RELATION && has_superclass(rte->relid))
+						ereport(ERROR,
+								(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+								 errmsg("partitions is not supported on incrementally maintainable materialized view")));
+
+					if (rte->relkind == RELKIND_RELATION && find_inheritance_children(rte->relid, NoLock) != NIL)
+						ereport(ERROR,
+								(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+								 errmsg("inheritance parent is not supported on incrementally maintainable materialized view")));
+
+					if (rte->relkind == RELKIND_FOREIGN_TABLE)
+						ereport(ERROR,
+								(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+								 errmsg("foreign table is not supported on incrementally maintainable materialized view")));
+
+					if (rte->relkind == RELKIND_VIEW ||
+						rte->relkind == RELKIND_MATVIEW)
+						ereport(ERROR,
+								(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+								 errmsg("VIEW or MATERIALIZED VIEW is not supported on incrementally maintainable materialized view")));
+
+					if (rte->rtekind == RTE_VALUES)
+						ereport(ERROR,
+								(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+								 errmsg("VALUES is not supported on incrementally maintainable materialized view")));
+
+				}
+
+				query_tree_walker(qry, check_ivm_restriction_walker, NULL, QTW_IGNORE_RANGE_TABLE);
+
+				break;
+			}
+		case T_TargetEntry:
+			{
+				TargetEntry *tle = (TargetEntry *)node;
+				if (isIvmName(tle->resname))
+						ereport(ERROR,
+								(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+								 errmsg("column name %s is not supported on incrementally maintainable materialized view", tle->resname)));
+
+				expression_tree_walker(node, check_ivm_restriction_walker, NULL);
+				break;
+			}
+		case T_JoinExpr:
+			{
+				JoinExpr *joinexpr = (JoinExpr *)node;
+
+				if (joinexpr->jointype > JOIN_INNER)
+						ereport(ERROR,
+								(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+								 errmsg("OUTER JOIN is not supported on incrementally maintainable materialized view")));
+
+				expression_tree_walker(node, check_ivm_restriction_walker, NULL);
+			}
+			break;
+		case T_Aggref:
+			ereport(ERROR,
+					(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+					 errmsg("aggregate function is not supported on incrementally maintainable materialized view")));
+			break;
+		default:
+			expression_tree_walker(node, check_ivm_restriction_walker, (void *) context);
+			break;
+	}
+	return false;
+}
+
+/*
+ * CreateIndexOnIMMV
+ *
+ * Create a unique index on incremental maintainable materialized view.
+ * If the view definition query has a GROUP BY clause, the index is created
+ * on the columns of GROUP BY expressions. Otherwise, if the view contains
+ * all primary key attritubes of its base tables in the target list, the index
+ * is created on these attritubes. In other cases, no index is created.
+ */
+void
+CreateIndexOnIMMV(Query *query, Relation matviewRel)
+{
+	ListCell *lc;
+	IndexStmt  *index;
+	ObjectAddress address;
+	List *constraintList = NIL;
+	char		idxname[NAMEDATALEN];
+	List	   *indexoidlist = RelationGetIndexList(matviewRel);
+	ListCell   *indexoidscan;
+	Bitmapset *key_attnos;
+
+	snprintf(idxname, sizeof(idxname), "%s_index", RelationGetRelationName(matviewRel));
+
+	index = makeNode(IndexStmt);
+
+	index->unique = true;
+	index->primary = false;
+	index->isconstraint = false;
+	index->deferrable = false;
+	index->initdeferred = false;
+	index->idxname = idxname;
+	index->relation =
+		makeRangeVar(get_namespace_name(RelationGetNamespace(matviewRel)),
+					 pstrdup(RelationGetRelationName(matviewRel)),
+					 -1);
+	index->accessMethod = DEFAULT_INDEX_TYPE;
+	index->options = NIL;
+	index->tableSpace = get_tablespace_name(matviewRel->rd_rel->reltablespace);
+	index->whereClause = NULL;
+	index->indexParams = NIL;
+	index->indexIncludingParams = NIL;
+	index->excludeOpNames = NIL;
+	index->idxcomment = NULL;
+	index->indexOid = InvalidOid;
+	index->oldNumber = InvalidRelFileNumber;
+	index->oldCreateSubid = InvalidSubTransactionId;
+	index->oldFirstRelfilelocatorSubid = InvalidSubTransactionId;
+	index->transformed = true;
+	index->concurrent = false;
+	index->if_not_exists = false;
+
+	/* create index on the base tables' primary key columns */
+	key_attnos = get_primary_key_attnos_from_query(query, &constraintList);
+	if (key_attnos)
+	{
+		foreach(lc, query->targetList)
+		{
+			TargetEntry *tle = (TargetEntry *) lfirst(lc);
+			Form_pg_attribute attr = TupleDescAttr(matviewRel->rd_att, tle->resno - 1);
+
+			if (bms_is_member(tle->resno - FirstLowInvalidHeapAttributeNumber, key_attnos))
+			{
+				IndexElem  *iparam;
+
+				iparam = makeNode(IndexElem);
+				iparam->name = pstrdup(NameStr(attr->attname));
+				iparam->expr = NULL;
+				iparam->indexcolname = NULL;
+				iparam->collation = NIL;
+				iparam->opclass = NIL;
+				iparam->opclassopts = NIL;
+				iparam->ordering = SORTBY_DEFAULT;
+				iparam->nulls_ordering = SORTBY_NULLS_DEFAULT;
+				index->indexParams = lappend(index->indexParams, iparam);
+			}
+		}
+	}
+	else
+	{
+		/* create no index, just notice that an appropriate index is necessary for efficient IVM */
+		ereport(NOTICE,
+				(errmsg("could not create an index on materialized view \"%s\" automatically",
+						RelationGetRelationName(matviewRel)),
+				 errdetail("This target list does not have all the primary key columns. "),
+				 errhint("Create an index on the materialized view for efficient incremental maintenance.")));
+		return;
+	}
+
+	/* If we have a compatible index, we don't need to create another. */
+	foreach(indexoidscan, indexoidlist)
+	{
+		Oid			indexoid = lfirst_oid(indexoidscan);
+		Relation	indexRel;
+		bool		hasCompatibleIndex = false;
+
+		indexRel = index_open(indexoid, AccessShareLock);
+
+		if (CheckIndexCompatible(indexRel->rd_id,
+								index->accessMethod,
+								index->indexParams,
+								index->excludeOpNames,
+								false))
+			hasCompatibleIndex = true;
+
+		index_close(indexRel, AccessShareLock);
+
+		if (hasCompatibleIndex)
+			return;
+	}
+
+	address = DefineIndex(RelationGetRelid(matviewRel),
+						  index,
+						  InvalidOid,
+						  InvalidOid,
+						  InvalidOid,
+						  -1,
+						  false, true, false, false, true);
+
+	ereport(NOTICE,
+			(errmsg("created index \"%s\" on materialized view \"%s\"",
+					idxname, RelationGetRelationName(matviewRel))));
+
+	/*
+	 * Make dependencies so that the index is dropped if any base tables's
+	 * primary key is dropped.
+	 */
+	foreach(lc, constraintList)
+	{
+		Oid constraintOid = lfirst_oid(lc);
+		ObjectAddress	refaddr;
+
+		refaddr.classId = ConstraintRelationId;
+		refaddr.objectId = constraintOid;
+		refaddr.objectSubId = 0;
+
+		recordDependencyOn(&address, &refaddr, DEPENDENCY_NORMAL);
+	}
+}
+
+
+/*
+ * get_primary_key_attnos_from_query
+ *
+ * Identify the columns in base tables' primary keys in the target list.
+ *
+ * Returns a Bitmapset of the column attnos of the primary key's columns of
+ * tables that used in the query.  The attnos are offset by
+ * FirstLowInvalidHeapAttributeNumber as same as get_primary_key_attnos.
+ *
+ * If any table has no primary key or any primary key's columns is not in
+ * the target list, return NULL.  We also return NULL if any pkey constraint
+ * is deferrable.
+ *
+ * constraintList is set to a list of the OIDs of the pkey constraints.
+ */
+static Bitmapset *
+get_primary_key_attnos_from_query(Query *query, List **constraintList)
+{
+	List *key_attnos_list = NIL;
+	ListCell *lc;
+	int i;
+	Bitmapset *keys = NULL;
+	Relids	rels_in_from;
+
+	/*
+	 * Collect primary key attributes from all tables used in query. The key attributes
+	 * sets for each table are stored in key_attnos_list in order by RTE index.
+	 */
+	foreach(lc, query->rtable)
+	{
+		RangeTblEntry *r = (RangeTblEntry*) lfirst(lc);
+		Bitmapset *key_attnos;
+		bool	has_pkey = true;
+
+		/* for tables, call get_primary_key_attnos */
+		if (r->rtekind == RTE_RELATION)
+		{
+			Oid constraintOid;
+			key_attnos = get_primary_key_attnos(r->relid, false, &constraintOid);
+			*constraintList = lappend_oid(*constraintList, constraintOid);
+			has_pkey = (key_attnos != NULL);
+		}
+		/* for other RTEs, store NULL into key_attnos_list */
+		else
+			key_attnos = NULL;
+
+		/*
+		 * If any table or subquery has no primary key or its pkey constraint is deferrable,
+		 * we cannot get key attributes for this query, so return NULL.
+		 */
+		if (!has_pkey)
+			return NULL;
+
+		key_attnos_list = lappend(key_attnos_list, key_attnos);
+	}
+
+	/* Collect key attributes appearing in the target list */
+	i = 1;
+	foreach(lc, query->targetList)
+	{
+		TargetEntry *tle = (TargetEntry *) flatten_join_alias_vars(NULL, query, lfirst(lc));
+
+		if (IsA(tle->expr, Var))
+		{
+			Var *var = (Var*) tle->expr;
+			Bitmapset *key_attnos = list_nth(key_attnos_list, var->varno - 1);
+
+			/* check if this attribute is from a base table's primary key */
+			if (bms_is_member(var->varattno - FirstLowInvalidHeapAttributeNumber, key_attnos))
+			{
+				/*
+				 * Remove found key attributes from key_attnos_list, and add this
+				 * to the result list.
+				 */
+				key_attnos = bms_del_member(key_attnos, var->varattno - FirstLowInvalidHeapAttributeNumber);
+				if (bms_is_empty(key_attnos))
+				{
+					key_attnos_list = list_delete_nth_cell(key_attnos_list, var->varno - 1);
+					key_attnos_list = list_insert_nth(key_attnos_list, var->varno - 1, NULL);
+				}
+				keys = bms_add_member(keys, i - FirstLowInvalidHeapAttributeNumber);
+			}
+		}
+		i++;
+	}
+
+	/* Collect RTE indexes of relations appearing in the FROM clause */
+	rels_in_from = get_relids_in_jointree((Node *) query->jointree, false, false);
+
+	/*
+	 * Check if all key attributes of relations in FROM are appearing in the target
+	 * list.  If an attribute remains in key_attnos_list in spite of the table is used
+	 * in FROM clause, the target is missing this key attribute, so we return NULL.
+	 */
+	i = 1;
+	foreach(lc, key_attnos_list)
+	{
+		Bitmapset *bms = (Bitmapset *)lfirst(lc);
+		if (!bms_is_empty(bms) && bms_is_member(i, rels_in_from))
+			return NULL;
+		i++;
+	}
+
+	return keys;
+}
diff --git a/src/backend/commands/matview.c b/src/backend/commands/matview.c
index 6d09b75556..1061c37b2c 100644
--- a/src/backend/commands/matview.c
+++ b/src/backend/commands/matview.c
@@ -23,23 +23,35 @@
 #include "catalog/indexing.h"
 #include "catalog/namespace.h"
 #include "catalog/pg_am.h"
+#include "catalog/pg_depend.h"
+#include "catalog/pg_trigger.h"
 #include "catalog/pg_opclass.h"
 #include "commands/cluster.h"
 #include "commands/matview.h"
 #include "commands/tablecmds.h"
 #include "commands/tablespace.h"
+#include "commands/createas.h"
 #include "executor/executor.h"
 #include "executor/spi.h"
+#include "executor/tstoreReceiver.h"
 #include "miscadmin.h"
+#include "nodes/makefuncs.h"
+#include "parser/analyze.h"
+#include "parser/parse_clause.h"
+#include "parser/parse_func.h"
+#include "parser/parse_relation.h"
 #include "pgstat.h"
 #include "rewrite/rewriteHandler.h"
+#include "rewrite/rowsecurity.h"
 #include "storage/lmgr.h"
 #include "tcop/tcopprot.h"
 #include "utils/builtins.h"
+#include "utils/fmgroids.h"
 #include "utils/lsyscache.h"
 #include "utils/rel.h"
 #include "utils/snapmgr.h"
 #include "utils/syscache.h"
+#include "utils/typcache.h"
 
 
 typedef struct
@@ -53,6 +65,52 @@ typedef struct
 	BulkInsertState bistate;	/* bulk insert state */
 } DR_transientrel;
 
+#define MV_INIT_QUERYHASHSIZE	16
+
+/*
+ * MV_TriggerHashEntry
+ *
+ * Hash entry for base tables on which IVM trigger is invoked
+ */
+typedef struct MV_TriggerHashEntry
+{
+	Oid	matview_id;			/* OID of the materialized view */
+	int	before_trig_count;	/* count of before triggers invoked */
+	int	after_trig_count;	/* count of after triggers invoked */
+
+	Snapshot	snapshot;	/* Snapshot just before table change */
+
+	List   *tables;		/* List of MV_TriggerTable */
+	bool	has_old;	/* tuples are deleted from any table? */
+	bool	has_new;	/* tuples are inserted into any table? */
+} MV_TriggerHashEntry;
+
+/*
+ * MV_TriggerTable
+ *
+ * IVM related data for tables on which the trigger is invoked.
+ */
+typedef struct MV_TriggerTable
+{
+	Oid		table_id;			/* OID of the modified table */
+	List   *old_tuplestores;	/* tuplestores for deleted tuples */
+	List   *new_tuplestores;	/* tuplestores for inserted tuples */
+
+	List   *rte_indexes;		/* List of RTE index of the modified table */
+	RangeTblEntry *original_rte;	/* the original RTE saved before rewriting query */
+
+	Relation	rel;			/* relation of the modified table */
+	TupleTableSlot *slot;		/* for checking visibility in the pre-state table */
+} MV_TriggerTable;
+
+static HTAB *mv_trigger_info = NULL;
+
+static bool in_delta_calculation = false;
+
+/* ENR name for materialized view delta */
+#define NEW_DELTA_ENRNAME "new_delta"
+#define OLD_DELTA_ENRNAME "old_delta"
+
 static int	matview_maintenance_depth = 0;
 
 static void transientrel_startup(DestReceiver *self, int operation, TupleDesc typeinfo);
@@ -60,7 +118,9 @@ static bool transientrel_receive(TupleTableSlot *slot, DestReceiver *self);
 static void transientrel_shutdown(DestReceiver *self);
 static void transientrel_destroy(DestReceiver *self);
 static uint64 refresh_matview_datafill(DestReceiver *dest, Query *query,
-									   const char *queryString);
+						 QueryEnvironment *queryEnv,
+						 TupleDesc *resultTupleDesc,
+						 const char *queryString);
 static char *make_temptable_name_n(char *tempname, int n);
 static void refresh_by_match_merge(Oid matviewOid, Oid tempOid, Oid relowner,
 								   int save_sec_context);
@@ -68,6 +128,37 @@ static void refresh_by_heap_swap(Oid matviewOid, Oid OIDNewHeap, char relpersist
 static bool is_usable_unique_index(Relation indexRel);
 static void OpenMatViewIncrementalMaintenance(void);
 static void CloseMatViewIncrementalMaintenance(void);
+static Query *get_matview_query(Relation matviewRel);
+
+static Query *rewrite_query_for_preupdate_state(Query *query, List *tables,
+								  ParseState *pstate, Oid matviewid);
+static void register_delta_ENRs(ParseState *pstate, Query *query, List *tables);
+static char *make_delta_enr_name(const char *prefix, Oid relid, int count);
+static RangeTblEntry *get_prestate_rte(RangeTblEntry *rte, MV_TriggerTable *table,
+				 QueryEnvironment *queryEnv, Oid matviewid);
+static RangeTblEntry *replace_rte_with_delta(RangeTblEntry *rte, MV_TriggerTable *table, bool is_new,
+		   QueryEnvironment *queryEnv);
+static Query *rewrite_query_for_counting(Query *query, ParseState *pstate);
+
+static void calc_delta(MV_TriggerTable *table, int rte_index, Query *query,
+			DestReceiver *dest_old, DestReceiver *dest_new,
+			TupleDesc *tupdesc_old, TupleDesc *tupdesc_new,
+			QueryEnvironment *queryEnv);
+static Query *rewrite_query_for_postupdate_state(Query *query, MV_TriggerTable *table, int rte_index);
+
+static void apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *new_tuplestores,
+			TupleDesc tupdesc_old, TupleDesc tupdesc_new,
+			Query *query);
+static void apply_old_delta(const char *matviewname, const char *deltaname_old,
+				List *keys);
+static void apply_new_delta(const char *matviewname, const char *deltaname_new,
+				StringInfo target_list);
+static char *get_matching_condition_string(List *keys);
+static void generate_equal(StringInfo querybuf, Oid opttype,
+			   const char *leftop, const char *rightop);
+
+static void mv_InitHashTables(void);
+static void clean_up_IVM_hash_entry(MV_TriggerHashEntry *entry, bool is_abort);
 
 /*
  * SetMatViewPopulatedState
@@ -109,6 +200,46 @@ SetMatViewPopulatedState(Relation relation, bool newstate)
 	CommandCounterIncrement();
 }
 
+/*
+ * SetMatViewIVMState
+ *		Mark a materialized view as IVM, or not.
+ *
+ * NOTE: caller must be holding an appropriate lock on the relation.
+ */
+void
+SetMatViewIVMState(Relation relation, bool newstate)
+{
+	Relation	pgrel;
+	HeapTuple	tuple;
+
+	Assert(relation->rd_rel->relkind == RELKIND_MATVIEW);
+
+	/*
+	 * Update relation's pg_class entry.  Crucial side-effect: other backends
+	 * (and this one too!) are sent SI message to make them rebuild relcache
+	 * entries.
+	 */
+	pgrel = table_open(RelationRelationId, RowExclusiveLock);
+	tuple = SearchSysCacheCopy1(RELOID,
+								ObjectIdGetDatum(RelationGetRelid(relation)));
+	if (!HeapTupleIsValid(tuple))
+		elog(ERROR, "cache lookup failed for relation %u",
+			 RelationGetRelid(relation));
+
+	((Form_pg_class) GETSTRUCT(tuple))->relisivm = newstate;
+
+	CatalogTupleUpdate(pgrel, &tuple->t_self, tuple);
+
+	heap_freetuple(tuple);
+	table_close(pgrel, RowExclusiveLock);
+
+	/*
+	 * Advance command counter to make the updated pg_class row locally
+	 * visible.
+	 */
+	CommandCounterIncrement();
+}
+
 /*
  * ExecRefreshMatView -- execute a REFRESH MATERIALIZED VIEW command
  *
@@ -135,8 +266,6 @@ ExecRefreshMatView(RefreshMatViewStmt *stmt, const char *queryString,
 {
 	Oid			matviewOid;
 	Relation	matviewRel;
-	RewriteRule *rule;
-	List	   *actions;
 	Query	   *dataQuery;
 	Oid			tableSpace;
 	Oid			relowner;
@@ -150,6 +279,7 @@ ExecRefreshMatView(RefreshMatViewStmt *stmt, const char *queryString,
 	int			save_sec_context;
 	int			save_nestlevel;
 	ObjectAddress address;
+	bool oldPopulated;
 
 	/* Determine strength of lock needed. */
 	concurrent = stmt->concurrent;
@@ -176,6 +306,8 @@ ExecRefreshMatView(RefreshMatViewStmt *stmt, const char *queryString,
 	save_nestlevel = NewGUCNestLevel();
 	RestrictSearchPath();
 
+	oldPopulated = RelationIsPopulated(matviewRel);
+
 	/* Make sure it is a materialized view. */
 	if (matviewRel->rd_rel->relkind != RELKIND_MATVIEW)
 		ereport(ERROR,
@@ -196,32 +328,9 @@ ExecRefreshMatView(RefreshMatViewStmt *stmt, const char *queryString,
 				 errmsg("%s and %s options cannot be used together",
 						"CONCURRENTLY", "WITH NO DATA")));
 
-	/*
-	 * Check that everything is correct for a refresh. Problems at this point
-	 * are internal errors, so elog is sufficient.
-	 */
-	if (matviewRel->rd_rel->relhasrules == false ||
-		matviewRel->rd_rules->numLocks < 1)
-		elog(ERROR,
-			 "materialized view \"%s\" is missing rewrite information",
-			 RelationGetRelationName(matviewRel));
-
-	if (matviewRel->rd_rules->numLocks > 1)
-		elog(ERROR,
-			 "materialized view \"%s\" has too many rules",
-			 RelationGetRelationName(matviewRel));
 
-	rule = matviewRel->rd_rules->rules[0];
-	if (rule->event != CMD_SELECT || !(rule->isInstead))
-		elog(ERROR,
-			 "the rule for materialized view \"%s\" is not a SELECT INSTEAD OF rule",
-			 RelationGetRelationName(matviewRel));
+	dataQuery = get_matview_query(matviewRel);
 
-	actions = rule->actions;
-	if (list_length(actions) != 1)
-		elog(ERROR,
-			 "the rule for materialized view \"%s\" is not a single action",
-			 RelationGetRelationName(matviewRel));
 
 	/*
 	 * Check that there is a unique index with no WHERE clause on one or more
@@ -256,12 +365,6 @@ ExecRefreshMatView(RefreshMatViewStmt *stmt, const char *queryString,
 					 errhint("Create a unique index with no WHERE clause on one or more columns of the materialized view.")));
 	}
 
-	/*
-	 * The stored query was rewritten at the time of the MV definition, but
-	 * has not been scribbled on by the planner.
-	 */
-	dataQuery = linitial_node(Query, actions);
-
 	/*
 	 * Check for active uses of the relation in the current transaction, such
 	 * as open scans.
@@ -289,6 +392,74 @@ ExecRefreshMatView(RefreshMatViewStmt *stmt, const char *queryString,
 		relpersistence = matviewRel->rd_rel->relpersistence;
 	}
 
+	/* delete IMMV triggers. */
+	if (RelationIsIVM(matviewRel) && stmt->skipData )
+	{
+		Relation	tgRel;
+		Relation	depRel;
+		ScanKeyData key;
+		SysScanDesc scan;
+		HeapTuple	tup;
+		ObjectAddresses *immv_triggers;
+
+		immv_triggers = new_object_addresses();
+
+		tgRel = table_open(TriggerRelationId, RowExclusiveLock);
+		depRel = table_open(DependRelationId, RowExclusiveLock);
+
+		/* search triggers that depends on IMMV. */
+		ScanKeyInit(&key,
+					Anum_pg_depend_refobjid,
+					BTEqualStrategyNumber, F_OIDEQ,
+					ObjectIdGetDatum(matviewOid));
+		scan = systable_beginscan(depRel, DependReferenceIndexId, true,
+								  NULL, 1, &key);
+		while ((tup = systable_getnext(scan)) != NULL)
+		{
+			ObjectAddress obj;
+			Form_pg_depend foundDep = (Form_pg_depend) GETSTRUCT(tup);
+
+			if (foundDep->classid == TriggerRelationId)
+			{
+				HeapTuple	tgtup;
+				ScanKeyData tgkey[1];
+				SysScanDesc tgscan;
+				Form_pg_trigger tgform;
+
+				/* Find the trigger name. */
+				ScanKeyInit(&tgkey[0],
+							Anum_pg_trigger_oid,
+							BTEqualStrategyNumber, F_OIDEQ,
+							ObjectIdGetDatum(foundDep->objid));
+
+				tgscan = systable_beginscan(tgRel, TriggerOidIndexId, true,
+											NULL, 1, tgkey);
+				tgtup = systable_getnext(tgscan);
+				if (!HeapTupleIsValid(tgtup))
+					elog(ERROR, "could not find tuple for immv trigger %u", foundDep->objid);
+
+				tgform = (Form_pg_trigger) GETSTRUCT(tgtup);
+
+				/* If trigger is created by IMMV, delete it. */
+				if (strncmp(NameStr(tgform->tgname), "IVM_trigger_", 12) == 0)
+				{
+					obj.classId = foundDep->classid;
+					obj.objectId = foundDep->objid;
+					obj.objectSubId = foundDep->refobjsubid;
+					add_exact_object_address(&obj, immv_triggers);
+				}
+				systable_endscan(tgscan);
+			}
+		}
+		systable_endscan(scan);
+
+		performMultipleDeletions(immv_triggers, DROP_RESTRICT, PERFORM_DELETION_INTERNAL);
+
+		table_close(depRel, RowExclusiveLock);
+		table_close(tgRel, RowExclusiveLock);
+		free_object_addresses(immv_triggers);
+	}
+
 	/*
 	 * Create the transient table that will receive the regenerated data. Lock
 	 * it against access by any other process until commit (by which time it
@@ -302,7 +473,7 @@ ExecRefreshMatView(RefreshMatViewStmt *stmt, const char *queryString,
 
 	/* Generate the data, if wanted. */
 	if (!stmt->skipData)
-		processed = refresh_matview_datafill(dest, dataQuery, queryString);
+		processed = refresh_matview_datafill(dest, dataQuery, NULL, NULL, queryString);
 
 	/* Make the matview match the newly generated data. */
 	if (concurrent)
@@ -337,6 +508,12 @@ ExecRefreshMatView(RefreshMatViewStmt *stmt, const char *queryString,
 			pgstat_count_heap_insert(matviewRel, processed);
 	}
 
+	if (!stmt->skipData && RelationIsIVM(matviewRel) && !oldPopulated)
+	{
+		CreateIndexOnIMMV(dataQuery, matviewRel);
+		CreateIvmTriggersOnBaseTables(dataQuery, matviewOid);
+	}
+
 	table_close(matviewRel, NoLock);
 
 	/* Roll back any GUC changes */
@@ -371,6 +548,8 @@ ExecRefreshMatView(RefreshMatViewStmt *stmt, const char *queryString,
  */
 static uint64
 refresh_matview_datafill(DestReceiver *dest, Query *query,
+						 QueryEnvironment *queryEnv,
+						 TupleDesc *resultTupleDesc,
 						 const char *queryString)
 {
 	List	   *rewritten;
@@ -407,7 +586,7 @@ refresh_matview_datafill(DestReceiver *dest, Query *query,
 	/* Create a QueryDesc, redirecting output to our tuple receiver */
 	queryDesc = CreateQueryDesc(plan, queryString,
 								GetActiveSnapshot(), InvalidSnapshot,
-								dest, NULL, NULL, 0);
+								dest, NULL, queryEnv ? queryEnv: NULL, 0);
 
 	/* call ExecutorStart to prepare the plan for execution */
 	ExecutorStart(queryDesc, 0);
@@ -417,6 +596,9 @@ refresh_matview_datafill(DestReceiver *dest, Query *query,
 
 	processed = queryDesc->estate->es_processed;
 
+	if (resultTupleDesc)
+		*resultTupleDesc = CreateTupleDescCopy(queryDesc->tupDesc);
+
 	/* and clean up */
 	ExecutorFinish(queryDesc);
 	ExecutorEnd(queryDesc);
@@ -950,3 +1132,1219 @@ CloseMatViewIncrementalMaintenance(void)
 	matview_maintenance_depth--;
 	Assert(matview_maintenance_depth >= 0);
 }
+
+/*
+ * get_matview_query - get the Query from a matview's _RETURN rule.
+ */
+static Query *
+get_matview_query(Relation matviewRel)
+{
+	RewriteRule *rule;
+	List * actions;
+
+	/*
+	 * Check that everything is correct for a refresh. Problems at this point
+	 * are internal errors, so elog is sufficient.
+	 */
+	if (matviewRel->rd_rel->relhasrules == false ||
+		matviewRel->rd_rules->numLocks < 1)
+		elog(ERROR,
+			 "materialized view \"%s\" is missing rewrite information",
+			 RelationGetRelationName(matviewRel));
+
+	if (matviewRel->rd_rules->numLocks > 1)
+		elog(ERROR,
+			 "materialized view \"%s\" has too many rules",
+			 RelationGetRelationName(matviewRel));
+
+	rule = matviewRel->rd_rules->rules[0];
+	if (rule->event != CMD_SELECT || !(rule->isInstead))
+		elog(ERROR,
+			 "the rule for materialized view \"%s\" is not a SELECT INSTEAD OF rule",
+			 RelationGetRelationName(matviewRel));
+
+	actions = rule->actions;
+	if (list_length(actions) != 1)
+		elog(ERROR,
+			 "the rule for materialized view \"%s\" is not a single action",
+			 RelationGetRelationName(matviewRel));
+
+	/*
+	 * The stored query was rewritten at the time of the MV definition, but
+	 * has not been scribbled on by the planner.
+	 */
+	return linitial_node(Query, actions);
+}
+
+
+/* ----------------------------------------------------
+ *		Incremental View Maintenance routines
+ * ---------------------------------------------------
+ */
+
+/*
+ * IVM_immediate_before
+ *
+ * IVM trigger function invoked before base table is modified. If this is
+ * invoked firstly in the same statement, we save the transaction id and the
+ * command id at that time.
+ */
+Datum
+IVM_immediate_before(PG_FUNCTION_ARGS)
+{
+	TriggerData *trigdata = (TriggerData *) fcinfo->context;
+	char	   *matviewOid_text = trigdata->tg_trigger->tgargs[0];
+	char	   *ex_lock_text = trigdata->tg_trigger->tgargs[1];
+	Oid			matviewOid;
+	MV_TriggerHashEntry *entry;
+	bool	found;
+	bool	ex_lock;
+
+	matviewOid = DatumGetObjectId(DirectFunctionCall1(oidin, CStringGetDatum(matviewOid_text)));
+	ex_lock = DatumGetBool(DirectFunctionCall1(boolin, CStringGetDatum(ex_lock_text)));
+
+	/* If the view has more than one tables, we have to use an exclusive lock. */
+	if (ex_lock)
+	{
+		/*
+		 * Wait for concurrent transactions which update this materialized view at
+		 * READ COMMITED. This is needed to see changes committed in other
+		 * transactions. No wait and raise an error at REPEATABLE READ or
+		 * SERIALIZABLE to prevent update anomalies of matviews.
+		 * XXX: dead-lock is possible here.
+		 */
+		if (!IsolationUsesXactSnapshot())
+			LockRelationOid(matviewOid, ExclusiveLock);
+		else if (!ConditionalLockRelationOid(matviewOid, ExclusiveLock))
+		{
+			/* try to throw error by name; relation could be deleted... */
+			char	   *relname = get_rel_name(matviewOid);
+
+			if (!relname)
+				ereport(ERROR,
+						(errcode(ERRCODE_LOCK_NOT_AVAILABLE),
+						errmsg("could not obtain lock on materialized view during incremental maintenance")));
+
+			ereport(ERROR,
+					(errcode(ERRCODE_LOCK_NOT_AVAILABLE),
+					errmsg("could not obtain lock on materialized view \"%s\" during incremental maintenance",
+							relname)));
+		}
+	}
+	else
+		LockRelationOid(matviewOid, RowExclusiveLock);
+
+	/*
+	 * On the first call initialize the hashtable
+	 */
+	if (!mv_trigger_info)
+		mv_InitHashTables();
+
+	entry = (MV_TriggerHashEntry *) hash_search(mv_trigger_info,
+											  (void *) &matviewOid,
+											  HASH_ENTER, &found);
+
+	/* On the first BEFORE to update the view, initialize trigger data */
+	if (!found)
+	{
+		/*
+		 * Get a snapshot just before the table was modified for checking
+		 * tuple visibility in the pre-update state of the table.
+		 */
+		Snapshot snapshot = GetActiveSnapshot();
+
+		entry->matview_id = matviewOid;
+		entry->before_trig_count = 0;
+		entry->after_trig_count = 0;
+		entry->snapshot = RegisterSnapshot(snapshot);
+		entry->tables = NIL;
+		entry->has_old = false;
+		entry->has_new = false;
+	}
+
+	entry->before_trig_count++;
+
+	return PointerGetDatum(NULL);
+}
+
+/*
+ * IVM_immediate_maintenance
+ *
+ * IVM trigger function invoked after base table is modified.
+ * For each table, tuplestores of transition tables are collected.
+ * and after the last modification
+ */
+Datum
+IVM_immediate_maintenance(PG_FUNCTION_ARGS)
+{
+	TriggerData *trigdata = (TriggerData *) fcinfo->context;
+	Relation	rel;
+	Oid			relid;
+	Oid			matviewOid;
+	Query	   *query;
+	Query	   *rewritten = NULL;
+	char	   *matviewOid_text = trigdata->tg_trigger->tgargs[0];
+	Relation	matviewRel;
+	int old_depth = matview_maintenance_depth;
+
+	Oid			relowner;
+	Tuplestorestate *old_tuplestore = NULL;
+	Tuplestorestate *new_tuplestore = NULL;
+	DestReceiver *dest_new = NULL, *dest_old = NULL;
+	Oid			save_userid;
+	int			save_sec_context;
+	int			save_nestlevel;
+
+	MV_TriggerHashEntry *entry;
+	MV_TriggerTable		*table;
+	bool	found;
+
+	ParseState		 *pstate;
+	QueryEnvironment *queryEnv = create_queryEnv();
+	MemoryContext	oldcxt;
+	ListCell   *lc;
+	int			i;
+
+
+	/* Create a ParseState for rewriting the view definition query */
+	pstate = make_parsestate(NULL);
+	pstate->p_queryEnv = queryEnv;
+	pstate->p_expr_kind = EXPR_KIND_SELECT_TARGET;
+
+	rel = trigdata->tg_relation;
+	relid = rel->rd_id;
+
+	matviewOid = DatumGetObjectId(DirectFunctionCall1(oidin, CStringGetDatum(matviewOid_text)));
+
+	/*
+	 * On the first call initialize the hashtable
+	 */
+	if (!mv_trigger_info)
+		mv_InitHashTables();
+
+	/* get the entry for this materialized view */
+	entry = (MV_TriggerHashEntry *) hash_search(mv_trigger_info,
+											  (void *) &matviewOid,
+											  HASH_FIND, &found);
+	Assert (found && entry != NULL);
+	entry->after_trig_count++;
+
+	/* search the entry for the modified table and create new entry if not found */
+	found = false;
+	foreach(lc, entry->tables)
+	{
+		table = (MV_TriggerTable *) lfirst(lc);
+		if (table->table_id == relid)
+		{
+			found = true;
+			break;
+		}
+	}
+	if (!found)
+	{
+		oldcxt = MemoryContextSwitchTo(TopTransactionContext);
+
+		table = (MV_TriggerTable *) palloc0(sizeof(MV_TriggerTable));
+		table->table_id = relid;
+		table->old_tuplestores = NIL;
+		table->new_tuplestores = NIL;
+		table->rte_indexes = NIL;
+		table->slot = MakeSingleTupleTableSlot(RelationGetDescr(rel), table_slot_callbacks(rel));
+		table->rel = table_open(RelationGetRelid(rel), NoLock);
+		entry->tables = lappend(entry->tables, table);
+
+		MemoryContextSwitchTo(oldcxt);
+	}
+
+	/* Save the transition tables and make a request to not free immediately */
+	if (trigdata->tg_oldtable)
+	{
+		oldcxt = MemoryContextSwitchTo(TopTransactionContext);
+		table->old_tuplestores = lappend(table->old_tuplestores, trigdata->tg_oldtable);
+		entry->has_old = true;
+		MemoryContextSwitchTo(oldcxt);
+	}
+	if (trigdata->tg_newtable)
+	{
+		oldcxt = MemoryContextSwitchTo(TopTransactionContext);
+		table->new_tuplestores = lappend(table->new_tuplestores, trigdata->tg_newtable);
+		entry->has_new = true;
+		MemoryContextSwitchTo(oldcxt);
+	}
+	if (entry->has_new || entry->has_old)
+	{
+		CmdType cmd;
+
+		if (TRIGGER_FIRED_BY_INSERT(trigdata->tg_event))
+			cmd = CMD_INSERT;
+		else if (TRIGGER_FIRED_BY_DELETE(trigdata->tg_event))
+			cmd = CMD_DELETE;
+		else if (TRIGGER_FIRED_BY_UPDATE(trigdata->tg_event))
+			cmd = CMD_UPDATE;
+		else
+			elog(ERROR,"unsupported trigger type");
+
+		/* Prolong lifespan of transition tables to the end of the last AFTER trigger */
+		SetTransitionTablePreserved(relid, cmd);
+	}
+
+
+	/* If this is not the last AFTER trigger call, immediately exit. */
+	Assert (entry->before_trig_count >= entry->after_trig_count);
+	if (entry->before_trig_count != entry->after_trig_count)
+		return PointerGetDatum(NULL);
+
+	/*
+	 * If this is the last AFTER trigger call, continue and update the view.
+	 */
+
+	/*
+	 * Advance command counter to make the updated base table row locally
+	 * visible.
+	 */
+	CommandCounterIncrement();
+
+	matviewRel = table_open(matviewOid, NoLock);
+
+	/* Make sure it is a materialized view. */
+	Assert(matviewRel->rd_rel->relkind == RELKIND_MATVIEW);
+
+	/*
+	 * Get and push the latast snapshot to see any changes which is committed
+	 * during waiting in other transactions at READ COMMITTED level.
+	 */
+	PushActiveSnapshot(GetTransactionSnapshot());
+
+	/*
+	 * Check for active uses of the relation in the current transaction, such
+	 * as open scans.
+	 *
+	 * NB: We count on this to protect us against problems with refreshing the
+	 * data using TABLE_INSERT_FROZEN.
+	 */
+	CheckTableNotInUse(matviewRel, "refresh a materialized view incrementally");
+
+	/*
+	 * Switch to the owner's userid, so that any functions are run as that
+	 * user.  Also arrange to make GUC variable changes local to this command.
+	 * We will switch modes when we are about to execute user code.
+	 */
+	relowner = matviewRel->rd_rel->relowner;
+	GetUserIdAndSecContext(&save_userid, &save_sec_context);
+	SetUserIdAndSecContext(relowner,
+						   save_sec_context | SECURITY_RESTRICTED_OPERATION);
+	save_nestlevel = NewGUCNestLevel();
+
+	/* get view query*/
+	query = get_matview_query(matviewRel);
+
+	/*
+	 * When a base table is truncated, the view content will be empty if the
+	 * view definition query does not contain an aggregate without a GROUP clause.
+	 * Therefore, such views can be truncated.
+	 */
+	if (TRIGGER_FIRED_BY_TRUNCATE(trigdata->tg_event))
+	{
+		ExecuteTruncateGuts(list_make1(matviewRel), list_make1_oid(matviewOid),
+							NIL, DROP_RESTRICT, false, false);
+
+		/* Clean up hash entry and delete tuplestores */
+		clean_up_IVM_hash_entry(entry, false);
+
+		/* Pop the original snapshot. */
+		PopActiveSnapshot();
+
+		table_close(matviewRel, NoLock);
+
+		/* Roll back any GUC changes */
+		AtEOXact_GUC(false, save_nestlevel);
+
+		/* Restore userid and security context */
+		SetUserIdAndSecContext(save_userid, save_sec_context);
+
+		return PointerGetDatum(NULL);
+	}
+
+	/*
+	 * rewrite query for calculating deltas
+	 */
+
+	rewritten = copyObject(query);
+
+	/* Replace resnames in a target list with materialized view's attnames */
+	i = 0;
+	foreach (lc, rewritten->targetList)
+	{
+		TargetEntry *tle = (TargetEntry *) lfirst(lc);
+		Form_pg_attribute attr = TupleDescAttr(matviewRel->rd_att, i);
+		char *resname = NameStr(attr->attname);
+
+		tle->resname = pstrdup(resname);
+		i++;
+	}
+
+	/* Set all tables in the query to pre-update state */
+	rewritten = rewrite_query_for_preupdate_state(rewritten, entry->tables,
+												  pstate, matviewOid);
+	/* Rewrite for counting duplicated tuples */
+	rewritten = rewrite_query_for_counting(rewritten, pstate);
+
+	/* Create tuplestores to store view deltas */
+	if (entry->has_old)
+	{
+		oldcxt = MemoryContextSwitchTo(TopTransactionContext);
+
+		old_tuplestore = tuplestore_begin_heap(false, false, work_mem);
+		dest_old = CreateDestReceiver(DestTuplestore);
+		SetTuplestoreDestReceiverParams(dest_old,
+									old_tuplestore,
+									TopTransactionContext,
+									false,
+									NULL,
+									NULL);
+
+		MemoryContextSwitchTo(oldcxt);
+	}
+	if (entry->has_new)
+	{
+		oldcxt = MemoryContextSwitchTo(TopTransactionContext);
+
+		new_tuplestore = tuplestore_begin_heap(false, false, work_mem);
+		dest_new = CreateDestReceiver(DestTuplestore);
+		SetTuplestoreDestReceiverParams(dest_new,
+									new_tuplestore,
+									TopTransactionContext,
+									false,
+									NULL,
+									NULL);
+		MemoryContextSwitchTo(oldcxt);
+	}
+
+	/* for all modified tables */
+	foreach(lc, entry->tables)
+	{
+		ListCell *lc2;
+
+		table = (MV_TriggerTable *) lfirst(lc);
+
+		/* loop for self-join */
+		foreach(lc2, table->rte_indexes)
+		{
+			int	rte_index = lfirst_int(lc2);
+			TupleDesc		tupdesc_old;
+			TupleDesc		tupdesc_new;
+
+			/* calculate delta tables */
+			calc_delta(table, rte_index, rewritten, dest_old, dest_new,
+					   &tupdesc_old, &tupdesc_new, queryEnv);
+
+			/* Set the table in the query to post-update state */
+			rewritten = rewrite_query_for_postupdate_state(rewritten, table, rte_index);
+
+			PG_TRY();
+			{
+				/* apply the delta tables to the materialized view */
+				apply_delta(matviewOid, old_tuplestore, new_tuplestore,
+							tupdesc_old, tupdesc_new, query);
+			}
+			PG_CATCH();
+			{
+				matview_maintenance_depth = old_depth;
+				PG_RE_THROW();
+			}
+			PG_END_TRY();
+
+			/* clear view delta tuplestores */
+			if (old_tuplestore)
+				tuplestore_clear(old_tuplestore);
+			if (new_tuplestore)
+				tuplestore_clear(new_tuplestore);
+		}
+	}
+
+	/* Clean up hash entry and delete tuplestores */
+	clean_up_IVM_hash_entry(entry, false);
+	if (old_tuplestore)
+	{
+		dest_old->rDestroy(dest_old);
+		tuplestore_end(old_tuplestore);
+	}
+	if (new_tuplestore)
+	{
+		dest_new->rDestroy(dest_new);
+		tuplestore_end(new_tuplestore);
+	}
+
+	/* Pop the original snapshot. */
+	PopActiveSnapshot();
+
+	table_close(matviewRel, NoLock);
+
+	/* Roll back any GUC changes */
+	AtEOXact_GUC(false, save_nestlevel);
+
+	/* Restore userid and security context */
+	SetUserIdAndSecContext(save_userid, save_sec_context);
+
+	return PointerGetDatum(NULL);
+}
+
+/*
+ * rewrite_query_for_preupdate_state
+ *
+ * Rewrite the query so that base tables' RTEs will represent "pre-update"
+ * state of tables. This is necessary to calculate view delta after multiple
+ * tables are modified.
+ */
+static Query*
+rewrite_query_for_preupdate_state(Query *query, List *tables,
+								  ParseState *pstate, Oid matviewid)
+{
+	ListCell *lc;
+	int num_rte = list_length(query->rtable);
+	int i;
+
+
+	/* register delta ENRs */
+	register_delta_ENRs(pstate, query, tables);
+
+	/* XXX: Is necessary? Is this right timing? */
+	AcquireRewriteLocks(query, true, false);
+
+	i = 1;
+	foreach(lc, query->rtable)
+	{
+		RangeTblEntry *r = (RangeTblEntry*) lfirst(lc);
+
+		ListCell *lc2;
+		foreach(lc2, tables)
+		{
+			MV_TriggerTable *table = (MV_TriggerTable *) lfirst(lc2);
+			/*
+			 * if the modified table is found then replace the original RTE with
+			 * "pre-state" RTE and append its index to the list.
+			 */
+			if (r->relid == table->table_id)
+			{
+				List *securityQuals;
+				List *withCheckOptions;
+				bool  hasRowSecurity;
+				bool  hasSubLinks;
+
+				RangeTblEntry *rte_pre = get_prestate_rte(r, table, pstate->p_queryEnv, matviewid);
+
+				/*
+				 * Set a row security poslicies of the modified table to the subquery RTE which
+				 * represents the pre-update state of the table.
+				 */
+				get_row_security_policies(query, table->original_rte, i,
+										  &securityQuals, &withCheckOptions,
+										  &hasRowSecurity, &hasSubLinks);
+
+				if (hasRowSecurity)
+				{
+					query->hasRowSecurity = true;
+					rte_pre->security_barrier = true;
+				}
+				if (hasSubLinks)
+					query->hasSubLinks = true;
+
+				rte_pre->securityQuals = securityQuals;
+				lfirst(lc) = rte_pre;
+
+				table->rte_indexes = lappend_int(table->rte_indexes, i);
+				break;
+			}
+		}
+
+		/* finish the loop if we processed all RTE included in the original query */
+		if (i++ >= num_rte)
+			break;
+	}
+
+	return query;
+}
+
+/*
+ * register_delta_ENRs
+ *
+ * For all modified tables, make ENRs for their transition tables
+ * and register them to the queryEnv. ENR's RTEs are also appended
+ * into the list in query tree.
+ */
+static void
+register_delta_ENRs(ParseState *pstate, Query *query, List *tables)
+{
+	QueryEnvironment *queryEnv = pstate->p_queryEnv;
+	ListCell *lc;
+	RangeTblEntry	*rte;
+
+	foreach(lc, tables)
+	{
+		MV_TriggerTable *table = (MV_TriggerTable *) lfirst(lc);
+		ListCell *lc2;
+		int count;
+
+		count = 0;
+		foreach(lc2, table->old_tuplestores)
+		{
+			Tuplestorestate *oldtable = (Tuplestorestate *) lfirst(lc2);
+			EphemeralNamedRelation enr =
+				palloc(sizeof(EphemeralNamedRelationData));
+			ParseNamespaceItem *nsitem;
+
+			enr->md.name = make_delta_enr_name("old", table->table_id, count);
+			enr->md.reliddesc = table->table_id;
+			enr->md.tupdesc = NULL;
+			enr->md.enrtype = ENR_NAMED_TUPLESTORE;
+			enr->md.enrtuples = tuplestore_tuple_count(oldtable);
+			enr->reldata = oldtable;
+			register_ENR(queryEnv, enr);
+
+			nsitem = addRangeTableEntryForENR(pstate, makeRangeVar(NULL, enr->md.name, -1), true);
+			rte = nsitem->p_rte;
+
+			query->rtable = lappend(query->rtable, rte);
+
+			count++;
+		}
+
+		count = 0;
+		foreach(lc2, table->new_tuplestores)
+		{
+			Tuplestorestate *newtable = (Tuplestorestate *) lfirst(lc2);
+			EphemeralNamedRelation enr =
+				palloc(sizeof(EphemeralNamedRelationData));
+			ParseNamespaceItem *nsitem;
+
+			enr->md.name = make_delta_enr_name("new", table->table_id, count);
+			enr->md.reliddesc = table->table_id;
+			enr->md.tupdesc = NULL;
+			enr->md.enrtype = ENR_NAMED_TUPLESTORE;
+			enr->md.enrtuples = tuplestore_tuple_count(newtable);
+			enr->reldata = newtable;
+			register_ENR(queryEnv, enr);
+
+			nsitem = addRangeTableEntryForENR(pstate, makeRangeVar(NULL, enr->md.name, -1), true);
+			rte = nsitem->p_rte;
+
+			query->rtable = lappend(query->rtable, rte);
+
+			count++;
+		}
+	}
+}
+
+#define DatumGetItemPointer(X)	 ((ItemPointer) DatumGetPointer(X))
+#define PG_GETARG_ITEMPOINTER(n) DatumGetItemPointer(PG_GETARG_DATUM(n))
+
+/*
+ * ivm_visible_in_prestate
+ *
+ * Check visibility of a tuple specified by the tableoid and item pointer
+ * using the snapshot taken just before the table was modified.
+ */
+Datum
+ivm_visible_in_prestate(PG_FUNCTION_ARGS)
+{
+	Oid			tableoid = PG_GETARG_OID(0);
+	ItemPointer itemPtr = PG_GETARG_ITEMPOINTER(1);
+	Oid			matviewOid = PG_GETARG_OID(2);
+	MV_TriggerHashEntry *entry;
+	MV_TriggerTable		*table = NULL;
+	ListCell   *lc;
+	bool	found;
+	bool	result;
+
+	if (!in_delta_calculation)
+		ereport(ERROR,
+				(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+				 errmsg("ivm_visible_in_prestate can be called only in delta calculation")));
+
+	entry = (MV_TriggerHashEntry *) hash_search(mv_trigger_info,
+											  (void *) &matviewOid,
+											  HASH_FIND, &found);
+	Assert (found && entry != NULL);
+
+	foreach(lc, entry->tables)
+	{
+		table = (MV_TriggerTable *) lfirst(lc);
+		if (table->table_id == tableoid)
+			break;
+	}
+
+	Assert (table != NULL);
+
+	result = table_tuple_fetch_row_version(table->rel, itemPtr, entry->snapshot, table->slot);
+
+	PG_RETURN_BOOL(result);
+}
+
+/*
+ * get_prestate_rte
+ *
+ * Rewrite RTE of the modified table to a subquery which represents
+ * "pre-state" table. The original RTE is saved in table->rte_original.
+ */
+static RangeTblEntry*
+get_prestate_rte(RangeTblEntry *rte, MV_TriggerTable *table,
+				 QueryEnvironment *queryEnv, Oid matviewid)
+{
+	StringInfoData str;
+	RawStmt *raw;
+	Query *subquery;
+	Relation rel;
+	ParseState *pstate;
+	char *relname;
+	int i;
+
+	pstate = make_parsestate(NULL);
+	pstate->p_queryEnv = queryEnv;
+	pstate->p_expr_kind = EXPR_KIND_SELECT_TARGET;
+
+	/*
+	 * We can use NoLock here since AcquireRewriteLocks should
+	 * have locked the relation already.
+	 */
+	rel = table_open(table->table_id, NoLock);
+	relname = quote_qualified_identifier(
+					get_namespace_name(RelationGetNamespace(rel)),
+									   RelationGetRelationName(rel));
+	table_close(rel, NoLock);
+
+	/*
+	 * Filtering inserted row using the snapshot taken before the table
+	 * is modified. ctid is required for maintaining outer join views.
+	 */
+	initStringInfo(&str);
+	appendStringInfo(&str,
+		"SELECT t.* FROM %s t"
+		" WHERE pg_catalog.ivm_visible_in_prestate(t.tableoid, t.ctid ,%d::pg_catalog.oid)",
+			relname, matviewid);
+
+	/*
+	 * Append deleted rows contained in old transition tables.
+	 */
+	for (i = 0; i < list_length(table->old_tuplestores); i++)
+	{
+		appendStringInfo(&str, " UNION ALL ");
+		appendStringInfo(&str," SELECT * FROM %s",
+			make_delta_enr_name("old", table->table_id, i));
+	}
+
+	/* Get a subquery representing pre-state of the table */
+	raw = (RawStmt*)linitial(raw_parser(str.data, RAW_PARSE_DEFAULT));
+	subquery = transformStmt(pstate, raw->stmt);
+
+	/* save the original RTE */
+	table->original_rte = copyObject(rte);
+
+	rte->rtekind = RTE_SUBQUERY;
+	rte->subquery = subquery;
+	rte->security_barrier = false;
+
+	/* Clear fields that should not be set in a subquery RTE */
+	rte->relid = InvalidOid;
+	rte->relkind = 0;
+	rte->rellockmode = 0;
+	rte->tablesample = NULL;
+	rte->perminfoindex = 0;         /* no permission checking for this RTE */
+	rte->inh = false;			/* must not be set for a subquery */
+
+	return rte;
+}
+
+/*
+ * make_delta_enr_name
+ *
+ * Make a name for ENR of a transition table from the base table's oid.
+ * prefix will be "new" or "old" depending on its transition table kind..
+ */
+static char*
+make_delta_enr_name(const char *prefix, Oid relid, int count)
+{
+	char buf[NAMEDATALEN];
+	char *name;
+
+	snprintf(buf, NAMEDATALEN, "__ivm_%s_%u_%u", prefix, relid, count);
+	name = pstrdup(buf);
+
+	return name;
+}
+
+/*
+ * replace_rte_with_delta
+ *
+ * Replace RTE of the modified table with a single table delta that combine its
+ * all transition tables.
+ */
+static RangeTblEntry*
+replace_rte_with_delta(RangeTblEntry *rte, MV_TriggerTable *table, bool is_new,
+					   QueryEnvironment *queryEnv)
+{
+	Oid relid = table->table_id;
+	StringInfoData str;
+	ParseState	*pstate;
+	RawStmt *raw;
+	Query *sub;
+	int		num_tuplestores = list_length(is_new ? table->new_tuplestores : table->old_tuplestores);
+	int		i;
+
+	/* the previous RTE must be a subquery which represents "pre-state" table */
+	Assert(rte->rtekind == RTE_SUBQUERY);
+
+	/* Create a ParseState for rewriting the view definition query */
+	pstate = make_parsestate(NULL);
+	pstate->p_queryEnv = queryEnv;
+	pstate->p_expr_kind = EXPR_KIND_SELECT_TARGET;
+
+	initStringInfo(&str);
+
+	for (i = 0; i < num_tuplestores; i++)
+	{
+		if (i > 0)
+			appendStringInfo(&str, " UNION ALL ");
+
+		appendStringInfo(&str,
+			" SELECT * FROM %s",
+			make_delta_enr_name(is_new ? "new" : "old", relid, i));
+	}
+
+	raw = (RawStmt*)linitial(raw_parser(str.data, RAW_PARSE_DEFAULT));
+	sub = transformStmt(pstate, raw->stmt);
+
+	/*
+	 * Update the subquery so that it represent the combined transition
+	 * table.  Note that we leave the security_barrier and securityQuals
+	 * fields so that the subquery relation can be protected by the RLS
+	 * policy as same as the modified table.
+	 */
+	rte->rtekind = RTE_SUBQUERY;
+	rte->subquery = sub;
+
+	return rte;
+}
+
+/*
+ * rewrite_query_for_counting
+ *
+ * Rewrite query for counting duplicated tuples.
+ */
+static Query *
+rewrite_query_for_counting(Query *query, ParseState *pstate)
+{
+	TargetEntry *tle_count;
+	FuncCall *fn;
+	Node *node;
+
+	/* Add count(*) for counting distinct tuples in views */
+	fn = makeFuncCall(SystemFuncName("count"), NIL, COERCE_EXPLICIT_CALL, -1);
+	fn->agg_star = true;
+	if (!query->groupClause && !query->hasAggs)
+		query->groupClause = transformDistinctClause(NULL, &query->targetList, query->sortClause, false);
+
+	node = ParseFuncOrColumn(pstate, fn->funcname, NIL, NULL, fn, false, -1);
+
+	tle_count = makeTargetEntry((Expr *) node,
+								list_length(query->targetList) + 1,
+								pstrdup("__ivm_count__"),
+								false);
+	query->targetList = lappend(query->targetList, tle_count);
+	query->hasAggs = true;
+
+	return query;
+}
+
+/*
+ * calc_delta
+ *
+ * Calculate view deltas generated under the modification of a table specified
+ * by the RTE index.
+ */
+static void
+calc_delta(MV_TriggerTable *table, int rte_index, Query *query,
+			DestReceiver *dest_old, DestReceiver *dest_new,
+			TupleDesc *tupdesc_old, TupleDesc *tupdesc_new,
+			QueryEnvironment *queryEnv)
+{
+	ListCell *lc = list_nth_cell(query->rtable, rte_index - 1);
+	RangeTblEntry *rte = (RangeTblEntry *) lfirst(lc);
+
+	in_delta_calculation = true;
+
+	/* Generate old delta */
+	if (list_length(table->old_tuplestores) > 0)
+	{
+		/* Replace the modified table with the old delta table and calculate the old view delta. */
+		replace_rte_with_delta(rte, table, false, queryEnv);
+		refresh_matview_datafill(dest_old, query, queryEnv, tupdesc_old, "");
+	}
+
+	/* Generate new delta */
+	if (list_length(table->new_tuplestores) > 0)
+	{
+		/* Replace the modified table with the new delta table and calculate the new view delta*/
+		replace_rte_with_delta(rte, table, true, queryEnv);
+		refresh_matview_datafill(dest_new, query, queryEnv, tupdesc_new, "");
+	}
+
+	in_delta_calculation = false;
+}
+
+/*
+ * rewrite_query_for_postupdate_state
+ *
+ * Rewrite the query so that the specified base table's RTEs will represent
+ * "post-update" state of tables. This is called after the view delta
+ * calculation due to changes on this table finishes.
+ */
+static Query*
+rewrite_query_for_postupdate_state(Query *query, MV_TriggerTable *table, int rte_index)
+{
+	ListCell *lc = list_nth_cell(query->rtable, rte_index - 1);
+
+	/* Retore the original RTE */
+	lfirst(lc) = table->original_rte;
+
+	return query;
+}
+
+/*
+ * apply_delta
+ *
+ * Apply deltas to the materialized view. In outer join cases, this requires
+ * the view maintenance graph.
+ */
+static void
+apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *new_tuplestores,
+			TupleDesc tupdesc_old, TupleDesc tupdesc_new,
+			Query *query)
+{
+	StringInfoData querybuf;
+	StringInfoData target_list_buf;
+	Relation	matviewRel;
+	char	   *matviewname;
+	ListCell	*lc;
+	int			i;
+	List	   *keys = NIL;
+
+
+	/*
+	 * get names of the materialized view and delta tables
+	 */
+
+	matviewRel = table_open(matviewOid, NoLock);
+	matviewname = quote_qualified_identifier(get_namespace_name(RelationGetNamespace(matviewRel)),
+											 RelationGetRelationName(matviewRel));
+
+	/*
+	 * Build parts of the maintenance queries
+	 */
+
+	initStringInfo(&querybuf);
+	initStringInfo(&target_list_buf);
+
+	/* build string of target list */
+	for (i = 0; i < matviewRel->rd_att->natts; i++)
+	{
+		Form_pg_attribute attr = TupleDescAttr(matviewRel->rd_att, i);
+		char   *resname = NameStr(attr->attname);
+
+		if (i != 0)
+			appendStringInfo(&target_list_buf, ", ");
+		appendStringInfo(&target_list_buf, "%s", quote_qualified_identifier(NULL, resname));
+	}
+
+	i = 0;
+	foreach (lc, query->targetList)
+	{
+		TargetEntry *tle = (TargetEntry *) lfirst(lc);
+		Form_pg_attribute attr = TupleDescAttr(matviewRel->rd_att, i);
+
+		i++;
+
+		if (tle->resjunk)
+			continue;
+
+		keys = lappend(keys, attr);
+	}
+
+	/* Start maintaining the materialized view. */
+	OpenMatViewIncrementalMaintenance();
+
+	/* Open SPI context. */
+	if (SPI_connect() != SPI_OK_CONNECT)
+		elog(ERROR, "SPI_connect failed");
+
+	/* For tuple deletion */
+	if (old_tuplestores && tuplestore_tuple_count(old_tuplestores) > 0)
+	{
+		EphemeralNamedRelation enr = palloc(sizeof(EphemeralNamedRelationData));
+		int				rc;
+
+		/* convert tuplestores to ENR, and register for SPI */
+		enr->md.name = pstrdup(OLD_DELTA_ENRNAME);
+		enr->md.reliddesc = InvalidOid;
+		enr->md.tupdesc = tupdesc_old;
+		enr->md.enrtype = ENR_NAMED_TUPLESTORE;
+		enr->md.enrtuples = tuplestore_tuple_count(old_tuplestores);
+		enr->reldata = old_tuplestores;
+
+		rc = SPI_register_relation(enr);
+		if (rc != SPI_OK_REL_REGISTER)
+			elog(ERROR, "SPI_register failed");
+
+		apply_old_delta(matviewname, OLD_DELTA_ENRNAME, keys);
+
+	}
+	/* For tuple insertion */
+	if (new_tuplestores && tuplestore_tuple_count(new_tuplestores) > 0)
+	{
+		EphemeralNamedRelation enr = palloc(sizeof(EphemeralNamedRelationData));
+		int rc;
+
+		/* convert tuplestores to ENR, and register for SPI */
+		enr->md.name = pstrdup(NEW_DELTA_ENRNAME);
+		enr->md.reliddesc = InvalidOid;
+		enr->md.tupdesc = tupdesc_new;;
+		enr->md.enrtype = ENR_NAMED_TUPLESTORE;
+		enr->md.enrtuples = tuplestore_tuple_count(new_tuplestores);
+		enr->reldata = new_tuplestores;
+
+		rc = SPI_register_relation(enr);
+		if (rc != SPI_OK_REL_REGISTER)
+			elog(ERROR, "SPI_register failed");
+
+		/* apply new delta */
+		apply_new_delta(matviewname, NEW_DELTA_ENRNAME, &target_list_buf);
+	}
+
+	/* We're done maintaining the materialized view. */
+	CloseMatViewIncrementalMaintenance();
+
+	table_close(matviewRel, NoLock);
+
+	/* Close SPI context. */
+	if (SPI_finish() != SPI_OK_FINISH)
+		elog(ERROR, "SPI_finish failed");
+}
+
+/*
+ * apply_old_delta
+ *
+ * Execute a query for applying a delta table given by deltname_old
+ * which contains tuples to be deleted from to a materialized view given by
+ * matviewname.  This is used when counting is not required.
+ */
+static void
+apply_old_delta(const char *matviewname, const char *deltaname_old,
+				List *keys)
+{
+	StringInfoData	querybuf;
+	StringInfoData	keysbuf;
+	char   *match_cond;
+	ListCell *lc;
+
+	/* build WHERE condition for searching tuples to be deleted */
+	match_cond = get_matching_condition_string(keys);
+
+	/* build string of keys list */
+	initStringInfo(&keysbuf);
+	foreach (lc, keys)
+	{
+		Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc);
+		char   *resname = NameStr(attr->attname);
+		appendStringInfo(&keysbuf, "%s", quote_qualified_identifier("mv", resname));
+		if (lnext(keys, lc))
+			appendStringInfo(&keysbuf, ", ");
+	}
+
+	/* Search for matching tuples from the view and update or delete if found. */
+	initStringInfo(&querybuf);
+	appendStringInfo(&querybuf,
+	"DELETE FROM %s WHERE ctid IN ("
+		"SELECT tid FROM (SELECT pg_catalog.row_number() over (partition by %s) AS \"__ivm_row_number__\","
+								  "mv.ctid AS tid,"
+								  "diff.\"__ivm_count__\""
+						 "FROM %s AS mv, %s AS diff "
+						 "WHERE %s) v "
+					"WHERE v.\"__ivm_row_number__\" OPERATOR(pg_catalog.<=) v.\"__ivm_count__\")",
+					matviewname,
+					keysbuf.data,
+					matviewname, deltaname_old,
+					match_cond);
+
+	if (SPI_exec(querybuf.data, 0) != SPI_OK_DELETE)
+		elog(ERROR, "SPI_exec failed: %s", querybuf.data);
+}
+
+/*
+ * apply_new_delta
+ *
+ * Execute a query for applying a delta table given by deltname_new
+ * which contains tuples to be inserted into a materialized view given by
+ * matviewname.  This is used when counting is not required.
+ */
+static void
+apply_new_delta(const char *matviewname, const char *deltaname_new,
+				StringInfo target_list)
+{
+	StringInfoData	querybuf;
+
+	/* Search for matching tuples from the view and update or delete if found. */
+	initStringInfo(&querybuf);
+	appendStringInfo(&querybuf,
+					"INSERT INTO %s (%s) SELECT %s FROM ("
+						"SELECT diff.*, pg_catalog.generate_series(1, diff.\"__ivm_count__\")"
+							" AS __ivm_generate_series__ "
+						"FROM %s AS diff) AS v",
+					matviewname, target_list->data, target_list->data,
+					deltaname_new);
+
+	if (SPI_exec(querybuf.data, 0) != SPI_OK_INSERT)
+		elog(ERROR, "SPI_exec failed: %s", querybuf.data);
+}
+
+/*
+ * get_matching_condition_string
+ *
+ * Build a predicate string for looking for a tuple with given keys.
+ */
+static char *
+get_matching_condition_string(List *keys)
+{
+	StringInfoData match_cond;
+	ListCell	*lc;
+
+	/* If there is no key columns, the condition is always true. */
+	if (keys == NIL)
+		return "true";
+
+	initStringInfo(&match_cond);
+	foreach (lc, keys)
+	{
+		Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc);
+		char   *resname = NameStr(attr->attname);
+		char   *mv_resname = quote_qualified_identifier("mv", resname);
+		char   *diff_resname = quote_qualified_identifier("diff", resname);
+		Oid		typid = attr->atttypid;
+
+		/* Considering NULL values, we can not use simple = operator. */
+		appendStringInfo(&match_cond, "(");
+		generate_equal(&match_cond, typid, mv_resname, diff_resname);
+		appendStringInfo(&match_cond, " OR (%s IS NULL AND %s IS NULL))",
+						 mv_resname, diff_resname);
+
+		if (lnext(keys, lc))
+			appendStringInfo(&match_cond, " AND ");
+	}
+
+	return match_cond.data;
+}
+
+/*
+ * generate_equals
+ *
+ * Generate an equality clause using given operands' default equality
+ * operator.
+ */
+static void
+generate_equal(StringInfo querybuf, Oid opttype,
+			   const char *leftop, const char *rightop)
+{
+	TypeCacheEntry *typentry;
+
+	typentry = lookup_type_cache(opttype, TYPECACHE_EQ_OPR);
+	if (!OidIsValid(typentry->eq_opr))
+		ereport(ERROR,
+				(errcode(ERRCODE_UNDEFINED_FUNCTION),
+				 errmsg("could not identify an equality operator for type %s",
+						format_type_be_qualified(opttype))));
+
+	generate_operator_clause(querybuf,
+							 leftop, opttype,
+							 typentry->eq_opr,
+							 rightop, opttype);
+}
+
+/*
+ * mv_InitHashTables
+ */
+static void
+mv_InitHashTables(void)
+{
+	HASHCTL		ctl;
+
+	memset(&ctl, 0, sizeof(ctl));
+	ctl.keysize = sizeof(Oid);
+	ctl.entrysize = sizeof(MV_TriggerHashEntry);
+	mv_trigger_info = hash_create("MV trigger info",
+								 MV_INIT_QUERYHASHSIZE,
+								 &ctl, HASH_ELEM | HASH_BLOBS);
+}
+
+/*
+ * AtAbort_IVM
+ *
+ * Clean up hash entries for all materialized views. This is called at
+ * transaction abort.
+ */
+void
+AtAbort_IVM()
+{
+	HASH_SEQ_STATUS seq;
+	MV_TriggerHashEntry *entry;
+
+	if (mv_trigger_info)
+	{
+		hash_seq_init(&seq, mv_trigger_info);
+		while ((entry = hash_seq_search(&seq)) != NULL)
+			clean_up_IVM_hash_entry(entry, true);
+	}
+	in_delta_calculation = false;
+}
+
+/*
+ * clean_up_IVM_hash_entry
+ *
+ * Clean up tuple stores and hash entries for a materialized view after its
+ * maintenance finished.
+ */
+static void
+clean_up_IVM_hash_entry(MV_TriggerHashEntry *entry, bool is_abort)
+{
+	bool found;
+	ListCell *lc;
+
+	foreach(lc, entry->tables)
+	{
+		MV_TriggerTable *table = (MV_TriggerTable *) lfirst(lc);
+
+		list_free(table->old_tuplestores);
+		list_free(table->new_tuplestores);
+		if (!is_abort)
+		{
+			ExecDropSingleTupleTableSlot(table->slot);
+			table_close(table->rel, NoLock);
+		}
+	}
+	list_free(entry->tables);
+
+	if (!is_abort)
+		UnregisterSnapshot(entry->snapshot);
+
+	hash_search(mv_trigger_info, (void *) &entry->matview_id, HASH_REMOVE, &found);
+}
+
+/*
+ * isIvmName
+ *
+ * Check if this is a IVM hidden column from the name.
+ */
+bool
+isIvmName(const char *s)
+{
+	if (s)
+		return (strncmp(s, "__ivm_", 6) == 0);
+	return false;
+}
diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat
index 07023ee61d..cae088ede0 100644
--- a/src/include/catalog/pg_proc.dat
+++ b/src/include/catalog/pg_proc.dat
@@ -12192,4 +12192,14 @@
   proargtypes => 'int2',
   prosrc => 'gist_stratnum_identity' },
 
+# IVM
+{ oid => '786', descr => 'ivm trigger (before)',
+  proname => 'IVM_immediate_before', provolatile => 'v', prorettype => 'trigger',
+  proargtypes => '', prosrc => 'IVM_immediate_before' },
+{ oid => '787', descr => 'ivm trigger (after)',
+  proname => 'IVM_immediate_maintenance', provolatile => 'v', prorettype => 'trigger',
+  proargtypes => '', prosrc => 'IVM_immediate_maintenance' },
+{ oid => '788', descr => 'ivm filetring ',
+  proname => 'ivm_visible_in_prestate', provolatile => 's', prorettype => 'bool',
+  proargtypes => 'oid tid oid', prosrc => 'ivm_visible_in_prestate' },
 ]
diff --git a/src/include/commands/createas.h b/src/include/commands/createas.h
index 94678e3834..396ad1bb4c 100644
--- a/src/include/commands/createas.h
+++ b/src/include/commands/createas.h
@@ -16,6 +16,7 @@
 
 #include "catalog/objectaddress.h"
 #include "nodes/params.h"
+#include "nodes/pathnodes.h"
 #include "parser/parse_node.h"
 #include "tcop/dest.h"
 #include "utils/queryenvironment.h"
@@ -25,6 +26,9 @@ extern ObjectAddress ExecCreateTableAs(ParseState *pstate, CreateTableAsStmt *st
 									   ParamListInfo params, QueryEnvironment *queryEnv,
 									   QueryCompletion *qc);
 
+extern void CreateIvmTriggersOnBaseTables(Query *qry, Oid matviewOid);
+extern void CreateIndexOnIMMV(Query *query, Relation matviewRel);
+
 extern int	GetIntoRelEFlags(IntoClause *intoClause);
 
 extern DestReceiver *CreateIntoRelDestReceiver(IntoClause *intoClause);
diff --git a/src/include/commands/matview.h b/src/include/commands/matview.h
index 817b2ba0b6..3257e1adff 100644
--- a/src/include/commands/matview.h
+++ b/src/include/commands/matview.h
@@ -15,6 +15,7 @@
 #define MATVIEW_H
 
 #include "catalog/objectaddress.h"
+#include "fmgr.h"
 #include "nodes/params.h"
 #include "nodes/parsenodes.h"
 #include "tcop/dest.h"
@@ -23,6 +24,8 @@
 
 extern void SetMatViewPopulatedState(Relation relation, bool newstate);
 
+extern void SetMatViewIVMState(Relation relation, bool newstate);
+
 extern ObjectAddress ExecRefreshMatView(RefreshMatViewStmt *stmt, const char *queryString,
 										ParamListInfo params, QueryCompletion *qc);
 
@@ -30,4 +33,10 @@ extern DestReceiver *CreateTransientRelDestReceiver(Oid transientoid);
 
 extern bool MatViewIncrementalMaintenanceIsEnabled(void);
 
+extern Datum IVM_immediate_before(PG_FUNCTION_ARGS);
+extern Datum IVM_immediate_maintenance(PG_FUNCTION_ARGS);
+extern Datum IVM_visible_in_prestate(PG_FUNCTION_ARGS);
+extern void AtAbort_IVM(void);
+extern bool isIvmName(const char *s);
+
 #endif							/* MATVIEW_H */
-- 
2.25.1


--Multipart=_Fri__29_Mar_2024_23_47_00_+0900_KGpmmDOIs1266Ib1
Content-Type: text/x-diff;
 name="v31-0007-Add-DISTINCT-support-for-IVM.patch"
Content-Disposition: attachment;
 filename="v31-0007-Add-DISTINCT-support-for-IVM.patch"
Content-Transfer-Encoding: 7bit



^ permalink  raw  reply  [nested|flat] 101+ messages in thread

* [PATCH v32 06/11] Add Incremental View Maintenance support
@ 2023-05-31 09:59  Yugo Nagata <[email protected]>
  0 siblings, 0 replies; 101+ messages in thread

From: Yugo Nagata @ 2023-05-31 09:59 UTC (permalink / raw)

In this implementation, AFTER triggers are used to collect
tuplestores containing transition table contents. When multiple tables
are changed, multiple AFTER triggers are invoked, then the final AFTER
trigger performs actual update of the matview. In addition, BEFORE
triggers are also used to handle global information for view
maintenance.

To calculate view deltas, we need both pre-state and post-state of base
tables. Post-update states are available in AFTER trigger, and pre-update
states can be calculated by removing inserted tuples and appending deleted
tuples. Insterted tuples are filtered using the snapshot taken before
table modiication, and deleted tuples are contained in the old transition
table.

Incrementally Maintainable Materialized Views (IMMV) can contain
duplicated tuples.

This patch also allows self-join, simultaneous updates of more than
one base table, and multiple updates of the same base table.
---
 src/backend/access/transam/xact.c |    5 +
 src/backend/commands/createas.c   |  682 ++++++++++++++
 src/backend/commands/matview.c    | 1468 ++++++++++++++++++++++++++++-
 src/include/catalog/pg_proc.dat   |   10 +
 src/include/commands/createas.h   |    4 +
 src/include/commands/matview.h    |    9 +
 6 files changed, 2143 insertions(+), 35 deletions(-)

diff --git a/src/backend/access/transam/xact.c b/src/backend/access/transam/xact.c
index df5a67e4c3..a2d5404912 100644
--- a/src/backend/access/transam/xact.c
+++ b/src/backend/access/transam/xact.c
@@ -36,6 +36,7 @@
 #include "catalog/pg_enum.h"
 #include "catalog/storage.h"
 #include "commands/async.h"
+#include "commands/matview.h"
 #include "commands/tablecmds.h"
 #include "commands/trigger.h"
 #include "common/pg_prng.h"
@@ -2860,6 +2861,7 @@ AbortTransaction(void)
 	AtAbort_Notify();
 	AtEOXact_RelationMap(false, is_parallel_worker);
 	AtAbort_Twophase();
+	AtAbort_IVM();
 
 	/*
 	 * Advertise the fact that we aborted in pg_xact (assuming that we got as
@@ -5198,6 +5200,9 @@ AbortSubTransaction(void)
 	pgstat_progress_end_command();
 	UnlockBuffers();
 
+	/* Clean up hash entries for incremental view maintenance */
+	AtAbort_IVM();
+
 	/* Reset WAL record construction state */
 	XLogResetInsertion();
 
diff --git a/src/backend/commands/createas.c b/src/backend/commands/createas.c
index afd3dace07..e9846c8d0f 100644
--- a/src/backend/commands/createas.c
+++ b/src/backend/commands/createas.c
@@ -29,15 +29,27 @@
 #include "access/tableam.h"
 #include "access/xact.h"
 #include "catalog/namespace.h"
+#include "catalog/index.h"
+#include "catalog/pg_constraint.h"
+#include "catalog/pg_inherits.h"
+#include "catalog/pg_trigger.h"
 #include "catalog/toasting.h"
 #include "commands/createas.h"
+#include "commands/defrem.h"
 #include "commands/matview.h"
 #include "commands/prepare.h"
 #include "commands/tablecmds.h"
+#include "commands/tablespace.h"
+#include "commands/trigger.h"
 #include "commands/view.h"
 #include "miscadmin.h"
+#include "optimizer/optimizer.h"
+#include "optimizer/prep.h"
 #include "nodes/makefuncs.h"
 #include "nodes/nodeFuncs.h"
+#include "parser/parser.h"
+#include "parser/parsetree.h"
+#include "parser/parse_clause.h"
 #include "rewrite/rewriteHandler.h"
 #include "tcop/tcopprot.h"
 #include "utils/builtins.h"
@@ -68,6 +80,12 @@ static bool intorel_receive(TupleTableSlot *slot, DestReceiver *self);
 static void intorel_shutdown(DestReceiver *self);
 static void intorel_destroy(DestReceiver *self);
 
+static void CreateIvmTriggersOnBaseTablesRecurse(Query *qry, Node *node, Oid matviewOid,
+									 Relids *relids, bool ex_lock);
+static void CreateIvmTrigger(Oid relOid, Oid viewOid, int16 type, int16 timing, bool ex_lock);
+static void check_ivm_restriction(Node *node);
+static bool check_ivm_restriction_walker(Node *node, void *context);
+static Bitmapset *get_primary_key_attnos_from_query(Query *query, List **constraintList);
 
 /*
  * create_ctas_internal
@@ -277,6 +295,18 @@ ExecCreateTableAs(ParseState *pstate, CreateTableAsStmt *stmt,
 		save_nestlevel = NewGUCNestLevel();
 	}
 
+	if (is_matview && into->ivm)
+	{
+		/* check if the query is supported in IMMV definition */
+		if (contain_mutable_functions((Node *) query))
+			ereport(ERROR,
+					(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+					 errmsg("mutable function is not supported on incrementally maintainable materialized view"),
+					 errhint("functions must be marked IMMUTABLE")));
+
+		check_ivm_restriction((Node *) query);
+	}
+
 	if (into->skipData)
 	{
 		/*
@@ -353,6 +383,27 @@ ExecCreateTableAs(ParseState *pstate, CreateTableAsStmt *stmt,
 
 		/* Restore userid and security context */
 		SetUserIdAndSecContext(save_userid, save_sec_context);
+
+		if (into->ivm)
+		{
+			Oid matviewOid = address.objectId;
+			Relation matviewRel = table_open(matviewOid, NoLock);
+
+			/*
+			 * Mark relisivm field, if it's a matview and into->ivm is true.
+			 */
+			SetMatViewIVMState(matviewRel, true);
+
+			if (!into->skipData)
+			{
+				/* Create an index on incremental maintainable materialized view, if possible */
+				CreateIndexOnIMMV((Query *) into->viewQuery, matviewRel);
+
+				/* Create triggers on incremental maintainable materialized view */
+				CreateIvmTriggersOnBaseTables((Query *) into->viewQuery, matviewOid);
+			}
+			table_close(matviewRel, NoLock);
+		}
 	}
 
 	return address;
@@ -632,3 +683,634 @@ intorel_destroy(DestReceiver *self)
 {
 	pfree(self);
 }
+
+/*
+ * CreateIvmTriggersOnBaseTables -- create IVM triggers on all base tables
+ */
+void
+CreateIvmTriggersOnBaseTables(Query *qry, Oid matviewOid)
+{
+	Relids	relids = NULL;
+	bool	ex_lock = false;
+	RangeTblEntry *rte;
+
+	/* Immediately return if we don't have any base tables. */
+	if (list_length(qry->rtable) < 1)
+		return;
+
+	/*
+	 * If the view has more than one base tables, we need an exclusive lock
+	 * on the view so that the view would be maintained serially to avoid
+	 * the inconsistency that occurs when two base tables are modified in
+	 * concurrent transactions. However, if the view has only one table,
+	 * we can use a weaker lock.
+	 *
+	 * The type of lock should be determined here, because if we check the
+	 * view definition at maintenance time, we need to acquire a weaker lock,
+	 * and upgrading the lock level after this increases probability of
+	 * deadlock.
+	 */
+
+	rte = list_nth(qry->rtable, 0);
+	if (list_length(qry->rtable) > 1 || rte->rtekind != RTE_RELATION)
+		ex_lock = true;
+
+	CreateIvmTriggersOnBaseTablesRecurse(qry, (Node *)qry, matviewOid, &relids, ex_lock);
+
+	bms_free(relids);
+}
+
+static void
+CreateIvmTriggersOnBaseTablesRecurse(Query *qry, Node *node, Oid matviewOid,
+									 Relids *relids, bool ex_lock)
+{
+	if (node == NULL)
+		return;
+
+	/* This can recurse, so check for excessive recursion */
+	check_stack_depth();
+
+	switch (nodeTag(node))
+	{
+		case T_Query:
+			{
+				Query *query = (Query *) node;
+
+				CreateIvmTriggersOnBaseTablesRecurse(qry, (Node *)query->jointree, matviewOid, relids, ex_lock);
+			}
+			break;
+
+		case T_RangeTblRef:
+			{
+				int			rti = ((RangeTblRef *) node)->rtindex;
+				RangeTblEntry *rte = rt_fetch(rti, qry->rtable);
+
+				if (rte->rtekind == RTE_RELATION && !bms_is_member(rte->relid, *relids))
+				{
+					CreateIvmTrigger(rte->relid, matviewOid, TRIGGER_TYPE_INSERT, TRIGGER_TYPE_BEFORE, ex_lock);
+					CreateIvmTrigger(rte->relid, matviewOid, TRIGGER_TYPE_DELETE, TRIGGER_TYPE_BEFORE, ex_lock);
+					CreateIvmTrigger(rte->relid, matviewOid, TRIGGER_TYPE_UPDATE, TRIGGER_TYPE_BEFORE, ex_lock);
+					CreateIvmTrigger(rte->relid, matviewOid, TRIGGER_TYPE_TRUNCATE, TRIGGER_TYPE_BEFORE, true);
+					CreateIvmTrigger(rte->relid, matviewOid, TRIGGER_TYPE_INSERT, TRIGGER_TYPE_AFTER, ex_lock);
+					CreateIvmTrigger(rte->relid, matviewOid, TRIGGER_TYPE_DELETE, TRIGGER_TYPE_AFTER, ex_lock);
+					CreateIvmTrigger(rte->relid, matviewOid, TRIGGER_TYPE_UPDATE, TRIGGER_TYPE_AFTER, ex_lock);
+					CreateIvmTrigger(rte->relid, matviewOid, TRIGGER_TYPE_TRUNCATE, TRIGGER_TYPE_AFTER, true);
+
+					*relids = bms_add_member(*relids, rte->relid);
+				}
+			}
+			break;
+
+		case T_FromExpr:
+			{
+				FromExpr   *f = (FromExpr *) node;
+				ListCell   *l;
+
+				foreach(l, f->fromlist)
+					CreateIvmTriggersOnBaseTablesRecurse(qry, lfirst(l), matviewOid, relids, ex_lock);
+			}
+			break;
+
+		case T_JoinExpr:
+			{
+				JoinExpr   *j = (JoinExpr *) node;
+
+				CreateIvmTriggersOnBaseTablesRecurse(qry, j->larg, matviewOid, relids, ex_lock);
+				CreateIvmTriggersOnBaseTablesRecurse(qry, j->rarg, matviewOid, relids, ex_lock);
+			}
+			break;
+
+		default:
+			elog(ERROR, "unrecognized node type: %d", (int) nodeTag(node));
+	}
+}
+
+/*
+ * CreateIvmTrigger -- create IVM trigger on a base table
+ */
+static void
+CreateIvmTrigger(Oid relOid, Oid viewOid, int16 type, int16 timing, bool ex_lock)
+{
+	ObjectAddress	refaddr;
+	ObjectAddress	address;
+	CreateTrigStmt *ivm_trigger;
+	List *transitionRels = NIL;
+
+	Assert(timing == TRIGGER_TYPE_BEFORE || timing == TRIGGER_TYPE_AFTER);
+
+	refaddr.classId = RelationRelationId;
+	refaddr.objectId = viewOid;
+	refaddr.objectSubId = 0;
+
+	ivm_trigger = makeNode(CreateTrigStmt);
+	ivm_trigger->relation = NULL;
+	ivm_trigger->row = false;
+
+	ivm_trigger->timing = timing;
+	ivm_trigger->events = type;
+
+	switch (type)
+	{
+		case TRIGGER_TYPE_INSERT:
+			ivm_trigger->trigname = (timing == TRIGGER_TYPE_BEFORE ? "IVM_trigger_ins_before" : "IVM_trigger_ins_after");
+			break;
+		case TRIGGER_TYPE_DELETE:
+			ivm_trigger->trigname = (timing == TRIGGER_TYPE_BEFORE ? "IVM_trigger_del_before" : "IVM_trigger_del_after");
+			break;
+		case TRIGGER_TYPE_UPDATE:
+			ivm_trigger->trigname = (timing == TRIGGER_TYPE_BEFORE ? "IVM_trigger_upd_before" : "IVM_trigger_upd_after");
+			break;
+		case TRIGGER_TYPE_TRUNCATE:
+			ivm_trigger->trigname = (timing == TRIGGER_TYPE_BEFORE ? "IVM_trigger_truncate_before" : "IVM_trigger_truncate_after");
+			break;
+		default:
+			elog(ERROR, "unsupported trigger type");
+	}
+
+	if (timing == TRIGGER_TYPE_AFTER)
+	{
+		if (type == TRIGGER_TYPE_INSERT || type == TRIGGER_TYPE_UPDATE)
+		{
+			TriggerTransition *n = makeNode(TriggerTransition);
+			n->name = "__ivm_newtable";
+			n->isNew = true;
+			n->isTable = true;
+
+			transitionRels = lappend(transitionRels, n);
+		}
+		if (type == TRIGGER_TYPE_DELETE || type == TRIGGER_TYPE_UPDATE)
+		{
+			TriggerTransition *n = makeNode(TriggerTransition);
+			n->name = "__ivm_oldtable";
+			n->isNew = false;
+			n->isTable = true;
+
+			transitionRels = lappend(transitionRels, n);
+		}
+	}
+
+	/*
+	 * XXX: When using DELETE or UPDATE, we must use exclusive lock for now
+	 * because apply_old_delta(_with_count) uses ctid to identify the tuple
+	 * to be deleted/deleted, but doesn't work in concurrent situations.
+	 *
+	 * If the view doesn't have aggregate, distinct, or tuple duplicate,
+	 * then it would work even in concurrent situations. However, we don't have
+	 * any way to guarantee the view has a unique key before opening the IMMV
+	 * at the maintenance time because users may drop the unique index.
+	 */
+
+	if (type == TRIGGER_TYPE_DELETE || type == TRIGGER_TYPE_UPDATE)
+		ex_lock = true;
+
+	ivm_trigger->funcname =
+		(timing == TRIGGER_TYPE_BEFORE ? SystemFuncName("IVM_immediate_before") : SystemFuncName("IVM_immediate_maintenance"));
+
+	ivm_trigger->columns = NIL;
+	ivm_trigger->transitionRels = transitionRels;
+	ivm_trigger->whenClause = NULL;
+	ivm_trigger->isconstraint = false;
+	ivm_trigger->deferrable = false;
+	ivm_trigger->initdeferred = false;
+	ivm_trigger->constrrel = NULL;
+	ivm_trigger->args = list_make2(
+		makeString(DatumGetPointer(DirectFunctionCall1(oidout, ObjectIdGetDatum(viewOid)))),
+		makeString(DatumGetPointer(DirectFunctionCall1(boolout, BoolGetDatum(ex_lock))))
+		);
+
+	address = CreateTrigger(ivm_trigger, NULL, relOid, InvalidOid, InvalidOid,
+						 InvalidOid, InvalidOid, InvalidOid, NULL, true, false);
+
+	recordDependencyOn(&address, &refaddr, DEPENDENCY_AUTO);
+
+	/* Make changes-so-far visible */
+	CommandCounterIncrement();
+}
+
+/*
+ * check_ivm_restriction --- look for specify nodes in the query tree
+ */
+static void
+check_ivm_restriction(Node *node)
+{
+	check_ivm_restriction_walker(node, NULL);
+}
+
+static bool
+check_ivm_restriction_walker(Node *node, void *context)
+{
+	if (node == NULL)
+		return false;
+
+	/*
+	 * We currently don't support Sub-Query.
+	 */
+	if (IsA(node, SubPlan) || IsA(node, SubLink))
+		ereport(ERROR,
+				(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+				 errmsg("subquery is not supported on incrementally maintainable materialized view")));
+
+	/* This can recurse, so check for excessive recursion */
+	check_stack_depth();
+
+	switch (nodeTag(node))
+	{
+		case T_Query:
+			{
+				Query *qry = (Query *)node;
+				ListCell   *lc;
+				List       *vars;
+
+				/* if contained CTE, return error */
+				if (qry->cteList != NIL)
+					ereport(ERROR,
+							(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+							 errmsg("CTE is not supported on incrementally maintainable materialized view")));
+				if (qry->havingQual != NULL)
+					ereport(ERROR,
+							(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+							 errmsg(" HAVING clause is not supported on incrementally maintainable materialized view")));
+				if (qry->sortClause != NIL)	/* There is a possibility that we don't need to return an error */
+					ereport(ERROR,
+							(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+							 errmsg("ORDER BY clause is not supported on incrementally maintainable materialized view")));
+				if (qry->limitOffset != NULL || qry->limitCount != NULL)
+					ereport(ERROR,
+							(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+							 errmsg("LIMIT/OFFSET clause is not supported on incrementally maintainable materialized view")));
+				if (qry->distinctClause)
+					ereport(ERROR,
+							(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+							 errmsg("DISTINCT is not supported on incrementally maintainable materialized view")));
+				if (qry->hasDistinctOn)
+					ereport(ERROR,
+							(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+							 errmsg("DISTINCT ON is not supported on incrementally maintainable materialized view")));
+				if (qry->hasWindowFuncs)
+					ereport(ERROR,
+							(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+							 errmsg("window functions are not supported on incrementally maintainable materialized view")));
+				if (qry->groupingSets != NIL)
+					ereport(ERROR,
+							(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+							 errmsg("GROUPING SETS, ROLLUP, or CUBE clauses is not supported on incrementally maintainable materialized view")));
+				if (qry->setOperations != NULL)
+					ereport(ERROR,
+							(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+							 errmsg("UNION/INTERSECT/EXCEPT statements are not supported on incrementally maintainable materialized view")));
+				if (list_length(qry->targetList) == 0)
+					ereport(ERROR,
+							(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+							 errmsg("empty target list is not supported on incrementally maintainable materialized view")));
+				if (qry->rowMarks != NIL)
+					ereport(ERROR,
+							(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+							 errmsg("FOR UPDATE/SHARE clause is not supported on incrementally maintainable materialized view")));
+
+				/* system column restrictions */
+				vars = pull_vars_of_level((Node *) qry, 0);
+				foreach(lc, vars)
+				{
+					if (IsA(lfirst(lc), Var))
+					{
+						Var *var = (Var *) lfirst(lc);
+						/* if system column, return error */
+						if (var->varattno < 0)
+							ereport(ERROR,
+									(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+									 errmsg("system column is not supported on incrementally maintainable materialized view")));
+					}
+				}
+
+				/* restrictions for rtable */
+				foreach(lc, qry->rtable)
+				{
+					RangeTblEntry *rte = (RangeTblEntry *) lfirst(lc);
+
+					if (rte->subquery)
+						ereport(ERROR,
+								(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+								 errmsg("subquery is not supported on incrementally maintainable materialized view")));
+
+					if (rte->tablesample != NULL)
+						ereport(ERROR,
+								(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+								 errmsg("TABLESAMPLE clause is not supported on incrementally maintainable materialized view")));
+
+					if (rte->relkind == RELKIND_PARTITIONED_TABLE)
+						ereport(ERROR,
+								(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+								 errmsg("partitioned table is not supported on incrementally maintainable materialized view")));
+
+					if (rte->relkind == RELKIND_RELATION && has_superclass(rte->relid))
+						ereport(ERROR,
+								(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+								 errmsg("partitions is not supported on incrementally maintainable materialized view")));
+
+					if (rte->relkind == RELKIND_RELATION && find_inheritance_children(rte->relid, NoLock) != NIL)
+						ereport(ERROR,
+								(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+								 errmsg("inheritance parent is not supported on incrementally maintainable materialized view")));
+
+					if (rte->relkind == RELKIND_FOREIGN_TABLE)
+						ereport(ERROR,
+								(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+								 errmsg("foreign table is not supported on incrementally maintainable materialized view")));
+
+					if (rte->relkind == RELKIND_VIEW ||
+						rte->relkind == RELKIND_MATVIEW)
+						ereport(ERROR,
+								(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+								 errmsg("VIEW or MATERIALIZED VIEW is not supported on incrementally maintainable materialized view")));
+
+					if (rte->rtekind == RTE_VALUES)
+						ereport(ERROR,
+								(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+								 errmsg("VALUES is not supported on incrementally maintainable materialized view")));
+
+				}
+
+				query_tree_walker(qry, check_ivm_restriction_walker, NULL, QTW_IGNORE_RANGE_TABLE);
+
+				break;
+			}
+		case T_TargetEntry:
+			{
+				TargetEntry *tle = (TargetEntry *)node;
+				if (isIvmName(tle->resname))
+						ereport(ERROR,
+								(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+								 errmsg("column name %s is not supported on incrementally maintainable materialized view", tle->resname)));
+
+				expression_tree_walker(node, check_ivm_restriction_walker, NULL);
+				break;
+			}
+		case T_JoinExpr:
+			{
+				JoinExpr *joinexpr = (JoinExpr *)node;
+
+				if (joinexpr->jointype > JOIN_INNER)
+						ereport(ERROR,
+								(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+								 errmsg("OUTER JOIN is not supported on incrementally maintainable materialized view")));
+
+				expression_tree_walker(node, check_ivm_restriction_walker, NULL);
+			}
+			break;
+		case T_Aggref:
+			ereport(ERROR,
+					(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+					 errmsg("aggregate function is not supported on incrementally maintainable materialized view")));
+			break;
+		default:
+			expression_tree_walker(node, check_ivm_restriction_walker, (void *) context);
+			break;
+	}
+	return false;
+}
+
+/*
+ * CreateIndexOnIMMV
+ *
+ * Create a unique index on incremental maintainable materialized view.
+ * If the view definition query has a GROUP BY clause, the index is created
+ * on the columns of GROUP BY expressions. Otherwise, if the view contains
+ * all primary key attritubes of its base tables in the target list, the index
+ * is created on these attritubes. In other cases, no index is created.
+ */
+void
+CreateIndexOnIMMV(Query *query, Relation matviewRel)
+{
+	ListCell *lc;
+	IndexStmt  *index;
+	ObjectAddress address;
+	List *constraintList = NIL;
+	char		idxname[NAMEDATALEN];
+	List	   *indexoidlist = RelationGetIndexList(matviewRel);
+	ListCell   *indexoidscan;
+	Bitmapset *key_attnos;
+
+	snprintf(idxname, sizeof(idxname), "%s_index", RelationGetRelationName(matviewRel));
+
+	index = makeNode(IndexStmt);
+
+	index->unique = true;
+	index->primary = false;
+	index->isconstraint = false;
+	index->deferrable = false;
+	index->initdeferred = false;
+	index->idxname = idxname;
+	index->relation =
+		makeRangeVar(get_namespace_name(RelationGetNamespace(matviewRel)),
+					 pstrdup(RelationGetRelationName(matviewRel)),
+					 -1);
+	index->accessMethod = DEFAULT_INDEX_TYPE;
+	index->options = NIL;
+	index->tableSpace = get_tablespace_name(matviewRel->rd_rel->reltablespace);
+	index->whereClause = NULL;
+	index->indexParams = NIL;
+	index->indexIncludingParams = NIL;
+	index->excludeOpNames = NIL;
+	index->idxcomment = NULL;
+	index->indexOid = InvalidOid;
+	index->oldNumber = InvalidRelFileNumber;
+	index->oldCreateSubid = InvalidSubTransactionId;
+	index->oldFirstRelfilelocatorSubid = InvalidSubTransactionId;
+	index->transformed = true;
+	index->concurrent = false;
+	index->if_not_exists = false;
+
+	/* create index on the base tables' primary key columns */
+	key_attnos = get_primary_key_attnos_from_query(query, &constraintList);
+	if (key_attnos)
+	{
+		foreach(lc, query->targetList)
+		{
+			TargetEntry *tle = (TargetEntry *) lfirst(lc);
+			Form_pg_attribute attr = TupleDescAttr(matviewRel->rd_att, tle->resno - 1);
+
+			if (bms_is_member(tle->resno - FirstLowInvalidHeapAttributeNumber, key_attnos))
+			{
+				IndexElem  *iparam;
+
+				iparam = makeNode(IndexElem);
+				iparam->name = pstrdup(NameStr(attr->attname));
+				iparam->expr = NULL;
+				iparam->indexcolname = NULL;
+				iparam->collation = NIL;
+				iparam->opclass = NIL;
+				iparam->opclassopts = NIL;
+				iparam->ordering = SORTBY_DEFAULT;
+				iparam->nulls_ordering = SORTBY_NULLS_DEFAULT;
+				index->indexParams = lappend(index->indexParams, iparam);
+			}
+		}
+	}
+	else
+	{
+		/* create no index, just notice that an appropriate index is necessary for efficient IVM */
+		ereport(NOTICE,
+				(errmsg("could not create an index on materialized view \"%s\" automatically",
+						RelationGetRelationName(matviewRel)),
+				 errdetail("This target list does not have all the primary key columns. "),
+				 errhint("Create an index on the materialized view for efficient incremental maintenance.")));
+		return;
+	}
+
+	/* If we have a compatible index, we don't need to create another. */
+	foreach(indexoidscan, indexoidlist)
+	{
+		Oid			indexoid = lfirst_oid(indexoidscan);
+		Relation	indexRel;
+		bool		hasCompatibleIndex = false;
+
+		indexRel = index_open(indexoid, AccessShareLock);
+
+		if (CheckIndexCompatible(indexRel->rd_id,
+								index->accessMethod,
+								index->indexParams,
+								index->excludeOpNames,
+								false))
+			hasCompatibleIndex = true;
+
+		index_close(indexRel, AccessShareLock);
+
+		if (hasCompatibleIndex)
+			return;
+	}
+
+	address = DefineIndex(RelationGetRelid(matviewRel),
+						  index,
+						  InvalidOid,
+						  InvalidOid,
+						  InvalidOid,
+						  -1,
+						  false, true, false, false, true);
+
+	ereport(NOTICE,
+			(errmsg("created index \"%s\" on materialized view \"%s\"",
+					idxname, RelationGetRelationName(matviewRel))));
+
+	/*
+	 * Make dependencies so that the index is dropped if any base tables's
+	 * primary key is dropped.
+	 */
+	foreach(lc, constraintList)
+	{
+		Oid constraintOid = lfirst_oid(lc);
+		ObjectAddress	refaddr;
+
+		refaddr.classId = ConstraintRelationId;
+		refaddr.objectId = constraintOid;
+		refaddr.objectSubId = 0;
+
+		recordDependencyOn(&address, &refaddr, DEPENDENCY_NORMAL);
+	}
+}
+
+
+/*
+ * get_primary_key_attnos_from_query
+ *
+ * Identify the columns in base tables' primary keys in the target list.
+ *
+ * Returns a Bitmapset of the column attnos of the primary key's columns of
+ * tables that used in the query.  The attnos are offset by
+ * FirstLowInvalidHeapAttributeNumber as same as get_primary_key_attnos.
+ *
+ * If any table has no primary key or any primary key's columns is not in
+ * the target list, return NULL.  We also return NULL if any pkey constraint
+ * is deferrable.
+ *
+ * constraintList is set to a list of the OIDs of the pkey constraints.
+ */
+static Bitmapset *
+get_primary_key_attnos_from_query(Query *query, List **constraintList)
+{
+	List *key_attnos_list = NIL;
+	ListCell *lc;
+	int i;
+	Bitmapset *keys = NULL;
+	Relids	rels_in_from;
+
+	/*
+	 * Collect primary key attributes from all tables used in query. The key attributes
+	 * sets for each table are stored in key_attnos_list in order by RTE index.
+	 */
+	foreach(lc, query->rtable)
+	{
+		RangeTblEntry *r = (RangeTblEntry*) lfirst(lc);
+		Bitmapset *key_attnos;
+		bool	has_pkey = true;
+
+		/* for tables, call get_primary_key_attnos */
+		if (r->rtekind == RTE_RELATION)
+		{
+			Oid constraintOid;
+			key_attnos = get_primary_key_attnos(r->relid, false, &constraintOid);
+			*constraintList = lappend_oid(*constraintList, constraintOid);
+			has_pkey = (key_attnos != NULL);
+		}
+		/* for other RTEs, store NULL into key_attnos_list */
+		else
+			key_attnos = NULL;
+
+		/*
+		 * If any table or subquery has no primary key or its pkey constraint is deferrable,
+		 * we cannot get key attributes for this query, so return NULL.
+		 */
+		if (!has_pkey)
+			return NULL;
+
+		key_attnos_list = lappend(key_attnos_list, key_attnos);
+	}
+
+	/* Collect key attributes appearing in the target list */
+	i = 1;
+	foreach(lc, query->targetList)
+	{
+		TargetEntry *tle = (TargetEntry *) flatten_join_alias_vars(NULL, query, lfirst(lc));
+
+		if (IsA(tle->expr, Var))
+		{
+			Var *var = (Var*) tle->expr;
+			Bitmapset *key_attnos = list_nth(key_attnos_list, var->varno - 1);
+
+			/* check if this attribute is from a base table's primary key */
+			if (bms_is_member(var->varattno - FirstLowInvalidHeapAttributeNumber, key_attnos))
+			{
+				/*
+				 * Remove found key attributes from key_attnos_list, and add this
+				 * to the result list.
+				 */
+				key_attnos = bms_del_member(key_attnos, var->varattno - FirstLowInvalidHeapAttributeNumber);
+				if (bms_is_empty(key_attnos))
+				{
+					key_attnos_list = list_delete_nth_cell(key_attnos_list, var->varno - 1);
+					key_attnos_list = list_insert_nth(key_attnos_list, var->varno - 1, NULL);
+				}
+				keys = bms_add_member(keys, i - FirstLowInvalidHeapAttributeNumber);
+			}
+		}
+		i++;
+	}
+
+	/* Collect RTE indexes of relations appearing in the FROM clause */
+	rels_in_from = get_relids_in_jointree((Node *) query->jointree, false, false);
+
+	/*
+	 * Check if all key attributes of relations in FROM are appearing in the target
+	 * list.  If an attribute remains in key_attnos_list in spite of the table is used
+	 * in FROM clause, the target is missing this key attribute, so we return NULL.
+	 */
+	i = 1;
+	foreach(lc, key_attnos_list)
+	{
+		Bitmapset *bms = (Bitmapset *)lfirst(lc);
+		if (!bms_is_empty(bms) && bms_is_member(i, rels_in_from))
+			return NULL;
+		i++;
+	}
+
+	return keys;
+}
diff --git a/src/backend/commands/matview.c b/src/backend/commands/matview.c
index 9ec13d0984..78a5dd1df9 100644
--- a/src/backend/commands/matview.c
+++ b/src/backend/commands/matview.c
@@ -23,23 +23,35 @@
 #include "catalog/indexing.h"
 #include "catalog/namespace.h"
 #include "catalog/pg_am.h"
+#include "catalog/pg_depend.h"
+#include "catalog/pg_trigger.h"
 #include "catalog/pg_opclass.h"
 #include "commands/cluster.h"
 #include "commands/matview.h"
 #include "commands/tablecmds.h"
 #include "commands/tablespace.h"
+#include "commands/createas.h"
 #include "executor/executor.h"
 #include "executor/spi.h"
+#include "executor/tstoreReceiver.h"
 #include "miscadmin.h"
+#include "nodes/makefuncs.h"
+#include "parser/analyze.h"
+#include "parser/parse_clause.h"
+#include "parser/parse_func.h"
+#include "parser/parse_relation.h"
 #include "pgstat.h"
 #include "rewrite/rewriteHandler.h"
+#include "rewrite/rowsecurity.h"
 #include "storage/lmgr.h"
 #include "tcop/tcopprot.h"
 #include "utils/builtins.h"
+#include "utils/fmgroids.h"
 #include "utils/lsyscache.h"
 #include "utils/rel.h"
 #include "utils/snapmgr.h"
 #include "utils/syscache.h"
+#include "utils/typcache.h"
 
 
 typedef struct
@@ -53,6 +65,52 @@ typedef struct
 	BulkInsertState bistate;	/* bulk insert state */
 } DR_transientrel;
 
+#define MV_INIT_QUERYHASHSIZE	16
+
+/*
+ * MV_TriggerHashEntry
+ *
+ * Hash entry for base tables on which IVM trigger is invoked
+ */
+typedef struct MV_TriggerHashEntry
+{
+	Oid	matview_id;			/* OID of the materialized view */
+	int	before_trig_count;	/* count of before triggers invoked */
+	int	after_trig_count;	/* count of after triggers invoked */
+
+	Snapshot	snapshot;	/* Snapshot just before table change */
+
+	List   *tables;		/* List of MV_TriggerTable */
+	bool	has_old;	/* tuples are deleted from any table? */
+	bool	has_new;	/* tuples are inserted into any table? */
+} MV_TriggerHashEntry;
+
+/*
+ * MV_TriggerTable
+ *
+ * IVM related data for tables on which the trigger is invoked.
+ */
+typedef struct MV_TriggerTable
+{
+	Oid		table_id;			/* OID of the modified table */
+	List   *old_tuplestores;	/* tuplestores for deleted tuples */
+	List   *new_tuplestores;	/* tuplestores for inserted tuples */
+
+	List   *rte_indexes;		/* List of RTE index of the modified table */
+	RangeTblEntry *original_rte;	/* the original RTE saved before rewriting query */
+
+	Relation	rel;			/* relation of the modified table */
+	TupleTableSlot *slot;		/* for checking visibility in the pre-state table */
+} MV_TriggerTable;
+
+static HTAB *mv_trigger_info = NULL;
+
+static bool in_delta_calculation = false;
+
+/* ENR name for materialized view delta */
+#define NEW_DELTA_ENRNAME "new_delta"
+#define OLD_DELTA_ENRNAME "old_delta"
+
 static int	matview_maintenance_depth = 0;
 
 static void transientrel_startup(DestReceiver *self, int operation, TupleDesc typeinfo);
@@ -60,7 +118,9 @@ static bool transientrel_receive(TupleTableSlot *slot, DestReceiver *self);
 static void transientrel_shutdown(DestReceiver *self);
 static void transientrel_destroy(DestReceiver *self);
 static uint64 refresh_matview_datafill(DestReceiver *dest, Query *query,
-									   const char *queryString);
+						 QueryEnvironment *queryEnv,
+						 TupleDesc *resultTupleDesc,
+						 const char *queryString);
 static char *make_temptable_name_n(char *tempname, int n);
 static void refresh_by_match_merge(Oid matviewOid, Oid tempOid, Oid relowner,
 								   int save_sec_context);
@@ -68,6 +128,37 @@ static void refresh_by_heap_swap(Oid matviewOid, Oid OIDNewHeap, char relpersist
 static bool is_usable_unique_index(Relation indexRel);
 static void OpenMatViewIncrementalMaintenance(void);
 static void CloseMatViewIncrementalMaintenance(void);
+static Query *get_matview_query(Relation matviewRel);
+
+static Query *rewrite_query_for_preupdate_state(Query *query, List *tables,
+								  ParseState *pstate, Oid matviewid);
+static void register_delta_ENRs(ParseState *pstate, Query *query, List *tables);
+static char *make_delta_enr_name(const char *prefix, Oid relid, int count);
+static RangeTblEntry *get_prestate_rte(RangeTblEntry *rte, MV_TriggerTable *table,
+				 QueryEnvironment *queryEnv, Oid matviewid);
+static RangeTblEntry *replace_rte_with_delta(RangeTblEntry *rte, MV_TriggerTable *table, bool is_new,
+		   QueryEnvironment *queryEnv);
+static Query *rewrite_query_for_counting(Query *query, ParseState *pstate);
+
+static void calc_delta(MV_TriggerTable *table, int rte_index, Query *query,
+			DestReceiver *dest_old, DestReceiver *dest_new,
+			TupleDesc *tupdesc_old, TupleDesc *tupdesc_new,
+			QueryEnvironment *queryEnv);
+static Query *rewrite_query_for_postupdate_state(Query *query, MV_TriggerTable *table, int rte_index);
+
+static void apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *new_tuplestores,
+			TupleDesc tupdesc_old, TupleDesc tupdesc_new,
+			Query *query);
+static void apply_old_delta(const char *matviewname, const char *deltaname_old,
+				List *keys);
+static void apply_new_delta(const char *matviewname, const char *deltaname_new,
+				StringInfo target_list);
+static char *get_matching_condition_string(List *keys);
+static void generate_equal(StringInfo querybuf, Oid opttype,
+			   const char *leftop, const char *rightop);
+
+static void mv_InitHashTables(void);
+static void clean_up_IVM_hash_entry(MV_TriggerHashEntry *entry, bool is_abort);
 
 /*
  * SetMatViewPopulatedState
@@ -109,6 +200,46 @@ SetMatViewPopulatedState(Relation relation, bool newstate)
 	CommandCounterIncrement();
 }
 
+/*
+ * SetMatViewIVMState
+ *		Mark a materialized view as IVM, or not.
+ *
+ * NOTE: caller must be holding an appropriate lock on the relation.
+ */
+void
+SetMatViewIVMState(Relation relation, bool newstate)
+{
+	Relation	pgrel;
+	HeapTuple	tuple;
+
+	Assert(relation->rd_rel->relkind == RELKIND_MATVIEW);
+
+	/*
+	 * Update relation's pg_class entry.  Crucial side-effect: other backends
+	 * (and this one too!) are sent SI message to make them rebuild relcache
+	 * entries.
+	 */
+	pgrel = table_open(RelationRelationId, RowExclusiveLock);
+	tuple = SearchSysCacheCopy1(RELOID,
+								ObjectIdGetDatum(RelationGetRelid(relation)));
+	if (!HeapTupleIsValid(tuple))
+		elog(ERROR, "cache lookup failed for relation %u",
+			 RelationGetRelid(relation));
+
+	((Form_pg_class) GETSTRUCT(tuple))->relisivm = newstate;
+
+	CatalogTupleUpdate(pgrel, &tuple->t_self, tuple);
+
+	heap_freetuple(tuple);
+	table_close(pgrel, RowExclusiveLock);
+
+	/*
+	 * Advance command counter to make the updated pg_class row locally
+	 * visible.
+	 */
+	CommandCounterIncrement();
+}
+
 /*
  * ExecRefreshMatView -- execute a REFRESH MATERIALIZED VIEW command
  *
@@ -135,8 +266,6 @@ ExecRefreshMatView(RefreshMatViewStmt *stmt, const char *queryString,
 {
 	Oid			matviewOid;
 	Relation	matviewRel;
-	RewriteRule *rule;
-	List	   *actions;
 	Query	   *dataQuery;
 	Oid			tableSpace;
 	Oid			relowner;
@@ -150,6 +279,7 @@ ExecRefreshMatView(RefreshMatViewStmt *stmt, const char *queryString,
 	int			save_sec_context;
 	int			save_nestlevel;
 	ObjectAddress address;
+	bool oldPopulated;
 
 	/* Determine strength of lock needed. */
 	concurrent = stmt->concurrent;
@@ -176,6 +306,8 @@ ExecRefreshMatView(RefreshMatViewStmt *stmt, const char *queryString,
 	save_nestlevel = NewGUCNestLevel();
 	RestrictSearchPath();
 
+	oldPopulated = RelationIsPopulated(matviewRel);
+
 	/* Make sure it is a materialized view. */
 	if (matviewRel->rd_rel->relkind != RELKIND_MATVIEW)
 		ereport(ERROR,
@@ -196,32 +328,9 @@ ExecRefreshMatView(RefreshMatViewStmt *stmt, const char *queryString,
 				 errmsg("%s and %s options cannot be used together",
 						"CONCURRENTLY", "WITH NO DATA")));
 
-	/*
-	 * Check that everything is correct for a refresh. Problems at this point
-	 * are internal errors, so elog is sufficient.
-	 */
-	if (matviewRel->rd_rel->relhasrules == false ||
-		matviewRel->rd_rules->numLocks < 1)
-		elog(ERROR,
-			 "materialized view \"%s\" is missing rewrite information",
-			 RelationGetRelationName(matviewRel));
-
-	if (matviewRel->rd_rules->numLocks > 1)
-		elog(ERROR,
-			 "materialized view \"%s\" has too many rules",
-			 RelationGetRelationName(matviewRel));
 
-	rule = matviewRel->rd_rules->rules[0];
-	if (rule->event != CMD_SELECT || !(rule->isInstead))
-		elog(ERROR,
-			 "the rule for materialized view \"%s\" is not a SELECT INSTEAD OF rule",
-			 RelationGetRelationName(matviewRel));
+	dataQuery = get_matview_query(matviewRel);
 
-	actions = rule->actions;
-	if (list_length(actions) != 1)
-		elog(ERROR,
-			 "the rule for materialized view \"%s\" is not a single action",
-			 RelationGetRelationName(matviewRel));
 
 	/*
 	 * Check that there is a unique index with no WHERE clause on one or more
@@ -256,12 +365,6 @@ ExecRefreshMatView(RefreshMatViewStmt *stmt, const char *queryString,
 					 errhint("Create a unique index with no WHERE clause on one or more columns of the materialized view.")));
 	}
 
-	/*
-	 * The stored query was rewritten at the time of the MV definition, but
-	 * has not been scribbled on by the planner.
-	 */
-	dataQuery = linitial_node(Query, actions);
-
 	/*
 	 * Check for active uses of the relation in the current transaction, such
 	 * as open scans.
@@ -289,6 +392,74 @@ ExecRefreshMatView(RefreshMatViewStmt *stmt, const char *queryString,
 		relpersistence = matviewRel->rd_rel->relpersistence;
 	}
 
+	/* delete IMMV triggers. */
+	if (RelationIsIVM(matviewRel) && stmt->skipData )
+	{
+		Relation	tgRel;
+		Relation	depRel;
+		ScanKeyData key;
+		SysScanDesc scan;
+		HeapTuple	tup;
+		ObjectAddresses *immv_triggers;
+
+		immv_triggers = new_object_addresses();
+
+		tgRel = table_open(TriggerRelationId, RowExclusiveLock);
+		depRel = table_open(DependRelationId, RowExclusiveLock);
+
+		/* search triggers that depends on IMMV. */
+		ScanKeyInit(&key,
+					Anum_pg_depend_refobjid,
+					BTEqualStrategyNumber, F_OIDEQ,
+					ObjectIdGetDatum(matviewOid));
+		scan = systable_beginscan(depRel, DependReferenceIndexId, true,
+								  NULL, 1, &key);
+		while ((tup = systable_getnext(scan)) != NULL)
+		{
+			ObjectAddress obj;
+			Form_pg_depend foundDep = (Form_pg_depend) GETSTRUCT(tup);
+
+			if (foundDep->classid == TriggerRelationId)
+			{
+				HeapTuple	tgtup;
+				ScanKeyData tgkey[1];
+				SysScanDesc tgscan;
+				Form_pg_trigger tgform;
+
+				/* Find the trigger name. */
+				ScanKeyInit(&tgkey[0],
+							Anum_pg_trigger_oid,
+							BTEqualStrategyNumber, F_OIDEQ,
+							ObjectIdGetDatum(foundDep->objid));
+
+				tgscan = systable_beginscan(tgRel, TriggerOidIndexId, true,
+											NULL, 1, tgkey);
+				tgtup = systable_getnext(tgscan);
+				if (!HeapTupleIsValid(tgtup))
+					elog(ERROR, "could not find tuple for immv trigger %u", foundDep->objid);
+
+				tgform = (Form_pg_trigger) GETSTRUCT(tgtup);
+
+				/* If trigger is created by IMMV, delete it. */
+				if (strncmp(NameStr(tgform->tgname), "IVM_trigger_", 12) == 0)
+				{
+					obj.classId = foundDep->classid;
+					obj.objectId = foundDep->objid;
+					obj.objectSubId = foundDep->refobjsubid;
+					add_exact_object_address(&obj, immv_triggers);
+				}
+				systable_endscan(tgscan);
+			}
+		}
+		systable_endscan(scan);
+
+		performMultipleDeletions(immv_triggers, DROP_RESTRICT, PERFORM_DELETION_INTERNAL);
+
+		table_close(depRel, RowExclusiveLock);
+		table_close(tgRel, RowExclusiveLock);
+		free_object_addresses(immv_triggers);
+	}
+
 	/*
 	 * Create the transient table that will receive the regenerated data. Lock
 	 * it against access by any other process until commit (by which time it
@@ -302,7 +473,7 @@ ExecRefreshMatView(RefreshMatViewStmt *stmt, const char *queryString,
 
 	/* Generate the data, if wanted. */
 	if (!stmt->skipData)
-		processed = refresh_matview_datafill(dest, dataQuery, queryString);
+		processed = refresh_matview_datafill(dest, dataQuery, NULL, NULL, queryString);
 
 	/* Make the matview match the newly generated data. */
 	if (concurrent)
@@ -337,6 +508,12 @@ ExecRefreshMatView(RefreshMatViewStmt *stmt, const char *queryString,
 			pgstat_count_heap_insert(matviewRel, processed);
 	}
 
+	if (!stmt->skipData && RelationIsIVM(matviewRel) && !oldPopulated)
+	{
+		CreateIndexOnIMMV(dataQuery, matviewRel);
+		CreateIvmTriggersOnBaseTables(dataQuery, matviewOid);
+	}
+
 	table_close(matviewRel, NoLock);
 
 	/* Roll back any GUC changes */
@@ -371,6 +548,8 @@ ExecRefreshMatView(RefreshMatViewStmt *stmt, const char *queryString,
  */
 static uint64
 refresh_matview_datafill(DestReceiver *dest, Query *query,
+						 QueryEnvironment *queryEnv,
+						 TupleDesc *resultTupleDesc,
 						 const char *queryString)
 {
 	List	   *rewritten;
@@ -407,7 +586,7 @@ refresh_matview_datafill(DestReceiver *dest, Query *query,
 	/* Create a QueryDesc, redirecting output to our tuple receiver */
 	queryDesc = CreateQueryDesc(plan, queryString,
 								GetActiveSnapshot(), InvalidSnapshot,
-								dest, NULL, NULL, 0);
+								dest, NULL, queryEnv ? queryEnv: NULL, 0);
 
 	/* call ExecutorStart to prepare the plan for execution */
 	ExecutorStart(queryDesc, 0);
@@ -417,6 +596,9 @@ refresh_matview_datafill(DestReceiver *dest, Query *query,
 
 	processed = queryDesc->estate->es_processed;
 
+	if (resultTupleDesc)
+		*resultTupleDesc = CreateTupleDescCopy(queryDesc->tupDesc);
+
 	/* and clean up */
 	ExecutorFinish(queryDesc);
 	ExecutorEnd(queryDesc);
@@ -952,3 +1134,1219 @@ CloseMatViewIncrementalMaintenance(void)
 	matview_maintenance_depth--;
 	Assert(matview_maintenance_depth >= 0);
 }
+
+/*
+ * get_matview_query - get the Query from a matview's _RETURN rule.
+ */
+static Query *
+get_matview_query(Relation matviewRel)
+{
+	RewriteRule *rule;
+	List * actions;
+
+	/*
+	 * Check that everything is correct for a refresh. Problems at this point
+	 * are internal errors, so elog is sufficient.
+	 */
+	if (matviewRel->rd_rel->relhasrules == false ||
+		matviewRel->rd_rules->numLocks < 1)
+		elog(ERROR,
+			 "materialized view \"%s\" is missing rewrite information",
+			 RelationGetRelationName(matviewRel));
+
+	if (matviewRel->rd_rules->numLocks > 1)
+		elog(ERROR,
+			 "materialized view \"%s\" has too many rules",
+			 RelationGetRelationName(matviewRel));
+
+	rule = matviewRel->rd_rules->rules[0];
+	if (rule->event != CMD_SELECT || !(rule->isInstead))
+		elog(ERROR,
+			 "the rule for materialized view \"%s\" is not a SELECT INSTEAD OF rule",
+			 RelationGetRelationName(matviewRel));
+
+	actions = rule->actions;
+	if (list_length(actions) != 1)
+		elog(ERROR,
+			 "the rule for materialized view \"%s\" is not a single action",
+			 RelationGetRelationName(matviewRel));
+
+	/*
+	 * The stored query was rewritten at the time of the MV definition, but
+	 * has not been scribbled on by the planner.
+	 */
+	return linitial_node(Query, actions);
+}
+
+
+/* ----------------------------------------------------
+ *		Incremental View Maintenance routines
+ * ---------------------------------------------------
+ */
+
+/*
+ * IVM_immediate_before
+ *
+ * IVM trigger function invoked before base table is modified. If this is
+ * invoked firstly in the same statement, we save the transaction id and the
+ * command id at that time.
+ */
+Datum
+IVM_immediate_before(PG_FUNCTION_ARGS)
+{
+	TriggerData *trigdata = (TriggerData *) fcinfo->context;
+	char	   *matviewOid_text = trigdata->tg_trigger->tgargs[0];
+	char	   *ex_lock_text = trigdata->tg_trigger->tgargs[1];
+	Oid			matviewOid;
+	MV_TriggerHashEntry *entry;
+	bool	found;
+	bool	ex_lock;
+
+	matviewOid = DatumGetObjectId(DirectFunctionCall1(oidin, CStringGetDatum(matviewOid_text)));
+	ex_lock = DatumGetBool(DirectFunctionCall1(boolin, CStringGetDatum(ex_lock_text)));
+
+	/* If the view has more than one tables, we have to use an exclusive lock. */
+	if (ex_lock)
+	{
+		/*
+		 * Wait for concurrent transactions which update this materialized view at
+		 * READ COMMITED. This is needed to see changes committed in other
+		 * transactions. No wait and raise an error at REPEATABLE READ or
+		 * SERIALIZABLE to prevent update anomalies of matviews.
+		 * XXX: dead-lock is possible here.
+		 */
+		if (!IsolationUsesXactSnapshot())
+			LockRelationOid(matviewOid, ExclusiveLock);
+		else if (!ConditionalLockRelationOid(matviewOid, ExclusiveLock))
+		{
+			/* try to throw error by name; relation could be deleted... */
+			char	   *relname = get_rel_name(matviewOid);
+
+			if (!relname)
+				ereport(ERROR,
+						(errcode(ERRCODE_LOCK_NOT_AVAILABLE),
+						errmsg("could not obtain lock on materialized view during incremental maintenance")));
+
+			ereport(ERROR,
+					(errcode(ERRCODE_LOCK_NOT_AVAILABLE),
+					errmsg("could not obtain lock on materialized view \"%s\" during incremental maintenance",
+							relname)));
+		}
+	}
+	else
+		LockRelationOid(matviewOid, RowExclusiveLock);
+
+	/*
+	 * On the first call initialize the hashtable
+	 */
+	if (!mv_trigger_info)
+		mv_InitHashTables();
+
+	entry = (MV_TriggerHashEntry *) hash_search(mv_trigger_info,
+											  (void *) &matviewOid,
+											  HASH_ENTER, &found);
+
+	/* On the first BEFORE to update the view, initialize trigger data */
+	if (!found)
+	{
+		/*
+		 * Get a snapshot just before the table was modified for checking
+		 * tuple visibility in the pre-update state of the table.
+		 */
+		Snapshot snapshot = GetActiveSnapshot();
+
+		entry->matview_id = matviewOid;
+		entry->before_trig_count = 0;
+		entry->after_trig_count = 0;
+		entry->snapshot = RegisterSnapshot(snapshot);
+		entry->tables = NIL;
+		entry->has_old = false;
+		entry->has_new = false;
+	}
+
+	entry->before_trig_count++;
+
+	return PointerGetDatum(NULL);
+}
+
+/*
+ * IVM_immediate_maintenance
+ *
+ * IVM trigger function invoked after base table is modified.
+ * For each table, tuplestores of transition tables are collected.
+ * and after the last modification
+ */
+Datum
+IVM_immediate_maintenance(PG_FUNCTION_ARGS)
+{
+	TriggerData *trigdata = (TriggerData *) fcinfo->context;
+	Relation	rel;
+	Oid			relid;
+	Oid			matviewOid;
+	Query	   *query;
+	Query	   *rewritten = NULL;
+	char	   *matviewOid_text = trigdata->tg_trigger->tgargs[0];
+	Relation	matviewRel;
+	int old_depth = matview_maintenance_depth;
+
+	Oid			relowner;
+	Tuplestorestate *old_tuplestore = NULL;
+	Tuplestorestate *new_tuplestore = NULL;
+	DestReceiver *dest_new = NULL, *dest_old = NULL;
+	Oid			save_userid;
+	int			save_sec_context;
+	int			save_nestlevel;
+
+	MV_TriggerHashEntry *entry;
+	MV_TriggerTable		*table;
+	bool	found;
+
+	ParseState		 *pstate;
+	QueryEnvironment *queryEnv = create_queryEnv();
+	MemoryContext	oldcxt;
+	ListCell   *lc;
+	int			i;
+
+
+	/* Create a ParseState for rewriting the view definition query */
+	pstate = make_parsestate(NULL);
+	pstate->p_queryEnv = queryEnv;
+	pstate->p_expr_kind = EXPR_KIND_SELECT_TARGET;
+
+	rel = trigdata->tg_relation;
+	relid = rel->rd_id;
+
+	matviewOid = DatumGetObjectId(DirectFunctionCall1(oidin, CStringGetDatum(matviewOid_text)));
+
+	/*
+	 * On the first call initialize the hashtable
+	 */
+	if (!mv_trigger_info)
+		mv_InitHashTables();
+
+	/* get the entry for this materialized view */
+	entry = (MV_TriggerHashEntry *) hash_search(mv_trigger_info,
+											  (void *) &matviewOid,
+											  HASH_FIND, &found);
+	Assert (found && entry != NULL);
+	entry->after_trig_count++;
+
+	/* search the entry for the modified table and create new entry if not found */
+	found = false;
+	foreach(lc, entry->tables)
+	{
+		table = (MV_TriggerTable *) lfirst(lc);
+		if (table->table_id == relid)
+		{
+			found = true;
+			break;
+		}
+	}
+	if (!found)
+	{
+		oldcxt = MemoryContextSwitchTo(TopTransactionContext);
+
+		table = (MV_TriggerTable *) palloc0(sizeof(MV_TriggerTable));
+		table->table_id = relid;
+		table->old_tuplestores = NIL;
+		table->new_tuplestores = NIL;
+		table->rte_indexes = NIL;
+		table->slot = MakeSingleTupleTableSlot(RelationGetDescr(rel), table_slot_callbacks(rel));
+		table->rel = table_open(RelationGetRelid(rel), NoLock);
+		entry->tables = lappend(entry->tables, table);
+
+		MemoryContextSwitchTo(oldcxt);
+	}
+
+	/* Save the transition tables and make a request to not free immediately */
+	if (trigdata->tg_oldtable)
+	{
+		oldcxt = MemoryContextSwitchTo(TopTransactionContext);
+		table->old_tuplestores = lappend(table->old_tuplestores, trigdata->tg_oldtable);
+		entry->has_old = true;
+		MemoryContextSwitchTo(oldcxt);
+	}
+	if (trigdata->tg_newtable)
+	{
+		oldcxt = MemoryContextSwitchTo(TopTransactionContext);
+		table->new_tuplestores = lappend(table->new_tuplestores, trigdata->tg_newtable);
+		entry->has_new = true;
+		MemoryContextSwitchTo(oldcxt);
+	}
+	if (entry->has_new || entry->has_old)
+	{
+		CmdType cmd;
+
+		if (TRIGGER_FIRED_BY_INSERT(trigdata->tg_event))
+			cmd = CMD_INSERT;
+		else if (TRIGGER_FIRED_BY_DELETE(trigdata->tg_event))
+			cmd = CMD_DELETE;
+		else if (TRIGGER_FIRED_BY_UPDATE(trigdata->tg_event))
+			cmd = CMD_UPDATE;
+		else
+			elog(ERROR,"unsupported trigger type");
+
+		/* Prolong lifespan of transition tables to the end of the last AFTER trigger */
+		SetTransitionTablePreserved(relid, cmd);
+	}
+
+
+	/* If this is not the last AFTER trigger call, immediately exit. */
+	Assert (entry->before_trig_count >= entry->after_trig_count);
+	if (entry->before_trig_count != entry->after_trig_count)
+		return PointerGetDatum(NULL);
+
+	/*
+	 * If this is the last AFTER trigger call, continue and update the view.
+	 */
+
+	/*
+	 * Advance command counter to make the updated base table row locally
+	 * visible.
+	 */
+	CommandCounterIncrement();
+
+	matviewRel = table_open(matviewOid, NoLock);
+
+	/* Make sure it is a materialized view. */
+	Assert(matviewRel->rd_rel->relkind == RELKIND_MATVIEW);
+
+	/*
+	 * Get and push the latast snapshot to see any changes which is committed
+	 * during waiting in other transactions at READ COMMITTED level.
+	 */
+	PushActiveSnapshot(GetTransactionSnapshot());
+
+	/*
+	 * Check for active uses of the relation in the current transaction, such
+	 * as open scans.
+	 *
+	 * NB: We count on this to protect us against problems with refreshing the
+	 * data using TABLE_INSERT_FROZEN.
+	 */
+	CheckTableNotInUse(matviewRel, "refresh a materialized view incrementally");
+
+	/*
+	 * Switch to the owner's userid, so that any functions are run as that
+	 * user.  Also arrange to make GUC variable changes local to this command.
+	 * We will switch modes when we are about to execute user code.
+	 */
+	relowner = matviewRel->rd_rel->relowner;
+	GetUserIdAndSecContext(&save_userid, &save_sec_context);
+	SetUserIdAndSecContext(relowner,
+						   save_sec_context | SECURITY_RESTRICTED_OPERATION);
+	save_nestlevel = NewGUCNestLevel();
+
+	/* get view query*/
+	query = get_matview_query(matviewRel);
+
+	/*
+	 * When a base table is truncated, the view content will be empty if the
+	 * view definition query does not contain an aggregate without a GROUP clause.
+	 * Therefore, such views can be truncated.
+	 */
+	if (TRIGGER_FIRED_BY_TRUNCATE(trigdata->tg_event))
+	{
+		ExecuteTruncateGuts(list_make1(matviewRel), list_make1_oid(matviewOid),
+							NIL, DROP_RESTRICT, false, false);
+
+		/* Clean up hash entry and delete tuplestores */
+		clean_up_IVM_hash_entry(entry, false);
+
+		/* Pop the original snapshot. */
+		PopActiveSnapshot();
+
+		table_close(matviewRel, NoLock);
+
+		/* Roll back any GUC changes */
+		AtEOXact_GUC(false, save_nestlevel);
+
+		/* Restore userid and security context */
+		SetUserIdAndSecContext(save_userid, save_sec_context);
+
+		return PointerGetDatum(NULL);
+	}
+
+	/*
+	 * rewrite query for calculating deltas
+	 */
+
+	rewritten = copyObject(query);
+
+	/* Replace resnames in a target list with materialized view's attnames */
+	i = 0;
+	foreach (lc, rewritten->targetList)
+	{
+		TargetEntry *tle = (TargetEntry *) lfirst(lc);
+		Form_pg_attribute attr = TupleDescAttr(matviewRel->rd_att, i);
+		char *resname = NameStr(attr->attname);
+
+		tle->resname = pstrdup(resname);
+		i++;
+	}
+
+	/* Set all tables in the query to pre-update state */
+	rewritten = rewrite_query_for_preupdate_state(rewritten, entry->tables,
+												  pstate, matviewOid);
+	/* Rewrite for counting duplicated tuples */
+	rewritten = rewrite_query_for_counting(rewritten, pstate);
+
+	/* Create tuplestores to store view deltas */
+	if (entry->has_old)
+	{
+		oldcxt = MemoryContextSwitchTo(TopTransactionContext);
+
+		old_tuplestore = tuplestore_begin_heap(false, false, work_mem);
+		dest_old = CreateDestReceiver(DestTuplestore);
+		SetTuplestoreDestReceiverParams(dest_old,
+									old_tuplestore,
+									TopTransactionContext,
+									false,
+									NULL,
+									NULL);
+
+		MemoryContextSwitchTo(oldcxt);
+	}
+	if (entry->has_new)
+	{
+		oldcxt = MemoryContextSwitchTo(TopTransactionContext);
+
+		new_tuplestore = tuplestore_begin_heap(false, false, work_mem);
+		dest_new = CreateDestReceiver(DestTuplestore);
+		SetTuplestoreDestReceiverParams(dest_new,
+									new_tuplestore,
+									TopTransactionContext,
+									false,
+									NULL,
+									NULL);
+		MemoryContextSwitchTo(oldcxt);
+	}
+
+	/* for all modified tables */
+	foreach(lc, entry->tables)
+	{
+		ListCell *lc2;
+
+		table = (MV_TriggerTable *) lfirst(lc);
+
+		/* loop for self-join */
+		foreach(lc2, table->rte_indexes)
+		{
+			int	rte_index = lfirst_int(lc2);
+			TupleDesc		tupdesc_old;
+			TupleDesc		tupdesc_new;
+
+			/* calculate delta tables */
+			calc_delta(table, rte_index, rewritten, dest_old, dest_new,
+					   &tupdesc_old, &tupdesc_new, queryEnv);
+
+			/* Set the table in the query to post-update state */
+			rewritten = rewrite_query_for_postupdate_state(rewritten, table, rte_index);
+
+			PG_TRY();
+			{
+				/* apply the delta tables to the materialized view */
+				apply_delta(matviewOid, old_tuplestore, new_tuplestore,
+							tupdesc_old, tupdesc_new, query);
+			}
+			PG_CATCH();
+			{
+				matview_maintenance_depth = old_depth;
+				PG_RE_THROW();
+			}
+			PG_END_TRY();
+
+			/* clear view delta tuplestores */
+			if (old_tuplestore)
+				tuplestore_clear(old_tuplestore);
+			if (new_tuplestore)
+				tuplestore_clear(new_tuplestore);
+		}
+	}
+
+	/* Clean up hash entry and delete tuplestores */
+	clean_up_IVM_hash_entry(entry, false);
+	if (old_tuplestore)
+	{
+		dest_old->rDestroy(dest_old);
+		tuplestore_end(old_tuplestore);
+	}
+	if (new_tuplestore)
+	{
+		dest_new->rDestroy(dest_new);
+		tuplestore_end(new_tuplestore);
+	}
+
+	/* Pop the original snapshot. */
+	PopActiveSnapshot();
+
+	table_close(matviewRel, NoLock);
+
+	/* Roll back any GUC changes */
+	AtEOXact_GUC(false, save_nestlevel);
+
+	/* Restore userid and security context */
+	SetUserIdAndSecContext(save_userid, save_sec_context);
+
+	return PointerGetDatum(NULL);
+}
+
+/*
+ * rewrite_query_for_preupdate_state
+ *
+ * Rewrite the query so that base tables' RTEs will represent "pre-update"
+ * state of tables. This is necessary to calculate view delta after multiple
+ * tables are modified.
+ */
+static Query*
+rewrite_query_for_preupdate_state(Query *query, List *tables,
+								  ParseState *pstate, Oid matviewid)
+{
+	ListCell *lc;
+	int num_rte = list_length(query->rtable);
+	int i;
+
+
+	/* register delta ENRs */
+	register_delta_ENRs(pstate, query, tables);
+
+	/* XXX: Is necessary? Is this right timing? */
+	AcquireRewriteLocks(query, true, false);
+
+	i = 1;
+	foreach(lc, query->rtable)
+	{
+		RangeTblEntry *r = (RangeTblEntry*) lfirst(lc);
+
+		ListCell *lc2;
+		foreach(lc2, tables)
+		{
+			MV_TriggerTable *table = (MV_TriggerTable *) lfirst(lc2);
+			/*
+			 * if the modified table is found then replace the original RTE with
+			 * "pre-state" RTE and append its index to the list.
+			 */
+			if (r->relid == table->table_id)
+			{
+				List *securityQuals;
+				List *withCheckOptions;
+				bool  hasRowSecurity;
+				bool  hasSubLinks;
+
+				RangeTblEntry *rte_pre = get_prestate_rte(r, table, pstate->p_queryEnv, matviewid);
+
+				/*
+				 * Set a row security poslicies of the modified table to the subquery RTE which
+				 * represents the pre-update state of the table.
+				 */
+				get_row_security_policies(query, table->original_rte, i,
+										  &securityQuals, &withCheckOptions,
+										  &hasRowSecurity, &hasSubLinks);
+
+				if (hasRowSecurity)
+				{
+					query->hasRowSecurity = true;
+					rte_pre->security_barrier = true;
+				}
+				if (hasSubLinks)
+					query->hasSubLinks = true;
+
+				rte_pre->securityQuals = securityQuals;
+				lfirst(lc) = rte_pre;
+
+				table->rte_indexes = lappend_int(table->rte_indexes, i);
+				break;
+			}
+		}
+
+		/* finish the loop if we processed all RTE included in the original query */
+		if (i++ >= num_rte)
+			break;
+	}
+
+	return query;
+}
+
+/*
+ * register_delta_ENRs
+ *
+ * For all modified tables, make ENRs for their transition tables
+ * and register them to the queryEnv. ENR's RTEs are also appended
+ * into the list in query tree.
+ */
+static void
+register_delta_ENRs(ParseState *pstate, Query *query, List *tables)
+{
+	QueryEnvironment *queryEnv = pstate->p_queryEnv;
+	ListCell *lc;
+	RangeTblEntry	*rte;
+
+	foreach(lc, tables)
+	{
+		MV_TriggerTable *table = (MV_TriggerTable *) lfirst(lc);
+		ListCell *lc2;
+		int count;
+
+		count = 0;
+		foreach(lc2, table->old_tuplestores)
+		{
+			Tuplestorestate *oldtable = (Tuplestorestate *) lfirst(lc2);
+			EphemeralNamedRelation enr =
+				palloc(sizeof(EphemeralNamedRelationData));
+			ParseNamespaceItem *nsitem;
+
+			enr->md.name = make_delta_enr_name("old", table->table_id, count);
+			enr->md.reliddesc = table->table_id;
+			enr->md.tupdesc = NULL;
+			enr->md.enrtype = ENR_NAMED_TUPLESTORE;
+			enr->md.enrtuples = tuplestore_tuple_count(oldtable);
+			enr->reldata = oldtable;
+			register_ENR(queryEnv, enr);
+
+			nsitem = addRangeTableEntryForENR(pstate, makeRangeVar(NULL, enr->md.name, -1), true);
+			rte = nsitem->p_rte;
+
+			query->rtable = lappend(query->rtable, rte);
+
+			count++;
+		}
+
+		count = 0;
+		foreach(lc2, table->new_tuplestores)
+		{
+			Tuplestorestate *newtable = (Tuplestorestate *) lfirst(lc2);
+			EphemeralNamedRelation enr =
+				palloc(sizeof(EphemeralNamedRelationData));
+			ParseNamespaceItem *nsitem;
+
+			enr->md.name = make_delta_enr_name("new", table->table_id, count);
+			enr->md.reliddesc = table->table_id;
+			enr->md.tupdesc = NULL;
+			enr->md.enrtype = ENR_NAMED_TUPLESTORE;
+			enr->md.enrtuples = tuplestore_tuple_count(newtable);
+			enr->reldata = newtable;
+			register_ENR(queryEnv, enr);
+
+			nsitem = addRangeTableEntryForENR(pstate, makeRangeVar(NULL, enr->md.name, -1), true);
+			rte = nsitem->p_rte;
+
+			query->rtable = lappend(query->rtable, rte);
+
+			count++;
+		}
+	}
+}
+
+#define DatumGetItemPointer(X)	 ((ItemPointer) DatumGetPointer(X))
+#define PG_GETARG_ITEMPOINTER(n) DatumGetItemPointer(PG_GETARG_DATUM(n))
+
+/*
+ * ivm_visible_in_prestate
+ *
+ * Check visibility of a tuple specified by the tableoid and item pointer
+ * using the snapshot taken just before the table was modified.
+ */
+Datum
+ivm_visible_in_prestate(PG_FUNCTION_ARGS)
+{
+	Oid			tableoid = PG_GETARG_OID(0);
+	ItemPointer itemPtr = PG_GETARG_ITEMPOINTER(1);
+	Oid			matviewOid = PG_GETARG_OID(2);
+	MV_TriggerHashEntry *entry;
+	MV_TriggerTable		*table = NULL;
+	ListCell   *lc;
+	bool	found;
+	bool	result;
+
+	if (!in_delta_calculation)
+		ereport(ERROR,
+				(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+				 errmsg("ivm_visible_in_prestate can be called only in delta calculation")));
+
+	entry = (MV_TriggerHashEntry *) hash_search(mv_trigger_info,
+											  (void *) &matviewOid,
+											  HASH_FIND, &found);
+	Assert (found && entry != NULL);
+
+	foreach(lc, entry->tables)
+	{
+		table = (MV_TriggerTable *) lfirst(lc);
+		if (table->table_id == tableoid)
+			break;
+	}
+
+	Assert (table != NULL);
+
+	result = table_tuple_fetch_row_version(table->rel, itemPtr, entry->snapshot, table->slot);
+
+	PG_RETURN_BOOL(result);
+}
+
+/*
+ * get_prestate_rte
+ *
+ * Rewrite RTE of the modified table to a subquery which represents
+ * "pre-state" table. The original RTE is saved in table->rte_original.
+ */
+static RangeTblEntry*
+get_prestate_rte(RangeTblEntry *rte, MV_TriggerTable *table,
+				 QueryEnvironment *queryEnv, Oid matviewid)
+{
+	StringInfoData str;
+	RawStmt *raw;
+	Query *subquery;
+	Relation rel;
+	ParseState *pstate;
+	char *relname;
+	int i;
+
+	pstate = make_parsestate(NULL);
+	pstate->p_queryEnv = queryEnv;
+	pstate->p_expr_kind = EXPR_KIND_SELECT_TARGET;
+
+	/*
+	 * We can use NoLock here since AcquireRewriteLocks should
+	 * have locked the relation already.
+	 */
+	rel = table_open(table->table_id, NoLock);
+	relname = quote_qualified_identifier(
+					get_namespace_name(RelationGetNamespace(rel)),
+									   RelationGetRelationName(rel));
+	table_close(rel, NoLock);
+
+	/*
+	 * Filtering inserted row using the snapshot taken before the table
+	 * is modified. ctid is required for maintaining outer join views.
+	 */
+	initStringInfo(&str);
+	appendStringInfo(&str,
+		"SELECT t.* FROM %s t"
+		" WHERE pg_catalog.ivm_visible_in_prestate(t.tableoid, t.ctid ,%d::pg_catalog.oid)",
+			relname, matviewid);
+
+	/*
+	 * Append deleted rows contained in old transition tables.
+	 */
+	for (i = 0; i < list_length(table->old_tuplestores); i++)
+	{
+		appendStringInfo(&str, " UNION ALL ");
+		appendStringInfo(&str," SELECT * FROM %s",
+			make_delta_enr_name("old", table->table_id, i));
+	}
+
+	/* Get a subquery representing pre-state of the table */
+	raw = (RawStmt*)linitial(raw_parser(str.data, RAW_PARSE_DEFAULT));
+	subquery = transformStmt(pstate, raw->stmt);
+
+	/* save the original RTE */
+	table->original_rte = copyObject(rte);
+
+	rte->rtekind = RTE_SUBQUERY;
+	rte->subquery = subquery;
+	rte->security_barrier = false;
+
+	/* Clear fields that should not be set in a subquery RTE */
+	rte->relid = InvalidOid;
+	rte->relkind = 0;
+	rte->rellockmode = 0;
+	rte->tablesample = NULL;
+	rte->perminfoindex = 0;         /* no permission checking for this RTE */
+	rte->inh = false;			/* must not be set for a subquery */
+
+	return rte;
+}
+
+/*
+ * make_delta_enr_name
+ *
+ * Make a name for ENR of a transition table from the base table's oid.
+ * prefix will be "new" or "old" depending on its transition table kind..
+ */
+static char*
+make_delta_enr_name(const char *prefix, Oid relid, int count)
+{
+	char buf[NAMEDATALEN];
+	char *name;
+
+	snprintf(buf, NAMEDATALEN, "__ivm_%s_%u_%u", prefix, relid, count);
+	name = pstrdup(buf);
+
+	return name;
+}
+
+/*
+ * replace_rte_with_delta
+ *
+ * Replace RTE of the modified table with a single table delta that combine its
+ * all transition tables.
+ */
+static RangeTblEntry*
+replace_rte_with_delta(RangeTblEntry *rte, MV_TriggerTable *table, bool is_new,
+					   QueryEnvironment *queryEnv)
+{
+	Oid relid = table->table_id;
+	StringInfoData str;
+	ParseState	*pstate;
+	RawStmt *raw;
+	Query *sub;
+	int		num_tuplestores = list_length(is_new ? table->new_tuplestores : table->old_tuplestores);
+	int		i;
+
+	/* the previous RTE must be a subquery which represents "pre-state" table */
+	Assert(rte->rtekind == RTE_SUBQUERY);
+
+	/* Create a ParseState for rewriting the view definition query */
+	pstate = make_parsestate(NULL);
+	pstate->p_queryEnv = queryEnv;
+	pstate->p_expr_kind = EXPR_KIND_SELECT_TARGET;
+
+	initStringInfo(&str);
+
+	for (i = 0; i < num_tuplestores; i++)
+	{
+		if (i > 0)
+			appendStringInfo(&str, " UNION ALL ");
+
+		appendStringInfo(&str,
+			" SELECT * FROM %s",
+			make_delta_enr_name(is_new ? "new" : "old", relid, i));
+	}
+
+	raw = (RawStmt*)linitial(raw_parser(str.data, RAW_PARSE_DEFAULT));
+	sub = transformStmt(pstate, raw->stmt);
+
+	/*
+	 * Update the subquery so that it represent the combined transition
+	 * table.  Note that we leave the security_barrier and securityQuals
+	 * fields so that the subquery relation can be protected by the RLS
+	 * policy as same as the modified table.
+	 */
+	rte->rtekind = RTE_SUBQUERY;
+	rte->subquery = sub;
+
+	return rte;
+}
+
+/*
+ * rewrite_query_for_counting
+ *
+ * Rewrite query for counting duplicated tuples.
+ */
+static Query *
+rewrite_query_for_counting(Query *query, ParseState *pstate)
+{
+	TargetEntry *tle_count;
+	FuncCall *fn;
+	Node *node;
+
+	/* Add count(*) for counting distinct tuples in views */
+	fn = makeFuncCall(SystemFuncName("count"), NIL, COERCE_EXPLICIT_CALL, -1);
+	fn->agg_star = true;
+	if (!query->groupClause && !query->hasAggs)
+		query->groupClause = transformDistinctClause(NULL, &query->targetList, query->sortClause, false);
+
+	node = ParseFuncOrColumn(pstate, fn->funcname, NIL, NULL, fn, false, -1);
+
+	tle_count = makeTargetEntry((Expr *) node,
+								list_length(query->targetList) + 1,
+								pstrdup("__ivm_count__"),
+								false);
+	query->targetList = lappend(query->targetList, tle_count);
+	query->hasAggs = true;
+
+	return query;
+}
+
+/*
+ * calc_delta
+ *
+ * Calculate view deltas generated under the modification of a table specified
+ * by the RTE index.
+ */
+static void
+calc_delta(MV_TriggerTable *table, int rte_index, Query *query,
+			DestReceiver *dest_old, DestReceiver *dest_new,
+			TupleDesc *tupdesc_old, TupleDesc *tupdesc_new,
+			QueryEnvironment *queryEnv)
+{
+	ListCell *lc = list_nth_cell(query->rtable, rte_index - 1);
+	RangeTblEntry *rte = (RangeTblEntry *) lfirst(lc);
+
+	in_delta_calculation = true;
+
+	/* Generate old delta */
+	if (list_length(table->old_tuplestores) > 0)
+	{
+		/* Replace the modified table with the old delta table and calculate the old view delta. */
+		replace_rte_with_delta(rte, table, false, queryEnv);
+		refresh_matview_datafill(dest_old, query, queryEnv, tupdesc_old, "");
+	}
+
+	/* Generate new delta */
+	if (list_length(table->new_tuplestores) > 0)
+	{
+		/* Replace the modified table with the new delta table and calculate the new view delta*/
+		replace_rte_with_delta(rte, table, true, queryEnv);
+		refresh_matview_datafill(dest_new, query, queryEnv, tupdesc_new, "");
+	}
+
+	in_delta_calculation = false;
+}
+
+/*
+ * rewrite_query_for_postupdate_state
+ *
+ * Rewrite the query so that the specified base table's RTEs will represent
+ * "post-update" state of tables. This is called after the view delta
+ * calculation due to changes on this table finishes.
+ */
+static Query*
+rewrite_query_for_postupdate_state(Query *query, MV_TriggerTable *table, int rte_index)
+{
+	ListCell *lc = list_nth_cell(query->rtable, rte_index - 1);
+
+	/* Retore the original RTE */
+	lfirst(lc) = table->original_rte;
+
+	return query;
+}
+
+/*
+ * apply_delta
+ *
+ * Apply deltas to the materialized view. In outer join cases, this requires
+ * the view maintenance graph.
+ */
+static void
+apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *new_tuplestores,
+			TupleDesc tupdesc_old, TupleDesc tupdesc_new,
+			Query *query)
+{
+	StringInfoData querybuf;
+	StringInfoData target_list_buf;
+	Relation	matviewRel;
+	char	   *matviewname;
+	ListCell	*lc;
+	int			i;
+	List	   *keys = NIL;
+
+
+	/*
+	 * get names of the materialized view and delta tables
+	 */
+
+	matviewRel = table_open(matviewOid, NoLock);
+	matviewname = quote_qualified_identifier(get_namespace_name(RelationGetNamespace(matviewRel)),
+											 RelationGetRelationName(matviewRel));
+
+	/*
+	 * Build parts of the maintenance queries
+	 */
+
+	initStringInfo(&querybuf);
+	initStringInfo(&target_list_buf);
+
+	/* build string of target list */
+	for (i = 0; i < matviewRel->rd_att->natts; i++)
+	{
+		Form_pg_attribute attr = TupleDescAttr(matviewRel->rd_att, i);
+		char   *resname = NameStr(attr->attname);
+
+		if (i != 0)
+			appendStringInfo(&target_list_buf, ", ");
+		appendStringInfo(&target_list_buf, "%s", quote_qualified_identifier(NULL, resname));
+	}
+
+	i = 0;
+	foreach (lc, query->targetList)
+	{
+		TargetEntry *tle = (TargetEntry *) lfirst(lc);
+		Form_pg_attribute attr = TupleDescAttr(matviewRel->rd_att, i);
+
+		i++;
+
+		if (tle->resjunk)
+			continue;
+
+		keys = lappend(keys, attr);
+	}
+
+	/* Start maintaining the materialized view. */
+	OpenMatViewIncrementalMaintenance();
+
+	/* Open SPI context. */
+	if (SPI_connect() != SPI_OK_CONNECT)
+		elog(ERROR, "SPI_connect failed");
+
+	/* For tuple deletion */
+	if (old_tuplestores && tuplestore_tuple_count(old_tuplestores) > 0)
+	{
+		EphemeralNamedRelation enr = palloc(sizeof(EphemeralNamedRelationData));
+		int				rc;
+
+		/* convert tuplestores to ENR, and register for SPI */
+		enr->md.name = pstrdup(OLD_DELTA_ENRNAME);
+		enr->md.reliddesc = InvalidOid;
+		enr->md.tupdesc = tupdesc_old;
+		enr->md.enrtype = ENR_NAMED_TUPLESTORE;
+		enr->md.enrtuples = tuplestore_tuple_count(old_tuplestores);
+		enr->reldata = old_tuplestores;
+
+		rc = SPI_register_relation(enr);
+		if (rc != SPI_OK_REL_REGISTER)
+			elog(ERROR, "SPI_register failed");
+
+		apply_old_delta(matviewname, OLD_DELTA_ENRNAME, keys);
+
+	}
+	/* For tuple insertion */
+	if (new_tuplestores && tuplestore_tuple_count(new_tuplestores) > 0)
+	{
+		EphemeralNamedRelation enr = palloc(sizeof(EphemeralNamedRelationData));
+		int rc;
+
+		/* convert tuplestores to ENR, and register for SPI */
+		enr->md.name = pstrdup(NEW_DELTA_ENRNAME);
+		enr->md.reliddesc = InvalidOid;
+		enr->md.tupdesc = tupdesc_new;;
+		enr->md.enrtype = ENR_NAMED_TUPLESTORE;
+		enr->md.enrtuples = tuplestore_tuple_count(new_tuplestores);
+		enr->reldata = new_tuplestores;
+
+		rc = SPI_register_relation(enr);
+		if (rc != SPI_OK_REL_REGISTER)
+			elog(ERROR, "SPI_register failed");
+
+		/* apply new delta */
+		apply_new_delta(matviewname, NEW_DELTA_ENRNAME, &target_list_buf);
+	}
+
+	/* We're done maintaining the materialized view. */
+	CloseMatViewIncrementalMaintenance();
+
+	table_close(matviewRel, NoLock);
+
+	/* Close SPI context. */
+	if (SPI_finish() != SPI_OK_FINISH)
+		elog(ERROR, "SPI_finish failed");
+}
+
+/*
+ * apply_old_delta
+ *
+ * Execute a query for applying a delta table given by deltname_old
+ * which contains tuples to be deleted from to a materialized view given by
+ * matviewname.  This is used when counting is not required.
+ */
+static void
+apply_old_delta(const char *matviewname, const char *deltaname_old,
+				List *keys)
+{
+	StringInfoData	querybuf;
+	StringInfoData	keysbuf;
+	char   *match_cond;
+	ListCell *lc;
+
+	/* build WHERE condition for searching tuples to be deleted */
+	match_cond = get_matching_condition_string(keys);
+
+	/* build string of keys list */
+	initStringInfo(&keysbuf);
+	foreach (lc, keys)
+	{
+		Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc);
+		char   *resname = NameStr(attr->attname);
+		appendStringInfo(&keysbuf, "%s", quote_qualified_identifier("mv", resname));
+		if (lnext(keys, lc))
+			appendStringInfo(&keysbuf, ", ");
+	}
+
+	/* Search for matching tuples from the view and update or delete if found. */
+	initStringInfo(&querybuf);
+	appendStringInfo(&querybuf,
+	"DELETE FROM %s WHERE ctid IN ("
+		"SELECT tid FROM (SELECT pg_catalog.row_number() over (partition by %s) AS \"__ivm_row_number__\","
+								  "mv.ctid AS tid,"
+								  "diff.\"__ivm_count__\""
+						 "FROM %s AS mv, %s AS diff "
+						 "WHERE %s) v "
+					"WHERE v.\"__ivm_row_number__\" OPERATOR(pg_catalog.<=) v.\"__ivm_count__\")",
+					matviewname,
+					keysbuf.data,
+					matviewname, deltaname_old,
+					match_cond);
+
+	if (SPI_exec(querybuf.data, 0) != SPI_OK_DELETE)
+		elog(ERROR, "SPI_exec failed: %s", querybuf.data);
+}
+
+/*
+ * apply_new_delta
+ *
+ * Execute a query for applying a delta table given by deltname_new
+ * which contains tuples to be inserted into a materialized view given by
+ * matviewname.  This is used when counting is not required.
+ */
+static void
+apply_new_delta(const char *matviewname, const char *deltaname_new,
+				StringInfo target_list)
+{
+	StringInfoData	querybuf;
+
+	/* Search for matching tuples from the view and update or delete if found. */
+	initStringInfo(&querybuf);
+	appendStringInfo(&querybuf,
+					"INSERT INTO %s (%s) SELECT %s FROM ("
+						"SELECT diff.*, pg_catalog.generate_series(1, diff.\"__ivm_count__\")"
+							" AS __ivm_generate_series__ "
+						"FROM %s AS diff) AS v",
+					matviewname, target_list->data, target_list->data,
+					deltaname_new);
+
+	if (SPI_exec(querybuf.data, 0) != SPI_OK_INSERT)
+		elog(ERROR, "SPI_exec failed: %s", querybuf.data);
+}
+
+/*
+ * get_matching_condition_string
+ *
+ * Build a predicate string for looking for a tuple with given keys.
+ */
+static char *
+get_matching_condition_string(List *keys)
+{
+	StringInfoData match_cond;
+	ListCell	*lc;
+
+	/* If there is no key columns, the condition is always true. */
+	if (keys == NIL)
+		return "true";
+
+	initStringInfo(&match_cond);
+	foreach (lc, keys)
+	{
+		Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc);
+		char   *resname = NameStr(attr->attname);
+		char   *mv_resname = quote_qualified_identifier("mv", resname);
+		char   *diff_resname = quote_qualified_identifier("diff", resname);
+		Oid		typid = attr->atttypid;
+
+		/* Considering NULL values, we can not use simple = operator. */
+		appendStringInfo(&match_cond, "(");
+		generate_equal(&match_cond, typid, mv_resname, diff_resname);
+		appendStringInfo(&match_cond, " OR (%s IS NULL AND %s IS NULL))",
+						 mv_resname, diff_resname);
+
+		if (lnext(keys, lc))
+			appendStringInfo(&match_cond, " AND ");
+	}
+
+	return match_cond.data;
+}
+
+/*
+ * generate_equals
+ *
+ * Generate an equality clause using given operands' default equality
+ * operator.
+ */
+static void
+generate_equal(StringInfo querybuf, Oid opttype,
+			   const char *leftop, const char *rightop)
+{
+	TypeCacheEntry *typentry;
+
+	typentry = lookup_type_cache(opttype, TYPECACHE_EQ_OPR);
+	if (!OidIsValid(typentry->eq_opr))
+		ereport(ERROR,
+				(errcode(ERRCODE_UNDEFINED_FUNCTION),
+				 errmsg("could not identify an equality operator for type %s",
+						format_type_be_qualified(opttype))));
+
+	generate_operator_clause(querybuf,
+							 leftop, opttype,
+							 typentry->eq_opr,
+							 rightop, opttype);
+}
+
+/*
+ * mv_InitHashTables
+ */
+static void
+mv_InitHashTables(void)
+{
+	HASHCTL		ctl;
+
+	memset(&ctl, 0, sizeof(ctl));
+	ctl.keysize = sizeof(Oid);
+	ctl.entrysize = sizeof(MV_TriggerHashEntry);
+	mv_trigger_info = hash_create("MV trigger info",
+								 MV_INIT_QUERYHASHSIZE,
+								 &ctl, HASH_ELEM | HASH_BLOBS);
+}
+
+/*
+ * AtAbort_IVM
+ *
+ * Clean up hash entries for all materialized views. This is called at
+ * transaction abort.
+ */
+void
+AtAbort_IVM()
+{
+	HASH_SEQ_STATUS seq;
+	MV_TriggerHashEntry *entry;
+
+	if (mv_trigger_info)
+	{
+		hash_seq_init(&seq, mv_trigger_info);
+		while ((entry = hash_seq_search(&seq)) != NULL)
+			clean_up_IVM_hash_entry(entry, true);
+	}
+	in_delta_calculation = false;
+}
+
+/*
+ * clean_up_IVM_hash_entry
+ *
+ * Clean up tuple stores and hash entries for a materialized view after its
+ * maintenance finished.
+ */
+static void
+clean_up_IVM_hash_entry(MV_TriggerHashEntry *entry, bool is_abort)
+{
+	bool found;
+	ListCell *lc;
+
+	foreach(lc, entry->tables)
+	{
+		MV_TriggerTable *table = (MV_TriggerTable *) lfirst(lc);
+
+		list_free(table->old_tuplestores);
+		list_free(table->new_tuplestores);
+		if (!is_abort)
+		{
+			ExecDropSingleTupleTableSlot(table->slot);
+			table_close(table->rel, NoLock);
+		}
+	}
+	list_free(entry->tables);
+
+	if (!is_abort)
+		UnregisterSnapshot(entry->snapshot);
+
+	hash_search(mv_trigger_info, (void *) &entry->matview_id, HASH_REMOVE, &found);
+}
+
+/*
+ * isIvmName
+ *
+ * Check if this is a IVM hidden column from the name.
+ */
+bool
+isIvmName(const char *s)
+{
+	if (s)
+		return (strncmp(s, "__ivm_", 6) == 0);
+	return false;
+}
diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat
index 134e3b22fd..8b1a87c934 100644
--- a/src/include/catalog/pg_proc.dat
+++ b/src/include/catalog/pg_proc.dat
@@ -12195,4 +12195,14 @@
   proargtypes => 'int2',
   prosrc => 'gist_stratnum_identity' },
 
+# IVM
+{ oid => '786', descr => 'ivm trigger (before)',
+  proname => 'IVM_immediate_before', provolatile => 'v', prorettype => 'trigger',
+  proargtypes => '', prosrc => 'IVM_immediate_before' },
+{ oid => '787', descr => 'ivm trigger (after)',
+  proname => 'IVM_immediate_maintenance', provolatile => 'v', prorettype => 'trigger',
+  proargtypes => '', prosrc => 'IVM_immediate_maintenance' },
+{ oid => '788', descr => 'ivm filetring ',
+  proname => 'ivm_visible_in_prestate', provolatile => 's', prorettype => 'bool',
+  proargtypes => 'oid tid oid', prosrc => 'ivm_visible_in_prestate' },
 ]
diff --git a/src/include/commands/createas.h b/src/include/commands/createas.h
index 94678e3834..396ad1bb4c 100644
--- a/src/include/commands/createas.h
+++ b/src/include/commands/createas.h
@@ -16,6 +16,7 @@
 
 #include "catalog/objectaddress.h"
 #include "nodes/params.h"
+#include "nodes/pathnodes.h"
 #include "parser/parse_node.h"
 #include "tcop/dest.h"
 #include "utils/queryenvironment.h"
@@ -25,6 +26,9 @@ extern ObjectAddress ExecCreateTableAs(ParseState *pstate, CreateTableAsStmt *st
 									   ParamListInfo params, QueryEnvironment *queryEnv,
 									   QueryCompletion *qc);
 
+extern void CreateIvmTriggersOnBaseTables(Query *qry, Oid matviewOid);
+extern void CreateIndexOnIMMV(Query *query, Relation matviewRel);
+
 extern int	GetIntoRelEFlags(IntoClause *intoClause);
 
 extern DestReceiver *CreateIntoRelDestReceiver(IntoClause *intoClause);
diff --git a/src/include/commands/matview.h b/src/include/commands/matview.h
index 817b2ba0b6..3257e1adff 100644
--- a/src/include/commands/matview.h
+++ b/src/include/commands/matview.h
@@ -15,6 +15,7 @@
 #define MATVIEW_H
 
 #include "catalog/objectaddress.h"
+#include "fmgr.h"
 #include "nodes/params.h"
 #include "nodes/parsenodes.h"
 #include "tcop/dest.h"
@@ -23,6 +24,8 @@
 
 extern void SetMatViewPopulatedState(Relation relation, bool newstate);
 
+extern void SetMatViewIVMState(Relation relation, bool newstate);
+
 extern ObjectAddress ExecRefreshMatView(RefreshMatViewStmt *stmt, const char *queryString,
 										ParamListInfo params, QueryCompletion *qc);
 
@@ -30,4 +33,10 @@ extern DestReceiver *CreateTransientRelDestReceiver(Oid transientoid);
 
 extern bool MatViewIncrementalMaintenanceIsEnabled(void);
 
+extern Datum IVM_immediate_before(PG_FUNCTION_ARGS);
+extern Datum IVM_immediate_maintenance(PG_FUNCTION_ARGS);
+extern Datum IVM_visible_in_prestate(PG_FUNCTION_ARGS);
+extern void AtAbort_IVM(void);
+extern bool isIvmName(const char *s);
+
 #endif							/* MATVIEW_H */
-- 
2.25.1


--Multipart=_Sun__31_Mar_2024_22_59_31_+0900_msknEviJj08_wgqO
Content-Type: text/x-diff;
 name="v32-0007-Add-DISTINCT-support-for-IVM.patch"
Content-Disposition: attachment;
 filename="v32-0007-Add-DISTINCT-support-for-IVM.patch"
Content-Transfer-Encoding: 7bit



^ permalink  raw  reply  [nested|flat] 101+ messages in thread

* [PATCH v29 06/11] Add Incremental View Maintenance support
@ 2023-05-31 09:59  Yugo Nagata <[email protected]>
  0 siblings, 0 replies; 101+ messages in thread

From: Yugo Nagata @ 2023-05-31 09:59 UTC (permalink / raw)

In this implementation, AFTER triggers are used to collect
tuplestores containing transition table contents. When multiple tables
are changed, multiple AFTER triggers are invoked, then the final AFTER
trigger performs actual update of the matview. In addition, BEFORE
triggers are also used to handle global information for view
maintenance.

To calculate view deltas, we need both pre-state and post-state of base
tables. Post-update states are available in AFTER trigger, and pre-update
states can be calculated by removing inserted tuples and appending deleted
tuples. Insterted tuples are filtered using the snapshot taken before
table modiication, and deleted tuples are contained in the old transition
table.

Incrementally Maintainable Materialized Views (IMMV) can contain
duplicated tuples.

This patch also allows self-join, simultaneous updates of more than
one base table, and multiple updates of the same base table.
---
 src/backend/access/transam/xact.c |    5 +
 src/backend/commands/createas.c   |  680 +++++++++++++
 src/backend/commands/matview.c    | 1466 ++++++++++++++++++++++++++++-
 src/include/catalog/pg_proc.dat   |   10 +
 src/include/commands/createas.h   |    4 +
 src/include/commands/matview.h    |    9 +
 6 files changed, 2139 insertions(+), 35 deletions(-)

diff --git a/src/backend/access/transam/xact.c b/src/backend/access/transam/xact.c
index 8daaa535ed..cd280bdffd 100644
--- a/src/backend/access/transam/xact.c
+++ b/src/backend/access/transam/xact.c
@@ -36,6 +36,7 @@
 #include "catalog/pg_enum.h"
 #include "catalog/storage.h"
 #include "commands/async.h"
+#include "commands/matview.h"
 #include "commands/tablecmds.h"
 #include "commands/trigger.h"
 #include "common/pg_prng.h"
@@ -2803,6 +2804,7 @@ AbortTransaction(void)
 	AtAbort_Notify();
 	AtEOXact_RelationMap(false, is_parallel_worker);
 	AtAbort_Twophase();
+	AtAbort_IVM();
 
 	/*
 	 * Advertise the fact that we aborted in pg_xact (assuming that we got as
@@ -5080,6 +5082,9 @@ AbortSubTransaction(void)
 	pgstat_progress_end_command();
 	UnlockBuffers();
 
+	/* Clean up hash entries for incremental view maintenance */
+	AtAbort_IVM();
+
 	/* Reset WAL record construction state */
 	XLogResetInsertion();
 
diff --git a/src/backend/commands/createas.c b/src/backend/commands/createas.c
index e91920ca14..415f110516 100644
--- a/src/backend/commands/createas.c
+++ b/src/backend/commands/createas.c
@@ -32,15 +32,26 @@
 #include "access/xact.h"
 #include "access/xlog.h"
 #include "catalog/namespace.h"
+#include "catalog/index.h"
+#include "catalog/pg_constraint.h"
+#include "catalog/pg_inherits.h"
+#include "catalog/pg_trigger.h"
 #include "catalog/toasting.h"
 #include "commands/createas.h"
+#include "commands/defrem.h"
 #include "commands/matview.h"
 #include "commands/prepare.h"
 #include "commands/tablecmds.h"
+#include "commands/tablespace.h"
+#include "commands/trigger.h"
 #include "commands/view.h"
 #include "miscadmin.h"
+#include "optimizer/optimizer.h"
+#include "optimizer/prep.h"
 #include "nodes/makefuncs.h"
 #include "nodes/nodeFuncs.h"
+#include "parser/parser.h"
+#include "parser/parsetree.h"
 #include "parser/parse_clause.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/smgr.h"
@@ -73,6 +84,12 @@ static bool intorel_receive(TupleTableSlot *slot, DestReceiver *self);
 static void intorel_shutdown(DestReceiver *self);
 static void intorel_destroy(DestReceiver *self);
 
+static void CreateIvmTriggersOnBaseTablesRecurse(Query *qry, Node *node, Oid matviewOid,
+									 Relids *relids, bool ex_lock);
+static void CreateIvmTrigger(Oid relOid, Oid viewOid, int16 type, int16 timing, bool ex_lock);
+static void check_ivm_restriction(Node *node);
+static bool check_ivm_restriction_walker(Node *node, void *context);
+static Bitmapset *get_primary_key_attnos_from_query(Query *query, List **constraintList);
 
 /*
  * create_ctas_internal
@@ -282,6 +299,18 @@ ExecCreateTableAs(ParseState *pstate, CreateTableAsStmt *stmt,
 		save_nestlevel = NewGUCNestLevel();
 	}
 
+	if (is_matview && into->ivm)
+	{
+		/* check if the query is supported in IMMV definition */
+		if (contain_mutable_functions((Node *) query))
+			ereport(ERROR,
+					(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+					 errmsg("mutable function is not supported on incrementally maintainable materialized view"),
+					 errhint("functions must be marked IMMUTABLE")));
+
+		check_ivm_restriction((Node *) query);
+	}
+
 	if (into->skipData)
 	{
 		/*
@@ -358,6 +387,27 @@ ExecCreateTableAs(ParseState *pstate, CreateTableAsStmt *stmt,
 
 		/* Restore userid and security context */
 		SetUserIdAndSecContext(save_userid, save_sec_context);
+
+		if (into->ivm)
+		{
+			Oid matviewOid = address.objectId;
+			Relation matviewRel = table_open(matviewOid, NoLock);
+
+			/*
+			 * Mark relisivm field, if it's a matview and into->ivm is true.
+			 */
+			SetMatViewIVMState(matviewRel, true);
+
+			if (!into->skipData)
+			{
+				/* Create an index on incremental maintainable materialized view, if possible */
+				CreateIndexOnIMMV((Query *) into->viewQuery, matviewRel);
+
+				/* Create triggers on incremental maintainable materialized view */
+				CreateIvmTriggersOnBaseTables((Query *) into->viewQuery, matviewOid);
+			}
+			table_close(matviewRel, NoLock);
+		}
 	}
 
 	return address;
@@ -635,3 +685,633 @@ intorel_destroy(DestReceiver *self)
 {
 	pfree(self);
 }
+
+/*
+ * CreateIvmTriggersOnBaseTables -- create IVM triggers on all base tables
+ */
+void
+CreateIvmTriggersOnBaseTables(Query *qry, Oid matviewOid)
+{
+	Relids	relids = NULL;
+	bool	ex_lock = false;
+	RangeTblEntry *rte;
+
+	/* Immediately return if we don't have any base tables. */
+	if (list_length(qry->rtable) < 1)
+		return;
+
+	/*
+	 * If the view has more than one base tables, we need an exclusive lock
+	 * on the view so that the view would be maintained serially to avoid
+	 * the inconsistency that occurs when two base tables are modified in
+	 * concurrent transactions. However, if the view has only one table,
+	 * we can use a weaker lock.
+	 *
+	 * The type of lock should be determined here, because if we check the
+	 * view definition at maintenance time, we need to acquire a weaker lock,
+	 * and upgrading the lock level after this increases probability of
+	 * deadlock.
+	 */
+
+	rte = list_nth(qry->rtable, 0);
+	if (list_length(qry->rtable) > 1 || rte->rtekind != RTE_RELATION)
+		ex_lock = true;
+
+	CreateIvmTriggersOnBaseTablesRecurse(qry, (Node *)qry, matviewOid, &relids, ex_lock);
+
+	bms_free(relids);
+}
+
+static void
+CreateIvmTriggersOnBaseTablesRecurse(Query *qry, Node *node, Oid matviewOid,
+									 Relids *relids, bool ex_lock)
+{
+	if (node == NULL)
+		return;
+
+	/* This can recurse, so check for excessive recursion */
+	check_stack_depth();
+
+	switch (nodeTag(node))
+	{
+		case T_Query:
+			{
+				Query *query = (Query *) node;
+
+				CreateIvmTriggersOnBaseTablesRecurse(qry, (Node *)query->jointree, matviewOid, relids, ex_lock);
+			}
+			break;
+
+		case T_RangeTblRef:
+			{
+				int			rti = ((RangeTblRef *) node)->rtindex;
+				RangeTblEntry *rte = rt_fetch(rti, qry->rtable);
+
+				if (rte->rtekind == RTE_RELATION && !bms_is_member(rte->relid, *relids))
+				{
+					CreateIvmTrigger(rte->relid, matviewOid, TRIGGER_TYPE_INSERT, TRIGGER_TYPE_BEFORE, ex_lock);
+					CreateIvmTrigger(rte->relid, matviewOid, TRIGGER_TYPE_DELETE, TRIGGER_TYPE_BEFORE, ex_lock);
+					CreateIvmTrigger(rte->relid, matviewOid, TRIGGER_TYPE_UPDATE, TRIGGER_TYPE_BEFORE, ex_lock);
+					CreateIvmTrigger(rte->relid, matviewOid, TRIGGER_TYPE_TRUNCATE, TRIGGER_TYPE_BEFORE, true);
+					CreateIvmTrigger(rte->relid, matviewOid, TRIGGER_TYPE_INSERT, TRIGGER_TYPE_AFTER, ex_lock);
+					CreateIvmTrigger(rte->relid, matviewOid, TRIGGER_TYPE_DELETE, TRIGGER_TYPE_AFTER, ex_lock);
+					CreateIvmTrigger(rte->relid, matviewOid, TRIGGER_TYPE_UPDATE, TRIGGER_TYPE_AFTER, ex_lock);
+					CreateIvmTrigger(rte->relid, matviewOid, TRIGGER_TYPE_TRUNCATE, TRIGGER_TYPE_AFTER, true);
+
+					*relids = bms_add_member(*relids, rte->relid);
+				}
+			}
+			break;
+
+		case T_FromExpr:
+			{
+				FromExpr   *f = (FromExpr *) node;
+				ListCell   *l;
+
+				foreach(l, f->fromlist)
+					CreateIvmTriggersOnBaseTablesRecurse(qry, lfirst(l), matviewOid, relids, ex_lock);
+			}
+			break;
+
+		case T_JoinExpr:
+			{
+				JoinExpr   *j = (JoinExpr *) node;
+
+				CreateIvmTriggersOnBaseTablesRecurse(qry, j->larg, matviewOid, relids, ex_lock);
+				CreateIvmTriggersOnBaseTablesRecurse(qry, j->rarg, matviewOid, relids, ex_lock);
+			}
+			break;
+
+		default:
+			elog(ERROR, "unrecognized node type: %d", (int) nodeTag(node));
+	}
+}
+
+/*
+ * CreateIvmTrigger -- create IVM trigger on a base table
+ */
+static void
+CreateIvmTrigger(Oid relOid, Oid viewOid, int16 type, int16 timing, bool ex_lock)
+{
+	ObjectAddress	refaddr;
+	ObjectAddress	address;
+	CreateTrigStmt *ivm_trigger;
+	List *transitionRels = NIL;
+
+	Assert(timing == TRIGGER_TYPE_BEFORE || timing == TRIGGER_TYPE_AFTER);
+
+	refaddr.classId = RelationRelationId;
+	refaddr.objectId = viewOid;
+	refaddr.objectSubId = 0;
+
+	ivm_trigger = makeNode(CreateTrigStmt);
+	ivm_trigger->relation = NULL;
+	ivm_trigger->row = false;
+
+	ivm_trigger->timing = timing;
+	ivm_trigger->events = type;
+
+	switch (type)
+	{
+		case TRIGGER_TYPE_INSERT:
+			ivm_trigger->trigname = (timing == TRIGGER_TYPE_BEFORE ? "IVM_trigger_ins_before" : "IVM_trigger_ins_after");
+			break;
+		case TRIGGER_TYPE_DELETE:
+			ivm_trigger->trigname = (timing == TRIGGER_TYPE_BEFORE ? "IVM_trigger_del_before" : "IVM_trigger_del_after");
+			break;
+		case TRIGGER_TYPE_UPDATE:
+			ivm_trigger->trigname = (timing == TRIGGER_TYPE_BEFORE ? "IVM_trigger_upd_before" : "IVM_trigger_upd_after");
+			break;
+		case TRIGGER_TYPE_TRUNCATE:
+			ivm_trigger->trigname = (timing == TRIGGER_TYPE_BEFORE ? "IVM_trigger_truncate_before" : "IVM_trigger_truncate_after");
+			break;
+		default:
+			elog(ERROR, "unsupported trigger type");
+	}
+
+	if (timing == TRIGGER_TYPE_AFTER)
+	{
+		if (type == TRIGGER_TYPE_INSERT || type == TRIGGER_TYPE_UPDATE)
+		{
+			TriggerTransition *n = makeNode(TriggerTransition);
+			n->name = "__ivm_newtable";
+			n->isNew = true;
+			n->isTable = true;
+
+			transitionRels = lappend(transitionRels, n);
+		}
+		if (type == TRIGGER_TYPE_DELETE || type == TRIGGER_TYPE_UPDATE)
+		{
+			TriggerTransition *n = makeNode(TriggerTransition);
+			n->name = "__ivm_oldtable";
+			n->isNew = false;
+			n->isTable = true;
+
+			transitionRels = lappend(transitionRels, n);
+		}
+	}
+
+	/*
+	 * XXX: When using DELETE or UPDATE, we must use exclusive lock for now
+	 * because apply_old_delta(_with_count) uses ctid to identify the tuple
+	 * to be deleted/deleted, but doesn't work in concurrent situations.
+	 *
+	 * If the view doesn't have aggregate, distinct, or tuple duplicate,
+	 * then it would work even in concurrent situations. However, we don't have
+	 * any way to guarantee the view has a unique key before opening the IMMV
+	 * at the maintenance time because users may drop the unique index.
+	 */
+
+	if (type == TRIGGER_TYPE_DELETE || type == TRIGGER_TYPE_UPDATE)
+		ex_lock = true;
+
+	ivm_trigger->funcname =
+		(timing == TRIGGER_TYPE_BEFORE ? SystemFuncName("IVM_immediate_before") : SystemFuncName("IVM_immediate_maintenance"));
+
+	ivm_trigger->columns = NIL;
+	ivm_trigger->transitionRels = transitionRels;
+	ivm_trigger->whenClause = NULL;
+	ivm_trigger->isconstraint = false;
+	ivm_trigger->deferrable = false;
+	ivm_trigger->initdeferred = false;
+	ivm_trigger->constrrel = NULL;
+	ivm_trigger->args = list_make2(
+		makeString(DatumGetPointer(DirectFunctionCall1(oidout, ObjectIdGetDatum(viewOid)))),
+		makeString(DatumGetPointer(DirectFunctionCall1(boolout, BoolGetDatum(ex_lock))))
+		);
+
+	address = CreateTrigger(ivm_trigger, NULL, relOid, InvalidOid, InvalidOid,
+						 InvalidOid, InvalidOid, InvalidOid, NULL, true, false);
+
+	recordDependencyOn(&address, &refaddr, DEPENDENCY_AUTO);
+
+	/* Make changes-so-far visible */
+	CommandCounterIncrement();
+}
+
+/*
+ * check_ivm_restriction --- look for specify nodes in the query tree
+ */
+static void
+check_ivm_restriction(Node *node)
+{
+	check_ivm_restriction_walker(node, NULL);
+}
+
+static bool
+check_ivm_restriction_walker(Node *node, void *context)
+{
+	if (node == NULL)
+		return false;
+
+	/*
+	 * We currently don't support Sub-Query.
+	 */
+	if (IsA(node, SubPlan) || IsA(node, SubLink))
+		ereport(ERROR,
+				(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+				 errmsg("subquery is not supported on incrementally maintainable materialized view")));
+
+	/* This can recurse, so check for excessive recursion */
+	check_stack_depth();
+
+	switch (nodeTag(node))
+	{
+		case T_Query:
+			{
+				Query *qry = (Query *)node;
+				ListCell   *lc;
+				List       *vars;
+
+				/* if contained CTE, return error */
+				if (qry->cteList != NIL)
+					ereport(ERROR,
+							(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+							 errmsg("CTE is not supported on incrementally maintainable materialized view")));
+				if (qry->havingQual != NULL)
+					ereport(ERROR,
+							(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+							 errmsg(" HAVING clause is not supported on incrementally maintainable materialized view")));
+				if (qry->sortClause != NIL)	/* There is a possibility that we don't need to return an error */
+					ereport(ERROR,
+							(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+							 errmsg("ORDER BY clause is not supported on incrementally maintainable materialized view")));
+				if (qry->limitOffset != NULL || qry->limitCount != NULL)
+					ereport(ERROR,
+							(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+							 errmsg("LIMIT/OFFSET clause is not supported on incrementally maintainable materialized view")));
+				if (qry->distinctClause)
+					ereport(ERROR,
+							(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+							 errmsg("DISTINCT is not supported on incrementally maintainable materialized view")));
+				if (qry->hasDistinctOn)
+					ereport(ERROR,
+							(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+							 errmsg("DISTINCT ON is not supported on incrementally maintainable materialized view")));
+				if (qry->hasWindowFuncs)
+					ereport(ERROR,
+							(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+							 errmsg("window functions are not supported on incrementally maintainable materialized view")));
+				if (qry->groupingSets != NIL)
+					ereport(ERROR,
+							(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+							 errmsg("GROUPING SETS, ROLLUP, or CUBE clauses is not supported on incrementally maintainable materialized view")));
+				if (qry->setOperations != NULL)
+					ereport(ERROR,
+							(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+							 errmsg("UNION/INTERSECT/EXCEPT statements are not supported on incrementally maintainable materialized view")));
+				if (list_length(qry->targetList) == 0)
+					ereport(ERROR,
+							(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+							 errmsg("empty target list is not supported on incrementally maintainable materialized view")));
+				if (qry->rowMarks != NIL)
+					ereport(ERROR,
+							(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+							 errmsg("FOR UPDATE/SHARE clause is not supported on incrementally maintainable materialized view")));
+
+				/* system column restrictions */
+				vars = pull_vars_of_level((Node *) qry, 0);
+				foreach(lc, vars)
+				{
+					if (IsA(lfirst(lc), Var))
+					{
+						Var *var = (Var *) lfirst(lc);
+						/* if system column, return error */
+						if (var->varattno < 0)
+							ereport(ERROR,
+									(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+									 errmsg("system column is not supported on incrementally maintainable materialized view")));
+					}
+				}
+
+				/* restrictions for rtable */
+				foreach(lc, qry->rtable)
+				{
+					RangeTblEntry *rte = (RangeTblEntry *) lfirst(lc);
+
+					if (rte->subquery)
+						ereport(ERROR,
+								(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+								 errmsg("subquery is not supported on incrementally maintainable materialized view")));
+
+					if (rte->tablesample != NULL)
+						ereport(ERROR,
+								(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+								 errmsg("TABLESAMPLE clause is not supported on incrementally maintainable materialized view")));
+
+					if (rte->relkind == RELKIND_PARTITIONED_TABLE)
+						ereport(ERROR,
+								(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+								 errmsg("partitioned table is not supported on incrementally maintainable materialized view")));
+
+					if (rte->relkind == RELKIND_RELATION && has_superclass(rte->relid))
+						ereport(ERROR,
+								(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+								 errmsg("partitions is not supported on incrementally maintainable materialized view")));
+
+					if (rte->relkind == RELKIND_RELATION && find_inheritance_children(rte->relid, NoLock) != NIL)
+						ereport(ERROR,
+								(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+								 errmsg("inheritance parent is not supported on incrementally maintainable materialized view")));
+
+					if (rte->relkind == RELKIND_FOREIGN_TABLE)
+						ereport(ERROR,
+								(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+								 errmsg("foreign table is not supported on incrementally maintainable materialized view")));
+
+					if (rte->relkind == RELKIND_VIEW ||
+						rte->relkind == RELKIND_MATVIEW)
+						ereport(ERROR,
+								(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+								 errmsg("VIEW or MATERIALIZED VIEW is not supported on incrementally maintainable materialized view")));
+
+					if (rte->rtekind == RTE_VALUES)
+						ereport(ERROR,
+								(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+								 errmsg("VALUES is not supported on incrementally maintainable materialized view")));
+
+				}
+
+				query_tree_walker(qry, check_ivm_restriction_walker, NULL, QTW_IGNORE_RANGE_TABLE);
+
+				break;
+			}
+		case T_TargetEntry:
+			{
+				TargetEntry *tle = (TargetEntry *)node;
+				if (isIvmName(tle->resname))
+						ereport(ERROR,
+								(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+								 errmsg("column name %s is not supported on incrementally maintainable materialized view", tle->resname)));
+
+				expression_tree_walker(node, check_ivm_restriction_walker, NULL);
+				break;
+			}
+		case T_JoinExpr:
+			{
+				JoinExpr *joinexpr = (JoinExpr *)node;
+
+				if (joinexpr->jointype > JOIN_INNER)
+						ereport(ERROR,
+								(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+								 errmsg("OUTER JOIN is not supported on incrementally maintainable materialized view")));
+
+				expression_tree_walker(node, check_ivm_restriction_walker, NULL);
+			}
+			break;
+		case T_Aggref:
+			ereport(ERROR,
+					(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+					 errmsg("aggregate function is not supported on incrementally maintainable materialized view")));
+			break;
+		default:
+			expression_tree_walker(node, check_ivm_restriction_walker, (void *) context);
+			break;
+	}
+	return false;
+}
+
+/*
+ * CreateIndexOnIMMV
+ *
+ * Create a unique index on incremental maintainable materialized view.
+ * If the view definition query has a GROUP BY clause, the index is created
+ * on the columns of GROUP BY expressions. Otherwise, if the view contains
+ * all primary key attritubes of its base tables in the target list, the index
+ * is created on these attritubes. In other cases, no index is created.
+ */
+void
+CreateIndexOnIMMV(Query *query, Relation matviewRel)
+{
+	ListCell *lc;
+	IndexStmt  *index;
+	ObjectAddress address;
+	List *constraintList = NIL;
+	char		idxname[NAMEDATALEN];
+	List	   *indexoidlist = RelationGetIndexList(matviewRel);
+	ListCell   *indexoidscan;
+	Bitmapset *key_attnos;
+
+	snprintf(idxname, sizeof(idxname), "%s_index", RelationGetRelationName(matviewRel));
+
+	index = makeNode(IndexStmt);
+
+	index->unique = true;
+	index->primary = false;
+	index->isconstraint = false;
+	index->deferrable = false;
+	index->initdeferred = false;
+	index->idxname = idxname;
+	index->relation =
+		makeRangeVar(get_namespace_name(RelationGetNamespace(matviewRel)),
+					 pstrdup(RelationGetRelationName(matviewRel)),
+					 -1);
+	index->accessMethod = DEFAULT_INDEX_TYPE;
+	index->options = NIL;
+	index->tableSpace = get_tablespace_name(matviewRel->rd_rel->reltablespace);
+	index->whereClause = NULL;
+	index->indexParams = NIL;
+	index->indexIncludingParams = NIL;
+	index->excludeOpNames = NIL;
+	index->idxcomment = NULL;
+	index->indexOid = InvalidOid;
+	index->oldNumber = InvalidRelFileNumber;
+	index->oldCreateSubid = InvalidSubTransactionId;
+	index->oldFirstRelfilelocatorSubid = InvalidSubTransactionId;
+	index->transformed = true;
+	index->concurrent = false;
+	index->if_not_exists = false;
+
+	/* create index on the base tables' primary key columns */
+	key_attnos = get_primary_key_attnos_from_query(query, &constraintList);
+	if (key_attnos)
+	{
+		foreach(lc, query->targetList)
+		{
+			TargetEntry *tle = (TargetEntry *) lfirst(lc);
+			Form_pg_attribute attr = TupleDescAttr(matviewRel->rd_att, tle->resno - 1);
+
+			if (bms_is_member(tle->resno - FirstLowInvalidHeapAttributeNumber, key_attnos))
+			{
+				IndexElem  *iparam;
+
+				iparam = makeNode(IndexElem);
+				iparam->name = pstrdup(NameStr(attr->attname));
+				iparam->expr = NULL;
+				iparam->indexcolname = NULL;
+				iparam->collation = NIL;
+				iparam->opclass = NIL;
+				iparam->opclassopts = NIL;
+				iparam->ordering = SORTBY_DEFAULT;
+				iparam->nulls_ordering = SORTBY_NULLS_DEFAULT;
+				index->indexParams = lappend(index->indexParams, iparam);
+			}
+		}
+	}
+	else
+	{
+		/* create no index, just notice that an appropriate index is necessary for efficient IVM */
+		ereport(NOTICE,
+				(errmsg("could not create an index on materialized view \"%s\" automatically",
+						RelationGetRelationName(matviewRel)),
+				 errdetail("This target list does not have all the primary key columns. "),
+				 errhint("Create an index on the materialized view for efficient incremental maintenance.")));
+		return;
+	}
+
+	/* If we have a compatible index, we don't need to create another. */
+	foreach(indexoidscan, indexoidlist)
+	{
+		Oid			indexoid = lfirst_oid(indexoidscan);
+		Relation	indexRel;
+		bool		hasCompatibleIndex = false;
+
+		indexRel = index_open(indexoid, AccessShareLock);
+
+		if (CheckIndexCompatible(indexRel->rd_id,
+								index->accessMethod,
+								index->indexParams,
+								index->excludeOpNames))
+			hasCompatibleIndex = true;
+
+		index_close(indexRel, AccessShareLock);
+
+		if (hasCompatibleIndex)
+			return;
+	}
+
+	address = DefineIndex(RelationGetRelid(matviewRel),
+						  index,
+						  InvalidOid,
+						  InvalidOid,
+						  InvalidOid,
+						  -1,
+						  false, true, false, false, true);
+
+	ereport(NOTICE,
+			(errmsg("created index \"%s\" on materialized view \"%s\"",
+					idxname, RelationGetRelationName(matviewRel))));
+
+	/*
+	 * Make dependencies so that the index is dropped if any base tables's
+	 * primary key is dropped.
+	 */
+	foreach(lc, constraintList)
+	{
+		Oid constraintOid = lfirst_oid(lc);
+		ObjectAddress	refaddr;
+
+		refaddr.classId = ConstraintRelationId;
+		refaddr.objectId = constraintOid;
+		refaddr.objectSubId = 0;
+
+		recordDependencyOn(&address, &refaddr, DEPENDENCY_NORMAL);
+	}
+}
+
+
+/*
+ * get_primary_key_attnos_from_query
+ *
+ * Identify the columns in base tables' primary keys in the target list.
+ *
+ * Returns a Bitmapset of the column attnos of the primary key's columns of
+ * tables that used in the query.  The attnos are offset by
+ * FirstLowInvalidHeapAttributeNumber as same as get_primary_key_attnos.
+ *
+ * If any table has no primary key or any primary key's columns is not in
+ * the target list, return NULL.  We also return NULL if any pkey constraint
+ * is deferrable.
+ *
+ * constraintList is set to a list of the OIDs of the pkey constraints.
+ */
+static Bitmapset *
+get_primary_key_attnos_from_query(Query *query, List **constraintList)
+{
+	List *key_attnos_list = NIL;
+	ListCell *lc;
+	int i;
+	Bitmapset *keys = NULL;
+	Relids	rels_in_from;
+
+	/*
+	 * Collect primary key attributes from all tables used in query. The key attributes
+	 * sets for each table are stored in key_attnos_list in order by RTE index.
+	 */
+	foreach(lc, query->rtable)
+	{
+		RangeTblEntry *r = (RangeTblEntry*) lfirst(lc);
+		Bitmapset *key_attnos;
+		bool	has_pkey = true;
+
+		/* for tables, call get_primary_key_attnos */
+		if (r->rtekind == RTE_RELATION)
+		{
+			Oid constraintOid;
+			key_attnos = get_primary_key_attnos(r->relid, false, &constraintOid);
+			*constraintList = lappend_oid(*constraintList, constraintOid);
+			has_pkey = (key_attnos != NULL);
+		}
+		/* for other RTEs, store NULL into key_attnos_list */
+		else
+			key_attnos = NULL;
+
+		/*
+		 * If any table or subquery has no primary key or its pkey constraint is deferrable,
+		 * we cannot get key attributes for this query, so return NULL.
+		 */
+		if (!has_pkey)
+			return NULL;
+
+		key_attnos_list = lappend(key_attnos_list, key_attnos);
+	}
+
+	/* Collect key attributes appearing in the target list */
+	i = 1;
+	foreach(lc, query->targetList)
+	{
+		TargetEntry *tle = (TargetEntry *) flatten_join_alias_vars(NULL, query, lfirst(lc));
+
+		if (IsA(tle->expr, Var))
+		{
+			Var *var = (Var*) tle->expr;
+			Bitmapset *key_attnos = list_nth(key_attnos_list, var->varno - 1);
+
+			/* check if this attribute is from a base table's primary key */
+			if (bms_is_member(var->varattno - FirstLowInvalidHeapAttributeNumber, key_attnos))
+			{
+				/*
+				 * Remove found key attributes from key_attnos_list, and add this
+				 * to the result list.
+				 */
+				key_attnos = bms_del_member(key_attnos, var->varattno - FirstLowInvalidHeapAttributeNumber);
+				if (bms_is_empty(key_attnos))
+				{
+					key_attnos_list = list_delete_nth_cell(key_attnos_list, var->varno - 1);
+					key_attnos_list = list_insert_nth(key_attnos_list, var->varno - 1, NULL);
+				}
+				keys = bms_add_member(keys, i - FirstLowInvalidHeapAttributeNumber);
+			}
+		}
+		i++;
+	}
+
+	/* Collect RTE indexes of relations appearing in the FROM clause */
+	rels_in_from = get_relids_in_jointree((Node *) query->jointree, false, false);
+
+	/*
+	 * Check if all key attributes of relations in FROM are appearing in the target
+	 * list.  If an attribute remains in key_attnos_list in spite of the table is used
+	 * in FROM clause, the target is missing this key attribute, so we return NULL.
+	 */
+	i = 1;
+	foreach(lc, key_attnos_list)
+	{
+		Bitmapset *bms = (Bitmapset *)lfirst(lc);
+		if (!bms_is_empty(bms) && bms_is_member(i, rels_in_from))
+			return NULL;
+		i++;
+	}
+
+	return keys;
+}
diff --git a/src/backend/commands/matview.c b/src/backend/commands/matview.c
index ac2e74fa3f..39305f3c49 100644
--- a/src/backend/commands/matview.c
+++ b/src/backend/commands/matview.c
@@ -25,26 +25,37 @@
 #include "catalog/indexing.h"
 #include "catalog/namespace.h"
 #include "catalog/pg_am.h"
+#include "catalog/pg_depend.h"
+#include "catalog/pg_trigger.h"
 #include "catalog/pg_opclass.h"
 #include "catalog/pg_operator.h"
 #include "commands/cluster.h"
 #include "commands/matview.h"
 #include "commands/tablecmds.h"
 #include "commands/tablespace.h"
+#include "commands/createas.h"
 #include "executor/executor.h"
 #include "executor/spi.h"
+#include "executor/tstoreReceiver.h"
 #include "miscadmin.h"
+#include "nodes/makefuncs.h"
+#include "parser/analyze.h"
+#include "parser/parse_clause.h"
+#include "parser/parse_func.h"
 #include "parser/parse_relation.h"
 #include "pgstat.h"
 #include "rewrite/rewriteHandler.h"
+#include "rewrite/rowsecurity.h"
 #include "storage/lmgr.h"
 #include "storage/smgr.h"
 #include "tcop/tcopprot.h"
 #include "utils/builtins.h"
+#include "utils/fmgroids.h"
 #include "utils/lsyscache.h"
 #include "utils/rel.h"
 #include "utils/snapmgr.h"
 #include "utils/syscache.h"
+#include "utils/typcache.h"
 
 
 typedef struct
@@ -58,6 +69,52 @@ typedef struct
 	BulkInsertState bistate;	/* bulk insert state */
 } DR_transientrel;
 
+#define MV_INIT_QUERYHASHSIZE	16
+
+/*
+ * MV_TriggerHashEntry
+ *
+ * Hash entry for base tables on which IVM trigger is invoked
+ */
+typedef struct MV_TriggerHashEntry
+{
+	Oid	matview_id;			/* OID of the materialized view */
+	int	before_trig_count;	/* count of before triggers invoked */
+	int	after_trig_count;	/* count of after triggers invoked */
+
+	Snapshot	snapshot;	/* Snapshot just before table change */
+
+	List   *tables;		/* List of MV_TriggerTable */
+	bool	has_old;	/* tuples are deleted from any table? */
+	bool	has_new;	/* tuples are inserted into any table? */
+} MV_TriggerHashEntry;
+
+/*
+ * MV_TriggerTable
+ *
+ * IVM related data for tables on which the trigger is invoked.
+ */
+typedef struct MV_TriggerTable
+{
+	Oid		table_id;			/* OID of the modified table */
+	List   *old_tuplestores;	/* tuplestores for deleted tuples */
+	List   *new_tuplestores;	/* tuplestores for inserted tuples */
+
+	List   *rte_indexes;		/* List of RTE index of the modified table */
+	RangeTblEntry *original_rte;	/* the original RTE saved before rewriting query */
+
+	Relation	rel;			/* relation of the modified table */
+	TupleTableSlot *slot;		/* for checking visibility in the pre-state table */
+} MV_TriggerTable;
+
+static HTAB *mv_trigger_info = NULL;
+
+static bool in_delta_calculation = false;
+
+/* ENR name for materialized view delta */
+#define NEW_DELTA_ENRNAME "new_delta"
+#define OLD_DELTA_ENRNAME "old_delta"
+
 static int	matview_maintenance_depth = 0;
 
 static void transientrel_startup(DestReceiver *self, int operation, TupleDesc typeinfo);
@@ -65,7 +122,9 @@ static bool transientrel_receive(TupleTableSlot *slot, DestReceiver *self);
 static void transientrel_shutdown(DestReceiver *self);
 static void transientrel_destroy(DestReceiver *self);
 static uint64 refresh_matview_datafill(DestReceiver *dest, Query *query,
-									   const char *queryString);
+						 QueryEnvironment *queryEnv,
+						 TupleDesc *resultTupleDesc,
+						 const char *queryString);
 static char *make_temptable_name_n(char *tempname, int n);
 static void refresh_by_match_merge(Oid matviewOid, Oid tempOid, Oid relowner,
 								   int save_sec_context);
@@ -73,6 +132,37 @@ static void refresh_by_heap_swap(Oid matviewOid, Oid OIDNewHeap, char relpersist
 static bool is_usable_unique_index(Relation indexRel);
 static void OpenMatViewIncrementalMaintenance(void);
 static void CloseMatViewIncrementalMaintenance(void);
+static Query *get_matview_query(Relation matviewRel);
+
+static Query *rewrite_query_for_preupdate_state(Query *query, List *tables,
+								  ParseState *pstate, Oid matviewid);
+static void register_delta_ENRs(ParseState *pstate, Query *query, List *tables);
+static char *make_delta_enr_name(const char *prefix, Oid relid, int count);
+static RangeTblEntry *get_prestate_rte(RangeTblEntry *rte, MV_TriggerTable *table,
+				 QueryEnvironment *queryEnv, Oid matviewid);
+static RangeTblEntry *replace_rte_with_delta(RangeTblEntry *rte, MV_TriggerTable *table, bool is_new,
+		   QueryEnvironment *queryEnv);
+static Query *rewrite_query_for_counting(Query *query, ParseState *pstate);
+
+static void calc_delta(MV_TriggerTable *table, int rte_index, Query *query,
+			DestReceiver *dest_old, DestReceiver *dest_new,
+			TupleDesc *tupdesc_old, TupleDesc *tupdesc_new,
+			QueryEnvironment *queryEnv);
+static Query *rewrite_query_for_postupdate_state(Query *query, MV_TriggerTable *table, int rte_index);
+
+static void apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *new_tuplestores,
+			TupleDesc tupdesc_old, TupleDesc tupdesc_new,
+			Query *query);
+static void apply_old_delta(const char *matviewname, const char *deltaname_old,
+				List *keys);
+static void apply_new_delta(const char *matviewname, const char *deltaname_new,
+				StringInfo target_list);
+static char *get_matching_condition_string(List *keys);
+static void generate_equal(StringInfo querybuf, Oid opttype,
+			   const char *leftop, const char *rightop);
+
+static void mv_InitHashTables(void);
+static void clean_up_IVM_hash_entry(MV_TriggerHashEntry *entry, bool is_abort);
 
 /*
  * SetMatViewPopulatedState
@@ -114,6 +204,46 @@ SetMatViewPopulatedState(Relation relation, bool newstate)
 	CommandCounterIncrement();
 }
 
+/*
+ * SetMatViewIVMState
+ *		Mark a materialized view as IVM, or not.
+ *
+ * NOTE: caller must be holding an appropriate lock on the relation.
+ */
+void
+SetMatViewIVMState(Relation relation, bool newstate)
+{
+	Relation	pgrel;
+	HeapTuple	tuple;
+
+	Assert(relation->rd_rel->relkind == RELKIND_MATVIEW);
+
+	/*
+	 * Update relation's pg_class entry.  Crucial side-effect: other backends
+	 * (and this one too!) are sent SI message to make them rebuild relcache
+	 * entries.
+	 */
+	pgrel = table_open(RelationRelationId, RowExclusiveLock);
+	tuple = SearchSysCacheCopy1(RELOID,
+								ObjectIdGetDatum(RelationGetRelid(relation)));
+	if (!HeapTupleIsValid(tuple))
+		elog(ERROR, "cache lookup failed for relation %u",
+			 RelationGetRelid(relation));
+
+	((Form_pg_class) GETSTRUCT(tuple))->relisivm = newstate;
+
+	CatalogTupleUpdate(pgrel, &tuple->t_self, tuple);
+
+	heap_freetuple(tuple);
+	table_close(pgrel, RowExclusiveLock);
+
+	/*
+	 * Advance command counter to make the updated pg_class row locally
+	 * visible.
+	 */
+	CommandCounterIncrement();
+}
+
 /*
  * ExecRefreshMatView -- execute a REFRESH MATERIALIZED VIEW command
  *
@@ -140,8 +270,6 @@ ExecRefreshMatView(RefreshMatViewStmt *stmt, const char *queryString,
 {
 	Oid			matviewOid;
 	Relation	matviewRel;
-	RewriteRule *rule;
-	List	   *actions;
 	Query	   *dataQuery;
 	Oid			tableSpace;
 	Oid			relowner;
@@ -155,6 +283,7 @@ ExecRefreshMatView(RefreshMatViewStmt *stmt, const char *queryString,
 	int			save_sec_context;
 	int			save_nestlevel;
 	ObjectAddress address;
+	bool oldPopulated;
 
 	/* Determine strength of lock needed. */
 	concurrent = stmt->concurrent;
@@ -178,6 +307,7 @@ ExecRefreshMatView(RefreshMatViewStmt *stmt, const char *queryString,
 	SetUserIdAndSecContext(relowner,
 						   save_sec_context | SECURITY_RESTRICTED_OPERATION);
 	save_nestlevel = NewGUCNestLevel();
+	oldPopulated = RelationIsPopulated(matviewRel);
 
 	/* Make sure it is a materialized view. */
 	if (matviewRel->rd_rel->relkind != RELKIND_MATVIEW)
@@ -199,32 +329,9 @@ ExecRefreshMatView(RefreshMatViewStmt *stmt, const char *queryString,
 				 errmsg("%s and %s options cannot be used together",
 						"CONCURRENTLY", "WITH NO DATA")));
 
-	/*
-	 * Check that everything is correct for a refresh. Problems at this point
-	 * are internal errors, so elog is sufficient.
-	 */
-	if (matviewRel->rd_rel->relhasrules == false ||
-		matviewRel->rd_rules->numLocks < 1)
-		elog(ERROR,
-			 "materialized view \"%s\" is missing rewrite information",
-			 RelationGetRelationName(matviewRel));
-
-	if (matviewRel->rd_rules->numLocks > 1)
-		elog(ERROR,
-			 "materialized view \"%s\" has too many rules",
-			 RelationGetRelationName(matviewRel));
 
-	rule = matviewRel->rd_rules->rules[0];
-	if (rule->event != CMD_SELECT || !(rule->isInstead))
-		elog(ERROR,
-			 "the rule for materialized view \"%s\" is not a SELECT INSTEAD OF rule",
-			 RelationGetRelationName(matviewRel));
+	dataQuery = get_matview_query(matviewRel);
 
-	actions = rule->actions;
-	if (list_length(actions) != 1)
-		elog(ERROR,
-			 "the rule for materialized view \"%s\" is not a single action",
-			 RelationGetRelationName(matviewRel));
 
 	/*
 	 * Check that there is a unique index with no WHERE clause on one or more
@@ -259,12 +366,6 @@ ExecRefreshMatView(RefreshMatViewStmt *stmt, const char *queryString,
 					 errhint("Create a unique index with no WHERE clause on one or more columns of the materialized view.")));
 	}
 
-	/*
-	 * The stored query was rewritten at the time of the MV definition, but
-	 * has not been scribbled on by the planner.
-	 */
-	dataQuery = linitial_node(Query, actions);
-
 	/*
 	 * Check for active uses of the relation in the current transaction, such
 	 * as open scans.
@@ -292,6 +393,74 @@ ExecRefreshMatView(RefreshMatViewStmt *stmt, const char *queryString,
 		relpersistence = matviewRel->rd_rel->relpersistence;
 	}
 
+	/* delete IMMV triggers. */
+	if (RelationIsIVM(matviewRel) && stmt->skipData )
+	{
+		Relation	tgRel;
+		Relation	depRel;
+		ScanKeyData key;
+		SysScanDesc scan;
+		HeapTuple	tup;
+		ObjectAddresses *immv_triggers;
+
+		immv_triggers = new_object_addresses();
+
+		tgRel = table_open(TriggerRelationId, RowExclusiveLock);
+		depRel = table_open(DependRelationId, RowExclusiveLock);
+
+		/* search triggers that depends on IMMV. */
+		ScanKeyInit(&key,
+					Anum_pg_depend_refobjid,
+					BTEqualStrategyNumber, F_OIDEQ,
+					ObjectIdGetDatum(matviewOid));
+		scan = systable_beginscan(depRel, DependReferenceIndexId, true,
+								  NULL, 1, &key);
+		while ((tup = systable_getnext(scan)) != NULL)
+		{
+			ObjectAddress obj;
+			Form_pg_depend foundDep = (Form_pg_depend) GETSTRUCT(tup);
+
+			if (foundDep->classid == TriggerRelationId)
+			{
+				HeapTuple	tgtup;
+				ScanKeyData tgkey[1];
+				SysScanDesc tgscan;
+				Form_pg_trigger tgform;
+
+				/* Find the trigger name. */
+				ScanKeyInit(&tgkey[0],
+							Anum_pg_trigger_oid,
+							BTEqualStrategyNumber, F_OIDEQ,
+							ObjectIdGetDatum(foundDep->objid));
+
+				tgscan = systable_beginscan(tgRel, TriggerOidIndexId, true,
+											NULL, 1, tgkey);
+				tgtup = systable_getnext(tgscan);
+				if (!HeapTupleIsValid(tgtup))
+					elog(ERROR, "could not find tuple for immv trigger %u", foundDep->objid);
+
+				tgform = (Form_pg_trigger) GETSTRUCT(tgtup);
+
+				/* If trigger is created by IMMV, delete it. */
+				if (strncmp(NameStr(tgform->tgname), "IVM_trigger_", 12) == 0)
+				{
+					obj.classId = foundDep->classid;
+					obj.objectId = foundDep->objid;
+					obj.objectSubId = foundDep->refobjsubid;
+					add_exact_object_address(&obj, immv_triggers);
+				}
+				systable_endscan(tgscan);
+			}
+		}
+		systable_endscan(scan);
+
+		performMultipleDeletions(immv_triggers, DROP_RESTRICT, PERFORM_DELETION_INTERNAL);
+
+		table_close(depRel, RowExclusiveLock);
+		table_close(tgRel, RowExclusiveLock);
+		free_object_addresses(immv_triggers);
+	}
+
 	/*
 	 * Create the transient table that will receive the regenerated data. Lock
 	 * it against access by any other process until commit (by which time it
@@ -305,7 +474,7 @@ ExecRefreshMatView(RefreshMatViewStmt *stmt, const char *queryString,
 
 	/* Generate the data, if wanted. */
 	if (!stmt->skipData)
-		processed = refresh_matview_datafill(dest, dataQuery, queryString);
+		processed = refresh_matview_datafill(dest, dataQuery, NULL, NULL, queryString);
 
 	/* Make the matview match the newly generated data. */
 	if (concurrent)
@@ -340,6 +509,12 @@ ExecRefreshMatView(RefreshMatViewStmt *stmt, const char *queryString,
 			pgstat_count_heap_insert(matviewRel, processed);
 	}
 
+	if (!stmt->skipData && RelationIsIVM(matviewRel) && !oldPopulated)
+	{
+		CreateIndexOnIMMV(dataQuery, matviewRel);
+		CreateIvmTriggersOnBaseTables(dataQuery, matviewOid);
+	}
+
 	table_close(matviewRel, NoLock);
 
 	/* Roll back any GUC changes */
@@ -374,6 +549,8 @@ ExecRefreshMatView(RefreshMatViewStmt *stmt, const char *queryString,
  */
 static uint64
 refresh_matview_datafill(DestReceiver *dest, Query *query,
+						 QueryEnvironment *queryEnv,
+						 TupleDesc *resultTupleDesc,
 						 const char *queryString)
 {
 	List	   *rewritten;
@@ -410,7 +587,7 @@ refresh_matview_datafill(DestReceiver *dest, Query *query,
 	/* Create a QueryDesc, redirecting output to our tuple receiver */
 	queryDesc = CreateQueryDesc(plan, queryString,
 								GetActiveSnapshot(), InvalidSnapshot,
-								dest, NULL, NULL, 0);
+								dest, NULL, queryEnv ? queryEnv: NULL, 0);
 
 	/* call ExecutorStart to prepare the plan for execution */
 	ExecutorStart(queryDesc, 0);
@@ -420,6 +597,9 @@ refresh_matview_datafill(DestReceiver *dest, Query *query,
 
 	processed = queryDesc->estate->es_processed;
 
+	if (resultTupleDesc)
+		*resultTupleDesc = CreateTupleDescCopy(queryDesc->tupDesc);
+
 	/* and clean up */
 	ExecutorFinish(queryDesc);
 	ExecutorEnd(queryDesc);
@@ -931,3 +1111,1219 @@ CloseMatViewIncrementalMaintenance(void)
 	matview_maintenance_depth--;
 	Assert(matview_maintenance_depth >= 0);
 }
+
+/*
+ * get_matview_query - get the Query from a matview's _RETURN rule.
+ */
+static Query *
+get_matview_query(Relation matviewRel)
+{
+	RewriteRule *rule;
+	List * actions;
+
+	/*
+	 * Check that everything is correct for a refresh. Problems at this point
+	 * are internal errors, so elog is sufficient.
+	 */
+	if (matviewRel->rd_rel->relhasrules == false ||
+		matviewRel->rd_rules->numLocks < 1)
+		elog(ERROR,
+			 "materialized view \"%s\" is missing rewrite information",
+			 RelationGetRelationName(matviewRel));
+
+	if (matviewRel->rd_rules->numLocks > 1)
+		elog(ERROR,
+			 "materialized view \"%s\" has too many rules",
+			 RelationGetRelationName(matviewRel));
+
+	rule = matviewRel->rd_rules->rules[0];
+	if (rule->event != CMD_SELECT || !(rule->isInstead))
+		elog(ERROR,
+			 "the rule for materialized view \"%s\" is not a SELECT INSTEAD OF rule",
+			 RelationGetRelationName(matviewRel));
+
+	actions = rule->actions;
+	if (list_length(actions) != 1)
+		elog(ERROR,
+			 "the rule for materialized view \"%s\" is not a single action",
+			 RelationGetRelationName(matviewRel));
+
+	/*
+	 * The stored query was rewritten at the time of the MV definition, but
+	 * has not been scribbled on by the planner.
+	 */
+	return linitial_node(Query, actions);
+}
+
+
+/* ----------------------------------------------------
+ *		Incremental View Maintenance routines
+ * ---------------------------------------------------
+ */
+
+/*
+ * IVM_immediate_before
+ *
+ * IVM trigger function invoked before base table is modified. If this is
+ * invoked firstly in the same statement, we save the transaction id and the
+ * command id at that time.
+ */
+Datum
+IVM_immediate_before(PG_FUNCTION_ARGS)
+{
+	TriggerData *trigdata = (TriggerData *) fcinfo->context;
+	char	   *matviewOid_text = trigdata->tg_trigger->tgargs[0];
+	char	   *ex_lock_text = trigdata->tg_trigger->tgargs[1];
+	Oid			matviewOid;
+	MV_TriggerHashEntry *entry;
+	bool	found;
+	bool	ex_lock;
+
+	matviewOid = DatumGetObjectId(DirectFunctionCall1(oidin, CStringGetDatum(matviewOid_text)));
+	ex_lock = DatumGetBool(DirectFunctionCall1(boolin, CStringGetDatum(ex_lock_text)));
+
+	/* If the view has more than one tables, we have to use an exclusive lock. */
+	if (ex_lock)
+	{
+		/*
+		 * Wait for concurrent transactions which update this materialized view at
+		 * READ COMMITED. This is needed to see changes committed in other
+		 * transactions. No wait and raise an error at REPEATABLE READ or
+		 * SERIALIZABLE to prevent update anomalies of matviews.
+		 * XXX: dead-lock is possible here.
+		 */
+		if (!IsolationUsesXactSnapshot())
+			LockRelationOid(matviewOid, ExclusiveLock);
+		else if (!ConditionalLockRelationOid(matviewOid, ExclusiveLock))
+		{
+			/* try to throw error by name; relation could be deleted... */
+			char	   *relname = get_rel_name(matviewOid);
+
+			if (!relname)
+				ereport(ERROR,
+						(errcode(ERRCODE_LOCK_NOT_AVAILABLE),
+						errmsg("could not obtain lock on materialized view during incremental maintenance")));
+
+			ereport(ERROR,
+					(errcode(ERRCODE_LOCK_NOT_AVAILABLE),
+					errmsg("could not obtain lock on materialized view \"%s\" during incremental maintenance",
+							relname)));
+		}
+	}
+	else
+		LockRelationOid(matviewOid, RowExclusiveLock);
+
+	/*
+	 * On the first call initialize the hashtable
+	 */
+	if (!mv_trigger_info)
+		mv_InitHashTables();
+
+	entry = (MV_TriggerHashEntry *) hash_search(mv_trigger_info,
+											  (void *) &matviewOid,
+											  HASH_ENTER, &found);
+
+	/* On the first BEFORE to update the view, initialize trigger data */
+	if (!found)
+	{
+		/*
+		 * Get a snapshot just before the table was modified for checking
+		 * tuple visibility in the pre-update state of the table.
+		 */
+		Snapshot snapshot = GetActiveSnapshot();
+
+		entry->matview_id = matviewOid;
+		entry->before_trig_count = 0;
+		entry->after_trig_count = 0;
+		entry->snapshot = RegisterSnapshot(snapshot);
+		entry->tables = NIL;
+		entry->has_old = false;
+		entry->has_new = false;
+	}
+
+	entry->before_trig_count++;
+
+	return PointerGetDatum(NULL);
+}
+
+/*
+ * IVM_immediate_maintenance
+ *
+ * IVM trigger function invoked after base table is modified.
+ * For each table, tuplestores of transition tables are collected.
+ * and after the last modification
+ */
+Datum
+IVM_immediate_maintenance(PG_FUNCTION_ARGS)
+{
+	TriggerData *trigdata = (TriggerData *) fcinfo->context;
+	Relation	rel;
+	Oid			relid;
+	Oid			matviewOid;
+	Query	   *query;
+	Query	   *rewritten = NULL;
+	char	   *matviewOid_text = trigdata->tg_trigger->tgargs[0];
+	Relation	matviewRel;
+	int old_depth = matview_maintenance_depth;
+
+	Oid			relowner;
+	Tuplestorestate *old_tuplestore = NULL;
+	Tuplestorestate *new_tuplestore = NULL;
+	DestReceiver *dest_new = NULL, *dest_old = NULL;
+	Oid			save_userid;
+	int			save_sec_context;
+	int			save_nestlevel;
+
+	MV_TriggerHashEntry *entry;
+	MV_TriggerTable		*table;
+	bool	found;
+
+	ParseState		 *pstate;
+	QueryEnvironment *queryEnv = create_queryEnv();
+	MemoryContext	oldcxt;
+	ListCell   *lc;
+	int			i;
+
+
+	/* Create a ParseState for rewriting the view definition query */
+	pstate = make_parsestate(NULL);
+	pstate->p_queryEnv = queryEnv;
+	pstate->p_expr_kind = EXPR_KIND_SELECT_TARGET;
+
+	rel = trigdata->tg_relation;
+	relid = rel->rd_id;
+
+	matviewOid = DatumGetObjectId(DirectFunctionCall1(oidin, CStringGetDatum(matviewOid_text)));
+
+	/*
+	 * On the first call initialize the hashtable
+	 */
+	if (!mv_trigger_info)
+		mv_InitHashTables();
+
+	/* get the entry for this materialized view */
+	entry = (MV_TriggerHashEntry *) hash_search(mv_trigger_info,
+											  (void *) &matviewOid,
+											  HASH_FIND, &found);
+	Assert (found && entry != NULL);
+	entry->after_trig_count++;
+
+	/* search the entry for the modified table and create new entry if not found */
+	found = false;
+	foreach(lc, entry->tables)
+	{
+		table = (MV_TriggerTable *) lfirst(lc);
+		if (table->table_id == relid)
+		{
+			found = true;
+			break;
+		}
+	}
+	if (!found)
+	{
+		oldcxt = MemoryContextSwitchTo(TopTransactionContext);
+
+		table = (MV_TriggerTable *) palloc0(sizeof(MV_TriggerTable));
+		table->table_id = relid;
+		table->old_tuplestores = NIL;
+		table->new_tuplestores = NIL;
+		table->rte_indexes = NIL;
+		table->slot = MakeSingleTupleTableSlot(RelationGetDescr(rel), table_slot_callbacks(rel));
+		table->rel = table_open(RelationGetRelid(rel), NoLock);
+		entry->tables = lappend(entry->tables, table);
+
+		MemoryContextSwitchTo(oldcxt);
+	}
+
+	/* Save the transition tables and make a request to not free immediately */
+	if (trigdata->tg_oldtable)
+	{
+		oldcxt = MemoryContextSwitchTo(TopTransactionContext);
+		table->old_tuplestores = lappend(table->old_tuplestores, trigdata->tg_oldtable);
+		entry->has_old = true;
+		MemoryContextSwitchTo(oldcxt);
+	}
+	if (trigdata->tg_newtable)
+	{
+		oldcxt = MemoryContextSwitchTo(TopTransactionContext);
+		table->new_tuplestores = lappend(table->new_tuplestores, trigdata->tg_newtable);
+		entry->has_new = true;
+		MemoryContextSwitchTo(oldcxt);
+	}
+	if (entry->has_new || entry->has_old)
+	{
+		CmdType cmd;
+
+		if (TRIGGER_FIRED_BY_INSERT(trigdata->tg_event))
+			cmd = CMD_INSERT;
+		else if (TRIGGER_FIRED_BY_DELETE(trigdata->tg_event))
+			cmd = CMD_DELETE;
+		else if (TRIGGER_FIRED_BY_UPDATE(trigdata->tg_event))
+			cmd = CMD_UPDATE;
+		else
+			elog(ERROR,"unsupported trigger type");
+
+		/* Prolong lifespan of transition tables to the end of the last AFTER trigger */
+		SetTransitionTablePreserved(relid, cmd);
+	}
+
+
+	/* If this is not the last AFTER trigger call, immediately exit. */
+	Assert (entry->before_trig_count >= entry->after_trig_count);
+	if (entry->before_trig_count != entry->after_trig_count)
+		return PointerGetDatum(NULL);
+
+	/*
+	 * If this is the last AFTER trigger call, continue and update the view.
+	 */
+
+	/*
+	 * Advance command counter to make the updated base table row locally
+	 * visible.
+	 */
+	CommandCounterIncrement();
+
+	matviewRel = table_open(matviewOid, NoLock);
+
+	/* Make sure it is a materialized view. */
+	Assert(matviewRel->rd_rel->relkind == RELKIND_MATVIEW);
+
+	/*
+	 * Get and push the latast snapshot to see any changes which is committed
+	 * during waiting in other transactions at READ COMMITTED level.
+	 */
+	PushActiveSnapshot(GetTransactionSnapshot());
+
+	/*
+	 * Check for active uses of the relation in the current transaction, such
+	 * as open scans.
+	 *
+	 * NB: We count on this to protect us against problems with refreshing the
+	 * data using TABLE_INSERT_FROZEN.
+	 */
+	CheckTableNotInUse(matviewRel, "refresh a materialized view incrementally");
+
+	/*
+	 * Switch to the owner's userid, so that any functions are run as that
+	 * user.  Also arrange to make GUC variable changes local to this command.
+	 * We will switch modes when we are about to execute user code.
+	 */
+	relowner = matviewRel->rd_rel->relowner;
+	GetUserIdAndSecContext(&save_userid, &save_sec_context);
+	SetUserIdAndSecContext(relowner,
+						   save_sec_context | SECURITY_RESTRICTED_OPERATION);
+	save_nestlevel = NewGUCNestLevel();
+
+	/* get view query*/
+	query = get_matview_query(matviewRel);
+
+	/*
+	 * When a base table is truncated, the view content will be empty if the
+	 * view definition query does not contain an aggregate without a GROUP clause.
+	 * Therefore, such views can be truncated.
+	 */
+	if (TRIGGER_FIRED_BY_TRUNCATE(trigdata->tg_event))
+	{
+		ExecuteTruncateGuts(list_make1(matviewRel), list_make1_oid(matviewOid),
+							NIL, DROP_RESTRICT, false, false);
+
+		/* Clean up hash entry and delete tuplestores */
+		clean_up_IVM_hash_entry(entry, false);
+
+		/* Pop the original snapshot. */
+		PopActiveSnapshot();
+
+		table_close(matviewRel, NoLock);
+
+		/* Roll back any GUC changes */
+		AtEOXact_GUC(false, save_nestlevel);
+
+		/* Restore userid and security context */
+		SetUserIdAndSecContext(save_userid, save_sec_context);
+
+		return PointerGetDatum(NULL);
+	}
+
+	/*
+	 * rewrite query for calculating deltas
+	 */
+
+	rewritten = copyObject(query);
+
+	/* Replace resnames in a target list with materialized view's attnames */
+	i = 0;
+	foreach (lc, rewritten->targetList)
+	{
+		TargetEntry *tle = (TargetEntry *) lfirst(lc);
+		Form_pg_attribute attr = TupleDescAttr(matviewRel->rd_att, i);
+		char *resname = NameStr(attr->attname);
+
+		tle->resname = pstrdup(resname);
+		i++;
+	}
+
+	/* Set all tables in the query to pre-update state */
+	rewritten = rewrite_query_for_preupdate_state(rewritten, entry->tables,
+												  pstate, matviewOid);
+	/* Rewrite for counting duplicated tuples */
+	rewritten = rewrite_query_for_counting(rewritten, pstate);
+
+	/* Create tuplestores to store view deltas */
+	if (entry->has_old)
+	{
+		oldcxt = MemoryContextSwitchTo(TopTransactionContext);
+
+		old_tuplestore = tuplestore_begin_heap(false, false, work_mem);
+		dest_old = CreateDestReceiver(DestTuplestore);
+		SetTuplestoreDestReceiverParams(dest_old,
+									old_tuplestore,
+									TopTransactionContext,
+									false,
+									NULL,
+									NULL);
+
+		MemoryContextSwitchTo(oldcxt);
+	}
+	if (entry->has_new)
+	{
+		oldcxt = MemoryContextSwitchTo(TopTransactionContext);
+
+		new_tuplestore = tuplestore_begin_heap(false, false, work_mem);
+		dest_new = CreateDestReceiver(DestTuplestore);
+		SetTuplestoreDestReceiverParams(dest_new,
+									new_tuplestore,
+									TopTransactionContext,
+									false,
+									NULL,
+									NULL);
+		MemoryContextSwitchTo(oldcxt);
+	}
+
+	/* for all modified tables */
+	foreach(lc, entry->tables)
+	{
+		ListCell *lc2;
+
+		table = (MV_TriggerTable *) lfirst(lc);
+
+		/* loop for self-join */
+		foreach(lc2, table->rte_indexes)
+		{
+			int	rte_index = lfirst_int(lc2);
+			TupleDesc		tupdesc_old;
+			TupleDesc		tupdesc_new;
+
+			/* calculate delta tables */
+			calc_delta(table, rte_index, rewritten, dest_old, dest_new,
+					   &tupdesc_old, &tupdesc_new, queryEnv);
+
+			/* Set the table in the query to post-update state */
+			rewritten = rewrite_query_for_postupdate_state(rewritten, table, rte_index);
+
+			PG_TRY();
+			{
+				/* apply the delta tables to the materialized view */
+				apply_delta(matviewOid, old_tuplestore, new_tuplestore,
+							tupdesc_old, tupdesc_new, query);
+			}
+			PG_CATCH();
+			{
+				matview_maintenance_depth = old_depth;
+				PG_RE_THROW();
+			}
+			PG_END_TRY();
+
+			/* clear view delta tuplestores */
+			if (old_tuplestore)
+				tuplestore_clear(old_tuplestore);
+			if (new_tuplestore)
+				tuplestore_clear(new_tuplestore);
+		}
+	}
+
+	/* Clean up hash entry and delete tuplestores */
+	clean_up_IVM_hash_entry(entry, false);
+	if (old_tuplestore)
+	{
+		dest_old->rDestroy(dest_old);
+		tuplestore_end(old_tuplestore);
+	}
+	if (new_tuplestore)
+	{
+		dest_new->rDestroy(dest_new);
+		tuplestore_end(new_tuplestore);
+	}
+
+	/* Pop the original snapshot. */
+	PopActiveSnapshot();
+
+	table_close(matviewRel, NoLock);
+
+	/* Roll back any GUC changes */
+	AtEOXact_GUC(false, save_nestlevel);
+
+	/* Restore userid and security context */
+	SetUserIdAndSecContext(save_userid, save_sec_context);
+
+	return PointerGetDatum(NULL);
+}
+
+/*
+ * rewrite_query_for_preupdate_state
+ *
+ * Rewrite the query so that base tables' RTEs will represent "pre-update"
+ * state of tables. This is necessary to calculate view delta after multiple
+ * tables are modified.
+ */
+static Query*
+rewrite_query_for_preupdate_state(Query *query, List *tables,
+								  ParseState *pstate, Oid matviewid)
+{
+	ListCell *lc;
+	int num_rte = list_length(query->rtable);
+	int i;
+
+
+	/* register delta ENRs */
+	register_delta_ENRs(pstate, query, tables);
+
+	/* XXX: Is necessary? Is this right timing? */
+	AcquireRewriteLocks(query, true, false);
+
+	i = 1;
+	foreach(lc, query->rtable)
+	{
+		RangeTblEntry *r = (RangeTblEntry*) lfirst(lc);
+
+		ListCell *lc2;
+		foreach(lc2, tables)
+		{
+			MV_TriggerTable *table = (MV_TriggerTable *) lfirst(lc2);
+			/*
+			 * if the modified table is found then replace the original RTE with
+			 * "pre-state" RTE and append its index to the list.
+			 */
+			if (r->relid == table->table_id)
+			{
+				List *securityQuals;
+				List *withCheckOptions;
+				bool  hasRowSecurity;
+				bool  hasSubLinks;
+
+				RangeTblEntry *rte_pre = get_prestate_rte(r, table, pstate->p_queryEnv, matviewid);
+
+				/*
+				 * Set a row security poslicies of the modified table to the subquery RTE which
+				 * represents the pre-update state of the table.
+				 */
+				get_row_security_policies(query, table->original_rte, i,
+										  &securityQuals, &withCheckOptions,
+										  &hasRowSecurity, &hasSubLinks);
+
+				if (hasRowSecurity)
+				{
+					query->hasRowSecurity = true;
+					rte_pre->security_barrier = true;
+				}
+				if (hasSubLinks)
+					query->hasSubLinks = true;
+
+				rte_pre->securityQuals = securityQuals;
+				lfirst(lc) = rte_pre;
+
+				table->rte_indexes = lappend_int(table->rte_indexes, i);
+				break;
+			}
+		}
+
+		/* finish the loop if we processed all RTE included in the original query */
+		if (i++ >= num_rte)
+			break;
+	}
+
+	return query;
+}
+
+/*
+ * register_delta_ENRs
+ *
+ * For all modified tables, make ENRs for their transition tables
+ * and register them to the queryEnv. ENR's RTEs are also appended
+ * into the list in query tree.
+ */
+static void
+register_delta_ENRs(ParseState *pstate, Query *query, List *tables)
+{
+	QueryEnvironment *queryEnv = pstate->p_queryEnv;
+	ListCell *lc;
+	RangeTblEntry	*rte;
+
+	foreach(lc, tables)
+	{
+		MV_TriggerTable *table = (MV_TriggerTable *) lfirst(lc);
+		ListCell *lc2;
+		int count;
+
+		count = 0;
+		foreach(lc2, table->old_tuplestores)
+		{
+			Tuplestorestate *oldtable = (Tuplestorestate *) lfirst(lc2);
+			EphemeralNamedRelation enr =
+				palloc(sizeof(EphemeralNamedRelationData));
+			ParseNamespaceItem *nsitem;
+
+			enr->md.name = make_delta_enr_name("old", table->table_id, count);
+			enr->md.reliddesc = table->table_id;
+			enr->md.tupdesc = NULL;
+			enr->md.enrtype = ENR_NAMED_TUPLESTORE;
+			enr->md.enrtuples = tuplestore_tuple_count(oldtable);
+			enr->reldata = oldtable;
+			register_ENR(queryEnv, enr);
+
+			nsitem = addRangeTableEntryForENR(pstate, makeRangeVar(NULL, enr->md.name, -1), true);
+			rte = nsitem->p_rte;
+
+			query->rtable = lappend(query->rtable, rte);
+
+			count++;
+		}
+
+		count = 0;
+		foreach(lc2, table->new_tuplestores)
+		{
+			Tuplestorestate *newtable = (Tuplestorestate *) lfirst(lc2);
+			EphemeralNamedRelation enr =
+				palloc(sizeof(EphemeralNamedRelationData));
+			ParseNamespaceItem *nsitem;
+
+			enr->md.name = make_delta_enr_name("new", table->table_id, count);
+			enr->md.reliddesc = table->table_id;
+			enr->md.tupdesc = NULL;
+			enr->md.enrtype = ENR_NAMED_TUPLESTORE;
+			enr->md.enrtuples = tuplestore_tuple_count(newtable);
+			enr->reldata = newtable;
+			register_ENR(queryEnv, enr);
+
+			nsitem = addRangeTableEntryForENR(pstate, makeRangeVar(NULL, enr->md.name, -1), true);
+			rte = nsitem->p_rte;
+
+			query->rtable = lappend(query->rtable, rte);
+
+			count++;
+		}
+	}
+}
+
+#define DatumGetItemPointer(X)	 ((ItemPointer) DatumGetPointer(X))
+#define PG_GETARG_ITEMPOINTER(n) DatumGetItemPointer(PG_GETARG_DATUM(n))
+
+/*
+ * ivm_visible_in_prestate
+ *
+ * Check visibility of a tuple specified by the tableoid and item pointer
+ * using the snapshot taken just before the table was modified.
+ */
+Datum
+ivm_visible_in_prestate(PG_FUNCTION_ARGS)
+{
+	Oid			tableoid = PG_GETARG_OID(0);
+	ItemPointer itemPtr = PG_GETARG_ITEMPOINTER(1);
+	Oid			matviewOid = PG_GETARG_OID(2);
+	MV_TriggerHashEntry *entry;
+	MV_TriggerTable		*table = NULL;
+	ListCell   *lc;
+	bool	found;
+	bool	result;
+
+	if (!in_delta_calculation)
+		ereport(ERROR,
+				(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+				 errmsg("ivm_visible_in_prestate can be called only in delta calculation")));
+
+	entry = (MV_TriggerHashEntry *) hash_search(mv_trigger_info,
+											  (void *) &matviewOid,
+											  HASH_FIND, &found);
+	Assert (found && entry != NULL);
+
+	foreach(lc, entry->tables)
+	{
+		table = (MV_TriggerTable *) lfirst(lc);
+		if (table->table_id == tableoid)
+			break;
+	}
+
+	Assert (table != NULL);
+
+	result = table_tuple_fetch_row_version(table->rel, itemPtr, entry->snapshot, table->slot);
+
+	PG_RETURN_BOOL(result);
+}
+
+/*
+ * get_prestate_rte
+ *
+ * Rewrite RTE of the modified table to a subquery which represents
+ * "pre-state" table. The original RTE is saved in table->rte_original.
+ */
+static RangeTblEntry*
+get_prestate_rte(RangeTblEntry *rte, MV_TriggerTable *table,
+				 QueryEnvironment *queryEnv, Oid matviewid)
+{
+	StringInfoData str;
+	RawStmt *raw;
+	Query *subquery;
+	Relation rel;
+	ParseState *pstate;
+	char *relname;
+	int i;
+
+	pstate = make_parsestate(NULL);
+	pstate->p_queryEnv = queryEnv;
+	pstate->p_expr_kind = EXPR_KIND_SELECT_TARGET;
+
+	/*
+	 * We can use NoLock here since AcquireRewriteLocks should
+	 * have locked the relation already.
+	 */
+	rel = table_open(table->table_id, NoLock);
+	relname = quote_qualified_identifier(
+					get_namespace_name(RelationGetNamespace(rel)),
+									   RelationGetRelationName(rel));
+	table_close(rel, NoLock);
+
+	/*
+	 * Filtering inserted row using the snapshot taken before the table
+	 * is modified. ctid is required for maintaining outer join views.
+	 */
+	initStringInfo(&str);
+	appendStringInfo(&str,
+		"SELECT t.* FROM %s t"
+		" WHERE pg_catalog.ivm_visible_in_prestate(t.tableoid, t.ctid ,%d::pg_catalog.oid)",
+			relname, matviewid);
+
+	/*
+	 * Append deleted rows contained in old transition tables.
+	 */
+	for (i = 0; i < list_length(table->old_tuplestores); i++)
+	{
+		appendStringInfo(&str, " UNION ALL ");
+		appendStringInfo(&str," SELECT * FROM %s",
+			make_delta_enr_name("old", table->table_id, i));
+	}
+
+	/* Get a subquery representing pre-state of the table */
+	raw = (RawStmt*)linitial(raw_parser(str.data, RAW_PARSE_DEFAULT));
+	subquery = transformStmt(pstate, raw->stmt);
+
+	/* save the original RTE */
+	table->original_rte = copyObject(rte);
+
+	rte->rtekind = RTE_SUBQUERY;
+	rte->subquery = subquery;
+	rte->security_barrier = false;
+
+	/* Clear fields that should not be set in a subquery RTE */
+	rte->relid = InvalidOid;
+	rte->relkind = 0;
+	rte->rellockmode = 0;
+	rte->tablesample = NULL;
+	rte->perminfoindex = 0;         /* no permission checking for this RTE */
+	rte->inh = false;			/* must not be set for a subquery */
+
+	return rte;
+}
+
+/*
+ * make_delta_enr_name
+ *
+ * Make a name for ENR of a transition table from the base table's oid.
+ * prefix will be "new" or "old" depending on its transition table kind..
+ */
+static char*
+make_delta_enr_name(const char *prefix, Oid relid, int count)
+{
+	char buf[NAMEDATALEN];
+	char *name;
+
+	snprintf(buf, NAMEDATALEN, "__ivm_%s_%u_%u", prefix, relid, count);
+	name = pstrdup(buf);
+
+	return name;
+}
+
+/*
+ * replace_rte_with_delta
+ *
+ * Replace RTE of the modified table with a single table delta that combine its
+ * all transition tables.
+ */
+static RangeTblEntry*
+replace_rte_with_delta(RangeTblEntry *rte, MV_TriggerTable *table, bool is_new,
+					   QueryEnvironment *queryEnv)
+{
+	Oid relid = table->table_id;
+	StringInfoData str;
+	ParseState	*pstate;
+	RawStmt *raw;
+	Query *sub;
+	int		num_tuplestores = list_length(is_new ? table->new_tuplestores : table->old_tuplestores);
+	int		i;
+
+	/* the previous RTE must be a subquery which represents "pre-state" table */
+	Assert(rte->rtekind == RTE_SUBQUERY);
+
+	/* Create a ParseState for rewriting the view definition query */
+	pstate = make_parsestate(NULL);
+	pstate->p_queryEnv = queryEnv;
+	pstate->p_expr_kind = EXPR_KIND_SELECT_TARGET;
+
+	initStringInfo(&str);
+
+	for (i = 0; i < num_tuplestores; i++)
+	{
+		if (i > 0)
+			appendStringInfo(&str, " UNION ALL ");
+
+		appendStringInfo(&str,
+			" SELECT * FROM %s",
+			make_delta_enr_name(is_new ? "new" : "old", relid, i));
+	}
+
+	raw = (RawStmt*)linitial(raw_parser(str.data, RAW_PARSE_DEFAULT));
+	sub = transformStmt(pstate, raw->stmt);
+
+	/*
+	 * Update the subquery so that it represent the combined transition
+	 * table.  Note that we leave the security_barrier and securityQuals
+	 * fields so that the subquery relation can be protected by the RLS
+	 * policy as same as the modified table.
+	 */
+	rte->rtekind = RTE_SUBQUERY;
+	rte->subquery = sub;
+
+	return rte;
+}
+
+/*
+ * rewrite_query_for_counting
+ *
+ * Rewrite query for counting duplicated tuples.
+ */
+static Query *
+rewrite_query_for_counting(Query *query, ParseState *pstate)
+{
+	TargetEntry *tle_count;
+	FuncCall *fn;
+	Node *node;
+
+	/* Add count(*) for counting distinct tuples in views */
+	fn = makeFuncCall(SystemFuncName("count"), NIL, COERCE_EXPLICIT_CALL, -1);
+	fn->agg_star = true;
+	if (!query->groupClause && !query->hasAggs)
+		query->groupClause = transformDistinctClause(NULL, &query->targetList, query->sortClause, false);
+
+	node = ParseFuncOrColumn(pstate, fn->funcname, NIL, NULL, fn, false, -1);
+
+	tle_count = makeTargetEntry((Expr *) node,
+								list_length(query->targetList) + 1,
+								pstrdup("__ivm_count__"),
+								false);
+	query->targetList = lappend(query->targetList, tle_count);
+	query->hasAggs = true;
+
+	return query;
+}
+
+/*
+ * calc_delta
+ *
+ * Calculate view deltas generated under the modification of a table specified
+ * by the RTE index.
+ */
+static void
+calc_delta(MV_TriggerTable *table, int rte_index, Query *query,
+			DestReceiver *dest_old, DestReceiver *dest_new,
+			TupleDesc *tupdesc_old, TupleDesc *tupdesc_new,
+			QueryEnvironment *queryEnv)
+{
+	ListCell *lc = list_nth_cell(query->rtable, rte_index - 1);
+	RangeTblEntry *rte = (RangeTblEntry *) lfirst(lc);
+
+	in_delta_calculation = true;
+
+	/* Generate old delta */
+	if (list_length(table->old_tuplestores) > 0)
+	{
+		/* Replace the modified table with the old delta table and calculate the old view delta. */
+		replace_rte_with_delta(rte, table, false, queryEnv);
+		refresh_matview_datafill(dest_old, query, queryEnv, tupdesc_old, "");
+	}
+
+	/* Generate new delta */
+	if (list_length(table->new_tuplestores) > 0)
+	{
+		/* Replace the modified table with the new delta table and calculate the new view delta*/
+		replace_rte_with_delta(rte, table, true, queryEnv);
+		refresh_matview_datafill(dest_new, query, queryEnv, tupdesc_new, "");
+	}
+
+	in_delta_calculation = false;
+}
+
+/*
+ * rewrite_query_for_postupdate_state
+ *
+ * Rewrite the query so that the specified base table's RTEs will represent
+ * "post-update" state of tables. This is called after the view delta
+ * calculation due to changes on this table finishes.
+ */
+static Query*
+rewrite_query_for_postupdate_state(Query *query, MV_TriggerTable *table, int rte_index)
+{
+	ListCell *lc = list_nth_cell(query->rtable, rte_index - 1);
+
+	/* Retore the original RTE */
+	lfirst(lc) = table->original_rte;
+
+	return query;
+}
+
+/*
+ * apply_delta
+ *
+ * Apply deltas to the materialized view. In outer join cases, this requires
+ * the view maintenance graph.
+ */
+static void
+apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *new_tuplestores,
+			TupleDesc tupdesc_old, TupleDesc tupdesc_new,
+			Query *query)
+{
+	StringInfoData querybuf;
+	StringInfoData target_list_buf;
+	Relation	matviewRel;
+	char	   *matviewname;
+	ListCell	*lc;
+	int			i;
+	List	   *keys = NIL;
+
+
+	/*
+	 * get names of the materialized view and delta tables
+	 */
+
+	matviewRel = table_open(matviewOid, NoLock);
+	matviewname = quote_qualified_identifier(get_namespace_name(RelationGetNamespace(matviewRel)),
+											 RelationGetRelationName(matviewRel));
+
+	/*
+	 * Build parts of the maintenance queries
+	 */
+
+	initStringInfo(&querybuf);
+	initStringInfo(&target_list_buf);
+
+	/* build string of target list */
+	for (i = 0; i < matviewRel->rd_att->natts; i++)
+	{
+		Form_pg_attribute attr = TupleDescAttr(matviewRel->rd_att, i);
+		char   *resname = NameStr(attr->attname);
+
+		if (i != 0)
+			appendStringInfo(&target_list_buf, ", ");
+		appendStringInfo(&target_list_buf, "%s", quote_qualified_identifier(NULL, resname));
+	}
+
+	i = 0;
+	foreach (lc, query->targetList)
+	{
+		TargetEntry *tle = (TargetEntry *) lfirst(lc);
+		Form_pg_attribute attr = TupleDescAttr(matviewRel->rd_att, i);
+
+		i++;
+
+		if (tle->resjunk)
+			continue;
+
+		keys = lappend(keys, attr);
+	}
+
+	/* Start maintaining the materialized view. */
+	OpenMatViewIncrementalMaintenance();
+
+	/* Open SPI context. */
+	if (SPI_connect() != SPI_OK_CONNECT)
+		elog(ERROR, "SPI_connect failed");
+
+	/* For tuple deletion */
+	if (old_tuplestores && tuplestore_tuple_count(old_tuplestores) > 0)
+	{
+		EphemeralNamedRelation enr = palloc(sizeof(EphemeralNamedRelationData));
+		int				rc;
+
+		/* convert tuplestores to ENR, and register for SPI */
+		enr->md.name = pstrdup(OLD_DELTA_ENRNAME);
+		enr->md.reliddesc = InvalidOid;
+		enr->md.tupdesc = tupdesc_old;
+		enr->md.enrtype = ENR_NAMED_TUPLESTORE;
+		enr->md.enrtuples = tuplestore_tuple_count(old_tuplestores);
+		enr->reldata = old_tuplestores;
+
+		rc = SPI_register_relation(enr);
+		if (rc != SPI_OK_REL_REGISTER)
+			elog(ERROR, "SPI_register failed");
+
+		apply_old_delta(matviewname, OLD_DELTA_ENRNAME, keys);
+
+	}
+	/* For tuple insertion */
+	if (new_tuplestores && tuplestore_tuple_count(new_tuplestores) > 0)
+	{
+		EphemeralNamedRelation enr = palloc(sizeof(EphemeralNamedRelationData));
+		int rc;
+
+		/* convert tuplestores to ENR, and register for SPI */
+		enr->md.name = pstrdup(NEW_DELTA_ENRNAME);
+		enr->md.reliddesc = InvalidOid;
+		enr->md.tupdesc = tupdesc_new;;
+		enr->md.enrtype = ENR_NAMED_TUPLESTORE;
+		enr->md.enrtuples = tuplestore_tuple_count(new_tuplestores);
+		enr->reldata = new_tuplestores;
+
+		rc = SPI_register_relation(enr);
+		if (rc != SPI_OK_REL_REGISTER)
+			elog(ERROR, "SPI_register failed");
+
+		/* apply new delta */
+		apply_new_delta(matviewname, NEW_DELTA_ENRNAME, &target_list_buf);
+	}
+
+	/* We're done maintaining the materialized view. */
+	CloseMatViewIncrementalMaintenance();
+
+	table_close(matviewRel, NoLock);
+
+	/* Close SPI context. */
+	if (SPI_finish() != SPI_OK_FINISH)
+		elog(ERROR, "SPI_finish failed");
+}
+
+/*
+ * apply_old_delta
+ *
+ * Execute a query for applying a delta table given by deltname_old
+ * which contains tuples to be deleted from to a materialized view given by
+ * matviewname.  This is used when counting is not required.
+ */
+static void
+apply_old_delta(const char *matviewname, const char *deltaname_old,
+				List *keys)
+{
+	StringInfoData	querybuf;
+	StringInfoData	keysbuf;
+	char   *match_cond;
+	ListCell *lc;
+
+	/* build WHERE condition for searching tuples to be deleted */
+	match_cond = get_matching_condition_string(keys);
+
+	/* build string of keys list */
+	initStringInfo(&keysbuf);
+	foreach (lc, keys)
+	{
+		Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc);
+		char   *resname = NameStr(attr->attname);
+		appendStringInfo(&keysbuf, "%s", quote_qualified_identifier("mv", resname));
+		if (lnext(keys, lc))
+			appendStringInfo(&keysbuf, ", ");
+	}
+
+	/* Search for matching tuples from the view and update or delete if found. */
+	initStringInfo(&querybuf);
+	appendStringInfo(&querybuf,
+	"DELETE FROM %s WHERE ctid IN ("
+		"SELECT tid FROM (SELECT pg_catalog.row_number() over (partition by %s) AS \"__ivm_row_number__\","
+								  "mv.ctid AS tid,"
+								  "diff.\"__ivm_count__\""
+						 "FROM %s AS mv, %s AS diff "
+						 "WHERE %s) v "
+					"WHERE v.\"__ivm_row_number__\" OPERATOR(pg_catalog.<=) v.\"__ivm_count__\")",
+					matviewname,
+					keysbuf.data,
+					matviewname, deltaname_old,
+					match_cond);
+
+	if (SPI_exec(querybuf.data, 0) != SPI_OK_DELETE)
+		elog(ERROR, "SPI_exec failed: %s", querybuf.data);
+}
+
+/*
+ * apply_new_delta
+ *
+ * Execute a query for applying a delta table given by deltname_new
+ * which contains tuples to be inserted into a materialized view given by
+ * matviewname.  This is used when counting is not required.
+ */
+static void
+apply_new_delta(const char *matviewname, const char *deltaname_new,
+				StringInfo target_list)
+{
+	StringInfoData	querybuf;
+
+	/* Search for matching tuples from the view and update or delete if found. */
+	initStringInfo(&querybuf);
+	appendStringInfo(&querybuf,
+					"INSERT INTO %s (%s) SELECT %s FROM ("
+						"SELECT diff.*, pg_catalog.generate_series(1, diff.\"__ivm_count__\")"
+							" AS __ivm_generate_series__ "
+						"FROM %s AS diff) AS v",
+					matviewname, target_list->data, target_list->data,
+					deltaname_new);
+
+	if (SPI_exec(querybuf.data, 0) != SPI_OK_INSERT)
+		elog(ERROR, "SPI_exec failed: %s", querybuf.data);
+}
+
+/*
+ * get_matching_condition_string
+ *
+ * Build a predicate string for looking for a tuple with given keys.
+ */
+static char *
+get_matching_condition_string(List *keys)
+{
+	StringInfoData match_cond;
+	ListCell	*lc;
+
+	/* If there is no key columns, the condition is always true. */
+	if (keys == NIL)
+		return "true";
+
+	initStringInfo(&match_cond);
+	foreach (lc, keys)
+	{
+		Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc);
+		char   *resname = NameStr(attr->attname);
+		char   *mv_resname = quote_qualified_identifier("mv", resname);
+		char   *diff_resname = quote_qualified_identifier("diff", resname);
+		Oid		typid = attr->atttypid;
+
+		/* Considering NULL values, we can not use simple = operator. */
+		appendStringInfo(&match_cond, "(");
+		generate_equal(&match_cond, typid, mv_resname, diff_resname);
+		appendStringInfo(&match_cond, " OR (%s IS NULL AND %s IS NULL))",
+						 mv_resname, diff_resname);
+
+		if (lnext(keys, lc))
+			appendStringInfo(&match_cond, " AND ");
+	}
+
+	return match_cond.data;
+}
+
+/*
+ * generate_equals
+ *
+ * Generate an equality clause using given operands' default equality
+ * operator.
+ */
+static void
+generate_equal(StringInfo querybuf, Oid opttype,
+			   const char *leftop, const char *rightop)
+{
+	TypeCacheEntry *typentry;
+
+	typentry = lookup_type_cache(opttype, TYPECACHE_EQ_OPR);
+	if (!OidIsValid(typentry->eq_opr))
+		ereport(ERROR,
+				(errcode(ERRCODE_UNDEFINED_FUNCTION),
+				 errmsg("could not identify an equality operator for type %s",
+						format_type_be_qualified(opttype))));
+
+	generate_operator_clause(querybuf,
+							 leftop, opttype,
+							 typentry->eq_opr,
+							 rightop, opttype);
+}
+
+/*
+ * mv_InitHashTables
+ */
+static void
+mv_InitHashTables(void)
+{
+	HASHCTL		ctl;
+
+	memset(&ctl, 0, sizeof(ctl));
+	ctl.keysize = sizeof(Oid);
+	ctl.entrysize = sizeof(MV_TriggerHashEntry);
+	mv_trigger_info = hash_create("MV trigger info",
+								 MV_INIT_QUERYHASHSIZE,
+								 &ctl, HASH_ELEM | HASH_BLOBS);
+}
+
+/*
+ * AtAbort_IVM
+ *
+ * Clean up hash entries for all materialized views. This is called at
+ * transaction abort.
+ */
+void
+AtAbort_IVM()
+{
+	HASH_SEQ_STATUS seq;
+	MV_TriggerHashEntry *entry;
+
+	if (mv_trigger_info)
+	{
+		hash_seq_init(&seq, mv_trigger_info);
+		while ((entry = hash_seq_search(&seq)) != NULL)
+			clean_up_IVM_hash_entry(entry, true);
+	}
+	in_delta_calculation = false;
+}
+
+/*
+ * clean_up_IVM_hash_entry
+ *
+ * Clean up tuple stores and hash entries for a materialized view after its
+ * maintenance finished.
+ */
+static void
+clean_up_IVM_hash_entry(MV_TriggerHashEntry *entry, bool is_abort)
+{
+	bool found;
+	ListCell *lc;
+
+	foreach(lc, entry->tables)
+	{
+		MV_TriggerTable *table = (MV_TriggerTable *) lfirst(lc);
+
+		list_free(table->old_tuplestores);
+		list_free(table->new_tuplestores);
+		if (!is_abort)
+		{
+			ExecDropSingleTupleTableSlot(table->slot);
+			table_close(table->rel, NoLock);
+		}
+	}
+	list_free(entry->tables);
+
+	if (!is_abort)
+		UnregisterSnapshot(entry->snapshot);
+
+	hash_search(mv_trigger_info, (void *) &entry->matview_id, HASH_REMOVE, &found);
+}
+
+/*
+ * isIvmName
+ *
+ * Check if this is a IVM hidden column from the name.
+ */
+bool
+isIvmName(const char *s)
+{
+	if (s)
+		return (strncmp(s, "__ivm_", 6) == 0);
+	return false;
+}
diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat
index 9805bc6118..f6896d77b4 100644
--- a/src/include/catalog/pg_proc.dat
+++ b/src/include/catalog/pg_proc.dat
@@ -12062,4 +12062,14 @@
   proname => 'any_value_transfn', prorettype => 'anyelement',
   proargtypes => 'anyelement anyelement', prosrc => 'any_value_transfn' },
 
+# IVM
+{ oid => '786', descr => 'ivm trigger (before)',
+  proname => 'IVM_immediate_before', provolatile => 'v', prorettype => 'trigger',
+  proargtypes => '', prosrc => 'IVM_immediate_before' },
+{ oid => '787', descr => 'ivm trigger (after)',
+  proname => 'IVM_immediate_maintenance', provolatile => 'v', prorettype => 'trigger',
+  proargtypes => '', prosrc => 'IVM_immediate_maintenance' },
+{ oid => '788', descr => 'ivm filetring ',
+  proname => 'ivm_visible_in_prestate', provolatile => 's', prorettype => 'bool',
+  proargtypes => 'oid tid oid', prosrc => 'ivm_visible_in_prestate' },
 ]
diff --git a/src/include/commands/createas.h b/src/include/commands/createas.h
index 3647f96f73..09a64fa2e5 100644
--- a/src/include/commands/createas.h
+++ b/src/include/commands/createas.h
@@ -16,6 +16,7 @@
 
 #include "catalog/objectaddress.h"
 #include "nodes/params.h"
+#include "nodes/pathnodes.h"
 #include "parser/parse_node.h"
 #include "tcop/dest.h"
 #include "utils/queryenvironment.h"
@@ -25,6 +26,9 @@ extern ObjectAddress ExecCreateTableAs(ParseState *pstate, CreateTableAsStmt *st
 									   ParamListInfo params, QueryEnvironment *queryEnv,
 									   QueryCompletion *qc);
 
+extern void CreateIvmTriggersOnBaseTables(Query *qry, Oid matviewOid);
+extern void CreateIndexOnIMMV(Query *query, Relation matviewRel);
+
 extern int	GetIntoRelEFlags(IntoClause *intoClause);
 
 extern DestReceiver *CreateIntoRelDestReceiver(IntoClause *intoClause);
diff --git a/src/include/commands/matview.h b/src/include/commands/matview.h
index 9eaa6212a1..504b83a446 100644
--- a/src/include/commands/matview.h
+++ b/src/include/commands/matview.h
@@ -15,6 +15,7 @@
 #define MATVIEW_H
 
 #include "catalog/objectaddress.h"
+#include "fmgr.h"
 #include "nodes/params.h"
 #include "nodes/parsenodes.h"
 #include "tcop/dest.h"
@@ -23,6 +24,8 @@
 
 extern void SetMatViewPopulatedState(Relation relation, bool newstate);
 
+extern void SetMatViewIVMState(Relation relation, bool newstate);
+
 extern ObjectAddress ExecRefreshMatView(RefreshMatViewStmt *stmt, const char *queryString,
 										ParamListInfo params, QueryCompletion *qc);
 
@@ -30,4 +33,10 @@ extern DestReceiver *CreateTransientRelDestReceiver(Oid transientoid);
 
 extern bool MatViewIncrementalMaintenanceIsEnabled(void);
 
+extern Datum IVM_immediate_before(PG_FUNCTION_ARGS);
+extern Datum IVM_immediate_maintenance(PG_FUNCTION_ARGS);
+extern Datum IVM_visible_in_prestate(PG_FUNCTION_ARGS);
+extern void AtAbort_IVM(void);
+extern bool isIvmName(const char *s);
+
 #endif							/* MATVIEW_H */
-- 
2.25.1


--Multipart=_Mon__28_Aug_2023_16_05_30_+0900_b1OvQD_3A3ZMTGvj
Content-Type: text/x-diff;
 name="v29-0007-Add-DISTINCT-support-for-IVM.patch"
Content-Disposition: attachment;
 filename="v29-0007-Add-DISTINCT-support-for-IVM.patch"
Content-Transfer-Encoding: 7bit



^ permalink  raw  reply  [nested|flat] 101+ messages in thread

* [PATCH v30 06/11] Add Incremental View Maintenance support
@ 2023-05-31 09:59  Yugo Nagata <[email protected]>
  0 siblings, 0 replies; 101+ messages in thread

From: Yugo Nagata @ 2023-05-31 09:59 UTC (permalink / raw)

In this implementation, AFTER triggers are used to collect
tuplestores containing transition table contents. When multiple tables
are changed, multiple AFTER triggers are invoked, then the final AFTER
trigger performs actual update of the matview. In addition, BEFORE
triggers are also used to handle global information for view
maintenance.

To calculate view deltas, we need both pre-state and post-state of base
tables. Post-update states are available in AFTER trigger, and pre-update
states can be calculated by removing inserted tuples and appending deleted
tuples. Insterted tuples are filtered using the snapshot taken before
table modiication, and deleted tuples are contained in the old transition
table.

Incrementally Maintainable Materialized Views (IMMV) can contain
duplicated tuples.

This patch also allows self-join, simultaneous updates of more than
one base table, and multiple updates of the same base table.
---
 src/backend/access/transam/xact.c |    5 +
 src/backend/commands/createas.c   |  681 ++++++++++++++
 src/backend/commands/matview.c    | 1466 ++++++++++++++++++++++++++++-
 src/include/catalog/pg_proc.dat   |   10 +
 src/include/commands/createas.h   |    4 +
 src/include/commands/matview.h    |    9 +
 6 files changed, 2140 insertions(+), 35 deletions(-)

diff --git a/src/backend/access/transam/xact.c b/src/backend/access/transam/xact.c
index 70ab6e27a1..0de7ab6abe 100644
--- a/src/backend/access/transam/xact.c
+++ b/src/backend/access/transam/xact.c
@@ -36,6 +36,7 @@
 #include "catalog/pg_enum.h"
 #include "catalog/storage.h"
 #include "commands/async.h"
+#include "commands/matview.h"
 #include "commands/tablecmds.h"
 #include "commands/trigger.h"
 #include "common/pg_prng.h"
@@ -2819,6 +2820,7 @@ AbortTransaction(void)
 	AtAbort_Notify();
 	AtEOXact_RelationMap(false, is_parallel_worker);
 	AtAbort_Twophase();
+	AtAbort_IVM();
 
 	/*
 	 * Advertise the fact that we aborted in pg_xact (assuming that we got as
@@ -5097,6 +5099,9 @@ AbortSubTransaction(void)
 	pgstat_progress_end_command();
 	UnlockBuffers();
 
+	/* Clean up hash entries for incremental view maintenance */
+	AtAbort_IVM();
+
 	/* Reset WAL record construction state */
 	XLogResetInsertion();
 
diff --git a/src/backend/commands/createas.c b/src/backend/commands/createas.c
index 16a2fe65e6..08262100ea 100644
--- a/src/backend/commands/createas.c
+++ b/src/backend/commands/createas.c
@@ -32,15 +32,26 @@
 #include "access/xact.h"
 #include "access/xlog.h"
 #include "catalog/namespace.h"
+#include "catalog/index.h"
+#include "catalog/pg_constraint.h"
+#include "catalog/pg_inherits.h"
+#include "catalog/pg_trigger.h"
 #include "catalog/toasting.h"
 #include "commands/createas.h"
+#include "commands/defrem.h"
 #include "commands/matview.h"
 #include "commands/prepare.h"
 #include "commands/tablecmds.h"
+#include "commands/tablespace.h"
+#include "commands/trigger.h"
 #include "commands/view.h"
 #include "miscadmin.h"
+#include "optimizer/optimizer.h"
+#include "optimizer/prep.h"
 #include "nodes/makefuncs.h"
 #include "nodes/nodeFuncs.h"
+#include "parser/parser.h"
+#include "parser/parsetree.h"
 #include "parser/parse_clause.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/smgr.h"
@@ -73,6 +84,12 @@ static bool intorel_receive(TupleTableSlot *slot, DestReceiver *self);
 static void intorel_shutdown(DestReceiver *self);
 static void intorel_destroy(DestReceiver *self);
 
+static void CreateIvmTriggersOnBaseTablesRecurse(Query *qry, Node *node, Oid matviewOid,
+									 Relids *relids, bool ex_lock);
+static void CreateIvmTrigger(Oid relOid, Oid viewOid, int16 type, int16 timing, bool ex_lock);
+static void check_ivm_restriction(Node *node);
+static bool check_ivm_restriction_walker(Node *node, void *context);
+static Bitmapset *get_primary_key_attnos_from_query(Query *query, List **constraintList);
 
 /*
  * create_ctas_internal
@@ -282,6 +299,18 @@ ExecCreateTableAs(ParseState *pstate, CreateTableAsStmt *stmt,
 		save_nestlevel = NewGUCNestLevel();
 	}
 
+	if (is_matview && into->ivm)
+	{
+		/* check if the query is supported in IMMV definition */
+		if (contain_mutable_functions((Node *) query))
+			ereport(ERROR,
+					(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+					 errmsg("mutable function is not supported on incrementally maintainable materialized view"),
+					 errhint("functions must be marked IMMUTABLE")));
+
+		check_ivm_restriction((Node *) query);
+	}
+
 	if (into->skipData)
 	{
 		/*
@@ -358,6 +387,27 @@ ExecCreateTableAs(ParseState *pstate, CreateTableAsStmt *stmt,
 
 		/* Restore userid and security context */
 		SetUserIdAndSecContext(save_userid, save_sec_context);
+
+		if (into->ivm)
+		{
+			Oid matviewOid = address.objectId;
+			Relation matviewRel = table_open(matviewOid, NoLock);
+
+			/*
+			 * Mark relisivm field, if it's a matview and into->ivm is true.
+			 */
+			SetMatViewIVMState(matviewRel, true);
+
+			if (!into->skipData)
+			{
+				/* Create an index on incremental maintainable materialized view, if possible */
+				CreateIndexOnIMMV((Query *) into->viewQuery, matviewRel);
+
+				/* Create triggers on incremental maintainable materialized view */
+				CreateIvmTriggersOnBaseTables((Query *) into->viewQuery, matviewOid);
+			}
+			table_close(matviewRel, NoLock);
+		}
 	}
 
 	return address;
@@ -635,3 +685,634 @@ intorel_destroy(DestReceiver *self)
 {
 	pfree(self);
 }
+
+/*
+ * CreateIvmTriggersOnBaseTables -- create IVM triggers on all base tables
+ */
+void
+CreateIvmTriggersOnBaseTables(Query *qry, Oid matviewOid)
+{
+	Relids	relids = NULL;
+	bool	ex_lock = false;
+	RangeTblEntry *rte;
+
+	/* Immediately return if we don't have any base tables. */
+	if (list_length(qry->rtable) < 1)
+		return;
+
+	/*
+	 * If the view has more than one base tables, we need an exclusive lock
+	 * on the view so that the view would be maintained serially to avoid
+	 * the inconsistency that occurs when two base tables are modified in
+	 * concurrent transactions. However, if the view has only one table,
+	 * we can use a weaker lock.
+	 *
+	 * The type of lock should be determined here, because if we check the
+	 * view definition at maintenance time, we need to acquire a weaker lock,
+	 * and upgrading the lock level after this increases probability of
+	 * deadlock.
+	 */
+
+	rte = list_nth(qry->rtable, 0);
+	if (list_length(qry->rtable) > 1 || rte->rtekind != RTE_RELATION)
+		ex_lock = true;
+
+	CreateIvmTriggersOnBaseTablesRecurse(qry, (Node *)qry, matviewOid, &relids, ex_lock);
+
+	bms_free(relids);
+}
+
+static void
+CreateIvmTriggersOnBaseTablesRecurse(Query *qry, Node *node, Oid matviewOid,
+									 Relids *relids, bool ex_lock)
+{
+	if (node == NULL)
+		return;
+
+	/* This can recurse, so check for excessive recursion */
+	check_stack_depth();
+
+	switch (nodeTag(node))
+	{
+		case T_Query:
+			{
+				Query *query = (Query *) node;
+
+				CreateIvmTriggersOnBaseTablesRecurse(qry, (Node *)query->jointree, matviewOid, relids, ex_lock);
+			}
+			break;
+
+		case T_RangeTblRef:
+			{
+				int			rti = ((RangeTblRef *) node)->rtindex;
+				RangeTblEntry *rte = rt_fetch(rti, qry->rtable);
+
+				if (rte->rtekind == RTE_RELATION && !bms_is_member(rte->relid, *relids))
+				{
+					CreateIvmTrigger(rte->relid, matviewOid, TRIGGER_TYPE_INSERT, TRIGGER_TYPE_BEFORE, ex_lock);
+					CreateIvmTrigger(rte->relid, matviewOid, TRIGGER_TYPE_DELETE, TRIGGER_TYPE_BEFORE, ex_lock);
+					CreateIvmTrigger(rte->relid, matviewOid, TRIGGER_TYPE_UPDATE, TRIGGER_TYPE_BEFORE, ex_lock);
+					CreateIvmTrigger(rte->relid, matviewOid, TRIGGER_TYPE_TRUNCATE, TRIGGER_TYPE_BEFORE, true);
+					CreateIvmTrigger(rte->relid, matviewOid, TRIGGER_TYPE_INSERT, TRIGGER_TYPE_AFTER, ex_lock);
+					CreateIvmTrigger(rte->relid, matviewOid, TRIGGER_TYPE_DELETE, TRIGGER_TYPE_AFTER, ex_lock);
+					CreateIvmTrigger(rte->relid, matviewOid, TRIGGER_TYPE_UPDATE, TRIGGER_TYPE_AFTER, ex_lock);
+					CreateIvmTrigger(rte->relid, matviewOid, TRIGGER_TYPE_TRUNCATE, TRIGGER_TYPE_AFTER, true);
+
+					*relids = bms_add_member(*relids, rte->relid);
+				}
+			}
+			break;
+
+		case T_FromExpr:
+			{
+				FromExpr   *f = (FromExpr *) node;
+				ListCell   *l;
+
+				foreach(l, f->fromlist)
+					CreateIvmTriggersOnBaseTablesRecurse(qry, lfirst(l), matviewOid, relids, ex_lock);
+			}
+			break;
+
+		case T_JoinExpr:
+			{
+				JoinExpr   *j = (JoinExpr *) node;
+
+				CreateIvmTriggersOnBaseTablesRecurse(qry, j->larg, matviewOid, relids, ex_lock);
+				CreateIvmTriggersOnBaseTablesRecurse(qry, j->rarg, matviewOid, relids, ex_lock);
+			}
+			break;
+
+		default:
+			elog(ERROR, "unrecognized node type: %d", (int) nodeTag(node));
+	}
+}
+
+/*
+ * CreateIvmTrigger -- create IVM trigger on a base table
+ */
+static void
+CreateIvmTrigger(Oid relOid, Oid viewOid, int16 type, int16 timing, bool ex_lock)
+{
+	ObjectAddress	refaddr;
+	ObjectAddress	address;
+	CreateTrigStmt *ivm_trigger;
+	List *transitionRels = NIL;
+
+	Assert(timing == TRIGGER_TYPE_BEFORE || timing == TRIGGER_TYPE_AFTER);
+
+	refaddr.classId = RelationRelationId;
+	refaddr.objectId = viewOid;
+	refaddr.objectSubId = 0;
+
+	ivm_trigger = makeNode(CreateTrigStmt);
+	ivm_trigger->relation = NULL;
+	ivm_trigger->row = false;
+
+	ivm_trigger->timing = timing;
+	ivm_trigger->events = type;
+
+	switch (type)
+	{
+		case TRIGGER_TYPE_INSERT:
+			ivm_trigger->trigname = (timing == TRIGGER_TYPE_BEFORE ? "IVM_trigger_ins_before" : "IVM_trigger_ins_after");
+			break;
+		case TRIGGER_TYPE_DELETE:
+			ivm_trigger->trigname = (timing == TRIGGER_TYPE_BEFORE ? "IVM_trigger_del_before" : "IVM_trigger_del_after");
+			break;
+		case TRIGGER_TYPE_UPDATE:
+			ivm_trigger->trigname = (timing == TRIGGER_TYPE_BEFORE ? "IVM_trigger_upd_before" : "IVM_trigger_upd_after");
+			break;
+		case TRIGGER_TYPE_TRUNCATE:
+			ivm_trigger->trigname = (timing == TRIGGER_TYPE_BEFORE ? "IVM_trigger_truncate_before" : "IVM_trigger_truncate_after");
+			break;
+		default:
+			elog(ERROR, "unsupported trigger type");
+	}
+
+	if (timing == TRIGGER_TYPE_AFTER)
+	{
+		if (type == TRIGGER_TYPE_INSERT || type == TRIGGER_TYPE_UPDATE)
+		{
+			TriggerTransition *n = makeNode(TriggerTransition);
+			n->name = "__ivm_newtable";
+			n->isNew = true;
+			n->isTable = true;
+
+			transitionRels = lappend(transitionRels, n);
+		}
+		if (type == TRIGGER_TYPE_DELETE || type == TRIGGER_TYPE_UPDATE)
+		{
+			TriggerTransition *n = makeNode(TriggerTransition);
+			n->name = "__ivm_oldtable";
+			n->isNew = false;
+			n->isTable = true;
+
+			transitionRels = lappend(transitionRels, n);
+		}
+	}
+
+	/*
+	 * XXX: When using DELETE or UPDATE, we must use exclusive lock for now
+	 * because apply_old_delta(_with_count) uses ctid to identify the tuple
+	 * to be deleted/deleted, but doesn't work in concurrent situations.
+	 *
+	 * If the view doesn't have aggregate, distinct, or tuple duplicate,
+	 * then it would work even in concurrent situations. However, we don't have
+	 * any way to guarantee the view has a unique key before opening the IMMV
+	 * at the maintenance time because users may drop the unique index.
+	 */
+
+	if (type == TRIGGER_TYPE_DELETE || type == TRIGGER_TYPE_UPDATE)
+		ex_lock = true;
+
+	ivm_trigger->funcname =
+		(timing == TRIGGER_TYPE_BEFORE ? SystemFuncName("IVM_immediate_before") : SystemFuncName("IVM_immediate_maintenance"));
+
+	ivm_trigger->columns = NIL;
+	ivm_trigger->transitionRels = transitionRels;
+	ivm_trigger->whenClause = NULL;
+	ivm_trigger->isconstraint = false;
+	ivm_trigger->deferrable = false;
+	ivm_trigger->initdeferred = false;
+	ivm_trigger->constrrel = NULL;
+	ivm_trigger->args = list_make2(
+		makeString(DatumGetPointer(DirectFunctionCall1(oidout, ObjectIdGetDatum(viewOid)))),
+		makeString(DatumGetPointer(DirectFunctionCall1(boolout, BoolGetDatum(ex_lock))))
+		);
+
+	address = CreateTrigger(ivm_trigger, NULL, relOid, InvalidOid, InvalidOid,
+						 InvalidOid, InvalidOid, InvalidOid, NULL, true, false);
+
+	recordDependencyOn(&address, &refaddr, DEPENDENCY_AUTO);
+
+	/* Make changes-so-far visible */
+	CommandCounterIncrement();
+}
+
+/*
+ * check_ivm_restriction --- look for specify nodes in the query tree
+ */
+static void
+check_ivm_restriction(Node *node)
+{
+	check_ivm_restriction_walker(node, NULL);
+}
+
+static bool
+check_ivm_restriction_walker(Node *node, void *context)
+{
+	if (node == NULL)
+		return false;
+
+	/*
+	 * We currently don't support Sub-Query.
+	 */
+	if (IsA(node, SubPlan) || IsA(node, SubLink))
+		ereport(ERROR,
+				(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+				 errmsg("subquery is not supported on incrementally maintainable materialized view")));
+
+	/* This can recurse, so check for excessive recursion */
+	check_stack_depth();
+
+	switch (nodeTag(node))
+	{
+		case T_Query:
+			{
+				Query *qry = (Query *)node;
+				ListCell   *lc;
+				List       *vars;
+
+				/* if contained CTE, return error */
+				if (qry->cteList != NIL)
+					ereport(ERROR,
+							(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+							 errmsg("CTE is not supported on incrementally maintainable materialized view")));
+				if (qry->havingQual != NULL)
+					ereport(ERROR,
+							(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+							 errmsg(" HAVING clause is not supported on incrementally maintainable materialized view")));
+				if (qry->sortClause != NIL)	/* There is a possibility that we don't need to return an error */
+					ereport(ERROR,
+							(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+							 errmsg("ORDER BY clause is not supported on incrementally maintainable materialized view")));
+				if (qry->limitOffset != NULL || qry->limitCount != NULL)
+					ereport(ERROR,
+							(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+							 errmsg("LIMIT/OFFSET clause is not supported on incrementally maintainable materialized view")));
+				if (qry->distinctClause)
+					ereport(ERROR,
+							(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+							 errmsg("DISTINCT is not supported on incrementally maintainable materialized view")));
+				if (qry->hasDistinctOn)
+					ereport(ERROR,
+							(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+							 errmsg("DISTINCT ON is not supported on incrementally maintainable materialized view")));
+				if (qry->hasWindowFuncs)
+					ereport(ERROR,
+							(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+							 errmsg("window functions are not supported on incrementally maintainable materialized view")));
+				if (qry->groupingSets != NIL)
+					ereport(ERROR,
+							(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+							 errmsg("GROUPING SETS, ROLLUP, or CUBE clauses is not supported on incrementally maintainable materialized view")));
+				if (qry->setOperations != NULL)
+					ereport(ERROR,
+							(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+							 errmsg("UNION/INTERSECT/EXCEPT statements are not supported on incrementally maintainable materialized view")));
+				if (list_length(qry->targetList) == 0)
+					ereport(ERROR,
+							(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+							 errmsg("empty target list is not supported on incrementally maintainable materialized view")));
+				if (qry->rowMarks != NIL)
+					ereport(ERROR,
+							(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+							 errmsg("FOR UPDATE/SHARE clause is not supported on incrementally maintainable materialized view")));
+
+				/* system column restrictions */
+				vars = pull_vars_of_level((Node *) qry, 0);
+				foreach(lc, vars)
+				{
+					if (IsA(lfirst(lc), Var))
+					{
+						Var *var = (Var *) lfirst(lc);
+						/* if system column, return error */
+						if (var->varattno < 0)
+							ereport(ERROR,
+									(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+									 errmsg("system column is not supported on incrementally maintainable materialized view")));
+					}
+				}
+
+				/* restrictions for rtable */
+				foreach(lc, qry->rtable)
+				{
+					RangeTblEntry *rte = (RangeTblEntry *) lfirst(lc);
+
+					if (rte->subquery)
+						ereport(ERROR,
+								(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+								 errmsg("subquery is not supported on incrementally maintainable materialized view")));
+
+					if (rte->tablesample != NULL)
+						ereport(ERROR,
+								(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+								 errmsg("TABLESAMPLE clause is not supported on incrementally maintainable materialized view")));
+
+					if (rte->relkind == RELKIND_PARTITIONED_TABLE)
+						ereport(ERROR,
+								(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+								 errmsg("partitioned table is not supported on incrementally maintainable materialized view")));
+
+					if (rte->relkind == RELKIND_RELATION && has_superclass(rte->relid))
+						ereport(ERROR,
+								(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+								 errmsg("partitions is not supported on incrementally maintainable materialized view")));
+
+					if (rte->relkind == RELKIND_RELATION && find_inheritance_children(rte->relid, NoLock) != NIL)
+						ereport(ERROR,
+								(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+								 errmsg("inheritance parent is not supported on incrementally maintainable materialized view")));
+
+					if (rte->relkind == RELKIND_FOREIGN_TABLE)
+						ereport(ERROR,
+								(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+								 errmsg("foreign table is not supported on incrementally maintainable materialized view")));
+
+					if (rte->relkind == RELKIND_VIEW ||
+						rte->relkind == RELKIND_MATVIEW)
+						ereport(ERROR,
+								(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+								 errmsg("VIEW or MATERIALIZED VIEW is not supported on incrementally maintainable materialized view")));
+
+					if (rte->rtekind == RTE_VALUES)
+						ereport(ERROR,
+								(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+								 errmsg("VALUES is not supported on incrementally maintainable materialized view")));
+
+				}
+
+				query_tree_walker(qry, check_ivm_restriction_walker, NULL, QTW_IGNORE_RANGE_TABLE);
+
+				break;
+			}
+		case T_TargetEntry:
+			{
+				TargetEntry *tle = (TargetEntry *)node;
+				if (isIvmName(tle->resname))
+						ereport(ERROR,
+								(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+								 errmsg("column name %s is not supported on incrementally maintainable materialized view", tle->resname)));
+
+				expression_tree_walker(node, check_ivm_restriction_walker, NULL);
+				break;
+			}
+		case T_JoinExpr:
+			{
+				JoinExpr *joinexpr = (JoinExpr *)node;
+
+				if (joinexpr->jointype > JOIN_INNER)
+						ereport(ERROR,
+								(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+								 errmsg("OUTER JOIN is not supported on incrementally maintainable materialized view")));
+
+				expression_tree_walker(node, check_ivm_restriction_walker, NULL);
+			}
+			break;
+		case T_Aggref:
+			ereport(ERROR,
+					(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+					 errmsg("aggregate function is not supported on incrementally maintainable materialized view")));
+			break;
+		default:
+			expression_tree_walker(node, check_ivm_restriction_walker, (void *) context);
+			break;
+	}
+	return false;
+}
+
+/*
+ * CreateIndexOnIMMV
+ *
+ * Create a unique index on incremental maintainable materialized view.
+ * If the view definition query has a GROUP BY clause, the index is created
+ * on the columns of GROUP BY expressions. Otherwise, if the view contains
+ * all primary key attritubes of its base tables in the target list, the index
+ * is created on these attritubes. In other cases, no index is created.
+ */
+void
+CreateIndexOnIMMV(Query *query, Relation matviewRel)
+{
+	ListCell *lc;
+	IndexStmt  *index;
+	ObjectAddress address;
+	List *constraintList = NIL;
+	char		idxname[NAMEDATALEN];
+	List	   *indexoidlist = RelationGetIndexList(matviewRel);
+	ListCell   *indexoidscan;
+	Bitmapset *key_attnos;
+
+	snprintf(idxname, sizeof(idxname), "%s_index", RelationGetRelationName(matviewRel));
+
+	index = makeNode(IndexStmt);
+
+	index->unique = true;
+	index->primary = false;
+	index->isconstraint = false;
+	index->deferrable = false;
+	index->initdeferred = false;
+	index->idxname = idxname;
+	index->relation =
+		makeRangeVar(get_namespace_name(RelationGetNamespace(matviewRel)),
+					 pstrdup(RelationGetRelationName(matviewRel)),
+					 -1);
+	index->accessMethod = DEFAULT_INDEX_TYPE;
+	index->options = NIL;
+	index->tableSpace = get_tablespace_name(matviewRel->rd_rel->reltablespace);
+	index->whereClause = NULL;
+	index->indexParams = NIL;
+	index->indexIncludingParams = NIL;
+	index->excludeOpNames = NIL;
+	index->idxcomment = NULL;
+	index->indexOid = InvalidOid;
+	index->oldNumber = InvalidRelFileNumber;
+	index->oldCreateSubid = InvalidSubTransactionId;
+	index->oldFirstRelfilelocatorSubid = InvalidSubTransactionId;
+	index->transformed = true;
+	index->concurrent = false;
+	index->if_not_exists = false;
+
+	/* create index on the base tables' primary key columns */
+	key_attnos = get_primary_key_attnos_from_query(query, &constraintList);
+	if (key_attnos)
+	{
+		foreach(lc, query->targetList)
+		{
+			TargetEntry *tle = (TargetEntry *) lfirst(lc);
+			Form_pg_attribute attr = TupleDescAttr(matviewRel->rd_att, tle->resno - 1);
+
+			if (bms_is_member(tle->resno - FirstLowInvalidHeapAttributeNumber, key_attnos))
+			{
+				IndexElem  *iparam;
+
+				iparam = makeNode(IndexElem);
+				iparam->name = pstrdup(NameStr(attr->attname));
+				iparam->expr = NULL;
+				iparam->indexcolname = NULL;
+				iparam->collation = NIL;
+				iparam->opclass = NIL;
+				iparam->opclassopts = NIL;
+				iparam->ordering = SORTBY_DEFAULT;
+				iparam->nulls_ordering = SORTBY_NULLS_DEFAULT;
+				index->indexParams = lappend(index->indexParams, iparam);
+			}
+		}
+	}
+	else
+	{
+		/* create no index, just notice that an appropriate index is necessary for efficient IVM */
+		ereport(NOTICE,
+				(errmsg("could not create an index on materialized view \"%s\" automatically",
+						RelationGetRelationName(matviewRel)),
+				 errdetail("This target list does not have all the primary key columns. "),
+				 errhint("Create an index on the materialized view for efficient incremental maintenance.")));
+		return;
+	}
+
+	/* If we have a compatible index, we don't need to create another. */
+	foreach(indexoidscan, indexoidlist)
+	{
+		Oid			indexoid = lfirst_oid(indexoidscan);
+		Relation	indexRel;
+		bool		hasCompatibleIndex = false;
+
+		indexRel = index_open(indexoid, AccessShareLock);
+
+		if (CheckIndexCompatible(indexRel->rd_id,
+								index->accessMethod,
+								index->indexParams,
+								index->excludeOpNames,
+								false))
+			hasCompatibleIndex = true;
+
+		index_close(indexRel, AccessShareLock);
+
+		if (hasCompatibleIndex)
+			return;
+	}
+
+	address = DefineIndex(RelationGetRelid(matviewRel),
+						  index,
+						  InvalidOid,
+						  InvalidOid,
+						  InvalidOid,
+						  -1,
+						  false, true, false, false, true);
+
+	ereport(NOTICE,
+			(errmsg("created index \"%s\" on materialized view \"%s\"",
+					idxname, RelationGetRelationName(matviewRel))));
+
+	/*
+	 * Make dependencies so that the index is dropped if any base tables's
+	 * primary key is dropped.
+	 */
+	foreach(lc, constraintList)
+	{
+		Oid constraintOid = lfirst_oid(lc);
+		ObjectAddress	refaddr;
+
+		refaddr.classId = ConstraintRelationId;
+		refaddr.objectId = constraintOid;
+		refaddr.objectSubId = 0;
+
+		recordDependencyOn(&address, &refaddr, DEPENDENCY_NORMAL);
+	}
+}
+
+
+/*
+ * get_primary_key_attnos_from_query
+ *
+ * Identify the columns in base tables' primary keys in the target list.
+ *
+ * Returns a Bitmapset of the column attnos of the primary key's columns of
+ * tables that used in the query.  The attnos are offset by
+ * FirstLowInvalidHeapAttributeNumber as same as get_primary_key_attnos.
+ *
+ * If any table has no primary key or any primary key's columns is not in
+ * the target list, return NULL.  We also return NULL if any pkey constraint
+ * is deferrable.
+ *
+ * constraintList is set to a list of the OIDs of the pkey constraints.
+ */
+static Bitmapset *
+get_primary_key_attnos_from_query(Query *query, List **constraintList)
+{
+	List *key_attnos_list = NIL;
+	ListCell *lc;
+	int i;
+	Bitmapset *keys = NULL;
+	Relids	rels_in_from;
+
+	/*
+	 * Collect primary key attributes from all tables used in query. The key attributes
+	 * sets for each table are stored in key_attnos_list in order by RTE index.
+	 */
+	foreach(lc, query->rtable)
+	{
+		RangeTblEntry *r = (RangeTblEntry*) lfirst(lc);
+		Bitmapset *key_attnos;
+		bool	has_pkey = true;
+
+		/* for tables, call get_primary_key_attnos */
+		if (r->rtekind == RTE_RELATION)
+		{
+			Oid constraintOid;
+			key_attnos = get_primary_key_attnos(r->relid, false, &constraintOid);
+			*constraintList = lappend_oid(*constraintList, constraintOid);
+			has_pkey = (key_attnos != NULL);
+		}
+		/* for other RTEs, store NULL into key_attnos_list */
+		else
+			key_attnos = NULL;
+
+		/*
+		 * If any table or subquery has no primary key or its pkey constraint is deferrable,
+		 * we cannot get key attributes for this query, so return NULL.
+		 */
+		if (!has_pkey)
+			return NULL;
+
+		key_attnos_list = lappend(key_attnos_list, key_attnos);
+	}
+
+	/* Collect key attributes appearing in the target list */
+	i = 1;
+	foreach(lc, query->targetList)
+	{
+		TargetEntry *tle = (TargetEntry *) flatten_join_alias_vars(NULL, query, lfirst(lc));
+
+		if (IsA(tle->expr, Var))
+		{
+			Var *var = (Var*) tle->expr;
+			Bitmapset *key_attnos = list_nth(key_attnos_list, var->varno - 1);
+
+			/* check if this attribute is from a base table's primary key */
+			if (bms_is_member(var->varattno - FirstLowInvalidHeapAttributeNumber, key_attnos))
+			{
+				/*
+				 * Remove found key attributes from key_attnos_list, and add this
+				 * to the result list.
+				 */
+				key_attnos = bms_del_member(key_attnos, var->varattno - FirstLowInvalidHeapAttributeNumber);
+				if (bms_is_empty(key_attnos))
+				{
+					key_attnos_list = list_delete_nth_cell(key_attnos_list, var->varno - 1);
+					key_attnos_list = list_insert_nth(key_attnos_list, var->varno - 1, NULL);
+				}
+				keys = bms_add_member(keys, i - FirstLowInvalidHeapAttributeNumber);
+			}
+		}
+		i++;
+	}
+
+	/* Collect RTE indexes of relations appearing in the FROM clause */
+	rels_in_from = get_relids_in_jointree((Node *) query->jointree, false, false);
+
+	/*
+	 * Check if all key attributes of relations in FROM are appearing in the target
+	 * list.  If an attribute remains in key_attnos_list in spite of the table is used
+	 * in FROM clause, the target is missing this key attribute, so we return NULL.
+	 */
+	i = 1;
+	foreach(lc, key_attnos_list)
+	{
+		Bitmapset *bms = (Bitmapset *)lfirst(lc);
+		if (!bms_is_empty(bms) && bms_is_member(i, rels_in_from))
+			return NULL;
+		i++;
+	}
+
+	return keys;
+}
diff --git a/src/backend/commands/matview.c b/src/backend/commands/matview.c
index 59920ced83..a821992a37 100644
--- a/src/backend/commands/matview.c
+++ b/src/backend/commands/matview.c
@@ -25,26 +25,37 @@
 #include "catalog/indexing.h"
 #include "catalog/namespace.h"
 #include "catalog/pg_am.h"
+#include "catalog/pg_depend.h"
+#include "catalog/pg_trigger.h"
 #include "catalog/pg_opclass.h"
 #include "catalog/pg_operator.h"
 #include "commands/cluster.h"
 #include "commands/matview.h"
 #include "commands/tablecmds.h"
 #include "commands/tablespace.h"
+#include "commands/createas.h"
 #include "executor/executor.h"
 #include "executor/spi.h"
+#include "executor/tstoreReceiver.h"
 #include "miscadmin.h"
+#include "nodes/makefuncs.h"
+#include "parser/analyze.h"
+#include "parser/parse_clause.h"
+#include "parser/parse_func.h"
 #include "parser/parse_relation.h"
 #include "pgstat.h"
 #include "rewrite/rewriteHandler.h"
+#include "rewrite/rowsecurity.h"
 #include "storage/lmgr.h"
 #include "storage/smgr.h"
 #include "tcop/tcopprot.h"
 #include "utils/builtins.h"
+#include "utils/fmgroids.h"
 #include "utils/lsyscache.h"
 #include "utils/rel.h"
 #include "utils/snapmgr.h"
 #include "utils/syscache.h"
+#include "utils/typcache.h"
 
 
 typedef struct
@@ -58,6 +69,52 @@ typedef struct
 	BulkInsertState bistate;	/* bulk insert state */
 } DR_transientrel;
 
+#define MV_INIT_QUERYHASHSIZE	16
+
+/*
+ * MV_TriggerHashEntry
+ *
+ * Hash entry for base tables on which IVM trigger is invoked
+ */
+typedef struct MV_TriggerHashEntry
+{
+	Oid	matview_id;			/* OID of the materialized view */
+	int	before_trig_count;	/* count of before triggers invoked */
+	int	after_trig_count;	/* count of after triggers invoked */
+
+	Snapshot	snapshot;	/* Snapshot just before table change */
+
+	List   *tables;		/* List of MV_TriggerTable */
+	bool	has_old;	/* tuples are deleted from any table? */
+	bool	has_new;	/* tuples are inserted into any table? */
+} MV_TriggerHashEntry;
+
+/*
+ * MV_TriggerTable
+ *
+ * IVM related data for tables on which the trigger is invoked.
+ */
+typedef struct MV_TriggerTable
+{
+	Oid		table_id;			/* OID of the modified table */
+	List   *old_tuplestores;	/* tuplestores for deleted tuples */
+	List   *new_tuplestores;	/* tuplestores for inserted tuples */
+
+	List   *rte_indexes;		/* List of RTE index of the modified table */
+	RangeTblEntry *original_rte;	/* the original RTE saved before rewriting query */
+
+	Relation	rel;			/* relation of the modified table */
+	TupleTableSlot *slot;		/* for checking visibility in the pre-state table */
+} MV_TriggerTable;
+
+static HTAB *mv_trigger_info = NULL;
+
+static bool in_delta_calculation = false;
+
+/* ENR name for materialized view delta */
+#define NEW_DELTA_ENRNAME "new_delta"
+#define OLD_DELTA_ENRNAME "old_delta"
+
 static int	matview_maintenance_depth = 0;
 
 static void transientrel_startup(DestReceiver *self, int operation, TupleDesc typeinfo);
@@ -65,7 +122,9 @@ static bool transientrel_receive(TupleTableSlot *slot, DestReceiver *self);
 static void transientrel_shutdown(DestReceiver *self);
 static void transientrel_destroy(DestReceiver *self);
 static uint64 refresh_matview_datafill(DestReceiver *dest, Query *query,
-									   const char *queryString);
+						 QueryEnvironment *queryEnv,
+						 TupleDesc *resultTupleDesc,
+						 const char *queryString);
 static char *make_temptable_name_n(char *tempname, int n);
 static void refresh_by_match_merge(Oid matviewOid, Oid tempOid, Oid relowner,
 								   int save_sec_context);
@@ -73,6 +132,37 @@ static void refresh_by_heap_swap(Oid matviewOid, Oid OIDNewHeap, char relpersist
 static bool is_usable_unique_index(Relation indexRel);
 static void OpenMatViewIncrementalMaintenance(void);
 static void CloseMatViewIncrementalMaintenance(void);
+static Query *get_matview_query(Relation matviewRel);
+
+static Query *rewrite_query_for_preupdate_state(Query *query, List *tables,
+								  ParseState *pstate, Oid matviewid);
+static void register_delta_ENRs(ParseState *pstate, Query *query, List *tables);
+static char *make_delta_enr_name(const char *prefix, Oid relid, int count);
+static RangeTblEntry *get_prestate_rte(RangeTblEntry *rte, MV_TriggerTable *table,
+				 QueryEnvironment *queryEnv, Oid matviewid);
+static RangeTblEntry *replace_rte_with_delta(RangeTblEntry *rte, MV_TriggerTable *table, bool is_new,
+		   QueryEnvironment *queryEnv);
+static Query *rewrite_query_for_counting(Query *query, ParseState *pstate);
+
+static void calc_delta(MV_TriggerTable *table, int rte_index, Query *query,
+			DestReceiver *dest_old, DestReceiver *dest_new,
+			TupleDesc *tupdesc_old, TupleDesc *tupdesc_new,
+			QueryEnvironment *queryEnv);
+static Query *rewrite_query_for_postupdate_state(Query *query, MV_TriggerTable *table, int rte_index);
+
+static void apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *new_tuplestores,
+			TupleDesc tupdesc_old, TupleDesc tupdesc_new,
+			Query *query);
+static void apply_old_delta(const char *matviewname, const char *deltaname_old,
+				List *keys);
+static void apply_new_delta(const char *matviewname, const char *deltaname_new,
+				StringInfo target_list);
+static char *get_matching_condition_string(List *keys);
+static void generate_equal(StringInfo querybuf, Oid opttype,
+			   const char *leftop, const char *rightop);
+
+static void mv_InitHashTables(void);
+static void clean_up_IVM_hash_entry(MV_TriggerHashEntry *entry, bool is_abort);
 
 /*
  * SetMatViewPopulatedState
@@ -114,6 +204,46 @@ SetMatViewPopulatedState(Relation relation, bool newstate)
 	CommandCounterIncrement();
 }
 
+/*
+ * SetMatViewIVMState
+ *		Mark a materialized view as IVM, or not.
+ *
+ * NOTE: caller must be holding an appropriate lock on the relation.
+ */
+void
+SetMatViewIVMState(Relation relation, bool newstate)
+{
+	Relation	pgrel;
+	HeapTuple	tuple;
+
+	Assert(relation->rd_rel->relkind == RELKIND_MATVIEW);
+
+	/*
+	 * Update relation's pg_class entry.  Crucial side-effect: other backends
+	 * (and this one too!) are sent SI message to make them rebuild relcache
+	 * entries.
+	 */
+	pgrel = table_open(RelationRelationId, RowExclusiveLock);
+	tuple = SearchSysCacheCopy1(RELOID,
+								ObjectIdGetDatum(RelationGetRelid(relation)));
+	if (!HeapTupleIsValid(tuple))
+		elog(ERROR, "cache lookup failed for relation %u",
+			 RelationGetRelid(relation));
+
+	((Form_pg_class) GETSTRUCT(tuple))->relisivm = newstate;
+
+	CatalogTupleUpdate(pgrel, &tuple->t_self, tuple);
+
+	heap_freetuple(tuple);
+	table_close(pgrel, RowExclusiveLock);
+
+	/*
+	 * Advance command counter to make the updated pg_class row locally
+	 * visible.
+	 */
+	CommandCounterIncrement();
+}
+
 /*
  * ExecRefreshMatView -- execute a REFRESH MATERIALIZED VIEW command
  *
@@ -140,8 +270,6 @@ ExecRefreshMatView(RefreshMatViewStmt *stmt, const char *queryString,
 {
 	Oid			matviewOid;
 	Relation	matviewRel;
-	RewriteRule *rule;
-	List	   *actions;
 	Query	   *dataQuery;
 	Oid			tableSpace;
 	Oid			relowner;
@@ -155,6 +283,7 @@ ExecRefreshMatView(RefreshMatViewStmt *stmt, const char *queryString,
 	int			save_sec_context;
 	int			save_nestlevel;
 	ObjectAddress address;
+	bool oldPopulated;
 
 	/* Determine strength of lock needed. */
 	concurrent = stmt->concurrent;
@@ -178,6 +307,7 @@ ExecRefreshMatView(RefreshMatViewStmt *stmt, const char *queryString,
 	SetUserIdAndSecContext(relowner,
 						   save_sec_context | SECURITY_RESTRICTED_OPERATION);
 	save_nestlevel = NewGUCNestLevel();
+	oldPopulated = RelationIsPopulated(matviewRel);
 
 	/* Make sure it is a materialized view. */
 	if (matviewRel->rd_rel->relkind != RELKIND_MATVIEW)
@@ -199,32 +329,9 @@ ExecRefreshMatView(RefreshMatViewStmt *stmt, const char *queryString,
 				 errmsg("%s and %s options cannot be used together",
 						"CONCURRENTLY", "WITH NO DATA")));
 
-	/*
-	 * Check that everything is correct for a refresh. Problems at this point
-	 * are internal errors, so elog is sufficient.
-	 */
-	if (matviewRel->rd_rel->relhasrules == false ||
-		matviewRel->rd_rules->numLocks < 1)
-		elog(ERROR,
-			 "materialized view \"%s\" is missing rewrite information",
-			 RelationGetRelationName(matviewRel));
-
-	if (matviewRel->rd_rules->numLocks > 1)
-		elog(ERROR,
-			 "materialized view \"%s\" has too many rules",
-			 RelationGetRelationName(matviewRel));
 
-	rule = matviewRel->rd_rules->rules[0];
-	if (rule->event != CMD_SELECT || !(rule->isInstead))
-		elog(ERROR,
-			 "the rule for materialized view \"%s\" is not a SELECT INSTEAD OF rule",
-			 RelationGetRelationName(matviewRel));
+	dataQuery = get_matview_query(matviewRel);
 
-	actions = rule->actions;
-	if (list_length(actions) != 1)
-		elog(ERROR,
-			 "the rule for materialized view \"%s\" is not a single action",
-			 RelationGetRelationName(matviewRel));
 
 	/*
 	 * Check that there is a unique index with no WHERE clause on one or more
@@ -259,12 +366,6 @@ ExecRefreshMatView(RefreshMatViewStmt *stmt, const char *queryString,
 					 errhint("Create a unique index with no WHERE clause on one or more columns of the materialized view.")));
 	}
 
-	/*
-	 * The stored query was rewritten at the time of the MV definition, but
-	 * has not been scribbled on by the planner.
-	 */
-	dataQuery = linitial_node(Query, actions);
-
 	/*
 	 * Check for active uses of the relation in the current transaction, such
 	 * as open scans.
@@ -292,6 +393,74 @@ ExecRefreshMatView(RefreshMatViewStmt *stmt, const char *queryString,
 		relpersistence = matviewRel->rd_rel->relpersistence;
 	}
 
+	/* delete IMMV triggers. */
+	if (RelationIsIVM(matviewRel) && stmt->skipData )
+	{
+		Relation	tgRel;
+		Relation	depRel;
+		ScanKeyData key;
+		SysScanDesc scan;
+		HeapTuple	tup;
+		ObjectAddresses *immv_triggers;
+
+		immv_triggers = new_object_addresses();
+
+		tgRel = table_open(TriggerRelationId, RowExclusiveLock);
+		depRel = table_open(DependRelationId, RowExclusiveLock);
+
+		/* search triggers that depends on IMMV. */
+		ScanKeyInit(&key,
+					Anum_pg_depend_refobjid,
+					BTEqualStrategyNumber, F_OIDEQ,
+					ObjectIdGetDatum(matviewOid));
+		scan = systable_beginscan(depRel, DependReferenceIndexId, true,
+								  NULL, 1, &key);
+		while ((tup = systable_getnext(scan)) != NULL)
+		{
+			ObjectAddress obj;
+			Form_pg_depend foundDep = (Form_pg_depend) GETSTRUCT(tup);
+
+			if (foundDep->classid == TriggerRelationId)
+			{
+				HeapTuple	tgtup;
+				ScanKeyData tgkey[1];
+				SysScanDesc tgscan;
+				Form_pg_trigger tgform;
+
+				/* Find the trigger name. */
+				ScanKeyInit(&tgkey[0],
+							Anum_pg_trigger_oid,
+							BTEqualStrategyNumber, F_OIDEQ,
+							ObjectIdGetDatum(foundDep->objid));
+
+				tgscan = systable_beginscan(tgRel, TriggerOidIndexId, true,
+											NULL, 1, tgkey);
+				tgtup = systable_getnext(tgscan);
+				if (!HeapTupleIsValid(tgtup))
+					elog(ERROR, "could not find tuple for immv trigger %u", foundDep->objid);
+
+				tgform = (Form_pg_trigger) GETSTRUCT(tgtup);
+
+				/* If trigger is created by IMMV, delete it. */
+				if (strncmp(NameStr(tgform->tgname), "IVM_trigger_", 12) == 0)
+				{
+					obj.classId = foundDep->classid;
+					obj.objectId = foundDep->objid;
+					obj.objectSubId = foundDep->refobjsubid;
+					add_exact_object_address(&obj, immv_triggers);
+				}
+				systable_endscan(tgscan);
+			}
+		}
+		systable_endscan(scan);
+
+		performMultipleDeletions(immv_triggers, DROP_RESTRICT, PERFORM_DELETION_INTERNAL);
+
+		table_close(depRel, RowExclusiveLock);
+		table_close(tgRel, RowExclusiveLock);
+		free_object_addresses(immv_triggers);
+	}
+
 	/*
 	 * Create the transient table that will receive the regenerated data. Lock
 	 * it against access by any other process until commit (by which time it
@@ -305,7 +474,7 @@ ExecRefreshMatView(RefreshMatViewStmt *stmt, const char *queryString,
 
 	/* Generate the data, if wanted. */
 	if (!stmt->skipData)
-		processed = refresh_matview_datafill(dest, dataQuery, queryString);
+		processed = refresh_matview_datafill(dest, dataQuery, NULL, NULL, queryString);
 
 	/* Make the matview match the newly generated data. */
 	if (concurrent)
@@ -340,6 +509,12 @@ ExecRefreshMatView(RefreshMatViewStmt *stmt, const char *queryString,
 			pgstat_count_heap_insert(matviewRel, processed);
 	}
 
+	if (!stmt->skipData && RelationIsIVM(matviewRel) && !oldPopulated)
+	{
+		CreateIndexOnIMMV(dataQuery, matviewRel);
+		CreateIvmTriggersOnBaseTables(dataQuery, matviewOid);
+	}
+
 	table_close(matviewRel, NoLock);
 
 	/* Roll back any GUC changes */
@@ -374,6 +549,8 @@ ExecRefreshMatView(RefreshMatViewStmt *stmt, const char *queryString,
  */
 static uint64
 refresh_matview_datafill(DestReceiver *dest, Query *query,
+						 QueryEnvironment *queryEnv,
+						 TupleDesc *resultTupleDesc,
 						 const char *queryString)
 {
 	List	   *rewritten;
@@ -410,7 +587,7 @@ refresh_matview_datafill(DestReceiver *dest, Query *query,
 	/* Create a QueryDesc, redirecting output to our tuple receiver */
 	queryDesc = CreateQueryDesc(plan, queryString,
 								GetActiveSnapshot(), InvalidSnapshot,
-								dest, NULL, NULL, 0);
+								dest, NULL, queryEnv ? queryEnv: NULL, 0);
 
 	/* call ExecutorStart to prepare the plan for execution */
 	ExecutorStart(queryDesc, 0);
@@ -420,6 +597,9 @@ refresh_matview_datafill(DestReceiver *dest, Query *query,
 
 	processed = queryDesc->estate->es_processed;
 
+	if (resultTupleDesc)
+		*resultTupleDesc = CreateTupleDescCopy(queryDesc->tupDesc);
+
 	/* and clean up */
 	ExecutorFinish(queryDesc);
 	ExecutorEnd(queryDesc);
@@ -953,3 +1133,1219 @@ CloseMatViewIncrementalMaintenance(void)
 	matview_maintenance_depth--;
 	Assert(matview_maintenance_depth >= 0);
 }
+
+/*
+ * get_matview_query - get the Query from a matview's _RETURN rule.
+ */
+static Query *
+get_matview_query(Relation matviewRel)
+{
+	RewriteRule *rule;
+	List * actions;
+
+	/*
+	 * Check that everything is correct for a refresh. Problems at this point
+	 * are internal errors, so elog is sufficient.
+	 */
+	if (matviewRel->rd_rel->relhasrules == false ||
+		matviewRel->rd_rules->numLocks < 1)
+		elog(ERROR,
+			 "materialized view \"%s\" is missing rewrite information",
+			 RelationGetRelationName(matviewRel));
+
+	if (matviewRel->rd_rules->numLocks > 1)
+		elog(ERROR,
+			 "materialized view \"%s\" has too many rules",
+			 RelationGetRelationName(matviewRel));
+
+	rule = matviewRel->rd_rules->rules[0];
+	if (rule->event != CMD_SELECT || !(rule->isInstead))
+		elog(ERROR,
+			 "the rule for materialized view \"%s\" is not a SELECT INSTEAD OF rule",
+			 RelationGetRelationName(matviewRel));
+
+	actions = rule->actions;
+	if (list_length(actions) != 1)
+		elog(ERROR,
+			 "the rule for materialized view \"%s\" is not a single action",
+			 RelationGetRelationName(matviewRel));
+
+	/*
+	 * The stored query was rewritten at the time of the MV definition, but
+	 * has not been scribbled on by the planner.
+	 */
+	return linitial_node(Query, actions);
+}
+
+
+/* ----------------------------------------------------
+ *		Incremental View Maintenance routines
+ * ---------------------------------------------------
+ */
+
+/*
+ * IVM_immediate_before
+ *
+ * IVM trigger function invoked before base table is modified. If this is
+ * invoked firstly in the same statement, we save the transaction id and the
+ * command id at that time.
+ */
+Datum
+IVM_immediate_before(PG_FUNCTION_ARGS)
+{
+	TriggerData *trigdata = (TriggerData *) fcinfo->context;
+	char	   *matviewOid_text = trigdata->tg_trigger->tgargs[0];
+	char	   *ex_lock_text = trigdata->tg_trigger->tgargs[1];
+	Oid			matviewOid;
+	MV_TriggerHashEntry *entry;
+	bool	found;
+	bool	ex_lock;
+
+	matviewOid = DatumGetObjectId(DirectFunctionCall1(oidin, CStringGetDatum(matviewOid_text)));
+	ex_lock = DatumGetBool(DirectFunctionCall1(boolin, CStringGetDatum(ex_lock_text)));
+
+	/* If the view has more than one tables, we have to use an exclusive lock. */
+	if (ex_lock)
+	{
+		/*
+		 * Wait for concurrent transactions which update this materialized view at
+		 * READ COMMITED. This is needed to see changes committed in other
+		 * transactions. No wait and raise an error at REPEATABLE READ or
+		 * SERIALIZABLE to prevent update anomalies of matviews.
+		 * XXX: dead-lock is possible here.
+		 */
+		if (!IsolationUsesXactSnapshot())
+			LockRelationOid(matviewOid, ExclusiveLock);
+		else if (!ConditionalLockRelationOid(matviewOid, ExclusiveLock))
+		{
+			/* try to throw error by name; relation could be deleted... */
+			char	   *relname = get_rel_name(matviewOid);
+
+			if (!relname)
+				ereport(ERROR,
+						(errcode(ERRCODE_LOCK_NOT_AVAILABLE),
+						errmsg("could not obtain lock on materialized view during incremental maintenance")));
+
+			ereport(ERROR,
+					(errcode(ERRCODE_LOCK_NOT_AVAILABLE),
+					errmsg("could not obtain lock on materialized view \"%s\" during incremental maintenance",
+							relname)));
+		}
+	}
+	else
+		LockRelationOid(matviewOid, RowExclusiveLock);
+
+	/*
+	 * On the first call initialize the hashtable
+	 */
+	if (!mv_trigger_info)
+		mv_InitHashTables();
+
+	entry = (MV_TriggerHashEntry *) hash_search(mv_trigger_info,
+											  (void *) &matviewOid,
+											  HASH_ENTER, &found);
+
+	/* On the first BEFORE to update the view, initialize trigger data */
+	if (!found)
+	{
+		/*
+		 * Get a snapshot just before the table was modified for checking
+		 * tuple visibility in the pre-update state of the table.
+		 */
+		Snapshot snapshot = GetActiveSnapshot();
+
+		entry->matview_id = matviewOid;
+		entry->before_trig_count = 0;
+		entry->after_trig_count = 0;
+		entry->snapshot = RegisterSnapshot(snapshot);
+		entry->tables = NIL;
+		entry->has_old = false;
+		entry->has_new = false;
+	}
+
+	entry->before_trig_count++;
+
+	return PointerGetDatum(NULL);
+}
+
+/*
+ * IVM_immediate_maintenance
+ *
+ * IVM trigger function invoked after base table is modified.
+ * For each table, tuplestores of transition tables are collected.
+ * and after the last modification
+ */
+Datum
+IVM_immediate_maintenance(PG_FUNCTION_ARGS)
+{
+	TriggerData *trigdata = (TriggerData *) fcinfo->context;
+	Relation	rel;
+	Oid			relid;
+	Oid			matviewOid;
+	Query	   *query;
+	Query	   *rewritten = NULL;
+	char	   *matviewOid_text = trigdata->tg_trigger->tgargs[0];
+	Relation	matviewRel;
+	int old_depth = matview_maintenance_depth;
+
+	Oid			relowner;
+	Tuplestorestate *old_tuplestore = NULL;
+	Tuplestorestate *new_tuplestore = NULL;
+	DestReceiver *dest_new = NULL, *dest_old = NULL;
+	Oid			save_userid;
+	int			save_sec_context;
+	int			save_nestlevel;
+
+	MV_TriggerHashEntry *entry;
+	MV_TriggerTable		*table;
+	bool	found;
+
+	ParseState		 *pstate;
+	QueryEnvironment *queryEnv = create_queryEnv();
+	MemoryContext	oldcxt;
+	ListCell   *lc;
+	int			i;
+
+
+	/* Create a ParseState for rewriting the view definition query */
+	pstate = make_parsestate(NULL);
+	pstate->p_queryEnv = queryEnv;
+	pstate->p_expr_kind = EXPR_KIND_SELECT_TARGET;
+
+	rel = trigdata->tg_relation;
+	relid = rel->rd_id;
+
+	matviewOid = DatumGetObjectId(DirectFunctionCall1(oidin, CStringGetDatum(matviewOid_text)));
+
+	/*
+	 * On the first call initialize the hashtable
+	 */
+	if (!mv_trigger_info)
+		mv_InitHashTables();
+
+	/* get the entry for this materialized view */
+	entry = (MV_TriggerHashEntry *) hash_search(mv_trigger_info,
+											  (void *) &matviewOid,
+											  HASH_FIND, &found);
+	Assert (found && entry != NULL);
+	entry->after_trig_count++;
+
+	/* search the entry for the modified table and create new entry if not found */
+	found = false;
+	foreach(lc, entry->tables)
+	{
+		table = (MV_TriggerTable *) lfirst(lc);
+		if (table->table_id == relid)
+		{
+			found = true;
+			break;
+		}
+	}
+	if (!found)
+	{
+		oldcxt = MemoryContextSwitchTo(TopTransactionContext);
+
+		table = (MV_TriggerTable *) palloc0(sizeof(MV_TriggerTable));
+		table->table_id = relid;
+		table->old_tuplestores = NIL;
+		table->new_tuplestores = NIL;
+		table->rte_indexes = NIL;
+		table->slot = MakeSingleTupleTableSlot(RelationGetDescr(rel), table_slot_callbacks(rel));
+		table->rel = table_open(RelationGetRelid(rel), NoLock);
+		entry->tables = lappend(entry->tables, table);
+
+		MemoryContextSwitchTo(oldcxt);
+	}
+
+	/* Save the transition tables and make a request to not free immediately */
+	if (trigdata->tg_oldtable)
+	{
+		oldcxt = MemoryContextSwitchTo(TopTransactionContext);
+		table->old_tuplestores = lappend(table->old_tuplestores, trigdata->tg_oldtable);
+		entry->has_old = true;
+		MemoryContextSwitchTo(oldcxt);
+	}
+	if (trigdata->tg_newtable)
+	{
+		oldcxt = MemoryContextSwitchTo(TopTransactionContext);
+		table->new_tuplestores = lappend(table->new_tuplestores, trigdata->tg_newtable);
+		entry->has_new = true;
+		MemoryContextSwitchTo(oldcxt);
+	}
+	if (entry->has_new || entry->has_old)
+	{
+		CmdType cmd;
+
+		if (TRIGGER_FIRED_BY_INSERT(trigdata->tg_event))
+			cmd = CMD_INSERT;
+		else if (TRIGGER_FIRED_BY_DELETE(trigdata->tg_event))
+			cmd = CMD_DELETE;
+		else if (TRIGGER_FIRED_BY_UPDATE(trigdata->tg_event))
+			cmd = CMD_UPDATE;
+		else
+			elog(ERROR,"unsupported trigger type");
+
+		/* Prolong lifespan of transition tables to the end of the last AFTER trigger */
+		SetTransitionTablePreserved(relid, cmd);
+	}
+
+
+	/* If this is not the last AFTER trigger call, immediately exit. */
+	Assert (entry->before_trig_count >= entry->after_trig_count);
+	if (entry->before_trig_count != entry->after_trig_count)
+		return PointerGetDatum(NULL);
+
+	/*
+	 * If this is the last AFTER trigger call, continue and update the view.
+	 */
+
+	/*
+	 * Advance command counter to make the updated base table row locally
+	 * visible.
+	 */
+	CommandCounterIncrement();
+
+	matviewRel = table_open(matviewOid, NoLock);
+
+	/* Make sure it is a materialized view. */
+	Assert(matviewRel->rd_rel->relkind == RELKIND_MATVIEW);
+
+	/*
+	 * Get and push the latast snapshot to see any changes which is committed
+	 * during waiting in other transactions at READ COMMITTED level.
+	 */
+	PushActiveSnapshot(GetTransactionSnapshot());
+
+	/*
+	 * Check for active uses of the relation in the current transaction, such
+	 * as open scans.
+	 *
+	 * NB: We count on this to protect us against problems with refreshing the
+	 * data using TABLE_INSERT_FROZEN.
+	 */
+	CheckTableNotInUse(matviewRel, "refresh a materialized view incrementally");
+
+	/*
+	 * Switch to the owner's userid, so that any functions are run as that
+	 * user.  Also arrange to make GUC variable changes local to this command.
+	 * We will switch modes when we are about to execute user code.
+	 */
+	relowner = matviewRel->rd_rel->relowner;
+	GetUserIdAndSecContext(&save_userid, &save_sec_context);
+	SetUserIdAndSecContext(relowner,
+						   save_sec_context | SECURITY_RESTRICTED_OPERATION);
+	save_nestlevel = NewGUCNestLevel();
+
+	/* get view query*/
+	query = get_matview_query(matviewRel);
+
+	/*
+	 * When a base table is truncated, the view content will be empty if the
+	 * view definition query does not contain an aggregate without a GROUP clause.
+	 * Therefore, such views can be truncated.
+	 */
+	if (TRIGGER_FIRED_BY_TRUNCATE(trigdata->tg_event))
+	{
+		ExecuteTruncateGuts(list_make1(matviewRel), list_make1_oid(matviewOid),
+							NIL, DROP_RESTRICT, false, false);
+
+		/* Clean up hash entry and delete tuplestores */
+		clean_up_IVM_hash_entry(entry, false);
+
+		/* Pop the original snapshot. */
+		PopActiveSnapshot();
+
+		table_close(matviewRel, NoLock);
+
+		/* Roll back any GUC changes */
+		AtEOXact_GUC(false, save_nestlevel);
+
+		/* Restore userid and security context */
+		SetUserIdAndSecContext(save_userid, save_sec_context);
+
+		return PointerGetDatum(NULL);
+	}
+
+	/*
+	 * rewrite query for calculating deltas
+	 */
+
+	rewritten = copyObject(query);
+
+	/* Replace resnames in a target list with materialized view's attnames */
+	i = 0;
+	foreach (lc, rewritten->targetList)
+	{
+		TargetEntry *tle = (TargetEntry *) lfirst(lc);
+		Form_pg_attribute attr = TupleDescAttr(matviewRel->rd_att, i);
+		char *resname = NameStr(attr->attname);
+
+		tle->resname = pstrdup(resname);
+		i++;
+	}
+
+	/* Set all tables in the query to pre-update state */
+	rewritten = rewrite_query_for_preupdate_state(rewritten, entry->tables,
+												  pstate, matviewOid);
+	/* Rewrite for counting duplicated tuples */
+	rewritten = rewrite_query_for_counting(rewritten, pstate);
+
+	/* Create tuplestores to store view deltas */
+	if (entry->has_old)
+	{
+		oldcxt = MemoryContextSwitchTo(TopTransactionContext);
+
+		old_tuplestore = tuplestore_begin_heap(false, false, work_mem);
+		dest_old = CreateDestReceiver(DestTuplestore);
+		SetTuplestoreDestReceiverParams(dest_old,
+									old_tuplestore,
+									TopTransactionContext,
+									false,
+									NULL,
+									NULL);
+
+		MemoryContextSwitchTo(oldcxt);
+	}
+	if (entry->has_new)
+	{
+		oldcxt = MemoryContextSwitchTo(TopTransactionContext);
+
+		new_tuplestore = tuplestore_begin_heap(false, false, work_mem);
+		dest_new = CreateDestReceiver(DestTuplestore);
+		SetTuplestoreDestReceiverParams(dest_new,
+									new_tuplestore,
+									TopTransactionContext,
+									false,
+									NULL,
+									NULL);
+		MemoryContextSwitchTo(oldcxt);
+	}
+
+	/* for all modified tables */
+	foreach(lc, entry->tables)
+	{
+		ListCell *lc2;
+
+		table = (MV_TriggerTable *) lfirst(lc);
+
+		/* loop for self-join */
+		foreach(lc2, table->rte_indexes)
+		{
+			int	rte_index = lfirst_int(lc2);
+			TupleDesc		tupdesc_old;
+			TupleDesc		tupdesc_new;
+
+			/* calculate delta tables */
+			calc_delta(table, rte_index, rewritten, dest_old, dest_new,
+					   &tupdesc_old, &tupdesc_new, queryEnv);
+
+			/* Set the table in the query to post-update state */
+			rewritten = rewrite_query_for_postupdate_state(rewritten, table, rte_index);
+
+			PG_TRY();
+			{
+				/* apply the delta tables to the materialized view */
+				apply_delta(matviewOid, old_tuplestore, new_tuplestore,
+							tupdesc_old, tupdesc_new, query);
+			}
+			PG_CATCH();
+			{
+				matview_maintenance_depth = old_depth;
+				PG_RE_THROW();
+			}
+			PG_END_TRY();
+
+			/* clear view delta tuplestores */
+			if (old_tuplestore)
+				tuplestore_clear(old_tuplestore);
+			if (new_tuplestore)
+				tuplestore_clear(new_tuplestore);
+		}
+	}
+
+	/* Clean up hash entry and delete tuplestores */
+	clean_up_IVM_hash_entry(entry, false);
+	if (old_tuplestore)
+	{
+		dest_old->rDestroy(dest_old);
+		tuplestore_end(old_tuplestore);
+	}
+	if (new_tuplestore)
+	{
+		dest_new->rDestroy(dest_new);
+		tuplestore_end(new_tuplestore);
+	}
+
+	/* Pop the original snapshot. */
+	PopActiveSnapshot();
+
+	table_close(matviewRel, NoLock);
+
+	/* Roll back any GUC changes */
+	AtEOXact_GUC(false, save_nestlevel);
+
+	/* Restore userid and security context */
+	SetUserIdAndSecContext(save_userid, save_sec_context);
+
+	return PointerGetDatum(NULL);
+}
+
+/*
+ * rewrite_query_for_preupdate_state
+ *
+ * Rewrite the query so that base tables' RTEs will represent "pre-update"
+ * state of tables. This is necessary to calculate view delta after multiple
+ * tables are modified.
+ */
+static Query*
+rewrite_query_for_preupdate_state(Query *query, List *tables,
+								  ParseState *pstate, Oid matviewid)
+{
+	ListCell *lc;
+	int num_rte = list_length(query->rtable);
+	int i;
+
+
+	/* register delta ENRs */
+	register_delta_ENRs(pstate, query, tables);
+
+	/* XXX: Is necessary? Is this right timing? */
+	AcquireRewriteLocks(query, true, false);
+
+	i = 1;
+	foreach(lc, query->rtable)
+	{
+		RangeTblEntry *r = (RangeTblEntry*) lfirst(lc);
+
+		ListCell *lc2;
+		foreach(lc2, tables)
+		{
+			MV_TriggerTable *table = (MV_TriggerTable *) lfirst(lc2);
+			/*
+			 * if the modified table is found then replace the original RTE with
+			 * "pre-state" RTE and append its index to the list.
+			 */
+			if (r->relid == table->table_id)
+			{
+				List *securityQuals;
+				List *withCheckOptions;
+				bool  hasRowSecurity;
+				bool  hasSubLinks;
+
+				RangeTblEntry *rte_pre = get_prestate_rte(r, table, pstate->p_queryEnv, matviewid);
+
+				/*
+				 * Set a row security poslicies of the modified table to the subquery RTE which
+				 * represents the pre-update state of the table.
+				 */
+				get_row_security_policies(query, table->original_rte, i,
+										  &securityQuals, &withCheckOptions,
+										  &hasRowSecurity, &hasSubLinks);
+
+				if (hasRowSecurity)
+				{
+					query->hasRowSecurity = true;
+					rte_pre->security_barrier = true;
+				}
+				if (hasSubLinks)
+					query->hasSubLinks = true;
+
+				rte_pre->securityQuals = securityQuals;
+				lfirst(lc) = rte_pre;
+
+				table->rte_indexes = lappend_int(table->rte_indexes, i);
+				break;
+			}
+		}
+
+		/* finish the loop if we processed all RTE included in the original query */
+		if (i++ >= num_rte)
+			break;
+	}
+
+	return query;
+}
+
+/*
+ * register_delta_ENRs
+ *
+ * For all modified tables, make ENRs for their transition tables
+ * and register them to the queryEnv. ENR's RTEs are also appended
+ * into the list in query tree.
+ */
+static void
+register_delta_ENRs(ParseState *pstate, Query *query, List *tables)
+{
+	QueryEnvironment *queryEnv = pstate->p_queryEnv;
+	ListCell *lc;
+	RangeTblEntry	*rte;
+
+	foreach(lc, tables)
+	{
+		MV_TriggerTable *table = (MV_TriggerTable *) lfirst(lc);
+		ListCell *lc2;
+		int count;
+
+		count = 0;
+		foreach(lc2, table->old_tuplestores)
+		{
+			Tuplestorestate *oldtable = (Tuplestorestate *) lfirst(lc2);
+			EphemeralNamedRelation enr =
+				palloc(sizeof(EphemeralNamedRelationData));
+			ParseNamespaceItem *nsitem;
+
+			enr->md.name = make_delta_enr_name("old", table->table_id, count);
+			enr->md.reliddesc = table->table_id;
+			enr->md.tupdesc = NULL;
+			enr->md.enrtype = ENR_NAMED_TUPLESTORE;
+			enr->md.enrtuples = tuplestore_tuple_count(oldtable);
+			enr->reldata = oldtable;
+			register_ENR(queryEnv, enr);
+
+			nsitem = addRangeTableEntryForENR(pstate, makeRangeVar(NULL, enr->md.name, -1), true);
+			rte = nsitem->p_rte;
+
+			query->rtable = lappend(query->rtable, rte);
+
+			count++;
+		}
+
+		count = 0;
+		foreach(lc2, table->new_tuplestores)
+		{
+			Tuplestorestate *newtable = (Tuplestorestate *) lfirst(lc2);
+			EphemeralNamedRelation enr =
+				palloc(sizeof(EphemeralNamedRelationData));
+			ParseNamespaceItem *nsitem;
+
+			enr->md.name = make_delta_enr_name("new", table->table_id, count);
+			enr->md.reliddesc = table->table_id;
+			enr->md.tupdesc = NULL;
+			enr->md.enrtype = ENR_NAMED_TUPLESTORE;
+			enr->md.enrtuples = tuplestore_tuple_count(newtable);
+			enr->reldata = newtable;
+			register_ENR(queryEnv, enr);
+
+			nsitem = addRangeTableEntryForENR(pstate, makeRangeVar(NULL, enr->md.name, -1), true);
+			rte = nsitem->p_rte;
+
+			query->rtable = lappend(query->rtable, rte);
+
+			count++;
+		}
+	}
+}
+
+#define DatumGetItemPointer(X)	 ((ItemPointer) DatumGetPointer(X))
+#define PG_GETARG_ITEMPOINTER(n) DatumGetItemPointer(PG_GETARG_DATUM(n))
+
+/*
+ * ivm_visible_in_prestate
+ *
+ * Check visibility of a tuple specified by the tableoid and item pointer
+ * using the snapshot taken just before the table was modified.
+ */
+Datum
+ivm_visible_in_prestate(PG_FUNCTION_ARGS)
+{
+	Oid			tableoid = PG_GETARG_OID(0);
+	ItemPointer itemPtr = PG_GETARG_ITEMPOINTER(1);
+	Oid			matviewOid = PG_GETARG_OID(2);
+	MV_TriggerHashEntry *entry;
+	MV_TriggerTable		*table = NULL;
+	ListCell   *lc;
+	bool	found;
+	bool	result;
+
+	if (!in_delta_calculation)
+		ereport(ERROR,
+				(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+				 errmsg("ivm_visible_in_prestate can be called only in delta calculation")));
+
+	entry = (MV_TriggerHashEntry *) hash_search(mv_trigger_info,
+											  (void *) &matviewOid,
+											  HASH_FIND, &found);
+	Assert (found && entry != NULL);
+
+	foreach(lc, entry->tables)
+	{
+		table = (MV_TriggerTable *) lfirst(lc);
+		if (table->table_id == tableoid)
+			break;
+	}
+
+	Assert (table != NULL);
+
+	result = table_tuple_fetch_row_version(table->rel, itemPtr, entry->snapshot, table->slot);
+
+	PG_RETURN_BOOL(result);
+}
+
+/*
+ * get_prestate_rte
+ *
+ * Rewrite RTE of the modified table to a subquery which represents
+ * "pre-state" table. The original RTE is saved in table->rte_original.
+ */
+static RangeTblEntry*
+get_prestate_rte(RangeTblEntry *rte, MV_TriggerTable *table,
+				 QueryEnvironment *queryEnv, Oid matviewid)
+{
+	StringInfoData str;
+	RawStmt *raw;
+	Query *subquery;
+	Relation rel;
+	ParseState *pstate;
+	char *relname;
+	int i;
+
+	pstate = make_parsestate(NULL);
+	pstate->p_queryEnv = queryEnv;
+	pstate->p_expr_kind = EXPR_KIND_SELECT_TARGET;
+
+	/*
+	 * We can use NoLock here since AcquireRewriteLocks should
+	 * have locked the relation already.
+	 */
+	rel = table_open(table->table_id, NoLock);
+	relname = quote_qualified_identifier(
+					get_namespace_name(RelationGetNamespace(rel)),
+									   RelationGetRelationName(rel));
+	table_close(rel, NoLock);
+
+	/*
+	 * Filtering inserted row using the snapshot taken before the table
+	 * is modified. ctid is required for maintaining outer join views.
+	 */
+	initStringInfo(&str);
+	appendStringInfo(&str,
+		"SELECT t.* FROM %s t"
+		" WHERE pg_catalog.ivm_visible_in_prestate(t.tableoid, t.ctid ,%d::pg_catalog.oid)",
+			relname, matviewid);
+
+	/*
+	 * Append deleted rows contained in old transition tables.
+	 */
+	for (i = 0; i < list_length(table->old_tuplestores); i++)
+	{
+		appendStringInfo(&str, " UNION ALL ");
+		appendStringInfo(&str," SELECT * FROM %s",
+			make_delta_enr_name("old", table->table_id, i));
+	}
+
+	/* Get a subquery representing pre-state of the table */
+	raw = (RawStmt*)linitial(raw_parser(str.data, RAW_PARSE_DEFAULT));
+	subquery = transformStmt(pstate, raw->stmt);
+
+	/* save the original RTE */
+	table->original_rte = copyObject(rte);
+
+	rte->rtekind = RTE_SUBQUERY;
+	rte->subquery = subquery;
+	rte->security_barrier = false;
+
+	/* Clear fields that should not be set in a subquery RTE */
+	rte->relid = InvalidOid;
+	rte->relkind = 0;
+	rte->rellockmode = 0;
+	rte->tablesample = NULL;
+	rte->perminfoindex = 0;         /* no permission checking for this RTE */
+	rte->inh = false;			/* must not be set for a subquery */
+
+	return rte;
+}
+
+/*
+ * make_delta_enr_name
+ *
+ * Make a name for ENR of a transition table from the base table's oid.
+ * prefix will be "new" or "old" depending on its transition table kind..
+ */
+static char*
+make_delta_enr_name(const char *prefix, Oid relid, int count)
+{
+	char buf[NAMEDATALEN];
+	char *name;
+
+	snprintf(buf, NAMEDATALEN, "__ivm_%s_%u_%u", prefix, relid, count);
+	name = pstrdup(buf);
+
+	return name;
+}
+
+/*
+ * replace_rte_with_delta
+ *
+ * Replace RTE of the modified table with a single table delta that combine its
+ * all transition tables.
+ */
+static RangeTblEntry*
+replace_rte_with_delta(RangeTblEntry *rte, MV_TriggerTable *table, bool is_new,
+					   QueryEnvironment *queryEnv)
+{
+	Oid relid = table->table_id;
+	StringInfoData str;
+	ParseState	*pstate;
+	RawStmt *raw;
+	Query *sub;
+	int		num_tuplestores = list_length(is_new ? table->new_tuplestores : table->old_tuplestores);
+	int		i;
+
+	/* the previous RTE must be a subquery which represents "pre-state" table */
+	Assert(rte->rtekind == RTE_SUBQUERY);
+
+	/* Create a ParseState for rewriting the view definition query */
+	pstate = make_parsestate(NULL);
+	pstate->p_queryEnv = queryEnv;
+	pstate->p_expr_kind = EXPR_KIND_SELECT_TARGET;
+
+	initStringInfo(&str);
+
+	for (i = 0; i < num_tuplestores; i++)
+	{
+		if (i > 0)
+			appendStringInfo(&str, " UNION ALL ");
+
+		appendStringInfo(&str,
+			" SELECT * FROM %s",
+			make_delta_enr_name(is_new ? "new" : "old", relid, i));
+	}
+
+	raw = (RawStmt*)linitial(raw_parser(str.data, RAW_PARSE_DEFAULT));
+	sub = transformStmt(pstate, raw->stmt);
+
+	/*
+	 * Update the subquery so that it represent the combined transition
+	 * table.  Note that we leave the security_barrier and securityQuals
+	 * fields so that the subquery relation can be protected by the RLS
+	 * policy as same as the modified table.
+	 */
+	rte->rtekind = RTE_SUBQUERY;
+	rte->subquery = sub;
+
+	return rte;
+}
+
+/*
+ * rewrite_query_for_counting
+ *
+ * Rewrite query for counting duplicated tuples.
+ */
+static Query *
+rewrite_query_for_counting(Query *query, ParseState *pstate)
+{
+	TargetEntry *tle_count;
+	FuncCall *fn;
+	Node *node;
+
+	/* Add count(*) for counting distinct tuples in views */
+	fn = makeFuncCall(SystemFuncName("count"), NIL, COERCE_EXPLICIT_CALL, -1);
+	fn->agg_star = true;
+	if (!query->groupClause && !query->hasAggs)
+		query->groupClause = transformDistinctClause(NULL, &query->targetList, query->sortClause, false);
+
+	node = ParseFuncOrColumn(pstate, fn->funcname, NIL, NULL, fn, false, -1);
+
+	tle_count = makeTargetEntry((Expr *) node,
+								list_length(query->targetList) + 1,
+								pstrdup("__ivm_count__"),
+								false);
+	query->targetList = lappend(query->targetList, tle_count);
+	query->hasAggs = true;
+
+	return query;
+}
+
+/*
+ * calc_delta
+ *
+ * Calculate view deltas generated under the modification of a table specified
+ * by the RTE index.
+ */
+static void
+calc_delta(MV_TriggerTable *table, int rte_index, Query *query,
+			DestReceiver *dest_old, DestReceiver *dest_new,
+			TupleDesc *tupdesc_old, TupleDesc *tupdesc_new,
+			QueryEnvironment *queryEnv)
+{
+	ListCell *lc = list_nth_cell(query->rtable, rte_index - 1);
+	RangeTblEntry *rte = (RangeTblEntry *) lfirst(lc);
+
+	in_delta_calculation = true;
+
+	/* Generate old delta */
+	if (list_length(table->old_tuplestores) > 0)
+	{
+		/* Replace the modified table with the old delta table and calculate the old view delta. */
+		replace_rte_with_delta(rte, table, false, queryEnv);
+		refresh_matview_datafill(dest_old, query, queryEnv, tupdesc_old, "");
+	}
+
+	/* Generate new delta */
+	if (list_length(table->new_tuplestores) > 0)
+	{
+		/* Replace the modified table with the new delta table and calculate the new view delta*/
+		replace_rte_with_delta(rte, table, true, queryEnv);
+		refresh_matview_datafill(dest_new, query, queryEnv, tupdesc_new, "");
+	}
+
+	in_delta_calculation = false;
+}
+
+/*
+ * rewrite_query_for_postupdate_state
+ *
+ * Rewrite the query so that the specified base table's RTEs will represent
+ * "post-update" state of tables. This is called after the view delta
+ * calculation due to changes on this table finishes.
+ */
+static Query*
+rewrite_query_for_postupdate_state(Query *query, MV_TriggerTable *table, int rte_index)
+{
+	ListCell *lc = list_nth_cell(query->rtable, rte_index - 1);
+
+	/* Retore the original RTE */
+	lfirst(lc) = table->original_rte;
+
+	return query;
+}
+
+/*
+ * apply_delta
+ *
+ * Apply deltas to the materialized view. In outer join cases, this requires
+ * the view maintenance graph.
+ */
+static void
+apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *new_tuplestores,
+			TupleDesc tupdesc_old, TupleDesc tupdesc_new,
+			Query *query)
+{
+	StringInfoData querybuf;
+	StringInfoData target_list_buf;
+	Relation	matviewRel;
+	char	   *matviewname;
+	ListCell	*lc;
+	int			i;
+	List	   *keys = NIL;
+
+
+	/*
+	 * get names of the materialized view and delta tables
+	 */
+
+	matviewRel = table_open(matviewOid, NoLock);
+	matviewname = quote_qualified_identifier(get_namespace_name(RelationGetNamespace(matviewRel)),
+											 RelationGetRelationName(matviewRel));
+
+	/*
+	 * Build parts of the maintenance queries
+	 */
+
+	initStringInfo(&querybuf);
+	initStringInfo(&target_list_buf);
+
+	/* build string of target list */
+	for (i = 0; i < matviewRel->rd_att->natts; i++)
+	{
+		Form_pg_attribute attr = TupleDescAttr(matviewRel->rd_att, i);
+		char   *resname = NameStr(attr->attname);
+
+		if (i != 0)
+			appendStringInfo(&target_list_buf, ", ");
+		appendStringInfo(&target_list_buf, "%s", quote_qualified_identifier(NULL, resname));
+	}
+
+	i = 0;
+	foreach (lc, query->targetList)
+	{
+		TargetEntry *tle = (TargetEntry *) lfirst(lc);
+		Form_pg_attribute attr = TupleDescAttr(matviewRel->rd_att, i);
+
+		i++;
+
+		if (tle->resjunk)
+			continue;
+
+		keys = lappend(keys, attr);
+	}
+
+	/* Start maintaining the materialized view. */
+	OpenMatViewIncrementalMaintenance();
+
+	/* Open SPI context. */
+	if (SPI_connect() != SPI_OK_CONNECT)
+		elog(ERROR, "SPI_connect failed");
+
+	/* For tuple deletion */
+	if (old_tuplestores && tuplestore_tuple_count(old_tuplestores) > 0)
+	{
+		EphemeralNamedRelation enr = palloc(sizeof(EphemeralNamedRelationData));
+		int				rc;
+
+		/* convert tuplestores to ENR, and register for SPI */
+		enr->md.name = pstrdup(OLD_DELTA_ENRNAME);
+		enr->md.reliddesc = InvalidOid;
+		enr->md.tupdesc = tupdesc_old;
+		enr->md.enrtype = ENR_NAMED_TUPLESTORE;
+		enr->md.enrtuples = tuplestore_tuple_count(old_tuplestores);
+		enr->reldata = old_tuplestores;
+
+		rc = SPI_register_relation(enr);
+		if (rc != SPI_OK_REL_REGISTER)
+			elog(ERROR, "SPI_register failed");
+
+		apply_old_delta(matviewname, OLD_DELTA_ENRNAME, keys);
+
+	}
+	/* For tuple insertion */
+	if (new_tuplestores && tuplestore_tuple_count(new_tuplestores) > 0)
+	{
+		EphemeralNamedRelation enr = palloc(sizeof(EphemeralNamedRelationData));
+		int rc;
+
+		/* convert tuplestores to ENR, and register for SPI */
+		enr->md.name = pstrdup(NEW_DELTA_ENRNAME);
+		enr->md.reliddesc = InvalidOid;
+		enr->md.tupdesc = tupdesc_new;;
+		enr->md.enrtype = ENR_NAMED_TUPLESTORE;
+		enr->md.enrtuples = tuplestore_tuple_count(new_tuplestores);
+		enr->reldata = new_tuplestores;
+
+		rc = SPI_register_relation(enr);
+		if (rc != SPI_OK_REL_REGISTER)
+			elog(ERROR, "SPI_register failed");
+
+		/* apply new delta */
+		apply_new_delta(matviewname, NEW_DELTA_ENRNAME, &target_list_buf);
+	}
+
+	/* We're done maintaining the materialized view. */
+	CloseMatViewIncrementalMaintenance();
+
+	table_close(matviewRel, NoLock);
+
+	/* Close SPI context. */
+	if (SPI_finish() != SPI_OK_FINISH)
+		elog(ERROR, "SPI_finish failed");
+}
+
+/*
+ * apply_old_delta
+ *
+ * Execute a query for applying a delta table given by deltname_old
+ * which contains tuples to be deleted from to a materialized view given by
+ * matviewname.  This is used when counting is not required.
+ */
+static void
+apply_old_delta(const char *matviewname, const char *deltaname_old,
+				List *keys)
+{
+	StringInfoData	querybuf;
+	StringInfoData	keysbuf;
+	char   *match_cond;
+	ListCell *lc;
+
+	/* build WHERE condition for searching tuples to be deleted */
+	match_cond = get_matching_condition_string(keys);
+
+	/* build string of keys list */
+	initStringInfo(&keysbuf);
+	foreach (lc, keys)
+	{
+		Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc);
+		char   *resname = NameStr(attr->attname);
+		appendStringInfo(&keysbuf, "%s", quote_qualified_identifier("mv", resname));
+		if (lnext(keys, lc))
+			appendStringInfo(&keysbuf, ", ");
+	}
+
+	/* Search for matching tuples from the view and update or delete if found. */
+	initStringInfo(&querybuf);
+	appendStringInfo(&querybuf,
+	"DELETE FROM %s WHERE ctid IN ("
+		"SELECT tid FROM (SELECT pg_catalog.row_number() over (partition by %s) AS \"__ivm_row_number__\","
+								  "mv.ctid AS tid,"
+								  "diff.\"__ivm_count__\""
+						 "FROM %s AS mv, %s AS diff "
+						 "WHERE %s) v "
+					"WHERE v.\"__ivm_row_number__\" OPERATOR(pg_catalog.<=) v.\"__ivm_count__\")",
+					matviewname,
+					keysbuf.data,
+					matviewname, deltaname_old,
+					match_cond);
+
+	if (SPI_exec(querybuf.data, 0) != SPI_OK_DELETE)
+		elog(ERROR, "SPI_exec failed: %s", querybuf.data);
+}
+
+/*
+ * apply_new_delta
+ *
+ * Execute a query for applying a delta table given by deltname_new
+ * which contains tuples to be inserted into a materialized view given by
+ * matviewname.  This is used when counting is not required.
+ */
+static void
+apply_new_delta(const char *matviewname, const char *deltaname_new,
+				StringInfo target_list)
+{
+	StringInfoData	querybuf;
+
+	/* Search for matching tuples from the view and update or delete if found. */
+	initStringInfo(&querybuf);
+	appendStringInfo(&querybuf,
+					"INSERT INTO %s (%s) SELECT %s FROM ("
+						"SELECT diff.*, pg_catalog.generate_series(1, diff.\"__ivm_count__\")"
+							" AS __ivm_generate_series__ "
+						"FROM %s AS diff) AS v",
+					matviewname, target_list->data, target_list->data,
+					deltaname_new);
+
+	if (SPI_exec(querybuf.data, 0) != SPI_OK_INSERT)
+		elog(ERROR, "SPI_exec failed: %s", querybuf.data);
+}
+
+/*
+ * get_matching_condition_string
+ *
+ * Build a predicate string for looking for a tuple with given keys.
+ */
+static char *
+get_matching_condition_string(List *keys)
+{
+	StringInfoData match_cond;
+	ListCell	*lc;
+
+	/* If there is no key columns, the condition is always true. */
+	if (keys == NIL)
+		return "true";
+
+	initStringInfo(&match_cond);
+	foreach (lc, keys)
+	{
+		Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc);
+		char   *resname = NameStr(attr->attname);
+		char   *mv_resname = quote_qualified_identifier("mv", resname);
+		char   *diff_resname = quote_qualified_identifier("diff", resname);
+		Oid		typid = attr->atttypid;
+
+		/* Considering NULL values, we can not use simple = operator. */
+		appendStringInfo(&match_cond, "(");
+		generate_equal(&match_cond, typid, mv_resname, diff_resname);
+		appendStringInfo(&match_cond, " OR (%s IS NULL AND %s IS NULL))",
+						 mv_resname, diff_resname);
+
+		if (lnext(keys, lc))
+			appendStringInfo(&match_cond, " AND ");
+	}
+
+	return match_cond.data;
+}
+
+/*
+ * generate_equals
+ *
+ * Generate an equality clause using given operands' default equality
+ * operator.
+ */
+static void
+generate_equal(StringInfo querybuf, Oid opttype,
+			   const char *leftop, const char *rightop)
+{
+	TypeCacheEntry *typentry;
+
+	typentry = lookup_type_cache(opttype, TYPECACHE_EQ_OPR);
+	if (!OidIsValid(typentry->eq_opr))
+		ereport(ERROR,
+				(errcode(ERRCODE_UNDEFINED_FUNCTION),
+				 errmsg("could not identify an equality operator for type %s",
+						format_type_be_qualified(opttype))));
+
+	generate_operator_clause(querybuf,
+							 leftop, opttype,
+							 typentry->eq_opr,
+							 rightop, opttype);
+}
+
+/*
+ * mv_InitHashTables
+ */
+static void
+mv_InitHashTables(void)
+{
+	HASHCTL		ctl;
+
+	memset(&ctl, 0, sizeof(ctl));
+	ctl.keysize = sizeof(Oid);
+	ctl.entrysize = sizeof(MV_TriggerHashEntry);
+	mv_trigger_info = hash_create("MV trigger info",
+								 MV_INIT_QUERYHASHSIZE,
+								 &ctl, HASH_ELEM | HASH_BLOBS);
+}
+
+/*
+ * AtAbort_IVM
+ *
+ * Clean up hash entries for all materialized views. This is called at
+ * transaction abort.
+ */
+void
+AtAbort_IVM()
+{
+	HASH_SEQ_STATUS seq;
+	MV_TriggerHashEntry *entry;
+
+	if (mv_trigger_info)
+	{
+		hash_seq_init(&seq, mv_trigger_info);
+		while ((entry = hash_seq_search(&seq)) != NULL)
+			clean_up_IVM_hash_entry(entry, true);
+	}
+	in_delta_calculation = false;
+}
+
+/*
+ * clean_up_IVM_hash_entry
+ *
+ * Clean up tuple stores and hash entries for a materialized view after its
+ * maintenance finished.
+ */
+static void
+clean_up_IVM_hash_entry(MV_TriggerHashEntry *entry, bool is_abort)
+{
+	bool found;
+	ListCell *lc;
+
+	foreach(lc, entry->tables)
+	{
+		MV_TriggerTable *table = (MV_TriggerTable *) lfirst(lc);
+
+		list_free(table->old_tuplestores);
+		list_free(table->new_tuplestores);
+		if (!is_abort)
+		{
+			ExecDropSingleTupleTableSlot(table->slot);
+			table_close(table->rel, NoLock);
+		}
+	}
+	list_free(entry->tables);
+
+	if (!is_abort)
+		UnregisterSnapshot(entry->snapshot);
+
+	hash_search(mv_trigger_info, (void *) &entry->matview_id, HASH_REMOVE, &found);
+}
+
+/*
+ * isIvmName
+ *
+ * Check if this is a IVM hidden column from the name.
+ */
+bool
+isIvmName(const char *s)
+{
+	if (s)
+		return (strncmp(s, "__ivm_", 6) == 0);
+	return false;
+}
diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat
index 9c120fc2b7..e111f11bf5 100644
--- a/src/include/catalog/pg_proc.dat
+++ b/src/include/catalog/pg_proc.dat
@@ -12174,4 +12174,14 @@
   proargtypes => 'int2',
   prosrc => 'gist_stratnum_identity' },
 
+# IVM
+{ oid => '786', descr => 'ivm trigger (before)',
+  proname => 'IVM_immediate_before', provolatile => 'v', prorettype => 'trigger',
+  proargtypes => '', prosrc => 'IVM_immediate_before' },
+{ oid => '787', descr => 'ivm trigger (after)',
+  proname => 'IVM_immediate_maintenance', provolatile => 'v', prorettype => 'trigger',
+  proargtypes => '', prosrc => 'IVM_immediate_maintenance' },
+{ oid => '788', descr => 'ivm filetring ',
+  proname => 'ivm_visible_in_prestate', provolatile => 's', prorettype => 'bool',
+  proargtypes => 'oid tid oid', prosrc => 'ivm_visible_in_prestate' },
 ]
diff --git a/src/include/commands/createas.h b/src/include/commands/createas.h
index 94678e3834..396ad1bb4c 100644
--- a/src/include/commands/createas.h
+++ b/src/include/commands/createas.h
@@ -16,6 +16,7 @@
 
 #include "catalog/objectaddress.h"
 #include "nodes/params.h"
+#include "nodes/pathnodes.h"
 #include "parser/parse_node.h"
 #include "tcop/dest.h"
 #include "utils/queryenvironment.h"
@@ -25,6 +26,9 @@ extern ObjectAddress ExecCreateTableAs(ParseState *pstate, CreateTableAsStmt *st
 									   ParamListInfo params, QueryEnvironment *queryEnv,
 									   QueryCompletion *qc);
 
+extern void CreateIvmTriggersOnBaseTables(Query *qry, Oid matviewOid);
+extern void CreateIndexOnIMMV(Query *query, Relation matviewRel);
+
 extern int	GetIntoRelEFlags(IntoClause *intoClause);
 
 extern DestReceiver *CreateIntoRelDestReceiver(IntoClause *intoClause);
diff --git a/src/include/commands/matview.h b/src/include/commands/matview.h
index 817b2ba0b6..3257e1adff 100644
--- a/src/include/commands/matview.h
+++ b/src/include/commands/matview.h
@@ -15,6 +15,7 @@
 #define MATVIEW_H
 
 #include "catalog/objectaddress.h"
+#include "fmgr.h"
 #include "nodes/params.h"
 #include "nodes/parsenodes.h"
 #include "tcop/dest.h"
@@ -23,6 +24,8 @@
 
 extern void SetMatViewPopulatedState(Relation relation, bool newstate);
 
+extern void SetMatViewIVMState(Relation relation, bool newstate);
+
 extern ObjectAddress ExecRefreshMatView(RefreshMatViewStmt *stmt, const char *queryString,
 										ParamListInfo params, QueryCompletion *qc);
 
@@ -30,4 +33,10 @@ extern DestReceiver *CreateTransientRelDestReceiver(Oid transientoid);
 
 extern bool MatViewIncrementalMaintenanceIsEnabled(void);
 
+extern Datum IVM_immediate_before(PG_FUNCTION_ARGS);
+extern Datum IVM_immediate_maintenance(PG_FUNCTION_ARGS);
+extern Datum IVM_visible_in_prestate(PG_FUNCTION_ARGS);
+extern void AtAbort_IVM(void);
+extern bool isIvmName(const char *s);
+
 #endif							/* MATVIEW_H */
-- 
2.25.1


--Multipart=_Mon__4_Mar_2024_11_58_46_+0900_UaponF/qQhQrVCFt
Content-Type: text/x-diff;
 name="v30-0007-Add-DISTINCT-support-for-IVM.patch"
Content-Disposition: attachment;
 filename="v30-0007-Add-DISTINCT-support-for-IVM.patch"
Content-Transfer-Encoding: 7bit



^ permalink  raw  reply  [nested|flat] 101+ messages in thread

* [PATCH v29 06/11] Add Incremental View Maintenance support
@ 2023-05-31 09:59  Yugo Nagata <[email protected]>
  0 siblings, 0 replies; 101+ messages in thread

From: Yugo Nagata @ 2023-05-31 09:59 UTC (permalink / raw)

In this implementation, AFTER triggers are used to collect
tuplestores containing transition table contents. When multiple tables
are changed, multiple AFTER triggers are invoked, then the final AFTER
trigger performs actual update of the matview. In addition, BEFORE
triggers are also used to handle global information for view
maintenance.

To calculate view deltas, we need both pre-state and post-state of base
tables. Post-update states are available in AFTER trigger, and pre-update
states can be calculated by removing inserted tuples and appending deleted
tuples. Insterted tuples are filtered using the snapshot taken before
table modiication, and deleted tuples are contained in the old transition
table.

Incrementally Maintainable Materialized Views (IMMV) can contain
duplicated tuples.

This patch also allows self-join, simultaneous updates of more than
one base table, and multiple updates of the same base table.
---
 src/backend/access/transam/xact.c |    5 +
 src/backend/commands/createas.c   |  680 +++++++++++++
 src/backend/commands/matview.c    | 1466 ++++++++++++++++++++++++++++-
 src/include/catalog/pg_proc.dat   |   10 +
 src/include/commands/createas.h   |    4 +
 src/include/commands/matview.h    |    9 +
 6 files changed, 2139 insertions(+), 35 deletions(-)

diff --git a/src/backend/access/transam/xact.c b/src/backend/access/transam/xact.c
index 8daaa535ed..cd280bdffd 100644
--- a/src/backend/access/transam/xact.c
+++ b/src/backend/access/transam/xact.c
@@ -36,6 +36,7 @@
 #include "catalog/pg_enum.h"
 #include "catalog/storage.h"
 #include "commands/async.h"
+#include "commands/matview.h"
 #include "commands/tablecmds.h"
 #include "commands/trigger.h"
 #include "common/pg_prng.h"
@@ -2803,6 +2804,7 @@ AbortTransaction(void)
 	AtAbort_Notify();
 	AtEOXact_RelationMap(false, is_parallel_worker);
 	AtAbort_Twophase();
+	AtAbort_IVM();
 
 	/*
 	 * Advertise the fact that we aborted in pg_xact (assuming that we got as
@@ -5080,6 +5082,9 @@ AbortSubTransaction(void)
 	pgstat_progress_end_command();
 	UnlockBuffers();
 
+	/* Clean up hash entries for incremental view maintenance */
+	AtAbort_IVM();
+
 	/* Reset WAL record construction state */
 	XLogResetInsertion();
 
diff --git a/src/backend/commands/createas.c b/src/backend/commands/createas.c
index e91920ca14..415f110516 100644
--- a/src/backend/commands/createas.c
+++ b/src/backend/commands/createas.c
@@ -32,15 +32,26 @@
 #include "access/xact.h"
 #include "access/xlog.h"
 #include "catalog/namespace.h"
+#include "catalog/index.h"
+#include "catalog/pg_constraint.h"
+#include "catalog/pg_inherits.h"
+#include "catalog/pg_trigger.h"
 #include "catalog/toasting.h"
 #include "commands/createas.h"
+#include "commands/defrem.h"
 #include "commands/matview.h"
 #include "commands/prepare.h"
 #include "commands/tablecmds.h"
+#include "commands/tablespace.h"
+#include "commands/trigger.h"
 #include "commands/view.h"
 #include "miscadmin.h"
+#include "optimizer/optimizer.h"
+#include "optimizer/prep.h"
 #include "nodes/makefuncs.h"
 #include "nodes/nodeFuncs.h"
+#include "parser/parser.h"
+#include "parser/parsetree.h"
 #include "parser/parse_clause.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/smgr.h"
@@ -73,6 +84,12 @@ static bool intorel_receive(TupleTableSlot *slot, DestReceiver *self);
 static void intorel_shutdown(DestReceiver *self);
 static void intorel_destroy(DestReceiver *self);
 
+static void CreateIvmTriggersOnBaseTablesRecurse(Query *qry, Node *node, Oid matviewOid,
+									 Relids *relids, bool ex_lock);
+static void CreateIvmTrigger(Oid relOid, Oid viewOid, int16 type, int16 timing, bool ex_lock);
+static void check_ivm_restriction(Node *node);
+static bool check_ivm_restriction_walker(Node *node, void *context);
+static Bitmapset *get_primary_key_attnos_from_query(Query *query, List **constraintList);
 
 /*
  * create_ctas_internal
@@ -282,6 +299,18 @@ ExecCreateTableAs(ParseState *pstate, CreateTableAsStmt *stmt,
 		save_nestlevel = NewGUCNestLevel();
 	}
 
+	if (is_matview && into->ivm)
+	{
+		/* check if the query is supported in IMMV definition */
+		if (contain_mutable_functions((Node *) query))
+			ereport(ERROR,
+					(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+					 errmsg("mutable function is not supported on incrementally maintainable materialized view"),
+					 errhint("functions must be marked IMMUTABLE")));
+
+		check_ivm_restriction((Node *) query);
+	}
+
 	if (into->skipData)
 	{
 		/*
@@ -358,6 +387,27 @@ ExecCreateTableAs(ParseState *pstate, CreateTableAsStmt *stmt,
 
 		/* Restore userid and security context */
 		SetUserIdAndSecContext(save_userid, save_sec_context);
+
+		if (into->ivm)
+		{
+			Oid matviewOid = address.objectId;
+			Relation matviewRel = table_open(matviewOid, NoLock);
+
+			/*
+			 * Mark relisivm field, if it's a matview and into->ivm is true.
+			 */
+			SetMatViewIVMState(matviewRel, true);
+
+			if (!into->skipData)
+			{
+				/* Create an index on incremental maintainable materialized view, if possible */
+				CreateIndexOnIMMV((Query *) into->viewQuery, matviewRel);
+
+				/* Create triggers on incremental maintainable materialized view */
+				CreateIvmTriggersOnBaseTables((Query *) into->viewQuery, matviewOid);
+			}
+			table_close(matviewRel, NoLock);
+		}
 	}
 
 	return address;
@@ -635,3 +685,633 @@ intorel_destroy(DestReceiver *self)
 {
 	pfree(self);
 }
+
+/*
+ * CreateIvmTriggersOnBaseTables -- create IVM triggers on all base tables
+ */
+void
+CreateIvmTriggersOnBaseTables(Query *qry, Oid matviewOid)
+{
+	Relids	relids = NULL;
+	bool	ex_lock = false;
+	RangeTblEntry *rte;
+
+	/* Immediately return if we don't have any base tables. */
+	if (list_length(qry->rtable) < 1)
+		return;
+
+	/*
+	 * If the view has more than one base tables, we need an exclusive lock
+	 * on the view so that the view would be maintained serially to avoid
+	 * the inconsistency that occurs when two base tables are modified in
+	 * concurrent transactions. However, if the view has only one table,
+	 * we can use a weaker lock.
+	 *
+	 * The type of lock should be determined here, because if we check the
+	 * view definition at maintenance time, we need to acquire a weaker lock,
+	 * and upgrading the lock level after this increases probability of
+	 * deadlock.
+	 */
+
+	rte = list_nth(qry->rtable, 0);
+	if (list_length(qry->rtable) > 1 || rte->rtekind != RTE_RELATION)
+		ex_lock = true;
+
+	CreateIvmTriggersOnBaseTablesRecurse(qry, (Node *)qry, matviewOid, &relids, ex_lock);
+
+	bms_free(relids);
+}
+
+static void
+CreateIvmTriggersOnBaseTablesRecurse(Query *qry, Node *node, Oid matviewOid,
+									 Relids *relids, bool ex_lock)
+{
+	if (node == NULL)
+		return;
+
+	/* This can recurse, so check for excessive recursion */
+	check_stack_depth();
+
+	switch (nodeTag(node))
+	{
+		case T_Query:
+			{
+				Query *query = (Query *) node;
+
+				CreateIvmTriggersOnBaseTablesRecurse(qry, (Node *)query->jointree, matviewOid, relids, ex_lock);
+			}
+			break;
+
+		case T_RangeTblRef:
+			{
+				int			rti = ((RangeTblRef *) node)->rtindex;
+				RangeTblEntry *rte = rt_fetch(rti, qry->rtable);
+
+				if (rte->rtekind == RTE_RELATION && !bms_is_member(rte->relid, *relids))
+				{
+					CreateIvmTrigger(rte->relid, matviewOid, TRIGGER_TYPE_INSERT, TRIGGER_TYPE_BEFORE, ex_lock);
+					CreateIvmTrigger(rte->relid, matviewOid, TRIGGER_TYPE_DELETE, TRIGGER_TYPE_BEFORE, ex_lock);
+					CreateIvmTrigger(rte->relid, matviewOid, TRIGGER_TYPE_UPDATE, TRIGGER_TYPE_BEFORE, ex_lock);
+					CreateIvmTrigger(rte->relid, matviewOid, TRIGGER_TYPE_TRUNCATE, TRIGGER_TYPE_BEFORE, true);
+					CreateIvmTrigger(rte->relid, matviewOid, TRIGGER_TYPE_INSERT, TRIGGER_TYPE_AFTER, ex_lock);
+					CreateIvmTrigger(rte->relid, matviewOid, TRIGGER_TYPE_DELETE, TRIGGER_TYPE_AFTER, ex_lock);
+					CreateIvmTrigger(rte->relid, matviewOid, TRIGGER_TYPE_UPDATE, TRIGGER_TYPE_AFTER, ex_lock);
+					CreateIvmTrigger(rte->relid, matviewOid, TRIGGER_TYPE_TRUNCATE, TRIGGER_TYPE_AFTER, true);
+
+					*relids = bms_add_member(*relids, rte->relid);
+				}
+			}
+			break;
+
+		case T_FromExpr:
+			{
+				FromExpr   *f = (FromExpr *) node;
+				ListCell   *l;
+
+				foreach(l, f->fromlist)
+					CreateIvmTriggersOnBaseTablesRecurse(qry, lfirst(l), matviewOid, relids, ex_lock);
+			}
+			break;
+
+		case T_JoinExpr:
+			{
+				JoinExpr   *j = (JoinExpr *) node;
+
+				CreateIvmTriggersOnBaseTablesRecurse(qry, j->larg, matviewOid, relids, ex_lock);
+				CreateIvmTriggersOnBaseTablesRecurse(qry, j->rarg, matviewOid, relids, ex_lock);
+			}
+			break;
+
+		default:
+			elog(ERROR, "unrecognized node type: %d", (int) nodeTag(node));
+	}
+}
+
+/*
+ * CreateIvmTrigger -- create IVM trigger on a base table
+ */
+static void
+CreateIvmTrigger(Oid relOid, Oid viewOid, int16 type, int16 timing, bool ex_lock)
+{
+	ObjectAddress	refaddr;
+	ObjectAddress	address;
+	CreateTrigStmt *ivm_trigger;
+	List *transitionRels = NIL;
+
+	Assert(timing == TRIGGER_TYPE_BEFORE || timing == TRIGGER_TYPE_AFTER);
+
+	refaddr.classId = RelationRelationId;
+	refaddr.objectId = viewOid;
+	refaddr.objectSubId = 0;
+
+	ivm_trigger = makeNode(CreateTrigStmt);
+	ivm_trigger->relation = NULL;
+	ivm_trigger->row = false;
+
+	ivm_trigger->timing = timing;
+	ivm_trigger->events = type;
+
+	switch (type)
+	{
+		case TRIGGER_TYPE_INSERT:
+			ivm_trigger->trigname = (timing == TRIGGER_TYPE_BEFORE ? "IVM_trigger_ins_before" : "IVM_trigger_ins_after");
+			break;
+		case TRIGGER_TYPE_DELETE:
+			ivm_trigger->trigname = (timing == TRIGGER_TYPE_BEFORE ? "IVM_trigger_del_before" : "IVM_trigger_del_after");
+			break;
+		case TRIGGER_TYPE_UPDATE:
+			ivm_trigger->trigname = (timing == TRIGGER_TYPE_BEFORE ? "IVM_trigger_upd_before" : "IVM_trigger_upd_after");
+			break;
+		case TRIGGER_TYPE_TRUNCATE:
+			ivm_trigger->trigname = (timing == TRIGGER_TYPE_BEFORE ? "IVM_trigger_truncate_before" : "IVM_trigger_truncate_after");
+			break;
+		default:
+			elog(ERROR, "unsupported trigger type");
+	}
+
+	if (timing == TRIGGER_TYPE_AFTER)
+	{
+		if (type == TRIGGER_TYPE_INSERT || type == TRIGGER_TYPE_UPDATE)
+		{
+			TriggerTransition *n = makeNode(TriggerTransition);
+			n->name = "__ivm_newtable";
+			n->isNew = true;
+			n->isTable = true;
+
+			transitionRels = lappend(transitionRels, n);
+		}
+		if (type == TRIGGER_TYPE_DELETE || type == TRIGGER_TYPE_UPDATE)
+		{
+			TriggerTransition *n = makeNode(TriggerTransition);
+			n->name = "__ivm_oldtable";
+			n->isNew = false;
+			n->isTable = true;
+
+			transitionRels = lappend(transitionRels, n);
+		}
+	}
+
+	/*
+	 * XXX: When using DELETE or UPDATE, we must use exclusive lock for now
+	 * because apply_old_delta(_with_count) uses ctid to identify the tuple
+	 * to be deleted/deleted, but doesn't work in concurrent situations.
+	 *
+	 * If the view doesn't have aggregate, distinct, or tuple duplicate,
+	 * then it would work even in concurrent situations. However, we don't have
+	 * any way to guarantee the view has a unique key before opening the IMMV
+	 * at the maintenance time because users may drop the unique index.
+	 */
+
+	if (type == TRIGGER_TYPE_DELETE || type == TRIGGER_TYPE_UPDATE)
+		ex_lock = true;
+
+	ivm_trigger->funcname =
+		(timing == TRIGGER_TYPE_BEFORE ? SystemFuncName("IVM_immediate_before") : SystemFuncName("IVM_immediate_maintenance"));
+
+	ivm_trigger->columns = NIL;
+	ivm_trigger->transitionRels = transitionRels;
+	ivm_trigger->whenClause = NULL;
+	ivm_trigger->isconstraint = false;
+	ivm_trigger->deferrable = false;
+	ivm_trigger->initdeferred = false;
+	ivm_trigger->constrrel = NULL;
+	ivm_trigger->args = list_make2(
+		makeString(DatumGetPointer(DirectFunctionCall1(oidout, ObjectIdGetDatum(viewOid)))),
+		makeString(DatumGetPointer(DirectFunctionCall1(boolout, BoolGetDatum(ex_lock))))
+		);
+
+	address = CreateTrigger(ivm_trigger, NULL, relOid, InvalidOid, InvalidOid,
+						 InvalidOid, InvalidOid, InvalidOid, NULL, true, false);
+
+	recordDependencyOn(&address, &refaddr, DEPENDENCY_AUTO);
+
+	/* Make changes-so-far visible */
+	CommandCounterIncrement();
+}
+
+/*
+ * check_ivm_restriction --- look for specify nodes in the query tree
+ */
+static void
+check_ivm_restriction(Node *node)
+{
+	check_ivm_restriction_walker(node, NULL);
+}
+
+static bool
+check_ivm_restriction_walker(Node *node, void *context)
+{
+	if (node == NULL)
+		return false;
+
+	/*
+	 * We currently don't support Sub-Query.
+	 */
+	if (IsA(node, SubPlan) || IsA(node, SubLink))
+		ereport(ERROR,
+				(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+				 errmsg("subquery is not supported on incrementally maintainable materialized view")));
+
+	/* This can recurse, so check for excessive recursion */
+	check_stack_depth();
+
+	switch (nodeTag(node))
+	{
+		case T_Query:
+			{
+				Query *qry = (Query *)node;
+				ListCell   *lc;
+				List       *vars;
+
+				/* if contained CTE, return error */
+				if (qry->cteList != NIL)
+					ereport(ERROR,
+							(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+							 errmsg("CTE is not supported on incrementally maintainable materialized view")));
+				if (qry->havingQual != NULL)
+					ereport(ERROR,
+							(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+							 errmsg(" HAVING clause is not supported on incrementally maintainable materialized view")));
+				if (qry->sortClause != NIL)	/* There is a possibility that we don't need to return an error */
+					ereport(ERROR,
+							(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+							 errmsg("ORDER BY clause is not supported on incrementally maintainable materialized view")));
+				if (qry->limitOffset != NULL || qry->limitCount != NULL)
+					ereport(ERROR,
+							(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+							 errmsg("LIMIT/OFFSET clause is not supported on incrementally maintainable materialized view")));
+				if (qry->distinctClause)
+					ereport(ERROR,
+							(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+							 errmsg("DISTINCT is not supported on incrementally maintainable materialized view")));
+				if (qry->hasDistinctOn)
+					ereport(ERROR,
+							(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+							 errmsg("DISTINCT ON is not supported on incrementally maintainable materialized view")));
+				if (qry->hasWindowFuncs)
+					ereport(ERROR,
+							(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+							 errmsg("window functions are not supported on incrementally maintainable materialized view")));
+				if (qry->groupingSets != NIL)
+					ereport(ERROR,
+							(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+							 errmsg("GROUPING SETS, ROLLUP, or CUBE clauses is not supported on incrementally maintainable materialized view")));
+				if (qry->setOperations != NULL)
+					ereport(ERROR,
+							(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+							 errmsg("UNION/INTERSECT/EXCEPT statements are not supported on incrementally maintainable materialized view")));
+				if (list_length(qry->targetList) == 0)
+					ereport(ERROR,
+							(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+							 errmsg("empty target list is not supported on incrementally maintainable materialized view")));
+				if (qry->rowMarks != NIL)
+					ereport(ERROR,
+							(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+							 errmsg("FOR UPDATE/SHARE clause is not supported on incrementally maintainable materialized view")));
+
+				/* system column restrictions */
+				vars = pull_vars_of_level((Node *) qry, 0);
+				foreach(lc, vars)
+				{
+					if (IsA(lfirst(lc), Var))
+					{
+						Var *var = (Var *) lfirst(lc);
+						/* if system column, return error */
+						if (var->varattno < 0)
+							ereport(ERROR,
+									(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+									 errmsg("system column is not supported on incrementally maintainable materialized view")));
+					}
+				}
+
+				/* restrictions for rtable */
+				foreach(lc, qry->rtable)
+				{
+					RangeTblEntry *rte = (RangeTblEntry *) lfirst(lc);
+
+					if (rte->subquery)
+						ereport(ERROR,
+								(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+								 errmsg("subquery is not supported on incrementally maintainable materialized view")));
+
+					if (rte->tablesample != NULL)
+						ereport(ERROR,
+								(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+								 errmsg("TABLESAMPLE clause is not supported on incrementally maintainable materialized view")));
+
+					if (rte->relkind == RELKIND_PARTITIONED_TABLE)
+						ereport(ERROR,
+								(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+								 errmsg("partitioned table is not supported on incrementally maintainable materialized view")));
+
+					if (rte->relkind == RELKIND_RELATION && has_superclass(rte->relid))
+						ereport(ERROR,
+								(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+								 errmsg("partitions is not supported on incrementally maintainable materialized view")));
+
+					if (rte->relkind == RELKIND_RELATION && find_inheritance_children(rte->relid, NoLock) != NIL)
+						ereport(ERROR,
+								(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+								 errmsg("inheritance parent is not supported on incrementally maintainable materialized view")));
+
+					if (rte->relkind == RELKIND_FOREIGN_TABLE)
+						ereport(ERROR,
+								(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+								 errmsg("foreign table is not supported on incrementally maintainable materialized view")));
+
+					if (rte->relkind == RELKIND_VIEW ||
+						rte->relkind == RELKIND_MATVIEW)
+						ereport(ERROR,
+								(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+								 errmsg("VIEW or MATERIALIZED VIEW is not supported on incrementally maintainable materialized view")));
+
+					if (rte->rtekind == RTE_VALUES)
+						ereport(ERROR,
+								(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+								 errmsg("VALUES is not supported on incrementally maintainable materialized view")));
+
+				}
+
+				query_tree_walker(qry, check_ivm_restriction_walker, NULL, QTW_IGNORE_RANGE_TABLE);
+
+				break;
+			}
+		case T_TargetEntry:
+			{
+				TargetEntry *tle = (TargetEntry *)node;
+				if (isIvmName(tle->resname))
+						ereport(ERROR,
+								(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+								 errmsg("column name %s is not supported on incrementally maintainable materialized view", tle->resname)));
+
+				expression_tree_walker(node, check_ivm_restriction_walker, NULL);
+				break;
+			}
+		case T_JoinExpr:
+			{
+				JoinExpr *joinexpr = (JoinExpr *)node;
+
+				if (joinexpr->jointype > JOIN_INNER)
+						ereport(ERROR,
+								(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+								 errmsg("OUTER JOIN is not supported on incrementally maintainable materialized view")));
+
+				expression_tree_walker(node, check_ivm_restriction_walker, NULL);
+			}
+			break;
+		case T_Aggref:
+			ereport(ERROR,
+					(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+					 errmsg("aggregate function is not supported on incrementally maintainable materialized view")));
+			break;
+		default:
+			expression_tree_walker(node, check_ivm_restriction_walker, (void *) context);
+			break;
+	}
+	return false;
+}
+
+/*
+ * CreateIndexOnIMMV
+ *
+ * Create a unique index on incremental maintainable materialized view.
+ * If the view definition query has a GROUP BY clause, the index is created
+ * on the columns of GROUP BY expressions. Otherwise, if the view contains
+ * all primary key attritubes of its base tables in the target list, the index
+ * is created on these attritubes. In other cases, no index is created.
+ */
+void
+CreateIndexOnIMMV(Query *query, Relation matviewRel)
+{
+	ListCell *lc;
+	IndexStmt  *index;
+	ObjectAddress address;
+	List *constraintList = NIL;
+	char		idxname[NAMEDATALEN];
+	List	   *indexoidlist = RelationGetIndexList(matviewRel);
+	ListCell   *indexoidscan;
+	Bitmapset *key_attnos;
+
+	snprintf(idxname, sizeof(idxname), "%s_index", RelationGetRelationName(matviewRel));
+
+	index = makeNode(IndexStmt);
+
+	index->unique = true;
+	index->primary = false;
+	index->isconstraint = false;
+	index->deferrable = false;
+	index->initdeferred = false;
+	index->idxname = idxname;
+	index->relation =
+		makeRangeVar(get_namespace_name(RelationGetNamespace(matviewRel)),
+					 pstrdup(RelationGetRelationName(matviewRel)),
+					 -1);
+	index->accessMethod = DEFAULT_INDEX_TYPE;
+	index->options = NIL;
+	index->tableSpace = get_tablespace_name(matviewRel->rd_rel->reltablespace);
+	index->whereClause = NULL;
+	index->indexParams = NIL;
+	index->indexIncludingParams = NIL;
+	index->excludeOpNames = NIL;
+	index->idxcomment = NULL;
+	index->indexOid = InvalidOid;
+	index->oldNumber = InvalidRelFileNumber;
+	index->oldCreateSubid = InvalidSubTransactionId;
+	index->oldFirstRelfilelocatorSubid = InvalidSubTransactionId;
+	index->transformed = true;
+	index->concurrent = false;
+	index->if_not_exists = false;
+
+	/* create index on the base tables' primary key columns */
+	key_attnos = get_primary_key_attnos_from_query(query, &constraintList);
+	if (key_attnos)
+	{
+		foreach(lc, query->targetList)
+		{
+			TargetEntry *tle = (TargetEntry *) lfirst(lc);
+			Form_pg_attribute attr = TupleDescAttr(matviewRel->rd_att, tle->resno - 1);
+
+			if (bms_is_member(tle->resno - FirstLowInvalidHeapAttributeNumber, key_attnos))
+			{
+				IndexElem  *iparam;
+
+				iparam = makeNode(IndexElem);
+				iparam->name = pstrdup(NameStr(attr->attname));
+				iparam->expr = NULL;
+				iparam->indexcolname = NULL;
+				iparam->collation = NIL;
+				iparam->opclass = NIL;
+				iparam->opclassopts = NIL;
+				iparam->ordering = SORTBY_DEFAULT;
+				iparam->nulls_ordering = SORTBY_NULLS_DEFAULT;
+				index->indexParams = lappend(index->indexParams, iparam);
+			}
+		}
+	}
+	else
+	{
+		/* create no index, just notice that an appropriate index is necessary for efficient IVM */
+		ereport(NOTICE,
+				(errmsg("could not create an index on materialized view \"%s\" automatically",
+						RelationGetRelationName(matviewRel)),
+				 errdetail("This target list does not have all the primary key columns. "),
+				 errhint("Create an index on the materialized view for efficient incremental maintenance.")));
+		return;
+	}
+
+	/* If we have a compatible index, we don't need to create another. */
+	foreach(indexoidscan, indexoidlist)
+	{
+		Oid			indexoid = lfirst_oid(indexoidscan);
+		Relation	indexRel;
+		bool		hasCompatibleIndex = false;
+
+		indexRel = index_open(indexoid, AccessShareLock);
+
+		if (CheckIndexCompatible(indexRel->rd_id,
+								index->accessMethod,
+								index->indexParams,
+								index->excludeOpNames))
+			hasCompatibleIndex = true;
+
+		index_close(indexRel, AccessShareLock);
+
+		if (hasCompatibleIndex)
+			return;
+	}
+
+	address = DefineIndex(RelationGetRelid(matviewRel),
+						  index,
+						  InvalidOid,
+						  InvalidOid,
+						  InvalidOid,
+						  -1,
+						  false, true, false, false, true);
+
+	ereport(NOTICE,
+			(errmsg("created index \"%s\" on materialized view \"%s\"",
+					idxname, RelationGetRelationName(matviewRel))));
+
+	/*
+	 * Make dependencies so that the index is dropped if any base tables's
+	 * primary key is dropped.
+	 */
+	foreach(lc, constraintList)
+	{
+		Oid constraintOid = lfirst_oid(lc);
+		ObjectAddress	refaddr;
+
+		refaddr.classId = ConstraintRelationId;
+		refaddr.objectId = constraintOid;
+		refaddr.objectSubId = 0;
+
+		recordDependencyOn(&address, &refaddr, DEPENDENCY_NORMAL);
+	}
+}
+
+
+/*
+ * get_primary_key_attnos_from_query
+ *
+ * Identify the columns in base tables' primary keys in the target list.
+ *
+ * Returns a Bitmapset of the column attnos of the primary key's columns of
+ * tables that used in the query.  The attnos are offset by
+ * FirstLowInvalidHeapAttributeNumber as same as get_primary_key_attnos.
+ *
+ * If any table has no primary key or any primary key's columns is not in
+ * the target list, return NULL.  We also return NULL if any pkey constraint
+ * is deferrable.
+ *
+ * constraintList is set to a list of the OIDs of the pkey constraints.
+ */
+static Bitmapset *
+get_primary_key_attnos_from_query(Query *query, List **constraintList)
+{
+	List *key_attnos_list = NIL;
+	ListCell *lc;
+	int i;
+	Bitmapset *keys = NULL;
+	Relids	rels_in_from;
+
+	/*
+	 * Collect primary key attributes from all tables used in query. The key attributes
+	 * sets for each table are stored in key_attnos_list in order by RTE index.
+	 */
+	foreach(lc, query->rtable)
+	{
+		RangeTblEntry *r = (RangeTblEntry*) lfirst(lc);
+		Bitmapset *key_attnos;
+		bool	has_pkey = true;
+
+		/* for tables, call get_primary_key_attnos */
+		if (r->rtekind == RTE_RELATION)
+		{
+			Oid constraintOid;
+			key_attnos = get_primary_key_attnos(r->relid, false, &constraintOid);
+			*constraintList = lappend_oid(*constraintList, constraintOid);
+			has_pkey = (key_attnos != NULL);
+		}
+		/* for other RTEs, store NULL into key_attnos_list */
+		else
+			key_attnos = NULL;
+
+		/*
+		 * If any table or subquery has no primary key or its pkey constraint is deferrable,
+		 * we cannot get key attributes for this query, so return NULL.
+		 */
+		if (!has_pkey)
+			return NULL;
+
+		key_attnos_list = lappend(key_attnos_list, key_attnos);
+	}
+
+	/* Collect key attributes appearing in the target list */
+	i = 1;
+	foreach(lc, query->targetList)
+	{
+		TargetEntry *tle = (TargetEntry *) flatten_join_alias_vars(NULL, query, lfirst(lc));
+
+		if (IsA(tle->expr, Var))
+		{
+			Var *var = (Var*) tle->expr;
+			Bitmapset *key_attnos = list_nth(key_attnos_list, var->varno - 1);
+
+			/* check if this attribute is from a base table's primary key */
+			if (bms_is_member(var->varattno - FirstLowInvalidHeapAttributeNumber, key_attnos))
+			{
+				/*
+				 * Remove found key attributes from key_attnos_list, and add this
+				 * to the result list.
+				 */
+				key_attnos = bms_del_member(key_attnos, var->varattno - FirstLowInvalidHeapAttributeNumber);
+				if (bms_is_empty(key_attnos))
+				{
+					key_attnos_list = list_delete_nth_cell(key_attnos_list, var->varno - 1);
+					key_attnos_list = list_insert_nth(key_attnos_list, var->varno - 1, NULL);
+				}
+				keys = bms_add_member(keys, i - FirstLowInvalidHeapAttributeNumber);
+			}
+		}
+		i++;
+	}
+
+	/* Collect RTE indexes of relations appearing in the FROM clause */
+	rels_in_from = get_relids_in_jointree((Node *) query->jointree, false, false);
+
+	/*
+	 * Check if all key attributes of relations in FROM are appearing in the target
+	 * list.  If an attribute remains in key_attnos_list in spite of the table is used
+	 * in FROM clause, the target is missing this key attribute, so we return NULL.
+	 */
+	i = 1;
+	foreach(lc, key_attnos_list)
+	{
+		Bitmapset *bms = (Bitmapset *)lfirst(lc);
+		if (!bms_is_empty(bms) && bms_is_member(i, rels_in_from))
+			return NULL;
+		i++;
+	}
+
+	return keys;
+}
diff --git a/src/backend/commands/matview.c b/src/backend/commands/matview.c
index ac2e74fa3f..39305f3c49 100644
--- a/src/backend/commands/matview.c
+++ b/src/backend/commands/matview.c
@@ -25,26 +25,37 @@
 #include "catalog/indexing.h"
 #include "catalog/namespace.h"
 #include "catalog/pg_am.h"
+#include "catalog/pg_depend.h"
+#include "catalog/pg_trigger.h"
 #include "catalog/pg_opclass.h"
 #include "catalog/pg_operator.h"
 #include "commands/cluster.h"
 #include "commands/matview.h"
 #include "commands/tablecmds.h"
 #include "commands/tablespace.h"
+#include "commands/createas.h"
 #include "executor/executor.h"
 #include "executor/spi.h"
+#include "executor/tstoreReceiver.h"
 #include "miscadmin.h"
+#include "nodes/makefuncs.h"
+#include "parser/analyze.h"
+#include "parser/parse_clause.h"
+#include "parser/parse_func.h"
 #include "parser/parse_relation.h"
 #include "pgstat.h"
 #include "rewrite/rewriteHandler.h"
+#include "rewrite/rowsecurity.h"
 #include "storage/lmgr.h"
 #include "storage/smgr.h"
 #include "tcop/tcopprot.h"
 #include "utils/builtins.h"
+#include "utils/fmgroids.h"
 #include "utils/lsyscache.h"
 #include "utils/rel.h"
 #include "utils/snapmgr.h"
 #include "utils/syscache.h"
+#include "utils/typcache.h"
 
 
 typedef struct
@@ -58,6 +69,52 @@ typedef struct
 	BulkInsertState bistate;	/* bulk insert state */
 } DR_transientrel;
 
+#define MV_INIT_QUERYHASHSIZE	16
+
+/*
+ * MV_TriggerHashEntry
+ *
+ * Hash entry for base tables on which IVM trigger is invoked
+ */
+typedef struct MV_TriggerHashEntry
+{
+	Oid	matview_id;			/* OID of the materialized view */
+	int	before_trig_count;	/* count of before triggers invoked */
+	int	after_trig_count;	/* count of after triggers invoked */
+
+	Snapshot	snapshot;	/* Snapshot just before table change */
+
+	List   *tables;		/* List of MV_TriggerTable */
+	bool	has_old;	/* tuples are deleted from any table? */
+	bool	has_new;	/* tuples are inserted into any table? */
+} MV_TriggerHashEntry;
+
+/*
+ * MV_TriggerTable
+ *
+ * IVM related data for tables on which the trigger is invoked.
+ */
+typedef struct MV_TriggerTable
+{
+	Oid		table_id;			/* OID of the modified table */
+	List   *old_tuplestores;	/* tuplestores for deleted tuples */
+	List   *new_tuplestores;	/* tuplestores for inserted tuples */
+
+	List   *rte_indexes;		/* List of RTE index of the modified table */
+	RangeTblEntry *original_rte;	/* the original RTE saved before rewriting query */
+
+	Relation	rel;			/* relation of the modified table */
+	TupleTableSlot *slot;		/* for checking visibility in the pre-state table */
+} MV_TriggerTable;
+
+static HTAB *mv_trigger_info = NULL;
+
+static bool in_delta_calculation = false;
+
+/* ENR name for materialized view delta */
+#define NEW_DELTA_ENRNAME "new_delta"
+#define OLD_DELTA_ENRNAME "old_delta"
+
 static int	matview_maintenance_depth = 0;
 
 static void transientrel_startup(DestReceiver *self, int operation, TupleDesc typeinfo);
@@ -65,7 +122,9 @@ static bool transientrel_receive(TupleTableSlot *slot, DestReceiver *self);
 static void transientrel_shutdown(DestReceiver *self);
 static void transientrel_destroy(DestReceiver *self);
 static uint64 refresh_matview_datafill(DestReceiver *dest, Query *query,
-									   const char *queryString);
+						 QueryEnvironment *queryEnv,
+						 TupleDesc *resultTupleDesc,
+						 const char *queryString);
 static char *make_temptable_name_n(char *tempname, int n);
 static void refresh_by_match_merge(Oid matviewOid, Oid tempOid, Oid relowner,
 								   int save_sec_context);
@@ -73,6 +132,37 @@ static void refresh_by_heap_swap(Oid matviewOid, Oid OIDNewHeap, char relpersist
 static bool is_usable_unique_index(Relation indexRel);
 static void OpenMatViewIncrementalMaintenance(void);
 static void CloseMatViewIncrementalMaintenance(void);
+static Query *get_matview_query(Relation matviewRel);
+
+static Query *rewrite_query_for_preupdate_state(Query *query, List *tables,
+								  ParseState *pstate, Oid matviewid);
+static void register_delta_ENRs(ParseState *pstate, Query *query, List *tables);
+static char *make_delta_enr_name(const char *prefix, Oid relid, int count);
+static RangeTblEntry *get_prestate_rte(RangeTblEntry *rte, MV_TriggerTable *table,
+				 QueryEnvironment *queryEnv, Oid matviewid);
+static RangeTblEntry *replace_rte_with_delta(RangeTblEntry *rte, MV_TriggerTable *table, bool is_new,
+		   QueryEnvironment *queryEnv);
+static Query *rewrite_query_for_counting(Query *query, ParseState *pstate);
+
+static void calc_delta(MV_TriggerTable *table, int rte_index, Query *query,
+			DestReceiver *dest_old, DestReceiver *dest_new,
+			TupleDesc *tupdesc_old, TupleDesc *tupdesc_new,
+			QueryEnvironment *queryEnv);
+static Query *rewrite_query_for_postupdate_state(Query *query, MV_TriggerTable *table, int rte_index);
+
+static void apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *new_tuplestores,
+			TupleDesc tupdesc_old, TupleDesc tupdesc_new,
+			Query *query);
+static void apply_old_delta(const char *matviewname, const char *deltaname_old,
+				List *keys);
+static void apply_new_delta(const char *matviewname, const char *deltaname_new,
+				StringInfo target_list);
+static char *get_matching_condition_string(List *keys);
+static void generate_equal(StringInfo querybuf, Oid opttype,
+			   const char *leftop, const char *rightop);
+
+static void mv_InitHashTables(void);
+static void clean_up_IVM_hash_entry(MV_TriggerHashEntry *entry, bool is_abort);
 
 /*
  * SetMatViewPopulatedState
@@ -114,6 +204,46 @@ SetMatViewPopulatedState(Relation relation, bool newstate)
 	CommandCounterIncrement();
 }
 
+/*
+ * SetMatViewIVMState
+ *		Mark a materialized view as IVM, or not.
+ *
+ * NOTE: caller must be holding an appropriate lock on the relation.
+ */
+void
+SetMatViewIVMState(Relation relation, bool newstate)
+{
+	Relation	pgrel;
+	HeapTuple	tuple;
+
+	Assert(relation->rd_rel->relkind == RELKIND_MATVIEW);
+
+	/*
+	 * Update relation's pg_class entry.  Crucial side-effect: other backends
+	 * (and this one too!) are sent SI message to make them rebuild relcache
+	 * entries.
+	 */
+	pgrel = table_open(RelationRelationId, RowExclusiveLock);
+	tuple = SearchSysCacheCopy1(RELOID,
+								ObjectIdGetDatum(RelationGetRelid(relation)));
+	if (!HeapTupleIsValid(tuple))
+		elog(ERROR, "cache lookup failed for relation %u",
+			 RelationGetRelid(relation));
+
+	((Form_pg_class) GETSTRUCT(tuple))->relisivm = newstate;
+
+	CatalogTupleUpdate(pgrel, &tuple->t_self, tuple);
+
+	heap_freetuple(tuple);
+	table_close(pgrel, RowExclusiveLock);
+
+	/*
+	 * Advance command counter to make the updated pg_class row locally
+	 * visible.
+	 */
+	CommandCounterIncrement();
+}
+
 /*
  * ExecRefreshMatView -- execute a REFRESH MATERIALIZED VIEW command
  *
@@ -140,8 +270,6 @@ ExecRefreshMatView(RefreshMatViewStmt *stmt, const char *queryString,
 {
 	Oid			matviewOid;
 	Relation	matviewRel;
-	RewriteRule *rule;
-	List	   *actions;
 	Query	   *dataQuery;
 	Oid			tableSpace;
 	Oid			relowner;
@@ -155,6 +283,7 @@ ExecRefreshMatView(RefreshMatViewStmt *stmt, const char *queryString,
 	int			save_sec_context;
 	int			save_nestlevel;
 	ObjectAddress address;
+	bool oldPopulated;
 
 	/* Determine strength of lock needed. */
 	concurrent = stmt->concurrent;
@@ -178,6 +307,7 @@ ExecRefreshMatView(RefreshMatViewStmt *stmt, const char *queryString,
 	SetUserIdAndSecContext(relowner,
 						   save_sec_context | SECURITY_RESTRICTED_OPERATION);
 	save_nestlevel = NewGUCNestLevel();
+	oldPopulated = RelationIsPopulated(matviewRel);
 
 	/* Make sure it is a materialized view. */
 	if (matviewRel->rd_rel->relkind != RELKIND_MATVIEW)
@@ -199,32 +329,9 @@ ExecRefreshMatView(RefreshMatViewStmt *stmt, const char *queryString,
 				 errmsg("%s and %s options cannot be used together",
 						"CONCURRENTLY", "WITH NO DATA")));
 
-	/*
-	 * Check that everything is correct for a refresh. Problems at this point
-	 * are internal errors, so elog is sufficient.
-	 */
-	if (matviewRel->rd_rel->relhasrules == false ||
-		matviewRel->rd_rules->numLocks < 1)
-		elog(ERROR,
-			 "materialized view \"%s\" is missing rewrite information",
-			 RelationGetRelationName(matviewRel));
-
-	if (matviewRel->rd_rules->numLocks > 1)
-		elog(ERROR,
-			 "materialized view \"%s\" has too many rules",
-			 RelationGetRelationName(matviewRel));
 
-	rule = matviewRel->rd_rules->rules[0];
-	if (rule->event != CMD_SELECT || !(rule->isInstead))
-		elog(ERROR,
-			 "the rule for materialized view \"%s\" is not a SELECT INSTEAD OF rule",
-			 RelationGetRelationName(matviewRel));
+	dataQuery = get_matview_query(matviewRel);
 
-	actions = rule->actions;
-	if (list_length(actions) != 1)
-		elog(ERROR,
-			 "the rule for materialized view \"%s\" is not a single action",
-			 RelationGetRelationName(matviewRel));
 
 	/*
 	 * Check that there is a unique index with no WHERE clause on one or more
@@ -259,12 +366,6 @@ ExecRefreshMatView(RefreshMatViewStmt *stmt, const char *queryString,
 					 errhint("Create a unique index with no WHERE clause on one or more columns of the materialized view.")));
 	}
 
-	/*
-	 * The stored query was rewritten at the time of the MV definition, but
-	 * has not been scribbled on by the planner.
-	 */
-	dataQuery = linitial_node(Query, actions);
-
 	/*
 	 * Check for active uses of the relation in the current transaction, such
 	 * as open scans.
@@ -292,6 +393,74 @@ ExecRefreshMatView(RefreshMatViewStmt *stmt, const char *queryString,
 		relpersistence = matviewRel->rd_rel->relpersistence;
 	}
 
+	/* delete IMMV triggers. */
+	if (RelationIsIVM(matviewRel) && stmt->skipData )
+	{
+		Relation	tgRel;
+		Relation	depRel;
+		ScanKeyData key;
+		SysScanDesc scan;
+		HeapTuple	tup;
+		ObjectAddresses *immv_triggers;
+
+		immv_triggers = new_object_addresses();
+
+		tgRel = table_open(TriggerRelationId, RowExclusiveLock);
+		depRel = table_open(DependRelationId, RowExclusiveLock);
+
+		/* search triggers that depends on IMMV. */
+		ScanKeyInit(&key,
+					Anum_pg_depend_refobjid,
+					BTEqualStrategyNumber, F_OIDEQ,
+					ObjectIdGetDatum(matviewOid));
+		scan = systable_beginscan(depRel, DependReferenceIndexId, true,
+								  NULL, 1, &key);
+		while ((tup = systable_getnext(scan)) != NULL)
+		{
+			ObjectAddress obj;
+			Form_pg_depend foundDep = (Form_pg_depend) GETSTRUCT(tup);
+
+			if (foundDep->classid == TriggerRelationId)
+			{
+				HeapTuple	tgtup;
+				ScanKeyData tgkey[1];
+				SysScanDesc tgscan;
+				Form_pg_trigger tgform;
+
+				/* Find the trigger name. */
+				ScanKeyInit(&tgkey[0],
+							Anum_pg_trigger_oid,
+							BTEqualStrategyNumber, F_OIDEQ,
+							ObjectIdGetDatum(foundDep->objid));
+
+				tgscan = systable_beginscan(tgRel, TriggerOidIndexId, true,
+											NULL, 1, tgkey);
+				tgtup = systable_getnext(tgscan);
+				if (!HeapTupleIsValid(tgtup))
+					elog(ERROR, "could not find tuple for immv trigger %u", foundDep->objid);
+
+				tgform = (Form_pg_trigger) GETSTRUCT(tgtup);
+
+				/* If trigger is created by IMMV, delete it. */
+				if (strncmp(NameStr(tgform->tgname), "IVM_trigger_", 12) == 0)
+				{
+					obj.classId = foundDep->classid;
+					obj.objectId = foundDep->objid;
+					obj.objectSubId = foundDep->refobjsubid;
+					add_exact_object_address(&obj, immv_triggers);
+				}
+				systable_endscan(tgscan);
+			}
+		}
+		systable_endscan(scan);
+
+		performMultipleDeletions(immv_triggers, DROP_RESTRICT, PERFORM_DELETION_INTERNAL);
+
+		table_close(depRel, RowExclusiveLock);
+		table_close(tgRel, RowExclusiveLock);
+		free_object_addresses(immv_triggers);
+	}
+
 	/*
 	 * Create the transient table that will receive the regenerated data. Lock
 	 * it against access by any other process until commit (by which time it
@@ -305,7 +474,7 @@ ExecRefreshMatView(RefreshMatViewStmt *stmt, const char *queryString,
 
 	/* Generate the data, if wanted. */
 	if (!stmt->skipData)
-		processed = refresh_matview_datafill(dest, dataQuery, queryString);
+		processed = refresh_matview_datafill(dest, dataQuery, NULL, NULL, queryString);
 
 	/* Make the matview match the newly generated data. */
 	if (concurrent)
@@ -340,6 +509,12 @@ ExecRefreshMatView(RefreshMatViewStmt *stmt, const char *queryString,
 			pgstat_count_heap_insert(matviewRel, processed);
 	}
 
+	if (!stmt->skipData && RelationIsIVM(matviewRel) && !oldPopulated)
+	{
+		CreateIndexOnIMMV(dataQuery, matviewRel);
+		CreateIvmTriggersOnBaseTables(dataQuery, matviewOid);
+	}
+
 	table_close(matviewRel, NoLock);
 
 	/* Roll back any GUC changes */
@@ -374,6 +549,8 @@ ExecRefreshMatView(RefreshMatViewStmt *stmt, const char *queryString,
  */
 static uint64
 refresh_matview_datafill(DestReceiver *dest, Query *query,
+						 QueryEnvironment *queryEnv,
+						 TupleDesc *resultTupleDesc,
 						 const char *queryString)
 {
 	List	   *rewritten;
@@ -410,7 +587,7 @@ refresh_matview_datafill(DestReceiver *dest, Query *query,
 	/* Create a QueryDesc, redirecting output to our tuple receiver */
 	queryDesc = CreateQueryDesc(plan, queryString,
 								GetActiveSnapshot(), InvalidSnapshot,
-								dest, NULL, NULL, 0);
+								dest, NULL, queryEnv ? queryEnv: NULL, 0);
 
 	/* call ExecutorStart to prepare the plan for execution */
 	ExecutorStart(queryDesc, 0);
@@ -420,6 +597,9 @@ refresh_matview_datafill(DestReceiver *dest, Query *query,
 
 	processed = queryDesc->estate->es_processed;
 
+	if (resultTupleDesc)
+		*resultTupleDesc = CreateTupleDescCopy(queryDesc->tupDesc);
+
 	/* and clean up */
 	ExecutorFinish(queryDesc);
 	ExecutorEnd(queryDesc);
@@ -931,3 +1111,1219 @@ CloseMatViewIncrementalMaintenance(void)
 	matview_maintenance_depth--;
 	Assert(matview_maintenance_depth >= 0);
 }
+
+/*
+ * get_matview_query - get the Query from a matview's _RETURN rule.
+ */
+static Query *
+get_matview_query(Relation matviewRel)
+{
+	RewriteRule *rule;
+	List * actions;
+
+	/*
+	 * Check that everything is correct for a refresh. Problems at this point
+	 * are internal errors, so elog is sufficient.
+	 */
+	if (matviewRel->rd_rel->relhasrules == false ||
+		matviewRel->rd_rules->numLocks < 1)
+		elog(ERROR,
+			 "materialized view \"%s\" is missing rewrite information",
+			 RelationGetRelationName(matviewRel));
+
+	if (matviewRel->rd_rules->numLocks > 1)
+		elog(ERROR,
+			 "materialized view \"%s\" has too many rules",
+			 RelationGetRelationName(matviewRel));
+
+	rule = matviewRel->rd_rules->rules[0];
+	if (rule->event != CMD_SELECT || !(rule->isInstead))
+		elog(ERROR,
+			 "the rule for materialized view \"%s\" is not a SELECT INSTEAD OF rule",
+			 RelationGetRelationName(matviewRel));
+
+	actions = rule->actions;
+	if (list_length(actions) != 1)
+		elog(ERROR,
+			 "the rule for materialized view \"%s\" is not a single action",
+			 RelationGetRelationName(matviewRel));
+
+	/*
+	 * The stored query was rewritten at the time of the MV definition, but
+	 * has not been scribbled on by the planner.
+	 */
+	return linitial_node(Query, actions);
+}
+
+
+/* ----------------------------------------------------
+ *		Incremental View Maintenance routines
+ * ---------------------------------------------------
+ */
+
+/*
+ * IVM_immediate_before
+ *
+ * IVM trigger function invoked before base table is modified. If this is
+ * invoked firstly in the same statement, we save the transaction id and the
+ * command id at that time.
+ */
+Datum
+IVM_immediate_before(PG_FUNCTION_ARGS)
+{
+	TriggerData *trigdata = (TriggerData *) fcinfo->context;
+	char	   *matviewOid_text = trigdata->tg_trigger->tgargs[0];
+	char	   *ex_lock_text = trigdata->tg_trigger->tgargs[1];
+	Oid			matviewOid;
+	MV_TriggerHashEntry *entry;
+	bool	found;
+	bool	ex_lock;
+
+	matviewOid = DatumGetObjectId(DirectFunctionCall1(oidin, CStringGetDatum(matviewOid_text)));
+	ex_lock = DatumGetBool(DirectFunctionCall1(boolin, CStringGetDatum(ex_lock_text)));
+
+	/* If the view has more than one tables, we have to use an exclusive lock. */
+	if (ex_lock)
+	{
+		/*
+		 * Wait for concurrent transactions which update this materialized view at
+		 * READ COMMITED. This is needed to see changes committed in other
+		 * transactions. No wait and raise an error at REPEATABLE READ or
+		 * SERIALIZABLE to prevent update anomalies of matviews.
+		 * XXX: dead-lock is possible here.
+		 */
+		if (!IsolationUsesXactSnapshot())
+			LockRelationOid(matviewOid, ExclusiveLock);
+		else if (!ConditionalLockRelationOid(matviewOid, ExclusiveLock))
+		{
+			/* try to throw error by name; relation could be deleted... */
+			char	   *relname = get_rel_name(matviewOid);
+
+			if (!relname)
+				ereport(ERROR,
+						(errcode(ERRCODE_LOCK_NOT_AVAILABLE),
+						errmsg("could not obtain lock on materialized view during incremental maintenance")));
+
+			ereport(ERROR,
+					(errcode(ERRCODE_LOCK_NOT_AVAILABLE),
+					errmsg("could not obtain lock on materialized view \"%s\" during incremental maintenance",
+							relname)));
+		}
+	}
+	else
+		LockRelationOid(matviewOid, RowExclusiveLock);
+
+	/*
+	 * On the first call initialize the hashtable
+	 */
+	if (!mv_trigger_info)
+		mv_InitHashTables();
+
+	entry = (MV_TriggerHashEntry *) hash_search(mv_trigger_info,
+											  (void *) &matviewOid,
+											  HASH_ENTER, &found);
+
+	/* On the first BEFORE to update the view, initialize trigger data */
+	if (!found)
+	{
+		/*
+		 * Get a snapshot just before the table was modified for checking
+		 * tuple visibility in the pre-update state of the table.
+		 */
+		Snapshot snapshot = GetActiveSnapshot();
+
+		entry->matview_id = matviewOid;
+		entry->before_trig_count = 0;
+		entry->after_trig_count = 0;
+		entry->snapshot = RegisterSnapshot(snapshot);
+		entry->tables = NIL;
+		entry->has_old = false;
+		entry->has_new = false;
+	}
+
+	entry->before_trig_count++;
+
+	return PointerGetDatum(NULL);
+}
+
+/*
+ * IVM_immediate_maintenance
+ *
+ * IVM trigger function invoked after base table is modified.
+ * For each table, tuplestores of transition tables are collected.
+ * and after the last modification
+ */
+Datum
+IVM_immediate_maintenance(PG_FUNCTION_ARGS)
+{
+	TriggerData *trigdata = (TriggerData *) fcinfo->context;
+	Relation	rel;
+	Oid			relid;
+	Oid			matviewOid;
+	Query	   *query;
+	Query	   *rewritten = NULL;
+	char	   *matviewOid_text = trigdata->tg_trigger->tgargs[0];
+	Relation	matviewRel;
+	int old_depth = matview_maintenance_depth;
+
+	Oid			relowner;
+	Tuplestorestate *old_tuplestore = NULL;
+	Tuplestorestate *new_tuplestore = NULL;
+	DestReceiver *dest_new = NULL, *dest_old = NULL;
+	Oid			save_userid;
+	int			save_sec_context;
+	int			save_nestlevel;
+
+	MV_TriggerHashEntry *entry;
+	MV_TriggerTable		*table;
+	bool	found;
+
+	ParseState		 *pstate;
+	QueryEnvironment *queryEnv = create_queryEnv();
+	MemoryContext	oldcxt;
+	ListCell   *lc;
+	int			i;
+
+
+	/* Create a ParseState for rewriting the view definition query */
+	pstate = make_parsestate(NULL);
+	pstate->p_queryEnv = queryEnv;
+	pstate->p_expr_kind = EXPR_KIND_SELECT_TARGET;
+
+	rel = trigdata->tg_relation;
+	relid = rel->rd_id;
+
+	matviewOid = DatumGetObjectId(DirectFunctionCall1(oidin, CStringGetDatum(matviewOid_text)));
+
+	/*
+	 * On the first call initialize the hashtable
+	 */
+	if (!mv_trigger_info)
+		mv_InitHashTables();
+
+	/* get the entry for this materialized view */
+	entry = (MV_TriggerHashEntry *) hash_search(mv_trigger_info,
+											  (void *) &matviewOid,
+											  HASH_FIND, &found);
+	Assert (found && entry != NULL);
+	entry->after_trig_count++;
+
+	/* search the entry for the modified table and create new entry if not found */
+	found = false;
+	foreach(lc, entry->tables)
+	{
+		table = (MV_TriggerTable *) lfirst(lc);
+		if (table->table_id == relid)
+		{
+			found = true;
+			break;
+		}
+	}
+	if (!found)
+	{
+		oldcxt = MemoryContextSwitchTo(TopTransactionContext);
+
+		table = (MV_TriggerTable *) palloc0(sizeof(MV_TriggerTable));
+		table->table_id = relid;
+		table->old_tuplestores = NIL;
+		table->new_tuplestores = NIL;
+		table->rte_indexes = NIL;
+		table->slot = MakeSingleTupleTableSlot(RelationGetDescr(rel), table_slot_callbacks(rel));
+		table->rel = table_open(RelationGetRelid(rel), NoLock);
+		entry->tables = lappend(entry->tables, table);
+
+		MemoryContextSwitchTo(oldcxt);
+	}
+
+	/* Save the transition tables and make a request to not free immediately */
+	if (trigdata->tg_oldtable)
+	{
+		oldcxt = MemoryContextSwitchTo(TopTransactionContext);
+		table->old_tuplestores = lappend(table->old_tuplestores, trigdata->tg_oldtable);
+		entry->has_old = true;
+		MemoryContextSwitchTo(oldcxt);
+	}
+	if (trigdata->tg_newtable)
+	{
+		oldcxt = MemoryContextSwitchTo(TopTransactionContext);
+		table->new_tuplestores = lappend(table->new_tuplestores, trigdata->tg_newtable);
+		entry->has_new = true;
+		MemoryContextSwitchTo(oldcxt);
+	}
+	if (entry->has_new || entry->has_old)
+	{
+		CmdType cmd;
+
+		if (TRIGGER_FIRED_BY_INSERT(trigdata->tg_event))
+			cmd = CMD_INSERT;
+		else if (TRIGGER_FIRED_BY_DELETE(trigdata->tg_event))
+			cmd = CMD_DELETE;
+		else if (TRIGGER_FIRED_BY_UPDATE(trigdata->tg_event))
+			cmd = CMD_UPDATE;
+		else
+			elog(ERROR,"unsupported trigger type");
+
+		/* Prolong lifespan of transition tables to the end of the last AFTER trigger */
+		SetTransitionTablePreserved(relid, cmd);
+	}
+
+
+	/* If this is not the last AFTER trigger call, immediately exit. */
+	Assert (entry->before_trig_count >= entry->after_trig_count);
+	if (entry->before_trig_count != entry->after_trig_count)
+		return PointerGetDatum(NULL);
+
+	/*
+	 * If this is the last AFTER trigger call, continue and update the view.
+	 */
+
+	/*
+	 * Advance command counter to make the updated base table row locally
+	 * visible.
+	 */
+	CommandCounterIncrement();
+
+	matviewRel = table_open(matviewOid, NoLock);
+
+	/* Make sure it is a materialized view. */
+	Assert(matviewRel->rd_rel->relkind == RELKIND_MATVIEW);
+
+	/*
+	 * Get and push the latast snapshot to see any changes which is committed
+	 * during waiting in other transactions at READ COMMITTED level.
+	 */
+	PushActiveSnapshot(GetTransactionSnapshot());
+
+	/*
+	 * Check for active uses of the relation in the current transaction, such
+	 * as open scans.
+	 *
+	 * NB: We count on this to protect us against problems with refreshing the
+	 * data using TABLE_INSERT_FROZEN.
+	 */
+	CheckTableNotInUse(matviewRel, "refresh a materialized view incrementally");
+
+	/*
+	 * Switch to the owner's userid, so that any functions are run as that
+	 * user.  Also arrange to make GUC variable changes local to this command.
+	 * We will switch modes when we are about to execute user code.
+	 */
+	relowner = matviewRel->rd_rel->relowner;
+	GetUserIdAndSecContext(&save_userid, &save_sec_context);
+	SetUserIdAndSecContext(relowner,
+						   save_sec_context | SECURITY_RESTRICTED_OPERATION);
+	save_nestlevel = NewGUCNestLevel();
+
+	/* get view query*/
+	query = get_matview_query(matviewRel);
+
+	/*
+	 * When a base table is truncated, the view content will be empty if the
+	 * view definition query does not contain an aggregate without a GROUP clause.
+	 * Therefore, such views can be truncated.
+	 */
+	if (TRIGGER_FIRED_BY_TRUNCATE(trigdata->tg_event))
+	{
+		ExecuteTruncateGuts(list_make1(matviewRel), list_make1_oid(matviewOid),
+							NIL, DROP_RESTRICT, false, false);
+
+		/* Clean up hash entry and delete tuplestores */
+		clean_up_IVM_hash_entry(entry, false);
+
+		/* Pop the original snapshot. */
+		PopActiveSnapshot();
+
+		table_close(matviewRel, NoLock);
+
+		/* Roll back any GUC changes */
+		AtEOXact_GUC(false, save_nestlevel);
+
+		/* Restore userid and security context */
+		SetUserIdAndSecContext(save_userid, save_sec_context);
+
+		return PointerGetDatum(NULL);
+	}
+
+	/*
+	 * rewrite query for calculating deltas
+	 */
+
+	rewritten = copyObject(query);
+
+	/* Replace resnames in a target list with materialized view's attnames */
+	i = 0;
+	foreach (lc, rewritten->targetList)
+	{
+		TargetEntry *tle = (TargetEntry *) lfirst(lc);
+		Form_pg_attribute attr = TupleDescAttr(matviewRel->rd_att, i);
+		char *resname = NameStr(attr->attname);
+
+		tle->resname = pstrdup(resname);
+		i++;
+	}
+
+	/* Set all tables in the query to pre-update state */
+	rewritten = rewrite_query_for_preupdate_state(rewritten, entry->tables,
+												  pstate, matviewOid);
+	/* Rewrite for counting duplicated tuples */
+	rewritten = rewrite_query_for_counting(rewritten, pstate);
+
+	/* Create tuplestores to store view deltas */
+	if (entry->has_old)
+	{
+		oldcxt = MemoryContextSwitchTo(TopTransactionContext);
+
+		old_tuplestore = tuplestore_begin_heap(false, false, work_mem);
+		dest_old = CreateDestReceiver(DestTuplestore);
+		SetTuplestoreDestReceiverParams(dest_old,
+									old_tuplestore,
+									TopTransactionContext,
+									false,
+									NULL,
+									NULL);
+
+		MemoryContextSwitchTo(oldcxt);
+	}
+	if (entry->has_new)
+	{
+		oldcxt = MemoryContextSwitchTo(TopTransactionContext);
+
+		new_tuplestore = tuplestore_begin_heap(false, false, work_mem);
+		dest_new = CreateDestReceiver(DestTuplestore);
+		SetTuplestoreDestReceiverParams(dest_new,
+									new_tuplestore,
+									TopTransactionContext,
+									false,
+									NULL,
+									NULL);
+		MemoryContextSwitchTo(oldcxt);
+	}
+
+	/* for all modified tables */
+	foreach(lc, entry->tables)
+	{
+		ListCell *lc2;
+
+		table = (MV_TriggerTable *) lfirst(lc);
+
+		/* loop for self-join */
+		foreach(lc2, table->rte_indexes)
+		{
+			int	rte_index = lfirst_int(lc2);
+			TupleDesc		tupdesc_old;
+			TupleDesc		tupdesc_new;
+
+			/* calculate delta tables */
+			calc_delta(table, rte_index, rewritten, dest_old, dest_new,
+					   &tupdesc_old, &tupdesc_new, queryEnv);
+
+			/* Set the table in the query to post-update state */
+			rewritten = rewrite_query_for_postupdate_state(rewritten, table, rte_index);
+
+			PG_TRY();
+			{
+				/* apply the delta tables to the materialized view */
+				apply_delta(matviewOid, old_tuplestore, new_tuplestore,
+							tupdesc_old, tupdesc_new, query);
+			}
+			PG_CATCH();
+			{
+				matview_maintenance_depth = old_depth;
+				PG_RE_THROW();
+			}
+			PG_END_TRY();
+
+			/* clear view delta tuplestores */
+			if (old_tuplestore)
+				tuplestore_clear(old_tuplestore);
+			if (new_tuplestore)
+				tuplestore_clear(new_tuplestore);
+		}
+	}
+
+	/* Clean up hash entry and delete tuplestores */
+	clean_up_IVM_hash_entry(entry, false);
+	if (old_tuplestore)
+	{
+		dest_old->rDestroy(dest_old);
+		tuplestore_end(old_tuplestore);
+	}
+	if (new_tuplestore)
+	{
+		dest_new->rDestroy(dest_new);
+		tuplestore_end(new_tuplestore);
+	}
+
+	/* Pop the original snapshot. */
+	PopActiveSnapshot();
+
+	table_close(matviewRel, NoLock);
+
+	/* Roll back any GUC changes */
+	AtEOXact_GUC(false, save_nestlevel);
+
+	/* Restore userid and security context */
+	SetUserIdAndSecContext(save_userid, save_sec_context);
+
+	return PointerGetDatum(NULL);
+}
+
+/*
+ * rewrite_query_for_preupdate_state
+ *
+ * Rewrite the query so that base tables' RTEs will represent "pre-update"
+ * state of tables. This is necessary to calculate view delta after multiple
+ * tables are modified.
+ */
+static Query*
+rewrite_query_for_preupdate_state(Query *query, List *tables,
+								  ParseState *pstate, Oid matviewid)
+{
+	ListCell *lc;
+	int num_rte = list_length(query->rtable);
+	int i;
+
+
+	/* register delta ENRs */
+	register_delta_ENRs(pstate, query, tables);
+
+	/* XXX: Is necessary? Is this right timing? */
+	AcquireRewriteLocks(query, true, false);
+
+	i = 1;
+	foreach(lc, query->rtable)
+	{
+		RangeTblEntry *r = (RangeTblEntry*) lfirst(lc);
+
+		ListCell *lc2;
+		foreach(lc2, tables)
+		{
+			MV_TriggerTable *table = (MV_TriggerTable *) lfirst(lc2);
+			/*
+			 * if the modified table is found then replace the original RTE with
+			 * "pre-state" RTE and append its index to the list.
+			 */
+			if (r->relid == table->table_id)
+			{
+				List *securityQuals;
+				List *withCheckOptions;
+				bool  hasRowSecurity;
+				bool  hasSubLinks;
+
+				RangeTblEntry *rte_pre = get_prestate_rte(r, table, pstate->p_queryEnv, matviewid);
+
+				/*
+				 * Set a row security poslicies of the modified table to the subquery RTE which
+				 * represents the pre-update state of the table.
+				 */
+				get_row_security_policies(query, table->original_rte, i,
+										  &securityQuals, &withCheckOptions,
+										  &hasRowSecurity, &hasSubLinks);
+
+				if (hasRowSecurity)
+				{
+					query->hasRowSecurity = true;
+					rte_pre->security_barrier = true;
+				}
+				if (hasSubLinks)
+					query->hasSubLinks = true;
+
+				rte_pre->securityQuals = securityQuals;
+				lfirst(lc) = rte_pre;
+
+				table->rte_indexes = lappend_int(table->rte_indexes, i);
+				break;
+			}
+		}
+
+		/* finish the loop if we processed all RTE included in the original query */
+		if (i++ >= num_rte)
+			break;
+	}
+
+	return query;
+}
+
+/*
+ * register_delta_ENRs
+ *
+ * For all modified tables, make ENRs for their transition tables
+ * and register them to the queryEnv. ENR's RTEs are also appended
+ * into the list in query tree.
+ */
+static void
+register_delta_ENRs(ParseState *pstate, Query *query, List *tables)
+{
+	QueryEnvironment *queryEnv = pstate->p_queryEnv;
+	ListCell *lc;
+	RangeTblEntry	*rte;
+
+	foreach(lc, tables)
+	{
+		MV_TriggerTable *table = (MV_TriggerTable *) lfirst(lc);
+		ListCell *lc2;
+		int count;
+
+		count = 0;
+		foreach(lc2, table->old_tuplestores)
+		{
+			Tuplestorestate *oldtable = (Tuplestorestate *) lfirst(lc2);
+			EphemeralNamedRelation enr =
+				palloc(sizeof(EphemeralNamedRelationData));
+			ParseNamespaceItem *nsitem;
+
+			enr->md.name = make_delta_enr_name("old", table->table_id, count);
+			enr->md.reliddesc = table->table_id;
+			enr->md.tupdesc = NULL;
+			enr->md.enrtype = ENR_NAMED_TUPLESTORE;
+			enr->md.enrtuples = tuplestore_tuple_count(oldtable);
+			enr->reldata = oldtable;
+			register_ENR(queryEnv, enr);
+
+			nsitem = addRangeTableEntryForENR(pstate, makeRangeVar(NULL, enr->md.name, -1), true);
+			rte = nsitem->p_rte;
+
+			query->rtable = lappend(query->rtable, rte);
+
+			count++;
+		}
+
+		count = 0;
+		foreach(lc2, table->new_tuplestores)
+		{
+			Tuplestorestate *newtable = (Tuplestorestate *) lfirst(lc2);
+			EphemeralNamedRelation enr =
+				palloc(sizeof(EphemeralNamedRelationData));
+			ParseNamespaceItem *nsitem;
+
+			enr->md.name = make_delta_enr_name("new", table->table_id, count);
+			enr->md.reliddesc = table->table_id;
+			enr->md.tupdesc = NULL;
+			enr->md.enrtype = ENR_NAMED_TUPLESTORE;
+			enr->md.enrtuples = tuplestore_tuple_count(newtable);
+			enr->reldata = newtable;
+			register_ENR(queryEnv, enr);
+
+			nsitem = addRangeTableEntryForENR(pstate, makeRangeVar(NULL, enr->md.name, -1), true);
+			rte = nsitem->p_rte;
+
+			query->rtable = lappend(query->rtable, rte);
+
+			count++;
+		}
+	}
+}
+
+#define DatumGetItemPointer(X)	 ((ItemPointer) DatumGetPointer(X))
+#define PG_GETARG_ITEMPOINTER(n) DatumGetItemPointer(PG_GETARG_DATUM(n))
+
+/*
+ * ivm_visible_in_prestate
+ *
+ * Check visibility of a tuple specified by the tableoid and item pointer
+ * using the snapshot taken just before the table was modified.
+ */
+Datum
+ivm_visible_in_prestate(PG_FUNCTION_ARGS)
+{
+	Oid			tableoid = PG_GETARG_OID(0);
+	ItemPointer itemPtr = PG_GETARG_ITEMPOINTER(1);
+	Oid			matviewOid = PG_GETARG_OID(2);
+	MV_TriggerHashEntry *entry;
+	MV_TriggerTable		*table = NULL;
+	ListCell   *lc;
+	bool	found;
+	bool	result;
+
+	if (!in_delta_calculation)
+		ereport(ERROR,
+				(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+				 errmsg("ivm_visible_in_prestate can be called only in delta calculation")));
+
+	entry = (MV_TriggerHashEntry *) hash_search(mv_trigger_info,
+											  (void *) &matviewOid,
+											  HASH_FIND, &found);
+	Assert (found && entry != NULL);
+
+	foreach(lc, entry->tables)
+	{
+		table = (MV_TriggerTable *) lfirst(lc);
+		if (table->table_id == tableoid)
+			break;
+	}
+
+	Assert (table != NULL);
+
+	result = table_tuple_fetch_row_version(table->rel, itemPtr, entry->snapshot, table->slot);
+
+	PG_RETURN_BOOL(result);
+}
+
+/*
+ * get_prestate_rte
+ *
+ * Rewrite RTE of the modified table to a subquery which represents
+ * "pre-state" table. The original RTE is saved in table->rte_original.
+ */
+static RangeTblEntry*
+get_prestate_rte(RangeTblEntry *rte, MV_TriggerTable *table,
+				 QueryEnvironment *queryEnv, Oid matviewid)
+{
+	StringInfoData str;
+	RawStmt *raw;
+	Query *subquery;
+	Relation rel;
+	ParseState *pstate;
+	char *relname;
+	int i;
+
+	pstate = make_parsestate(NULL);
+	pstate->p_queryEnv = queryEnv;
+	pstate->p_expr_kind = EXPR_KIND_SELECT_TARGET;
+
+	/*
+	 * We can use NoLock here since AcquireRewriteLocks should
+	 * have locked the relation already.
+	 */
+	rel = table_open(table->table_id, NoLock);
+	relname = quote_qualified_identifier(
+					get_namespace_name(RelationGetNamespace(rel)),
+									   RelationGetRelationName(rel));
+	table_close(rel, NoLock);
+
+	/*
+	 * Filtering inserted row using the snapshot taken before the table
+	 * is modified. ctid is required for maintaining outer join views.
+	 */
+	initStringInfo(&str);
+	appendStringInfo(&str,
+		"SELECT t.* FROM %s t"
+		" WHERE pg_catalog.ivm_visible_in_prestate(t.tableoid, t.ctid ,%d::pg_catalog.oid)",
+			relname, matviewid);
+
+	/*
+	 * Append deleted rows contained in old transition tables.
+	 */
+	for (i = 0; i < list_length(table->old_tuplestores); i++)
+	{
+		appendStringInfo(&str, " UNION ALL ");
+		appendStringInfo(&str," SELECT * FROM %s",
+			make_delta_enr_name("old", table->table_id, i));
+	}
+
+	/* Get a subquery representing pre-state of the table */
+	raw = (RawStmt*)linitial(raw_parser(str.data, RAW_PARSE_DEFAULT));
+	subquery = transformStmt(pstate, raw->stmt);
+
+	/* save the original RTE */
+	table->original_rte = copyObject(rte);
+
+	rte->rtekind = RTE_SUBQUERY;
+	rte->subquery = subquery;
+	rte->security_barrier = false;
+
+	/* Clear fields that should not be set in a subquery RTE */
+	rte->relid = InvalidOid;
+	rte->relkind = 0;
+	rte->rellockmode = 0;
+	rte->tablesample = NULL;
+	rte->perminfoindex = 0;         /* no permission checking for this RTE */
+	rte->inh = false;			/* must not be set for a subquery */
+
+	return rte;
+}
+
+/*
+ * make_delta_enr_name
+ *
+ * Make a name for ENR of a transition table from the base table's oid.
+ * prefix will be "new" or "old" depending on its transition table kind..
+ */
+static char*
+make_delta_enr_name(const char *prefix, Oid relid, int count)
+{
+	char buf[NAMEDATALEN];
+	char *name;
+
+	snprintf(buf, NAMEDATALEN, "__ivm_%s_%u_%u", prefix, relid, count);
+	name = pstrdup(buf);
+
+	return name;
+}
+
+/*
+ * replace_rte_with_delta
+ *
+ * Replace RTE of the modified table with a single table delta that combine its
+ * all transition tables.
+ */
+static RangeTblEntry*
+replace_rte_with_delta(RangeTblEntry *rte, MV_TriggerTable *table, bool is_new,
+					   QueryEnvironment *queryEnv)
+{
+	Oid relid = table->table_id;
+	StringInfoData str;
+	ParseState	*pstate;
+	RawStmt *raw;
+	Query *sub;
+	int		num_tuplestores = list_length(is_new ? table->new_tuplestores : table->old_tuplestores);
+	int		i;
+
+	/* the previous RTE must be a subquery which represents "pre-state" table */
+	Assert(rte->rtekind == RTE_SUBQUERY);
+
+	/* Create a ParseState for rewriting the view definition query */
+	pstate = make_parsestate(NULL);
+	pstate->p_queryEnv = queryEnv;
+	pstate->p_expr_kind = EXPR_KIND_SELECT_TARGET;
+
+	initStringInfo(&str);
+
+	for (i = 0; i < num_tuplestores; i++)
+	{
+		if (i > 0)
+			appendStringInfo(&str, " UNION ALL ");
+
+		appendStringInfo(&str,
+			" SELECT * FROM %s",
+			make_delta_enr_name(is_new ? "new" : "old", relid, i));
+	}
+
+	raw = (RawStmt*)linitial(raw_parser(str.data, RAW_PARSE_DEFAULT));
+	sub = transformStmt(pstate, raw->stmt);
+
+	/*
+	 * Update the subquery so that it represent the combined transition
+	 * table.  Note that we leave the security_barrier and securityQuals
+	 * fields so that the subquery relation can be protected by the RLS
+	 * policy as same as the modified table.
+	 */
+	rte->rtekind = RTE_SUBQUERY;
+	rte->subquery = sub;
+
+	return rte;
+}
+
+/*
+ * rewrite_query_for_counting
+ *
+ * Rewrite query for counting duplicated tuples.
+ */
+static Query *
+rewrite_query_for_counting(Query *query, ParseState *pstate)
+{
+	TargetEntry *tle_count;
+	FuncCall *fn;
+	Node *node;
+
+	/* Add count(*) for counting distinct tuples in views */
+	fn = makeFuncCall(SystemFuncName("count"), NIL, COERCE_EXPLICIT_CALL, -1);
+	fn->agg_star = true;
+	if (!query->groupClause && !query->hasAggs)
+		query->groupClause = transformDistinctClause(NULL, &query->targetList, query->sortClause, false);
+
+	node = ParseFuncOrColumn(pstate, fn->funcname, NIL, NULL, fn, false, -1);
+
+	tle_count = makeTargetEntry((Expr *) node,
+								list_length(query->targetList) + 1,
+								pstrdup("__ivm_count__"),
+								false);
+	query->targetList = lappend(query->targetList, tle_count);
+	query->hasAggs = true;
+
+	return query;
+}
+
+/*
+ * calc_delta
+ *
+ * Calculate view deltas generated under the modification of a table specified
+ * by the RTE index.
+ */
+static void
+calc_delta(MV_TriggerTable *table, int rte_index, Query *query,
+			DestReceiver *dest_old, DestReceiver *dest_new,
+			TupleDesc *tupdesc_old, TupleDesc *tupdesc_new,
+			QueryEnvironment *queryEnv)
+{
+	ListCell *lc = list_nth_cell(query->rtable, rte_index - 1);
+	RangeTblEntry *rte = (RangeTblEntry *) lfirst(lc);
+
+	in_delta_calculation = true;
+
+	/* Generate old delta */
+	if (list_length(table->old_tuplestores) > 0)
+	{
+		/* Replace the modified table with the old delta table and calculate the old view delta. */
+		replace_rte_with_delta(rte, table, false, queryEnv);
+		refresh_matview_datafill(dest_old, query, queryEnv, tupdesc_old, "");
+	}
+
+	/* Generate new delta */
+	if (list_length(table->new_tuplestores) > 0)
+	{
+		/* Replace the modified table with the new delta table and calculate the new view delta*/
+		replace_rte_with_delta(rte, table, true, queryEnv);
+		refresh_matview_datafill(dest_new, query, queryEnv, tupdesc_new, "");
+	}
+
+	in_delta_calculation = false;
+}
+
+/*
+ * rewrite_query_for_postupdate_state
+ *
+ * Rewrite the query so that the specified base table's RTEs will represent
+ * "post-update" state of tables. This is called after the view delta
+ * calculation due to changes on this table finishes.
+ */
+static Query*
+rewrite_query_for_postupdate_state(Query *query, MV_TriggerTable *table, int rte_index)
+{
+	ListCell *lc = list_nth_cell(query->rtable, rte_index - 1);
+
+	/* Retore the original RTE */
+	lfirst(lc) = table->original_rte;
+
+	return query;
+}
+
+/*
+ * apply_delta
+ *
+ * Apply deltas to the materialized view. In outer join cases, this requires
+ * the view maintenance graph.
+ */
+static void
+apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *new_tuplestores,
+			TupleDesc tupdesc_old, TupleDesc tupdesc_new,
+			Query *query)
+{
+	StringInfoData querybuf;
+	StringInfoData target_list_buf;
+	Relation	matviewRel;
+	char	   *matviewname;
+	ListCell	*lc;
+	int			i;
+	List	   *keys = NIL;
+
+
+	/*
+	 * get names of the materialized view and delta tables
+	 */
+
+	matviewRel = table_open(matviewOid, NoLock);
+	matviewname = quote_qualified_identifier(get_namespace_name(RelationGetNamespace(matviewRel)),
+											 RelationGetRelationName(matviewRel));
+
+	/*
+	 * Build parts of the maintenance queries
+	 */
+
+	initStringInfo(&querybuf);
+	initStringInfo(&target_list_buf);
+
+	/* build string of target list */
+	for (i = 0; i < matviewRel->rd_att->natts; i++)
+	{
+		Form_pg_attribute attr = TupleDescAttr(matviewRel->rd_att, i);
+		char   *resname = NameStr(attr->attname);
+
+		if (i != 0)
+			appendStringInfo(&target_list_buf, ", ");
+		appendStringInfo(&target_list_buf, "%s", quote_qualified_identifier(NULL, resname));
+	}
+
+	i = 0;
+	foreach (lc, query->targetList)
+	{
+		TargetEntry *tle = (TargetEntry *) lfirst(lc);
+		Form_pg_attribute attr = TupleDescAttr(matviewRel->rd_att, i);
+
+		i++;
+
+		if (tle->resjunk)
+			continue;
+
+		keys = lappend(keys, attr);
+	}
+
+	/* Start maintaining the materialized view. */
+	OpenMatViewIncrementalMaintenance();
+
+	/* Open SPI context. */
+	if (SPI_connect() != SPI_OK_CONNECT)
+		elog(ERROR, "SPI_connect failed");
+
+	/* For tuple deletion */
+	if (old_tuplestores && tuplestore_tuple_count(old_tuplestores) > 0)
+	{
+		EphemeralNamedRelation enr = palloc(sizeof(EphemeralNamedRelationData));
+		int				rc;
+
+		/* convert tuplestores to ENR, and register for SPI */
+		enr->md.name = pstrdup(OLD_DELTA_ENRNAME);
+		enr->md.reliddesc = InvalidOid;
+		enr->md.tupdesc = tupdesc_old;
+		enr->md.enrtype = ENR_NAMED_TUPLESTORE;
+		enr->md.enrtuples = tuplestore_tuple_count(old_tuplestores);
+		enr->reldata = old_tuplestores;
+
+		rc = SPI_register_relation(enr);
+		if (rc != SPI_OK_REL_REGISTER)
+			elog(ERROR, "SPI_register failed");
+
+		apply_old_delta(matviewname, OLD_DELTA_ENRNAME, keys);
+
+	}
+	/* For tuple insertion */
+	if (new_tuplestores && tuplestore_tuple_count(new_tuplestores) > 0)
+	{
+		EphemeralNamedRelation enr = palloc(sizeof(EphemeralNamedRelationData));
+		int rc;
+
+		/* convert tuplestores to ENR, and register for SPI */
+		enr->md.name = pstrdup(NEW_DELTA_ENRNAME);
+		enr->md.reliddesc = InvalidOid;
+		enr->md.tupdesc = tupdesc_new;;
+		enr->md.enrtype = ENR_NAMED_TUPLESTORE;
+		enr->md.enrtuples = tuplestore_tuple_count(new_tuplestores);
+		enr->reldata = new_tuplestores;
+
+		rc = SPI_register_relation(enr);
+		if (rc != SPI_OK_REL_REGISTER)
+			elog(ERROR, "SPI_register failed");
+
+		/* apply new delta */
+		apply_new_delta(matviewname, NEW_DELTA_ENRNAME, &target_list_buf);
+	}
+
+	/* We're done maintaining the materialized view. */
+	CloseMatViewIncrementalMaintenance();
+
+	table_close(matviewRel, NoLock);
+
+	/* Close SPI context. */
+	if (SPI_finish() != SPI_OK_FINISH)
+		elog(ERROR, "SPI_finish failed");
+}
+
+/*
+ * apply_old_delta
+ *
+ * Execute a query for applying a delta table given by deltname_old
+ * which contains tuples to be deleted from to a materialized view given by
+ * matviewname.  This is used when counting is not required.
+ */
+static void
+apply_old_delta(const char *matviewname, const char *deltaname_old,
+				List *keys)
+{
+	StringInfoData	querybuf;
+	StringInfoData	keysbuf;
+	char   *match_cond;
+	ListCell *lc;
+
+	/* build WHERE condition for searching tuples to be deleted */
+	match_cond = get_matching_condition_string(keys);
+
+	/* build string of keys list */
+	initStringInfo(&keysbuf);
+	foreach (lc, keys)
+	{
+		Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc);
+		char   *resname = NameStr(attr->attname);
+		appendStringInfo(&keysbuf, "%s", quote_qualified_identifier("mv", resname));
+		if (lnext(keys, lc))
+			appendStringInfo(&keysbuf, ", ");
+	}
+
+	/* Search for matching tuples from the view and update or delete if found. */
+	initStringInfo(&querybuf);
+	appendStringInfo(&querybuf,
+	"DELETE FROM %s WHERE ctid IN ("
+		"SELECT tid FROM (SELECT pg_catalog.row_number() over (partition by %s) AS \"__ivm_row_number__\","
+								  "mv.ctid AS tid,"
+								  "diff.\"__ivm_count__\""
+						 "FROM %s AS mv, %s AS diff "
+						 "WHERE %s) v "
+					"WHERE v.\"__ivm_row_number__\" OPERATOR(pg_catalog.<=) v.\"__ivm_count__\")",
+					matviewname,
+					keysbuf.data,
+					matviewname, deltaname_old,
+					match_cond);
+
+	if (SPI_exec(querybuf.data, 0) != SPI_OK_DELETE)
+		elog(ERROR, "SPI_exec failed: %s", querybuf.data);
+}
+
+/*
+ * apply_new_delta
+ *
+ * Execute a query for applying a delta table given by deltname_new
+ * which contains tuples to be inserted into a materialized view given by
+ * matviewname.  This is used when counting is not required.
+ */
+static void
+apply_new_delta(const char *matviewname, const char *deltaname_new,
+				StringInfo target_list)
+{
+	StringInfoData	querybuf;
+
+	/* Search for matching tuples from the view and update or delete if found. */
+	initStringInfo(&querybuf);
+	appendStringInfo(&querybuf,
+					"INSERT INTO %s (%s) SELECT %s FROM ("
+						"SELECT diff.*, pg_catalog.generate_series(1, diff.\"__ivm_count__\")"
+							" AS __ivm_generate_series__ "
+						"FROM %s AS diff) AS v",
+					matviewname, target_list->data, target_list->data,
+					deltaname_new);
+
+	if (SPI_exec(querybuf.data, 0) != SPI_OK_INSERT)
+		elog(ERROR, "SPI_exec failed: %s", querybuf.data);
+}
+
+/*
+ * get_matching_condition_string
+ *
+ * Build a predicate string for looking for a tuple with given keys.
+ */
+static char *
+get_matching_condition_string(List *keys)
+{
+	StringInfoData match_cond;
+	ListCell	*lc;
+
+	/* If there is no key columns, the condition is always true. */
+	if (keys == NIL)
+		return "true";
+
+	initStringInfo(&match_cond);
+	foreach (lc, keys)
+	{
+		Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc);
+		char   *resname = NameStr(attr->attname);
+		char   *mv_resname = quote_qualified_identifier("mv", resname);
+		char   *diff_resname = quote_qualified_identifier("diff", resname);
+		Oid		typid = attr->atttypid;
+
+		/* Considering NULL values, we can not use simple = operator. */
+		appendStringInfo(&match_cond, "(");
+		generate_equal(&match_cond, typid, mv_resname, diff_resname);
+		appendStringInfo(&match_cond, " OR (%s IS NULL AND %s IS NULL))",
+						 mv_resname, diff_resname);
+
+		if (lnext(keys, lc))
+			appendStringInfo(&match_cond, " AND ");
+	}
+
+	return match_cond.data;
+}
+
+/*
+ * generate_equals
+ *
+ * Generate an equality clause using given operands' default equality
+ * operator.
+ */
+static void
+generate_equal(StringInfo querybuf, Oid opttype,
+			   const char *leftop, const char *rightop)
+{
+	TypeCacheEntry *typentry;
+
+	typentry = lookup_type_cache(opttype, TYPECACHE_EQ_OPR);
+	if (!OidIsValid(typentry->eq_opr))
+		ereport(ERROR,
+				(errcode(ERRCODE_UNDEFINED_FUNCTION),
+				 errmsg("could not identify an equality operator for type %s",
+						format_type_be_qualified(opttype))));
+
+	generate_operator_clause(querybuf,
+							 leftop, opttype,
+							 typentry->eq_opr,
+							 rightop, opttype);
+}
+
+/*
+ * mv_InitHashTables
+ */
+static void
+mv_InitHashTables(void)
+{
+	HASHCTL		ctl;
+
+	memset(&ctl, 0, sizeof(ctl));
+	ctl.keysize = sizeof(Oid);
+	ctl.entrysize = sizeof(MV_TriggerHashEntry);
+	mv_trigger_info = hash_create("MV trigger info",
+								 MV_INIT_QUERYHASHSIZE,
+								 &ctl, HASH_ELEM | HASH_BLOBS);
+}
+
+/*
+ * AtAbort_IVM
+ *
+ * Clean up hash entries for all materialized views. This is called at
+ * transaction abort.
+ */
+void
+AtAbort_IVM()
+{
+	HASH_SEQ_STATUS seq;
+	MV_TriggerHashEntry *entry;
+
+	if (mv_trigger_info)
+	{
+		hash_seq_init(&seq, mv_trigger_info);
+		while ((entry = hash_seq_search(&seq)) != NULL)
+			clean_up_IVM_hash_entry(entry, true);
+	}
+	in_delta_calculation = false;
+}
+
+/*
+ * clean_up_IVM_hash_entry
+ *
+ * Clean up tuple stores and hash entries for a materialized view after its
+ * maintenance finished.
+ */
+static void
+clean_up_IVM_hash_entry(MV_TriggerHashEntry *entry, bool is_abort)
+{
+	bool found;
+	ListCell *lc;
+
+	foreach(lc, entry->tables)
+	{
+		MV_TriggerTable *table = (MV_TriggerTable *) lfirst(lc);
+
+		list_free(table->old_tuplestores);
+		list_free(table->new_tuplestores);
+		if (!is_abort)
+		{
+			ExecDropSingleTupleTableSlot(table->slot);
+			table_close(table->rel, NoLock);
+		}
+	}
+	list_free(entry->tables);
+
+	if (!is_abort)
+		UnregisterSnapshot(entry->snapshot);
+
+	hash_search(mv_trigger_info, (void *) &entry->matview_id, HASH_REMOVE, &found);
+}
+
+/*
+ * isIvmName
+ *
+ * Check if this is a IVM hidden column from the name.
+ */
+bool
+isIvmName(const char *s)
+{
+	if (s)
+		return (strncmp(s, "__ivm_", 6) == 0);
+	return false;
+}
diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat
index 9805bc6118..f6896d77b4 100644
--- a/src/include/catalog/pg_proc.dat
+++ b/src/include/catalog/pg_proc.dat
@@ -12062,4 +12062,14 @@
   proname => 'any_value_transfn', prorettype => 'anyelement',
   proargtypes => 'anyelement anyelement', prosrc => 'any_value_transfn' },
 
+# IVM
+{ oid => '786', descr => 'ivm trigger (before)',
+  proname => 'IVM_immediate_before', provolatile => 'v', prorettype => 'trigger',
+  proargtypes => '', prosrc => 'IVM_immediate_before' },
+{ oid => '787', descr => 'ivm trigger (after)',
+  proname => 'IVM_immediate_maintenance', provolatile => 'v', prorettype => 'trigger',
+  proargtypes => '', prosrc => 'IVM_immediate_maintenance' },
+{ oid => '788', descr => 'ivm filetring ',
+  proname => 'ivm_visible_in_prestate', provolatile => 's', prorettype => 'bool',
+  proargtypes => 'oid tid oid', prosrc => 'ivm_visible_in_prestate' },
 ]
diff --git a/src/include/commands/createas.h b/src/include/commands/createas.h
index 3647f96f73..09a64fa2e5 100644
--- a/src/include/commands/createas.h
+++ b/src/include/commands/createas.h
@@ -16,6 +16,7 @@
 
 #include "catalog/objectaddress.h"
 #include "nodes/params.h"
+#include "nodes/pathnodes.h"
 #include "parser/parse_node.h"
 #include "tcop/dest.h"
 #include "utils/queryenvironment.h"
@@ -25,6 +26,9 @@ extern ObjectAddress ExecCreateTableAs(ParseState *pstate, CreateTableAsStmt *st
 									   ParamListInfo params, QueryEnvironment *queryEnv,
 									   QueryCompletion *qc);
 
+extern void CreateIvmTriggersOnBaseTables(Query *qry, Oid matviewOid);
+extern void CreateIndexOnIMMV(Query *query, Relation matviewRel);
+
 extern int	GetIntoRelEFlags(IntoClause *intoClause);
 
 extern DestReceiver *CreateIntoRelDestReceiver(IntoClause *intoClause);
diff --git a/src/include/commands/matview.h b/src/include/commands/matview.h
index 9eaa6212a1..504b83a446 100644
--- a/src/include/commands/matview.h
+++ b/src/include/commands/matview.h
@@ -15,6 +15,7 @@
 #define MATVIEW_H
 
 #include "catalog/objectaddress.h"
+#include "fmgr.h"
 #include "nodes/params.h"
 #include "nodes/parsenodes.h"
 #include "tcop/dest.h"
@@ -23,6 +24,8 @@
 
 extern void SetMatViewPopulatedState(Relation relation, bool newstate);
 
+extern void SetMatViewIVMState(Relation relation, bool newstate);
+
 extern ObjectAddress ExecRefreshMatView(RefreshMatViewStmt *stmt, const char *queryString,
 										ParamListInfo params, QueryCompletion *qc);
 
@@ -30,4 +33,10 @@ extern DestReceiver *CreateTransientRelDestReceiver(Oid transientoid);
 
 extern bool MatViewIncrementalMaintenanceIsEnabled(void);
 
+extern Datum IVM_immediate_before(PG_FUNCTION_ARGS);
+extern Datum IVM_immediate_maintenance(PG_FUNCTION_ARGS);
+extern Datum IVM_visible_in_prestate(PG_FUNCTION_ARGS);
+extern void AtAbort_IVM(void);
+extern bool isIvmName(const char *s);
+
 #endif							/* MATVIEW_H */
-- 
2.25.1


--Multipart=_Mon__28_Aug_2023_11_52_52_+0900_hj6L5h176QaSGtg7
Content-Type: text/x-diff;
 name="v29-0007-Add-DISTINCT-support-for-IVM.patch"
Content-Disposition: attachment;
 filename="v29-0007-Add-DISTINCT-support-for-IVM.patch"
Content-Transfer-Encoding: 7bit



^ permalink  raw  reply  [nested|flat] 101+ messages in thread

* [PATCH v30 06/11] Add Incremental View Maintenance support
@ 2023-05-31 09:59  Yugo Nagata <[email protected]>
  0 siblings, 0 replies; 101+ messages in thread

From: Yugo Nagata @ 2023-05-31 09:59 UTC (permalink / raw)

In this implementation, AFTER triggers are used to collect
tuplestores containing transition table contents. When multiple tables
are changed, multiple AFTER triggers are invoked, then the final AFTER
trigger performs actual update of the matview. In addition, BEFORE
triggers are also used to handle global information for view
maintenance.

To calculate view deltas, we need both pre-state and post-state of base
tables. Post-update states are available in AFTER trigger, and pre-update
states can be calculated by removing inserted tuples and appending deleted
tuples. Insterted tuples are filtered using the snapshot taken before
table modiication, and deleted tuples are contained in the old transition
table.

Incrementally Maintainable Materialized Views (IMMV) can contain
duplicated tuples.

This patch also allows self-join, simultaneous updates of more than
one base table, and multiple updates of the same base table.
---
 src/backend/access/transam/xact.c |    5 +
 src/backend/commands/createas.c   |  681 ++++++++++++++
 src/backend/commands/matview.c    | 1466 ++++++++++++++++++++++++++++-
 src/include/catalog/pg_proc.dat   |   10 +
 src/include/commands/createas.h   |    4 +
 src/include/commands/matview.h    |    9 +
 6 files changed, 2140 insertions(+), 35 deletions(-)

diff --git a/src/backend/access/transam/xact.c b/src/backend/access/transam/xact.c
index 70ab6e27a1..0de7ab6abe 100644
--- a/src/backend/access/transam/xact.c
+++ b/src/backend/access/transam/xact.c
@@ -36,6 +36,7 @@
 #include "catalog/pg_enum.h"
 #include "catalog/storage.h"
 #include "commands/async.h"
+#include "commands/matview.h"
 #include "commands/tablecmds.h"
 #include "commands/trigger.h"
 #include "common/pg_prng.h"
@@ -2819,6 +2820,7 @@ AbortTransaction(void)
 	AtAbort_Notify();
 	AtEOXact_RelationMap(false, is_parallel_worker);
 	AtAbort_Twophase();
+	AtAbort_IVM();
 
 	/*
 	 * Advertise the fact that we aborted in pg_xact (assuming that we got as
@@ -5097,6 +5099,9 @@ AbortSubTransaction(void)
 	pgstat_progress_end_command();
 	UnlockBuffers();
 
+	/* Clean up hash entries for incremental view maintenance */
+	AtAbort_IVM();
+
 	/* Reset WAL record construction state */
 	XLogResetInsertion();
 
diff --git a/src/backend/commands/createas.c b/src/backend/commands/createas.c
index 16a2fe65e6..08262100ea 100644
--- a/src/backend/commands/createas.c
+++ b/src/backend/commands/createas.c
@@ -32,15 +32,26 @@
 #include "access/xact.h"
 #include "access/xlog.h"
 #include "catalog/namespace.h"
+#include "catalog/index.h"
+#include "catalog/pg_constraint.h"
+#include "catalog/pg_inherits.h"
+#include "catalog/pg_trigger.h"
 #include "catalog/toasting.h"
 #include "commands/createas.h"
+#include "commands/defrem.h"
 #include "commands/matview.h"
 #include "commands/prepare.h"
 #include "commands/tablecmds.h"
+#include "commands/tablespace.h"
+#include "commands/trigger.h"
 #include "commands/view.h"
 #include "miscadmin.h"
+#include "optimizer/optimizer.h"
+#include "optimizer/prep.h"
 #include "nodes/makefuncs.h"
 #include "nodes/nodeFuncs.h"
+#include "parser/parser.h"
+#include "parser/parsetree.h"
 #include "parser/parse_clause.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/smgr.h"
@@ -73,6 +84,12 @@ static bool intorel_receive(TupleTableSlot *slot, DestReceiver *self);
 static void intorel_shutdown(DestReceiver *self);
 static void intorel_destroy(DestReceiver *self);
 
+static void CreateIvmTriggersOnBaseTablesRecurse(Query *qry, Node *node, Oid matviewOid,
+									 Relids *relids, bool ex_lock);
+static void CreateIvmTrigger(Oid relOid, Oid viewOid, int16 type, int16 timing, bool ex_lock);
+static void check_ivm_restriction(Node *node);
+static bool check_ivm_restriction_walker(Node *node, void *context);
+static Bitmapset *get_primary_key_attnos_from_query(Query *query, List **constraintList);
 
 /*
  * create_ctas_internal
@@ -282,6 +299,18 @@ ExecCreateTableAs(ParseState *pstate, CreateTableAsStmt *stmt,
 		save_nestlevel = NewGUCNestLevel();
 	}
 
+	if (is_matview && into->ivm)
+	{
+		/* check if the query is supported in IMMV definition */
+		if (contain_mutable_functions((Node *) query))
+			ereport(ERROR,
+					(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+					 errmsg("mutable function is not supported on incrementally maintainable materialized view"),
+					 errhint("functions must be marked IMMUTABLE")));
+
+		check_ivm_restriction((Node *) query);
+	}
+
 	if (into->skipData)
 	{
 		/*
@@ -358,6 +387,27 @@ ExecCreateTableAs(ParseState *pstate, CreateTableAsStmt *stmt,
 
 		/* Restore userid and security context */
 		SetUserIdAndSecContext(save_userid, save_sec_context);
+
+		if (into->ivm)
+		{
+			Oid matviewOid = address.objectId;
+			Relation matviewRel = table_open(matviewOid, NoLock);
+
+			/*
+			 * Mark relisivm field, if it's a matview and into->ivm is true.
+			 */
+			SetMatViewIVMState(matviewRel, true);
+
+			if (!into->skipData)
+			{
+				/* Create an index on incremental maintainable materialized view, if possible */
+				CreateIndexOnIMMV((Query *) into->viewQuery, matviewRel);
+
+				/* Create triggers on incremental maintainable materialized view */
+				CreateIvmTriggersOnBaseTables((Query *) into->viewQuery, matviewOid);
+			}
+			table_close(matviewRel, NoLock);
+		}
 	}
 
 	return address;
@@ -635,3 +685,634 @@ intorel_destroy(DestReceiver *self)
 {
 	pfree(self);
 }
+
+/*
+ * CreateIvmTriggersOnBaseTables -- create IVM triggers on all base tables
+ */
+void
+CreateIvmTriggersOnBaseTables(Query *qry, Oid matviewOid)
+{
+	Relids	relids = NULL;
+	bool	ex_lock = false;
+	RangeTblEntry *rte;
+
+	/* Immediately return if we don't have any base tables. */
+	if (list_length(qry->rtable) < 1)
+		return;
+
+	/*
+	 * If the view has more than one base tables, we need an exclusive lock
+	 * on the view so that the view would be maintained serially to avoid
+	 * the inconsistency that occurs when two base tables are modified in
+	 * concurrent transactions. However, if the view has only one table,
+	 * we can use a weaker lock.
+	 *
+	 * The type of lock should be determined here, because if we check the
+	 * view definition at maintenance time, we need to acquire a weaker lock,
+	 * and upgrading the lock level after this increases probability of
+	 * deadlock.
+	 */
+
+	rte = list_nth(qry->rtable, 0);
+	if (list_length(qry->rtable) > 1 || rte->rtekind != RTE_RELATION)
+		ex_lock = true;
+
+	CreateIvmTriggersOnBaseTablesRecurse(qry, (Node *)qry, matviewOid, &relids, ex_lock);
+
+	bms_free(relids);
+}
+
+static void
+CreateIvmTriggersOnBaseTablesRecurse(Query *qry, Node *node, Oid matviewOid,
+									 Relids *relids, bool ex_lock)
+{
+	if (node == NULL)
+		return;
+
+	/* This can recurse, so check for excessive recursion */
+	check_stack_depth();
+
+	switch (nodeTag(node))
+	{
+		case T_Query:
+			{
+				Query *query = (Query *) node;
+
+				CreateIvmTriggersOnBaseTablesRecurse(qry, (Node *)query->jointree, matviewOid, relids, ex_lock);
+			}
+			break;
+
+		case T_RangeTblRef:
+			{
+				int			rti = ((RangeTblRef *) node)->rtindex;
+				RangeTblEntry *rte = rt_fetch(rti, qry->rtable);
+
+				if (rte->rtekind == RTE_RELATION && !bms_is_member(rte->relid, *relids))
+				{
+					CreateIvmTrigger(rte->relid, matviewOid, TRIGGER_TYPE_INSERT, TRIGGER_TYPE_BEFORE, ex_lock);
+					CreateIvmTrigger(rte->relid, matviewOid, TRIGGER_TYPE_DELETE, TRIGGER_TYPE_BEFORE, ex_lock);
+					CreateIvmTrigger(rte->relid, matviewOid, TRIGGER_TYPE_UPDATE, TRIGGER_TYPE_BEFORE, ex_lock);
+					CreateIvmTrigger(rte->relid, matviewOid, TRIGGER_TYPE_TRUNCATE, TRIGGER_TYPE_BEFORE, true);
+					CreateIvmTrigger(rte->relid, matviewOid, TRIGGER_TYPE_INSERT, TRIGGER_TYPE_AFTER, ex_lock);
+					CreateIvmTrigger(rte->relid, matviewOid, TRIGGER_TYPE_DELETE, TRIGGER_TYPE_AFTER, ex_lock);
+					CreateIvmTrigger(rte->relid, matviewOid, TRIGGER_TYPE_UPDATE, TRIGGER_TYPE_AFTER, ex_lock);
+					CreateIvmTrigger(rte->relid, matviewOid, TRIGGER_TYPE_TRUNCATE, TRIGGER_TYPE_AFTER, true);
+
+					*relids = bms_add_member(*relids, rte->relid);
+				}
+			}
+			break;
+
+		case T_FromExpr:
+			{
+				FromExpr   *f = (FromExpr *) node;
+				ListCell   *l;
+
+				foreach(l, f->fromlist)
+					CreateIvmTriggersOnBaseTablesRecurse(qry, lfirst(l), matviewOid, relids, ex_lock);
+			}
+			break;
+
+		case T_JoinExpr:
+			{
+				JoinExpr   *j = (JoinExpr *) node;
+
+				CreateIvmTriggersOnBaseTablesRecurse(qry, j->larg, matviewOid, relids, ex_lock);
+				CreateIvmTriggersOnBaseTablesRecurse(qry, j->rarg, matviewOid, relids, ex_lock);
+			}
+			break;
+
+		default:
+			elog(ERROR, "unrecognized node type: %d", (int) nodeTag(node));
+	}
+}
+
+/*
+ * CreateIvmTrigger -- create IVM trigger on a base table
+ */
+static void
+CreateIvmTrigger(Oid relOid, Oid viewOid, int16 type, int16 timing, bool ex_lock)
+{
+	ObjectAddress	refaddr;
+	ObjectAddress	address;
+	CreateTrigStmt *ivm_trigger;
+	List *transitionRels = NIL;
+
+	Assert(timing == TRIGGER_TYPE_BEFORE || timing == TRIGGER_TYPE_AFTER);
+
+	refaddr.classId = RelationRelationId;
+	refaddr.objectId = viewOid;
+	refaddr.objectSubId = 0;
+
+	ivm_trigger = makeNode(CreateTrigStmt);
+	ivm_trigger->relation = NULL;
+	ivm_trigger->row = false;
+
+	ivm_trigger->timing = timing;
+	ivm_trigger->events = type;
+
+	switch (type)
+	{
+		case TRIGGER_TYPE_INSERT:
+			ivm_trigger->trigname = (timing == TRIGGER_TYPE_BEFORE ? "IVM_trigger_ins_before" : "IVM_trigger_ins_after");
+			break;
+		case TRIGGER_TYPE_DELETE:
+			ivm_trigger->trigname = (timing == TRIGGER_TYPE_BEFORE ? "IVM_trigger_del_before" : "IVM_trigger_del_after");
+			break;
+		case TRIGGER_TYPE_UPDATE:
+			ivm_trigger->trigname = (timing == TRIGGER_TYPE_BEFORE ? "IVM_trigger_upd_before" : "IVM_trigger_upd_after");
+			break;
+		case TRIGGER_TYPE_TRUNCATE:
+			ivm_trigger->trigname = (timing == TRIGGER_TYPE_BEFORE ? "IVM_trigger_truncate_before" : "IVM_trigger_truncate_after");
+			break;
+		default:
+			elog(ERROR, "unsupported trigger type");
+	}
+
+	if (timing == TRIGGER_TYPE_AFTER)
+	{
+		if (type == TRIGGER_TYPE_INSERT || type == TRIGGER_TYPE_UPDATE)
+		{
+			TriggerTransition *n = makeNode(TriggerTransition);
+			n->name = "__ivm_newtable";
+			n->isNew = true;
+			n->isTable = true;
+
+			transitionRels = lappend(transitionRels, n);
+		}
+		if (type == TRIGGER_TYPE_DELETE || type == TRIGGER_TYPE_UPDATE)
+		{
+			TriggerTransition *n = makeNode(TriggerTransition);
+			n->name = "__ivm_oldtable";
+			n->isNew = false;
+			n->isTable = true;
+
+			transitionRels = lappend(transitionRels, n);
+		}
+	}
+
+	/*
+	 * XXX: When using DELETE or UPDATE, we must use exclusive lock for now
+	 * because apply_old_delta(_with_count) uses ctid to identify the tuple
+	 * to be deleted/deleted, but doesn't work in concurrent situations.
+	 *
+	 * If the view doesn't have aggregate, distinct, or tuple duplicate,
+	 * then it would work even in concurrent situations. However, we don't have
+	 * any way to guarantee the view has a unique key before opening the IMMV
+	 * at the maintenance time because users may drop the unique index.
+	 */
+
+	if (type == TRIGGER_TYPE_DELETE || type == TRIGGER_TYPE_UPDATE)
+		ex_lock = true;
+
+	ivm_trigger->funcname =
+		(timing == TRIGGER_TYPE_BEFORE ? SystemFuncName("IVM_immediate_before") : SystemFuncName("IVM_immediate_maintenance"));
+
+	ivm_trigger->columns = NIL;
+	ivm_trigger->transitionRels = transitionRels;
+	ivm_trigger->whenClause = NULL;
+	ivm_trigger->isconstraint = false;
+	ivm_trigger->deferrable = false;
+	ivm_trigger->initdeferred = false;
+	ivm_trigger->constrrel = NULL;
+	ivm_trigger->args = list_make2(
+		makeString(DatumGetPointer(DirectFunctionCall1(oidout, ObjectIdGetDatum(viewOid)))),
+		makeString(DatumGetPointer(DirectFunctionCall1(boolout, BoolGetDatum(ex_lock))))
+		);
+
+	address = CreateTrigger(ivm_trigger, NULL, relOid, InvalidOid, InvalidOid,
+						 InvalidOid, InvalidOid, InvalidOid, NULL, true, false);
+
+	recordDependencyOn(&address, &refaddr, DEPENDENCY_AUTO);
+
+	/* Make changes-so-far visible */
+	CommandCounterIncrement();
+}
+
+/*
+ * check_ivm_restriction --- look for specify nodes in the query tree
+ */
+static void
+check_ivm_restriction(Node *node)
+{
+	check_ivm_restriction_walker(node, NULL);
+}
+
+static bool
+check_ivm_restriction_walker(Node *node, void *context)
+{
+	if (node == NULL)
+		return false;
+
+	/*
+	 * We currently don't support Sub-Query.
+	 */
+	if (IsA(node, SubPlan) || IsA(node, SubLink))
+		ereport(ERROR,
+				(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+				 errmsg("subquery is not supported on incrementally maintainable materialized view")));
+
+	/* This can recurse, so check for excessive recursion */
+	check_stack_depth();
+
+	switch (nodeTag(node))
+	{
+		case T_Query:
+			{
+				Query *qry = (Query *)node;
+				ListCell   *lc;
+				List       *vars;
+
+				/* if contained CTE, return error */
+				if (qry->cteList != NIL)
+					ereport(ERROR,
+							(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+							 errmsg("CTE is not supported on incrementally maintainable materialized view")));
+				if (qry->havingQual != NULL)
+					ereport(ERROR,
+							(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+							 errmsg(" HAVING clause is not supported on incrementally maintainable materialized view")));
+				if (qry->sortClause != NIL)	/* There is a possibility that we don't need to return an error */
+					ereport(ERROR,
+							(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+							 errmsg("ORDER BY clause is not supported on incrementally maintainable materialized view")));
+				if (qry->limitOffset != NULL || qry->limitCount != NULL)
+					ereport(ERROR,
+							(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+							 errmsg("LIMIT/OFFSET clause is not supported on incrementally maintainable materialized view")));
+				if (qry->distinctClause)
+					ereport(ERROR,
+							(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+							 errmsg("DISTINCT is not supported on incrementally maintainable materialized view")));
+				if (qry->hasDistinctOn)
+					ereport(ERROR,
+							(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+							 errmsg("DISTINCT ON is not supported on incrementally maintainable materialized view")));
+				if (qry->hasWindowFuncs)
+					ereport(ERROR,
+							(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+							 errmsg("window functions are not supported on incrementally maintainable materialized view")));
+				if (qry->groupingSets != NIL)
+					ereport(ERROR,
+							(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+							 errmsg("GROUPING SETS, ROLLUP, or CUBE clauses is not supported on incrementally maintainable materialized view")));
+				if (qry->setOperations != NULL)
+					ereport(ERROR,
+							(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+							 errmsg("UNION/INTERSECT/EXCEPT statements are not supported on incrementally maintainable materialized view")));
+				if (list_length(qry->targetList) == 0)
+					ereport(ERROR,
+							(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+							 errmsg("empty target list is not supported on incrementally maintainable materialized view")));
+				if (qry->rowMarks != NIL)
+					ereport(ERROR,
+							(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+							 errmsg("FOR UPDATE/SHARE clause is not supported on incrementally maintainable materialized view")));
+
+				/* system column restrictions */
+				vars = pull_vars_of_level((Node *) qry, 0);
+				foreach(lc, vars)
+				{
+					if (IsA(lfirst(lc), Var))
+					{
+						Var *var = (Var *) lfirst(lc);
+						/* if system column, return error */
+						if (var->varattno < 0)
+							ereport(ERROR,
+									(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+									 errmsg("system column is not supported on incrementally maintainable materialized view")));
+					}
+				}
+
+				/* restrictions for rtable */
+				foreach(lc, qry->rtable)
+				{
+					RangeTblEntry *rte = (RangeTblEntry *) lfirst(lc);
+
+					if (rte->subquery)
+						ereport(ERROR,
+								(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+								 errmsg("subquery is not supported on incrementally maintainable materialized view")));
+
+					if (rte->tablesample != NULL)
+						ereport(ERROR,
+								(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+								 errmsg("TABLESAMPLE clause is not supported on incrementally maintainable materialized view")));
+
+					if (rte->relkind == RELKIND_PARTITIONED_TABLE)
+						ereport(ERROR,
+								(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+								 errmsg("partitioned table is not supported on incrementally maintainable materialized view")));
+
+					if (rte->relkind == RELKIND_RELATION && has_superclass(rte->relid))
+						ereport(ERROR,
+								(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+								 errmsg("partitions is not supported on incrementally maintainable materialized view")));
+
+					if (rte->relkind == RELKIND_RELATION && find_inheritance_children(rte->relid, NoLock) != NIL)
+						ereport(ERROR,
+								(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+								 errmsg("inheritance parent is not supported on incrementally maintainable materialized view")));
+
+					if (rte->relkind == RELKIND_FOREIGN_TABLE)
+						ereport(ERROR,
+								(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+								 errmsg("foreign table is not supported on incrementally maintainable materialized view")));
+
+					if (rte->relkind == RELKIND_VIEW ||
+						rte->relkind == RELKIND_MATVIEW)
+						ereport(ERROR,
+								(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+								 errmsg("VIEW or MATERIALIZED VIEW is not supported on incrementally maintainable materialized view")));
+
+					if (rte->rtekind == RTE_VALUES)
+						ereport(ERROR,
+								(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+								 errmsg("VALUES is not supported on incrementally maintainable materialized view")));
+
+				}
+
+				query_tree_walker(qry, check_ivm_restriction_walker, NULL, QTW_IGNORE_RANGE_TABLE);
+
+				break;
+			}
+		case T_TargetEntry:
+			{
+				TargetEntry *tle = (TargetEntry *)node;
+				if (isIvmName(tle->resname))
+						ereport(ERROR,
+								(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+								 errmsg("column name %s is not supported on incrementally maintainable materialized view", tle->resname)));
+
+				expression_tree_walker(node, check_ivm_restriction_walker, NULL);
+				break;
+			}
+		case T_JoinExpr:
+			{
+				JoinExpr *joinexpr = (JoinExpr *)node;
+
+				if (joinexpr->jointype > JOIN_INNER)
+						ereport(ERROR,
+								(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+								 errmsg("OUTER JOIN is not supported on incrementally maintainable materialized view")));
+
+				expression_tree_walker(node, check_ivm_restriction_walker, NULL);
+			}
+			break;
+		case T_Aggref:
+			ereport(ERROR,
+					(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+					 errmsg("aggregate function is not supported on incrementally maintainable materialized view")));
+			break;
+		default:
+			expression_tree_walker(node, check_ivm_restriction_walker, (void *) context);
+			break;
+	}
+	return false;
+}
+
+/*
+ * CreateIndexOnIMMV
+ *
+ * Create a unique index on incremental maintainable materialized view.
+ * If the view definition query has a GROUP BY clause, the index is created
+ * on the columns of GROUP BY expressions. Otherwise, if the view contains
+ * all primary key attritubes of its base tables in the target list, the index
+ * is created on these attritubes. In other cases, no index is created.
+ */
+void
+CreateIndexOnIMMV(Query *query, Relation matviewRel)
+{
+	ListCell *lc;
+	IndexStmt  *index;
+	ObjectAddress address;
+	List *constraintList = NIL;
+	char		idxname[NAMEDATALEN];
+	List	   *indexoidlist = RelationGetIndexList(matviewRel);
+	ListCell   *indexoidscan;
+	Bitmapset *key_attnos;
+
+	snprintf(idxname, sizeof(idxname), "%s_index", RelationGetRelationName(matviewRel));
+
+	index = makeNode(IndexStmt);
+
+	index->unique = true;
+	index->primary = false;
+	index->isconstraint = false;
+	index->deferrable = false;
+	index->initdeferred = false;
+	index->idxname = idxname;
+	index->relation =
+		makeRangeVar(get_namespace_name(RelationGetNamespace(matviewRel)),
+					 pstrdup(RelationGetRelationName(matviewRel)),
+					 -1);
+	index->accessMethod = DEFAULT_INDEX_TYPE;
+	index->options = NIL;
+	index->tableSpace = get_tablespace_name(matviewRel->rd_rel->reltablespace);
+	index->whereClause = NULL;
+	index->indexParams = NIL;
+	index->indexIncludingParams = NIL;
+	index->excludeOpNames = NIL;
+	index->idxcomment = NULL;
+	index->indexOid = InvalidOid;
+	index->oldNumber = InvalidRelFileNumber;
+	index->oldCreateSubid = InvalidSubTransactionId;
+	index->oldFirstRelfilelocatorSubid = InvalidSubTransactionId;
+	index->transformed = true;
+	index->concurrent = false;
+	index->if_not_exists = false;
+
+	/* create index on the base tables' primary key columns */
+	key_attnos = get_primary_key_attnos_from_query(query, &constraintList);
+	if (key_attnos)
+	{
+		foreach(lc, query->targetList)
+		{
+			TargetEntry *tle = (TargetEntry *) lfirst(lc);
+			Form_pg_attribute attr = TupleDescAttr(matviewRel->rd_att, tle->resno - 1);
+
+			if (bms_is_member(tle->resno - FirstLowInvalidHeapAttributeNumber, key_attnos))
+			{
+				IndexElem  *iparam;
+
+				iparam = makeNode(IndexElem);
+				iparam->name = pstrdup(NameStr(attr->attname));
+				iparam->expr = NULL;
+				iparam->indexcolname = NULL;
+				iparam->collation = NIL;
+				iparam->opclass = NIL;
+				iparam->opclassopts = NIL;
+				iparam->ordering = SORTBY_DEFAULT;
+				iparam->nulls_ordering = SORTBY_NULLS_DEFAULT;
+				index->indexParams = lappend(index->indexParams, iparam);
+			}
+		}
+	}
+	else
+	{
+		/* create no index, just notice that an appropriate index is necessary for efficient IVM */
+		ereport(NOTICE,
+				(errmsg("could not create an index on materialized view \"%s\" automatically",
+						RelationGetRelationName(matviewRel)),
+				 errdetail("This target list does not have all the primary key columns. "),
+				 errhint("Create an index on the materialized view for efficient incremental maintenance.")));
+		return;
+	}
+
+	/* If we have a compatible index, we don't need to create another. */
+	foreach(indexoidscan, indexoidlist)
+	{
+		Oid			indexoid = lfirst_oid(indexoidscan);
+		Relation	indexRel;
+		bool		hasCompatibleIndex = false;
+
+		indexRel = index_open(indexoid, AccessShareLock);
+
+		if (CheckIndexCompatible(indexRel->rd_id,
+								index->accessMethod,
+								index->indexParams,
+								index->excludeOpNames,
+								false))
+			hasCompatibleIndex = true;
+
+		index_close(indexRel, AccessShareLock);
+
+		if (hasCompatibleIndex)
+			return;
+	}
+
+	address = DefineIndex(RelationGetRelid(matviewRel),
+						  index,
+						  InvalidOid,
+						  InvalidOid,
+						  InvalidOid,
+						  -1,
+						  false, true, false, false, true);
+
+	ereport(NOTICE,
+			(errmsg("created index \"%s\" on materialized view \"%s\"",
+					idxname, RelationGetRelationName(matviewRel))));
+
+	/*
+	 * Make dependencies so that the index is dropped if any base tables's
+	 * primary key is dropped.
+	 */
+	foreach(lc, constraintList)
+	{
+		Oid constraintOid = lfirst_oid(lc);
+		ObjectAddress	refaddr;
+
+		refaddr.classId = ConstraintRelationId;
+		refaddr.objectId = constraintOid;
+		refaddr.objectSubId = 0;
+
+		recordDependencyOn(&address, &refaddr, DEPENDENCY_NORMAL);
+	}
+}
+
+
+/*
+ * get_primary_key_attnos_from_query
+ *
+ * Identify the columns in base tables' primary keys in the target list.
+ *
+ * Returns a Bitmapset of the column attnos of the primary key's columns of
+ * tables that used in the query.  The attnos are offset by
+ * FirstLowInvalidHeapAttributeNumber as same as get_primary_key_attnos.
+ *
+ * If any table has no primary key or any primary key's columns is not in
+ * the target list, return NULL.  We also return NULL if any pkey constraint
+ * is deferrable.
+ *
+ * constraintList is set to a list of the OIDs of the pkey constraints.
+ */
+static Bitmapset *
+get_primary_key_attnos_from_query(Query *query, List **constraintList)
+{
+	List *key_attnos_list = NIL;
+	ListCell *lc;
+	int i;
+	Bitmapset *keys = NULL;
+	Relids	rels_in_from;
+
+	/*
+	 * Collect primary key attributes from all tables used in query. The key attributes
+	 * sets for each table are stored in key_attnos_list in order by RTE index.
+	 */
+	foreach(lc, query->rtable)
+	{
+		RangeTblEntry *r = (RangeTblEntry*) lfirst(lc);
+		Bitmapset *key_attnos;
+		bool	has_pkey = true;
+
+		/* for tables, call get_primary_key_attnos */
+		if (r->rtekind == RTE_RELATION)
+		{
+			Oid constraintOid;
+			key_attnos = get_primary_key_attnos(r->relid, false, &constraintOid);
+			*constraintList = lappend_oid(*constraintList, constraintOid);
+			has_pkey = (key_attnos != NULL);
+		}
+		/* for other RTEs, store NULL into key_attnos_list */
+		else
+			key_attnos = NULL;
+
+		/*
+		 * If any table or subquery has no primary key or its pkey constraint is deferrable,
+		 * we cannot get key attributes for this query, so return NULL.
+		 */
+		if (!has_pkey)
+			return NULL;
+
+		key_attnos_list = lappend(key_attnos_list, key_attnos);
+	}
+
+	/* Collect key attributes appearing in the target list */
+	i = 1;
+	foreach(lc, query->targetList)
+	{
+		TargetEntry *tle = (TargetEntry *) flatten_join_alias_vars(NULL, query, lfirst(lc));
+
+		if (IsA(tle->expr, Var))
+		{
+			Var *var = (Var*) tle->expr;
+			Bitmapset *key_attnos = list_nth(key_attnos_list, var->varno - 1);
+
+			/* check if this attribute is from a base table's primary key */
+			if (bms_is_member(var->varattno - FirstLowInvalidHeapAttributeNumber, key_attnos))
+			{
+				/*
+				 * Remove found key attributes from key_attnos_list, and add this
+				 * to the result list.
+				 */
+				key_attnos = bms_del_member(key_attnos, var->varattno - FirstLowInvalidHeapAttributeNumber);
+				if (bms_is_empty(key_attnos))
+				{
+					key_attnos_list = list_delete_nth_cell(key_attnos_list, var->varno - 1);
+					key_attnos_list = list_insert_nth(key_attnos_list, var->varno - 1, NULL);
+				}
+				keys = bms_add_member(keys, i - FirstLowInvalidHeapAttributeNumber);
+			}
+		}
+		i++;
+	}
+
+	/* Collect RTE indexes of relations appearing in the FROM clause */
+	rels_in_from = get_relids_in_jointree((Node *) query->jointree, false, false);
+
+	/*
+	 * Check if all key attributes of relations in FROM are appearing in the target
+	 * list.  If an attribute remains in key_attnos_list in spite of the table is used
+	 * in FROM clause, the target is missing this key attribute, so we return NULL.
+	 */
+	i = 1;
+	foreach(lc, key_attnos_list)
+	{
+		Bitmapset *bms = (Bitmapset *)lfirst(lc);
+		if (!bms_is_empty(bms) && bms_is_member(i, rels_in_from))
+			return NULL;
+		i++;
+	}
+
+	return keys;
+}
diff --git a/src/backend/commands/matview.c b/src/backend/commands/matview.c
index 59920ced83..a821992a37 100644
--- a/src/backend/commands/matview.c
+++ b/src/backend/commands/matview.c
@@ -25,26 +25,37 @@
 #include "catalog/indexing.h"
 #include "catalog/namespace.h"
 #include "catalog/pg_am.h"
+#include "catalog/pg_depend.h"
+#include "catalog/pg_trigger.h"
 #include "catalog/pg_opclass.h"
 #include "catalog/pg_operator.h"
 #include "commands/cluster.h"
 #include "commands/matview.h"
 #include "commands/tablecmds.h"
 #include "commands/tablespace.h"
+#include "commands/createas.h"
 #include "executor/executor.h"
 #include "executor/spi.h"
+#include "executor/tstoreReceiver.h"
 #include "miscadmin.h"
+#include "nodes/makefuncs.h"
+#include "parser/analyze.h"
+#include "parser/parse_clause.h"
+#include "parser/parse_func.h"
 #include "parser/parse_relation.h"
 #include "pgstat.h"
 #include "rewrite/rewriteHandler.h"
+#include "rewrite/rowsecurity.h"
 #include "storage/lmgr.h"
 #include "storage/smgr.h"
 #include "tcop/tcopprot.h"
 #include "utils/builtins.h"
+#include "utils/fmgroids.h"
 #include "utils/lsyscache.h"
 #include "utils/rel.h"
 #include "utils/snapmgr.h"
 #include "utils/syscache.h"
+#include "utils/typcache.h"
 
 
 typedef struct
@@ -58,6 +69,52 @@ typedef struct
 	BulkInsertState bistate;	/* bulk insert state */
 } DR_transientrel;
 
+#define MV_INIT_QUERYHASHSIZE	16
+
+/*
+ * MV_TriggerHashEntry
+ *
+ * Hash entry for base tables on which IVM trigger is invoked
+ */
+typedef struct MV_TriggerHashEntry
+{
+	Oid	matview_id;			/* OID of the materialized view */
+	int	before_trig_count;	/* count of before triggers invoked */
+	int	after_trig_count;	/* count of after triggers invoked */
+
+	Snapshot	snapshot;	/* Snapshot just before table change */
+
+	List   *tables;		/* List of MV_TriggerTable */
+	bool	has_old;	/* tuples are deleted from any table? */
+	bool	has_new;	/* tuples are inserted into any table? */
+} MV_TriggerHashEntry;
+
+/*
+ * MV_TriggerTable
+ *
+ * IVM related data for tables on which the trigger is invoked.
+ */
+typedef struct MV_TriggerTable
+{
+	Oid		table_id;			/* OID of the modified table */
+	List   *old_tuplestores;	/* tuplestores for deleted tuples */
+	List   *new_tuplestores;	/* tuplestores for inserted tuples */
+
+	List   *rte_indexes;		/* List of RTE index of the modified table */
+	RangeTblEntry *original_rte;	/* the original RTE saved before rewriting query */
+
+	Relation	rel;			/* relation of the modified table */
+	TupleTableSlot *slot;		/* for checking visibility in the pre-state table */
+} MV_TriggerTable;
+
+static HTAB *mv_trigger_info = NULL;
+
+static bool in_delta_calculation = false;
+
+/* ENR name for materialized view delta */
+#define NEW_DELTA_ENRNAME "new_delta"
+#define OLD_DELTA_ENRNAME "old_delta"
+
 static int	matview_maintenance_depth = 0;
 
 static void transientrel_startup(DestReceiver *self, int operation, TupleDesc typeinfo);
@@ -65,7 +122,9 @@ static bool transientrel_receive(TupleTableSlot *slot, DestReceiver *self);
 static void transientrel_shutdown(DestReceiver *self);
 static void transientrel_destroy(DestReceiver *self);
 static uint64 refresh_matview_datafill(DestReceiver *dest, Query *query,
-									   const char *queryString);
+						 QueryEnvironment *queryEnv,
+						 TupleDesc *resultTupleDesc,
+						 const char *queryString);
 static char *make_temptable_name_n(char *tempname, int n);
 static void refresh_by_match_merge(Oid matviewOid, Oid tempOid, Oid relowner,
 								   int save_sec_context);
@@ -73,6 +132,37 @@ static void refresh_by_heap_swap(Oid matviewOid, Oid OIDNewHeap, char relpersist
 static bool is_usable_unique_index(Relation indexRel);
 static void OpenMatViewIncrementalMaintenance(void);
 static void CloseMatViewIncrementalMaintenance(void);
+static Query *get_matview_query(Relation matviewRel);
+
+static Query *rewrite_query_for_preupdate_state(Query *query, List *tables,
+								  ParseState *pstate, Oid matviewid);
+static void register_delta_ENRs(ParseState *pstate, Query *query, List *tables);
+static char *make_delta_enr_name(const char *prefix, Oid relid, int count);
+static RangeTblEntry *get_prestate_rte(RangeTblEntry *rte, MV_TriggerTable *table,
+				 QueryEnvironment *queryEnv, Oid matviewid);
+static RangeTblEntry *replace_rte_with_delta(RangeTblEntry *rte, MV_TriggerTable *table, bool is_new,
+		   QueryEnvironment *queryEnv);
+static Query *rewrite_query_for_counting(Query *query, ParseState *pstate);
+
+static void calc_delta(MV_TriggerTable *table, int rte_index, Query *query,
+			DestReceiver *dest_old, DestReceiver *dest_new,
+			TupleDesc *tupdesc_old, TupleDesc *tupdesc_new,
+			QueryEnvironment *queryEnv);
+static Query *rewrite_query_for_postupdate_state(Query *query, MV_TriggerTable *table, int rte_index);
+
+static void apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *new_tuplestores,
+			TupleDesc tupdesc_old, TupleDesc tupdesc_new,
+			Query *query);
+static void apply_old_delta(const char *matviewname, const char *deltaname_old,
+				List *keys);
+static void apply_new_delta(const char *matviewname, const char *deltaname_new,
+				StringInfo target_list);
+static char *get_matching_condition_string(List *keys);
+static void generate_equal(StringInfo querybuf, Oid opttype,
+			   const char *leftop, const char *rightop);
+
+static void mv_InitHashTables(void);
+static void clean_up_IVM_hash_entry(MV_TriggerHashEntry *entry, bool is_abort);
 
 /*
  * SetMatViewPopulatedState
@@ -114,6 +204,46 @@ SetMatViewPopulatedState(Relation relation, bool newstate)
 	CommandCounterIncrement();
 }
 
+/*
+ * SetMatViewIVMState
+ *		Mark a materialized view as IVM, or not.
+ *
+ * NOTE: caller must be holding an appropriate lock on the relation.
+ */
+void
+SetMatViewIVMState(Relation relation, bool newstate)
+{
+	Relation	pgrel;
+	HeapTuple	tuple;
+
+	Assert(relation->rd_rel->relkind == RELKIND_MATVIEW);
+
+	/*
+	 * Update relation's pg_class entry.  Crucial side-effect: other backends
+	 * (and this one too!) are sent SI message to make them rebuild relcache
+	 * entries.
+	 */
+	pgrel = table_open(RelationRelationId, RowExclusiveLock);
+	tuple = SearchSysCacheCopy1(RELOID,
+								ObjectIdGetDatum(RelationGetRelid(relation)));
+	if (!HeapTupleIsValid(tuple))
+		elog(ERROR, "cache lookup failed for relation %u",
+			 RelationGetRelid(relation));
+
+	((Form_pg_class) GETSTRUCT(tuple))->relisivm = newstate;
+
+	CatalogTupleUpdate(pgrel, &tuple->t_self, tuple);
+
+	heap_freetuple(tuple);
+	table_close(pgrel, RowExclusiveLock);
+
+	/*
+	 * Advance command counter to make the updated pg_class row locally
+	 * visible.
+	 */
+	CommandCounterIncrement();
+}
+
 /*
  * ExecRefreshMatView -- execute a REFRESH MATERIALIZED VIEW command
  *
@@ -140,8 +270,6 @@ ExecRefreshMatView(RefreshMatViewStmt *stmt, const char *queryString,
 {
 	Oid			matviewOid;
 	Relation	matviewRel;
-	RewriteRule *rule;
-	List	   *actions;
 	Query	   *dataQuery;
 	Oid			tableSpace;
 	Oid			relowner;
@@ -155,6 +283,7 @@ ExecRefreshMatView(RefreshMatViewStmt *stmt, const char *queryString,
 	int			save_sec_context;
 	int			save_nestlevel;
 	ObjectAddress address;
+	bool oldPopulated;
 
 	/* Determine strength of lock needed. */
 	concurrent = stmt->concurrent;
@@ -178,6 +307,7 @@ ExecRefreshMatView(RefreshMatViewStmt *stmt, const char *queryString,
 	SetUserIdAndSecContext(relowner,
 						   save_sec_context | SECURITY_RESTRICTED_OPERATION);
 	save_nestlevel = NewGUCNestLevel();
+	oldPopulated = RelationIsPopulated(matviewRel);
 
 	/* Make sure it is a materialized view. */
 	if (matviewRel->rd_rel->relkind != RELKIND_MATVIEW)
@@ -199,32 +329,9 @@ ExecRefreshMatView(RefreshMatViewStmt *stmt, const char *queryString,
 				 errmsg("%s and %s options cannot be used together",
 						"CONCURRENTLY", "WITH NO DATA")));
 
-	/*
-	 * Check that everything is correct for a refresh. Problems at this point
-	 * are internal errors, so elog is sufficient.
-	 */
-	if (matviewRel->rd_rel->relhasrules == false ||
-		matviewRel->rd_rules->numLocks < 1)
-		elog(ERROR,
-			 "materialized view \"%s\" is missing rewrite information",
-			 RelationGetRelationName(matviewRel));
-
-	if (matviewRel->rd_rules->numLocks > 1)
-		elog(ERROR,
-			 "materialized view \"%s\" has too many rules",
-			 RelationGetRelationName(matviewRel));
 
-	rule = matviewRel->rd_rules->rules[0];
-	if (rule->event != CMD_SELECT || !(rule->isInstead))
-		elog(ERROR,
-			 "the rule for materialized view \"%s\" is not a SELECT INSTEAD OF rule",
-			 RelationGetRelationName(matviewRel));
+	dataQuery = get_matview_query(matviewRel);
 
-	actions = rule->actions;
-	if (list_length(actions) != 1)
-		elog(ERROR,
-			 "the rule for materialized view \"%s\" is not a single action",
-			 RelationGetRelationName(matviewRel));
 
 	/*
 	 * Check that there is a unique index with no WHERE clause on one or more
@@ -259,12 +366,6 @@ ExecRefreshMatView(RefreshMatViewStmt *stmt, const char *queryString,
 					 errhint("Create a unique index with no WHERE clause on one or more columns of the materialized view.")));
 	}
 
-	/*
-	 * The stored query was rewritten at the time of the MV definition, but
-	 * has not been scribbled on by the planner.
-	 */
-	dataQuery = linitial_node(Query, actions);
-
 	/*
 	 * Check for active uses of the relation in the current transaction, such
 	 * as open scans.
@@ -292,6 +393,74 @@ ExecRefreshMatView(RefreshMatViewStmt *stmt, const char *queryString,
 		relpersistence = matviewRel->rd_rel->relpersistence;
 	}
 
+	/* delete IMMV triggers. */
+	if (RelationIsIVM(matviewRel) && stmt->skipData )
+	{
+		Relation	tgRel;
+		Relation	depRel;
+		ScanKeyData key;
+		SysScanDesc scan;
+		HeapTuple	tup;
+		ObjectAddresses *immv_triggers;
+
+		immv_triggers = new_object_addresses();
+
+		tgRel = table_open(TriggerRelationId, RowExclusiveLock);
+		depRel = table_open(DependRelationId, RowExclusiveLock);
+
+		/* search triggers that depends on IMMV. */
+		ScanKeyInit(&key,
+					Anum_pg_depend_refobjid,
+					BTEqualStrategyNumber, F_OIDEQ,
+					ObjectIdGetDatum(matviewOid));
+		scan = systable_beginscan(depRel, DependReferenceIndexId, true,
+								  NULL, 1, &key);
+		while ((tup = systable_getnext(scan)) != NULL)
+		{
+			ObjectAddress obj;
+			Form_pg_depend foundDep = (Form_pg_depend) GETSTRUCT(tup);
+
+			if (foundDep->classid == TriggerRelationId)
+			{
+				HeapTuple	tgtup;
+				ScanKeyData tgkey[1];
+				SysScanDesc tgscan;
+				Form_pg_trigger tgform;
+
+				/* Find the trigger name. */
+				ScanKeyInit(&tgkey[0],
+							Anum_pg_trigger_oid,
+							BTEqualStrategyNumber, F_OIDEQ,
+							ObjectIdGetDatum(foundDep->objid));
+
+				tgscan = systable_beginscan(tgRel, TriggerOidIndexId, true,
+											NULL, 1, tgkey);
+				tgtup = systable_getnext(tgscan);
+				if (!HeapTupleIsValid(tgtup))
+					elog(ERROR, "could not find tuple for immv trigger %u", foundDep->objid);
+
+				tgform = (Form_pg_trigger) GETSTRUCT(tgtup);
+
+				/* If trigger is created by IMMV, delete it. */
+				if (strncmp(NameStr(tgform->tgname), "IVM_trigger_", 12) == 0)
+				{
+					obj.classId = foundDep->classid;
+					obj.objectId = foundDep->objid;
+					obj.objectSubId = foundDep->refobjsubid;
+					add_exact_object_address(&obj, immv_triggers);
+				}
+				systable_endscan(tgscan);
+			}
+		}
+		systable_endscan(scan);
+
+		performMultipleDeletions(immv_triggers, DROP_RESTRICT, PERFORM_DELETION_INTERNAL);
+
+		table_close(depRel, RowExclusiveLock);
+		table_close(tgRel, RowExclusiveLock);
+		free_object_addresses(immv_triggers);
+	}
+
 	/*
 	 * Create the transient table that will receive the regenerated data. Lock
 	 * it against access by any other process until commit (by which time it
@@ -305,7 +474,7 @@ ExecRefreshMatView(RefreshMatViewStmt *stmt, const char *queryString,
 
 	/* Generate the data, if wanted. */
 	if (!stmt->skipData)
-		processed = refresh_matview_datafill(dest, dataQuery, queryString);
+		processed = refresh_matview_datafill(dest, dataQuery, NULL, NULL, queryString);
 
 	/* Make the matview match the newly generated data. */
 	if (concurrent)
@@ -340,6 +509,12 @@ ExecRefreshMatView(RefreshMatViewStmt *stmt, const char *queryString,
 			pgstat_count_heap_insert(matviewRel, processed);
 	}
 
+	if (!stmt->skipData && RelationIsIVM(matviewRel) && !oldPopulated)
+	{
+		CreateIndexOnIMMV(dataQuery, matviewRel);
+		CreateIvmTriggersOnBaseTables(dataQuery, matviewOid);
+	}
+
 	table_close(matviewRel, NoLock);
 
 	/* Roll back any GUC changes */
@@ -374,6 +549,8 @@ ExecRefreshMatView(RefreshMatViewStmt *stmt, const char *queryString,
  */
 static uint64
 refresh_matview_datafill(DestReceiver *dest, Query *query,
+						 QueryEnvironment *queryEnv,
+						 TupleDesc *resultTupleDesc,
 						 const char *queryString)
 {
 	List	   *rewritten;
@@ -410,7 +587,7 @@ refresh_matview_datafill(DestReceiver *dest, Query *query,
 	/* Create a QueryDesc, redirecting output to our tuple receiver */
 	queryDesc = CreateQueryDesc(plan, queryString,
 								GetActiveSnapshot(), InvalidSnapshot,
-								dest, NULL, NULL, 0);
+								dest, NULL, queryEnv ? queryEnv: NULL, 0);
 
 	/* call ExecutorStart to prepare the plan for execution */
 	ExecutorStart(queryDesc, 0);
@@ -420,6 +597,9 @@ refresh_matview_datafill(DestReceiver *dest, Query *query,
 
 	processed = queryDesc->estate->es_processed;
 
+	if (resultTupleDesc)
+		*resultTupleDesc = CreateTupleDescCopy(queryDesc->tupDesc);
+
 	/* and clean up */
 	ExecutorFinish(queryDesc);
 	ExecutorEnd(queryDesc);
@@ -953,3 +1133,1219 @@ CloseMatViewIncrementalMaintenance(void)
 	matview_maintenance_depth--;
 	Assert(matview_maintenance_depth >= 0);
 }
+
+/*
+ * get_matview_query - get the Query from a matview's _RETURN rule.
+ */
+static Query *
+get_matview_query(Relation matviewRel)
+{
+	RewriteRule *rule;
+	List * actions;
+
+	/*
+	 * Check that everything is correct for a refresh. Problems at this point
+	 * are internal errors, so elog is sufficient.
+	 */
+	if (matviewRel->rd_rel->relhasrules == false ||
+		matviewRel->rd_rules->numLocks < 1)
+		elog(ERROR,
+			 "materialized view \"%s\" is missing rewrite information",
+			 RelationGetRelationName(matviewRel));
+
+	if (matviewRel->rd_rules->numLocks > 1)
+		elog(ERROR,
+			 "materialized view \"%s\" has too many rules",
+			 RelationGetRelationName(matviewRel));
+
+	rule = matviewRel->rd_rules->rules[0];
+	if (rule->event != CMD_SELECT || !(rule->isInstead))
+		elog(ERROR,
+			 "the rule for materialized view \"%s\" is not a SELECT INSTEAD OF rule",
+			 RelationGetRelationName(matviewRel));
+
+	actions = rule->actions;
+	if (list_length(actions) != 1)
+		elog(ERROR,
+			 "the rule for materialized view \"%s\" is not a single action",
+			 RelationGetRelationName(matviewRel));
+
+	/*
+	 * The stored query was rewritten at the time of the MV definition, but
+	 * has not been scribbled on by the planner.
+	 */
+	return linitial_node(Query, actions);
+}
+
+
+/* ----------------------------------------------------
+ *		Incremental View Maintenance routines
+ * ---------------------------------------------------
+ */
+
+/*
+ * IVM_immediate_before
+ *
+ * IVM trigger function invoked before base table is modified. If this is
+ * invoked firstly in the same statement, we save the transaction id and the
+ * command id at that time.
+ */
+Datum
+IVM_immediate_before(PG_FUNCTION_ARGS)
+{
+	TriggerData *trigdata = (TriggerData *) fcinfo->context;
+	char	   *matviewOid_text = trigdata->tg_trigger->tgargs[0];
+	char	   *ex_lock_text = trigdata->tg_trigger->tgargs[1];
+	Oid			matviewOid;
+	MV_TriggerHashEntry *entry;
+	bool	found;
+	bool	ex_lock;
+
+	matviewOid = DatumGetObjectId(DirectFunctionCall1(oidin, CStringGetDatum(matviewOid_text)));
+	ex_lock = DatumGetBool(DirectFunctionCall1(boolin, CStringGetDatum(ex_lock_text)));
+
+	/* If the view has more than one tables, we have to use an exclusive lock. */
+	if (ex_lock)
+	{
+		/*
+		 * Wait for concurrent transactions which update this materialized view at
+		 * READ COMMITED. This is needed to see changes committed in other
+		 * transactions. No wait and raise an error at REPEATABLE READ or
+		 * SERIALIZABLE to prevent update anomalies of matviews.
+		 * XXX: dead-lock is possible here.
+		 */
+		if (!IsolationUsesXactSnapshot())
+			LockRelationOid(matviewOid, ExclusiveLock);
+		else if (!ConditionalLockRelationOid(matviewOid, ExclusiveLock))
+		{
+			/* try to throw error by name; relation could be deleted... */
+			char	   *relname = get_rel_name(matviewOid);
+
+			if (!relname)
+				ereport(ERROR,
+						(errcode(ERRCODE_LOCK_NOT_AVAILABLE),
+						errmsg("could not obtain lock on materialized view during incremental maintenance")));
+
+			ereport(ERROR,
+					(errcode(ERRCODE_LOCK_NOT_AVAILABLE),
+					errmsg("could not obtain lock on materialized view \"%s\" during incremental maintenance",
+							relname)));
+		}
+	}
+	else
+		LockRelationOid(matviewOid, RowExclusiveLock);
+
+	/*
+	 * On the first call initialize the hashtable
+	 */
+	if (!mv_trigger_info)
+		mv_InitHashTables();
+
+	entry = (MV_TriggerHashEntry *) hash_search(mv_trigger_info,
+											  (void *) &matviewOid,
+											  HASH_ENTER, &found);
+
+	/* On the first BEFORE to update the view, initialize trigger data */
+	if (!found)
+	{
+		/*
+		 * Get a snapshot just before the table was modified for checking
+		 * tuple visibility in the pre-update state of the table.
+		 */
+		Snapshot snapshot = GetActiveSnapshot();
+
+		entry->matview_id = matviewOid;
+		entry->before_trig_count = 0;
+		entry->after_trig_count = 0;
+		entry->snapshot = RegisterSnapshot(snapshot);
+		entry->tables = NIL;
+		entry->has_old = false;
+		entry->has_new = false;
+	}
+
+	entry->before_trig_count++;
+
+	return PointerGetDatum(NULL);
+}
+
+/*
+ * IVM_immediate_maintenance
+ *
+ * IVM trigger function invoked after base table is modified.
+ * For each table, tuplestores of transition tables are collected.
+ * and after the last modification
+ */
+Datum
+IVM_immediate_maintenance(PG_FUNCTION_ARGS)
+{
+	TriggerData *trigdata = (TriggerData *) fcinfo->context;
+	Relation	rel;
+	Oid			relid;
+	Oid			matviewOid;
+	Query	   *query;
+	Query	   *rewritten = NULL;
+	char	   *matviewOid_text = trigdata->tg_trigger->tgargs[0];
+	Relation	matviewRel;
+	int old_depth = matview_maintenance_depth;
+
+	Oid			relowner;
+	Tuplestorestate *old_tuplestore = NULL;
+	Tuplestorestate *new_tuplestore = NULL;
+	DestReceiver *dest_new = NULL, *dest_old = NULL;
+	Oid			save_userid;
+	int			save_sec_context;
+	int			save_nestlevel;
+
+	MV_TriggerHashEntry *entry;
+	MV_TriggerTable		*table;
+	bool	found;
+
+	ParseState		 *pstate;
+	QueryEnvironment *queryEnv = create_queryEnv();
+	MemoryContext	oldcxt;
+	ListCell   *lc;
+	int			i;
+
+
+	/* Create a ParseState for rewriting the view definition query */
+	pstate = make_parsestate(NULL);
+	pstate->p_queryEnv = queryEnv;
+	pstate->p_expr_kind = EXPR_KIND_SELECT_TARGET;
+
+	rel = trigdata->tg_relation;
+	relid = rel->rd_id;
+
+	matviewOid = DatumGetObjectId(DirectFunctionCall1(oidin, CStringGetDatum(matviewOid_text)));
+
+	/*
+	 * On the first call initialize the hashtable
+	 */
+	if (!mv_trigger_info)
+		mv_InitHashTables();
+
+	/* get the entry for this materialized view */
+	entry = (MV_TriggerHashEntry *) hash_search(mv_trigger_info,
+											  (void *) &matviewOid,
+											  HASH_FIND, &found);
+	Assert (found && entry != NULL);
+	entry->after_trig_count++;
+
+	/* search the entry for the modified table and create new entry if not found */
+	found = false;
+	foreach(lc, entry->tables)
+	{
+		table = (MV_TriggerTable *) lfirst(lc);
+		if (table->table_id == relid)
+		{
+			found = true;
+			break;
+		}
+	}
+	if (!found)
+	{
+		oldcxt = MemoryContextSwitchTo(TopTransactionContext);
+
+		table = (MV_TriggerTable *) palloc0(sizeof(MV_TriggerTable));
+		table->table_id = relid;
+		table->old_tuplestores = NIL;
+		table->new_tuplestores = NIL;
+		table->rte_indexes = NIL;
+		table->slot = MakeSingleTupleTableSlot(RelationGetDescr(rel), table_slot_callbacks(rel));
+		table->rel = table_open(RelationGetRelid(rel), NoLock);
+		entry->tables = lappend(entry->tables, table);
+
+		MemoryContextSwitchTo(oldcxt);
+	}
+
+	/* Save the transition tables and make a request to not free immediately */
+	if (trigdata->tg_oldtable)
+	{
+		oldcxt = MemoryContextSwitchTo(TopTransactionContext);
+		table->old_tuplestores = lappend(table->old_tuplestores, trigdata->tg_oldtable);
+		entry->has_old = true;
+		MemoryContextSwitchTo(oldcxt);
+	}
+	if (trigdata->tg_newtable)
+	{
+		oldcxt = MemoryContextSwitchTo(TopTransactionContext);
+		table->new_tuplestores = lappend(table->new_tuplestores, trigdata->tg_newtable);
+		entry->has_new = true;
+		MemoryContextSwitchTo(oldcxt);
+	}
+	if (entry->has_new || entry->has_old)
+	{
+		CmdType cmd;
+
+		if (TRIGGER_FIRED_BY_INSERT(trigdata->tg_event))
+			cmd = CMD_INSERT;
+		else if (TRIGGER_FIRED_BY_DELETE(trigdata->tg_event))
+			cmd = CMD_DELETE;
+		else if (TRIGGER_FIRED_BY_UPDATE(trigdata->tg_event))
+			cmd = CMD_UPDATE;
+		else
+			elog(ERROR,"unsupported trigger type");
+
+		/* Prolong lifespan of transition tables to the end of the last AFTER trigger */
+		SetTransitionTablePreserved(relid, cmd);
+	}
+
+
+	/* If this is not the last AFTER trigger call, immediately exit. */
+	Assert (entry->before_trig_count >= entry->after_trig_count);
+	if (entry->before_trig_count != entry->after_trig_count)
+		return PointerGetDatum(NULL);
+
+	/*
+	 * If this is the last AFTER trigger call, continue and update the view.
+	 */
+
+	/*
+	 * Advance command counter to make the updated base table row locally
+	 * visible.
+	 */
+	CommandCounterIncrement();
+
+	matviewRel = table_open(matviewOid, NoLock);
+
+	/* Make sure it is a materialized view. */
+	Assert(matviewRel->rd_rel->relkind == RELKIND_MATVIEW);
+
+	/*
+	 * Get and push the latast snapshot to see any changes which is committed
+	 * during waiting in other transactions at READ COMMITTED level.
+	 */
+	PushActiveSnapshot(GetTransactionSnapshot());
+
+	/*
+	 * Check for active uses of the relation in the current transaction, such
+	 * as open scans.
+	 *
+	 * NB: We count on this to protect us against problems with refreshing the
+	 * data using TABLE_INSERT_FROZEN.
+	 */
+	CheckTableNotInUse(matviewRel, "refresh a materialized view incrementally");
+
+	/*
+	 * Switch to the owner's userid, so that any functions are run as that
+	 * user.  Also arrange to make GUC variable changes local to this command.
+	 * We will switch modes when we are about to execute user code.
+	 */
+	relowner = matviewRel->rd_rel->relowner;
+	GetUserIdAndSecContext(&save_userid, &save_sec_context);
+	SetUserIdAndSecContext(relowner,
+						   save_sec_context | SECURITY_RESTRICTED_OPERATION);
+	save_nestlevel = NewGUCNestLevel();
+
+	/* get view query*/
+	query = get_matview_query(matviewRel);
+
+	/*
+	 * When a base table is truncated, the view content will be empty if the
+	 * view definition query does not contain an aggregate without a GROUP clause.
+	 * Therefore, such views can be truncated.
+	 */
+	if (TRIGGER_FIRED_BY_TRUNCATE(trigdata->tg_event))
+	{
+		ExecuteTruncateGuts(list_make1(matviewRel), list_make1_oid(matviewOid),
+							NIL, DROP_RESTRICT, false, false);
+
+		/* Clean up hash entry and delete tuplestores */
+		clean_up_IVM_hash_entry(entry, false);
+
+		/* Pop the original snapshot. */
+		PopActiveSnapshot();
+
+		table_close(matviewRel, NoLock);
+
+		/* Roll back any GUC changes */
+		AtEOXact_GUC(false, save_nestlevel);
+
+		/* Restore userid and security context */
+		SetUserIdAndSecContext(save_userid, save_sec_context);
+
+		return PointerGetDatum(NULL);
+	}
+
+	/*
+	 * rewrite query for calculating deltas
+	 */
+
+	rewritten = copyObject(query);
+
+	/* Replace resnames in a target list with materialized view's attnames */
+	i = 0;
+	foreach (lc, rewritten->targetList)
+	{
+		TargetEntry *tle = (TargetEntry *) lfirst(lc);
+		Form_pg_attribute attr = TupleDescAttr(matviewRel->rd_att, i);
+		char *resname = NameStr(attr->attname);
+
+		tle->resname = pstrdup(resname);
+		i++;
+	}
+
+	/* Set all tables in the query to pre-update state */
+	rewritten = rewrite_query_for_preupdate_state(rewritten, entry->tables,
+												  pstate, matviewOid);
+	/* Rewrite for counting duplicated tuples */
+	rewritten = rewrite_query_for_counting(rewritten, pstate);
+
+	/* Create tuplestores to store view deltas */
+	if (entry->has_old)
+	{
+		oldcxt = MemoryContextSwitchTo(TopTransactionContext);
+
+		old_tuplestore = tuplestore_begin_heap(false, false, work_mem);
+		dest_old = CreateDestReceiver(DestTuplestore);
+		SetTuplestoreDestReceiverParams(dest_old,
+									old_tuplestore,
+									TopTransactionContext,
+									false,
+									NULL,
+									NULL);
+
+		MemoryContextSwitchTo(oldcxt);
+	}
+	if (entry->has_new)
+	{
+		oldcxt = MemoryContextSwitchTo(TopTransactionContext);
+
+		new_tuplestore = tuplestore_begin_heap(false, false, work_mem);
+		dest_new = CreateDestReceiver(DestTuplestore);
+		SetTuplestoreDestReceiverParams(dest_new,
+									new_tuplestore,
+									TopTransactionContext,
+									false,
+									NULL,
+									NULL);
+		MemoryContextSwitchTo(oldcxt);
+	}
+
+	/* for all modified tables */
+	foreach(lc, entry->tables)
+	{
+		ListCell *lc2;
+
+		table = (MV_TriggerTable *) lfirst(lc);
+
+		/* loop for self-join */
+		foreach(lc2, table->rte_indexes)
+		{
+			int	rte_index = lfirst_int(lc2);
+			TupleDesc		tupdesc_old;
+			TupleDesc		tupdesc_new;
+
+			/* calculate delta tables */
+			calc_delta(table, rte_index, rewritten, dest_old, dest_new,
+					   &tupdesc_old, &tupdesc_new, queryEnv);
+
+			/* Set the table in the query to post-update state */
+			rewritten = rewrite_query_for_postupdate_state(rewritten, table, rte_index);
+
+			PG_TRY();
+			{
+				/* apply the delta tables to the materialized view */
+				apply_delta(matviewOid, old_tuplestore, new_tuplestore,
+							tupdesc_old, tupdesc_new, query);
+			}
+			PG_CATCH();
+			{
+				matview_maintenance_depth = old_depth;
+				PG_RE_THROW();
+			}
+			PG_END_TRY();
+
+			/* clear view delta tuplestores */
+			if (old_tuplestore)
+				tuplestore_clear(old_tuplestore);
+			if (new_tuplestore)
+				tuplestore_clear(new_tuplestore);
+		}
+	}
+
+	/* Clean up hash entry and delete tuplestores */
+	clean_up_IVM_hash_entry(entry, false);
+	if (old_tuplestore)
+	{
+		dest_old->rDestroy(dest_old);
+		tuplestore_end(old_tuplestore);
+	}
+	if (new_tuplestore)
+	{
+		dest_new->rDestroy(dest_new);
+		tuplestore_end(new_tuplestore);
+	}
+
+	/* Pop the original snapshot. */
+	PopActiveSnapshot();
+
+	table_close(matviewRel, NoLock);
+
+	/* Roll back any GUC changes */
+	AtEOXact_GUC(false, save_nestlevel);
+
+	/* Restore userid and security context */
+	SetUserIdAndSecContext(save_userid, save_sec_context);
+
+	return PointerGetDatum(NULL);
+}
+
+/*
+ * rewrite_query_for_preupdate_state
+ *
+ * Rewrite the query so that base tables' RTEs will represent "pre-update"
+ * state of tables. This is necessary to calculate view delta after multiple
+ * tables are modified.
+ */
+static Query*
+rewrite_query_for_preupdate_state(Query *query, List *tables,
+								  ParseState *pstate, Oid matviewid)
+{
+	ListCell *lc;
+	int num_rte = list_length(query->rtable);
+	int i;
+
+
+	/* register delta ENRs */
+	register_delta_ENRs(pstate, query, tables);
+
+	/* XXX: Is necessary? Is this right timing? */
+	AcquireRewriteLocks(query, true, false);
+
+	i = 1;
+	foreach(lc, query->rtable)
+	{
+		RangeTblEntry *r = (RangeTblEntry*) lfirst(lc);
+
+		ListCell *lc2;
+		foreach(lc2, tables)
+		{
+			MV_TriggerTable *table = (MV_TriggerTable *) lfirst(lc2);
+			/*
+			 * if the modified table is found then replace the original RTE with
+			 * "pre-state" RTE and append its index to the list.
+			 */
+			if (r->relid == table->table_id)
+			{
+				List *securityQuals;
+				List *withCheckOptions;
+				bool  hasRowSecurity;
+				bool  hasSubLinks;
+
+				RangeTblEntry *rte_pre = get_prestate_rte(r, table, pstate->p_queryEnv, matviewid);
+
+				/*
+				 * Set a row security poslicies of the modified table to the subquery RTE which
+				 * represents the pre-update state of the table.
+				 */
+				get_row_security_policies(query, table->original_rte, i,
+										  &securityQuals, &withCheckOptions,
+										  &hasRowSecurity, &hasSubLinks);
+
+				if (hasRowSecurity)
+				{
+					query->hasRowSecurity = true;
+					rte_pre->security_barrier = true;
+				}
+				if (hasSubLinks)
+					query->hasSubLinks = true;
+
+				rte_pre->securityQuals = securityQuals;
+				lfirst(lc) = rte_pre;
+
+				table->rte_indexes = lappend_int(table->rte_indexes, i);
+				break;
+			}
+		}
+
+		/* finish the loop if we processed all RTE included in the original query */
+		if (i++ >= num_rte)
+			break;
+	}
+
+	return query;
+}
+
+/*
+ * register_delta_ENRs
+ *
+ * For all modified tables, make ENRs for their transition tables
+ * and register them to the queryEnv. ENR's RTEs are also appended
+ * into the list in query tree.
+ */
+static void
+register_delta_ENRs(ParseState *pstate, Query *query, List *tables)
+{
+	QueryEnvironment *queryEnv = pstate->p_queryEnv;
+	ListCell *lc;
+	RangeTblEntry	*rte;
+
+	foreach(lc, tables)
+	{
+		MV_TriggerTable *table = (MV_TriggerTable *) lfirst(lc);
+		ListCell *lc2;
+		int count;
+
+		count = 0;
+		foreach(lc2, table->old_tuplestores)
+		{
+			Tuplestorestate *oldtable = (Tuplestorestate *) lfirst(lc2);
+			EphemeralNamedRelation enr =
+				palloc(sizeof(EphemeralNamedRelationData));
+			ParseNamespaceItem *nsitem;
+
+			enr->md.name = make_delta_enr_name("old", table->table_id, count);
+			enr->md.reliddesc = table->table_id;
+			enr->md.tupdesc = NULL;
+			enr->md.enrtype = ENR_NAMED_TUPLESTORE;
+			enr->md.enrtuples = tuplestore_tuple_count(oldtable);
+			enr->reldata = oldtable;
+			register_ENR(queryEnv, enr);
+
+			nsitem = addRangeTableEntryForENR(pstate, makeRangeVar(NULL, enr->md.name, -1), true);
+			rte = nsitem->p_rte;
+
+			query->rtable = lappend(query->rtable, rte);
+
+			count++;
+		}
+
+		count = 0;
+		foreach(lc2, table->new_tuplestores)
+		{
+			Tuplestorestate *newtable = (Tuplestorestate *) lfirst(lc2);
+			EphemeralNamedRelation enr =
+				palloc(sizeof(EphemeralNamedRelationData));
+			ParseNamespaceItem *nsitem;
+
+			enr->md.name = make_delta_enr_name("new", table->table_id, count);
+			enr->md.reliddesc = table->table_id;
+			enr->md.tupdesc = NULL;
+			enr->md.enrtype = ENR_NAMED_TUPLESTORE;
+			enr->md.enrtuples = tuplestore_tuple_count(newtable);
+			enr->reldata = newtable;
+			register_ENR(queryEnv, enr);
+
+			nsitem = addRangeTableEntryForENR(pstate, makeRangeVar(NULL, enr->md.name, -1), true);
+			rte = nsitem->p_rte;
+
+			query->rtable = lappend(query->rtable, rte);
+
+			count++;
+		}
+	}
+}
+
+#define DatumGetItemPointer(X)	 ((ItemPointer) DatumGetPointer(X))
+#define PG_GETARG_ITEMPOINTER(n) DatumGetItemPointer(PG_GETARG_DATUM(n))
+
+/*
+ * ivm_visible_in_prestate
+ *
+ * Check visibility of a tuple specified by the tableoid and item pointer
+ * using the snapshot taken just before the table was modified.
+ */
+Datum
+ivm_visible_in_prestate(PG_FUNCTION_ARGS)
+{
+	Oid			tableoid = PG_GETARG_OID(0);
+	ItemPointer itemPtr = PG_GETARG_ITEMPOINTER(1);
+	Oid			matviewOid = PG_GETARG_OID(2);
+	MV_TriggerHashEntry *entry;
+	MV_TriggerTable		*table = NULL;
+	ListCell   *lc;
+	bool	found;
+	bool	result;
+
+	if (!in_delta_calculation)
+		ereport(ERROR,
+				(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+				 errmsg("ivm_visible_in_prestate can be called only in delta calculation")));
+
+	entry = (MV_TriggerHashEntry *) hash_search(mv_trigger_info,
+											  (void *) &matviewOid,
+											  HASH_FIND, &found);
+	Assert (found && entry != NULL);
+
+	foreach(lc, entry->tables)
+	{
+		table = (MV_TriggerTable *) lfirst(lc);
+		if (table->table_id == tableoid)
+			break;
+	}
+
+	Assert (table != NULL);
+
+	result = table_tuple_fetch_row_version(table->rel, itemPtr, entry->snapshot, table->slot);
+
+	PG_RETURN_BOOL(result);
+}
+
+/*
+ * get_prestate_rte
+ *
+ * Rewrite RTE of the modified table to a subquery which represents
+ * "pre-state" table. The original RTE is saved in table->rte_original.
+ */
+static RangeTblEntry*
+get_prestate_rte(RangeTblEntry *rte, MV_TriggerTable *table,
+				 QueryEnvironment *queryEnv, Oid matviewid)
+{
+	StringInfoData str;
+	RawStmt *raw;
+	Query *subquery;
+	Relation rel;
+	ParseState *pstate;
+	char *relname;
+	int i;
+
+	pstate = make_parsestate(NULL);
+	pstate->p_queryEnv = queryEnv;
+	pstate->p_expr_kind = EXPR_KIND_SELECT_TARGET;
+
+	/*
+	 * We can use NoLock here since AcquireRewriteLocks should
+	 * have locked the relation already.
+	 */
+	rel = table_open(table->table_id, NoLock);
+	relname = quote_qualified_identifier(
+					get_namespace_name(RelationGetNamespace(rel)),
+									   RelationGetRelationName(rel));
+	table_close(rel, NoLock);
+
+	/*
+	 * Filtering inserted row using the snapshot taken before the table
+	 * is modified. ctid is required for maintaining outer join views.
+	 */
+	initStringInfo(&str);
+	appendStringInfo(&str,
+		"SELECT t.* FROM %s t"
+		" WHERE pg_catalog.ivm_visible_in_prestate(t.tableoid, t.ctid ,%d::pg_catalog.oid)",
+			relname, matviewid);
+
+	/*
+	 * Append deleted rows contained in old transition tables.
+	 */
+	for (i = 0; i < list_length(table->old_tuplestores); i++)
+	{
+		appendStringInfo(&str, " UNION ALL ");
+		appendStringInfo(&str," SELECT * FROM %s",
+			make_delta_enr_name("old", table->table_id, i));
+	}
+
+	/* Get a subquery representing pre-state of the table */
+	raw = (RawStmt*)linitial(raw_parser(str.data, RAW_PARSE_DEFAULT));
+	subquery = transformStmt(pstate, raw->stmt);
+
+	/* save the original RTE */
+	table->original_rte = copyObject(rte);
+
+	rte->rtekind = RTE_SUBQUERY;
+	rte->subquery = subquery;
+	rte->security_barrier = false;
+
+	/* Clear fields that should not be set in a subquery RTE */
+	rte->relid = InvalidOid;
+	rte->relkind = 0;
+	rte->rellockmode = 0;
+	rte->tablesample = NULL;
+	rte->perminfoindex = 0;         /* no permission checking for this RTE */
+	rte->inh = false;			/* must not be set for a subquery */
+
+	return rte;
+}
+
+/*
+ * make_delta_enr_name
+ *
+ * Make a name for ENR of a transition table from the base table's oid.
+ * prefix will be "new" or "old" depending on its transition table kind..
+ */
+static char*
+make_delta_enr_name(const char *prefix, Oid relid, int count)
+{
+	char buf[NAMEDATALEN];
+	char *name;
+
+	snprintf(buf, NAMEDATALEN, "__ivm_%s_%u_%u", prefix, relid, count);
+	name = pstrdup(buf);
+
+	return name;
+}
+
+/*
+ * replace_rte_with_delta
+ *
+ * Replace RTE of the modified table with a single table delta that combine its
+ * all transition tables.
+ */
+static RangeTblEntry*
+replace_rte_with_delta(RangeTblEntry *rte, MV_TriggerTable *table, bool is_new,
+					   QueryEnvironment *queryEnv)
+{
+	Oid relid = table->table_id;
+	StringInfoData str;
+	ParseState	*pstate;
+	RawStmt *raw;
+	Query *sub;
+	int		num_tuplestores = list_length(is_new ? table->new_tuplestores : table->old_tuplestores);
+	int		i;
+
+	/* the previous RTE must be a subquery which represents "pre-state" table */
+	Assert(rte->rtekind == RTE_SUBQUERY);
+
+	/* Create a ParseState for rewriting the view definition query */
+	pstate = make_parsestate(NULL);
+	pstate->p_queryEnv = queryEnv;
+	pstate->p_expr_kind = EXPR_KIND_SELECT_TARGET;
+
+	initStringInfo(&str);
+
+	for (i = 0; i < num_tuplestores; i++)
+	{
+		if (i > 0)
+			appendStringInfo(&str, " UNION ALL ");
+
+		appendStringInfo(&str,
+			" SELECT * FROM %s",
+			make_delta_enr_name(is_new ? "new" : "old", relid, i));
+	}
+
+	raw = (RawStmt*)linitial(raw_parser(str.data, RAW_PARSE_DEFAULT));
+	sub = transformStmt(pstate, raw->stmt);
+
+	/*
+	 * Update the subquery so that it represent the combined transition
+	 * table.  Note that we leave the security_barrier and securityQuals
+	 * fields so that the subquery relation can be protected by the RLS
+	 * policy as same as the modified table.
+	 */
+	rte->rtekind = RTE_SUBQUERY;
+	rte->subquery = sub;
+
+	return rte;
+}
+
+/*
+ * rewrite_query_for_counting
+ *
+ * Rewrite query for counting duplicated tuples.
+ */
+static Query *
+rewrite_query_for_counting(Query *query, ParseState *pstate)
+{
+	TargetEntry *tle_count;
+	FuncCall *fn;
+	Node *node;
+
+	/* Add count(*) for counting distinct tuples in views */
+	fn = makeFuncCall(SystemFuncName("count"), NIL, COERCE_EXPLICIT_CALL, -1);
+	fn->agg_star = true;
+	if (!query->groupClause && !query->hasAggs)
+		query->groupClause = transformDistinctClause(NULL, &query->targetList, query->sortClause, false);
+
+	node = ParseFuncOrColumn(pstate, fn->funcname, NIL, NULL, fn, false, -1);
+
+	tle_count = makeTargetEntry((Expr *) node,
+								list_length(query->targetList) + 1,
+								pstrdup("__ivm_count__"),
+								false);
+	query->targetList = lappend(query->targetList, tle_count);
+	query->hasAggs = true;
+
+	return query;
+}
+
+/*
+ * calc_delta
+ *
+ * Calculate view deltas generated under the modification of a table specified
+ * by the RTE index.
+ */
+static void
+calc_delta(MV_TriggerTable *table, int rte_index, Query *query,
+			DestReceiver *dest_old, DestReceiver *dest_new,
+			TupleDesc *tupdesc_old, TupleDesc *tupdesc_new,
+			QueryEnvironment *queryEnv)
+{
+	ListCell *lc = list_nth_cell(query->rtable, rte_index - 1);
+	RangeTblEntry *rte = (RangeTblEntry *) lfirst(lc);
+
+	in_delta_calculation = true;
+
+	/* Generate old delta */
+	if (list_length(table->old_tuplestores) > 0)
+	{
+		/* Replace the modified table with the old delta table and calculate the old view delta. */
+		replace_rte_with_delta(rte, table, false, queryEnv);
+		refresh_matview_datafill(dest_old, query, queryEnv, tupdesc_old, "");
+	}
+
+	/* Generate new delta */
+	if (list_length(table->new_tuplestores) > 0)
+	{
+		/* Replace the modified table with the new delta table and calculate the new view delta*/
+		replace_rte_with_delta(rte, table, true, queryEnv);
+		refresh_matview_datafill(dest_new, query, queryEnv, tupdesc_new, "");
+	}
+
+	in_delta_calculation = false;
+}
+
+/*
+ * rewrite_query_for_postupdate_state
+ *
+ * Rewrite the query so that the specified base table's RTEs will represent
+ * "post-update" state of tables. This is called after the view delta
+ * calculation due to changes on this table finishes.
+ */
+static Query*
+rewrite_query_for_postupdate_state(Query *query, MV_TriggerTable *table, int rte_index)
+{
+	ListCell *lc = list_nth_cell(query->rtable, rte_index - 1);
+
+	/* Retore the original RTE */
+	lfirst(lc) = table->original_rte;
+
+	return query;
+}
+
+/*
+ * apply_delta
+ *
+ * Apply deltas to the materialized view. In outer join cases, this requires
+ * the view maintenance graph.
+ */
+static void
+apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *new_tuplestores,
+			TupleDesc tupdesc_old, TupleDesc tupdesc_new,
+			Query *query)
+{
+	StringInfoData querybuf;
+	StringInfoData target_list_buf;
+	Relation	matviewRel;
+	char	   *matviewname;
+	ListCell	*lc;
+	int			i;
+	List	   *keys = NIL;
+
+
+	/*
+	 * get names of the materialized view and delta tables
+	 */
+
+	matviewRel = table_open(matviewOid, NoLock);
+	matviewname = quote_qualified_identifier(get_namespace_name(RelationGetNamespace(matviewRel)),
+											 RelationGetRelationName(matviewRel));
+
+	/*
+	 * Build parts of the maintenance queries
+	 */
+
+	initStringInfo(&querybuf);
+	initStringInfo(&target_list_buf);
+
+	/* build string of target list */
+	for (i = 0; i < matviewRel->rd_att->natts; i++)
+	{
+		Form_pg_attribute attr = TupleDescAttr(matviewRel->rd_att, i);
+		char   *resname = NameStr(attr->attname);
+
+		if (i != 0)
+			appendStringInfo(&target_list_buf, ", ");
+		appendStringInfo(&target_list_buf, "%s", quote_qualified_identifier(NULL, resname));
+	}
+
+	i = 0;
+	foreach (lc, query->targetList)
+	{
+		TargetEntry *tle = (TargetEntry *) lfirst(lc);
+		Form_pg_attribute attr = TupleDescAttr(matviewRel->rd_att, i);
+
+		i++;
+
+		if (tle->resjunk)
+			continue;
+
+		keys = lappend(keys, attr);
+	}
+
+	/* Start maintaining the materialized view. */
+	OpenMatViewIncrementalMaintenance();
+
+	/* Open SPI context. */
+	if (SPI_connect() != SPI_OK_CONNECT)
+		elog(ERROR, "SPI_connect failed");
+
+	/* For tuple deletion */
+	if (old_tuplestores && tuplestore_tuple_count(old_tuplestores) > 0)
+	{
+		EphemeralNamedRelation enr = palloc(sizeof(EphemeralNamedRelationData));
+		int				rc;
+
+		/* convert tuplestores to ENR, and register for SPI */
+		enr->md.name = pstrdup(OLD_DELTA_ENRNAME);
+		enr->md.reliddesc = InvalidOid;
+		enr->md.tupdesc = tupdesc_old;
+		enr->md.enrtype = ENR_NAMED_TUPLESTORE;
+		enr->md.enrtuples = tuplestore_tuple_count(old_tuplestores);
+		enr->reldata = old_tuplestores;
+
+		rc = SPI_register_relation(enr);
+		if (rc != SPI_OK_REL_REGISTER)
+			elog(ERROR, "SPI_register failed");
+
+		apply_old_delta(matviewname, OLD_DELTA_ENRNAME, keys);
+
+	}
+	/* For tuple insertion */
+	if (new_tuplestores && tuplestore_tuple_count(new_tuplestores) > 0)
+	{
+		EphemeralNamedRelation enr = palloc(sizeof(EphemeralNamedRelationData));
+		int rc;
+
+		/* convert tuplestores to ENR, and register for SPI */
+		enr->md.name = pstrdup(NEW_DELTA_ENRNAME);
+		enr->md.reliddesc = InvalidOid;
+		enr->md.tupdesc = tupdesc_new;;
+		enr->md.enrtype = ENR_NAMED_TUPLESTORE;
+		enr->md.enrtuples = tuplestore_tuple_count(new_tuplestores);
+		enr->reldata = new_tuplestores;
+
+		rc = SPI_register_relation(enr);
+		if (rc != SPI_OK_REL_REGISTER)
+			elog(ERROR, "SPI_register failed");
+
+		/* apply new delta */
+		apply_new_delta(matviewname, NEW_DELTA_ENRNAME, &target_list_buf);
+	}
+
+	/* We're done maintaining the materialized view. */
+	CloseMatViewIncrementalMaintenance();
+
+	table_close(matviewRel, NoLock);
+
+	/* Close SPI context. */
+	if (SPI_finish() != SPI_OK_FINISH)
+		elog(ERROR, "SPI_finish failed");
+}
+
+/*
+ * apply_old_delta
+ *
+ * Execute a query for applying a delta table given by deltname_old
+ * which contains tuples to be deleted from to a materialized view given by
+ * matviewname.  This is used when counting is not required.
+ */
+static void
+apply_old_delta(const char *matviewname, const char *deltaname_old,
+				List *keys)
+{
+	StringInfoData	querybuf;
+	StringInfoData	keysbuf;
+	char   *match_cond;
+	ListCell *lc;
+
+	/* build WHERE condition for searching tuples to be deleted */
+	match_cond = get_matching_condition_string(keys);
+
+	/* build string of keys list */
+	initStringInfo(&keysbuf);
+	foreach (lc, keys)
+	{
+		Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc);
+		char   *resname = NameStr(attr->attname);
+		appendStringInfo(&keysbuf, "%s", quote_qualified_identifier("mv", resname));
+		if (lnext(keys, lc))
+			appendStringInfo(&keysbuf, ", ");
+	}
+
+	/* Search for matching tuples from the view and update or delete if found. */
+	initStringInfo(&querybuf);
+	appendStringInfo(&querybuf,
+	"DELETE FROM %s WHERE ctid IN ("
+		"SELECT tid FROM (SELECT pg_catalog.row_number() over (partition by %s) AS \"__ivm_row_number__\","
+								  "mv.ctid AS tid,"
+								  "diff.\"__ivm_count__\""
+						 "FROM %s AS mv, %s AS diff "
+						 "WHERE %s) v "
+					"WHERE v.\"__ivm_row_number__\" OPERATOR(pg_catalog.<=) v.\"__ivm_count__\")",
+					matviewname,
+					keysbuf.data,
+					matviewname, deltaname_old,
+					match_cond);
+
+	if (SPI_exec(querybuf.data, 0) != SPI_OK_DELETE)
+		elog(ERROR, "SPI_exec failed: %s", querybuf.data);
+}
+
+/*
+ * apply_new_delta
+ *
+ * Execute a query for applying a delta table given by deltname_new
+ * which contains tuples to be inserted into a materialized view given by
+ * matviewname.  This is used when counting is not required.
+ */
+static void
+apply_new_delta(const char *matviewname, const char *deltaname_new,
+				StringInfo target_list)
+{
+	StringInfoData	querybuf;
+
+	/* Search for matching tuples from the view and update or delete if found. */
+	initStringInfo(&querybuf);
+	appendStringInfo(&querybuf,
+					"INSERT INTO %s (%s) SELECT %s FROM ("
+						"SELECT diff.*, pg_catalog.generate_series(1, diff.\"__ivm_count__\")"
+							" AS __ivm_generate_series__ "
+						"FROM %s AS diff) AS v",
+					matviewname, target_list->data, target_list->data,
+					deltaname_new);
+
+	if (SPI_exec(querybuf.data, 0) != SPI_OK_INSERT)
+		elog(ERROR, "SPI_exec failed: %s", querybuf.data);
+}
+
+/*
+ * get_matching_condition_string
+ *
+ * Build a predicate string for looking for a tuple with given keys.
+ */
+static char *
+get_matching_condition_string(List *keys)
+{
+	StringInfoData match_cond;
+	ListCell	*lc;
+
+	/* If there is no key columns, the condition is always true. */
+	if (keys == NIL)
+		return "true";
+
+	initStringInfo(&match_cond);
+	foreach (lc, keys)
+	{
+		Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc);
+		char   *resname = NameStr(attr->attname);
+		char   *mv_resname = quote_qualified_identifier("mv", resname);
+		char   *diff_resname = quote_qualified_identifier("diff", resname);
+		Oid		typid = attr->atttypid;
+
+		/* Considering NULL values, we can not use simple = operator. */
+		appendStringInfo(&match_cond, "(");
+		generate_equal(&match_cond, typid, mv_resname, diff_resname);
+		appendStringInfo(&match_cond, " OR (%s IS NULL AND %s IS NULL))",
+						 mv_resname, diff_resname);
+
+		if (lnext(keys, lc))
+			appendStringInfo(&match_cond, " AND ");
+	}
+
+	return match_cond.data;
+}
+
+/*
+ * generate_equals
+ *
+ * Generate an equality clause using given operands' default equality
+ * operator.
+ */
+static void
+generate_equal(StringInfo querybuf, Oid opttype,
+			   const char *leftop, const char *rightop)
+{
+	TypeCacheEntry *typentry;
+
+	typentry = lookup_type_cache(opttype, TYPECACHE_EQ_OPR);
+	if (!OidIsValid(typentry->eq_opr))
+		ereport(ERROR,
+				(errcode(ERRCODE_UNDEFINED_FUNCTION),
+				 errmsg("could not identify an equality operator for type %s",
+						format_type_be_qualified(opttype))));
+
+	generate_operator_clause(querybuf,
+							 leftop, opttype,
+							 typentry->eq_opr,
+							 rightop, opttype);
+}
+
+/*
+ * mv_InitHashTables
+ */
+static void
+mv_InitHashTables(void)
+{
+	HASHCTL		ctl;
+
+	memset(&ctl, 0, sizeof(ctl));
+	ctl.keysize = sizeof(Oid);
+	ctl.entrysize = sizeof(MV_TriggerHashEntry);
+	mv_trigger_info = hash_create("MV trigger info",
+								 MV_INIT_QUERYHASHSIZE,
+								 &ctl, HASH_ELEM | HASH_BLOBS);
+}
+
+/*
+ * AtAbort_IVM
+ *
+ * Clean up hash entries for all materialized views. This is called at
+ * transaction abort.
+ */
+void
+AtAbort_IVM()
+{
+	HASH_SEQ_STATUS seq;
+	MV_TriggerHashEntry *entry;
+
+	if (mv_trigger_info)
+	{
+		hash_seq_init(&seq, mv_trigger_info);
+		while ((entry = hash_seq_search(&seq)) != NULL)
+			clean_up_IVM_hash_entry(entry, true);
+	}
+	in_delta_calculation = false;
+}
+
+/*
+ * clean_up_IVM_hash_entry
+ *
+ * Clean up tuple stores and hash entries for a materialized view after its
+ * maintenance finished.
+ */
+static void
+clean_up_IVM_hash_entry(MV_TriggerHashEntry *entry, bool is_abort)
+{
+	bool found;
+	ListCell *lc;
+
+	foreach(lc, entry->tables)
+	{
+		MV_TriggerTable *table = (MV_TriggerTable *) lfirst(lc);
+
+		list_free(table->old_tuplestores);
+		list_free(table->new_tuplestores);
+		if (!is_abort)
+		{
+			ExecDropSingleTupleTableSlot(table->slot);
+			table_close(table->rel, NoLock);
+		}
+	}
+	list_free(entry->tables);
+
+	if (!is_abort)
+		UnregisterSnapshot(entry->snapshot);
+
+	hash_search(mv_trigger_info, (void *) &entry->matview_id, HASH_REMOVE, &found);
+}
+
+/*
+ * isIvmName
+ *
+ * Check if this is a IVM hidden column from the name.
+ */
+bool
+isIvmName(const char *s)
+{
+	if (s)
+		return (strncmp(s, "__ivm_", 6) == 0);
+	return false;
+}
diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat
index 9c120fc2b7..e111f11bf5 100644
--- a/src/include/catalog/pg_proc.dat
+++ b/src/include/catalog/pg_proc.dat
@@ -12174,4 +12174,14 @@
   proargtypes => 'int2',
   prosrc => 'gist_stratnum_identity' },
 
+# IVM
+{ oid => '786', descr => 'ivm trigger (before)',
+  proname => 'IVM_immediate_before', provolatile => 'v', prorettype => 'trigger',
+  proargtypes => '', prosrc => 'IVM_immediate_before' },
+{ oid => '787', descr => 'ivm trigger (after)',
+  proname => 'IVM_immediate_maintenance', provolatile => 'v', prorettype => 'trigger',
+  proargtypes => '', prosrc => 'IVM_immediate_maintenance' },
+{ oid => '788', descr => 'ivm filetring ',
+  proname => 'ivm_visible_in_prestate', provolatile => 's', prorettype => 'bool',
+  proargtypes => 'oid tid oid', prosrc => 'ivm_visible_in_prestate' },
 ]
diff --git a/src/include/commands/createas.h b/src/include/commands/createas.h
index 94678e3834..396ad1bb4c 100644
--- a/src/include/commands/createas.h
+++ b/src/include/commands/createas.h
@@ -16,6 +16,7 @@
 
 #include "catalog/objectaddress.h"
 #include "nodes/params.h"
+#include "nodes/pathnodes.h"
 #include "parser/parse_node.h"
 #include "tcop/dest.h"
 #include "utils/queryenvironment.h"
@@ -25,6 +26,9 @@ extern ObjectAddress ExecCreateTableAs(ParseState *pstate, CreateTableAsStmt *st
 									   ParamListInfo params, QueryEnvironment *queryEnv,
 									   QueryCompletion *qc);
 
+extern void CreateIvmTriggersOnBaseTables(Query *qry, Oid matviewOid);
+extern void CreateIndexOnIMMV(Query *query, Relation matviewRel);
+
 extern int	GetIntoRelEFlags(IntoClause *intoClause);
 
 extern DestReceiver *CreateIntoRelDestReceiver(IntoClause *intoClause);
diff --git a/src/include/commands/matview.h b/src/include/commands/matview.h
index 817b2ba0b6..3257e1adff 100644
--- a/src/include/commands/matview.h
+++ b/src/include/commands/matview.h
@@ -15,6 +15,7 @@
 #define MATVIEW_H
 
 #include "catalog/objectaddress.h"
+#include "fmgr.h"
 #include "nodes/params.h"
 #include "nodes/parsenodes.h"
 #include "tcop/dest.h"
@@ -23,6 +24,8 @@
 
 extern void SetMatViewPopulatedState(Relation relation, bool newstate);
 
+extern void SetMatViewIVMState(Relation relation, bool newstate);
+
 extern ObjectAddress ExecRefreshMatView(RefreshMatViewStmt *stmt, const char *queryString,
 										ParamListInfo params, QueryCompletion *qc);
 
@@ -30,4 +33,10 @@ extern DestReceiver *CreateTransientRelDestReceiver(Oid transientoid);
 
 extern bool MatViewIncrementalMaintenanceIsEnabled(void);
 
+extern Datum IVM_immediate_before(PG_FUNCTION_ARGS);
+extern Datum IVM_immediate_maintenance(PG_FUNCTION_ARGS);
+extern Datum IVM_visible_in_prestate(PG_FUNCTION_ARGS);
+extern void AtAbort_IVM(void);
+extern bool isIvmName(const char *s);
+
 #endif							/* MATVIEW_H */
-- 
2.25.1


--Multipart=_Mon__4_Mar_2024_11_58_46_+0900_UaponF/qQhQrVCFt
Content-Type: text/x-diff;
 name="v30-0007-Add-DISTINCT-support-for-IVM.patch"
Content-Disposition: attachment;
 filename="v30-0007-Add-DISTINCT-support-for-IVM.patch"
Content-Transfer-Encoding: 7bit



^ permalink  raw  reply  [nested|flat] 101+ messages in thread

* Re: Conflict Detection and Resolution
@ 2024-07-03 05:30  shveta malik <[email protected]>
  0 siblings, 1 reply; 101+ messages in thread

From: shveta malik @ 2024-07-03 05:30 UTC (permalink / raw)
  To: Dilip Kumar <[email protected]>; +Cc: Amit Kapila <[email protected]>; Tomas Vondra <[email protected]>; pgsql-hackers; Zhijie Hou (Fujitsu) <[email protected]>; Nisha Moond <[email protected]>; shveta malik <[email protected]>

On Wed, Jul 3, 2024 at 10:47 AM Dilip Kumar <[email protected]> wrote:
>
> On Tue, Jul 2, 2024 at 2:40 PM shveta malik <[email protected]> wrote:
> >
> > On Wed, Jun 19, 2024 at 1:52 PM Dilip Kumar <[email protected]> wrote:
> > >
> > > On Tue, Jun 18, 2024 at 3:29 PM shveta malik <[email protected]> wrote:
> > > > On Tue, Jun 18, 2024 at 11:34 AM Dilip Kumar <[email protected]> wrote:
> > > >
> > > > I tried to work out a few scenarios with this, where the apply worker
> > > > will wait until its local clock hits 'remote_commit_tts - max_skew
> > > > permitted'. Please have a look.
> > > >
> > > > Let's say, we have a GUC to configure max_clock_skew permitted.
> > > > Resolver is last_update_wins in both cases.
> > > > ----------------
> > > > 1) Case 1: max_clock_skew set to 0 i.e. no tolerance for clock skew.
> > > >
> > > > Remote Update with commit_timestamp = 10.20AM.
> > > > Local clock (which is say 5 min behind) shows = 10.15AM.
> > > >
> > > > When remote update arrives at local node, we see that skew is greater
> > > > than max_clock_skew and thus apply worker waits till local clock hits
> > > > 'remote's commit_tts - max_clock_skew' i.e. till 10.20 AM. Once the
> > > > local clock hits 10.20 AM, the worker applies the remote change with
> > > > commit_tts of 10.20AM. In the meantime (during wait period of apply
> > > > worker)) if some local update on same row has happened at say 10.18am,
> > > > that will applied first, which will be later overwritten by above
> > > > remote change of 10.20AM as remote-change's timestamp appear more
> > > > latest, even though it has happened earlier than local change.
> > >
> > > For the sake of simplicity let's call the change that happened at
> > > 10:20 AM change-1 and the change that happened at 10:15 as change-2
> > > and assume we are talking about the synchronous commit only.
> > >
> > > I think now from an application perspective the change-1 wouldn't have
> > > caused the change-2 because we delayed applying change-2 on the local
> > > node which would have delayed the confirmation of the change-1 to the
> > > application that means we have got the change-2 on the local node
> > > without the confirmation of change-1 hence change-2 has no causal
> > > dependency on the change-1.  So it's fine that we perform change-1
> > > before change-2 and the timestamp will also show the same at any other
> > > node if they receive these 2 changes.
> > >
> > > The goal is to ensure that if we define the order where change-2
> > > happens before change-1, this same order should be visible on all
> > > other nodes. This will hold true because the commit timestamp of
> > > change-2 is earlier than that of change-1.
> > >
> > > > 2)  Case 2: max_clock_skew is set to 2min.
> > > >
> > > > Remote Update with commit_timestamp=10.20AM
> > > > Local clock (which is say 5 min behind) = 10.15AM.
> > > >
> > > > Now apply worker will notice skew greater than 2min and thus will wait
> > > > till local clock hits 'remote's commit_tts - max_clock_skew' i.e.
> > > > 10.18 and will apply the change with commit_tts of 10.20 ( as we
> > > > always save the origin's commit timestamp into local commit_tts, see
> > > > RecordTransactionCommit->TransactionTreeSetCommitTsData). Now lets say
> > > > another local update is triggered at 10.19am, it will be applied
> > > > locally but it will be ignored on remote node. On the remote node ,
> > > > the existing change with a timestamp of 10.20 am will win resulting in
> > > > data divergence.
> > >
> > > Let's call the 10:20 AM change as a change-1 and the change that
> > > happened at 10:19 as change-2
> > >
> > > IIUC, although we apply the change-1 at 10:18 AM the commit_ts of that
> > > commit_ts of that change is 10:20, and the same will be visible to all
> > > other nodes.  So in conflict resolution still the change-1 happened
> > > after the change-2 because change-2's commit_ts is 10:19 AM.   Now
> > > there could be a problem with the causal order because we applied the
> > > change-1 at 10:18 AM so the application might have gotten confirmation
> > > at 10:18 AM and the change-2 of the local node may be triggered as a
> > > result of confirmation of the change-1 that means now change-2 has a
> > > causal dependency on the change-1 but commit_ts shows change-2
> > > happened before the change-1 on all the nodes.
> > >
> > > So, is this acceptable? I think yes because the user has configured a
> > > maximum clock skew of 2 minutes, which means the detected order might
> > > not always align with the causal order for transactions occurring
> > > within that time frame. Generally, the ideal configuration for
> > > max_clock_skew should be in multiple of the network round trip time.
> > > Assuming this configuration, we wouldn’t encounter this problem
> > > because for change-2 to be caused by change-1, the client would need
> > > to get confirmation of change-1 and then trigger change-2, which would
> > > take at least 2-3 network round trips.
> >
> > As we agreed, the subscriber should wait before applying an operation
> > if the commit timestamp of the currently replayed transaction is in
> > the future and the difference exceeds the maximum clock skew. This
> > raises the question: should the subscriber wait only for insert,
> > update, and delete operations when timestamp-based resolution methods
> > are set, or should it wait regardless of the type of remote operation,
> > the presence or absence of conflicts, and the resolvers configured?
> > I believe the latter approach is the way to go i.e. this should be
> > independent of CDR, though needed by CDR for better timestamp based
> > resolutions. Thoughts?
>
> Yes, I also think it should be independent of CDR.  IMHO, it should be
> based on the user-configured maximum clock skew tolerance and can be
> independent of CDR.

+1

> IIUC we would make the remote apply wait just
> before committing if the remote commit timestamp is ahead of the local
> clock by more than the maximum clock skew tolerance, is that correct?

+1 on condition to wait.

But I think we should make apply worker wait during begin
(apply_handle_begin) instead of commit. It makes more sense to delay
the entire operation to manage clock-skew rather than the commit
alone. And only then CDR's timestamp based resolution which are much
prior to commit-stage can benefit from this. Thoughts?

thanks
Shveta






^ permalink  raw  reply  [nested|flat] 101+ messages in thread

* Re: Conflict Detection and Resolution
@ 2024-07-03 05:59  Dilip Kumar <[email protected]>
  parent: shveta malik <[email protected]>
  0 siblings, 2 replies; 101+ messages in thread

From: Dilip Kumar @ 2024-07-03 05:59 UTC (permalink / raw)
  To: shveta malik <[email protected]>; +Cc: Amit Kapila <[email protected]>; Tomas Vondra <[email protected]>; pgsql-hackers; Zhijie Hou (Fujitsu) <[email protected]>; Nisha Moond <[email protected]>

On Wed, Jul 3, 2024 at 11:00 AM shveta malik <[email protected]> wrote:
>
> > Yes, I also think it should be independent of CDR.  IMHO, it should be
> > based on the user-configured maximum clock skew tolerance and can be
> > independent of CDR.
>
> +1
>
> > IIUC we would make the remote apply wait just
> > before committing if the remote commit timestamp is ahead of the local
> > clock by more than the maximum clock skew tolerance, is that correct?
>
> +1 on condition to wait.
>
> But I think we should make apply worker wait during begin
> (apply_handle_begin) instead of commit. It makes more sense to delay
> the entire operation to manage clock-skew rather than the commit
> alone. And only then CDR's timestamp based resolution which are much
> prior to commit-stage can benefit from this. Thoughts?

But do we really need to wait at apply_handle_begin()? I mean if we
already know the commit_ts then we can perform the conflict resolution
no?  I mean we should wait before committing because we are
considering this remote transaction to be in the future and we do not
want to confirm the commit of this transaction to the remote node
before the local clock reaches the record commit_ts to preserve the
causal order.  However, we can still perform conflict resolution
beforehand since we already know the commit_ts. The conflict
resolution function will be something like "out_version =
CRF(version1_commit_ts, version2_commit_ts)," so the result should be
the same regardless of when we apply it, correct?  From a performance
standpoint, wouldn't it be beneficial to perform as much work as
possible in advance? By the time we apply all the operations, the
local clock might already be in sync with the commit_ts of the remote
transaction.  Am I missing something?

However, while thinking about this, I'm wondering about how we will
handle the streaming of in-progress transactions. If we start applying
with parallel workers, we might not know the commit_ts of those
transactions since they may not have been committed yet. One simple
option could be to prevent parallel workers from applying in-progress
transactions when CDR is set up. Instead, we could let these
transactions spill to files and only apply them once we receive the
commit record.

--
Regards,
Dilip Kumar
EnterpriseDB: http://www.enterprisedb.com






^ permalink  raw  reply  [nested|flat] 101+ messages in thread

* Re: Conflict Detection and Resolution
@ 2024-07-03 07:00  Amit Kapila <[email protected]>
  parent: Dilip Kumar <[email protected]>
  1 sibling, 2 replies; 101+ messages in thread

From: Amit Kapila @ 2024-07-03 07:00 UTC (permalink / raw)
  To: Dilip Kumar <[email protected]>; +Cc: shveta malik <[email protected]>; Tomas Vondra <[email protected]>; pgsql-hackers; Zhijie Hou (Fujitsu) <[email protected]>; Nisha Moond <[email protected]>

On Wed, Jul 3, 2024 at 11:29 AM Dilip Kumar <[email protected]> wrote:
>
> On Wed, Jul 3, 2024 at 11:00 AM shveta malik <[email protected]> wrote:
> >
> > > Yes, I also think it should be independent of CDR.  IMHO, it should be
> > > based on the user-configured maximum clock skew tolerance and can be
> > > independent of CDR.
> >
> > +1
> >
> > > IIUC we would make the remote apply wait just
> > > before committing if the remote commit timestamp is ahead of the local
> > > clock by more than the maximum clock skew tolerance, is that correct?
> >
> > +1 on condition to wait.
> >
> > But I think we should make apply worker wait during begin
> > (apply_handle_begin) instead of commit. It makes more sense to delay
> > the entire operation to manage clock-skew rather than the commit
> > alone. And only then CDR's timestamp based resolution which are much
> > prior to commit-stage can benefit from this. Thoughts?
>
> But do we really need to wait at apply_handle_begin()? I mean if we
> already know the commit_ts then we can perform the conflict resolution
> no?  I mean we should wait before committing because we are
> considering this remote transaction to be in the future and we do not
> want to confirm the commit of this transaction to the remote node
> before the local clock reaches the record commit_ts to preserve the
> causal order.  However, we can still perform conflict resolution
> beforehand since we already know the commit_ts. The conflict
> resolution function will be something like "out_version =
> CRF(version1_commit_ts, version2_commit_ts)," so the result should be
> the same regardless of when we apply it, correct?  From a performance
> standpoint, wouldn't it be beneficial to perform as much work as
> possible in advance? By the time we apply all the operations, the
> local clock might already be in sync with the commit_ts of the remote
> transaction.  Am I missing something?
>

But waiting after applying the operations and before applying the
commit would mean that we need to wait with the locks held. That could
be a recipe for deadlocks in the system. I see your point related to
performance but as we are not expecting clock skew in normal cases, we
shouldn't be too much bothered on the performance due to this. If
there is clock skew, we expect users to fix it, this is just a
worst-case aid for users.

> However, while thinking about this, I'm wondering about how we will
> handle the streaming of in-progress transactions. If we start applying
> with parallel workers, we might not know the commit_ts of those
> transactions since they may not have been committed yet. One simple
> option could be to prevent parallel workers from applying in-progress
> transactions when CDR is set up. Instead, we could let these
> transactions spill to files and only apply them once we receive the
> commit record.
>

Agreed, we should do it as you have suggested and document it.

-- 
With Regards,
Amit Kapila.






^ permalink  raw  reply  [nested|flat] 101+ messages in thread

* Re: Conflict Detection and Resolution
@ 2024-07-03 08:46  Dilip Kumar <[email protected]>
  parent: Amit Kapila <[email protected]>
  1 sibling, 1 reply; 101+ messages in thread

From: Dilip Kumar @ 2024-07-03 08:46 UTC (permalink / raw)
  To: Amit Kapila <[email protected]>; +Cc: shveta malik <[email protected]>; Tomas Vondra <[email protected]>; pgsql-hackers; Zhijie Hou (Fujitsu) <[email protected]>; Nisha Moond <[email protected]>

On Wed, Jul 3, 2024 at 12:30 PM Amit Kapila <[email protected]> wrote:
>
> On Wed, Jul 3, 2024 at 11:29 AM Dilip Kumar <[email protected]> wrote:

> But waiting after applying the operations and before applying the
> commit would mean that we need to wait with the locks held. That could
> be a recipe for deadlocks in the system. I see your point related to
> performance but as we are not expecting clock skew in normal cases, we
> shouldn't be too much bothered on the performance due to this. If
> there is clock skew, we expect users to fix it, this is just a
> worst-case aid for users.

But if we make it wait at the very first operation that means we will
not suck more decoded data from the network and wouldn't that make the
sender wait for the network buffer to get sucked in by the receiver?
Also, we already have a handling of parallel apply workers so if we do
not have an issue of deadlock there or if we can handle those issues
there we can do it here as well no?

-- 
Regards,
Dilip Kumar
EnterpriseDB: http://www.enterprisedb.com






^ permalink  raw  reply  [nested|flat] 101+ messages in thread

* Re: Conflict Detection and Resolution
@ 2024-07-03 10:05  Amit Kapila <[email protected]>
  parent: Dilip Kumar <[email protected]>
  0 siblings, 2 replies; 101+ messages in thread

From: Amit Kapila @ 2024-07-03 10:05 UTC (permalink / raw)
  To: Dilip Kumar <[email protected]>; +Cc: shveta malik <[email protected]>; Tomas Vondra <[email protected]>; pgsql-hackers; Zhijie Hou (Fujitsu) <[email protected]>; Nisha Moond <[email protected]>

On Wed, Jul 3, 2024 at 2:16 PM Dilip Kumar <[email protected]> wrote:
>
> On Wed, Jul 3, 2024 at 12:30 PM Amit Kapila <[email protected]> wrote:
> >
> > On Wed, Jul 3, 2024 at 11:29 AM Dilip Kumar <[email protected]> wrote:
>
> > But waiting after applying the operations and before applying the
> > commit would mean that we need to wait with the locks held. That could
> > be a recipe for deadlocks in the system. I see your point related to
> > performance but as we are not expecting clock skew in normal cases, we
> > shouldn't be too much bothered on the performance due to this. If
> > there is clock skew, we expect users to fix it, this is just a
> > worst-case aid for users.
>
> But if we make it wait at the very first operation that means we will
> not suck more decoded data from the network and wouldn't that make the
> sender wait for the network buffer to get sucked in by the receiver?
>

That would be true even if we wait just before applying the commit
record considering the transaction is small and the wait time is
large.

> Also, we already have a handling of parallel apply workers so if we do
> not have an issue of deadlock there or if we can handle those issues
> there we can do it here as well no?
>

Parallel apply workers won't wait for a long time. There is some
similarity and in both cases, deadlock will be detected but chances of
such implementation-related deadlocks will be higher if we start
waiting for a random amount of times. The other possibility is that we
can keep a cap on the max clock skew time above which we will give
ERROR even if the user has configured wait. This is because anyway the
system will be choked (walsender won't be able to send more data,
vacuum on publisher won't be able to remove dead rows) if we wait for
longer times. But even with that, I am not sure if waiting after
holding locks is a good idea or gives us the benefit that is worth the
risk of deadlocks.

-- 
With Regards,
Amit Kapila.






^ permalink  raw  reply  [nested|flat] 101+ messages in thread

* Re: Conflict Detection and Resolution
@ 2024-07-03 10:32  shveta malik <[email protected]>
  parent: Dilip Kumar <[email protected]>
  1 sibling, 1 reply; 101+ messages in thread

From: shveta malik @ 2024-07-03 10:32 UTC (permalink / raw)
  To: Dilip Kumar <[email protected]>; +Cc: Amit Kapila <[email protected]>; Tomas Vondra <[email protected]>; pgsql-hackers; Zhijie Hou (Fujitsu) <[email protected]>; Nisha Moond <[email protected]>; shveta malik <[email protected]>

On Wed, Jul 3, 2024 at 11:29 AM Dilip Kumar <[email protected]> wrote:
>
> On Wed, Jul 3, 2024 at 11:00 AM shveta malik <[email protected]> wrote:
> >
> > > Yes, I also think it should be independent of CDR.  IMHO, it should be
> > > based on the user-configured maximum clock skew tolerance and can be
> > > independent of CDR.
> >
> > +1
> >
> > > IIUC we would make the remote apply wait just
> > > before committing if the remote commit timestamp is ahead of the local
> > > clock by more than the maximum clock skew tolerance, is that correct?
> >
> > +1 on condition to wait.
> >
> > But I think we should make apply worker wait during begin
> > (apply_handle_begin) instead of commit. It makes more sense to delay
> > the entire operation to manage clock-skew rather than the commit
> > alone. And only then CDR's timestamp based resolution which are much
> > prior to commit-stage can benefit from this. Thoughts?
>
> But do we really need to wait at apply_handle_begin()? I mean if we
> already know the commit_ts then we can perform the conflict resolution
> no?

I would like to highlight one point here that the resultant data may
be different depending upon at what stage (begin or commit) we
conclude to wait. Example:

--max_clock_skew set to 0 i.e. no tolerance for clock skew.
--Remote Update with commit_timestamp = 10.20AM.
--Local clock (which is say 5 min behind) shows = 10.15AM.

Case 1: Wait during Begin:
When remote update arrives at local node, apply worker waits till
local clock hits 'remote's commit_tts - max_clock_skew' i.e. till
10.20 AM. In the meantime (during the wait period of apply worker) if
some local update on the same row has happened at say 10.18am (local
clock), that will be applied first. Now when apply worker's wait is
over, it will detect 'update_diffe'r conflict and as per
'last_update_win', remote_tuple will win as 10.20 is latest than
10.18.

Case 2: Wait during Commit:
When remote update arrives at local node, it finds no conflict and
goes for commit. But before commit, it waits till the local clock hits
10.20 AM. In the meantime (during wait period of apply worker)) if
some local update is trying to update the same row say at 10.18, it
has to wait (due to locks taken by remote update on that row) and
remote tuple will get committed first with commit timestamp of 10.20.
Then local update will proceed and will overwrite remote tuple.

So in case1, remote tuple is the final change while in case2, local
tuple is the final change.

thanks
Shveta






^ permalink  raw  reply  [nested|flat] 101+ messages in thread

* Re: Conflict Detection and Resolution
@ 2024-07-03 10:34  Dilip Kumar <[email protected]>
  parent: Amit Kapila <[email protected]>
  1 sibling, 1 reply; 101+ messages in thread

From: Dilip Kumar @ 2024-07-03 10:34 UTC (permalink / raw)
  To: Amit Kapila <[email protected]>; +Cc: shveta malik <[email protected]>; Tomas Vondra <[email protected]>; pgsql-hackers; Zhijie Hou (Fujitsu) <[email protected]>; Nisha Moond <[email protected]>

On Wed, Jul 3, 2024 at 3:35 PM Amit Kapila <[email protected]> wrote:
>
> On Wed, Jul 3, 2024 at 2:16 PM Dilip Kumar <[email protected]> wrote:
> >
> > On Wed, Jul 3, 2024 at 12:30 PM Amit Kapila <[email protected]> wrote:
> > >
> > > On Wed, Jul 3, 2024 at 11:29 AM Dilip Kumar <[email protected]> wrote:
> >
> > > But waiting after applying the operations and before applying the
> > > commit would mean that we need to wait with the locks held. That could
> > > be a recipe for deadlocks in the system. I see your point related to
> > > performance but as we are not expecting clock skew in normal cases, we
> > > shouldn't be too much bothered on the performance due to this. If
> > > there is clock skew, we expect users to fix it, this is just a
> > > worst-case aid for users.
> >
> > But if we make it wait at the very first operation that means we will
> > not suck more decoded data from the network and wouldn't that make the
> > sender wait for the network buffer to get sucked in by the receiver?
> >
>
> That would be true even if we wait just before applying the commit
> record considering the transaction is small and the wait time is
> large.

What I am saying is that if we are not applying the whole transaction,
it means we are not receiving it either unless we plan to spill it to
a file. If we don't spill it to a file, the network buffer will fill
up very quickly. This issue wouldn't occur if we waited right before
the commit because, by that time, we would have already received all
the data from the network.

-- 
Regards,
Dilip Kumar
EnterpriseDB: http://www.enterprisedb.com






^ permalink  raw  reply  [nested|flat] 101+ messages in thread

* Re: Conflict Detection and Resolution
@ 2024-07-03 10:39  shveta malik <[email protected]>
  parent: Amit Kapila <[email protected]>
  1 sibling, 0 replies; 101+ messages in thread

From: shveta malik @ 2024-07-03 10:39 UTC (permalink / raw)
  To: Amit Kapila <[email protected]>; +Cc: Dilip Kumar <[email protected]>; Tomas Vondra <[email protected]>; pgsql-hackers; Zhijie Hou (Fujitsu) <[email protected]>; Nisha Moond <[email protected]>; shveta malik <[email protected]>

On Wed, Jul 3, 2024 at 3:35 PM Amit Kapila <[email protected]> wrote:
>
> On Wed, Jul 3, 2024 at 2:16 PM Dilip Kumar <[email protected]> wrote:
> >
> > On Wed, Jul 3, 2024 at 12:30 PM Amit Kapila <[email protected]> wrote:
> > >
> > > On Wed, Jul 3, 2024 at 11:29 AM Dilip Kumar <[email protected]> wrote:
> >
> > > But waiting after applying the operations and before applying the
> > > commit would mean that we need to wait with the locks held. That could
> > > be a recipe for deadlocks in the system. I see your point related to
> > > performance but as we are not expecting clock skew in normal cases, we
> > > shouldn't be too much bothered on the performance due to this. If
> > > there is clock skew, we expect users to fix it, this is just a
> > > worst-case aid for users.
> >
> > But if we make it wait at the very first operation that means we will
> > not suck more decoded data from the network and wouldn't that make the
> > sender wait for the network buffer to get sucked in by the receiver?
> >
>
> That would be true even if we wait just before applying the commit
> record considering the transaction is small and the wait time is
> large.
>
> > Also, we already have a handling of parallel apply workers so if we do
> > not have an issue of deadlock there or if we can handle those issues
> > there we can do it here as well no?
> >
>
> Parallel apply workers won't wait for a long time. There is some
> similarity and in both cases, deadlock will be detected but chances of
> such implementation-related deadlocks will be higher if we start
> waiting for a random amount of times. The other possibility is that we
> can keep a cap on the max clock skew time above which we will give
> ERROR even if the user has configured wait.

+1. But I think cap has to be on wait-time. As an example, let's say
the user has configured 'clock skew tolerance' of 10sec while the
actual clock skew between nodes is 5 min. It means, we will mostly
have to  wait '5 min - 10sec' to bring the clock skew to a tolerable
limit, which is a huge waiting time. We can keep a max limit on this
wait time.

thanks
Shveta






^ permalink  raw  reply  [nested|flat] 101+ messages in thread

* Re: Conflict Detection and Resolution
@ 2024-07-03 10:42  Dilip Kumar <[email protected]>
  parent: shveta malik <[email protected]>
  0 siblings, 1 reply; 101+ messages in thread

From: Dilip Kumar @ 2024-07-03 10:42 UTC (permalink / raw)
  To: shveta malik <[email protected]>; +Cc: Amit Kapila <[email protected]>; Tomas Vondra <[email protected]>; pgsql-hackers; Zhijie Hou (Fujitsu) <[email protected]>; Nisha Moond <[email protected]>

On Wed, Jul 3, 2024 at 4:02 PM shveta malik <[email protected]> wrote:
>
> On Wed, Jul 3, 2024 at 11:29 AM Dilip Kumar <[email protected]> wrote:
> >
> > On Wed, Jul 3, 2024 at 11:00 AM shveta malik <[email protected]> wrote:
> > >
> > > > Yes, I also think it should be independent of CDR.  IMHO, it should be
> > > > based on the user-configured maximum clock skew tolerance and can be
> > > > independent of CDR.
> > >
> > > +1
> > >
> > > > IIUC we would make the remote apply wait just
> > > > before committing if the remote commit timestamp is ahead of the local
> > > > clock by more than the maximum clock skew tolerance, is that correct?
> > >
> > > +1 on condition to wait.
> > >
> > > But I think we should make apply worker wait during begin
> > > (apply_handle_begin) instead of commit. It makes more sense to delay
> > > the entire operation to manage clock-skew rather than the commit
> > > alone. And only then CDR's timestamp based resolution which are much
> > > prior to commit-stage can benefit from this. Thoughts?
> >
> > But do we really need to wait at apply_handle_begin()? I mean if we
> > already know the commit_ts then we can perform the conflict resolution
> > no?
>
> I would like to highlight one point here that the resultant data may
> be different depending upon at what stage (begin or commit) we
> conclude to wait. Example:
>
> --max_clock_skew set to 0 i.e. no tolerance for clock skew.
> --Remote Update with commit_timestamp = 10.20AM.
> --Local clock (which is say 5 min behind) shows = 10.15AM.
>
> Case 1: Wait during Begin:
> When remote update arrives at local node, apply worker waits till
> local clock hits 'remote's commit_tts - max_clock_skew' i.e. till
> 10.20 AM. In the meantime (during the wait period of apply worker) if
> some local update on the same row has happened at say 10.18am (local
> clock), that will be applied first. Now when apply worker's wait is
> over, it will detect 'update_diffe'r conflict and as per
> 'last_update_win', remote_tuple will win as 10.20 is latest than
> 10.18.
>
> Case 2: Wait during Commit:
> When remote update arrives at local node, it finds no conflict and
> goes for commit. But before commit, it waits till the local clock hits
> 10.20 AM. In the meantime (during wait period of apply worker)) if
> some local update is trying to update the same row say at 10.18, it
> has to wait (due to locks taken by remote update on that row) and
> remote tuple will get committed first with commit timestamp of 10.20.
> Then local update will proceed and will overwrite remote tuple.
>
> So in case1, remote tuple is the final change while in case2, local
> tuple is the final change.

Got it, but which case is correct, I think both.  Because in case-1
local commit's commit_ts is 10:18 and the remote commit's commit_ts is
10:20 so remote apply wins.  And case 2, the remote commit's commit_ts
is 10:20 whereas the local commit's commit_ts must be 10:20 + delta
(because it waited for the remote transaction to get committed).

Now say which is better, in case-1 we have to make the remote apply to
wait at the beginning state without knowing what would be the local
clock when it actually comes to commit, it may so happen that if we
choose case-2 by the time the remote transaction finish applying the
local clock is beyond 10:20 and we do not even need to wait?

-- 
Regards,
Dilip Kumar
EnterpriseDB: http://www.enterprisedb.com






^ permalink  raw  reply  [nested|flat] 101+ messages in thread

* Re: Conflict Detection and Resolution
@ 2024-07-03 11:17  Amit Kapila <[email protected]>
  parent: Dilip Kumar <[email protected]>
  0 siblings, 1 reply; 101+ messages in thread

From: Amit Kapila @ 2024-07-03 11:17 UTC (permalink / raw)
  To: Dilip Kumar <[email protected]>; +Cc: shveta malik <[email protected]>; Tomas Vondra <[email protected]>; pgsql-hackers; Zhijie Hou (Fujitsu) <[email protected]>; Nisha Moond <[email protected]>

On Wed, Jul 3, 2024 at 4:04 PM Dilip Kumar <[email protected]> wrote:
>
> On Wed, Jul 3, 2024 at 3:35 PM Amit Kapila <[email protected]> wrote:
> >
> > On Wed, Jul 3, 2024 at 2:16 PM Dilip Kumar <[email protected]> wrote:
> > >
> > > On Wed, Jul 3, 2024 at 12:30 PM Amit Kapila <[email protected]> wrote:
> > > >
> > > > On Wed, Jul 3, 2024 at 11:29 AM Dilip Kumar <[email protected]> wrote:
> > >
> > > > But waiting after applying the operations and before applying the
> > > > commit would mean that we need to wait with the locks held. That could
> > > > be a recipe for deadlocks in the system. I see your point related to
> > > > performance but as we are not expecting clock skew in normal cases, we
> > > > shouldn't be too much bothered on the performance due to this. If
> > > > there is clock skew, we expect users to fix it, this is just a
> > > > worst-case aid for users.
> > >
> > > But if we make it wait at the very first operation that means we will
> > > not suck more decoded data from the network and wouldn't that make the
> > > sender wait for the network buffer to get sucked in by the receiver?
> > >
> >
> > That would be true even if we wait just before applying the commit
> > record considering the transaction is small and the wait time is
> > large.
>
> What I am saying is that if we are not applying the whole transaction,
> it means we are not receiving it either unless we plan to spill it to
> a file. If we don't spill it to a file, the network buffer will fill
> up very quickly. This issue wouldn't occur if we waited right before
> the commit because, by that time, we would have already received all
> the data from the network.
>

We would have received the transaction data but there could be other
transactions that need to wait because the apply worker is waiting
before the commit. So, the situation will be the same. We can even
decide to spill the data to files if the decision is that we need to
wait to avoid network buffer-fill situations. But note that the wait
in apply worker has consequences that the subscriber won't be able to
confirm the flush position and publisher won't be able to vacuum the
dead rows and we won't be remove WAL as well. Last time when we
discussed the delay_apply feature, we decided not to proceed because
of such issues. This is the reason I proposed a cap on wait time.

-- 
With Regards,
Amit Kapila.






^ permalink  raw  reply  [nested|flat] 101+ messages in thread

* Re: Conflict Detection and Resolution
@ 2024-07-03 11:36  Dilip Kumar <[email protected]>
  parent: Amit Kapila <[email protected]>
  0 siblings, 1 reply; 101+ messages in thread

From: Dilip Kumar @ 2024-07-03 11:36 UTC (permalink / raw)
  To: Amit Kapila <[email protected]>; +Cc: shveta malik <[email protected]>; Tomas Vondra <[email protected]>; pgsql-hackers; Zhijie Hou (Fujitsu) <[email protected]>; Nisha Moond <[email protected]>

On Wed, Jul 3, 2024 at 4:48 PM Amit Kapila <[email protected]> wrote:
>
> On Wed, Jul 3, 2024 at 4:04 PM Dilip Kumar <[email protected]> wrote:
> >
> > On Wed, Jul 3, 2024 at 3:35 PM Amit Kapila <[email protected]> wrote:
> > >
> > > On Wed, Jul 3, 2024 at 2:16 PM Dilip Kumar <[email protected]> wrote:
> > > >
> > > > On Wed, Jul 3, 2024 at 12:30 PM Amit Kapila <[email protected]> wrote:
> > > > >
> > > > > On Wed, Jul 3, 2024 at 11:29 AM Dilip Kumar <[email protected]> wrote:
> > > >
> > > > > But waiting after applying the operations and before applying the
> > > > > commit would mean that we need to wait with the locks held. That could
> > > > > be a recipe for deadlocks in the system. I see your point related to
> > > > > performance but as we are not expecting clock skew in normal cases, we
> > > > > shouldn't be too much bothered on the performance due to this. If
> > > > > there is clock skew, we expect users to fix it, this is just a
> > > > > worst-case aid for users.
> > > >
> > > > But if we make it wait at the very first operation that means we will
> > > > not suck more decoded data from the network and wouldn't that make the
> > > > sender wait for the network buffer to get sucked in by the receiver?
> > > >
> > >
> > > That would be true even if we wait just before applying the commit
> > > record considering the transaction is small and the wait time is
> > > large.
> >
> > What I am saying is that if we are not applying the whole transaction,
> > it means we are not receiving it either unless we plan to spill it to
> > a file. If we don't spill it to a file, the network buffer will fill
> > up very quickly. This issue wouldn't occur if we waited right before
> > the commit because, by that time, we would have already received all
> > the data from the network.
> >
>
> We would have received the transaction data but there could be other
> transactions that need to wait because the apply worker is waiting
> before the commit.

Yeah, that's a valid point, can parallel apply worker help here?

 So, the situation will be the same. We can even
> decide to spill the data to files if the decision is that we need to
> wait to avoid network buffer-fill situations. But note that the wait
> in apply worker has consequences that the subscriber won't be able to
> confirm the flush position and publisher won't be able to vacuum the
> dead rows and we won't be remove WAL as well. Last time when we
> discussed the delay_apply feature, we decided not to proceed because
> of such issues. This is the reason I proposed a cap on wait time.

Yes, spilling to file or cap on the wait time should help, and as I
said above maybe a parallel apply worker can also help.

So I agree that the problem with network buffers arises in both cases,
whether we wait before committing or before beginning. So keeping that
in mind I don't have any strong objections against waiting at the
beginning if it simplifies the design compared to waiting at the
commit.

However, one point to remember in favor of waiting before applying the
commit is that if we decide to wait before beginning the transaction,
we would end up waiting in many more cases compared to waiting before
committing. Because in cases, when transactions are large and the
clock skew is small, the local clock would have already passed the
remote commit_ts by the time we reach the commit.

--
Regards,
Dilip Kumar
EnterpriseDB: http://www.enterprisedb.com






^ permalink  raw  reply  [nested|flat] 101+ messages in thread

* Re: Conflict Detection and Resolution
@ 2024-07-03 11:38  shveta malik <[email protected]>
  parent: Dilip Kumar <[email protected]>
  0 siblings, 1 reply; 101+ messages in thread

From: shveta malik @ 2024-07-03 11:38 UTC (permalink / raw)
  To: Dilip Kumar <[email protected]>; +Cc: Amit Kapila <[email protected]>; Tomas Vondra <[email protected]>; pgsql-hackers; Zhijie Hou (Fujitsu) <[email protected]>; Nisha Moond <[email protected]>; shveta malik <[email protected]>

On Wed, Jul 3, 2024 at 4:12 PM Dilip Kumar <[email protected]> wrote:
>
> On Wed, Jul 3, 2024 at 4:02 PM shveta malik <[email protected]> wrote:
> >
> > On Wed, Jul 3, 2024 at 11:29 AM Dilip Kumar <[email protected]> wrote:
> > >
> > > On Wed, Jul 3, 2024 at 11:00 AM shveta malik <[email protected]> wrote:
> > > >
> > > > > Yes, I also think it should be independent of CDR.  IMHO, it should be
> > > > > based on the user-configured maximum clock skew tolerance and can be
> > > > > independent of CDR.
> > > >
> > > > +1
> > > >
> > > > > IIUC we would make the remote apply wait just
> > > > > before committing if the remote commit timestamp is ahead of the local
> > > > > clock by more than the maximum clock skew tolerance, is that correct?
> > > >
> > > > +1 on condition to wait.
> > > >
> > > > But I think we should make apply worker wait during begin
> > > > (apply_handle_begin) instead of commit. It makes more sense to delay
> > > > the entire operation to manage clock-skew rather than the commit
> > > > alone. And only then CDR's timestamp based resolution which are much
> > > > prior to commit-stage can benefit from this. Thoughts?
> > >
> > > But do we really need to wait at apply_handle_begin()? I mean if we
> > > already know the commit_ts then we can perform the conflict resolution
> > > no?
> >
> > I would like to highlight one point here that the resultant data may
> > be different depending upon at what stage (begin or commit) we
> > conclude to wait. Example:
> >
> > --max_clock_skew set to 0 i.e. no tolerance for clock skew.
> > --Remote Update with commit_timestamp = 10.20AM.
> > --Local clock (which is say 5 min behind) shows = 10.15AM.
> >
> > Case 1: Wait during Begin:
> > When remote update arrives at local node, apply worker waits till
> > local clock hits 'remote's commit_tts - max_clock_skew' i.e. till
> > 10.20 AM. In the meantime (during the wait period of apply worker) if
> > some local update on the same row has happened at say 10.18am (local
> > clock), that will be applied first. Now when apply worker's wait is
> > over, it will detect 'update_diffe'r conflict and as per
> > 'last_update_win', remote_tuple will win as 10.20 is latest than
> > 10.18.
> >
> > Case 2: Wait during Commit:
> > When remote update arrives at local node, it finds no conflict and
> > goes for commit. But before commit, it waits till the local clock hits
> > 10.20 AM. In the meantime (during wait period of apply worker)) if
> > some local update is trying to update the same row say at 10.18, it
> > has to wait (due to locks taken by remote update on that row) and
> > remote tuple will get committed first with commit timestamp of 10.20.
> > Then local update will proceed and will overwrite remote tuple.
> >
> > So in case1, remote tuple is the final change while in case2, local
> > tuple is the final change.
>
> Got it, but which case is correct, I think both.  Because in case-1
> local commit's commit_ts is 10:18 and the remote commit's commit_ts is
> 10:20 so remote apply wins.  And case 2, the remote commit's commit_ts
> is 10:20 whereas the local commit's commit_ts must be 10:20 + delta
> (because it waited for the remote transaction to get committed).
>
> Now say which is better, in case-1 we have to make the remote apply to
> wait at the beginning state without knowing what would be the local
> clock when it actually comes to commit, it may so happen that if we
> choose case-2 by the time the remote transaction finish applying the
> local clock is beyond 10:20 and we do not even need to wait?

yes, agree that wait time could be lesser to some extent in case 2.
But the wait during commit will make user operations on the same row
wait, without user having any clue on concurrent blocking operations.
I am not sure if it will be acceptable.

thanks
Shveta






^ permalink  raw  reply  [nested|flat] 101+ messages in thread

* Re: Conflict Detection and Resolution
@ 2024-07-03 11:52  Dilip Kumar <[email protected]>
  parent: shveta malik <[email protected]>
  0 siblings, 0 replies; 101+ messages in thread

From: Dilip Kumar @ 2024-07-03 11:52 UTC (permalink / raw)
  To: shveta malik <[email protected]>; +Cc: Amit Kapila <[email protected]>; Tomas Vondra <[email protected]>; pgsql-hackers; Zhijie Hou (Fujitsu) <[email protected]>; Nisha Moond <[email protected]>

On Wed, Jul 3, 2024 at 5:08 PM shveta malik <[email protected]> wrote:
>
> On Wed, Jul 3, 2024 at 4:12 PM Dilip Kumar <[email protected]> wrote:
> >
> > On Wed, Jul 3, 2024 at 4:02 PM shveta malik <[email protected]> wrote:
> > >
> > > On Wed, Jul 3, 2024 at 11:29 AM Dilip Kumar <[email protected]> wrote:
> > > >
> > > > On Wed, Jul 3, 2024 at 11:00 AM shveta malik <[email protected]> wrote:
> > > > >
> > > > > > Yes, I also think it should be independent of CDR.  IMHO, it should be
> > > > > > based on the user-configured maximum clock skew tolerance and can be
> > > > > > independent of CDR.
> > > > >
> > > > > +1
> > > > >
> > > > > > IIUC we would make the remote apply wait just
> > > > > > before committing if the remote commit timestamp is ahead of the local
> > > > > > clock by more than the maximum clock skew tolerance, is that correct?
> > > > >
> > > > > +1 on condition to wait.
> > > > >
> > > > > But I think we should make apply worker wait during begin
> > > > > (apply_handle_begin) instead of commit. It makes more sense to delay
> > > > > the entire operation to manage clock-skew rather than the commit
> > > > > alone. And only then CDR's timestamp based resolution which are much
> > > > > prior to commit-stage can benefit from this. Thoughts?
> > > >
> > > > But do we really need to wait at apply_handle_begin()? I mean if we
> > > > already know the commit_ts then we can perform the conflict resolution
> > > > no?
> > >
> > > I would like to highlight one point here that the resultant data may
> > > be different depending upon at what stage (begin or commit) we
> > > conclude to wait. Example:
> > >
> > > --max_clock_skew set to 0 i.e. no tolerance for clock skew.
> > > --Remote Update with commit_timestamp = 10.20AM.
> > > --Local clock (which is say 5 min behind) shows = 10.15AM.
> > >
> > > Case 1: Wait during Begin:
> > > When remote update arrives at local node, apply worker waits till
> > > local clock hits 'remote's commit_tts - max_clock_skew' i.e. till
> > > 10.20 AM. In the meantime (during the wait period of apply worker) if
> > > some local update on the same row has happened at say 10.18am (local
> > > clock), that will be applied first. Now when apply worker's wait is
> > > over, it will detect 'update_diffe'r conflict and as per
> > > 'last_update_win', remote_tuple will win as 10.20 is latest than
> > > 10.18.
> > >
> > > Case 2: Wait during Commit:
> > > When remote update arrives at local node, it finds no conflict and
> > > goes for commit. But before commit, it waits till the local clock hits
> > > 10.20 AM. In the meantime (during wait period of apply worker)) if
> > > some local update is trying to update the same row say at 10.18, it
> > > has to wait (due to locks taken by remote update on that row) and
> > > remote tuple will get committed first with commit timestamp of 10.20.
> > > Then local update will proceed and will overwrite remote tuple.
> > >
> > > So in case1, remote tuple is the final change while in case2, local
> > > tuple is the final change.
> >
> > Got it, but which case is correct, I think both.  Because in case-1
> > local commit's commit_ts is 10:18 and the remote commit's commit_ts is
> > 10:20 so remote apply wins.  And case 2, the remote commit's commit_ts
> > is 10:20 whereas the local commit's commit_ts must be 10:20 + delta
> > (because it waited for the remote transaction to get committed).
> >
> > Now say which is better, in case-1 we have to make the remote apply to
> > wait at the beginning state without knowing what would be the local
> > clock when it actually comes to commit, it may so happen that if we
> > choose case-2 by the time the remote transaction finish applying the
> > local clock is beyond 10:20 and we do not even need to wait?
>
> yes, agree that wait time could be lesser to some extent in case 2.
> But the wait during commit will make user operations on the same row
> wait, without user having any clue on concurrent blocking operations.
> I am not sure if it will be acceptable.

I don't think there is any problem with the acceptance of user
experience because even while applying the remote transaction
(irrespective of whether we implement this wait feature) the user
transaction might have to wait if updating the common rows right?

-- 
Regards,
Dilip Kumar
EnterpriseDB: http://www.enterprisedb.com






^ permalink  raw  reply  [nested|flat] 101+ messages in thread

* Re: Conflict Detection and Resolution
@ 2024-07-04 04:01  shveta malik <[email protected]>
  parent: Amit Kapila <[email protected]>
  1 sibling, 0 replies; 101+ messages in thread

From: shveta malik @ 2024-07-04 04:01 UTC (permalink / raw)
  To: Amit Kapila <[email protected]>; +Cc: Dilip Kumar <[email protected]>; Tomas Vondra <[email protected]>; pgsql-hackers; Zhijie Hou (Fujitsu) <[email protected]>; Nisha Moond <[email protected]>; shveta malik <[email protected]>

On Wed, Jul 3, 2024 at 12:30 PM Amit Kapila <[email protected]> wrote:
>
> On Wed, Jul 3, 2024 at 11:29 AM Dilip Kumar <[email protected]> wrote:
> >
> > On Wed, Jul 3, 2024 at 11:00 AM shveta malik <[email protected]> wrote:
> > >
> > > > Yes, I also think it should be independent of CDR.  IMHO, it should be
> > > > based on the user-configured maximum clock skew tolerance and can be
> > > > independent of CDR.
> > >
> > > +1
> > >
> > > > IIUC we would make the remote apply wait just
> > > > before committing if the remote commit timestamp is ahead of the local
> > > > clock by more than the maximum clock skew tolerance, is that correct?
> > >
> > > +1 on condition to wait.
> > >
> > > But I think we should make apply worker wait during begin
> > > (apply_handle_begin) instead of commit. It makes more sense to delay
> > > the entire operation to manage clock-skew rather than the commit
> > > alone. And only then CDR's timestamp based resolution which are much
> > > prior to commit-stage can benefit from this. Thoughts?
> >
> > But do we really need to wait at apply_handle_begin()? I mean if we
> > already know the commit_ts then we can perform the conflict resolution
> > no?  I mean we should wait before committing because we are
> > considering this remote transaction to be in the future and we do not
> > want to confirm the commit of this transaction to the remote node
> > before the local clock reaches the record commit_ts to preserve the
> > causal order.  However, we can still perform conflict resolution
> > beforehand since we already know the commit_ts. The conflict
> > resolution function will be something like "out_version =
> > CRF(version1_commit_ts, version2_commit_ts)," so the result should be
> > the same regardless of when we apply it, correct?  From a performance
> > standpoint, wouldn't it be beneficial to perform as much work as
> > possible in advance? By the time we apply all the operations, the
> > local clock might already be in sync with the commit_ts of the remote
> > transaction.  Am I missing something?
> >
>
> But waiting after applying the operations and before applying the
> commit would mean that we need to wait with the locks held. That could
> be a recipe for deadlocks in the system. I see your point related to
> performance but as we are not expecting clock skew in normal cases, we
> shouldn't be too much bothered on the performance due to this. If
> there is clock skew, we expect users to fix it, this is just a
> worst-case aid for users.
>

Please find the new patch set.  patch004 is the new patch which
attempts to implement:

1) Either wait or error out on clock skew as configured. Please note
that currently wait is implemented during 'begin'. Once the ongoing
discussion is concluded, it can be changed as needed.
2) last_update_wins resolver. Thanks Nisha for providing the resolver
related changes.

Next to be done:
1) parallel apply worker related changes as mentioned in [1]
2) cap on wait time due to clock skew
3) resolvers for delete_differ as conflict detection thread [2] has
implemented detection for that.

[1]: https://www.postgresql.org/message-id/CAFiTN-sf23K%3DsRsnxw-BKNJqg5P6JXcqXBBkx%3DEULX8QGSQYaw%40mail...
[2]: https://www.postgresql.org/message-id/OS0PR01MB571686E464A325F26CEFCCEF94DD2%40OS0PR01MB5716.jpnprd0...

thanks
Shveta


Attachments:

  [application/octet-stream] v3-0005-Configure-table-level-conflict-resolvers.patch (48.8K, ../../CAJpy0uCv8R1Y5herLLANhGGqCotAFzBw3ikzhpXZvbqLDuoMTw@mail.gmail.com/2-v3-0005-Configure-table-level-conflict-resolvers.patch)
  download | inline diff:
From a2ac74aea89fec60049f6bd5eb4f18515ac7637f Mon Sep 17 00:00:00 2001
From: Shveta Malik <[email protected]>
Date: Wed, 3 Jul 2024 14:53:39 +0530
Subject: [PATCH v3 5/5] Configure table level conflict resolvers

This patch provides support for configuring table level conflict
resolvers using ALTER TABLE cmd.

Syntax to SET resolvers:
ALTER TABLE <name> SET CONFLICT RESOLVER <resolver1> on <conflict_type1>,
                   SET CONFLICT RESOLVER <resolver2> on <conflict_type2>, ...;

A new catalog table pg_conflict_rel has been created to store
table-level conflict_type and conflict_resolver configurations given by
above DDL command.

Syntax to RESET resolvers:
ALTER TABLE <name> RESET CONFLICT RESOLVER on <conflict_type1>,
                   RESET CONFLICT RESOLVER on <conflict_type2>, ...;

Above RESET command will remove entry for that particular conflict_type for
the given table from pg_conflict_rel catalog table.
---
 src/backend/catalog/dependency.c              |   6 +
 src/backend/catalog/objectaddress.c           |  30 ++
 src/backend/commands/tablecmds.c              |  70 ++++
 src/backend/parser/gram.y                     |  30 ++
 src/backend/replication/logical/conflict.c    | 330 +++++++++++++++++-
 src/include/catalog/Makefile                  |   4 +-
 src/include/catalog/meson.build               |   1 +
 src/include/catalog/pg_conflict.h             |   2 +-
 src/include/catalog/pg_conflict_rel.h         |  58 +++
 src/include/nodes/parsenodes.h                |   2 +
 src/include/replication/conflict.h            |  13 +
 .../regress/expected/conflict_resolver.out    | 245 ++++++++++++-
 src/test/regress/expected/oidjoins.out        |   1 +
 src/test/regress/sql/conflict_resolver.sql    | 161 ++++++++-
 14 files changed, 929 insertions(+), 24 deletions(-)
 create mode 100644 src/include/catalog/pg_conflict_rel.h

diff --git a/src/backend/catalog/dependency.c b/src/backend/catalog/dependency.c
index 0489cbabcb..9dd78d9094 100644
--- a/src/backend/catalog/dependency.c
+++ b/src/backend/catalog/dependency.c
@@ -31,6 +31,7 @@
 #include "catalog/pg_auth_members.h"
 #include "catalog/pg_cast.h"
 #include "catalog/pg_collation.h"
+#include "catalog/pg_conflict_rel.h"
 #include "catalog/pg_constraint.h"
 #include "catalog/pg_conversion.h"
 #include "catalog/pg_database.h"
@@ -79,6 +80,7 @@
 #include "miscadmin.h"
 #include "nodes/nodeFuncs.h"
 #include "parser/parsetree.h"
+#include "replication/conflict.h"
 #include "rewrite/rewriteRemove.h"
 #include "storage/lmgr.h"
 #include "utils/fmgroids.h"
@@ -1444,6 +1446,10 @@ doDeletion(const ObjectAddress *object, int flags)
 			RemovePublicationById(object->objectId);
 			break;
 
+		case ConflictRelRelationId:
+			RemoveTableConflictById(object->objectId);
+			break;
+
 		case CastRelationId:
 		case CollationRelationId:
 		case ConversionRelationId:
diff --git a/src/backend/catalog/objectaddress.c b/src/backend/catalog/objectaddress.c
index 7b536ac6fd..bd0d48ec78 100644
--- a/src/backend/catalog/objectaddress.c
+++ b/src/backend/catalog/objectaddress.c
@@ -30,6 +30,7 @@
 #include "catalog/pg_cast.h"
 #include "catalog/pg_collation.h"
 #include "catalog/pg_constraint.h"
+#include "catalog/pg_conflict_rel.h"
 #include "catalog/pg_conversion.h"
 #include "catalog/pg_database.h"
 #include "catalog/pg_default_acl.h"
@@ -3005,6 +3006,35 @@ getObjectDescription(const ObjectAddress *object, bool missing_ok)
 				break;
 			}
 
+		case ConflictRelRelationId:
+			{
+				HeapTuple	confTup;
+				Datum		typeDatum;
+				Datum		resDatum;
+				char	   *contype;
+				char	   *conres;
+
+				confTup = SearchSysCache1(CONFLICTRELOID,
+										  ObjectIdGetDatum(object->objectId));
+				if (!HeapTupleIsValid(confTup))
+				{
+					if (!missing_ok)
+						elog(ERROR, "cache lookup failed for table conflict %u",
+							 object->objectId);
+					break;
+				}
+
+				typeDatum = SysCacheGetAttrNotNull(CONFLICTRELOID, confTup,
+												   Anum_pg_conflict_rel_confrtype);
+				resDatum = SysCacheGetAttrNotNull(CONFLICTRELOID, confTup,
+												  Anum_pg_conflict_rel_confrres);
+				contype = TextDatumGetCString(typeDatum);
+				conres = TextDatumGetCString(resDatum);
+				ReleaseSysCache(confTup);
+				appendStringInfo(&buffer, _("conflict_resolver %s on conflict_type %s"),
+								 conres, contype);
+				break;
+			}
 		case ConstraintRelationId:
 			{
 				HeapTuple	conTup;
diff --git a/src/backend/commands/tablecmds.c b/src/backend/commands/tablecmds.c
index dbfe0d6b1c..2d75297340 100644
--- a/src/backend/commands/tablecmds.c
+++ b/src/backend/commands/tablecmds.c
@@ -83,6 +83,7 @@
 #include "partitioning/partbounds.h"
 #include "partitioning/partdesc.h"
 #include "pgstat.h"
+#include "replication/conflict.h"
 #include "rewrite/rewriteDefine.h"
 #include "rewrite/rewriteHandler.h"
 #include "rewrite/rewriteManip.h"
@@ -662,6 +663,11 @@ static void ATExecSplitPartition(List **wqueue, AlteredTableInfo *tab,
 								 AlterTableUtilityContext *context);
 static void ATExecMergePartitions(List **wqueue, AlteredTableInfo *tab, Relation rel,
 								  PartitionCmd *cmd, AlterTableUtilityContext *context);
+static void ATExecSetConflictResolver(Relation rel, ConflictResolverStmt *stmt,
+									  bool recurse, bool recursing, LOCKMODE lockmode);
+static void
+			ATExecResetConflictResolver(Relation rel, ConflictResolverStmt *stmt,
+										bool recurse, bool recursing, LOCKMODE lockmode);
 
 /* ----------------------------------------------------------------
  *		DefineRelation
@@ -1245,6 +1251,9 @@ DefineRelation(CreateStmt *stmt, char relkind, Oid ownerId,
 		 */
 		CloneForeignKeyConstraints(NULL, parent, rel);
 
+		/* Inherit conflict resolvers configuration from parent. */
+		InheritTableConflictResolvers(rel, parent);
+
 		table_close(parent, NoLock);
 	}
 
@@ -4543,6 +4552,8 @@ AlterTableGetLockLevel(List *cmds)
 			case AT_SetExpression:
 			case AT_DropExpression:
 			case AT_SetCompression:
+			case AT_SetConflictResolver:
+			case AT_ResetConflictResolver:
 				cmd_lockmode = AccessExclusiveLock;
 				break;
 
@@ -5116,6 +5127,15 @@ ATPrepCmd(List **wqueue, Relation rel, AlterTableCmd *cmd,
 			/* No command-specific prep needed */
 			pass = AT_PASS_MISC;
 			break;
+		case AT_ResetConflictResolver:	/* RESET CONFLICT RESOLVER */
+		case AT_SetConflictResolver:	/* SET CONFLICT RESOLVER */
+			ATSimplePermissions(cmd->subtype, rel, ATT_TABLE);
+			/* Recursion occurs during execution phase */
+			/* No command-specific prep needed except saving recurse flag */
+			if (recurse)
+				cmd->recurse = true;
+			pass = AT_PASS_MISC;
+			break;
 		default:				/* oops */
 			elog(ERROR, "unrecognized alter table type: %d",
 				 (int) cmd->subtype);
@@ -5528,6 +5548,14 @@ ATExecCmd(List **wqueue, AlteredTableInfo *tab,
 			ATExecMergePartitions(wqueue, tab, rel, (PartitionCmd *) cmd->def,
 								  context);
 			break;
+		case AT_SetConflictResolver:
+			ATExecSetConflictResolver(rel, (ConflictResolverStmt *) cmd->def,
+									  cmd->recurse, false, lockmode);
+			break;
+		case AT_ResetConflictResolver:
+			ATExecResetConflictResolver(rel, (ConflictResolverStmt *) cmd->def,
+										cmd->recurse, false, lockmode);
+			break;
 		default:				/* oops */
 			elog(ERROR, "unrecognized alter table type: %d",
 				 (int) cmd->subtype);
@@ -6528,6 +6556,10 @@ alter_table_type_to_string(AlterTableType cmdtype)
 			return "ALTER COLUMN ... DROP IDENTITY";
 		case AT_ReAddStatistics:
 			return NULL;		/* not real grammar */
+		case AT_SetConflictResolver:
+			return "SET CONFLICT RESOLVER";
+		case AT_ResetConflictResolver:
+			return "RESET CONFLICT RESOLVER";
 	}
 
 	return NULL;
@@ -15650,6 +15682,13 @@ CreateInheritance(Relation child_rel, Relation parent_rel, bool ispartition)
 	/* Match up the constraints and bump coninhcount as needed */
 	MergeConstraintsIntoExisting(child_rel, parent_rel);
 
+	/*
+	 * Inherit resolvers configuration from parent if not explicitly set for
+	 * child partition.
+	 */
+	if (ispartition)
+		InheritTableConflictResolvers(child_rel, parent_rel);
+
 	/*
 	 * OK, it looks valid.  Make the catalog entries that show inheritance.
 	 */
@@ -16238,6 +16277,10 @@ RemoveInheritance(Relation child_rel, Relation parent_rel, bool expect_detached)
 	systable_endscan(scan);
 	table_close(catalogRelation, RowExclusiveLock);
 
+	/* Find inherited conflict resolvers and disinherit them */
+	if (is_partitioning)
+		ResetResolversInheritance(child_rel);
+
 	drop_parent_dependency(RelationGetRelid(child_rel),
 						   RelationRelationId,
 						   RelationGetRelid(parent_rel),
@@ -20766,3 +20809,30 @@ ATExecMergePartitions(List **wqueue, AlteredTableInfo *tab, Relation rel,
 	/* Keep the lock until commit. */
 	table_close(newPartRel, NoLock);
 }
+
+/*
+ * ALTER TABLE <name> SET CONFLICT RESOLVER ...
+ */
+static void
+ATExecSetConflictResolver(Relation rel, ConflictResolverStmt *stmt,
+						  bool recurse, bool recursing, LOCKMODE lockmode)
+{
+	ValidateConflictTypeAndResolver(stmt->conflict_type, stmt->conflict_resolver, false);
+
+	SetTableConflictResolver(NULL, rel, stmt->conflict_type,
+							 stmt->conflict_resolver,
+							 recurse, recursing, lockmode);
+}
+
+/*
+ * ALTER TABLE <name> RESET CONFLICT RESOLVER ...
+ */
+static void
+ATExecResetConflictResolver(Relation rel, ConflictResolverStmt *stmt,
+							bool recurse, bool recursing, LOCKMODE lockmode)
+{
+	ValidateConflictTypeAndResolver(stmt->conflict_type, stmt->conflict_resolver, true);
+
+	ResetTableConflictResolver(rel, stmt->conflict_type,
+							   recurse, recursing, lockmode);
+}
diff --git a/src/backend/parser/gram.y b/src/backend/parser/gram.y
index 42726fe3a6..628b9d10e2 100644
--- a/src/backend/parser/gram.y
+++ b/src/backend/parser/gram.y
@@ -3015,6 +3015,36 @@ alter_table_cmd:
 
 					n->subtype = AT_GenericOptions;
 					n->def = (Node *) $1;
+					$$ = (Node *) n;
+				}
+			/*
+			 * ALTER TABLE <name> SET CONFLICT RESOLVER <conflict_resolver>
+			 *		on <conflict_type>
+			 */
+			| SET CONFLICT RESOLVER conflict_resolver ON conflict_type
+				{
+					AlterTableCmd *n = makeNode(AlterTableCmd);
+					ConflictResolverStmt *c = makeNode(ConflictResolverStmt);
+
+					c->conflict_resolver = $4;
+					c->conflict_type = $6;
+
+					n->subtype = AT_SetConflictResolver;
+					n->def = (Node *) c;
+
+					$$ = (Node *) n;
+				}
+			/* ALTER TABLE <name> RESET CONFLICT RESOLVER on <conflict_type> */
+			| RESET CONFLICT RESOLVER ON conflict_type
+				{
+					AlterTableCmd *n = makeNode(AlterTableCmd);
+					ConflictResolverStmt *c = makeNode(ConflictResolverStmt);
+
+					c->conflict_type = $5;
+
+					n->subtype = AT_ResetConflictResolver;
+					n->def = (Node *) c;
+
 					$$ = (Node *) n;
 				}
 		;
diff --git a/src/backend/replication/logical/conflict.c b/src/backend/replication/logical/conflict.c
index cbd3a65a27..2384bc53f9 100644
--- a/src/backend/replication/logical/conflict.c
+++ b/src/backend/replication/logical/conflict.c
@@ -19,8 +19,11 @@
 #include "access/htup_details.h"
 #include "access/skey.h"
 #include "access/table.h"
+#include "catalog/dependency.h"
 #include "catalog/indexing.h"
 #include "catalog/pg_conflict.h"
+#include "catalog/pg_conflict_rel.h"
+#include "catalog/pg_inherits.h"
 #include "executor/executor.h"
 #include "replication/conflict.h"
 #include "replication/logicalproto.h"
@@ -28,8 +31,10 @@
 #include "replication/origin.h"
 #include "utils/builtins.h"
 #include "utils/fmgroids.h"
+#include "utils/inval.h"
 #include "utils/lsyscache.h"
 #include "utils/rel.h"
+#include "utils/syscache.h"
 #include "utils/timestamp.h"
 #include "utils/syscache.h"
 
@@ -279,9 +284,9 @@ build_index_value_desc(Oid indexoid, TupleTableSlot *conflictslot)
  *
  * Return ConflictType enum value corresponding to given conflict_type.
  */
-static ConflictType
-validate_conflict_type_and_resolver(char *conflict_type, char *conflict_resolver,
-									bool isReset)
+ConflictType
+ValidateConflictTypeAndResolver(char *conflict_type, char *conflict_resolver,
+								bool isReset)
 {
 	ConflictType type;
 	ConflictResolver resolver;
@@ -484,10 +489,9 @@ ExecConflictResolverStmt(ConflictResolverStmt *stmt)
 	HeapTuple	newtup = NULL;
 	ConflictType type;
 
-	type = validate_conflict_type_and_resolver(stmt->conflict_type,
-											   stmt->conflict_resolver,
-											   stmt->isReset);
-
+	type = ValidateConflictTypeAndResolver(stmt->conflict_type,
+										   stmt->conflict_resolver,
+										   stmt->isReset);
 
 	/* Prepare to update a tuple in pg_conflict system catalog */
 	memset(values, 0, sizeof(values));
@@ -515,7 +519,7 @@ ExecConflictResolverStmt(ConflictResolverStmt *stmt)
 				BTEqualStrategyNumber, F_TEXTEQ,
 				values[Anum_pg_conflict_conftype - 1]);
 
-	pg_conflict = table_open(ConflictResRelationId, RowExclusiveLock);
+	pg_conflict = table_open(ConflictRelationId, RowExclusiveLock);
 
 	scan = systable_beginscan(pg_conflict, ConflictTypeIndexId, true,
 							  NULL, 1, keys);
@@ -604,3 +608,313 @@ GetConflictResolver(TupleTableSlot *localslot, Relation localrel,
 
 	return resolver;
 }
+
+/*
+ * Update the table level conflict resolver for a conflict_type in
+ * pg_conflict_rel system catalog.
+ */
+void
+SetTableConflictResolver(Relation pg_conf_rel, Relation rel, char *conflict_type, char *conflict_resolver,
+						 bool recurse, bool recursing, LOCKMODE lockmode)
+{
+	Relation	pg_conflict_rel;
+	Datum		values[Natts_pg_conflict_rel];
+	bool		nulls[Natts_pg_conflict_rel];
+	bool		replaces[Natts_pg_conflict_rel];
+	HeapTuple	oldtup;
+	HeapTuple	newtup = NULL;
+	Oid			relid = rel->rd_id;
+
+	/* Prepare to update a tuple. */
+	memset(nulls, false, sizeof(nulls));
+	memset(replaces, false, sizeof(replaces));
+
+	if (!pg_conf_rel)
+		pg_conflict_rel = table_open(ConflictRelRelationId, RowExclusiveLock);
+	else
+		pg_conflict_rel = pg_conf_rel;
+
+	values[Anum_pg_conflict_rel_confrrelid - 1] = ObjectIdGetDatum(relid);
+	values[Anum_pg_conflict_rel_confrtype - 1] = CStringGetTextDatum(conflict_type);
+	values[Anum_pg_conflict_rel_confrres - 1] = CStringGetTextDatum(conflict_resolver);
+	values[Anum_pg_conflict_rel_confrinherited - 1] = BoolGetDatum(recursing);
+
+	oldtup = SearchSysCache2(CONFLICTRELTYPE,
+							 values[Anum_pg_conflict_rel_confrrelid - 1],
+							 values[Anum_pg_conflict_rel_confrtype - 1]);
+	if (HeapTupleIsValid(oldtup))
+	{
+		Form_pg_conflict_rel confForm = (Form_pg_conflict_rel) GETSTRUCT(oldtup);
+
+		/*
+		 * Update resolver for recursing=false cases.
+		 *
+		 * recursing=true indicates it is a child parittion table and if it
+		 * already has a resolver set then overwrite it only if it is an
+		 * inherited resolver. We should not overwrite non-inherited resolvers
+		 * for child partition tables during recursion.
+		 */
+		if (!recursing || (recursing && confForm->confrinherited))
+		{
+			replaces[Anum_pg_conflict_rel_confrres - 1] = true;
+			replaces[Anum_pg_conflict_rel_confrinherited - 1] = !recursing;
+
+			newtup = heap_modify_tuple(oldtup, RelationGetDescr(pg_conflict_rel),
+									   values, nulls, replaces);
+			CatalogTupleUpdate(pg_conflict_rel, &oldtup->t_self, newtup);
+		}
+		else
+		{
+			/*
+			 * If we did not update resolver for this child table, do not
+			 * update for child's child tables as well.
+			 */
+			recurse = false;
+		}
+
+		ReleaseSysCache(oldtup);
+	}
+	/* If we didn't find an old tuple, insert a new one */
+	else
+	{
+		ObjectAddress myself,
+					referenced;
+		Oid			conflict_oid;
+
+		conflict_oid = GetNewOidWithIndex(pg_conflict_rel, ConflictRelOidIndexId,
+										  Anum_pg_conflict_rel_oid);
+		values[Anum_pg_conflict_rel_oid - 1] = ObjectIdGetDatum(conflict_oid);
+
+		newtup = heap_form_tuple(RelationGetDescr(pg_conflict_rel),
+								 values, nulls);
+		CatalogTupleInsert(pg_conflict_rel, newtup);
+
+		/* Add dependency on the relation */
+		ObjectAddressSet(myself, ConflictRelRelationId, conflict_oid);
+		ObjectAddressSet(referenced, RelationRelationId, relid);
+		recordDependencyOn(&myself, &referenced, DEPENDENCY_AUTO);
+	}
+
+	if (HeapTupleIsValid(newtup))
+		heap_freetuple(newtup);
+
+	if (!pg_conf_rel)
+		table_close(pg_conflict_rel, RowExclusiveLock);
+
+	if (recurse && (rel->rd_rel->relkind == RELKIND_PARTITIONED_TABLE))
+	{
+		List	   *children;
+		ListCell   *lc;
+
+		children =
+			find_inheritance_children(RelationGetRelid(rel), lockmode);
+
+		foreach(lc, children)
+		{
+			Relation	childrel;
+
+			/* find_inheritance_children already got lock */
+			childrel = table_open(lfirst_oid(lc), NoLock);
+			SetTableConflictResolver(NULL, childrel, conflict_type, conflict_resolver, recurse, true, lockmode);
+			table_close(childrel, NoLock);
+		}
+	}
+}
+
+/*
+ * Reset table level conflict_type configuration.
+ *
+ * Removes table's resolver configuration for given conflict_type from
+ * pg_conflict_rel system catalog.
+ */
+void
+ResetTableConflictResolver(Relation rel, char *conflict_type,
+						   bool recurse, bool recursing, LOCKMODE lockmode)
+{
+	Oid			relid = rel->rd_id;
+	HeapTuple	tup;
+	ObjectAddress confobj;
+	Form_pg_conflict_rel confForm;
+
+	tup = SearchSysCache2(CONFLICTRELTYPE,
+						  ObjectIdGetDatum(relid),
+						  CStringGetTextDatum(conflict_type));
+
+	/* Nothing to reset */
+	if (!HeapTupleIsValid(tup))
+		return;
+
+	confForm = (Form_pg_conflict_rel) GETSTRUCT(tup);
+
+	if (confForm->confrinherited && !recursing)
+		ereport(ERROR,
+				(errcode(ERRCODE_INVALID_TABLE_DEFINITION),
+				 errmsg("cannot reset inherited resolver for conflict type \"%s\" of relation \"%s\"",
+						conflict_type, RelationGetRelationName(rel))));
+
+	/*
+	 * While resetting resolver on parent table, reset resolver for child
+	 * partition table only if it is inherited one.
+	 *
+	 * OTOH, if user has invoked RESET directly on child partition table,
+	 * ensure  we reset only non-inherited resolvers. Inherited resolvers can
+	 * not be reset alone on child table, RESET has to come through parent
+	 * table.
+	 */
+	if ((recursing && confForm->confrinherited) ||
+		(!recursing && !confForm->confrinherited))
+	{
+		ObjectAddressSet(confobj, ConflictRelRelationId, confForm->oid);
+		performDeletion(&confobj, DROP_CASCADE, 0);
+	}
+	else
+	{
+		/*
+		 * If we did not reset resolver for this child table, do not reset for
+		 * child's child tables as well.
+		 */
+		recurse = false;
+	}
+
+	ReleaseSysCache(tup);
+
+	if (recurse && (rel->rd_rel->relkind == RELKIND_PARTITIONED_TABLE))
+	{
+		List	   *children;
+		ListCell   *lc;
+
+		children =
+			find_inheritance_children(RelationGetRelid(rel), lockmode);
+
+		foreach(lc, children)
+		{
+			Relation	childrel;
+
+			/* find_inheritance_children already got lock */
+			childrel = table_open(lfirst_oid(lc), NoLock);
+			ResetTableConflictResolver(childrel, conflict_type, recurse, true, lockmode);
+			table_close(childrel, NoLock);
+		}
+	}
+}
+
+/*
+ * Inherit conflict resolvers from parent paritioned table.
+ *
+ * If child partition table has resolvers set already for some conflict
+ * types, do not overwrite those, inherit rest from parent.
+ *
+ * Used during attach partition operation.
+ */
+void
+InheritTableConflictResolvers(Relation child_rel, Relation parent_rel)
+{
+	Relation	pg_conflict_rel;
+	SysScanDesc parent_scan;
+	ScanKeyData parent_key;
+	HeapTuple	parent_tuple;
+	Oid			parent_relid = RelationGetRelid(parent_rel);
+
+	Assert(parent_rel->rd_rel->relkind == RELKIND_PARTITIONED_TABLE);
+
+	pg_conflict_rel = table_open(ConflictRelRelationId, RowExclusiveLock);
+
+	ScanKeyInit(&parent_key,
+				Anum_pg_conflict_rel_confrrelid,
+				BTEqualStrategyNumber, F_OIDEQ,
+				ObjectIdGetDatum(parent_relid));
+
+	parent_scan = systable_beginscan(pg_conflict_rel, InvalidOid, false, NULL, 1, &parent_key);
+
+	while (HeapTupleIsValid(parent_tuple = systable_getnext(parent_scan)))
+	{
+		Datum		typeDatum;
+		Datum		resDatum;
+		char	   *parent_conftype;
+		char	   *parent_confres;
+
+		typeDatum = SysCacheGetAttrNotNull(CONFLICTRELOID, parent_tuple,
+										   Anum_pg_conflict_rel_confrtype);
+		parent_conftype = TextDatumGetCString(typeDatum);
+
+		resDatum = SysCacheGetAttrNotNull(CONFLICTRELOID, parent_tuple,
+										  Anum_pg_conflict_rel_confrres);
+		parent_confres = TextDatumGetCString(resDatum);
+
+		SetTableConflictResolver(pg_conflict_rel, child_rel, parent_conftype, parent_confres, true, true, AccessExclusiveLock);
+	}
+
+	systable_endscan(parent_scan);
+	table_close(pg_conflict_rel, RowExclusiveLock);
+}
+
+/*
+ * Reset inheritance of conflict resolvers.
+ *
+ * Used during detach partition operation. Detach partition
+ * will not remove inherited resolvers but will mark them
+ * as non inherited.
+ */
+void
+ResetResolversInheritance(Relation rel)
+{
+	Relation	pg_conflict_rel;
+	SysScanDesc scan;
+	ScanKeyData key;
+	HeapTuple	tuple;
+	Oid			relid = RelationGetRelid(rel);
+
+	Assert(rel->rd_rel->relispartition);
+
+	pg_conflict_rel = table_open(ConflictRelRelationId, RowExclusiveLock);
+
+	ScanKeyInit(&key,
+				Anum_pg_conflict_rel_confrrelid,
+				BTEqualStrategyNumber, F_OIDEQ,
+				ObjectIdGetDatum(relid));
+
+	scan = systable_beginscan(pg_conflict_rel, InvalidOid, false, NULL, 1, &key);
+
+	while (HeapTupleIsValid(tuple = systable_getnext(scan)))
+	{
+		Form_pg_conflict_rel conf =
+			(Form_pg_conflict_rel) GETSTRUCT(tuple);
+
+		if (conf->confrinherited)
+		{
+			HeapTuple	copy_tuple = heap_copytuple(tuple);
+			Form_pg_conflict_rel copy_conf =
+				(Form_pg_conflict_rel) GETSTRUCT(copy_tuple);
+
+			copy_conf->confrinherited = false;
+			CatalogTupleUpdate(pg_conflict_rel, &copy_tuple->t_self, copy_tuple);
+			heap_freetuple(copy_tuple);
+
+		}
+	}
+
+	systable_endscan(scan);
+	table_close(pg_conflict_rel, RowExclusiveLock);
+}
+
+/*
+ * Remove the conflict resolver configuration by table conflict oid.
+ */
+void
+RemoveTableConflictById(Oid confid)
+{
+	Relation	rel;
+	HeapTuple	tup;
+
+	rel = table_open(ConflictRelRelationId, RowExclusiveLock);
+
+	tup = SearchSysCache1(CONFLICTRELOID, ObjectIdGetDatum(confid));
+	if (!HeapTupleIsValid(tup))
+		elog(ERROR, "cache lookup failed for table conflict %u", confid);
+
+	CatalogTupleDelete(rel, &tup->t_self);
+
+	ReleaseSysCache(tup);
+
+	table_close(rel, RowExclusiveLock);
+}
diff --git a/src/include/catalog/Makefile b/src/include/catalog/Makefile
index 8619d73e5a..e192375fa0 100644
--- a/src/include/catalog/Makefile
+++ b/src/include/catalog/Makefile
@@ -82,7 +82,9 @@ CATALOG_HEADERS := \
 	pg_publication_rel.h \
 	pg_subscription.h \
 	pg_subscription_rel.h \
-	pg_conflict.h
+	pg_conflict.h \
+	pg_conflict_rel.h
+
 
 GENERATED_HEADERS := $(CATALOG_HEADERS:%.h=%_d.h)
 
diff --git a/src/include/catalog/meson.build b/src/include/catalog/meson.build
index 4d6732a303..28924f5df8 100644
--- a/src/include/catalog/meson.build
+++ b/src/include/catalog/meson.build
@@ -70,6 +70,7 @@ catalog_headers = [
   'pg_subscription.h',
   'pg_subscription_rel.h',
   'pg_conflict.h',
+  'pg_conflict_rel.h',
 ]
 
 # The .dat files we need can just be listed alphabetically.
diff --git a/src/include/catalog/pg_conflict.h b/src/include/catalog/pg_conflict.h
index e3fe3e6d30..c080a0d0be 100644
--- a/src/include/catalog/pg_conflict.h
+++ b/src/include/catalog/pg_conflict.h
@@ -26,7 +26,7 @@
  *		typedef struct FormData_pg_conflict
  * ----------------
  */
-CATALOG(pg_conflict,8688,ConflictResRelationId)
+CATALOG(pg_conflict,8688,ConflictRelationId)
 {
 #ifdef CATALOG_VARLEN			/* variable-length fields start here */
 	text		conftype BKI_FORCE_NOT_NULL;	/* conflict type */
diff --git a/src/include/catalog/pg_conflict_rel.h b/src/include/catalog/pg_conflict_rel.h
new file mode 100644
index 0000000000..636398baf1
--- /dev/null
+++ b/src/include/catalog/pg_conflict_rel.h
@@ -0,0 +1,58 @@
+/* -------------------------------------------------------------------------
+ *
+ * pg_conflict_rel.h
+ *	  definition of the "table level conflict detection" system
+ *        catalog (pg_conflict_rel)
+ *
+ * Portions Copyright (c) 1996-2024, PostgreSQL Global Development Group
+ * Portions Copyright (c) 1994, Regents of the University of California
+ *
+ * src/include/catalog/pg_conflict_rel.h
+ *
+ * NOTES
+ *	  The Catalog.pm module reads this file and derives schema
+ *	  information.
+ *
+ * -------------------------------------------------------------------------
+ */
+#ifndef PG_CONFLICT_REL_H
+#define PG_CONFLICT_REL_H
+
+#include "catalog/genbki.h"
+#include "catalog/pg_conflict_rel_d.h"
+
+/* ----------------
+ *		pg_conflict_rel definition.  cpp turns this into
+ *		typedef struct FormData_pg_conflict_rel
+ * ----------------
+ */
+CATALOG(pg_conflict_rel,8881,ConflictRelRelationId)
+{
+	Oid			oid;			/* OID of the object itself */
+	Oid			confrrelid BKI_LOOKUP(pg_class);	/* Oid of the relation
+													 * having resolver */
+	bool		confrinherited; /* Is this an inherited configuration */
+
+#ifdef CATALOG_VARLEN			/* variable-length fields start here */
+	text		confrtype BKI_FORCE_NOT_NULL;	/* conflict type */
+	text		confrres BKI_FORCE_NOT_NULL;	/* conflict resolver */
+#endif
+} FormData_pg_conflict_rel;
+
+/* ----------------
+ *		Form_pg_conflict_rel corresponds to a pointer to a row with
+ *		the format of pg_conflict_rel relation.
+ * ----------------
+ */
+typedef FormData_pg_conflict_rel * Form_pg_conflict_rel;
+
+DECLARE_TOAST(pg_conflict_rel, 8882, 8883);
+
+DECLARE_UNIQUE_INDEX_PKEY(pg_conflict_rel_oid_index, 8884, ConflictRelOidIndexId, pg_conflict_rel, btree(oid oid_ops));
+
+DECLARE_UNIQUE_INDEX(pg_conflict_rel_type_index, 8885, ConflictRelTypeIndexId, pg_conflict_rel, btree(confrrelid oid_ops, confrtype text_ops));
+
+MAKE_SYSCACHE(CONFLICTRELOID, pg_conflict_rel_oid_index, 256);
+MAKE_SYSCACHE(CONFLICTRELTYPE, pg_conflict_rel_type_index, 256);
+
+#endif							/* PG_CONFLICT_REL_H */
diff --git a/src/include/nodes/parsenodes.h b/src/include/nodes/parsenodes.h
index 1d41169d5e..7677cf023b 100644
--- a/src/include/nodes/parsenodes.h
+++ b/src/include/nodes/parsenodes.h
@@ -2419,6 +2419,8 @@ typedef enum AlterTableType
 	AT_SetIdentity,				/* SET identity column options */
 	AT_DropIdentity,			/* DROP IDENTITY */
 	AT_ReAddStatistics,			/* internal to commands/tablecmds.c */
+	AT_SetConflictResolver,		/* SET CONFLICT RESOLVER */
+	AT_ResetConflictResolver,	/* RESET CONFLICT RESOLVER */
 } AlterTableType;
 
 typedef struct ReplicaIdentityStmt
diff --git a/src/include/replication/conflict.h b/src/include/replication/conflict.h
index 82f4f5ec49..bbbab5bbc2 100644
--- a/src/include/replication/conflict.h
+++ b/src/include/replication/conflict.h
@@ -93,4 +93,17 @@ extern ConflictResolver GetConflictResolver(TupleTableSlot *localslot,
 											TimestampTz committs);
 extern bool CanCreateFullTuple(Relation localrel,
 							   LogicalRepTupleData *newtup);
+
+extern ConflictType ValidateConflictTypeAndResolver(char *conflict_type,
+													char *conflict_resolver,
+													bool isReset);
+extern void SetTableConflictResolver(Relation pg_conf_rel, Relation rel, char *conflict_type,
+									 char *conflict_resolver, bool recurse,
+									 bool recursing, LOCKMODE lockmode);
+extern void ResetTableConflictResolver(Relation rel, char *conflict_type,
+									   bool recurse, bool recursing, LOCKMODE lockmode);
+extern void RemoveTableConflictById(Oid confid);
+extern void InheritTableConflictResolvers(Relation child_rel, Relation parent_rel);
+extern void ResetResolversInheritance(Relation rel);
+
 #endif
diff --git a/src/test/regress/expected/conflict_resolver.out b/src/test/regress/expected/conflict_resolver.out
index d0157ba830..8f0948306b 100644
--- a/src/test/regress/expected/conflict_resolver.out
+++ b/src/test/regress/expected/conflict_resolver.out
@@ -1,5 +1,8 @@
+--
+-- Test for configuration of global resolvers
+--
 --check default global resolvers in system catalog
-select * from pg_conflict order by conftype;
+SELECT * FROM pg_conflict order by conftype;
     conftype    |     confres      
 ----------------+------------------
  delete_missing | skip
@@ -8,9 +11,7 @@ select * from pg_conflict order by conftype;
  update_missing | apply_or_skip
 (4 rows)
 
---
 -- Test of SET/RESET CONFLICT RESOLVER with invalid names
---
 SET CONFLICT RESOLVER 'keep_local' for 'aaaa'; -- fail
 ERROR:  aaaa is not a valid conflict type
 SET CONFLICT RESOLVER 'bbbbb' for 'delete_missing'; -- fail
@@ -19,15 +20,13 @@ SET CONFLICT RESOLVER 'remote_apply' for 'delete_missing'; -- fail
 ERROR:  remote_apply is not a valid conflict resolver for conflict type delete_missing
 RESET CONFLICT RESOLVER for 'ct'; -- fail
 ERROR:  ct is not a valid conflict type
---
 -- Test of SET/RESET CONFLICT RESOLVER with valid names
---
 SET CONFLICT RESOLVER 'error' for 'delete_missing';
 SET CONFLICT RESOLVER 'keep_local' for 'insert_exists';
 SET CONFLICT RESOLVER 'keep_local' for 'update_differ';
 SET CONFLICT RESOLVER 'apply_or_error' for 'update_missing';
 --check new resolvers are saved
-select * from pg_conflict order by conftype;
+SELECT * FROM pg_conflict order by conftype;
     conftype    |    confres     
 ----------------+----------------
  delete_missing | error
@@ -39,7 +38,7 @@ select * from pg_conflict order by conftype;
 RESET CONFLICT RESOLVER for 'delete_missing';
 RESET CONFLICT RESOLVER for 'insert_exists';
 --check resolvers are reset to default for delete_missing and insert_exists
-select * from pg_conflict order by conftype;
+SELECT * FROM pg_conflict order by conftype;
     conftype    |     confres      
 ----------------+------------------
  delete_missing | skip
@@ -48,3 +47,235 @@ select * from pg_conflict order by conftype;
  update_missing | apply_or_error
 (4 rows)
 
+--
+-- Test for configuration of table level resolvers
+--
+-- Test for ALTER TABLE..SET/RESET CONFLICT RESOLVER
+CREATE TABLE ptntable (
+    city_id         int not null,
+    logdate         date not null,
+    peaktemp        int,
+    unitsales       int
+) PARTITION BY RANGE (logdate);
+CREATE TABLE ptntable_1 PARTITION OF ptntable
+    FOR VALUES FROM ('2006-02-01') TO ('2006-03-01');
+CREATE TABLE ptntable_2 PARTITION OF ptntable
+    FOR VALUES FROM ('2006-03-01') TO ('2006-04-01')
+    PARTITION BY RANGE (logdate);
+CREATE TABLE ptntable_2_1 PARTITION OF ptntable_2
+    FOR VALUES FROM ('2006-03-20') TO ('2006-04-01');
+ALTER TABLE ptntable SET CONFLICT RESOLVER 'error' ON 'delete_missing',
+                     SET CONFLICT RESOLVER 'keep_local' ON 'insert_exists';
+--Expect 8 entries. 2 for parent and 2 for each child partition (inherited
+--resolvers)
+SELECT relname, confrtype, confrres, confrinherited FROM pg_class pc,
+  (SELECT confrrelid, confrtype, confrres, confrinherited FROM pg_conflict_rel)conf
+  WHERE conf.confrrelid= pc.oid order by relname, confrtype;
+   relname    |   confrtype    |  confrres  | confrinherited 
+--------------+----------------+------------+----------------
+ ptntable     | delete_missing | error      | f
+ ptntable     | insert_exists  | keep_local | f
+ ptntable_1   | delete_missing | error      | t
+ ptntable_1   | insert_exists  | keep_local | t
+ ptntable_2   | delete_missing | error      | t
+ ptntable_2   | insert_exists  | keep_local | t
+ ptntable_2_1 | delete_missing | error      | t
+ ptntable_2_1 | insert_exists  | keep_local | t
+(8 rows)
+
+ALTER TABLE ptntable_2 SET CONFLICT RESOLVER 'skip' ON 'delete_missing',
+                       SET CONFLICT RESOLVER 'remote_apply' ON 'update_differ';
+--For both ptntable_2 and ptntable_2_1, expect:
+--The resolver for 'delete_missing' changed from 'error' to 'skip'
+--The 'update_differ'configuration added
+SELECT relname, confrtype, confrres, confrinherited FROM pg_class pc,
+  (SELECT confrrelid, confrtype, confrres, confrinherited FROM pg_conflict_rel)conf
+  WHERE conf.confrrelid= pc.oid order by relname, confrtype;
+   relname    |   confrtype    |   confrres   | confrinherited 
+--------------+----------------+--------------+----------------
+ ptntable     | delete_missing | error        | f
+ ptntable     | insert_exists  | keep_local   | f
+ ptntable_1   | delete_missing | error        | t
+ ptntable_1   | insert_exists  | keep_local   | t
+ ptntable_2   | delete_missing | skip         | f
+ ptntable_2   | insert_exists  | keep_local   | t
+ ptntable_2   | update_differ  | remote_apply | f
+ ptntable_2_1 | delete_missing | skip         | t
+ ptntable_2_1 | insert_exists  | keep_local   | t
+ ptntable_2_1 | update_differ  | remote_apply | t
+(10 rows)
+
+--Set resolvers on parent table again. It should not overwrite non inherited
+--entries for ptntable_2 and corresponding entries for ptntable_2_1
+ALTER TABLE ptntable SET CONFLICT RESOLVER 'error' ON 'delete_missing',
+                     SET CONFLICT RESOLVER 'remote_apply' ON 'insert_exists';
+SELECT relname, confrtype, confrres, confrinherited FROM pg_class pc,
+  (SELECT confrrelid, confrtype, confrres, confrinherited FROM pg_conflict_rel)conf
+  WHERE conf.confrrelid= pc.oid order by relname, confrtype;
+   relname    |   confrtype    |   confrres   | confrinherited 
+--------------+----------------+--------------+----------------
+ ptntable     | delete_missing | error        | f
+ ptntable     | insert_exists  | remote_apply | f
+ ptntable_1   | delete_missing | error        | t
+ ptntable_1   | insert_exists  | remote_apply | t
+ ptntable_2   | delete_missing | skip         | f
+ ptntable_2   | insert_exists  | remote_apply | t
+ ptntable_2   | update_differ  | remote_apply | f
+ ptntable_2_1 | delete_missing | skip         | t
+ ptntable_2_1 | insert_exists  | remote_apply | t
+ ptntable_2_1 | update_differ  | remote_apply | t
+(10 rows)
+
+--Reset of inherited entry ON child alone should result in error
+ALTER TABLE ptntable_2 RESET CONFLICT RESOLVER ON 'insert_exists';
+ERROR:  cannot reset inherited resolver for conflict type "insert_exists" of relation "ptntable_2"
+--Reset of non-inherited entry ON child alone should suceed
+ALTER TABLE ptntable_2 RESET CONFLICT RESOLVER ON 'update_differ';
+SELECT relname, confrtype, confrres, confrinherited FROM pg_class pc,
+  (SELECT confrrelid, confrtype, confrres, confrinherited FROM pg_conflict_rel)conf
+  WHERE conf.confrrelid= pc.oid order by relname, confrtype;
+   relname    |   confrtype    |   confrres   | confrinherited 
+--------------+----------------+--------------+----------------
+ ptntable     | delete_missing | error        | f
+ ptntable     | insert_exists  | remote_apply | f
+ ptntable_1   | delete_missing | error        | t
+ ptntable_1   | insert_exists  | remote_apply | t
+ ptntable_2   | delete_missing | skip         | f
+ ptntable_2   | insert_exists  | remote_apply | t
+ ptntable_2_1 | delete_missing | skip         | t
+ ptntable_2_1 | insert_exists  | remote_apply | t
+(8 rows)
+
+DROP TABLE ptntable_2;
+--Expect entries removed for both ptntable_2 and its child ptntable_2_1
+SELECT relname, confrtype, confrres, confrinherited FROM pg_class pc,
+  (SELECT confrrelid, confrtype, confrres, confrinherited FROM pg_conflict_rel)conf
+  WHERE conf.confrrelid= pc.oid order by relname, confrtype;
+  relname   |   confrtype    |   confrres   | confrinherited 
+------------+----------------+--------------+----------------
+ ptntable   | delete_missing | error        | f
+ ptntable   | insert_exists  | remote_apply | f
+ ptntable_1 | delete_missing | error        | t
+ ptntable_1 | insert_exists  | remote_apply | t
+(4 rows)
+
+-- Test for ALTER TABLE..SPLIT PARTITION and ALTER TABLE..MERGE PARTITIONS
+ALTER TABLE ptntable SPLIT PARTITION ptntable_1 INTO
+   (PARTITION ptntable_1_1 FOR VALUES FROM ('2006-02-01') TO ('2006-02-10'),
+    PARTITION ptntable_1_10 FOR VALUES FROM ('2006-02-10') TO ('2006-02-20'),
+    PARTITION ptntable_1_20 FOR VALUES FROM ('2006-02-20') TO ('2006-03-01'));
+--Expect split partitions to inherit resolvers FROM parent
+SELECT relname, confrtype, confrres, confrinherited FROM pg_class pc,
+  (SELECT confrrelid, confrtype, confrres, confrinherited FROM pg_conflict_rel)conf
+  WHERE conf.confrrelid= pc.oid order by relname, confrtype;
+    relname    |   confrtype    |   confrres   | confrinherited 
+---------------+----------------+--------------+----------------
+ ptntable      | delete_missing | error        | f
+ ptntable      | insert_exists  | remote_apply | f
+ ptntable_1_1  | delete_missing | error        | t
+ ptntable_1_1  | insert_exists  | remote_apply | t
+ ptntable_1_10 | delete_missing | error        | t
+ ptntable_1_10 | insert_exists  | remote_apply | t
+ ptntable_1_20 | delete_missing | error        | t
+ ptntable_1_20 | insert_exists  | remote_apply | t
+(8 rows)
+
+ALTER TABLE ptntable MERGE PARTITIONS (ptntable_1_1, ptntable_1_10, ptntable_1_20)
+    INTO ptntable_1;
+--Expect merged partition to inherit resolvers FROM parent
+SELECT relname, confrtype, confrres, confrinherited FROM pg_class pc,
+  (SELECT confrrelid, confrtype, confrres, confrinherited FROM pg_conflict_rel)conf
+  WHERE conf.confrrelid= pc.oid order by relname, confrtype;
+  relname   |   confrtype    |   confrres   | confrinherited 
+------------+----------------+--------------+----------------
+ ptntable   | delete_missing | error        | f
+ ptntable   | insert_exists  | remote_apply | f
+ ptntable_1 | delete_missing | error        | t
+ ptntable_1 | insert_exists  | remote_apply | t
+(4 rows)
+
+-- Test for ALTER TABLE..ATTACH PARTITION and CREATE TABLE..PARTITION OF
+CREATE TABLE ptntable_2(
+    city_id         int not null,
+    logdate         date not null,
+    peaktemp        int,
+    unitsales       int
+) PARTITION BY RANGE (logdate);
+ALTER TABLE ptntable_2 SET CONFLICT RESOLVER 'remote_apply' ON 'update_differ',
+		       SET CONFLICT RESOLVER 'skip' ON 'delete_missing';
+--Expect ptntable_2_1 to inherit resolvers of  ptntable_2
+CREATE TABLE ptntable_2_1 PARTITION OF ptntable_2
+    FOR VALUES FROM ('2006-03-20') TO ('2006-04-01');
+--Expect 4 new entries for ptntable_2 and its child ptntable_2_1
+--Entried for ptntable_2_1 should be marked as inherited.
+SELECT relname, confrtype, confrres, confrinherited FROM pg_class pc,
+  (SELECT confrrelid, confrtype, confrres, confrinherited FROM pg_conflict_rel)conf
+  WHERE conf.confrrelid= pc.oid order by relname, confrtype;
+   relname    |   confrtype    |   confrres   | confrinherited 
+--------------+----------------+--------------+----------------
+ ptntable     | delete_missing | error        | f
+ ptntable     | insert_exists  | remote_apply | f
+ ptntable_1   | delete_missing | error        | t
+ ptntable_1   | insert_exists  | remote_apply | t
+ ptntable_2   | delete_missing | skip         | f
+ ptntable_2   | update_differ  | remote_apply | f
+ ptntable_2_1 | delete_missing | skip         | t
+ ptntable_2_1 | update_differ  | remote_apply | t
+(8 rows)
+
+--Attach ptntable_2 to ptntable now
+ALTER TABLE ptntable ATTACH PARTITION ptntable_2
+      FOR VALUES FROM ('2006-03-01') TO ('2006-04-01');
+--For both ptntable_2 and ptntable_2_1, expect:
+--The 'insert_exists' configuration inherited
+--Resolver for 'delete_missing' not overwritten
+--Resolver for 'update_differ' retained.
+SELECT relname, confrtype, confrres, confrinherited FROM pg_class pc,
+  (SELECT confrrelid, confrtype, confrres, confrinherited FROM pg_conflict_rel)conf
+  WHERE conf.confrrelid= pc.oid order by relname, confrtype;
+   relname    |   confrtype    |   confrres   | confrinherited 
+--------------+----------------+--------------+----------------
+ ptntable     | delete_missing | error        | f
+ ptntable     | insert_exists  | remote_apply | f
+ ptntable_1   | delete_missing | error        | t
+ ptntable_1   | insert_exists  | remote_apply | t
+ ptntable_2   | delete_missing | skip         | f
+ ptntable_2   | insert_exists  | remote_apply | t
+ ptntable_2   | update_differ  | remote_apply | f
+ ptntable_2_1 | delete_missing | skip         | t
+ ptntable_2_1 | insert_exists  | remote_apply | t
+ ptntable_2_1 | update_differ  | remote_apply | t
+(10 rows)
+
+-- Test for ALTER TABLE..DETACH PARTITION
+ALTER TABLE ptntable DETACH PARTITION ptntable_2;
+--All resolvers of ptntable_2 should be marked as non-inherited
+--All resolvers for ptntable_2_1's should still be marked as inherited (as
+--they are still inherited from ptntable_2)
+SELECT relname, confrtype, confrres, confrinherited FROM pg_class pc,
+  (SELECT confrrelid, confrtype, confrres, confrinherited FROM pg_conflict_rel)conf
+  WHERE conf.confrrelid= pc.oid order by relname, confrtype;
+   relname    |   confrtype    |   confrres   | confrinherited 
+--------------+----------------+--------------+----------------
+ ptntable     | delete_missing | error        | f
+ ptntable     | insert_exists  | remote_apply | f
+ ptntable_1   | delete_missing | error        | t
+ ptntable_1   | insert_exists  | remote_apply | t
+ ptntable_2   | delete_missing | skip         | f
+ ptntable_2   | insert_exists  | remote_apply | f
+ ptntable_2   | update_differ  | remote_apply | f
+ ptntable_2_1 | delete_missing | skip         | t
+ ptntable_2_1 | insert_exists  | remote_apply | t
+ ptntable_2_1 | update_differ  | remote_apply | t
+(10 rows)
+
+DROP TABLE ptntable_2;
+DROP TABLE ptntable;
+--Expect no resolvers
+SELECT relname, confrtype, confrres, confrinherited FROM pg_class pc,
+  (SELECT confrrelid, confrtype, confrres, confrinherited FROM pg_conflict_rel)conf
+  WHERE conf.confrrelid= pc.oid order by relname, confrtype;
+ relname | confrtype | confrres | confrinherited 
+---------+-----------+----------+----------------
+(0 rows)
+
diff --git a/src/test/regress/expected/oidjoins.out b/src/test/regress/expected/oidjoins.out
index 215eb899be..8caf852600 100644
--- a/src/test/regress/expected/oidjoins.out
+++ b/src/test/regress/expected/oidjoins.out
@@ -266,3 +266,4 @@ NOTICE:  checking pg_subscription {subdbid} => pg_database {oid}
 NOTICE:  checking pg_subscription {subowner} => pg_authid {oid}
 NOTICE:  checking pg_subscription_rel {srsubid} => pg_subscription {oid}
 NOTICE:  checking pg_subscription_rel {srrelid} => pg_class {oid}
+NOTICE:  checking pg_conflict_rel {confrrelid} => pg_class {oid}
diff --git a/src/test/regress/sql/conflict_resolver.sql b/src/test/regress/sql/conflict_resolver.sql
index e3540d7ac8..346590303f 100644
--- a/src/test/regress/sql/conflict_resolver.sql
+++ b/src/test/regress/sql/conflict_resolver.sql
@@ -1,27 +1,174 @@
+--
+-- Test for configuration of global resolvers
+--
+
 --check default global resolvers in system catalog
-select * from pg_conflict order by conftype;
+SELECT * FROM pg_conflict order by conftype;
 
---
 -- Test of SET/RESET CONFLICT RESOLVER with invalid names
---
+
 SET CONFLICT RESOLVER 'keep_local' for 'aaaa'; -- fail
 SET CONFLICT RESOLVER 'bbbbb' for 'delete_missing'; -- fail
 SET CONFLICT RESOLVER 'remote_apply' for 'delete_missing'; -- fail
 RESET CONFLICT RESOLVER for 'ct'; -- fail
 
---
 -- Test of SET/RESET CONFLICT RESOLVER with valid names
---
+
 SET CONFLICT RESOLVER 'error' for 'delete_missing';
 SET CONFLICT RESOLVER 'keep_local' for 'insert_exists';
 SET CONFLICT RESOLVER 'keep_local' for 'update_differ';
 SET CONFLICT RESOLVER 'apply_or_error' for 'update_missing';
 
 --check new resolvers are saved
-select * from pg_conflict order by conftype;
+SELECT * FROM pg_conflict order by conftype;
 
 RESET CONFLICT RESOLVER for 'delete_missing';
 RESET CONFLICT RESOLVER for 'insert_exists';
 
 --check resolvers are reset to default for delete_missing and insert_exists
-select * from pg_conflict order by conftype;
+SELECT * FROM pg_conflict order by conftype;
+
+--
+-- Test for configuration of table level resolvers
+--
+
+
+-- Test for ALTER TABLE..SET/RESET CONFLICT RESOLVER
+
+CREATE TABLE ptntable (
+    city_id         int not null,
+    logdate         date not null,
+    peaktemp        int,
+    unitsales       int
+) PARTITION BY RANGE (logdate);
+
+CREATE TABLE ptntable_1 PARTITION OF ptntable
+    FOR VALUES FROM ('2006-02-01') TO ('2006-03-01');
+
+CREATE TABLE ptntable_2 PARTITION OF ptntable
+    FOR VALUES FROM ('2006-03-01') TO ('2006-04-01')
+    PARTITION BY RANGE (logdate);
+
+CREATE TABLE ptntable_2_1 PARTITION OF ptntable_2
+    FOR VALUES FROM ('2006-03-20') TO ('2006-04-01');
+
+ALTER TABLE ptntable SET CONFLICT RESOLVER 'error' ON 'delete_missing',
+                     SET CONFLICT RESOLVER 'keep_local' ON 'insert_exists';
+
+--Expect 8 entries. 2 for parent and 2 for each child partition (inherited
+--resolvers)
+SELECT relname, confrtype, confrres, confrinherited FROM pg_class pc,
+  (SELECT confrrelid, confrtype, confrres, confrinherited FROM pg_conflict_rel)conf
+  WHERE conf.confrrelid= pc.oid order by relname, confrtype;
+
+ALTER TABLE ptntable_2 SET CONFLICT RESOLVER 'skip' ON 'delete_missing',
+                       SET CONFLICT RESOLVER 'remote_apply' ON 'update_differ';
+
+--For both ptntable_2 and ptntable_2_1, expect:
+--The resolver for 'delete_missing' changed from 'error' to 'skip'
+--The 'update_differ'configuration added
+SELECT relname, confrtype, confrres, confrinherited FROM pg_class pc,
+  (SELECT confrrelid, confrtype, confrres, confrinherited FROM pg_conflict_rel)conf
+  WHERE conf.confrrelid= pc.oid order by relname, confrtype;
+
+--Set resolvers on parent table again. It should not overwrite non inherited
+--entries for ptntable_2 and corresponding entries for ptntable_2_1
+ALTER TABLE ptntable SET CONFLICT RESOLVER 'error' ON 'delete_missing',
+                     SET CONFLICT RESOLVER 'remote_apply' ON 'insert_exists';
+
+SELECT relname, confrtype, confrres, confrinherited FROM pg_class pc,
+  (SELECT confrrelid, confrtype, confrres, confrinherited FROM pg_conflict_rel)conf
+  WHERE conf.confrrelid= pc.oid order by relname, confrtype;
+
+--Reset of inherited entry ON child alone should result in error
+ALTER TABLE ptntable_2 RESET CONFLICT RESOLVER ON 'insert_exists';
+
+--Reset of non-inherited entry ON child alone should suceed
+ALTER TABLE ptntable_2 RESET CONFLICT RESOLVER ON 'update_differ';
+
+SELECT relname, confrtype, confrres, confrinherited FROM pg_class pc,
+  (SELECT confrrelid, confrtype, confrres, confrinherited FROM pg_conflict_rel)conf
+  WHERE conf.confrrelid= pc.oid order by relname, confrtype;
+
+DROP TABLE ptntable_2;
+
+--Expect entries removed for both ptntable_2 and its child ptntable_2_1
+SELECT relname, confrtype, confrres, confrinherited FROM pg_class pc,
+  (SELECT confrrelid, confrtype, confrres, confrinherited FROM pg_conflict_rel)conf
+  WHERE conf.confrrelid= pc.oid order by relname, confrtype;
+
+
+-- Test for ALTER TABLE..SPLIT PARTITION and ALTER TABLE..MERGE PARTITIONS
+
+ALTER TABLE ptntable SPLIT PARTITION ptntable_1 INTO
+   (PARTITION ptntable_1_1 FOR VALUES FROM ('2006-02-01') TO ('2006-02-10'),
+    PARTITION ptntable_1_10 FOR VALUES FROM ('2006-02-10') TO ('2006-02-20'),
+    PARTITION ptntable_1_20 FOR VALUES FROM ('2006-02-20') TO ('2006-03-01'));
+
+--Expect split partitions to inherit resolvers FROM parent
+SELECT relname, confrtype, confrres, confrinherited FROM pg_class pc,
+  (SELECT confrrelid, confrtype, confrres, confrinherited FROM pg_conflict_rel)conf
+  WHERE conf.confrrelid= pc.oid order by relname, confrtype;
+
+ALTER TABLE ptntable MERGE PARTITIONS (ptntable_1_1, ptntable_1_10, ptntable_1_20)
+    INTO ptntable_1;
+
+--Expect merged partition to inherit resolvers FROM parent
+SELECT relname, confrtype, confrres, confrinherited FROM pg_class pc,
+  (SELECT confrrelid, confrtype, confrres, confrinherited FROM pg_conflict_rel)conf
+  WHERE conf.confrrelid= pc.oid order by relname, confrtype;
+
+
+-- Test for ALTER TABLE..ATTACH PARTITION and CREATE TABLE..PARTITION OF
+
+CREATE TABLE ptntable_2(
+    city_id         int not null,
+    logdate         date not null,
+    peaktemp        int,
+    unitsales       int
+) PARTITION BY RANGE (logdate);
+
+ALTER TABLE ptntable_2 SET CONFLICT RESOLVER 'remote_apply' ON 'update_differ',
+		       SET CONFLICT RESOLVER 'skip' ON 'delete_missing';
+
+--Expect ptntable_2_1 to inherit resolvers of  ptntable_2
+CREATE TABLE ptntable_2_1 PARTITION OF ptntable_2
+    FOR VALUES FROM ('2006-03-20') TO ('2006-04-01');
+
+--Expect 4 new entries for ptntable_2 and its child ptntable_2_1
+--Entried for ptntable_2_1 should be marked as inherited.
+SELECT relname, confrtype, confrres, confrinherited FROM pg_class pc,
+  (SELECT confrrelid, confrtype, confrres, confrinherited FROM pg_conflict_rel)conf
+  WHERE conf.confrrelid= pc.oid order by relname, confrtype;
+
+--Attach ptntable_2 to ptntable now
+ALTER TABLE ptntable ATTACH PARTITION ptntable_2
+      FOR VALUES FROM ('2006-03-01') TO ('2006-04-01');
+
+--For both ptntable_2 and ptntable_2_1, expect:
+--The 'insert_exists' configuration inherited
+--Resolver for 'delete_missing' not overwritten
+--Resolver for 'update_differ' retained.
+SELECT relname, confrtype, confrres, confrinherited FROM pg_class pc,
+  (SELECT confrrelid, confrtype, confrres, confrinherited FROM pg_conflict_rel)conf
+  WHERE conf.confrrelid= pc.oid order by relname, confrtype;
+
+
+-- Test for ALTER TABLE..DETACH PARTITION
+
+ALTER TABLE ptntable DETACH PARTITION ptntable_2;
+
+--All resolvers of ptntable_2 should be marked as non-inherited
+--All resolvers for ptntable_2_1's should still be marked as inherited (as
+--they are still inherited from ptntable_2)
+SELECT relname, confrtype, confrres, confrinherited FROM pg_class pc,
+  (SELECT confrrelid, confrtype, confrres, confrinherited FROM pg_conflict_rel)conf
+  WHERE conf.confrrelid= pc.oid order by relname, confrtype;
+
+DROP TABLE ptntable_2;
+DROP TABLE ptntable;
+
+--Expect no resolvers
+SELECT relname, confrtype, confrres, confrinherited FROM pg_class pc,
+  (SELECT confrrelid, confrtype, confrres, confrinherited FROM pg_conflict_rel)conf
+  WHERE conf.confrrelid= pc.oid order by relname, confrtype;
-- 
2.34.1



  [application/octet-stream] v3-0001-Detect-and-log-conflicts-in-logical-replication.patch (89.1K, ../../CAJpy0uCv8R1Y5herLLANhGGqCotAFzBw3ikzhpXZvbqLDuoMTw@mail.gmail.com/3-v3-0001-Detect-and-log-conflicts-in-logical-replication.patch)
  download | inline diff:
From 4b66fe543e1cc68102313f891914d023a5748ac7 Mon Sep 17 00:00:00 2001
From: Hou Zhijie <[email protected]>
Date: Fri, 31 May 2024 14:20:45 +0530
Subject: [PATCH v3 1/5] Detect and log conflicts in logical replication

This patch adds a new parameter detect_conflict for CREATE and ALTER
subscription commands. This new parameter will decide if subscription will
go for confict detection. By default, conflict detection will be off for a
subscription.

When conflict detection is enabled, additional logging is triggered in the
following conflict scenarios:

insert_exists: Inserting a row that iolates a NOT DEFERRABLE unique constraint.
update_differ: updating a row that was previously modified by another origin.
update_missing: The tuple to be updated is missing.
delete_missing: The tuple to be deleted is missing.

For insert_exists conflict, the log can include origin and commit
timestamp details of the conflicting key with track_commit_timestamp
enabled.

update_differ conflict can only be detected when track_commit_timestamp is
enabled.
---
 doc/src/sgml/catalogs.sgml                  |   9 +
 doc/src/sgml/ref/alter_subscription.sgml    |   5 +-
 doc/src/sgml/ref/create_subscription.sgml   |  55 ++++++
 src/backend/catalog/pg_subscription.c       |   1 +
 src/backend/catalog/system_views.sql        |   3 +-
 src/backend/commands/subscriptioncmds.c     |  31 +++-
 src/backend/executor/execIndexing.c         |  14 +-
 src/backend/executor/execReplication.c      | 117 +++++++++++-
 src/backend/replication/logical/Makefile    |   1 +
 src/backend/replication/logical/conflict.c  | 187 ++++++++++++++++++++
 src/backend/replication/logical/meson.build |   1 +
 src/backend/replication/logical/worker.c    |  50 ++++--
 src/bin/pg_dump/pg_dump.c                   |  17 +-
 src/bin/pg_dump/pg_dump.h                   |   1 +
 src/bin/psql/describe.c                     |   6 +-
 src/bin/psql/tab-complete.c                 |  14 +-
 src/include/catalog/pg_subscription.h       |   4 +
 src/include/replication/conflict.h          |  44 +++++
 src/test/regress/expected/subscription.out  | 176 ++++++++++--------
 src/test/regress/sql/subscription.sql       |  15 ++
 src/test/subscription/t/001_rep_changes.pl  |  15 +-
 src/test/subscription/t/013_partition.pl    |  48 ++---
 src/test/subscription/t/029_on_error.pl     |   5 +-
 src/test/subscription/t/030_origin.pl       |  26 +++
 src/tools/pgindent/typedefs.list            |   1 +
 25 files changed, 695 insertions(+), 151 deletions(-)
 create mode 100644 src/backend/replication/logical/conflict.c
 create mode 100644 src/include/replication/conflict.h

diff --git a/doc/src/sgml/catalogs.sgml b/doc/src/sgml/catalogs.sgml
index b654fae1b2..b042a5a94a 100644
--- a/doc/src/sgml/catalogs.sgml
+++ b/doc/src/sgml/catalogs.sgml
@@ -8035,6 +8035,15 @@ SCRAM-SHA-256$<replaceable>&lt;iteration count&gt;</replaceable>:<replaceable>&l
       </para></entry>
      </row>
 
+     <row>
+      <entry role="catalog_table_entry"><para role="column_definition">
+       <structfield>subdetectconflict</structfield> <type>bool</type>
+      </para>
+      <para>
+       If true, the subscription is enabled for conflict detection.
+      </para></entry>
+     </row>
+
      <row>
       <entry role="catalog_table_entry"><para role="column_definition">
        <structfield>subconninfo</structfield> <type>text</type>
diff --git a/doc/src/sgml/ref/alter_subscription.sgml b/doc/src/sgml/ref/alter_subscription.sgml
index 476f195622..5f6b83e415 100644
--- a/doc/src/sgml/ref/alter_subscription.sgml
+++ b/doc/src/sgml/ref/alter_subscription.sgml
@@ -228,8 +228,9 @@ ALTER SUBSCRIPTION <replaceable class="parameter">name</replaceable> RENAME TO <
       <link linkend="sql-createsubscription-params-with-disable-on-error"><literal>disable_on_error</literal></link>,
       <link linkend="sql-createsubscription-params-with-password-required"><literal>password_required</literal></link>,
       <link linkend="sql-createsubscription-params-with-run-as-owner"><literal>run_as_owner</literal></link>,
-      <link linkend="sql-createsubscription-params-with-origin"><literal>origin</literal></link>, and
-      <link linkend="sql-createsubscription-params-with-failover"><literal>failover</literal></link>.
+      <link linkend="sql-createsubscription-params-with-origin"><literal>origin</literal></link>,
+      <link linkend="sql-createsubscription-params-with-failover"><literal>failover</literal></link>, and
+      <link linkend="sql-createsubscription-params-with-detect-conflict"><literal>detect_conflict</literal></link>.
       Only a superuser can set <literal>password_required = false</literal>.
      </para>
 
diff --git a/doc/src/sgml/ref/create_subscription.sgml b/doc/src/sgml/ref/create_subscription.sgml
index 740b7d9421..ce37fa6490 100644
--- a/doc/src/sgml/ref/create_subscription.sgml
+++ b/doc/src/sgml/ref/create_subscription.sgml
@@ -428,6 +428,61 @@ CREATE SUBSCRIPTION <replaceable class="parameter">subscription_name</replaceabl
          </para>
         </listitem>
        </varlistentry>
+
+      <varlistentry id="sql-createsubscription-params-with-detect-conflict">
+        <term><literal>detect_conflict</literal> (<type>boolean</type>)</term>
+        <listitem>
+         <para>
+          Specifies whether the subscription is enabled for conflict detection.
+          The default is <literal>false</literal>.
+         </para>
+         <para>
+          When conflict detection is enabled, additional logging is triggered
+          in the following scenarios:
+          <variablelist>
+           <varlistentry>
+            <term><literal>insert_exists</literal></term>
+            <listitem>
+             <para>
+              Inserting a row that violates a <literal>NOT DEFERRABLE</literal>
+              unique constraint. Note that to obtain the origin and commit
+              timestamp details of the conflicting key in the log, ensure that
+              <link linkend="guc-track-commit-timestamp"><varname>track_commit_timestamp</varname></link>
+              is enabled.
+             </para>
+            </listitem>
+           </varlistentry>
+           <varlistentry>
+            <term><literal>update_differ</literal></term>
+            <listitem>
+             <para>
+              Updating a row that was previously modified by another origin. Note that this
+              conflict can only be detected when
+              <link linkend="guc-track-commit-timestamp"><varname>track_commit_timestamp</varname></link>
+              is enabled.
+             </para>
+            </listitem>
+           </varlistentry>
+           <varlistentry>
+            <term><literal>update_missing</literal></term>
+            <listitem>
+             <para>
+              The tuple to be updated is not found.
+             </para>
+            </listitem>
+           </varlistentry>
+           <varlistentry>
+            <term><literal>delete_missing</literal></term>
+            <listitem>
+             <para>
+              The tuple to be deleted is not found.
+             </para>
+            </listitem>
+           </varlistentry>
+          </variablelist>
+         </para>
+        </listitem>
+       </varlistentry>
       </variablelist></para>
 
     </listitem>
diff --git a/src/backend/catalog/pg_subscription.c b/src/backend/catalog/pg_subscription.c
index 9efc9159f2..5a423f4fb0 100644
--- a/src/backend/catalog/pg_subscription.c
+++ b/src/backend/catalog/pg_subscription.c
@@ -72,6 +72,7 @@ GetSubscription(Oid subid, bool missing_ok)
 	sub->passwordrequired = subform->subpasswordrequired;
 	sub->runasowner = subform->subrunasowner;
 	sub->failover = subform->subfailover;
+	sub->detectconflict = subform->subdetectconflict;
 
 	/* Get conninfo */
 	datum = SysCacheGetAttrNotNull(SUBSCRIPTIONOID,
diff --git a/src/backend/catalog/system_views.sql b/src/backend/catalog/system_views.sql
index 19cabc9a47..d084bfc48a 100644
--- a/src/backend/catalog/system_views.sql
+++ b/src/backend/catalog/system_views.sql
@@ -1356,7 +1356,8 @@ REVOKE ALL ON pg_subscription FROM public;
 GRANT SELECT (oid, subdbid, subskiplsn, subname, subowner, subenabled,
               subbinary, substream, subtwophasestate, subdisableonerr,
 			  subpasswordrequired, subrunasowner, subfailover,
-              subslotname, subsynccommit, subpublications, suborigin)
+			  subdetectconflict, subslotname, subsynccommit,
+			  subpublications, suborigin)
     ON pg_subscription TO public;
 
 CREATE VIEW pg_stat_subscription_stats AS
diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e407428dbc..e670d72708 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -70,8 +70,9 @@
 #define SUBOPT_PASSWORD_REQUIRED	0x00000800
 #define SUBOPT_RUN_AS_OWNER			0x00001000
 #define SUBOPT_FAILOVER				0x00002000
-#define SUBOPT_LSN					0x00004000
-#define SUBOPT_ORIGIN				0x00008000
+#define SUBOPT_DETECT_CONFLICT		0x00004000
+#define SUBOPT_LSN					0x00008000
+#define SUBOPT_ORIGIN				0x00010000
 
 /* check if the 'val' has 'bits' set */
 #define IsSet(val, bits)  (((val) & (bits)) == (bits))
@@ -97,6 +98,7 @@ typedef struct SubOpts
 	bool		passwordrequired;
 	bool		runasowner;
 	bool		failover;
+	bool		detectconflict;
 	char	   *origin;
 	XLogRecPtr	lsn;
 } SubOpts;
@@ -159,6 +161,8 @@ parse_subscription_options(ParseState *pstate, List *stmt_options,
 		opts->runasowner = false;
 	if (IsSet(supported_opts, SUBOPT_FAILOVER))
 		opts->failover = false;
+	if (IsSet(supported_opts, SUBOPT_DETECT_CONFLICT))
+		opts->detectconflict = false;
 	if (IsSet(supported_opts, SUBOPT_ORIGIN))
 		opts->origin = pstrdup(LOGICALREP_ORIGIN_ANY);
 
@@ -316,6 +320,15 @@ parse_subscription_options(ParseState *pstate, List *stmt_options,
 			opts->specified_opts |= SUBOPT_FAILOVER;
 			opts->failover = defGetBoolean(defel);
 		}
+		else if (IsSet(supported_opts, SUBOPT_DETECT_CONFLICT) &&
+				 strcmp(defel->defname, "detect_conflict") == 0)
+		{
+			if (IsSet(opts->specified_opts, SUBOPT_DETECT_CONFLICT))
+				errorConflictingDefElem(defel, pstate);
+
+			opts->specified_opts |= SUBOPT_DETECT_CONFLICT;
+			opts->detectconflict = defGetBoolean(defel);
+		}
 		else if (IsSet(supported_opts, SUBOPT_ORIGIN) &&
 				 strcmp(defel->defname, "origin") == 0)
 		{
@@ -603,7 +616,8 @@ CreateSubscription(ParseState *pstate, CreateSubscriptionStmt *stmt,
 					  SUBOPT_SYNCHRONOUS_COMMIT | SUBOPT_BINARY |
 					  SUBOPT_STREAMING | SUBOPT_TWOPHASE_COMMIT |
 					  SUBOPT_DISABLE_ON_ERR | SUBOPT_PASSWORD_REQUIRED |
-					  SUBOPT_RUN_AS_OWNER | SUBOPT_FAILOVER | SUBOPT_ORIGIN);
+					  SUBOPT_RUN_AS_OWNER | SUBOPT_FAILOVER |
+					  SUBOPT_DETECT_CONFLICT | SUBOPT_ORIGIN);
 	parse_subscription_options(pstate, stmt->options, supported_opts, &opts);
 
 	/*
@@ -710,6 +724,8 @@ CreateSubscription(ParseState *pstate, CreateSubscriptionStmt *stmt,
 	values[Anum_pg_subscription_subpasswordrequired - 1] = BoolGetDatum(opts.passwordrequired);
 	values[Anum_pg_subscription_subrunasowner - 1] = BoolGetDatum(opts.runasowner);
 	values[Anum_pg_subscription_subfailover - 1] = BoolGetDatum(opts.failover);
+	values[Anum_pg_subscription_subdetectconflict - 1] =
+		BoolGetDatum(opts.detectconflict);
 	values[Anum_pg_subscription_subconninfo - 1] =
 		CStringGetTextDatum(conninfo);
 	if (opts.slot_name)
@@ -1146,7 +1162,7 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 								  SUBOPT_STREAMING | SUBOPT_DISABLE_ON_ERR |
 								  SUBOPT_PASSWORD_REQUIRED |
 								  SUBOPT_RUN_AS_OWNER | SUBOPT_FAILOVER |
-								  SUBOPT_ORIGIN);
+								  SUBOPT_DETECT_CONFLICT | SUBOPT_ORIGIN);
 
 				parse_subscription_options(pstate, stmt->options,
 										   supported_opts, &opts);
@@ -1256,6 +1272,13 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 					replaces[Anum_pg_subscription_subfailover - 1] = true;
 				}
 
+				if (IsSet(opts.specified_opts, SUBOPT_DETECT_CONFLICT))
+				{
+					values[Anum_pg_subscription_subdetectconflict - 1] =
+						BoolGetDatum(opts.detectconflict);
+					replaces[Anum_pg_subscription_subdetectconflict - 1] = true;
+				}
+
 				if (IsSet(opts.specified_opts, SUBOPT_ORIGIN))
 				{
 					values[Anum_pg_subscription_suborigin - 1] =
diff --git a/src/backend/executor/execIndexing.c b/src/backend/executor/execIndexing.c
index 9f05b3654c..2a2d188b19 100644
--- a/src/backend/executor/execIndexing.c
+++ b/src/backend/executor/execIndexing.c
@@ -207,8 +207,9 @@ ExecOpenIndices(ResultRelInfo *resultRelInfo, bool speculative)
 		ii = BuildIndexInfo(indexDesc);
 
 		/*
-		 * If the indexes are to be used for speculative insertion, add extra
-		 * information required by unique index entries.
+		 * If the indexes are to be used for speculative insertion or conflict
+		 * detection in logical replication, add extra information required by
+		 * unique index entries.
 		 */
 		if (speculative && ii->ii_Unique)
 			BuildSpeculativeIndexInfo(indexDesc, ii);
@@ -521,6 +522,11 @@ ExecInsertIndexTuples(ResultRelInfo *resultRelInfo,
  *		possible that a conflicting tuple is inserted immediately
  *		after this returns.  But this can be used for a pre-check
  *		before insertion.
+ *
+ *		If the 'slot' holds a tuple with valid tid, this tuple will
+ *		be ingored when checking conflict. This can help in scenarios
+ *		where we want to re-check for conflicts after inserting a
+ *		tuple.
  * ----------------------------------------------------------------
  */
 bool
@@ -536,11 +542,9 @@ ExecCheckIndexConstraints(ResultRelInfo *resultRelInfo, TupleTableSlot *slot,
 	ExprContext *econtext;
 	Datum		values[INDEX_MAX_KEYS];
 	bool		isnull[INDEX_MAX_KEYS];
-	ItemPointerData invalidItemPtr;
 	bool		checkedIndex = false;
 
 	ItemPointerSetInvalid(conflictTid);
-	ItemPointerSetInvalid(&invalidItemPtr);
 
 	/*
 	 * Get information from the result relation info structure.
@@ -629,7 +633,7 @@ ExecCheckIndexConstraints(ResultRelInfo *resultRelInfo, TupleTableSlot *slot,
 
 		satisfiesConstraint =
 			check_exclusion_or_unique_constraint(heapRelation, indexRelation,
-												 indexInfo, &invalidItemPtr,
+												 indexInfo, &slot->tts_tid,
 												 values, isnull, estate, false,
 												 CEOUC_WAIT, true,
 												 conflictTid);
diff --git a/src/backend/executor/execReplication.c b/src/backend/executor/execReplication.c
index d0a89cd577..f01927a933 100644
--- a/src/backend/executor/execReplication.c
+++ b/src/backend/executor/execReplication.c
@@ -23,6 +23,7 @@
 #include "commands/trigger.h"
 #include "executor/executor.h"
 #include "executor/nodeModifyTable.h"
+#include "replication/conflict.h"
 #include "replication/logicalrelation.h"
 #include "storage/lmgr.h"
 #include "utils/builtins.h"
@@ -480,6 +481,83 @@ retry:
 	return found;
 }
 
+/*
+ * Find the tuple that violates the passed in unique index constraint
+ * (conflictindex).
+ *
+ * Return false if there is no conflict and *conflictslot is set to NULL.
+ * Otherwise return true, and the conflicting tuple is locked and returned
+ * in *conflictslot.
+ */
+static bool
+FindConflictTuple(ResultRelInfo *resultRelInfo, EState *estate,
+				  Oid conflictindex, TupleTableSlot *slot,
+				  TupleTableSlot **conflictslot)
+{
+	Relation	rel = resultRelInfo->ri_RelationDesc;
+	ItemPointerData conflictTid;
+	TM_FailureData tmfd;
+	TM_Result	res;
+
+	*conflictslot = NULL;
+
+retry:
+	if (ExecCheckIndexConstraints(resultRelInfo, slot, estate,
+								  &conflictTid, list_make1_oid(conflictindex)))
+	{
+		if (*conflictslot)
+			ExecDropSingleTupleTableSlot(*conflictslot);
+
+		*conflictslot = NULL;
+		return false;
+	}
+
+	*conflictslot = table_slot_create(rel, NULL);
+
+	PushActiveSnapshot(GetLatestSnapshot());
+
+	res = table_tuple_lock(rel, &conflictTid, GetLatestSnapshot(),
+						   *conflictslot,
+						   GetCurrentCommandId(false),
+						   LockTupleShare,
+						   LockWaitBlock,
+						   0 /* don't follow updates */ ,
+						   &tmfd);
+
+	PopActiveSnapshot();
+
+	switch (res)
+	{
+		case TM_Ok:
+			break;
+		case TM_Updated:
+			/* XXX: Improve handling here */
+			if (ItemPointerIndicatesMovedPartitions(&tmfd.ctid))
+				ereport(LOG,
+						(errcode(ERRCODE_T_R_SERIALIZATION_FAILURE),
+						 errmsg("tuple to be locked was already moved to another partition due to concurrent update, retrying")));
+			else
+				ereport(LOG,
+						(errcode(ERRCODE_T_R_SERIALIZATION_FAILURE),
+						 errmsg("concurrent update, retrying")));
+			goto retry;
+		case TM_Deleted:
+			/* XXX: Improve handling here */
+			ereport(LOG,
+					(errcode(ERRCODE_T_R_SERIALIZATION_FAILURE),
+					 errmsg("concurrent delete, retrying")));
+			goto retry;
+		case TM_Invisible:
+			elog(ERROR, "attempted to lock invisible tuple");
+			break;
+		default:
+			elog(ERROR, "unexpected table_tuple_lock status: %u", res);
+			break;
+	}
+
+	return true;
+}
+
 /*
  * Insert tuple represented in the slot to the relation, update the indexes,
  * and execute any constraints and per-row triggers.
@@ -509,6 +587,8 @@ ExecSimpleRelationInsert(ResultRelInfo *resultRelInfo,
 	if (!skip_tuple)
 	{
 		List	   *recheckIndexes = NIL;
+		List	   *conflictindexes;
+		bool		conflict = false;
 
 		/* Compute stored generated columns */
 		if (rel->rd_att->constr &&
@@ -525,10 +605,43 @@ ExecSimpleRelationInsert(ResultRelInfo *resultRelInfo,
 		/* OK, store the tuple and create index entries for it */
 		simple_table_tuple_insert(resultRelInfo->ri_RelationDesc, slot);
 
+		conflictindexes = resultRelInfo->ri_onConflictArbiterIndexes;
+
 		if (resultRelInfo->ri_NumIndices > 0)
 			recheckIndexes = ExecInsertIndexTuples(resultRelInfo,
-												   slot, estate, false, false,
-												   NULL, NIL, false);
+												   slot, estate, false,
+												   conflictindexes, &conflict,
+												   conflictindexes, false);
+
+		/* Re-check all the unique indexes for potential conflicts */
+		foreach_oid(uniqueidx, (conflict ? conflictindexes : NIL))
+		{
+			TupleTableSlot *conflictslot;
+
+			/*
+			 * Reports the conflict if any.
+			 *
+			 * Here, we attempt to find the conflict tuple. This operation may
+			 * seem redundant with the unique violation check of indexam, but
+			 * since we perform this only when we are detecting conflict in
+			 * logical replication and encountering potential conflicts with
+			 * any unique index constraints (which should not be frequent), so
+			 * it's ok. Moreover, upon detecting a conflict, we will report an
+			 * ERROR and restart the logical replication, so the additional
+			 * cost of finding the tuple should be acceptable in this case.
+			 */
+			if (list_member_oid(recheckIndexes, uniqueidx) &&
+				FindConflictTuple(resultRelInfo, estate, uniqueidx, slot, &conflictslot))
+			{
+				RepOriginId origin;
+				TimestampTz committs;
+				TransactionId xmin;
+
+				GetTupleCommitTs(conflictslot, &xmin, &origin, &committs);
+				ReportApplyConflict(ERROR, CT_INSERT_EXISTS, rel, uniqueidx,
+									xmin, origin, committs, conflictslot);
+			}
+		}
 
 		/* AFTER ROW INSERT Triggers */
 		ExecARInsertTriggers(estate, resultRelInfo, slot,
diff --git a/src/backend/replication/logical/Makefile b/src/backend/replication/logical/Makefile
index ba03eeff1c..1e08bbbd4e 100644
--- a/src/backend/replication/logical/Makefile
+++ b/src/backend/replication/logical/Makefile
@@ -16,6 +16,7 @@ override CPPFLAGS := -I$(srcdir) $(CPPFLAGS)
 
 OBJS = \
 	applyparallelworker.o \
+	conflict.o \
 	decode.o \
 	launcher.o \
 	logical.o \
diff --git a/src/backend/replication/logical/conflict.c b/src/backend/replication/logical/conflict.c
new file mode 100644
index 0000000000..f24f048054
--- /dev/null
+++ b/src/backend/replication/logical/conflict.c
@@ -0,0 +1,187 @@
+/*-------------------------------------------------------------------------
+ * conflict.c
+ *	   Functionality for detecting and logging conflicts.
+ *
+ * Copyright (c) 2024, PostgreSQL Global Development Group
+ *
+ * IDENTIFICATION
+ *	  src/backend/replication/logical/conflict.c
+ *
+ * This file contains the code for detecting and logging conflicts on
+ * the subscriber during logical replication.
+ *-------------------------------------------------------------------------
+ */
+
+#include "postgres.h"
+
+#include "access/commit_ts.h"
+#include "replication/conflict.h"
+#include "replication/origin.h"
+#include "utils/lsyscache.h"
+#include "utils/rel.h"
+
+const char *const ConflictTypeNames[] = {
+	[CT_INSERT_EXISTS] = "insert_exists",
+	[CT_UPDATE_DIFFER] = "update_differ",
+	[CT_UPDATE_MISSING] = "update_missing",
+	[CT_DELETE_MISSING] = "delete_missing"
+};
+
+static char *build_index_value_desc(Oid indexoid, TupleTableSlot *conflictslot);
+static int	errdetail_apply_conflict(ConflictType type, Oid conflictidx,
+									 TransactionId localxmin,
+									 RepOriginId localorigin,
+									 TimestampTz localts,
+									 TupleTableSlot *conflictslot);
+
+/*
+ * Get the xmin and commit timestamp data (origin and timestamp) associated
+ * with the provided local tuple.
+ *
+ * Return true if the commit timestamp data was found, false otherwise.
+ */
+bool
+GetTupleCommitTs(TupleTableSlot *localslot, TransactionId *xmin,
+				 RepOriginId *localorigin, TimestampTz *localts)
+{
+	Datum		xminDatum;
+	bool		isnull;
+
+	xminDatum = slot_getsysattr(localslot, MinTransactionIdAttributeNumber,
+								&isnull);
+	*xmin = DatumGetTransactionId(xminDatum);
+	Assert(!isnull);
+
+	/*
+	 * The commit timestamp data is not available if track_commit_timestamp is
+	 * disabled.
+	 */
+	if (!track_commit_timestamp)
+	{
+		*localorigin = InvalidRepOriginId;
+		*localts = 0;
+		return false;
+	}
+
+	return TransactionIdGetCommitTsData(*xmin, localts, localorigin);
+}
+
+/*
+ * Report a conflict when applying remote changes.
+ */
+void
+ReportApplyConflict(int elevel, ConflictType type, Relation localrel,
+					Oid conflictidx, TransactionId localxmin,
+					RepOriginId localorigin, TimestampTz localts,
+					TupleTableSlot *conflictslot)
+{
+	ereport(elevel,
+			errcode(ERRCODE_INTEGRITY_CONSTRAINT_VIOLATION),
+			errmsg("conflict %s detected on relation \"%s.%s\"",
+				   ConflictTypeNames[type],
+				   get_namespace_name(RelationGetNamespace(localrel)),
+				   RelationGetRelationName(localrel)),
+			errdetail_apply_conflict(type, conflictidx, localxmin, localorigin,
+									 localts, conflictslot));
+}
+
+/*
+ * Find all unique indexes to check for a conflict and store them into
+ * ResultRelInfo.
+ */
+void
+InitConflictIndexes(ResultRelInfo *relInfo)
+{
+	List	   *uniqueIndexes = NIL;
+
+	for (int i = 0; i < relInfo->ri_NumIndices; i++)
+	{
+		Relation	indexRelation = relInfo->ri_IndexRelationDescs[i];
+
+		if (indexRelation == NULL)
+			continue;
+
+		/* Detect conflict only for unique indexes */
+		if (!relInfo->ri_IndexRelationInfo[i]->ii_Unique)
+			continue;
+
+		/* Don't support conflict detection for deferrable index */
+		if (!indexRelation->rd_index->indimmediate)
+			continue;
+
+		uniqueIndexes = lappend_oid(uniqueIndexes,
+									RelationGetRelid(indexRelation));
+	}
+
+	relInfo->ri_onConflictArbiterIndexes = uniqueIndexes;
+}
+
+/*
+ * Add an errdetail() line showing conflict detail.
+ */
+static int
+errdetail_apply_conflict(ConflictType type, Oid conflictidx,
+						 TransactionId localxmin, RepOriginId localorigin,
+						 TimestampTz localts, TupleTableSlot *conflictslot)
+{
+	switch (type)
+	{
+		case CT_INSERT_EXISTS:
+			{
+				/*
+				 * Bulid the index value string. If the return value is NULL,
+				 * it indicates that the current user lacks permissions to
+				 * view all the columns involved.
+				 */
+				char	   *index_value = build_index_value_desc(conflictidx,
+																 conflictslot);
+
+				if (index_value && localts)
+					return errdetail("Key %s already exists in unique index \"%s\", which was modified by origin %u in transaction %u at %s.",
+									 index_value, get_rel_name(conflictidx), localorigin,
+									 localxmin, timestamptz_to_str(localts));
+				else if (index_value && !localts)
+					return errdetail("Key %s already exists in unique index \"%s\", which was modified in transaction %u.",
+									 index_value, get_rel_name(conflictidx), localxmin);
+				else
+					return errdetail("Key already exists in unique index \"%s\".",
+									 get_rel_name(conflictidx));
+			}
+		case CT_UPDATE_DIFFER:
+			return errdetail("Updating a row that was modified by a different origin %u in transaction %u at %s.",
+							 localorigin, localxmin, timestamptz_to_str(localts));
+		case CT_UPDATE_MISSING:
+			return errdetail("Did not find the row to be updated.");
+		case CT_DELETE_MISSING:
+			return errdetail("Did not find the row to be deleted.");
+	}
+
+	return 0;					/* silence compiler warning */
+}
+
+/*
+ * Helper functions to construct a string describing the contents of an index
+ * entry. See BuildIndexValueDescription for details.
+ */
+static char *
+build_index_value_desc(Oid indexoid, TupleTableSlot *conflictslot)
+{
+	char	   *conflict_row;
+	Relation	indexDesc;
+
+	if (!conflictslot)
+		return NULL;
+
+	/* Assume the index has been locked */
+	indexDesc = index_open(indexoid, NoLock);
+
+	slot_getallattrs(conflictslot);
+
+	conflict_row = BuildIndexValueDescription(indexDesc,
+											  conflictslot->tts_values,
+											  conflictslot->tts_isnull);
+
+	index_close(indexDesc, NoLock);
+
+	return conflict_row;
+}
diff --git a/src/backend/replication/logical/meson.build b/src/backend/replication/logical/meson.build
index 3dec36a6de..3d36249d8a 100644
--- a/src/backend/replication/logical/meson.build
+++ b/src/backend/replication/logical/meson.build
@@ -2,6 +2,7 @@
 
 backend_sources += files(
   'applyparallelworker.c',
+  'conflict.c',
   'decode.c',
   'launcher.c',
   'logical.c',
diff --git a/src/backend/replication/logical/worker.c b/src/backend/replication/logical/worker.c
index 3b285894db..06ee46886b 100644
--- a/src/backend/replication/logical/worker.c
+++ b/src/backend/replication/logical/worker.c
@@ -167,6 +167,7 @@
 #include "postmaster/bgworker.h"
 #include "postmaster/interrupt.h"
 #include "postmaster/walwriter.h"
+#include "replication/conflict.h"
 #include "replication/logicallauncher.h"
 #include "replication/logicalproto.h"
 #include "replication/logicalrelation.h"
@@ -2461,7 +2462,10 @@ apply_handle_insert_internal(ApplyExecutionData *edata,
 	EState	   *estate = edata->estate;
 
 	/* We must open indexes here. */
-	ExecOpenIndices(relinfo, false);
+	ExecOpenIndices(relinfo, MySubscription->detectconflict);
+
+	if (MySubscription->detectconflict)
+		InitConflictIndexes(relinfo);
 
 	/* Do the insert. */
 	TargetPrivilegesCheck(relinfo->ri_RelationDesc, ACL_INSERT);
@@ -2664,6 +2668,20 @@ apply_handle_update_internal(ApplyExecutionData *edata,
 	 */
 	if (found)
 	{
+		RepOriginId localorigin;
+		TransactionId localxmin;
+		TimestampTz localts;
+
+		/*
+		 * If conflict detection is enabled, check whether the local tuple was
+		 * modified by a different origin. If detected, report the conflict.
+		 */
+		if (MySubscription->detectconflict &&
+			GetTupleCommitTs(localslot, &localxmin, &localorigin, &localts) &&
+			localorigin != replorigin_session_origin)
+			ReportApplyConflict(LOG, CT_UPDATE_DIFFER, localrel, InvalidOid,
+								localxmin, localorigin, localts, NULL);
+
 		/* Process and store remote tuple in the slot */
 		oldctx = MemoryContextSwitchTo(GetPerTupleMemoryContext(estate));
 		slot_modify_data(remoteslot, localslot, relmapentry, newtup);
@@ -2681,13 +2699,10 @@ apply_handle_update_internal(ApplyExecutionData *edata,
 		/*
 		 * The tuple to be updated could not be found.  Do nothing except for
 		 * emitting a log message.
-		 *
-		 * XXX should this be promoted to ereport(LOG) perhaps?
 		 */
-		elog(DEBUG1,
-			 "logical replication did not find row to be updated "
-			 "in replication target relation \"%s\"",
-			 RelationGetRelationName(localrel));
+		if (MySubscription->detectconflict)
+			ReportApplyConflict(LOG, CT_UPDATE_MISSING, localrel, InvalidOid,
+								InvalidTransactionId, InvalidRepOriginId, 0, NULL);
 	}
 
 	/* Cleanup. */
@@ -2821,13 +2836,10 @@ apply_handle_delete_internal(ApplyExecutionData *edata,
 		/*
 		 * The tuple to be deleted could not be found.  Do nothing except for
 		 * emitting a log message.
-		 *
-		 * XXX should this be promoted to ereport(LOG) perhaps?
 		 */
-		elog(DEBUG1,
-			 "logical replication did not find row to be deleted "
-			 "in replication target relation \"%s\"",
-			 RelationGetRelationName(localrel));
+		if (MySubscription->detectconflict)
+			ReportApplyConflict(LOG, CT_DELETE_MISSING, localrel, InvalidOid,
+								InvalidTransactionId, InvalidRepOriginId, 0, NULL);
 	}
 
 	/* Cleanup. */
@@ -3005,13 +3017,13 @@ apply_handle_tuple_routing(ApplyExecutionData *edata,
 					/*
 					 * The tuple to be updated could not be found.  Do nothing
 					 * except for emitting a log message.
-					 *
-					 * XXX should this be promoted to ereport(LOG) perhaps?
 					 */
-					elog(DEBUG1,
-						 "logical replication did not find row to be updated "
-						 "in replication target relation's partition \"%s\"",
-						 RelationGetRelationName(partrel));
+					if (MySubscription->detectconflict)
+						ReportApplyConflict(LOG, CT_UPDATE_MISSING,
+											partrel, InvalidOid,
+											InvalidTransactionId,
+											InvalidRepOriginId, 0, NULL);
+
 					return;
 				}
 
diff --git a/src/bin/pg_dump/pg_dump.c b/src/bin/pg_dump/pg_dump.c
index 5426f1177c..e0ecadd081 100644
--- a/src/bin/pg_dump/pg_dump.c
+++ b/src/bin/pg_dump/pg_dump.c
@@ -4754,6 +4754,7 @@ getSubscriptions(Archive *fout)
 	int			i_suboriginremotelsn;
 	int			i_subenabled;
 	int			i_subfailover;
+	int			i_subdetectconflict;
 	int			i,
 				ntups;
 
@@ -4826,11 +4827,17 @@ getSubscriptions(Archive *fout)
 
 	if (fout->remoteVersion >= 170000)
 		appendPQExpBufferStr(query,
-							 " s.subfailover\n");
+							 " s.subfailover,\n");
 	else
 		appendPQExpBuffer(query,
-						  " false AS subfailover\n");
+						  " false AS subfailover,\n");
 
+	if (fout->remoteVersion >= 170000)
+		appendPQExpBufferStr(query,
+							 " s.subdetectconflict\n");
+	else
+		appendPQExpBuffer(query,
+						  " false AS subdetectconflict\n");
 	appendPQExpBufferStr(query,
 						 "FROM pg_subscription s\n");
 
@@ -4869,6 +4876,7 @@ getSubscriptions(Archive *fout)
 	i_suboriginremotelsn = PQfnumber(res, "suboriginremotelsn");
 	i_subenabled = PQfnumber(res, "subenabled");
 	i_subfailover = PQfnumber(res, "subfailover");
+	i_subdetectconflict = PQfnumber(res, "subdetectconflict");
 
 	subinfo = pg_malloc(ntups * sizeof(SubscriptionInfo));
 
@@ -4915,6 +4923,8 @@ getSubscriptions(Archive *fout)
 			pg_strdup(PQgetvalue(res, i, i_subenabled));
 		subinfo[i].subfailover =
 			pg_strdup(PQgetvalue(res, i, i_subfailover));
+		subinfo[i].subdetectconflict =
+			pg_strdup(PQgetvalue(res, i, i_subdetectconflict));
 
 		/* Decide whether we want to dump it */
 		selectDumpableObject(&(subinfo[i].dobj), fout);
@@ -5155,6 +5165,9 @@ dumpSubscription(Archive *fout, const SubscriptionInfo *subinfo)
 	if (strcmp(subinfo->subfailover, "t") == 0)
 		appendPQExpBufferStr(query, ", failover = true");
 
+	if (strcmp(subinfo->subdetectconflict, "t") == 0)
+		appendPQExpBufferStr(query, ", detect_conflict = true");
+
 	if (strcmp(subinfo->subsynccommit, "off") != 0)
 		appendPQExpBuffer(query, ", synchronous_commit = %s", fmtId(subinfo->subsynccommit));
 
diff --git a/src/bin/pg_dump/pg_dump.h b/src/bin/pg_dump/pg_dump.h
index 4b2e5870a9..bbd7cbeff6 100644
--- a/src/bin/pg_dump/pg_dump.h
+++ b/src/bin/pg_dump/pg_dump.h
@@ -671,6 +671,7 @@ typedef struct _SubscriptionInfo
 	char	   *suborigin;
 	char	   *suboriginremotelsn;
 	char	   *subfailover;
+	char	   *subdetectconflict;
 } SubscriptionInfo;
 
 /*
diff --git a/src/bin/psql/describe.c b/src/bin/psql/describe.c
index 7c9a1f234c..fef1ad0d70 100644
--- a/src/bin/psql/describe.c
+++ b/src/bin/psql/describe.c
@@ -6539,7 +6539,7 @@ describeSubscriptions(const char *pattern, bool verbose)
 	printQueryOpt myopt = pset.popt;
 	static const bool translate_columns[] = {false, false, false, false,
 		false, false, false, false, false, false, false, false, false, false,
-	false};
+	false, false};
 
 	if (pset.sversion < 100000)
 	{
@@ -6607,6 +6607,10 @@ describeSubscriptions(const char *pattern, bool verbose)
 			appendPQExpBuffer(&buf,
 							  ", subfailover AS \"%s\"\n",
 							  gettext_noop("Failover"));
+		if (pset.sversion >= 170000)
+			appendPQExpBuffer(&buf,
+							  ", subdetectconflict AS \"%s\"\n",
+							  gettext_noop("Detect conflict"));
 
 		appendPQExpBuffer(&buf,
 						  ",  subsynccommit AS \"%s\"\n"
diff --git a/src/bin/psql/tab-complete.c b/src/bin/psql/tab-complete.c
index d453e224d9..219fac7e71 100644
--- a/src/bin/psql/tab-complete.c
+++ b/src/bin/psql/tab-complete.c
@@ -1946,9 +1946,10 @@ psql_completion(const char *text, int start, int end)
 		COMPLETE_WITH("(", "PUBLICATION");
 	/* ALTER SUBSCRIPTION <name> SET ( */
 	else if (HeadMatches("ALTER", "SUBSCRIPTION", MatchAny) && TailMatches("SET", "("))
-		COMPLETE_WITH("binary", "disable_on_error", "failover", "origin",
-					  "password_required", "run_as_owner", "slot_name",
-					  "streaming", "synchronous_commit");
+		COMPLETE_WITH("binary", "detect_conflict", "disable_on_error",
+					  "failover", "origin", "password_required",
+					  "run_as_owner", "slot_name", "streaming",
+					  "synchronous_commit");
 	/* ALTER SUBSCRIPTION <name> SKIP ( */
 	else if (HeadMatches("ALTER", "SUBSCRIPTION", MatchAny) && TailMatches("SKIP", "("))
 		COMPLETE_WITH("lsn");
@@ -3363,9 +3364,10 @@ psql_completion(const char *text, int start, int end)
 	/* Complete "CREATE SUBSCRIPTION <name> ...  WITH ( <opt>" */
 	else if (HeadMatches("CREATE", "SUBSCRIPTION") && TailMatches("WITH", "("))
 		COMPLETE_WITH("binary", "connect", "copy_data", "create_slot",
-					  "disable_on_error", "enabled", "failover", "origin",
-					  "password_required", "run_as_owner", "slot_name",
-					  "streaming", "synchronous_commit", "two_phase");
+					  "detect_conflict", "disable_on_error", "enabled",
+					  "failover", "origin", "password_required",
+					  "run_as_owner", "slot_name", "streaming",
+					  "synchronous_commit", "two_phase");
 
 /* CREATE TRIGGER --- is allowed inside CREATE SCHEMA, so use TailMatches */
 
diff --git a/src/include/catalog/pg_subscription.h b/src/include/catalog/pg_subscription.h
index 0aa14ec4a2..17daf11dc7 100644
--- a/src/include/catalog/pg_subscription.h
+++ b/src/include/catalog/pg_subscription.h
@@ -98,6 +98,9 @@ CATALOG(pg_subscription,6100,SubscriptionRelationId) BKI_SHARED_RELATION BKI_ROW
 								 * slots) in the upstream database are enabled
 								 * to be synchronized to the standbys. */
 
+	bool		subdetectconflict;	/* True if replication should perform
+									 * conflict detection */
+
 #ifdef CATALOG_VARLEN			/* variable-length fields start here */
 	/* Connection string to the publisher */
 	text		subconninfo BKI_FORCE_NOT_NULL;
@@ -151,6 +154,7 @@ typedef struct Subscription
 								 * (i.e. the main slot and the table sync
 								 * slots) in the upstream database are enabled
 								 * to be synchronized to the standbys. */
+	bool		detectconflict; /* True if conflict detection is enabled */
 	char	   *conninfo;		/* Connection string to the publisher */
 	char	   *slotname;		/* Name of the replication slot */
 	char	   *synccommit;		/* Synchronous commit setting for worker */
diff --git a/src/include/replication/conflict.h b/src/include/replication/conflict.h
new file mode 100644
index 0000000000..0bc9db991e
--- /dev/null
+++ b/src/include/replication/conflict.h
@@ -0,0 +1,44 @@
+/*-------------------------------------------------------------------------
+ * conflict.h
+ *	   Exports for conflict detection and log
+ *
+ * Copyright (c) 2012-2024, PostgreSQL Global Development Group
+ *
+ *-------------------------------------------------------------------------
+ */
+#ifndef CONFLICT_H
+#define CONFLICT_H
+
+#include "access/xlogdefs.h"
+#include "executor/tuptable.h"
+#include "nodes/execnodes.h"
+#include "utils/relcache.h"
+#include "utils/timestamp.h"
+
+/*
+ * Conflict types that could be encountered when applying remote changes.
+ */
+typedef enum
+{
+	/* The row to be inserted violates unique constraint */
+	CT_INSERT_EXISTS,
+
+	/* The row to be updated was modified by a different origin */
+	CT_UPDATE_DIFFER,
+
+	/* The row to be updated is missing */
+	CT_UPDATE_MISSING,
+
+	/* The row to be deleted is missing */
+	CT_DELETE_MISSING,
+} ConflictType;
+
+extern bool GetTupleCommitTs(TupleTableSlot *localslot, TransactionId *xmin,
+							 RepOriginId *localorigin, TimestampTz *localts);
+extern void ReportApplyConflict(int elevel, ConflictType type,
+								Relation localrel, Oid conflictidx,
+								TransactionId localxmin, RepOriginId localorigin,
+								TimestampTz localts, TupleTableSlot *conflictslot);
+extern void InitConflictIndexes(ResultRelInfo *relInfo);
+
+#endif
diff --git a/src/test/regress/expected/subscription.out b/src/test/regress/expected/subscription.out
index 0f2a25cdc1..a8b0086dd9 100644
--- a/src/test/regress/expected/subscription.out
+++ b/src/test/regress/expected/subscription.out
@@ -116,18 +116,18 @@ CREATE SUBSCRIPTION regress_testsub4 CONNECTION 'dbname=regress_doesnotexist' PU
 WARNING:  subscription was created, but is not connected
 HINT:  To initiate replication, you must manually create the replication slot, enable the subscription, and refresh the subscription.
 \dRs+ regress_testsub4
-                                                                                                                 List of subscriptions
-       Name       |           Owner           | Enabled | Publication | Binary | Streaming | Two-phase commit | Disable on error | Origin | Password required | Run as owner? | Failover | Synchronous commit |          Conninfo           | Skip LSN 
-------------------+---------------------------+---------+-------------+--------+-----------+------------------+------------------+--------+-------------------+---------------+----------+--------------------+-----------------------------+----------
- regress_testsub4 | regress_subscription_user | f       | {testpub}   | f      | off       | d                | f                | none   | t                 | f             | f        | off                | dbname=regress_doesnotexist | 0/0
+                                                                                                                          List of subscriptions
+       Name       |           Owner           | Enabled | Publication | Binary | Streaming | Two-phase commit | Disable on error | Origin | Password required | Run as owner? | Failover | Detect conflict | Synchronous commit |          Conninfo           | Skip LSN 
+------------------+---------------------------+---------+-------------+--------+-----------+------------------+------------------+--------+-------------------+---------------+----------+-----------------+--------------------+-----------------------------+----------
+ regress_testsub4 | regress_subscription_user | f       | {testpub}   | f      | off       | d                | f                | none   | t                 | f             | f        | f               | off                | dbname=regress_doesnotexist | 0/0
 (1 row)
 
 ALTER SUBSCRIPTION regress_testsub4 SET (origin = any);
 \dRs+ regress_testsub4
-                                                                                                                 List of subscriptions
-       Name       |           Owner           | Enabled | Publication | Binary | Streaming | Two-phase commit | Disable on error | Origin | Password required | Run as owner? | Failover | Synchronous commit |          Conninfo           | Skip LSN 
-------------------+---------------------------+---------+-------------+--------+-----------+------------------+------------------+--------+-------------------+---------------+----------+--------------------+-----------------------------+----------
- regress_testsub4 | regress_subscription_user | f       | {testpub}   | f      | off       | d                | f                | any    | t                 | f             | f        | off                | dbname=regress_doesnotexist | 0/0
+                                                                                                                          List of subscriptions
+       Name       |           Owner           | Enabled | Publication | Binary | Streaming | Two-phase commit | Disable on error | Origin | Password required | Run as owner? | Failover | Detect conflict | Synchronous commit |          Conninfo           | Skip LSN 
+------------------+---------------------------+---------+-------------+--------+-----------+------------------+------------------+--------+-------------------+---------------+----------+-----------------+--------------------+-----------------------------+----------
+ regress_testsub4 | regress_subscription_user | f       | {testpub}   | f      | off       | d                | f                | any    | t                 | f             | f        | f               | off                | dbname=regress_doesnotexist | 0/0
 (1 row)
 
 DROP SUBSCRIPTION regress_testsub3;
@@ -145,10 +145,10 @@ ALTER SUBSCRIPTION regress_testsub CONNECTION 'foobar';
 ERROR:  invalid connection string syntax: missing "=" after "foobar" in connection info string
 
 \dRs+
-                                                                                                                List of subscriptions
-      Name       |           Owner           | Enabled | Publication | Binary | Streaming | Two-phase commit | Disable on error | Origin | Password required | Run as owner? | Failover | Synchronous commit |          Conninfo           | Skip LSN 
------------------+---------------------------+---------+-------------+--------+-----------+------------------+------------------+--------+-------------------+---------------+----------+--------------------+-----------------------------+----------
- regress_testsub | regress_subscription_user | f       | {testpub}   | f      | off       | d                | f                | any    | t                 | f             | f        | off                | dbname=regress_doesnotexist | 0/0
+                                                                                                                         List of subscriptions
+      Name       |           Owner           | Enabled | Publication | Binary | Streaming | Two-phase commit | Disable on error | Origin | Password required | Run as owner? | Failover | Detect conflict | Synchronous commit |          Conninfo           | Skip LSN 
+-----------------+---------------------------+---------+-------------+--------+-----------+------------------+------------------+--------+-------------------+---------------+----------+-----------------+--------------------+-----------------------------+----------
+ regress_testsub | regress_subscription_user | f       | {testpub}   | f      | off       | d                | f                | any    | t                 | f             | f        | f               | off                | dbname=regress_doesnotexist | 0/0
 (1 row)
 
 ALTER SUBSCRIPTION regress_testsub SET PUBLICATION testpub2, testpub3 WITH (refresh = false);
@@ -157,10 +157,10 @@ ALTER SUBSCRIPTION regress_testsub SET (slot_name = 'newname');
 ALTER SUBSCRIPTION regress_testsub SET (password_required = false);
 ALTER SUBSCRIPTION regress_testsub SET (run_as_owner = true);
 \dRs+
-                                                                                                                     List of subscriptions
-      Name       |           Owner           | Enabled |     Publication     | Binary | Streaming | Two-phase commit | Disable on error | Origin | Password required | Run as owner? | Failover | Synchronous commit |           Conninfo           | Skip LSN 
------------------+---------------------------+---------+---------------------+--------+-----------+------------------+------------------+--------+-------------------+---------------+----------+--------------------+------------------------------+----------
- regress_testsub | regress_subscription_user | f       | {testpub2,testpub3} | f      | off       | d                | f                | any    | f                 | t             | f        | off                | dbname=regress_doesnotexist2 | 0/0
+                                                                                                                              List of subscriptions
+      Name       |           Owner           | Enabled |     Publication     | Binary | Streaming | Two-phase commit | Disable on error | Origin | Password required | Run as owner? | Failover | Detect conflict | Synchronous commit |           Conninfo           | Skip LSN 
+-----------------+---------------------------+---------+---------------------+--------+-----------+------------------+------------------+--------+-------------------+---------------+----------+-----------------+--------------------+------------------------------+----------
+ regress_testsub | regress_subscription_user | f       | {testpub2,testpub3} | f      | off       | d                | f                | any    | f                 | t             | f        | f               | off                | dbname=regress_doesnotexist2 | 0/0
 (1 row)
 
 ALTER SUBSCRIPTION regress_testsub SET (password_required = true);
@@ -176,10 +176,10 @@ ERROR:  unrecognized subscription parameter: "create_slot"
 -- ok
 ALTER SUBSCRIPTION regress_testsub SKIP (lsn = '0/12345');
 \dRs+
-                                                                                                                     List of subscriptions
-      Name       |           Owner           | Enabled |     Publication     | Binary | Streaming | Two-phase commit | Disable on error | Origin | Password required | Run as owner? | Failover | Synchronous commit |           Conninfo           | Skip LSN 
------------------+---------------------------+---------+---------------------+--------+-----------+------------------+------------------+--------+-------------------+---------------+----------+--------------------+------------------------------+----------
- regress_testsub | regress_subscription_user | f       | {testpub2,testpub3} | f      | off       | d                | f                | any    | t                 | f             | f        | off                | dbname=regress_doesnotexist2 | 0/12345
+                                                                                                                              List of subscriptions
+      Name       |           Owner           | Enabled |     Publication     | Binary | Streaming | Two-phase commit | Disable on error | Origin | Password required | Run as owner? | Failover | Detect conflict | Synchronous commit |           Conninfo           | Skip LSN 
+-----------------+---------------------------+---------+---------------------+--------+-----------+------------------+------------------+--------+-------------------+---------------+----------+-----------------+--------------------+------------------------------+----------
+ regress_testsub | regress_subscription_user | f       | {testpub2,testpub3} | f      | off       | d                | f                | any    | t                 | f             | f        | f               | off                | dbname=regress_doesnotexist2 | 0/12345
 (1 row)
 
 -- ok - with lsn = NONE
@@ -188,10 +188,10 @@ ALTER SUBSCRIPTION regress_testsub SKIP (lsn = NONE);
 ALTER SUBSCRIPTION regress_testsub SKIP (lsn = '0/0');
 ERROR:  invalid WAL location (LSN): 0/0
 \dRs+
-                                                                                                                     List of subscriptions
-      Name       |           Owner           | Enabled |     Publication     | Binary | Streaming | Two-phase commit | Disable on error | Origin | Password required | Run as owner? | Failover | Synchronous commit |           Conninfo           | Skip LSN 
------------------+---------------------------+---------+---------------------+--------+-----------+------------------+------------------+--------+-------------------+---------------+----------+--------------------+------------------------------+----------
- regress_testsub | regress_subscription_user | f       | {testpub2,testpub3} | f      | off       | d                | f                | any    | t                 | f             | f        | off                | dbname=regress_doesnotexist2 | 0/0
+                                                                                                                              List of subscriptions
+      Name       |           Owner           | Enabled |     Publication     | Binary | Streaming | Two-phase commit | Disable on error | Origin | Password required | Run as owner? | Failover | Detect conflict | Synchronous commit |           Conninfo           | Skip LSN 
+-----------------+---------------------------+---------+---------------------+--------+-----------+------------------+------------------+--------+-------------------+---------------+----------+-----------------+--------------------+------------------------------+----------
+ regress_testsub | regress_subscription_user | f       | {testpub2,testpub3} | f      | off       | d                | f                | any    | t                 | f             | f        | f               | off                | dbname=regress_doesnotexist2 | 0/0
 (1 row)
 
 BEGIN;
@@ -223,10 +223,10 @@ ALTER SUBSCRIPTION regress_testsub_foo SET (synchronous_commit = foobar);
 ERROR:  invalid value for parameter "synchronous_commit": "foobar"
 HINT:  Available values: local, remote_write, remote_apply, on, off.
 \dRs+
-                                                                                                                       List of subscriptions
-        Name         |           Owner           | Enabled |     Publication     | Binary | Streaming | Two-phase commit | Disable on error | Origin | Password required | Run as owner? | Failover | Synchronous commit |           Conninfo           | Skip LSN 
----------------------+---------------------------+---------+---------------------+--------+-----------+------------------+------------------+--------+-------------------+---------------+----------+--------------------+------------------------------+----------
- regress_testsub_foo | regress_subscription_user | f       | {testpub2,testpub3} | f      | off       | d                | f                | any    | t                 | f             | f        | local              | dbname=regress_doesnotexist2 | 0/0
+                                                                                                                                List of subscriptions
+        Name         |           Owner           | Enabled |     Publication     | Binary | Streaming | Two-phase commit | Disable on error | Origin | Password required | Run as owner? | Failover | Detect conflict | Synchronous commit |           Conninfo           | Skip LSN 
+---------------------+---------------------------+---------+---------------------+--------+-----------+------------------+------------------+--------+-------------------+---------------+----------+-----------------+--------------------+------------------------------+----------
+ regress_testsub_foo | regress_subscription_user | f       | {testpub2,testpub3} | f      | off       | d                | f                | any    | t                 | f             | f        | f               | local              | dbname=regress_doesnotexist2 | 0/0
 (1 row)
 
 -- rename back to keep the rest simple
@@ -255,19 +255,19 @@ CREATE SUBSCRIPTION regress_testsub CONNECTION 'dbname=regress_doesnotexist' PUB
 WARNING:  subscription was created, but is not connected
 HINT:  To initiate replication, you must manually create the replication slot, enable the subscription, and refresh the subscription.
 \dRs+
-                                                                                                                List of subscriptions
-      Name       |           Owner           | Enabled | Publication | Binary | Streaming | Two-phase commit | Disable on error | Origin | Password required | Run as owner? | Failover | Synchronous commit |          Conninfo           | Skip LSN 
------------------+---------------------------+---------+-------------+--------+-----------+------------------+------------------+--------+-------------------+---------------+----------+--------------------+-----------------------------+----------
- regress_testsub | regress_subscription_user | f       | {testpub}   | t      | off       | d                | f                | any    | t                 | f             | f        | off                | dbname=regress_doesnotexist | 0/0
+                                                                                                                         List of subscriptions
+      Name       |           Owner           | Enabled | Publication | Binary | Streaming | Two-phase commit | Disable on error | Origin | Password required | Run as owner? | Failover | Detect conflict | Synchronous commit |          Conninfo           | Skip LSN 
+-----------------+---------------------------+---------+-------------+--------+-----------+------------------+------------------+--------+-------------------+---------------+----------+-----------------+--------------------+-----------------------------+----------
+ regress_testsub | regress_subscription_user | f       | {testpub}   | t      | off       | d                | f                | any    | t                 | f             | f        | f               | off                | dbname=regress_doesnotexist | 0/0
 (1 row)
 
 ALTER SUBSCRIPTION regress_testsub SET (binary = false);
 ALTER SUBSCRIPTION regress_testsub SET (slot_name = NONE);
 \dRs+
-                                                                                                                List of subscriptions
-      Name       |           Owner           | Enabled | Publication | Binary | Streaming | Two-phase commit | Disable on error | Origin | Password required | Run as owner? | Failover | Synchronous commit |          Conninfo           | Skip LSN 
------------------+---------------------------+---------+-------------+--------+-----------+------------------+------------------+--------+-------------------+---------------+----------+--------------------+-----------------------------+----------
- regress_testsub | regress_subscription_user | f       | {testpub}   | f      | off       | d                | f                | any    | t                 | f             | f        | off                | dbname=regress_doesnotexist | 0/0
+                                                                                                                         List of subscriptions
+      Name       |           Owner           | Enabled | Publication | Binary | Streaming | Two-phase commit | Disable on error | Origin | Password required | Run as owner? | Failover | Detect conflict | Synchronous commit |          Conninfo           | Skip LSN 
+-----------------+---------------------------+---------+-------------+--------+-----------+------------------+------------------+--------+-------------------+---------------+----------+-----------------+--------------------+-----------------------------+----------
+ regress_testsub | regress_subscription_user | f       | {testpub}   | f      | off       | d                | f                | any    | t                 | f             | f        | f               | off                | dbname=regress_doesnotexist | 0/0
 (1 row)
 
 DROP SUBSCRIPTION regress_testsub;
@@ -279,27 +279,27 @@ CREATE SUBSCRIPTION regress_testsub CONNECTION 'dbname=regress_doesnotexist' PUB
 WARNING:  subscription was created, but is not connected
 HINT:  To initiate replication, you must manually create the replication slot, enable the subscription, and refresh the subscription.
 \dRs+
-                                                                                                                List of subscriptions
-      Name       |           Owner           | Enabled | Publication | Binary | Streaming | Two-phase commit | Disable on error | Origin | Password required | Run as owner? | Failover | Synchronous commit |          Conninfo           | Skip LSN 
------------------+---------------------------+---------+-------------+--------+-----------+------------------+------------------+--------+-------------------+---------------+----------+--------------------+-----------------------------+----------
- regress_testsub | regress_subscription_user | f       | {testpub}   | f      | on        | d                | f                | any    | t                 | f             | f        | off                | dbname=regress_doesnotexist | 0/0
+                                                                                                                         List of subscriptions
+      Name       |           Owner           | Enabled | Publication | Binary | Streaming | Two-phase commit | Disable on error | Origin | Password required | Run as owner? | Failover | Detect conflict | Synchronous commit |          Conninfo           | Skip LSN 
+-----------------+---------------------------+---------+-------------+--------+-----------+------------------+------------------+--------+-------------------+---------------+----------+-----------------+--------------------+-----------------------------+----------
+ regress_testsub | regress_subscription_user | f       | {testpub}   | f      | on        | d                | f                | any    | t                 | f             | f        | f               | off                | dbname=regress_doesnotexist | 0/0
 (1 row)
 
 ALTER SUBSCRIPTION regress_testsub SET (streaming = parallel);
 \dRs+
-                                                                                                                List of subscriptions
-      Name       |           Owner           | Enabled | Publication | Binary | Streaming | Two-phase commit | Disable on error | Origin | Password required | Run as owner? | Failover | Synchronous commit |          Conninfo           | Skip LSN 
------------------+---------------------------+---------+-------------+--------+-----------+------------------+------------------+--------+-------------------+---------------+----------+--------------------+-----------------------------+----------
- regress_testsub | regress_subscription_user | f       | {testpub}   | f      | parallel  | d                | f                | any    | t                 | f             | f        | off                | dbname=regress_doesnotexist | 0/0
+                                                                                                                         List of subscriptions
+      Name       |           Owner           | Enabled | Publication | Binary | Streaming | Two-phase commit | Disable on error | Origin | Password required | Run as owner? | Failover | Detect conflict | Synchronous commit |          Conninfo           | Skip LSN 
+-----------------+---------------------------+---------+-------------+--------+-----------+------------------+------------------+--------+-------------------+---------------+----------+-----------------+--------------------+-----------------------------+----------
+ regress_testsub | regress_subscription_user | f       | {testpub}   | f      | parallel  | d                | f                | any    | t                 | f             | f        | f               | off                | dbname=regress_doesnotexist | 0/0
 (1 row)
 
 ALTER SUBSCRIPTION regress_testsub SET (streaming = false);
 ALTER SUBSCRIPTION regress_testsub SET (slot_name = NONE);
 \dRs+
-                                                                                                                List of subscriptions
-      Name       |           Owner           | Enabled | Publication | Binary | Streaming | Two-phase commit | Disable on error | Origin | Password required | Run as owner? | Failover | Synchronous commit |          Conninfo           | Skip LSN 
------------------+---------------------------+---------+-------------+--------+-----------+------------------+------------------+--------+-------------------+---------------+----------+--------------------+-----------------------------+----------
- regress_testsub | regress_subscription_user | f       | {testpub}   | f      | off       | d                | f                | any    | t                 | f             | f        | off                | dbname=regress_doesnotexist | 0/0
+                                                                                                                         List of subscriptions
+      Name       |           Owner           | Enabled | Publication | Binary | Streaming | Two-phase commit | Disable on error | Origin | Password required | Run as owner? | Failover | Detect conflict | Synchronous commit |          Conninfo           | Skip LSN 
+-----------------+---------------------------+---------+-------------+--------+-----------+------------------+------------------+--------+-------------------+---------------+----------+-----------------+--------------------+-----------------------------+----------
+ regress_testsub | regress_subscription_user | f       | {testpub}   | f      | off       | d                | f                | any    | t                 | f             | f        | f               | off                | dbname=regress_doesnotexist | 0/0
 (1 row)
 
 -- fail - publication already exists
@@ -314,10 +314,10 @@ ALTER SUBSCRIPTION regress_testsub ADD PUBLICATION testpub1, testpub2 WITH (refr
 ALTER SUBSCRIPTION regress_testsub ADD PUBLICATION testpub1, testpub2 WITH (refresh = false);
 ERROR:  publication "testpub1" is already in subscription "regress_testsub"
 \dRs+
-                                                                                                                        List of subscriptions
-      Name       |           Owner           | Enabled |         Publication         | Binary | Streaming | Two-phase commit | Disable on error | Origin | Password required | Run as owner? | Failover | Synchronous commit |          Conninfo           | Skip LSN 
------------------+---------------------------+---------+-----------------------------+--------+-----------+------------------+------------------+--------+-------------------+---------------+----------+--------------------+-----------------------------+----------
- regress_testsub | regress_subscription_user | f       | {testpub,testpub1,testpub2} | f      | off       | d                | f                | any    | t                 | f             | f        | off                | dbname=regress_doesnotexist | 0/0
+                                                                                                                                 List of subscriptions
+      Name       |           Owner           | Enabled |         Publication         | Binary | Streaming | Two-phase commit | Disable on error | Origin | Password required | Run as owner? | Failover | Detect conflict | Synchronous commit |          Conninfo           | Skip LSN 
+-----------------+---------------------------+---------+-----------------------------+--------+-----------+------------------+------------------+--------+-------------------+---------------+----------+-----------------+--------------------+-----------------------------+----------
+ regress_testsub | regress_subscription_user | f       | {testpub,testpub1,testpub2} | f      | off       | d                | f                | any    | t                 | f             | f        | f               | off                | dbname=regress_doesnotexist | 0/0
 (1 row)
 
 -- fail - publication used more than once
@@ -332,10 +332,10 @@ ERROR:  publication "testpub3" is not in subscription "regress_testsub"
 -- ok - delete publications
 ALTER SUBSCRIPTION regress_testsub DROP PUBLICATION testpub1, testpub2 WITH (refresh = false);
 \dRs+
-                                                                                                                List of subscriptions
-      Name       |           Owner           | Enabled | Publication | Binary | Streaming | Two-phase commit | Disable on error | Origin | Password required | Run as owner? | Failover | Synchronous commit |          Conninfo           | Skip LSN 
------------------+---------------------------+---------+-------------+--------+-----------+------------------+------------------+--------+-------------------+---------------+----------+--------------------+-----------------------------+----------
- regress_testsub | regress_subscription_user | f       | {testpub}   | f      | off       | d                | f                | any    | t                 | f             | f        | off                | dbname=regress_doesnotexist | 0/0
+                                                                                                                         List of subscriptions
+      Name       |           Owner           | Enabled | Publication | Binary | Streaming | Two-phase commit | Disable on error | Origin | Password required | Run as owner? | Failover | Detect conflict | Synchronous commit |          Conninfo           | Skip LSN 
+-----------------+---------------------------+---------+-------------+--------+-----------+------------------+------------------+--------+-------------------+---------------+----------+-----------------+--------------------+-----------------------------+----------
+ regress_testsub | regress_subscription_user | f       | {testpub}   | f      | off       | d                | f                | any    | t                 | f             | f        | f               | off                | dbname=regress_doesnotexist | 0/0
 (1 row)
 
 DROP SUBSCRIPTION regress_testsub;
@@ -371,10 +371,10 @@ CREATE SUBSCRIPTION regress_testsub CONNECTION 'dbname=regress_doesnotexist' PUB
 WARNING:  subscription was created, but is not connected
 HINT:  To initiate replication, you must manually create the replication slot, enable the subscription, and refresh the subscription.
 \dRs+
-                                                                                                                List of subscriptions
-      Name       |           Owner           | Enabled | Publication | Binary | Streaming | Two-phase commit | Disable on error | Origin | Password required | Run as owner? | Failover | Synchronous commit |          Conninfo           | Skip LSN 
------------------+---------------------------+---------+-------------+--------+-----------+------------------+------------------+--------+-------------------+---------------+----------+--------------------+-----------------------------+----------
- regress_testsub | regress_subscription_user | f       | {testpub}   | f      | off       | p                | f                | any    | t                 | f             | f        | off                | dbname=regress_doesnotexist | 0/0
+                                                                                                                         List of subscriptions
+      Name       |           Owner           | Enabled | Publication | Binary | Streaming | Two-phase commit | Disable on error | Origin | Password required | Run as owner? | Failover | Detect conflict | Synchronous commit |          Conninfo           | Skip LSN 
+-----------------+---------------------------+---------+-------------+--------+-----------+------------------+------------------+--------+-------------------+---------------+----------+-----------------+--------------------+-----------------------------+----------
+ regress_testsub | regress_subscription_user | f       | {testpub}   | f      | off       | p                | f                | any    | t                 | f             | f        | f               | off                | dbname=regress_doesnotexist | 0/0
 (1 row)
 
 --fail - alter of two_phase option not supported.
@@ -383,10 +383,10 @@ ERROR:  unrecognized subscription parameter: "two_phase"
 -- but can alter streaming when two_phase enabled
 ALTER SUBSCRIPTION regress_testsub SET (streaming = true);
 \dRs+
-                                                                                                                List of subscriptions
-      Name       |           Owner           | Enabled | Publication | Binary | Streaming | Two-phase commit | Disable on error | Origin | Password required | Run as owner? | Failover | Synchronous commit |          Conninfo           | Skip LSN 
------------------+---------------------------+---------+-------------+--------+-----------+------------------+------------------+--------+-------------------+---------------+----------+--------------------+-----------------------------+----------
- regress_testsub | regress_subscription_user | f       | {testpub}   | f      | on        | p                | f                | any    | t                 | f             | f        | off                | dbname=regress_doesnotexist | 0/0
+                                                                                                                         List of subscriptions
+      Name       |           Owner           | Enabled | Publication | Binary | Streaming | Two-phase commit | Disable on error | Origin | Password required | Run as owner? | Failover | Detect conflict | Synchronous commit |          Conninfo           | Skip LSN 
+-----------------+---------------------------+---------+-------------+--------+-----------+------------------+------------------+--------+-------------------+---------------+----------+-----------------+--------------------+-----------------------------+----------
+ regress_testsub | regress_subscription_user | f       | {testpub}   | f      | on        | p                | f                | any    | t                 | f             | f        | f               | off                | dbname=regress_doesnotexist | 0/0
 (1 row)
 
 ALTER SUBSCRIPTION regress_testsub SET (slot_name = NONE);
@@ -396,10 +396,10 @@ CREATE SUBSCRIPTION regress_testsub CONNECTION 'dbname=regress_doesnotexist' PUB
 WARNING:  subscription was created, but is not connected
 HINT:  To initiate replication, you must manually create the replication slot, enable the subscription, and refresh the subscription.
 \dRs+
-                                                                                                                List of subscriptions
-      Name       |           Owner           | Enabled | Publication | Binary | Streaming | Two-phase commit | Disable on error | Origin | Password required | Run as owner? | Failover | Synchronous commit |          Conninfo           | Skip LSN 
------------------+---------------------------+---------+-------------+--------+-----------+------------------+------------------+--------+-------------------+---------------+----------+--------------------+-----------------------------+----------
- regress_testsub | regress_subscription_user | f       | {testpub}   | f      | on        | p                | f                | any    | t                 | f             | f        | off                | dbname=regress_doesnotexist | 0/0
+                                                                                                                         List of subscriptions
+      Name       |           Owner           | Enabled | Publication | Binary | Streaming | Two-phase commit | Disable on error | Origin | Password required | Run as owner? | Failover | Detect conflict | Synchronous commit |          Conninfo           | Skip LSN 
+-----------------+---------------------------+---------+-------------+--------+-----------+------------------+------------------+--------+-------------------+---------------+----------+-----------------+--------------------+-----------------------------+----------
+ regress_testsub | regress_subscription_user | f       | {testpub}   | f      | on        | p                | f                | any    | t                 | f             | f        | f               | off                | dbname=regress_doesnotexist | 0/0
 (1 row)
 
 ALTER SUBSCRIPTION regress_testsub SET (slot_name = NONE);
@@ -412,18 +412,42 @@ CREATE SUBSCRIPTION regress_testsub CONNECTION 'dbname=regress_doesnotexist' PUB
 WARNING:  subscription was created, but is not connected
 HINT:  To initiate replication, you must manually create the replication slot, enable the subscription, and refresh the subscription.
 \dRs+
-                                                                                                                List of subscriptions
-      Name       |           Owner           | Enabled | Publication | Binary | Streaming | Two-phase commit | Disable on error | Origin | Password required | Run as owner? | Failover | Synchronous commit |          Conninfo           | Skip LSN 
------------------+---------------------------+---------+-------------+--------+-----------+------------------+------------------+--------+-------------------+---------------+----------+--------------------+-----------------------------+----------
- regress_testsub | regress_subscription_user | f       | {testpub}   | f      | off       | d                | f                | any    | t                 | f             | f        | off                | dbname=regress_doesnotexist | 0/0
+                                                                                                                         List of subscriptions
+      Name       |           Owner           | Enabled | Publication | Binary | Streaming | Two-phase commit | Disable on error | Origin | Password required | Run as owner? | Failover | Detect conflict | Synchronous commit |          Conninfo           | Skip LSN 
+-----------------+---------------------------+---------+-------------+--------+-----------+------------------+------------------+--------+-------------------+---------------+----------+-----------------+--------------------+-----------------------------+----------
+ regress_testsub | regress_subscription_user | f       | {testpub}   | f      | off       | d                | f                | any    | t                 | f             | f        | f               | off                | dbname=regress_doesnotexist | 0/0
 (1 row)
 
 ALTER SUBSCRIPTION regress_testsub SET (disable_on_error = true);
 \dRs+
-                                                                                                                List of subscriptions
-      Name       |           Owner           | Enabled | Publication | Binary | Streaming | Two-phase commit | Disable on error | Origin | Password required | Run as owner? | Failover | Synchronous commit |          Conninfo           | Skip LSN 
------------------+---------------------------+---------+-------------+--------+-----------+------------------+------------------+--------+-------------------+---------------+----------+--------------------+-----------------------------+----------
- regress_testsub | regress_subscription_user | f       | {testpub}   | f      | off       | d                | t                | any    | t                 | f             | f        | off                | dbname=regress_doesnotexist | 0/0
+                                                                                                                         List of subscriptions
+      Name       |           Owner           | Enabled | Publication | Binary | Streaming | Two-phase commit | Disable on error | Origin | Password required | Run as owner? | Failover | Detect conflict | Synchronous commit |          Conninfo           | Skip LSN 
+-----------------+---------------------------+---------+-------------+--------+-----------+------------------+------------------+--------+-------------------+---------------+----------+-----------------+--------------------+-----------------------------+----------
+ regress_testsub | regress_subscription_user | f       | {testpub}   | f      | off       | d                | t                | any    | t                 | f             | f        | f               | off                | dbname=regress_doesnotexist | 0/0
+(1 row)
+
+ALTER SUBSCRIPTION regress_testsub SET (slot_name = NONE);
+DROP SUBSCRIPTION regress_testsub;
+-- fail - detect_conflict must be boolean
+CREATE SUBSCRIPTION regress_testsub CONNECTION 'dbname=regress_doesnotexist' PUBLICATION testpub WITH (connect = false, detect_conflict = foo);
+ERROR:  detect_conflict requires a Boolean value
+-- now it works
+CREATE SUBSCRIPTION regress_testsub CONNECTION 'dbname=regress_doesnotexist' PUBLICATION testpub WITH (connect = false, detect_conflict = true);
+WARNING:  subscription was created, but is not connected
+HINT:  To initiate replication, you must manually create the replication slot, enable the subscription, and refresh the subscription.
+\dRs+
+                                                                                                                         List of subscriptions
+      Name       |           Owner           | Enabled | Publication | Binary | Streaming | Two-phase commit | Disable on error | Origin | Password required | Run as owner? | Failover | Detect conflict | Synchronous commit |          Conninfo           | Skip LSN 
+-----------------+---------------------------+---------+-------------+--------+-----------+------------------+------------------+--------+-------------------+---------------+----------+-----------------+--------------------+-----------------------------+----------
+ regress_testsub | regress_subscription_user | f       | {testpub}   | f      | off       | d                | f                | any    | t                 | f             | f        | t               | off                | dbname=regress_doesnotexist | 0/0
+(1 row)
+
+ALTER SUBSCRIPTION regress_testsub SET (detect_conflict = false);
+\dRs+
+                                                                                                                         List of subscriptions
+      Name       |           Owner           | Enabled | Publication | Binary | Streaming | Two-phase commit | Disable on error | Origin | Password required | Run as owner? | Failover | Detect conflict | Synchronous commit |          Conninfo           | Skip LSN 
+-----------------+---------------------------+---------+-------------+--------+-----------+------------------+------------------+--------+-------------------+---------------+----------+-----------------+--------------------+-----------------------------+----------
+ regress_testsub | regress_subscription_user | f       | {testpub}   | f      | off       | d                | f                | any    | t                 | f             | f        | f               | off                | dbname=regress_doesnotexist | 0/0
 (1 row)
 
 ALTER SUBSCRIPTION regress_testsub SET (slot_name = NONE);
diff --git a/src/test/regress/sql/subscription.sql b/src/test/regress/sql/subscription.sql
index 3e5ba4cb8c..a77b196704 100644
--- a/src/test/regress/sql/subscription.sql
+++ b/src/test/regress/sql/subscription.sql
@@ -290,6 +290,21 @@ ALTER SUBSCRIPTION regress_testsub SET (disable_on_error = true);
 ALTER SUBSCRIPTION regress_testsub SET (slot_name = NONE);
 DROP SUBSCRIPTION regress_testsub;
 
+-- fail - detect_conflict must be boolean
+CREATE SUBSCRIPTION regress_testsub CONNECTION 'dbname=regress_doesnotexist' PUBLICATION testpub WITH (connect = false, detect_conflict = foo);
+
+-- now it works
+CREATE SUBSCRIPTION regress_testsub CONNECTION 'dbname=regress_doesnotexist' PUBLICATION testpub WITH (connect = false, detect_conflict = true);
+
+\dRs+
+
+ALTER SUBSCRIPTION regress_testsub SET (detect_conflict = false);
+
+\dRs+
+
+ALTER SUBSCRIPTION regress_testsub SET (slot_name = NONE);
+DROP SUBSCRIPTION regress_testsub;
+
 -- let's do some tests with pg_create_subscription rather than superuser
 SET SESSION AUTHORIZATION regress_subscription_user3;
 
diff --git a/src/test/subscription/t/001_rep_changes.pl b/src/test/subscription/t/001_rep_changes.pl
index 471e981962..78c0307165 100644
--- a/src/test/subscription/t/001_rep_changes.pl
+++ b/src/test/subscription/t/001_rep_changes.pl
@@ -331,11 +331,12 @@ is( $result, qq(1|bar
 2|baz),
 	'update works with REPLICA IDENTITY FULL and a primary key');
 
-# Check that subscriber handles cases where update/delete target tuple
-# is missing.  We have to look for the DEBUG1 log messages about that,
-# so temporarily bump up the log verbosity.
-$node_subscriber->append_conf('postgresql.conf', "log_min_messages = debug1");
-$node_subscriber->reload;
+# To check that subscriber handles cases where update/delete target tuple
+# is missing, detect_conflict is temporarily enabled to log conflicts
+# related to missing tuples.
+$node_subscriber->safe_psql('postgres',
+	"ALTER SUBSCRIPTION tap_sub SET (detect_conflict = true)"
+);
 
 $node_subscriber->safe_psql('postgres', "DELETE FROM tab_full_pk");
 
@@ -352,10 +353,10 @@ $node_publisher->wait_for_catchup('tap_sub');
 
 my $logfile = slurp_file($node_subscriber->logfile, $log_location);
 ok( $logfile =~
-	  qr/logical replication did not find row to be updated in replication target relation "tab_full_pk"/,
+	  qr/conflict update_missing detected on relation "public.tab_full_pk".*\n.*DETAIL:.* Did not find the row to be updated./m,
 	'update target row is missing');
 ok( $logfile =~
-	  qr/logical replication did not find row to be deleted in replication target relation "tab_full_pk"/,
+	  qr/conflict delete_missing detected on relation "public.tab_full_pk".*\n.*DETAIL:.* Did not find the row to be deleted./m,
 	'delete target row is missing');
 
 $node_subscriber->append_conf('postgresql.conf',
diff --git a/src/test/subscription/t/013_partition.pl b/src/test/subscription/t/013_partition.pl
index 29580525a9..c64f17211d 100644
--- a/src/test/subscription/t/013_partition.pl
+++ b/src/test/subscription/t/013_partition.pl
@@ -343,12 +343,12 @@ $result =
   $node_subscriber2->safe_psql('postgres', "SELECT a FROM tab1 ORDER BY 1");
 is($result, qq(), 'truncate of tab1 replicated');
 
-# Check that subscriber handles cases where update/delete target tuple
-# is missing.  We have to look for the DEBUG1 log messages about that,
-# so temporarily bump up the log verbosity.
-$node_subscriber1->append_conf('postgresql.conf',
-	"log_min_messages = debug1");
-$node_subscriber1->reload;
+# To check that subscriber handles cases where update/delete target tuple
+# is missing, detect_conflict is temporarily enabled to log conflicts
+# related to missing tuples.
+$node_subscriber1->safe_psql('postgres',
+	"ALTER SUBSCRIPTION sub1 SET (detect_conflict = true)"
+);
 
 $node_publisher->safe_psql('postgres',
 	"INSERT INTO tab1 VALUES (1, 'foo'), (4, 'bar'), (10, 'baz')");
@@ -372,21 +372,21 @@ $node_publisher->wait_for_catchup('sub2');
 
 my $logfile = slurp_file($node_subscriber1->logfile(), $log_location);
 ok( $logfile =~
-	  qr/logical replication did not find row to be updated in replication target relation's partition "tab1_2_2"/,
+	  qr/conflict update_missing detected on relation "public.tab1_2_2".*\n.*DETAIL:.* Did not find the row to be updated./,
 	'update target row is missing in tab1_2_2');
 ok( $logfile =~
-	  qr/logical replication did not find row to be deleted in replication target relation "tab1_1"/,
+	  qr/conflict delete_missing detected on relation "public.tab1_1".*\n.*DETAIL:.* Did not find the row to be deleted./,
 	'delete target row is missing in tab1_1');
 ok( $logfile =~
-	  qr/logical replication did not find row to be deleted in replication target relation "tab1_2_2"/,
+	  qr/conflict delete_missing detected on relation "public.tab1_2_2".*\n.*DETAIL:.* Did not find the row to be deleted./,
 	'delete target row is missing in tab1_2_2');
 ok( $logfile =~
-	  qr/logical replication did not find row to be deleted in replication target relation "tab1_def"/,
+	  qr/conflict delete_missing detected on relation "public.tab1_def".*\n.*DETAIL:.* Did not find the row to be deleted./,
 	'delete target row is missing in tab1_def');
 
-$node_subscriber1->append_conf('postgresql.conf',
-	"log_min_messages = warning");
-$node_subscriber1->reload;
+$node_subscriber1->safe_psql('postgres',
+	"ALTER SUBSCRIPTION sub1 SET (detect_conflict = false)"
+);
 
 # Tests for replication using root table identity and schema
 
@@ -773,12 +773,12 @@ pub_tab2|3|yyy
 pub_tab2|5|zzz
 xxx_c|6|aaa), 'inserts into tab2 replicated');
 
-# Check that subscriber handles cases where update/delete target tuple
-# is missing.  We have to look for the DEBUG1 log messages about that,
-# so temporarily bump up the log verbosity.
-$node_subscriber1->append_conf('postgresql.conf',
-	"log_min_messages = debug1");
-$node_subscriber1->reload;
+# To check that subscriber handles cases where update/delete target tuple
+# is missing, detect_conflict is temporarily enabled to log conflicts
+# related to missing tuples.
+$node_subscriber1->safe_psql('postgres',
+	"ALTER SUBSCRIPTION sub_viaroot SET (detect_conflict = true)"
+);
 
 $node_subscriber1->safe_psql('postgres', "DELETE FROM tab2");
 
@@ -796,15 +796,15 @@ $node_publisher->wait_for_catchup('sub2');
 
 $logfile = slurp_file($node_subscriber1->logfile(), $log_location);
 ok( $logfile =~
-	  qr/logical replication did not find row to be updated in replication target relation's partition "tab2_1"/,
+	  qr/conflict update_missing detected on relation "public.tab2_1".*\n.*DETAIL:.* Did not find the row to be updated./,
 	'update target row is missing in tab2_1');
 ok( $logfile =~
-	  qr/logical replication did not find row to be deleted in replication target relation "tab2_1"/,
+	  qr/conflict delete_missing detected on relation "public.tab2_1".*\n.*DETAIL:.* Did not find the row to be deleted./,
 	'delete target row is missing in tab2_1');
 
-$node_subscriber1->append_conf('postgresql.conf',
-	"log_min_messages = warning");
-$node_subscriber1->reload;
+$node_subscriber1->safe_psql('postgres',
+	"ALTER SUBSCRIPTION sub_viaroot SET (detect_conflict = false)"
+);
 
 # Test that replication continues to work correctly after altering the
 # partition of a partitioned target table.
diff --git a/src/test/subscription/t/029_on_error.pl b/src/test/subscription/t/029_on_error.pl
index 0ab57a4b5b..496a3c6cd9 100644
--- a/src/test/subscription/t/029_on_error.pl
+++ b/src/test/subscription/t/029_on_error.pl
@@ -30,7 +30,7 @@ sub test_skip_lsn
 	# ERROR with its CONTEXT when retrieving this information.
 	my $contents = slurp_file($node_subscriber->logfile, $offset);
 	$contents =~
-	  qr/duplicate key value violates unique constraint "tbl_pkey".*\n.*DETAIL:.*\n.*CONTEXT:.* for replication target relation "public.tbl" in transaction \d+, finished at ([[:xdigit:]]+\/[[:xdigit:]]+)/m
+	  qr/conflict insert_exists detected on relation "public.tbl".*\n.*DETAIL:.* Key \(i\)=\(1\) already exists in unique index "tbl_pkey", which was modified by origin \d+ in transaction \d+ at .*\n.*CONTEXT:.* for replication target relation "public.tbl" in transaction \d+, finished at ([[:xdigit:]]+\/[[:xdigit:]]+)/m
 	  or die "could not get error-LSN";
 	my $lsn = $1;
 
@@ -83,6 +83,7 @@ $node_subscriber->append_conf(
 	'postgresql.conf',
 	qq[
 max_prepared_transactions = 10
+track_commit_timestamp = on
 ]);
 $node_subscriber->start;
 
@@ -109,7 +110,7 @@ my $publisher_connstr = $node_publisher->connstr . ' dbname=postgres';
 $node_publisher->safe_psql('postgres',
 	"CREATE PUBLICATION pub FOR TABLE tbl");
 $node_subscriber->safe_psql('postgres',
-	"CREATE SUBSCRIPTION sub CONNECTION '$publisher_connstr' PUBLICATION pub WITH (disable_on_error = true, streaming = on, two_phase = on)"
+	"CREATE SUBSCRIPTION sub CONNECTION '$publisher_connstr' PUBLICATION pub WITH (disable_on_error = true, streaming = on, two_phase = on, detect_conflict = on)"
 );
 
 # Initial synchronization failure causes the subscription to be disabled.
diff --git a/src/test/subscription/t/030_origin.pl b/src/test/subscription/t/030_origin.pl
index 056561f008..03dabfeb72 100644
--- a/src/test/subscription/t/030_origin.pl
+++ b/src/test/subscription/t/030_origin.pl
@@ -26,7 +26,12 @@ my $stderr;
 # node_A
 my $node_A = PostgreSQL::Test::Cluster->new('node_A');
 $node_A->init(allows_streaming => 'logical');
+
+# Enable the track_commit_timestamp to detect the conflict when attempting to
+# update a row that was previously modified by a different origin.
+$node_A->append_conf('postgresql.conf', 'track_commit_timestamp = on');
 $node_A->start;
+
 # node_B
 my $node_B = PostgreSQL::Test::Cluster->new('node_B');
 $node_B->init(allows_streaming => 'logical');
@@ -89,11 +94,32 @@ is( $result, qq(11
 	'Inserted successfully without leading to infinite recursion in bidirectional replication setup'
 );
 
+###############################################################################
+# Check that the conflict can be detected when attempting to update a row that
+# was previously modified by a different source.
+###############################################################################
+
+$node_A->safe_psql('postgres',
+	"ALTER SUBSCRIPTION $subname_AB SET (detect_conflict = true);");
+
+$node_B->safe_psql('postgres', "UPDATE tab SET a = 10 WHERE a = 11;");
+
+$node_A->wait_for_log(
+	qr/Updating a row that was modified by a different origin [0-9]+ in transaction [0-9]+ at .*/
+);
+
 $node_A->safe_psql('postgres', "DELETE FROM tab;");
 
 $node_A->wait_for_catchup($subname_BA);
 $node_B->wait_for_catchup($subname_AB);
 
+# The remaining tests no longer test conflict detection.
+$node_A->safe_psql('postgres',
+	"ALTER SUBSCRIPTION $subname_AB SET (detect_conflict = false);");
+
+$node_A->append_conf('postgresql.conf', 'track_commit_timestamp = off');
+$node_A->restart;
+
 ###############################################################################
 # Check that remote data of node_B (that originated from node_C) is not
 # published to node_A.
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index e710fa48e5..2485a80833 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -466,6 +466,7 @@ ConditionVariableMinimallyPadded
 ConditionalStack
 ConfigData
 ConfigVariable
+ConflictType
 ConnCacheEntry
 ConnCacheKey
 ConnParams
-- 
2.34.1



  [application/octet-stream] v3-0003-Implement-conflict-resolution-for-INSERT-UPDATE-a.patch (34.4K, ../../CAJpy0uCv8R1Y5herLLANhGGqCotAFzBw3ikzhpXZvbqLDuoMTw@mail.gmail.com/4-v3-0003-Implement-conflict-resolution-for-INSERT-UPDATE-a.patch)
  download | inline diff:
From 60aeafbaa835499a6049c9c62d578c0d31c17f84 Mon Sep 17 00:00:00 2001
From: Nisha Moond <[email protected]>
Date: Tue, 25 Jun 2024 15:45:37 +0530
Subject: [PATCH v3 3/5] Implement conflict resolution for INSERT, UPDATE, and
 DELETE operations.

This patch introduces support for handling conflicts with the following resolutions:
- For INSERT conflicts:
  - insert_exists: remote_apply, keep_local, error
- For UPDATE conflicts:
  - update_differ: remote_apply, keep_local, error
  - update_missing: apply_or_skip, apply_or_error, skip, error
- For DELETE conflicts:
  - delete_missing: skip, error

Each of the conflict type now has defined actions to manage data synchronization
between Publisher and subscriber databases.
---
 src/backend/executor/execReplication.c     |  80 ++++-
 src/backend/replication/logical/conflict.c | 190 ++++++++++--
 src/backend/replication/logical/worker.c   | 333 ++++++++++++++++-----
 src/include/executor/executor.h            |   5 +-
 src/include/replication/conflict.h         |  19 +-
 src/test/subscription/t/029_on_error.pl    |   7 +
 6 files changed, 525 insertions(+), 109 deletions(-)

diff --git a/src/backend/executor/execReplication.c b/src/backend/executor/execReplication.c
index f01927a933..3e8d768214 100644
--- a/src/backend/executor/execReplication.c
+++ b/src/backend/executor/execReplication.c
@@ -566,7 +566,8 @@ retry:
  */
 void
 ExecSimpleRelationInsert(ResultRelInfo *resultRelInfo,
-						 EState *estate, TupleTableSlot *slot)
+						 EState *estate, TupleTableSlot *slot,
+						 TupleTableSlot **conflictslot)
 {
 	bool		skip_tuple = false;
 	Relation	rel = resultRelInfo->ri_RelationDesc;
@@ -602,21 +603,82 @@ ExecSimpleRelationInsert(ResultRelInfo *resultRelInfo,
 		if (rel->rd_rel->relispartition)
 			ExecPartitionCheck(resultRelInfo, slot, estate, true);
 
+		conflictindexes = resultRelInfo->ri_onConflictArbiterIndexes;
+
+		/*
+		 * If caller has passed non null conflictslot, check all the unique
+		 * indexes for potential conflicts. If the configured resolver is in
+		 * favour of apply, give the conflicted tuple information in
+		 * conflictslot.
+		 */
+		if (conflictslot)
+		{
+			foreach_oid(uniqueidx, conflictindexes)
+			{
+				/*
+				 * Return if any conflict is found other than one with 'ERROR'
+				 * resolver configured. In case of 'ERROR' resolver, emit
+				 * error here; otherwise return to caller for resolutions.
+				 */
+				if (FindConflictTuple(resultRelInfo, estate, uniqueidx,
+									  slot, &(*conflictslot)))
+				{
+					RepOriginId origin;
+					TimestampTz committs;
+					TransactionId xmin;
+					ConflictResolver resolver;
+					bool		apply_remote = false;
+
+					GetTupleCommitTs(*conflictslot, &xmin, &origin, &committs);
+					resolver = GetConflictResolver(*conflictslot, rel,
+												   CT_INSERT_EXISTS,
+												   &apply_remote, NULL, uniqueidx,
+												   xmin, origin, committs);
+
+					ReportApplyConflict(LOG, CT_INSERT_EXISTS, resolver, rel,
+										uniqueidx, xmin, origin, committs,
+										*conflictslot);
+
+					/* Nothing to apply, free the resources */
+					if (!apply_remote)
+					{
+						ExecDropSingleTupleTableSlot(*conflictslot);
+						*conflictslot = NULL;
+					}
+
+					return;
+				}
+			}
+		}
+
+
 		/* OK, store the tuple and create index entries for it */
 		simple_table_tuple_insert(resultRelInfo->ri_RelationDesc, slot);
 
-		conflictindexes = resultRelInfo->ri_onConflictArbiterIndexes;
-
 		if (resultRelInfo->ri_NumIndices > 0)
 			recheckIndexes = ExecInsertIndexTuples(resultRelInfo,
 												   slot, estate, false,
 												   conflictindexes, &conflict,
 												   conflictindexes, false);
 
-		/* Re-check all the unique indexes for potential conflicts */
+		/*
+		 * Re-check all the unique indexes for potential conflicts.
+		 *
+		 * The Reason for doing the check again is:
+		 *
+		 * 1. If the remote change violated multiple unique constraints, the
+		 * current resolution cannot solve it, so we still need to report this
+		 * conflict after resolution.
+		 *
+		 * 2. If the local data is changed immediately after converting the
+		 * insert to update but before updating the data, then the conflict
+		 * can still happen, and we may need to report it again.
+		 *
+		 * XXX: Needs further review and discussion on usefulness of this
+		 * repeated call.
+		 */
 		foreach_oid(uniqueidx, (conflict ? conflictindexes : NIL))
 		{
-			TupleTableSlot *conflictslot;
 
 			/*
 			 * Reports the conflict if any.
@@ -631,15 +693,15 @@ ExecSimpleRelationInsert(ResultRelInfo *resultRelInfo,
 			 * cost of finding the tuple should be acceptable in this case.
 			 */
 			if (list_member_oid(recheckIndexes, uniqueidx) &&
-				FindConflictTuple(resultRelInfo, estate, uniqueidx, slot, &conflictslot))
+				FindConflictTuple(resultRelInfo, estate, uniqueidx, slot, &(*conflictslot)))
 			{
 				RepOriginId origin;
 				TimestampTz committs;
 				TransactionId xmin;
 
-				GetTupleCommitTs(conflictslot, &xmin, &origin, &committs);
-				ReportApplyConflict(ERROR, CT_INSERT_EXISTS, rel, uniqueidx,
-									xmin, origin, committs, conflictslot);
+				GetTupleCommitTs(*conflictslot, &xmin, &origin, &committs);
+				ReportApplyConflict(ERROR, CT_INSERT_EXISTS, 0, rel, uniqueidx,
+									xmin, origin, committs, *conflictslot);
 			}
 		}
 
diff --git a/src/backend/replication/logical/conflict.c b/src/backend/replication/logical/conflict.c
index 87b1ea0ab3..a622a0ea8b 100644
--- a/src/backend/replication/logical/conflict.c
+++ b/src/backend/replication/logical/conflict.c
@@ -21,13 +21,17 @@
 #include "access/table.h"
 #include "catalog/indexing.h"
 #include "catalog/pg_conflict.h"
+#include "executor/executor.h"
 #include "replication/conflict.h"
+#include "replication/logicalproto.h"
+#include "replication/logicalrelation.h"
 #include "replication/origin.h"
 #include "utils/builtins.h"
 #include "utils/fmgroids.h"
 #include "utils/lsyscache.h"
 #include "utils/rel.h"
 #include "utils/timestamp.h"
+#include "utils/syscache.h"
 
 const char *const ConflictTypeNames[] = {
 	[CT_INSERT_EXISTS] = "insert_exists",
@@ -82,8 +86,9 @@ const int	ConflictTypeDefaultResolvers[] = {
 };
 
 static char *build_index_value_desc(Oid indexoid, TupleTableSlot *conflictslot);
-static int	errdetail_apply_conflict(ConflictType type, Oid conflictidx,
-									 TransactionId localxmin,
+static int	errdetail_apply_conflict(ConflictType type,
+									 ConflictResolver resolver,
+									 Oid conflictidx, TransactionId localxmin,
 									 RepOriginId localorigin,
 									 TimestampTz localts,
 									 TupleTableSlot *conflictslot);
@@ -122,13 +127,13 @@ GetTupleCommitTs(TupleTableSlot *localslot, TransactionId *xmin,
 }
 
 /*
- * Report a conflict when applying remote changes.
+ * Report conflict and resolution applied while applying remote changes.
  */
 void
-ReportApplyConflict(int elevel, ConflictType type, Relation localrel,
-					Oid conflictidx, TransactionId localxmin,
-					RepOriginId localorigin, TimestampTz localts,
-					TupleTableSlot *conflictslot)
+ReportApplyConflict(int elevel, ConflictType type, ConflictResolver resolver,
+					Relation localrel, Oid conflictidx,
+					TransactionId localxmin, RepOriginId localorigin,
+					TimestampTz localts, TupleTableSlot *conflictslot)
 {
 	ereport(elevel,
 			errcode(ERRCODE_INTEGRITY_CONSTRAINT_VIOLATION),
@@ -136,7 +141,7 @@ ReportApplyConflict(int elevel, ConflictType type, Relation localrel,
 				   ConflictTypeNames[type],
 				   get_namespace_name(RelationGetNamespace(localrel)),
 				   RelationGetRelationName(localrel)),
-			errdetail_apply_conflict(type, conflictidx, localxmin, localorigin,
+			errdetail_apply_conflict(type, resolver, conflictidx, localxmin, localorigin,
 									 localts, conflictslot));
 }
 
@@ -172,12 +177,13 @@ InitConflictIndexes(ResultRelInfo *relInfo)
 }
 
 /*
- * Add an errdetail() line showing conflict detail.
+ * Add an errdetail() line showing conflict and resolution details.
  */
 static int
-errdetail_apply_conflict(ConflictType type, Oid conflictidx,
-						 TransactionId localxmin, RepOriginId localorigin,
-						 TimestampTz localts, TupleTableSlot *conflictslot)
+errdetail_apply_conflict(ConflictType type, ConflictResolver resolver,
+						 Oid conflictidx, TransactionId localxmin,
+						 RepOriginId localorigin, TimestampTz localts,
+						 TupleTableSlot *conflictslot)
 {
 	switch (type)
 	{
@@ -191,24 +197,29 @@ errdetail_apply_conflict(ConflictType type, Oid conflictidx,
 				char	   *index_value = build_index_value_desc(conflictidx,
 																 conflictslot);
 
-				if (index_value && localts)
-					return errdetail("Key %s already exists in unique index \"%s\", which was modified by origin %u in transaction %u at %s.",
-									 index_value, get_rel_name(conflictidx), localorigin,
-									 localxmin, timestamptz_to_str(localts));
-				else if (index_value && !localts)
-					return errdetail("Key %s already exists in unique index \"%s\", which was modified in transaction %u.",
-									 index_value, get_rel_name(conflictidx), localxmin);
+				if (!resolver || (resolver == CR_ERROR))
+				{
+					if (index_value && localts)
+						return errdetail("Key %s already exists in unique index \"%s\", which was modified by origin %u in transaction %u at %s.",
+										 index_value, get_rel_name(conflictidx), localorigin,
+										 localxmin, timestamptz_to_str(localts));
+					else if (index_value && !localts)
+						return errdetail("Key %s already exists in unique index \"%s\", which was modified in transaction %u.",
+										 index_value, get_rel_name(conflictidx), localxmin);
+					else
+						return errdetail("Key already exists in unique index \"%s\".",
+										 get_rel_name(conflictidx));
+				}
 				else
-					return errdetail("Key already exists in unique index \"%s\".",
-									 get_rel_name(conflictidx));
+					return errdetail("Key already exists. Applying resolution method \"%s\"", ConflictResolverNames[resolver]);
 			}
 		case CT_UPDATE_DIFFER:
-			return errdetail("Updating a row that was modified by a different origin %u in transaction %u at %s.",
-							 localorigin, localxmin, timestamptz_to_str(localts));
+			return errdetail("Updating a row that was modified by a different origin %u in transaction %u at %s. Applying resolution method \"%s\"",
+							 localorigin, localxmin, timestamptz_to_str(localts), ConflictResolverNames[resolver]);
 		case CT_UPDATE_MISSING:
-			return errdetail("Did not find the row to be updated.");
+			return errdetail("Did not find the row to be updated. Applying resolution method \"%s\"", ConflictResolverNames[resolver]);
 		case CT_DELETE_MISSING:
-			return errdetail("Did not find the row to be deleted.");
+			return errdetail("Did not find the row to be deleted. Applying resolution method \"%s\"", ConflictResolverNames[resolver]);
 	}
 
 	return 0;					/* silence compiler warning */
@@ -322,6 +333,71 @@ validate_conflict_type_and_resolver(char *conflict_type, char *conflict_resolver
 	return type;
 }
 
+/*
+ * Get the global conflict resolver configured for given conflict type
+ */
+static ConflictResolver
+get_conflict_resolver_internal(ConflictType type)
+{
+
+	ConflictResolver resolver;
+	HeapTuple	tuple;
+	Datum		datum;
+	char	   *conflict_res;
+
+	/*
+	 * XXX: Currently, we fetch the conflict resolver from cache for each
+	 * conflict detection. If needed, we can keep the info in global variable
+	 * and fetch from cache only once after cache invalidation.
+	 */
+	tuple = SearchSysCache1(CONFLICTTYPE,
+							CStringGetTextDatum(ConflictTypeNames[type]));
+
+	if (!HeapTupleIsValid(tuple))
+		elog(ERROR, "cache lookup failed for conflict type %u", type);
+
+	datum = SysCacheGetAttrNotNull(CONFLICTTYPE,
+								   tuple, Anum_pg_conflict_confres);
+
+	conflict_res = TextDatumGetCString(datum);
+
+	for (resolver = CR_MIN; resolver <= CR_MAX; resolver++)
+	{
+		if (strcmp(ConflictResolverNames[resolver], conflict_res) == 0)
+			break;
+	}
+
+	ReleaseSysCache(tuple);
+	return resolver;
+}
+
+/*
+ * Check if a full tuple can be created from the new tuple.
+ * Return true if yes, false otherwise.
+ *
+ * XXX: Currently, it only handles the simple case of identical table
+ * structures on both Publisher and subscriber. Need to analyze if more
+ * cases can be supported.
+ */
+static bool
+can_create_full_tuple(Relation localrel,
+					  LogicalRepTupleData *newtup)
+{
+	int			i;
+	int			local_att = RelationGetNumberOfAttributes(localrel);
+
+	if (newtup->ncols != local_att)
+		return false;
+
+	for (i = 0; i < newtup->ncols; i++)
+	{
+		if (newtup->colstatus[i] == LOGICALREP_COLUMN_UNCHANGED)
+			return false;
+	}
+
+	return true;
+}
+
 /*
  * Execute Conflict Resolver Stmt
  *
@@ -352,7 +428,7 @@ ExecConflictResolverStmt(ConflictResolverStmt *stmt)
 	memset(replaces, false, sizeof(replaces));
 
 	values[Anum_pg_conflict_conftype - 1] =
-			CStringGetTextDatum(stmt->conflict_type);
+		CStringGetTextDatum(stmt->conflict_type);
 
 	if (stmt->isReset)
 	{
@@ -396,3 +472,65 @@ ExecConflictResolverStmt(ConflictResolverStmt *stmt)
 
 	table_close(pg_conflict, RowExclusiveLock);
 }
+
+/*
+ * Find the global resolver for the given conflict type.
+ * It emits error in case the resolver is set to 'ERROR'.
+ *
+ * Set 'apply_remote' to true if remote tuple should be applied,
+ * false otherwise.
+ */
+ConflictResolver
+GetConflictResolver(TupleTableSlot *localslot, Relation localrel,
+					ConflictType type, bool *apply_remote,
+					LogicalRepTupleData *newtup,
+					Oid conflictidx, TransactionId xmin,
+					RepOriginId origin, TimestampTz committs)
+{
+	ConflictResolver resolver;
+
+	resolver = get_conflict_resolver_internal(type);
+
+	switch (resolver)
+	{
+		case CR_REMOTE_APPLY:
+			*apply_remote = true;
+			break;
+		case CR_APPLY_OR_SKIP:
+			if (can_create_full_tuple(localrel, newtup))
+			{
+				*apply_remote = true;
+				break;
+			}
+			else
+			{
+				*apply_remote = false;
+				elog(LOG, "UPDATE can not be converted to INSERT, hence SKIP the update!");
+				break;
+			}
+		case CR_APPLY_OR_ERROR:
+			if (can_create_full_tuple(localrel, newtup))
+			{
+				*apply_remote = true;
+				break;
+			}
+			else
+			{
+				ReportApplyConflict(ERROR, type, resolver, localrel, conflictidx,
+									xmin, origin, committs, localslot);
+				break;
+			}
+		case CR_KEEP_LOCAL:
+		case CR_SKIP:
+			*apply_remote = false;
+			break;
+		case CR_ERROR:
+			ReportApplyConflict(ERROR, type, resolver, localrel, conflictidx,
+								xmin, origin, committs, localslot);
+			break;
+		default:
+			elog(ERROR, "Conflict %s is detected! Unrecogonized conflict resolution method", ConflictTypeNames[type]);
+	}
+
+	return resolver;
+}
diff --git a/src/backend/replication/logical/worker.c b/src/backend/replication/logical/worker.c
index 06ee46886b..c4dc03e964 100644
--- a/src/backend/replication/logical/worker.c
+++ b/src/backend/replication/logical/worker.c
@@ -382,7 +382,9 @@ static void send_feedback(XLogRecPtr recvpos, bool force, bool requestReply);
 static void apply_handle_commit_internal(LogicalRepCommitData *commit_data);
 static void apply_handle_insert_internal(ApplyExecutionData *edata,
 										 ResultRelInfo *relinfo,
-										 TupleTableSlot *remoteslot);
+										 TupleTableSlot *remoteslot,
+										 LogicalRepTupleData *newtup,
+										 LogicalRepRelMapEntry *rel_entry);
 static void apply_handle_update_internal(ApplyExecutionData *edata,
 										 ResultRelInfo *relinfo,
 										 TupleTableSlot *remoteslot,
@@ -2431,10 +2433,10 @@ apply_handle_insert(StringInfo s)
 	/* For a partitioned table, insert the tuple into a partition. */
 	if (rel->localrel->rd_rel->relkind == RELKIND_PARTITIONED_TABLE)
 		apply_handle_tuple_routing(edata,
-								   remoteslot, NULL, CMD_INSERT);
+								   remoteslot, &newtup, CMD_INSERT);
 	else
 		apply_handle_insert_internal(edata, edata->targetRelInfo,
-									 remoteslot);
+									 remoteslot, &newtup, rel);
 
 	finish_edata(edata);
 
@@ -2457,9 +2459,13 @@ apply_handle_insert(StringInfo s)
 static void
 apply_handle_insert_internal(ApplyExecutionData *edata,
 							 ResultRelInfo *relinfo,
-							 TupleTableSlot *remoteslot)
+							 TupleTableSlot *remoteslot,
+							 LogicalRepTupleData *newtup,
+							 LogicalRepRelMapEntry *rel_entry)
 {
 	EState	   *estate = edata->estate;
+	MemoryContext oldctx;
+	TupleTableSlot *conflictslot = NULL;
 
 	/* We must open indexes here. */
 	ExecOpenIndices(relinfo, MySubscription->detectconflict);
@@ -2469,7 +2475,33 @@ apply_handle_insert_internal(ApplyExecutionData *edata,
 
 	/* Do the insert. */
 	TargetPrivilegesCheck(relinfo->ri_RelationDesc, ACL_INSERT);
-	ExecSimpleRelationInsert(relinfo, estate, remoteslot);
+
+	if (MySubscription->detectconflict)
+		ExecSimpleRelationInsert(relinfo, estate, remoteslot, &conflictslot);
+	else
+		ExecSimpleRelationInsert(relinfo, estate, remoteslot, NULL);
+
+
+	/* Apply remote tuple by converting INSERT to UPDATE */
+	if (conflictslot)
+	{
+		EPQState	epqstate;
+
+		EvalPlanQualInit(&epqstate, estate, NULL, NIL, -1, NIL);
+
+		/* Process and store remote tuple in the slot */
+		oldctx = MemoryContextSwitchTo(GetPerTupleMemoryContext(estate));
+		slot_modify_data(remoteslot, conflictslot, rel_entry, newtup);
+		MemoryContextSwitchTo(oldctx);
+
+		EvalPlanQualSetSlot(&epqstate, remoteslot);
+
+		/* Do the update */
+		TargetPrivilegesCheck(relinfo->ri_RelationDesc, ACL_UPDATE);
+		ExecSimpleRelationUpdate(relinfo, estate, &epqstate, conflictslot,
+								 remoteslot);
+	}
+
 
 	/* Cleanup. */
 	ExecCloseIndices(relinfo);
@@ -2651,6 +2683,8 @@ apply_handle_update_internal(ApplyExecutionData *edata,
 	TupleTableSlot *localslot;
 	bool		found;
 	MemoryContext oldctx;
+	bool		apply_remote = true;
+	ConflictResolver resolver;
 
 	EvalPlanQualInit(&epqstate, estate, NULL, NIL, -1, NIL);
 	ExecOpenIndices(relinfo, false);
@@ -2674,35 +2708,73 @@ apply_handle_update_internal(ApplyExecutionData *edata,
 
 		/*
 		 * If conflict detection is enabled, check whether the local tuple was
-		 * modified by a different origin. If detected, report the conflict.
+		 * modified by a different origin. If detected, report the conflict
+		 * and configured resolver.
 		 */
 		if (MySubscription->detectconflict &&
 			GetTupleCommitTs(localslot, &localxmin, &localorigin, &localts) &&
 			localorigin != replorigin_session_origin)
-			ReportApplyConflict(LOG, CT_UPDATE_DIFFER, localrel, InvalidOid,
-								localxmin, localorigin, localts, NULL);
+		{
+			resolver = GetConflictResolver(localslot, localrel, CT_UPDATE_DIFFER,
+										   &apply_remote, NULL, InvalidOid,
+										   localxmin, localorigin, localts);
 
-		/* Process and store remote tuple in the slot */
-		oldctx = MemoryContextSwitchTo(GetPerTupleMemoryContext(estate));
-		slot_modify_data(remoteslot, localslot, relmapentry, newtup);
-		MemoryContextSwitchTo(oldctx);
+			ReportApplyConflict(LOG, CT_UPDATE_DIFFER, resolver, localrel,
+								InvalidOid, localxmin, localorigin, localts,
+								NULL);
+		}
 
-		EvalPlanQualSetSlot(&epqstate, remoteslot);
+		/*
+		 * Apply the change if configured resolver is in favor of that, else
+		 * ignore the remote update.
+		 */
+		if (apply_remote)
+		{
+			/* Process and store remote tuple in the slot */
+			oldctx = MemoryContextSwitchTo(GetPerTupleMemoryContext(estate));
+			slot_modify_data(remoteslot, localslot, relmapentry, newtup);
+			MemoryContextSwitchTo(oldctx);
 
-		/* Do the actual update. */
-		TargetPrivilegesCheck(relinfo->ri_RelationDesc, ACL_UPDATE);
-		ExecSimpleRelationUpdate(relinfo, estate, &epqstate, localslot,
-								 remoteslot);
+			EvalPlanQualSetSlot(&epqstate, remoteslot);
+
+			/* Do the actual update. */
+			TargetPrivilegesCheck(relinfo->ri_RelationDesc, ACL_UPDATE);
+			ExecSimpleRelationUpdate(relinfo, estate, &epqstate, localslot,
+									 remoteslot);
+		}
 	}
 	else
 	{
 		/*
-		 * The tuple to be updated could not be found.  Do nothing except for
-		 * emitting a log message.
+		 * The tuple to be updated could not be found. Report the conflict. If
+		 * the configured resolver is in favor of applying the change, convert
+		 * UPDATE to INSERT and apply the change.
 		 */
 		if (MySubscription->detectconflict)
-			ReportApplyConflict(LOG, CT_UPDATE_MISSING, localrel, InvalidOid,
-								InvalidTransactionId, InvalidRepOriginId, 0, NULL);
+		{
+			resolver = GetConflictResolver(localslot, localrel, CT_UPDATE_MISSING,
+										   &apply_remote, newtup, InvalidOid,
+										   InvalidTransactionId,
+										   InvalidRepOriginId, 0);
+
+			ReportApplyConflict(LOG, CT_UPDATE_MISSING, resolver, localrel,
+								InvalidOid, InvalidTransactionId,
+								InvalidRepOriginId, 0, NULL);
+
+			/* Process and store remote tuple in the slot */
+			oldctx = MemoryContextSwitchTo(GetPerTupleMemoryContext(estate));
+			slot_store_data(remoteslot, relmapentry, newtup);
+			slot_fill_defaults(relmapentry, estate, remoteslot);
+			MemoryContextSwitchTo(oldctx);
+
+			if (apply_remote)
+			{
+				elog(LOG, "Converting UPDATE to INSERT and applying!");
+				apply_handle_insert_internal(edata, relinfo, remoteslot,
+											 newtup, relmapentry);
+			}
+
+		}
 	}
 
 	/* Cleanup. */
@@ -2834,12 +2906,25 @@ apply_handle_delete_internal(ApplyExecutionData *edata,
 	else
 	{
 		/*
-		 * The tuple to be deleted could not be found.  Do nothing except for
-		 * emitting a log message.
+		 * The tuple to be deleted could not be found. Based on resolver
+		 * configured, either skip and log a message or emit an error.
 		 */
 		if (MySubscription->detectconflict)
-			ReportApplyConflict(LOG, CT_DELETE_MISSING, localrel, InvalidOid,
-								InvalidTransactionId, InvalidRepOriginId, 0, NULL);
+		{
+			ConflictResolver resolver;
+			bool		apply_remote = false;
+
+			resolver = GetConflictResolver(localslot, localrel, CT_DELETE_MISSING,
+										   &apply_remote, NULL, InvalidOid,
+										   InvalidTransactionId,
+										   InvalidRepOriginId, 0);
+
+			/* Resolver is set to skip, thus report the conflict and skip */
+			if (!apply_remote)
+				ReportApplyConflict(LOG, CT_DELETE_MISSING, resolver, localrel,
+									InvalidOid, InvalidTransactionId,
+									InvalidRepOriginId, 0, NULL);
+		}
 	}
 
 	/* Cleanup. */
@@ -2972,19 +3057,21 @@ apply_handle_tuple_routing(ApplyExecutionData *edata,
 	}
 	MemoryContextSwitchTo(oldctx);
 
-	/* Check if we can do the update or delete on the leaf partition. */
-	if (operation == CMD_UPDATE || operation == CMD_DELETE)
+	if (operation == CMD_INSERT || operation == CMD_UPDATE ||
+		operation == CMD_DELETE)
 	{
-		part_entry = logicalrep_partition_open(relmapentry, partrel,
-											   attrmap);
-		check_relation_updatable(part_entry);
+		part_entry = logicalrep_partition_open(relmapentry, partrel, attrmap);
+
+		/* Check if we can do the update or delete on the leaf partition */
+		if (operation != CMD_INSERT)
+			check_relation_updatable(part_entry);
 	}
 
 	switch (operation)
 	{
 		case CMD_INSERT:
 			apply_handle_insert_internal(edata, partrelinfo,
-										 remoteslot_part);
+										 remoteslot_part, newtup, part_entry);
 			break;
 
 		case CMD_DELETE:
@@ -3006,6 +3093,9 @@ apply_handle_tuple_routing(ApplyExecutionData *edata,
 				ResultRelInfo *partrelinfo_new;
 				Relation	partrel_new;
 				bool		found;
+				LogicalRepRelMapEntry *part_entry_new = NULL;
+				ConflictResolver resolver;
+				bool		apply_remote = true;
 
 				/* Get the matching local tuple from the partition. */
 				found = FindReplTupleInLocalRel(edata, partrel,
@@ -3015,26 +3105,85 @@ apply_handle_tuple_routing(ApplyExecutionData *edata,
 				if (!found)
 				{
 					/*
-					 * The tuple to be updated could not be found.  Do nothing
-					 * except for emitting a log message.
+					 * The tuple to be updated could not be found. Report the
+					 * conflict and resolver. And take action based on the
+					 * configured resolver.
 					 */
 					if (MySubscription->detectconflict)
-						ReportApplyConflict(LOG, CT_UPDATE_MISSING,
-											partrel, InvalidOid,
-											InvalidTransactionId,
+					{
+						resolver = GetConflictResolver(localslot, partrel, CT_UPDATE_MISSING,
+													   &apply_remote, newtup, InvalidOid,
+													   InvalidTransactionId, InvalidRepOriginId, 0);
+
+						ReportApplyConflict(LOG, CT_UPDATE_MISSING, resolver, partrel,
+											InvalidOid, InvalidTransactionId,
 											InvalidRepOriginId, 0, NULL);
 
-					return;
+						if (apply_remote)
+						{
+							/*
+							 * Resolver is in favour of applying the remote
+							 * changes. Prepare the slot for the INSERT.
+							 */
+							oldctx = MemoryContextSwitchTo(GetPerTupleMemoryContext(estate));
+							slot_store_data(remoteslot_part, part_entry, newtup);
+							slot_fill_defaults(part_entry, estate, remoteslot_part);
+							MemoryContextSwitchTo(oldctx);
+						}
+					}
 				}
+				else
+				{
+					RepOriginId localorigin;
+					TransactionId localxmin;
+					TimestampTz localts;
 
-				/*
-				 * Apply the update to the local tuple, putting the result in
-				 * remoteslot_part.
-				 */
-				oldctx = MemoryContextSwitchTo(GetPerTupleMemoryContext(estate));
-				slot_modify_data(remoteslot_part, localslot, part_entry,
-								 newtup);
-				MemoryContextSwitchTo(oldctx);
+					/*
+					 * The tuple to be updated is found. If conflict detection
+					 * is enabled, check whether the local tuple was modified
+					 * by a different origin. If detected, report and resolve
+					 * the conflict.
+					 */
+					if (MySubscription->detectconflict &&
+						GetTupleCommitTs(localslot, &localxmin, &localorigin, &localts) &&
+						localorigin != replorigin_session_origin)
+					{
+						resolver = GetConflictResolver(localslot, partrel, CT_UPDATE_DIFFER,
+													   &apply_remote, NULL, InvalidOid,
+													   localxmin, localorigin, localts);
+
+						ReportApplyConflict(LOG, CT_UPDATE_DIFFER, resolver, partrel,
+											InvalidOid, localxmin, localorigin, localts,
+											NULL);
+					}
+
+					if (apply_remote)
+					{
+						/*
+						 * We can reach here in two cases:
+						 *
+						 * 1. If we found a tuple but conflict detection is
+						 * OFF
+						 *
+						 * 2. If we found a tuple and resolver is in favor of
+						 * applying the change when conflict detection is ON
+						 *
+						 * Putting the result in remoteslot_part.
+						 */
+						oldctx = MemoryContextSwitchTo(GetPerTupleMemoryContext(estate));
+						slot_modify_data(remoteslot_part, localslot, part_entry,
+										 newtup);
+						MemoryContextSwitchTo(oldctx);
+					}
+					else
+
+						/*
+						 * apply_remote can be toggled if resolver for
+						 * update_differ is set to skip. Ignore remote update.
+						 */
+						return;
+
+				}
 
 				/*
 				 * Does the updated tuple still satisfy the current
@@ -3044,27 +3193,59 @@ apply_handle_tuple_routing(ApplyExecutionData *edata,
 					ExecPartitionCheck(partrelinfo, remoteslot_part, estate,
 									   false))
 				{
-					/*
-					 * Yes, so simply UPDATE the partition.  We don't call
-					 * apply_handle_update_internal() here, which would
-					 * normally do the following work, to avoid repeating some
-					 * work already done above to find the local tuple in the
-					 * partition.
-					 */
-					EPQState	epqstate;
-
-					EvalPlanQualInit(&epqstate, estate, NULL, NIL, -1, NIL);
-					ExecOpenIndices(partrelinfo, false);
-
-					EvalPlanQualSetSlot(&epqstate, remoteslot_part);
-					TargetPrivilegesCheck(partrelinfo->ri_RelationDesc,
-										  ACL_UPDATE);
-					ExecSimpleRelationUpdate(partrelinfo, estate, &epqstate,
-											 localslot, remoteslot_part);
-					ExecCloseIndices(partrelinfo);
-					EvalPlanQualEnd(&epqstate);
+					if (found && apply_remote)
+					{
+						/*
+						 * Yes, so simply UPDATE the partition.  We don't call
+						 * apply_handle_update_internal() here, which would
+						 * normally do the following work, to avoid repeating
+						 * some work already done above to find the local
+						 * tuple in the partition.
+						 *
+						 * Do the update in cases - 1. conflict detection is
+						 * OFF and found a tuple 2. conflict detection is ON,
+						 * update_differ conflict is detected for the found
+						 * tuple and the resolver is in favour of applying the
+						 * update.
+						 */
+
+						EPQState	epqstate;
+
+						EvalPlanQualInit(&epqstate, estate, NULL, NIL, -1, NIL);
+						ExecOpenIndices(partrelinfo, false);
+
+						EvalPlanQualSetSlot(&epqstate, remoteslot_part);
+						TargetPrivilegesCheck(partrelinfo->ri_RelationDesc,
+											  ACL_UPDATE);
+						ExecSimpleRelationUpdate(partrelinfo, estate, &epqstate,
+												 localslot, remoteslot_part);
+						ExecCloseIndices(partrelinfo);
+						EvalPlanQualEnd(&epqstate);
+
+					}
+					else if (apply_remote)
+					{
+						/*
+						 * Tuple is not found but update_missing resolver is
+						 * in favour of applying the change as INSERT.
+						 */
+						apply_handle_insert_internal(edata, partrelinfo,
+													 remoteslot_part, newtup,
+													 part_entry);
+					}
 				}
-				else
+
+				/*
+				 * Updated tuple doesn't satisfy the current partition's
+				 * constraint.
+				 *
+				 * If conflict detection is OFF, proceed by always applying
+				 * the update (as 'apply_remote' is by default true). If
+				 * conflict detection is ON, 'apply_remote' can be OFF as well
+				 * if the resolver for update_missing conflict conveys to skip
+				 * the update.
+				 */
+				else if (apply_remote)
 				{
 					/* Move the tuple into the new partition. */
 
@@ -3105,10 +3286,16 @@ apply_handle_tuple_routing(ApplyExecutionData *edata,
 											 get_namespace_name(RelationGetNamespace(partrel_new)),
 											 RelationGetRelationName(partrel_new));
 
-					/* DELETE old tuple found in the old partition. */
-					apply_handle_delete_internal(edata, partrelinfo,
-												 localslot,
-												 part_entry->localindexoid);
+					/*
+					 * If tuple is found, delete it from old partition. We can
+					 * reach this flow even for the case when the 'found' flag
+					 * is false for 'update_missing' conflict and resolver is
+					 * in favor of inserting the tuple.
+					 */
+					if (found)
+						apply_handle_delete_internal(edata, partrelinfo,
+													 localslot,
+													 part_entry->localindexoid);
 
 					/* INSERT new tuple into the new partition. */
 
@@ -3124,19 +3311,25 @@ apply_handle_tuple_routing(ApplyExecutionData *edata,
 					map = ExecGetRootToChildMap(partrelinfo_new, estate);
 					if (map != NULL)
 					{
+						attrmap = map->attrMap;
 						remoteslot_part = execute_attr_map_slot(map->attrMap,
 																remoteslot,
 																remoteslot_part);
 					}
 					else
 					{
+						attrmap = NULL;
 						remoteslot_part = ExecCopySlot(remoteslot_part,
 													   remoteslot);
 						slot_getallattrs(remoteslot);
 					}
 					MemoryContextSwitchTo(oldctx);
+					part_entry_new = logicalrep_partition_open(part_entry,
+															   partrel_new,
+															   attrmap);
 					apply_handle_insert_internal(edata, partrelinfo_new,
-												 remoteslot_part);
+												 remoteslot_part, newtup,
+												 part_entry_new);
 				}
 			}
 			break;
diff --git a/src/include/executor/executor.h b/src/include/executor/executor.h
index 9770752ea3..bc72b1f4fd 100644
--- a/src/include/executor/executor.h
+++ b/src/include/executor/executor.h
@@ -18,6 +18,8 @@
 #include "fmgr.h"
 #include "nodes/lockoptions.h"
 #include "nodes/parsenodes.h"
+#include "replication/logicalproto.h"
+#include "replication/logicalrelation.h"
 #include "utils/memutils.h"
 
 
@@ -655,7 +657,8 @@ extern bool RelationFindReplTupleSeq(Relation rel, LockTupleMode lockmode,
 									 TupleTableSlot *searchslot, TupleTableSlot *outslot);
 
 extern void ExecSimpleRelationInsert(ResultRelInfo *resultRelInfo,
-									 EState *estate, TupleTableSlot *slot);
+									 EState *estate, TupleTableSlot *slot,
+									 TupleTableSlot **conflictsloty);
 extern void ExecSimpleRelationUpdate(ResultRelInfo *resultRelInfo,
 									 EState *estate, EPQState *epqstate,
 									 TupleTableSlot *searchslot, TupleTableSlot *slot);
diff --git a/src/include/replication/conflict.h b/src/include/replication/conflict.h
index 7eff93eff3..aa21886ee7 100644
--- a/src/include/replication/conflict.h
+++ b/src/include/replication/conflict.h
@@ -13,6 +13,8 @@
 #include "catalog/objectaddress.h"
 #include "executor/tuptable.h"
 #include "nodes/execnodes.h"
+#include "replication/logicalproto.h"
+#include "replication/logicalrelation.h"
 #include "utils/relcache.h"
 #include "utils/timestamp.h"
 
@@ -72,9 +74,20 @@ typedef enum ConflictResolver
 extern bool GetTupleCommitTs(TupleTableSlot *localslot, TransactionId *xmin,
 							 RepOriginId *localorigin, TimestampTz *localts);
 extern void ReportApplyConflict(int elevel, ConflictType type,
-								Relation localrel, Oid conflictidx,
-								TransactionId localxmin, RepOriginId localorigin,
-								TimestampTz localts, TupleTableSlot *conflictslot);
+								ConflictResolver resolver, Relation localrel,
+								Oid conflictidx, TransactionId localxmin,
+								RepOriginId localorigin, TimestampTz localts,
+								TupleTableSlot *conflictslot);
 extern void InitConflictIndexes(ResultRelInfo *relInfo);
 extern void ExecConflictResolverStmt(ConflictResolverStmt *stmt);
+extern ConflictResolver GetConflictResolver(TupleTableSlot *localslot,
+											Relation localrel,
+											ConflictType type,
+											bool *apply_remote,
+											LogicalRepTupleData *newtup,
+											Oid conflictidx, TransactionId xmin,
+											RepOriginId origin,
+											TimestampTz committs);
+extern bool CanCreateFullTuple(Relation localrel,
+							   LogicalRepTupleData *newtup);
 #endif
diff --git a/src/test/subscription/t/029_on_error.pl b/src/test/subscription/t/029_on_error.pl
index 496a3c6cd9..c746191601 100644
--- a/src/test/subscription/t/029_on_error.pl
+++ b/src/test/subscription/t/029_on_error.pl
@@ -113,6 +113,10 @@ $node_subscriber->safe_psql('postgres',
 	"CREATE SUBSCRIPTION sub CONNECTION '$publisher_connstr' PUBLICATION pub WITH (disable_on_error = true, streaming = on, two_phase = on, detect_conflict = on)"
 );
 
+# Set 'ERROR' conflict resolver for 'insert_exist' conflict type
+$node_subscriber->safe_psql('postgres',"set conflict resolver 'error' for 'insert_exists'");
+
+
 # Initial synchronization failure causes the subscription to be disabled.
 $node_subscriber->poll_query_until('postgres',
 	"SELECT subenabled = false FROM pg_catalog.pg_subscription WHERE subname = 'sub'"
@@ -177,6 +181,9 @@ $result = $node_subscriber->safe_psql('postgres',
 is($result, "0",
 	"check all prepared transactions are resolved on the subscriber");
 
+# Reset conflict resolver for 'insert_exist' conflict type to default.
+$node_subscriber->safe_psql('postgres',"reset conflict resolver for 'insert_exists'");
+
 $node_subscriber->stop;
 $node_publisher->stop;
 
-- 
2.34.1



  [application/octet-stream] v3-0002-DDL-command-to-configure-Global-Conflict-Resolver.patch (26.1K, ../../CAJpy0uCv8R1Y5herLLANhGGqCotAFzBw3ikzhpXZvbqLDuoMTw@mail.gmail.com/5-v3-0002-DDL-command-to-configure-Global-Conflict-Resolver.patch)
  download | inline diff:
From fbf56a37afd3e92d4fa4da30d49cd3f8d13635de Mon Sep 17 00:00:00 2001
From: Shveta Malik <[email protected]>
Date: Mon, 24 Jun 2024 09:55:15 +0530
Subject: [PATCH v3 2/5] DDL command to configure Global Conflict Resolvers

This patch adds new DDL commands to configure resolvers
at global level:

a) To set global resolver for a given conflict_type:
SET CONFLICT RESOLVER 'conflict_resolver' FOR 'conflict_type'

b) To reset to default:
RESET CONFLICT RESOLVER FOR 'conflict_type'

A new catalog table pg_conflict has been created to store
global conflict_type and conflict_resolver configurations given by
above DDL command. Initially, this catalog table holds default
configuration for resolvers which is overwritten by the ones given
by the user in 'SET CONFLICT RESOLVER' command.
'RESET CONFLICT RESOLVER' command will reset the resolver to default.

This patch provides support to configure resolvers for below conflict
types:
- insert_exists
- update_differ
- update_missing
- delete_missing
---
 src/backend/parser/gram.y                     |  42 +++-
 src/backend/replication/logical/conflict.c    | 215 +++++++++++++++++-
 src/backend/tcop/utility.c                    |  15 ++
 src/include/catalog/Makefile                  |   4 +-
 src/include/catalog/meson.build               |   2 +
 src/include/catalog/pg_conflict.dat           |  20 ++
 src/include/catalog/pg_conflict.h             |  43 ++++
 src/include/nodes/parsenodes.h                |  12 +
 src/include/parser/kwlist.h                   |   1 +
 src/include/replication/conflict.h            |  38 +++-
 src/include/tcop/cmdtaglist.h                 |   1 +
 .../regress/expected/conflict_resolver.out    |  50 ++++
 src/test/regress/parallel_schedule            |   2 +-
 src/test/regress/sql/conflict_resolver.sql    |  27 +++
 src/tools/pgindent/typedefs.list              |   2 +
 15 files changed, 467 insertions(+), 7 deletions(-)
 create mode 100644 src/include/catalog/pg_conflict.dat
 create mode 100644 src/include/catalog/pg_conflict.h
 create mode 100644 src/test/regress/expected/conflict_resolver.out
 create mode 100644 src/test/regress/sql/conflict_resolver.sql

diff --git a/src/backend/parser/gram.y b/src/backend/parser/gram.y
index a043fd4c66..42726fe3a6 100644
--- a/src/backend/parser/gram.y
+++ b/src/backend/parser/gram.y
@@ -292,7 +292,7 @@ static Node *makeRecursiveViewSelect(char *relname, List *aliases, Node *query);
 		AlterRoleStmt AlterRoleSetStmt AlterPolicyStmt AlterStatsStmt
 		AlterDefaultPrivilegesStmt DefACLAction
 		AnalyzeStmt CallStmt ClosePortalStmt ClusterStmt CommentStmt
-		ConstraintsSetStmt CopyStmt CreateAsStmt CreateCastStmt
+		ConflictResolverStmt ConstraintsSetStmt CopyStmt CreateAsStmt CreateCastStmt
 		CreateDomainStmt CreateExtensionStmt CreateGroupStmt CreateOpClassStmt
 		CreateOpFamilyStmt AlterOpFamilyStmt CreatePLangStmt
 		CreateSchemaStmt CreateSeqStmt CreateStmt CreateStatsStmt CreateTableSpaceStmt
@@ -613,6 +613,7 @@ static Node *makeRecursiveViewSelect(char *relname, List *aliases, Node *query);
 %type <ival>	opt_check_option
 
 %type <str>		opt_provider security_label
+%type <str>		conflict_type conflict_resolver
 
 %type <target>	xml_attribute_el
 %type <list>	xml_attribute_list xml_attributes
@@ -772,7 +773,7 @@ static Node *makeRecursiveViewSelect(char *relname, List *aliases, Node *query);
 
 	RANGE READ REAL REASSIGN RECHECK RECURSIVE REF_P REFERENCES REFERENCING
 	REFRESH REINDEX RELATIVE_P RELEASE RENAME REPEATABLE REPLACE REPLICA
-	RESET RESTART RESTRICT RETURN RETURNING RETURNS REVOKE RIGHT ROLE ROLLBACK ROLLUP
+	RESET RESOLVER RESTART RESTRICT RETURN RETURNING RETURNS REVOKE RIGHT ROLE ROLLBACK ROLLUP
 	ROUTINE ROUTINES ROW ROWS RULE
 
 	SAVEPOINT SCALAR SCHEMA SCHEMAS SCROLL SEARCH SECOND_P SECURITY SELECT
@@ -1039,6 +1040,7 @@ stmt:
 			| ClosePortalStmt
 			| ClusterStmt
 			| CommentStmt
+			| ConflictResolverStmt
 			| ConstraintsSetStmt
 			| CopyStmt
 			| CreateAmStmt
@@ -7266,7 +7268,41 @@ comment_text:
 			| NULL_P							{ $$ = NULL; }
 		;
 
+/*****************************************************************************
+ *
+ *  SET CONFLICT RESOLVER <conflict_resolver> FOR <conflict_type>
+ *  RESET CONFLICT RESOLVER FOR <conflict_type>
+ *
+ *****************************************************************************/
+
+ConflictResolverStmt:
+			SET CONFLICT RESOLVER conflict_resolver FOR conflict_type
+				{
+					ConflictResolverStmt *n = makeNode(ConflictResolverStmt);
+
+					n->conflict_resolver = $4;
+					n->conflict_type = $6;
+					n->isReset = false;
+					$$ = (Node *) n;
+				}
+			| RESET CONFLICT RESOLVER FOR conflict_type
+				{
+					ConflictResolverStmt *n = makeNode(ConflictResolverStmt);
 
+					n->conflict_type = $5;
+					n->isReset = true;
+					$$ = (Node *) n;
+				}
+		;
+conflict_type:
+			Sconst								{ $$ = $1; }
+			| NULL_P							{ $$ = NULL; }
+		;
+
+conflict_resolver:
+			Sconst								{ $$ = $1; }
+			| NULL_P							{ $$ = NULL; }
+		;
 /*****************************************************************************
  *
  *  SECURITY LABEL [FOR <provider>] ON <object> IS <label>
@@ -17797,6 +17833,7 @@ unreserved_keyword:
 			| REPLACE
 			| REPLICA
 			| RESET
+			| RESOLVER
 			| RESTART
 			| RESTRICT
 			| RETURN
@@ -18428,6 +18465,7 @@ bare_label_keyword:
 			| REPLACE
 			| REPLICA
 			| RESET
+			| RESOLVER
 			| RESTART
 			| RESTRICT
 			| RETURN
diff --git a/src/backend/replication/logical/conflict.c b/src/backend/replication/logical/conflict.c
index f24f048054..87b1ea0ab3 100644
--- a/src/backend/replication/logical/conflict.c
+++ b/src/backend/replication/logical/conflict.c
@@ -1,13 +1,13 @@
 /*-------------------------------------------------------------------------
  * conflict.c
- *	   Functionality for detecting and logging conflicts.
+ *	   Functionality for detecting, logging and configuring conflicts.
  *
  * Copyright (c) 2024, PostgreSQL Global Development Group
  *
  * IDENTIFICATION
  *	  src/backend/replication/logical/conflict.c
  *
- * This file contains the code for detecting and logging conflicts on
+ * This file contains the code for detecting and handling conflicts on
  * the subscriber during logical replication.
  *-------------------------------------------------------------------------
  */
@@ -15,10 +15,19 @@
 #include "postgres.h"
 
 #include "access/commit_ts.h"
+#include "access/genam.h"
+#include "access/htup_details.h"
+#include "access/skey.h"
+#include "access/table.h"
+#include "catalog/indexing.h"
+#include "catalog/pg_conflict.h"
 #include "replication/conflict.h"
 #include "replication/origin.h"
+#include "utils/builtins.h"
+#include "utils/fmgroids.h"
 #include "utils/lsyscache.h"
 #include "utils/rel.h"
+#include "utils/timestamp.h"
 
 const char *const ConflictTypeNames[] = {
 	[CT_INSERT_EXISTS] = "insert_exists",
@@ -27,6 +36,51 @@ const char *const ConflictTypeNames[] = {
 	[CT_DELETE_MISSING] = "delete_missing"
 };
 
+const char *const ConflictResolverNames[] = {
+	[CR_REMOTE_APPLY] = "remote_apply",
+	[CR_KEEP_LOCAL] = "keep_local",
+	[CR_APPLY_OR_SKIP] = "apply_or_skip",
+	[CR_APPLY_OR_ERROR] = "apply_or_error",
+	[CR_SKIP] = "skip",
+	[CR_ERROR] = "error"
+};
+
+#define CONFLICT_TYPE_MAX_RESOLVERS 4
+
+/*
+ * Valid conflict resolvers for each conflict type.
+ *
+ * XXX: If we do not want to maintain different resolvers such as
+ * apply_or_skip and apply_or_error for update_missing conflict,
+ * then we can retain remote_apply and keep_local only. Then these
+ * resolvers in context of update_missing will mean:
+ *
+ * keep_local: do not apply the update as INSERT.
+ * remote_apply: apply the update as INSERT. If we could not apply,
+ * then log and skip.
+ *
+ * Similarly SKIP can be replaced with KEEP_LOCAL for both update_missing
+ * and delete_missing conflicts. For missing rows, 'SKIP' sounds more user
+ * friendly name for a resolver and thus has been added here.
+ */
+const int	ConflictTypeResolverMap[][CONFLICT_TYPE_MAX_RESOLVERS] = {
+	[CT_INSERT_EXISTS] = {CR_REMOTE_APPLY, CR_KEEP_LOCAL, CR_ERROR},
+	[CT_UPDATE_DIFFER] = {CR_REMOTE_APPLY, CR_KEEP_LOCAL, CR_ERROR},
+	[CT_UPDATE_MISSING] = {CR_APPLY_OR_SKIP, CR_APPLY_OR_ERROR, CR_SKIP, CR_ERROR},
+	[CT_DELETE_MISSING] = {CR_SKIP, CR_ERROR}
+};
+
+/*
+ * Default conflict resolver for each conflict type.
+ * If this changes, change it in pg_conflict.dat as well.
+ */
+const int	ConflictTypeDefaultResolvers[] = {
+	[CT_INSERT_EXISTS] = CR_REMOTE_APPLY,
+	[CT_UPDATE_DIFFER] = CR_REMOTE_APPLY,
+	[CT_UPDATE_MISSING] = CR_APPLY_OR_SKIP,
+	[CT_DELETE_MISSING] = CR_SKIP
+};
+
 static char *build_index_value_desc(Oid indexoid, TupleTableSlot *conflictslot);
 static int	errdetail_apply_conflict(ConflictType type, Oid conflictidx,
 									 TransactionId localxmin,
@@ -34,6 +88,7 @@ static int	errdetail_apply_conflict(ConflictType type, Oid conflictidx,
 									 TimestampTz localts,
 									 TupleTableSlot *conflictslot);
 
+
 /*
  * Get the xmin and commit timestamp data (origin and timestamp) associated
  * with the provided local tuple.
@@ -185,3 +240,159 @@ build_index_value_desc(Oid indexoid, TupleTableSlot *conflictslot)
 
 	return conflict_row;
 }
+
+/*
+ * Validate the conflict type and resolver.
+ *
+ * Return ConflictType enum value corresponding to given conflict_type.
+ */
+static ConflictType
+validate_conflict_type_and_resolver(char *conflict_type, char *conflict_resolver,
+									bool isReset)
+{
+	ConflictType type;
+	ConflictResolver resolver;
+	bool		valid = false;
+	int			i;
+
+	/* Check conflict type validity */
+	for (type = CT_MIN; type <= CT_MAX; type++)
+	{
+		if (strcmp(ConflictTypeNames[type], conflict_type) == 0)
+		{
+			valid = true;
+			break;
+		}
+	}
+
+	if (!valid)
+		ereport(ERROR,
+				errcode(ERRCODE_INVALID_PARAMETER_VALUE),
+				errmsg("%s is not a valid conflict type", conflict_type));
+
+	/* If it is RESET statement, we are done */
+	if (isReset)
+		return type;
+
+	/* Reset */
+	valid = false;
+
+	/* Check conflict resolver validity. */
+	for (resolver = CR_MIN; resolver <= CR_MAX; resolver++)
+	{
+		if (strcmp(ConflictResolverNames[resolver], conflict_resolver) == 0)
+		{
+			valid = true;
+			break;
+		}
+	}
+
+	/*
+	 * XXX: Shall we give supported resolvers list for given type in error
+	 * hint?
+	 */
+	if (!valid)
+		ereport(ERROR,
+				errcode(ERRCODE_INVALID_PARAMETER_VALUE),
+				errmsg("%s is not a valid conflict resolver", conflict_resolver));
+
+	/* Reset */
+	valid = false;
+
+	/* Check if conflict resolver is a valid one for the given conflict type */
+	for (i = 0; i < CONFLICT_TYPE_MAX_RESOLVERS; i++)
+	{
+		if (ConflictTypeResolverMap[type][i] == resolver)
+		{
+			valid = true;
+			break;
+		}
+	}
+
+	/*
+	 * XXX: Shall we give supported resolvers list for given type in error
+	 * hint?
+	 */
+	if (!valid)
+		ereport(ERROR,
+				errcode(ERRCODE_INVALID_PARAMETER_VALUE),
+				errmsg("%s is not a valid conflict resolver for conflict type %s",
+					   conflict_resolver,
+					   conflict_type));
+	return type;
+}
+
+/*
+ * Execute Conflict Resolver Stmt
+ *
+ * Validate conflict_type and conflict_resolver given by the user
+ * and save the info in pg_conflict system catalog.
+ */
+void
+ExecConflictResolverStmt(ConflictResolverStmt *stmt)
+{
+	Relation	pg_conflict;
+	Datum		values[Natts_pg_conflict];
+	bool		nulls[Natts_pg_conflict];
+	bool		replaces[Natts_pg_conflict];
+	ScanKeyData keys[1];
+	SysScanDesc scan;
+	HeapTuple	oldtup;
+	HeapTuple	newtup = NULL;
+	ConflictType type;
+
+	type = validate_conflict_type_and_resolver(stmt->conflict_type,
+											   stmt->conflict_resolver,
+											   stmt->isReset);
+
+
+	/* Prepare to update a tuple in pg_conflict system catalog */
+	memset(values, 0, sizeof(values));
+	memset(nulls, false, sizeof(nulls));
+	memset(replaces, false, sizeof(replaces));
+
+	values[Anum_pg_conflict_conftype - 1] =
+			CStringGetTextDatum(stmt->conflict_type);
+
+	if (stmt->isReset)
+	{
+		/* Set resolver to default */
+		ConflictResolver resolver = ConflictTypeDefaultResolvers[type];
+
+		values[Anum_pg_conflict_confres - 1] =
+			CStringGetTextDatum(ConflictResolverNames[resolver]);
+	}
+	else
+		values[Anum_pg_conflict_confres - 1] =
+			CStringGetTextDatum(stmt->conflict_resolver);
+
+	/* Use the index to search for a matching old tuple */
+	ScanKeyInit(&keys[0],
+				Anum_pg_conflict_conftype,
+				BTEqualStrategyNumber, F_TEXTEQ,
+				values[Anum_pg_conflict_conftype - 1]);
+
+	pg_conflict = table_open(ConflictResRelationId, RowExclusiveLock);
+
+	scan = systable_beginscan(pg_conflict, ConflictTypeIndexId, true,
+							  NULL, 1, keys);
+
+	oldtup = systable_getnext(scan);
+	if (HeapTupleIsValid(oldtup))
+	{
+		replaces[Anum_pg_conflict_confres - 1] = true;
+		newtup = heap_modify_tuple(oldtup, RelationGetDescr(pg_conflict),
+								   values, nulls, replaces);
+		CatalogTupleUpdate(pg_conflict, &oldtup->t_self, newtup);
+	}
+	else
+		Assert(oldtup);			/* We must have a tuple for given
+								 * conflict_type */
+
+	systable_endscan(scan);
+
+	if (newtup != NULL)
+		heap_freetuple(newtup);
+
+	table_close(pg_conflict, RowExclusiveLock);
+}
diff --git a/src/backend/tcop/utility.c b/src/backend/tcop/utility.c
index fa66b8017e..4ddf4aaff0 100644
--- a/src/backend/tcop/utility.c
+++ b/src/backend/tcop/utility.c
@@ -59,6 +59,7 @@
 #include "miscadmin.h"
 #include "parser/parse_utilcmd.h"
 #include "postmaster/bgwriter.h"
+#include "replication/conflict.h"
 #include "rewrite/rewriteDefine.h"
 #include "storage/fd.h"
 #include "tcop/utility.h"
@@ -163,6 +164,7 @@ ClassifyUtilityCommandAsReadOnly(Node *parsetree)
 		case T_AlterUserMappingStmt:
 		case T_CommentStmt:
 		case T_CompositeTypeStmt:
+		case T_ConflictResolverStmt:
 		case T_CreateAmStmt:
 		case T_CreateCastStmt:
 		case T_CreateConversionStmt:
@@ -1062,6 +1064,11 @@ standard_ProcessUtility(PlannedStmt *pstmt,
 				break;
 			}
 
+		case T_ConflictResolverStmt:
+			/* no event triggers for conflict types and resolvers */
+			ExecConflictResolverStmt((ConflictResolverStmt *) parsetree);
+			break;
+
 		default:
 			/* All other statement types have event trigger support */
 			ProcessUtilitySlow(pstate, pstmt, queryString,
@@ -2659,6 +2666,10 @@ CreateCommandTag(Node *parsetree)
 			tag = CMDTAG_COMMENT;
 			break;
 
+		case T_ConflictResolverStmt:
+			tag = CMDTAG_CONFLICT_RESOLVER;
+			break;
+
 		case T_SecLabelStmt:
 			tag = CMDTAG_SECURITY_LABEL;
 			break;
@@ -3334,6 +3345,10 @@ GetCommandLogLevel(Node *parsetree)
 			lev = LOGSTMT_DDL;
 			break;
 
+		case T_ConflictResolverStmt:
+			lev = LOGSTMT_DDL;
+			break;
+
 		case T_SecLabelStmt:
 			lev = LOGSTMT_DDL;
 			break;
diff --git a/src/include/catalog/Makefile b/src/include/catalog/Makefile
index 167f91a6e3..8619d73e5a 100644
--- a/src/include/catalog/Makefile
+++ b/src/include/catalog/Makefile
@@ -81,7 +81,8 @@ CATALOG_HEADERS := \
 	pg_publication_namespace.h \
 	pg_publication_rel.h \
 	pg_subscription.h \
-	pg_subscription_rel.h
+	pg_subscription_rel.h \
+	pg_conflict.h
 
 GENERATED_HEADERS := $(CATALOG_HEADERS:%.h=%_d.h)
 
@@ -97,6 +98,7 @@ POSTGRES_BKI_DATA = \
 	pg_cast.dat \
 	pg_class.dat \
 	pg_collation.dat \
+	pg_conflict.dat \
 	pg_conversion.dat \
 	pg_database.dat \
 	pg_language.dat \
diff --git a/src/include/catalog/meson.build b/src/include/catalog/meson.build
index f70d1daba5..4d6732a303 100644
--- a/src/include/catalog/meson.build
+++ b/src/include/catalog/meson.build
@@ -69,6 +69,7 @@ catalog_headers = [
   'pg_publication_rel.h',
   'pg_subscription.h',
   'pg_subscription_rel.h',
+  'pg_conflict.h',
 ]
 
 # The .dat files we need can just be listed alphabetically.
@@ -81,6 +82,7 @@ bki_data = [
   'pg_cast.dat',
   'pg_class.dat',
   'pg_collation.dat',
+  'pg_conflict.dat',
   'pg_conversion.dat',
   'pg_database.dat',
   'pg_language.dat',
diff --git a/src/include/catalog/pg_conflict.dat b/src/include/catalog/pg_conflict.dat
new file mode 100644
index 0000000000..a3e5e10d97
--- /dev/null
+++ b/src/include/catalog/pg_conflict.dat
@@ -0,0 +1,20 @@
+#----------------------------------------------------------------------
+#
+# pg_conflict.dat
+#    Initial contents of the pg_conflict system catalog.
+#
+# Portions Copyright (c) 1996-2024, PostgreSQL Global Development Group
+# Portions Copyright (c) 1994, Regents of the University of California
+#
+# src/include/catalog/pg_conflict.dat
+#
+#----------------------------------------------------------------------
+
+[
+
+{ conftype => 'insert_exists', confres => 'remote_apply' },
+{ conftype => 'update_differ', confres => 'remote_apply' },
+{ conftype => 'update_missing', confres => 'apply_or_skip' },
+{ conftype => 'delete_missing', confres => 'skip' }
+
+]
diff --git a/src/include/catalog/pg_conflict.h b/src/include/catalog/pg_conflict.h
new file mode 100644
index 0000000000..e3fe3e6d30
--- /dev/null
+++ b/src/include/catalog/pg_conflict.h
@@ -0,0 +1,43 @@
+/* -------------------------------------------------------------------------
+ *
+ * pg_conflict.h
+ *	  definition of the "global conflict detection" system catalog
+ *	  (pg_conflict)
+ *
+ * Portions Copyright (c) 1996-2024, PostgreSQL Global Development Group
+ * Portions Copyright (c) 1994, Regents of the University of California
+ *
+ * src/include/catalog/pg_conflict.h
+ *
+ * NOTES
+ *	  The Catalog.pm module reads this file and derives schema
+ *	  information.
+ *
+ * -------------------------------------------------------------------------
+ */
+#ifndef PG_CONFLICT_H
+#define PG_CONFLICT_H
+
+#include "catalog/genbki.h"
+#include "catalog/pg_conflict_d.h"
+
+/* ----------------
+ *		pg_conflict definition.  cpp turns this into
+ *		typedef struct FormData_pg_conflict
+ * ----------------
+ */
+CATALOG(pg_conflict,8688,ConflictResRelationId)
+{
+#ifdef CATALOG_VARLEN			/* variable-length fields start here */
+	text		conftype BKI_FORCE_NOT_NULL;	/* conflict type */
+	text		confres BKI_FORCE_NOT_NULL; /* conflict resolver */
+#endif
+} FormData_pg_conflict;
+
+DECLARE_TOAST(pg_conflict, 8689, 8690);
+
+DECLARE_UNIQUE_INDEX_PKEY(pg_conflict_type_index, 8691, ConflictTypeIndexId, pg_conflict, btree(conftype text_ops));
+
+MAKE_SYSCACHE(CONFLICTTYPE, pg_conflict_type_index, 16);
+
+#endif							/* PG_CONFLICT_H */
diff --git a/src/include/nodes/parsenodes.h b/src/include/nodes/parsenodes.h
index 85a62b538e..1d41169d5e 100644
--- a/src/include/nodes/parsenodes.h
+++ b/src/include/nodes/parsenodes.h
@@ -3262,6 +3262,18 @@ typedef struct CommentStmt
 	char	   *comment;		/* Comment to insert, or NULL to remove */
 } CommentStmt;
 
+/* ----------------------
+ *				CONFLICT RESOLVER Statement
+ * ----------------------
+ */
+typedef struct ConflictResolverStmt
+{
+	NodeTag		type;
+	char	   *conflict_type;
+	char	   *conflict_resolver;
+	bool		isReset;
+} ConflictResolverStmt;
+
 /* ----------------------
  *				SECURITY LABEL Statement
  * ----------------------
diff --git a/src/include/parser/kwlist.h b/src/include/parser/kwlist.h
index f7fe834cf4..21e5cb162d 100644
--- a/src/include/parser/kwlist.h
+++ b/src/include/parser/kwlist.h
@@ -377,6 +377,7 @@ PG_KEYWORD("repeatable", REPEATABLE, UNRESERVED_KEYWORD, BARE_LABEL)
 PG_KEYWORD("replace", REPLACE, UNRESERVED_KEYWORD, BARE_LABEL)
 PG_KEYWORD("replica", REPLICA, UNRESERVED_KEYWORD, BARE_LABEL)
 PG_KEYWORD("reset", RESET, UNRESERVED_KEYWORD, BARE_LABEL)
+PG_KEYWORD("resolver", RESOLVER, UNRESERVED_KEYWORD, BARE_LABEL)
 PG_KEYWORD("restart", RESTART, UNRESERVED_KEYWORD, BARE_LABEL)
 PG_KEYWORD("restrict", RESTRICT, UNRESERVED_KEYWORD, BARE_LABEL)
 PG_KEYWORD("return", RETURN, UNRESERVED_KEYWORD, BARE_LABEL)
diff --git a/src/include/replication/conflict.h b/src/include/replication/conflict.h
index 0bc9db991e..7eff93eff3 100644
--- a/src/include/replication/conflict.h
+++ b/src/include/replication/conflict.h
@@ -10,6 +10,7 @@
 #define CONFLICT_H
 
 #include "access/xlogdefs.h"
+#include "catalog/objectaddress.h"
 #include "executor/tuptable.h"
 #include "nodes/execnodes.h"
 #include "utils/relcache.h"
@@ -33,6 +34,41 @@ typedef enum
 	CT_DELETE_MISSING,
 } ConflictType;
 
+/* Min and max conflict type */
+#define CT_MIN CT_INSERT_EXISTS
+#define CT_MAX CT_DELETE_MISSING
+
+/*
+ * Conflict resolvers that can be used to resolve various conflicts.
+ *
+ * See ConflictTypeResolverMap in conflcit.c to find out which all
+ * resolvers are supported for each conflict type.
+ */
+typedef enum ConflictResolver
+{
+	/* Apply the remote change */
+	CR_REMOTE_APPLY = 1,
+
+	/* Keep the local change */
+	CR_KEEP_LOCAL,
+
+	/* Apply the remote change; skip if it can not be applied */
+	CR_APPLY_OR_SKIP,
+
+	/* Apply the remote change; emit error if it can not be applied */
+	CR_APPLY_OR_ERROR,
+
+	/* Skip applying the change */
+	CR_SKIP,
+
+	/* Error out */
+	CR_ERROR,
+} ConflictResolver;
+
+/* Min and max conflict resolver */
+#define CR_MIN CR_REMOTE_APPLY
+#define CR_MAX CR_ERROR
+
 extern bool GetTupleCommitTs(TupleTableSlot *localslot, TransactionId *xmin,
 							 RepOriginId *localorigin, TimestampTz *localts);
 extern void ReportApplyConflict(int elevel, ConflictType type,
@@ -40,5 +76,5 @@ extern void ReportApplyConflict(int elevel, ConflictType type,
 								TransactionId localxmin, RepOriginId localorigin,
 								TimestampTz localts, TupleTableSlot *conflictslot);
 extern void InitConflictIndexes(ResultRelInfo *relInfo);
-
+extern void ExecConflictResolverStmt(ConflictResolverStmt *stmt);
 #endif
diff --git a/src/include/tcop/cmdtaglist.h b/src/include/tcop/cmdtaglist.h
index 7fdcec6dd9..562478e232 100644
--- a/src/include/tcop/cmdtaglist.h
+++ b/src/include/tcop/cmdtaglist.h
@@ -80,6 +80,7 @@ PG_CMDTAG(CMDTAG_CLUSTER, "CLUSTER", false, false, false)
 PG_CMDTAG(CMDTAG_COMMENT, "COMMENT", true, false, false)
 PG_CMDTAG(CMDTAG_COMMIT, "COMMIT", false, false, false)
 PG_CMDTAG(CMDTAG_COMMIT_PREPARED, "COMMIT PREPARED", false, false, false)
+PG_CMDTAG(CMDTAG_CONFLICT_RESOLVER, "CONFLICT RESOLVER", false, false, false)
 PG_CMDTAG(CMDTAG_COPY, "COPY", false, false, true)
 PG_CMDTAG(CMDTAG_COPY_FROM, "COPY FROM", false, false, false)
 PG_CMDTAG(CMDTAG_CREATE_ACCESS_METHOD, "CREATE ACCESS METHOD", true, false, false)
diff --git a/src/test/regress/expected/conflict_resolver.out b/src/test/regress/expected/conflict_resolver.out
new file mode 100644
index 0000000000..15c8c0cdba
--- /dev/null
+++ b/src/test/regress/expected/conflict_resolver.out
@@ -0,0 +1,50 @@
+--check default global resolvers in system catalog
+select * from pg_conflict order by conftype;
+    conftype    |    confres    
+----------------+---------------
+ delete_missing | skip
+ insert_exists  | remote_apply
+ update_differ  | remote_apply
+ update_missing | apply_or_skip
+(4 rows)
+
+--
+-- Test of SET/RESET CONFLICT RESOLVER with invalid names
+--
+SET CONFLICT RESOLVER 'keep_local' for 'aaaa'; -- fail 
+ERROR:  aaaa is not a valid conflict type
+SET CONFLICT RESOLVER 'bbbbb' for 'delete_missing'; -- fail 
+ERROR:  bbbbb is not a valid conflict resolver
+SET CONFLICT RESOLVER 'remote_apply' for 'delete_missing'; -- fail 
+ERROR:  remote_apply is not a valid conflict resolver for conflict type delete_missing
+RESET CONFLICT RESOLVER for 'ct'; -- fail 
+ERROR:  ct is not a valid conflict type
+--
+-- Test of SET/RESET CONFLICT RESOLVER with valid names
+--
+SET CONFLICT RESOLVER 'error' for 'delete_missing';
+SET CONFLICT RESOLVER 'keep_local' for 'insert_exists';
+SET CONFLICT RESOLVER 'keep_local' for 'update_differ';
+SET CONFLICT RESOLVER 'apply_or_error' for 'update_missing';
+--check new resolvers are saved
+select * from pg_conflict order by conftype;
+    conftype    |    confres     
+----------------+----------------
+ delete_missing | error
+ insert_exists  | keep_local
+ update_differ  | keep_local
+ update_missing | apply_or_error
+(4 rows)
+
+RESET CONFLICT RESOLVER for 'delete_missing';
+RESET CONFLICT RESOLVER for 'insert_exists';
+--check resolvers are reset to default for delete_missing and insert_exists
+select * from pg_conflict order by conftype;
+    conftype    |    confres     
+----------------+----------------
+ delete_missing | skip
+ insert_exists  | remote_apply
+ update_differ  | keep_local
+ update_missing | apply_or_error
+(4 rows)
+
diff --git a/src/test/regress/parallel_schedule b/src/test/regress/parallel_schedule
index 2429ec2bba..76ea2d359b 100644
--- a/src/test/regress/parallel_schedule
+++ b/src/test/regress/parallel_schedule
@@ -48,7 +48,7 @@ test: create_index create_index_spgist create_view index_including index_includi
 # ----------
 # Another group of parallel tests
 # ----------
-test: create_aggregate create_function_sql create_cast constraints triggers select inherit typed_table vacuum drop_if_exists updatable_views roleattributes create_am hash_func errors infinite_recurse
+test: create_aggregate create_function_sql create_cast conflict_resolver constraints triggers select inherit typed_table vacuum drop_if_exists updatable_views roleattributes create_am hash_func errors infinite_recurse
 
 # ----------
 # sanity_check does a vacuum, affecting the sort order of SELECT *
diff --git a/src/test/regress/sql/conflict_resolver.sql b/src/test/regress/sql/conflict_resolver.sql
new file mode 100644
index 0000000000..e3540d7ac8
--- /dev/null
+++ b/src/test/regress/sql/conflict_resolver.sql
@@ -0,0 +1,27 @@
+--check default global resolvers in system catalog
+select * from pg_conflict order by conftype;
+
+--
+-- Test of SET/RESET CONFLICT RESOLVER with invalid names
+--
+SET CONFLICT RESOLVER 'keep_local' for 'aaaa'; -- fail
+SET CONFLICT RESOLVER 'bbbbb' for 'delete_missing'; -- fail
+SET CONFLICT RESOLVER 'remote_apply' for 'delete_missing'; -- fail
+RESET CONFLICT RESOLVER for 'ct'; -- fail
+
+--
+-- Test of SET/RESET CONFLICT RESOLVER with valid names
+--
+SET CONFLICT RESOLVER 'error' for 'delete_missing';
+SET CONFLICT RESOLVER 'keep_local' for 'insert_exists';
+SET CONFLICT RESOLVER 'keep_local' for 'update_differ';
+SET CONFLICT RESOLVER 'apply_or_error' for 'update_missing';
+
+--check new resolvers are saved
+select * from pg_conflict order by conftype;
+
+RESET CONFLICT RESOLVER for 'delete_missing';
+RESET CONFLICT RESOLVER for 'insert_exists';
+
+--check resolvers are reset to default for delete_missing and insert_exists
+select * from pg_conflict order by conftype;
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index 2485a80833..784194903a 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -466,6 +466,8 @@ ConditionVariableMinimallyPadded
 ConditionalStack
 ConfigData
 ConfigVariable
+ConflictResolver
+ConflictResolverStmt
 ConflictType
 ConnCacheEntry
 ConnCacheKey
-- 
2.34.1



  [application/octet-stream] v3-0004-Manage-Clock-skew-and-implement-last_update_wins.patch (21.9K, ../../CAJpy0uCv8R1Y5herLLANhGGqCotAFzBw3ikzhpXZvbqLDuoMTw@mail.gmail.com/6-v3-0004-Manage-Clock-skew-and-implement-last_update_wins.patch)
  download | inline diff:
From 75077a9567540dcf973b9f4dd7840e9bbf28dca3 Mon Sep 17 00:00:00 2001
From: Shveta Malik <[email protected]>
Date: Tue, 2 Jul 2024 11:06:28 +0530
Subject: [PATCH v3 4/5] Manage Clock skew and implement last_update_wins

This patch attempts to manage clock skew between nodes by
introducing two new GUCs:
a) max_logical_rep_clock_skew
b) max_logical_rep_clock_skew_action

This patch also implements last_update_wins resolver.
---
 src/backend/replication/logical/conflict.c    |  88 ++++++++++++--
 src/backend/replication/logical/origin.c      |   1 +
 src/backend/replication/logical/worker.c      | 108 +++++++++++++++++-
 .../utils/activity/wait_event_names.txt       |   1 +
 src/backend/utils/misc/guc_tables.c           |  26 +++++
 src/backend/utils/misc/postgresql.conf.sample |   6 +-
 src/include/catalog/pg_conflict.dat           |   4 +-
 src/include/replication/conflict.h            |   3 +
 src/include/replication/logicalworker.h       |  17 +++
 src/include/replication/origin.h              |   1 +
 src/include/utils/timestamp.h                 |   1 +
 .../regress/expected/conflict_resolver.out    |  22 ++--
 src/tools/pgindent/typedefs.list              |   1 +
 13 files changed, 253 insertions(+), 26 deletions(-)

diff --git a/src/backend/replication/logical/conflict.c b/src/backend/replication/logical/conflict.c
index a622a0ea8b..cbd3a65a27 100644
--- a/src/backend/replication/logical/conflict.c
+++ b/src/backend/replication/logical/conflict.c
@@ -43,6 +43,7 @@ const char *const ConflictTypeNames[] = {
 const char *const ConflictResolverNames[] = {
 	[CR_REMOTE_APPLY] = "remote_apply",
 	[CR_KEEP_LOCAL] = "keep_local",
+	[CR_LAST_UPDATE_WINS] = "last_update_wins",
 	[CR_APPLY_OR_SKIP] = "apply_or_skip",
 	[CR_APPLY_OR_ERROR] = "apply_or_error",
 	[CR_SKIP] = "skip",
@@ -68,8 +69,8 @@ const char *const ConflictResolverNames[] = {
  * friendly name for a resolver and thus has been added here.
  */
 const int	ConflictTypeResolverMap[][CONFLICT_TYPE_MAX_RESOLVERS] = {
-	[CT_INSERT_EXISTS] = {CR_REMOTE_APPLY, CR_KEEP_LOCAL, CR_ERROR},
-	[CT_UPDATE_DIFFER] = {CR_REMOTE_APPLY, CR_KEEP_LOCAL, CR_ERROR},
+	[CT_INSERT_EXISTS] = {CR_REMOTE_APPLY, CR_KEEP_LOCAL, CR_LAST_UPDATE_WINS, CR_ERROR},
+	[CT_UPDATE_DIFFER] = {CR_REMOTE_APPLY, CR_KEEP_LOCAL, CR_LAST_UPDATE_WINS, CR_ERROR},
 	[CT_UPDATE_MISSING] = {CR_APPLY_OR_SKIP, CR_APPLY_OR_ERROR, CR_SKIP, CR_ERROR},
 	[CT_DELETE_MISSING] = {CR_SKIP, CR_ERROR}
 };
@@ -79,8 +80,8 @@ const int	ConflictTypeResolverMap[][CONFLICT_TYPE_MAX_RESOLVERS] = {
  * If this changes, change it in pg_conflict.dat as well.
  */
 const int	ConflictTypeDefaultResolvers[] = {
-	[CT_INSERT_EXISTS] = CR_REMOTE_APPLY,
-	[CT_UPDATE_DIFFER] = CR_REMOTE_APPLY,
+	[CT_INSERT_EXISTS] = CR_LAST_UPDATE_WINS,
+	[CT_UPDATE_DIFFER] = CR_LAST_UPDATE_WINS,
 	[CT_UPDATE_MISSING] = CR_APPLY_OR_SKIP,
 	[CT_DELETE_MISSING] = CR_SKIP
 };
@@ -211,15 +212,36 @@ errdetail_apply_conflict(ConflictType type, ConflictResolver resolver,
 										 get_rel_name(conflictidx));
 				}
 				else
-					return errdetail("Key already exists. Applying resolution method \"%s\"", ConflictResolverNames[resolver]);
+				{
+					if (resolver == CR_LAST_UPDATE_WINS)
+						return errdetail("Key already exists. Applying resolution method \"%s\". The local tuple : origin=%u, timestamp=%s; The remote tuple : origin=%u, timestamp=%s.",
+										 ConflictResolverNames[resolver],
+										 localorigin, timestamptz_to_str(localts),
+										 replorigin_session_origin,
+										 timestamptz_to_str(replorigin_session_origin_timestamp));
+					else
+						return errdetail("Key already exists. Applying resolution method \"%s\"",
+										 ConflictResolverNames[resolver]);
+				}
+
 			}
 		case CT_UPDATE_DIFFER:
-			return errdetail("Updating a row that was modified by a different origin %u in transaction %u at %s. Applying resolution method \"%s\"",
-							 localorigin, localxmin, timestamptz_to_str(localts), ConflictResolverNames[resolver]);
+			if (resolver == CR_LAST_UPDATE_WINS)
+				return errdetail("Updating a row that was modified by a different origin %u in transaction %u at %s. Applying resolution method \"%s\". The remote tuple : origin=%u, timestamp=%s.",
+								 localorigin, localxmin, timestamptz_to_str(localts),
+								 ConflictResolverNames[resolver],
+								 replorigin_session_origin,
+								 timestamptz_to_str(replorigin_session_origin_timestamp));
+			else
+				return errdetail("Updating a row that was modified by a different origin %u in transaction %u at %s. Applying resolution method \"%s\"",
+								 localorigin, localxmin, timestamptz_to_str(localts),
+								 ConflictResolverNames[resolver]);
 		case CT_UPDATE_MISSING:
-			return errdetail("Did not find the row to be updated. Applying resolution method \"%s\"", ConflictResolverNames[resolver]);
+			return errdetail("Did not find the row to be updated. Applying resolution method \"%s\"",
+							 ConflictResolverNames[resolver]);
 		case CT_DELETE_MISSING:
-			return errdetail("Did not find the row to be deleted. Applying resolution method \"%s\"", ConflictResolverNames[resolver]);
+			return errdetail("Did not find the row to be deleted. Applying resolution method \"%s\"",
+							 ConflictResolverNames[resolver]);
 	}
 
 	return 0;					/* silence compiler warning */
@@ -330,6 +352,15 @@ validate_conflict_type_and_resolver(char *conflict_type, char *conflict_resolver
 				errmsg("%s is not a valid conflict resolver for conflict type %s",
 					   conflict_resolver,
 					   conflict_type));
+
+	if ((resolver == CR_LAST_UPDATE_WINS) && !track_commit_timestamp)
+		ereport(ERROR,
+				errcode(ERRCODE_INVALID_PARAMETER_VALUE),
+				errmsg("resolver %s requires %s to be enabled",
+					   conflict_resolver, "track_commit_timestamp"),
+				errhint("Make sure the configuration parameter %s is set.",
+						"track_commit_timestamp"));
+
 	return type;
 }
 
@@ -371,6 +402,42 @@ get_conflict_resolver_internal(ConflictType type)
 	return resolver;
 }
 
+/*
+ * Compare the timestamps of given local tuple and the remote tuple to
+ * resolve the conflict.
+ *
+ * Returns true if remote tuple has the latest timestamp, false otherwise.
+ */
+static bool
+resolve_by_timestamp(TupleTableSlot *localslot)
+{
+	TransactionId local_xmin;
+	TimestampTz local_ts;
+	RepOriginId local_origin;
+	int			ts_cmp;
+	uint64		local_system_identifier;
+
+	/* Get origin and timestamp info of the local tuple */
+	GetTupleCommitTs(localslot, &local_xmin, &local_origin, &local_ts);
+
+	/* Compare the timestamps of remote & local tuple to decide the winner */
+	ts_cmp = timestamptz_cmp_internal(replorigin_session_origin_timestamp,
+									  local_ts);
+
+	if (ts_cmp == 0)
+	{
+		elog(LOG, "Timestamps of remote and local tuple are equal, comparing remote and local system identifiers");
+
+		/* Get current system's identifier */
+		local_system_identifier = GetSystemIdentifier();
+
+		return local_system_identifier <= replorigin_session_origin_sysid;
+	}
+	else
+		return (ts_cmp > 0);
+
+}
+
 /*
  * Check if a full tuple can be created from the new tuple.
  * Return true if yes, false otherwise.
@@ -493,6 +560,9 @@ GetConflictResolver(TupleTableSlot *localslot, Relation localrel,
 
 	switch (resolver)
 	{
+		case CR_LAST_UPDATE_WINS:
+			*apply_remote = resolve_by_timestamp(localslot);
+			break;
 		case CR_REMOTE_APPLY:
 			*apply_remote = true;
 			break;
diff --git a/src/backend/replication/logical/origin.c b/src/backend/replication/logical/origin.c
index 419e4814f0..bd8e6f0024 100644
--- a/src/backend/replication/logical/origin.c
+++ b/src/backend/replication/logical/origin.c
@@ -155,6 +155,7 @@ typedef struct ReplicationStateCtl
 RepOriginId replorigin_session_origin = InvalidRepOriginId; /* assumed identity */
 XLogRecPtr	replorigin_session_origin_lsn = InvalidXLogRecPtr;
 TimestampTz replorigin_session_origin_timestamp = 0;
+uint64		replorigin_session_origin_sysid = 0;
 
 /*
  * Base address into a shared memory array of replication states of size
diff --git a/src/backend/replication/logical/worker.c b/src/backend/replication/logical/worker.c
index c4dc03e964..55fb4f18f5 100644
--- a/src/backend/replication/logical/worker.c
+++ b/src/backend/replication/logical/worker.c
@@ -318,6 +318,19 @@ static uint32 parallel_stream_nchanges = 0;
 /* Are we initializing an apply worker? */
 bool		InitializingApplyWorker = false;
 
+/*
+ * GUC support
+ */
+const struct config_enum_entry logical_rep_clock_skew_action_options[] = {
+	{"error", LR_CLOCK_SKEW_ACTION_ERROR, false},
+	{"wait", LR_CLOCK_SKEW_ACTION_WAIT, false},
+	{NULL, 0, false}
+};
+
+/* GUCs */
+int			max_logical_rep_clock_skew = 0;
+int			max_logical_rep_clock_skew_action = LR_CLOCK_SKEW_ACTION_ERROR;
+
 /*
  * We enable skipping all data modification changes (INSERT, UPDATE, etc.) for
  * the subscription if the remote transaction's finish LSN matches the subskiplsn.
@@ -987,6 +1000,86 @@ slot_modify_data(TupleTableSlot *slot, TupleTableSlot *srcslot,
 	ExecStoreVirtualTuple(slot);
 }
 
+/*
+ * Manage clock skew between nodes.
+ *
+ * It checks if the remote commit timestamp is ahead of the local clock
+ * and if the difference exceeds max_logical_rep_clock_skew, it performs
+ * the action specified by the max_logical_rep_clock_skew_action.
+ */
+static void
+manage_clock_skew()
+{
+	TimestampTz current;
+	TimestampTz delayUntil;
+	long		msecs;
+	int			rc;
+
+	/* nothing to do if no max clock skew configured */
+	if (max_logical_rep_clock_skew == LR_CLOCK_SKEW_DEFAULT)
+		return;
+
+	current = GetCurrentTimestamp();
+
+	/*
+	 * If the timestamp of the currently replayed transaction is in the future
+	 * compared to the current time on the subscriber and the difference is
+	 * larger than max_logical_rep_clock_skew, then perform the action
+	 * specified by the max_logical_rep_clock_skew_action setting.
+	 */
+	if (replorigin_session_origin_timestamp > current &&
+		TimestampDifferenceExceeds(current, replorigin_session_origin_timestamp,
+								   max_logical_rep_clock_skew * 1000))
+	{
+		if (max_logical_rep_clock_skew_action == LR_CLOCK_SKEW_ACTION_ERROR)
+			ereport(ERROR,
+					(errcode(ERRCODE_PROTOCOL_VIOLATION),
+					 errmsg_internal("logical replication clock skew exceeded max tolerated value of %d seconds",
+									 max_logical_rep_clock_skew)));
+
+		/* Perform the wait */
+		while (true)
+		{
+			delayUntil =
+				TimestampTzMinusSeconds(replorigin_session_origin_timestamp,
+										max_logical_rep_clock_skew);
+
+			/* Exit without waiting if it's already past 'delayUntil' time */
+			msecs = TimestampDifferenceMilliseconds(GetCurrentTimestamp(),
+													delayUntil);
+			if (msecs <= 0)
+				break;
+
+			elog(LOG, "delaying apply for %ld milliseconds to bring clock skew "
+				 "within permissible value of %d seconds",
+				 msecs, max_logical_rep_clock_skew);
+
+			/* Sleep until we are signaled or msecs have elapsed */
+			rc = WaitLatch(MyLatch,
+						   WL_LATCH_SET | WL_TIMEOUT | WL_EXIT_ON_PM_DEATH,
+						   msecs,
+						   WAIT_EVENT_LOGICAL_CLOCK_SKEW);
+
+			/* Exit the loop if msecs have elapsed */
+			if (rc & WL_TIMEOUT)
+				break;
+
+			if (rc & WL_LATCH_SET)
+			{
+				ResetLatch(MyLatch);
+				CHECK_FOR_INTERRUPTS();
+			}
+
+			/* This might change max_logical_rep_clock_skew. */
+			if (ConfigReloadPending)
+			{
+				ConfigReloadPending = false;
+				ProcessConfigFile(PGC_SIGHUP);
+			}
+		}
+	}
+}
+
 /*
  * Handle BEGIN message.
  */
@@ -1008,6 +1101,12 @@ apply_handle_begin(StringInfo s)
 	in_remote_transaction = true;
 
 	pgstat_report_activity(STATE_RUNNING, NULL);
+
+	/* Capture the commit timestamp of the remote transaction */
+	replorigin_session_origin_timestamp = begin_data.committime;
+
+	/* Check if there is any clock skew and take configured action */
+	manage_clock_skew();
 }
 
 /*
@@ -4669,6 +4768,7 @@ run_apply_worker()
 	TimeLineID	startpointTLI;
 	char	   *err;
 	bool		must_use_password;
+	char	   *replorigin_sysid;
 
 	slotname = MySubscription->slotname;
 
@@ -4708,10 +4808,12 @@ run_apply_worker()
 				 errmsg("could not connect to the publisher: %s", err)));
 
 	/*
-	 * We don't really use the output identify_system for anything but it does
-	 * some initializations on the upstream so let's still call it.
+	 * Call identify_system to do some initializations on the upstream and
+	 * store the output as system identifier of the replication origin node.
 	 */
-	(void) walrcv_identify_system(LogRepWorkerWalRcvConn, &startpointTLI);
+	replorigin_sysid = walrcv_identify_system(LogRepWorkerWalRcvConn,
+											  &startpointTLI);
+	replorigin_session_origin_sysid = strtoul(replorigin_sysid, NULL, 10);
 
 	set_apply_error_context_origin(originname);
 
diff --git a/src/backend/utils/activity/wait_event_names.txt b/src/backend/utils/activity/wait_event_names.txt
index db37beeaae..a51f82169e 100644
--- a/src/backend/utils/activity/wait_event_names.txt
+++ b/src/backend/utils/activity/wait_event_names.txt
@@ -59,6 +59,7 @@ CHECKPOINTER_MAIN	"Waiting in main loop of checkpointer process."
 LOGICAL_APPLY_MAIN	"Waiting in main loop of logical replication apply process."
 LOGICAL_LAUNCHER_MAIN	"Waiting in main loop of logical replication launcher process."
 LOGICAL_PARALLEL_APPLY_MAIN	"Waiting in main loop of logical replication parallel apply process."
+LOGICAL_CLOCK_SKEW	"Waiting in apply-begin of logical replication apply process to bring clock skew in permissible range."
 RECOVERY_WAL_STREAM	"Waiting in main loop of startup process for WAL to arrive, during streaming recovery."
 REPLICATION_SLOTSYNC_MAIN	"Waiting in main loop of slot sync worker."
 REPLICATION_SLOTSYNC_SHUTDOWN	"Waiting for slot sync worker to shut down."
diff --git a/src/backend/utils/misc/guc_tables.c b/src/backend/utils/misc/guc_tables.c
index d28b0bcb40..6dc23f28cf 100644
--- a/src/backend/utils/misc/guc_tables.c
+++ b/src/backend/utils/misc/guc_tables.c
@@ -67,6 +67,7 @@
 #include "postmaster/walsummarizer.h"
 #include "postmaster/walwriter.h"
 #include "replication/logicallauncher.h"
+#include "replication/logicalworker.h"
 #include "replication/slot.h"
 #include "replication/slotsync.h"
 #include "replication/syncrep.h"
@@ -492,6 +493,7 @@ extern const struct config_enum_entry archive_mode_options[];
 extern const struct config_enum_entry recovery_target_action_options[];
 extern const struct config_enum_entry wal_sync_method_options[];
 extern const struct config_enum_entry dynamic_shared_memory_options[];
+extern const struct config_enum_entry logical_rep_clock_skew_action_options[];
 
 /*
  * GUC option variables that are exported from this module
@@ -3649,6 +3651,19 @@ struct config_int ConfigureNamesInt[] =
 		NULL, NULL, NULL
 	},
 
+	{
+		{"max_logical_rep_clock_skew", PGC_SIGHUP, REPLICATION_SUBSCRIBERS,
+			gettext_noop("Sets maximum clock skew tolerance between logical "
+						 "replication nodes beyond which action configured "
+						 "in max_logical_rep_clock_skew_action is triggered."),
+			NULL,
+			GUC_UNIT_S
+		},
+		&max_logical_rep_clock_skew,
+		LR_CLOCK_SKEW_DEFAULT, LR_CLOCK_SKEW_DEFAULT, INT_MAX,
+		NULL, NULL, NULL
+	},
+
 	/* End-of-list marker */
 	{
 		{NULL, 0, 0, NULL, NULL}, NULL, 0, 0, 0, NULL, NULL, NULL
@@ -4915,6 +4930,17 @@ struct config_enum ConfigureNamesEnum[] =
 		NULL, NULL, NULL
 	},
 
+	{
+		{"max_logical_rep_clock_skew_action", PGC_POSTMASTER, REPLICATION_SUBSCRIBERS,
+			gettext_noop("Sets the action to perform if a clock skew higher "
+						 "than max_logical_rep_clock_skew is detected."),
+			NULL
+		},
+		&max_logical_rep_clock_skew_action,
+		LR_CLOCK_SKEW_ACTION_ERROR, logical_rep_clock_skew_action_options,
+		NULL, NULL, NULL
+	},
+
 	{
 		{"track_functions", PGC_SUSET, STATS_CUMULATIVE,
 			gettext_noop("Collects function-level statistics on database activity."),
diff --git a/src/backend/utils/misc/postgresql.conf.sample b/src/backend/utils/misc/postgresql.conf.sample
index 9ec9f97e92..3a7fd70506 100644
--- a/src/backend/utils/misc/postgresql.conf.sample
+++ b/src/backend/utils/misc/postgresql.conf.sample
@@ -383,7 +383,11 @@
 					# (change requires restart)
 #max_sync_workers_per_subscription = 2	# taken from max_logical_replication_workers
 #max_parallel_apply_workers_per_subscription = 2	# taken from max_logical_replication_workers
-
+#max_logical_rep_clock_skew = -1	# maximum clock skew tolerance between logical
+					# replication nodes beyond which action configured in
+					# 'max_logical_rep_clock_skew_action' is triggered.
+#max_logical_rep_clock_skew_action = error # error or wait
+					   # (change requires restart)
 
 #------------------------------------------------------------------------------
 # QUERY TUNING
diff --git a/src/include/catalog/pg_conflict.dat b/src/include/catalog/pg_conflict.dat
index a3e5e10d97..2f7fd2394a 100644
--- a/src/include/catalog/pg_conflict.dat
+++ b/src/include/catalog/pg_conflict.dat
@@ -12,8 +12,8 @@
 
 [
 
-{ conftype => 'insert_exists', confres => 'remote_apply' },
-{ conftype => 'update_differ', confres => 'remote_apply' },
+{ conftype => 'insert_exists', confres => 'last_update_wins' },
+{ conftype => 'update_differ', confres => 'last_update_wins' },
 { conftype => 'update_missing', confres => 'apply_or_skip' },
 { conftype => 'delete_missing', confres => 'skip' }
 
diff --git a/src/include/replication/conflict.h b/src/include/replication/conflict.h
index aa21886ee7..82f4f5ec49 100644
--- a/src/include/replication/conflict.h
+++ b/src/include/replication/conflict.h
@@ -54,6 +54,9 @@ typedef enum ConflictResolver
 	/* Keep the local change */
 	CR_KEEP_LOCAL,
 
+	/* Apply the change with latest timestamp */
+	CR_LAST_UPDATE_WINS,
+
 	/* Apply the remote change; skip if it can not be applied */
 	CR_APPLY_OR_SKIP,
 
diff --git a/src/include/replication/logicalworker.h b/src/include/replication/logicalworker.h
index a18d79d1b2..2b922f9c62 100644
--- a/src/include/replication/logicalworker.h
+++ b/src/include/replication/logicalworker.h
@@ -14,7 +14,24 @@
 
 #include <signal.h>
 
+/*
+ * The default for max_logical_rep_clock_skew is -1, which means ignore clock
+ * skew (the check is turned off).
+ */
+#define LR_CLOCK_SKEW_DEFAULT -1
+
+/*
+ * Worker Clock Skew Action.
+ */
+typedef enum
+{
+	LR_CLOCK_SKEW_ACTION_ERROR,
+	LR_CLOCK_SKEW_ACTION_WAIT,
+} LogicalRepClockSkewAction;
+
 extern PGDLLIMPORT volatile sig_atomic_t ParallelApplyMessagePending;
+extern PGDLLIMPORT int max_logical_rep_clock_skew;
+extern PGDLLIMPORT int max_logical_rep_clock_skew_action;
 
 extern void ApplyWorkerMain(Datum main_arg);
 extern void ParallelApplyWorkerMain(Datum main_arg);
diff --git a/src/include/replication/origin.h b/src/include/replication/origin.h
index 7189ba9e76..dcbbbdf6ea 100644
--- a/src/include/replication/origin.h
+++ b/src/include/replication/origin.h
@@ -36,6 +36,7 @@ typedef struct xl_replorigin_drop
 extern PGDLLIMPORT RepOriginId replorigin_session_origin;
 extern PGDLLIMPORT XLogRecPtr replorigin_session_origin_lsn;
 extern PGDLLIMPORT TimestampTz replorigin_session_origin_timestamp;
+extern PGDLLIMPORT uint64 replorigin_session_origin_sysid;
 
 /* API for querying & manipulating replication origins */
 extern RepOriginId replorigin_by_name(const char *roname, bool missing_ok);
diff --git a/src/include/utils/timestamp.h b/src/include/utils/timestamp.h
index a6ce03ed46..53b828d89d 100644
--- a/src/include/utils/timestamp.h
+++ b/src/include/utils/timestamp.h
@@ -84,6 +84,7 @@ IntervalPGetDatum(const Interval *X)
 /* Macros for doing timestamp arithmetic without assuming timestamp's units */
 #define TimestampTzPlusMilliseconds(tz,ms) ((tz) + ((ms) * (int64) 1000))
 #define TimestampTzPlusSeconds(tz,s) ((tz) + ((s) * (int64) 1000000))
+#define TimestampTzMinusSeconds(tz,s) ((tz) - ((s) * (int64) 1000000))
 
 
 /* Set at postmaster start */
diff --git a/src/test/regress/expected/conflict_resolver.out b/src/test/regress/expected/conflict_resolver.out
index 15c8c0cdba..d0157ba830 100644
--- a/src/test/regress/expected/conflict_resolver.out
+++ b/src/test/regress/expected/conflict_resolver.out
@@ -1,23 +1,23 @@
 --check default global resolvers in system catalog
 select * from pg_conflict order by conftype;
-    conftype    |    confres    
-----------------+---------------
+    conftype    |     confres      
+----------------+------------------
  delete_missing | skip
- insert_exists  | remote_apply
- update_differ  | remote_apply
+ insert_exists  | last_update_wins
+ update_differ  | last_update_wins
  update_missing | apply_or_skip
 (4 rows)
 
 --
 -- Test of SET/RESET CONFLICT RESOLVER with invalid names
 --
-SET CONFLICT RESOLVER 'keep_local' for 'aaaa'; -- fail 
+SET CONFLICT RESOLVER 'keep_local' for 'aaaa'; -- fail
 ERROR:  aaaa is not a valid conflict type
-SET CONFLICT RESOLVER 'bbbbb' for 'delete_missing'; -- fail 
+SET CONFLICT RESOLVER 'bbbbb' for 'delete_missing'; -- fail
 ERROR:  bbbbb is not a valid conflict resolver
-SET CONFLICT RESOLVER 'remote_apply' for 'delete_missing'; -- fail 
+SET CONFLICT RESOLVER 'remote_apply' for 'delete_missing'; -- fail
 ERROR:  remote_apply is not a valid conflict resolver for conflict type delete_missing
-RESET CONFLICT RESOLVER for 'ct'; -- fail 
+RESET CONFLICT RESOLVER for 'ct'; -- fail
 ERROR:  ct is not a valid conflict type
 --
 -- Test of SET/RESET CONFLICT RESOLVER with valid names
@@ -40,10 +40,10 @@ RESET CONFLICT RESOLVER for 'delete_missing';
 RESET CONFLICT RESOLVER for 'insert_exists';
 --check resolvers are reset to default for delete_missing and insert_exists
 select * from pg_conflict order by conftype;
-    conftype    |    confres     
-----------------+----------------
+    conftype    |     confres      
+----------------+------------------
  delete_missing | skip
- insert_exists  | remote_apply
+ insert_exists  | last_update_wins
  update_differ  | keep_local
  update_missing | apply_or_error
 (4 rows)
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index 784194903a..15e5a494ba 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -1565,6 +1565,7 @@ LogicalOutputPluginWriterPrepareWrite
 LogicalOutputPluginWriterUpdateProgress
 LogicalOutputPluginWriterWrite
 LogicalRepBeginData
+LogicalRepClockSkewAction
 LogicalRepCommitData
 LogicalRepCommitPreparedTxnData
 LogicalRepCtxStruct
-- 
2.34.1



^ permalink  raw  reply  [nested|flat] 101+ messages in thread

* Re: Conflict Detection and Resolution
@ 2024-07-04 12:07  Amit Kapila <[email protected]>
  parent: Dilip Kumar <[email protected]>
  0 siblings, 1 reply; 101+ messages in thread

From: Amit Kapila @ 2024-07-04 12:07 UTC (permalink / raw)
  To: Dilip Kumar <[email protected]>; +Cc: shveta malik <[email protected]>; Tomas Vondra <[email protected]>; pgsql-hackers; Zhijie Hou (Fujitsu) <[email protected]>; Nisha Moond <[email protected]>

On Wed, Jul 3, 2024 at 5:06 PM Dilip Kumar <[email protected]> wrote:
>
> On Wed, Jul 3, 2024 at 4:48 PM Amit Kapila <[email protected]> wrote:
> >
> > On Wed, Jul 3, 2024 at 4:04 PM Dilip Kumar <[email protected]> wrote:
> > >
> > >
> > > What I am saying is that if we are not applying the whole transaction,
> > > it means we are not receiving it either unless we plan to spill it to
> > > a file. If we don't spill it to a file, the network buffer will fill
> > > up very quickly. This issue wouldn't occur if we waited right before
> > > the commit because, by that time, we would have already received all
> > > the data from the network.
> > >
> >
> > We would have received the transaction data but there could be other
> > transactions that need to wait because the apply worker is waiting
> > before the commit.
>
> Yeah, that's a valid point, can parallel apply worker help here?
>
>  So, the situation will be the same. We can even
> > decide to spill the data to files if the decision is that we need to
> > wait to avoid network buffer-fill situations. But note that the wait
> > in apply worker has consequences that the subscriber won't be able to
> > confirm the flush position and publisher won't be able to vacuum the
> > dead rows and we won't be remove WAL as well. Last time when we
> > discussed the delay_apply feature, we decided not to proceed because
> > of such issues. This is the reason I proposed a cap on wait time.
>
> Yes, spilling to file or cap on the wait time should help, and as I
> said above maybe a parallel apply worker can also help.
>

It is not clear to me how a parallel apply worker can help in this
case. Can you elaborate on what you have in mind?

-- 
With Regards,
Amit Kapila.






^ permalink  raw  reply  [nested|flat] 101+ messages in thread

* Re: Conflict Detection and Resolution
@ 2024-07-05 06:27  Dilip Kumar <[email protected]>
  parent: Amit Kapila <[email protected]>
  0 siblings, 2 replies; 101+ messages in thread

From: Dilip Kumar @ 2024-07-05 06:27 UTC (permalink / raw)
  To: Amit Kapila <[email protected]>; +Cc: shveta malik <[email protected]>; Tomas Vondra <[email protected]>; pgsql-hackers; Zhijie Hou (Fujitsu) <[email protected]>; Nisha Moond <[email protected]>

On Thu, Jul 4, 2024 at 5:37 PM Amit Kapila <[email protected]> wrote:
> >  So, the situation will be the same. We can even
> > > decide to spill the data to files if the decision is that we need to
> > > wait to avoid network buffer-fill situations. But note that the wait
> > > in apply worker has consequences that the subscriber won't be able to
> > > confirm the flush position and publisher won't be able to vacuum the
> > > dead rows and we won't be remove WAL as well. Last time when we
> > > discussed the delay_apply feature, we decided not to proceed because
> > > of such issues. This is the reason I proposed a cap on wait time.
> >
> > Yes, spilling to file or cap on the wait time should help, and as I
> > said above maybe a parallel apply worker can also help.
> >
>
> It is not clear to me how a parallel apply worker can help in this
> case. Can you elaborate on what you have in mind?

If we decide to wait at commit time, and before starting to apply if
we already see a remote commit_ts clock is ahead, then if we apply
such transactions using the parallel worker, wouldn't it solve the
issue of the network buffer congestion? Now the apply worker can move
ahead and fetch new transactions from the buffer as our waiting
transaction will not block it.  I understand that if this transaction
is going to wait at commit then any future transaction that we are
going to fetch might also going to wait again because if the previous
transaction committed before is in the future then the subsequent
transaction committed after this must also be in future so eventually
that will also go to some another parallel worker and soon we end up
consuming all the parallel worker if the clock skew is large.  So I
won't say this will resolve the problem and we would still have to
fall back to the spilling to the disk but that's just in the worst
case when the clock skew is really huge.  In most cases which is due
to slight clock drift by the time we apply the medium to large size
transaction, the local clock should be able to catch up the remote
commit_ts and we might not have to wait in most of the cases.

-- 
Regards,
Dilip Kumar
EnterpriseDB: http://www.enterprisedb.com






^ permalink  raw  reply  [nested|flat] 101+ messages in thread

* Re: Conflict Detection and Resolution
@ 2024-07-05 06:52  Nisha Moond <[email protected]>
  parent: Dilip Kumar <[email protected]>
  1 sibling, 0 replies; 101+ messages in thread

From: Nisha Moond @ 2024-07-05 06:52 UTC (permalink / raw)
  To: Dilip Kumar <[email protected]>; +Cc: Amit Kapila <[email protected]>; shveta malik <[email protected]>; Tomas Vondra <[email protected]>; pgsql-hackers; Zhijie Hou (Fujitsu) <[email protected]>; Nisha Moond <[email protected]>

Please find the new patch set (v4). It implements the resolvers for
conflict type : 'delete_differ'.
Supported resolutions for ‘delete_differ’ are :
 - ‘last_update_wins': Apply the change with the latest timestamp (default)
 - 'remote_apply': Apply the remote delete.
 - 'keep_local': Skip the remote delete and continue.
 - 'error': The apply worker will error out and restart.

The changes made in the patches are as follows:
 - Updated the conflict detection patch (patch0001) to the latest
version from [1], which implements delete_differ conflict detection.
 - Patch0002 now supports resolver settings for delete_differ.
 - Patch0003 implements resolutions for delete_differ as well.
 - Patch0004 includes changes to support last_update_wins resolution
for delete_differ.

[1] https://www.postgresql.org/message-id/OS0PR01MB571686E464A325F26CEFCCEF94DD2%40OS0PR01MB5716.jpnprd0...

--
Thanks,
Nisha


Attachments:

  [application/octet-stream] v4-0001-Detect-and-log-conflicts-in-logical-replication.patch (95.5K, ../../CABdArM47myyKnOU4LB54k3wmgpFu63s2gxmAQVK-DdWzCLKAaw@mail.gmail.com/2-v4-0001-Detect-and-log-conflicts-in-logical-replication.patch)
  download | inline diff:
From 3c5017cd591ee1f289607ec936bfb8798615074d Mon Sep 17 00:00:00 2001
From: Hou Zhijie <[email protected]>
Date: Fri, 31 May 2024 14:20:45 +0530
Subject: [PATCH v4 1/5] Detect and log conflicts in logical replication

This patch adds a new parameter detect_conflict for CREATE and ALTER
subscription commands. This new parameter will decide if subscription will
go for confict detection. By default, conflict detection will be off for a
subscription.

When conflict detection is enabled, additional logging is triggered in the
following conflict scenarios:

insert_exists: Inserting a row that violates a NOT DEFERRABLE unique constraint.
update_differ: Updating a row that was previously modified by another origin.
update_missing: The tuple to be updated is missing.
delete_missing: The tuple to be deleted is missing.
delete_differ: Deleting a row that was previously modified by another origin.

For insert_exists conflict, the log can include origin and commit
timestamp details of the conflicting key with track_commit_timestamp
enabled.

update_differ and delete_differ conflicts can only be detected when
track_commit_timestamp is enabled.
---
 doc/src/sgml/catalogs.sgml                  |   9 +
 doc/src/sgml/logical-replication.sgml       |  23 ++-
 doc/src/sgml/ref/alter_subscription.sgml    |   5 +-
 doc/src/sgml/ref/create_subscription.sgml   |  66 +++++++
 src/backend/catalog/pg_subscription.c       |   1 +
 src/backend/catalog/system_views.sql        |   3 +-
 src/backend/commands/subscriptioncmds.c     |  31 +++-
 src/backend/executor/execIndexing.c         |  14 +-
 src/backend/executor/execReplication.c      | 117 +++++++++++-
 src/backend/replication/logical/Makefile    |   1 +
 src/backend/replication/logical/conflict.c  | 191 ++++++++++++++++++++
 src/backend/replication/logical/meson.build |   1 +
 src/backend/replication/logical/worker.c    |  79 ++++++--
 src/bin/pg_dump/pg_dump.c                   |  17 +-
 src/bin/pg_dump/pg_dump.h                   |   1 +
 src/bin/psql/describe.c                     |   6 +-
 src/bin/psql/tab-complete.c                 |  14 +-
 src/include/catalog/pg_subscription.h       |   4 +
 src/include/replication/conflict.h          |  47 +++++
 src/test/regress/expected/subscription.out  | 176 ++++++++++--------
 src/test/regress/sql/subscription.sql       |  15 ++
 src/test/subscription/t/001_rep_changes.pl  |  15 +-
 src/test/subscription/t/013_partition.pl    |  68 ++++---
 src/test/subscription/t/029_on_error.pl     |   5 +-
 src/test/subscription/t/030_origin.pl       |  43 +++++
 src/tools/pgindent/typedefs.list            |   1 +
 26 files changed, 801 insertions(+), 152 deletions(-)
 create mode 100644 src/backend/replication/logical/conflict.c
 create mode 100644 src/include/replication/conflict.h

diff --git a/doc/src/sgml/catalogs.sgml b/doc/src/sgml/catalogs.sgml
index b654fae1b2..b042a5a94a 100644
--- a/doc/src/sgml/catalogs.sgml
+++ b/doc/src/sgml/catalogs.sgml
@@ -8035,6 +8035,15 @@ SCRAM-SHA-256$<replaceable>&lt;iteration count&gt;</replaceable>:<replaceable>&l
       </para></entry>
      </row>
 
+     <row>
+      <entry role="catalog_table_entry"><para role="column_definition">
+       <structfield>subdetectconflict</structfield> <type>bool</type>
+      </para>
+      <para>
+       If true, the subscription is enabled for conflict detection.
+      </para></entry>
+     </row>
+
      <row>
       <entry role="catalog_table_entry"><para role="column_definition">
        <structfield>subconninfo</structfield> <type>text</type>
diff --git a/doc/src/sgml/logical-replication.sgml b/doc/src/sgml/logical-replication.sgml
index ccdd24312b..f078d6364b 100644
--- a/doc/src/sgml/logical-replication.sgml
+++ b/doc/src/sgml/logical-replication.sgml
@@ -1565,7 +1565,9 @@ test_sub=# SELECT * FROM t1 ORDER BY id;
    stop.  This is referred to as a <firstterm>conflict</firstterm>.  When
    replicating <command>UPDATE</command> or <command>DELETE</command>
    operations, missing data will not produce a conflict and such operations
-   will simply be skipped.
+   will simply be skipped, but note that this scenario can be reported in the server log
+   if <link linkend="sql-createsubscription-params-with-detect-conflict"><literal>detect_conflict</literal></link>
+   is enabled.
   </para>
 
   <para>
@@ -1634,6 +1636,25 @@ CONTEXT:  processing remote data for replication origin "pg_16395" during "INSER
    linkend="sql-altersubscription"><command>ALTER SUBSCRIPTION ...
    SKIP</command></link>.
   </para>
+
+  <para>
+   Enabling both <link linkend="sql-createsubscription-params-with-detect-conflict"><literal>detect_conflict</literal></link>
+   and <link linkend="guc-track-commit-timestamp"><varname>track_commit_timestamp</varname></link>
+   on the subscriber can provide additional details regarding conflicting
+   rows, such as their origin and commit timestamp, in case of a unique
+   constraint violation conflict:
+<screen>
+ERROR:  conflict insert_exists detected on relation "public.t"
+DETAIL:  Key (a)=(1) already exists in unique index "t_pkey", which was modified by origin 0 in transaction 740 at 2024-06-26 10:47:04.727375+08.
+CONTEXT:  processing remote data for replication origin "pg_16389" during message type "INSERT" for replication target relation "public.t" in transaction 740, finished at 0/14F7EC0
+</screen>
+   Users can use these information to make decisions on whether to retain
+   the local change or adopt the remote alteration. For instance, the
+   origin in above log indicates that the existing row was modified by a
+   local change, users can manually perform a remote-change-win resolution
+   by deleting the local row. Refer to <link linkend="sql-createsubscription-params-with-detect-conflict"><literal>detect_conflict</literal></link>
+   for other conflicts that will be logged when enabling <literal>detect_conflict</literal>.
+  </para>
  </sect1>
 
  <sect1 id="logical-replication-restrictions">
diff --git a/doc/src/sgml/ref/alter_subscription.sgml b/doc/src/sgml/ref/alter_subscription.sgml
index 476f195622..5f6b83e415 100644
--- a/doc/src/sgml/ref/alter_subscription.sgml
+++ b/doc/src/sgml/ref/alter_subscription.sgml
@@ -228,8 +228,9 @@ ALTER SUBSCRIPTION <replaceable class="parameter">name</replaceable> RENAME TO <
       <link linkend="sql-createsubscription-params-with-disable-on-error"><literal>disable_on_error</literal></link>,
       <link linkend="sql-createsubscription-params-with-password-required"><literal>password_required</literal></link>,
       <link linkend="sql-createsubscription-params-with-run-as-owner"><literal>run_as_owner</literal></link>,
-      <link linkend="sql-createsubscription-params-with-origin"><literal>origin</literal></link>, and
-      <link linkend="sql-createsubscription-params-with-failover"><literal>failover</literal></link>.
+      <link linkend="sql-createsubscription-params-with-origin"><literal>origin</literal></link>,
+      <link linkend="sql-createsubscription-params-with-failover"><literal>failover</literal></link>, and
+      <link linkend="sql-createsubscription-params-with-detect-conflict"><literal>detect_conflict</literal></link>.
       Only a superuser can set <literal>password_required = false</literal>.
      </para>
 
diff --git a/doc/src/sgml/ref/create_subscription.sgml b/doc/src/sgml/ref/create_subscription.sgml
index 740b7d9421..caa523b9bd 100644
--- a/doc/src/sgml/ref/create_subscription.sgml
+++ b/doc/src/sgml/ref/create_subscription.sgml
@@ -428,6 +428,72 @@ CREATE SUBSCRIPTION <replaceable class="parameter">subscription_name</replaceabl
          </para>
         </listitem>
        </varlistentry>
+
+      <varlistentry id="sql-createsubscription-params-with-detect-conflict">
+        <term><literal>detect_conflict</literal> (<type>boolean</type>)</term>
+        <listitem>
+         <para>
+          Specifies whether the subscription is enabled for conflict detection.
+          The default is <literal>false</literal>.
+         </para>
+         <para>
+          When conflict detection is enabled, additional logging is triggered
+          in the following scenarios:
+          <variablelist>
+           <varlistentry>
+            <term><literal>insert_exists</literal></term>
+            <listitem>
+             <para>
+              Inserting a row that violates a <literal>NOT DEFERRABLE</literal>
+              unique constraint. Note that to obtain the origin and commit
+              timestamp details of the conflicting key in the log, ensure that
+              <link linkend="guc-track-commit-timestamp"><varname>track_commit_timestamp</varname></link>
+              is enabled.
+             </para>
+            </listitem>
+           </varlistentry>
+           <varlistentry>
+            <term><literal>update_differ</literal></term>
+            <listitem>
+             <para>
+              Updating a row that was previously modified by another origin. Note that this
+              conflict can only be detected when
+              <link linkend="guc-track-commit-timestamp"><varname>track_commit_timestamp</varname></link>
+              is enabled.
+             </para>
+            </listitem>
+           </varlistentry>
+           <varlistentry>
+            <term><literal>update_missing</literal></term>
+            <listitem>
+             <para>
+              The tuple to be updated is not found.
+             </para>
+            </listitem>
+           </varlistentry>
+           <varlistentry>
+            <term><literal>delete_missing</literal></term>
+            <listitem>
+             <para>
+              The tuple to be deleted is not found.
+             </para>
+            </listitem>
+           </varlistentry>
+           <varlistentry>
+            <term><literal>delete_differ</literal></term>
+            <listitem>
+             <para>
+              Deleting a row that was previously modified by another origin. Note that this
+              conflict can only be detected when
+              <link linkend="guc-track-commit-timestamp"><varname>track_commit_timestamp</varname></link>
+              is enabled.
+             </para>
+            </listitem>
+           </varlistentry>
+          </variablelist>
+         </para>
+        </listitem>
+       </varlistentry>
       </variablelist></para>
 
     </listitem>
diff --git a/src/backend/catalog/pg_subscription.c b/src/backend/catalog/pg_subscription.c
index 9efc9159f2..5a423f4fb0 100644
--- a/src/backend/catalog/pg_subscription.c
+++ b/src/backend/catalog/pg_subscription.c
@@ -72,6 +72,7 @@ GetSubscription(Oid subid, bool missing_ok)
 	sub->passwordrequired = subform->subpasswordrequired;
 	sub->runasowner = subform->subrunasowner;
 	sub->failover = subform->subfailover;
+	sub->detectconflict = subform->subdetectconflict;
 
 	/* Get conninfo */
 	datum = SysCacheGetAttrNotNull(SUBSCRIPTIONOID,
diff --git a/src/backend/catalog/system_views.sql b/src/backend/catalog/system_views.sql
index 19cabc9a47..d084bfc48a 100644
--- a/src/backend/catalog/system_views.sql
+++ b/src/backend/catalog/system_views.sql
@@ -1356,7 +1356,8 @@ REVOKE ALL ON pg_subscription FROM public;
 GRANT SELECT (oid, subdbid, subskiplsn, subname, subowner, subenabled,
               subbinary, substream, subtwophasestate, subdisableonerr,
 			  subpasswordrequired, subrunasowner, subfailover,
-              subslotname, subsynccommit, subpublications, suborigin)
+			  subdetectconflict, subslotname, subsynccommit,
+			  subpublications, suborigin)
     ON pg_subscription TO public;
 
 CREATE VIEW pg_stat_subscription_stats AS
diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c
index e407428dbc..e670d72708 100644
--- a/src/backend/commands/subscriptioncmds.c
+++ b/src/backend/commands/subscriptioncmds.c
@@ -70,8 +70,9 @@
 #define SUBOPT_PASSWORD_REQUIRED	0x00000800
 #define SUBOPT_RUN_AS_OWNER			0x00001000
 #define SUBOPT_FAILOVER				0x00002000
-#define SUBOPT_LSN					0x00004000
-#define SUBOPT_ORIGIN				0x00008000
+#define SUBOPT_DETECT_CONFLICT		0x00004000
+#define SUBOPT_LSN					0x00008000
+#define SUBOPT_ORIGIN				0x00010000
 
 /* check if the 'val' has 'bits' set */
 #define IsSet(val, bits)  (((val) & (bits)) == (bits))
@@ -97,6 +98,7 @@ typedef struct SubOpts
 	bool		passwordrequired;
 	bool		runasowner;
 	bool		failover;
+	bool		detectconflict;
 	char	   *origin;
 	XLogRecPtr	lsn;
 } SubOpts;
@@ -159,6 +161,8 @@ parse_subscription_options(ParseState *pstate, List *stmt_options,
 		opts->runasowner = false;
 	if (IsSet(supported_opts, SUBOPT_FAILOVER))
 		opts->failover = false;
+	if (IsSet(supported_opts, SUBOPT_DETECT_CONFLICT))
+		opts->detectconflict = false;
 	if (IsSet(supported_opts, SUBOPT_ORIGIN))
 		opts->origin = pstrdup(LOGICALREP_ORIGIN_ANY);
 
@@ -316,6 +320,15 @@ parse_subscription_options(ParseState *pstate, List *stmt_options,
 			opts->specified_opts |= SUBOPT_FAILOVER;
 			opts->failover = defGetBoolean(defel);
 		}
+		else if (IsSet(supported_opts, SUBOPT_DETECT_CONFLICT) &&
+				 strcmp(defel->defname, "detect_conflict") == 0)
+		{
+			if (IsSet(opts->specified_opts, SUBOPT_DETECT_CONFLICT))
+				errorConflictingDefElem(defel, pstate);
+
+			opts->specified_opts |= SUBOPT_DETECT_CONFLICT;
+			opts->detectconflict = defGetBoolean(defel);
+		}
 		else if (IsSet(supported_opts, SUBOPT_ORIGIN) &&
 				 strcmp(defel->defname, "origin") == 0)
 		{
@@ -603,7 +616,8 @@ CreateSubscription(ParseState *pstate, CreateSubscriptionStmt *stmt,
 					  SUBOPT_SYNCHRONOUS_COMMIT | SUBOPT_BINARY |
 					  SUBOPT_STREAMING | SUBOPT_TWOPHASE_COMMIT |
 					  SUBOPT_DISABLE_ON_ERR | SUBOPT_PASSWORD_REQUIRED |
-					  SUBOPT_RUN_AS_OWNER | SUBOPT_FAILOVER | SUBOPT_ORIGIN);
+					  SUBOPT_RUN_AS_OWNER | SUBOPT_FAILOVER |
+					  SUBOPT_DETECT_CONFLICT | SUBOPT_ORIGIN);
 	parse_subscription_options(pstate, stmt->options, supported_opts, &opts);
 
 	/*
@@ -710,6 +724,8 @@ CreateSubscription(ParseState *pstate, CreateSubscriptionStmt *stmt,
 	values[Anum_pg_subscription_subpasswordrequired - 1] = BoolGetDatum(opts.passwordrequired);
 	values[Anum_pg_subscription_subrunasowner - 1] = BoolGetDatum(opts.runasowner);
 	values[Anum_pg_subscription_subfailover - 1] = BoolGetDatum(opts.failover);
+	values[Anum_pg_subscription_subdetectconflict - 1] =
+		BoolGetDatum(opts.detectconflict);
 	values[Anum_pg_subscription_subconninfo - 1] =
 		CStringGetTextDatum(conninfo);
 	if (opts.slot_name)
@@ -1146,7 +1162,7 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 								  SUBOPT_STREAMING | SUBOPT_DISABLE_ON_ERR |
 								  SUBOPT_PASSWORD_REQUIRED |
 								  SUBOPT_RUN_AS_OWNER | SUBOPT_FAILOVER |
-								  SUBOPT_ORIGIN);
+								  SUBOPT_DETECT_CONFLICT | SUBOPT_ORIGIN);
 
 				parse_subscription_options(pstate, stmt->options,
 										   supported_opts, &opts);
@@ -1256,6 +1272,13 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt,
 					replaces[Anum_pg_subscription_subfailover - 1] = true;
 				}
 
+				if (IsSet(opts.specified_opts, SUBOPT_DETECT_CONFLICT))
+				{
+					values[Anum_pg_subscription_subdetectconflict - 1] =
+						BoolGetDatum(opts.detectconflict);
+					replaces[Anum_pg_subscription_subdetectconflict - 1] = true;
+				}
+
 				if (IsSet(opts.specified_opts, SUBOPT_ORIGIN))
 				{
 					values[Anum_pg_subscription_suborigin - 1] =
diff --git a/src/backend/executor/execIndexing.c b/src/backend/executor/execIndexing.c
index 9f05b3654c..ef522778a2 100644
--- a/src/backend/executor/execIndexing.c
+++ b/src/backend/executor/execIndexing.c
@@ -207,8 +207,9 @@ ExecOpenIndices(ResultRelInfo *resultRelInfo, bool speculative)
 		ii = BuildIndexInfo(indexDesc);
 
 		/*
-		 * If the indexes are to be used for speculative insertion, add extra
-		 * information required by unique index entries.
+		 * If the indexes are to be used for speculative insertion or conflict
+		 * detection in logical replication, add extra information required by
+		 * unique index entries.
 		 */
 		if (speculative && ii->ii_Unique)
 			BuildSpeculativeIndexInfo(indexDesc, ii);
@@ -521,6 +522,11 @@ ExecInsertIndexTuples(ResultRelInfo *resultRelInfo,
  *		possible that a conflicting tuple is inserted immediately
  *		after this returns.  But this can be used for a pre-check
  *		before insertion.
+ *
+ *		If the 'slot' holds a tuple with valid tid, this tuple will
+ *		be ignored when checking conflict. This can help in scenarios
+ *		where we want to re-check for conflicts after inserting a
+ *		tuple.
  * ----------------------------------------------------------------
  */
 bool
@@ -536,11 +542,9 @@ ExecCheckIndexConstraints(ResultRelInfo *resultRelInfo, TupleTableSlot *slot,
 	ExprContext *econtext;
 	Datum		values[INDEX_MAX_KEYS];
 	bool		isnull[INDEX_MAX_KEYS];
-	ItemPointerData invalidItemPtr;
 	bool		checkedIndex = false;
 
 	ItemPointerSetInvalid(conflictTid);
-	ItemPointerSetInvalid(&invalidItemPtr);
 
 	/*
 	 * Get information from the result relation info structure.
@@ -629,7 +633,7 @@ ExecCheckIndexConstraints(ResultRelInfo *resultRelInfo, TupleTableSlot *slot,
 
 		satisfiesConstraint =
 			check_exclusion_or_unique_constraint(heapRelation, indexRelation,
-												 indexInfo, &invalidItemPtr,
+												 indexInfo, &slot->tts_tid,
 												 values, isnull, estate, false,
 												 CEOUC_WAIT, true,
 												 conflictTid);
diff --git a/src/backend/executor/execReplication.c b/src/backend/executor/execReplication.c
index d0a89cd577..f01927a933 100644
--- a/src/backend/executor/execReplication.c
+++ b/src/backend/executor/execReplication.c
@@ -23,6 +23,7 @@
 #include "commands/trigger.h"
 #include "executor/executor.h"
 #include "executor/nodeModifyTable.h"
+#include "replication/conflict.h"
 #include "replication/logicalrelation.h"
 #include "storage/lmgr.h"
 #include "utils/builtins.h"
@@ -480,6 +481,83 @@ retry:
 	return found;
 }
 
+/*
+ * Find the tuple that violates the passed in unique index constraint
+ * (conflictindex).
+ *
+ * Return false if there is no conflict and *conflictslot is set to NULL.
+ * Otherwise return true, and the conflicting tuple is locked and returned
+ * in *conflictslot.
+ */
+static bool
+FindConflictTuple(ResultRelInfo *resultRelInfo, EState *estate,
+				  Oid conflictindex, TupleTableSlot *slot,
+				  TupleTableSlot **conflictslot)
+{
+	Relation	rel = resultRelInfo->ri_RelationDesc;
+	ItemPointerData conflictTid;
+	TM_FailureData tmfd;
+	TM_Result	res;
+
+	*conflictslot = NULL;
+
+retry:
+	if (ExecCheckIndexConstraints(resultRelInfo, slot, estate,
+								  &conflictTid, list_make1_oid(conflictindex)))
+	{
+		if (*conflictslot)
+			ExecDropSingleTupleTableSlot(*conflictslot);
+
+		*conflictslot = NULL;
+		return false;
+	}
+
+	*conflictslot = table_slot_create(rel, NULL);
+
+	PushActiveSnapshot(GetLatestSnapshot());
+
+	res = table_tuple_lock(rel, &conflictTid, GetLatestSnapshot(),
+						   *conflictslot,
+						   GetCurrentCommandId(false),
+						   LockTupleShare,
+						   LockWaitBlock,
+						   0 /* don't follow updates */ ,
+						   &tmfd);
+
+	PopActiveSnapshot();
+
+	switch (res)
+	{
+		case TM_Ok:
+			break;
+		case TM_Updated:
+			/* XXX: Improve handling here */
+			if (ItemPointerIndicatesMovedPartitions(&tmfd.ctid))
+				ereport(LOG,
+						(errcode(ERRCODE_T_R_SERIALIZATION_FAILURE),
+						 errmsg("tuple to be locked was already moved to another partition due to concurrent update, retrying")));
+			else
+				ereport(LOG,
+						(errcode(ERRCODE_T_R_SERIALIZATION_FAILURE),
+						 errmsg("concurrent update, retrying")));
+			goto retry;
+		case TM_Deleted:
+			/* XXX: Improve handling here */
+			ereport(LOG,
+					(errcode(ERRCODE_T_R_SERIALIZATION_FAILURE),
+					 errmsg("concurrent delete, retrying")));
+			goto retry;
+		case TM_Invisible:
+			elog(ERROR, "attempted to lock invisible tuple");
+			break;
+		default:
+			elog(ERROR, "unexpected table_tuple_lock status: %u", res);
+			break;
+	}
+
+	return true;
+}
+
 /*
  * Insert tuple represented in the slot to the relation, update the indexes,
  * and execute any constraints and per-row triggers.
@@ -509,6 +587,8 @@ ExecSimpleRelationInsert(ResultRelInfo *resultRelInfo,
 	if (!skip_tuple)
 	{
 		List	   *recheckIndexes = NIL;
+		List	   *conflictindexes;
+		bool		conflict = false;
 
 		/* Compute stored generated columns */
 		if (rel->rd_att->constr &&
@@ -525,10 +605,43 @@ ExecSimpleRelationInsert(ResultRelInfo *resultRelInfo,
 		/* OK, store the tuple and create index entries for it */
 		simple_table_tuple_insert(resultRelInfo->ri_RelationDesc, slot);
 
+		conflictindexes = resultRelInfo->ri_onConflictArbiterIndexes;
+
 		if (resultRelInfo->ri_NumIndices > 0)
 			recheckIndexes = ExecInsertIndexTuples(resultRelInfo,
-												   slot, estate, false, false,
-												   NULL, NIL, false);
+												   slot, estate, false,
+												   conflictindexes, &conflict,
+												   conflictindexes, false);
+
+		/* Re-check all the unique indexes for potential conflicts */
+		foreach_oid(uniqueidx, (conflict ? conflictindexes : NIL))
+		{
+			TupleTableSlot *conflictslot;
+
+			/*
+			 * Reports the conflict if any.
+			 *
+			 * Here, we attempt to find the conflict tuple. This operation may
+			 * seem redundant with the unique violation check of indexam, but
+			 * since we perform this only when we are detecting conflict in
+			 * logical replication and encountering potential conflicts with
+			 * any unique index constraints (which should not be frequent), so
+			 * it's ok. Moreover, upon detecting a conflict, we will report an
+			 * ERROR and restart the logical replication, so the additional
+			 * cost of finding the tuple should be acceptable in this case.
+			 */
+			if (list_member_oid(recheckIndexes, uniqueidx) &&
+				FindConflictTuple(resultRelInfo, estate, uniqueidx, slot, &conflictslot))
+			{
+				RepOriginId origin;
+				TimestampTz committs;
+				TransactionId xmin;
+
+				GetTupleCommitTs(conflictslot, &xmin, &origin, &committs);
+				ReportApplyConflict(ERROR, CT_INSERT_EXISTS, rel, uniqueidx,
+									xmin, origin, committs, conflictslot);
+			}
+		}
 
 		/* AFTER ROW INSERT Triggers */
 		ExecARInsertTriggers(estate, resultRelInfo, slot,
diff --git a/src/backend/replication/logical/Makefile b/src/backend/replication/logical/Makefile
index ba03eeff1c..1e08bbbd4e 100644
--- a/src/backend/replication/logical/Makefile
+++ b/src/backend/replication/logical/Makefile
@@ -16,6 +16,7 @@ override CPPFLAGS := -I$(srcdir) $(CPPFLAGS)
 
 OBJS = \
 	applyparallelworker.o \
+	conflict.o \
 	decode.o \
 	launcher.o \
 	logical.o \
diff --git a/src/backend/replication/logical/conflict.c b/src/backend/replication/logical/conflict.c
new file mode 100644
index 0000000000..b90e64b05b
--- /dev/null
+++ b/src/backend/replication/logical/conflict.c
@@ -0,0 +1,191 @@
+/*-------------------------------------------------------------------------
+ * conflict.c
+ *	   Functionality for detecting and logging conflicts.
+ *
+ * Copyright (c) 2024, PostgreSQL Global Development Group
+ *
+ * IDENTIFICATION
+ *	  src/backend/replication/logical/conflict.c
+ *
+ * This file contains the code for detecting and logging conflicts on
+ * the subscriber during logical replication.
+ *-------------------------------------------------------------------------
+ */
+
+#include "postgres.h"
+
+#include "access/commit_ts.h"
+#include "replication/conflict.h"
+#include "replication/origin.h"
+#include "utils/lsyscache.h"
+#include "utils/rel.h"
+
+const char *const ConflictTypeNames[] = {
+	[CT_INSERT_EXISTS] = "insert_exists",
+	[CT_UPDATE_DIFFER] = "update_differ",
+	[CT_UPDATE_MISSING] = "update_missing",
+	[CT_DELETE_MISSING] = "delete_missing",
+	[CT_DELETE_DIFFER] = "delete_differ"
+};
+
+static char *build_index_value_desc(Oid indexoid, TupleTableSlot *conflictslot);
+static int	errdetail_apply_conflict(ConflictType type, Oid conflictidx,
+									 TransactionId localxmin,
+									 RepOriginId localorigin,
+									 TimestampTz localts,
+									 TupleTableSlot *conflictslot);
+
+/*
+ * Get the xmin and commit timestamp data (origin and timestamp) associated
+ * with the provided local tuple.
+ *
+ * Return true if the commit timestamp data was found, false otherwise.
+ */
+bool
+GetTupleCommitTs(TupleTableSlot *localslot, TransactionId *xmin,
+				 RepOriginId *localorigin, TimestampTz *localts)
+{
+	Datum		xminDatum;
+	bool		isnull;
+
+	xminDatum = slot_getsysattr(localslot, MinTransactionIdAttributeNumber,
+								&isnull);
+	*xmin = DatumGetTransactionId(xminDatum);
+	Assert(!isnull);
+
+	/*
+	 * The commit timestamp data is not available if track_commit_timestamp is
+	 * disabled.
+	 */
+	if (!track_commit_timestamp)
+	{
+		*localorigin = InvalidRepOriginId;
+		*localts = 0;
+		return false;
+	}
+
+	return TransactionIdGetCommitTsData(*xmin, localts, localorigin);
+}
+
+/*
+ * Report a conflict when applying remote changes.
+ */
+void
+ReportApplyConflict(int elevel, ConflictType type, Relation localrel,
+					Oid conflictidx, TransactionId localxmin,
+					RepOriginId localorigin, TimestampTz localts,
+					TupleTableSlot *conflictslot)
+{
+	ereport(elevel,
+			errcode(ERRCODE_INTEGRITY_CONSTRAINT_VIOLATION),
+			errmsg("conflict %s detected on relation \"%s.%s\"",
+				   ConflictTypeNames[type],
+				   get_namespace_name(RelationGetNamespace(localrel)),
+				   RelationGetRelationName(localrel)),
+			errdetail_apply_conflict(type, conflictidx, localxmin, localorigin,
+									 localts, conflictslot));
+}
+
+/*
+ * Find all unique indexes to check for a conflict and store them into
+ * ResultRelInfo.
+ */
+void
+InitConflictIndexes(ResultRelInfo *relInfo)
+{
+	List	   *uniqueIndexes = NIL;
+
+	for (int i = 0; i < relInfo->ri_NumIndices; i++)
+	{
+		Relation	indexRelation = relInfo->ri_IndexRelationDescs[i];
+
+		if (indexRelation == NULL)
+			continue;
+
+		/* Detect conflict only for unique indexes */
+		if (!relInfo->ri_IndexRelationInfo[i]->ii_Unique)
+			continue;
+
+		/* Don't support conflict detection for deferrable index */
+		if (!indexRelation->rd_index->indimmediate)
+			continue;
+
+		uniqueIndexes = lappend_oid(uniqueIndexes,
+									RelationGetRelid(indexRelation));
+	}
+
+	relInfo->ri_onConflictArbiterIndexes = uniqueIndexes;
+}
+
+/*
+ * Add an errdetail() line showing conflict detail.
+ */
+static int
+errdetail_apply_conflict(ConflictType type, Oid conflictidx,
+						 TransactionId localxmin, RepOriginId localorigin,
+						 TimestampTz localts, TupleTableSlot *conflictslot)
+{
+	switch (type)
+	{
+		case CT_INSERT_EXISTS:
+			{
+				/*
+				 * Bulid the index value string. If the return value is NULL,
+				 * it indicates that the current user lacks permissions to
+				 * view all the columns involved.
+				 */
+				char	   *index_value = build_index_value_desc(conflictidx,
+																 conflictslot);
+
+				if (index_value && localts)
+					return errdetail("Key %s already exists in unique index \"%s\", which was modified by origin %u in transaction %u at %s.",
+									 index_value, get_rel_name(conflictidx), localorigin,
+									 localxmin, timestamptz_to_str(localts));
+				else if (index_value && !localts)
+					return errdetail("Key %s already exists in unique index \"%s\", which was modified in transaction %u.",
+									 index_value, get_rel_name(conflictidx), localxmin);
+				else
+					return errdetail("Key already exists in unique index \"%s\".",
+									 get_rel_name(conflictidx));
+			}
+		case CT_UPDATE_DIFFER:
+			return errdetail("Updating a row that was modified by a different origin %u in transaction %u at %s.",
+							 localorigin, localxmin, timestamptz_to_str(localts));
+		case CT_UPDATE_MISSING:
+			return errdetail("Did not find the row to be updated.");
+		case CT_DELETE_MISSING:
+			return errdetail("Did not find the row to be deleted.");
+		case CT_DELETE_DIFFER:
+			return errdetail("Deleting a row that was modified by a different origin %u in transaction %u at %s.",
+							 localorigin, localxmin, timestamptz_to_str(localts));
+	}
+
+	return 0;					/* silence compiler warning */
+}
+
+/*
+ * Helper functions to construct a string describing the contents of an index
+ * entry. See BuildIndexValueDescription for details.
+ */
+static char *
+build_index_value_desc(Oid indexoid, TupleTableSlot *conflictslot)
+{
+	char	   *conflict_row;
+	Relation	indexDesc;
+
+	if (!conflictslot)
+		return NULL;
+
+	/* Assume the index has been locked */
+	indexDesc = index_open(indexoid, NoLock);
+
+	slot_getallattrs(conflictslot);
+
+	conflict_row = BuildIndexValueDescription(indexDesc,
+											  conflictslot->tts_values,
+											  conflictslot->tts_isnull);
+
+	index_close(indexDesc, NoLock);
+
+	return conflict_row;
+}
diff --git a/src/backend/replication/logical/meson.build b/src/backend/replication/logical/meson.build
index 3dec36a6de..3d36249d8a 100644
--- a/src/backend/replication/logical/meson.build
+++ b/src/backend/replication/logical/meson.build
@@ -2,6 +2,7 @@
 
 backend_sources += files(
   'applyparallelworker.c',
+  'conflict.c',
   'decode.c',
   'launcher.c',
   'logical.c',
diff --git a/src/backend/replication/logical/worker.c b/src/backend/replication/logical/worker.c
index 3b285894db..b4c834ed3f 100644
--- a/src/backend/replication/logical/worker.c
+++ b/src/backend/replication/logical/worker.c
@@ -167,6 +167,7 @@
 #include "postmaster/bgworker.h"
 #include "postmaster/interrupt.h"
 #include "postmaster/walwriter.h"
+#include "replication/conflict.h"
 #include "replication/logicallauncher.h"
 #include "replication/logicalproto.h"
 #include "replication/logicalrelation.h"
@@ -2461,7 +2462,10 @@ apply_handle_insert_internal(ApplyExecutionData *edata,
 	EState	   *estate = edata->estate;
 
 	/* We must open indexes here. */
-	ExecOpenIndices(relinfo, false);
+	ExecOpenIndices(relinfo, MySubscription->detectconflict);
+
+	if (MySubscription->detectconflict)
+		InitConflictIndexes(relinfo);
 
 	/* Do the insert. */
 	TargetPrivilegesCheck(relinfo->ri_RelationDesc, ACL_INSERT);
@@ -2664,6 +2668,20 @@ apply_handle_update_internal(ApplyExecutionData *edata,
 	 */
 	if (found)
 	{
+		RepOriginId localorigin;
+		TransactionId localxmin;
+		TimestampTz localts;
+
+		/*
+		 * If conflict detection is enabled, check whether the local tuple was
+		 * modified by a different origin. If detected, report the conflict.
+		 */
+		if (MySubscription->detectconflict &&
+			GetTupleCommitTs(localslot, &localxmin, &localorigin, &localts) &&
+			localorigin != replorigin_session_origin)
+			ReportApplyConflict(LOG, CT_UPDATE_DIFFER, localrel, InvalidOid,
+								localxmin, localorigin, localts, NULL);
+
 		/* Process and store remote tuple in the slot */
 		oldctx = MemoryContextSwitchTo(GetPerTupleMemoryContext(estate));
 		slot_modify_data(remoteslot, localslot, relmapentry, newtup);
@@ -2681,13 +2699,10 @@ apply_handle_update_internal(ApplyExecutionData *edata,
 		/*
 		 * The tuple to be updated could not be found.  Do nothing except for
 		 * emitting a log message.
-		 *
-		 * XXX should this be promoted to ereport(LOG) perhaps?
 		 */
-		elog(DEBUG1,
-			 "logical replication did not find row to be updated "
-			 "in replication target relation \"%s\"",
-			 RelationGetRelationName(localrel));
+		if (MySubscription->detectconflict)
+			ReportApplyConflict(LOG, CT_UPDATE_MISSING, localrel, InvalidOid,
+								InvalidTransactionId, InvalidRepOriginId, 0, NULL);
 	}
 
 	/* Cleanup. */
@@ -2810,6 +2825,20 @@ apply_handle_delete_internal(ApplyExecutionData *edata,
 	/* If found delete it. */
 	if (found)
 	{
+		RepOriginId localorigin;
+		TransactionId localxmin;
+		TimestampTz localts;
+
+		/*
+		 * If conflict detection is enabled, check whether the local tuple was
+		 * modified by a different origin. If detected, report the conflict.
+		 */
+		if (MySubscription->detectconflict &&
+			GetTupleCommitTs(localslot, &localxmin, &localorigin, &localts) &&
+			localorigin != replorigin_session_origin)
+			ReportApplyConflict(LOG, CT_DELETE_DIFFER, localrel, InvalidOid,
+								localxmin, localorigin, localts, NULL);
+
 		EvalPlanQualSetSlot(&epqstate, localslot);
 
 		/* Do the actual delete. */
@@ -2821,13 +2850,10 @@ apply_handle_delete_internal(ApplyExecutionData *edata,
 		/*
 		 * The tuple to be deleted could not be found.  Do nothing except for
 		 * emitting a log message.
-		 *
-		 * XXX should this be promoted to ereport(LOG) perhaps?
 		 */
-		elog(DEBUG1,
-			 "logical replication did not find row to be deleted "
-			 "in replication target relation \"%s\"",
-			 RelationGetRelationName(localrel));
+		if (MySubscription->detectconflict)
+			ReportApplyConflict(LOG, CT_DELETE_MISSING, localrel, InvalidOid,
+								InvalidTransactionId, InvalidRepOriginId, 0, NULL);
 	}
 
 	/* Cleanup. */
@@ -2994,6 +3020,9 @@ apply_handle_tuple_routing(ApplyExecutionData *edata,
 				ResultRelInfo *partrelinfo_new;
 				Relation	partrel_new;
 				bool		found;
+				RepOriginId localorigin;
+				TransactionId localxmin;
+				TimestampTz localts;
 
 				/* Get the matching local tuple from the partition. */
 				found = FindReplTupleInLocalRel(edata, partrel,
@@ -3005,16 +3034,28 @@ apply_handle_tuple_routing(ApplyExecutionData *edata,
 					/*
 					 * The tuple to be updated could not be found.  Do nothing
 					 * except for emitting a log message.
-					 *
-					 * XXX should this be promoted to ereport(LOG) perhaps?
 					 */
-					elog(DEBUG1,
-						 "logical replication did not find row to be updated "
-						 "in replication target relation's partition \"%s\"",
-						 RelationGetRelationName(partrel));
+					if (MySubscription->detectconflict)
+						ReportApplyConflict(LOG, CT_UPDATE_MISSING,
+											partrel, InvalidOid,
+											InvalidTransactionId,
+											InvalidRepOriginId, 0, NULL);
+
 					return;
 				}
 
+				/*
+				 * If conflict detection is enabled, check whether the local
+				 * tuple was modified by a different origin. If detected,
+				 * report the conflict.
+				 */
+				if (MySubscription->detectconflict &&
+					GetTupleCommitTs(localslot, &localxmin, &localorigin, &localts) &&
+					localorigin != replorigin_session_origin)
+					ReportApplyConflict(LOG, CT_UPDATE_DIFFER, partrel,
+										InvalidOid, localxmin, localorigin,
+										localts, NULL);
+
 				/*
 				 * Apply the update to the local tuple, putting the result in
 				 * remoteslot_part.
diff --git a/src/bin/pg_dump/pg_dump.c b/src/bin/pg_dump/pg_dump.c
index 5426f1177c..e0ecadd081 100644
--- a/src/bin/pg_dump/pg_dump.c
+++ b/src/bin/pg_dump/pg_dump.c
@@ -4754,6 +4754,7 @@ getSubscriptions(Archive *fout)
 	int			i_suboriginremotelsn;
 	int			i_subenabled;
 	int			i_subfailover;
+	int			i_subdetectconflict;
 	int			i,
 				ntups;
 
@@ -4826,11 +4827,17 @@ getSubscriptions(Archive *fout)
 
 	if (fout->remoteVersion >= 170000)
 		appendPQExpBufferStr(query,
-							 " s.subfailover\n");
+							 " s.subfailover,\n");
 	else
 		appendPQExpBuffer(query,
-						  " false AS subfailover\n");
+						  " false AS subfailover,\n");
 
+	if (fout->remoteVersion >= 170000)
+		appendPQExpBufferStr(query,
+							 " s.subdetectconflict\n");
+	else
+		appendPQExpBuffer(query,
+						  " false AS subdetectconflict\n");
 	appendPQExpBufferStr(query,
 						 "FROM pg_subscription s\n");
 
@@ -4869,6 +4876,7 @@ getSubscriptions(Archive *fout)
 	i_suboriginremotelsn = PQfnumber(res, "suboriginremotelsn");
 	i_subenabled = PQfnumber(res, "subenabled");
 	i_subfailover = PQfnumber(res, "subfailover");
+	i_subdetectconflict = PQfnumber(res, "subdetectconflict");
 
 	subinfo = pg_malloc(ntups * sizeof(SubscriptionInfo));
 
@@ -4915,6 +4923,8 @@ getSubscriptions(Archive *fout)
 			pg_strdup(PQgetvalue(res, i, i_subenabled));
 		subinfo[i].subfailover =
 			pg_strdup(PQgetvalue(res, i, i_subfailover));
+		subinfo[i].subdetectconflict =
+			pg_strdup(PQgetvalue(res, i, i_subdetectconflict));
 
 		/* Decide whether we want to dump it */
 		selectDumpableObject(&(subinfo[i].dobj), fout);
@@ -5155,6 +5165,9 @@ dumpSubscription(Archive *fout, const SubscriptionInfo *subinfo)
 	if (strcmp(subinfo->subfailover, "t") == 0)
 		appendPQExpBufferStr(query, ", failover = true");
 
+	if (strcmp(subinfo->subdetectconflict, "t") == 0)
+		appendPQExpBufferStr(query, ", detect_conflict = true");
+
 	if (strcmp(subinfo->subsynccommit, "off") != 0)
 		appendPQExpBuffer(query, ", synchronous_commit = %s", fmtId(subinfo->subsynccommit));
 
diff --git a/src/bin/pg_dump/pg_dump.h b/src/bin/pg_dump/pg_dump.h
index 4b2e5870a9..bbd7cbeff6 100644
--- a/src/bin/pg_dump/pg_dump.h
+++ b/src/bin/pg_dump/pg_dump.h
@@ -671,6 +671,7 @@ typedef struct _SubscriptionInfo
 	char	   *suborigin;
 	char	   *suboriginremotelsn;
 	char	   *subfailover;
+	char	   *subdetectconflict;
 } SubscriptionInfo;
 
 /*
diff --git a/src/bin/psql/describe.c b/src/bin/psql/describe.c
index 7c9a1f234c..fef1ad0d70 100644
--- a/src/bin/psql/describe.c
+++ b/src/bin/psql/describe.c
@@ -6539,7 +6539,7 @@ describeSubscriptions(const char *pattern, bool verbose)
 	printQueryOpt myopt = pset.popt;
 	static const bool translate_columns[] = {false, false, false, false,
 		false, false, false, false, false, false, false, false, false, false,
-	false};
+	false, false};
 
 	if (pset.sversion < 100000)
 	{
@@ -6607,6 +6607,10 @@ describeSubscriptions(const char *pattern, bool verbose)
 			appendPQExpBuffer(&buf,
 							  ", subfailover AS \"%s\"\n",
 							  gettext_noop("Failover"));
+		if (pset.sversion >= 170000)
+			appendPQExpBuffer(&buf,
+							  ", subdetectconflict AS \"%s\"\n",
+							  gettext_noop("Detect conflict"));
 
 		appendPQExpBuffer(&buf,
 						  ",  subsynccommit AS \"%s\"\n"
diff --git a/src/bin/psql/tab-complete.c b/src/bin/psql/tab-complete.c
index d453e224d9..219fac7e71 100644
--- a/src/bin/psql/tab-complete.c
+++ b/src/bin/psql/tab-complete.c
@@ -1946,9 +1946,10 @@ psql_completion(const char *text, int start, int end)
 		COMPLETE_WITH("(", "PUBLICATION");
 	/* ALTER SUBSCRIPTION <name> SET ( */
 	else if (HeadMatches("ALTER", "SUBSCRIPTION", MatchAny) && TailMatches("SET", "("))
-		COMPLETE_WITH("binary", "disable_on_error", "failover", "origin",
-					  "password_required", "run_as_owner", "slot_name",
-					  "streaming", "synchronous_commit");
+		COMPLETE_WITH("binary", "detect_conflict", "disable_on_error",
+					  "failover", "origin", "password_required",
+					  "run_as_owner", "slot_name", "streaming",
+					  "synchronous_commit");
 	/* ALTER SUBSCRIPTION <name> SKIP ( */
 	else if (HeadMatches("ALTER", "SUBSCRIPTION", MatchAny) && TailMatches("SKIP", "("))
 		COMPLETE_WITH("lsn");
@@ -3363,9 +3364,10 @@ psql_completion(const char *text, int start, int end)
 	/* Complete "CREATE SUBSCRIPTION <name> ...  WITH ( <opt>" */
 	else if (HeadMatches("CREATE", "SUBSCRIPTION") && TailMatches("WITH", "("))
 		COMPLETE_WITH("binary", "connect", "copy_data", "create_slot",
-					  "disable_on_error", "enabled", "failover", "origin",
-					  "password_required", "run_as_owner", "slot_name",
-					  "streaming", "synchronous_commit", "two_phase");
+					  "detect_conflict", "disable_on_error", "enabled",
+					  "failover", "origin", "password_required",
+					  "run_as_owner", "slot_name", "streaming",
+					  "synchronous_commit", "two_phase");
 
 /* CREATE TRIGGER --- is allowed inside CREATE SCHEMA, so use TailMatches */
 
diff --git a/src/include/catalog/pg_subscription.h b/src/include/catalog/pg_subscription.h
index 0aa14ec4a2..17daf11dc7 100644
--- a/src/include/catalog/pg_subscription.h
+++ b/src/include/catalog/pg_subscription.h
@@ -98,6 +98,9 @@ CATALOG(pg_subscription,6100,SubscriptionRelationId) BKI_SHARED_RELATION BKI_ROW
 								 * slots) in the upstream database are enabled
 								 * to be synchronized to the standbys. */
 
+	bool		subdetectconflict;	/* True if replication should perform
+									 * conflict detection */
+
 #ifdef CATALOG_VARLEN			/* variable-length fields start here */
 	/* Connection string to the publisher */
 	text		subconninfo BKI_FORCE_NOT_NULL;
@@ -151,6 +154,7 @@ typedef struct Subscription
 								 * (i.e. the main slot and the table sync
 								 * slots) in the upstream database are enabled
 								 * to be synchronized to the standbys. */
+	bool		detectconflict; /* True if conflict detection is enabled */
 	char	   *conninfo;		/* Connection string to the publisher */
 	char	   *slotname;		/* Name of the replication slot */
 	char	   *synccommit;		/* Synchronous commit setting for worker */
diff --git a/src/include/replication/conflict.h b/src/include/replication/conflict.h
new file mode 100644
index 0000000000..a9f521aaca
--- /dev/null
+++ b/src/include/replication/conflict.h
@@ -0,0 +1,47 @@
+/*-------------------------------------------------------------------------
+ * conflict.h
+ *	   Exports for conflict detection and log
+ *
+ * Copyright (c) 2012-2024, PostgreSQL Global Development Group
+ *
+ *-------------------------------------------------------------------------
+ */
+#ifndef CONFLICT_H
+#define CONFLICT_H
+
+#include "access/xlogdefs.h"
+#include "executor/tuptable.h"
+#include "nodes/execnodes.h"
+#include "utils/relcache.h"
+#include "utils/timestamp.h"
+
+/*
+ * Conflict types that could be encountered when applying remote changes.
+ */
+typedef enum
+{
+	/* The row to be inserted violates unique constraint */
+	CT_INSERT_EXISTS,
+
+	/* The row to be updated was modified by a different origin */
+	CT_UPDATE_DIFFER,
+
+	/* The row to be updated is missing */
+	CT_UPDATE_MISSING,
+
+	/* The row to be deleted is missing */
+	CT_DELETE_MISSING,
+
+	/* The row to be deleted was modified by a different origin */
+	CT_DELETE_DIFFER,
+} ConflictType;
+
+extern bool GetTupleCommitTs(TupleTableSlot *localslot, TransactionId *xmin,
+							 RepOriginId *localorigin, TimestampTz *localts);
+extern void ReportApplyConflict(int elevel, ConflictType type,
+								Relation localrel, Oid conflictidx,
+								TransactionId localxmin, RepOriginId localorigin,
+								TimestampTz localts, TupleTableSlot *conflictslot);
+extern void InitConflictIndexes(ResultRelInfo *relInfo);
+
+#endif
diff --git a/src/test/regress/expected/subscription.out b/src/test/regress/expected/subscription.out
index 0f2a25cdc1..a8b0086dd9 100644
--- a/src/test/regress/expected/subscription.out
+++ b/src/test/regress/expected/subscription.out
@@ -116,18 +116,18 @@ CREATE SUBSCRIPTION regress_testsub4 CONNECTION 'dbname=regress_doesnotexist' PU
 WARNING:  subscription was created, but is not connected
 HINT:  To initiate replication, you must manually create the replication slot, enable the subscription, and refresh the subscription.
 \dRs+ regress_testsub4
-                                                                                                                 List of subscriptions
-       Name       |           Owner           | Enabled | Publication | Binary | Streaming | Two-phase commit | Disable on error | Origin | Password required | Run as owner? | Failover | Synchronous commit |          Conninfo           | Skip LSN 
-------------------+---------------------------+---------+-------------+--------+-----------+------------------+------------------+--------+-------------------+---------------+----------+--------------------+-----------------------------+----------
- regress_testsub4 | regress_subscription_user | f       | {testpub}   | f      | off       | d                | f                | none   | t                 | f             | f        | off                | dbname=regress_doesnotexist | 0/0
+                                                                                                                          List of subscriptions
+       Name       |           Owner           | Enabled | Publication | Binary | Streaming | Two-phase commit | Disable on error | Origin | Password required | Run as owner? | Failover | Detect conflict | Synchronous commit |          Conninfo           | Skip LSN 
+------------------+---------------------------+---------+-------------+--------+-----------+------------------+------------------+--------+-------------------+---------------+----------+-----------------+--------------------+-----------------------------+----------
+ regress_testsub4 | regress_subscription_user | f       | {testpub}   | f      | off       | d                | f                | none   | t                 | f             | f        | f               | off                | dbname=regress_doesnotexist | 0/0
 (1 row)
 
 ALTER SUBSCRIPTION regress_testsub4 SET (origin = any);
 \dRs+ regress_testsub4
-                                                                                                                 List of subscriptions
-       Name       |           Owner           | Enabled | Publication | Binary | Streaming | Two-phase commit | Disable on error | Origin | Password required | Run as owner? | Failover | Synchronous commit |          Conninfo           | Skip LSN 
-------------------+---------------------------+---------+-------------+--------+-----------+------------------+------------------+--------+-------------------+---------------+----------+--------------------+-----------------------------+----------
- regress_testsub4 | regress_subscription_user | f       | {testpub}   | f      | off       | d                | f                | any    | t                 | f             | f        | off                | dbname=regress_doesnotexist | 0/0
+                                                                                                                          List of subscriptions
+       Name       |           Owner           | Enabled | Publication | Binary | Streaming | Two-phase commit | Disable on error | Origin | Password required | Run as owner? | Failover | Detect conflict | Synchronous commit |          Conninfo           | Skip LSN 
+------------------+---------------------------+---------+-------------+--------+-----------+------------------+------------------+--------+-------------------+---------------+----------+-----------------+--------------------+-----------------------------+----------
+ regress_testsub4 | regress_subscription_user | f       | {testpub}   | f      | off       | d                | f                | any    | t                 | f             | f        | f               | off                | dbname=regress_doesnotexist | 0/0
 (1 row)
 
 DROP SUBSCRIPTION regress_testsub3;
@@ -145,10 +145,10 @@ ALTER SUBSCRIPTION regress_testsub CONNECTION 'foobar';
 ERROR:  invalid connection string syntax: missing "=" after "foobar" in connection info string
 
 \dRs+
-                                                                                                                List of subscriptions
-      Name       |           Owner           | Enabled | Publication | Binary | Streaming | Two-phase commit | Disable on error | Origin | Password required | Run as owner? | Failover | Synchronous commit |          Conninfo           | Skip LSN 
------------------+---------------------------+---------+-------------+--------+-----------+------------------+------------------+--------+-------------------+---------------+----------+--------------------+-----------------------------+----------
- regress_testsub | regress_subscription_user | f       | {testpub}   | f      | off       | d                | f                | any    | t                 | f             | f        | off                | dbname=regress_doesnotexist | 0/0
+                                                                                                                         List of subscriptions
+      Name       |           Owner           | Enabled | Publication | Binary | Streaming | Two-phase commit | Disable on error | Origin | Password required | Run as owner? | Failover | Detect conflict | Synchronous commit |          Conninfo           | Skip LSN 
+-----------------+---------------------------+---------+-------------+--------+-----------+------------------+------------------+--------+-------------------+---------------+----------+-----------------+--------------------+-----------------------------+----------
+ regress_testsub | regress_subscription_user | f       | {testpub}   | f      | off       | d                | f                | any    | t                 | f             | f        | f               | off                | dbname=regress_doesnotexist | 0/0
 (1 row)
 
 ALTER SUBSCRIPTION regress_testsub SET PUBLICATION testpub2, testpub3 WITH (refresh = false);
@@ -157,10 +157,10 @@ ALTER SUBSCRIPTION regress_testsub SET (slot_name = 'newname');
 ALTER SUBSCRIPTION regress_testsub SET (password_required = false);
 ALTER SUBSCRIPTION regress_testsub SET (run_as_owner = true);
 \dRs+
-                                                                                                                     List of subscriptions
-      Name       |           Owner           | Enabled |     Publication     | Binary | Streaming | Two-phase commit | Disable on error | Origin | Password required | Run as owner? | Failover | Synchronous commit |           Conninfo           | Skip LSN 
------------------+---------------------------+---------+---------------------+--------+-----------+------------------+------------------+--------+-------------------+---------------+----------+--------------------+------------------------------+----------
- regress_testsub | regress_subscription_user | f       | {testpub2,testpub3} | f      | off       | d                | f                | any    | f                 | t             | f        | off                | dbname=regress_doesnotexist2 | 0/0
+                                                                                                                              List of subscriptions
+      Name       |           Owner           | Enabled |     Publication     | Binary | Streaming | Two-phase commit | Disable on error | Origin | Password required | Run as owner? | Failover | Detect conflict | Synchronous commit |           Conninfo           | Skip LSN 
+-----------------+---------------------------+---------+---------------------+--------+-----------+------------------+------------------+--------+-------------------+---------------+----------+-----------------+--------------------+------------------------------+----------
+ regress_testsub | regress_subscription_user | f       | {testpub2,testpub3} | f      | off       | d                | f                | any    | f                 | t             | f        | f               | off                | dbname=regress_doesnotexist2 | 0/0
 (1 row)
 
 ALTER SUBSCRIPTION regress_testsub SET (password_required = true);
@@ -176,10 +176,10 @@ ERROR:  unrecognized subscription parameter: "create_slot"
 -- ok
 ALTER SUBSCRIPTION regress_testsub SKIP (lsn = '0/12345');
 \dRs+
-                                                                                                                     List of subscriptions
-      Name       |           Owner           | Enabled |     Publication     | Binary | Streaming | Two-phase commit | Disable on error | Origin | Password required | Run as owner? | Failover | Synchronous commit |           Conninfo           | Skip LSN 
------------------+---------------------------+---------+---------------------+--------+-----------+------------------+------------------+--------+-------------------+---------------+----------+--------------------+------------------------------+----------
- regress_testsub | regress_subscription_user | f       | {testpub2,testpub3} | f      | off       | d                | f                | any    | t                 | f             | f        | off                | dbname=regress_doesnotexist2 | 0/12345
+                                                                                                                              List of subscriptions
+      Name       |           Owner           | Enabled |     Publication     | Binary | Streaming | Two-phase commit | Disable on error | Origin | Password required | Run as owner? | Failover | Detect conflict | Synchronous commit |           Conninfo           | Skip LSN 
+-----------------+---------------------------+---------+---------------------+--------+-----------+------------------+------------------+--------+-------------------+---------------+----------+-----------------+--------------------+------------------------------+----------
+ regress_testsub | regress_subscription_user | f       | {testpub2,testpub3} | f      | off       | d                | f                | any    | t                 | f             | f        | f               | off                | dbname=regress_doesnotexist2 | 0/12345
 (1 row)
 
 -- ok - with lsn = NONE
@@ -188,10 +188,10 @@ ALTER SUBSCRIPTION regress_testsub SKIP (lsn = NONE);
 ALTER SUBSCRIPTION regress_testsub SKIP (lsn = '0/0');
 ERROR:  invalid WAL location (LSN): 0/0
 \dRs+
-                                                                                                                     List of subscriptions
-      Name       |           Owner           | Enabled |     Publication     | Binary | Streaming | Two-phase commit | Disable on error | Origin | Password required | Run as owner? | Failover | Synchronous commit |           Conninfo           | Skip LSN 
------------------+---------------------------+---------+---------------------+--------+-----------+------------------+------------------+--------+-------------------+---------------+----------+--------------------+------------------------------+----------
- regress_testsub | regress_subscription_user | f       | {testpub2,testpub3} | f      | off       | d                | f                | any    | t                 | f             | f        | off                | dbname=regress_doesnotexist2 | 0/0
+                                                                                                                              List of subscriptions
+      Name       |           Owner           | Enabled |     Publication     | Binary | Streaming | Two-phase commit | Disable on error | Origin | Password required | Run as owner? | Failover | Detect conflict | Synchronous commit |           Conninfo           | Skip LSN 
+-----------------+---------------------------+---------+---------------------+--------+-----------+------------------+------------------+--------+-------------------+---------------+----------+-----------------+--------------------+------------------------------+----------
+ regress_testsub | regress_subscription_user | f       | {testpub2,testpub3} | f      | off       | d                | f                | any    | t                 | f             | f        | f               | off                | dbname=regress_doesnotexist2 | 0/0
 (1 row)
 
 BEGIN;
@@ -223,10 +223,10 @@ ALTER SUBSCRIPTION regress_testsub_foo SET (synchronous_commit = foobar);
 ERROR:  invalid value for parameter "synchronous_commit": "foobar"
 HINT:  Available values: local, remote_write, remote_apply, on, off.
 \dRs+
-                                                                                                                       List of subscriptions
-        Name         |           Owner           | Enabled |     Publication     | Binary | Streaming | Two-phase commit | Disable on error | Origin | Password required | Run as owner? | Failover | Synchronous commit |           Conninfo           | Skip LSN 
----------------------+---------------------------+---------+---------------------+--------+-----------+------------------+------------------+--------+-------------------+---------------+----------+--------------------+------------------------------+----------
- regress_testsub_foo | regress_subscription_user | f       | {testpub2,testpub3} | f      | off       | d                | f                | any    | t                 | f             | f        | local              | dbname=regress_doesnotexist2 | 0/0
+                                                                                                                                List of subscriptions
+        Name         |           Owner           | Enabled |     Publication     | Binary | Streaming | Two-phase commit | Disable on error | Origin | Password required | Run as owner? | Failover | Detect conflict | Synchronous commit |           Conninfo           | Skip LSN 
+---------------------+---------------------------+---------+---------------------+--------+-----------+------------------+------------------+--------+-------------------+---------------+----------+-----------------+--------------------+------------------------------+----------
+ regress_testsub_foo | regress_subscription_user | f       | {testpub2,testpub3} | f      | off       | d                | f                | any    | t                 | f             | f        | f               | local              | dbname=regress_doesnotexist2 | 0/0
 (1 row)
 
 -- rename back to keep the rest simple
@@ -255,19 +255,19 @@ CREATE SUBSCRIPTION regress_testsub CONNECTION 'dbname=regress_doesnotexist' PUB
 WARNING:  subscription was created, but is not connected
 HINT:  To initiate replication, you must manually create the replication slot, enable the subscription, and refresh the subscription.
 \dRs+
-                                                                                                                List of subscriptions
-      Name       |           Owner           | Enabled | Publication | Binary | Streaming | Two-phase commit | Disable on error | Origin | Password required | Run as owner? | Failover | Synchronous commit |          Conninfo           | Skip LSN 
------------------+---------------------------+---------+-------------+--------+-----------+------------------+------------------+--------+-------------------+---------------+----------+--------------------+-----------------------------+----------
- regress_testsub | regress_subscription_user | f       | {testpub}   | t      | off       | d                | f                | any    | t                 | f             | f        | off                | dbname=regress_doesnotexist | 0/0
+                                                                                                                         List of subscriptions
+      Name       |           Owner           | Enabled | Publication | Binary | Streaming | Two-phase commit | Disable on error | Origin | Password required | Run as owner? | Failover | Detect conflict | Synchronous commit |          Conninfo           | Skip LSN 
+-----------------+---------------------------+---------+-------------+--------+-----------+------------------+------------------+--------+-------------------+---------------+----------+-----------------+--------------------+-----------------------------+----------
+ regress_testsub | regress_subscription_user | f       | {testpub}   | t      | off       | d                | f                | any    | t                 | f             | f        | f               | off                | dbname=regress_doesnotexist | 0/0
 (1 row)
 
 ALTER SUBSCRIPTION regress_testsub SET (binary = false);
 ALTER SUBSCRIPTION regress_testsub SET (slot_name = NONE);
 \dRs+
-                                                                                                                List of subscriptions
-      Name       |           Owner           | Enabled | Publication | Binary | Streaming | Two-phase commit | Disable on error | Origin | Password required | Run as owner? | Failover | Synchronous commit |          Conninfo           | Skip LSN 
------------------+---------------------------+---------+-------------+--------+-----------+------------------+------------------+--------+-------------------+---------------+----------+--------------------+-----------------------------+----------
- regress_testsub | regress_subscription_user | f       | {testpub}   | f      | off       | d                | f                | any    | t                 | f             | f        | off                | dbname=regress_doesnotexist | 0/0
+                                                                                                                         List of subscriptions
+      Name       |           Owner           | Enabled | Publication | Binary | Streaming | Two-phase commit | Disable on error | Origin | Password required | Run as owner? | Failover | Detect conflict | Synchronous commit |          Conninfo           | Skip LSN 
+-----------------+---------------------------+---------+-------------+--------+-----------+------------------+------------------+--------+-------------------+---------------+----------+-----------------+--------------------+-----------------------------+----------
+ regress_testsub | regress_subscription_user | f       | {testpub}   | f      | off       | d                | f                | any    | t                 | f             | f        | f               | off                | dbname=regress_doesnotexist | 0/0
 (1 row)
 
 DROP SUBSCRIPTION regress_testsub;
@@ -279,27 +279,27 @@ CREATE SUBSCRIPTION regress_testsub CONNECTION 'dbname=regress_doesnotexist' PUB
 WARNING:  subscription was created, but is not connected
 HINT:  To initiate replication, you must manually create the replication slot, enable the subscription, and refresh the subscription.
 \dRs+
-                                                                                                                List of subscriptions
-      Name       |           Owner           | Enabled | Publication | Binary | Streaming | Two-phase commit | Disable on error | Origin | Password required | Run as owner? | Failover | Synchronous commit |          Conninfo           | Skip LSN 
------------------+---------------------------+---------+-------------+--------+-----------+------------------+------------------+--------+-------------------+---------------+----------+--------------------+-----------------------------+----------
- regress_testsub | regress_subscription_user | f       | {testpub}   | f      | on        | d                | f                | any    | t                 | f             | f        | off                | dbname=regress_doesnotexist | 0/0
+                                                                                                                         List of subscriptions
+      Name       |           Owner           | Enabled | Publication | Binary | Streaming | Two-phase commit | Disable on error | Origin | Password required | Run as owner? | Failover | Detect conflict | Synchronous commit |          Conninfo           | Skip LSN 
+-----------------+---------------------------+---------+-------------+--------+-----------+------------------+------------------+--------+-------------------+---------------+----------+-----------------+--------------------+-----------------------------+----------
+ regress_testsub | regress_subscription_user | f       | {testpub}   | f      | on        | d                | f                | any    | t                 | f             | f        | f               | off                | dbname=regress_doesnotexist | 0/0
 (1 row)
 
 ALTER SUBSCRIPTION regress_testsub SET (streaming = parallel);
 \dRs+
-                                                                                                                List of subscriptions
-      Name       |           Owner           | Enabled | Publication | Binary | Streaming | Two-phase commit | Disable on error | Origin | Password required | Run as owner? | Failover | Synchronous commit |          Conninfo           | Skip LSN 
------------------+---------------------------+---------+-------------+--------+-----------+------------------+------------------+--------+-------------------+---------------+----------+--------------------+-----------------------------+----------
- regress_testsub | regress_subscription_user | f       | {testpub}   | f      | parallel  | d                | f                | any    | t                 | f             | f        | off                | dbname=regress_doesnotexist | 0/0
+                                                                                                                         List of subscriptions
+      Name       |           Owner           | Enabled | Publication | Binary | Streaming | Two-phase commit | Disable on error | Origin | Password required | Run as owner? | Failover | Detect conflict | Synchronous commit |          Conninfo           | Skip LSN 
+-----------------+---------------------------+---------+-------------+--------+-----------+------------------+------------------+--------+-------------------+---------------+----------+-----------------+--------------------+-----------------------------+----------
+ regress_testsub | regress_subscription_user | f       | {testpub}   | f      | parallel  | d                | f                | any    | t                 | f             | f        | f               | off                | dbname=regress_doesnotexist | 0/0
 (1 row)
 
 ALTER SUBSCRIPTION regress_testsub SET (streaming = false);
 ALTER SUBSCRIPTION regress_testsub SET (slot_name = NONE);
 \dRs+
-                                                                                                                List of subscriptions
-      Name       |           Owner           | Enabled | Publication | Binary | Streaming | Two-phase commit | Disable on error | Origin | Password required | Run as owner? | Failover | Synchronous commit |          Conninfo           | Skip LSN 
------------------+---------------------------+---------+-------------+--------+-----------+------------------+------------------+--------+-------------------+---------------+----------+--------------------+-----------------------------+----------
- regress_testsub | regress_subscription_user | f       | {testpub}   | f      | off       | d                | f                | any    | t                 | f             | f        | off                | dbname=regress_doesnotexist | 0/0
+                                                                                                                         List of subscriptions
+      Name       |           Owner           | Enabled | Publication | Binary | Streaming | Two-phase commit | Disable on error | Origin | Password required | Run as owner? | Failover | Detect conflict | Synchronous commit |          Conninfo           | Skip LSN 
+-----------------+---------------------------+---------+-------------+--------+-----------+------------------+------------------+--------+-------------------+---------------+----------+-----------------+--------------------+-----------------------------+----------
+ regress_testsub | regress_subscription_user | f       | {testpub}   | f      | off       | d                | f                | any    | t                 | f             | f        | f               | off                | dbname=regress_doesnotexist | 0/0
 (1 row)
 
 -- fail - publication already exists
@@ -314,10 +314,10 @@ ALTER SUBSCRIPTION regress_testsub ADD PUBLICATION testpub1, testpub2 WITH (refr
 ALTER SUBSCRIPTION regress_testsub ADD PUBLICATION testpub1, testpub2 WITH (refresh = false);
 ERROR:  publication "testpub1" is already in subscription "regress_testsub"
 \dRs+
-                                                                                                                        List of subscriptions
-      Name       |           Owner           | Enabled |         Publication         | Binary | Streaming | Two-phase commit | Disable on error | Origin | Password required | Run as owner? | Failover | Synchronous commit |          Conninfo           | Skip LSN 
------------------+---------------------------+---------+-----------------------------+--------+-----------+------------------+------------------+--------+-------------------+---------------+----------+--------------------+-----------------------------+----------
- regress_testsub | regress_subscription_user | f       | {testpub,testpub1,testpub2} | f      | off       | d                | f                | any    | t                 | f             | f        | off                | dbname=regress_doesnotexist | 0/0
+                                                                                                                                 List of subscriptions
+      Name       |           Owner           | Enabled |         Publication         | Binary | Streaming | Two-phase commit | Disable on error | Origin | Password required | Run as owner? | Failover | Detect conflict | Synchronous commit |          Conninfo           | Skip LSN 
+-----------------+---------------------------+---------+-----------------------------+--------+-----------+------------------+------------------+--------+-------------------+---------------+----------+-----------------+--------------------+-----------------------------+----------
+ regress_testsub | regress_subscription_user | f       | {testpub,testpub1,testpub2} | f      | off       | d                | f                | any    | t                 | f             | f        | f               | off                | dbname=regress_doesnotexist | 0/0
 (1 row)
 
 -- fail - publication used more than once
@@ -332,10 +332,10 @@ ERROR:  publication "testpub3" is not in subscription "regress_testsub"
 -- ok - delete publications
 ALTER SUBSCRIPTION regress_testsub DROP PUBLICATION testpub1, testpub2 WITH (refresh = false);
 \dRs+
-                                                                                                                List of subscriptions
-      Name       |           Owner           | Enabled | Publication | Binary | Streaming | Two-phase commit | Disable on error | Origin | Password required | Run as owner? | Failover | Synchronous commit |          Conninfo           | Skip LSN 
------------------+---------------------------+---------+-------------+--------+-----------+------------------+------------------+--------+-------------------+---------------+----------+--------------------+-----------------------------+----------
- regress_testsub | regress_subscription_user | f       | {testpub}   | f      | off       | d                | f                | any    | t                 | f             | f        | off                | dbname=regress_doesnotexist | 0/0
+                                                                                                                         List of subscriptions
+      Name       |           Owner           | Enabled | Publication | Binary | Streaming | Two-phase commit | Disable on error | Origin | Password required | Run as owner? | Failover | Detect conflict | Synchronous commit |          Conninfo           | Skip LSN 
+-----------------+---------------------------+---------+-------------+--------+-----------+------------------+------------------+--------+-------------------+---------------+----------+-----------------+--------------------+-----------------------------+----------
+ regress_testsub | regress_subscription_user | f       | {testpub}   | f      | off       | d                | f                | any    | t                 | f             | f        | f               | off                | dbname=regress_doesnotexist | 0/0
 (1 row)
 
 DROP SUBSCRIPTION regress_testsub;
@@ -371,10 +371,10 @@ CREATE SUBSCRIPTION regress_testsub CONNECTION 'dbname=regress_doesnotexist' PUB
 WARNING:  subscription was created, but is not connected
 HINT:  To initiate replication, you must manually create the replication slot, enable the subscription, and refresh the subscription.
 \dRs+
-                                                                                                                List of subscriptions
-      Name       |           Owner           | Enabled | Publication | Binary | Streaming | Two-phase commit | Disable on error | Origin | Password required | Run as owner? | Failover | Synchronous commit |          Conninfo           | Skip LSN 
------------------+---------------------------+---------+-------------+--------+-----------+------------------+------------------+--------+-------------------+---------------+----------+--------------------+-----------------------------+----------
- regress_testsub | regress_subscription_user | f       | {testpub}   | f      | off       | p                | f                | any    | t                 | f             | f        | off                | dbname=regress_doesnotexist | 0/0
+                                                                                                                         List of subscriptions
+      Name       |           Owner           | Enabled | Publication | Binary | Streaming | Two-phase commit | Disable on error | Origin | Password required | Run as owner? | Failover | Detect conflict | Synchronous commit |          Conninfo           | Skip LSN 
+-----------------+---------------------------+---------+-------------+--------+-----------+------------------+------------------+--------+-------------------+---------------+----------+-----------------+--------------------+-----------------------------+----------
+ regress_testsub | regress_subscription_user | f       | {testpub}   | f      | off       | p                | f                | any    | t                 | f             | f        | f               | off                | dbname=regress_doesnotexist | 0/0
 (1 row)
 
 --fail - alter of two_phase option not supported.
@@ -383,10 +383,10 @@ ERROR:  unrecognized subscription parameter: "two_phase"
 -- but can alter streaming when two_phase enabled
 ALTER SUBSCRIPTION regress_testsub SET (streaming = true);
 \dRs+
-                                                                                                                List of subscriptions
-      Name       |           Owner           | Enabled | Publication | Binary | Streaming | Two-phase commit | Disable on error | Origin | Password required | Run as owner? | Failover | Synchronous commit |          Conninfo           | Skip LSN 
------------------+---------------------------+---------+-------------+--------+-----------+------------------+------------------+--------+-------------------+---------------+----------+--------------------+-----------------------------+----------
- regress_testsub | regress_subscription_user | f       | {testpub}   | f      | on        | p                | f                | any    | t                 | f             | f        | off                | dbname=regress_doesnotexist | 0/0
+                                                                                                                         List of subscriptions
+      Name       |           Owner           | Enabled | Publication | Binary | Streaming | Two-phase commit | Disable on error | Origin | Password required | Run as owner? | Failover | Detect conflict | Synchronous commit |          Conninfo           | Skip LSN 
+-----------------+---------------------------+---------+-------------+--------+-----------+------------------+------------------+--------+-------------------+---------------+----------+-----------------+--------------------+-----------------------------+----------
+ regress_testsub | regress_subscription_user | f       | {testpub}   | f      | on        | p                | f                | any    | t                 | f             | f        | f               | off                | dbname=regress_doesnotexist | 0/0
 (1 row)
 
 ALTER SUBSCRIPTION regress_testsub SET (slot_name = NONE);
@@ -396,10 +396,10 @@ CREATE SUBSCRIPTION regress_testsub CONNECTION 'dbname=regress_doesnotexist' PUB
 WARNING:  subscription was created, but is not connected
 HINT:  To initiate replication, you must manually create the replication slot, enable the subscription, and refresh the subscription.
 \dRs+
-                                                                                                                List of subscriptions
-      Name       |           Owner           | Enabled | Publication | Binary | Streaming | Two-phase commit | Disable on error | Origin | Password required | Run as owner? | Failover | Synchronous commit |          Conninfo           | Skip LSN 
------------------+---------------------------+---------+-------------+--------+-----------+------------------+------------------+--------+-------------------+---------------+----------+--------------------+-----------------------------+----------
- regress_testsub | regress_subscription_user | f       | {testpub}   | f      | on        | p                | f                | any    | t                 | f             | f        | off                | dbname=regress_doesnotexist | 0/0
+                                                                                                                         List of subscriptions
+      Name       |           Owner           | Enabled | Publication | Binary | Streaming | Two-phase commit | Disable on error | Origin | Password required | Run as owner? | Failover | Detect conflict | Synchronous commit |          Conninfo           | Skip LSN 
+-----------------+---------------------------+---------+-------------+--------+-----------+------------------+------------------+--------+-------------------+---------------+----------+-----------------+--------------------+-----------------------------+----------
+ regress_testsub | regress_subscription_user | f       | {testpub}   | f      | on        | p                | f                | any    | t                 | f             | f        | f               | off                | dbname=regress_doesnotexist | 0/0
 (1 row)
 
 ALTER SUBSCRIPTION regress_testsub SET (slot_name = NONE);
@@ -412,18 +412,42 @@ CREATE SUBSCRIPTION regress_testsub CONNECTION 'dbname=regress_doesnotexist' PUB
 WARNING:  subscription was created, but is not connected
 HINT:  To initiate replication, you must manually create the replication slot, enable the subscription, and refresh the subscription.
 \dRs+
-                                                                                                                List of subscriptions
-      Name       |           Owner           | Enabled | Publication | Binary | Streaming | Two-phase commit | Disable on error | Origin | Password required | Run as owner? | Failover | Synchronous commit |          Conninfo           | Skip LSN 
------------------+---------------------------+---------+-------------+--------+-----------+------------------+------------------+--------+-------------------+---------------+----------+--------------------+-----------------------------+----------
- regress_testsub | regress_subscription_user | f       | {testpub}   | f      | off       | d                | f                | any    | t                 | f             | f        | off                | dbname=regress_doesnotexist | 0/0
+                                                                                                                         List of subscriptions
+      Name       |           Owner           | Enabled | Publication | Binary | Streaming | Two-phase commit | Disable on error | Origin | Password required | Run as owner? | Failover | Detect conflict | Synchronous commit |          Conninfo           | Skip LSN 
+-----------------+---------------------------+---------+-------------+--------+-----------+------------------+------------------+--------+-------------------+---------------+----------+-----------------+--------------------+-----------------------------+----------
+ regress_testsub | regress_subscription_user | f       | {testpub}   | f      | off       | d                | f                | any    | t                 | f             | f        | f               | off                | dbname=regress_doesnotexist | 0/0
 (1 row)
 
 ALTER SUBSCRIPTION regress_testsub SET (disable_on_error = true);
 \dRs+
-                                                                                                                List of subscriptions
-      Name       |           Owner           | Enabled | Publication | Binary | Streaming | Two-phase commit | Disable on error | Origin | Password required | Run as owner? | Failover | Synchronous commit |          Conninfo           | Skip LSN 
------------------+---------------------------+---------+-------------+--------+-----------+------------------+------------------+--------+-------------------+---------------+----------+--------------------+-----------------------------+----------
- regress_testsub | regress_subscription_user | f       | {testpub}   | f      | off       | d                | t                | any    | t                 | f             | f        | off                | dbname=regress_doesnotexist | 0/0
+                                                                                                                         List of subscriptions
+      Name       |           Owner           | Enabled | Publication | Binary | Streaming | Two-phase commit | Disable on error | Origin | Password required | Run as owner? | Failover | Detect conflict | Synchronous commit |          Conninfo           | Skip LSN 
+-----------------+---------------------------+---------+-------------+--------+-----------+------------------+------------------+--------+-------------------+---------------+----------+-----------------+--------------------+-----------------------------+----------
+ regress_testsub | regress_subscription_user | f       | {testpub}   | f      | off       | d                | t                | any    | t                 | f             | f        | f               | off                | dbname=regress_doesnotexist | 0/0
+(1 row)
+
+ALTER SUBSCRIPTION regress_testsub SET (slot_name = NONE);
+DROP SUBSCRIPTION regress_testsub;
+-- fail - detect_conflict must be boolean
+CREATE SUBSCRIPTION regress_testsub CONNECTION 'dbname=regress_doesnotexist' PUBLICATION testpub WITH (connect = false, detect_conflict = foo);
+ERROR:  detect_conflict requires a Boolean value
+-- now it works
+CREATE SUBSCRIPTION regress_testsub CONNECTION 'dbname=regress_doesnotexist' PUBLICATION testpub WITH (connect = false, detect_conflict = true);
+WARNING:  subscription was created, but is not connected
+HINT:  To initiate replication, you must manually create the replication slot, enable the subscription, and refresh the subscription.
+\dRs+
+                                                                                                                         List of subscriptions
+      Name       |           Owner           | Enabled | Publication | Binary | Streaming | Two-phase commit | Disable on error | Origin | Password required | Run as owner? | Failover | Detect conflict | Synchronous commit |          Conninfo           | Skip LSN 
+-----------------+---------------------------+---------+-------------+--------+-----------+------------------+------------------+--------+-------------------+---------------+----------+-----------------+--------------------+-----------------------------+----------
+ regress_testsub | regress_subscription_user | f       | {testpub}   | f      | off       | d                | f                | any    | t                 | f             | f        | t               | off                | dbname=regress_doesnotexist | 0/0
+(1 row)
+
+ALTER SUBSCRIPTION regress_testsub SET (detect_conflict = false);
+\dRs+
+                                                                                                                         List of subscriptions
+      Name       |           Owner           | Enabled | Publication | Binary | Streaming | Two-phase commit | Disable on error | Origin | Password required | Run as owner? | Failover | Detect conflict | Synchronous commit |          Conninfo           | Skip LSN 
+-----------------+---------------------------+---------+-------------+--------+-----------+------------------+------------------+--------+-------------------+---------------+----------+-----------------+--------------------+-----------------------------+----------
+ regress_testsub | regress_subscription_user | f       | {testpub}   | f      | off       | d                | f                | any    | t                 | f             | f        | f               | off                | dbname=regress_doesnotexist | 0/0
 (1 row)
 
 ALTER SUBSCRIPTION regress_testsub SET (slot_name = NONE);
diff --git a/src/test/regress/sql/subscription.sql b/src/test/regress/sql/subscription.sql
index 3e5ba4cb8c..a77b196704 100644
--- a/src/test/regress/sql/subscription.sql
+++ b/src/test/regress/sql/subscription.sql
@@ -290,6 +290,21 @@ ALTER SUBSCRIPTION regress_testsub SET (disable_on_error = true);
 ALTER SUBSCRIPTION regress_testsub SET (slot_name = NONE);
 DROP SUBSCRIPTION regress_testsub;
 
+-- fail - detect_conflict must be boolean
+CREATE SUBSCRIPTION regress_testsub CONNECTION 'dbname=regress_doesnotexist' PUBLICATION testpub WITH (connect = false, detect_conflict = foo);
+
+-- now it works
+CREATE SUBSCRIPTION regress_testsub CONNECTION 'dbname=regress_doesnotexist' PUBLICATION testpub WITH (connect = false, detect_conflict = true);
+
+\dRs+
+
+ALTER SUBSCRIPTION regress_testsub SET (detect_conflict = false);
+
+\dRs+
+
+ALTER SUBSCRIPTION regress_testsub SET (slot_name = NONE);
+DROP SUBSCRIPTION regress_testsub;
+
 -- let's do some tests with pg_create_subscription rather than superuser
 SET SESSION AUTHORIZATION regress_subscription_user3;
 
diff --git a/src/test/subscription/t/001_rep_changes.pl b/src/test/subscription/t/001_rep_changes.pl
index 471e981962..78c0307165 100644
--- a/src/test/subscription/t/001_rep_changes.pl
+++ b/src/test/subscription/t/001_rep_changes.pl
@@ -331,11 +331,12 @@ is( $result, qq(1|bar
 2|baz),
 	'update works with REPLICA IDENTITY FULL and a primary key');
 
-# Check that subscriber handles cases where update/delete target tuple
-# is missing.  We have to look for the DEBUG1 log messages about that,
-# so temporarily bump up the log verbosity.
-$node_subscriber->append_conf('postgresql.conf', "log_min_messages = debug1");
-$node_subscriber->reload;
+# To check that subscriber handles cases where update/delete target tuple
+# is missing, detect_conflict is temporarily enabled to log conflicts
+# related to missing tuples.
+$node_subscriber->safe_psql('postgres',
+	"ALTER SUBSCRIPTION tap_sub SET (detect_conflict = true)"
+);
 
 $node_subscriber->safe_psql('postgres', "DELETE FROM tab_full_pk");
 
@@ -352,10 +353,10 @@ $node_publisher->wait_for_catchup('tap_sub');
 
 my $logfile = slurp_file($node_subscriber->logfile, $log_location);
 ok( $logfile =~
-	  qr/logical replication did not find row to be updated in replication target relation "tab_full_pk"/,
+	  qr/conflict update_missing detected on relation "public.tab_full_pk".*\n.*DETAIL:.* Did not find the row to be updated./m,
 	'update target row is missing');
 ok( $logfile =~
-	  qr/logical replication did not find row to be deleted in replication target relation "tab_full_pk"/,
+	  qr/conflict delete_missing detected on relation "public.tab_full_pk".*\n.*DETAIL:.* Did not find the row to be deleted./m,
 	'delete target row is missing');
 
 $node_subscriber->append_conf('postgresql.conf',
diff --git a/src/test/subscription/t/013_partition.pl b/src/test/subscription/t/013_partition.pl
index 29580525a9..7a66a06b51 100644
--- a/src/test/subscription/t/013_partition.pl
+++ b/src/test/subscription/t/013_partition.pl
@@ -343,12 +343,12 @@ $result =
   $node_subscriber2->safe_psql('postgres', "SELECT a FROM tab1 ORDER BY 1");
 is($result, qq(), 'truncate of tab1 replicated');
 
-# Check that subscriber handles cases where update/delete target tuple
-# is missing.  We have to look for the DEBUG1 log messages about that,
-# so temporarily bump up the log verbosity.
-$node_subscriber1->append_conf('postgresql.conf',
-	"log_min_messages = debug1");
-$node_subscriber1->reload;
+# To check that subscriber handles cases where update/delete target tuple
+# is missing, detect_conflict is temporarily enabled to log conflicts
+# related to missing tuples.
+$node_subscriber1->safe_psql('postgres',
+	"ALTER SUBSCRIPTION sub1 SET (detect_conflict = true)"
+);
 
 $node_publisher->safe_psql('postgres',
 	"INSERT INTO tab1 VALUES (1, 'foo'), (4, 'bar'), (10, 'baz')");
@@ -372,21 +372,21 @@ $node_publisher->wait_for_catchup('sub2');
 
 my $logfile = slurp_file($node_subscriber1->logfile(), $log_location);
 ok( $logfile =~
-	  qr/logical replication did not find row to be updated in replication target relation's partition "tab1_2_2"/,
+	  qr/conflict update_missing detected on relation "public.tab1_2_2".*\n.*DETAIL:.* Did not find the row to be updated./,
 	'update target row is missing in tab1_2_2');
 ok( $logfile =~
-	  qr/logical replication did not find row to be deleted in replication target relation "tab1_1"/,
+	  qr/conflict delete_missing detected on relation "public.tab1_1".*\n.*DETAIL:.* Did not find the row to be deleted./,
 	'delete target row is missing in tab1_1');
 ok( $logfile =~
-	  qr/logical replication did not find row to be deleted in replication target relation "tab1_2_2"/,
+	  qr/conflict delete_missing detected on relation "public.tab1_2_2".*\n.*DETAIL:.* Did not find the row to be deleted./,
 	'delete target row is missing in tab1_2_2');
 ok( $logfile =~
-	  qr/logical replication did not find row to be deleted in replication target relation "tab1_def"/,
+	  qr/conflict delete_missing detected on relation "public.tab1_def".*\n.*DETAIL:.* Did not find the row to be deleted./,
 	'delete target row is missing in tab1_def');
 
-$node_subscriber1->append_conf('postgresql.conf',
-	"log_min_messages = warning");
-$node_subscriber1->reload;
+$node_subscriber1->safe_psql('postgres',
+	"ALTER SUBSCRIPTION sub1 SET (detect_conflict = false)"
+);
 
 # Tests for replication using root table identity and schema
 
@@ -773,12 +773,12 @@ pub_tab2|3|yyy
 pub_tab2|5|zzz
 xxx_c|6|aaa), 'inserts into tab2 replicated');
 
-# Check that subscriber handles cases where update/delete target tuple
-# is missing.  We have to look for the DEBUG1 log messages about that,
-# so temporarily bump up the log verbosity.
-$node_subscriber1->append_conf('postgresql.conf',
-	"log_min_messages = debug1");
-$node_subscriber1->reload;
+# To check that subscriber handles cases where update/delete target tuple
+# is missing, detect_conflict is temporarily enabled to log conflicts
+# related to missing tuples.
+$node_subscriber1->safe_psql('postgres',
+	"ALTER SUBSCRIPTION sub_viaroot SET (detect_conflict = true)"
+);
 
 $node_subscriber1->safe_psql('postgres', "DELETE FROM tab2");
 
@@ -796,15 +796,35 @@ $node_publisher->wait_for_catchup('sub2');
 
 $logfile = slurp_file($node_subscriber1->logfile(), $log_location);
 ok( $logfile =~
-	  qr/logical replication did not find row to be updated in replication target relation's partition "tab2_1"/,
+	  qr/conflict update_missing detected on relation "public.tab2_1".*\n.*DETAIL:.* Did not find the row to be updated./,
 	'update target row is missing in tab2_1');
 ok( $logfile =~
-	  qr/logical replication did not find row to be deleted in replication target relation "tab2_1"/,
+	  qr/conflict delete_missing detected on relation "public.tab2_1".*\n.*DETAIL:.* Did not find the row to be deleted./,
 	'delete target row is missing in tab2_1');
 
-$node_subscriber1->append_conf('postgresql.conf',
-	"log_min_messages = warning");
-$node_subscriber1->reload;
+# Enable the track_commit_timestamp to detect the conflict when attempting
+# to update a row that was previously modified by a different origin.
+$node_subscriber1->append_conf('postgresql.conf', 'track_commit_timestamp = on');
+$node_subscriber1->restart;
+
+$node_subscriber1->safe_psql('postgres', "INSERT INTO tab2 VALUES (3, 'yyy')");
+$node_publisher->safe_psql('postgres',
+	"UPDATE tab2 SET b = 'quux' WHERE a = 3");
+
+$node_publisher->wait_for_catchup('sub_viaroot');
+
+$logfile = slurp_file($node_subscriber1->logfile(), $log_location);
+ok( $logfile =~
+	  qr/Updating a row that was modified by a different origin [0-9]+ in transaction [0-9]+ at .*/,
+	'updating a tuple that was modified by a different origin');
+
+# The remaining tests no longer test conflict detection.
+$node_subscriber1->safe_psql('postgres',
+	"ALTER SUBSCRIPTION sub_viaroot SET (detect_conflict = false)"
+);
+
+$node_subscriber1->append_conf('postgresql.conf', 'track_commit_timestamp = off');
+$node_subscriber1->restart;
 
 # Test that replication continues to work correctly after altering the
 # partition of a partitioned target table.
diff --git a/src/test/subscription/t/029_on_error.pl b/src/test/subscription/t/029_on_error.pl
index 0ab57a4b5b..496a3c6cd9 100644
--- a/src/test/subscription/t/029_on_error.pl
+++ b/src/test/subscription/t/029_on_error.pl
@@ -30,7 +30,7 @@ sub test_skip_lsn
 	# ERROR with its CONTEXT when retrieving this information.
 	my $contents = slurp_file($node_subscriber->logfile, $offset);
 	$contents =~
-	  qr/duplicate key value violates unique constraint "tbl_pkey".*\n.*DETAIL:.*\n.*CONTEXT:.* for replication target relation "public.tbl" in transaction \d+, finished at ([[:xdigit:]]+\/[[:xdigit:]]+)/m
+	  qr/conflict insert_exists detected on relation "public.tbl".*\n.*DETAIL:.* Key \(i\)=\(1\) already exists in unique index "tbl_pkey", which was modified by origin \d+ in transaction \d+ at .*\n.*CONTEXT:.* for replication target relation "public.tbl" in transaction \d+, finished at ([[:xdigit:]]+\/[[:xdigit:]]+)/m
 	  or die "could not get error-LSN";
 	my $lsn = $1;
 
@@ -83,6 +83,7 @@ $node_subscriber->append_conf(
 	'postgresql.conf',
 	qq[
 max_prepared_transactions = 10
+track_commit_timestamp = on
 ]);
 $node_subscriber->start;
 
@@ -109,7 +110,7 @@ my $publisher_connstr = $node_publisher->connstr . ' dbname=postgres';
 $node_publisher->safe_psql('postgres',
 	"CREATE PUBLICATION pub FOR TABLE tbl");
 $node_subscriber->safe_psql('postgres',
-	"CREATE SUBSCRIPTION sub CONNECTION '$publisher_connstr' PUBLICATION pub WITH (disable_on_error = true, streaming = on, two_phase = on)"
+	"CREATE SUBSCRIPTION sub CONNECTION '$publisher_connstr' PUBLICATION pub WITH (disable_on_error = true, streaming = on, two_phase = on, detect_conflict = on)"
 );
 
 # Initial synchronization failure causes the subscription to be disabled.
diff --git a/src/test/subscription/t/030_origin.pl b/src/test/subscription/t/030_origin.pl
index 056561f008..8c929c07c7 100644
--- a/src/test/subscription/t/030_origin.pl
+++ b/src/test/subscription/t/030_origin.pl
@@ -27,9 +27,14 @@ my $stderr;
 my $node_A = PostgreSQL::Test::Cluster->new('node_A');
 $node_A->init(allows_streaming => 'logical');
 $node_A->start;
+
 # node_B
 my $node_B = PostgreSQL::Test::Cluster->new('node_B');
 $node_B->init(allows_streaming => 'logical');
+
+# Enable the track_commit_timestamp to detect the conflict when attempting to
+# update a row that was previously modified by a different origin.
+$node_B->append_conf('postgresql.conf', 'track_commit_timestamp = on');
 $node_B->start;
 
 # Create table on node_A
@@ -139,6 +144,44 @@ is($result, qq(),
 	'Remote data originating from another node (not the publisher) is not replicated when origin parameter is none'
 );
 
+###############################################################################
+# Check that the conflict can be detected when attempting to update or
+# delete a row that was previously modified by a different source.
+###############################################################################
+
+$node_B->safe_psql('postgres',
+	"ALTER SUBSCRIPTION $subname_BC SET (detect_conflict = true);
+	 DELETE FROM tab;");
+
+$node_A->safe_psql('postgres', "INSERT INTO tab VALUES (32);");
+
+# The update should update the row on node B that was inserted by node A.
+$node_C->safe_psql('postgres', "UPDATE tab SET a = 33 WHERE a = 32;");
+
+$node_B->wait_for_log(
+	qr/Updating a row that was modified by a different origin [0-9]+ in transaction [0-9]+ at .*/
+);
+
+$node_B->safe_psql('postgres', "DELETE FROM tab;");
+$node_A->safe_psql('postgres', "INSERT INTO tab VALUES (33);");
+
+# The delete should remove the row on node B that was inserted by node A.
+$node_C->safe_psql('postgres', "DELETE FROM tab WHERE a = 33;");
+
+$node_B->wait_for_log(
+	qr/Deleting a row that was modified by a different origin [0-9]+ in transaction [0-9]+ at .*/
+);
+
+$node_A->wait_for_catchup($subname_BA);
+$node_B->wait_for_catchup($subname_AB);
+
+# The remaining tests no longer test conflict detection.
+$node_B->safe_psql('postgres',
+	"ALTER SUBSCRIPTION $subname_BC SET (detect_conflict = false);");
+
+$node_B->append_conf('postgresql.conf', 'track_commit_timestamp = off');
+$node_B->restart;
+
 ###############################################################################
 # Specifying origin = NONE indicates that the publisher should only replicate the
 # changes that are generated locally from node_B, but in this case since the
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index e710fa48e5..2485a80833 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -466,6 +466,7 @@ ConditionVariableMinimallyPadded
 ConditionalStack
 ConfigData
 ConfigVariable
+ConflictType
 ConnCacheEntry
 ConnCacheKey
 ConnParams
-- 
2.34.1



  [application/octet-stream] v4-0002-DDL-command-to-configure-Global-Conflict-Resolver.patch (26.5K, ../../CABdArM47myyKnOU4LB54k3wmgpFu63s2gxmAQVK-DdWzCLKAaw@mail.gmail.com/3-v4-0002-DDL-command-to-configure-Global-Conflict-Resolver.patch)
  download | inline diff:
From 07df9b3843d9b8d72b1448f2ed83185fc46804fc Mon Sep 17 00:00:00 2001
From: Nisha Moond <[email protected]>
Date: Wed, 3 Jul 2024 10:23:58 +0530
Subject: [PATCH v4 2/5] DDL command to configure Global Conflict Resolvers

This patch adds new DDL commands to configure resolvers
at global level:

a) To set global resolver for a given conflict_type:
SET CONFLICT RESOLVER 'conflict_resolver' FOR 'conflict_type'

b) To reset to default:
RESET CONFLICT RESOLVER FOR 'conflict_type'

A new catalog table pg_conflict has been created to store
global conflict_type and conflict_resolver configurations given by
above DDL command. Initially, this catalog table holds default
configuration for resolvers which is overwritten by the ones given
by the user in 'SET CONFLICT RESOLVER' command.
'RESET CONFLICT RESOLVER' command will reset the resolver to default.

This patch provides support to configure resolvers for below conflict
types:
- insert_exists
- update_differ
- update_missing
- delete_missing
- delete_differ
---
 src/backend/parser/gram.y                     |  42 +++-
 src/backend/replication/logical/conflict.c    | 218 +++++++++++++++++-
 src/backend/tcop/utility.c                    |  15 ++
 src/include/catalog/Makefile                  |   4 +-
 src/include/catalog/meson.build               |   2 +
 src/include/catalog/pg_conflict.dat           |  21 ++
 src/include/catalog/pg_conflict.h             |  43 ++++
 src/include/nodes/parsenodes.h                |  12 +
 src/include/parser/kwlist.h                   |   1 +
 src/include/replication/conflict.h            |  38 ++-
 src/include/tcop/cmdtaglist.h                 |   1 +
 .../regress/expected/conflict_resolver.out    |  54 +++++
 src/test/regress/parallel_schedule            |   2 +-
 src/test/regress/sql/conflict_resolver.sql    |  28 +++
 src/tools/pgindent/typedefs.list              |   2 +
 15 files changed, 476 insertions(+), 7 deletions(-)
 create mode 100644 src/include/catalog/pg_conflict.dat
 create mode 100644 src/include/catalog/pg_conflict.h
 create mode 100644 src/test/regress/expected/conflict_resolver.out
 create mode 100644 src/test/regress/sql/conflict_resolver.sql

diff --git a/src/backend/parser/gram.y b/src/backend/parser/gram.y
index a043fd4c66..42726fe3a6 100644
--- a/src/backend/parser/gram.y
+++ b/src/backend/parser/gram.y
@@ -292,7 +292,7 @@ static Node *makeRecursiveViewSelect(char *relname, List *aliases, Node *query);
 		AlterRoleStmt AlterRoleSetStmt AlterPolicyStmt AlterStatsStmt
 		AlterDefaultPrivilegesStmt DefACLAction
 		AnalyzeStmt CallStmt ClosePortalStmt ClusterStmt CommentStmt
-		ConstraintsSetStmt CopyStmt CreateAsStmt CreateCastStmt
+		ConflictResolverStmt ConstraintsSetStmt CopyStmt CreateAsStmt CreateCastStmt
 		CreateDomainStmt CreateExtensionStmt CreateGroupStmt CreateOpClassStmt
 		CreateOpFamilyStmt AlterOpFamilyStmt CreatePLangStmt
 		CreateSchemaStmt CreateSeqStmt CreateStmt CreateStatsStmt CreateTableSpaceStmt
@@ -613,6 +613,7 @@ static Node *makeRecursiveViewSelect(char *relname, List *aliases, Node *query);
 %type <ival>	opt_check_option
 
 %type <str>		opt_provider security_label
+%type <str>		conflict_type conflict_resolver
 
 %type <target>	xml_attribute_el
 %type <list>	xml_attribute_list xml_attributes
@@ -772,7 +773,7 @@ static Node *makeRecursiveViewSelect(char *relname, List *aliases, Node *query);
 
 	RANGE READ REAL REASSIGN RECHECK RECURSIVE REF_P REFERENCES REFERENCING
 	REFRESH REINDEX RELATIVE_P RELEASE RENAME REPEATABLE REPLACE REPLICA
-	RESET RESTART RESTRICT RETURN RETURNING RETURNS REVOKE RIGHT ROLE ROLLBACK ROLLUP
+	RESET RESOLVER RESTART RESTRICT RETURN RETURNING RETURNS REVOKE RIGHT ROLE ROLLBACK ROLLUP
 	ROUTINE ROUTINES ROW ROWS RULE
 
 	SAVEPOINT SCALAR SCHEMA SCHEMAS SCROLL SEARCH SECOND_P SECURITY SELECT
@@ -1039,6 +1040,7 @@ stmt:
 			| ClosePortalStmt
 			| ClusterStmt
 			| CommentStmt
+			| ConflictResolverStmt
 			| ConstraintsSetStmt
 			| CopyStmt
 			| CreateAmStmt
@@ -7266,7 +7268,41 @@ comment_text:
 			| NULL_P							{ $$ = NULL; }
 		;
 
+/*****************************************************************************
+ *
+ *  SET CONFLICT RESOLVER <conflict_resolver> FOR <conflict_type>
+ *  RESET CONFLICT RESOLVER FOR <conflict_type>
+ *
+ *****************************************************************************/
+
+ConflictResolverStmt:
+			SET CONFLICT RESOLVER conflict_resolver FOR conflict_type
+				{
+					ConflictResolverStmt *n = makeNode(ConflictResolverStmt);
+
+					n->conflict_resolver = $4;
+					n->conflict_type = $6;
+					n->isReset = false;
+					$$ = (Node *) n;
+				}
+			| RESET CONFLICT RESOLVER FOR conflict_type
+				{
+					ConflictResolverStmt *n = makeNode(ConflictResolverStmt);
 
+					n->conflict_type = $5;
+					n->isReset = true;
+					$$ = (Node *) n;
+				}
+		;
+conflict_type:
+			Sconst								{ $$ = $1; }
+			| NULL_P							{ $$ = NULL; }
+		;
+
+conflict_resolver:
+			Sconst								{ $$ = $1; }
+			| NULL_P							{ $$ = NULL; }
+		;
 /*****************************************************************************
  *
  *  SECURITY LABEL [FOR <provider>] ON <object> IS <label>
@@ -17797,6 +17833,7 @@ unreserved_keyword:
 			| REPLACE
 			| REPLICA
 			| RESET
+			| RESOLVER
 			| RESTART
 			| RESTRICT
 			| RETURN
@@ -18428,6 +18465,7 @@ bare_label_keyword:
 			| REPLACE
 			| REPLICA
 			| RESET
+			| RESOLVER
 			| RESTART
 			| RESTRICT
 			| RETURN
diff --git a/src/backend/replication/logical/conflict.c b/src/backend/replication/logical/conflict.c
index b90e64b05b..93d9659752 100644
--- a/src/backend/replication/logical/conflict.c
+++ b/src/backend/replication/logical/conflict.c
@@ -1,13 +1,13 @@
 /*-------------------------------------------------------------------------
  * conflict.c
- *	   Functionality for detecting and logging conflicts.
+ *	   Functionality for detecting, logging and configuring conflicts.
  *
  * Copyright (c) 2024, PostgreSQL Global Development Group
  *
  * IDENTIFICATION
  *	  src/backend/replication/logical/conflict.c
  *
- * This file contains the code for detecting and logging conflicts on
+ * This file contains the code for detecting and handling conflicts on
  * the subscriber during logical replication.
  *-------------------------------------------------------------------------
  */
@@ -15,10 +15,19 @@
 #include "postgres.h"
 
 #include "access/commit_ts.h"
+#include "access/genam.h"
+#include "access/htup_details.h"
+#include "access/skey.h"
+#include "access/table.h"
+#include "catalog/indexing.h"
+#include "catalog/pg_conflict.h"
 #include "replication/conflict.h"
 #include "replication/origin.h"
+#include "utils/builtins.h"
+#include "utils/fmgroids.h"
 #include "utils/lsyscache.h"
 #include "utils/rel.h"
+#include "utils/timestamp.h"
 
 const char *const ConflictTypeNames[] = {
 	[CT_INSERT_EXISTS] = "insert_exists",
@@ -28,6 +37,54 @@ const char *const ConflictTypeNames[] = {
 	[CT_DELETE_DIFFER] = "delete_differ"
 };
 
+const char *const ConflictResolverNames[] = {
+	[CR_REMOTE_APPLY] = "remote_apply",
+	[CR_KEEP_LOCAL] = "keep_local",
+	[CR_APPLY_OR_SKIP] = "apply_or_skip",
+	[CR_APPLY_OR_ERROR] = "apply_or_error",
+	[CR_SKIP] = "skip",
+	[CR_ERROR] = "error"
+};
+
+#define CONFLICT_TYPE_MAX_RESOLVERS 4
+
+/*
+ * Valid conflict resolvers for each conflict type.
+ *
+ * XXX: If we do not want to maintain different resolvers such as
+ * apply_or_skip and apply_or_error for update_missing conflict,
+ * then we can retain remote_apply and keep_local only. Then these
+ * resolvers in context of update_missing will mean:
+ *
+ * keep_local: do not apply the update as INSERT.
+ * remote_apply: apply the update as INSERT. If we could not apply,
+ * then log and skip.
+ *
+ * Similarly SKIP can be replaced with KEEP_LOCAL for both update_missing
+ * and delete_missing conflicts. For missing rows, 'SKIP' sounds more user
+ * friendly name for a resolver and thus has been added here.
+ */
+const int	ConflictTypeResolverMap[][CONFLICT_TYPE_MAX_RESOLVERS] = {
+	[CT_INSERT_EXISTS] = {CR_REMOTE_APPLY, CR_KEEP_LOCAL, CR_ERROR},
+	[CT_UPDATE_DIFFER] = {CR_REMOTE_APPLY, CR_KEEP_LOCAL, CR_ERROR},
+	[CT_UPDATE_MISSING] = {CR_APPLY_OR_SKIP, CR_APPLY_OR_ERROR, CR_SKIP, CR_ERROR},
+	[CT_DELETE_MISSING] = {CR_SKIP, CR_ERROR},
+	[CT_DELETE_DIFFER] = {CR_REMOTE_APPLY, CR_KEEP_LOCAL, CR_ERROR}
+};
+
+/*
+ * Default conflict resolver for each conflict type.
+ * If this changes, change it in pg_conflict.dat as well.
+ */
+const int	ConflictTypeDefaultResolvers[] = {
+	[CT_INSERT_EXISTS] = CR_REMOTE_APPLY,
+	[CT_UPDATE_DIFFER] = CR_REMOTE_APPLY,
+	[CT_UPDATE_MISSING] = CR_APPLY_OR_SKIP,
+	[CT_DELETE_MISSING] = CR_SKIP,
+	[CT_DELETE_DIFFER] = CR_REMOTE_APPLY
+
+};
+
 static char *build_index_value_desc(Oid indexoid, TupleTableSlot *conflictslot);
 static int	errdetail_apply_conflict(ConflictType type, Oid conflictidx,
 									 TransactionId localxmin,
@@ -35,6 +92,7 @@ static int	errdetail_apply_conflict(ConflictType type, Oid conflictidx,
 									 TimestampTz localts,
 									 TupleTableSlot *conflictslot);
 
+
 /*
  * Get the xmin and commit timestamp data (origin and timestamp) associated
  * with the provided local tuple.
@@ -189,3 +247,159 @@ build_index_value_desc(Oid indexoid, TupleTableSlot *conflictslot)
 
 	return conflict_row;
 }
+
+/*
+ * Validate the conflict type and resolver.
+ *
+ * Return ConflictType enum value corresponding to given conflict_type.
+ */
+static ConflictType
+validate_conflict_type_and_resolver(char *conflict_type, char *conflict_resolver,
+									bool isReset)
+{
+	ConflictType type;
+	ConflictResolver resolver;
+	bool		valid = false;
+	int			i;
+
+	/* Check conflict type validity */
+	for (type = CT_MIN; type <= CT_MAX; type++)
+	{
+		if (strcmp(ConflictTypeNames[type], conflict_type) == 0)
+		{
+			valid = true;
+			break;
+		}
+	}
+
+	if (!valid)
+		ereport(ERROR,
+				errcode(ERRCODE_INVALID_PARAMETER_VALUE),
+				errmsg("%s is not a valid conflict type", conflict_type));
+
+	/* If it is RESET statement, we are done */
+	if (isReset)
+		return type;
+
+	/* Reset */
+	valid = false;
+
+	/* Check conflict resolver validity. */
+	for (resolver = CR_MIN; resolver <= CR_MAX; resolver++)
+	{
+		if (strcmp(ConflictResolverNames[resolver], conflict_resolver) == 0)
+		{
+			valid = true;
+			break;
+		}
+	}
+
+	/*
+	 * XXX: Shall we give supported resolvers list for given type in error
+	 * hint?
+	 */
+	if (!valid)
+		ereport(ERROR,
+				errcode(ERRCODE_INVALID_PARAMETER_VALUE),
+				errmsg("%s is not a valid conflict resolver", conflict_resolver));
+
+	/* Reset */
+	valid = false;
+
+	/* Check if conflict resolver is a valid one for the given conflict type */
+	for (i = 0; i < CONFLICT_TYPE_MAX_RESOLVERS; i++)
+	{
+		if (ConflictTypeResolverMap[type][i] == resolver)
+		{
+			valid = true;
+			break;
+		}
+	}
+
+	/*
+	 * XXX: Shall we give supported resolvers list for given type in error
+	 * hint?
+	 */
+	if (!valid)
+		ereport(ERROR,
+				errcode(ERRCODE_INVALID_PARAMETER_VALUE),
+				errmsg("%s is not a valid conflict resolver for conflict type %s",
+					   conflict_resolver,
+					   conflict_type));
+	return type;
+}
+
+/*
+ * Execute Conflict Resolver Stmt
+ *
+ * Validate conflict_type and conflict_resolver given by the user
+ * and save the info in pg_conflict system catalog.
+ */
+void
+ExecConflictResolverStmt(ConflictResolverStmt *stmt)
+{
+	Relation	pg_conflict;
+	Datum		values[Natts_pg_conflict];
+	bool		nulls[Natts_pg_conflict];
+	bool		replaces[Natts_pg_conflict];
+	ScanKeyData keys[1];
+	SysScanDesc scan;
+	HeapTuple	oldtup;
+	HeapTuple	newtup = NULL;
+	ConflictType type;
+
+	type = validate_conflict_type_and_resolver(stmt->conflict_type,
+											   stmt->conflict_resolver,
+											   stmt->isReset);
+
+
+	/* Prepare to update a tuple in pg_conflict system catalog */
+	memset(values, 0, sizeof(values));
+	memset(nulls, false, sizeof(nulls));
+	memset(replaces, false, sizeof(replaces));
+
+	values[Anum_pg_conflict_conftype - 1] =
+		CStringGetTextDatum(stmt->conflict_type);
+
+	if (stmt->isReset)
+	{
+		/* Set resolver to default */
+		ConflictResolver resolver = ConflictTypeDefaultResolvers[type];
+
+		values[Anum_pg_conflict_confres - 1] =
+			CStringGetTextDatum(ConflictResolverNames[resolver]);
+	}
+	else
+		values[Anum_pg_conflict_confres - 1] =
+			CStringGetTextDatum(stmt->conflict_resolver);
+
+	/* Use the index to search for a matching old tuple */
+	ScanKeyInit(&keys[0],
+				Anum_pg_conflict_conftype,
+				BTEqualStrategyNumber, F_TEXTEQ,
+				values[Anum_pg_conflict_conftype - 1]);
+
+	pg_conflict = table_open(ConflictResRelationId, RowExclusiveLock);
+
+	scan = systable_beginscan(pg_conflict, ConflictTypeIndexId, true,
+							  NULL, 1, keys);
+
+	oldtup = systable_getnext(scan);
+	if (HeapTupleIsValid(oldtup))
+	{
+		replaces[Anum_pg_conflict_confres - 1] = true;
+		newtup = heap_modify_tuple(oldtup, RelationGetDescr(pg_conflict),
+								   values, nulls, replaces);
+		CatalogTupleUpdate(pg_conflict, &oldtup->t_self, newtup);
+	}
+	else
+		Assert(oldtup);			/* We must have a tuple for given
+								 * conflict_type */
+
+	systable_endscan(scan);
+
+	if (newtup != NULL)
+		heap_freetuple(newtup);
+
+	table_close(pg_conflict, RowExclusiveLock);
+}
diff --git a/src/backend/tcop/utility.c b/src/backend/tcop/utility.c
index fa66b8017e..4ddf4aaff0 100644
--- a/src/backend/tcop/utility.c
+++ b/src/backend/tcop/utility.c
@@ -59,6 +59,7 @@
 #include "miscadmin.h"
 #include "parser/parse_utilcmd.h"
 #include "postmaster/bgwriter.h"
+#include "replication/conflict.h"
 #include "rewrite/rewriteDefine.h"
 #include "storage/fd.h"
 #include "tcop/utility.h"
@@ -163,6 +164,7 @@ ClassifyUtilityCommandAsReadOnly(Node *parsetree)
 		case T_AlterUserMappingStmt:
 		case T_CommentStmt:
 		case T_CompositeTypeStmt:
+		case T_ConflictResolverStmt:
 		case T_CreateAmStmt:
 		case T_CreateCastStmt:
 		case T_CreateConversionStmt:
@@ -1062,6 +1064,11 @@ standard_ProcessUtility(PlannedStmt *pstmt,
 				break;
 			}
 
+		case T_ConflictResolverStmt:
+			/* no event triggers for conflict types and resolvers */
+			ExecConflictResolverStmt((ConflictResolverStmt *) parsetree);
+			break;
+
 		default:
 			/* All other statement types have event trigger support */
 			ProcessUtilitySlow(pstate, pstmt, queryString,
@@ -2659,6 +2666,10 @@ CreateCommandTag(Node *parsetree)
 			tag = CMDTAG_COMMENT;
 			break;
 
+		case T_ConflictResolverStmt:
+			tag = CMDTAG_CONFLICT_RESOLVER;
+			break;
+
 		case T_SecLabelStmt:
 			tag = CMDTAG_SECURITY_LABEL;
 			break;
@@ -3334,6 +3345,10 @@ GetCommandLogLevel(Node *parsetree)
 			lev = LOGSTMT_DDL;
 			break;
 
+		case T_ConflictResolverStmt:
+			lev = LOGSTMT_DDL;
+			break;
+
 		case T_SecLabelStmt:
 			lev = LOGSTMT_DDL;
 			break;
diff --git a/src/include/catalog/Makefile b/src/include/catalog/Makefile
index 167f91a6e3..8619d73e5a 100644
--- a/src/include/catalog/Makefile
+++ b/src/include/catalog/Makefile
@@ -81,7 +81,8 @@ CATALOG_HEADERS := \
 	pg_publication_namespace.h \
 	pg_publication_rel.h \
 	pg_subscription.h \
-	pg_subscription_rel.h
+	pg_subscription_rel.h \
+	pg_conflict.h
 
 GENERATED_HEADERS := $(CATALOG_HEADERS:%.h=%_d.h)
 
@@ -97,6 +98,7 @@ POSTGRES_BKI_DATA = \
 	pg_cast.dat \
 	pg_class.dat \
 	pg_collation.dat \
+	pg_conflict.dat \
 	pg_conversion.dat \
 	pg_database.dat \
 	pg_language.dat \
diff --git a/src/include/catalog/meson.build b/src/include/catalog/meson.build
index f70d1daba5..4d6732a303 100644
--- a/src/include/catalog/meson.build
+++ b/src/include/catalog/meson.build
@@ -69,6 +69,7 @@ catalog_headers = [
   'pg_publication_rel.h',
   'pg_subscription.h',
   'pg_subscription_rel.h',
+  'pg_conflict.h',
 ]
 
 # The .dat files we need can just be listed alphabetically.
@@ -81,6 +82,7 @@ bki_data = [
   'pg_cast.dat',
   'pg_class.dat',
   'pg_collation.dat',
+  'pg_conflict.dat',
   'pg_conversion.dat',
   'pg_database.dat',
   'pg_language.dat',
diff --git a/src/include/catalog/pg_conflict.dat b/src/include/catalog/pg_conflict.dat
new file mode 100644
index 0000000000..8d6183e3f2
--- /dev/null
+++ b/src/include/catalog/pg_conflict.dat
@@ -0,0 +1,21 @@
+#----------------------------------------------------------------------
+#
+# pg_conflict.dat
+#    Initial contents of the pg_conflict system catalog.
+#
+# Portions Copyright (c) 1996-2024, PostgreSQL Global Development Group
+# Portions Copyright (c) 1994, Regents of the University of California
+#
+# src/include/catalog/pg_conflict.dat
+#
+#----------------------------------------------------------------------
+
+[
+
+{ conftype => 'insert_exists', confres => 'remote_apply' },
+{ conftype => 'update_differ', confres => 'remote_apply' },
+{ conftype => 'update_missing', confres => 'apply_or_skip' },
+{ conftype => 'delete_missing', confres => 'skip' },
+{ conftype => 'delete_differ', confres => 'remote_apply' }
+
+]
diff --git a/src/include/catalog/pg_conflict.h b/src/include/catalog/pg_conflict.h
new file mode 100644
index 0000000000..e3fe3e6d30
--- /dev/null
+++ b/src/include/catalog/pg_conflict.h
@@ -0,0 +1,43 @@
+/* -------------------------------------------------------------------------
+ *
+ * pg_conflict.h
+ *	  definition of the "global conflict detection" system catalog
+ *	  (pg_conflict)
+ *
+ * Portions Copyright (c) 1996-2024, PostgreSQL Global Development Group
+ * Portions Copyright (c) 1994, Regents of the University of California
+ *
+ * src/include/catalog/pg_conflict.h
+ *
+ * NOTES
+ *	  The Catalog.pm module reads this file and derives schema
+ *	  information.
+ *
+ * -------------------------------------------------------------------------
+ */
+#ifndef PG_CONFLICT_H
+#define PG_CONFLICT_H
+
+#include "catalog/genbki.h"
+#include "catalog/pg_conflict_d.h"
+
+/* ----------------
+ *		pg_conflict definition.  cpp turns this into
+ *		typedef struct FormData_pg_conflict
+ * ----------------
+ */
+CATALOG(pg_conflict,8688,ConflictResRelationId)
+{
+#ifdef CATALOG_VARLEN			/* variable-length fields start here */
+	text		conftype BKI_FORCE_NOT_NULL;	/* conflict type */
+	text		confres BKI_FORCE_NOT_NULL; /* conflict resolver */
+#endif
+} FormData_pg_conflict;
+
+DECLARE_TOAST(pg_conflict, 8689, 8690);
+
+DECLARE_UNIQUE_INDEX_PKEY(pg_conflict_type_index, 8691, ConflictTypeIndexId, pg_conflict, btree(conftype text_ops));
+
+MAKE_SYSCACHE(CONFLICTTYPE, pg_conflict_type_index, 16);
+
+#endif							/* PG_CONFLICT_H */
diff --git a/src/include/nodes/parsenodes.h b/src/include/nodes/parsenodes.h
index 85a62b538e..1d41169d5e 100644
--- a/src/include/nodes/parsenodes.h
+++ b/src/include/nodes/parsenodes.h
@@ -3262,6 +3262,18 @@ typedef struct CommentStmt
 	char	   *comment;		/* Comment to insert, or NULL to remove */
 } CommentStmt;
 
+/* ----------------------
+ *				CONFLICT RESOLVER Statement
+ * ----------------------
+ */
+typedef struct ConflictResolverStmt
+{
+	NodeTag		type;
+	char	   *conflict_type;
+	char	   *conflict_resolver;
+	bool		isReset;
+} ConflictResolverStmt;
+
 /* ----------------------
  *				SECURITY LABEL Statement
  * ----------------------
diff --git a/src/include/parser/kwlist.h b/src/include/parser/kwlist.h
index f7fe834cf4..21e5cb162d 100644
--- a/src/include/parser/kwlist.h
+++ b/src/include/parser/kwlist.h
@@ -377,6 +377,7 @@ PG_KEYWORD("repeatable", REPEATABLE, UNRESERVED_KEYWORD, BARE_LABEL)
 PG_KEYWORD("replace", REPLACE, UNRESERVED_KEYWORD, BARE_LABEL)
 PG_KEYWORD("replica", REPLICA, UNRESERVED_KEYWORD, BARE_LABEL)
 PG_KEYWORD("reset", RESET, UNRESERVED_KEYWORD, BARE_LABEL)
+PG_KEYWORD("resolver", RESOLVER, UNRESERVED_KEYWORD, BARE_LABEL)
 PG_KEYWORD("restart", RESTART, UNRESERVED_KEYWORD, BARE_LABEL)
 PG_KEYWORD("restrict", RESTRICT, UNRESERVED_KEYWORD, BARE_LABEL)
 PG_KEYWORD("return", RETURN, UNRESERVED_KEYWORD, BARE_LABEL)
diff --git a/src/include/replication/conflict.h b/src/include/replication/conflict.h
index a9f521aaca..c6023e0914 100644
--- a/src/include/replication/conflict.h
+++ b/src/include/replication/conflict.h
@@ -10,6 +10,7 @@
 #define CONFLICT_H
 
 #include "access/xlogdefs.h"
+#include "catalog/objectaddress.h"
 #include "executor/tuptable.h"
 #include "nodes/execnodes.h"
 #include "utils/relcache.h"
@@ -36,6 +37,41 @@ typedef enum
 	CT_DELETE_DIFFER,
 } ConflictType;
 
+/* Min and max conflict type */
+#define CT_MIN CT_INSERT_EXISTS
+#define CT_MAX CT_DELETE_DIFFER
+
+/*
+ * Conflict resolvers that can be used to resolve various conflicts.
+ *
+ * See ConflictTypeResolverMap in conflcit.c to find out which all
+ * resolvers are supported for each conflict type.
+ */
+typedef enum ConflictResolver
+{
+	/* Apply the remote change */
+	CR_REMOTE_APPLY = 1,
+
+	/* Keep the local change */
+	CR_KEEP_LOCAL,
+
+	/* Apply the remote change; skip if it can not be applied */
+	CR_APPLY_OR_SKIP,
+
+	/* Apply the remote change; emit error if it can not be applied */
+	CR_APPLY_OR_ERROR,
+
+	/* Skip applying the change */
+	CR_SKIP,
+
+	/* Error out */
+	CR_ERROR,
+} ConflictResolver;
+
+/* Min and max conflict resolver */
+#define CR_MIN CR_REMOTE_APPLY
+#define CR_MAX CR_ERROR
+
 extern bool GetTupleCommitTs(TupleTableSlot *localslot, TransactionId *xmin,
 							 RepOriginId *localorigin, TimestampTz *localts);
 extern void ReportApplyConflict(int elevel, ConflictType type,
@@ -43,5 +79,5 @@ extern void ReportApplyConflict(int elevel, ConflictType type,
 								TransactionId localxmin, RepOriginId localorigin,
 								TimestampTz localts, TupleTableSlot *conflictslot);
 extern void InitConflictIndexes(ResultRelInfo *relInfo);
-
+extern void ExecConflictResolverStmt(ConflictResolverStmt *stmt);
 #endif
diff --git a/src/include/tcop/cmdtaglist.h b/src/include/tcop/cmdtaglist.h
index 7fdcec6dd9..562478e232 100644
--- a/src/include/tcop/cmdtaglist.h
+++ b/src/include/tcop/cmdtaglist.h
@@ -80,6 +80,7 @@ PG_CMDTAG(CMDTAG_CLUSTER, "CLUSTER", false, false, false)
 PG_CMDTAG(CMDTAG_COMMENT, "COMMENT", true, false, false)
 PG_CMDTAG(CMDTAG_COMMIT, "COMMIT", false, false, false)
 PG_CMDTAG(CMDTAG_COMMIT_PREPARED, "COMMIT PREPARED", false, false, false)
+PG_CMDTAG(CMDTAG_CONFLICT_RESOLVER, "CONFLICT RESOLVER", false, false, false)
 PG_CMDTAG(CMDTAG_COPY, "COPY", false, false, true)
 PG_CMDTAG(CMDTAG_COPY_FROM, "COPY FROM", false, false, false)
 PG_CMDTAG(CMDTAG_CREATE_ACCESS_METHOD, "CREATE ACCESS METHOD", true, false, false)
diff --git a/src/test/regress/expected/conflict_resolver.out b/src/test/regress/expected/conflict_resolver.out
new file mode 100644
index 0000000000..53ecb430fa
--- /dev/null
+++ b/src/test/regress/expected/conflict_resolver.out
@@ -0,0 +1,54 @@
+--check default global resolvers in system catalog
+select * from pg_conflict order by conftype;
+    conftype    |    confres    
+----------------+---------------
+ delete_differ  | remote_apply
+ delete_missing | skip
+ insert_exists  | remote_apply
+ update_differ  | remote_apply
+ update_missing | apply_or_skip
+(5 rows)
+
+--
+-- Test of SET/RESET CONFLICT RESOLVER with invalid names
+--
+SET CONFLICT RESOLVER 'keep_local' for 'aaaa'; -- fail
+ERROR:  aaaa is not a valid conflict type
+SET CONFLICT RESOLVER 'bbbbb' for 'delete_missing'; -- fail
+ERROR:  bbbbb is not a valid conflict resolver
+SET CONFLICT RESOLVER 'remote_apply' for 'delete_missing'; -- fail
+ERROR:  remote_apply is not a valid conflict resolver for conflict type delete_missing
+RESET CONFLICT RESOLVER for 'ct'; -- fail
+ERROR:  ct is not a valid conflict type
+--
+-- Test of SET/RESET CONFLICT RESOLVER with valid names
+--
+SET CONFLICT RESOLVER 'error' for 'delete_missing';
+SET CONFLICT RESOLVER 'keep_local' for 'insert_exists';
+SET CONFLICT RESOLVER 'keep_local' for 'update_differ';
+SET CONFLICT RESOLVER 'apply_or_error' for 'update_missing';
+SET CONFLICT RESOLVER 'keep_local' for 'delete_differ';
+--check new resolvers are saved
+select * from pg_conflict order by conftype;
+    conftype    |    confres     
+----------------+----------------
+ delete_differ  | keep_local
+ delete_missing | error
+ insert_exists  | keep_local
+ update_differ  | keep_local
+ update_missing | apply_or_error
+(5 rows)
+
+RESET CONFLICT RESOLVER for 'delete_missing';
+RESET CONFLICT RESOLVER for 'insert_exists';
+--check resolvers are reset to default for delete_missing and insert_exists
+select * from pg_conflict order by conftype;
+    conftype    |    confres     
+----------------+----------------
+ delete_differ  | keep_local
+ delete_missing | skip
+ insert_exists  | remote_apply
+ update_differ  | keep_local
+ update_missing | apply_or_error
+(5 rows)
+
diff --git a/src/test/regress/parallel_schedule b/src/test/regress/parallel_schedule
index 2429ec2bba..76ea2d359b 100644
--- a/src/test/regress/parallel_schedule
+++ b/src/test/regress/parallel_schedule
@@ -48,7 +48,7 @@ test: create_index create_index_spgist create_view index_including index_includi
 # ----------
 # Another group of parallel tests
 # ----------
-test: create_aggregate create_function_sql create_cast constraints triggers select inherit typed_table vacuum drop_if_exists updatable_views roleattributes create_am hash_func errors infinite_recurse
+test: create_aggregate create_function_sql create_cast conflict_resolver constraints triggers select inherit typed_table vacuum drop_if_exists updatable_views roleattributes create_am hash_func errors infinite_recurse
 
 # ----------
 # sanity_check does a vacuum, affecting the sort order of SELECT *
diff --git a/src/test/regress/sql/conflict_resolver.sql b/src/test/regress/sql/conflict_resolver.sql
new file mode 100644
index 0000000000..f83d14b229
--- /dev/null
+++ b/src/test/regress/sql/conflict_resolver.sql
@@ -0,0 +1,28 @@
+--check default global resolvers in system catalog
+select * from pg_conflict order by conftype;
+
+--
+-- Test of SET/RESET CONFLICT RESOLVER with invalid names
+--
+SET CONFLICT RESOLVER 'keep_local' for 'aaaa'; -- fail
+SET CONFLICT RESOLVER 'bbbbb' for 'delete_missing'; -- fail
+SET CONFLICT RESOLVER 'remote_apply' for 'delete_missing'; -- fail
+RESET CONFLICT RESOLVER for 'ct'; -- fail
+
+--
+-- Test of SET/RESET CONFLICT RESOLVER with valid names
+--
+SET CONFLICT RESOLVER 'error' for 'delete_missing';
+SET CONFLICT RESOLVER 'keep_local' for 'insert_exists';
+SET CONFLICT RESOLVER 'keep_local' for 'update_differ';
+SET CONFLICT RESOLVER 'apply_or_error' for 'update_missing';
+SET CONFLICT RESOLVER 'keep_local' for 'delete_differ';
+
+--check new resolvers are saved
+select * from pg_conflict order by conftype;
+
+RESET CONFLICT RESOLVER for 'delete_missing';
+RESET CONFLICT RESOLVER for 'insert_exists';
+
+--check resolvers are reset to default for delete_missing and insert_exists
+select * from pg_conflict order by conftype;
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index 2485a80833..784194903a 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -466,6 +466,8 @@ ConditionVariableMinimallyPadded
 ConditionalStack
 ConfigData
 ConfigVariable
+ConflictResolver
+ConflictResolverStmt
 ConflictType
 ConnCacheEntry
 ConnCacheKey
-- 
2.34.1



  [application/octet-stream] v4-0003-Implement-conflict-resolution-for-INSERT-UPDATE-a.patch (36.3K, ../../CABdArM47myyKnOU4LB54k3wmgpFu63s2gxmAQVK-DdWzCLKAaw@mail.gmail.com/4-v4-0003-Implement-conflict-resolution-for-INSERT-UPDATE-a.patch)
  download | inline diff:
From 816d6bf0e2dee0394190511ad9c091e39c97302e Mon Sep 17 00:00:00 2001
From: Nisha Moond <[email protected]>
Date: Wed, 3 Jul 2024 15:46:58 +0530
Subject: [PATCH v4 3/5] Implement conflict resolution for INSERT, UPDATE, and
 DELETE operations.

This patch introduces support for handling conflicts with the following resolutions:
- For INSERT conflicts:
  - insert_exists: remote_apply, keep_local, error
- For UPDATE conflicts:
  - update_differ: remote_apply, keep_local, error
  - update_missing: apply_or_skip, apply_or_error, skip, error
- For DELETE conflicts:
  - delete_missing: skip, error
  - delete_differ: remote_apply, keep_local, error

Each of the conflict type now has defined actions to manage data synchronization
between Publisher and subscriber databases.
---
 src/backend/executor/execReplication.c     |  80 ++++-
 src/backend/replication/logical/conflict.c | 195 +++++++++--
 src/backend/replication/logical/worker.c   | 361 ++++++++++++++++-----
 src/include/executor/executor.h            |   5 +-
 src/include/replication/conflict.h         |  19 +-
 src/test/subscription/t/029_on_error.pl    |   7 +
 6 files changed, 541 insertions(+), 126 deletions(-)

diff --git a/src/backend/executor/execReplication.c b/src/backend/executor/execReplication.c
index f01927a933..3e8d768214 100644
--- a/src/backend/executor/execReplication.c
+++ b/src/backend/executor/execReplication.c
@@ -566,7 +566,8 @@ retry:
  */
 void
 ExecSimpleRelationInsert(ResultRelInfo *resultRelInfo,
-						 EState *estate, TupleTableSlot *slot)
+						 EState *estate, TupleTableSlot *slot,
+						 TupleTableSlot **conflictslot)
 {
 	bool		skip_tuple = false;
 	Relation	rel = resultRelInfo->ri_RelationDesc;
@@ -602,21 +603,82 @@ ExecSimpleRelationInsert(ResultRelInfo *resultRelInfo,
 		if (rel->rd_rel->relispartition)
 			ExecPartitionCheck(resultRelInfo, slot, estate, true);
 
+		conflictindexes = resultRelInfo->ri_onConflictArbiterIndexes;
+
+		/*
+		 * If caller has passed non null conflictslot, check all the unique
+		 * indexes for potential conflicts. If the configured resolver is in
+		 * favour of apply, give the conflicted tuple information in
+		 * conflictslot.
+		 */
+		if (conflictslot)
+		{
+			foreach_oid(uniqueidx, conflictindexes)
+			{
+				/*
+				 * Return if any conflict is found other than one with 'ERROR'
+				 * resolver configured. In case of 'ERROR' resolver, emit
+				 * error here; otherwise return to caller for resolutions.
+				 */
+				if (FindConflictTuple(resultRelInfo, estate, uniqueidx,
+									  slot, &(*conflictslot)))
+				{
+					RepOriginId origin;
+					TimestampTz committs;
+					TransactionId xmin;
+					ConflictResolver resolver;
+					bool		apply_remote = false;
+
+					GetTupleCommitTs(*conflictslot, &xmin, &origin, &committs);
+					resolver = GetConflictResolver(*conflictslot, rel,
+												   CT_INSERT_EXISTS,
+												   &apply_remote, NULL, uniqueidx,
+												   xmin, origin, committs);
+
+					ReportApplyConflict(LOG, CT_INSERT_EXISTS, resolver, rel,
+										uniqueidx, xmin, origin, committs,
+										*conflictslot);
+
+					/* Nothing to apply, free the resources */
+					if (!apply_remote)
+					{
+						ExecDropSingleTupleTableSlot(*conflictslot);
+						*conflictslot = NULL;
+					}
+
+					return;
+				}
+			}
+		}
+
+
 		/* OK, store the tuple and create index entries for it */
 		simple_table_tuple_insert(resultRelInfo->ri_RelationDesc, slot);
 
-		conflictindexes = resultRelInfo->ri_onConflictArbiterIndexes;
-
 		if (resultRelInfo->ri_NumIndices > 0)
 			recheckIndexes = ExecInsertIndexTuples(resultRelInfo,
 												   slot, estate, false,
 												   conflictindexes, &conflict,
 												   conflictindexes, false);
 
-		/* Re-check all the unique indexes for potential conflicts */
+		/*
+		 * Re-check all the unique indexes for potential conflicts.
+		 *
+		 * The Reason for doing the check again is:
+		 *
+		 * 1. If the remote change violated multiple unique constraints, the
+		 * current resolution cannot solve it, so we still need to report this
+		 * conflict after resolution.
+		 *
+		 * 2. If the local data is changed immediately after converting the
+		 * insert to update but before updating the data, then the conflict
+		 * can still happen, and we may need to report it again.
+		 *
+		 * XXX: Needs further review and discussion on usefulness of this
+		 * repeated call.
+		 */
 		foreach_oid(uniqueidx, (conflict ? conflictindexes : NIL))
 		{
-			TupleTableSlot *conflictslot;
 
 			/*
 			 * Reports the conflict if any.
@@ -631,15 +693,15 @@ ExecSimpleRelationInsert(ResultRelInfo *resultRelInfo,
 			 * cost of finding the tuple should be acceptable in this case.
 			 */
 			if (list_member_oid(recheckIndexes, uniqueidx) &&
-				FindConflictTuple(resultRelInfo, estate, uniqueidx, slot, &conflictslot))
+				FindConflictTuple(resultRelInfo, estate, uniqueidx, slot, &(*conflictslot)))
 			{
 				RepOriginId origin;
 				TimestampTz committs;
 				TransactionId xmin;
 
-				GetTupleCommitTs(conflictslot, &xmin, &origin, &committs);
-				ReportApplyConflict(ERROR, CT_INSERT_EXISTS, rel, uniqueidx,
-									xmin, origin, committs, conflictslot);
+				GetTupleCommitTs(*conflictslot, &xmin, &origin, &committs);
+				ReportApplyConflict(ERROR, CT_INSERT_EXISTS, 0, rel, uniqueidx,
+									xmin, origin, committs, *conflictslot);
 			}
 		}
 
diff --git a/src/backend/replication/logical/conflict.c b/src/backend/replication/logical/conflict.c
index 93d9659752..d215d48dc6 100644
--- a/src/backend/replication/logical/conflict.c
+++ b/src/backend/replication/logical/conflict.c
@@ -21,13 +21,17 @@
 #include "access/table.h"
 #include "catalog/indexing.h"
 #include "catalog/pg_conflict.h"
+#include "executor/executor.h"
 #include "replication/conflict.h"
+#include "replication/logicalproto.h"
+#include "replication/logicalrelation.h"
 #include "replication/origin.h"
 #include "utils/builtins.h"
 #include "utils/fmgroids.h"
 #include "utils/lsyscache.h"
 #include "utils/rel.h"
 #include "utils/timestamp.h"
+#include "utils/syscache.h"
 
 const char *const ConflictTypeNames[] = {
 	[CT_INSERT_EXISTS] = "insert_exists",
@@ -86,8 +90,9 @@ const int	ConflictTypeDefaultResolvers[] = {
 };
 
 static char *build_index_value_desc(Oid indexoid, TupleTableSlot *conflictslot);
-static int	errdetail_apply_conflict(ConflictType type, Oid conflictidx,
-									 TransactionId localxmin,
+static int	errdetail_apply_conflict(ConflictType type,
+									 ConflictResolver resolver,
+									 Oid conflictidx, TransactionId localxmin,
 									 RepOriginId localorigin,
 									 TimestampTz localts,
 									 TupleTableSlot *conflictslot);
@@ -126,13 +131,13 @@ GetTupleCommitTs(TupleTableSlot *localslot, TransactionId *xmin,
 }
 
 /*
- * Report a conflict when applying remote changes.
+ * Report conflict and resolution applied while applying remote changes.
  */
 void
-ReportApplyConflict(int elevel, ConflictType type, Relation localrel,
-					Oid conflictidx, TransactionId localxmin,
-					RepOriginId localorigin, TimestampTz localts,
-					TupleTableSlot *conflictslot)
+ReportApplyConflict(int elevel, ConflictType type, ConflictResolver resolver,
+					Relation localrel, Oid conflictidx,
+					TransactionId localxmin, RepOriginId localorigin,
+					TimestampTz localts, TupleTableSlot *conflictslot)
 {
 	ereport(elevel,
 			errcode(ERRCODE_INTEGRITY_CONSTRAINT_VIOLATION),
@@ -140,7 +145,7 @@ ReportApplyConflict(int elevel, ConflictType type, Relation localrel,
 				   ConflictTypeNames[type],
 				   get_namespace_name(RelationGetNamespace(localrel)),
 				   RelationGetRelationName(localrel)),
-			errdetail_apply_conflict(type, conflictidx, localxmin, localorigin,
+			errdetail_apply_conflict(type, resolver, conflictidx, localxmin, localorigin,
 									 localts, conflictslot));
 }
 
@@ -176,12 +181,13 @@ InitConflictIndexes(ResultRelInfo *relInfo)
 }
 
 /*
- * Add an errdetail() line showing conflict detail.
+ * Add an errdetail() line showing conflict and resolution details.
  */
 static int
-errdetail_apply_conflict(ConflictType type, Oid conflictidx,
-						 TransactionId localxmin, RepOriginId localorigin,
-						 TimestampTz localts, TupleTableSlot *conflictslot)
+errdetail_apply_conflict(ConflictType type, ConflictResolver resolver,
+						 Oid conflictidx, TransactionId localxmin,
+						 RepOriginId localorigin, TimestampTz localts,
+						 TupleTableSlot *conflictslot)
 {
 	switch (type)
 	{
@@ -195,27 +201,35 @@ errdetail_apply_conflict(ConflictType type, Oid conflictidx,
 				char	   *index_value = build_index_value_desc(conflictidx,
 																 conflictslot);
 
-				if (index_value && localts)
-					return errdetail("Key %s already exists in unique index \"%s\", which was modified by origin %u in transaction %u at %s.",
-									 index_value, get_rel_name(conflictidx), localorigin,
-									 localxmin, timestamptz_to_str(localts));
-				else if (index_value && !localts)
-					return errdetail("Key %s already exists in unique index \"%s\", which was modified in transaction %u.",
-									 index_value, get_rel_name(conflictidx), localxmin);
+				if (!resolver || (resolver == CR_ERROR))
+				{
+					if (index_value && localts)
+						return errdetail("Key %s already exists in unique index \"%s\", which was modified by origin %u in transaction %u at %s.",
+										 index_value, get_rel_name(conflictidx), localorigin,
+										 localxmin, timestamptz_to_str(localts));
+					else if (index_value && !localts)
+						return errdetail("Key %s already exists in unique index \"%s\", which was modified in transaction %u.",
+										 index_value, get_rel_name(conflictidx), localxmin);
+					else
+						return errdetail("Key already exists in unique index \"%s\".",
+										 get_rel_name(conflictidx));
+				}
 				else
-					return errdetail("Key already exists in unique index \"%s\".",
-									 get_rel_name(conflictidx));
+					return errdetail("Key already exists. Applying resolution method \"%s\"", ConflictResolverNames[resolver]);
 			}
 		case CT_UPDATE_DIFFER:
-			return errdetail("Updating a row that was modified by a different origin %u in transaction %u at %s.",
-							 localorigin, localxmin, timestamptz_to_str(localts));
+			return errdetail("Updating a row that was modified by a different origin %u in transaction %u at %s. Applying resolution method \"%s\"",
+							 localorigin, localxmin, timestamptz_to_str(localts), ConflictResolverNames[resolver]);
 		case CT_UPDATE_MISSING:
-			return errdetail("Did not find the row to be updated.");
+			return errdetail("Did not find the row to be updated. Applying resolution method \"%s\"",
+							 ConflictResolverNames[resolver]);
 		case CT_DELETE_MISSING:
-			return errdetail("Did not find the row to be deleted.");
+			return errdetail("Did not find the row to be deleted. Applying resolution method \"%s\"",
+							 ConflictResolverNames[resolver]);
 		case CT_DELETE_DIFFER:
-			return errdetail("Deleting a row that was modified by a different origin %u in transaction %u at %s.",
-							 localorigin, localxmin, timestamptz_to_str(localts));
+			return errdetail("Deleting a row that was modified by a different origin %u in transaction %u at %s. Applying resolution method \"%s\"",
+							 localorigin, localxmin, timestamptz_to_str(localts),
+							 ConflictResolverNames[resolver]);
 	}
 
 	return 0;					/* silence compiler warning */
@@ -329,6 +343,71 @@ validate_conflict_type_and_resolver(char *conflict_type, char *conflict_resolver
 	return type;
 }
 
+/*
+ * Get the global conflict resolver configured for given conflict type
+ */
+static ConflictResolver
+get_conflict_resolver_internal(ConflictType type)
+{
+
+	ConflictResolver resolver;
+	HeapTuple	tuple;
+	Datum		datum;
+	char	   *conflict_res;
+
+	/*
+	 * XXX: Currently, we fetch the conflict resolver from cache for each
+	 * conflict detection. If needed, we can keep the info in global variable
+	 * and fetch from cache only once after cache invalidation.
+	 */
+	tuple = SearchSysCache1(CONFLICTTYPE,
+							CStringGetTextDatum(ConflictTypeNames[type]));
+
+	if (!HeapTupleIsValid(tuple))
+		elog(ERROR, "cache lookup failed for conflict type %u", type);
+
+	datum = SysCacheGetAttrNotNull(CONFLICTTYPE,
+								   tuple, Anum_pg_conflict_confres);
+
+	conflict_res = TextDatumGetCString(datum);
+
+	for (resolver = CR_MIN; resolver <= CR_MAX; resolver++)
+	{
+		if (strcmp(ConflictResolverNames[resolver], conflict_res) == 0)
+			break;
+	}
+
+	ReleaseSysCache(tuple);
+	return resolver;
+}
+
+/*
+ * Check if a full tuple can be created from the new tuple.
+ * Return true if yes, false otherwise.
+ *
+ * XXX: Currently, it only handles the simple case of identical table
+ * structures on both Publisher and subscriber. Need to analyze if more
+ * cases can be supported.
+ */
+static bool
+can_create_full_tuple(Relation localrel,
+					  LogicalRepTupleData *newtup)
+{
+	int			i;
+	int			local_att = RelationGetNumberOfAttributes(localrel);
+
+	if (newtup->ncols != local_att)
+		return false;
+
+	for (i = 0; i < newtup->ncols; i++)
+	{
+		if (newtup->colstatus[i] == LOGICALREP_COLUMN_UNCHANGED)
+			return false;
+	}
+
+	return true;
+}
+
 /*
  * Execute Conflict Resolver Stmt
  *
@@ -403,3 +482,65 @@ ExecConflictResolverStmt(ConflictResolverStmt *stmt)
 
 	table_close(pg_conflict, RowExclusiveLock);
 }
+
+/*
+ * Find the global resolver for the given conflict type.
+ * It emits error in case the resolver is set to 'ERROR'.
+ *
+ * Set 'apply_remote' to true if remote tuple should be applied,
+ * false otherwise.
+ */
+ConflictResolver
+GetConflictResolver(TupleTableSlot *localslot, Relation localrel,
+					ConflictType type, bool *apply_remote,
+					LogicalRepTupleData *newtup,
+					Oid conflictidx, TransactionId xmin,
+					RepOriginId origin, TimestampTz committs)
+{
+	ConflictResolver resolver;
+
+	resolver = get_conflict_resolver_internal(type);
+
+	switch (resolver)
+	{
+		case CR_REMOTE_APPLY:
+			*apply_remote = true;
+			break;
+		case CR_APPLY_OR_SKIP:
+			if (can_create_full_tuple(localrel, newtup))
+			{
+				*apply_remote = true;
+				break;
+			}
+			else
+			{
+				*apply_remote = false;
+				elog(LOG, "UPDATE can not be converted to INSERT, hence SKIP the update!");
+				break;
+			}
+		case CR_APPLY_OR_ERROR:
+			if (can_create_full_tuple(localrel, newtup))
+			{
+				*apply_remote = true;
+				break;
+			}
+			else
+			{
+				ReportApplyConflict(ERROR, type, resolver, localrel, conflictidx,
+									xmin, origin, committs, localslot);
+				break;
+			}
+		case CR_KEEP_LOCAL:
+		case CR_SKIP:
+			*apply_remote = false;
+			break;
+		case CR_ERROR:
+			ReportApplyConflict(ERROR, type, resolver, localrel, conflictidx,
+								xmin, origin, committs, localslot);
+			break;
+		default:
+			elog(ERROR, "Conflict %s is detected! Unrecogonized conflict resolution method", ConflictTypeNames[type]);
+	}
+
+	return resolver;
+}
diff --git a/src/backend/replication/logical/worker.c b/src/backend/replication/logical/worker.c
index b4c834ed3f..239d5c7cd1 100644
--- a/src/backend/replication/logical/worker.c
+++ b/src/backend/replication/logical/worker.c
@@ -382,7 +382,9 @@ static void send_feedback(XLogRecPtr recvpos, bool force, bool requestReply);
 static void apply_handle_commit_internal(LogicalRepCommitData *commit_data);
 static void apply_handle_insert_internal(ApplyExecutionData *edata,
 										 ResultRelInfo *relinfo,
-										 TupleTableSlot *remoteslot);
+										 TupleTableSlot *remoteslot,
+										 LogicalRepTupleData *newtup,
+										 LogicalRepRelMapEntry *rel_entry);
 static void apply_handle_update_internal(ApplyExecutionData *edata,
 										 ResultRelInfo *relinfo,
 										 TupleTableSlot *remoteslot,
@@ -2431,10 +2433,10 @@ apply_handle_insert(StringInfo s)
 	/* For a partitioned table, insert the tuple into a partition. */
 	if (rel->localrel->rd_rel->relkind == RELKIND_PARTITIONED_TABLE)
 		apply_handle_tuple_routing(edata,
-								   remoteslot, NULL, CMD_INSERT);
+								   remoteslot, &newtup, CMD_INSERT);
 	else
 		apply_handle_insert_internal(edata, edata->targetRelInfo,
-									 remoteslot);
+									 remoteslot, &newtup, rel);
 
 	finish_edata(edata);
 
@@ -2457,9 +2459,13 @@ apply_handle_insert(StringInfo s)
 static void
 apply_handle_insert_internal(ApplyExecutionData *edata,
 							 ResultRelInfo *relinfo,
-							 TupleTableSlot *remoteslot)
+							 TupleTableSlot *remoteslot,
+							 LogicalRepTupleData *newtup,
+							 LogicalRepRelMapEntry *rel_entry)
 {
 	EState	   *estate = edata->estate;
+	MemoryContext oldctx;
+	TupleTableSlot *conflictslot = NULL;
 
 	/* We must open indexes here. */
 	ExecOpenIndices(relinfo, MySubscription->detectconflict);
@@ -2469,7 +2475,35 @@ apply_handle_insert_internal(ApplyExecutionData *edata,
 
 	/* Do the insert. */
 	TargetPrivilegesCheck(relinfo->ri_RelationDesc, ACL_INSERT);
-	ExecSimpleRelationInsert(relinfo, estate, remoteslot);
+
+	if (MySubscription->detectconflict)
+		ExecSimpleRelationInsert(relinfo, estate, remoteslot, &conflictslot);
+	else
+		ExecSimpleRelationInsert(relinfo, estate, remoteslot, NULL);
+
+
+	/* Apply remote tuple by converting INSERT to UPDATE */
+	if (conflictslot)
+	{
+		EPQState	epqstate;
+
+		EvalPlanQualInit(&epqstate, estate, NULL, NIL, -1, NIL);
+
+		/* Process and store remote tuple in the slot */
+		oldctx = MemoryContextSwitchTo(GetPerTupleMemoryContext(estate));
+		slot_modify_data(remoteslot, conflictslot, rel_entry, newtup);
+		MemoryContextSwitchTo(oldctx);
+
+		EvalPlanQualSetSlot(&epqstate, remoteslot);
+
+		/* Do the update */
+		TargetPrivilegesCheck(relinfo->ri_RelationDesc, ACL_UPDATE);
+		ExecSimpleRelationUpdate(relinfo, estate, &epqstate, conflictslot,
+								 remoteslot);
+
+		EvalPlanQualEnd(&epqstate);
+		ExecDropSingleTupleTableSlot(conflictslot);
+	}
 
 	/* Cleanup. */
 	ExecCloseIndices(relinfo);
@@ -2651,6 +2685,8 @@ apply_handle_update_internal(ApplyExecutionData *edata,
 	TupleTableSlot *localslot;
 	bool		found;
 	MemoryContext oldctx;
+	bool		apply_remote = true;
+	ConflictResolver resolver;
 
 	EvalPlanQualInit(&epqstate, estate, NULL, NIL, -1, NIL);
 	ExecOpenIndices(relinfo, false);
@@ -2674,35 +2710,73 @@ apply_handle_update_internal(ApplyExecutionData *edata,
 
 		/*
 		 * If conflict detection is enabled, check whether the local tuple was
-		 * modified by a different origin. If detected, report the conflict.
+		 * modified by a different origin. If detected, report the conflict
+		 * and configured resolver.
 		 */
 		if (MySubscription->detectconflict &&
 			GetTupleCommitTs(localslot, &localxmin, &localorigin, &localts) &&
 			localorigin != replorigin_session_origin)
-			ReportApplyConflict(LOG, CT_UPDATE_DIFFER, localrel, InvalidOid,
-								localxmin, localorigin, localts, NULL);
+		{
+			resolver = GetConflictResolver(localslot, localrel, CT_UPDATE_DIFFER,
+										   &apply_remote, NULL, InvalidOid,
+										   localxmin, localorigin, localts);
 
-		/* Process and store remote tuple in the slot */
-		oldctx = MemoryContextSwitchTo(GetPerTupleMemoryContext(estate));
-		slot_modify_data(remoteslot, localslot, relmapentry, newtup);
-		MemoryContextSwitchTo(oldctx);
+			ReportApplyConflict(LOG, CT_UPDATE_DIFFER, resolver, localrel,
+								InvalidOid, localxmin, localorigin, localts,
+								NULL);
+		}
 
-		EvalPlanQualSetSlot(&epqstate, remoteslot);
+		/*
+		 * Apply the change if configured resolver is in favor of that, else
+		 * ignore the remote update.
+		 */
+		if (apply_remote)
+		{
+			/* Process and store remote tuple in the slot */
+			oldctx = MemoryContextSwitchTo(GetPerTupleMemoryContext(estate));
+			slot_modify_data(remoteslot, localslot, relmapentry, newtup);
+			MemoryContextSwitchTo(oldctx);
 
-		/* Do the actual update. */
-		TargetPrivilegesCheck(relinfo->ri_RelationDesc, ACL_UPDATE);
-		ExecSimpleRelationUpdate(relinfo, estate, &epqstate, localslot,
-								 remoteslot);
+			EvalPlanQualSetSlot(&epqstate, remoteslot);
+
+			/* Do the actual update. */
+			TargetPrivilegesCheck(relinfo->ri_RelationDesc, ACL_UPDATE);
+			ExecSimpleRelationUpdate(relinfo, estate, &epqstate, localslot,
+									 remoteslot);
+		}
 	}
 	else
 	{
 		/*
-		 * The tuple to be updated could not be found.  Do nothing except for
-		 * emitting a log message.
+		 * The tuple to be updated could not be found. Report the conflict. If
+		 * the configured resolver is in favor of applying the change, convert
+		 * UPDATE to INSERT and apply the change.
 		 */
 		if (MySubscription->detectconflict)
-			ReportApplyConflict(LOG, CT_UPDATE_MISSING, localrel, InvalidOid,
-								InvalidTransactionId, InvalidRepOriginId, 0, NULL);
+		{
+			resolver = GetConflictResolver(localslot, localrel, CT_UPDATE_MISSING,
+										   &apply_remote, newtup, InvalidOid,
+										   InvalidTransactionId,
+										   InvalidRepOriginId, 0);
+
+			ReportApplyConflict(LOG, CT_UPDATE_MISSING, resolver, localrel,
+								InvalidOid, InvalidTransactionId,
+								InvalidRepOriginId, 0, NULL);
+
+			/* Process and store remote tuple in the slot */
+			oldctx = MemoryContextSwitchTo(GetPerTupleMemoryContext(estate));
+			slot_store_data(remoteslot, relmapentry, newtup);
+			slot_fill_defaults(relmapentry, estate, remoteslot);
+			MemoryContextSwitchTo(oldctx);
+
+			if (apply_remote)
+			{
+				elog(LOG, "Converting UPDATE to INSERT and applying!");
+				apply_handle_insert_internal(edata, relinfo, remoteslot,
+											 newtup, relmapentry);
+			}
+
+		}
 	}
 
 	/* Cleanup. */
@@ -2815,6 +2889,8 @@ apply_handle_delete_internal(ApplyExecutionData *edata,
 	EPQState	epqstate;
 	TupleTableSlot *localslot;
 	bool		found;
+	bool		apply_remote = true;
+	ConflictResolver resolver;
 
 	EvalPlanQualInit(&epqstate, estate, NULL, NIL, -1, NIL);
 	ExecOpenIndices(relinfo, false);
@@ -2836,24 +2912,45 @@ apply_handle_delete_internal(ApplyExecutionData *edata,
 		if (MySubscription->detectconflict &&
 			GetTupleCommitTs(localslot, &localxmin, &localorigin, &localts) &&
 			localorigin != replorigin_session_origin)
-			ReportApplyConflict(LOG, CT_DELETE_DIFFER, localrel, InvalidOid,
+		{
+			resolver = GetConflictResolver(localslot, localrel, CT_DELETE_DIFFER,
+										   &apply_remote, NULL, InvalidOid,
+										   InvalidTransactionId,
+										   InvalidRepOriginId, 0);
+
+			ReportApplyConflict(LOG, CT_DELETE_DIFFER, resolver, localrel, InvalidOid,
 								localxmin, localorigin, localts, NULL);
+		}
 
-		EvalPlanQualSetSlot(&epqstate, localslot);
+		if (apply_remote)
+		{
+			EvalPlanQualSetSlot(&epqstate, localslot);
+
+			/* Do the actual delete. */
+			TargetPrivilegesCheck(relinfo->ri_RelationDesc, ACL_DELETE);
+			ExecSimpleRelationDelete(relinfo, estate, &epqstate, localslot);
+		}
 
-		/* Do the actual delete. */
-		TargetPrivilegesCheck(relinfo->ri_RelationDesc, ACL_DELETE);
-		ExecSimpleRelationDelete(relinfo, estate, &epqstate, localslot);
 	}
 	else
 	{
 		/*
-		 * The tuple to be deleted could not be found.  Do nothing except for
-		 * emitting a log message.
+		 * The tuple to be deleted could not be found. Based on resolver
+		 * configured, either skip and log a message or emit an error.
 		 */
 		if (MySubscription->detectconflict)
-			ReportApplyConflict(LOG, CT_DELETE_MISSING, localrel, InvalidOid,
-								InvalidTransactionId, InvalidRepOriginId, 0, NULL);
+		{
+			resolver = GetConflictResolver(localslot, localrel, CT_DELETE_MISSING,
+										   &apply_remote, NULL, InvalidOid,
+										   InvalidTransactionId,
+										   InvalidRepOriginId, 0);
+
+			/* Resolver is set to skip, thus report the conflict and skip */
+			if (!apply_remote)
+				ReportApplyConflict(LOG, CT_DELETE_MISSING, resolver, localrel,
+									InvalidOid, InvalidTransactionId,
+									InvalidRepOriginId, 0, NULL);
+		}
 	}
 
 	/* Cleanup. */
@@ -2986,19 +3083,21 @@ apply_handle_tuple_routing(ApplyExecutionData *edata,
 	}
 	MemoryContextSwitchTo(oldctx);
 
-	/* Check if we can do the update or delete on the leaf partition. */
-	if (operation == CMD_UPDATE || operation == CMD_DELETE)
+	if (operation == CMD_INSERT || operation == CMD_UPDATE ||
+		operation == CMD_DELETE)
 	{
-		part_entry = logicalrep_partition_open(relmapentry, partrel,
-											   attrmap);
-		check_relation_updatable(part_entry);
+		part_entry = logicalrep_partition_open(relmapentry, partrel, attrmap);
+
+		/* Check if we can do the update or delete on the leaf partition */
+		if (operation != CMD_INSERT)
+			check_relation_updatable(part_entry);
 	}
 
 	switch (operation)
 	{
 		case CMD_INSERT:
 			apply_handle_insert_internal(edata, partrelinfo,
-										 remoteslot_part);
+										 remoteslot_part, newtup, part_entry);
 			break;
 
 		case CMD_DELETE:
@@ -3023,6 +3122,9 @@ apply_handle_tuple_routing(ApplyExecutionData *edata,
 				RepOriginId localorigin;
 				TransactionId localxmin;
 				TimestampTz localts;
+				LogicalRepRelMapEntry *part_entry_new = NULL;
+				ConflictResolver resolver;
+				bool		apply_remote = true;
 
 				/* Get the matching local tuple from the partition. */
 				found = FindReplTupleInLocalRel(edata, partrel,
@@ -3032,38 +3134,81 @@ apply_handle_tuple_routing(ApplyExecutionData *edata,
 				if (!found)
 				{
 					/*
-					 * The tuple to be updated could not be found.  Do nothing
-					 * except for emitting a log message.
+					 * The tuple to be updated could not be found. Report the
+					 * conflict and resolver. And take action based on the
+					 * configured resolver.
 					 */
 					if (MySubscription->detectconflict)
-						ReportApplyConflict(LOG, CT_UPDATE_MISSING,
-											partrel, InvalidOid,
-											InvalidTransactionId,
+					{
+						resolver = GetConflictResolver(localslot, partrel, CT_UPDATE_MISSING,
+													   &apply_remote, newtup, InvalidOid,
+													   InvalidTransactionId, InvalidRepOriginId, 0);
+
+						ReportApplyConflict(LOG, CT_UPDATE_MISSING, resolver, partrel,
+											InvalidOid, InvalidTransactionId,
 											InvalidRepOriginId, 0, NULL);
 
-					return;
+						if (apply_remote)
+						{
+							/*
+							 * Resolver is in favour of applying the remote
+							 * changes. Prepare the slot for the INSERT.
+							 */
+							oldctx = MemoryContextSwitchTo(GetPerTupleMemoryContext(estate));
+							slot_store_data(remoteslot_part, part_entry, newtup);
+							slot_fill_defaults(part_entry, estate, remoteslot_part);
+							MemoryContextSwitchTo(oldctx);
+						}
+					}
 				}
+				else
+				{
+					/*
+					 * The tuple to be updated is found. If conflict detection
+					 * is enabled, check whether the local tuple was modified
+					 * by a different origin. If detected, report and resolve
+					 * the conflict.
+					 */
+					if (MySubscription->detectconflict &&
+						GetTupleCommitTs(localslot, &localxmin, &localorigin, &localts) &&
+						localorigin != replorigin_session_origin)
+					{
+						resolver = GetConflictResolver(localslot, partrel, CT_UPDATE_DIFFER,
+													   &apply_remote, NULL, InvalidOid,
+													   localxmin, localorigin, localts);
 
-				/*
-				 * If conflict detection is enabled, check whether the local
-				 * tuple was modified by a different origin. If detected,
-				 * report the conflict.
-				 */
-				if (MySubscription->detectconflict &&
-					GetTupleCommitTs(localslot, &localxmin, &localorigin, &localts) &&
-					localorigin != replorigin_session_origin)
-					ReportApplyConflict(LOG, CT_UPDATE_DIFFER, partrel,
-										InvalidOid, localxmin, localorigin,
-										localts, NULL);
+						ReportApplyConflict(LOG, CT_UPDATE_DIFFER, resolver, partrel,
+											InvalidOid, localxmin, localorigin, localts,
+											NULL);
+					}
 
-				/*
-				 * Apply the update to the local tuple, putting the result in
-				 * remoteslot_part.
-				 */
-				oldctx = MemoryContextSwitchTo(GetPerTupleMemoryContext(estate));
-				slot_modify_data(remoteslot_part, localslot, part_entry,
-								 newtup);
-				MemoryContextSwitchTo(oldctx);
+					if (apply_remote)
+					{
+						/*
+						 * We can reach here in two cases:
+						 *
+						 * 1. If we found a tuple but conflict detection is
+						 * OFF
+						 *
+						 * 2. If we found a tuple and resolver is in favor of
+						 * applying the change when conflict detection is ON
+						 *
+						 * Putting the result in remoteslot_part.
+						 */
+						oldctx = MemoryContextSwitchTo(GetPerTupleMemoryContext(estate));
+						slot_modify_data(remoteslot_part, localslot, part_entry,
+										 newtup);
+						MemoryContextSwitchTo(oldctx);
+					}
+					else
+
+						/*
+						 * apply_remote can be toggled if resolver for
+						 * update_differ is set to skip. Ignore remote update.
+						 */
+						return;
+
+				}
 
 				/*
 				 * Does the updated tuple still satisfy the current
@@ -3073,27 +3218,59 @@ apply_handle_tuple_routing(ApplyExecutionData *edata,
 					ExecPartitionCheck(partrelinfo, remoteslot_part, estate,
 									   false))
 				{
-					/*
-					 * Yes, so simply UPDATE the partition.  We don't call
-					 * apply_handle_update_internal() here, which would
-					 * normally do the following work, to avoid repeating some
-					 * work already done above to find the local tuple in the
-					 * partition.
-					 */
-					EPQState	epqstate;
-
-					EvalPlanQualInit(&epqstate, estate, NULL, NIL, -1, NIL);
-					ExecOpenIndices(partrelinfo, false);
-
-					EvalPlanQualSetSlot(&epqstate, remoteslot_part);
-					TargetPrivilegesCheck(partrelinfo->ri_RelationDesc,
-										  ACL_UPDATE);
-					ExecSimpleRelationUpdate(partrelinfo, estate, &epqstate,
-											 localslot, remoteslot_part);
-					ExecCloseIndices(partrelinfo);
-					EvalPlanQualEnd(&epqstate);
+					if (found && apply_remote)
+					{
+						/*
+						 * Yes, so simply UPDATE the partition.  We don't call
+						 * apply_handle_update_internal() here, which would
+						 * normally do the following work, to avoid repeating
+						 * some work already done above to find the local
+						 * tuple in the partition.
+						 *
+						 * Do the update in cases - 1. conflict detection is
+						 * OFF and found a tuple 2. conflict detection is ON,
+						 * update_differ conflict is detected for the found
+						 * tuple and the resolver is in favour of applying the
+						 * update.
+						 */
+
+						EPQState	epqstate;
+
+						EvalPlanQualInit(&epqstate, estate, NULL, NIL, -1, NIL);
+						ExecOpenIndices(partrelinfo, false);
+
+						EvalPlanQualSetSlot(&epqstate, remoteslot_part);
+						TargetPrivilegesCheck(partrelinfo->ri_RelationDesc,
+											  ACL_UPDATE);
+						ExecSimpleRelationUpdate(partrelinfo, estate, &epqstate,
+												 localslot, remoteslot_part);
+						ExecCloseIndices(partrelinfo);
+						EvalPlanQualEnd(&epqstate);
+
+					}
+					else if (apply_remote)
+					{
+						/*
+						 * Tuple is not found but update_missing resolver is
+						 * in favour of applying the change as INSERT.
+						 */
+						apply_handle_insert_internal(edata, partrelinfo,
+													 remoteslot_part, newtup,
+													 part_entry);
+					}
 				}
-				else
+
+				/*
+				 * Updated tuple doesn't satisfy the current partition's
+				 * constraint.
+				 *
+				 * If conflict detection is OFF, proceed by always applying
+				 * the update (as 'apply_remote' is by default true). If
+				 * conflict detection is ON, 'apply_remote' can be OFF as well
+				 * if the resolver for update_missing conflict conveys to skip
+				 * the update.
+				 */
+				else if (apply_remote)
 				{
 					/* Move the tuple into the new partition. */
 
@@ -3134,10 +3311,16 @@ apply_handle_tuple_routing(ApplyExecutionData *edata,
 											 get_namespace_name(RelationGetNamespace(partrel_new)),
 											 RelationGetRelationName(partrel_new));
 
-					/* DELETE old tuple found in the old partition. */
-					apply_handle_delete_internal(edata, partrelinfo,
-												 localslot,
-												 part_entry->localindexoid);
+					/*
+					 * If tuple is found, delete it from old partition. We can
+					 * reach this flow even for the case when the 'found' flag
+					 * is false for 'update_missing' conflict and resolver is
+					 * in favor of inserting the tuple.
+					 */
+					if (found)
+						apply_handle_delete_internal(edata, partrelinfo,
+													 localslot,
+													 part_entry->localindexoid);
 
 					/* INSERT new tuple into the new partition. */
 
@@ -3153,19 +3336,25 @@ apply_handle_tuple_routing(ApplyExecutionData *edata,
 					map = ExecGetRootToChildMap(partrelinfo_new, estate);
 					if (map != NULL)
 					{
+						attrmap = map->attrMap;
 						remoteslot_part = execute_attr_map_slot(map->attrMap,
 																remoteslot,
 																remoteslot_part);
 					}
 					else
 					{
+						attrmap = NULL;
 						remoteslot_part = ExecCopySlot(remoteslot_part,
 													   remoteslot);
 						slot_getallattrs(remoteslot);
 					}
 					MemoryContextSwitchTo(oldctx);
+					part_entry_new = logicalrep_partition_open(part_entry,
+															   partrel_new,
+															   attrmap);
 					apply_handle_insert_internal(edata, partrelinfo_new,
-												 remoteslot_part);
+												 remoteslot_part, newtup,
+												 part_entry_new);
 				}
 			}
 			break;
diff --git a/src/include/executor/executor.h b/src/include/executor/executor.h
index 9770752ea3..bc72b1f4fd 100644
--- a/src/include/executor/executor.h
+++ b/src/include/executor/executor.h
@@ -18,6 +18,8 @@
 #include "fmgr.h"
 #include "nodes/lockoptions.h"
 #include "nodes/parsenodes.h"
+#include "replication/logicalproto.h"
+#include "replication/logicalrelation.h"
 #include "utils/memutils.h"
 
 
@@ -655,7 +657,8 @@ extern bool RelationFindReplTupleSeq(Relation rel, LockTupleMode lockmode,
 									 TupleTableSlot *searchslot, TupleTableSlot *outslot);
 
 extern void ExecSimpleRelationInsert(ResultRelInfo *resultRelInfo,
-									 EState *estate, TupleTableSlot *slot);
+									 EState *estate, TupleTableSlot *slot,
+									 TupleTableSlot **conflictsloty);
 extern void ExecSimpleRelationUpdate(ResultRelInfo *resultRelInfo,
 									 EState *estate, EPQState *epqstate,
 									 TupleTableSlot *searchslot, TupleTableSlot *slot);
diff --git a/src/include/replication/conflict.h b/src/include/replication/conflict.h
index c6023e0914..dcc89f222f 100644
--- a/src/include/replication/conflict.h
+++ b/src/include/replication/conflict.h
@@ -13,6 +13,8 @@
 #include "catalog/objectaddress.h"
 #include "executor/tuptable.h"
 #include "nodes/execnodes.h"
+#include "replication/logicalproto.h"
+#include "replication/logicalrelation.h"
 #include "utils/relcache.h"
 #include "utils/timestamp.h"
 
@@ -75,9 +77,20 @@ typedef enum ConflictResolver
 extern bool GetTupleCommitTs(TupleTableSlot *localslot, TransactionId *xmin,
 							 RepOriginId *localorigin, TimestampTz *localts);
 extern void ReportApplyConflict(int elevel, ConflictType type,
-								Relation localrel, Oid conflictidx,
-								TransactionId localxmin, RepOriginId localorigin,
-								TimestampTz localts, TupleTableSlot *conflictslot);
+								ConflictResolver resolver, Relation localrel,
+								Oid conflictidx, TransactionId localxmin,
+								RepOriginId localorigin, TimestampTz localts,
+								TupleTableSlot *conflictslot);
 extern void InitConflictIndexes(ResultRelInfo *relInfo);
 extern void ExecConflictResolverStmt(ConflictResolverStmt *stmt);
+extern ConflictResolver GetConflictResolver(TupleTableSlot *localslot,
+											Relation localrel,
+											ConflictType type,
+											bool *apply_remote,
+											LogicalRepTupleData *newtup,
+											Oid conflictidx, TransactionId xmin,
+											RepOriginId origin,
+											TimestampTz committs);
+extern bool CanCreateFullTuple(Relation localrel,
+							   LogicalRepTupleData *newtup);
 #endif
diff --git a/src/test/subscription/t/029_on_error.pl b/src/test/subscription/t/029_on_error.pl
index 496a3c6cd9..c746191601 100644
--- a/src/test/subscription/t/029_on_error.pl
+++ b/src/test/subscription/t/029_on_error.pl
@@ -113,6 +113,10 @@ $node_subscriber->safe_psql('postgres',
 	"CREATE SUBSCRIPTION sub CONNECTION '$publisher_connstr' PUBLICATION pub WITH (disable_on_error = true, streaming = on, two_phase = on, detect_conflict = on)"
 );
 
+# Set 'ERROR' conflict resolver for 'insert_exist' conflict type
+$node_subscriber->safe_psql('postgres',"set conflict resolver 'error' for 'insert_exists'");
+
+
 # Initial synchronization failure causes the subscription to be disabled.
 $node_subscriber->poll_query_until('postgres',
 	"SELECT subenabled = false FROM pg_catalog.pg_subscription WHERE subname = 'sub'"
@@ -177,6 +181,9 @@ $result = $node_subscriber->safe_psql('postgres',
 is($result, "0",
 	"check all prepared transactions are resolved on the subscriber");
 
+# Reset conflict resolver for 'insert_exist' conflict type to default.
+$node_subscriber->safe_psql('postgres',"reset conflict resolver for 'insert_exists'");
+
 $node_subscriber->stop;
 $node_publisher->stop;
 
-- 
2.34.1



  [application/octet-stream] v4-0004-Manage-Clock-skew-and-implement-last_update_wins.patch (22.3K, ../../CABdArM47myyKnOU4LB54k3wmgpFu63s2gxmAQVK-DdWzCLKAaw@mail.gmail.com/5-v4-0004-Manage-Clock-skew-and-implement-last_update_wins.patch)
  download | inline diff:
From 62b5dd1c41d30888a37b5365ad35f2603eb2b704 Mon Sep 17 00:00:00 2001
From: Nisha Moond <[email protected]>
Date: Thu, 4 Jul 2024 16:16:46 +0530
Subject: [PATCH v4 4/5] Manage Clock skew and implement last_update_wins

This patch attempts to manage clock skew between nodes by
introducing two new GUCs:
a) max_logical_rep_clock_skew
b) max_logical_rep_clock_skew_action

This patch also implements last_update_wins resolver.
---
 src/backend/replication/logical/conflict.c    |  99 ++++++++++++++--
 src/backend/replication/logical/origin.c      |   1 +
 src/backend/replication/logical/worker.c      | 108 +++++++++++++++++-
 .../utils/activity/wait_event_names.txt       |   1 +
 src/backend/utils/misc/guc_tables.c           |  26 +++++
 src/backend/utils/misc/postgresql.conf.sample |   6 +-
 src/include/catalog/pg_conflict.dat           |   6 +-
 src/include/replication/conflict.h            |   3 +
 src/include/replication/logicalworker.h       |  17 +++
 src/include/replication/origin.h              |   1 +
 src/include/utils/timestamp.h                 |   1 +
 .../regress/expected/conflict_resolver.out    |  16 +--
 src/tools/pgindent/typedefs.list              |   1 +
 13 files changed, 259 insertions(+), 27 deletions(-)

diff --git a/src/backend/replication/logical/conflict.c b/src/backend/replication/logical/conflict.c
index d215d48dc6..4934099cc8 100644
--- a/src/backend/replication/logical/conflict.c
+++ b/src/backend/replication/logical/conflict.c
@@ -44,6 +44,7 @@ const char *const ConflictTypeNames[] = {
 const char *const ConflictResolverNames[] = {
 	[CR_REMOTE_APPLY] = "remote_apply",
 	[CR_KEEP_LOCAL] = "keep_local",
+	[CR_LAST_UPDATE_WINS] = "last_update_wins",
 	[CR_APPLY_OR_SKIP] = "apply_or_skip",
 	[CR_APPLY_OR_ERROR] = "apply_or_error",
 	[CR_SKIP] = "skip",
@@ -69,11 +70,11 @@ const char *const ConflictResolverNames[] = {
  * friendly name for a resolver and thus has been added here.
  */
 const int	ConflictTypeResolverMap[][CONFLICT_TYPE_MAX_RESOLVERS] = {
-	[CT_INSERT_EXISTS] = {CR_REMOTE_APPLY, CR_KEEP_LOCAL, CR_ERROR},
-	[CT_UPDATE_DIFFER] = {CR_REMOTE_APPLY, CR_KEEP_LOCAL, CR_ERROR},
+	[CT_INSERT_EXISTS] = {CR_REMOTE_APPLY, CR_KEEP_LOCAL, CR_LAST_UPDATE_WINS, CR_ERROR},
+	[CT_UPDATE_DIFFER] = {CR_REMOTE_APPLY, CR_KEEP_LOCAL, CR_LAST_UPDATE_WINS, CR_ERROR},
 	[CT_UPDATE_MISSING] = {CR_APPLY_OR_SKIP, CR_APPLY_OR_ERROR, CR_SKIP, CR_ERROR},
 	[CT_DELETE_MISSING] = {CR_SKIP, CR_ERROR},
-	[CT_DELETE_DIFFER] = {CR_REMOTE_APPLY, CR_KEEP_LOCAL, CR_ERROR}
+	[CT_DELETE_DIFFER] = {CR_REMOTE_APPLY, CR_KEEP_LOCAL, CR_LAST_UPDATE_WINS, CR_ERROR}
 };
 
 /*
@@ -81,11 +82,11 @@ const int	ConflictTypeResolverMap[][CONFLICT_TYPE_MAX_RESOLVERS] = {
  * If this changes, change it in pg_conflict.dat as well.
  */
 const int	ConflictTypeDefaultResolvers[] = {
-	[CT_INSERT_EXISTS] = CR_REMOTE_APPLY,
-	[CT_UPDATE_DIFFER] = CR_REMOTE_APPLY,
+	[CT_INSERT_EXISTS] = CR_LAST_UPDATE_WINS,
+	[CT_UPDATE_DIFFER] = CR_LAST_UPDATE_WINS,
 	[CT_UPDATE_MISSING] = CR_APPLY_OR_SKIP,
 	[CT_DELETE_MISSING] = CR_SKIP,
-	[CT_DELETE_DIFFER] = CR_REMOTE_APPLY
+	[CT_DELETE_DIFFER] = CR_LAST_UPDATE_WINS
 
 };
 
@@ -215,11 +216,30 @@ errdetail_apply_conflict(ConflictType type, ConflictResolver resolver,
 										 get_rel_name(conflictidx));
 				}
 				else
-					return errdetail("Key already exists. Applying resolution method \"%s\"", ConflictResolverNames[resolver]);
+				{
+					if (resolver == CR_LAST_UPDATE_WINS)
+						return errdetail("Key already exists. Applying resolution method \"%s\". The local tuple : origin=%u, timestamp=%s; The remote tuple : origin=%u, timestamp=%s.",
+										 ConflictResolverNames[resolver],
+										 localorigin, timestamptz_to_str(localts),
+										 replorigin_session_origin,
+										 timestamptz_to_str(replorigin_session_origin_timestamp));
+					else
+						return errdetail("Key already exists. Applying resolution method \"%s\"",
+										 ConflictResolverNames[resolver]);
+				}
+
 			}
 		case CT_UPDATE_DIFFER:
-			return errdetail("Updating a row that was modified by a different origin %u in transaction %u at %s. Applying resolution method \"%s\"",
-							 localorigin, localxmin, timestamptz_to_str(localts), ConflictResolverNames[resolver]);
+			if (resolver == CR_LAST_UPDATE_WINS)
+				return errdetail("Updating a row that was modified by a different origin %u in transaction %u at %s. Applying resolution method \"%s\". The remote tuple : origin=%u, timestamp=%s.",
+								 localorigin, localxmin, timestamptz_to_str(localts),
+								 ConflictResolverNames[resolver],
+								 replorigin_session_origin,
+								 timestamptz_to_str(replorigin_session_origin_timestamp));
+			else
+				return errdetail("Updating a row that was modified by a different origin %u in transaction %u at %s. Applying resolution method \"%s\"",
+								 localorigin, localxmin, timestamptz_to_str(localts),
+								 ConflictResolverNames[resolver]);
 		case CT_UPDATE_MISSING:
 			return errdetail("Did not find the row to be updated. Applying resolution method \"%s\"",
 							 ConflictResolverNames[resolver]);
@@ -227,9 +247,16 @@ errdetail_apply_conflict(ConflictType type, ConflictResolver resolver,
 			return errdetail("Did not find the row to be deleted. Applying resolution method \"%s\"",
 							 ConflictResolverNames[resolver]);
 		case CT_DELETE_DIFFER:
-			return errdetail("Deleting a row that was modified by a different origin %u in transaction %u at %s. Applying resolution method \"%s\"",
-							 localorigin, localxmin, timestamptz_to_str(localts),
-							 ConflictResolverNames[resolver]);
+			if (resolver == CR_LAST_UPDATE_WINS)
+				return errdetail("Deleting a row that was modified by a different origin %u in transaction %u at %s. Applying resolution method \"%s\". The remote tuple : origin=%u, timestamp=%s.",
+								 localorigin, localxmin, timestamptz_to_str(localts),
+								 ConflictResolverNames[resolver],
+								 replorigin_session_origin,
+								 timestamptz_to_str(replorigin_session_origin_timestamp));
+			else
+				return errdetail("Deleting a row that was modified by a different origin %u in transaction %u at %s. Applying resolution method \"%s\"",
+								 localorigin, localxmin, timestamptz_to_str(localts),
+								 ConflictResolverNames[resolver]);
 	}
 
 	return 0;					/* silence compiler warning */
@@ -340,6 +367,15 @@ validate_conflict_type_and_resolver(char *conflict_type, char *conflict_resolver
 				errmsg("%s is not a valid conflict resolver for conflict type %s",
 					   conflict_resolver,
 					   conflict_type));
+
+	if ((resolver == CR_LAST_UPDATE_WINS) && !track_commit_timestamp)
+		ereport(ERROR,
+				errcode(ERRCODE_INVALID_PARAMETER_VALUE),
+				errmsg("resolver %s requires %s to be enabled",
+					   conflict_resolver, "track_commit_timestamp"),
+				errhint("Make sure the configuration parameter %s is set.",
+						"track_commit_timestamp"));
+
 	return type;
 }
 
@@ -381,6 +417,42 @@ get_conflict_resolver_internal(ConflictType type)
 	return resolver;
 }
 
+/*
+ * Compare the timestamps of given local tuple and the remote tuple to
+ * resolve the conflict.
+ *
+ * Returns true if remote tuple has the latest timestamp, false otherwise.
+ */
+static bool
+resolve_by_timestamp(TupleTableSlot *localslot)
+{
+	TransactionId local_xmin;
+	TimestampTz local_ts;
+	RepOriginId local_origin;
+	int			ts_cmp;
+	uint64		local_system_identifier;
+
+	/* Get origin and timestamp info of the local tuple */
+	GetTupleCommitTs(localslot, &local_xmin, &local_origin, &local_ts);
+
+	/* Compare the timestamps of remote & local tuple to decide the winner */
+	ts_cmp = timestamptz_cmp_internal(replorigin_session_origin_timestamp,
+									  local_ts);
+
+	if (ts_cmp == 0)
+	{
+		elog(LOG, "Timestamps of remote and local tuple are equal, comparing remote and local system identifiers");
+
+		/* Get current system's identifier */
+		local_system_identifier = GetSystemIdentifier();
+
+		return local_system_identifier <= replorigin_session_origin_sysid;
+	}
+	else
+		return (ts_cmp > 0);
+
+}
+
 /*
  * Check if a full tuple can be created from the new tuple.
  * Return true if yes, false otherwise.
@@ -503,6 +575,9 @@ GetConflictResolver(TupleTableSlot *localslot, Relation localrel,
 
 	switch (resolver)
 	{
+		case CR_LAST_UPDATE_WINS:
+			*apply_remote = resolve_by_timestamp(localslot);
+			break;
 		case CR_REMOTE_APPLY:
 			*apply_remote = true;
 			break;
diff --git a/src/backend/replication/logical/origin.c b/src/backend/replication/logical/origin.c
index 419e4814f0..bd8e6f0024 100644
--- a/src/backend/replication/logical/origin.c
+++ b/src/backend/replication/logical/origin.c
@@ -155,6 +155,7 @@ typedef struct ReplicationStateCtl
 RepOriginId replorigin_session_origin = InvalidRepOriginId; /* assumed identity */
 XLogRecPtr	replorigin_session_origin_lsn = InvalidXLogRecPtr;
 TimestampTz replorigin_session_origin_timestamp = 0;
+uint64		replorigin_session_origin_sysid = 0;
 
 /*
  * Base address into a shared memory array of replication states of size
diff --git a/src/backend/replication/logical/worker.c b/src/backend/replication/logical/worker.c
index 239d5c7cd1..7586aa53ae 100644
--- a/src/backend/replication/logical/worker.c
+++ b/src/backend/replication/logical/worker.c
@@ -318,6 +318,19 @@ static uint32 parallel_stream_nchanges = 0;
 /* Are we initializing an apply worker? */
 bool		InitializingApplyWorker = false;
 
+/*
+ * GUC support
+ */
+const struct config_enum_entry logical_rep_clock_skew_action_options[] = {
+	{"error", LR_CLOCK_SKEW_ACTION_ERROR, false},
+	{"wait", LR_CLOCK_SKEW_ACTION_WAIT, false},
+	{NULL, 0, false}
+};
+
+/* GUCs */
+int			max_logical_rep_clock_skew = 0;
+int			max_logical_rep_clock_skew_action = LR_CLOCK_SKEW_ACTION_ERROR;
+
 /*
  * We enable skipping all data modification changes (INSERT, UPDATE, etc.) for
  * the subscription if the remote transaction's finish LSN matches the subskiplsn.
@@ -987,6 +1000,86 @@ slot_modify_data(TupleTableSlot *slot, TupleTableSlot *srcslot,
 	ExecStoreVirtualTuple(slot);
 }
 
+/*
+ * Manage clock skew between nodes.
+ *
+ * It checks if the remote commit timestamp is ahead of the local clock
+ * and if the difference exceeds max_logical_rep_clock_skew, it performs
+ * the action specified by the max_logical_rep_clock_skew_action.
+ */
+static void
+manage_clock_skew()
+{
+	TimestampTz current;
+	TimestampTz delayUntil;
+	long		msecs;
+	int			rc;
+
+	/* nothing to do if no max clock skew configured */
+	if (max_logical_rep_clock_skew == LR_CLOCK_SKEW_DEFAULT)
+		return;
+
+	current = GetCurrentTimestamp();
+
+	/*
+	 * If the timestamp of the currently replayed transaction is in the future
+	 * compared to the current time on the subscriber and the difference is
+	 * larger than max_logical_rep_clock_skew, then perform the action
+	 * specified by the max_logical_rep_clock_skew_action setting.
+	 */
+	if (replorigin_session_origin_timestamp > current &&
+		TimestampDifferenceExceeds(current, replorigin_session_origin_timestamp,
+								   max_logical_rep_clock_skew * 1000))
+	{
+		if (max_logical_rep_clock_skew_action == LR_CLOCK_SKEW_ACTION_ERROR)
+			ereport(ERROR,
+					(errcode(ERRCODE_PROTOCOL_VIOLATION),
+					 errmsg_internal("logical replication clock skew exceeded max tolerated value of %d seconds",
+									 max_logical_rep_clock_skew)));
+
+		/* Perform the wait */
+		while (true)
+		{
+			delayUntil =
+				TimestampTzMinusSeconds(replorigin_session_origin_timestamp,
+										max_logical_rep_clock_skew);
+
+			/* Exit without waiting if it's already past 'delayUntil' time */
+			msecs = TimestampDifferenceMilliseconds(GetCurrentTimestamp(),
+													delayUntil);
+			if (msecs <= 0)
+				break;
+
+			elog(LOG, "delaying apply for %ld milliseconds to bring clock skew "
+				 "within permissible value of %d seconds",
+				 msecs, max_logical_rep_clock_skew);
+
+			/* Sleep until we are signaled or msecs have elapsed */
+			rc = WaitLatch(MyLatch,
+						   WL_LATCH_SET | WL_TIMEOUT | WL_EXIT_ON_PM_DEATH,
+						   msecs,
+						   WAIT_EVENT_LOGICAL_CLOCK_SKEW);
+
+			/* Exit the loop if msecs have elapsed */
+			if (rc & WL_TIMEOUT)
+				break;
+
+			if (rc & WL_LATCH_SET)
+			{
+				ResetLatch(MyLatch);
+				CHECK_FOR_INTERRUPTS();
+			}
+
+			/* This might change max_logical_rep_clock_skew. */
+			if (ConfigReloadPending)
+			{
+				ConfigReloadPending = false;
+				ProcessConfigFile(PGC_SIGHUP);
+			}
+		}
+	}
+}
+
 /*
  * Handle BEGIN message.
  */
@@ -1008,6 +1101,12 @@ apply_handle_begin(StringInfo s)
 	in_remote_transaction = true;
 
 	pgstat_report_activity(STATE_RUNNING, NULL);
+
+	/* Capture the commit timestamp of the remote transaction */
+	replorigin_session_origin_timestamp = begin_data.committime;
+
+	/* Check if there is any clock skew and take configured action */
+	manage_clock_skew();
 }
 
 /*
@@ -4694,6 +4793,7 @@ run_apply_worker()
 	TimeLineID	startpointTLI;
 	char	   *err;
 	bool		must_use_password;
+	char	   *replorigin_sysid;
 
 	slotname = MySubscription->slotname;
 
@@ -4733,10 +4833,12 @@ run_apply_worker()
 				 errmsg("could not connect to the publisher: %s", err)));
 
 	/*
-	 * We don't really use the output identify_system for anything but it does
-	 * some initializations on the upstream so let's still call it.
+	 * Call identify_system to do some initializations on the upstream and
+	 * store the output as system identifier of the replication origin node.
 	 */
-	(void) walrcv_identify_system(LogRepWorkerWalRcvConn, &startpointTLI);
+	replorigin_sysid = walrcv_identify_system(LogRepWorkerWalRcvConn,
+											  &startpointTLI);
+	replorigin_session_origin_sysid = strtoul(replorigin_sysid, NULL, 10);
 
 	set_apply_error_context_origin(originname);
 
diff --git a/src/backend/utils/activity/wait_event_names.txt b/src/backend/utils/activity/wait_event_names.txt
index db37beeaae..a51f82169e 100644
--- a/src/backend/utils/activity/wait_event_names.txt
+++ b/src/backend/utils/activity/wait_event_names.txt
@@ -59,6 +59,7 @@ CHECKPOINTER_MAIN	"Waiting in main loop of checkpointer process."
 LOGICAL_APPLY_MAIN	"Waiting in main loop of logical replication apply process."
 LOGICAL_LAUNCHER_MAIN	"Waiting in main loop of logical replication launcher process."
 LOGICAL_PARALLEL_APPLY_MAIN	"Waiting in main loop of logical replication parallel apply process."
+LOGICAL_CLOCK_SKEW	"Waiting in apply-begin of logical replication apply process to bring clock skew in permissible range."
 RECOVERY_WAL_STREAM	"Waiting in main loop of startup process for WAL to arrive, during streaming recovery."
 REPLICATION_SLOTSYNC_MAIN	"Waiting in main loop of slot sync worker."
 REPLICATION_SLOTSYNC_SHUTDOWN	"Waiting for slot sync worker to shut down."
diff --git a/src/backend/utils/misc/guc_tables.c b/src/backend/utils/misc/guc_tables.c
index d28b0bcb40..6dc23f28cf 100644
--- a/src/backend/utils/misc/guc_tables.c
+++ b/src/backend/utils/misc/guc_tables.c
@@ -67,6 +67,7 @@
 #include "postmaster/walsummarizer.h"
 #include "postmaster/walwriter.h"
 #include "replication/logicallauncher.h"
+#include "replication/logicalworker.h"
 #include "replication/slot.h"
 #include "replication/slotsync.h"
 #include "replication/syncrep.h"
@@ -492,6 +493,7 @@ extern const struct config_enum_entry archive_mode_options[];
 extern const struct config_enum_entry recovery_target_action_options[];
 extern const struct config_enum_entry wal_sync_method_options[];
 extern const struct config_enum_entry dynamic_shared_memory_options[];
+extern const struct config_enum_entry logical_rep_clock_skew_action_options[];
 
 /*
  * GUC option variables that are exported from this module
@@ -3649,6 +3651,19 @@ struct config_int ConfigureNamesInt[] =
 		NULL, NULL, NULL
 	},
 
+	{
+		{"max_logical_rep_clock_skew", PGC_SIGHUP, REPLICATION_SUBSCRIBERS,
+			gettext_noop("Sets maximum clock skew tolerance between logical "
+						 "replication nodes beyond which action configured "
+						 "in max_logical_rep_clock_skew_action is triggered."),
+			NULL,
+			GUC_UNIT_S
+		},
+		&max_logical_rep_clock_skew,
+		LR_CLOCK_SKEW_DEFAULT, LR_CLOCK_SKEW_DEFAULT, INT_MAX,
+		NULL, NULL, NULL
+	},
+
 	/* End-of-list marker */
 	{
 		{NULL, 0, 0, NULL, NULL}, NULL, 0, 0, 0, NULL, NULL, NULL
@@ -4915,6 +4930,17 @@ struct config_enum ConfigureNamesEnum[] =
 		NULL, NULL, NULL
 	},
 
+	{
+		{"max_logical_rep_clock_skew_action", PGC_POSTMASTER, REPLICATION_SUBSCRIBERS,
+			gettext_noop("Sets the action to perform if a clock skew higher "
+						 "than max_logical_rep_clock_skew is detected."),
+			NULL
+		},
+		&max_logical_rep_clock_skew_action,
+		LR_CLOCK_SKEW_ACTION_ERROR, logical_rep_clock_skew_action_options,
+		NULL, NULL, NULL
+	},
+
 	{
 		{"track_functions", PGC_SUSET, STATS_CUMULATIVE,
 			gettext_noop("Collects function-level statistics on database activity."),
diff --git a/src/backend/utils/misc/postgresql.conf.sample b/src/backend/utils/misc/postgresql.conf.sample
index 9ec9f97e92..3a7fd70506 100644
--- a/src/backend/utils/misc/postgresql.conf.sample
+++ b/src/backend/utils/misc/postgresql.conf.sample
@@ -383,7 +383,11 @@
 					# (change requires restart)
 #max_sync_workers_per_subscription = 2	# taken from max_logical_replication_workers
 #max_parallel_apply_workers_per_subscription = 2	# taken from max_logical_replication_workers
-
+#max_logical_rep_clock_skew = -1	# maximum clock skew tolerance between logical
+					# replication nodes beyond which action configured in
+					# 'max_logical_rep_clock_skew_action' is triggered.
+#max_logical_rep_clock_skew_action = error # error or wait
+					   # (change requires restart)
 
 #------------------------------------------------------------------------------
 # QUERY TUNING
diff --git a/src/include/catalog/pg_conflict.dat b/src/include/catalog/pg_conflict.dat
index 8d6183e3f2..1905151840 100644
--- a/src/include/catalog/pg_conflict.dat
+++ b/src/include/catalog/pg_conflict.dat
@@ -12,10 +12,10 @@
 
 [
 
-{ conftype => 'insert_exists', confres => 'remote_apply' },
-{ conftype => 'update_differ', confres => 'remote_apply' },
+{ conftype => 'insert_exists', confres => 'last_update_wins' },
+{ conftype => 'update_differ', confres => 'last_update_wins' },
 { conftype => 'update_missing', confres => 'apply_or_skip' },
 { conftype => 'delete_missing', confres => 'skip' },
-{ conftype => 'delete_differ', confres => 'remote_apply' }
+{ conftype => 'delete_differ', confres => 'last_update_wins' }
 
 ]
diff --git a/src/include/replication/conflict.h b/src/include/replication/conflict.h
index dcc89f222f..d38a22ddde 100644
--- a/src/include/replication/conflict.h
+++ b/src/include/replication/conflict.h
@@ -57,6 +57,9 @@ typedef enum ConflictResolver
 	/* Keep the local change */
 	CR_KEEP_LOCAL,
 
+	/* Apply the change with latest timestamp */
+	CR_LAST_UPDATE_WINS,
+
 	/* Apply the remote change; skip if it can not be applied */
 	CR_APPLY_OR_SKIP,
 
diff --git a/src/include/replication/logicalworker.h b/src/include/replication/logicalworker.h
index a18d79d1b2..2b922f9c62 100644
--- a/src/include/replication/logicalworker.h
+++ b/src/include/replication/logicalworker.h
@@ -14,7 +14,24 @@
 
 #include <signal.h>
 
+/*
+ * The default for max_logical_rep_clock_skew is -1, which means ignore clock
+ * skew (the check is turned off).
+ */
+#define LR_CLOCK_SKEW_DEFAULT -1
+
+/*
+ * Worker Clock Skew Action.
+ */
+typedef enum
+{
+	LR_CLOCK_SKEW_ACTION_ERROR,
+	LR_CLOCK_SKEW_ACTION_WAIT,
+} LogicalRepClockSkewAction;
+
 extern PGDLLIMPORT volatile sig_atomic_t ParallelApplyMessagePending;
+extern PGDLLIMPORT int max_logical_rep_clock_skew;
+extern PGDLLIMPORT int max_logical_rep_clock_skew_action;
 
 extern void ApplyWorkerMain(Datum main_arg);
 extern void ParallelApplyWorkerMain(Datum main_arg);
diff --git a/src/include/replication/origin.h b/src/include/replication/origin.h
index 7189ba9e76..dcbbbdf6ea 100644
--- a/src/include/replication/origin.h
+++ b/src/include/replication/origin.h
@@ -36,6 +36,7 @@ typedef struct xl_replorigin_drop
 extern PGDLLIMPORT RepOriginId replorigin_session_origin;
 extern PGDLLIMPORT XLogRecPtr replorigin_session_origin_lsn;
 extern PGDLLIMPORT TimestampTz replorigin_session_origin_timestamp;
+extern PGDLLIMPORT uint64 replorigin_session_origin_sysid;
 
 /* API for querying & manipulating replication origins */
 extern RepOriginId replorigin_by_name(const char *roname, bool missing_ok);
diff --git a/src/include/utils/timestamp.h b/src/include/utils/timestamp.h
index a6ce03ed46..53b828d89d 100644
--- a/src/include/utils/timestamp.h
+++ b/src/include/utils/timestamp.h
@@ -84,6 +84,7 @@ IntervalPGetDatum(const Interval *X)
 /* Macros for doing timestamp arithmetic without assuming timestamp's units */
 #define TimestampTzPlusMilliseconds(tz,ms) ((tz) + ((ms) * (int64) 1000))
 #define TimestampTzPlusSeconds(tz,s) ((tz) + ((s) * (int64) 1000000))
+#define TimestampTzMinusSeconds(tz,s) ((tz) - ((s) * (int64) 1000000))
 
 
 /* Set at postmaster start */
diff --git a/src/test/regress/expected/conflict_resolver.out b/src/test/regress/expected/conflict_resolver.out
index 53ecb430fa..c21486dbb4 100644
--- a/src/test/regress/expected/conflict_resolver.out
+++ b/src/test/regress/expected/conflict_resolver.out
@@ -1,11 +1,11 @@
 --check default global resolvers in system catalog
 select * from pg_conflict order by conftype;
-    conftype    |    confres    
-----------------+---------------
- delete_differ  | remote_apply
+    conftype    |     confres      
+----------------+------------------
+ delete_differ  | last_update_wins
  delete_missing | skip
- insert_exists  | remote_apply
- update_differ  | remote_apply
+ insert_exists  | last_update_wins
+ update_differ  | last_update_wins
  update_missing | apply_or_skip
 (5 rows)
 
@@ -43,11 +43,11 @@ RESET CONFLICT RESOLVER for 'delete_missing';
 RESET CONFLICT RESOLVER for 'insert_exists';
 --check resolvers are reset to default for delete_missing and insert_exists
 select * from pg_conflict order by conftype;
-    conftype    |    confres     
-----------------+----------------
+    conftype    |     confres      
+----------------+------------------
  delete_differ  | keep_local
  delete_missing | skip
- insert_exists  | remote_apply
+ insert_exists  | last_update_wins
  update_differ  | keep_local
  update_missing | apply_or_error
 (5 rows)
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index 784194903a..15e5a494ba 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -1565,6 +1565,7 @@ LogicalOutputPluginWriterPrepareWrite
 LogicalOutputPluginWriterUpdateProgress
 LogicalOutputPluginWriterWrite
 LogicalRepBeginData
+LogicalRepClockSkewAction
 LogicalRepCommitData
 LogicalRepCommitPreparedTxnData
 LogicalRepCtxStruct
-- 
2.34.1



  [application/octet-stream] v4-0005-Configure-table-level-conflict-resolvers.patch (48.9K, ../../CABdArM47myyKnOU4LB54k3wmgpFu63s2gxmAQVK-DdWzCLKAaw@mail.gmail.com/6-v4-0005-Configure-table-level-conflict-resolvers.patch)
  download | inline diff:
From 2f7f588de7b0a7c028586bc59075e5cdccd3c521 Mon Sep 17 00:00:00 2001
From: Nisha Moond <[email protected]>
Date: Fri, 5 Jul 2024 11:29:45 +0530
Subject: [PATCH v4 5/5] Configure table level conflict resolvers

This patch provides support for configuring table level conflict
resolvers using ALTER TABLE cmd.

Syntax to SET resolvers:
ALTER TABLE <name> SET CONFLICT RESOLVER <resolver1> on <conflict_type1>,
                   SET CONFLICT RESOLVER <resolver2> on <conflict_type2>, ...;

A new catalog table pg_conflict_rel has been created to store
table-level conflict_type and conflict_resolver configurations given by
above DDL command.

Syntax to RESET resolvers:
ALTER TABLE <name> RESET CONFLICT RESOLVER on <conflict_type1>,
                   RESET CONFLICT RESOLVER on <conflict_type2>, ...;

Above RESET command will remove entry for that particular conflict_type for
the given table from pg_conflict_rel catalog table.
---
 src/backend/catalog/dependency.c              |   6 +
 src/backend/catalog/objectaddress.c           |  30 ++
 src/backend/commands/tablecmds.c              |  70 ++++
 src/backend/parser/gram.y                     |  30 ++
 src/backend/replication/logical/conflict.c    | 330 +++++++++++++++++-
 src/include/catalog/Makefile                  |   4 +-
 src/include/catalog/meson.build               |   1 +
 src/include/catalog/pg_conflict.h             |   2 +-
 src/include/catalog/pg_conflict_rel.h         |  58 +++
 src/include/nodes/parsenodes.h                |   2 +
 src/include/replication/conflict.h            |  13 +
 .../regress/expected/conflict_resolver.out    | 245 ++++++++++++-
 src/test/regress/expected/oidjoins.out        |   1 +
 src/test/regress/sql/conflict_resolver.sql    | 161 ++++++++-
 14 files changed, 929 insertions(+), 24 deletions(-)
 create mode 100644 src/include/catalog/pg_conflict_rel.h

diff --git a/src/backend/catalog/dependency.c b/src/backend/catalog/dependency.c
index 0489cbabcb..9dd78d9094 100644
--- a/src/backend/catalog/dependency.c
+++ b/src/backend/catalog/dependency.c
@@ -31,6 +31,7 @@
 #include "catalog/pg_auth_members.h"
 #include "catalog/pg_cast.h"
 #include "catalog/pg_collation.h"
+#include "catalog/pg_conflict_rel.h"
 #include "catalog/pg_constraint.h"
 #include "catalog/pg_conversion.h"
 #include "catalog/pg_database.h"
@@ -79,6 +80,7 @@
 #include "miscadmin.h"
 #include "nodes/nodeFuncs.h"
 #include "parser/parsetree.h"
+#include "replication/conflict.h"
 #include "rewrite/rewriteRemove.h"
 #include "storage/lmgr.h"
 #include "utils/fmgroids.h"
@@ -1444,6 +1446,10 @@ doDeletion(const ObjectAddress *object, int flags)
 			RemovePublicationById(object->objectId);
 			break;
 
+		case ConflictRelRelationId:
+			RemoveTableConflictById(object->objectId);
+			break;
+
 		case CastRelationId:
 		case CollationRelationId:
 		case ConversionRelationId:
diff --git a/src/backend/catalog/objectaddress.c b/src/backend/catalog/objectaddress.c
index 2983b9180f..1ba0f74a2d 100644
--- a/src/backend/catalog/objectaddress.c
+++ b/src/backend/catalog/objectaddress.c
@@ -30,6 +30,7 @@
 #include "catalog/pg_cast.h"
 #include "catalog/pg_collation.h"
 #include "catalog/pg_constraint.h"
+#include "catalog/pg_conflict_rel.h"
 #include "catalog/pg_conversion.h"
 #include "catalog/pg_database.h"
 #include "catalog/pg_default_acl.h"
@@ -3005,6 +3006,35 @@ getObjectDescription(const ObjectAddress *object, bool missing_ok)
 				break;
 			}
 
+		case ConflictRelRelationId:
+			{
+				HeapTuple	confTup;
+				Datum		typeDatum;
+				Datum		resDatum;
+				char	   *contype;
+				char	   *conres;
+
+				confTup = SearchSysCache1(CONFLICTRELOID,
+										  ObjectIdGetDatum(object->objectId));
+				if (!HeapTupleIsValid(confTup))
+				{
+					if (!missing_ok)
+						elog(ERROR, "cache lookup failed for table conflict %u",
+							 object->objectId);
+					break;
+				}
+
+				typeDatum = SysCacheGetAttrNotNull(CONFLICTRELOID, confTup,
+												   Anum_pg_conflict_rel_confrtype);
+				resDatum = SysCacheGetAttrNotNull(CONFLICTRELOID, confTup,
+												  Anum_pg_conflict_rel_confrres);
+				contype = TextDatumGetCString(typeDatum);
+				conres = TextDatumGetCString(resDatum);
+				ReleaseSysCache(confTup);
+				appendStringInfo(&buffer, _("conflict_resolver %s on conflict_type %s"),
+								 conres, contype);
+				break;
+			}
 		case ConstraintRelationId:
 			{
 				HeapTuple	conTup;
diff --git a/src/backend/commands/tablecmds.c b/src/backend/commands/tablecmds.c
index dbfe0d6b1c..2d75297340 100644
--- a/src/backend/commands/tablecmds.c
+++ b/src/backend/commands/tablecmds.c
@@ -83,6 +83,7 @@
 #include "partitioning/partbounds.h"
 #include "partitioning/partdesc.h"
 #include "pgstat.h"
+#include "replication/conflict.h"
 #include "rewrite/rewriteDefine.h"
 #include "rewrite/rewriteHandler.h"
 #include "rewrite/rewriteManip.h"
@@ -662,6 +663,11 @@ static void ATExecSplitPartition(List **wqueue, AlteredTableInfo *tab,
 								 AlterTableUtilityContext *context);
 static void ATExecMergePartitions(List **wqueue, AlteredTableInfo *tab, Relation rel,
 								  PartitionCmd *cmd, AlterTableUtilityContext *context);
+static void ATExecSetConflictResolver(Relation rel, ConflictResolverStmt *stmt,
+									  bool recurse, bool recursing, LOCKMODE lockmode);
+static void
+			ATExecResetConflictResolver(Relation rel, ConflictResolverStmt *stmt,
+										bool recurse, bool recursing, LOCKMODE lockmode);
 
 /* ----------------------------------------------------------------
  *		DefineRelation
@@ -1245,6 +1251,9 @@ DefineRelation(CreateStmt *stmt, char relkind, Oid ownerId,
 		 */
 		CloneForeignKeyConstraints(NULL, parent, rel);
 
+		/* Inherit conflict resolvers configuration from parent. */
+		InheritTableConflictResolvers(rel, parent);
+
 		table_close(parent, NoLock);
 	}
 
@@ -4543,6 +4552,8 @@ AlterTableGetLockLevel(List *cmds)
 			case AT_SetExpression:
 			case AT_DropExpression:
 			case AT_SetCompression:
+			case AT_SetConflictResolver:
+			case AT_ResetConflictResolver:
 				cmd_lockmode = AccessExclusiveLock;
 				break;
 
@@ -5116,6 +5127,15 @@ ATPrepCmd(List **wqueue, Relation rel, AlterTableCmd *cmd,
 			/* No command-specific prep needed */
 			pass = AT_PASS_MISC;
 			break;
+		case AT_ResetConflictResolver:	/* RESET CONFLICT RESOLVER */
+		case AT_SetConflictResolver:	/* SET CONFLICT RESOLVER */
+			ATSimplePermissions(cmd->subtype, rel, ATT_TABLE);
+			/* Recursion occurs during execution phase */
+			/* No command-specific prep needed except saving recurse flag */
+			if (recurse)
+				cmd->recurse = true;
+			pass = AT_PASS_MISC;
+			break;
 		default:				/* oops */
 			elog(ERROR, "unrecognized alter table type: %d",
 				 (int) cmd->subtype);
@@ -5528,6 +5548,14 @@ ATExecCmd(List **wqueue, AlteredTableInfo *tab,
 			ATExecMergePartitions(wqueue, tab, rel, (PartitionCmd *) cmd->def,
 								  context);
 			break;
+		case AT_SetConflictResolver:
+			ATExecSetConflictResolver(rel, (ConflictResolverStmt *) cmd->def,
+									  cmd->recurse, false, lockmode);
+			break;
+		case AT_ResetConflictResolver:
+			ATExecResetConflictResolver(rel, (ConflictResolverStmt *) cmd->def,
+										cmd->recurse, false, lockmode);
+			break;
 		default:				/* oops */
 			elog(ERROR, "unrecognized alter table type: %d",
 				 (int) cmd->subtype);
@@ -6528,6 +6556,10 @@ alter_table_type_to_string(AlterTableType cmdtype)
 			return "ALTER COLUMN ... DROP IDENTITY";
 		case AT_ReAddStatistics:
 			return NULL;		/* not real grammar */
+		case AT_SetConflictResolver:
+			return "SET CONFLICT RESOLVER";
+		case AT_ResetConflictResolver:
+			return "RESET CONFLICT RESOLVER";
 	}
 
 	return NULL;
@@ -15650,6 +15682,13 @@ CreateInheritance(Relation child_rel, Relation parent_rel, bool ispartition)
 	/* Match up the constraints and bump coninhcount as needed */
 	MergeConstraintsIntoExisting(child_rel, parent_rel);
 
+	/*
+	 * Inherit resolvers configuration from parent if not explicitly set for
+	 * child partition.
+	 */
+	if (ispartition)
+		InheritTableConflictResolvers(child_rel, parent_rel);
+
 	/*
 	 * OK, it looks valid.  Make the catalog entries that show inheritance.
 	 */
@@ -16238,6 +16277,10 @@ RemoveInheritance(Relation child_rel, Relation parent_rel, bool expect_detached)
 	systable_endscan(scan);
 	table_close(catalogRelation, RowExclusiveLock);
 
+	/* Find inherited conflict resolvers and disinherit them */
+	if (is_partitioning)
+		ResetResolversInheritance(child_rel);
+
 	drop_parent_dependency(RelationGetRelid(child_rel),
 						   RelationRelationId,
 						   RelationGetRelid(parent_rel),
@@ -20766,3 +20809,30 @@ ATExecMergePartitions(List **wqueue, AlteredTableInfo *tab, Relation rel,
 	/* Keep the lock until commit. */
 	table_close(newPartRel, NoLock);
 }
+
+/*
+ * ALTER TABLE <name> SET CONFLICT RESOLVER ...
+ */
+static void
+ATExecSetConflictResolver(Relation rel, ConflictResolverStmt *stmt,
+						  bool recurse, bool recursing, LOCKMODE lockmode)
+{
+	ValidateConflictTypeAndResolver(stmt->conflict_type, stmt->conflict_resolver, false);
+
+	SetTableConflictResolver(NULL, rel, stmt->conflict_type,
+							 stmt->conflict_resolver,
+							 recurse, recursing, lockmode);
+}
+
+/*
+ * ALTER TABLE <name> RESET CONFLICT RESOLVER ...
+ */
+static void
+ATExecResetConflictResolver(Relation rel, ConflictResolverStmt *stmt,
+							bool recurse, bool recursing, LOCKMODE lockmode)
+{
+	ValidateConflictTypeAndResolver(stmt->conflict_type, stmt->conflict_resolver, true);
+
+	ResetTableConflictResolver(rel, stmt->conflict_type,
+							   recurse, recursing, lockmode);
+}
diff --git a/src/backend/parser/gram.y b/src/backend/parser/gram.y
index 42726fe3a6..628b9d10e2 100644
--- a/src/backend/parser/gram.y
+++ b/src/backend/parser/gram.y
@@ -3015,6 +3015,36 @@ alter_table_cmd:
 
 					n->subtype = AT_GenericOptions;
 					n->def = (Node *) $1;
+					$$ = (Node *) n;
+				}
+			/*
+			 * ALTER TABLE <name> SET CONFLICT RESOLVER <conflict_resolver>
+			 *		on <conflict_type>
+			 */
+			| SET CONFLICT RESOLVER conflict_resolver ON conflict_type
+				{
+					AlterTableCmd *n = makeNode(AlterTableCmd);
+					ConflictResolverStmt *c = makeNode(ConflictResolverStmt);
+
+					c->conflict_resolver = $4;
+					c->conflict_type = $6;
+
+					n->subtype = AT_SetConflictResolver;
+					n->def = (Node *) c;
+
+					$$ = (Node *) n;
+				}
+			/* ALTER TABLE <name> RESET CONFLICT RESOLVER on <conflict_type> */
+			| RESET CONFLICT RESOLVER ON conflict_type
+				{
+					AlterTableCmd *n = makeNode(AlterTableCmd);
+					ConflictResolverStmt *c = makeNode(ConflictResolverStmt);
+
+					c->conflict_type = $5;
+
+					n->subtype = AT_ResetConflictResolver;
+					n->def = (Node *) c;
+
 					$$ = (Node *) n;
 				}
 		;
diff --git a/src/backend/replication/logical/conflict.c b/src/backend/replication/logical/conflict.c
index 4934099cc8..0b4f0e25a9 100644
--- a/src/backend/replication/logical/conflict.c
+++ b/src/backend/replication/logical/conflict.c
@@ -19,8 +19,11 @@
 #include "access/htup_details.h"
 #include "access/skey.h"
 #include "access/table.h"
+#include "catalog/dependency.h"
 #include "catalog/indexing.h"
 #include "catalog/pg_conflict.h"
+#include "catalog/pg_conflict_rel.h"
+#include "catalog/pg_inherits.h"
 #include "executor/executor.h"
 #include "replication/conflict.h"
 #include "replication/logicalproto.h"
@@ -28,8 +31,10 @@
 #include "replication/origin.h"
 #include "utils/builtins.h"
 #include "utils/fmgroids.h"
+#include "utils/inval.h"
 #include "utils/lsyscache.h"
 #include "utils/rel.h"
+#include "utils/syscache.h"
 #include "utils/timestamp.h"
 #include "utils/syscache.h"
 
@@ -294,9 +299,9 @@ build_index_value_desc(Oid indexoid, TupleTableSlot *conflictslot)
  *
  * Return ConflictType enum value corresponding to given conflict_type.
  */
-static ConflictType
-validate_conflict_type_and_resolver(char *conflict_type, char *conflict_resolver,
-									bool isReset)
+ConflictType
+ValidateConflictTypeAndResolver(char *conflict_type, char *conflict_resolver,
+								bool isReset)
 {
 	ConflictType type;
 	ConflictResolver resolver;
@@ -499,10 +504,9 @@ ExecConflictResolverStmt(ConflictResolverStmt *stmt)
 	HeapTuple	newtup = NULL;
 	ConflictType type;
 
-	type = validate_conflict_type_and_resolver(stmt->conflict_type,
-											   stmt->conflict_resolver,
-											   stmt->isReset);
-
+	type = ValidateConflictTypeAndResolver(stmt->conflict_type,
+										   stmt->conflict_resolver,
+										   stmt->isReset);
 
 	/* Prepare to update a tuple in pg_conflict system catalog */
 	memset(values, 0, sizeof(values));
@@ -530,7 +534,7 @@ ExecConflictResolverStmt(ConflictResolverStmt *stmt)
 				BTEqualStrategyNumber, F_TEXTEQ,
 				values[Anum_pg_conflict_conftype - 1]);
 
-	pg_conflict = table_open(ConflictResRelationId, RowExclusiveLock);
+	pg_conflict = table_open(ConflictRelationId, RowExclusiveLock);
 
 	scan = systable_beginscan(pg_conflict, ConflictTypeIndexId, true,
 							  NULL, 1, keys);
@@ -619,3 +623,313 @@ GetConflictResolver(TupleTableSlot *localslot, Relation localrel,
 
 	return resolver;
 }
+
+/*
+ * Update the table level conflict resolver for a conflict_type in
+ * pg_conflict_rel system catalog.
+ */
+void
+SetTableConflictResolver(Relation pg_conf_rel, Relation rel, char *conflict_type, char *conflict_resolver,
+						 bool recurse, bool recursing, LOCKMODE lockmode)
+{
+	Relation	pg_conflict_rel;
+	Datum		values[Natts_pg_conflict_rel];
+	bool		nulls[Natts_pg_conflict_rel];
+	bool		replaces[Natts_pg_conflict_rel];
+	HeapTuple	oldtup;
+	HeapTuple	newtup = NULL;
+	Oid			relid = rel->rd_id;
+
+	/* Prepare to update a tuple. */
+	memset(nulls, false, sizeof(nulls));
+	memset(replaces, false, sizeof(replaces));
+
+	if (!pg_conf_rel)
+		pg_conflict_rel = table_open(ConflictRelRelationId, RowExclusiveLock);
+	else
+		pg_conflict_rel = pg_conf_rel;
+
+	values[Anum_pg_conflict_rel_confrrelid - 1] = ObjectIdGetDatum(relid);
+	values[Anum_pg_conflict_rel_confrtype - 1] = CStringGetTextDatum(conflict_type);
+	values[Anum_pg_conflict_rel_confrres - 1] = CStringGetTextDatum(conflict_resolver);
+	values[Anum_pg_conflict_rel_confrinherited - 1] = BoolGetDatum(recursing);
+
+	oldtup = SearchSysCache2(CONFLICTRELTYPE,
+							 values[Anum_pg_conflict_rel_confrrelid - 1],
+							 values[Anum_pg_conflict_rel_confrtype - 1]);
+	if (HeapTupleIsValid(oldtup))
+	{
+		Form_pg_conflict_rel confForm = (Form_pg_conflict_rel) GETSTRUCT(oldtup);
+
+		/*
+		 * Update resolver for recursing=false cases.
+		 *
+		 * recursing=true indicates it is a child parittion table and if it
+		 * already has a resolver set then overwrite it only if it is an
+		 * inherited resolver. We should not overwrite non-inherited resolvers
+		 * for child partition tables during recursion.
+		 */
+		if (!recursing || (recursing && confForm->confrinherited))
+		{
+			replaces[Anum_pg_conflict_rel_confrres - 1] = true;
+			replaces[Anum_pg_conflict_rel_confrinherited - 1] = !recursing;
+
+			newtup = heap_modify_tuple(oldtup, RelationGetDescr(pg_conflict_rel),
+									   values, nulls, replaces);
+			CatalogTupleUpdate(pg_conflict_rel, &oldtup->t_self, newtup);
+		}
+		else
+		{
+			/*
+			 * If we did not update resolver for this child table, do not
+			 * update for child's child tables as well.
+			 */
+			recurse = false;
+		}
+
+		ReleaseSysCache(oldtup);
+	}
+	/* If we didn't find an old tuple, insert a new one */
+	else
+	{
+		ObjectAddress myself,
+					referenced;
+		Oid			conflict_oid;
+
+		conflict_oid = GetNewOidWithIndex(pg_conflict_rel, ConflictRelOidIndexId,
+										  Anum_pg_conflict_rel_oid);
+		values[Anum_pg_conflict_rel_oid - 1] = ObjectIdGetDatum(conflict_oid);
+
+		newtup = heap_form_tuple(RelationGetDescr(pg_conflict_rel),
+								 values, nulls);
+		CatalogTupleInsert(pg_conflict_rel, newtup);
+
+		/* Add dependency on the relation */
+		ObjectAddressSet(myself, ConflictRelRelationId, conflict_oid);
+		ObjectAddressSet(referenced, RelationRelationId, relid);
+		recordDependencyOn(&myself, &referenced, DEPENDENCY_AUTO);
+	}
+
+	if (HeapTupleIsValid(newtup))
+		heap_freetuple(newtup);
+
+	if (!pg_conf_rel)
+		table_close(pg_conflict_rel, RowExclusiveLock);
+
+	if (recurse && (rel->rd_rel->relkind == RELKIND_PARTITIONED_TABLE))
+	{
+		List	   *children;
+		ListCell   *lc;
+
+		children =
+			find_inheritance_children(RelationGetRelid(rel), lockmode);
+
+		foreach(lc, children)
+		{
+			Relation	childrel;
+
+			/* find_inheritance_children already got lock */
+			childrel = table_open(lfirst_oid(lc), NoLock);
+			SetTableConflictResolver(NULL, childrel, conflict_type, conflict_resolver, recurse, true, lockmode);
+			table_close(childrel, NoLock);
+		}
+	}
+}
+
+/*
+ * Reset table level conflict_type configuration.
+ *
+ * Removes table's resolver configuration for given conflict_type from
+ * pg_conflict_rel system catalog.
+ */
+void
+ResetTableConflictResolver(Relation rel, char *conflict_type,
+						   bool recurse, bool recursing, LOCKMODE lockmode)
+{
+	Oid			relid = rel->rd_id;
+	HeapTuple	tup;
+	ObjectAddress confobj;
+	Form_pg_conflict_rel confForm;
+
+	tup = SearchSysCache2(CONFLICTRELTYPE,
+						  ObjectIdGetDatum(relid),
+						  CStringGetTextDatum(conflict_type));
+
+	/* Nothing to reset */
+	if (!HeapTupleIsValid(tup))
+		return;
+
+	confForm = (Form_pg_conflict_rel) GETSTRUCT(tup);
+
+	if (confForm->confrinherited && !recursing)
+		ereport(ERROR,
+				(errcode(ERRCODE_INVALID_TABLE_DEFINITION),
+				 errmsg("cannot reset inherited resolver for conflict type \"%s\" of relation \"%s\"",
+						conflict_type, RelationGetRelationName(rel))));
+
+	/*
+	 * While resetting resolver on parent table, reset resolver for child
+	 * partition table only if it is inherited one.
+	 *
+	 * OTOH, if user has invoked RESET directly on child partition table,
+	 * ensure  we reset only non-inherited resolvers. Inherited resolvers can
+	 * not be reset alone on child table, RESET has to come through parent
+	 * table.
+	 */
+	if ((recursing && confForm->confrinherited) ||
+		(!recursing && !confForm->confrinherited))
+	{
+		ObjectAddressSet(confobj, ConflictRelRelationId, confForm->oid);
+		performDeletion(&confobj, DROP_CASCADE, 0);
+	}
+	else
+	{
+		/*
+		 * If we did not reset resolver for this child table, do not reset for
+		 * child's child tables as well.
+		 */
+		recurse = false;
+	}
+
+	ReleaseSysCache(tup);
+
+	if (recurse && (rel->rd_rel->relkind == RELKIND_PARTITIONED_TABLE))
+	{
+		List	   *children;
+		ListCell   *lc;
+
+		children =
+			find_inheritance_children(RelationGetRelid(rel), lockmode);
+
+		foreach(lc, children)
+		{
+			Relation	childrel;
+
+			/* find_inheritance_children already got lock */
+			childrel = table_open(lfirst_oid(lc), NoLock);
+			ResetTableConflictResolver(childrel, conflict_type, recurse, true, lockmode);
+			table_close(childrel, NoLock);
+		}
+	}
+}
+
+/*
+ * Inherit conflict resolvers from parent paritioned table.
+ *
+ * If child partition table has resolvers set already for some conflict
+ * types, do not overwrite those, inherit rest from parent.
+ *
+ * Used during attach partition operation.
+ */
+void
+InheritTableConflictResolvers(Relation child_rel, Relation parent_rel)
+{
+	Relation	pg_conflict_rel;
+	SysScanDesc parent_scan;
+	ScanKeyData parent_key;
+	HeapTuple	parent_tuple;
+	Oid			parent_relid = RelationGetRelid(parent_rel);
+
+	Assert(parent_rel->rd_rel->relkind == RELKIND_PARTITIONED_TABLE);
+
+	pg_conflict_rel = table_open(ConflictRelRelationId, RowExclusiveLock);
+
+	ScanKeyInit(&parent_key,
+				Anum_pg_conflict_rel_confrrelid,
+				BTEqualStrategyNumber, F_OIDEQ,
+				ObjectIdGetDatum(parent_relid));
+
+	parent_scan = systable_beginscan(pg_conflict_rel, InvalidOid, false, NULL, 1, &parent_key);
+
+	while (HeapTupleIsValid(parent_tuple = systable_getnext(parent_scan)))
+	{
+		Datum		typeDatum;
+		Datum		resDatum;
+		char	   *parent_conftype;
+		char	   *parent_confres;
+
+		typeDatum = SysCacheGetAttrNotNull(CONFLICTRELOID, parent_tuple,
+										   Anum_pg_conflict_rel_confrtype);
+		parent_conftype = TextDatumGetCString(typeDatum);
+
+		resDatum = SysCacheGetAttrNotNull(CONFLICTRELOID, parent_tuple,
+										  Anum_pg_conflict_rel_confrres);
+		parent_confres = TextDatumGetCString(resDatum);
+
+		SetTableConflictResolver(pg_conflict_rel, child_rel, parent_conftype, parent_confres, true, true, AccessExclusiveLock);
+	}
+
+	systable_endscan(parent_scan);
+	table_close(pg_conflict_rel, RowExclusiveLock);
+}
+
+/*
+ * Reset inheritance of conflict resolvers.
+ *
+ * Used during detach partition operation. Detach partition
+ * will not remove inherited resolvers but will mark them
+ * as non inherited.
+ */
+void
+ResetResolversInheritance(Relation rel)
+{
+	Relation	pg_conflict_rel;
+	SysScanDesc scan;
+	ScanKeyData key;
+	HeapTuple	tuple;
+	Oid			relid = RelationGetRelid(rel);
+
+	Assert(rel->rd_rel->relispartition);
+
+	pg_conflict_rel = table_open(ConflictRelRelationId, RowExclusiveLock);
+
+	ScanKeyInit(&key,
+				Anum_pg_conflict_rel_confrrelid,
+				BTEqualStrategyNumber, F_OIDEQ,
+				ObjectIdGetDatum(relid));
+
+	scan = systable_beginscan(pg_conflict_rel, InvalidOid, false, NULL, 1, &key);
+
+	while (HeapTupleIsValid(tuple = systable_getnext(scan)))
+	{
+		Form_pg_conflict_rel conf =
+			(Form_pg_conflict_rel) GETSTRUCT(tuple);
+
+		if (conf->confrinherited)
+		{
+			HeapTuple	copy_tuple = heap_copytuple(tuple);
+			Form_pg_conflict_rel copy_conf =
+				(Form_pg_conflict_rel) GETSTRUCT(copy_tuple);
+
+			copy_conf->confrinherited = false;
+			CatalogTupleUpdate(pg_conflict_rel, &copy_tuple->t_self, copy_tuple);
+			heap_freetuple(copy_tuple);
+
+		}
+	}
+
+	systable_endscan(scan);
+	table_close(pg_conflict_rel, RowExclusiveLock);
+}
+
+/*
+ * Remove the conflict resolver configuration by table conflict oid.
+ */
+void
+RemoveTableConflictById(Oid confid)
+{
+	Relation	rel;
+	HeapTuple	tup;
+
+	rel = table_open(ConflictRelRelationId, RowExclusiveLock);
+
+	tup = SearchSysCache1(CONFLICTRELOID, ObjectIdGetDatum(confid));
+	if (!HeapTupleIsValid(tup))
+		elog(ERROR, "cache lookup failed for table conflict %u", confid);
+
+	CatalogTupleDelete(rel, &tup->t_self);
+
+	ReleaseSysCache(tup);
+
+	table_close(rel, RowExclusiveLock);
+}
diff --git a/src/include/catalog/Makefile b/src/include/catalog/Makefile
index 8619d73e5a..e192375fa0 100644
--- a/src/include/catalog/Makefile
+++ b/src/include/catalog/Makefile
@@ -82,7 +82,9 @@ CATALOG_HEADERS := \
 	pg_publication_rel.h \
 	pg_subscription.h \
 	pg_subscription_rel.h \
-	pg_conflict.h
+	pg_conflict.h \
+	pg_conflict_rel.h
+
 
 GENERATED_HEADERS := $(CATALOG_HEADERS:%.h=%_d.h)
 
diff --git a/src/include/catalog/meson.build b/src/include/catalog/meson.build
index 4d6732a303..28924f5df8 100644
--- a/src/include/catalog/meson.build
+++ b/src/include/catalog/meson.build
@@ -70,6 +70,7 @@ catalog_headers = [
   'pg_subscription.h',
   'pg_subscription_rel.h',
   'pg_conflict.h',
+  'pg_conflict_rel.h',
 ]
 
 # The .dat files we need can just be listed alphabetically.
diff --git a/src/include/catalog/pg_conflict.h b/src/include/catalog/pg_conflict.h
index e3fe3e6d30..c080a0d0be 100644
--- a/src/include/catalog/pg_conflict.h
+++ b/src/include/catalog/pg_conflict.h
@@ -26,7 +26,7 @@
  *		typedef struct FormData_pg_conflict
  * ----------------
  */
-CATALOG(pg_conflict,8688,ConflictResRelationId)
+CATALOG(pg_conflict,8688,ConflictRelationId)
 {
 #ifdef CATALOG_VARLEN			/* variable-length fields start here */
 	text		conftype BKI_FORCE_NOT_NULL;	/* conflict type */
diff --git a/src/include/catalog/pg_conflict_rel.h b/src/include/catalog/pg_conflict_rel.h
new file mode 100644
index 0000000000..636398baf1
--- /dev/null
+++ b/src/include/catalog/pg_conflict_rel.h
@@ -0,0 +1,58 @@
+/* -------------------------------------------------------------------------
+ *
+ * pg_conflict_rel.h
+ *	  definition of the "table level conflict detection" system
+ *        catalog (pg_conflict_rel)
+ *
+ * Portions Copyright (c) 1996-2024, PostgreSQL Global Development Group
+ * Portions Copyright (c) 1994, Regents of the University of California
+ *
+ * src/include/catalog/pg_conflict_rel.h
+ *
+ * NOTES
+ *	  The Catalog.pm module reads this file and derives schema
+ *	  information.
+ *
+ * -------------------------------------------------------------------------
+ */
+#ifndef PG_CONFLICT_REL_H
+#define PG_CONFLICT_REL_H
+
+#include "catalog/genbki.h"
+#include "catalog/pg_conflict_rel_d.h"
+
+/* ----------------
+ *		pg_conflict_rel definition.  cpp turns this into
+ *		typedef struct FormData_pg_conflict_rel
+ * ----------------
+ */
+CATALOG(pg_conflict_rel,8881,ConflictRelRelationId)
+{
+	Oid			oid;			/* OID of the object itself */
+	Oid			confrrelid BKI_LOOKUP(pg_class);	/* Oid of the relation
+													 * having resolver */
+	bool		confrinherited; /* Is this an inherited configuration */
+
+#ifdef CATALOG_VARLEN			/* variable-length fields start here */
+	text		confrtype BKI_FORCE_NOT_NULL;	/* conflict type */
+	text		confrres BKI_FORCE_NOT_NULL;	/* conflict resolver */
+#endif
+} FormData_pg_conflict_rel;
+
+/* ----------------
+ *		Form_pg_conflict_rel corresponds to a pointer to a row with
+ *		the format of pg_conflict_rel relation.
+ * ----------------
+ */
+typedef FormData_pg_conflict_rel * Form_pg_conflict_rel;
+
+DECLARE_TOAST(pg_conflict_rel, 8882, 8883);
+
+DECLARE_UNIQUE_INDEX_PKEY(pg_conflict_rel_oid_index, 8884, ConflictRelOidIndexId, pg_conflict_rel, btree(oid oid_ops));
+
+DECLARE_UNIQUE_INDEX(pg_conflict_rel_type_index, 8885, ConflictRelTypeIndexId, pg_conflict_rel, btree(confrrelid oid_ops, confrtype text_ops));
+
+MAKE_SYSCACHE(CONFLICTRELOID, pg_conflict_rel_oid_index, 256);
+MAKE_SYSCACHE(CONFLICTRELTYPE, pg_conflict_rel_type_index, 256);
+
+#endif							/* PG_CONFLICT_REL_H */
diff --git a/src/include/nodes/parsenodes.h b/src/include/nodes/parsenodes.h
index 1d41169d5e..7677cf023b 100644
--- a/src/include/nodes/parsenodes.h
+++ b/src/include/nodes/parsenodes.h
@@ -2419,6 +2419,8 @@ typedef enum AlterTableType
 	AT_SetIdentity,				/* SET identity column options */
 	AT_DropIdentity,			/* DROP IDENTITY */
 	AT_ReAddStatistics,			/* internal to commands/tablecmds.c */
+	AT_SetConflictResolver,		/* SET CONFLICT RESOLVER */
+	AT_ResetConflictResolver,	/* RESET CONFLICT RESOLVER */
 } AlterTableType;
 
 typedef struct ReplicaIdentityStmt
diff --git a/src/include/replication/conflict.h b/src/include/replication/conflict.h
index d38a22ddde..3ba83a25cd 100644
--- a/src/include/replication/conflict.h
+++ b/src/include/replication/conflict.h
@@ -96,4 +96,17 @@ extern ConflictResolver GetConflictResolver(TupleTableSlot *localslot,
 											TimestampTz committs);
 extern bool CanCreateFullTuple(Relation localrel,
 							   LogicalRepTupleData *newtup);
+
+extern ConflictType ValidateConflictTypeAndResolver(char *conflict_type,
+													char *conflict_resolver,
+													bool isReset);
+extern void SetTableConflictResolver(Relation pg_conf_rel, Relation rel, char *conflict_type,
+									 char *conflict_resolver, bool recurse,
+									 bool recursing, LOCKMODE lockmode);
+extern void ResetTableConflictResolver(Relation rel, char *conflict_type,
+									   bool recurse, bool recursing, LOCKMODE lockmode);
+extern void RemoveTableConflictById(Oid confid);
+extern void InheritTableConflictResolvers(Relation child_rel, Relation parent_rel);
+extern void ResetResolversInheritance(Relation rel);
+
 #endif
diff --git a/src/test/regress/expected/conflict_resolver.out b/src/test/regress/expected/conflict_resolver.out
index c21486dbb4..802a7583d4 100644
--- a/src/test/regress/expected/conflict_resolver.out
+++ b/src/test/regress/expected/conflict_resolver.out
@@ -1,5 +1,8 @@
+--
+-- Test for configuration of global resolvers
+--
 --check default global resolvers in system catalog
-select * from pg_conflict order by conftype;
+SELECT * FROM pg_conflict order by conftype;
     conftype    |     confres      
 ----------------+------------------
  delete_differ  | last_update_wins
@@ -9,9 +12,7 @@ select * from pg_conflict order by conftype;
  update_missing | apply_or_skip
 (5 rows)
 
---
 -- Test of SET/RESET CONFLICT RESOLVER with invalid names
---
 SET CONFLICT RESOLVER 'keep_local' for 'aaaa'; -- fail
 ERROR:  aaaa is not a valid conflict type
 SET CONFLICT RESOLVER 'bbbbb' for 'delete_missing'; -- fail
@@ -20,16 +21,14 @@ SET CONFLICT RESOLVER 'remote_apply' for 'delete_missing'; -- fail
 ERROR:  remote_apply is not a valid conflict resolver for conflict type delete_missing
 RESET CONFLICT RESOLVER for 'ct'; -- fail
 ERROR:  ct is not a valid conflict type
---
 -- Test of SET/RESET CONFLICT RESOLVER with valid names
---
 SET CONFLICT RESOLVER 'error' for 'delete_missing';
 SET CONFLICT RESOLVER 'keep_local' for 'insert_exists';
 SET CONFLICT RESOLVER 'keep_local' for 'update_differ';
 SET CONFLICT RESOLVER 'apply_or_error' for 'update_missing';
 SET CONFLICT RESOLVER 'keep_local' for 'delete_differ';
 --check new resolvers are saved
-select * from pg_conflict order by conftype;
+SELECT * FROM pg_conflict order by conftype;
     conftype    |    confres     
 ----------------+----------------
  delete_differ  | keep_local
@@ -42,7 +41,7 @@ select * from pg_conflict order by conftype;
 RESET CONFLICT RESOLVER for 'delete_missing';
 RESET CONFLICT RESOLVER for 'insert_exists';
 --check resolvers are reset to default for delete_missing and insert_exists
-select * from pg_conflict order by conftype;
+SELECT * FROM pg_conflict order by conftype;
     conftype    |     confres      
 ----------------+------------------
  delete_differ  | keep_local
@@ -52,3 +51,235 @@ select * from pg_conflict order by conftype;
  update_missing | apply_or_error
 (5 rows)
 
+--
+-- Test for configuration of table level resolvers
+--
+-- Test for ALTER TABLE..SET/RESET CONFLICT RESOLVER
+CREATE TABLE ptntable (
+    city_id         int not null,
+    logdate         date not null,
+    peaktemp        int,
+    unitsales       int
+) PARTITION BY RANGE (logdate);
+CREATE TABLE ptntable_1 PARTITION OF ptntable
+    FOR VALUES FROM ('2006-02-01') TO ('2006-03-01');
+CREATE TABLE ptntable_2 PARTITION OF ptntable
+    FOR VALUES FROM ('2006-03-01') TO ('2006-04-01')
+    PARTITION BY RANGE (logdate);
+CREATE TABLE ptntable_2_1 PARTITION OF ptntable_2
+    FOR VALUES FROM ('2006-03-20') TO ('2006-04-01');
+ALTER TABLE ptntable SET CONFLICT RESOLVER 'error' ON 'delete_missing',
+                     SET CONFLICT RESOLVER 'keep_local' ON 'insert_exists';
+--Expect 8 entries. 2 for parent and 2 for each child partition (inherited
+--resolvers)
+SELECT relname, confrtype, confrres, confrinherited FROM pg_class pc,
+  (SELECT confrrelid, confrtype, confrres, confrinherited FROM pg_conflict_rel)conf
+  WHERE conf.confrrelid= pc.oid order by relname, confrtype;
+   relname    |   confrtype    |  confrres  | confrinherited 
+--------------+----------------+------------+----------------
+ ptntable     | delete_missing | error      | f
+ ptntable     | insert_exists  | keep_local | f
+ ptntable_1   | delete_missing | error      | t
+ ptntable_1   | insert_exists  | keep_local | t
+ ptntable_2   | delete_missing | error      | t
+ ptntable_2   | insert_exists  | keep_local | t
+ ptntable_2_1 | delete_missing | error      | t
+ ptntable_2_1 | insert_exists  | keep_local | t
+(8 rows)
+
+ALTER TABLE ptntable_2 SET CONFLICT RESOLVER 'skip' ON 'delete_missing',
+                       SET CONFLICT RESOLVER 'remote_apply' ON 'update_differ';
+--For both ptntable_2 and ptntable_2_1, expect:
+--The resolver for 'delete_missing' changed from 'error' to 'skip'
+--The 'update_differ'configuration added
+SELECT relname, confrtype, confrres, confrinherited FROM pg_class pc,
+  (SELECT confrrelid, confrtype, confrres, confrinherited FROM pg_conflict_rel)conf
+  WHERE conf.confrrelid= pc.oid order by relname, confrtype;
+   relname    |   confrtype    |   confrres   | confrinherited 
+--------------+----------------+--------------+----------------
+ ptntable     | delete_missing | error        | f
+ ptntable     | insert_exists  | keep_local   | f
+ ptntable_1   | delete_missing | error        | t
+ ptntable_1   | insert_exists  | keep_local   | t
+ ptntable_2   | delete_missing | skip         | f
+ ptntable_2   | insert_exists  | keep_local   | t
+ ptntable_2   | update_differ  | remote_apply | f
+ ptntable_2_1 | delete_missing | skip         | t
+ ptntable_2_1 | insert_exists  | keep_local   | t
+ ptntable_2_1 | update_differ  | remote_apply | t
+(10 rows)
+
+--Set resolvers on parent table again. It should not overwrite non inherited
+--entries for ptntable_2 and corresponding entries for ptntable_2_1
+ALTER TABLE ptntable SET CONFLICT RESOLVER 'error' ON 'delete_missing',
+                     SET CONFLICT RESOLVER 'remote_apply' ON 'insert_exists';
+SELECT relname, confrtype, confrres, confrinherited FROM pg_class pc,
+  (SELECT confrrelid, confrtype, confrres, confrinherited FROM pg_conflict_rel)conf
+  WHERE conf.confrrelid= pc.oid order by relname, confrtype;
+   relname    |   confrtype    |   confrres   | confrinherited 
+--------------+----------------+--------------+----------------
+ ptntable     | delete_missing | error        | f
+ ptntable     | insert_exists  | remote_apply | f
+ ptntable_1   | delete_missing | error        | t
+ ptntable_1   | insert_exists  | remote_apply | t
+ ptntable_2   | delete_missing | skip         | f
+ ptntable_2   | insert_exists  | remote_apply | t
+ ptntable_2   | update_differ  | remote_apply | f
+ ptntable_2_1 | delete_missing | skip         | t
+ ptntable_2_1 | insert_exists  | remote_apply | t
+ ptntable_2_1 | update_differ  | remote_apply | t
+(10 rows)
+
+--Reset of inherited entry ON child alone should result in error
+ALTER TABLE ptntable_2 RESET CONFLICT RESOLVER ON 'insert_exists';
+ERROR:  cannot reset inherited resolver for conflict type "insert_exists" of relation "ptntable_2"
+--Reset of non-inherited entry ON child alone should suceed
+ALTER TABLE ptntable_2 RESET CONFLICT RESOLVER ON 'update_differ';
+SELECT relname, confrtype, confrres, confrinherited FROM pg_class pc,
+  (SELECT confrrelid, confrtype, confrres, confrinherited FROM pg_conflict_rel)conf
+  WHERE conf.confrrelid= pc.oid order by relname, confrtype;
+   relname    |   confrtype    |   confrres   | confrinherited 
+--------------+----------------+--------------+----------------
+ ptntable     | delete_missing | error        | f
+ ptntable     | insert_exists  | remote_apply | f
+ ptntable_1   | delete_missing | error        | t
+ ptntable_1   | insert_exists  | remote_apply | t
+ ptntable_2   | delete_missing | skip         | f
+ ptntable_2   | insert_exists  | remote_apply | t
+ ptntable_2_1 | delete_missing | skip         | t
+ ptntable_2_1 | insert_exists  | remote_apply | t
+(8 rows)
+
+DROP TABLE ptntable_2;
+--Expect entries removed for both ptntable_2 and its child ptntable_2_1
+SELECT relname, confrtype, confrres, confrinherited FROM pg_class pc,
+  (SELECT confrrelid, confrtype, confrres, confrinherited FROM pg_conflict_rel)conf
+  WHERE conf.confrrelid= pc.oid order by relname, confrtype;
+  relname   |   confrtype    |   confrres   | confrinherited 
+------------+----------------+--------------+----------------
+ ptntable   | delete_missing | error        | f
+ ptntable   | insert_exists  | remote_apply | f
+ ptntable_1 | delete_missing | error        | t
+ ptntable_1 | insert_exists  | remote_apply | t
+(4 rows)
+
+-- Test for ALTER TABLE..SPLIT PARTITION and ALTER TABLE..MERGE PARTITIONS
+ALTER TABLE ptntable SPLIT PARTITION ptntable_1 INTO
+   (PARTITION ptntable_1_1 FOR VALUES FROM ('2006-02-01') TO ('2006-02-10'),
+    PARTITION ptntable_1_10 FOR VALUES FROM ('2006-02-10') TO ('2006-02-20'),
+    PARTITION ptntable_1_20 FOR VALUES FROM ('2006-02-20') TO ('2006-03-01'));
+--Expect split partitions to inherit resolvers FROM parent
+SELECT relname, confrtype, confrres, confrinherited FROM pg_class pc,
+  (SELECT confrrelid, confrtype, confrres, confrinherited FROM pg_conflict_rel)conf
+  WHERE conf.confrrelid= pc.oid order by relname, confrtype;
+    relname    |   confrtype    |   confrres   | confrinherited 
+---------------+----------------+--------------+----------------
+ ptntable      | delete_missing | error        | f
+ ptntable      | insert_exists  | remote_apply | f
+ ptntable_1_1  | delete_missing | error        | t
+ ptntable_1_1  | insert_exists  | remote_apply | t
+ ptntable_1_10 | delete_missing | error        | t
+ ptntable_1_10 | insert_exists  | remote_apply | t
+ ptntable_1_20 | delete_missing | error        | t
+ ptntable_1_20 | insert_exists  | remote_apply | t
+(8 rows)
+
+ALTER TABLE ptntable MERGE PARTITIONS (ptntable_1_1, ptntable_1_10, ptntable_1_20)
+    INTO ptntable_1;
+--Expect merged partition to inherit resolvers FROM parent
+SELECT relname, confrtype, confrres, confrinherited FROM pg_class pc,
+  (SELECT confrrelid, confrtype, confrres, confrinherited FROM pg_conflict_rel)conf
+  WHERE conf.confrrelid= pc.oid order by relname, confrtype;
+  relname   |   confrtype    |   confrres   | confrinherited 
+------------+----------------+--------------+----------------
+ ptntable   | delete_missing | error        | f
+ ptntable   | insert_exists  | remote_apply | f
+ ptntable_1 | delete_missing | error        | t
+ ptntable_1 | insert_exists  | remote_apply | t
+(4 rows)
+
+-- Test for ALTER TABLE..ATTACH PARTITION and CREATE TABLE..PARTITION OF
+CREATE TABLE ptntable_2(
+    city_id         int not null,
+    logdate         date not null,
+    peaktemp        int,
+    unitsales       int
+) PARTITION BY RANGE (logdate);
+ALTER TABLE ptntable_2 SET CONFLICT RESOLVER 'remote_apply' ON 'update_differ',
+		       SET CONFLICT RESOLVER 'skip' ON 'delete_missing';
+--Expect ptntable_2_1 to inherit resolvers of  ptntable_2
+CREATE TABLE ptntable_2_1 PARTITION OF ptntable_2
+    FOR VALUES FROM ('2006-03-20') TO ('2006-04-01');
+--Expect 4 new entries for ptntable_2 and its child ptntable_2_1
+--Entried for ptntable_2_1 should be marked as inherited.
+SELECT relname, confrtype, confrres, confrinherited FROM pg_class pc,
+  (SELECT confrrelid, confrtype, confrres, confrinherited FROM pg_conflict_rel)conf
+  WHERE conf.confrrelid= pc.oid order by relname, confrtype;
+   relname    |   confrtype    |   confrres   | confrinherited 
+--------------+----------------+--------------+----------------
+ ptntable     | delete_missing | error        | f
+ ptntable     | insert_exists  | remote_apply | f
+ ptntable_1   | delete_missing | error        | t
+ ptntable_1   | insert_exists  | remote_apply | t
+ ptntable_2   | delete_missing | skip         | f
+ ptntable_2   | update_differ  | remote_apply | f
+ ptntable_2_1 | delete_missing | skip         | t
+ ptntable_2_1 | update_differ  | remote_apply | t
+(8 rows)
+
+--Attach ptntable_2 to ptntable now
+ALTER TABLE ptntable ATTACH PARTITION ptntable_2
+      FOR VALUES FROM ('2006-03-01') TO ('2006-04-01');
+--For both ptntable_2 and ptntable_2_1, expect:
+--The 'insert_exists' configuration inherited
+--Resolver for 'delete_missing' not overwritten
+--Resolver for 'update_differ' retained.
+SELECT relname, confrtype, confrres, confrinherited FROM pg_class pc,
+  (SELECT confrrelid, confrtype, confrres, confrinherited FROM pg_conflict_rel)conf
+  WHERE conf.confrrelid= pc.oid order by relname, confrtype;
+   relname    |   confrtype    |   confrres   | confrinherited 
+--------------+----------------+--------------+----------------
+ ptntable     | delete_missing | error        | f
+ ptntable     | insert_exists  | remote_apply | f
+ ptntable_1   | delete_missing | error        | t
+ ptntable_1   | insert_exists  | remote_apply | t
+ ptntable_2   | delete_missing | skip         | f
+ ptntable_2   | insert_exists  | remote_apply | t
+ ptntable_2   | update_differ  | remote_apply | f
+ ptntable_2_1 | delete_missing | skip         | t
+ ptntable_2_1 | insert_exists  | remote_apply | t
+ ptntable_2_1 | update_differ  | remote_apply | t
+(10 rows)
+
+-- Test for ALTER TABLE..DETACH PARTITION
+ALTER TABLE ptntable DETACH PARTITION ptntable_2;
+--All resolvers of ptntable_2 should be marked as non-inherited
+--All resolvers for ptntable_2_1's should still be marked as inherited (as
+--they are still inherited from ptntable_2)
+SELECT relname, confrtype, confrres, confrinherited FROM pg_class pc,
+  (SELECT confrrelid, confrtype, confrres, confrinherited FROM pg_conflict_rel)conf
+  WHERE conf.confrrelid= pc.oid order by relname, confrtype;
+   relname    |   confrtype    |   confrres   | confrinherited 
+--------------+----------------+--------------+----------------
+ ptntable     | delete_missing | error        | f
+ ptntable     | insert_exists  | remote_apply | f
+ ptntable_1   | delete_missing | error        | t
+ ptntable_1   | insert_exists  | remote_apply | t
+ ptntable_2   | delete_missing | skip         | f
+ ptntable_2   | insert_exists  | remote_apply | f
+ ptntable_2   | update_differ  | remote_apply | f
+ ptntable_2_1 | delete_missing | skip         | t
+ ptntable_2_1 | insert_exists  | remote_apply | t
+ ptntable_2_1 | update_differ  | remote_apply | t
+(10 rows)
+
+DROP TABLE ptntable_2;
+DROP TABLE ptntable;
+--Expect no resolvers
+SELECT relname, confrtype, confrres, confrinherited FROM pg_class pc,
+  (SELECT confrrelid, confrtype, confrres, confrinherited FROM pg_conflict_rel)conf
+  WHERE conf.confrrelid= pc.oid order by relname, confrtype;
+ relname | confrtype | confrres | confrinherited 
+---------+-----------+----------+----------------
+(0 rows)
+
diff --git a/src/test/regress/expected/oidjoins.out b/src/test/regress/expected/oidjoins.out
index 215eb899be..8caf852600 100644
--- a/src/test/regress/expected/oidjoins.out
+++ b/src/test/regress/expected/oidjoins.out
@@ -266,3 +266,4 @@ NOTICE:  checking pg_subscription {subdbid} => pg_database {oid}
 NOTICE:  checking pg_subscription {subowner} => pg_authid {oid}
 NOTICE:  checking pg_subscription_rel {srsubid} => pg_subscription {oid}
 NOTICE:  checking pg_subscription_rel {srrelid} => pg_class {oid}
+NOTICE:  checking pg_conflict_rel {confrrelid} => pg_class {oid}
diff --git a/src/test/regress/sql/conflict_resolver.sql b/src/test/regress/sql/conflict_resolver.sql
index f83d14b229..b4574d1df4 100644
--- a/src/test/regress/sql/conflict_resolver.sql
+++ b/src/test/regress/sql/conflict_resolver.sql
@@ -1,17 +1,19 @@
+--
+-- Test for configuration of global resolvers
+--
+
 --check default global resolvers in system catalog
-select * from pg_conflict order by conftype;
+SELECT * FROM pg_conflict order by conftype;
 
---
 -- Test of SET/RESET CONFLICT RESOLVER with invalid names
---
+
 SET CONFLICT RESOLVER 'keep_local' for 'aaaa'; -- fail
 SET CONFLICT RESOLVER 'bbbbb' for 'delete_missing'; -- fail
 SET CONFLICT RESOLVER 'remote_apply' for 'delete_missing'; -- fail
 RESET CONFLICT RESOLVER for 'ct'; -- fail
 
---
 -- Test of SET/RESET CONFLICT RESOLVER with valid names
---
+
 SET CONFLICT RESOLVER 'error' for 'delete_missing';
 SET CONFLICT RESOLVER 'keep_local' for 'insert_exists';
 SET CONFLICT RESOLVER 'keep_local' for 'update_differ';
@@ -19,10 +21,155 @@ SET CONFLICT RESOLVER 'apply_or_error' for 'update_missing';
 SET CONFLICT RESOLVER 'keep_local' for 'delete_differ';
 
 --check new resolvers are saved
-select * from pg_conflict order by conftype;
+SELECT * FROM pg_conflict order by conftype;
 
 RESET CONFLICT RESOLVER for 'delete_missing';
 RESET CONFLICT RESOLVER for 'insert_exists';
 
 --check resolvers are reset to default for delete_missing and insert_exists
-select * from pg_conflict order by conftype;
+SELECT * FROM pg_conflict order by conftype;
+
+--
+-- Test for configuration of table level resolvers
+--
+
+
+-- Test for ALTER TABLE..SET/RESET CONFLICT RESOLVER
+
+CREATE TABLE ptntable (
+    city_id         int not null,
+    logdate         date not null,
+    peaktemp        int,
+    unitsales       int
+) PARTITION BY RANGE (logdate);
+
+CREATE TABLE ptntable_1 PARTITION OF ptntable
+    FOR VALUES FROM ('2006-02-01') TO ('2006-03-01');
+
+CREATE TABLE ptntable_2 PARTITION OF ptntable
+    FOR VALUES FROM ('2006-03-01') TO ('2006-04-01')
+    PARTITION BY RANGE (logdate);
+
+CREATE TABLE ptntable_2_1 PARTITION OF ptntable_2
+    FOR VALUES FROM ('2006-03-20') TO ('2006-04-01');
+
+ALTER TABLE ptntable SET CONFLICT RESOLVER 'error' ON 'delete_missing',
+                     SET CONFLICT RESOLVER 'keep_local' ON 'insert_exists';
+
+--Expect 8 entries. 2 for parent and 2 for each child partition (inherited
+--resolvers)
+SELECT relname, confrtype, confrres, confrinherited FROM pg_class pc,
+  (SELECT confrrelid, confrtype, confrres, confrinherited FROM pg_conflict_rel)conf
+  WHERE conf.confrrelid= pc.oid order by relname, confrtype;
+
+ALTER TABLE ptntable_2 SET CONFLICT RESOLVER 'skip' ON 'delete_missing',
+                       SET CONFLICT RESOLVER 'remote_apply' ON 'update_differ';
+
+--For both ptntable_2 and ptntable_2_1, expect:
+--The resolver for 'delete_missing' changed from 'error' to 'skip'
+--The 'update_differ'configuration added
+SELECT relname, confrtype, confrres, confrinherited FROM pg_class pc,
+  (SELECT confrrelid, confrtype, confrres, confrinherited FROM pg_conflict_rel)conf
+  WHERE conf.confrrelid= pc.oid order by relname, confrtype;
+
+--Set resolvers on parent table again. It should not overwrite non inherited
+--entries for ptntable_2 and corresponding entries for ptntable_2_1
+ALTER TABLE ptntable SET CONFLICT RESOLVER 'error' ON 'delete_missing',
+                     SET CONFLICT RESOLVER 'remote_apply' ON 'insert_exists';
+
+SELECT relname, confrtype, confrres, confrinherited FROM pg_class pc,
+  (SELECT confrrelid, confrtype, confrres, confrinherited FROM pg_conflict_rel)conf
+  WHERE conf.confrrelid= pc.oid order by relname, confrtype;
+
+--Reset of inherited entry ON child alone should result in error
+ALTER TABLE ptntable_2 RESET CONFLICT RESOLVER ON 'insert_exists';
+
+--Reset of non-inherited entry ON child alone should suceed
+ALTER TABLE ptntable_2 RESET CONFLICT RESOLVER ON 'update_differ';
+
+SELECT relname, confrtype, confrres, confrinherited FROM pg_class pc,
+  (SELECT confrrelid, confrtype, confrres, confrinherited FROM pg_conflict_rel)conf
+  WHERE conf.confrrelid= pc.oid order by relname, confrtype;
+
+DROP TABLE ptntable_2;
+
+--Expect entries removed for both ptntable_2 and its child ptntable_2_1
+SELECT relname, confrtype, confrres, confrinherited FROM pg_class pc,
+  (SELECT confrrelid, confrtype, confrres, confrinherited FROM pg_conflict_rel)conf
+  WHERE conf.confrrelid= pc.oid order by relname, confrtype;
+
+
+-- Test for ALTER TABLE..SPLIT PARTITION and ALTER TABLE..MERGE PARTITIONS
+
+ALTER TABLE ptntable SPLIT PARTITION ptntable_1 INTO
+   (PARTITION ptntable_1_1 FOR VALUES FROM ('2006-02-01') TO ('2006-02-10'),
+    PARTITION ptntable_1_10 FOR VALUES FROM ('2006-02-10') TO ('2006-02-20'),
+    PARTITION ptntable_1_20 FOR VALUES FROM ('2006-02-20') TO ('2006-03-01'));
+
+--Expect split partitions to inherit resolvers FROM parent
+SELECT relname, confrtype, confrres, confrinherited FROM pg_class pc,
+  (SELECT confrrelid, confrtype, confrres, confrinherited FROM pg_conflict_rel)conf
+  WHERE conf.confrrelid= pc.oid order by relname, confrtype;
+
+ALTER TABLE ptntable MERGE PARTITIONS (ptntable_1_1, ptntable_1_10, ptntable_1_20)
+    INTO ptntable_1;
+
+--Expect merged partition to inherit resolvers FROM parent
+SELECT relname, confrtype, confrres, confrinherited FROM pg_class pc,
+  (SELECT confrrelid, confrtype, confrres, confrinherited FROM pg_conflict_rel)conf
+  WHERE conf.confrrelid= pc.oid order by relname, confrtype;
+
+
+-- Test for ALTER TABLE..ATTACH PARTITION and CREATE TABLE..PARTITION OF
+
+CREATE TABLE ptntable_2(
+    city_id         int not null,
+    logdate         date not null,
+    peaktemp        int,
+    unitsales       int
+) PARTITION BY RANGE (logdate);
+
+ALTER TABLE ptntable_2 SET CONFLICT RESOLVER 'remote_apply' ON 'update_differ',
+		       SET CONFLICT RESOLVER 'skip' ON 'delete_missing';
+
+--Expect ptntable_2_1 to inherit resolvers of  ptntable_2
+CREATE TABLE ptntable_2_1 PARTITION OF ptntable_2
+    FOR VALUES FROM ('2006-03-20') TO ('2006-04-01');
+
+--Expect 4 new entries for ptntable_2 and its child ptntable_2_1
+--Entried for ptntable_2_1 should be marked as inherited.
+SELECT relname, confrtype, confrres, confrinherited FROM pg_class pc,
+  (SELECT confrrelid, confrtype, confrres, confrinherited FROM pg_conflict_rel)conf
+  WHERE conf.confrrelid= pc.oid order by relname, confrtype;
+
+--Attach ptntable_2 to ptntable now
+ALTER TABLE ptntable ATTACH PARTITION ptntable_2
+      FOR VALUES FROM ('2006-03-01') TO ('2006-04-01');
+
+--For both ptntable_2 and ptntable_2_1, expect:
+--The 'insert_exists' configuration inherited
+--Resolver for 'delete_missing' not overwritten
+--Resolver for 'update_differ' retained.
+SELECT relname, confrtype, confrres, confrinherited FROM pg_class pc,
+  (SELECT confrrelid, confrtype, confrres, confrinherited FROM pg_conflict_rel)conf
+  WHERE conf.confrrelid= pc.oid order by relname, confrtype;
+
+
+-- Test for ALTER TABLE..DETACH PARTITION
+
+ALTER TABLE ptntable DETACH PARTITION ptntable_2;
+
+--All resolvers of ptntable_2 should be marked as non-inherited
+--All resolvers for ptntable_2_1's should still be marked as inherited (as
+--they are still inherited from ptntable_2)
+SELECT relname, confrtype, confrres, confrinherited FROM pg_class pc,
+  (SELECT confrrelid, confrtype, confrres, confrinherited FROM pg_conflict_rel)conf
+  WHERE conf.confrrelid= pc.oid order by relname, confrtype;
+
+DROP TABLE ptntable_2;
+DROP TABLE ptntable;
+
+--Expect no resolvers
+SELECT relname, confrtype, confrres, confrinherited FROM pg_class pc,
+  (SELECT confrrelid, confrtype, confrres, confrinherited FROM pg_conflict_rel)conf
+  WHERE conf.confrrelid= pc.oid order by relname, confrtype;
-- 
2.34.1



^ permalink  raw  reply  [nested|flat] 101+ messages in thread

* Re: Conflict Detection and Resolution
@ 2024-07-05 08:53  Amit Kapila <[email protected]>
  parent: Dilip Kumar <[email protected]>
  1 sibling, 1 reply; 101+ messages in thread

From: Amit Kapila @ 2024-07-05 08:53 UTC (permalink / raw)
  To: Dilip Kumar <[email protected]>; +Cc: shveta malik <[email protected]>; Tomas Vondra <[email protected]>; pgsql-hackers; Zhijie Hou (Fujitsu) <[email protected]>; Nisha Moond <[email protected]>

On Fri, Jul 5, 2024 at 11:58 AM Dilip Kumar <[email protected]> wrote:
>
> On Thu, Jul 4, 2024 at 5:37 PM Amit Kapila <[email protected]> wrote:
> > >  So, the situation will be the same. We can even
> > > > decide to spill the data to files if the decision is that we need to
> > > > wait to avoid network buffer-fill situations. But note that the wait
> > > > in apply worker has consequences that the subscriber won't be able to
> > > > confirm the flush position and publisher won't be able to vacuum the
> > > > dead rows and we won't be remove WAL as well. Last time when we
> > > > discussed the delay_apply feature, we decided not to proceed because
> > > > of such issues. This is the reason I proposed a cap on wait time.
> > >
> > > Yes, spilling to file or cap on the wait time should help, and as I
> > > said above maybe a parallel apply worker can also help.
> > >
> >
> > It is not clear to me how a parallel apply worker can help in this
> > case. Can you elaborate on what you have in mind?
>
> If we decide to wait at commit time, and before starting to apply if
> we already see a remote commit_ts clock is ahead, then if we apply
> such transactions using the parallel worker, wouldn't it solve the
> issue of the network buffer congestion? Now the apply worker can move
> ahead and fetch new transactions from the buffer as our waiting
> transaction will not block it.  I understand that if this transaction
> is going to wait at commit then any future transaction that we are
> going to fetch might also going to wait again because if the previous
> transaction committed before is in the future then the subsequent
> transaction committed after this must also be in future so eventually
> that will also go to some another parallel worker and soon we end up
> consuming all the parallel worker if the clock skew is large.  So I
> won't say this will resolve the problem and we would still have to
> fall back to the spilling to the disk but that's just in the worst
> case when the clock skew is really huge.  In most cases which is due
> to slight clock drift by the time we apply the medium to large size
> transaction, the local clock should be able to catch up the remote
> commit_ts and we might not have to wait in most of the cases.
>

Yeah, this is possible but even if go with the spilling logic at first
it should work for all cases. If we get some complaints then we can
explore executing such transactions by parallel apply workers.
Personally, I am of the opinion that clock synchronization should be
handled outside the database system via network time protocols like
NTP. Still, we can have some simple solution to inform users about the
clock_skew.

-- 
With Regards,
Amit Kapila.






^ permalink  raw  reply  [nested|flat] 101+ messages in thread

* Re: Conflict Detection and Resolution
@ 2024-07-05 11:41  Dilip Kumar <[email protected]>
  parent: Amit Kapila <[email protected]>
  0 siblings, 0 replies; 101+ messages in thread

From: Dilip Kumar @ 2024-07-05 11:41 UTC (permalink / raw)
  To: Amit Kapila <[email protected]>; +Cc: shveta malik <[email protected]>; Tomas Vondra <[email protected]>; pgsql-hackers; Zhijie Hou (Fujitsu) <[email protected]>; Nisha Moond <[email protected]>

On Fri, Jul 5, 2024 at 2:23 PM Amit Kapila <[email protected]> wrote:
>
> On Fri, Jul 5, 2024 at 11:58 AM Dilip Kumar <[email protected]> wrote:
> >
> > On Thu, Jul 4, 2024 at 5:37 PM Amit Kapila <[email protected]> wrote:
> > > >  So, the situation will be the same. We can even
> > > > > decide to spill the data to files if the decision is that we need to
> > > > > wait to avoid network buffer-fill situations. But note that the wait
> > > > > in apply worker has consequences that the subscriber won't be able to
> > > > > confirm the flush position and publisher won't be able to vacuum the
> > > > > dead rows and we won't be remove WAL as well. Last time when we
> > > > > discussed the delay_apply feature, we decided not to proceed because
> > > > > of such issues. This is the reason I proposed a cap on wait time.
> > > >
> > > > Yes, spilling to file or cap on the wait time should help, and as I
> > > > said above maybe a parallel apply worker can also help.
> > > >
> > >
> > > It is not clear to me how a parallel apply worker can help in this
> > > case. Can you elaborate on what you have in mind?
> >
> > If we decide to wait at commit time, and before starting to apply if
> > we already see a remote commit_ts clock is ahead, then if we apply
> > such transactions using the parallel worker, wouldn't it solve the
> > issue of the network buffer congestion? Now the apply worker can move
> > ahead and fetch new transactions from the buffer as our waiting
> > transaction will not block it.  I understand that if this transaction
> > is going to wait at commit then any future transaction that we are
> > going to fetch might also going to wait again because if the previous
> > transaction committed before is in the future then the subsequent
> > transaction committed after this must also be in future so eventually
> > that will also go to some another parallel worker and soon we end up
> > consuming all the parallel worker if the clock skew is large.  So I
> > won't say this will resolve the problem and we would still have to
> > fall back to the spilling to the disk but that's just in the worst
> > case when the clock skew is really huge.  In most cases which is due
> > to slight clock drift by the time we apply the medium to large size
> > transaction, the local clock should be able to catch up the remote
> > commit_ts and we might not have to wait in most of the cases.
> >
>
> Yeah, this is possible but even if go with the spilling logic at first
> it should work for all cases. If we get some complaints then we can
> explore executing such transactions by parallel apply workers.
> Personally, I am of the opinion that clock synchronization should be
> handled outside the database system via network time protocols like
> NTP. Still, we can have some simple solution to inform users about the
> clock_skew.

Yeah, that makes sense, in the first version we can have a simple
solution and we can further improvise it based on the feedback.

-- 
Regards,
Dilip Kumar
EnterpriseDB: http://www.enterprisedb.com






^ permalink  raw  reply  [nested|flat] 101+ messages in thread

* [PATCH v39 5/8] Add Incremental View Maintenance support to psql
@ 2026-05-29 09:05  Yugo Nagata <[email protected]>
  0 siblings, 0 replies; 101+ messages in thread

From: Yugo Nagata @ 2026-05-29 09:05 UTC (permalink / raw)

Add tab completion and meta-command output for IVM.
---
 src/bin/psql/describe.c        | 32 +++++++++++++++++++++++++++++++-
 src/bin/psql/tab-complete.in.c | 30 ++++++++++++++++++------------
 2 files changed, 49 insertions(+), 13 deletions(-)

diff --git a/src/bin/psql/describe.c b/src/bin/psql/describe.c
index fef86b4cca3..5b7bf626c32 100644
--- a/src/bin/psql/describe.c
+++ b/src/bin/psql/describe.c
@@ -1580,6 +1580,7 @@ describeOneTableDetails(const char *schemaname,
 		char		relpersistence;
 		char		relreplident;
 		char	   *relam;
+		bool		isivm;
 	}			tableinfo;
 	bool		show_column_details = false;
 
@@ -1594,7 +1595,26 @@ describeOneTableDetails(const char *schemaname,
 	/* Get general table info */
 	printfPQExpBuffer(&buf, "/* %s */\n",
 					  _("Get general information about one relation"));
-	if (pset.sversion >= 120000)
+	if (pset.sversion >= 200000)
+	{
+		printfPQExpBuffer(&buf,
+						  "SELECT c.relchecks, c.relkind, c.relhasindex, c.relhasrules, "
+						  "c.relhastriggers, c.relrowsecurity, c.relforcerowsecurity, "
+						  "false AS relhasoids, c.relispartition, %s, c.reltablespace, "
+						  "CASE WHEN c.reloftype = 0 THEN '' ELSE c.reloftype::pg_catalog.regtype::pg_catalog.text END, "
+						  "c.relpersistence, c.relreplident, am.amname, "
+						  "c.relisivm\n"
+						  "FROM pg_catalog.pg_class c\n "
+						  "LEFT JOIN pg_catalog.pg_class tc ON (c.reltoastrelid = tc.oid)\n"
+						  "LEFT JOIN pg_catalog.pg_am am ON (c.relam = am.oid)\n"
+						  "WHERE c.oid = '%s';",
+						  (verbose ?
+						   "pg_catalog.array_to_string(c.reloptions || "
+						   "array(select 'toast.' || x from pg_catalog.unnest(tc.reloptions) x), ', ')\n"
+						   : "''"),
+						  oid);
+	}
+	else if (pset.sversion >= 120000)
 	{
 		appendPQExpBuffer(&buf,
 						  "SELECT c.relchecks, c.relkind, c.relhasindex, c.relhasrules, "
@@ -1662,6 +1682,10 @@ describeOneTableDetails(const char *schemaname,
 			NULL : pg_strdup(PQgetvalue(res, 0, 14));
 	else
 		tableinfo.relam = NULL;
+	if (pset.sversion >= 200000)
+		tableinfo.isivm = strcmp(PQgetvalue(res, 0, 15), "t") == 0;
+	else
+		tableinfo.isivm = false;
 	PQclear(res);
 	res = NULL;
 
@@ -3670,6 +3694,12 @@ describeOneTableDetails(const char *schemaname,
 			printfPQExpBuffer(&buf, _("Access method: %s"), tableinfo.relam);
 			printTableAddFooter(&cont, buf.data);
 		}
+
+		/* Incremental view maintance info */
+		if (verbose && tableinfo.relkind == RELKIND_MATVIEW && tableinfo.isivm)
+		{
+			printTableAddFooter(&cont, _("Incremental view maintenance: yes"));
+		}
 	}
 
 	/* reloptions, if verbose */
diff --git a/src/bin/psql/tab-complete.in.c b/src/bin/psql/tab-complete.in.c
index e4bc2c93145..6dfad8a8102 100644
--- a/src/bin/psql/tab-complete.in.c
+++ b/src/bin/psql/tab-complete.in.c
@@ -1320,6 +1320,7 @@ static const pgsql_thing_t words_after_create[] = {
 	{"FOREIGN TABLE", NULL, NULL, NULL},
 	{"FUNCTION", NULL, NULL, Query_for_list_of_functions},
 	{"GROUP", Query_for_list_of_roles},
+	{"INCREMENTAL MATERIALIZED VIEW", NULL, NULL, &Query_for_list_of_matviews, NULL, THING_NO_DROP | THING_NO_ALTER},
 	{"INDEX", NULL, NULL, &Query_for_list_of_indexes},
 	{"LANGUAGE", Query_for_list_of_languages},
 	{"LARGE OBJECT", NULL, NULL, NULL, NULL, THING_NO_CREATE | THING_NO_DROP},
@@ -4242,28 +4243,33 @@ match_previous_words(int pattern_id,
 		COMPLETE_WITH("SELECT");
 
 /* CREATE MATERIALIZED VIEW */
-	else if (Matches("CREATE", "MATERIALIZED"))
+	else if (Matches("CREATE", "MATERIALIZED") ||
+			 Matches("CREATE", "INCREMENTAL", "MATERIALIZED"))
 		COMPLETE_WITH("VIEW");
-	/* Complete CREATE MATERIALIZED VIEW <name> with AS or USING */
-	else if (Matches("CREATE", "MATERIALIZED", "VIEW", MatchAny))
-		COMPLETE_WITH("AS", "USING");
 
+	/* Complete CREATE [INCREMENTAL] MATERIALIZED VIEW <name> with AS or USING */
+	else if (Matches("CREATE", "MATERIALIZED", "VIEW", MatchAny) ||
+			 Matches("CREATE", "INCREMENTAL", "MATERIALIZED", "VIEW", MatchAny))
+		COMPLETE_WITH("AS", "USING");
 	/*
-	 * Complete CREATE MATERIALIZED VIEW <name> USING with list of access
-	 * methods
+	 * Complete CREATE [INCREMENTAL] MATERIALIZED VIEW <name> USING with list
+	 * of access methods
 	 */
-	else if (Matches("CREATE", "MATERIALIZED", "VIEW", MatchAny, "USING"))
+	else if (Matches("CREATE", "MATERIALIZED", "VIEW", MatchAny, "USING") ||
+			 Matches("CREATE", "INCREMENTAL", "MATERIALIZED", "VIEW", MatchAny, "USING"))
 		COMPLETE_WITH_QUERY(Query_for_list_of_table_access_methods);
-	/* Complete CREATE MATERIALIZED VIEW <name> USING <access method> with AS */
-	else if (Matches("CREATE", "MATERIALIZED", "VIEW", MatchAny, "USING", MatchAny))
+	/* Complete CREATE [INCREMENTAL] MATERIALIZED VIEW <name> USING <am> with AS */
+	else if (Matches("CREATE", "MATERIALIZED", "VIEW", MatchAny, "USING", MatchAny) ||
+			 Matches("CREATE", "INCREMENTAL", "MATERIALIZED", "VIEW", MatchAny, "USING", MatchAny))
 		COMPLETE_WITH("AS");
-
 	/*
-	 * Complete CREATE MATERIALIZED VIEW <name> [USING <access method> ] AS
+	 * Complete CREATE [INCREMENTAL] MATERIALIZED VIEW <name> [USING <am>] AS
 	 * with "SELECT"
 	 */
 	else if (Matches("CREATE", "MATERIALIZED", "VIEW", MatchAny, "AS") ||
-			 Matches("CREATE", "MATERIALIZED", "VIEW", MatchAny, "USING", MatchAny, "AS"))
+			 Matches("CREATE", "MATERIALIZED", "VIEW", MatchAny, "USING", MatchAny, "AS") ||
+			 Matches("CREATE", "INCREMENTAL", "MATERIALIZED", "VIEW", MatchAny, "AS") ||
+			 Matches("CREATE", "INCREMENTAL", "MATERIALIZED", "VIEW", MatchAny, "USING", MatchAny, "AS"))
 		COMPLETE_WITH("SELECT");
 
 /* CREATE EVENT TRIGGER */
-- 
2.43.0


--Multipart=_Fri__3_Jul_2026_19_11_16_+0900_CskxSIu_iGcDMEyM
Content-Type: text/x-diff;
 name="v39-0004-Add-Incremental-View-Maintenance-support-to-pg_d.patch"
Content-Disposition: attachment;
 filename="v39-0004-Add-Incremental-View-Maintenance-support-to-pg_d.patch"
Content-Transfer-Encoding: 7bit



^ permalink  raw  reply  [nested|flat] 101+ messages in thread

* [PATCH v37 05/11] Add Incremental View Maintenance support to psql
@ 2026-05-29 09:05  Yugo Nagata <[email protected]>
  0 siblings, 0 replies; 101+ messages in thread

From: Yugo Nagata @ 2026-05-29 09:05 UTC (permalink / raw)

Add tab completion and meta-command output for IVM.
---
 src/bin/psql/describe.c        | 32 +++++++++++++++++++++++++++++++-
 src/bin/psql/tab-complete.in.c | 30 ++++++++++++++++++------------
 2 files changed, 49 insertions(+), 13 deletions(-)

diff --git a/src/bin/psql/describe.c b/src/bin/psql/describe.c
index e1449654f96..2321f66d871 100644
--- a/src/bin/psql/describe.c
+++ b/src/bin/psql/describe.c
@@ -1634,6 +1634,7 @@ describeOneTableDetails(const char *schemaname,
 		char		relpersistence;
 		char		relreplident;
 		char	   *relam;
+		bool		isivm;
 	}			tableinfo;
 	bool		show_column_details = false;
 
@@ -1648,7 +1649,26 @@ describeOneTableDetails(const char *schemaname,
 	/* Get general table info */
 	printfPQExpBuffer(&buf, "/* %s */\n",
 					  _("Get general information about one relation"));
-	if (pset.sversion >= 120000)
+	if (pset.sversion >= 200000)
+	{
+		printfPQExpBuffer(&buf,
+						  "SELECT c.relchecks, c.relkind, c.relhasindex, c.relhasrules, "
+						  "c.relhastriggers, c.relrowsecurity, c.relforcerowsecurity, "
+						  "false AS relhasoids, c.relispartition, %s, c.reltablespace, "
+						  "CASE WHEN c.reloftype = 0 THEN '' ELSE c.reloftype::pg_catalog.regtype::pg_catalog.text END, "
+						  "c.relpersistence, c.relreplident, am.amname, "
+						  "c.relisivm\n"
+						  "FROM pg_catalog.pg_class c\n "
+						  "LEFT JOIN pg_catalog.pg_class tc ON (c.reltoastrelid = tc.oid)\n"
+						  "LEFT JOIN pg_catalog.pg_am am ON (c.relam = am.oid)\n"
+						  "WHERE c.oid = '%s';",
+						  (verbose ?
+						   "pg_catalog.array_to_string(c.reloptions || "
+						   "array(select 'toast.' || x from pg_catalog.unnest(tc.reloptions) x), ', ')\n"
+						   : "''"),
+						  oid);
+	}
+	else if (pset.sversion >= 120000)
 	{
 		appendPQExpBuffer(&buf,
 						  "SELECT c.relchecks, c.relkind, c.relhasindex, c.relhasrules, "
@@ -1768,6 +1788,10 @@ describeOneTableDetails(const char *schemaname,
 			NULL : pg_strdup(PQgetvalue(res, 0, 14));
 	else
 		tableinfo.relam = NULL;
+	if (pset.sversion >= 200000)
+		tableinfo.isivm = strcmp(PQgetvalue(res, 0, 15), "t") == 0;
+	else
+		tableinfo.isivm = false;
 	PQclear(res);
 	res = NULL;
 
@@ -3830,6 +3854,12 @@ describeOneTableDetails(const char *schemaname,
 			printfPQExpBuffer(&buf, _("Access method: %s"), tableinfo.relam);
 			printTableAddFooter(&cont, buf.data);
 		}
+
+		/* Incremental view maintance info */
+		if (verbose && tableinfo.relkind == RELKIND_MATVIEW && tableinfo.isivm)
+		{
+			printTableAddFooter(&cont, _("Incremental view maintenance: yes"));
+		}
 	}
 
 	/* reloptions, if verbose */
diff --git a/src/bin/psql/tab-complete.in.c b/src/bin/psql/tab-complete.in.c
index de547a8cb37..590e33833f2 100644
--- a/src/bin/psql/tab-complete.in.c
+++ b/src/bin/psql/tab-complete.in.c
@@ -1334,6 +1334,7 @@ static const pgsql_thing_t words_after_create[] = {
 	{"FOREIGN TABLE", NULL, NULL, NULL},
 	{"FUNCTION", NULL, NULL, Query_for_list_of_functions},
 	{"GROUP", Query_for_list_of_roles},
+	{"INCREMENTAL MATERIALIZED VIEW", NULL, NULL, &Query_for_list_of_matviews, NULL, THING_NO_DROP | THING_NO_ALTER},
 	{"INDEX", NULL, NULL, &Query_for_list_of_indexes},
 	{"LANGUAGE", Query_for_list_of_languages},
 	{"LARGE OBJECT", NULL, NULL, NULL, NULL, THING_NO_CREATE | THING_NO_DROP},
@@ -4254,28 +4255,33 @@ match_previous_words(int pattern_id,
 		COMPLETE_WITH("SELECT");
 
 /* CREATE MATERIALIZED VIEW */
-	else if (Matches("CREATE", "MATERIALIZED"))
+	else if (Matches("CREATE", "MATERIALIZED") ||
+			 Matches("CREATE", "INCREMENTAL", "MATERIALIZED"))
 		COMPLETE_WITH("VIEW");
-	/* Complete CREATE MATERIALIZED VIEW <name> with AS or USING */
-	else if (Matches("CREATE", "MATERIALIZED", "VIEW", MatchAny))
-		COMPLETE_WITH("AS", "USING");
 
+	/* Complete CREATE [INCREMENTAL] MATERIALIZED VIEW <name> with AS or USING */
+	else if (Matches("CREATE", "MATERIALIZED", "VIEW", MatchAny) ||
+			 Matches("CREATE", "INCREMENTAL", "MATERIALIZED", "VIEW", MatchAny))
+		COMPLETE_WITH("AS", "USING");
 	/*
-	 * Complete CREATE MATERIALIZED VIEW <name> USING with list of access
-	 * methods
+	 * Complete CREATE [INCREMENTAL] MATERIALIZED VIEW <name> USING with list
+	 * of access methods
 	 */
-	else if (Matches("CREATE", "MATERIALIZED", "VIEW", MatchAny, "USING"))
+	else if (Matches("CREATE", "MATERIALIZED", "VIEW", MatchAny, "USING") ||
+			 Matches("CREATE", "INCREMENTAL", "MATERIALIZED", "VIEW", MatchAny, "USING"))
 		COMPLETE_WITH_QUERY(Query_for_list_of_table_access_methods);
-	/* Complete CREATE MATERIALIZED VIEW <name> USING <access method> with AS */
-	else if (Matches("CREATE", "MATERIALIZED", "VIEW", MatchAny, "USING", MatchAny))
+	/* Complete CREATE [INCREMENTAL] MATERIALIZED VIEW <name> USING <am> with AS */
+	else if (Matches("CREATE", "MATERIALIZED", "VIEW", MatchAny, "USING", MatchAny) ||
+			 Matches("CREATE", "INCREMENTAL", "MATERIALIZED", "VIEW", MatchAny, "USING", MatchAny))
 		COMPLETE_WITH("AS");
-
 	/*
-	 * Complete CREATE MATERIALIZED VIEW <name> [USING <access method> ] AS
+	 * Complete CREATE [INCREMENTAL] MATERIALIZED VIEW <name> [USING <am>] AS
 	 * with "SELECT"
 	 */
 	else if (Matches("CREATE", "MATERIALIZED", "VIEW", MatchAny, "AS") ||
-			 Matches("CREATE", "MATERIALIZED", "VIEW", MatchAny, "USING", MatchAny, "AS"))
+			 Matches("CREATE", "MATERIALIZED", "VIEW", MatchAny, "USING", MatchAny, "AS") ||
+			 Matches("CREATE", "INCREMENTAL", "MATERIALIZED", "VIEW", MatchAny, "AS") ||
+			 Matches("CREATE", "INCREMENTAL", "MATERIALIZED", "VIEW", MatchAny, "USING", MatchAny, "AS"))
 		COMPLETE_WITH("SELECT");
 
 /* CREATE EVENT TRIGGER */
-- 
2.43.0


--Multipart=_Fri__29_May_2026_23_14_17_+0900_Te0o73X2VqYK57Gd
Content-Type: text/x-diff;
 name="v37-0004-Add-Incremental-View-Maintenance-support-to-pg_d.patch"
Content-Disposition: attachment;
 filename="v37-0004-Add-Incremental-View-Maintenance-support-to-pg_d.patch"
Content-Transfer-Encoding: 7bit



^ permalink  raw  reply  [nested|flat] 101+ messages in thread

* [PATCH v38 05/11] Add Incremental View Maintenance support to psql
@ 2026-05-29 09:05  Yugo Nagata <[email protected]>
  0 siblings, 0 replies; 101+ messages in thread

From: Yugo Nagata @ 2026-05-29 09:05 UTC (permalink / raw)

Add tab completion and meta-command output for IVM.
---
 src/bin/psql/describe.c        | 32 +++++++++++++++++++++++++++++++-
 src/bin/psql/tab-complete.in.c | 30 ++++++++++++++++++------------
 2 files changed, 49 insertions(+), 13 deletions(-)

diff --git a/src/bin/psql/describe.c b/src/bin/psql/describe.c
index af3935b0078..ad5c8274af0 100644
--- a/src/bin/psql/describe.c
+++ b/src/bin/psql/describe.c
@@ -1634,6 +1634,7 @@ describeOneTableDetails(const char *schemaname,
 		char		relpersistence;
 		char		relreplident;
 		char	   *relam;
+		bool		isivm;
 	}			tableinfo;
 	bool		show_column_details = false;
 
@@ -1648,7 +1649,26 @@ describeOneTableDetails(const char *schemaname,
 	/* Get general table info */
 	printfPQExpBuffer(&buf, "/* %s */\n",
 					  _("Get general information about one relation"));
-	if (pset.sversion >= 120000)
+	if (pset.sversion >= 200000)
+	{
+		printfPQExpBuffer(&buf,
+						  "SELECT c.relchecks, c.relkind, c.relhasindex, c.relhasrules, "
+						  "c.relhastriggers, c.relrowsecurity, c.relforcerowsecurity, "
+						  "false AS relhasoids, c.relispartition, %s, c.reltablespace, "
+						  "CASE WHEN c.reloftype = 0 THEN '' ELSE c.reloftype::pg_catalog.regtype::pg_catalog.text END, "
+						  "c.relpersistence, c.relreplident, am.amname, "
+						  "c.relisivm\n"
+						  "FROM pg_catalog.pg_class c\n "
+						  "LEFT JOIN pg_catalog.pg_class tc ON (c.reltoastrelid = tc.oid)\n"
+						  "LEFT JOIN pg_catalog.pg_am am ON (c.relam = am.oid)\n"
+						  "WHERE c.oid = '%s';",
+						  (verbose ?
+						   "pg_catalog.array_to_string(c.reloptions || "
+						   "array(select 'toast.' || x from pg_catalog.unnest(tc.reloptions) x), ', ')\n"
+						   : "''"),
+						  oid);
+	}
+	else if (pset.sversion >= 120000)
 	{
 		appendPQExpBuffer(&buf,
 						  "SELECT c.relchecks, c.relkind, c.relhasindex, c.relhasrules, "
@@ -1768,6 +1788,10 @@ describeOneTableDetails(const char *schemaname,
 			NULL : pg_strdup(PQgetvalue(res, 0, 14));
 	else
 		tableinfo.relam = NULL;
+	if (pset.sversion >= 200000)
+		tableinfo.isivm = strcmp(PQgetvalue(res, 0, 15), "t") == 0;
+	else
+		tableinfo.isivm = false;
 	PQclear(res);
 	res = NULL;
 
@@ -3830,6 +3854,12 @@ describeOneTableDetails(const char *schemaname,
 			printfPQExpBuffer(&buf, _("Access method: %s"), tableinfo.relam);
 			printTableAddFooter(&cont, buf.data);
 		}
+
+		/* Incremental view maintance info */
+		if (verbose && tableinfo.relkind == RELKIND_MATVIEW && tableinfo.isivm)
+		{
+			printTableAddFooter(&cont, _("Incremental view maintenance: yes"));
+		}
 	}
 
 	/* reloptions, if verbose */
diff --git a/src/bin/psql/tab-complete.in.c b/src/bin/psql/tab-complete.in.c
index 46b9add0604..e5ef41710a0 100644
--- a/src/bin/psql/tab-complete.in.c
+++ b/src/bin/psql/tab-complete.in.c
@@ -1334,6 +1334,7 @@ static const pgsql_thing_t words_after_create[] = {
 	{"FOREIGN TABLE", NULL, NULL, NULL},
 	{"FUNCTION", NULL, NULL, Query_for_list_of_functions},
 	{"GROUP", Query_for_list_of_roles},
+	{"INCREMENTAL MATERIALIZED VIEW", NULL, NULL, &Query_for_list_of_matviews, NULL, THING_NO_DROP | THING_NO_ALTER},
 	{"INDEX", NULL, NULL, &Query_for_list_of_indexes},
 	{"LANGUAGE", Query_for_list_of_languages},
 	{"LARGE OBJECT", NULL, NULL, NULL, NULL, THING_NO_CREATE | THING_NO_DROP},
@@ -4256,28 +4257,33 @@ match_previous_words(int pattern_id,
 		COMPLETE_WITH("SELECT");
 
 /* CREATE MATERIALIZED VIEW */
-	else if (Matches("CREATE", "MATERIALIZED"))
+	else if (Matches("CREATE", "MATERIALIZED") ||
+			 Matches("CREATE", "INCREMENTAL", "MATERIALIZED"))
 		COMPLETE_WITH("VIEW");
-	/* Complete CREATE MATERIALIZED VIEW <name> with AS or USING */
-	else if (Matches("CREATE", "MATERIALIZED", "VIEW", MatchAny))
-		COMPLETE_WITH("AS", "USING");
 
+	/* Complete CREATE [INCREMENTAL] MATERIALIZED VIEW <name> with AS or USING */
+	else if (Matches("CREATE", "MATERIALIZED", "VIEW", MatchAny) ||
+			 Matches("CREATE", "INCREMENTAL", "MATERIALIZED", "VIEW", MatchAny))
+		COMPLETE_WITH("AS", "USING");
 	/*
-	 * Complete CREATE MATERIALIZED VIEW <name> USING with list of access
-	 * methods
+	 * Complete CREATE [INCREMENTAL] MATERIALIZED VIEW <name> USING with list
+	 * of access methods
 	 */
-	else if (Matches("CREATE", "MATERIALIZED", "VIEW", MatchAny, "USING"))
+	else if (Matches("CREATE", "MATERIALIZED", "VIEW", MatchAny, "USING") ||
+			 Matches("CREATE", "INCREMENTAL", "MATERIALIZED", "VIEW", MatchAny, "USING"))
 		COMPLETE_WITH_QUERY(Query_for_list_of_table_access_methods);
-	/* Complete CREATE MATERIALIZED VIEW <name> USING <access method> with AS */
-	else if (Matches("CREATE", "MATERIALIZED", "VIEW", MatchAny, "USING", MatchAny))
+	/* Complete CREATE [INCREMENTAL] MATERIALIZED VIEW <name> USING <am> with AS */
+	else if (Matches("CREATE", "MATERIALIZED", "VIEW", MatchAny, "USING", MatchAny) ||
+			 Matches("CREATE", "INCREMENTAL", "MATERIALIZED", "VIEW", MatchAny, "USING", MatchAny))
 		COMPLETE_WITH("AS");
-
 	/*
-	 * Complete CREATE MATERIALIZED VIEW <name> [USING <access method> ] AS
+	 * Complete CREATE [INCREMENTAL] MATERIALIZED VIEW <name> [USING <am>] AS
 	 * with "SELECT"
 	 */
 	else if (Matches("CREATE", "MATERIALIZED", "VIEW", MatchAny, "AS") ||
-			 Matches("CREATE", "MATERIALIZED", "VIEW", MatchAny, "USING", MatchAny, "AS"))
+			 Matches("CREATE", "MATERIALIZED", "VIEW", MatchAny, "USING", MatchAny, "AS") ||
+			 Matches("CREATE", "INCREMENTAL", "MATERIALIZED", "VIEW", MatchAny, "AS") ||
+			 Matches("CREATE", "INCREMENTAL", "MATERIALIZED", "VIEW", MatchAny, "USING", MatchAny, "AS"))
 		COMPLETE_WITH("SELECT");
 
 /* CREATE EVENT TRIGGER */
-- 
2.43.0


--Multipart=_Wed__1_Jul_2026_00_04_01_+0900_OVSy2WWK_9aByzDJ
Content-Type: text/x-diff;
 name="v38-0004-Add-Incremental-View-Maintenance-support-to-pg_d.patch"
Content-Disposition: attachment;
 filename="v38-0004-Add-Incremental-View-Maintenance-support-to-pg_d.patch"
Content-Transfer-Encoding: 7bit



^ permalink  raw  reply  [nested|flat] 101+ messages in thread

* [PATCH v38 05/11] Add Incremental View Maintenance support to psql
@ 2026-05-29 09:05  Yugo Nagata <[email protected]>
  0 siblings, 0 replies; 101+ messages in thread

From: Yugo Nagata @ 2026-05-29 09:05 UTC (permalink / raw)

Add tab completion and meta-command output for IVM.
---
 src/bin/psql/describe.c        | 32 +++++++++++++++++++++++++++++++-
 src/bin/psql/tab-complete.in.c | 30 ++++++++++++++++++------------
 2 files changed, 49 insertions(+), 13 deletions(-)

diff --git a/src/bin/psql/describe.c b/src/bin/psql/describe.c
index af3935b0078..ad5c8274af0 100644
--- a/src/bin/psql/describe.c
+++ b/src/bin/psql/describe.c
@@ -1634,6 +1634,7 @@ describeOneTableDetails(const char *schemaname,
 		char		relpersistence;
 		char		relreplident;
 		char	   *relam;
+		bool		isivm;
 	}			tableinfo;
 	bool		show_column_details = false;
 
@@ -1648,7 +1649,26 @@ describeOneTableDetails(const char *schemaname,
 	/* Get general table info */
 	printfPQExpBuffer(&buf, "/* %s */\n",
 					  _("Get general information about one relation"));
-	if (pset.sversion >= 120000)
+	if (pset.sversion >= 200000)
+	{
+		printfPQExpBuffer(&buf,
+						  "SELECT c.relchecks, c.relkind, c.relhasindex, c.relhasrules, "
+						  "c.relhastriggers, c.relrowsecurity, c.relforcerowsecurity, "
+						  "false AS relhasoids, c.relispartition, %s, c.reltablespace, "
+						  "CASE WHEN c.reloftype = 0 THEN '' ELSE c.reloftype::pg_catalog.regtype::pg_catalog.text END, "
+						  "c.relpersistence, c.relreplident, am.amname, "
+						  "c.relisivm\n"
+						  "FROM pg_catalog.pg_class c\n "
+						  "LEFT JOIN pg_catalog.pg_class tc ON (c.reltoastrelid = tc.oid)\n"
+						  "LEFT JOIN pg_catalog.pg_am am ON (c.relam = am.oid)\n"
+						  "WHERE c.oid = '%s';",
+						  (verbose ?
+						   "pg_catalog.array_to_string(c.reloptions || "
+						   "array(select 'toast.' || x from pg_catalog.unnest(tc.reloptions) x), ', ')\n"
+						   : "''"),
+						  oid);
+	}
+	else if (pset.sversion >= 120000)
 	{
 		appendPQExpBuffer(&buf,
 						  "SELECT c.relchecks, c.relkind, c.relhasindex, c.relhasrules, "
@@ -1768,6 +1788,10 @@ describeOneTableDetails(const char *schemaname,
 			NULL : pg_strdup(PQgetvalue(res, 0, 14));
 	else
 		tableinfo.relam = NULL;
+	if (pset.sversion >= 200000)
+		tableinfo.isivm = strcmp(PQgetvalue(res, 0, 15), "t") == 0;
+	else
+		tableinfo.isivm = false;
 	PQclear(res);
 	res = NULL;
 
@@ -3830,6 +3854,12 @@ describeOneTableDetails(const char *schemaname,
 			printfPQExpBuffer(&buf, _("Access method: %s"), tableinfo.relam);
 			printTableAddFooter(&cont, buf.data);
 		}
+
+		/* Incremental view maintance info */
+		if (verbose && tableinfo.relkind == RELKIND_MATVIEW && tableinfo.isivm)
+		{
+			printTableAddFooter(&cont, _("Incremental view maintenance: yes"));
+		}
 	}
 
 	/* reloptions, if verbose */
diff --git a/src/bin/psql/tab-complete.in.c b/src/bin/psql/tab-complete.in.c
index 46b9add0604..e5ef41710a0 100644
--- a/src/bin/psql/tab-complete.in.c
+++ b/src/bin/psql/tab-complete.in.c
@@ -1334,6 +1334,7 @@ static const pgsql_thing_t words_after_create[] = {
 	{"FOREIGN TABLE", NULL, NULL, NULL},
 	{"FUNCTION", NULL, NULL, Query_for_list_of_functions},
 	{"GROUP", Query_for_list_of_roles},
+	{"INCREMENTAL MATERIALIZED VIEW", NULL, NULL, &Query_for_list_of_matviews, NULL, THING_NO_DROP | THING_NO_ALTER},
 	{"INDEX", NULL, NULL, &Query_for_list_of_indexes},
 	{"LANGUAGE", Query_for_list_of_languages},
 	{"LARGE OBJECT", NULL, NULL, NULL, NULL, THING_NO_CREATE | THING_NO_DROP},
@@ -4256,28 +4257,33 @@ match_previous_words(int pattern_id,
 		COMPLETE_WITH("SELECT");
 
 /* CREATE MATERIALIZED VIEW */
-	else if (Matches("CREATE", "MATERIALIZED"))
+	else if (Matches("CREATE", "MATERIALIZED") ||
+			 Matches("CREATE", "INCREMENTAL", "MATERIALIZED"))
 		COMPLETE_WITH("VIEW");
-	/* Complete CREATE MATERIALIZED VIEW <name> with AS or USING */
-	else if (Matches("CREATE", "MATERIALIZED", "VIEW", MatchAny))
-		COMPLETE_WITH("AS", "USING");
 
+	/* Complete CREATE [INCREMENTAL] MATERIALIZED VIEW <name> with AS or USING */
+	else if (Matches("CREATE", "MATERIALIZED", "VIEW", MatchAny) ||
+			 Matches("CREATE", "INCREMENTAL", "MATERIALIZED", "VIEW", MatchAny))
+		COMPLETE_WITH("AS", "USING");
 	/*
-	 * Complete CREATE MATERIALIZED VIEW <name> USING with list of access
-	 * methods
+	 * Complete CREATE [INCREMENTAL] MATERIALIZED VIEW <name> USING with list
+	 * of access methods
 	 */
-	else if (Matches("CREATE", "MATERIALIZED", "VIEW", MatchAny, "USING"))
+	else if (Matches("CREATE", "MATERIALIZED", "VIEW", MatchAny, "USING") ||
+			 Matches("CREATE", "INCREMENTAL", "MATERIALIZED", "VIEW", MatchAny, "USING"))
 		COMPLETE_WITH_QUERY(Query_for_list_of_table_access_methods);
-	/* Complete CREATE MATERIALIZED VIEW <name> USING <access method> with AS */
-	else if (Matches("CREATE", "MATERIALIZED", "VIEW", MatchAny, "USING", MatchAny))
+	/* Complete CREATE [INCREMENTAL] MATERIALIZED VIEW <name> USING <am> with AS */
+	else if (Matches("CREATE", "MATERIALIZED", "VIEW", MatchAny, "USING", MatchAny) ||
+			 Matches("CREATE", "INCREMENTAL", "MATERIALIZED", "VIEW", MatchAny, "USING", MatchAny))
 		COMPLETE_WITH("AS");
-
 	/*
-	 * Complete CREATE MATERIALIZED VIEW <name> [USING <access method> ] AS
+	 * Complete CREATE [INCREMENTAL] MATERIALIZED VIEW <name> [USING <am>] AS
 	 * with "SELECT"
 	 */
 	else if (Matches("CREATE", "MATERIALIZED", "VIEW", MatchAny, "AS") ||
-			 Matches("CREATE", "MATERIALIZED", "VIEW", MatchAny, "USING", MatchAny, "AS"))
+			 Matches("CREATE", "MATERIALIZED", "VIEW", MatchAny, "USING", MatchAny, "AS") ||
+			 Matches("CREATE", "INCREMENTAL", "MATERIALIZED", "VIEW", MatchAny, "AS") ||
+			 Matches("CREATE", "INCREMENTAL", "MATERIALIZED", "VIEW", MatchAny, "USING", MatchAny, "AS"))
 		COMPLETE_WITH("SELECT");
 
 /* CREATE EVENT TRIGGER */
-- 
2.43.0


--Multipart=_Wed__1_Jul_2026_00_04_01_+0900_OVSy2WWK_9aByzDJ
Content-Type: text/x-diff;
 name="v38-0004-Add-Incremental-View-Maintenance-support-to-pg_d.patch"
Content-Disposition: attachment;
 filename="v38-0004-Add-Incremental-View-Maintenance-support-to-pg_d.patch"
Content-Transfer-Encoding: 7bit



^ permalink  raw  reply  [nested|flat] 101+ messages in thread

* [PATCH v38 05/11] Add Incremental View Maintenance support to psql
@ 2026-05-29 09:05  Yugo Nagata <[email protected]>
  0 siblings, 0 replies; 101+ messages in thread

From: Yugo Nagata @ 2026-05-29 09:05 UTC (permalink / raw)

Add tab completion and meta-command output for IVM.
---
 src/bin/psql/describe.c        | 32 +++++++++++++++++++++++++++++++-
 src/bin/psql/tab-complete.in.c | 30 ++++++++++++++++++------------
 2 files changed, 49 insertions(+), 13 deletions(-)

diff --git a/src/bin/psql/describe.c b/src/bin/psql/describe.c
index af3935b0078..ad5c8274af0 100644
--- a/src/bin/psql/describe.c
+++ b/src/bin/psql/describe.c
@@ -1634,6 +1634,7 @@ describeOneTableDetails(const char *schemaname,
 		char		relpersistence;
 		char		relreplident;
 		char	   *relam;
+		bool		isivm;
 	}			tableinfo;
 	bool		show_column_details = false;
 
@@ -1648,7 +1649,26 @@ describeOneTableDetails(const char *schemaname,
 	/* Get general table info */
 	printfPQExpBuffer(&buf, "/* %s */\n",
 					  _("Get general information about one relation"));
-	if (pset.sversion >= 120000)
+	if (pset.sversion >= 200000)
+	{
+		printfPQExpBuffer(&buf,
+						  "SELECT c.relchecks, c.relkind, c.relhasindex, c.relhasrules, "
+						  "c.relhastriggers, c.relrowsecurity, c.relforcerowsecurity, "
+						  "false AS relhasoids, c.relispartition, %s, c.reltablespace, "
+						  "CASE WHEN c.reloftype = 0 THEN '' ELSE c.reloftype::pg_catalog.regtype::pg_catalog.text END, "
+						  "c.relpersistence, c.relreplident, am.amname, "
+						  "c.relisivm\n"
+						  "FROM pg_catalog.pg_class c\n "
+						  "LEFT JOIN pg_catalog.pg_class tc ON (c.reltoastrelid = tc.oid)\n"
+						  "LEFT JOIN pg_catalog.pg_am am ON (c.relam = am.oid)\n"
+						  "WHERE c.oid = '%s';",
+						  (verbose ?
+						   "pg_catalog.array_to_string(c.reloptions || "
+						   "array(select 'toast.' || x from pg_catalog.unnest(tc.reloptions) x), ', ')\n"
+						   : "''"),
+						  oid);
+	}
+	else if (pset.sversion >= 120000)
 	{
 		appendPQExpBuffer(&buf,
 						  "SELECT c.relchecks, c.relkind, c.relhasindex, c.relhasrules, "
@@ -1768,6 +1788,10 @@ describeOneTableDetails(const char *schemaname,
 			NULL : pg_strdup(PQgetvalue(res, 0, 14));
 	else
 		tableinfo.relam = NULL;
+	if (pset.sversion >= 200000)
+		tableinfo.isivm = strcmp(PQgetvalue(res, 0, 15), "t") == 0;
+	else
+		tableinfo.isivm = false;
 	PQclear(res);
 	res = NULL;
 
@@ -3830,6 +3854,12 @@ describeOneTableDetails(const char *schemaname,
 			printfPQExpBuffer(&buf, _("Access method: %s"), tableinfo.relam);
 			printTableAddFooter(&cont, buf.data);
 		}
+
+		/* Incremental view maintance info */
+		if (verbose && tableinfo.relkind == RELKIND_MATVIEW && tableinfo.isivm)
+		{
+			printTableAddFooter(&cont, _("Incremental view maintenance: yes"));
+		}
 	}
 
 	/* reloptions, if verbose */
diff --git a/src/bin/psql/tab-complete.in.c b/src/bin/psql/tab-complete.in.c
index 46b9add0604..e5ef41710a0 100644
--- a/src/bin/psql/tab-complete.in.c
+++ b/src/bin/psql/tab-complete.in.c
@@ -1334,6 +1334,7 @@ static const pgsql_thing_t words_after_create[] = {
 	{"FOREIGN TABLE", NULL, NULL, NULL},
 	{"FUNCTION", NULL, NULL, Query_for_list_of_functions},
 	{"GROUP", Query_for_list_of_roles},
+	{"INCREMENTAL MATERIALIZED VIEW", NULL, NULL, &Query_for_list_of_matviews, NULL, THING_NO_DROP | THING_NO_ALTER},
 	{"INDEX", NULL, NULL, &Query_for_list_of_indexes},
 	{"LANGUAGE", Query_for_list_of_languages},
 	{"LARGE OBJECT", NULL, NULL, NULL, NULL, THING_NO_CREATE | THING_NO_DROP},
@@ -4256,28 +4257,33 @@ match_previous_words(int pattern_id,
 		COMPLETE_WITH("SELECT");
 
 /* CREATE MATERIALIZED VIEW */
-	else if (Matches("CREATE", "MATERIALIZED"))
+	else if (Matches("CREATE", "MATERIALIZED") ||
+			 Matches("CREATE", "INCREMENTAL", "MATERIALIZED"))
 		COMPLETE_WITH("VIEW");
-	/* Complete CREATE MATERIALIZED VIEW <name> with AS or USING */
-	else if (Matches("CREATE", "MATERIALIZED", "VIEW", MatchAny))
-		COMPLETE_WITH("AS", "USING");
 
+	/* Complete CREATE [INCREMENTAL] MATERIALIZED VIEW <name> with AS or USING */
+	else if (Matches("CREATE", "MATERIALIZED", "VIEW", MatchAny) ||
+			 Matches("CREATE", "INCREMENTAL", "MATERIALIZED", "VIEW", MatchAny))
+		COMPLETE_WITH("AS", "USING");
 	/*
-	 * Complete CREATE MATERIALIZED VIEW <name> USING with list of access
-	 * methods
+	 * Complete CREATE [INCREMENTAL] MATERIALIZED VIEW <name> USING with list
+	 * of access methods
 	 */
-	else if (Matches("CREATE", "MATERIALIZED", "VIEW", MatchAny, "USING"))
+	else if (Matches("CREATE", "MATERIALIZED", "VIEW", MatchAny, "USING") ||
+			 Matches("CREATE", "INCREMENTAL", "MATERIALIZED", "VIEW", MatchAny, "USING"))
 		COMPLETE_WITH_QUERY(Query_for_list_of_table_access_methods);
-	/* Complete CREATE MATERIALIZED VIEW <name> USING <access method> with AS */
-	else if (Matches("CREATE", "MATERIALIZED", "VIEW", MatchAny, "USING", MatchAny))
+	/* Complete CREATE [INCREMENTAL] MATERIALIZED VIEW <name> USING <am> with AS */
+	else if (Matches("CREATE", "MATERIALIZED", "VIEW", MatchAny, "USING", MatchAny) ||
+			 Matches("CREATE", "INCREMENTAL", "MATERIALIZED", "VIEW", MatchAny, "USING", MatchAny))
 		COMPLETE_WITH("AS");
-
 	/*
-	 * Complete CREATE MATERIALIZED VIEW <name> [USING <access method> ] AS
+	 * Complete CREATE [INCREMENTAL] MATERIALIZED VIEW <name> [USING <am>] AS
 	 * with "SELECT"
 	 */
 	else if (Matches("CREATE", "MATERIALIZED", "VIEW", MatchAny, "AS") ||
-			 Matches("CREATE", "MATERIALIZED", "VIEW", MatchAny, "USING", MatchAny, "AS"))
+			 Matches("CREATE", "MATERIALIZED", "VIEW", MatchAny, "USING", MatchAny, "AS") ||
+			 Matches("CREATE", "INCREMENTAL", "MATERIALIZED", "VIEW", MatchAny, "AS") ||
+			 Matches("CREATE", "INCREMENTAL", "MATERIALIZED", "VIEW", MatchAny, "USING", MatchAny, "AS"))
 		COMPLETE_WITH("SELECT");
 
 /* CREATE EVENT TRIGGER */
-- 
2.43.0


--Multipart=_Wed__1_Jul_2026_00_04_01_+0900_OVSy2WWK_9aByzDJ
Content-Type: text/x-diff;
 name="v38-0004-Add-Incremental-View-Maintenance-support-to-pg_d.patch"
Content-Disposition: attachment;
 filename="v38-0004-Add-Incremental-View-Maintenance-support-to-pg_d.patch"
Content-Transfer-Encoding: 7bit



^ permalink  raw  reply  [nested|flat] 101+ messages in thread

* [PATCH v37 05/11] Add Incremental View Maintenance support to psql
@ 2026-05-29 09:05  Yugo Nagata <[email protected]>
  0 siblings, 0 replies; 101+ messages in thread

From: Yugo Nagata @ 2026-05-29 09:05 UTC (permalink / raw)

Add tab completion and meta-command output for IVM.
---
 src/bin/psql/describe.c        | 32 +++++++++++++++++++++++++++++++-
 src/bin/psql/tab-complete.in.c | 30 ++++++++++++++++++------------
 2 files changed, 49 insertions(+), 13 deletions(-)

diff --git a/src/bin/psql/describe.c b/src/bin/psql/describe.c
index e1449654f96..2321f66d871 100644
--- a/src/bin/psql/describe.c
+++ b/src/bin/psql/describe.c
@@ -1634,6 +1634,7 @@ describeOneTableDetails(const char *schemaname,
 		char		relpersistence;
 		char		relreplident;
 		char	   *relam;
+		bool		isivm;
 	}			tableinfo;
 	bool		show_column_details = false;
 
@@ -1648,7 +1649,26 @@ describeOneTableDetails(const char *schemaname,
 	/* Get general table info */
 	printfPQExpBuffer(&buf, "/* %s */\n",
 					  _("Get general information about one relation"));
-	if (pset.sversion >= 120000)
+	if (pset.sversion >= 200000)
+	{
+		printfPQExpBuffer(&buf,
+						  "SELECT c.relchecks, c.relkind, c.relhasindex, c.relhasrules, "
+						  "c.relhastriggers, c.relrowsecurity, c.relforcerowsecurity, "
+						  "false AS relhasoids, c.relispartition, %s, c.reltablespace, "
+						  "CASE WHEN c.reloftype = 0 THEN '' ELSE c.reloftype::pg_catalog.regtype::pg_catalog.text END, "
+						  "c.relpersistence, c.relreplident, am.amname, "
+						  "c.relisivm\n"
+						  "FROM pg_catalog.pg_class c\n "
+						  "LEFT JOIN pg_catalog.pg_class tc ON (c.reltoastrelid = tc.oid)\n"
+						  "LEFT JOIN pg_catalog.pg_am am ON (c.relam = am.oid)\n"
+						  "WHERE c.oid = '%s';",
+						  (verbose ?
+						   "pg_catalog.array_to_string(c.reloptions || "
+						   "array(select 'toast.' || x from pg_catalog.unnest(tc.reloptions) x), ', ')\n"
+						   : "''"),
+						  oid);
+	}
+	else if (pset.sversion >= 120000)
 	{
 		appendPQExpBuffer(&buf,
 						  "SELECT c.relchecks, c.relkind, c.relhasindex, c.relhasrules, "
@@ -1768,6 +1788,10 @@ describeOneTableDetails(const char *schemaname,
 			NULL : pg_strdup(PQgetvalue(res, 0, 14));
 	else
 		tableinfo.relam = NULL;
+	if (pset.sversion >= 200000)
+		tableinfo.isivm = strcmp(PQgetvalue(res, 0, 15), "t") == 0;
+	else
+		tableinfo.isivm = false;
 	PQclear(res);
 	res = NULL;
 
@@ -3830,6 +3854,12 @@ describeOneTableDetails(const char *schemaname,
 			printfPQExpBuffer(&buf, _("Access method: %s"), tableinfo.relam);
 			printTableAddFooter(&cont, buf.data);
 		}
+
+		/* Incremental view maintance info */
+		if (verbose && tableinfo.relkind == RELKIND_MATVIEW && tableinfo.isivm)
+		{
+			printTableAddFooter(&cont, _("Incremental view maintenance: yes"));
+		}
 	}
 
 	/* reloptions, if verbose */
diff --git a/src/bin/psql/tab-complete.in.c b/src/bin/psql/tab-complete.in.c
index de547a8cb37..590e33833f2 100644
--- a/src/bin/psql/tab-complete.in.c
+++ b/src/bin/psql/tab-complete.in.c
@@ -1334,6 +1334,7 @@ static const pgsql_thing_t words_after_create[] = {
 	{"FOREIGN TABLE", NULL, NULL, NULL},
 	{"FUNCTION", NULL, NULL, Query_for_list_of_functions},
 	{"GROUP", Query_for_list_of_roles},
+	{"INCREMENTAL MATERIALIZED VIEW", NULL, NULL, &Query_for_list_of_matviews, NULL, THING_NO_DROP | THING_NO_ALTER},
 	{"INDEX", NULL, NULL, &Query_for_list_of_indexes},
 	{"LANGUAGE", Query_for_list_of_languages},
 	{"LARGE OBJECT", NULL, NULL, NULL, NULL, THING_NO_CREATE | THING_NO_DROP},
@@ -4254,28 +4255,33 @@ match_previous_words(int pattern_id,
 		COMPLETE_WITH("SELECT");
 
 /* CREATE MATERIALIZED VIEW */
-	else if (Matches("CREATE", "MATERIALIZED"))
+	else if (Matches("CREATE", "MATERIALIZED") ||
+			 Matches("CREATE", "INCREMENTAL", "MATERIALIZED"))
 		COMPLETE_WITH("VIEW");
-	/* Complete CREATE MATERIALIZED VIEW <name> with AS or USING */
-	else if (Matches("CREATE", "MATERIALIZED", "VIEW", MatchAny))
-		COMPLETE_WITH("AS", "USING");
 
+	/* Complete CREATE [INCREMENTAL] MATERIALIZED VIEW <name> with AS or USING */
+	else if (Matches("CREATE", "MATERIALIZED", "VIEW", MatchAny) ||
+			 Matches("CREATE", "INCREMENTAL", "MATERIALIZED", "VIEW", MatchAny))
+		COMPLETE_WITH("AS", "USING");
 	/*
-	 * Complete CREATE MATERIALIZED VIEW <name> USING with list of access
-	 * methods
+	 * Complete CREATE [INCREMENTAL] MATERIALIZED VIEW <name> USING with list
+	 * of access methods
 	 */
-	else if (Matches("CREATE", "MATERIALIZED", "VIEW", MatchAny, "USING"))
+	else if (Matches("CREATE", "MATERIALIZED", "VIEW", MatchAny, "USING") ||
+			 Matches("CREATE", "INCREMENTAL", "MATERIALIZED", "VIEW", MatchAny, "USING"))
 		COMPLETE_WITH_QUERY(Query_for_list_of_table_access_methods);
-	/* Complete CREATE MATERIALIZED VIEW <name> USING <access method> with AS */
-	else if (Matches("CREATE", "MATERIALIZED", "VIEW", MatchAny, "USING", MatchAny))
+	/* Complete CREATE [INCREMENTAL] MATERIALIZED VIEW <name> USING <am> with AS */
+	else if (Matches("CREATE", "MATERIALIZED", "VIEW", MatchAny, "USING", MatchAny) ||
+			 Matches("CREATE", "INCREMENTAL", "MATERIALIZED", "VIEW", MatchAny, "USING", MatchAny))
 		COMPLETE_WITH("AS");
-
 	/*
-	 * Complete CREATE MATERIALIZED VIEW <name> [USING <access method> ] AS
+	 * Complete CREATE [INCREMENTAL] MATERIALIZED VIEW <name> [USING <am>] AS
 	 * with "SELECT"
 	 */
 	else if (Matches("CREATE", "MATERIALIZED", "VIEW", MatchAny, "AS") ||
-			 Matches("CREATE", "MATERIALIZED", "VIEW", MatchAny, "USING", MatchAny, "AS"))
+			 Matches("CREATE", "MATERIALIZED", "VIEW", MatchAny, "USING", MatchAny, "AS") ||
+			 Matches("CREATE", "INCREMENTAL", "MATERIALIZED", "VIEW", MatchAny, "AS") ||
+			 Matches("CREATE", "INCREMENTAL", "MATERIALIZED", "VIEW", MatchAny, "USING", MatchAny, "AS"))
 		COMPLETE_WITH("SELECT");
 
 /* CREATE EVENT TRIGGER */
-- 
2.43.0


--Multipart=_Fri__29_May_2026_23_14_17_+0900_Te0o73X2VqYK57Gd
Content-Type: text/x-diff;
 name="v37-0004-Add-Incremental-View-Maintenance-support-to-pg_d.patch"
Content-Disposition: attachment;
 filename="v37-0004-Add-Incremental-View-Maintenance-support-to-pg_d.patch"
Content-Transfer-Encoding: 7bit



^ permalink  raw  reply  [nested|flat] 101+ messages in thread

* [PATCH v37 05/11] Add Incremental View Maintenance support to psql
@ 2026-05-29 09:05  Yugo Nagata <[email protected]>
  0 siblings, 0 replies; 101+ messages in thread

From: Yugo Nagata @ 2026-05-29 09:05 UTC (permalink / raw)

Add tab completion and meta-command output for IVM.
---
 src/bin/psql/describe.c        | 32 +++++++++++++++++++++++++++++++-
 src/bin/psql/tab-complete.in.c | 30 ++++++++++++++++++------------
 2 files changed, 49 insertions(+), 13 deletions(-)

diff --git a/src/bin/psql/describe.c b/src/bin/psql/describe.c
index e1449654f96..2321f66d871 100644
--- a/src/bin/psql/describe.c
+++ b/src/bin/psql/describe.c
@@ -1634,6 +1634,7 @@ describeOneTableDetails(const char *schemaname,
 		char		relpersistence;
 		char		relreplident;
 		char	   *relam;
+		bool		isivm;
 	}			tableinfo;
 	bool		show_column_details = false;
 
@@ -1648,7 +1649,26 @@ describeOneTableDetails(const char *schemaname,
 	/* Get general table info */
 	printfPQExpBuffer(&buf, "/* %s */\n",
 					  _("Get general information about one relation"));
-	if (pset.sversion >= 120000)
+	if (pset.sversion >= 200000)
+	{
+		printfPQExpBuffer(&buf,
+						  "SELECT c.relchecks, c.relkind, c.relhasindex, c.relhasrules, "
+						  "c.relhastriggers, c.relrowsecurity, c.relforcerowsecurity, "
+						  "false AS relhasoids, c.relispartition, %s, c.reltablespace, "
+						  "CASE WHEN c.reloftype = 0 THEN '' ELSE c.reloftype::pg_catalog.regtype::pg_catalog.text END, "
+						  "c.relpersistence, c.relreplident, am.amname, "
+						  "c.relisivm\n"
+						  "FROM pg_catalog.pg_class c\n "
+						  "LEFT JOIN pg_catalog.pg_class tc ON (c.reltoastrelid = tc.oid)\n"
+						  "LEFT JOIN pg_catalog.pg_am am ON (c.relam = am.oid)\n"
+						  "WHERE c.oid = '%s';",
+						  (verbose ?
+						   "pg_catalog.array_to_string(c.reloptions || "
+						   "array(select 'toast.' || x from pg_catalog.unnest(tc.reloptions) x), ', ')\n"
+						   : "''"),
+						  oid);
+	}
+	else if (pset.sversion >= 120000)
 	{
 		appendPQExpBuffer(&buf,
 						  "SELECT c.relchecks, c.relkind, c.relhasindex, c.relhasrules, "
@@ -1768,6 +1788,10 @@ describeOneTableDetails(const char *schemaname,
 			NULL : pg_strdup(PQgetvalue(res, 0, 14));
 	else
 		tableinfo.relam = NULL;
+	if (pset.sversion >= 200000)
+		tableinfo.isivm = strcmp(PQgetvalue(res, 0, 15), "t") == 0;
+	else
+		tableinfo.isivm = false;
 	PQclear(res);
 	res = NULL;
 
@@ -3830,6 +3854,12 @@ describeOneTableDetails(const char *schemaname,
 			printfPQExpBuffer(&buf, _("Access method: %s"), tableinfo.relam);
 			printTableAddFooter(&cont, buf.data);
 		}
+
+		/* Incremental view maintance info */
+		if (verbose && tableinfo.relkind == RELKIND_MATVIEW && tableinfo.isivm)
+		{
+			printTableAddFooter(&cont, _("Incremental view maintenance: yes"));
+		}
 	}
 
 	/* reloptions, if verbose */
diff --git a/src/bin/psql/tab-complete.in.c b/src/bin/psql/tab-complete.in.c
index de547a8cb37..590e33833f2 100644
--- a/src/bin/psql/tab-complete.in.c
+++ b/src/bin/psql/tab-complete.in.c
@@ -1334,6 +1334,7 @@ static const pgsql_thing_t words_after_create[] = {
 	{"FOREIGN TABLE", NULL, NULL, NULL},
 	{"FUNCTION", NULL, NULL, Query_for_list_of_functions},
 	{"GROUP", Query_for_list_of_roles},
+	{"INCREMENTAL MATERIALIZED VIEW", NULL, NULL, &Query_for_list_of_matviews, NULL, THING_NO_DROP | THING_NO_ALTER},
 	{"INDEX", NULL, NULL, &Query_for_list_of_indexes},
 	{"LANGUAGE", Query_for_list_of_languages},
 	{"LARGE OBJECT", NULL, NULL, NULL, NULL, THING_NO_CREATE | THING_NO_DROP},
@@ -4254,28 +4255,33 @@ match_previous_words(int pattern_id,
 		COMPLETE_WITH("SELECT");
 
 /* CREATE MATERIALIZED VIEW */
-	else if (Matches("CREATE", "MATERIALIZED"))
+	else if (Matches("CREATE", "MATERIALIZED") ||
+			 Matches("CREATE", "INCREMENTAL", "MATERIALIZED"))
 		COMPLETE_WITH("VIEW");
-	/* Complete CREATE MATERIALIZED VIEW <name> with AS or USING */
-	else if (Matches("CREATE", "MATERIALIZED", "VIEW", MatchAny))
-		COMPLETE_WITH("AS", "USING");
 
+	/* Complete CREATE [INCREMENTAL] MATERIALIZED VIEW <name> with AS or USING */
+	else if (Matches("CREATE", "MATERIALIZED", "VIEW", MatchAny) ||
+			 Matches("CREATE", "INCREMENTAL", "MATERIALIZED", "VIEW", MatchAny))
+		COMPLETE_WITH("AS", "USING");
 	/*
-	 * Complete CREATE MATERIALIZED VIEW <name> USING with list of access
-	 * methods
+	 * Complete CREATE [INCREMENTAL] MATERIALIZED VIEW <name> USING with list
+	 * of access methods
 	 */
-	else if (Matches("CREATE", "MATERIALIZED", "VIEW", MatchAny, "USING"))
+	else if (Matches("CREATE", "MATERIALIZED", "VIEW", MatchAny, "USING") ||
+			 Matches("CREATE", "INCREMENTAL", "MATERIALIZED", "VIEW", MatchAny, "USING"))
 		COMPLETE_WITH_QUERY(Query_for_list_of_table_access_methods);
-	/* Complete CREATE MATERIALIZED VIEW <name> USING <access method> with AS */
-	else if (Matches("CREATE", "MATERIALIZED", "VIEW", MatchAny, "USING", MatchAny))
+	/* Complete CREATE [INCREMENTAL] MATERIALIZED VIEW <name> USING <am> with AS */
+	else if (Matches("CREATE", "MATERIALIZED", "VIEW", MatchAny, "USING", MatchAny) ||
+			 Matches("CREATE", "INCREMENTAL", "MATERIALIZED", "VIEW", MatchAny, "USING", MatchAny))
 		COMPLETE_WITH("AS");
-
 	/*
-	 * Complete CREATE MATERIALIZED VIEW <name> [USING <access method> ] AS
+	 * Complete CREATE [INCREMENTAL] MATERIALIZED VIEW <name> [USING <am>] AS
 	 * with "SELECT"
 	 */
 	else if (Matches("CREATE", "MATERIALIZED", "VIEW", MatchAny, "AS") ||
-			 Matches("CREATE", "MATERIALIZED", "VIEW", MatchAny, "USING", MatchAny, "AS"))
+			 Matches("CREATE", "MATERIALIZED", "VIEW", MatchAny, "USING", MatchAny, "AS") ||
+			 Matches("CREATE", "INCREMENTAL", "MATERIALIZED", "VIEW", MatchAny, "AS") ||
+			 Matches("CREATE", "INCREMENTAL", "MATERIALIZED", "VIEW", MatchAny, "USING", MatchAny, "AS"))
 		COMPLETE_WITH("SELECT");
 
 /* CREATE EVENT TRIGGER */
-- 
2.43.0


--Multipart=_Fri__29_May_2026_23_14_17_+0900_Te0o73X2VqYK57Gd
Content-Type: text/x-diff;
 name="v37-0004-Add-Incremental-View-Maintenance-support-to-pg_d.patch"
Content-Disposition: attachment;
 filename="v37-0004-Add-Incremental-View-Maintenance-support-to-pg_d.patch"
Content-Transfer-Encoding: 7bit



^ permalink  raw  reply  [nested|flat] 101+ messages in thread

* [PATCH v39 5/8] Add Incremental View Maintenance support to psql
@ 2026-05-29 09:05  Yugo Nagata <[email protected]>
  0 siblings, 0 replies; 101+ messages in thread

From: Yugo Nagata @ 2026-05-29 09:05 UTC (permalink / raw)

Add tab completion and meta-command output for IVM.
---
 src/bin/psql/describe.c        | 32 +++++++++++++++++++++++++++++++-
 src/bin/psql/tab-complete.in.c | 30 ++++++++++++++++++------------
 2 files changed, 49 insertions(+), 13 deletions(-)

diff --git a/src/bin/psql/describe.c b/src/bin/psql/describe.c
index fef86b4cca3..5b7bf626c32 100644
--- a/src/bin/psql/describe.c
+++ b/src/bin/psql/describe.c
@@ -1580,6 +1580,7 @@ describeOneTableDetails(const char *schemaname,
 		char		relpersistence;
 		char		relreplident;
 		char	   *relam;
+		bool		isivm;
 	}			tableinfo;
 	bool		show_column_details = false;
 
@@ -1594,7 +1595,26 @@ describeOneTableDetails(const char *schemaname,
 	/* Get general table info */
 	printfPQExpBuffer(&buf, "/* %s */\n",
 					  _("Get general information about one relation"));
-	if (pset.sversion >= 120000)
+	if (pset.sversion >= 200000)
+	{
+		printfPQExpBuffer(&buf,
+						  "SELECT c.relchecks, c.relkind, c.relhasindex, c.relhasrules, "
+						  "c.relhastriggers, c.relrowsecurity, c.relforcerowsecurity, "
+						  "false AS relhasoids, c.relispartition, %s, c.reltablespace, "
+						  "CASE WHEN c.reloftype = 0 THEN '' ELSE c.reloftype::pg_catalog.regtype::pg_catalog.text END, "
+						  "c.relpersistence, c.relreplident, am.amname, "
+						  "c.relisivm\n"
+						  "FROM pg_catalog.pg_class c\n "
+						  "LEFT JOIN pg_catalog.pg_class tc ON (c.reltoastrelid = tc.oid)\n"
+						  "LEFT JOIN pg_catalog.pg_am am ON (c.relam = am.oid)\n"
+						  "WHERE c.oid = '%s';",
+						  (verbose ?
+						   "pg_catalog.array_to_string(c.reloptions || "
+						   "array(select 'toast.' || x from pg_catalog.unnest(tc.reloptions) x), ', ')\n"
+						   : "''"),
+						  oid);
+	}
+	else if (pset.sversion >= 120000)
 	{
 		appendPQExpBuffer(&buf,
 						  "SELECT c.relchecks, c.relkind, c.relhasindex, c.relhasrules, "
@@ -1662,6 +1682,10 @@ describeOneTableDetails(const char *schemaname,
 			NULL : pg_strdup(PQgetvalue(res, 0, 14));
 	else
 		tableinfo.relam = NULL;
+	if (pset.sversion >= 200000)
+		tableinfo.isivm = strcmp(PQgetvalue(res, 0, 15), "t") == 0;
+	else
+		tableinfo.isivm = false;
 	PQclear(res);
 	res = NULL;
 
@@ -3670,6 +3694,12 @@ describeOneTableDetails(const char *schemaname,
 			printfPQExpBuffer(&buf, _("Access method: %s"), tableinfo.relam);
 			printTableAddFooter(&cont, buf.data);
 		}
+
+		/* Incremental view maintance info */
+		if (verbose && tableinfo.relkind == RELKIND_MATVIEW && tableinfo.isivm)
+		{
+			printTableAddFooter(&cont, _("Incremental view maintenance: yes"));
+		}
 	}
 
 	/* reloptions, if verbose */
diff --git a/src/bin/psql/tab-complete.in.c b/src/bin/psql/tab-complete.in.c
index e4bc2c93145..6dfad8a8102 100644
--- a/src/bin/psql/tab-complete.in.c
+++ b/src/bin/psql/tab-complete.in.c
@@ -1320,6 +1320,7 @@ static const pgsql_thing_t words_after_create[] = {
 	{"FOREIGN TABLE", NULL, NULL, NULL},
 	{"FUNCTION", NULL, NULL, Query_for_list_of_functions},
 	{"GROUP", Query_for_list_of_roles},
+	{"INCREMENTAL MATERIALIZED VIEW", NULL, NULL, &Query_for_list_of_matviews, NULL, THING_NO_DROP | THING_NO_ALTER},
 	{"INDEX", NULL, NULL, &Query_for_list_of_indexes},
 	{"LANGUAGE", Query_for_list_of_languages},
 	{"LARGE OBJECT", NULL, NULL, NULL, NULL, THING_NO_CREATE | THING_NO_DROP},
@@ -4242,28 +4243,33 @@ match_previous_words(int pattern_id,
 		COMPLETE_WITH("SELECT");
 
 /* CREATE MATERIALIZED VIEW */
-	else if (Matches("CREATE", "MATERIALIZED"))
+	else if (Matches("CREATE", "MATERIALIZED") ||
+			 Matches("CREATE", "INCREMENTAL", "MATERIALIZED"))
 		COMPLETE_WITH("VIEW");
-	/* Complete CREATE MATERIALIZED VIEW <name> with AS or USING */
-	else if (Matches("CREATE", "MATERIALIZED", "VIEW", MatchAny))
-		COMPLETE_WITH("AS", "USING");
 
+	/* Complete CREATE [INCREMENTAL] MATERIALIZED VIEW <name> with AS or USING */
+	else if (Matches("CREATE", "MATERIALIZED", "VIEW", MatchAny) ||
+			 Matches("CREATE", "INCREMENTAL", "MATERIALIZED", "VIEW", MatchAny))
+		COMPLETE_WITH("AS", "USING");
 	/*
-	 * Complete CREATE MATERIALIZED VIEW <name> USING with list of access
-	 * methods
+	 * Complete CREATE [INCREMENTAL] MATERIALIZED VIEW <name> USING with list
+	 * of access methods
 	 */
-	else if (Matches("CREATE", "MATERIALIZED", "VIEW", MatchAny, "USING"))
+	else if (Matches("CREATE", "MATERIALIZED", "VIEW", MatchAny, "USING") ||
+			 Matches("CREATE", "INCREMENTAL", "MATERIALIZED", "VIEW", MatchAny, "USING"))
 		COMPLETE_WITH_QUERY(Query_for_list_of_table_access_methods);
-	/* Complete CREATE MATERIALIZED VIEW <name> USING <access method> with AS */
-	else if (Matches("CREATE", "MATERIALIZED", "VIEW", MatchAny, "USING", MatchAny))
+	/* Complete CREATE [INCREMENTAL] MATERIALIZED VIEW <name> USING <am> with AS */
+	else if (Matches("CREATE", "MATERIALIZED", "VIEW", MatchAny, "USING", MatchAny) ||
+			 Matches("CREATE", "INCREMENTAL", "MATERIALIZED", "VIEW", MatchAny, "USING", MatchAny))
 		COMPLETE_WITH("AS");
-
 	/*
-	 * Complete CREATE MATERIALIZED VIEW <name> [USING <access method> ] AS
+	 * Complete CREATE [INCREMENTAL] MATERIALIZED VIEW <name> [USING <am>] AS
 	 * with "SELECT"
 	 */
 	else if (Matches("CREATE", "MATERIALIZED", "VIEW", MatchAny, "AS") ||
-			 Matches("CREATE", "MATERIALIZED", "VIEW", MatchAny, "USING", MatchAny, "AS"))
+			 Matches("CREATE", "MATERIALIZED", "VIEW", MatchAny, "USING", MatchAny, "AS") ||
+			 Matches("CREATE", "INCREMENTAL", "MATERIALIZED", "VIEW", MatchAny, "AS") ||
+			 Matches("CREATE", "INCREMENTAL", "MATERIALIZED", "VIEW", MatchAny, "USING", MatchAny, "AS"))
 		COMPLETE_WITH("SELECT");
 
 /* CREATE EVENT TRIGGER */
-- 
2.43.0


--Multipart=_Fri__3_Jul_2026_19_11_16_+0900_CskxSIu_iGcDMEyM
Content-Type: text/x-diff;
 name="v39-0004-Add-Incremental-View-Maintenance-support-to-pg_d.patch"
Content-Disposition: attachment;
 filename="v39-0004-Add-Incremental-View-Maintenance-support-to-pg_d.patch"
Content-Transfer-Encoding: 7bit



^ permalink  raw  reply  [nested|flat] 101+ messages in thread

* [PATCH v39 5/8] Add Incremental View Maintenance support to psql
@ 2026-05-29 09:05  Yugo Nagata <[email protected]>
  0 siblings, 0 replies; 101+ messages in thread

From: Yugo Nagata @ 2026-05-29 09:05 UTC (permalink / raw)

Add tab completion and meta-command output for IVM.
---
 src/bin/psql/describe.c        | 32 +++++++++++++++++++++++++++++++-
 src/bin/psql/tab-complete.in.c | 30 ++++++++++++++++++------------
 2 files changed, 49 insertions(+), 13 deletions(-)

diff --git a/src/bin/psql/describe.c b/src/bin/psql/describe.c
index fef86b4cca3..5b7bf626c32 100644
--- a/src/bin/psql/describe.c
+++ b/src/bin/psql/describe.c
@@ -1580,6 +1580,7 @@ describeOneTableDetails(const char *schemaname,
 		char		relpersistence;
 		char		relreplident;
 		char	   *relam;
+		bool		isivm;
 	}			tableinfo;
 	bool		show_column_details = false;
 
@@ -1594,7 +1595,26 @@ describeOneTableDetails(const char *schemaname,
 	/* Get general table info */
 	printfPQExpBuffer(&buf, "/* %s */\n",
 					  _("Get general information about one relation"));
-	if (pset.sversion >= 120000)
+	if (pset.sversion >= 200000)
+	{
+		printfPQExpBuffer(&buf,
+						  "SELECT c.relchecks, c.relkind, c.relhasindex, c.relhasrules, "
+						  "c.relhastriggers, c.relrowsecurity, c.relforcerowsecurity, "
+						  "false AS relhasoids, c.relispartition, %s, c.reltablespace, "
+						  "CASE WHEN c.reloftype = 0 THEN '' ELSE c.reloftype::pg_catalog.regtype::pg_catalog.text END, "
+						  "c.relpersistence, c.relreplident, am.amname, "
+						  "c.relisivm\n"
+						  "FROM pg_catalog.pg_class c\n "
+						  "LEFT JOIN pg_catalog.pg_class tc ON (c.reltoastrelid = tc.oid)\n"
+						  "LEFT JOIN pg_catalog.pg_am am ON (c.relam = am.oid)\n"
+						  "WHERE c.oid = '%s';",
+						  (verbose ?
+						   "pg_catalog.array_to_string(c.reloptions || "
+						   "array(select 'toast.' || x from pg_catalog.unnest(tc.reloptions) x), ', ')\n"
+						   : "''"),
+						  oid);
+	}
+	else if (pset.sversion >= 120000)
 	{
 		appendPQExpBuffer(&buf,
 						  "SELECT c.relchecks, c.relkind, c.relhasindex, c.relhasrules, "
@@ -1662,6 +1682,10 @@ describeOneTableDetails(const char *schemaname,
 			NULL : pg_strdup(PQgetvalue(res, 0, 14));
 	else
 		tableinfo.relam = NULL;
+	if (pset.sversion >= 200000)
+		tableinfo.isivm = strcmp(PQgetvalue(res, 0, 15), "t") == 0;
+	else
+		tableinfo.isivm = false;
 	PQclear(res);
 	res = NULL;
 
@@ -3670,6 +3694,12 @@ describeOneTableDetails(const char *schemaname,
 			printfPQExpBuffer(&buf, _("Access method: %s"), tableinfo.relam);
 			printTableAddFooter(&cont, buf.data);
 		}
+
+		/* Incremental view maintance info */
+		if (verbose && tableinfo.relkind == RELKIND_MATVIEW && tableinfo.isivm)
+		{
+			printTableAddFooter(&cont, _("Incremental view maintenance: yes"));
+		}
 	}
 
 	/* reloptions, if verbose */
diff --git a/src/bin/psql/tab-complete.in.c b/src/bin/psql/tab-complete.in.c
index e4bc2c93145..6dfad8a8102 100644
--- a/src/bin/psql/tab-complete.in.c
+++ b/src/bin/psql/tab-complete.in.c
@@ -1320,6 +1320,7 @@ static const pgsql_thing_t words_after_create[] = {
 	{"FOREIGN TABLE", NULL, NULL, NULL},
 	{"FUNCTION", NULL, NULL, Query_for_list_of_functions},
 	{"GROUP", Query_for_list_of_roles},
+	{"INCREMENTAL MATERIALIZED VIEW", NULL, NULL, &Query_for_list_of_matviews, NULL, THING_NO_DROP | THING_NO_ALTER},
 	{"INDEX", NULL, NULL, &Query_for_list_of_indexes},
 	{"LANGUAGE", Query_for_list_of_languages},
 	{"LARGE OBJECT", NULL, NULL, NULL, NULL, THING_NO_CREATE | THING_NO_DROP},
@@ -4242,28 +4243,33 @@ match_previous_words(int pattern_id,
 		COMPLETE_WITH("SELECT");
 
 /* CREATE MATERIALIZED VIEW */
-	else if (Matches("CREATE", "MATERIALIZED"))
+	else if (Matches("CREATE", "MATERIALIZED") ||
+			 Matches("CREATE", "INCREMENTAL", "MATERIALIZED"))
 		COMPLETE_WITH("VIEW");
-	/* Complete CREATE MATERIALIZED VIEW <name> with AS or USING */
-	else if (Matches("CREATE", "MATERIALIZED", "VIEW", MatchAny))
-		COMPLETE_WITH("AS", "USING");
 
+	/* Complete CREATE [INCREMENTAL] MATERIALIZED VIEW <name> with AS or USING */
+	else if (Matches("CREATE", "MATERIALIZED", "VIEW", MatchAny) ||
+			 Matches("CREATE", "INCREMENTAL", "MATERIALIZED", "VIEW", MatchAny))
+		COMPLETE_WITH("AS", "USING");
 	/*
-	 * Complete CREATE MATERIALIZED VIEW <name> USING with list of access
-	 * methods
+	 * Complete CREATE [INCREMENTAL] MATERIALIZED VIEW <name> USING with list
+	 * of access methods
 	 */
-	else if (Matches("CREATE", "MATERIALIZED", "VIEW", MatchAny, "USING"))
+	else if (Matches("CREATE", "MATERIALIZED", "VIEW", MatchAny, "USING") ||
+			 Matches("CREATE", "INCREMENTAL", "MATERIALIZED", "VIEW", MatchAny, "USING"))
 		COMPLETE_WITH_QUERY(Query_for_list_of_table_access_methods);
-	/* Complete CREATE MATERIALIZED VIEW <name> USING <access method> with AS */
-	else if (Matches("CREATE", "MATERIALIZED", "VIEW", MatchAny, "USING", MatchAny))
+	/* Complete CREATE [INCREMENTAL] MATERIALIZED VIEW <name> USING <am> with AS */
+	else if (Matches("CREATE", "MATERIALIZED", "VIEW", MatchAny, "USING", MatchAny) ||
+			 Matches("CREATE", "INCREMENTAL", "MATERIALIZED", "VIEW", MatchAny, "USING", MatchAny))
 		COMPLETE_WITH("AS");
-
 	/*
-	 * Complete CREATE MATERIALIZED VIEW <name> [USING <access method> ] AS
+	 * Complete CREATE [INCREMENTAL] MATERIALIZED VIEW <name> [USING <am>] AS
 	 * with "SELECT"
 	 */
 	else if (Matches("CREATE", "MATERIALIZED", "VIEW", MatchAny, "AS") ||
-			 Matches("CREATE", "MATERIALIZED", "VIEW", MatchAny, "USING", MatchAny, "AS"))
+			 Matches("CREATE", "MATERIALIZED", "VIEW", MatchAny, "USING", MatchAny, "AS") ||
+			 Matches("CREATE", "INCREMENTAL", "MATERIALIZED", "VIEW", MatchAny, "AS") ||
+			 Matches("CREATE", "INCREMENTAL", "MATERIALIZED", "VIEW", MatchAny, "USING", MatchAny, "AS"))
 		COMPLETE_WITH("SELECT");
 
 /* CREATE EVENT TRIGGER */
-- 
2.43.0


--Multipart=_Fri__3_Jul_2026_19_11_16_+0900_CskxSIu_iGcDMEyM
Content-Type: text/x-diff;
 name="v39-0004-Add-Incremental-View-Maintenance-support-to-pg_d.patch"
Content-Disposition: attachment;
 filename="v39-0004-Add-Incremental-View-Maintenance-support-to-pg_d.patch"
Content-Transfer-Encoding: 7bit



^ permalink  raw  reply  [nested|flat] 101+ messages in thread

* [PATCH v39 6/8] Add Incremental View Maintenance support
@ 2026-05-29 09:06  Yugo Nagata <[email protected]>
  0 siblings, 0 replies; 101+ messages in thread

From: Yugo Nagata @ 2026-05-29 09:06 UTC (permalink / raw)

In this implementation, AFTER triggers are used to collect
tuplestores containing transition table contents. When multiple tables
are changed, multiple AFTER triggers are invoked, then the final AFTER
trigger performs actual update of the matview. In addition, BEFORE
triggers are also used to handle global information for view
maintenance.

To calculate view deltas, we need both pre-state and post-state of base
tables. Post-update states are available in AFTER trigger, and pre-update
states can be calculated by removing inserted tuples and appending deleted
tuples. Insterted tuples are filtered using the snapshot taken before
table modification, and deleted tuples are contained in the old transition
table.

Incrementally Maintainable Materialized Views (IMMV) can contain
duplicated tuples.

This patch also allows self-join, simultaneous updates of more than
one base table, and multiple updates of the same base table.
---
 src/backend/access/transam/xact.c             |    8 +
 src/backend/commands/createas.c               |  709 +++++++
 src/backend/commands/matview.c                | 1835 ++++++++++++++++-
 src/backend/commands/tablecmds.c              |    4 +
 .../utils/activity/wait_event_names.txt       |    1 +
 src/include/catalog/pg_proc.dat               |   10 +
 src/include/commands/createas.h               |    4 +
 src/include/commands/matview.h                |   11 +
 src/include/storage/lwlocklist.h              |    1 +
 src/include/storage/subsystemlist.h           |    3 +
 10 files changed, 2548 insertions(+), 38 deletions(-)

diff --git a/src/backend/access/transam/xact.c b/src/backend/access/transam/xact.c
index 3a89149016f..0e6cb5493d2 100644
--- a/src/backend/access/transam/xact.c
+++ b/src/backend/access/transam/xact.c
@@ -37,6 +37,7 @@
 #include "catalog/pg_enum.h"
 #include "catalog/storage.h"
 #include "commands/async.h"
+#include "commands/matview.h"
 #include "commands/tablecmds.h"
 #include "commands/trigger.h"
 #include "common/pg_prng.h"
@@ -2322,6 +2323,9 @@ CommitTransaction(void)
 	CallXactCallbacks(is_parallel_worker ? XACT_EVENT_PARALLEL_PRE_COMMIT
 					  : XACT_EVENT_PRE_COMMIT);
 
+	/* Store the transaction ID that updated the view incrementally */
+	AtPreCommit_IVM();
+
 	/*
 	 * If this xact has started any unfinished parallel operation, clean up
 	 * its workers, warning about leaked resources.  (But we don't actually
@@ -2973,6 +2977,7 @@ AbortTransaction(void)
 	AtAbort_Notify();
 	AtEOXact_RelationMap(false, is_parallel_worker);
 	AtAbort_Twophase();
+	AtAbort_IVM(InvalidSubTransactionId);
 
 	/*
 	 * Advertise the fact that we aborted in pg_xact (assuming that we got as
@@ -5304,6 +5309,9 @@ AbortSubTransaction(void)
 
 	UnlockBuffers();
 
+	/* Clean up hash entries for incremental view maintenance */
+	AtAbort_IVM(s->subTransactionId);
+
 	/* Reset WAL record construction state */
 	XLogResetInsertion();
 
diff --git a/src/backend/commands/createas.c b/src/backend/commands/createas.c
index 6dbb831ca89..a499688b79d 100644
--- a/src/backend/commands/createas.c
+++ b/src/backend/commands/createas.c
@@ -29,18 +29,32 @@
 #include "access/tableam.h"
 #include "access/xact.h"
 #include "catalog/namespace.h"
+#include "catalog/index.h"
+#include "catalog/pg_am_d.h"
+#include "catalog/pg_constraint.h"
+#include "catalog/pg_inherits.h"
+#include "catalog/pg_trigger.h"
 #include "catalog/toasting.h"
 #include "commands/createas.h"
+#include "commands/defrem.h"
 #include "commands/matview.h"
 #include "commands/prepare.h"
 #include "commands/tablecmds.h"
+#include "commands/tablespace.h"
+#include "commands/trigger.h"
 #include "commands/view.h"
 #include "executor/execdesc.h"
 #include "executor/executor.h"
+#include "miscadmin.h"
 #include "nodes/makefuncs.h"
 #include "nodes/nodeFuncs.h"
 #include "nodes/queryjumble.h"
+#include "optimizer/optimizer.h"
+#include "optimizer/prep.h"
 #include "parser/analyze.h"
+#include "parser/parser.h"
+#include "parser/parsetree.h"
+#include "parser/parse_clause.h"
 #include "rewrite/rewriteHandler.h"
 #include "tcop/tcopprot.h"
 #include "utils/builtins.h"
@@ -70,6 +84,12 @@ static bool intorel_receive(TupleTableSlot *slot, DestReceiver *self);
 static void intorel_shutdown(DestReceiver *self);
 static void intorel_destroy(DestReceiver *self);
 
+static void CreateIvmTriggersOnBaseTablesRecurse(Query *qry, Node *node, Oid matviewOid,
+									 List **relids, bool ex_lock);
+static void CreateIvmTrigger(Oid relOid, Oid viewOid, int16 type, int16 timing, bool ex_lock);
+static void check_ivm_restriction(Node *node);
+static bool check_ivm_restriction_walker(Node *node, void *context);
+static Bitmapset *get_primary_key_attnos_from_query(Query *query, List **constraintList);
 
 /*
  * create_ctas_internal
@@ -277,6 +297,18 @@ ExecCreateTableAs(ParseState *pstate, CreateTableAsStmt *stmt,
 		into->skipData = true;
 	}
 
+	if (is_matview && into->ivm)
+	{
+		/* check if the query is supported in IMMV definition */
+		if (contain_mutable_functions((Node *) query))
+			ereport(ERROR,
+					(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+					 errmsg("mutable function is not supported on incrementally maintainable materialized view"),
+					 errhint("functions must be marked IMMUTABLE")));
+
+		check_ivm_restriction((Node *) query);
+	}
+
 	if (into->skipData)
 	{
 		/*
@@ -287,15 +319,36 @@ ExecCreateTableAs(ParseState *pstate, CreateTableAsStmt *stmt,
 		 */
 		address = create_ctas_nodata(query->targetList, into);
 
+		/*
+		 * For IVM, mark the matview before refresh so RelationIsIVM()
+		 * returns true inside RefreshMatViewByOid.
+		 */
+		if (is_matview && into->ivm)
+		{
+			Relation matviewRel = table_open(address.objectId, NoLock);
+
+			SetMatViewIVMState(matviewRel, true);
+			table_close(matviewRel, NoLock);
+			CommandCounterIncrement();
+		}
+
 		/*
 		 * For materialized views, reuse the REFRESH logic, which locks down
 		 * security-restricted operations and restricts the search_path.  This
 		 * reduces the chance that a subsequent refresh will fail.
 		 */
 		if (do_refresh)
+		{
 			RefreshMatViewByOid(address.objectId, true, false, false,
 								pstate->p_sourcetext, qc);
 
+			if (is_matview && into->ivm && IsolationUsesXactSnapshot())
+				ereport(WARNING,
+						(errmsg("inconsistent view can be created in isolation level SERIALIZABLE or REPEATABLE READ"),
+						 errdetail("The view may not include effects of a concurrent transaction."),
+						 errhint("The view with incremental maintenance should be created in isolation level READ COMMITTED, "
+								 "or refreshed manually to make sure the view is consistent.")));
+		}
 	}
 	else
 	{
@@ -635,3 +688,659 @@ intorel_destroy(DestReceiver *self)
 {
 	pfree(self);
 }
+
+/*
+ * CreateIvmTriggersOnBaseTables -- create IVM triggers on all base tables
+ */
+void
+CreateIvmTriggersOnBaseTables(Query *qry, Oid matviewOid)
+{
+	List   *relids = NIL;
+	bool	ex_lock = false;
+	RangeTblEntry *rte;
+
+	/* Immediately return if we don't have any base tables. */
+	if (list_length(qry->rtable) < 1)
+		return;
+
+	/*
+	 * If the view has more than one base tables, we need an exclusive lock
+	 * on the view so that the view would be maintained serially to avoid
+	 * the inconsistency that occurs when two base tables are modified in
+	 * concurrent transactions. However, if the view has only one table,
+	 * we can use a weaker lock.
+	 *
+	 * The type of lock should be determined here, because if we check the
+	 * view definition at maintenance time, we need to acquire a weaker lock,
+	 * and upgrading the lock level after this increases probability of
+	 * deadlock.
+	 */
+
+	rte = list_nth(qry->rtable, 0);
+	if (list_length(qry->rtable) > 1 || rte->rtekind != RTE_RELATION)
+		ex_lock = true;
+
+	CreateIvmTriggersOnBaseTablesRecurse(qry, (Node *)qry, matviewOid, &relids, ex_lock);
+
+	list_free(relids);
+}
+
+static void
+CreateIvmTriggersOnBaseTablesRecurse(Query *qry, Node *node, Oid matviewOid,
+									 List **relids, bool ex_lock)
+{
+	if (node == NULL)
+		return;
+
+	/* This can recurse, so check for excessive recursion */
+	check_stack_depth();
+
+	switch (nodeTag(node))
+	{
+		case T_Query:
+			{
+				Query *query = (Query *) node;
+
+				CreateIvmTriggersOnBaseTablesRecurse(qry, (Node *)query->jointree, matviewOid, relids, ex_lock);
+			}
+			break;
+
+		case T_RangeTblRef:
+			{
+				int			rti = ((RangeTblRef *) node)->rtindex;
+				RangeTblEntry *rte = rt_fetch(rti, qry->rtable);
+
+				if (rte->rtekind == RTE_RELATION && !list_member_oid(*relids, rte->relid))
+				{
+					CreateIvmTrigger(rte->relid, matviewOid, TRIGGER_TYPE_INSERT, TRIGGER_TYPE_BEFORE, ex_lock);
+					CreateIvmTrigger(rte->relid, matviewOid, TRIGGER_TYPE_DELETE, TRIGGER_TYPE_BEFORE, ex_lock);
+					CreateIvmTrigger(rte->relid, matviewOid, TRIGGER_TYPE_UPDATE, TRIGGER_TYPE_BEFORE, ex_lock);
+					CreateIvmTrigger(rte->relid, matviewOid, TRIGGER_TYPE_TRUNCATE, TRIGGER_TYPE_BEFORE, true);
+					CreateIvmTrigger(rte->relid, matviewOid, TRIGGER_TYPE_INSERT, TRIGGER_TYPE_AFTER, ex_lock);
+					CreateIvmTrigger(rte->relid, matviewOid, TRIGGER_TYPE_DELETE, TRIGGER_TYPE_AFTER, ex_lock);
+					CreateIvmTrigger(rte->relid, matviewOid, TRIGGER_TYPE_UPDATE, TRIGGER_TYPE_AFTER, ex_lock);
+					CreateIvmTrigger(rte->relid, matviewOid, TRIGGER_TYPE_TRUNCATE, TRIGGER_TYPE_AFTER, true);
+
+					*relids = lappend_oid(*relids, rte->relid);
+				}
+			}
+			break;
+
+		case T_FromExpr:
+			{
+				FromExpr   *f = (FromExpr *) node;
+				ListCell   *l;
+
+				foreach(l, f->fromlist)
+					CreateIvmTriggersOnBaseTablesRecurse(qry, lfirst(l), matviewOid, relids, ex_lock);
+			}
+			break;
+
+		case T_JoinExpr:
+			{
+				JoinExpr   *j = (JoinExpr *) node;
+
+				CreateIvmTriggersOnBaseTablesRecurse(qry, j->larg, matviewOid, relids, ex_lock);
+				CreateIvmTriggersOnBaseTablesRecurse(qry, j->rarg, matviewOid, relids, ex_lock);
+			}
+			break;
+
+		default:
+			elog(ERROR, "unrecognized node type: %d", (int) nodeTag(node));
+	}
+}
+
+/*
+ * CreateIvmTrigger -- create IVM trigger on a base table
+ */
+static void
+CreateIvmTrigger(Oid relOid, Oid viewOid, int16 type, int16 timing, bool ex_lock)
+{
+	ObjectAddress	refaddr;
+	ObjectAddress	address;
+	CreateTrigStmt *ivm_trigger;
+	List *transitionRels = NIL;
+
+	Assert(timing == TRIGGER_TYPE_BEFORE || timing == TRIGGER_TYPE_AFTER);
+
+	refaddr.classId = RelationRelationId;
+	refaddr.objectId = viewOid;
+	refaddr.objectSubId = 0;
+
+	ivm_trigger = makeNode(CreateTrigStmt);
+	ivm_trigger->relation = NULL;
+	ivm_trigger->row = false;
+
+	ivm_trigger->timing = timing;
+	ivm_trigger->events = type;
+
+	switch (type)
+	{
+		case TRIGGER_TYPE_INSERT:
+			ivm_trigger->trigname = (timing == TRIGGER_TYPE_BEFORE ? "IVM_trigger_ins_before" : "IVM_trigger_ins_after");
+			break;
+		case TRIGGER_TYPE_DELETE:
+			ivm_trigger->trigname = (timing == TRIGGER_TYPE_BEFORE ? "IVM_trigger_del_before" : "IVM_trigger_del_after");
+			break;
+		case TRIGGER_TYPE_UPDATE:
+			ivm_trigger->trigname = (timing == TRIGGER_TYPE_BEFORE ? "IVM_trigger_upd_before" : "IVM_trigger_upd_after");
+			break;
+		case TRIGGER_TYPE_TRUNCATE:
+			ivm_trigger->trigname = (timing == TRIGGER_TYPE_BEFORE ? "IVM_trigger_truncate_before" : "IVM_trigger_truncate_after");
+			break;
+		default:
+			elog(ERROR, "unsupported trigger type");
+	}
+
+	if (timing == TRIGGER_TYPE_AFTER)
+	{
+		if (type == TRIGGER_TYPE_INSERT || type == TRIGGER_TYPE_UPDATE)
+		{
+			TriggerTransition *n = makeNode(TriggerTransition);
+			n->name = "__ivm_newtable";
+			n->isNew = true;
+			n->isTable = true;
+
+			transitionRels = lappend(transitionRels, n);
+		}
+		if (type == TRIGGER_TYPE_DELETE || type == TRIGGER_TYPE_UPDATE)
+		{
+			TriggerTransition *n = makeNode(TriggerTransition);
+			n->name = "__ivm_oldtable";
+			n->isNew = false;
+			n->isTable = true;
+
+			transitionRels = lappend(transitionRels, n);
+		}
+	}
+
+	/*
+	 * XXX: When using DELETE or UPDATE, we must use exclusive lock for now
+	 * because apply_old_delta(_with_count) uses ctid to identify the tuple
+	 * to be deleted/deleted, but doesn't work in concurrent situations.
+	 *
+	 * If the view doesn't have aggregate, distinct, or tuple duplicate,
+	 * then it would work even in concurrent situations. However, we don't have
+	 * any way to guarantee the view has a unique key before opening the IMMV
+	 * at the maintenance time because users may drop the unique index.
+	 */
+
+	if (type == TRIGGER_TYPE_DELETE || type == TRIGGER_TYPE_UPDATE)
+		ex_lock = true;
+
+	ivm_trigger->funcname =
+		(timing == TRIGGER_TYPE_BEFORE ? SystemFuncName("IVM_immediate_before") : SystemFuncName("IVM_immediate_maintenance"));
+
+	ivm_trigger->columns = NIL;
+	ivm_trigger->transitionRels = transitionRels;
+	ivm_trigger->whenClause = NULL;
+	ivm_trigger->isconstraint = false;
+	ivm_trigger->deferrable = false;
+	ivm_trigger->initdeferred = false;
+	ivm_trigger->constrrel = NULL;
+	ivm_trigger->args = list_make2(
+		makeString(DatumGetPointer(DirectFunctionCall1(oidout, ObjectIdGetDatum(viewOid)))),
+		makeString(DatumGetPointer(DirectFunctionCall1(boolout, BoolGetDatum(ex_lock))))
+		);
+
+	address = CreateTrigger(ivm_trigger, NULL, relOid, InvalidOid, InvalidOid,
+						 InvalidOid, InvalidOid, InvalidOid, NULL, true, false);
+
+	recordDependencyOn(&address, &refaddr, DEPENDENCY_AUTO);
+
+	/* Make changes-so-far visible */
+	CommandCounterIncrement();
+}
+
+/*
+ * check_ivm_restriction --- look for specify nodes in the query tree
+ */
+static void
+check_ivm_restriction(Node *node)
+{
+	check_ivm_restriction_walker(node, NULL);
+}
+
+static bool
+check_ivm_restriction_walker(Node *node, void *context)
+{
+	if (node == NULL)
+		return false;
+
+	/*
+	 * We currently don't support Sub-Query.
+	 */
+	if (IsA(node, SubPlan) || IsA(node, SubLink))
+		ereport(ERROR,
+				(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+				 errmsg("subquery is not supported on incrementally maintainable materialized view")));
+
+	/* This can recurse, so check for excessive recursion */
+	check_stack_depth();
+
+	switch (nodeTag(node))
+	{
+		case T_Query:
+			{
+				Query *qry = (Query *)node;
+				ListCell   *lc;
+				List       *vars;
+
+				/* if contained CTE, return error */
+				if (qry->cteList != NIL)
+					ereport(ERROR,
+							(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+							 errmsg("CTE is not supported on incrementally maintainable materialized view")));
+				if (qry->havingQual != NULL)
+					ereport(ERROR,
+							(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+							 errmsg(" HAVING clause is not supported on incrementally maintainable materialized view")));
+				if (qry->sortClause != NIL)	/* There is a possibility that we don't need to return an error */
+					ereport(ERROR,
+							(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+							 errmsg("ORDER BY clause is not supported on incrementally maintainable materialized view")));
+				if (qry->limitOffset != NULL || qry->limitCount != NULL)
+					ereport(ERROR,
+							(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+							 errmsg("LIMIT/OFFSET clause is not supported on incrementally maintainable materialized view")));
+				if (qry->distinctClause)
+					ereport(ERROR,
+							(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+							 errmsg("DISTINCT is not supported on incrementally maintainable materialized view")));
+				if (qry->hasDistinctOn)
+					ereport(ERROR,
+							(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+							 errmsg("DISTINCT ON is not supported on incrementally maintainable materialized view")));
+				if (qry->hasWindowFuncs)
+					ereport(ERROR,
+							(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+							 errmsg("window functions are not supported on incrementally maintainable materialized view")));
+				if (qry->groupingSets != NIL)
+					ereport(ERROR,
+							(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+							 errmsg("GROUPING SETS, ROLLUP, or CUBE clauses is not supported on incrementally maintainable materialized view")));
+				if (qry->setOperations != NULL)
+					ereport(ERROR,
+							(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+							 errmsg("UNION/INTERSECT/EXCEPT statements are not supported on incrementally maintainable materialized view")));
+				if (list_length(qry->targetList) == 0)
+					ereport(ERROR,
+							(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+							 errmsg("empty target list is not supported on incrementally maintainable materialized view")));
+				if (qry->rowMarks != NIL)
+					ereport(ERROR,
+							(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+							 errmsg("FOR UPDATE/SHARE clause is not supported on incrementally maintainable materialized view")));
+
+				/* system column restrictions */
+				vars = pull_vars_of_level((Node *) qry, 0);
+				foreach(lc, vars)
+				{
+					if (IsA(lfirst(lc), Var))
+					{
+						Var *var = (Var *) lfirst(lc);
+						/* if system column, return error */
+						if (var->varattno < 0)
+							ereport(ERROR,
+									(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+									 errmsg("system column is not supported on incrementally maintainable materialized view")));
+					}
+				}
+
+				/* check if type in the target list had an equality operator */
+				foreach(lc, qry->targetList)
+				{
+					TargetEntry *tle = (TargetEntry *) lfirst(lc);
+					Oid             atttype = exprType((Node *) tle->expr);
+					Oid             opclass;
+
+					opclass = GetDefaultOpClass(atttype, BTREE_AM_OID);
+					if (!OidIsValid(opclass))
+						ereport(ERROR,
+								(errcode(ERRCODE_UNDEFINED_OBJECT),
+								 errmsg("data type %s has no default operator class for access method \"%s\"",
+									format_type_be(atttype), "btree")));
+				}
+
+				/* restrictions for rtable */
+				foreach(lc, qry->rtable)
+				{
+					RangeTblEntry *rte = (RangeTblEntry *) lfirst(lc);
+
+					if (rte->subquery)
+						ereport(ERROR,
+								(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+								 errmsg("subquery is not supported on incrementally maintainable materialized view")));
+
+					if (rte->tablesample != NULL)
+						ereport(ERROR,
+								(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+								 errmsg("TABLESAMPLE clause is not supported on incrementally maintainable materialized view")));
+
+					if (rte->relkind == RELKIND_PARTITIONED_TABLE)
+						ereport(ERROR,
+								(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+								 errmsg("partitioned table is not supported on incrementally maintainable materialized view")));
+
+					if (rte->relkind == RELKIND_RELATION && has_superclass(rte->relid))
+						ereport(ERROR,
+								(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+								 errmsg("partitions is not supported on incrementally maintainable materialized view")));
+
+					if (rte->relkind == RELKIND_RELATION && find_inheritance_children(rte->relid, NoLock) != NIL)
+						ereport(ERROR,
+								(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+								 errmsg("inheritance parent is not supported on incrementally maintainable materialized view")));
+
+					if (rte->relkind == RELKIND_FOREIGN_TABLE)
+						ereport(ERROR,
+								(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+								 errmsg("foreign table is not supported on incrementally maintainable materialized view")));
+
+					if (rte->relkind == RELKIND_VIEW ||
+						rte->relkind == RELKIND_MATVIEW)
+						ereport(ERROR,
+								(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+								 errmsg("VIEW or MATERIALIZED VIEW is not supported on incrementally maintainable materialized view")));
+
+					if (rte->rtekind == RTE_VALUES)
+						ereport(ERROR,
+								(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+								 errmsg("VALUES is not supported on incrementally maintainable materialized view")));
+
+				}
+
+				query_tree_walker(qry, check_ivm_restriction_walker, NULL, QTW_IGNORE_RANGE_TABLE);
+
+				break;
+			}
+		case T_TargetEntry:
+			{
+				TargetEntry *tle = (TargetEntry *)node;
+				if (isIvmName(tle->resname))
+						ereport(ERROR,
+								(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+								 errmsg("column name %s is not supported on incrementally maintainable materialized view", tle->resname)));
+
+				expression_tree_walker(node, check_ivm_restriction_walker, NULL);
+				break;
+			}
+		case T_JoinExpr:
+			{
+				JoinExpr *joinexpr = (JoinExpr *)node;
+
+				if (joinexpr->jointype > JOIN_INNER)
+						ereport(ERROR,
+								(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+								 errmsg("OUTER JOIN is not supported on incrementally maintainable materialized view")));
+
+				expression_tree_walker(node, check_ivm_restriction_walker, NULL);
+			}
+			break;
+		case T_Aggref:
+			ereport(ERROR,
+					(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+					 errmsg("aggregate function is not supported on incrementally maintainable materialized view")));
+			break;
+		default:
+			expression_tree_walker(node, check_ivm_restriction_walker, (void *) context);
+			break;
+	}
+	return false;
+}
+
+/*
+ * CreateIndexOnIMMV
+ *
+ * Create a unique index on incremental maintainable materialized view.
+ * If the view definition query has a GROUP BY clause, the index is created
+ * on the columns of GROUP BY expressions. Otherwise, if the view contains
+ * all primary key attributes of its base tables in the target list, the index
+ * is created on these attributes. In other cases, no index is created.
+ */
+void
+CreateIndexOnIMMV(Query *query, Relation matviewRel)
+{
+	ListCell *lc;
+	IndexStmt  *index;
+	ObjectAddress address;
+	List *constraintList = NIL;
+	char		idxname[NAMEDATALEN];
+	List	   *indexoidlist = RelationGetIndexList(matviewRel);
+	ListCell   *indexoidscan;
+	Bitmapset *key_attnos;
+
+	snprintf(idxname, sizeof(idxname), "%s_index", RelationGetRelationName(matviewRel));
+
+	index = makeNode(IndexStmt);
+
+	index->unique = true;
+	index->primary = false;
+	index->isconstraint = false;
+	index->deferrable = false;
+	index->initdeferred = false;
+	index->idxname = idxname;
+	index->relation =
+		makeRangeVar(get_namespace_name(RelationGetNamespace(matviewRel)),
+					 pstrdup(RelationGetRelationName(matviewRel)),
+					 -1);
+	index->accessMethod = DEFAULT_INDEX_TYPE;
+	index->options = NIL;
+	index->tableSpace = get_tablespace_name(matviewRel->rd_rel->reltablespace);
+	index->whereClause = NULL;
+	index->indexParams = NIL;
+	index->indexIncludingParams = NIL;
+	index->excludeOpNames = NIL;
+	index->idxcomment = NULL;
+	index->indexOid = InvalidOid;
+	index->oldNumber = InvalidRelFileNumber;
+	index->oldCreateSubid = InvalidSubTransactionId;
+	index->oldFirstRelfilelocatorSubid = InvalidSubTransactionId;
+	index->transformed = true;
+	index->concurrent = false;
+	index->if_not_exists = false;
+
+	/* create index on the base tables' primary key columns */
+	key_attnos = get_primary_key_attnos_from_query(query, &constraintList);
+	if (key_attnos)
+	{
+		foreach(lc, query->targetList)
+		{
+			TargetEntry *tle = (TargetEntry *) lfirst(lc);
+			Form_pg_attribute attr = TupleDescAttr(matviewRel->rd_att, tle->resno - 1);
+
+			if (bms_is_member(tle->resno - FirstLowInvalidHeapAttributeNumber, key_attnos))
+			{
+				IndexElem  *iparam;
+
+				iparam = makeNode(IndexElem);
+				iparam->name = pstrdup(NameStr(attr->attname));
+				iparam->expr = NULL;
+				iparam->indexcolname = NULL;
+				iparam->collation = NIL;
+				iparam->opclass = NIL;
+				iparam->opclassopts = NIL;
+				iparam->ordering = SORTBY_DEFAULT;
+				iparam->nulls_ordering = SORTBY_NULLS_DEFAULT;
+				index->indexParams = lappend(index->indexParams, iparam);
+			}
+		}
+	}
+	else
+	{
+		/* create no index, just notice that an appropriate index is necessary for efficient IVM */
+		ereport(NOTICE,
+				(errmsg("could not create an index on materialized view \"%s\" automatically",
+						RelationGetRelationName(matviewRel)),
+				 errdetail("This target list does not have all the primary key columns. "),
+				 errhint("Create an index on the materialized view for efficient incremental maintenance.")));
+		return;
+	}
+
+	/* If we have a compatible index, we don't need to create another. */
+	foreach(indexoidscan, indexoidlist)
+	{
+		Oid			indexoid = lfirst_oid(indexoidscan);
+		Relation	indexRel;
+		bool		hasCompatibleIndex = false;
+
+		indexRel = index_open(indexoid, AccessShareLock);
+
+		if (CheckIndexCompatible(indexRel->rd_id,
+								index->accessMethod,
+								index->indexParams,
+								index->excludeOpNames,
+								false))
+			hasCompatibleIndex = true;
+
+		index_close(indexRel, AccessShareLock);
+
+		if (hasCompatibleIndex)
+			return;
+	}
+
+	address = DefineIndex(NULL,
+						  RelationGetRelid(matviewRel),
+						  index,
+						  InvalidOid,
+						  InvalidOid,
+						  InvalidOid,
+						  -1,
+						  false, true, false, false, true);
+
+	ereport(NOTICE,
+			(errmsg("created index \"%s\" on materialized view \"%s\"",
+					idxname, RelationGetRelationName(matviewRel))));
+
+	/*
+	 * Make dependencies so that the index is dropped if any base tables'
+	 * primary key is dropped.
+	 */
+	foreach(lc, constraintList)
+	{
+		Oid constraintOid = lfirst_oid(lc);
+		ObjectAddress	refaddr;
+
+		refaddr.classId = ConstraintRelationId;
+		refaddr.objectId = constraintOid;
+		refaddr.objectSubId = 0;
+
+		recordDependencyOn(&address, &refaddr, DEPENDENCY_NORMAL);
+	}
+}
+
+
+/*
+ * get_primary_key_attnos_from_query
+ *
+ * Identify the columns in base tables' primary keys in the target list.
+ *
+ * Returns a Bitmapset of the column attnos of the primary key's columns of
+ * tables that used in the query.  The attnos are offset by
+ * FirstLowInvalidHeapAttributeNumber as same as get_primary_key_attnos.
+ *
+ * If any table has no primary key or any primary key's columns is not in
+ * the target list, return NULL.  We also return NULL if any pkey constraint
+ * is deferrable.
+ *
+ * constraintList is set to a list of the OIDs of the pkey constraints.
+ */
+static Bitmapset *
+get_primary_key_attnos_from_query(Query *query, List **constraintList)
+{
+	List *key_attnos_list = NIL;
+	ListCell *lc;
+	int i;
+	Bitmapset *keys = NULL;
+	Relids	rels_in_from;
+
+	/*
+	 * Collect primary key attributes from all tables used in query. The key attributes
+	 * sets for each table are stored in key_attnos_list in order by RTE index.
+	 */
+	foreach(lc, query->rtable)
+	{
+		RangeTblEntry *r = (RangeTblEntry*) lfirst(lc);
+		Bitmapset *key_attnos;
+		bool	has_no_pkey = false;
+
+		/* for tables, call get_primary_key_attnos */
+		if (r->rtekind == RTE_RELATION)
+		{
+			Oid constraintOid;
+			key_attnos = get_primary_key_attnos(r->relid, false, &constraintOid);
+			*constraintList = lappend_oid(*constraintList, constraintOid);
+			has_no_pkey = (key_attnos == NULL);
+		}
+		/*
+		 * Ignore join rels, because they are flatten later by
+		 * flatten_join_alias_vars(). Store NULL into key_attnos_list
+		 * as a dummy.
+		 */
+		 else if (r->rtekind == RTE_JOIN)
+		 {
+			key_attnos = NULL;
+		}
+		/* for other RTEs, store NULL into key_attnos_list */
+		else
+			has_no_pkey = true;
+
+		/*
+		 * If any table or subquery has no primary key or its pkey constraint is deferrable,
+		 * we cannot get key attributes for this query, so return NULL.
+		 */
+		if (has_no_pkey)
+			return NULL;
+
+		key_attnos_list = lappend(key_attnos_list, key_attnos);
+	}
+
+	/* Collect key attributes appearing in the target list */
+	i = 1;
+	foreach(lc, query->targetList)
+	{
+		TargetEntry *tle = (TargetEntry *) flatten_join_alias_vars(NULL, query, lfirst(lc));
+
+		if (IsA(tle->expr, Var))
+		{
+			Var *var = (Var*) tle->expr;
+			Bitmapset *key_attnos = list_nth(key_attnos_list, var->varno - 1);
+
+			/* check if this attribute is from a base table's primary key */
+			if (bms_is_member(var->varattno - FirstLowInvalidHeapAttributeNumber, key_attnos))
+			{
+				/*
+				 * Remove found key attributes from key_attnos_list, and add this
+				 * to the result list.
+				 */
+				key_attnos = bms_del_member(key_attnos, var->varattno - FirstLowInvalidHeapAttributeNumber);
+				if (bms_is_empty(key_attnos))
+				{
+					key_attnos_list = list_delete_nth_cell(key_attnos_list, var->varno - 1);
+					key_attnos_list = list_insert_nth(key_attnos_list, var->varno - 1, NULL);
+				}
+				keys = bms_add_member(keys, i - FirstLowInvalidHeapAttributeNumber);
+			}
+		}
+		i++;
+	}
+
+	/* Collect RTE indexes of relations appearing in the FROM clause */
+	rels_in_from = get_relids_in_jointree((Node *) query->jointree, false, false);
+
+	/*
+	 * Check if all key attributes of relations in FROM are appearing in the target
+	 * list.  If an attribute remains in key_attnos_list in spite of the table is used
+	 * in FROM clause, the target is missing this key attribute, so we return NULL.
+	 */
+	i = 1;
+	foreach(lc, key_attnos_list)
+	{
+		Bitmapset *bms = (Bitmapset *)lfirst(lc);
+		if (!bms_is_empty(bms) && bms_is_member(i, rels_in_from))
+			return NULL;
+		i++;
+	}
+
+	return keys;
+}
diff --git a/src/backend/commands/matview.c b/src/backend/commands/matview.c
index f7d8007f796..eaf39f80cd3 100644
--- a/src/backend/commands/matview.c
+++ b/src/backend/commands/matview.c
@@ -23,24 +23,36 @@
 #include "catalog/indexing.h"
 #include "catalog/namespace.h"
 #include "catalog/pg_am.h"
+#include "catalog/pg_depend.h"
+#include "catalog/pg_trigger.h"
 #include "catalog/pg_opclass.h"
 #include "commands/matview.h"
 #include "commands/repack.h"
 #include "commands/tablecmds.h"
 #include "commands/tablespace.h"
+#include "commands/createas.h"
 #include "executor/executor.h"
 #include "executor/spi.h"
+#include "executor/tstoreReceiver.h"
 #include "miscadmin.h"
+#include "nodes/makefuncs.h"
+#include "parser/analyze.h"
+#include "parser/parse_clause.h"
+#include "parser/parse_func.h"
+#include "parser/parse_relation.h"
 #include "pgstat.h"
 #include "rewrite/rewriteHandler.h"
+#include "rewrite/rowsecurity.h"
 #include "storage/lmgr.h"
+#include "storage/lwlock.h"
 #include "tcop/tcopprot.h"
 #include "utils/builtins.h"
+#include "utils/fmgroids.h"
 #include "utils/lsyscache.h"
 #include "utils/rel.h"
 #include "utils/snapmgr.h"
 #include "utils/syscache.h"
-
+#include "utils/typcache.h"
 
 typedef struct
 {
@@ -53,6 +65,97 @@ typedef struct
 	BulkInsertState bistate;	/* bulk insert state */
 } DR_transientrel;
 
+#define MV_INIT_QUERYHASHSIZE	16
+
+/*
+ * MV_TriggerHashEntry
+ *
+ * Hash entry for base tables on which IVM trigger is invoked
+ */
+typedef struct MV_TriggerHashEntry
+{
+	Oid	matview_id;			/* OID of the materialized view */
+	int	before_trig_count;	/* count of before triggers invoked */
+	int	after_trig_count;	/* count of after triggers invoked */
+
+	Snapshot	snapshot;	/* Snapshot just before table change */
+
+	List   *tables;		/* List of MV_TriggerTable */
+	bool	has_old;	/* tuples are deleted from any table? */
+	bool	has_new;	/* tuples are inserted into any table? */
+
+	/*
+	 * List of sub-transaction IDs that incrementally updated the view.
+	 * This list is maintained through a transaction, and an ID is removed
+	 * when a sub-transaction is aborted. If any ID is left when the
+	 * transaction is committed, this means the view is incrementally
+	 * updated in this transaction.
+	 */
+	List   *subxids;
+} MV_TriggerHashEntry;
+
+/*
+ * MV_TriggerTable
+ *
+ * IVM related data for tables on which the trigger is invoked.
+ */
+typedef struct MV_TriggerTable
+{
+	Oid		table_id;			/* OID of the modified table */
+	List   *old_tuplestores;	/* tuplestores for deleted tuples */
+	List   *new_tuplestores;	/* tuplestores for inserted tuples */
+
+	List   *rte_indexes;		/* List of RTE index of the modified table */
+	RangeTblEntry *original_rte;	/* the original RTE saved before rewriting query */
+
+	Relation	rel;			/* relation of the modified table */
+	TupleTableSlot *slot;		/* for checking visibility in the pre-state table */
+} MV_TriggerTable;
+
+typedef struct DroppedImmvInfo
+{
+	Oid					immv_oid;
+	SubTransactionId	subxid;
+} DroppedImmvInfo;
+
+static HTAB *mv_trigger_info = NULL;
+static HTAB *dropped_immv = NULL;
+
+static HTAB *LastIvmUpdateHash;
+
+#define LAST_IVM_UPDATE_HASH_SIZE 256
+
+static void IvmShmemRequest(void *arg);
+
+/* hash table entries */
+typedef struct LastIvmUpdateEntry
+{
+	Oid		oid;	/* hash key */
+	FullTransactionId	last_ivm_update;
+} LastIvmUpdateEntry;
+
+const ShmemCallbacks IvmShmemCallbacks = {
+	.request_fn = IvmShmemRequest,
+};
+
+static void
+IvmShmemRequest(void *arg)
+{
+	ShmemRequestHash(.name = "LastIvmUpdate hash",
+					 .nelems = LAST_IVM_UPDATE_HASH_SIZE,
+					 .ptr = &LastIvmUpdateHash,
+					 .hash_info.keysize = sizeof(Oid),
+					 .hash_info.entrysize = sizeof(LastIvmUpdateEntry),
+					 .hash_flags = HASH_ELEM | HASH_BLOBS,
+		);
+}
+
+static bool in_delta_calculation = false;
+
+/* ENR name for materialized view delta */
+#define NEW_DELTA_ENRNAME "new_delta"
+#define OLD_DELTA_ENRNAME "old_delta"
+
 static int	matview_maintenance_depth = 0;
 
 static void transientrel_startup(DestReceiver *self, int operation, TupleDesc typeinfo);
@@ -60,6 +163,8 @@ static bool transientrel_receive(TupleTableSlot *slot, DestReceiver *self);
 static void transientrel_shutdown(DestReceiver *self);
 static void transientrel_destroy(DestReceiver *self);
 static uint64 refresh_matview_datafill(DestReceiver *dest, Query *query,
+									   QueryEnvironment *queryEnv,
+									   TupleDesc *resultTupleDesc,
 									   const char *queryString, bool is_create);
 static void refresh_by_match_merge(Oid matviewOid, Oid tempOid, Oid relowner,
 								   int save_sec_context);
@@ -67,6 +172,41 @@ static void refresh_by_heap_swap(Oid matviewOid, Oid OIDNewHeap, char relpersist
 static bool is_usable_unique_index(Relation indexRel);
 static void OpenMatViewIncrementalMaintenance(void);
 static void CloseMatViewIncrementalMaintenance(void);
+static Query *get_matview_query(Relation matviewRel);
+
+static Query *rewrite_query_for_preupdate_state(Query *query, List *tables,
+								  ParseState *pstate, Oid matviewid);
+static void register_delta_ENRs(ParseState *pstate, Query *query, List *tables);
+static char *make_subquery_targetlist_from_table(MV_TriggerTable *table);
+static char *make_delta_enr_name(const char *prefix, Oid relid, int count);
+static RangeTblEntry *get_prestate_rte(RangeTblEntry *rte, MV_TriggerTable *table,
+				 QueryEnvironment *queryEnv, Oid matviewid);
+static RangeTblEntry *makeDeltaTable(RangeTblEntry *rte, MV_TriggerTable *table,
+									 bool is_new, QueryEnvironment *queryEnv);
+static Query *rewrite_query_for_counting(Query *query, ParseState *pstate);
+
+static void calc_delta(MV_TriggerTable *table, int rte_index, Query *query,
+			DestReceiver *dest_old, DestReceiver *dest_new,
+			TupleDesc *tupdesc_old, TupleDesc *tupdesc_new,
+			QueryEnvironment *queryEnv);
+static Query *rewrite_query_for_postupdate_state(Query *query, MV_TriggerTable *table, int rte_index);
+
+static void apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *new_tuplestores,
+			TupleDesc tupdesc_old, TupleDesc tupdesc_new,
+			Query *query);
+static void apply_old_delta(const char *matviewname, const char *deltaname_old,
+				List *keys);
+static void apply_new_delta(const char *matviewname, const char *deltaname_new,
+				StringInfo target_list);
+static char *get_matching_condition_string(List *keys);
+static void generate_equal(StringInfo querybuf, Oid opttype,
+			   const char *leftop, const char *rightop);
+
+static void mv_InitHashTables(void);
+static void clean_up_IVM_hash_entry(MV_TriggerHashEntry *entry, bool is_abort,
+									SubTransactionId subxid);
+static void setLastUpdateXid(Oid immv_oid, FullTransactionId xid);
+static FullTransactionId getLastUpdateXid(Oid immv_oid);
 
 /*
  * SetMatViewPopulatedState
@@ -108,6 +248,46 @@ SetMatViewPopulatedState(Relation relation, bool newstate)
 	CommandCounterIncrement();
 }
 
+/*
+ * SetMatViewIVMState
+ *		Mark a materialized view as IVM, or not.
+ *
+ * NOTE: caller must be holding an appropriate lock on the relation.
+ */
+void
+SetMatViewIVMState(Relation relation, bool newstate)
+{
+	Relation	pgrel;
+	HeapTuple	tuple;
+
+	Assert(relation->rd_rel->relkind == RELKIND_MATVIEW);
+
+	/*
+	 * Update relation's pg_class entry.  Crucial side-effect: other backends
+	 * (and this one too!) are sent SI message to make them rebuild relcache
+	 * entries.
+	 */
+	pgrel = table_open(RelationRelationId, RowExclusiveLock);
+	tuple = SearchSysCacheCopy1(RELOID,
+								ObjectIdGetDatum(RelationGetRelid(relation)));
+	if (!HeapTupleIsValid(tuple))
+		elog(ERROR, "cache lookup failed for relation %u",
+			 RelationGetRelid(relation));
+
+	((Form_pg_class) GETSTRUCT(tuple))->relisivm = newstate;
+
+	CatalogTupleUpdate(pgrel, &tuple->t_self, tuple);
+
+	heap_freetuple(tuple);
+	table_close(pgrel, RowExclusiveLock);
+
+	/*
+	 * Advance command counter to make the updated pg_class row locally
+	 * visible.
+	 */
+	CommandCounterIncrement();
+}
+
 /*
  * ExecRefreshMatView -- execute a REFRESH MATERIALIZED VIEW command
  *
@@ -166,8 +346,6 @@ RefreshMatViewByOid(Oid matviewOid, bool is_create, bool skipData,
 					QueryCompletion *qc)
 {
 	Relation	matviewRel;
-	RewriteRule *rule;
-	List	   *actions;
 	Query	   *dataQuery;
 	Oid			tableSpace;
 	Oid			relowner;
@@ -178,6 +356,7 @@ RefreshMatViewByOid(Oid matviewOid, bool is_create, bool skipData,
 	int			save_sec_context;
 	int			save_nestlevel;
 	ObjectAddress address;
+	bool oldPopulated;
 
 	matviewRel = table_open(matviewOid, NoLock);
 	relowner = matviewRel->rd_rel->relowner;
@@ -193,6 +372,8 @@ RefreshMatViewByOid(Oid matviewOid, bool is_create, bool skipData,
 	save_nestlevel = NewGUCNestLevel();
 	RestrictSearchPath();
 
+	oldPopulated = RelationIsPopulated(matviewRel);
+
 	/* Make sure it is a materialized view. */
 	if (matviewRel->rd_rel->relkind != RELKIND_MATVIEW)
 		ereport(ERROR,
@@ -213,32 +394,7 @@ RefreshMatViewByOid(Oid matviewOid, bool is_create, bool skipData,
 				 errmsg("%s options %s and %s cannot be used together",
 						"REFRESH", "CONCURRENTLY", "WITH NO DATA")));
 
-	/*
-	 * Check that everything is correct for a refresh. Problems at this point
-	 * are internal errors, so elog is sufficient.
-	 */
-	if (matviewRel->rd_rel->relhasrules == false ||
-		matviewRel->rd_rules->numLocks < 1)
-		elog(ERROR,
-			 "materialized view \"%s\" is missing rewrite information",
-			 RelationGetRelationName(matviewRel));
-
-	if (matviewRel->rd_rules->numLocks > 1)
-		elog(ERROR,
-			 "materialized view \"%s\" has too many rules",
-			 RelationGetRelationName(matviewRel));
-
-	rule = matviewRel->rd_rules->rules[0];
-	if (rule->event != CMD_SELECT || !(rule->isInstead))
-		elog(ERROR,
-			 "the rule for materialized view \"%s\" is not a SELECT INSTEAD OF rule",
-			 RelationGetRelationName(matviewRel));
-
-	actions = rule->actions;
-	if (list_length(actions) != 1)
-		elog(ERROR,
-			 "the rule for materialized view \"%s\" is not a single action",
-			 RelationGetRelationName(matviewRel));
+	dataQuery = get_matview_query(matviewRel);
 
 	/*
 	 * Check that there is a unique index with no WHERE clause on one or more
@@ -275,12 +431,6 @@ RefreshMatViewByOid(Oid matviewOid, bool is_create, bool skipData,
 					 errhint("Create a unique index with no WHERE clause on one or more columns of the materialized view.")));
 	}
 
-	/*
-	 * The stored query was rewritten at the time of the MV definition, but
-	 * has not been scribbled on by the planner.
-	 */
-	dataQuery = linitial_node(Query, actions);
-
 	/*
 	 * Check for active uses of the relation in the current transaction, such
 	 * as open scans.
@@ -310,6 +460,90 @@ RefreshMatViewByOid(Oid matviewOid, bool is_create, bool skipData,
 		relpersistence = matviewRel->rd_rel->relpersistence;
 	}
 
+	/* delete IMMV triggers. */
+	if (RelationIsIVM(matviewRel) && skipData)
+	{
+		Relation	tgRel;
+		Relation	depRel;
+		ScanKeyData key;
+		SysScanDesc scan;
+		HeapTuple	tup;
+		ObjectAddresses *immv_triggers;
+
+		immv_triggers = new_object_addresses();
+
+		tgRel = table_open(TriggerRelationId, RowExclusiveLock);
+		depRel = table_open(DependRelationId, RowExclusiveLock);
+
+		/* search triggers that depends on IMMV. */
+		ScanKeyInit(&key,
+					Anum_pg_depend_refobjid,
+					BTEqualStrategyNumber, F_OIDEQ,
+					ObjectIdGetDatum(matviewOid));
+		scan = systable_beginscan(depRel, DependReferenceIndexId, true,
+								  NULL, 1, &key);
+		while ((tup = systable_getnext(scan)) != NULL)
+		{
+			ObjectAddress obj;
+			Form_pg_depend foundDep = (Form_pg_depend) GETSTRUCT(tup);
+
+			if (foundDep->classid == TriggerRelationId)
+			{
+				HeapTuple	tgtup;
+				ScanKeyData tgkey[1];
+				SysScanDesc tgscan;
+				Form_pg_trigger tgform;
+
+				/* Find the trigger name. */
+				ScanKeyInit(&tgkey[0],
+							Anum_pg_trigger_oid,
+							BTEqualStrategyNumber, F_OIDEQ,
+							ObjectIdGetDatum(foundDep->objid));
+
+				tgscan = systable_beginscan(tgRel, TriggerOidIndexId, true,
+											NULL, 1, tgkey);
+				tgtup = systable_getnext(tgscan);
+				if (!HeapTupleIsValid(tgtup))
+					elog(ERROR, "could not find tuple for immv trigger %u", foundDep->objid);
+
+				tgform = (Form_pg_trigger) GETSTRUCT(tgtup);
+
+				/* If trigger is created by IMMV, delete it. */
+				if (strncmp(NameStr(tgform->tgname), "IVM_trigger_", 12) == 0)
+				{
+					obj.classId = foundDep->classid;
+					obj.objectId = foundDep->objid;
+					obj.objectSubId = foundDep->refobjsubid;
+					add_exact_object_address(&obj, immv_triggers);
+				}
+				systable_endscan(tgscan);
+			}
+		}
+		systable_endscan(scan);
+
+		performMultipleDeletions(immv_triggers, DROP_RESTRICT, PERFORM_DELETION_INTERNAL);
+
+		table_close(depRel, RowExclusiveLock);
+		table_close(tgRel, RowExclusiveLock);
+		free_object_addresses(immv_triggers);
+	}
+
+	/*
+	 * Create triggers on incremental maintainable materialized view
+	 * This argument should use 'dataQuery'. This needs to use a rewritten query,
+	 * because a sublink in jointree is not supported by this function.
+	 *
+	 * This is performed before generating data because we have to wait
+	 * concurrent transactions modifying a base table and then take a snapshot
+	 * to see changes by these transactions to make sure a consistent view
+	 * is created.
+	 */
+	if (RelationIsIVM(matviewRel) && !skipData && !oldPopulated)
+	{
+		CreateIvmTriggersOnBaseTables(dataQuery, matviewOid);
+		CreateIndexOnIMMV(dataQuery, matviewRel);
+	}
+
 	/*
 	 * Create the transient table that will receive the regenerated data. Lock
 	 * it against access by any other process until commit (by which time it
@@ -326,8 +560,43 @@ RefreshMatViewByOid(Oid matviewOid, bool is_create, bool skipData,
 		DestReceiver *dest;
 
 		dest = CreateTransientRelDestReceiver(OIDNewHeap);
-		processed = refresh_matview_datafill(dest, dataQuery, queryString,
-											 is_create);
+
+		if (RelationIsIVM(matviewRel))
+		{
+			/*
+			 * In READ COMMITTED, get and push the latest snapshot again to see the
+			 * results of concurrent transactions committed after the current
+			 * transaction started.
+			 */
+			if (!IsolationUsesXactSnapshot())
+				PushActiveSnapshot(GetTransactionSnapshot());
+
+			/*
+			 * If a concurrent transaction updated the view incrementally and was
+			 * committed before we acquired the lock, the results of refresh_immv could
+			 * be inconsistent. Therefore, we have to check the transaction ID of the
+			 * most recent update of the view, and if this was in progress at the
+			 * transaction start, raise an error to prevent anomalies.
+			 */
+			if (!is_create)
+			{
+				FullTransactionId xid;
+
+				xid = getLastUpdateXid(matviewOid);
+				if (XidInMVCCSnapshot(XidFromFullTransactionId(xid), GetActiveSnapshot()))
+					ereport(ERROR,
+							(errcode(ERRCODE_T_R_SERIALIZATION_FAILURE),
+							 errmsg("the materialized view is incrementally updated in concurrent transaction"),
+							 errhint("The transaction might succeed if retried.")));
+			}
+		}
+
+		processed = refresh_matview_datafill(dest, dataQuery, NULL, NULL,
+											 queryString, is_create);
+
+		/* Pop the original snapshot. */
+		if (RelationIsIVM(matviewRel) && !IsolationUsesXactSnapshot())
+			PopActiveSnapshot();
 	}
 
 	/* Make the matview match the newly generated data. */
@@ -402,6 +671,8 @@ RefreshMatViewByOid(Oid matviewOid, bool is_create, bool skipData,
  */
 static uint64
 refresh_matview_datafill(DestReceiver *dest, Query *query,
+						 QueryEnvironment *queryEnv,
+						 TupleDesc *resultTupleDesc,
 						 const char *queryString, bool is_create)
 {
 	List	   *rewritten;
@@ -439,7 +710,7 @@ refresh_matview_datafill(DestReceiver *dest, Query *query,
 	/* Create a QueryDesc, redirecting output to our tuple receiver */
 	queryDesc = CreateQueryDesc(plan, queryString,
 								GetActiveSnapshot(), InvalidSnapshot,
-								dest, NULL, NULL, 0);
+								dest, NULL, queryEnv ? queryEnv: NULL, 0);
 
 	/* call ExecutorStart to prepare the plan for execution */
 	ExecutorStart(queryDesc, 0);
@@ -449,6 +720,9 @@ refresh_matview_datafill(DestReceiver *dest, Query *query,
 
 	processed = queryDesc->estate->es_processed;
 
+	if (resultTupleDesc)
+		*resultTupleDesc = CreateTupleDescCopy(queryDesc->tupDesc);
+
 	/* and clean up */
 	ExecutorFinish(queryDesc);
 	ExecutorEnd(queryDesc);
@@ -967,3 +1241,1488 @@ CloseMatViewIncrementalMaintenance(void)
 	matview_maintenance_depth--;
 	Assert(matview_maintenance_depth >= 0);
 }
+
+/*
+ * get_matview_query - get the Query from a matview's _RETURN rule.
+ */
+static Query *
+get_matview_query(Relation matviewRel)
+{
+	RewriteRule *rule;
+	List * actions;
+
+	/*
+	 * Check that everything is correct for a refresh. Problems at this point
+	 * are internal errors, so elog is sufficient.
+	 */
+	if (matviewRel->rd_rel->relhasrules == false ||
+		matviewRel->rd_rules->numLocks < 1)
+		elog(ERROR,
+			 "materialized view \"%s\" is missing rewrite information",
+			 RelationGetRelationName(matviewRel));
+
+	if (matviewRel->rd_rules->numLocks > 1)
+		elog(ERROR,
+			 "materialized view \"%s\" has too many rules",
+			 RelationGetRelationName(matviewRel));
+
+	rule = matviewRel->rd_rules->rules[0];
+	if (rule->event != CMD_SELECT || !(rule->isInstead))
+		elog(ERROR,
+			 "the rule for materialized view \"%s\" is not a SELECT INSTEAD OF rule",
+			 RelationGetRelationName(matviewRel));
+
+	actions = rule->actions;
+	if (list_length(actions) != 1)
+		elog(ERROR,
+			 "the rule for materialized view \"%s\" is not a single action",
+			 RelationGetRelationName(matviewRel));
+
+	/*
+	 * The stored query was rewritten at the time of the MV definition, but
+	 * has not been scribbled on by the planner.
+	 */
+	return linitial_node(Query, actions);
+}
+
+
+/* ----------------------------------------------------
+ *		Incremental View Maintenance routines
+ * ---------------------------------------------------
+ */
+
+/*
+ * IVM_immediate_before
+ *
+ * IVM trigger function invoked before base table is modified. If this is
+ * invoked firstly in the same statement, we save the transaction id and the
+ * command id at that time.
+ */
+Datum
+IVM_immediate_before(PG_FUNCTION_ARGS)
+{
+	TriggerData *trigdata = (TriggerData *) fcinfo->context;
+	char	   *matviewOid_text = trigdata->tg_trigger->tgargs[0];
+	char	   *ex_lock_text = trigdata->tg_trigger->tgargs[1];
+	Oid			matviewOid;
+	MV_TriggerHashEntry *entry;
+	bool	found;
+	bool	ex_lock;
+
+	matviewOid = DatumGetObjectId(DirectFunctionCall1(oidin, CStringGetDatum(matviewOid_text)));
+	ex_lock = DatumGetBool(DirectFunctionCall1(boolin, CStringGetDatum(ex_lock_text)));
+
+	/* If the view has more than one tables, we have to use an exclusive lock. */
+	if (ex_lock)
+	{
+		FullTransactionId xid;
+
+		/*
+		 * Wait for concurrent transactions which update this materialized view at
+		 * READ COMMITED. This is needed to see changes committed in other
+		 * transactions. No wait and raise an error at REPEATABLE READ or
+		 * SERIALIZABLE to prevent update anomalies of matviews.
+		 * XXX: dead-lock is possible here.
+		 */
+		if (!IsolationUsesXactSnapshot())
+			LockRelationOid(matviewOid, ExclusiveLock);
+		else if (!ConditionalLockRelationOid(matviewOid, ExclusiveLock))
+		{
+			/* try to throw error by name; relation could be deleted... */
+			char	   *relname = get_rel_name(matviewOid);
+
+			if (!relname)
+				ereport(ERROR,
+						(errcode(ERRCODE_LOCK_NOT_AVAILABLE),
+						errmsg("could not obtain lock on materialized view during incremental maintenance")));
+
+			ereport(ERROR,
+					(errcode(ERRCODE_LOCK_NOT_AVAILABLE),
+					errmsg("could not obtain lock on materialized view \"%s\" during incremental maintenance",
+							relname)));
+		}
+
+		/*
+		 * Even if we can acquire an lock, a concurrent transaction could have
+		 * updated the view incrementally and been committed before we acquired
+		 * the lock. Therefore, we have to check the transaction ID of the most
+		 * recent update of the view, and if this was in progress at the
+		 * transaction start, raise an error to prevent anomalies.
+		 */
+		xid = getLastUpdateXid(matviewOid);
+		if (XidInMVCCSnapshot(XidFromFullTransactionId(xid), GetTransactionSnapshot()))
+			ereport(ERROR,
+					(errcode(ERRCODE_T_R_SERIALIZATION_FAILURE),
+					 errmsg("the materialized view is incrementally updated in concurrent transaction"),
+					 errhint("The transaction might succeed if retried.")));
+	}
+	else
+		LockRelationOid(matviewOid, RowExclusiveLock);
+
+	/*
+	 * On the first call initialize the hashtable
+	 */
+	if (!mv_trigger_info)
+		mv_InitHashTables();
+
+	entry = (MV_TriggerHashEntry *) hash_search(mv_trigger_info,
+											  (void *) &matviewOid,
+											  HASH_ENTER, &found);
+
+	/* On the first BEFORE to update the view, initialize trigger data */
+	if (!found || entry->snapshot == InvalidSnapshot)
+	{
+		Snapshot snapshot;
+
+		/*
+		 * Get a snapshot just before the table was modified for checking
+		 * tuple visibility in the pre-update state of the table.
+		 *
+		 * In READ COMMITTED, use the latest snapshot again to see the
+		 * results of concurrent transactions committed after the current
+		 * transaction started.
+		 */
+		if (IsolationUsesXactSnapshot())
+			snapshot = GetActiveSnapshot();
+		else
+			snapshot = GetTransactionSnapshot();
+
+		entry->matview_id = matviewOid;
+		entry->before_trig_count = 0;
+		entry->after_trig_count = 0;
+		entry->snapshot = RegisterSnapshot(snapshot);
+		entry->tables = NIL;
+		entry->has_old = false;
+		entry->has_new = false;
+
+		/*
+		 * If this is the first table modifying query in the transaction,
+		 * initialize the list of subxids.
+		 */
+		if (!found)
+			entry->subxids = NIL;
+	}
+
+	entry->before_trig_count++;
+
+	return PointerGetDatum(NULL);
+}
+
+/*
+ * IVM_immediate_maintenance
+ *
+ * IVM trigger function invoked after base table is modified.
+ * For each table, tuplestores of transition tables are collected.
+ * and after the last modification
+ */
+Datum
+IVM_immediate_maintenance(PG_FUNCTION_ARGS)
+{
+	TriggerData *trigdata = (TriggerData *) fcinfo->context;
+	Relation	rel;
+	Oid			relid;
+	Oid			matviewOid;
+	Query	   *query;
+	Query	   *rewritten = NULL;
+	char	   *matviewOid_text = trigdata->tg_trigger->tgargs[0];
+	Relation	matviewRel;
+	int old_depth = matview_maintenance_depth;
+	SubTransactionId subxid;
+
+	Oid			relowner;
+	Tuplestorestate *old_tuplestore = NULL;
+	Tuplestorestate *new_tuplestore = NULL;
+	DestReceiver *dest_new = NULL, *dest_old = NULL;
+	Oid			save_userid;
+	int			save_sec_context;
+	int			save_nestlevel;
+
+	MV_TriggerHashEntry *entry;
+	MV_TriggerTable		*table;
+	bool	found;
+
+	ParseState		 *pstate;
+	QueryEnvironment *queryEnv = create_queryEnv();
+	MemoryContext	oldcxt;
+	ListCell   *lc;
+	int			i;
+
+
+	/* Create a ParseState for rewriting the view definition query */
+	pstate = make_parsestate(NULL);
+	pstate->p_queryEnv = queryEnv;
+	pstate->p_expr_kind = EXPR_KIND_SELECT_TARGET;
+
+	rel = trigdata->tg_relation;
+	relid = rel->rd_id;
+
+	matviewOid = DatumGetObjectId(DirectFunctionCall1(oidin, CStringGetDatum(matviewOid_text)));
+
+	/*
+	 * On the first call initialize the hashtable
+	 */
+	if (!mv_trigger_info)
+		mv_InitHashTables();
+
+	/* get the entry for this materialized view */
+	entry = (MV_TriggerHashEntry *) hash_search(mv_trigger_info,
+											  (void *) &matviewOid,
+											  HASH_FIND, &found);
+	Assert (found && entry != NULL);
+	entry->after_trig_count++;
+
+	/* search the entry for the modified table and create new entry if not found */
+	found = false;
+	foreach(lc, entry->tables)
+	{
+		table = (MV_TriggerTable *) lfirst(lc);
+		if (table->table_id == relid)
+		{
+			found = true;
+			break;
+		}
+	}
+	if (!found)
+	{
+		oldcxt = MemoryContextSwitchTo(TopTransactionContext);
+
+		table = (MV_TriggerTable *) palloc0(sizeof(MV_TriggerTable));
+		table->table_id = relid;
+		table->old_tuplestores = NIL;
+		table->new_tuplestores = NIL;
+		table->rte_indexes = NIL;
+		table->slot = MakeSingleTupleTableSlot(RelationGetDescr(rel), table_slot_callbacks(rel));
+		/* We assume we have at least RowExclusiveLock on modified tables. */
+		table->rel = table_open(RelationGetRelid(rel), NoLock);
+		entry->tables = lappend(entry->tables, table);
+
+		MemoryContextSwitchTo(oldcxt);
+	}
+
+	/* Save the transition tables and make a request to not free immediately */
+	if (trigdata->tg_oldtable)
+	{
+		oldcxt = MemoryContextSwitchTo(TopTransactionContext);
+		table->old_tuplestores = lappend(table->old_tuplestores, trigdata->tg_oldtable);
+		entry->has_old = true;
+		MemoryContextSwitchTo(oldcxt);
+	}
+	if (trigdata->tg_newtable)
+	{
+		oldcxt = MemoryContextSwitchTo(TopTransactionContext);
+		table->new_tuplestores = lappend(table->new_tuplestores, trigdata->tg_newtable);
+		entry->has_new = true;
+		MemoryContextSwitchTo(oldcxt);
+	}
+	if (entry->has_new || entry->has_old)
+	{
+		CmdType cmd;
+
+		if (TRIGGER_FIRED_BY_INSERT(trigdata->tg_event))
+			cmd = CMD_INSERT;
+		else if (TRIGGER_FIRED_BY_DELETE(trigdata->tg_event))
+			cmd = CMD_DELETE;
+		else if (TRIGGER_FIRED_BY_UPDATE(trigdata->tg_event))
+			cmd = CMD_UPDATE;
+		else
+			elog(ERROR,"unsupported trigger type");
+
+		/* Prolong lifespan of transition tables to the end of the last AFTER trigger */
+		SetTransitionTablePreserved(relid, cmd);
+	}
+
+
+	/* If this is not the last AFTER trigger call, immediately exit. */
+	Assert (entry->before_trig_count >= entry->after_trig_count);
+	if (entry->before_trig_count != entry->after_trig_count)
+		return PointerGetDatum(NULL);
+
+	/*
+	 * If this is the last AFTER trigger call, continue and update the view.
+	 */
+
+	/* record the subxid that updated the view incrementally */
+	subxid = GetCurrentSubTransactionId();
+	if (!list_member_xid(entry->subxids, subxid))
+	{
+		oldcxt = MemoryContextSwitchTo(TopTransactionContext);
+		entry->subxids = lappend_xid(entry->subxids, subxid);
+		MemoryContextSwitchTo(oldcxt);
+	}
+
+	/*
+	 * Advance command counter to make the updated base table rows locally
+	 * visible.
+	 */
+	CommandCounterIncrement();
+
+	matviewRel = table_open(matviewOid, NoLock);
+
+	/* Make sure it is a materialized view. */
+	Assert(matviewRel->rd_rel->relkind == RELKIND_MATVIEW);
+
+	/*
+	 * In READ COMMITTED, get and push the latest snapshot again to see the
+	 * results of concurrent transactions committed after the current
+	 * transaction started.
+	 */
+	if (!IsolationUsesXactSnapshot())
+		PushActiveSnapshot(GetTransactionSnapshot());
+
+	/*
+	 * Check for active uses of the relation in the current transaction, such
+	 * as open scans.
+	 *
+	 * NB: We count on this to protect us against problems with refreshing the
+	 * data using TABLE_INSERT_FROZEN.
+	 */
+	CheckTableNotInUse(matviewRel, "refresh a materialized view incrementally");
+
+	/*
+	 * Switch to the owner's userid, so that any functions are run as that
+	 * user.  Also arrange to make GUC variable changes local to this command.
+	 * We will switch modes when we are about to execute user code.
+	 */
+	relowner = matviewRel->rd_rel->relowner;
+	GetUserIdAndSecContext(&save_userid, &save_sec_context);
+	SetUserIdAndSecContext(relowner,
+						   save_sec_context | SECURITY_RESTRICTED_OPERATION);
+	save_nestlevel = NewGUCNestLevel();
+
+	/* get view query*/
+	query = get_matview_query(matviewRel);
+
+	/*
+	 * When a base table is truncated, the view content will be empty if the
+	 * view definition query does not contain an aggregate without a GROUP clause.
+	 * Therefore, such views can be truncated.
+	 */
+	if (TRIGGER_FIRED_BY_TRUNCATE(trigdata->tg_event))
+	{
+		ExecuteTruncateGuts(list_make1(matviewRel), list_make1_oid(matviewOid),
+							NIL, DROP_RESTRICT, false, false);
+
+		/* Clean up hash entry and delete tuplestores */
+		clean_up_IVM_hash_entry(entry, false, InvalidSubTransactionId);
+
+		/* Pop the original snapshot. */
+		if (!IsolationUsesXactSnapshot())
+			PopActiveSnapshot();
+
+		table_close(matviewRel, NoLock);
+
+		/* Roll back any GUC changes */
+		AtEOXact_GUC(false, save_nestlevel);
+
+		/* Restore userid and security context */
+		SetUserIdAndSecContext(save_userid, save_sec_context);
+
+		return PointerGetDatum(NULL);
+	}
+
+	/*
+	 * rewrite query for calculating deltas
+	 */
+
+	rewritten = copyObject(query);
+
+	/* Replace resnames in a target list with materialized view's attnames */
+	i = 0;
+	foreach (lc, rewritten->targetList)
+	{
+		TargetEntry *tle = (TargetEntry *) lfirst(lc);
+		Form_pg_attribute attr = TupleDescAttr(matviewRel->rd_att, i);
+		char *resname = NameStr(attr->attname);
+
+		tle->resname = pstrdup(resname);
+		i++;
+	}
+
+	/* Set all tables in the query to pre-update state */
+	rewritten = rewrite_query_for_preupdate_state(rewritten, entry->tables,
+												  pstate, matviewOid);
+	/* Rewrite for counting duplicated tuples */
+	rewritten = rewrite_query_for_counting(rewritten, pstate);
+
+	/* Create tuplestores to store view deltas */
+	if (entry->has_old)
+	{
+		oldcxt = MemoryContextSwitchTo(TopTransactionContext);
+
+		old_tuplestore = tuplestore_begin_heap(false, false, work_mem);
+		dest_old = CreateDestReceiver(DestTuplestore);
+		SetTuplestoreDestReceiverParams(dest_old,
+									old_tuplestore,
+									TopTransactionContext,
+									false,
+									NULL,
+									NULL);
+
+		MemoryContextSwitchTo(oldcxt);
+	}
+	if (entry->has_new)
+	{
+		oldcxt = MemoryContextSwitchTo(TopTransactionContext);
+
+		new_tuplestore = tuplestore_begin_heap(false, false, work_mem);
+		dest_new = CreateDestReceiver(DestTuplestore);
+		SetTuplestoreDestReceiverParams(dest_new,
+									new_tuplestore,
+									TopTransactionContext,
+									false,
+									NULL,
+									NULL);
+		MemoryContextSwitchTo(oldcxt);
+	}
+
+	/* for all modified tables */
+	foreach(lc, entry->tables)
+	{
+		ListCell *lc2;
+
+		table = (MV_TriggerTable *) lfirst(lc);
+
+		/* loop for self-join */
+		foreach(lc2, table->rte_indexes)
+		{
+			int	rte_index = lfirst_int(lc2);
+			TupleDesc		tupdesc_old;
+			TupleDesc		tupdesc_new;
+
+			/* calculate delta tables */
+			calc_delta(table, rte_index, rewritten, dest_old, dest_new,
+					   &tupdesc_old, &tupdesc_new, queryEnv);
+
+			/* Set the table in the query to post-update state */
+			rewritten = rewrite_query_for_postupdate_state(rewritten, table, rte_index);
+
+			PG_TRY();
+			{
+				/* apply the delta tables to the materialized view */
+				apply_delta(matviewOid, old_tuplestore, new_tuplestore,
+							tupdesc_old, tupdesc_new, query);
+			}
+			PG_CATCH();
+			{
+				matview_maintenance_depth = old_depth;
+				PG_RE_THROW();
+			}
+			PG_END_TRY();
+
+			/* clear view delta tuplestores */
+			if (old_tuplestore)
+				tuplestore_clear(old_tuplestore);
+			if (new_tuplestore)
+				tuplestore_clear(new_tuplestore);
+		}
+	}
+
+	/* Clean up hash entry and delete tuplestores */
+	clean_up_IVM_hash_entry(entry, false, InvalidSubTransactionId);
+	if (old_tuplestore)
+	{
+		dest_old->rDestroy(dest_old);
+		tuplestore_end(old_tuplestore);
+	}
+	if (new_tuplestore)
+	{
+		dest_new->rDestroy(dest_new);
+		tuplestore_end(new_tuplestore);
+	}
+
+	/* Pop the original snapshot. */
+	if (!IsolationUsesXactSnapshot())
+		PopActiveSnapshot();
+
+	table_close(matviewRel, NoLock);
+
+	/* Roll back any GUC changes */
+	AtEOXact_GUC(false, save_nestlevel);
+
+	/* Restore userid and security context */
+	SetUserIdAndSecContext(save_userid, save_sec_context);
+
+	return PointerGetDatum(NULL);
+}
+
+/*
+ * rewrite_query_for_preupdate_state
+ *
+ * Rewrite the query so that base tables' RTEs will represent "pre-update"
+ * state of tables. This is necessary to calculate view delta after multiple
+ * tables are modified.
+ */
+static Query*
+rewrite_query_for_preupdate_state(Query *query, List *tables,
+								  ParseState *pstate, Oid matviewid)
+{
+	ListCell *lc;
+	int num_rte = list_length(query->rtable);
+	int i;
+
+
+	/* register delta ENRs */
+	register_delta_ENRs(pstate, query, tables);
+
+	/* XXX: Is necessary? Is this right timing? */
+	AcquireRewriteLocks(query, true, false);
+
+	i = 1;
+	foreach(lc, query->rtable)
+	{
+		RangeTblEntry *r = (RangeTblEntry*) lfirst(lc);
+
+		ListCell *lc2;
+		foreach(lc2, tables)
+		{
+			MV_TriggerTable *table = (MV_TriggerTable *) lfirst(lc2);
+			/*
+			 * if the modified table is found then replace the original RTE with
+			 * "pre-state" RTE and append its index to the list.
+			 */
+			if (r->relid == table->table_id)
+			{
+				List *securityQuals;
+				List *withCheckOptions;
+				bool  hasRowSecurity;
+				bool  hasSubLinks;
+
+				RangeTblEntry *rte_pre = get_prestate_rte(r, table, pstate->p_queryEnv, matviewid);
+
+				/*
+				 * Set a row security poslicies of the modified table to the subquery RTE which
+				 * represents the pre-update state of the table.
+				 */
+				get_row_security_policies(query, table->original_rte, i,
+										  &securityQuals, &withCheckOptions,
+										  &hasRowSecurity, &hasSubLinks);
+
+				if (hasRowSecurity)
+				{
+					query->hasRowSecurity = true;
+					rte_pre->security_barrier = true;
+				}
+				if (hasSubLinks)
+					query->hasSubLinks = true;
+
+				rte_pre->securityQuals = securityQuals;
+				lfirst(lc) = rte_pre;
+
+				table->rte_indexes = lappend_int(table->rte_indexes, i);
+				break;
+			}
+		}
+
+		/* finish the loop if we processed all RTE included in the original query */
+		if (i++ >= num_rte)
+			break;
+	}
+
+	return query;
+}
+
+/*
+ * register_delta_ENRs
+ *
+ * For all modified tables, make ENRs for their transition tables
+ * and register them to the queryEnv. ENR's RTEs are also appended
+ * into the list in query tree.
+ */
+static void
+register_delta_ENRs(ParseState *pstate, Query *query, List *tables)
+{
+	QueryEnvironment *queryEnv = pstate->p_queryEnv;
+	ListCell *lc;
+	RangeTblEntry	*rte;
+
+	foreach(lc, tables)
+	{
+		MV_TriggerTable *table = (MV_TriggerTable *) lfirst(lc);
+		ListCell *lc2;
+		int count;
+
+		count = 0;
+		foreach(lc2, table->old_tuplestores)
+		{
+			Tuplestorestate *oldtable = (Tuplestorestate *) lfirst(lc2);
+			EphemeralNamedRelation enr =
+				palloc(sizeof(EphemeralNamedRelationData));
+			ParseNamespaceItem *nsitem;
+
+			enr->md.name = make_delta_enr_name("old", table->table_id, count);
+			enr->md.reliddesc = table->table_id;
+			enr->md.tupdesc = NULL;
+			enr->md.enrtype = ENR_NAMED_TUPLESTORE;
+			enr->md.enrtuples = tuplestore_tuple_count(oldtable);
+			enr->reldata = oldtable;
+			register_ENR(queryEnv, enr);
+
+			nsitem = addRangeTableEntryForENR(pstate, makeRangeVar(NULL, enr->md.name, -1), true);
+			rte = nsitem->p_rte;
+
+			query->rtable = lappend(query->rtable, rte);
+
+			count++;
+		}
+
+		count = 0;
+		foreach(lc2, table->new_tuplestores)
+		{
+			Tuplestorestate *newtable = (Tuplestorestate *) lfirst(lc2);
+			EphemeralNamedRelation enr =
+				palloc(sizeof(EphemeralNamedRelationData));
+			ParseNamespaceItem *nsitem;
+
+			enr->md.name = make_delta_enr_name("new", table->table_id, count);
+			enr->md.reliddesc = table->table_id;
+			enr->md.tupdesc = NULL;
+			enr->md.enrtype = ENR_NAMED_TUPLESTORE;
+			enr->md.enrtuples = tuplestore_tuple_count(newtable);
+			enr->reldata = newtable;
+			register_ENR(queryEnv, enr);
+
+			nsitem = addRangeTableEntryForENR(pstate, makeRangeVar(NULL, enr->md.name, -1), true);
+			rte = nsitem->p_rte;
+
+			query->rtable = lappend(query->rtable, rte);
+
+			count++;
+		}
+	}
+}
+
+#define DatumGetItemPointer(X)	 ((ItemPointer) DatumGetPointer(X))
+#define PG_GETARG_ITEMPOINTER(n) DatumGetItemPointer(PG_GETARG_DATUM(n))
+
+/*
+ * ivm_visible_in_prestate
+ *
+ * Check visibility of a tuple specified by the tableoid and item pointer
+ * using the snapshot taken just before the table was modified.
+ */
+Datum
+ivm_visible_in_prestate(PG_FUNCTION_ARGS)
+{
+	Oid			tableoid = PG_GETARG_OID(0);
+	ItemPointer itemPtr = PG_GETARG_ITEMPOINTER(1);
+	Oid			matviewOid = PG_GETARG_OID(2);
+	MV_TriggerHashEntry *entry;
+	MV_TriggerTable		*table = NULL;
+	ListCell   *lc;
+	bool	found;
+	bool	result;
+
+	if (!in_delta_calculation)
+		ereport(ERROR,
+				(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+				 errmsg("ivm_visible_in_prestate can be called only in delta calculation")));
+
+	entry = (MV_TriggerHashEntry *) hash_search(mv_trigger_info,
+											  (void *) &matviewOid,
+											  HASH_FIND, &found);
+	Assert (found && entry != NULL);
+
+	foreach(lc, entry->tables)
+	{
+		table = (MV_TriggerTable *) lfirst(lc);
+		if (table->table_id == tableoid)
+			break;
+	}
+
+	Assert (table != NULL);
+
+	result = table_tuple_fetch_row_version(table->rel, itemPtr, entry->snapshot, table->slot);
+
+	PG_RETURN_BOOL(result);
+}
+
+/*
+ * get_prestate_rte
+ *
+ * Rewrite RTE of the modified table to a subquery which represents
+ * "pre-state" table. The original RTE is saved in table->rte_original.
+ */
+static RangeTblEntry*
+get_prestate_rte(RangeTblEntry *rte, MV_TriggerTable *table,
+				 QueryEnvironment *queryEnv, Oid matviewid)
+{
+	StringInfoData str;
+	RawStmt *raw;
+	Query *subquery;
+	ParseState *pstate;
+	char *relname;
+	static char *subquery_tl;
+	int i;
+
+	pstate = make_parsestate(NULL);
+	pstate->p_queryEnv = queryEnv;
+	pstate->p_expr_kind = EXPR_KIND_SELECT_TARGET;
+
+	relname = quote_qualified_identifier(
+					get_namespace_name(RelationGetNamespace(table->rel)),
+									   RelationGetRelationName(table->rel));
+
+	subquery_tl = make_subquery_targetlist_from_table(table);
+
+	/*
+	 * Filtering inserted row using the snapshot taken before the table
+	 * is modified. ctid is required for maintaining outer join views.
+	 */
+	initStringInfo(&str);
+	appendStringInfo(&str,
+		"SELECT %s FROM %s t"
+		" WHERE pg_catalog.ivm_visible_in_prestate(t.tableoid, t.ctid ,%d::pg_catalog.oid)",
+			subquery_tl, relname, matviewid);
+
+	/*
+	 * Re-add rows deleted from the old transition tables, excluding those
+	 * also present in the new transition tables.
+	 */
+	if (list_length(table->old_tuplestores) > 0)
+	{
+		appendStringInfo(&str," UNION ALL SELECT %s  FROM (",
+			subquery_tl);
+
+		for (i = 0; i < list_length(table->old_tuplestores); i++)
+		{
+			if (i != 0)
+				appendStringInfo(&str, " UNION ALL ");
+			appendStringInfo(&str," TABLE %s",
+				make_delta_enr_name("old", table->table_id, i));
+		}
+		for (i = 0; i < list_length(table->new_tuplestores); i++)
+		{
+			appendStringInfo(&str, " EXCEPT ALL ");
+			appendStringInfo(&str," TABLE %s",
+				make_delta_enr_name("new", table->table_id, i));
+		}
+		appendStringInfo(&str,")");
+	}
+
+	/* Get a subquery representing pre-state of the table */
+	raw = (RawStmt*)linitial(raw_parser(str.data, RAW_PARSE_DEFAULT));
+	subquery = transformStmt(pstate, raw->stmt);
+
+	/* save the original RTE */
+	table->original_rte = copyObject(rte);
+
+	rte->rtekind = RTE_SUBQUERY;
+	rte->subquery = subquery;
+	rte->security_barrier = false;
+
+	/* Clear fields that should not be set in a subquery RTE */
+	rte->relid = InvalidOid;
+	rte->relkind = 0;
+	rte->rellockmode = 0;
+	rte->tablesample = NULL;
+	rte->perminfoindex = 0;         /* no permission checking for this RTE */
+	rte->inh = false;			/* must not be set for a subquery */
+
+	return rte;
+}
+
+/*
+ * make_subquery_targetlist_from_table
+ *
+ * Make a targetlist string of a subquery representing a delta table or a
+ * pre-update state table. This subquery substitutes a modified table RTE
+ * in the view definition query during view maintenance. In the targetlist,
+ * column names appear in order of the table definition. However, for
+ * attribute numbers of vars in the query tree to reference columns of the
+ * subquery  correctly even though the table has a dropped column, put "null"
+ * as a dummy value at the position of a dropped column.
+ *
+ * We would also able to walk the query tree to rewrite varattnos, but
+ * crafting targetlist is more simple and reasonable.
+ */
+static char*
+make_subquery_targetlist_from_table(MV_TriggerTable *table)
+{
+	StringInfoData str;
+	TupleDesc	tupdesc;
+	int			i;
+
+	tupdesc = RelationGetDescr(table->rel);
+	initStringInfo(&str);
+	for (i = 0; i < tupdesc->natts; i++)
+	{
+		Form_pg_attribute attr = TupleDescAttr(tupdesc, i);
+
+		if (i > 0)
+			appendStringInfo(&str, ", ");
+
+		if (attr->attisdropped)
+			appendStringInfo(&str, "null");
+		else
+			appendStringInfo(&str, "%s", quote_identifier(NameStr(attr->attname)));
+	}
+
+	return str.data;
+}
+
+/*
+ * make_delta_enr_name
+ *
+ * Make a name for ENR of a transition table from the base table's oid.
+ * prefix will be "new" or "old" depending on its transition table kind..
+ */
+static char*
+make_delta_enr_name(const char *prefix, Oid relid, int count)
+{
+	char buf[NAMEDATALEN];
+	char *name;
+
+	snprintf(buf, NAMEDATALEN, "__ivm_%s_%u_%u", prefix, relid, count);
+	name = pstrdup(buf);
+
+	return name;
+}
+
+/*
+ * makeDeltaTable
+ *
+ * Make a RTE representing a delta of the specified table.
+ */
+static RangeTblEntry*
+makeDeltaTable(RangeTblEntry *rte, MV_TriggerTable *table,
+		   bool is_new, QueryEnvironment *queryEnv)
+{
+	StringInfoData str;
+	ParseState	*pstate;
+	RawStmt *raw;
+	Query *sub;
+	int		i;
+
+	const char *prefix_union = is_new ? "new" : "old";
+	const char *prefix_except = is_new ? "old" : "new";
+	int num_union = is_new ? list_length(table->new_tuplestores) : list_length(table->old_tuplestores);
+	int num_except = is_new ? list_length(table->old_tuplestores) : list_length(table->new_tuplestores);
+
+	/* the previous RTE must be a subquery which represents "pre-state" table */
+	Assert(rte->rtekind == RTE_SUBQUERY);
+
+	/* Create a ParseState for rewriting the view definition query */
+	pstate = make_parsestate(NULL);
+	pstate->p_queryEnv = queryEnv;
+	pstate->p_expr_kind = EXPR_KIND_NONE;
+
+	initStringInfo(&str);
+	appendStringInfo(&str,
+		" SELECT %s FROM ( ",
+		make_subquery_targetlist_from_table(table));
+
+	for (i = 0; i < num_union; i++)
+	{
+		if (i > 0)
+			appendStringInfo(&str, " UNION ALL ");
+
+		appendStringInfo(&str,
+			" TABLE  %s",
+			make_delta_enr_name(prefix_union, table->table_id, i));
+	}
+	for (i = 0; i < num_except; i++)
+	{
+		appendStringInfo(&str, " EXCEPT ALL ");
+
+		appendStringInfo(&str,
+			" TABLE  %s",
+			make_delta_enr_name(prefix_except, table->table_id, i));
+	}
+	appendStringInfo(&str,")");
+
+	raw = (RawStmt*)linitial(raw_parser(str.data, RAW_PARSE_DEFAULT));
+	sub = transformStmt(pstate, raw->stmt);
+
+	/*
+	 * Update the subquery so that it represent the combined transition
+	 * table.  Note that we leave the security_barrier and securityQuals
+	 * fields so that the subquery relation can be protected by the RLS
+	 * policy as same as the modified table.
+	 */
+	rte->rtekind = RTE_SUBQUERY;
+	rte->subquery = sub;
+
+	return rte;
+}
+
+/*
+ * rewrite_query_for_counting
+ *
+ * Rewrite query for counting duplicated tuples.
+ */
+static Query *
+rewrite_query_for_counting(Query *query, ParseState *pstate)
+{
+	TargetEntry *tle_count;
+	FuncCall *fn;
+	Node *node;
+
+	/* Add count(*) for counting distinct tuples in views */
+	fn = makeFuncCall(SystemFuncName("count"), NIL, COERCE_EXPLICIT_CALL, -1);
+	fn->agg_star = true;
+	if (!query->groupClause && !query->hasAggs)
+		query->groupClause = transformDistinctClause(NULL, &query->targetList, query->sortClause, false);
+
+	node = ParseFuncOrColumn(pstate, fn->funcname, NIL, NULL, fn, false, -1);
+
+	tle_count = makeTargetEntry((Expr *) node,
+								list_length(query->targetList) + 1,
+								pstrdup("__ivm_count__"),
+								false);
+	query->targetList = lappend(query->targetList, tle_count);
+	query->hasAggs = true;
+
+	return query;
+}
+
+/*
+ * calc_delta
+ *
+ * Calculate view deltas generated under the modification of a table specified
+ * by the RTE index.
+ */
+static void
+calc_delta(MV_TriggerTable *table, int rte_index, Query *query,
+			DestReceiver *dest_old, DestReceiver *dest_new,
+			TupleDesc *tupdesc_old, TupleDesc *tupdesc_new,
+			QueryEnvironment *queryEnv)
+{
+	ListCell *lc = list_nth_cell(query->rtable, rte_index - 1);
+	RangeTblEntry *rte = (RangeTblEntry *) lfirst(lc);
+
+	in_delta_calculation = true;
+
+	/* Generate old delta */
+	if (dest_old && list_length(table->old_tuplestores) > 0)
+	{
+		/* Replace the modified table with the old delta table and calculate the old view delta. */
+		lfirst(lc) = makeDeltaTable(rte, table, false, queryEnv);
+		refresh_matview_datafill(dest_old, query, queryEnv, tupdesc_old, "", false);
+	}
+
+	/* Generate new delta */
+	if (dest_new && list_length(table->new_tuplestores) > 0)
+	{
+		/* Replace the modified table with the new delta table and calculate the new view delta*/
+		lfirst(lc) = makeDeltaTable(rte, table, true, queryEnv);
+		refresh_matview_datafill(dest_new, query, queryEnv, tupdesc_new, "", false);
+	}
+
+	in_delta_calculation = false;
+}
+
+/*
+ * rewrite_query_for_postupdate_state
+ *
+ * Rewrite the query so that the specified base table's RTEs will represent
+ * "post-update" state of tables. This is called after the view delta
+ * calculation due to changes on this table finishes.
+ */
+static Query*
+rewrite_query_for_postupdate_state(Query *query, MV_TriggerTable *table, int rte_index)
+{
+	ListCell *lc = list_nth_cell(query->rtable, rte_index - 1);
+
+	/* Retore the original RTE */
+	lfirst(lc) = table->original_rte;
+
+	return query;
+}
+
+/*
+ * apply_delta
+ *
+ * Apply deltas to the materialized view. In outer join cases, this requires
+ * the view maintenance graph.
+ */
+static void
+apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *new_tuplestores,
+			TupleDesc tupdesc_old, TupleDesc tupdesc_new,
+			Query *query)
+{
+	StringInfoData querybuf;
+	StringInfoData target_list_buf;
+	Relation	matviewRel;
+	char	   *matviewname;
+	ListCell	*lc;
+	int			i;
+	List	   *keys = NIL;
+
+
+	/*
+	 * get names of the materialized view and delta tables
+	 */
+
+	matviewRel = table_open(matviewOid, NoLock);
+	matviewname = quote_qualified_identifier(get_namespace_name(RelationGetNamespace(matviewRel)),
+											 RelationGetRelationName(matviewRel));
+
+	/*
+	 * Build parts of the maintenance queries
+	 */
+
+	initStringInfo(&querybuf);
+	initStringInfo(&target_list_buf);
+
+	/* build string of target list */
+	for (i = 0; i < matviewRel->rd_att->natts; i++)
+	{
+		Form_pg_attribute attr = TupleDescAttr(matviewRel->rd_att, i);
+		char   *resname = NameStr(attr->attname);
+
+		if (i != 0)
+			appendStringInfo(&target_list_buf, ", ");
+		appendStringInfo(&target_list_buf, "%s", quote_qualified_identifier(NULL, resname));
+	}
+
+	i = 0;
+	foreach (lc, query->targetList)
+	{
+		TargetEntry *tle = (TargetEntry *) lfirst(lc);
+		Form_pg_attribute attr = TupleDescAttr(matviewRel->rd_att, i);
+
+		i++;
+
+		if (tle->resjunk)
+			continue;
+
+		keys = lappend(keys, attr);
+	}
+
+	/* Start maintaining the materialized view. */
+	OpenMatViewIncrementalMaintenance();
+
+	/* Open SPI context. */
+	if (SPI_connect() != SPI_OK_CONNECT)
+		elog(ERROR, "SPI_connect failed");
+
+	/* For tuple deletion */
+	if (old_tuplestores && tuplestore_tuple_count(old_tuplestores) > 0)
+	{
+		EphemeralNamedRelation enr = palloc(sizeof(EphemeralNamedRelationData));
+		int				rc;
+
+		/* convert tuplestores to ENR, and register for SPI */
+		enr->md.name = pstrdup(OLD_DELTA_ENRNAME);
+		enr->md.reliddesc = InvalidOid;
+		enr->md.tupdesc = tupdesc_old;
+		enr->md.enrtype = ENR_NAMED_TUPLESTORE;
+		enr->md.enrtuples = tuplestore_tuple_count(old_tuplestores);
+		enr->reldata = old_tuplestores;
+
+		rc = SPI_register_relation(enr);
+		if (rc != SPI_OK_REL_REGISTER)
+			elog(ERROR, "SPI_register failed");
+
+		apply_old_delta(matviewname, OLD_DELTA_ENRNAME, keys);
+
+	}
+	/* For tuple insertion */
+	if (new_tuplestores && tuplestore_tuple_count(new_tuplestores) > 0)
+	{
+		EphemeralNamedRelation enr = palloc(sizeof(EphemeralNamedRelationData));
+		int rc;
+
+		/* convert tuplestores to ENR, and register for SPI */
+		enr->md.name = pstrdup(NEW_DELTA_ENRNAME);
+		enr->md.reliddesc = InvalidOid;
+		enr->md.tupdesc = tupdesc_new;;
+		enr->md.enrtype = ENR_NAMED_TUPLESTORE;
+		enr->md.enrtuples = tuplestore_tuple_count(new_tuplestores);
+		enr->reldata = new_tuplestores;
+
+		rc = SPI_register_relation(enr);
+		if (rc != SPI_OK_REL_REGISTER)
+			elog(ERROR, "SPI_register failed");
+
+		/* apply new delta */
+		apply_new_delta(matviewname, NEW_DELTA_ENRNAME, &target_list_buf);
+	}
+
+	/* We're done maintaining the materialized view. */
+	CloseMatViewIncrementalMaintenance();
+
+	table_close(matviewRel, NoLock);
+
+	/* Close SPI context. */
+	if (SPI_finish() != SPI_OK_FINISH)
+		elog(ERROR, "SPI_finish failed");
+}
+
+/*
+ * apply_old_delta
+ *
+ * Execute a query for applying a delta table given by deltname_old
+ * which contains tuples to be deleted from to a materialized view given by
+ * matviewname.  This is used when counting is not required.
+ */
+static void
+apply_old_delta(const char *matviewname, const char *deltaname_old,
+				List *keys)
+{
+	StringInfoData	querybuf;
+	StringInfoData	keysbuf;
+	char   *match_cond;
+	ListCell *lc;
+
+	/* build WHERE condition for searching tuples to be deleted */
+	match_cond = get_matching_condition_string(keys);
+
+	/* build string of keys list */
+	initStringInfo(&keysbuf);
+	foreach (lc, keys)
+	{
+		Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc);
+		char   *resname = NameStr(attr->attname);
+		appendStringInfo(&keysbuf, "%s", quote_qualified_identifier("mv", resname));
+		if (lnext(keys, lc))
+			appendStringInfo(&keysbuf, ", ");
+	}
+
+	/* Search for matching tuples from the view and update or delete if found. */
+	initStringInfo(&querybuf);
+	appendStringInfo(&querybuf,
+	"DELETE FROM %s WHERE ctid IN ("
+		"SELECT tid FROM (SELECT pg_catalog.row_number() over (partition by %s) AS \"__ivm_row_number__\","
+								  "mv.ctid AS tid,"
+								  "diff.\"__ivm_count__\""
+						 "FROM %s AS mv, %s AS diff "
+						 "WHERE %s) v "
+					"WHERE v.\"__ivm_row_number__\" OPERATOR(pg_catalog.<=) v.\"__ivm_count__\")",
+					matviewname,
+					keysbuf.data,
+					matviewname, deltaname_old,
+					match_cond);
+
+	if (SPI_exec(querybuf.data, 0) != SPI_OK_DELETE)
+		elog(ERROR, "SPI_exec failed: %s", querybuf.data);
+}
+
+/*
+ * apply_new_delta
+ *
+ * Execute a query for applying a delta table given by deltname_new
+ * which contains tuples to be inserted into a materialized view given by
+ * matviewname.  This is used when counting is not required.
+ */
+static void
+apply_new_delta(const char *matviewname, const char *deltaname_new,
+				StringInfo target_list)
+{
+	StringInfoData	querybuf;
+
+	/* Search for matching tuples from the view and update or delete if found. */
+	initStringInfo(&querybuf);
+	appendStringInfo(&querybuf,
+					"INSERT INTO %s (%s) SELECT %s FROM ("
+						"SELECT diff.*, pg_catalog.generate_series(1, diff.\"__ivm_count__\")"
+							" AS __ivm_generate_series__ "
+						"FROM %s AS diff) AS v",
+					matviewname, target_list->data, target_list->data,
+					deltaname_new);
+
+	if (SPI_exec(querybuf.data, 0) != SPI_OK_INSERT)
+		elog(ERROR, "SPI_exec failed: %s", querybuf.data);
+}
+
+/*
+ * get_matching_condition_string
+ *
+ * Build a predicate string for looking for a tuple with given keys.
+ */
+static char *
+get_matching_condition_string(List *keys)
+{
+	StringInfoData match_cond;
+	ListCell	*lc;
+
+	/* If there is no key columns, the condition is always true. */
+	if (keys == NIL)
+		return "true";
+
+	initStringInfo(&match_cond);
+	foreach (lc, keys)
+	{
+		Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc);
+		char   *resname = NameStr(attr->attname);
+		char   *mv_resname = quote_qualified_identifier("mv", resname);
+		char   *diff_resname = quote_qualified_identifier("diff", resname);
+		Oid		typid = attr->atttypid;
+
+		/* Considering NULL values, we can not use simple = operator. */
+		appendStringInfo(&match_cond, "(");
+		generate_equal(&match_cond, typid, mv_resname, diff_resname);
+		appendStringInfo(&match_cond, " OR (%s IS NULL AND %s IS NULL))",
+						 mv_resname, diff_resname);
+
+		if (lnext(keys, lc))
+			appendStringInfo(&match_cond, " AND ");
+	}
+
+	return match_cond.data;
+}
+
+/*
+ * generate_equals
+ *
+ * Generate an equality clause using given operands' default equality
+ * operator.
+ */
+static void
+generate_equal(StringInfo querybuf, Oid opttype,
+			   const char *leftop, const char *rightop)
+{
+	TypeCacheEntry *typentry;
+
+	typentry = lookup_type_cache(opttype, TYPECACHE_EQ_OPR);
+	if (!OidIsValid(typentry->eq_opr))
+		ereport(ERROR,
+				(errcode(ERRCODE_UNDEFINED_FUNCTION),
+				 errmsg("could not identify an equality operator for type %s",
+						format_type_be_qualified(opttype))));
+
+	generate_operator_clause(querybuf,
+							 leftop, opttype,
+							 typentry->eq_opr,
+							 rightop, opttype);
+}
+
+/*
+ * mv_InitHashTables
+ */
+static void
+mv_InitHashTables(void)
+{
+	HASHCTL		ctl;
+
+	memset(&ctl, 0, sizeof(ctl));
+	ctl.keysize = sizeof(Oid);
+	ctl.entrysize = sizeof(MV_TriggerHashEntry);
+	mv_trigger_info = hash_create("MV trigger info",
+								 MV_INIT_QUERYHASHSIZE,
+								 &ctl, HASH_ELEM | HASH_BLOBS);
+
+	memset(&ctl, 0, sizeof(ctl));
+	ctl.keysize = sizeof(Oid);
+	ctl.entrysize = sizeof(DroppedImmvInfo);
+	dropped_immv = hash_create("Dropped IMMVs", 16,
+							   &ctl, HASH_ELEM | HASH_BLOBS);
+}
+
+/*
+ * AtAbort_IVM
+ *
+ * Clean up hash entries for all materialized views. This is called at
+ * (sub-)transaction abort. When the top-level transaction is aborted,
+ * InvalidSubTransactionId is set to subxid.
+ *
+ * Also, remove dropped IMMV information if it is aborted.
+ */
+void
+AtAbort_IVM(SubTransactionId subxid)
+{
+	HASH_SEQ_STATUS seq;
+
+	if (mv_trigger_info)
+	{
+		MV_TriggerHashEntry *entry;
+		hash_seq_init(&seq, mv_trigger_info);
+		while ((entry = hash_seq_search(&seq)) != NULL)
+			clean_up_IVM_hash_entry(entry, true, subxid);
+	}
+
+	if (dropped_immv)
+	{
+		DroppedImmvInfo *entry;
+		hash_seq_init(&seq, dropped_immv);
+		while ((entry = hash_seq_search(&seq)) != NULL)
+		{
+			if (subxid == InvalidSubTransactionId || subxid == entry->subxid)
+				hash_search(dropped_immv, (void *) &entry->immv_oid, HASH_REMOVE, NULL);
+		}
+	}
+
+	in_delta_calculation = false;
+}
+
+/*
+ * AtPreCommit_IVM
+ *
+ * Record the transaction ID that updated the view incrementally.
+ * Also, remove the entry for dropped IMMVs.
+ */
+void
+AtPreCommit_IVM(void)
+{
+	HASH_SEQ_STATUS seq;
+
+	if (mv_trigger_info)
+	{
+		MV_TriggerHashEntry *entry;
+
+		/*
+		 * Record the transaction ID that udpate the view incrementally,
+		 * and perform the final clean up of the entry.
+		 */
+		hash_seq_init(&seq, mv_trigger_info);
+		while ((entry = hash_seq_search(&seq)) != NULL)
+		{
+			setLastUpdateXid(entry->matview_id, GetTopFullTransactionId());
+			hash_search(mv_trigger_info, (void *) &entry->matview_id, HASH_REMOVE, NULL);
+		}
+	}
+
+	if (dropped_immv)
+	{
+		DroppedImmvInfo *entry;
+
+		LWLockAcquire(IvmControlLock, LW_EXCLUSIVE);
+		hash_seq_init(&seq, dropped_immv);
+		while ((entry = hash_seq_search(&seq)) != NULL)
+		{
+			hash_search(LastIvmUpdateHash, (void *) &entry->immv_oid, HASH_REMOVE, NULL);
+			hash_search(dropped_immv, (void *) &entry->immv_oid, HASH_REMOVE, NULL);
+		}
+		LWLockRelease(IvmControlLock);
+	}
+
+	in_delta_calculation = false;
+}
+
+/*
+ * clean_up_IVM_hash_entry
+ *
+ * Clean up tuple stores and hash entries for a materialized view after its
+ * maintenance finished. This is called at the end of table modifying query
+ * or (sub-)transaction abort. When the top-level transaction is aborted,
+ * InvalidSubTransactionId is set to subxid.
+ */
+static void
+clean_up_IVM_hash_entry(MV_TriggerHashEntry *entry, bool is_abort,
+						SubTransactionId subxid)
+{
+	bool found;
+	ListCell *lc;
+
+	/* clean up tuple stores */
+	foreach(lc, entry->tables)
+	{
+		MV_TriggerTable *table = (MV_TriggerTable *) lfirst(lc);
+
+		list_free(table->old_tuplestores);
+		list_free(table->new_tuplestores);
+		if (!is_abort)
+		{
+			ExecDropSingleTupleTableSlot(table->slot);
+			table_close(table->rel, NoLock);
+		}
+	}
+	list_free(entry->tables);
+	entry->tables = NIL;
+
+	if (is_abort)
+	{
+		bool	remove_entry = false;
+
+		/*
+		 * When the top-level transaction is aborted, remove all subxids.
+		 * When a sub-transaction is aborted, remove only its subxid.
+		 */
+		if (subxid == InvalidSubTransactionId)
+			remove_entry = true;
+		else
+		{
+			foreach(lc, entry->subxids)
+			{
+				if (lfirst_xid(lc) == subxid)
+				{
+					entry->subxids = list_delete_cell(entry->subxids, lc);
+					break;
+				}
+			}
+
+			/*
+			 * If all the subxid are removed, it means that the view was not
+			 * updated at all in this transaction.
+			 */
+			if (list_length(entry->subxids) == 0)
+				remove_entry = true;
+		}
+
+		/*
+		 * Remove entries of not updated views from the hash table.
+		 */
+		if (remove_entry)
+			hash_search(mv_trigger_info, (void *) &entry->matview_id, HASH_REMOVE, &found);
+	}
+	else
+	{
+		/* When the query sucsessully finished, unregister the snapshot */
+		UnregisterSnapshot(entry->snapshot);
+	}
+
+	entry->snapshot = InvalidSnapshot;
+}
+
+/*
+ * setLastUpdateXid
+ *
+ * Store the transaction ID that updated the view incremenally.
+ */
+static void
+setLastUpdateXid(Oid immv_oid, FullTransactionId xid)
+{
+	LastIvmUpdateEntry *entry;
+
+	LWLockAcquire(IvmControlLock, LW_EXCLUSIVE);
+	entry = (LastIvmUpdateEntry *) hash_search(LastIvmUpdateHash, (void *) &immv_oid, HASH_ENTER, NULL);
+	entry->oid = immv_oid;
+	entry->last_ivm_update = xid;
+	LWLockRelease(IvmControlLock);
+}
+
+/*
+ * getLastUpdateXid
+ *
+ * Get the most recent transaction ID that updated the view incrementally.
+ */
+static FullTransactionId
+getLastUpdateXid(Oid immv_oid)
+{
+	FullTransactionId xid = InvalidFullTransactionId;
+	LastIvmUpdateEntry *entry;
+	bool found;
+
+	LWLockAcquire(IvmControlLock, LW_SHARED);
+	entry = (LastIvmUpdateEntry *) hash_search(LastIvmUpdateHash, (void *) &immv_oid, HASH_FIND, &found);
+	LWLockRelease(IvmControlLock);
+	if (found)
+		xid = entry->last_ivm_update;
+
+	return xid;
+}
+
+void
+removeImmv(Oid immv_oid)
+{
+	DroppedImmvInfo *entry;
+
+	if (!dropped_immv)
+		mv_InitHashTables();
+
+	entry = (DroppedImmvInfo *) hash_search(dropped_immv, (void *) &immv_oid, HASH_ENTER, NULL);
+	entry->subxid = GetCurrentSubTransactionId();
+}
+
+/*
+ * isIvmName
+ *
+ * Check if this is a IVM hidden column from the name.
+ */
+bool
+isIvmName(const char *s)
+{
+	if (s)
+		return (strncmp(s, "__ivm_", 6) == 0);
+	return false;
+}
diff --git a/src/backend/commands/tablecmds.c b/src/backend/commands/tablecmds.c
index 95abaf4890c..95e974e1138 100644
--- a/src/backend/commands/tablecmds.c
+++ b/src/backend/commands/tablecmds.c
@@ -62,6 +62,7 @@
 #include "commands/defrem.h"
 #include "commands/event_trigger.h"
 #include "commands/extension.h"
+#include "commands/matview.h"
 #include "commands/repack.h"
 #include "commands/sequence.h"
 #include "commands/tablecmds.h"
@@ -1811,6 +1812,9 @@ RangeVarCallbackForDropRelation(const RangeVar *rel, Oid relOid, Oid oldRelOid,
 	state->actual_relkind = classform->relkind;
 	state->actual_relpersistence = classform->relpersistence;
 
+	if (classform->relkind == RELKIND_MATVIEW && classform->relisivm)
+		removeImmv(relOid);
+
 	/*
 	 * Both RELKIND_RELATION and RELKIND_PARTITIONED_TABLE are OBJECT_TABLE,
 	 * but RemoveRelations() can only pass one relkind for a given relation.
diff --git a/src/backend/utils/activity/wait_event_names.txt b/src/backend/utils/activity/wait_event_names.txt
index 560659f9568..d97c35eeef0 100644
--- a/src/backend/utils/activity/wait_event_names.txt
+++ b/src/backend/utils/activity/wait_event_names.txt
@@ -370,6 +370,7 @@ WaitLSN	"Waiting to read or update shared Wait-for-LSN state."
 LogicalDecodingControl	"Waiting to read or update logical decoding status information."
 DataChecksumsWorker	"Waiting for data checksums worker."
 AioWorkerControl	"Waiting to update AIO worker information."
+IvmControl	"Waiting for read or update IMMV information.."
 
 #
 # END OF PREDEFINED LWLOCKS (DO NOT CHANGE THIS LINE)
diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat
index 3cb84359adf..65a739af22a 100644
--- a/src/include/catalog/pg_proc.dat
+++ b/src/include/catalog/pg_proc.dat
@@ -12718,4 +12718,14 @@
   proname => 'hashoid8extended', prorettype => 'int8',
   proargtypes => 'oid8 int8', prosrc => 'hashoid8extended' },
 
+# IVM
+{ oid => '786', descr => 'ivm trigger (before)',
+  proname => 'IVM_immediate_before', provolatile => 'v', prorettype => 'trigger',
+  proargtypes => '', prosrc => 'IVM_immediate_before' },
+{ oid => '787', descr => 'ivm trigger (after)',
+  proname => 'IVM_immediate_maintenance', provolatile => 'v', prorettype => 'trigger',
+  proargtypes => '', prosrc => 'IVM_immediate_maintenance' },
+{ oid => '788', descr => 'ivm filetring ',
+  proname => 'ivm_visible_in_prestate', provolatile => 's', prorettype => 'bool',
+  proargtypes => 'oid tid oid', prosrc => 'ivm_visible_in_prestate' },
 ]
diff --git a/src/include/commands/createas.h b/src/include/commands/createas.h
index f895c67c0c2..c286ebcd70e 100644
--- a/src/include/commands/createas.h
+++ b/src/include/commands/createas.h
@@ -16,6 +16,7 @@
 
 #include "catalog/objectaddress.h"
 #include "nodes/params.h"
+#include "nodes/pathnodes.h"
 #include "parser/parse_node.h"
 #include "tcop/dest.h"
 #include "utils/queryenvironment.h"
@@ -25,6 +26,9 @@ extern ObjectAddress ExecCreateTableAs(ParseState *pstate, CreateTableAsStmt *st
 									   ParamListInfo params, QueryEnvironment *queryEnv,
 									   QueryCompletion *qc);
 
+extern void CreateIvmTriggersOnBaseTables(Query *qry, Oid matviewOid);
+extern void CreateIndexOnIMMV(Query *query, Relation matviewRel);
+
 extern int	GetIntoRelEFlags(IntoClause *intoClause);
 
 extern DestReceiver *CreateIntoRelDestReceiver(IntoClause *intoClause);
diff --git a/src/include/commands/matview.h b/src/include/commands/matview.h
index 738c731c1a9..f1dbfc052c5 100644
--- a/src/include/commands/matview.h
+++ b/src/include/commands/matview.h
@@ -15,6 +15,7 @@
 #define MATVIEW_H
 
 #include "catalog/objectaddress.h"
+#include "fmgr.h"
 #include "nodes/params.h"
 #include "nodes/parsenodes.h"
 #include "tcop/dest.h"
@@ -23,6 +24,8 @@
 
 extern void SetMatViewPopulatedState(Relation relation, bool newstate);
 
+extern void SetMatViewIVMState(Relation relation, bool newstate);
+
 extern ObjectAddress ExecRefreshMatView(RefreshMatViewStmt *stmt, const char *queryString,
 										QueryCompletion *qc);
 extern ObjectAddress RefreshMatViewByOid(Oid matviewOid, bool is_create, bool skipData,
@@ -33,4 +36,12 @@ extern DestReceiver *CreateTransientRelDestReceiver(Oid transientoid);
 
 extern bool MatViewIncrementalMaintenanceIsEnabled(void);
 
+extern Datum IVM_immediate_before(PG_FUNCTION_ARGS);
+extern Datum IVM_immediate_maintenance(PG_FUNCTION_ARGS);
+extern Datum IVM_visible_in_prestate(PG_FUNCTION_ARGS);
+extern void AtAbort_IVM(SubTransactionId subtxid);
+extern void AtPreCommit_IVM(void);
+extern void removeImmv(Oid immv_oid);
+extern bool isIvmName(const char *s);
+
 #endif							/* MATVIEW_H */
diff --git a/src/include/storage/lwlocklist.h b/src/include/storage/lwlocklist.h
index d7eb648bd27..756c63baf97 100644
--- a/src/include/storage/lwlocklist.h
+++ b/src/include/storage/lwlocklist.h
@@ -89,6 +89,7 @@ PG_LWLOCK(54, WaitLSN)
 PG_LWLOCK(55, LogicalDecodingControl)
 PG_LWLOCK(56, DataChecksumsWorker)
 PG_LWLOCK(57, AioWorkerControl)
+PG_LWLOCK(58, IvmControl)
 
 /*
  * There also exist several built-in LWLock tranches.  As with the predefined
diff --git a/src/include/storage/subsystemlist.h b/src/include/storage/subsystemlist.h
index 9ad619080be..481e15d00a1 100644
--- a/src/include/storage/subsystemlist.h
+++ b/src/include/storage/subsystemlist.h
@@ -88,3 +88,6 @@ PG_SHMEM_SUBSYSTEM(DataChecksumsShmemCallbacks)
 
 /* AIO subsystem. This delegates to the method-specific callbacks */
 PG_SHMEM_SUBSYSTEM(AioShmemCallbacks)
+
+/* Incremental View Maintenance */
+PG_SHMEM_SUBSYSTEM(IvmShmemCallbacks)
-- 
2.43.0


--Multipart=_Fri__3_Jul_2026_19_11_16_+0900_CskxSIu_iGcDMEyM
Content-Type: text/x-diff;
 name="v39-0005-Add-Incremental-View-Maintenance-support-to-psql.patch"
Content-Disposition: attachment;
 filename="v39-0005-Add-Incremental-View-Maintenance-support-to-psql.patch"
Content-Transfer-Encoding: 7bit



^ permalink  raw  reply  [nested|flat] 101+ messages in thread

* [PATCH v37 06/11] Add Incremental View Maintenance support
@ 2026-05-29 09:06  Yugo Nagata <[email protected]>
  0 siblings, 0 replies; 101+ messages in thread

From: Yugo Nagata @ 2026-05-29 09:06 UTC (permalink / raw)

In this implementation, AFTER triggers are used to collect
tuplestores containing transition table contents. When multiple tables
are changed, multiple AFTER triggers are invoked, then the final AFTER
trigger performs actual update of the matview. In addition, BEFORE
triggers are also used to handle global information for view
maintenance.

To calculate view deltas, we need both pre-state and post-state of base
tables. Post-update states are available in AFTER trigger, and pre-update
states can be calculated by removing inserted tuples and appending deleted
tuples. Insterted tuples are filtered using the snapshot taken before
table modification, and deleted tuples are contained in the old transition
table.

Incrementally Maintainable Materialized Views (IMMV) can contain
duplicated tuples.

This patch also allows self-join, simultaneous updates of more than
one base table, and multiple updates of the same base table.
---
 src/backend/access/transam/xact.c             |    8 +
 src/backend/commands/createas.c               |  709 +++++++
 src/backend/commands/matview.c                | 1835 ++++++++++++++++-
 src/backend/commands/tablecmds.c              |    4 +
 .../utils/activity/wait_event_names.txt       |    1 +
 src/include/catalog/pg_proc.dat               |   10 +
 src/include/commands/createas.h               |    4 +
 src/include/commands/matview.h                |   11 +
 src/include/storage/lwlocklist.h              |    1 +
 src/include/storage/subsystemlist.h           |    3 +
 10 files changed, 2548 insertions(+), 38 deletions(-)

diff --git a/src/backend/access/transam/xact.c b/src/backend/access/transam/xact.c
index 5586fbe5b07..302a4822d50 100644
--- a/src/backend/access/transam/xact.c
+++ b/src/backend/access/transam/xact.c
@@ -37,6 +37,7 @@
 #include "catalog/pg_enum.h"
 #include "catalog/storage.h"
 #include "commands/async.h"
+#include "commands/matview.h"
 #include "commands/tablecmds.h"
 #include "commands/trigger.h"
 #include "common/pg_prng.h"
@@ -2322,6 +2323,9 @@ CommitTransaction(void)
 	CallXactCallbacks(is_parallel_worker ? XACT_EVENT_PARALLEL_PRE_COMMIT
 					  : XACT_EVENT_PRE_COMMIT);
 
+	/* Store the transaction ID that updated the view incrementally */
+	AtPreCommit_IVM();
+
 	/*
 	 * If this xact has started any unfinished parallel operation, clean up
 	 * its workers, warning about leaked resources.  (But we don't actually
@@ -2971,6 +2975,7 @@ AbortTransaction(void)
 	AtAbort_Notify();
 	AtEOXact_RelationMap(false, is_parallel_worker);
 	AtAbort_Twophase();
+	AtAbort_IVM(InvalidSubTransactionId);
 
 	/*
 	 * Advertise the fact that we aborted in pg_xact (assuming that we got as
@@ -5301,6 +5306,9 @@ AbortSubTransaction(void)
 
 	UnlockBuffers();
 
+	/* Clean up hash entries for incremental view maintenance */
+	AtAbort_IVM(s->subTransactionId);
+
 	/* Reset WAL record construction state */
 	XLogResetInsertion();
 
diff --git a/src/backend/commands/createas.c b/src/backend/commands/createas.c
index 6dbb831ca89..a499688b79d 100644
--- a/src/backend/commands/createas.c
+++ b/src/backend/commands/createas.c
@@ -29,18 +29,32 @@
 #include "access/tableam.h"
 #include "access/xact.h"
 #include "catalog/namespace.h"
+#include "catalog/index.h"
+#include "catalog/pg_am_d.h"
+#include "catalog/pg_constraint.h"
+#include "catalog/pg_inherits.h"
+#include "catalog/pg_trigger.h"
 #include "catalog/toasting.h"
 #include "commands/createas.h"
+#include "commands/defrem.h"
 #include "commands/matview.h"
 #include "commands/prepare.h"
 #include "commands/tablecmds.h"
+#include "commands/tablespace.h"
+#include "commands/trigger.h"
 #include "commands/view.h"
 #include "executor/execdesc.h"
 #include "executor/executor.h"
+#include "miscadmin.h"
 #include "nodes/makefuncs.h"
 #include "nodes/nodeFuncs.h"
 #include "nodes/queryjumble.h"
+#include "optimizer/optimizer.h"
+#include "optimizer/prep.h"
 #include "parser/analyze.h"
+#include "parser/parser.h"
+#include "parser/parsetree.h"
+#include "parser/parse_clause.h"
 #include "rewrite/rewriteHandler.h"
 #include "tcop/tcopprot.h"
 #include "utils/builtins.h"
@@ -70,6 +84,12 @@ static bool intorel_receive(TupleTableSlot *slot, DestReceiver *self);
 static void intorel_shutdown(DestReceiver *self);
 static void intorel_destroy(DestReceiver *self);
 
+static void CreateIvmTriggersOnBaseTablesRecurse(Query *qry, Node *node, Oid matviewOid,
+									 List **relids, bool ex_lock);
+static void CreateIvmTrigger(Oid relOid, Oid viewOid, int16 type, int16 timing, bool ex_lock);
+static void check_ivm_restriction(Node *node);
+static bool check_ivm_restriction_walker(Node *node, void *context);
+static Bitmapset *get_primary_key_attnos_from_query(Query *query, List **constraintList);
 
 /*
  * create_ctas_internal
@@ -277,6 +297,18 @@ ExecCreateTableAs(ParseState *pstate, CreateTableAsStmt *stmt,
 		into->skipData = true;
 	}
 
+	if (is_matview && into->ivm)
+	{
+		/* check if the query is supported in IMMV definition */
+		if (contain_mutable_functions((Node *) query))
+			ereport(ERROR,
+					(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+					 errmsg("mutable function is not supported on incrementally maintainable materialized view"),
+					 errhint("functions must be marked IMMUTABLE")));
+
+		check_ivm_restriction((Node *) query);
+	}
+
 	if (into->skipData)
 	{
 		/*
@@ -287,15 +319,36 @@ ExecCreateTableAs(ParseState *pstate, CreateTableAsStmt *stmt,
 		 */
 		address = create_ctas_nodata(query->targetList, into);
 
+		/*
+		 * For IVM, mark the matview before refresh so RelationIsIVM()
+		 * returns true inside RefreshMatViewByOid.
+		 */
+		if (is_matview && into->ivm)
+		{
+			Relation matviewRel = table_open(address.objectId, NoLock);
+
+			SetMatViewIVMState(matviewRel, true);
+			table_close(matviewRel, NoLock);
+			CommandCounterIncrement();
+		}
+
 		/*
 		 * For materialized views, reuse the REFRESH logic, which locks down
 		 * security-restricted operations and restricts the search_path.  This
 		 * reduces the chance that a subsequent refresh will fail.
 		 */
 		if (do_refresh)
+		{
 			RefreshMatViewByOid(address.objectId, true, false, false,
 								pstate->p_sourcetext, qc);
 
+			if (is_matview && into->ivm && IsolationUsesXactSnapshot())
+				ereport(WARNING,
+						(errmsg("inconsistent view can be created in isolation level SERIALIZABLE or REPEATABLE READ"),
+						 errdetail("The view may not include effects of a concurrent transaction."),
+						 errhint("The view with incremental maintenance should be created in isolation level READ COMMITTED, "
+								 "or refreshed manually to make sure the view is consistent.")));
+		}
 	}
 	else
 	{
@@ -635,3 +688,659 @@ intorel_destroy(DestReceiver *self)
 {
 	pfree(self);
 }
+
+/*
+ * CreateIvmTriggersOnBaseTables -- create IVM triggers on all base tables
+ */
+void
+CreateIvmTriggersOnBaseTables(Query *qry, Oid matviewOid)
+{
+	List   *relids = NIL;
+	bool	ex_lock = false;
+	RangeTblEntry *rte;
+
+	/* Immediately return if we don't have any base tables. */
+	if (list_length(qry->rtable) < 1)
+		return;
+
+	/*
+	 * If the view has more than one base tables, we need an exclusive lock
+	 * on the view so that the view would be maintained serially to avoid
+	 * the inconsistency that occurs when two base tables are modified in
+	 * concurrent transactions. However, if the view has only one table,
+	 * we can use a weaker lock.
+	 *
+	 * The type of lock should be determined here, because if we check the
+	 * view definition at maintenance time, we need to acquire a weaker lock,
+	 * and upgrading the lock level after this increases probability of
+	 * deadlock.
+	 */
+
+	rte = list_nth(qry->rtable, 0);
+	if (list_length(qry->rtable) > 1 || rte->rtekind != RTE_RELATION)
+		ex_lock = true;
+
+	CreateIvmTriggersOnBaseTablesRecurse(qry, (Node *)qry, matviewOid, &relids, ex_lock);
+
+	list_free(relids);
+}
+
+static void
+CreateIvmTriggersOnBaseTablesRecurse(Query *qry, Node *node, Oid matviewOid,
+									 List **relids, bool ex_lock)
+{
+	if (node == NULL)
+		return;
+
+	/* This can recurse, so check for excessive recursion */
+	check_stack_depth();
+
+	switch (nodeTag(node))
+	{
+		case T_Query:
+			{
+				Query *query = (Query *) node;
+
+				CreateIvmTriggersOnBaseTablesRecurse(qry, (Node *)query->jointree, matviewOid, relids, ex_lock);
+			}
+			break;
+
+		case T_RangeTblRef:
+			{
+				int			rti = ((RangeTblRef *) node)->rtindex;
+				RangeTblEntry *rte = rt_fetch(rti, qry->rtable);
+
+				if (rte->rtekind == RTE_RELATION && !list_member_oid(*relids, rte->relid))
+				{
+					CreateIvmTrigger(rte->relid, matviewOid, TRIGGER_TYPE_INSERT, TRIGGER_TYPE_BEFORE, ex_lock);
+					CreateIvmTrigger(rte->relid, matviewOid, TRIGGER_TYPE_DELETE, TRIGGER_TYPE_BEFORE, ex_lock);
+					CreateIvmTrigger(rte->relid, matviewOid, TRIGGER_TYPE_UPDATE, TRIGGER_TYPE_BEFORE, ex_lock);
+					CreateIvmTrigger(rte->relid, matviewOid, TRIGGER_TYPE_TRUNCATE, TRIGGER_TYPE_BEFORE, true);
+					CreateIvmTrigger(rte->relid, matviewOid, TRIGGER_TYPE_INSERT, TRIGGER_TYPE_AFTER, ex_lock);
+					CreateIvmTrigger(rte->relid, matviewOid, TRIGGER_TYPE_DELETE, TRIGGER_TYPE_AFTER, ex_lock);
+					CreateIvmTrigger(rte->relid, matviewOid, TRIGGER_TYPE_UPDATE, TRIGGER_TYPE_AFTER, ex_lock);
+					CreateIvmTrigger(rte->relid, matviewOid, TRIGGER_TYPE_TRUNCATE, TRIGGER_TYPE_AFTER, true);
+
+					*relids = lappend_oid(*relids, rte->relid);
+				}
+			}
+			break;
+
+		case T_FromExpr:
+			{
+				FromExpr   *f = (FromExpr *) node;
+				ListCell   *l;
+
+				foreach(l, f->fromlist)
+					CreateIvmTriggersOnBaseTablesRecurse(qry, lfirst(l), matviewOid, relids, ex_lock);
+			}
+			break;
+
+		case T_JoinExpr:
+			{
+				JoinExpr   *j = (JoinExpr *) node;
+
+				CreateIvmTriggersOnBaseTablesRecurse(qry, j->larg, matviewOid, relids, ex_lock);
+				CreateIvmTriggersOnBaseTablesRecurse(qry, j->rarg, matviewOid, relids, ex_lock);
+			}
+			break;
+
+		default:
+			elog(ERROR, "unrecognized node type: %d", (int) nodeTag(node));
+	}
+}
+
+/*
+ * CreateIvmTrigger -- create IVM trigger on a base table
+ */
+static void
+CreateIvmTrigger(Oid relOid, Oid viewOid, int16 type, int16 timing, bool ex_lock)
+{
+	ObjectAddress	refaddr;
+	ObjectAddress	address;
+	CreateTrigStmt *ivm_trigger;
+	List *transitionRels = NIL;
+
+	Assert(timing == TRIGGER_TYPE_BEFORE || timing == TRIGGER_TYPE_AFTER);
+
+	refaddr.classId = RelationRelationId;
+	refaddr.objectId = viewOid;
+	refaddr.objectSubId = 0;
+
+	ivm_trigger = makeNode(CreateTrigStmt);
+	ivm_trigger->relation = NULL;
+	ivm_trigger->row = false;
+
+	ivm_trigger->timing = timing;
+	ivm_trigger->events = type;
+
+	switch (type)
+	{
+		case TRIGGER_TYPE_INSERT:
+			ivm_trigger->trigname = (timing == TRIGGER_TYPE_BEFORE ? "IVM_trigger_ins_before" : "IVM_trigger_ins_after");
+			break;
+		case TRIGGER_TYPE_DELETE:
+			ivm_trigger->trigname = (timing == TRIGGER_TYPE_BEFORE ? "IVM_trigger_del_before" : "IVM_trigger_del_after");
+			break;
+		case TRIGGER_TYPE_UPDATE:
+			ivm_trigger->trigname = (timing == TRIGGER_TYPE_BEFORE ? "IVM_trigger_upd_before" : "IVM_trigger_upd_after");
+			break;
+		case TRIGGER_TYPE_TRUNCATE:
+			ivm_trigger->trigname = (timing == TRIGGER_TYPE_BEFORE ? "IVM_trigger_truncate_before" : "IVM_trigger_truncate_after");
+			break;
+		default:
+			elog(ERROR, "unsupported trigger type");
+	}
+
+	if (timing == TRIGGER_TYPE_AFTER)
+	{
+		if (type == TRIGGER_TYPE_INSERT || type == TRIGGER_TYPE_UPDATE)
+		{
+			TriggerTransition *n = makeNode(TriggerTransition);
+			n->name = "__ivm_newtable";
+			n->isNew = true;
+			n->isTable = true;
+
+			transitionRels = lappend(transitionRels, n);
+		}
+		if (type == TRIGGER_TYPE_DELETE || type == TRIGGER_TYPE_UPDATE)
+		{
+			TriggerTransition *n = makeNode(TriggerTransition);
+			n->name = "__ivm_oldtable";
+			n->isNew = false;
+			n->isTable = true;
+
+			transitionRels = lappend(transitionRels, n);
+		}
+	}
+
+	/*
+	 * XXX: When using DELETE or UPDATE, we must use exclusive lock for now
+	 * because apply_old_delta(_with_count) uses ctid to identify the tuple
+	 * to be deleted/deleted, but doesn't work in concurrent situations.
+	 *
+	 * If the view doesn't have aggregate, distinct, or tuple duplicate,
+	 * then it would work even in concurrent situations. However, we don't have
+	 * any way to guarantee the view has a unique key before opening the IMMV
+	 * at the maintenance time because users may drop the unique index.
+	 */
+
+	if (type == TRIGGER_TYPE_DELETE || type == TRIGGER_TYPE_UPDATE)
+		ex_lock = true;
+
+	ivm_trigger->funcname =
+		(timing == TRIGGER_TYPE_BEFORE ? SystemFuncName("IVM_immediate_before") : SystemFuncName("IVM_immediate_maintenance"));
+
+	ivm_trigger->columns = NIL;
+	ivm_trigger->transitionRels = transitionRels;
+	ivm_trigger->whenClause = NULL;
+	ivm_trigger->isconstraint = false;
+	ivm_trigger->deferrable = false;
+	ivm_trigger->initdeferred = false;
+	ivm_trigger->constrrel = NULL;
+	ivm_trigger->args = list_make2(
+		makeString(DatumGetPointer(DirectFunctionCall1(oidout, ObjectIdGetDatum(viewOid)))),
+		makeString(DatumGetPointer(DirectFunctionCall1(boolout, BoolGetDatum(ex_lock))))
+		);
+
+	address = CreateTrigger(ivm_trigger, NULL, relOid, InvalidOid, InvalidOid,
+						 InvalidOid, InvalidOid, InvalidOid, NULL, true, false);
+
+	recordDependencyOn(&address, &refaddr, DEPENDENCY_AUTO);
+
+	/* Make changes-so-far visible */
+	CommandCounterIncrement();
+}
+
+/*
+ * check_ivm_restriction --- look for specify nodes in the query tree
+ */
+static void
+check_ivm_restriction(Node *node)
+{
+	check_ivm_restriction_walker(node, NULL);
+}
+
+static bool
+check_ivm_restriction_walker(Node *node, void *context)
+{
+	if (node == NULL)
+		return false;
+
+	/*
+	 * We currently don't support Sub-Query.
+	 */
+	if (IsA(node, SubPlan) || IsA(node, SubLink))
+		ereport(ERROR,
+				(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+				 errmsg("subquery is not supported on incrementally maintainable materialized view")));
+
+	/* This can recurse, so check for excessive recursion */
+	check_stack_depth();
+
+	switch (nodeTag(node))
+	{
+		case T_Query:
+			{
+				Query *qry = (Query *)node;
+				ListCell   *lc;
+				List       *vars;
+
+				/* if contained CTE, return error */
+				if (qry->cteList != NIL)
+					ereport(ERROR,
+							(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+							 errmsg("CTE is not supported on incrementally maintainable materialized view")));
+				if (qry->havingQual != NULL)
+					ereport(ERROR,
+							(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+							 errmsg(" HAVING clause is not supported on incrementally maintainable materialized view")));
+				if (qry->sortClause != NIL)	/* There is a possibility that we don't need to return an error */
+					ereport(ERROR,
+							(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+							 errmsg("ORDER BY clause is not supported on incrementally maintainable materialized view")));
+				if (qry->limitOffset != NULL || qry->limitCount != NULL)
+					ereport(ERROR,
+							(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+							 errmsg("LIMIT/OFFSET clause is not supported on incrementally maintainable materialized view")));
+				if (qry->distinctClause)
+					ereport(ERROR,
+							(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+							 errmsg("DISTINCT is not supported on incrementally maintainable materialized view")));
+				if (qry->hasDistinctOn)
+					ereport(ERROR,
+							(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+							 errmsg("DISTINCT ON is not supported on incrementally maintainable materialized view")));
+				if (qry->hasWindowFuncs)
+					ereport(ERROR,
+							(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+							 errmsg("window functions are not supported on incrementally maintainable materialized view")));
+				if (qry->groupingSets != NIL)
+					ereport(ERROR,
+							(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+							 errmsg("GROUPING SETS, ROLLUP, or CUBE clauses is not supported on incrementally maintainable materialized view")));
+				if (qry->setOperations != NULL)
+					ereport(ERROR,
+							(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+							 errmsg("UNION/INTERSECT/EXCEPT statements are not supported on incrementally maintainable materialized view")));
+				if (list_length(qry->targetList) == 0)
+					ereport(ERROR,
+							(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+							 errmsg("empty target list is not supported on incrementally maintainable materialized view")));
+				if (qry->rowMarks != NIL)
+					ereport(ERROR,
+							(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+							 errmsg("FOR UPDATE/SHARE clause is not supported on incrementally maintainable materialized view")));
+
+				/* system column restrictions */
+				vars = pull_vars_of_level((Node *) qry, 0);
+				foreach(lc, vars)
+				{
+					if (IsA(lfirst(lc), Var))
+					{
+						Var *var = (Var *) lfirst(lc);
+						/* if system column, return error */
+						if (var->varattno < 0)
+							ereport(ERROR,
+									(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+									 errmsg("system column is not supported on incrementally maintainable materialized view")));
+					}
+				}
+
+				/* check if type in the target list had an equality operator */
+				foreach(lc, qry->targetList)
+				{
+					TargetEntry *tle = (TargetEntry *) lfirst(lc);
+					Oid             atttype = exprType((Node *) tle->expr);
+					Oid             opclass;
+
+					opclass = GetDefaultOpClass(atttype, BTREE_AM_OID);
+					if (!OidIsValid(opclass))
+						ereport(ERROR,
+								(errcode(ERRCODE_UNDEFINED_OBJECT),
+								 errmsg("data type %s has no default operator class for access method \"%s\"",
+									format_type_be(atttype), "btree")));
+				}
+
+				/* restrictions for rtable */
+				foreach(lc, qry->rtable)
+				{
+					RangeTblEntry *rte = (RangeTblEntry *) lfirst(lc);
+
+					if (rte->subquery)
+						ereport(ERROR,
+								(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+								 errmsg("subquery is not supported on incrementally maintainable materialized view")));
+
+					if (rte->tablesample != NULL)
+						ereport(ERROR,
+								(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+								 errmsg("TABLESAMPLE clause is not supported on incrementally maintainable materialized view")));
+
+					if (rte->relkind == RELKIND_PARTITIONED_TABLE)
+						ereport(ERROR,
+								(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+								 errmsg("partitioned table is not supported on incrementally maintainable materialized view")));
+
+					if (rte->relkind == RELKIND_RELATION && has_superclass(rte->relid))
+						ereport(ERROR,
+								(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+								 errmsg("partitions is not supported on incrementally maintainable materialized view")));
+
+					if (rte->relkind == RELKIND_RELATION && find_inheritance_children(rte->relid, NoLock) != NIL)
+						ereport(ERROR,
+								(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+								 errmsg("inheritance parent is not supported on incrementally maintainable materialized view")));
+
+					if (rte->relkind == RELKIND_FOREIGN_TABLE)
+						ereport(ERROR,
+								(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+								 errmsg("foreign table is not supported on incrementally maintainable materialized view")));
+
+					if (rte->relkind == RELKIND_VIEW ||
+						rte->relkind == RELKIND_MATVIEW)
+						ereport(ERROR,
+								(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+								 errmsg("VIEW or MATERIALIZED VIEW is not supported on incrementally maintainable materialized view")));
+
+					if (rte->rtekind == RTE_VALUES)
+						ereport(ERROR,
+								(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+								 errmsg("VALUES is not supported on incrementally maintainable materialized view")));
+
+				}
+
+				query_tree_walker(qry, check_ivm_restriction_walker, NULL, QTW_IGNORE_RANGE_TABLE);
+
+				break;
+			}
+		case T_TargetEntry:
+			{
+				TargetEntry *tle = (TargetEntry *)node;
+				if (isIvmName(tle->resname))
+						ereport(ERROR,
+								(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+								 errmsg("column name %s is not supported on incrementally maintainable materialized view", tle->resname)));
+
+				expression_tree_walker(node, check_ivm_restriction_walker, NULL);
+				break;
+			}
+		case T_JoinExpr:
+			{
+				JoinExpr *joinexpr = (JoinExpr *)node;
+
+				if (joinexpr->jointype > JOIN_INNER)
+						ereport(ERROR,
+								(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+								 errmsg("OUTER JOIN is not supported on incrementally maintainable materialized view")));
+
+				expression_tree_walker(node, check_ivm_restriction_walker, NULL);
+			}
+			break;
+		case T_Aggref:
+			ereport(ERROR,
+					(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+					 errmsg("aggregate function is not supported on incrementally maintainable materialized view")));
+			break;
+		default:
+			expression_tree_walker(node, check_ivm_restriction_walker, (void *) context);
+			break;
+	}
+	return false;
+}
+
+/*
+ * CreateIndexOnIMMV
+ *
+ * Create a unique index on incremental maintainable materialized view.
+ * If the view definition query has a GROUP BY clause, the index is created
+ * on the columns of GROUP BY expressions. Otherwise, if the view contains
+ * all primary key attributes of its base tables in the target list, the index
+ * is created on these attributes. In other cases, no index is created.
+ */
+void
+CreateIndexOnIMMV(Query *query, Relation matviewRel)
+{
+	ListCell *lc;
+	IndexStmt  *index;
+	ObjectAddress address;
+	List *constraintList = NIL;
+	char		idxname[NAMEDATALEN];
+	List	   *indexoidlist = RelationGetIndexList(matviewRel);
+	ListCell   *indexoidscan;
+	Bitmapset *key_attnos;
+
+	snprintf(idxname, sizeof(idxname), "%s_index", RelationGetRelationName(matviewRel));
+
+	index = makeNode(IndexStmt);
+
+	index->unique = true;
+	index->primary = false;
+	index->isconstraint = false;
+	index->deferrable = false;
+	index->initdeferred = false;
+	index->idxname = idxname;
+	index->relation =
+		makeRangeVar(get_namespace_name(RelationGetNamespace(matviewRel)),
+					 pstrdup(RelationGetRelationName(matviewRel)),
+					 -1);
+	index->accessMethod = DEFAULT_INDEX_TYPE;
+	index->options = NIL;
+	index->tableSpace = get_tablespace_name(matviewRel->rd_rel->reltablespace);
+	index->whereClause = NULL;
+	index->indexParams = NIL;
+	index->indexIncludingParams = NIL;
+	index->excludeOpNames = NIL;
+	index->idxcomment = NULL;
+	index->indexOid = InvalidOid;
+	index->oldNumber = InvalidRelFileNumber;
+	index->oldCreateSubid = InvalidSubTransactionId;
+	index->oldFirstRelfilelocatorSubid = InvalidSubTransactionId;
+	index->transformed = true;
+	index->concurrent = false;
+	index->if_not_exists = false;
+
+	/* create index on the base tables' primary key columns */
+	key_attnos = get_primary_key_attnos_from_query(query, &constraintList);
+	if (key_attnos)
+	{
+		foreach(lc, query->targetList)
+		{
+			TargetEntry *tle = (TargetEntry *) lfirst(lc);
+			Form_pg_attribute attr = TupleDescAttr(matviewRel->rd_att, tle->resno - 1);
+
+			if (bms_is_member(tle->resno - FirstLowInvalidHeapAttributeNumber, key_attnos))
+			{
+				IndexElem  *iparam;
+
+				iparam = makeNode(IndexElem);
+				iparam->name = pstrdup(NameStr(attr->attname));
+				iparam->expr = NULL;
+				iparam->indexcolname = NULL;
+				iparam->collation = NIL;
+				iparam->opclass = NIL;
+				iparam->opclassopts = NIL;
+				iparam->ordering = SORTBY_DEFAULT;
+				iparam->nulls_ordering = SORTBY_NULLS_DEFAULT;
+				index->indexParams = lappend(index->indexParams, iparam);
+			}
+		}
+	}
+	else
+	{
+		/* create no index, just notice that an appropriate index is necessary for efficient IVM */
+		ereport(NOTICE,
+				(errmsg("could not create an index on materialized view \"%s\" automatically",
+						RelationGetRelationName(matviewRel)),
+				 errdetail("This target list does not have all the primary key columns. "),
+				 errhint("Create an index on the materialized view for efficient incremental maintenance.")));
+		return;
+	}
+
+	/* If we have a compatible index, we don't need to create another. */
+	foreach(indexoidscan, indexoidlist)
+	{
+		Oid			indexoid = lfirst_oid(indexoidscan);
+		Relation	indexRel;
+		bool		hasCompatibleIndex = false;
+
+		indexRel = index_open(indexoid, AccessShareLock);
+
+		if (CheckIndexCompatible(indexRel->rd_id,
+								index->accessMethod,
+								index->indexParams,
+								index->excludeOpNames,
+								false))
+			hasCompatibleIndex = true;
+
+		index_close(indexRel, AccessShareLock);
+
+		if (hasCompatibleIndex)
+			return;
+	}
+
+	address = DefineIndex(NULL,
+						  RelationGetRelid(matviewRel),
+						  index,
+						  InvalidOid,
+						  InvalidOid,
+						  InvalidOid,
+						  -1,
+						  false, true, false, false, true);
+
+	ereport(NOTICE,
+			(errmsg("created index \"%s\" on materialized view \"%s\"",
+					idxname, RelationGetRelationName(matviewRel))));
+
+	/*
+	 * Make dependencies so that the index is dropped if any base tables'
+	 * primary key is dropped.
+	 */
+	foreach(lc, constraintList)
+	{
+		Oid constraintOid = lfirst_oid(lc);
+		ObjectAddress	refaddr;
+
+		refaddr.classId = ConstraintRelationId;
+		refaddr.objectId = constraintOid;
+		refaddr.objectSubId = 0;
+
+		recordDependencyOn(&address, &refaddr, DEPENDENCY_NORMAL);
+	}
+}
+
+
+/*
+ * get_primary_key_attnos_from_query
+ *
+ * Identify the columns in base tables' primary keys in the target list.
+ *
+ * Returns a Bitmapset of the column attnos of the primary key's columns of
+ * tables that used in the query.  The attnos are offset by
+ * FirstLowInvalidHeapAttributeNumber as same as get_primary_key_attnos.
+ *
+ * If any table has no primary key or any primary key's columns is not in
+ * the target list, return NULL.  We also return NULL if any pkey constraint
+ * is deferrable.
+ *
+ * constraintList is set to a list of the OIDs of the pkey constraints.
+ */
+static Bitmapset *
+get_primary_key_attnos_from_query(Query *query, List **constraintList)
+{
+	List *key_attnos_list = NIL;
+	ListCell *lc;
+	int i;
+	Bitmapset *keys = NULL;
+	Relids	rels_in_from;
+
+	/*
+	 * Collect primary key attributes from all tables used in query. The key attributes
+	 * sets for each table are stored in key_attnos_list in order by RTE index.
+	 */
+	foreach(lc, query->rtable)
+	{
+		RangeTblEntry *r = (RangeTblEntry*) lfirst(lc);
+		Bitmapset *key_attnos;
+		bool	has_no_pkey = false;
+
+		/* for tables, call get_primary_key_attnos */
+		if (r->rtekind == RTE_RELATION)
+		{
+			Oid constraintOid;
+			key_attnos = get_primary_key_attnos(r->relid, false, &constraintOid);
+			*constraintList = lappend_oid(*constraintList, constraintOid);
+			has_no_pkey = (key_attnos == NULL);
+		}
+		/*
+		 * Ignore join rels, because they are flatten later by
+		 * flatten_join_alias_vars(). Store NULL into key_attnos_list
+		 * as a dummy.
+		 */
+		 else if (r->rtekind == RTE_JOIN)
+		 {
+			key_attnos = NULL;
+		}
+		/* for other RTEs, store NULL into key_attnos_list */
+		else
+			has_no_pkey = true;
+
+		/*
+		 * If any table or subquery has no primary key or its pkey constraint is deferrable,
+		 * we cannot get key attributes for this query, so return NULL.
+		 */
+		if (has_no_pkey)
+			return NULL;
+
+		key_attnos_list = lappend(key_attnos_list, key_attnos);
+	}
+
+	/* Collect key attributes appearing in the target list */
+	i = 1;
+	foreach(lc, query->targetList)
+	{
+		TargetEntry *tle = (TargetEntry *) flatten_join_alias_vars(NULL, query, lfirst(lc));
+
+		if (IsA(tle->expr, Var))
+		{
+			Var *var = (Var*) tle->expr;
+			Bitmapset *key_attnos = list_nth(key_attnos_list, var->varno - 1);
+
+			/* check if this attribute is from a base table's primary key */
+			if (bms_is_member(var->varattno - FirstLowInvalidHeapAttributeNumber, key_attnos))
+			{
+				/*
+				 * Remove found key attributes from key_attnos_list, and add this
+				 * to the result list.
+				 */
+				key_attnos = bms_del_member(key_attnos, var->varattno - FirstLowInvalidHeapAttributeNumber);
+				if (bms_is_empty(key_attnos))
+				{
+					key_attnos_list = list_delete_nth_cell(key_attnos_list, var->varno - 1);
+					key_attnos_list = list_insert_nth(key_attnos_list, var->varno - 1, NULL);
+				}
+				keys = bms_add_member(keys, i - FirstLowInvalidHeapAttributeNumber);
+			}
+		}
+		i++;
+	}
+
+	/* Collect RTE indexes of relations appearing in the FROM clause */
+	rels_in_from = get_relids_in_jointree((Node *) query->jointree, false, false);
+
+	/*
+	 * Check if all key attributes of relations in FROM are appearing in the target
+	 * list.  If an attribute remains in key_attnos_list in spite of the table is used
+	 * in FROM clause, the target is missing this key attribute, so we return NULL.
+	 */
+	i = 1;
+	foreach(lc, key_attnos_list)
+	{
+		Bitmapset *bms = (Bitmapset *)lfirst(lc);
+		if (!bms_is_empty(bms) && bms_is_member(i, rels_in_from))
+			return NULL;
+		i++;
+	}
+
+	return keys;
+}
diff --git a/src/backend/commands/matview.c b/src/backend/commands/matview.c
index f7d8007f796..eaf39f80cd3 100644
--- a/src/backend/commands/matview.c
+++ b/src/backend/commands/matview.c
@@ -23,24 +23,36 @@
 #include "catalog/indexing.h"
 #include "catalog/namespace.h"
 #include "catalog/pg_am.h"
+#include "catalog/pg_depend.h"
+#include "catalog/pg_trigger.h"
 #include "catalog/pg_opclass.h"
 #include "commands/matview.h"
 #include "commands/repack.h"
 #include "commands/tablecmds.h"
 #include "commands/tablespace.h"
+#include "commands/createas.h"
 #include "executor/executor.h"
 #include "executor/spi.h"
+#include "executor/tstoreReceiver.h"
 #include "miscadmin.h"
+#include "nodes/makefuncs.h"
+#include "parser/analyze.h"
+#include "parser/parse_clause.h"
+#include "parser/parse_func.h"
+#include "parser/parse_relation.h"
 #include "pgstat.h"
 #include "rewrite/rewriteHandler.h"
+#include "rewrite/rowsecurity.h"
 #include "storage/lmgr.h"
+#include "storage/lwlock.h"
 #include "tcop/tcopprot.h"
 #include "utils/builtins.h"
+#include "utils/fmgroids.h"
 #include "utils/lsyscache.h"
 #include "utils/rel.h"
 #include "utils/snapmgr.h"
 #include "utils/syscache.h"
-
+#include "utils/typcache.h"
 
 typedef struct
 {
@@ -53,6 +65,97 @@ typedef struct
 	BulkInsertState bistate;	/* bulk insert state */
 } DR_transientrel;
 
+#define MV_INIT_QUERYHASHSIZE	16
+
+/*
+ * MV_TriggerHashEntry
+ *
+ * Hash entry for base tables on which IVM trigger is invoked
+ */
+typedef struct MV_TriggerHashEntry
+{
+	Oid	matview_id;			/* OID of the materialized view */
+	int	before_trig_count;	/* count of before triggers invoked */
+	int	after_trig_count;	/* count of after triggers invoked */
+
+	Snapshot	snapshot;	/* Snapshot just before table change */
+
+	List   *tables;		/* List of MV_TriggerTable */
+	bool	has_old;	/* tuples are deleted from any table? */
+	bool	has_new;	/* tuples are inserted into any table? */
+
+	/*
+	 * List of sub-transaction IDs that incrementally updated the view.
+	 * This list is maintained through a transaction, and an ID is removed
+	 * when a sub-transaction is aborted. If any ID is left when the
+	 * transaction is committed, this means the view is incrementally
+	 * updated in this transaction.
+	 */
+	List   *subxids;
+} MV_TriggerHashEntry;
+
+/*
+ * MV_TriggerTable
+ *
+ * IVM related data for tables on which the trigger is invoked.
+ */
+typedef struct MV_TriggerTable
+{
+	Oid		table_id;			/* OID of the modified table */
+	List   *old_tuplestores;	/* tuplestores for deleted tuples */
+	List   *new_tuplestores;	/* tuplestores for inserted tuples */
+
+	List   *rte_indexes;		/* List of RTE index of the modified table */
+	RangeTblEntry *original_rte;	/* the original RTE saved before rewriting query */
+
+	Relation	rel;			/* relation of the modified table */
+	TupleTableSlot *slot;		/* for checking visibility in the pre-state table */
+} MV_TriggerTable;
+
+typedef struct DroppedImmvInfo
+{
+	Oid					immv_oid;
+	SubTransactionId	subxid;
+} DroppedImmvInfo;
+
+static HTAB *mv_trigger_info = NULL;
+static HTAB *dropped_immv = NULL;
+
+static HTAB *LastIvmUpdateHash;
+
+#define LAST_IVM_UPDATE_HASH_SIZE 256
+
+static void IvmShmemRequest(void *arg);
+
+/* hash table entries */
+typedef struct LastIvmUpdateEntry
+{
+	Oid		oid;	/* hash key */
+	FullTransactionId	last_ivm_update;
+} LastIvmUpdateEntry;
+
+const ShmemCallbacks IvmShmemCallbacks = {
+	.request_fn = IvmShmemRequest,
+};
+
+static void
+IvmShmemRequest(void *arg)
+{
+	ShmemRequestHash(.name = "LastIvmUpdate hash",
+					 .nelems = LAST_IVM_UPDATE_HASH_SIZE,
+					 .ptr = &LastIvmUpdateHash,
+					 .hash_info.keysize = sizeof(Oid),
+					 .hash_info.entrysize = sizeof(LastIvmUpdateEntry),
+					 .hash_flags = HASH_ELEM | HASH_BLOBS,
+		);
+}
+
+static bool in_delta_calculation = false;
+
+/* ENR name for materialized view delta */
+#define NEW_DELTA_ENRNAME "new_delta"
+#define OLD_DELTA_ENRNAME "old_delta"
+
 static int	matview_maintenance_depth = 0;
 
 static void transientrel_startup(DestReceiver *self, int operation, TupleDesc typeinfo);
@@ -60,6 +163,8 @@ static bool transientrel_receive(TupleTableSlot *slot, DestReceiver *self);
 static void transientrel_shutdown(DestReceiver *self);
 static void transientrel_destroy(DestReceiver *self);
 static uint64 refresh_matview_datafill(DestReceiver *dest, Query *query,
+									   QueryEnvironment *queryEnv,
+									   TupleDesc *resultTupleDesc,
 									   const char *queryString, bool is_create);
 static void refresh_by_match_merge(Oid matviewOid, Oid tempOid, Oid relowner,
 								   int save_sec_context);
@@ -67,6 +172,41 @@ static void refresh_by_heap_swap(Oid matviewOid, Oid OIDNewHeap, char relpersist
 static bool is_usable_unique_index(Relation indexRel);
 static void OpenMatViewIncrementalMaintenance(void);
 static void CloseMatViewIncrementalMaintenance(void);
+static Query *get_matview_query(Relation matviewRel);
+
+static Query *rewrite_query_for_preupdate_state(Query *query, List *tables,
+								  ParseState *pstate, Oid matviewid);
+static void register_delta_ENRs(ParseState *pstate, Query *query, List *tables);
+static char *make_subquery_targetlist_from_table(MV_TriggerTable *table);
+static char *make_delta_enr_name(const char *prefix, Oid relid, int count);
+static RangeTblEntry *get_prestate_rte(RangeTblEntry *rte, MV_TriggerTable *table,
+				 QueryEnvironment *queryEnv, Oid matviewid);
+static RangeTblEntry *makeDeltaTable(RangeTblEntry *rte, MV_TriggerTable *table,
+									 bool is_new, QueryEnvironment *queryEnv);
+static Query *rewrite_query_for_counting(Query *query, ParseState *pstate);
+
+static void calc_delta(MV_TriggerTable *table, int rte_index, Query *query,
+			DestReceiver *dest_old, DestReceiver *dest_new,
+			TupleDesc *tupdesc_old, TupleDesc *tupdesc_new,
+			QueryEnvironment *queryEnv);
+static Query *rewrite_query_for_postupdate_state(Query *query, MV_TriggerTable *table, int rte_index);
+
+static void apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *new_tuplestores,
+			TupleDesc tupdesc_old, TupleDesc tupdesc_new,
+			Query *query);
+static void apply_old_delta(const char *matviewname, const char *deltaname_old,
+				List *keys);
+static void apply_new_delta(const char *matviewname, const char *deltaname_new,
+				StringInfo target_list);
+static char *get_matching_condition_string(List *keys);
+static void generate_equal(StringInfo querybuf, Oid opttype,
+			   const char *leftop, const char *rightop);
+
+static void mv_InitHashTables(void);
+static void clean_up_IVM_hash_entry(MV_TriggerHashEntry *entry, bool is_abort,
+									SubTransactionId subxid);
+static void setLastUpdateXid(Oid immv_oid, FullTransactionId xid);
+static FullTransactionId getLastUpdateXid(Oid immv_oid);
 
 /*
  * SetMatViewPopulatedState
@@ -108,6 +248,46 @@ SetMatViewPopulatedState(Relation relation, bool newstate)
 	CommandCounterIncrement();
 }
 
+/*
+ * SetMatViewIVMState
+ *		Mark a materialized view as IVM, or not.
+ *
+ * NOTE: caller must be holding an appropriate lock on the relation.
+ */
+void
+SetMatViewIVMState(Relation relation, bool newstate)
+{
+	Relation	pgrel;
+	HeapTuple	tuple;
+
+	Assert(relation->rd_rel->relkind == RELKIND_MATVIEW);
+
+	/*
+	 * Update relation's pg_class entry.  Crucial side-effect: other backends
+	 * (and this one too!) are sent SI message to make them rebuild relcache
+	 * entries.
+	 */
+	pgrel = table_open(RelationRelationId, RowExclusiveLock);
+	tuple = SearchSysCacheCopy1(RELOID,
+								ObjectIdGetDatum(RelationGetRelid(relation)));
+	if (!HeapTupleIsValid(tuple))
+		elog(ERROR, "cache lookup failed for relation %u",
+			 RelationGetRelid(relation));
+
+	((Form_pg_class) GETSTRUCT(tuple))->relisivm = newstate;
+
+	CatalogTupleUpdate(pgrel, &tuple->t_self, tuple);
+
+	heap_freetuple(tuple);
+	table_close(pgrel, RowExclusiveLock);
+
+	/*
+	 * Advance command counter to make the updated pg_class row locally
+	 * visible.
+	 */
+	CommandCounterIncrement();
+}
+
 /*
  * ExecRefreshMatView -- execute a REFRESH MATERIALIZED VIEW command
  *
@@ -166,8 +346,6 @@ RefreshMatViewByOid(Oid matviewOid, bool is_create, bool skipData,
 					QueryCompletion *qc)
 {
 	Relation	matviewRel;
-	RewriteRule *rule;
-	List	   *actions;
 	Query	   *dataQuery;
 	Oid			tableSpace;
 	Oid			relowner;
@@ -178,6 +356,7 @@ RefreshMatViewByOid(Oid matviewOid, bool is_create, bool skipData,
 	int			save_sec_context;
 	int			save_nestlevel;
 	ObjectAddress address;
+	bool oldPopulated;
 
 	matviewRel = table_open(matviewOid, NoLock);
 	relowner = matviewRel->rd_rel->relowner;
@@ -193,6 +372,8 @@ RefreshMatViewByOid(Oid matviewOid, bool is_create, bool skipData,
 	save_nestlevel = NewGUCNestLevel();
 	RestrictSearchPath();
 
+	oldPopulated = RelationIsPopulated(matviewRel);
+
 	/* Make sure it is a materialized view. */
 	if (matviewRel->rd_rel->relkind != RELKIND_MATVIEW)
 		ereport(ERROR,
@@ -213,32 +394,7 @@ RefreshMatViewByOid(Oid matviewOid, bool is_create, bool skipData,
 				 errmsg("%s options %s and %s cannot be used together",
 						"REFRESH", "CONCURRENTLY", "WITH NO DATA")));
 
-	/*
-	 * Check that everything is correct for a refresh. Problems at this point
-	 * are internal errors, so elog is sufficient.
-	 */
-	if (matviewRel->rd_rel->relhasrules == false ||
-		matviewRel->rd_rules->numLocks < 1)
-		elog(ERROR,
-			 "materialized view \"%s\" is missing rewrite information",
-			 RelationGetRelationName(matviewRel));
-
-	if (matviewRel->rd_rules->numLocks > 1)
-		elog(ERROR,
-			 "materialized view \"%s\" has too many rules",
-			 RelationGetRelationName(matviewRel));
-
-	rule = matviewRel->rd_rules->rules[0];
-	if (rule->event != CMD_SELECT || !(rule->isInstead))
-		elog(ERROR,
-			 "the rule for materialized view \"%s\" is not a SELECT INSTEAD OF rule",
-			 RelationGetRelationName(matviewRel));
-
-	actions = rule->actions;
-	if (list_length(actions) != 1)
-		elog(ERROR,
-			 "the rule for materialized view \"%s\" is not a single action",
-			 RelationGetRelationName(matviewRel));
+	dataQuery = get_matview_query(matviewRel);
 
 	/*
 	 * Check that there is a unique index with no WHERE clause on one or more
@@ -275,12 +431,6 @@ RefreshMatViewByOid(Oid matviewOid, bool is_create, bool skipData,
 					 errhint("Create a unique index with no WHERE clause on one or more columns of the materialized view.")));
 	}
 
-	/*
-	 * The stored query was rewritten at the time of the MV definition, but
-	 * has not been scribbled on by the planner.
-	 */
-	dataQuery = linitial_node(Query, actions);
-
 	/*
 	 * Check for active uses of the relation in the current transaction, such
 	 * as open scans.
@@ -310,6 +460,90 @@ RefreshMatViewByOid(Oid matviewOid, bool is_create, bool skipData,
 		relpersistence = matviewRel->rd_rel->relpersistence;
 	}
 
+	/* delete IMMV triggers. */
+	if (RelationIsIVM(matviewRel) && skipData)
+	{
+		Relation	tgRel;
+		Relation	depRel;
+		ScanKeyData key;
+		SysScanDesc scan;
+		HeapTuple	tup;
+		ObjectAddresses *immv_triggers;
+
+		immv_triggers = new_object_addresses();
+
+		tgRel = table_open(TriggerRelationId, RowExclusiveLock);
+		depRel = table_open(DependRelationId, RowExclusiveLock);
+
+		/* search triggers that depends on IMMV. */
+		ScanKeyInit(&key,
+					Anum_pg_depend_refobjid,
+					BTEqualStrategyNumber, F_OIDEQ,
+					ObjectIdGetDatum(matviewOid));
+		scan = systable_beginscan(depRel, DependReferenceIndexId, true,
+								  NULL, 1, &key);
+		while ((tup = systable_getnext(scan)) != NULL)
+		{
+			ObjectAddress obj;
+			Form_pg_depend foundDep = (Form_pg_depend) GETSTRUCT(tup);
+
+			if (foundDep->classid == TriggerRelationId)
+			{
+				HeapTuple	tgtup;
+				ScanKeyData tgkey[1];
+				SysScanDesc tgscan;
+				Form_pg_trigger tgform;
+
+				/* Find the trigger name. */
+				ScanKeyInit(&tgkey[0],
+							Anum_pg_trigger_oid,
+							BTEqualStrategyNumber, F_OIDEQ,
+							ObjectIdGetDatum(foundDep->objid));
+
+				tgscan = systable_beginscan(tgRel, TriggerOidIndexId, true,
+											NULL, 1, tgkey);
+				tgtup = systable_getnext(tgscan);
+				if (!HeapTupleIsValid(tgtup))
+					elog(ERROR, "could not find tuple for immv trigger %u", foundDep->objid);
+
+				tgform = (Form_pg_trigger) GETSTRUCT(tgtup);
+
+				/* If trigger is created by IMMV, delete it. */
+				if (strncmp(NameStr(tgform->tgname), "IVM_trigger_", 12) == 0)
+				{
+					obj.classId = foundDep->classid;
+					obj.objectId = foundDep->objid;
+					obj.objectSubId = foundDep->refobjsubid;
+					add_exact_object_address(&obj, immv_triggers);
+				}
+				systable_endscan(tgscan);
+			}
+		}
+		systable_endscan(scan);
+
+		performMultipleDeletions(immv_triggers, DROP_RESTRICT, PERFORM_DELETION_INTERNAL);
+
+		table_close(depRel, RowExclusiveLock);
+		table_close(tgRel, RowExclusiveLock);
+		free_object_addresses(immv_triggers);
+	}
+
+	/*
+	 * Create triggers on incremental maintainable materialized view
+	 * This argument should use 'dataQuery'. This needs to use a rewritten query,
+	 * because a sublink in jointree is not supported by this function.
+	 *
+	 * This is performed before generating data because we have to wait
+	 * concurrent transactions modifying a base table and then take a snapshot
+	 * to see changes by these transactions to make sure a consistent view
+	 * is created.
+	 */
+	if (RelationIsIVM(matviewRel) && !skipData && !oldPopulated)
+	{
+		CreateIvmTriggersOnBaseTables(dataQuery, matviewOid);
+		CreateIndexOnIMMV(dataQuery, matviewRel);
+	}
+
 	/*
 	 * Create the transient table that will receive the regenerated data. Lock
 	 * it against access by any other process until commit (by which time it
@@ -326,8 +560,43 @@ RefreshMatViewByOid(Oid matviewOid, bool is_create, bool skipData,
 		DestReceiver *dest;
 
 		dest = CreateTransientRelDestReceiver(OIDNewHeap);
-		processed = refresh_matview_datafill(dest, dataQuery, queryString,
-											 is_create);
+
+		if (RelationIsIVM(matviewRel))
+		{
+			/*
+			 * In READ COMMITTED, get and push the latest snapshot again to see the
+			 * results of concurrent transactions committed after the current
+			 * transaction started.
+			 */
+			if (!IsolationUsesXactSnapshot())
+				PushActiveSnapshot(GetTransactionSnapshot());
+
+			/*
+			 * If a concurrent transaction updated the view incrementally and was
+			 * committed before we acquired the lock, the results of refresh_immv could
+			 * be inconsistent. Therefore, we have to check the transaction ID of the
+			 * most recent update of the view, and if this was in progress at the
+			 * transaction start, raise an error to prevent anomalies.
+			 */
+			if (!is_create)
+			{
+				FullTransactionId xid;
+
+				xid = getLastUpdateXid(matviewOid);
+				if (XidInMVCCSnapshot(XidFromFullTransactionId(xid), GetActiveSnapshot()))
+					ereport(ERROR,
+							(errcode(ERRCODE_T_R_SERIALIZATION_FAILURE),
+							 errmsg("the materialized view is incrementally updated in concurrent transaction"),
+							 errhint("The transaction might succeed if retried.")));
+			}
+		}
+
+		processed = refresh_matview_datafill(dest, dataQuery, NULL, NULL,
+											 queryString, is_create);
+
+		/* Pop the original snapshot. */
+		if (RelationIsIVM(matviewRel) && !IsolationUsesXactSnapshot())
+			PopActiveSnapshot();
 	}
 
 	/* Make the matview match the newly generated data. */
@@ -402,6 +671,8 @@ RefreshMatViewByOid(Oid matviewOid, bool is_create, bool skipData,
  */
 static uint64
 refresh_matview_datafill(DestReceiver *dest, Query *query,
+						 QueryEnvironment *queryEnv,
+						 TupleDesc *resultTupleDesc,
 						 const char *queryString, bool is_create)
 {
 	List	   *rewritten;
@@ -439,7 +710,7 @@ refresh_matview_datafill(DestReceiver *dest, Query *query,
 	/* Create a QueryDesc, redirecting output to our tuple receiver */
 	queryDesc = CreateQueryDesc(plan, queryString,
 								GetActiveSnapshot(), InvalidSnapshot,
-								dest, NULL, NULL, 0);
+								dest, NULL, queryEnv ? queryEnv: NULL, 0);
 
 	/* call ExecutorStart to prepare the plan for execution */
 	ExecutorStart(queryDesc, 0);
@@ -449,6 +720,9 @@ refresh_matview_datafill(DestReceiver *dest, Query *query,
 
 	processed = queryDesc->estate->es_processed;
 
+	if (resultTupleDesc)
+		*resultTupleDesc = CreateTupleDescCopy(queryDesc->tupDesc);
+
 	/* and clean up */
 	ExecutorFinish(queryDesc);
 	ExecutorEnd(queryDesc);
@@ -967,3 +1241,1488 @@ CloseMatViewIncrementalMaintenance(void)
 	matview_maintenance_depth--;
 	Assert(matview_maintenance_depth >= 0);
 }
+
+/*
+ * get_matview_query - get the Query from a matview's _RETURN rule.
+ */
+static Query *
+get_matview_query(Relation matviewRel)
+{
+	RewriteRule *rule;
+	List * actions;
+
+	/*
+	 * Check that everything is correct for a refresh. Problems at this point
+	 * are internal errors, so elog is sufficient.
+	 */
+	if (matviewRel->rd_rel->relhasrules == false ||
+		matviewRel->rd_rules->numLocks < 1)
+		elog(ERROR,
+			 "materialized view \"%s\" is missing rewrite information",
+			 RelationGetRelationName(matviewRel));
+
+	if (matviewRel->rd_rules->numLocks > 1)
+		elog(ERROR,
+			 "materialized view \"%s\" has too many rules",
+			 RelationGetRelationName(matviewRel));
+
+	rule = matviewRel->rd_rules->rules[0];
+	if (rule->event != CMD_SELECT || !(rule->isInstead))
+		elog(ERROR,
+			 "the rule for materialized view \"%s\" is not a SELECT INSTEAD OF rule",
+			 RelationGetRelationName(matviewRel));
+
+	actions = rule->actions;
+	if (list_length(actions) != 1)
+		elog(ERROR,
+			 "the rule for materialized view \"%s\" is not a single action",
+			 RelationGetRelationName(matviewRel));
+
+	/*
+	 * The stored query was rewritten at the time of the MV definition, but
+	 * has not been scribbled on by the planner.
+	 */
+	return linitial_node(Query, actions);
+}
+
+
+/* ----------------------------------------------------
+ *		Incremental View Maintenance routines
+ * ---------------------------------------------------
+ */
+
+/*
+ * IVM_immediate_before
+ *
+ * IVM trigger function invoked before base table is modified. If this is
+ * invoked firstly in the same statement, we save the transaction id and the
+ * command id at that time.
+ */
+Datum
+IVM_immediate_before(PG_FUNCTION_ARGS)
+{
+	TriggerData *trigdata = (TriggerData *) fcinfo->context;
+	char	   *matviewOid_text = trigdata->tg_trigger->tgargs[0];
+	char	   *ex_lock_text = trigdata->tg_trigger->tgargs[1];
+	Oid			matviewOid;
+	MV_TriggerHashEntry *entry;
+	bool	found;
+	bool	ex_lock;
+
+	matviewOid = DatumGetObjectId(DirectFunctionCall1(oidin, CStringGetDatum(matviewOid_text)));
+	ex_lock = DatumGetBool(DirectFunctionCall1(boolin, CStringGetDatum(ex_lock_text)));
+
+	/* If the view has more than one tables, we have to use an exclusive lock. */
+	if (ex_lock)
+	{
+		FullTransactionId xid;
+
+		/*
+		 * Wait for concurrent transactions which update this materialized view at
+		 * READ COMMITED. This is needed to see changes committed in other
+		 * transactions. No wait and raise an error at REPEATABLE READ or
+		 * SERIALIZABLE to prevent update anomalies of matviews.
+		 * XXX: dead-lock is possible here.
+		 */
+		if (!IsolationUsesXactSnapshot())
+			LockRelationOid(matviewOid, ExclusiveLock);
+		else if (!ConditionalLockRelationOid(matviewOid, ExclusiveLock))
+		{
+			/* try to throw error by name; relation could be deleted... */
+			char	   *relname = get_rel_name(matviewOid);
+
+			if (!relname)
+				ereport(ERROR,
+						(errcode(ERRCODE_LOCK_NOT_AVAILABLE),
+						errmsg("could not obtain lock on materialized view during incremental maintenance")));
+
+			ereport(ERROR,
+					(errcode(ERRCODE_LOCK_NOT_AVAILABLE),
+					errmsg("could not obtain lock on materialized view \"%s\" during incremental maintenance",
+							relname)));
+		}
+
+		/*
+		 * Even if we can acquire an lock, a concurrent transaction could have
+		 * updated the view incrementally and been committed before we acquired
+		 * the lock. Therefore, we have to check the transaction ID of the most
+		 * recent update of the view, and if this was in progress at the
+		 * transaction start, raise an error to prevent anomalies.
+		 */
+		xid = getLastUpdateXid(matviewOid);
+		if (XidInMVCCSnapshot(XidFromFullTransactionId(xid), GetTransactionSnapshot()))
+			ereport(ERROR,
+					(errcode(ERRCODE_T_R_SERIALIZATION_FAILURE),
+					 errmsg("the materialized view is incrementally updated in concurrent transaction"),
+					 errhint("The transaction might succeed if retried.")));
+	}
+	else
+		LockRelationOid(matviewOid, RowExclusiveLock);
+
+	/*
+	 * On the first call initialize the hashtable
+	 */
+	if (!mv_trigger_info)
+		mv_InitHashTables();
+
+	entry = (MV_TriggerHashEntry *) hash_search(mv_trigger_info,
+											  (void *) &matviewOid,
+											  HASH_ENTER, &found);
+
+	/* On the first BEFORE to update the view, initialize trigger data */
+	if (!found || entry->snapshot == InvalidSnapshot)
+	{
+		Snapshot snapshot;
+
+		/*
+		 * Get a snapshot just before the table was modified for checking
+		 * tuple visibility in the pre-update state of the table.
+		 *
+		 * In READ COMMITTED, use the latest snapshot again to see the
+		 * results of concurrent transactions committed after the current
+		 * transaction started.
+		 */
+		if (IsolationUsesXactSnapshot())
+			snapshot = GetActiveSnapshot();
+		else
+			snapshot = GetTransactionSnapshot();
+
+		entry->matview_id = matviewOid;
+		entry->before_trig_count = 0;
+		entry->after_trig_count = 0;
+		entry->snapshot = RegisterSnapshot(snapshot);
+		entry->tables = NIL;
+		entry->has_old = false;
+		entry->has_new = false;
+
+		/*
+		 * If this is the first table modifying query in the transaction,
+		 * initialize the list of subxids.
+		 */
+		if (!found)
+			entry->subxids = NIL;
+	}
+
+	entry->before_trig_count++;
+
+	return PointerGetDatum(NULL);
+}
+
+/*
+ * IVM_immediate_maintenance
+ *
+ * IVM trigger function invoked after base table is modified.
+ * For each table, tuplestores of transition tables are collected.
+ * and after the last modification
+ */
+Datum
+IVM_immediate_maintenance(PG_FUNCTION_ARGS)
+{
+	TriggerData *trigdata = (TriggerData *) fcinfo->context;
+	Relation	rel;
+	Oid			relid;
+	Oid			matviewOid;
+	Query	   *query;
+	Query	   *rewritten = NULL;
+	char	   *matviewOid_text = trigdata->tg_trigger->tgargs[0];
+	Relation	matviewRel;
+	int old_depth = matview_maintenance_depth;
+	SubTransactionId subxid;
+
+	Oid			relowner;
+	Tuplestorestate *old_tuplestore = NULL;
+	Tuplestorestate *new_tuplestore = NULL;
+	DestReceiver *dest_new = NULL, *dest_old = NULL;
+	Oid			save_userid;
+	int			save_sec_context;
+	int			save_nestlevel;
+
+	MV_TriggerHashEntry *entry;
+	MV_TriggerTable		*table;
+	bool	found;
+
+	ParseState		 *pstate;
+	QueryEnvironment *queryEnv = create_queryEnv();
+	MemoryContext	oldcxt;
+	ListCell   *lc;
+	int			i;
+
+
+	/* Create a ParseState for rewriting the view definition query */
+	pstate = make_parsestate(NULL);
+	pstate->p_queryEnv = queryEnv;
+	pstate->p_expr_kind = EXPR_KIND_SELECT_TARGET;
+
+	rel = trigdata->tg_relation;
+	relid = rel->rd_id;
+
+	matviewOid = DatumGetObjectId(DirectFunctionCall1(oidin, CStringGetDatum(matviewOid_text)));
+
+	/*
+	 * On the first call initialize the hashtable
+	 */
+	if (!mv_trigger_info)
+		mv_InitHashTables();
+
+	/* get the entry for this materialized view */
+	entry = (MV_TriggerHashEntry *) hash_search(mv_trigger_info,
+											  (void *) &matviewOid,
+											  HASH_FIND, &found);
+	Assert (found && entry != NULL);
+	entry->after_trig_count++;
+
+	/* search the entry for the modified table and create new entry if not found */
+	found = false;
+	foreach(lc, entry->tables)
+	{
+		table = (MV_TriggerTable *) lfirst(lc);
+		if (table->table_id == relid)
+		{
+			found = true;
+			break;
+		}
+	}
+	if (!found)
+	{
+		oldcxt = MemoryContextSwitchTo(TopTransactionContext);
+
+		table = (MV_TriggerTable *) palloc0(sizeof(MV_TriggerTable));
+		table->table_id = relid;
+		table->old_tuplestores = NIL;
+		table->new_tuplestores = NIL;
+		table->rte_indexes = NIL;
+		table->slot = MakeSingleTupleTableSlot(RelationGetDescr(rel), table_slot_callbacks(rel));
+		/* We assume we have at least RowExclusiveLock on modified tables. */
+		table->rel = table_open(RelationGetRelid(rel), NoLock);
+		entry->tables = lappend(entry->tables, table);
+
+		MemoryContextSwitchTo(oldcxt);
+	}
+
+	/* Save the transition tables and make a request to not free immediately */
+	if (trigdata->tg_oldtable)
+	{
+		oldcxt = MemoryContextSwitchTo(TopTransactionContext);
+		table->old_tuplestores = lappend(table->old_tuplestores, trigdata->tg_oldtable);
+		entry->has_old = true;
+		MemoryContextSwitchTo(oldcxt);
+	}
+	if (trigdata->tg_newtable)
+	{
+		oldcxt = MemoryContextSwitchTo(TopTransactionContext);
+		table->new_tuplestores = lappend(table->new_tuplestores, trigdata->tg_newtable);
+		entry->has_new = true;
+		MemoryContextSwitchTo(oldcxt);
+	}
+	if (entry->has_new || entry->has_old)
+	{
+		CmdType cmd;
+
+		if (TRIGGER_FIRED_BY_INSERT(trigdata->tg_event))
+			cmd = CMD_INSERT;
+		else if (TRIGGER_FIRED_BY_DELETE(trigdata->tg_event))
+			cmd = CMD_DELETE;
+		else if (TRIGGER_FIRED_BY_UPDATE(trigdata->tg_event))
+			cmd = CMD_UPDATE;
+		else
+			elog(ERROR,"unsupported trigger type");
+
+		/* Prolong lifespan of transition tables to the end of the last AFTER trigger */
+		SetTransitionTablePreserved(relid, cmd);
+	}
+
+
+	/* If this is not the last AFTER trigger call, immediately exit. */
+	Assert (entry->before_trig_count >= entry->after_trig_count);
+	if (entry->before_trig_count != entry->after_trig_count)
+		return PointerGetDatum(NULL);
+
+	/*
+	 * If this is the last AFTER trigger call, continue and update the view.
+	 */
+
+	/* record the subxid that updated the view incrementally */
+	subxid = GetCurrentSubTransactionId();
+	if (!list_member_xid(entry->subxids, subxid))
+	{
+		oldcxt = MemoryContextSwitchTo(TopTransactionContext);
+		entry->subxids = lappend_xid(entry->subxids, subxid);
+		MemoryContextSwitchTo(oldcxt);
+	}
+
+	/*
+	 * Advance command counter to make the updated base table rows locally
+	 * visible.
+	 */
+	CommandCounterIncrement();
+
+	matviewRel = table_open(matviewOid, NoLock);
+
+	/* Make sure it is a materialized view. */
+	Assert(matviewRel->rd_rel->relkind == RELKIND_MATVIEW);
+
+	/*
+	 * In READ COMMITTED, get and push the latest snapshot again to see the
+	 * results of concurrent transactions committed after the current
+	 * transaction started.
+	 */
+	if (!IsolationUsesXactSnapshot())
+		PushActiveSnapshot(GetTransactionSnapshot());
+
+	/*
+	 * Check for active uses of the relation in the current transaction, such
+	 * as open scans.
+	 *
+	 * NB: We count on this to protect us against problems with refreshing the
+	 * data using TABLE_INSERT_FROZEN.
+	 */
+	CheckTableNotInUse(matviewRel, "refresh a materialized view incrementally");
+
+	/*
+	 * Switch to the owner's userid, so that any functions are run as that
+	 * user.  Also arrange to make GUC variable changes local to this command.
+	 * We will switch modes when we are about to execute user code.
+	 */
+	relowner = matviewRel->rd_rel->relowner;
+	GetUserIdAndSecContext(&save_userid, &save_sec_context);
+	SetUserIdAndSecContext(relowner,
+						   save_sec_context | SECURITY_RESTRICTED_OPERATION);
+	save_nestlevel = NewGUCNestLevel();
+
+	/* get view query*/
+	query = get_matview_query(matviewRel);
+
+	/*
+	 * When a base table is truncated, the view content will be empty if the
+	 * view definition query does not contain an aggregate without a GROUP clause.
+	 * Therefore, such views can be truncated.
+	 */
+	if (TRIGGER_FIRED_BY_TRUNCATE(trigdata->tg_event))
+	{
+		ExecuteTruncateGuts(list_make1(matviewRel), list_make1_oid(matviewOid),
+							NIL, DROP_RESTRICT, false, false);
+
+		/* Clean up hash entry and delete tuplestores */
+		clean_up_IVM_hash_entry(entry, false, InvalidSubTransactionId);
+
+		/* Pop the original snapshot. */
+		if (!IsolationUsesXactSnapshot())
+			PopActiveSnapshot();
+
+		table_close(matviewRel, NoLock);
+
+		/* Roll back any GUC changes */
+		AtEOXact_GUC(false, save_nestlevel);
+
+		/* Restore userid and security context */
+		SetUserIdAndSecContext(save_userid, save_sec_context);
+
+		return PointerGetDatum(NULL);
+	}
+
+	/*
+	 * rewrite query for calculating deltas
+	 */
+
+	rewritten = copyObject(query);
+
+	/* Replace resnames in a target list with materialized view's attnames */
+	i = 0;
+	foreach (lc, rewritten->targetList)
+	{
+		TargetEntry *tle = (TargetEntry *) lfirst(lc);
+		Form_pg_attribute attr = TupleDescAttr(matviewRel->rd_att, i);
+		char *resname = NameStr(attr->attname);
+
+		tle->resname = pstrdup(resname);
+		i++;
+	}
+
+	/* Set all tables in the query to pre-update state */
+	rewritten = rewrite_query_for_preupdate_state(rewritten, entry->tables,
+												  pstate, matviewOid);
+	/* Rewrite for counting duplicated tuples */
+	rewritten = rewrite_query_for_counting(rewritten, pstate);
+
+	/* Create tuplestores to store view deltas */
+	if (entry->has_old)
+	{
+		oldcxt = MemoryContextSwitchTo(TopTransactionContext);
+
+		old_tuplestore = tuplestore_begin_heap(false, false, work_mem);
+		dest_old = CreateDestReceiver(DestTuplestore);
+		SetTuplestoreDestReceiverParams(dest_old,
+									old_tuplestore,
+									TopTransactionContext,
+									false,
+									NULL,
+									NULL);
+
+		MemoryContextSwitchTo(oldcxt);
+	}
+	if (entry->has_new)
+	{
+		oldcxt = MemoryContextSwitchTo(TopTransactionContext);
+
+		new_tuplestore = tuplestore_begin_heap(false, false, work_mem);
+		dest_new = CreateDestReceiver(DestTuplestore);
+		SetTuplestoreDestReceiverParams(dest_new,
+									new_tuplestore,
+									TopTransactionContext,
+									false,
+									NULL,
+									NULL);
+		MemoryContextSwitchTo(oldcxt);
+	}
+
+	/* for all modified tables */
+	foreach(lc, entry->tables)
+	{
+		ListCell *lc2;
+
+		table = (MV_TriggerTable *) lfirst(lc);
+
+		/* loop for self-join */
+		foreach(lc2, table->rte_indexes)
+		{
+			int	rte_index = lfirst_int(lc2);
+			TupleDesc		tupdesc_old;
+			TupleDesc		tupdesc_new;
+
+			/* calculate delta tables */
+			calc_delta(table, rte_index, rewritten, dest_old, dest_new,
+					   &tupdesc_old, &tupdesc_new, queryEnv);
+
+			/* Set the table in the query to post-update state */
+			rewritten = rewrite_query_for_postupdate_state(rewritten, table, rte_index);
+
+			PG_TRY();
+			{
+				/* apply the delta tables to the materialized view */
+				apply_delta(matviewOid, old_tuplestore, new_tuplestore,
+							tupdesc_old, tupdesc_new, query);
+			}
+			PG_CATCH();
+			{
+				matview_maintenance_depth = old_depth;
+				PG_RE_THROW();
+			}
+			PG_END_TRY();
+
+			/* clear view delta tuplestores */
+			if (old_tuplestore)
+				tuplestore_clear(old_tuplestore);
+			if (new_tuplestore)
+				tuplestore_clear(new_tuplestore);
+		}
+	}
+
+	/* Clean up hash entry and delete tuplestores */
+	clean_up_IVM_hash_entry(entry, false, InvalidSubTransactionId);
+	if (old_tuplestore)
+	{
+		dest_old->rDestroy(dest_old);
+		tuplestore_end(old_tuplestore);
+	}
+	if (new_tuplestore)
+	{
+		dest_new->rDestroy(dest_new);
+		tuplestore_end(new_tuplestore);
+	}
+
+	/* Pop the original snapshot. */
+	if (!IsolationUsesXactSnapshot())
+		PopActiveSnapshot();
+
+	table_close(matviewRel, NoLock);
+
+	/* Roll back any GUC changes */
+	AtEOXact_GUC(false, save_nestlevel);
+
+	/* Restore userid and security context */
+	SetUserIdAndSecContext(save_userid, save_sec_context);
+
+	return PointerGetDatum(NULL);
+}
+
+/*
+ * rewrite_query_for_preupdate_state
+ *
+ * Rewrite the query so that base tables' RTEs will represent "pre-update"
+ * state of tables. This is necessary to calculate view delta after multiple
+ * tables are modified.
+ */
+static Query*
+rewrite_query_for_preupdate_state(Query *query, List *tables,
+								  ParseState *pstate, Oid matviewid)
+{
+	ListCell *lc;
+	int num_rte = list_length(query->rtable);
+	int i;
+
+
+	/* register delta ENRs */
+	register_delta_ENRs(pstate, query, tables);
+
+	/* XXX: Is necessary? Is this right timing? */
+	AcquireRewriteLocks(query, true, false);
+
+	i = 1;
+	foreach(lc, query->rtable)
+	{
+		RangeTblEntry *r = (RangeTblEntry*) lfirst(lc);
+
+		ListCell *lc2;
+		foreach(lc2, tables)
+		{
+			MV_TriggerTable *table = (MV_TriggerTable *) lfirst(lc2);
+			/*
+			 * if the modified table is found then replace the original RTE with
+			 * "pre-state" RTE and append its index to the list.
+			 */
+			if (r->relid == table->table_id)
+			{
+				List *securityQuals;
+				List *withCheckOptions;
+				bool  hasRowSecurity;
+				bool  hasSubLinks;
+
+				RangeTblEntry *rte_pre = get_prestate_rte(r, table, pstate->p_queryEnv, matviewid);
+
+				/*
+				 * Set a row security poslicies of the modified table to the subquery RTE which
+				 * represents the pre-update state of the table.
+				 */
+				get_row_security_policies(query, table->original_rte, i,
+										  &securityQuals, &withCheckOptions,
+										  &hasRowSecurity, &hasSubLinks);
+
+				if (hasRowSecurity)
+				{
+					query->hasRowSecurity = true;
+					rte_pre->security_barrier = true;
+				}
+				if (hasSubLinks)
+					query->hasSubLinks = true;
+
+				rte_pre->securityQuals = securityQuals;
+				lfirst(lc) = rte_pre;
+
+				table->rte_indexes = lappend_int(table->rte_indexes, i);
+				break;
+			}
+		}
+
+		/* finish the loop if we processed all RTE included in the original query */
+		if (i++ >= num_rte)
+			break;
+	}
+
+	return query;
+}
+
+/*
+ * register_delta_ENRs
+ *
+ * For all modified tables, make ENRs for their transition tables
+ * and register them to the queryEnv. ENR's RTEs are also appended
+ * into the list in query tree.
+ */
+static void
+register_delta_ENRs(ParseState *pstate, Query *query, List *tables)
+{
+	QueryEnvironment *queryEnv = pstate->p_queryEnv;
+	ListCell *lc;
+	RangeTblEntry	*rte;
+
+	foreach(lc, tables)
+	{
+		MV_TriggerTable *table = (MV_TriggerTable *) lfirst(lc);
+		ListCell *lc2;
+		int count;
+
+		count = 0;
+		foreach(lc2, table->old_tuplestores)
+		{
+			Tuplestorestate *oldtable = (Tuplestorestate *) lfirst(lc2);
+			EphemeralNamedRelation enr =
+				palloc(sizeof(EphemeralNamedRelationData));
+			ParseNamespaceItem *nsitem;
+
+			enr->md.name = make_delta_enr_name("old", table->table_id, count);
+			enr->md.reliddesc = table->table_id;
+			enr->md.tupdesc = NULL;
+			enr->md.enrtype = ENR_NAMED_TUPLESTORE;
+			enr->md.enrtuples = tuplestore_tuple_count(oldtable);
+			enr->reldata = oldtable;
+			register_ENR(queryEnv, enr);
+
+			nsitem = addRangeTableEntryForENR(pstate, makeRangeVar(NULL, enr->md.name, -1), true);
+			rte = nsitem->p_rte;
+
+			query->rtable = lappend(query->rtable, rte);
+
+			count++;
+		}
+
+		count = 0;
+		foreach(lc2, table->new_tuplestores)
+		{
+			Tuplestorestate *newtable = (Tuplestorestate *) lfirst(lc2);
+			EphemeralNamedRelation enr =
+				palloc(sizeof(EphemeralNamedRelationData));
+			ParseNamespaceItem *nsitem;
+
+			enr->md.name = make_delta_enr_name("new", table->table_id, count);
+			enr->md.reliddesc = table->table_id;
+			enr->md.tupdesc = NULL;
+			enr->md.enrtype = ENR_NAMED_TUPLESTORE;
+			enr->md.enrtuples = tuplestore_tuple_count(newtable);
+			enr->reldata = newtable;
+			register_ENR(queryEnv, enr);
+
+			nsitem = addRangeTableEntryForENR(pstate, makeRangeVar(NULL, enr->md.name, -1), true);
+			rte = nsitem->p_rte;
+
+			query->rtable = lappend(query->rtable, rte);
+
+			count++;
+		}
+	}
+}
+
+#define DatumGetItemPointer(X)	 ((ItemPointer) DatumGetPointer(X))
+#define PG_GETARG_ITEMPOINTER(n) DatumGetItemPointer(PG_GETARG_DATUM(n))
+
+/*
+ * ivm_visible_in_prestate
+ *
+ * Check visibility of a tuple specified by the tableoid and item pointer
+ * using the snapshot taken just before the table was modified.
+ */
+Datum
+ivm_visible_in_prestate(PG_FUNCTION_ARGS)
+{
+	Oid			tableoid = PG_GETARG_OID(0);
+	ItemPointer itemPtr = PG_GETARG_ITEMPOINTER(1);
+	Oid			matviewOid = PG_GETARG_OID(2);
+	MV_TriggerHashEntry *entry;
+	MV_TriggerTable		*table = NULL;
+	ListCell   *lc;
+	bool	found;
+	bool	result;
+
+	if (!in_delta_calculation)
+		ereport(ERROR,
+				(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+				 errmsg("ivm_visible_in_prestate can be called only in delta calculation")));
+
+	entry = (MV_TriggerHashEntry *) hash_search(mv_trigger_info,
+											  (void *) &matviewOid,
+											  HASH_FIND, &found);
+	Assert (found && entry != NULL);
+
+	foreach(lc, entry->tables)
+	{
+		table = (MV_TriggerTable *) lfirst(lc);
+		if (table->table_id == tableoid)
+			break;
+	}
+
+	Assert (table != NULL);
+
+	result = table_tuple_fetch_row_version(table->rel, itemPtr, entry->snapshot, table->slot);
+
+	PG_RETURN_BOOL(result);
+}
+
+/*
+ * get_prestate_rte
+ *
+ * Rewrite RTE of the modified table to a subquery which represents
+ * "pre-state" table. The original RTE is saved in table->rte_original.
+ */
+static RangeTblEntry*
+get_prestate_rte(RangeTblEntry *rte, MV_TriggerTable *table,
+				 QueryEnvironment *queryEnv, Oid matviewid)
+{
+	StringInfoData str;
+	RawStmt *raw;
+	Query *subquery;
+	ParseState *pstate;
+	char *relname;
+	static char *subquery_tl;
+	int i;
+
+	pstate = make_parsestate(NULL);
+	pstate->p_queryEnv = queryEnv;
+	pstate->p_expr_kind = EXPR_KIND_SELECT_TARGET;
+
+	relname = quote_qualified_identifier(
+					get_namespace_name(RelationGetNamespace(table->rel)),
+									   RelationGetRelationName(table->rel));
+
+	subquery_tl = make_subquery_targetlist_from_table(table);
+
+	/*
+	 * Filtering inserted row using the snapshot taken before the table
+	 * is modified. ctid is required for maintaining outer join views.
+	 */
+	initStringInfo(&str);
+	appendStringInfo(&str,
+		"SELECT %s FROM %s t"
+		" WHERE pg_catalog.ivm_visible_in_prestate(t.tableoid, t.ctid ,%d::pg_catalog.oid)",
+			subquery_tl, relname, matviewid);
+
+	/*
+	 * Re-add rows deleted from the old transition tables, excluding those
+	 * also present in the new transition tables.
+	 */
+	if (list_length(table->old_tuplestores) > 0)
+	{
+		appendStringInfo(&str," UNION ALL SELECT %s  FROM (",
+			subquery_tl);
+
+		for (i = 0; i < list_length(table->old_tuplestores); i++)
+		{
+			if (i != 0)
+				appendStringInfo(&str, " UNION ALL ");
+			appendStringInfo(&str," TABLE %s",
+				make_delta_enr_name("old", table->table_id, i));
+		}
+		for (i = 0; i < list_length(table->new_tuplestores); i++)
+		{
+			appendStringInfo(&str, " EXCEPT ALL ");
+			appendStringInfo(&str," TABLE %s",
+				make_delta_enr_name("new", table->table_id, i));
+		}
+		appendStringInfo(&str,")");
+	}
+
+	/* Get a subquery representing pre-state of the table */
+	raw = (RawStmt*)linitial(raw_parser(str.data, RAW_PARSE_DEFAULT));
+	subquery = transformStmt(pstate, raw->stmt);
+
+	/* save the original RTE */
+	table->original_rte = copyObject(rte);
+
+	rte->rtekind = RTE_SUBQUERY;
+	rte->subquery = subquery;
+	rte->security_barrier = false;
+
+	/* Clear fields that should not be set in a subquery RTE */
+	rte->relid = InvalidOid;
+	rte->relkind = 0;
+	rte->rellockmode = 0;
+	rte->tablesample = NULL;
+	rte->perminfoindex = 0;         /* no permission checking for this RTE */
+	rte->inh = false;			/* must not be set for a subquery */
+
+	return rte;
+}
+
+/*
+ * make_subquery_targetlist_from_table
+ *
+ * Make a targetlist string of a subquery representing a delta table or a
+ * pre-update state table. This subquery substitutes a modified table RTE
+ * in the view definition query during view maintenance. In the targetlist,
+ * column names appear in order of the table definition. However, for
+ * attribute numbers of vars in the query tree to reference columns of the
+ * subquery  correctly even though the table has a dropped column, put "null"
+ * as a dummy value at the position of a dropped column.
+ *
+ * We would also able to walk the query tree to rewrite varattnos, but
+ * crafting targetlist is more simple and reasonable.
+ */
+static char*
+make_subquery_targetlist_from_table(MV_TriggerTable *table)
+{
+	StringInfoData str;
+	TupleDesc	tupdesc;
+	int			i;
+
+	tupdesc = RelationGetDescr(table->rel);
+	initStringInfo(&str);
+	for (i = 0; i < tupdesc->natts; i++)
+	{
+		Form_pg_attribute attr = TupleDescAttr(tupdesc, i);
+
+		if (i > 0)
+			appendStringInfo(&str, ", ");
+
+		if (attr->attisdropped)
+			appendStringInfo(&str, "null");
+		else
+			appendStringInfo(&str, "%s", quote_identifier(NameStr(attr->attname)));
+	}
+
+	return str.data;
+}
+
+/*
+ * make_delta_enr_name
+ *
+ * Make a name for ENR of a transition table from the base table's oid.
+ * prefix will be "new" or "old" depending on its transition table kind..
+ */
+static char*
+make_delta_enr_name(const char *prefix, Oid relid, int count)
+{
+	char buf[NAMEDATALEN];
+	char *name;
+
+	snprintf(buf, NAMEDATALEN, "__ivm_%s_%u_%u", prefix, relid, count);
+	name = pstrdup(buf);
+
+	return name;
+}
+
+/*
+ * makeDeltaTable
+ *
+ * Make a RTE representing a delta of the specified table.
+ */
+static RangeTblEntry*
+makeDeltaTable(RangeTblEntry *rte, MV_TriggerTable *table,
+		   bool is_new, QueryEnvironment *queryEnv)
+{
+	StringInfoData str;
+	ParseState	*pstate;
+	RawStmt *raw;
+	Query *sub;
+	int		i;
+
+	const char *prefix_union = is_new ? "new" : "old";
+	const char *prefix_except = is_new ? "old" : "new";
+	int num_union = is_new ? list_length(table->new_tuplestores) : list_length(table->old_tuplestores);
+	int num_except = is_new ? list_length(table->old_tuplestores) : list_length(table->new_tuplestores);
+
+	/* the previous RTE must be a subquery which represents "pre-state" table */
+	Assert(rte->rtekind == RTE_SUBQUERY);
+
+	/* Create a ParseState for rewriting the view definition query */
+	pstate = make_parsestate(NULL);
+	pstate->p_queryEnv = queryEnv;
+	pstate->p_expr_kind = EXPR_KIND_NONE;
+
+	initStringInfo(&str);
+	appendStringInfo(&str,
+		" SELECT %s FROM ( ",
+		make_subquery_targetlist_from_table(table));
+
+	for (i = 0; i < num_union; i++)
+	{
+		if (i > 0)
+			appendStringInfo(&str, " UNION ALL ");
+
+		appendStringInfo(&str,
+			" TABLE  %s",
+			make_delta_enr_name(prefix_union, table->table_id, i));
+	}
+	for (i = 0; i < num_except; i++)
+	{
+		appendStringInfo(&str, " EXCEPT ALL ");
+
+		appendStringInfo(&str,
+			" TABLE  %s",
+			make_delta_enr_name(prefix_except, table->table_id, i));
+	}
+	appendStringInfo(&str,")");
+
+	raw = (RawStmt*)linitial(raw_parser(str.data, RAW_PARSE_DEFAULT));
+	sub = transformStmt(pstate, raw->stmt);
+
+	/*
+	 * Update the subquery so that it represent the combined transition
+	 * table.  Note that we leave the security_barrier and securityQuals
+	 * fields so that the subquery relation can be protected by the RLS
+	 * policy as same as the modified table.
+	 */
+	rte->rtekind = RTE_SUBQUERY;
+	rte->subquery = sub;
+
+	return rte;
+}
+
+/*
+ * rewrite_query_for_counting
+ *
+ * Rewrite query for counting duplicated tuples.
+ */
+static Query *
+rewrite_query_for_counting(Query *query, ParseState *pstate)
+{
+	TargetEntry *tle_count;
+	FuncCall *fn;
+	Node *node;
+
+	/* Add count(*) for counting distinct tuples in views */
+	fn = makeFuncCall(SystemFuncName("count"), NIL, COERCE_EXPLICIT_CALL, -1);
+	fn->agg_star = true;
+	if (!query->groupClause && !query->hasAggs)
+		query->groupClause = transformDistinctClause(NULL, &query->targetList, query->sortClause, false);
+
+	node = ParseFuncOrColumn(pstate, fn->funcname, NIL, NULL, fn, false, -1);
+
+	tle_count = makeTargetEntry((Expr *) node,
+								list_length(query->targetList) + 1,
+								pstrdup("__ivm_count__"),
+								false);
+	query->targetList = lappend(query->targetList, tle_count);
+	query->hasAggs = true;
+
+	return query;
+}
+
+/*
+ * calc_delta
+ *
+ * Calculate view deltas generated under the modification of a table specified
+ * by the RTE index.
+ */
+static void
+calc_delta(MV_TriggerTable *table, int rte_index, Query *query,
+			DestReceiver *dest_old, DestReceiver *dest_new,
+			TupleDesc *tupdesc_old, TupleDesc *tupdesc_new,
+			QueryEnvironment *queryEnv)
+{
+	ListCell *lc = list_nth_cell(query->rtable, rte_index - 1);
+	RangeTblEntry *rte = (RangeTblEntry *) lfirst(lc);
+
+	in_delta_calculation = true;
+
+	/* Generate old delta */
+	if (dest_old && list_length(table->old_tuplestores) > 0)
+	{
+		/* Replace the modified table with the old delta table and calculate the old view delta. */
+		lfirst(lc) = makeDeltaTable(rte, table, false, queryEnv);
+		refresh_matview_datafill(dest_old, query, queryEnv, tupdesc_old, "", false);
+	}
+
+	/* Generate new delta */
+	if (dest_new && list_length(table->new_tuplestores) > 0)
+	{
+		/* Replace the modified table with the new delta table and calculate the new view delta*/
+		lfirst(lc) = makeDeltaTable(rte, table, true, queryEnv);
+		refresh_matview_datafill(dest_new, query, queryEnv, tupdesc_new, "", false);
+	}
+
+	in_delta_calculation = false;
+}
+
+/*
+ * rewrite_query_for_postupdate_state
+ *
+ * Rewrite the query so that the specified base table's RTEs will represent
+ * "post-update" state of tables. This is called after the view delta
+ * calculation due to changes on this table finishes.
+ */
+static Query*
+rewrite_query_for_postupdate_state(Query *query, MV_TriggerTable *table, int rte_index)
+{
+	ListCell *lc = list_nth_cell(query->rtable, rte_index - 1);
+
+	/* Retore the original RTE */
+	lfirst(lc) = table->original_rte;
+
+	return query;
+}
+
+/*
+ * apply_delta
+ *
+ * Apply deltas to the materialized view. In outer join cases, this requires
+ * the view maintenance graph.
+ */
+static void
+apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *new_tuplestores,
+			TupleDesc tupdesc_old, TupleDesc tupdesc_new,
+			Query *query)
+{
+	StringInfoData querybuf;
+	StringInfoData target_list_buf;
+	Relation	matviewRel;
+	char	   *matviewname;
+	ListCell	*lc;
+	int			i;
+	List	   *keys = NIL;
+
+
+	/*
+	 * get names of the materialized view and delta tables
+	 */
+
+	matviewRel = table_open(matviewOid, NoLock);
+	matviewname = quote_qualified_identifier(get_namespace_name(RelationGetNamespace(matviewRel)),
+											 RelationGetRelationName(matviewRel));
+
+	/*
+	 * Build parts of the maintenance queries
+	 */
+
+	initStringInfo(&querybuf);
+	initStringInfo(&target_list_buf);
+
+	/* build string of target list */
+	for (i = 0; i < matviewRel->rd_att->natts; i++)
+	{
+		Form_pg_attribute attr = TupleDescAttr(matviewRel->rd_att, i);
+		char   *resname = NameStr(attr->attname);
+
+		if (i != 0)
+			appendStringInfo(&target_list_buf, ", ");
+		appendStringInfo(&target_list_buf, "%s", quote_qualified_identifier(NULL, resname));
+	}
+
+	i = 0;
+	foreach (lc, query->targetList)
+	{
+		TargetEntry *tle = (TargetEntry *) lfirst(lc);
+		Form_pg_attribute attr = TupleDescAttr(matviewRel->rd_att, i);
+
+		i++;
+
+		if (tle->resjunk)
+			continue;
+
+		keys = lappend(keys, attr);
+	}
+
+	/* Start maintaining the materialized view. */
+	OpenMatViewIncrementalMaintenance();
+
+	/* Open SPI context. */
+	if (SPI_connect() != SPI_OK_CONNECT)
+		elog(ERROR, "SPI_connect failed");
+
+	/* For tuple deletion */
+	if (old_tuplestores && tuplestore_tuple_count(old_tuplestores) > 0)
+	{
+		EphemeralNamedRelation enr = palloc(sizeof(EphemeralNamedRelationData));
+		int				rc;
+
+		/* convert tuplestores to ENR, and register for SPI */
+		enr->md.name = pstrdup(OLD_DELTA_ENRNAME);
+		enr->md.reliddesc = InvalidOid;
+		enr->md.tupdesc = tupdesc_old;
+		enr->md.enrtype = ENR_NAMED_TUPLESTORE;
+		enr->md.enrtuples = tuplestore_tuple_count(old_tuplestores);
+		enr->reldata = old_tuplestores;
+
+		rc = SPI_register_relation(enr);
+		if (rc != SPI_OK_REL_REGISTER)
+			elog(ERROR, "SPI_register failed");
+
+		apply_old_delta(matviewname, OLD_DELTA_ENRNAME, keys);
+
+	}
+	/* For tuple insertion */
+	if (new_tuplestores && tuplestore_tuple_count(new_tuplestores) > 0)
+	{
+		EphemeralNamedRelation enr = palloc(sizeof(EphemeralNamedRelationData));
+		int rc;
+
+		/* convert tuplestores to ENR, and register for SPI */
+		enr->md.name = pstrdup(NEW_DELTA_ENRNAME);
+		enr->md.reliddesc = InvalidOid;
+		enr->md.tupdesc = tupdesc_new;;
+		enr->md.enrtype = ENR_NAMED_TUPLESTORE;
+		enr->md.enrtuples = tuplestore_tuple_count(new_tuplestores);
+		enr->reldata = new_tuplestores;
+
+		rc = SPI_register_relation(enr);
+		if (rc != SPI_OK_REL_REGISTER)
+			elog(ERROR, "SPI_register failed");
+
+		/* apply new delta */
+		apply_new_delta(matviewname, NEW_DELTA_ENRNAME, &target_list_buf);
+	}
+
+	/* We're done maintaining the materialized view. */
+	CloseMatViewIncrementalMaintenance();
+
+	table_close(matviewRel, NoLock);
+
+	/* Close SPI context. */
+	if (SPI_finish() != SPI_OK_FINISH)
+		elog(ERROR, "SPI_finish failed");
+}
+
+/*
+ * apply_old_delta
+ *
+ * Execute a query for applying a delta table given by deltname_old
+ * which contains tuples to be deleted from to a materialized view given by
+ * matviewname.  This is used when counting is not required.
+ */
+static void
+apply_old_delta(const char *matviewname, const char *deltaname_old,
+				List *keys)
+{
+	StringInfoData	querybuf;
+	StringInfoData	keysbuf;
+	char   *match_cond;
+	ListCell *lc;
+
+	/* build WHERE condition for searching tuples to be deleted */
+	match_cond = get_matching_condition_string(keys);
+
+	/* build string of keys list */
+	initStringInfo(&keysbuf);
+	foreach (lc, keys)
+	{
+		Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc);
+		char   *resname = NameStr(attr->attname);
+		appendStringInfo(&keysbuf, "%s", quote_qualified_identifier("mv", resname));
+		if (lnext(keys, lc))
+			appendStringInfo(&keysbuf, ", ");
+	}
+
+	/* Search for matching tuples from the view and update or delete if found. */
+	initStringInfo(&querybuf);
+	appendStringInfo(&querybuf,
+	"DELETE FROM %s WHERE ctid IN ("
+		"SELECT tid FROM (SELECT pg_catalog.row_number() over (partition by %s) AS \"__ivm_row_number__\","
+								  "mv.ctid AS tid,"
+								  "diff.\"__ivm_count__\""
+						 "FROM %s AS mv, %s AS diff "
+						 "WHERE %s) v "
+					"WHERE v.\"__ivm_row_number__\" OPERATOR(pg_catalog.<=) v.\"__ivm_count__\")",
+					matviewname,
+					keysbuf.data,
+					matviewname, deltaname_old,
+					match_cond);
+
+	if (SPI_exec(querybuf.data, 0) != SPI_OK_DELETE)
+		elog(ERROR, "SPI_exec failed: %s", querybuf.data);
+}
+
+/*
+ * apply_new_delta
+ *
+ * Execute a query for applying a delta table given by deltname_new
+ * which contains tuples to be inserted into a materialized view given by
+ * matviewname.  This is used when counting is not required.
+ */
+static void
+apply_new_delta(const char *matviewname, const char *deltaname_new,
+				StringInfo target_list)
+{
+	StringInfoData	querybuf;
+
+	/* Search for matching tuples from the view and update or delete if found. */
+	initStringInfo(&querybuf);
+	appendStringInfo(&querybuf,
+					"INSERT INTO %s (%s) SELECT %s FROM ("
+						"SELECT diff.*, pg_catalog.generate_series(1, diff.\"__ivm_count__\")"
+							" AS __ivm_generate_series__ "
+						"FROM %s AS diff) AS v",
+					matviewname, target_list->data, target_list->data,
+					deltaname_new);
+
+	if (SPI_exec(querybuf.data, 0) != SPI_OK_INSERT)
+		elog(ERROR, "SPI_exec failed: %s", querybuf.data);
+}
+
+/*
+ * get_matching_condition_string
+ *
+ * Build a predicate string for looking for a tuple with given keys.
+ */
+static char *
+get_matching_condition_string(List *keys)
+{
+	StringInfoData match_cond;
+	ListCell	*lc;
+
+	/* If there is no key columns, the condition is always true. */
+	if (keys == NIL)
+		return "true";
+
+	initStringInfo(&match_cond);
+	foreach (lc, keys)
+	{
+		Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc);
+		char   *resname = NameStr(attr->attname);
+		char   *mv_resname = quote_qualified_identifier("mv", resname);
+		char   *diff_resname = quote_qualified_identifier("diff", resname);
+		Oid		typid = attr->atttypid;
+
+		/* Considering NULL values, we can not use simple = operator. */
+		appendStringInfo(&match_cond, "(");
+		generate_equal(&match_cond, typid, mv_resname, diff_resname);
+		appendStringInfo(&match_cond, " OR (%s IS NULL AND %s IS NULL))",
+						 mv_resname, diff_resname);
+
+		if (lnext(keys, lc))
+			appendStringInfo(&match_cond, " AND ");
+	}
+
+	return match_cond.data;
+}
+
+/*
+ * generate_equals
+ *
+ * Generate an equality clause using given operands' default equality
+ * operator.
+ */
+static void
+generate_equal(StringInfo querybuf, Oid opttype,
+			   const char *leftop, const char *rightop)
+{
+	TypeCacheEntry *typentry;
+
+	typentry = lookup_type_cache(opttype, TYPECACHE_EQ_OPR);
+	if (!OidIsValid(typentry->eq_opr))
+		ereport(ERROR,
+				(errcode(ERRCODE_UNDEFINED_FUNCTION),
+				 errmsg("could not identify an equality operator for type %s",
+						format_type_be_qualified(opttype))));
+
+	generate_operator_clause(querybuf,
+							 leftop, opttype,
+							 typentry->eq_opr,
+							 rightop, opttype);
+}
+
+/*
+ * mv_InitHashTables
+ */
+static void
+mv_InitHashTables(void)
+{
+	HASHCTL		ctl;
+
+	memset(&ctl, 0, sizeof(ctl));
+	ctl.keysize = sizeof(Oid);
+	ctl.entrysize = sizeof(MV_TriggerHashEntry);
+	mv_trigger_info = hash_create("MV trigger info",
+								 MV_INIT_QUERYHASHSIZE,
+								 &ctl, HASH_ELEM | HASH_BLOBS);
+
+	memset(&ctl, 0, sizeof(ctl));
+	ctl.keysize = sizeof(Oid);
+	ctl.entrysize = sizeof(DroppedImmvInfo);
+	dropped_immv = hash_create("Dropped IMMVs", 16,
+							   &ctl, HASH_ELEM | HASH_BLOBS);
+}
+
+/*
+ * AtAbort_IVM
+ *
+ * Clean up hash entries for all materialized views. This is called at
+ * (sub-)transaction abort. When the top-level transaction is aborted,
+ * InvalidSubTransactionId is set to subxid.
+ *
+ * Also, remove dropped IMMV information if it is aborted.
+ */
+void
+AtAbort_IVM(SubTransactionId subxid)
+{
+	HASH_SEQ_STATUS seq;
+
+	if (mv_trigger_info)
+	{
+		MV_TriggerHashEntry *entry;
+		hash_seq_init(&seq, mv_trigger_info);
+		while ((entry = hash_seq_search(&seq)) != NULL)
+			clean_up_IVM_hash_entry(entry, true, subxid);
+	}
+
+	if (dropped_immv)
+	{
+		DroppedImmvInfo *entry;
+		hash_seq_init(&seq, dropped_immv);
+		while ((entry = hash_seq_search(&seq)) != NULL)
+		{
+			if (subxid == InvalidSubTransactionId || subxid == entry->subxid)
+				hash_search(dropped_immv, (void *) &entry->immv_oid, HASH_REMOVE, NULL);
+		}
+	}
+
+	in_delta_calculation = false;
+}
+
+/*
+ * AtPreCommit_IVM
+ *
+ * Record the transaction ID that updated the view incrementally.
+ * Also, remove the entry for dropped IMMVs.
+ */
+void
+AtPreCommit_IVM(void)
+{
+	HASH_SEQ_STATUS seq;
+
+	if (mv_trigger_info)
+	{
+		MV_TriggerHashEntry *entry;
+
+		/*
+		 * Record the transaction ID that udpate the view incrementally,
+		 * and perform the final clean up of the entry.
+		 */
+		hash_seq_init(&seq, mv_trigger_info);
+		while ((entry = hash_seq_search(&seq)) != NULL)
+		{
+			setLastUpdateXid(entry->matview_id, GetTopFullTransactionId());
+			hash_search(mv_trigger_info, (void *) &entry->matview_id, HASH_REMOVE, NULL);
+		}
+	}
+
+	if (dropped_immv)
+	{
+		DroppedImmvInfo *entry;
+
+		LWLockAcquire(IvmControlLock, LW_EXCLUSIVE);
+		hash_seq_init(&seq, dropped_immv);
+		while ((entry = hash_seq_search(&seq)) != NULL)
+		{
+			hash_search(LastIvmUpdateHash, (void *) &entry->immv_oid, HASH_REMOVE, NULL);
+			hash_search(dropped_immv, (void *) &entry->immv_oid, HASH_REMOVE, NULL);
+		}
+		LWLockRelease(IvmControlLock);
+	}
+
+	in_delta_calculation = false;
+}
+
+/*
+ * clean_up_IVM_hash_entry
+ *
+ * Clean up tuple stores and hash entries for a materialized view after its
+ * maintenance finished. This is called at the end of table modifying query
+ * or (sub-)transaction abort. When the top-level transaction is aborted,
+ * InvalidSubTransactionId is set to subxid.
+ */
+static void
+clean_up_IVM_hash_entry(MV_TriggerHashEntry *entry, bool is_abort,
+						SubTransactionId subxid)
+{
+	bool found;
+	ListCell *lc;
+
+	/* clean up tuple stores */
+	foreach(lc, entry->tables)
+	{
+		MV_TriggerTable *table = (MV_TriggerTable *) lfirst(lc);
+
+		list_free(table->old_tuplestores);
+		list_free(table->new_tuplestores);
+		if (!is_abort)
+		{
+			ExecDropSingleTupleTableSlot(table->slot);
+			table_close(table->rel, NoLock);
+		}
+	}
+	list_free(entry->tables);
+	entry->tables = NIL;
+
+	if (is_abort)
+	{
+		bool	remove_entry = false;
+
+		/*
+		 * When the top-level transaction is aborted, remove all subxids.
+		 * When a sub-transaction is aborted, remove only its subxid.
+		 */
+		if (subxid == InvalidSubTransactionId)
+			remove_entry = true;
+		else
+		{
+			foreach(lc, entry->subxids)
+			{
+				if (lfirst_xid(lc) == subxid)
+				{
+					entry->subxids = list_delete_cell(entry->subxids, lc);
+					break;
+				}
+			}
+
+			/*
+			 * If all the subxid are removed, it means that the view was not
+			 * updated at all in this transaction.
+			 */
+			if (list_length(entry->subxids) == 0)
+				remove_entry = true;
+		}
+
+		/*
+		 * Remove entries of not updated views from the hash table.
+		 */
+		if (remove_entry)
+			hash_search(mv_trigger_info, (void *) &entry->matview_id, HASH_REMOVE, &found);
+	}
+	else
+	{
+		/* When the query sucsessully finished, unregister the snapshot */
+		UnregisterSnapshot(entry->snapshot);
+	}
+
+	entry->snapshot = InvalidSnapshot;
+}
+
+/*
+ * setLastUpdateXid
+ *
+ * Store the transaction ID that updated the view incremenally.
+ */
+static void
+setLastUpdateXid(Oid immv_oid, FullTransactionId xid)
+{
+	LastIvmUpdateEntry *entry;
+
+	LWLockAcquire(IvmControlLock, LW_EXCLUSIVE);
+	entry = (LastIvmUpdateEntry *) hash_search(LastIvmUpdateHash, (void *) &immv_oid, HASH_ENTER, NULL);
+	entry->oid = immv_oid;
+	entry->last_ivm_update = xid;
+	LWLockRelease(IvmControlLock);
+}
+
+/*
+ * getLastUpdateXid
+ *
+ * Get the most recent transaction ID that updated the view incrementally.
+ */
+static FullTransactionId
+getLastUpdateXid(Oid immv_oid)
+{
+	FullTransactionId xid = InvalidFullTransactionId;
+	LastIvmUpdateEntry *entry;
+	bool found;
+
+	LWLockAcquire(IvmControlLock, LW_SHARED);
+	entry = (LastIvmUpdateEntry *) hash_search(LastIvmUpdateHash, (void *) &immv_oid, HASH_FIND, &found);
+	LWLockRelease(IvmControlLock);
+	if (found)
+		xid = entry->last_ivm_update;
+
+	return xid;
+}
+
+void
+removeImmv(Oid immv_oid)
+{
+	DroppedImmvInfo *entry;
+
+	if (!dropped_immv)
+		mv_InitHashTables();
+
+	entry = (DroppedImmvInfo *) hash_search(dropped_immv, (void *) &immv_oid, HASH_ENTER, NULL);
+	entry->subxid = GetCurrentSubTransactionId();
+}
+
+/*
+ * isIvmName
+ *
+ * Check if this is a IVM hidden column from the name.
+ */
+bool
+isIvmName(const char *s)
+{
+	if (s)
+		return (strncmp(s, "__ivm_", 6) == 0);
+	return false;
+}
diff --git a/src/backend/commands/tablecmds.c b/src/backend/commands/tablecmds.c
index a1845240a98..99bc709959a 100644
--- a/src/backend/commands/tablecmds.c
+++ b/src/backend/commands/tablecmds.c
@@ -62,6 +62,7 @@
 #include "commands/defrem.h"
 #include "commands/event_trigger.h"
 #include "commands/extension.h"
+#include "commands/matview.h"
 #include "commands/repack.h"
 #include "commands/sequence.h"
 #include "commands/tablecmds.h"
@@ -1804,6 +1805,9 @@ RangeVarCallbackForDropRelation(const RangeVar *rel, Oid relOid, Oid oldRelOid,
 	state->actual_relkind = classform->relkind;
 	state->actual_relpersistence = classform->relpersistence;
 
+	if (classform->relkind == RELKIND_MATVIEW && classform->relisivm)
+		removeImmv(relOid);
+
 	/*
 	 * Both RELKIND_RELATION and RELKIND_PARTITIONED_TABLE are OBJECT_TABLE,
 	 * but RemoveRelations() can only pass one relkind for a given relation.
diff --git a/src/backend/utils/activity/wait_event_names.txt b/src/backend/utils/activity/wait_event_names.txt
index 560659f9568..d97c35eeef0 100644
--- a/src/backend/utils/activity/wait_event_names.txt
+++ b/src/backend/utils/activity/wait_event_names.txt
@@ -370,6 +370,7 @@ WaitLSN	"Waiting to read or update shared Wait-for-LSN state."
 LogicalDecodingControl	"Waiting to read or update logical decoding status information."
 DataChecksumsWorker	"Waiting for data checksums worker."
 AioWorkerControl	"Waiting to update AIO worker information."
+IvmControl	"Waiting for read or update IMMV information.."
 
 #
 # END OF PREDEFINED LWLOCKS (DO NOT CHANGE THIS LINE)
diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat
index be157a5fbe9..b8722eea7a4 100644
--- a/src/include/catalog/pg_proc.dat
+++ b/src/include/catalog/pg_proc.dat
@@ -12693,4 +12693,14 @@
   proname => 'hashoid8extended', prorettype => 'int8',
   proargtypes => 'oid8 int8', prosrc => 'hashoid8extended' },
 
+# IVM
+{ oid => '786', descr => 'ivm trigger (before)',
+  proname => 'IVM_immediate_before', provolatile => 'v', prorettype => 'trigger',
+  proargtypes => '', prosrc => 'IVM_immediate_before' },
+{ oid => '787', descr => 'ivm trigger (after)',
+  proname => 'IVM_immediate_maintenance', provolatile => 'v', prorettype => 'trigger',
+  proargtypes => '', prosrc => 'IVM_immediate_maintenance' },
+{ oid => '788', descr => 'ivm filetring ',
+  proname => 'ivm_visible_in_prestate', provolatile => 's', prorettype => 'bool',
+  proargtypes => 'oid tid oid', prosrc => 'ivm_visible_in_prestate' },
 ]
diff --git a/src/include/commands/createas.h b/src/include/commands/createas.h
index f895c67c0c2..c286ebcd70e 100644
--- a/src/include/commands/createas.h
+++ b/src/include/commands/createas.h
@@ -16,6 +16,7 @@
 
 #include "catalog/objectaddress.h"
 #include "nodes/params.h"
+#include "nodes/pathnodes.h"
 #include "parser/parse_node.h"
 #include "tcop/dest.h"
 #include "utils/queryenvironment.h"
@@ -25,6 +26,9 @@ extern ObjectAddress ExecCreateTableAs(ParseState *pstate, CreateTableAsStmt *st
 									   ParamListInfo params, QueryEnvironment *queryEnv,
 									   QueryCompletion *qc);
 
+extern void CreateIvmTriggersOnBaseTables(Query *qry, Oid matviewOid);
+extern void CreateIndexOnIMMV(Query *query, Relation matviewRel);
+
 extern int	GetIntoRelEFlags(IntoClause *intoClause);
 
 extern DestReceiver *CreateIntoRelDestReceiver(IntoClause *intoClause);
diff --git a/src/include/commands/matview.h b/src/include/commands/matview.h
index 738c731c1a9..f1dbfc052c5 100644
--- a/src/include/commands/matview.h
+++ b/src/include/commands/matview.h
@@ -15,6 +15,7 @@
 #define MATVIEW_H
 
 #include "catalog/objectaddress.h"
+#include "fmgr.h"
 #include "nodes/params.h"
 #include "nodes/parsenodes.h"
 #include "tcop/dest.h"
@@ -23,6 +24,8 @@
 
 extern void SetMatViewPopulatedState(Relation relation, bool newstate);
 
+extern void SetMatViewIVMState(Relation relation, bool newstate);
+
 extern ObjectAddress ExecRefreshMatView(RefreshMatViewStmt *stmt, const char *queryString,
 										QueryCompletion *qc);
 extern ObjectAddress RefreshMatViewByOid(Oid matviewOid, bool is_create, bool skipData,
@@ -33,4 +36,12 @@ extern DestReceiver *CreateTransientRelDestReceiver(Oid transientoid);
 
 extern bool MatViewIncrementalMaintenanceIsEnabled(void);
 
+extern Datum IVM_immediate_before(PG_FUNCTION_ARGS);
+extern Datum IVM_immediate_maintenance(PG_FUNCTION_ARGS);
+extern Datum IVM_visible_in_prestate(PG_FUNCTION_ARGS);
+extern void AtAbort_IVM(SubTransactionId subtxid);
+extern void AtPreCommit_IVM(void);
+extern void removeImmv(Oid immv_oid);
+extern bool isIvmName(const char *s);
+
 #endif							/* MATVIEW_H */
diff --git a/src/include/storage/lwlocklist.h b/src/include/storage/lwlocklist.h
index d7eb648bd27..756c63baf97 100644
--- a/src/include/storage/lwlocklist.h
+++ b/src/include/storage/lwlocklist.h
@@ -89,6 +89,7 @@ PG_LWLOCK(54, WaitLSN)
 PG_LWLOCK(55, LogicalDecodingControl)
 PG_LWLOCK(56, DataChecksumsWorker)
 PG_LWLOCK(57, AioWorkerControl)
+PG_LWLOCK(58, IvmControl)
 
 /*
  * There also exist several built-in LWLock tranches.  As with the predefined
diff --git a/src/include/storage/subsystemlist.h b/src/include/storage/subsystemlist.h
index 9ad619080be..481e15d00a1 100644
--- a/src/include/storage/subsystemlist.h
+++ b/src/include/storage/subsystemlist.h
@@ -88,3 +88,6 @@ PG_SHMEM_SUBSYSTEM(DataChecksumsShmemCallbacks)
 
 /* AIO subsystem. This delegates to the method-specific callbacks */
 PG_SHMEM_SUBSYSTEM(AioShmemCallbacks)
+
+/* Incremental View Maintenance */
+PG_SHMEM_SUBSYSTEM(IvmShmemCallbacks)
-- 
2.43.0


--Multipart=_Fri__29_May_2026_23_14_17_+0900_Te0o73X2VqYK57Gd
Content-Type: text/x-diff;
 name="v37-0005-Add-Incremental-View-Maintenance-support-to-psql.patch"
Content-Disposition: attachment;
 filename="v37-0005-Add-Incremental-View-Maintenance-support-to-psql.patch"
Content-Transfer-Encoding: 7bit



^ permalink  raw  reply  [nested|flat] 101+ messages in thread

* [PATCH v39 6/8] Add Incremental View Maintenance support
@ 2026-05-29 09:06  Yugo Nagata <[email protected]>
  0 siblings, 0 replies; 101+ messages in thread

From: Yugo Nagata @ 2026-05-29 09:06 UTC (permalink / raw)

In this implementation, AFTER triggers are used to collect
tuplestores containing transition table contents. When multiple tables
are changed, multiple AFTER triggers are invoked, then the final AFTER
trigger performs actual update of the matview. In addition, BEFORE
triggers are also used to handle global information for view
maintenance.

To calculate view deltas, we need both pre-state and post-state of base
tables. Post-update states are available in AFTER trigger, and pre-update
states can be calculated by removing inserted tuples and appending deleted
tuples. Insterted tuples are filtered using the snapshot taken before
table modification, and deleted tuples are contained in the old transition
table.

Incrementally Maintainable Materialized Views (IMMV) can contain
duplicated tuples.

This patch also allows self-join, simultaneous updates of more than
one base table, and multiple updates of the same base table.
---
 src/backend/access/transam/xact.c             |    8 +
 src/backend/commands/createas.c               |  709 +++++++
 src/backend/commands/matview.c                | 1835 ++++++++++++++++-
 src/backend/commands/tablecmds.c              |    4 +
 .../utils/activity/wait_event_names.txt       |    1 +
 src/include/catalog/pg_proc.dat               |   10 +
 src/include/commands/createas.h               |    4 +
 src/include/commands/matview.h                |   11 +
 src/include/storage/lwlocklist.h              |    1 +
 src/include/storage/subsystemlist.h           |    3 +
 10 files changed, 2548 insertions(+), 38 deletions(-)

diff --git a/src/backend/access/transam/xact.c b/src/backend/access/transam/xact.c
index 3a89149016f..0e6cb5493d2 100644
--- a/src/backend/access/transam/xact.c
+++ b/src/backend/access/transam/xact.c
@@ -37,6 +37,7 @@
 #include "catalog/pg_enum.h"
 #include "catalog/storage.h"
 #include "commands/async.h"
+#include "commands/matview.h"
 #include "commands/tablecmds.h"
 #include "commands/trigger.h"
 #include "common/pg_prng.h"
@@ -2322,6 +2323,9 @@ CommitTransaction(void)
 	CallXactCallbacks(is_parallel_worker ? XACT_EVENT_PARALLEL_PRE_COMMIT
 					  : XACT_EVENT_PRE_COMMIT);
 
+	/* Store the transaction ID that updated the view incrementally */
+	AtPreCommit_IVM();
+
 	/*
 	 * If this xact has started any unfinished parallel operation, clean up
 	 * its workers, warning about leaked resources.  (But we don't actually
@@ -2973,6 +2977,7 @@ AbortTransaction(void)
 	AtAbort_Notify();
 	AtEOXact_RelationMap(false, is_parallel_worker);
 	AtAbort_Twophase();
+	AtAbort_IVM(InvalidSubTransactionId);
 
 	/*
 	 * Advertise the fact that we aborted in pg_xact (assuming that we got as
@@ -5304,6 +5309,9 @@ AbortSubTransaction(void)
 
 	UnlockBuffers();
 
+	/* Clean up hash entries for incremental view maintenance */
+	AtAbort_IVM(s->subTransactionId);
+
 	/* Reset WAL record construction state */
 	XLogResetInsertion();
 
diff --git a/src/backend/commands/createas.c b/src/backend/commands/createas.c
index 6dbb831ca89..a499688b79d 100644
--- a/src/backend/commands/createas.c
+++ b/src/backend/commands/createas.c
@@ -29,18 +29,32 @@
 #include "access/tableam.h"
 #include "access/xact.h"
 #include "catalog/namespace.h"
+#include "catalog/index.h"
+#include "catalog/pg_am_d.h"
+#include "catalog/pg_constraint.h"
+#include "catalog/pg_inherits.h"
+#include "catalog/pg_trigger.h"
 #include "catalog/toasting.h"
 #include "commands/createas.h"
+#include "commands/defrem.h"
 #include "commands/matview.h"
 #include "commands/prepare.h"
 #include "commands/tablecmds.h"
+#include "commands/tablespace.h"
+#include "commands/trigger.h"
 #include "commands/view.h"
 #include "executor/execdesc.h"
 #include "executor/executor.h"
+#include "miscadmin.h"
 #include "nodes/makefuncs.h"
 #include "nodes/nodeFuncs.h"
 #include "nodes/queryjumble.h"
+#include "optimizer/optimizer.h"
+#include "optimizer/prep.h"
 #include "parser/analyze.h"
+#include "parser/parser.h"
+#include "parser/parsetree.h"
+#include "parser/parse_clause.h"
 #include "rewrite/rewriteHandler.h"
 #include "tcop/tcopprot.h"
 #include "utils/builtins.h"
@@ -70,6 +84,12 @@ static bool intorel_receive(TupleTableSlot *slot, DestReceiver *self);
 static void intorel_shutdown(DestReceiver *self);
 static void intorel_destroy(DestReceiver *self);
 
+static void CreateIvmTriggersOnBaseTablesRecurse(Query *qry, Node *node, Oid matviewOid,
+									 List **relids, bool ex_lock);
+static void CreateIvmTrigger(Oid relOid, Oid viewOid, int16 type, int16 timing, bool ex_lock);
+static void check_ivm_restriction(Node *node);
+static bool check_ivm_restriction_walker(Node *node, void *context);
+static Bitmapset *get_primary_key_attnos_from_query(Query *query, List **constraintList);
 
 /*
  * create_ctas_internal
@@ -277,6 +297,18 @@ ExecCreateTableAs(ParseState *pstate, CreateTableAsStmt *stmt,
 		into->skipData = true;
 	}
 
+	if (is_matview && into->ivm)
+	{
+		/* check if the query is supported in IMMV definition */
+		if (contain_mutable_functions((Node *) query))
+			ereport(ERROR,
+					(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+					 errmsg("mutable function is not supported on incrementally maintainable materialized view"),
+					 errhint("functions must be marked IMMUTABLE")));
+
+		check_ivm_restriction((Node *) query);
+	}
+
 	if (into->skipData)
 	{
 		/*
@@ -287,15 +319,36 @@ ExecCreateTableAs(ParseState *pstate, CreateTableAsStmt *stmt,
 		 */
 		address = create_ctas_nodata(query->targetList, into);
 
+		/*
+		 * For IVM, mark the matview before refresh so RelationIsIVM()
+		 * returns true inside RefreshMatViewByOid.
+		 */
+		if (is_matview && into->ivm)
+		{
+			Relation matviewRel = table_open(address.objectId, NoLock);
+
+			SetMatViewIVMState(matviewRel, true);
+			table_close(matviewRel, NoLock);
+			CommandCounterIncrement();
+		}
+
 		/*
 		 * For materialized views, reuse the REFRESH logic, which locks down
 		 * security-restricted operations and restricts the search_path.  This
 		 * reduces the chance that a subsequent refresh will fail.
 		 */
 		if (do_refresh)
+		{
 			RefreshMatViewByOid(address.objectId, true, false, false,
 								pstate->p_sourcetext, qc);
 
+			if (is_matview && into->ivm && IsolationUsesXactSnapshot())
+				ereport(WARNING,
+						(errmsg("inconsistent view can be created in isolation level SERIALIZABLE or REPEATABLE READ"),
+						 errdetail("The view may not include effects of a concurrent transaction."),
+						 errhint("The view with incremental maintenance should be created in isolation level READ COMMITTED, "
+								 "or refreshed manually to make sure the view is consistent.")));
+		}
 	}
 	else
 	{
@@ -635,3 +688,659 @@ intorel_destroy(DestReceiver *self)
 {
 	pfree(self);
 }
+
+/*
+ * CreateIvmTriggersOnBaseTables -- create IVM triggers on all base tables
+ */
+void
+CreateIvmTriggersOnBaseTables(Query *qry, Oid matviewOid)
+{
+	List   *relids = NIL;
+	bool	ex_lock = false;
+	RangeTblEntry *rte;
+
+	/* Immediately return if we don't have any base tables. */
+	if (list_length(qry->rtable) < 1)
+		return;
+
+	/*
+	 * If the view has more than one base tables, we need an exclusive lock
+	 * on the view so that the view would be maintained serially to avoid
+	 * the inconsistency that occurs when two base tables are modified in
+	 * concurrent transactions. However, if the view has only one table,
+	 * we can use a weaker lock.
+	 *
+	 * The type of lock should be determined here, because if we check the
+	 * view definition at maintenance time, we need to acquire a weaker lock,
+	 * and upgrading the lock level after this increases probability of
+	 * deadlock.
+	 */
+
+	rte = list_nth(qry->rtable, 0);
+	if (list_length(qry->rtable) > 1 || rte->rtekind != RTE_RELATION)
+		ex_lock = true;
+
+	CreateIvmTriggersOnBaseTablesRecurse(qry, (Node *)qry, matviewOid, &relids, ex_lock);
+
+	list_free(relids);
+}
+
+static void
+CreateIvmTriggersOnBaseTablesRecurse(Query *qry, Node *node, Oid matviewOid,
+									 List **relids, bool ex_lock)
+{
+	if (node == NULL)
+		return;
+
+	/* This can recurse, so check for excessive recursion */
+	check_stack_depth();
+
+	switch (nodeTag(node))
+	{
+		case T_Query:
+			{
+				Query *query = (Query *) node;
+
+				CreateIvmTriggersOnBaseTablesRecurse(qry, (Node *)query->jointree, matviewOid, relids, ex_lock);
+			}
+			break;
+
+		case T_RangeTblRef:
+			{
+				int			rti = ((RangeTblRef *) node)->rtindex;
+				RangeTblEntry *rte = rt_fetch(rti, qry->rtable);
+
+				if (rte->rtekind == RTE_RELATION && !list_member_oid(*relids, rte->relid))
+				{
+					CreateIvmTrigger(rte->relid, matviewOid, TRIGGER_TYPE_INSERT, TRIGGER_TYPE_BEFORE, ex_lock);
+					CreateIvmTrigger(rte->relid, matviewOid, TRIGGER_TYPE_DELETE, TRIGGER_TYPE_BEFORE, ex_lock);
+					CreateIvmTrigger(rte->relid, matviewOid, TRIGGER_TYPE_UPDATE, TRIGGER_TYPE_BEFORE, ex_lock);
+					CreateIvmTrigger(rte->relid, matviewOid, TRIGGER_TYPE_TRUNCATE, TRIGGER_TYPE_BEFORE, true);
+					CreateIvmTrigger(rte->relid, matviewOid, TRIGGER_TYPE_INSERT, TRIGGER_TYPE_AFTER, ex_lock);
+					CreateIvmTrigger(rte->relid, matviewOid, TRIGGER_TYPE_DELETE, TRIGGER_TYPE_AFTER, ex_lock);
+					CreateIvmTrigger(rte->relid, matviewOid, TRIGGER_TYPE_UPDATE, TRIGGER_TYPE_AFTER, ex_lock);
+					CreateIvmTrigger(rte->relid, matviewOid, TRIGGER_TYPE_TRUNCATE, TRIGGER_TYPE_AFTER, true);
+
+					*relids = lappend_oid(*relids, rte->relid);
+				}
+			}
+			break;
+
+		case T_FromExpr:
+			{
+				FromExpr   *f = (FromExpr *) node;
+				ListCell   *l;
+
+				foreach(l, f->fromlist)
+					CreateIvmTriggersOnBaseTablesRecurse(qry, lfirst(l), matviewOid, relids, ex_lock);
+			}
+			break;
+
+		case T_JoinExpr:
+			{
+				JoinExpr   *j = (JoinExpr *) node;
+
+				CreateIvmTriggersOnBaseTablesRecurse(qry, j->larg, matviewOid, relids, ex_lock);
+				CreateIvmTriggersOnBaseTablesRecurse(qry, j->rarg, matviewOid, relids, ex_lock);
+			}
+			break;
+
+		default:
+			elog(ERROR, "unrecognized node type: %d", (int) nodeTag(node));
+	}
+}
+
+/*
+ * CreateIvmTrigger -- create IVM trigger on a base table
+ */
+static void
+CreateIvmTrigger(Oid relOid, Oid viewOid, int16 type, int16 timing, bool ex_lock)
+{
+	ObjectAddress	refaddr;
+	ObjectAddress	address;
+	CreateTrigStmt *ivm_trigger;
+	List *transitionRels = NIL;
+
+	Assert(timing == TRIGGER_TYPE_BEFORE || timing == TRIGGER_TYPE_AFTER);
+
+	refaddr.classId = RelationRelationId;
+	refaddr.objectId = viewOid;
+	refaddr.objectSubId = 0;
+
+	ivm_trigger = makeNode(CreateTrigStmt);
+	ivm_trigger->relation = NULL;
+	ivm_trigger->row = false;
+
+	ivm_trigger->timing = timing;
+	ivm_trigger->events = type;
+
+	switch (type)
+	{
+		case TRIGGER_TYPE_INSERT:
+			ivm_trigger->trigname = (timing == TRIGGER_TYPE_BEFORE ? "IVM_trigger_ins_before" : "IVM_trigger_ins_after");
+			break;
+		case TRIGGER_TYPE_DELETE:
+			ivm_trigger->trigname = (timing == TRIGGER_TYPE_BEFORE ? "IVM_trigger_del_before" : "IVM_trigger_del_after");
+			break;
+		case TRIGGER_TYPE_UPDATE:
+			ivm_trigger->trigname = (timing == TRIGGER_TYPE_BEFORE ? "IVM_trigger_upd_before" : "IVM_trigger_upd_after");
+			break;
+		case TRIGGER_TYPE_TRUNCATE:
+			ivm_trigger->trigname = (timing == TRIGGER_TYPE_BEFORE ? "IVM_trigger_truncate_before" : "IVM_trigger_truncate_after");
+			break;
+		default:
+			elog(ERROR, "unsupported trigger type");
+	}
+
+	if (timing == TRIGGER_TYPE_AFTER)
+	{
+		if (type == TRIGGER_TYPE_INSERT || type == TRIGGER_TYPE_UPDATE)
+		{
+			TriggerTransition *n = makeNode(TriggerTransition);
+			n->name = "__ivm_newtable";
+			n->isNew = true;
+			n->isTable = true;
+
+			transitionRels = lappend(transitionRels, n);
+		}
+		if (type == TRIGGER_TYPE_DELETE || type == TRIGGER_TYPE_UPDATE)
+		{
+			TriggerTransition *n = makeNode(TriggerTransition);
+			n->name = "__ivm_oldtable";
+			n->isNew = false;
+			n->isTable = true;
+
+			transitionRels = lappend(transitionRels, n);
+		}
+	}
+
+	/*
+	 * XXX: When using DELETE or UPDATE, we must use exclusive lock for now
+	 * because apply_old_delta(_with_count) uses ctid to identify the tuple
+	 * to be deleted/deleted, but doesn't work in concurrent situations.
+	 *
+	 * If the view doesn't have aggregate, distinct, or tuple duplicate,
+	 * then it would work even in concurrent situations. However, we don't have
+	 * any way to guarantee the view has a unique key before opening the IMMV
+	 * at the maintenance time because users may drop the unique index.
+	 */
+
+	if (type == TRIGGER_TYPE_DELETE || type == TRIGGER_TYPE_UPDATE)
+		ex_lock = true;
+
+	ivm_trigger->funcname =
+		(timing == TRIGGER_TYPE_BEFORE ? SystemFuncName("IVM_immediate_before") : SystemFuncName("IVM_immediate_maintenance"));
+
+	ivm_trigger->columns = NIL;
+	ivm_trigger->transitionRels = transitionRels;
+	ivm_trigger->whenClause = NULL;
+	ivm_trigger->isconstraint = false;
+	ivm_trigger->deferrable = false;
+	ivm_trigger->initdeferred = false;
+	ivm_trigger->constrrel = NULL;
+	ivm_trigger->args = list_make2(
+		makeString(DatumGetPointer(DirectFunctionCall1(oidout, ObjectIdGetDatum(viewOid)))),
+		makeString(DatumGetPointer(DirectFunctionCall1(boolout, BoolGetDatum(ex_lock))))
+		);
+
+	address = CreateTrigger(ivm_trigger, NULL, relOid, InvalidOid, InvalidOid,
+						 InvalidOid, InvalidOid, InvalidOid, NULL, true, false);
+
+	recordDependencyOn(&address, &refaddr, DEPENDENCY_AUTO);
+
+	/* Make changes-so-far visible */
+	CommandCounterIncrement();
+}
+
+/*
+ * check_ivm_restriction --- look for specify nodes in the query tree
+ */
+static void
+check_ivm_restriction(Node *node)
+{
+	check_ivm_restriction_walker(node, NULL);
+}
+
+static bool
+check_ivm_restriction_walker(Node *node, void *context)
+{
+	if (node == NULL)
+		return false;
+
+	/*
+	 * We currently don't support Sub-Query.
+	 */
+	if (IsA(node, SubPlan) || IsA(node, SubLink))
+		ereport(ERROR,
+				(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+				 errmsg("subquery is not supported on incrementally maintainable materialized view")));
+
+	/* This can recurse, so check for excessive recursion */
+	check_stack_depth();
+
+	switch (nodeTag(node))
+	{
+		case T_Query:
+			{
+				Query *qry = (Query *)node;
+				ListCell   *lc;
+				List       *vars;
+
+				/* if contained CTE, return error */
+				if (qry->cteList != NIL)
+					ereport(ERROR,
+							(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+							 errmsg("CTE is not supported on incrementally maintainable materialized view")));
+				if (qry->havingQual != NULL)
+					ereport(ERROR,
+							(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+							 errmsg(" HAVING clause is not supported on incrementally maintainable materialized view")));
+				if (qry->sortClause != NIL)	/* There is a possibility that we don't need to return an error */
+					ereport(ERROR,
+							(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+							 errmsg("ORDER BY clause is not supported on incrementally maintainable materialized view")));
+				if (qry->limitOffset != NULL || qry->limitCount != NULL)
+					ereport(ERROR,
+							(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+							 errmsg("LIMIT/OFFSET clause is not supported on incrementally maintainable materialized view")));
+				if (qry->distinctClause)
+					ereport(ERROR,
+							(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+							 errmsg("DISTINCT is not supported on incrementally maintainable materialized view")));
+				if (qry->hasDistinctOn)
+					ereport(ERROR,
+							(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+							 errmsg("DISTINCT ON is not supported on incrementally maintainable materialized view")));
+				if (qry->hasWindowFuncs)
+					ereport(ERROR,
+							(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+							 errmsg("window functions are not supported on incrementally maintainable materialized view")));
+				if (qry->groupingSets != NIL)
+					ereport(ERROR,
+							(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+							 errmsg("GROUPING SETS, ROLLUP, or CUBE clauses is not supported on incrementally maintainable materialized view")));
+				if (qry->setOperations != NULL)
+					ereport(ERROR,
+							(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+							 errmsg("UNION/INTERSECT/EXCEPT statements are not supported on incrementally maintainable materialized view")));
+				if (list_length(qry->targetList) == 0)
+					ereport(ERROR,
+							(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+							 errmsg("empty target list is not supported on incrementally maintainable materialized view")));
+				if (qry->rowMarks != NIL)
+					ereport(ERROR,
+							(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+							 errmsg("FOR UPDATE/SHARE clause is not supported on incrementally maintainable materialized view")));
+
+				/* system column restrictions */
+				vars = pull_vars_of_level((Node *) qry, 0);
+				foreach(lc, vars)
+				{
+					if (IsA(lfirst(lc), Var))
+					{
+						Var *var = (Var *) lfirst(lc);
+						/* if system column, return error */
+						if (var->varattno < 0)
+							ereport(ERROR,
+									(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+									 errmsg("system column is not supported on incrementally maintainable materialized view")));
+					}
+				}
+
+				/* check if type in the target list had an equality operator */
+				foreach(lc, qry->targetList)
+				{
+					TargetEntry *tle = (TargetEntry *) lfirst(lc);
+					Oid             atttype = exprType((Node *) tle->expr);
+					Oid             opclass;
+
+					opclass = GetDefaultOpClass(atttype, BTREE_AM_OID);
+					if (!OidIsValid(opclass))
+						ereport(ERROR,
+								(errcode(ERRCODE_UNDEFINED_OBJECT),
+								 errmsg("data type %s has no default operator class for access method \"%s\"",
+									format_type_be(atttype), "btree")));
+				}
+
+				/* restrictions for rtable */
+				foreach(lc, qry->rtable)
+				{
+					RangeTblEntry *rte = (RangeTblEntry *) lfirst(lc);
+
+					if (rte->subquery)
+						ereport(ERROR,
+								(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+								 errmsg("subquery is not supported on incrementally maintainable materialized view")));
+
+					if (rte->tablesample != NULL)
+						ereport(ERROR,
+								(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+								 errmsg("TABLESAMPLE clause is not supported on incrementally maintainable materialized view")));
+
+					if (rte->relkind == RELKIND_PARTITIONED_TABLE)
+						ereport(ERROR,
+								(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+								 errmsg("partitioned table is not supported on incrementally maintainable materialized view")));
+
+					if (rte->relkind == RELKIND_RELATION && has_superclass(rte->relid))
+						ereport(ERROR,
+								(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+								 errmsg("partitions is not supported on incrementally maintainable materialized view")));
+
+					if (rte->relkind == RELKIND_RELATION && find_inheritance_children(rte->relid, NoLock) != NIL)
+						ereport(ERROR,
+								(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+								 errmsg("inheritance parent is not supported on incrementally maintainable materialized view")));
+
+					if (rte->relkind == RELKIND_FOREIGN_TABLE)
+						ereport(ERROR,
+								(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+								 errmsg("foreign table is not supported on incrementally maintainable materialized view")));
+
+					if (rte->relkind == RELKIND_VIEW ||
+						rte->relkind == RELKIND_MATVIEW)
+						ereport(ERROR,
+								(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+								 errmsg("VIEW or MATERIALIZED VIEW is not supported on incrementally maintainable materialized view")));
+
+					if (rte->rtekind == RTE_VALUES)
+						ereport(ERROR,
+								(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+								 errmsg("VALUES is not supported on incrementally maintainable materialized view")));
+
+				}
+
+				query_tree_walker(qry, check_ivm_restriction_walker, NULL, QTW_IGNORE_RANGE_TABLE);
+
+				break;
+			}
+		case T_TargetEntry:
+			{
+				TargetEntry *tle = (TargetEntry *)node;
+				if (isIvmName(tle->resname))
+						ereport(ERROR,
+								(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+								 errmsg("column name %s is not supported on incrementally maintainable materialized view", tle->resname)));
+
+				expression_tree_walker(node, check_ivm_restriction_walker, NULL);
+				break;
+			}
+		case T_JoinExpr:
+			{
+				JoinExpr *joinexpr = (JoinExpr *)node;
+
+				if (joinexpr->jointype > JOIN_INNER)
+						ereport(ERROR,
+								(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+								 errmsg("OUTER JOIN is not supported on incrementally maintainable materialized view")));
+
+				expression_tree_walker(node, check_ivm_restriction_walker, NULL);
+			}
+			break;
+		case T_Aggref:
+			ereport(ERROR,
+					(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+					 errmsg("aggregate function is not supported on incrementally maintainable materialized view")));
+			break;
+		default:
+			expression_tree_walker(node, check_ivm_restriction_walker, (void *) context);
+			break;
+	}
+	return false;
+}
+
+/*
+ * CreateIndexOnIMMV
+ *
+ * Create a unique index on incremental maintainable materialized view.
+ * If the view definition query has a GROUP BY clause, the index is created
+ * on the columns of GROUP BY expressions. Otherwise, if the view contains
+ * all primary key attributes of its base tables in the target list, the index
+ * is created on these attributes. In other cases, no index is created.
+ */
+void
+CreateIndexOnIMMV(Query *query, Relation matviewRel)
+{
+	ListCell *lc;
+	IndexStmt  *index;
+	ObjectAddress address;
+	List *constraintList = NIL;
+	char		idxname[NAMEDATALEN];
+	List	   *indexoidlist = RelationGetIndexList(matviewRel);
+	ListCell   *indexoidscan;
+	Bitmapset *key_attnos;
+
+	snprintf(idxname, sizeof(idxname), "%s_index", RelationGetRelationName(matviewRel));
+
+	index = makeNode(IndexStmt);
+
+	index->unique = true;
+	index->primary = false;
+	index->isconstraint = false;
+	index->deferrable = false;
+	index->initdeferred = false;
+	index->idxname = idxname;
+	index->relation =
+		makeRangeVar(get_namespace_name(RelationGetNamespace(matviewRel)),
+					 pstrdup(RelationGetRelationName(matviewRel)),
+					 -1);
+	index->accessMethod = DEFAULT_INDEX_TYPE;
+	index->options = NIL;
+	index->tableSpace = get_tablespace_name(matviewRel->rd_rel->reltablespace);
+	index->whereClause = NULL;
+	index->indexParams = NIL;
+	index->indexIncludingParams = NIL;
+	index->excludeOpNames = NIL;
+	index->idxcomment = NULL;
+	index->indexOid = InvalidOid;
+	index->oldNumber = InvalidRelFileNumber;
+	index->oldCreateSubid = InvalidSubTransactionId;
+	index->oldFirstRelfilelocatorSubid = InvalidSubTransactionId;
+	index->transformed = true;
+	index->concurrent = false;
+	index->if_not_exists = false;
+
+	/* create index on the base tables' primary key columns */
+	key_attnos = get_primary_key_attnos_from_query(query, &constraintList);
+	if (key_attnos)
+	{
+		foreach(lc, query->targetList)
+		{
+			TargetEntry *tle = (TargetEntry *) lfirst(lc);
+			Form_pg_attribute attr = TupleDescAttr(matviewRel->rd_att, tle->resno - 1);
+
+			if (bms_is_member(tle->resno - FirstLowInvalidHeapAttributeNumber, key_attnos))
+			{
+				IndexElem  *iparam;
+
+				iparam = makeNode(IndexElem);
+				iparam->name = pstrdup(NameStr(attr->attname));
+				iparam->expr = NULL;
+				iparam->indexcolname = NULL;
+				iparam->collation = NIL;
+				iparam->opclass = NIL;
+				iparam->opclassopts = NIL;
+				iparam->ordering = SORTBY_DEFAULT;
+				iparam->nulls_ordering = SORTBY_NULLS_DEFAULT;
+				index->indexParams = lappend(index->indexParams, iparam);
+			}
+		}
+	}
+	else
+	{
+		/* create no index, just notice that an appropriate index is necessary for efficient IVM */
+		ereport(NOTICE,
+				(errmsg("could not create an index on materialized view \"%s\" automatically",
+						RelationGetRelationName(matviewRel)),
+				 errdetail("This target list does not have all the primary key columns. "),
+				 errhint("Create an index on the materialized view for efficient incremental maintenance.")));
+		return;
+	}
+
+	/* If we have a compatible index, we don't need to create another. */
+	foreach(indexoidscan, indexoidlist)
+	{
+		Oid			indexoid = lfirst_oid(indexoidscan);
+		Relation	indexRel;
+		bool		hasCompatibleIndex = false;
+
+		indexRel = index_open(indexoid, AccessShareLock);
+
+		if (CheckIndexCompatible(indexRel->rd_id,
+								index->accessMethod,
+								index->indexParams,
+								index->excludeOpNames,
+								false))
+			hasCompatibleIndex = true;
+
+		index_close(indexRel, AccessShareLock);
+
+		if (hasCompatibleIndex)
+			return;
+	}
+
+	address = DefineIndex(NULL,
+						  RelationGetRelid(matviewRel),
+						  index,
+						  InvalidOid,
+						  InvalidOid,
+						  InvalidOid,
+						  -1,
+						  false, true, false, false, true);
+
+	ereport(NOTICE,
+			(errmsg("created index \"%s\" on materialized view \"%s\"",
+					idxname, RelationGetRelationName(matviewRel))));
+
+	/*
+	 * Make dependencies so that the index is dropped if any base tables'
+	 * primary key is dropped.
+	 */
+	foreach(lc, constraintList)
+	{
+		Oid constraintOid = lfirst_oid(lc);
+		ObjectAddress	refaddr;
+
+		refaddr.classId = ConstraintRelationId;
+		refaddr.objectId = constraintOid;
+		refaddr.objectSubId = 0;
+
+		recordDependencyOn(&address, &refaddr, DEPENDENCY_NORMAL);
+	}
+}
+
+
+/*
+ * get_primary_key_attnos_from_query
+ *
+ * Identify the columns in base tables' primary keys in the target list.
+ *
+ * Returns a Bitmapset of the column attnos of the primary key's columns of
+ * tables that used in the query.  The attnos are offset by
+ * FirstLowInvalidHeapAttributeNumber as same as get_primary_key_attnos.
+ *
+ * If any table has no primary key or any primary key's columns is not in
+ * the target list, return NULL.  We also return NULL if any pkey constraint
+ * is deferrable.
+ *
+ * constraintList is set to a list of the OIDs of the pkey constraints.
+ */
+static Bitmapset *
+get_primary_key_attnos_from_query(Query *query, List **constraintList)
+{
+	List *key_attnos_list = NIL;
+	ListCell *lc;
+	int i;
+	Bitmapset *keys = NULL;
+	Relids	rels_in_from;
+
+	/*
+	 * Collect primary key attributes from all tables used in query. The key attributes
+	 * sets for each table are stored in key_attnos_list in order by RTE index.
+	 */
+	foreach(lc, query->rtable)
+	{
+		RangeTblEntry *r = (RangeTblEntry*) lfirst(lc);
+		Bitmapset *key_attnos;
+		bool	has_no_pkey = false;
+
+		/* for tables, call get_primary_key_attnos */
+		if (r->rtekind == RTE_RELATION)
+		{
+			Oid constraintOid;
+			key_attnos = get_primary_key_attnos(r->relid, false, &constraintOid);
+			*constraintList = lappend_oid(*constraintList, constraintOid);
+			has_no_pkey = (key_attnos == NULL);
+		}
+		/*
+		 * Ignore join rels, because they are flatten later by
+		 * flatten_join_alias_vars(). Store NULL into key_attnos_list
+		 * as a dummy.
+		 */
+		 else if (r->rtekind == RTE_JOIN)
+		 {
+			key_attnos = NULL;
+		}
+		/* for other RTEs, store NULL into key_attnos_list */
+		else
+			has_no_pkey = true;
+
+		/*
+		 * If any table or subquery has no primary key or its pkey constraint is deferrable,
+		 * we cannot get key attributes for this query, so return NULL.
+		 */
+		if (has_no_pkey)
+			return NULL;
+
+		key_attnos_list = lappend(key_attnos_list, key_attnos);
+	}
+
+	/* Collect key attributes appearing in the target list */
+	i = 1;
+	foreach(lc, query->targetList)
+	{
+		TargetEntry *tle = (TargetEntry *) flatten_join_alias_vars(NULL, query, lfirst(lc));
+
+		if (IsA(tle->expr, Var))
+		{
+			Var *var = (Var*) tle->expr;
+			Bitmapset *key_attnos = list_nth(key_attnos_list, var->varno - 1);
+
+			/* check if this attribute is from a base table's primary key */
+			if (bms_is_member(var->varattno - FirstLowInvalidHeapAttributeNumber, key_attnos))
+			{
+				/*
+				 * Remove found key attributes from key_attnos_list, and add this
+				 * to the result list.
+				 */
+				key_attnos = bms_del_member(key_attnos, var->varattno - FirstLowInvalidHeapAttributeNumber);
+				if (bms_is_empty(key_attnos))
+				{
+					key_attnos_list = list_delete_nth_cell(key_attnos_list, var->varno - 1);
+					key_attnos_list = list_insert_nth(key_attnos_list, var->varno - 1, NULL);
+				}
+				keys = bms_add_member(keys, i - FirstLowInvalidHeapAttributeNumber);
+			}
+		}
+		i++;
+	}
+
+	/* Collect RTE indexes of relations appearing in the FROM clause */
+	rels_in_from = get_relids_in_jointree((Node *) query->jointree, false, false);
+
+	/*
+	 * Check if all key attributes of relations in FROM are appearing in the target
+	 * list.  If an attribute remains in key_attnos_list in spite of the table is used
+	 * in FROM clause, the target is missing this key attribute, so we return NULL.
+	 */
+	i = 1;
+	foreach(lc, key_attnos_list)
+	{
+		Bitmapset *bms = (Bitmapset *)lfirst(lc);
+		if (!bms_is_empty(bms) && bms_is_member(i, rels_in_from))
+			return NULL;
+		i++;
+	}
+
+	return keys;
+}
diff --git a/src/backend/commands/matview.c b/src/backend/commands/matview.c
index f7d8007f796..eaf39f80cd3 100644
--- a/src/backend/commands/matview.c
+++ b/src/backend/commands/matview.c
@@ -23,24 +23,36 @@
 #include "catalog/indexing.h"
 #include "catalog/namespace.h"
 #include "catalog/pg_am.h"
+#include "catalog/pg_depend.h"
+#include "catalog/pg_trigger.h"
 #include "catalog/pg_opclass.h"
 #include "commands/matview.h"
 #include "commands/repack.h"
 #include "commands/tablecmds.h"
 #include "commands/tablespace.h"
+#include "commands/createas.h"
 #include "executor/executor.h"
 #include "executor/spi.h"
+#include "executor/tstoreReceiver.h"
 #include "miscadmin.h"
+#include "nodes/makefuncs.h"
+#include "parser/analyze.h"
+#include "parser/parse_clause.h"
+#include "parser/parse_func.h"
+#include "parser/parse_relation.h"
 #include "pgstat.h"
 #include "rewrite/rewriteHandler.h"
+#include "rewrite/rowsecurity.h"
 #include "storage/lmgr.h"
+#include "storage/lwlock.h"
 #include "tcop/tcopprot.h"
 #include "utils/builtins.h"
+#include "utils/fmgroids.h"
 #include "utils/lsyscache.h"
 #include "utils/rel.h"
 #include "utils/snapmgr.h"
 #include "utils/syscache.h"
-
+#include "utils/typcache.h"
 
 typedef struct
 {
@@ -53,6 +65,97 @@ typedef struct
 	BulkInsertState bistate;	/* bulk insert state */
 } DR_transientrel;
 
+#define MV_INIT_QUERYHASHSIZE	16
+
+/*
+ * MV_TriggerHashEntry
+ *
+ * Hash entry for base tables on which IVM trigger is invoked
+ */
+typedef struct MV_TriggerHashEntry
+{
+	Oid	matview_id;			/* OID of the materialized view */
+	int	before_trig_count;	/* count of before triggers invoked */
+	int	after_trig_count;	/* count of after triggers invoked */
+
+	Snapshot	snapshot;	/* Snapshot just before table change */
+
+	List   *tables;		/* List of MV_TriggerTable */
+	bool	has_old;	/* tuples are deleted from any table? */
+	bool	has_new;	/* tuples are inserted into any table? */
+
+	/*
+	 * List of sub-transaction IDs that incrementally updated the view.
+	 * This list is maintained through a transaction, and an ID is removed
+	 * when a sub-transaction is aborted. If any ID is left when the
+	 * transaction is committed, this means the view is incrementally
+	 * updated in this transaction.
+	 */
+	List   *subxids;
+} MV_TriggerHashEntry;
+
+/*
+ * MV_TriggerTable
+ *
+ * IVM related data for tables on which the trigger is invoked.
+ */
+typedef struct MV_TriggerTable
+{
+	Oid		table_id;			/* OID of the modified table */
+	List   *old_tuplestores;	/* tuplestores for deleted tuples */
+	List   *new_tuplestores;	/* tuplestores for inserted tuples */
+
+	List   *rte_indexes;		/* List of RTE index of the modified table */
+	RangeTblEntry *original_rte;	/* the original RTE saved before rewriting query */
+
+	Relation	rel;			/* relation of the modified table */
+	TupleTableSlot *slot;		/* for checking visibility in the pre-state table */
+} MV_TriggerTable;
+
+typedef struct DroppedImmvInfo
+{
+	Oid					immv_oid;
+	SubTransactionId	subxid;
+} DroppedImmvInfo;
+
+static HTAB *mv_trigger_info = NULL;
+static HTAB *dropped_immv = NULL;
+
+static HTAB *LastIvmUpdateHash;
+
+#define LAST_IVM_UPDATE_HASH_SIZE 256
+
+static void IvmShmemRequest(void *arg);
+
+/* hash table entries */
+typedef struct LastIvmUpdateEntry
+{
+	Oid		oid;	/* hash key */
+	FullTransactionId	last_ivm_update;
+} LastIvmUpdateEntry;
+
+const ShmemCallbacks IvmShmemCallbacks = {
+	.request_fn = IvmShmemRequest,
+};
+
+static void
+IvmShmemRequest(void *arg)
+{
+	ShmemRequestHash(.name = "LastIvmUpdate hash",
+					 .nelems = LAST_IVM_UPDATE_HASH_SIZE,
+					 .ptr = &LastIvmUpdateHash,
+					 .hash_info.keysize = sizeof(Oid),
+					 .hash_info.entrysize = sizeof(LastIvmUpdateEntry),
+					 .hash_flags = HASH_ELEM | HASH_BLOBS,
+		);
+}
+
+static bool in_delta_calculation = false;
+
+/* ENR name for materialized view delta */
+#define NEW_DELTA_ENRNAME "new_delta"
+#define OLD_DELTA_ENRNAME "old_delta"
+
 static int	matview_maintenance_depth = 0;
 
 static void transientrel_startup(DestReceiver *self, int operation, TupleDesc typeinfo);
@@ -60,6 +163,8 @@ static bool transientrel_receive(TupleTableSlot *slot, DestReceiver *self);
 static void transientrel_shutdown(DestReceiver *self);
 static void transientrel_destroy(DestReceiver *self);
 static uint64 refresh_matview_datafill(DestReceiver *dest, Query *query,
+									   QueryEnvironment *queryEnv,
+									   TupleDesc *resultTupleDesc,
 									   const char *queryString, bool is_create);
 static void refresh_by_match_merge(Oid matviewOid, Oid tempOid, Oid relowner,
 								   int save_sec_context);
@@ -67,6 +172,41 @@ static void refresh_by_heap_swap(Oid matviewOid, Oid OIDNewHeap, char relpersist
 static bool is_usable_unique_index(Relation indexRel);
 static void OpenMatViewIncrementalMaintenance(void);
 static void CloseMatViewIncrementalMaintenance(void);
+static Query *get_matview_query(Relation matviewRel);
+
+static Query *rewrite_query_for_preupdate_state(Query *query, List *tables,
+								  ParseState *pstate, Oid matviewid);
+static void register_delta_ENRs(ParseState *pstate, Query *query, List *tables);
+static char *make_subquery_targetlist_from_table(MV_TriggerTable *table);
+static char *make_delta_enr_name(const char *prefix, Oid relid, int count);
+static RangeTblEntry *get_prestate_rte(RangeTblEntry *rte, MV_TriggerTable *table,
+				 QueryEnvironment *queryEnv, Oid matviewid);
+static RangeTblEntry *makeDeltaTable(RangeTblEntry *rte, MV_TriggerTable *table,
+									 bool is_new, QueryEnvironment *queryEnv);
+static Query *rewrite_query_for_counting(Query *query, ParseState *pstate);
+
+static void calc_delta(MV_TriggerTable *table, int rte_index, Query *query,
+			DestReceiver *dest_old, DestReceiver *dest_new,
+			TupleDesc *tupdesc_old, TupleDesc *tupdesc_new,
+			QueryEnvironment *queryEnv);
+static Query *rewrite_query_for_postupdate_state(Query *query, MV_TriggerTable *table, int rte_index);
+
+static void apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *new_tuplestores,
+			TupleDesc tupdesc_old, TupleDesc tupdesc_new,
+			Query *query);
+static void apply_old_delta(const char *matviewname, const char *deltaname_old,
+				List *keys);
+static void apply_new_delta(const char *matviewname, const char *deltaname_new,
+				StringInfo target_list);
+static char *get_matching_condition_string(List *keys);
+static void generate_equal(StringInfo querybuf, Oid opttype,
+			   const char *leftop, const char *rightop);
+
+static void mv_InitHashTables(void);
+static void clean_up_IVM_hash_entry(MV_TriggerHashEntry *entry, bool is_abort,
+									SubTransactionId subxid);
+static void setLastUpdateXid(Oid immv_oid, FullTransactionId xid);
+static FullTransactionId getLastUpdateXid(Oid immv_oid);
 
 /*
  * SetMatViewPopulatedState
@@ -108,6 +248,46 @@ SetMatViewPopulatedState(Relation relation, bool newstate)
 	CommandCounterIncrement();
 }
 
+/*
+ * SetMatViewIVMState
+ *		Mark a materialized view as IVM, or not.
+ *
+ * NOTE: caller must be holding an appropriate lock on the relation.
+ */
+void
+SetMatViewIVMState(Relation relation, bool newstate)
+{
+	Relation	pgrel;
+	HeapTuple	tuple;
+
+	Assert(relation->rd_rel->relkind == RELKIND_MATVIEW);
+
+	/*
+	 * Update relation's pg_class entry.  Crucial side-effect: other backends
+	 * (and this one too!) are sent SI message to make them rebuild relcache
+	 * entries.
+	 */
+	pgrel = table_open(RelationRelationId, RowExclusiveLock);
+	tuple = SearchSysCacheCopy1(RELOID,
+								ObjectIdGetDatum(RelationGetRelid(relation)));
+	if (!HeapTupleIsValid(tuple))
+		elog(ERROR, "cache lookup failed for relation %u",
+			 RelationGetRelid(relation));
+
+	((Form_pg_class) GETSTRUCT(tuple))->relisivm = newstate;
+
+	CatalogTupleUpdate(pgrel, &tuple->t_self, tuple);
+
+	heap_freetuple(tuple);
+	table_close(pgrel, RowExclusiveLock);
+
+	/*
+	 * Advance command counter to make the updated pg_class row locally
+	 * visible.
+	 */
+	CommandCounterIncrement();
+}
+
 /*
  * ExecRefreshMatView -- execute a REFRESH MATERIALIZED VIEW command
  *
@@ -166,8 +346,6 @@ RefreshMatViewByOid(Oid matviewOid, bool is_create, bool skipData,
 					QueryCompletion *qc)
 {
 	Relation	matviewRel;
-	RewriteRule *rule;
-	List	   *actions;
 	Query	   *dataQuery;
 	Oid			tableSpace;
 	Oid			relowner;
@@ -178,6 +356,7 @@ RefreshMatViewByOid(Oid matviewOid, bool is_create, bool skipData,
 	int			save_sec_context;
 	int			save_nestlevel;
 	ObjectAddress address;
+	bool oldPopulated;
 
 	matviewRel = table_open(matviewOid, NoLock);
 	relowner = matviewRel->rd_rel->relowner;
@@ -193,6 +372,8 @@ RefreshMatViewByOid(Oid matviewOid, bool is_create, bool skipData,
 	save_nestlevel = NewGUCNestLevel();
 	RestrictSearchPath();
 
+	oldPopulated = RelationIsPopulated(matviewRel);
+
 	/* Make sure it is a materialized view. */
 	if (matviewRel->rd_rel->relkind != RELKIND_MATVIEW)
 		ereport(ERROR,
@@ -213,32 +394,7 @@ RefreshMatViewByOid(Oid matviewOid, bool is_create, bool skipData,
 				 errmsg("%s options %s and %s cannot be used together",
 						"REFRESH", "CONCURRENTLY", "WITH NO DATA")));
 
-	/*
-	 * Check that everything is correct for a refresh. Problems at this point
-	 * are internal errors, so elog is sufficient.
-	 */
-	if (matviewRel->rd_rel->relhasrules == false ||
-		matviewRel->rd_rules->numLocks < 1)
-		elog(ERROR,
-			 "materialized view \"%s\" is missing rewrite information",
-			 RelationGetRelationName(matviewRel));
-
-	if (matviewRel->rd_rules->numLocks > 1)
-		elog(ERROR,
-			 "materialized view \"%s\" has too many rules",
-			 RelationGetRelationName(matviewRel));
-
-	rule = matviewRel->rd_rules->rules[0];
-	if (rule->event != CMD_SELECT || !(rule->isInstead))
-		elog(ERROR,
-			 "the rule for materialized view \"%s\" is not a SELECT INSTEAD OF rule",
-			 RelationGetRelationName(matviewRel));
-
-	actions = rule->actions;
-	if (list_length(actions) != 1)
-		elog(ERROR,
-			 "the rule for materialized view \"%s\" is not a single action",
-			 RelationGetRelationName(matviewRel));
+	dataQuery = get_matview_query(matviewRel);
 
 	/*
 	 * Check that there is a unique index with no WHERE clause on one or more
@@ -275,12 +431,6 @@ RefreshMatViewByOid(Oid matviewOid, bool is_create, bool skipData,
 					 errhint("Create a unique index with no WHERE clause on one or more columns of the materialized view.")));
 	}
 
-	/*
-	 * The stored query was rewritten at the time of the MV definition, but
-	 * has not been scribbled on by the planner.
-	 */
-	dataQuery = linitial_node(Query, actions);
-
 	/*
 	 * Check for active uses of the relation in the current transaction, such
 	 * as open scans.
@@ -310,6 +460,90 @@ RefreshMatViewByOid(Oid matviewOid, bool is_create, bool skipData,
 		relpersistence = matviewRel->rd_rel->relpersistence;
 	}
 
+	/* delete IMMV triggers. */
+	if (RelationIsIVM(matviewRel) && skipData)
+	{
+		Relation	tgRel;
+		Relation	depRel;
+		ScanKeyData key;
+		SysScanDesc scan;
+		HeapTuple	tup;
+		ObjectAddresses *immv_triggers;
+
+		immv_triggers = new_object_addresses();
+
+		tgRel = table_open(TriggerRelationId, RowExclusiveLock);
+		depRel = table_open(DependRelationId, RowExclusiveLock);
+
+		/* search triggers that depends on IMMV. */
+		ScanKeyInit(&key,
+					Anum_pg_depend_refobjid,
+					BTEqualStrategyNumber, F_OIDEQ,
+					ObjectIdGetDatum(matviewOid));
+		scan = systable_beginscan(depRel, DependReferenceIndexId, true,
+								  NULL, 1, &key);
+		while ((tup = systable_getnext(scan)) != NULL)
+		{
+			ObjectAddress obj;
+			Form_pg_depend foundDep = (Form_pg_depend) GETSTRUCT(tup);
+
+			if (foundDep->classid == TriggerRelationId)
+			{
+				HeapTuple	tgtup;
+				ScanKeyData tgkey[1];
+				SysScanDesc tgscan;
+				Form_pg_trigger tgform;
+
+				/* Find the trigger name. */
+				ScanKeyInit(&tgkey[0],
+							Anum_pg_trigger_oid,
+							BTEqualStrategyNumber, F_OIDEQ,
+							ObjectIdGetDatum(foundDep->objid));
+
+				tgscan = systable_beginscan(tgRel, TriggerOidIndexId, true,
+											NULL, 1, tgkey);
+				tgtup = systable_getnext(tgscan);
+				if (!HeapTupleIsValid(tgtup))
+					elog(ERROR, "could not find tuple for immv trigger %u", foundDep->objid);
+
+				tgform = (Form_pg_trigger) GETSTRUCT(tgtup);
+
+				/* If trigger is created by IMMV, delete it. */
+				if (strncmp(NameStr(tgform->tgname), "IVM_trigger_", 12) == 0)
+				{
+					obj.classId = foundDep->classid;
+					obj.objectId = foundDep->objid;
+					obj.objectSubId = foundDep->refobjsubid;
+					add_exact_object_address(&obj, immv_triggers);
+				}
+				systable_endscan(tgscan);
+			}
+		}
+		systable_endscan(scan);
+
+		performMultipleDeletions(immv_triggers, DROP_RESTRICT, PERFORM_DELETION_INTERNAL);
+
+		table_close(depRel, RowExclusiveLock);
+		table_close(tgRel, RowExclusiveLock);
+		free_object_addresses(immv_triggers);
+	}
+
+	/*
+	 * Create triggers on incremental maintainable materialized view
+	 * This argument should use 'dataQuery'. This needs to use a rewritten query,
+	 * because a sublink in jointree is not supported by this function.
+	 *
+	 * This is performed before generating data because we have to wait
+	 * concurrent transactions modifying a base table and then take a snapshot
+	 * to see changes by these transactions to make sure a consistent view
+	 * is created.
+	 */
+	if (RelationIsIVM(matviewRel) && !skipData && !oldPopulated)
+	{
+		CreateIvmTriggersOnBaseTables(dataQuery, matviewOid);
+		CreateIndexOnIMMV(dataQuery, matviewRel);
+	}
+
 	/*
 	 * Create the transient table that will receive the regenerated data. Lock
 	 * it against access by any other process until commit (by which time it
@@ -326,8 +560,43 @@ RefreshMatViewByOid(Oid matviewOid, bool is_create, bool skipData,
 		DestReceiver *dest;
 
 		dest = CreateTransientRelDestReceiver(OIDNewHeap);
-		processed = refresh_matview_datafill(dest, dataQuery, queryString,
-											 is_create);
+
+		if (RelationIsIVM(matviewRel))
+		{
+			/*
+			 * In READ COMMITTED, get and push the latest snapshot again to see the
+			 * results of concurrent transactions committed after the current
+			 * transaction started.
+			 */
+			if (!IsolationUsesXactSnapshot())
+				PushActiveSnapshot(GetTransactionSnapshot());
+
+			/*
+			 * If a concurrent transaction updated the view incrementally and was
+			 * committed before we acquired the lock, the results of refresh_immv could
+			 * be inconsistent. Therefore, we have to check the transaction ID of the
+			 * most recent update of the view, and if this was in progress at the
+			 * transaction start, raise an error to prevent anomalies.
+			 */
+			if (!is_create)
+			{
+				FullTransactionId xid;
+
+				xid = getLastUpdateXid(matviewOid);
+				if (XidInMVCCSnapshot(XidFromFullTransactionId(xid), GetActiveSnapshot()))
+					ereport(ERROR,
+							(errcode(ERRCODE_T_R_SERIALIZATION_FAILURE),
+							 errmsg("the materialized view is incrementally updated in concurrent transaction"),
+							 errhint("The transaction might succeed if retried.")));
+			}
+		}
+
+		processed = refresh_matview_datafill(dest, dataQuery, NULL, NULL,
+											 queryString, is_create);
+
+		/* Pop the original snapshot. */
+		if (RelationIsIVM(matviewRel) && !IsolationUsesXactSnapshot())
+			PopActiveSnapshot();
 	}
 
 	/* Make the matview match the newly generated data. */
@@ -402,6 +671,8 @@ RefreshMatViewByOid(Oid matviewOid, bool is_create, bool skipData,
  */
 static uint64
 refresh_matview_datafill(DestReceiver *dest, Query *query,
+						 QueryEnvironment *queryEnv,
+						 TupleDesc *resultTupleDesc,
 						 const char *queryString, bool is_create)
 {
 	List	   *rewritten;
@@ -439,7 +710,7 @@ refresh_matview_datafill(DestReceiver *dest, Query *query,
 	/* Create a QueryDesc, redirecting output to our tuple receiver */
 	queryDesc = CreateQueryDesc(plan, queryString,
 								GetActiveSnapshot(), InvalidSnapshot,
-								dest, NULL, NULL, 0);
+								dest, NULL, queryEnv ? queryEnv: NULL, 0);
 
 	/* call ExecutorStart to prepare the plan for execution */
 	ExecutorStart(queryDesc, 0);
@@ -449,6 +720,9 @@ refresh_matview_datafill(DestReceiver *dest, Query *query,
 
 	processed = queryDesc->estate->es_processed;
 
+	if (resultTupleDesc)
+		*resultTupleDesc = CreateTupleDescCopy(queryDesc->tupDesc);
+
 	/* and clean up */
 	ExecutorFinish(queryDesc);
 	ExecutorEnd(queryDesc);
@@ -967,3 +1241,1488 @@ CloseMatViewIncrementalMaintenance(void)
 	matview_maintenance_depth--;
 	Assert(matview_maintenance_depth >= 0);
 }
+
+/*
+ * get_matview_query - get the Query from a matview's _RETURN rule.
+ */
+static Query *
+get_matview_query(Relation matviewRel)
+{
+	RewriteRule *rule;
+	List * actions;
+
+	/*
+	 * Check that everything is correct for a refresh. Problems at this point
+	 * are internal errors, so elog is sufficient.
+	 */
+	if (matviewRel->rd_rel->relhasrules == false ||
+		matviewRel->rd_rules->numLocks < 1)
+		elog(ERROR,
+			 "materialized view \"%s\" is missing rewrite information",
+			 RelationGetRelationName(matviewRel));
+
+	if (matviewRel->rd_rules->numLocks > 1)
+		elog(ERROR,
+			 "materialized view \"%s\" has too many rules",
+			 RelationGetRelationName(matviewRel));
+
+	rule = matviewRel->rd_rules->rules[0];
+	if (rule->event != CMD_SELECT || !(rule->isInstead))
+		elog(ERROR,
+			 "the rule for materialized view \"%s\" is not a SELECT INSTEAD OF rule",
+			 RelationGetRelationName(matviewRel));
+
+	actions = rule->actions;
+	if (list_length(actions) != 1)
+		elog(ERROR,
+			 "the rule for materialized view \"%s\" is not a single action",
+			 RelationGetRelationName(matviewRel));
+
+	/*
+	 * The stored query was rewritten at the time of the MV definition, but
+	 * has not been scribbled on by the planner.
+	 */
+	return linitial_node(Query, actions);
+}
+
+
+/* ----------------------------------------------------
+ *		Incremental View Maintenance routines
+ * ---------------------------------------------------
+ */
+
+/*
+ * IVM_immediate_before
+ *
+ * IVM trigger function invoked before base table is modified. If this is
+ * invoked firstly in the same statement, we save the transaction id and the
+ * command id at that time.
+ */
+Datum
+IVM_immediate_before(PG_FUNCTION_ARGS)
+{
+	TriggerData *trigdata = (TriggerData *) fcinfo->context;
+	char	   *matviewOid_text = trigdata->tg_trigger->tgargs[0];
+	char	   *ex_lock_text = trigdata->tg_trigger->tgargs[1];
+	Oid			matviewOid;
+	MV_TriggerHashEntry *entry;
+	bool	found;
+	bool	ex_lock;
+
+	matviewOid = DatumGetObjectId(DirectFunctionCall1(oidin, CStringGetDatum(matviewOid_text)));
+	ex_lock = DatumGetBool(DirectFunctionCall1(boolin, CStringGetDatum(ex_lock_text)));
+
+	/* If the view has more than one tables, we have to use an exclusive lock. */
+	if (ex_lock)
+	{
+		FullTransactionId xid;
+
+		/*
+		 * Wait for concurrent transactions which update this materialized view at
+		 * READ COMMITED. This is needed to see changes committed in other
+		 * transactions. No wait and raise an error at REPEATABLE READ or
+		 * SERIALIZABLE to prevent update anomalies of matviews.
+		 * XXX: dead-lock is possible here.
+		 */
+		if (!IsolationUsesXactSnapshot())
+			LockRelationOid(matviewOid, ExclusiveLock);
+		else if (!ConditionalLockRelationOid(matviewOid, ExclusiveLock))
+		{
+			/* try to throw error by name; relation could be deleted... */
+			char	   *relname = get_rel_name(matviewOid);
+
+			if (!relname)
+				ereport(ERROR,
+						(errcode(ERRCODE_LOCK_NOT_AVAILABLE),
+						errmsg("could not obtain lock on materialized view during incremental maintenance")));
+
+			ereport(ERROR,
+					(errcode(ERRCODE_LOCK_NOT_AVAILABLE),
+					errmsg("could not obtain lock on materialized view \"%s\" during incremental maintenance",
+							relname)));
+		}
+
+		/*
+		 * Even if we can acquire an lock, a concurrent transaction could have
+		 * updated the view incrementally and been committed before we acquired
+		 * the lock. Therefore, we have to check the transaction ID of the most
+		 * recent update of the view, and if this was in progress at the
+		 * transaction start, raise an error to prevent anomalies.
+		 */
+		xid = getLastUpdateXid(matviewOid);
+		if (XidInMVCCSnapshot(XidFromFullTransactionId(xid), GetTransactionSnapshot()))
+			ereport(ERROR,
+					(errcode(ERRCODE_T_R_SERIALIZATION_FAILURE),
+					 errmsg("the materialized view is incrementally updated in concurrent transaction"),
+					 errhint("The transaction might succeed if retried.")));
+	}
+	else
+		LockRelationOid(matviewOid, RowExclusiveLock);
+
+	/*
+	 * On the first call initialize the hashtable
+	 */
+	if (!mv_trigger_info)
+		mv_InitHashTables();
+
+	entry = (MV_TriggerHashEntry *) hash_search(mv_trigger_info,
+											  (void *) &matviewOid,
+											  HASH_ENTER, &found);
+
+	/* On the first BEFORE to update the view, initialize trigger data */
+	if (!found || entry->snapshot == InvalidSnapshot)
+	{
+		Snapshot snapshot;
+
+		/*
+		 * Get a snapshot just before the table was modified for checking
+		 * tuple visibility in the pre-update state of the table.
+		 *
+		 * In READ COMMITTED, use the latest snapshot again to see the
+		 * results of concurrent transactions committed after the current
+		 * transaction started.
+		 */
+		if (IsolationUsesXactSnapshot())
+			snapshot = GetActiveSnapshot();
+		else
+			snapshot = GetTransactionSnapshot();
+
+		entry->matview_id = matviewOid;
+		entry->before_trig_count = 0;
+		entry->after_trig_count = 0;
+		entry->snapshot = RegisterSnapshot(snapshot);
+		entry->tables = NIL;
+		entry->has_old = false;
+		entry->has_new = false;
+
+		/*
+		 * If this is the first table modifying query in the transaction,
+		 * initialize the list of subxids.
+		 */
+		if (!found)
+			entry->subxids = NIL;
+	}
+
+	entry->before_trig_count++;
+
+	return PointerGetDatum(NULL);
+}
+
+/*
+ * IVM_immediate_maintenance
+ *
+ * IVM trigger function invoked after base table is modified.
+ * For each table, tuplestores of transition tables are collected.
+ * and after the last modification
+ */
+Datum
+IVM_immediate_maintenance(PG_FUNCTION_ARGS)
+{
+	TriggerData *trigdata = (TriggerData *) fcinfo->context;
+	Relation	rel;
+	Oid			relid;
+	Oid			matviewOid;
+	Query	   *query;
+	Query	   *rewritten = NULL;
+	char	   *matviewOid_text = trigdata->tg_trigger->tgargs[0];
+	Relation	matviewRel;
+	int old_depth = matview_maintenance_depth;
+	SubTransactionId subxid;
+
+	Oid			relowner;
+	Tuplestorestate *old_tuplestore = NULL;
+	Tuplestorestate *new_tuplestore = NULL;
+	DestReceiver *dest_new = NULL, *dest_old = NULL;
+	Oid			save_userid;
+	int			save_sec_context;
+	int			save_nestlevel;
+
+	MV_TriggerHashEntry *entry;
+	MV_TriggerTable		*table;
+	bool	found;
+
+	ParseState		 *pstate;
+	QueryEnvironment *queryEnv = create_queryEnv();
+	MemoryContext	oldcxt;
+	ListCell   *lc;
+	int			i;
+
+
+	/* Create a ParseState for rewriting the view definition query */
+	pstate = make_parsestate(NULL);
+	pstate->p_queryEnv = queryEnv;
+	pstate->p_expr_kind = EXPR_KIND_SELECT_TARGET;
+
+	rel = trigdata->tg_relation;
+	relid = rel->rd_id;
+
+	matviewOid = DatumGetObjectId(DirectFunctionCall1(oidin, CStringGetDatum(matviewOid_text)));
+
+	/*
+	 * On the first call initialize the hashtable
+	 */
+	if (!mv_trigger_info)
+		mv_InitHashTables();
+
+	/* get the entry for this materialized view */
+	entry = (MV_TriggerHashEntry *) hash_search(mv_trigger_info,
+											  (void *) &matviewOid,
+											  HASH_FIND, &found);
+	Assert (found && entry != NULL);
+	entry->after_trig_count++;
+
+	/* search the entry for the modified table and create new entry if not found */
+	found = false;
+	foreach(lc, entry->tables)
+	{
+		table = (MV_TriggerTable *) lfirst(lc);
+		if (table->table_id == relid)
+		{
+			found = true;
+			break;
+		}
+	}
+	if (!found)
+	{
+		oldcxt = MemoryContextSwitchTo(TopTransactionContext);
+
+		table = (MV_TriggerTable *) palloc0(sizeof(MV_TriggerTable));
+		table->table_id = relid;
+		table->old_tuplestores = NIL;
+		table->new_tuplestores = NIL;
+		table->rte_indexes = NIL;
+		table->slot = MakeSingleTupleTableSlot(RelationGetDescr(rel), table_slot_callbacks(rel));
+		/* We assume we have at least RowExclusiveLock on modified tables. */
+		table->rel = table_open(RelationGetRelid(rel), NoLock);
+		entry->tables = lappend(entry->tables, table);
+
+		MemoryContextSwitchTo(oldcxt);
+	}
+
+	/* Save the transition tables and make a request to not free immediately */
+	if (trigdata->tg_oldtable)
+	{
+		oldcxt = MemoryContextSwitchTo(TopTransactionContext);
+		table->old_tuplestores = lappend(table->old_tuplestores, trigdata->tg_oldtable);
+		entry->has_old = true;
+		MemoryContextSwitchTo(oldcxt);
+	}
+	if (trigdata->tg_newtable)
+	{
+		oldcxt = MemoryContextSwitchTo(TopTransactionContext);
+		table->new_tuplestores = lappend(table->new_tuplestores, trigdata->tg_newtable);
+		entry->has_new = true;
+		MemoryContextSwitchTo(oldcxt);
+	}
+	if (entry->has_new || entry->has_old)
+	{
+		CmdType cmd;
+
+		if (TRIGGER_FIRED_BY_INSERT(trigdata->tg_event))
+			cmd = CMD_INSERT;
+		else if (TRIGGER_FIRED_BY_DELETE(trigdata->tg_event))
+			cmd = CMD_DELETE;
+		else if (TRIGGER_FIRED_BY_UPDATE(trigdata->tg_event))
+			cmd = CMD_UPDATE;
+		else
+			elog(ERROR,"unsupported trigger type");
+
+		/* Prolong lifespan of transition tables to the end of the last AFTER trigger */
+		SetTransitionTablePreserved(relid, cmd);
+	}
+
+
+	/* If this is not the last AFTER trigger call, immediately exit. */
+	Assert (entry->before_trig_count >= entry->after_trig_count);
+	if (entry->before_trig_count != entry->after_trig_count)
+		return PointerGetDatum(NULL);
+
+	/*
+	 * If this is the last AFTER trigger call, continue and update the view.
+	 */
+
+	/* record the subxid that updated the view incrementally */
+	subxid = GetCurrentSubTransactionId();
+	if (!list_member_xid(entry->subxids, subxid))
+	{
+		oldcxt = MemoryContextSwitchTo(TopTransactionContext);
+		entry->subxids = lappend_xid(entry->subxids, subxid);
+		MemoryContextSwitchTo(oldcxt);
+	}
+
+	/*
+	 * Advance command counter to make the updated base table rows locally
+	 * visible.
+	 */
+	CommandCounterIncrement();
+
+	matviewRel = table_open(matviewOid, NoLock);
+
+	/* Make sure it is a materialized view. */
+	Assert(matviewRel->rd_rel->relkind == RELKIND_MATVIEW);
+
+	/*
+	 * In READ COMMITTED, get and push the latest snapshot again to see the
+	 * results of concurrent transactions committed after the current
+	 * transaction started.
+	 */
+	if (!IsolationUsesXactSnapshot())
+		PushActiveSnapshot(GetTransactionSnapshot());
+
+	/*
+	 * Check for active uses of the relation in the current transaction, such
+	 * as open scans.
+	 *
+	 * NB: We count on this to protect us against problems with refreshing the
+	 * data using TABLE_INSERT_FROZEN.
+	 */
+	CheckTableNotInUse(matviewRel, "refresh a materialized view incrementally");
+
+	/*
+	 * Switch to the owner's userid, so that any functions are run as that
+	 * user.  Also arrange to make GUC variable changes local to this command.
+	 * We will switch modes when we are about to execute user code.
+	 */
+	relowner = matviewRel->rd_rel->relowner;
+	GetUserIdAndSecContext(&save_userid, &save_sec_context);
+	SetUserIdAndSecContext(relowner,
+						   save_sec_context | SECURITY_RESTRICTED_OPERATION);
+	save_nestlevel = NewGUCNestLevel();
+
+	/* get view query*/
+	query = get_matview_query(matviewRel);
+
+	/*
+	 * When a base table is truncated, the view content will be empty if the
+	 * view definition query does not contain an aggregate without a GROUP clause.
+	 * Therefore, such views can be truncated.
+	 */
+	if (TRIGGER_FIRED_BY_TRUNCATE(trigdata->tg_event))
+	{
+		ExecuteTruncateGuts(list_make1(matviewRel), list_make1_oid(matviewOid),
+							NIL, DROP_RESTRICT, false, false);
+
+		/* Clean up hash entry and delete tuplestores */
+		clean_up_IVM_hash_entry(entry, false, InvalidSubTransactionId);
+
+		/* Pop the original snapshot. */
+		if (!IsolationUsesXactSnapshot())
+			PopActiveSnapshot();
+
+		table_close(matviewRel, NoLock);
+
+		/* Roll back any GUC changes */
+		AtEOXact_GUC(false, save_nestlevel);
+
+		/* Restore userid and security context */
+		SetUserIdAndSecContext(save_userid, save_sec_context);
+
+		return PointerGetDatum(NULL);
+	}
+
+	/*
+	 * rewrite query for calculating deltas
+	 */
+
+	rewritten = copyObject(query);
+
+	/* Replace resnames in a target list with materialized view's attnames */
+	i = 0;
+	foreach (lc, rewritten->targetList)
+	{
+		TargetEntry *tle = (TargetEntry *) lfirst(lc);
+		Form_pg_attribute attr = TupleDescAttr(matviewRel->rd_att, i);
+		char *resname = NameStr(attr->attname);
+
+		tle->resname = pstrdup(resname);
+		i++;
+	}
+
+	/* Set all tables in the query to pre-update state */
+	rewritten = rewrite_query_for_preupdate_state(rewritten, entry->tables,
+												  pstate, matviewOid);
+	/* Rewrite for counting duplicated tuples */
+	rewritten = rewrite_query_for_counting(rewritten, pstate);
+
+	/* Create tuplestores to store view deltas */
+	if (entry->has_old)
+	{
+		oldcxt = MemoryContextSwitchTo(TopTransactionContext);
+
+		old_tuplestore = tuplestore_begin_heap(false, false, work_mem);
+		dest_old = CreateDestReceiver(DestTuplestore);
+		SetTuplestoreDestReceiverParams(dest_old,
+									old_tuplestore,
+									TopTransactionContext,
+									false,
+									NULL,
+									NULL);
+
+		MemoryContextSwitchTo(oldcxt);
+	}
+	if (entry->has_new)
+	{
+		oldcxt = MemoryContextSwitchTo(TopTransactionContext);
+
+		new_tuplestore = tuplestore_begin_heap(false, false, work_mem);
+		dest_new = CreateDestReceiver(DestTuplestore);
+		SetTuplestoreDestReceiverParams(dest_new,
+									new_tuplestore,
+									TopTransactionContext,
+									false,
+									NULL,
+									NULL);
+		MemoryContextSwitchTo(oldcxt);
+	}
+
+	/* for all modified tables */
+	foreach(lc, entry->tables)
+	{
+		ListCell *lc2;
+
+		table = (MV_TriggerTable *) lfirst(lc);
+
+		/* loop for self-join */
+		foreach(lc2, table->rte_indexes)
+		{
+			int	rte_index = lfirst_int(lc2);
+			TupleDesc		tupdesc_old;
+			TupleDesc		tupdesc_new;
+
+			/* calculate delta tables */
+			calc_delta(table, rte_index, rewritten, dest_old, dest_new,
+					   &tupdesc_old, &tupdesc_new, queryEnv);
+
+			/* Set the table in the query to post-update state */
+			rewritten = rewrite_query_for_postupdate_state(rewritten, table, rte_index);
+
+			PG_TRY();
+			{
+				/* apply the delta tables to the materialized view */
+				apply_delta(matviewOid, old_tuplestore, new_tuplestore,
+							tupdesc_old, tupdesc_new, query);
+			}
+			PG_CATCH();
+			{
+				matview_maintenance_depth = old_depth;
+				PG_RE_THROW();
+			}
+			PG_END_TRY();
+
+			/* clear view delta tuplestores */
+			if (old_tuplestore)
+				tuplestore_clear(old_tuplestore);
+			if (new_tuplestore)
+				tuplestore_clear(new_tuplestore);
+		}
+	}
+
+	/* Clean up hash entry and delete tuplestores */
+	clean_up_IVM_hash_entry(entry, false, InvalidSubTransactionId);
+	if (old_tuplestore)
+	{
+		dest_old->rDestroy(dest_old);
+		tuplestore_end(old_tuplestore);
+	}
+	if (new_tuplestore)
+	{
+		dest_new->rDestroy(dest_new);
+		tuplestore_end(new_tuplestore);
+	}
+
+	/* Pop the original snapshot. */
+	if (!IsolationUsesXactSnapshot())
+		PopActiveSnapshot();
+
+	table_close(matviewRel, NoLock);
+
+	/* Roll back any GUC changes */
+	AtEOXact_GUC(false, save_nestlevel);
+
+	/* Restore userid and security context */
+	SetUserIdAndSecContext(save_userid, save_sec_context);
+
+	return PointerGetDatum(NULL);
+}
+
+/*
+ * rewrite_query_for_preupdate_state
+ *
+ * Rewrite the query so that base tables' RTEs will represent "pre-update"
+ * state of tables. This is necessary to calculate view delta after multiple
+ * tables are modified.
+ */
+static Query*
+rewrite_query_for_preupdate_state(Query *query, List *tables,
+								  ParseState *pstate, Oid matviewid)
+{
+	ListCell *lc;
+	int num_rte = list_length(query->rtable);
+	int i;
+
+
+	/* register delta ENRs */
+	register_delta_ENRs(pstate, query, tables);
+
+	/* XXX: Is necessary? Is this right timing? */
+	AcquireRewriteLocks(query, true, false);
+
+	i = 1;
+	foreach(lc, query->rtable)
+	{
+		RangeTblEntry *r = (RangeTblEntry*) lfirst(lc);
+
+		ListCell *lc2;
+		foreach(lc2, tables)
+		{
+			MV_TriggerTable *table = (MV_TriggerTable *) lfirst(lc2);
+			/*
+			 * if the modified table is found then replace the original RTE with
+			 * "pre-state" RTE and append its index to the list.
+			 */
+			if (r->relid == table->table_id)
+			{
+				List *securityQuals;
+				List *withCheckOptions;
+				bool  hasRowSecurity;
+				bool  hasSubLinks;
+
+				RangeTblEntry *rte_pre = get_prestate_rte(r, table, pstate->p_queryEnv, matviewid);
+
+				/*
+				 * Set a row security poslicies of the modified table to the subquery RTE which
+				 * represents the pre-update state of the table.
+				 */
+				get_row_security_policies(query, table->original_rte, i,
+										  &securityQuals, &withCheckOptions,
+										  &hasRowSecurity, &hasSubLinks);
+
+				if (hasRowSecurity)
+				{
+					query->hasRowSecurity = true;
+					rte_pre->security_barrier = true;
+				}
+				if (hasSubLinks)
+					query->hasSubLinks = true;
+
+				rte_pre->securityQuals = securityQuals;
+				lfirst(lc) = rte_pre;
+
+				table->rte_indexes = lappend_int(table->rte_indexes, i);
+				break;
+			}
+		}
+
+		/* finish the loop if we processed all RTE included in the original query */
+		if (i++ >= num_rte)
+			break;
+	}
+
+	return query;
+}
+
+/*
+ * register_delta_ENRs
+ *
+ * For all modified tables, make ENRs for their transition tables
+ * and register them to the queryEnv. ENR's RTEs are also appended
+ * into the list in query tree.
+ */
+static void
+register_delta_ENRs(ParseState *pstate, Query *query, List *tables)
+{
+	QueryEnvironment *queryEnv = pstate->p_queryEnv;
+	ListCell *lc;
+	RangeTblEntry	*rte;
+
+	foreach(lc, tables)
+	{
+		MV_TriggerTable *table = (MV_TriggerTable *) lfirst(lc);
+		ListCell *lc2;
+		int count;
+
+		count = 0;
+		foreach(lc2, table->old_tuplestores)
+		{
+			Tuplestorestate *oldtable = (Tuplestorestate *) lfirst(lc2);
+			EphemeralNamedRelation enr =
+				palloc(sizeof(EphemeralNamedRelationData));
+			ParseNamespaceItem *nsitem;
+
+			enr->md.name = make_delta_enr_name("old", table->table_id, count);
+			enr->md.reliddesc = table->table_id;
+			enr->md.tupdesc = NULL;
+			enr->md.enrtype = ENR_NAMED_TUPLESTORE;
+			enr->md.enrtuples = tuplestore_tuple_count(oldtable);
+			enr->reldata = oldtable;
+			register_ENR(queryEnv, enr);
+
+			nsitem = addRangeTableEntryForENR(pstate, makeRangeVar(NULL, enr->md.name, -1), true);
+			rte = nsitem->p_rte;
+
+			query->rtable = lappend(query->rtable, rte);
+
+			count++;
+		}
+
+		count = 0;
+		foreach(lc2, table->new_tuplestores)
+		{
+			Tuplestorestate *newtable = (Tuplestorestate *) lfirst(lc2);
+			EphemeralNamedRelation enr =
+				palloc(sizeof(EphemeralNamedRelationData));
+			ParseNamespaceItem *nsitem;
+
+			enr->md.name = make_delta_enr_name("new", table->table_id, count);
+			enr->md.reliddesc = table->table_id;
+			enr->md.tupdesc = NULL;
+			enr->md.enrtype = ENR_NAMED_TUPLESTORE;
+			enr->md.enrtuples = tuplestore_tuple_count(newtable);
+			enr->reldata = newtable;
+			register_ENR(queryEnv, enr);
+
+			nsitem = addRangeTableEntryForENR(pstate, makeRangeVar(NULL, enr->md.name, -1), true);
+			rte = nsitem->p_rte;
+
+			query->rtable = lappend(query->rtable, rte);
+
+			count++;
+		}
+	}
+}
+
+#define DatumGetItemPointer(X)	 ((ItemPointer) DatumGetPointer(X))
+#define PG_GETARG_ITEMPOINTER(n) DatumGetItemPointer(PG_GETARG_DATUM(n))
+
+/*
+ * ivm_visible_in_prestate
+ *
+ * Check visibility of a tuple specified by the tableoid and item pointer
+ * using the snapshot taken just before the table was modified.
+ */
+Datum
+ivm_visible_in_prestate(PG_FUNCTION_ARGS)
+{
+	Oid			tableoid = PG_GETARG_OID(0);
+	ItemPointer itemPtr = PG_GETARG_ITEMPOINTER(1);
+	Oid			matviewOid = PG_GETARG_OID(2);
+	MV_TriggerHashEntry *entry;
+	MV_TriggerTable		*table = NULL;
+	ListCell   *lc;
+	bool	found;
+	bool	result;
+
+	if (!in_delta_calculation)
+		ereport(ERROR,
+				(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+				 errmsg("ivm_visible_in_prestate can be called only in delta calculation")));
+
+	entry = (MV_TriggerHashEntry *) hash_search(mv_trigger_info,
+											  (void *) &matviewOid,
+											  HASH_FIND, &found);
+	Assert (found && entry != NULL);
+
+	foreach(lc, entry->tables)
+	{
+		table = (MV_TriggerTable *) lfirst(lc);
+		if (table->table_id == tableoid)
+			break;
+	}
+
+	Assert (table != NULL);
+
+	result = table_tuple_fetch_row_version(table->rel, itemPtr, entry->snapshot, table->slot);
+
+	PG_RETURN_BOOL(result);
+}
+
+/*
+ * get_prestate_rte
+ *
+ * Rewrite RTE of the modified table to a subquery which represents
+ * "pre-state" table. The original RTE is saved in table->rte_original.
+ */
+static RangeTblEntry*
+get_prestate_rte(RangeTblEntry *rte, MV_TriggerTable *table,
+				 QueryEnvironment *queryEnv, Oid matviewid)
+{
+	StringInfoData str;
+	RawStmt *raw;
+	Query *subquery;
+	ParseState *pstate;
+	char *relname;
+	static char *subquery_tl;
+	int i;
+
+	pstate = make_parsestate(NULL);
+	pstate->p_queryEnv = queryEnv;
+	pstate->p_expr_kind = EXPR_KIND_SELECT_TARGET;
+
+	relname = quote_qualified_identifier(
+					get_namespace_name(RelationGetNamespace(table->rel)),
+									   RelationGetRelationName(table->rel));
+
+	subquery_tl = make_subquery_targetlist_from_table(table);
+
+	/*
+	 * Filtering inserted row using the snapshot taken before the table
+	 * is modified. ctid is required for maintaining outer join views.
+	 */
+	initStringInfo(&str);
+	appendStringInfo(&str,
+		"SELECT %s FROM %s t"
+		" WHERE pg_catalog.ivm_visible_in_prestate(t.tableoid, t.ctid ,%d::pg_catalog.oid)",
+			subquery_tl, relname, matviewid);
+
+	/*
+	 * Re-add rows deleted from the old transition tables, excluding those
+	 * also present in the new transition tables.
+	 */
+	if (list_length(table->old_tuplestores) > 0)
+	{
+		appendStringInfo(&str," UNION ALL SELECT %s  FROM (",
+			subquery_tl);
+
+		for (i = 0; i < list_length(table->old_tuplestores); i++)
+		{
+			if (i != 0)
+				appendStringInfo(&str, " UNION ALL ");
+			appendStringInfo(&str," TABLE %s",
+				make_delta_enr_name("old", table->table_id, i));
+		}
+		for (i = 0; i < list_length(table->new_tuplestores); i++)
+		{
+			appendStringInfo(&str, " EXCEPT ALL ");
+			appendStringInfo(&str," TABLE %s",
+				make_delta_enr_name("new", table->table_id, i));
+		}
+		appendStringInfo(&str,")");
+	}
+
+	/* Get a subquery representing pre-state of the table */
+	raw = (RawStmt*)linitial(raw_parser(str.data, RAW_PARSE_DEFAULT));
+	subquery = transformStmt(pstate, raw->stmt);
+
+	/* save the original RTE */
+	table->original_rte = copyObject(rte);
+
+	rte->rtekind = RTE_SUBQUERY;
+	rte->subquery = subquery;
+	rte->security_barrier = false;
+
+	/* Clear fields that should not be set in a subquery RTE */
+	rte->relid = InvalidOid;
+	rte->relkind = 0;
+	rte->rellockmode = 0;
+	rte->tablesample = NULL;
+	rte->perminfoindex = 0;         /* no permission checking for this RTE */
+	rte->inh = false;			/* must not be set for a subquery */
+
+	return rte;
+}
+
+/*
+ * make_subquery_targetlist_from_table
+ *
+ * Make a targetlist string of a subquery representing a delta table or a
+ * pre-update state table. This subquery substitutes a modified table RTE
+ * in the view definition query during view maintenance. In the targetlist,
+ * column names appear in order of the table definition. However, for
+ * attribute numbers of vars in the query tree to reference columns of the
+ * subquery  correctly even though the table has a dropped column, put "null"
+ * as a dummy value at the position of a dropped column.
+ *
+ * We would also able to walk the query tree to rewrite varattnos, but
+ * crafting targetlist is more simple and reasonable.
+ */
+static char*
+make_subquery_targetlist_from_table(MV_TriggerTable *table)
+{
+	StringInfoData str;
+	TupleDesc	tupdesc;
+	int			i;
+
+	tupdesc = RelationGetDescr(table->rel);
+	initStringInfo(&str);
+	for (i = 0; i < tupdesc->natts; i++)
+	{
+		Form_pg_attribute attr = TupleDescAttr(tupdesc, i);
+
+		if (i > 0)
+			appendStringInfo(&str, ", ");
+
+		if (attr->attisdropped)
+			appendStringInfo(&str, "null");
+		else
+			appendStringInfo(&str, "%s", quote_identifier(NameStr(attr->attname)));
+	}
+
+	return str.data;
+}
+
+/*
+ * make_delta_enr_name
+ *
+ * Make a name for ENR of a transition table from the base table's oid.
+ * prefix will be "new" or "old" depending on its transition table kind..
+ */
+static char*
+make_delta_enr_name(const char *prefix, Oid relid, int count)
+{
+	char buf[NAMEDATALEN];
+	char *name;
+
+	snprintf(buf, NAMEDATALEN, "__ivm_%s_%u_%u", prefix, relid, count);
+	name = pstrdup(buf);
+
+	return name;
+}
+
+/*
+ * makeDeltaTable
+ *
+ * Make a RTE representing a delta of the specified table.
+ */
+static RangeTblEntry*
+makeDeltaTable(RangeTblEntry *rte, MV_TriggerTable *table,
+		   bool is_new, QueryEnvironment *queryEnv)
+{
+	StringInfoData str;
+	ParseState	*pstate;
+	RawStmt *raw;
+	Query *sub;
+	int		i;
+
+	const char *prefix_union = is_new ? "new" : "old";
+	const char *prefix_except = is_new ? "old" : "new";
+	int num_union = is_new ? list_length(table->new_tuplestores) : list_length(table->old_tuplestores);
+	int num_except = is_new ? list_length(table->old_tuplestores) : list_length(table->new_tuplestores);
+
+	/* the previous RTE must be a subquery which represents "pre-state" table */
+	Assert(rte->rtekind == RTE_SUBQUERY);
+
+	/* Create a ParseState for rewriting the view definition query */
+	pstate = make_parsestate(NULL);
+	pstate->p_queryEnv = queryEnv;
+	pstate->p_expr_kind = EXPR_KIND_NONE;
+
+	initStringInfo(&str);
+	appendStringInfo(&str,
+		" SELECT %s FROM ( ",
+		make_subquery_targetlist_from_table(table));
+
+	for (i = 0; i < num_union; i++)
+	{
+		if (i > 0)
+			appendStringInfo(&str, " UNION ALL ");
+
+		appendStringInfo(&str,
+			" TABLE  %s",
+			make_delta_enr_name(prefix_union, table->table_id, i));
+	}
+	for (i = 0; i < num_except; i++)
+	{
+		appendStringInfo(&str, " EXCEPT ALL ");
+
+		appendStringInfo(&str,
+			" TABLE  %s",
+			make_delta_enr_name(prefix_except, table->table_id, i));
+	}
+	appendStringInfo(&str,")");
+
+	raw = (RawStmt*)linitial(raw_parser(str.data, RAW_PARSE_DEFAULT));
+	sub = transformStmt(pstate, raw->stmt);
+
+	/*
+	 * Update the subquery so that it represent the combined transition
+	 * table.  Note that we leave the security_barrier and securityQuals
+	 * fields so that the subquery relation can be protected by the RLS
+	 * policy as same as the modified table.
+	 */
+	rte->rtekind = RTE_SUBQUERY;
+	rte->subquery = sub;
+
+	return rte;
+}
+
+/*
+ * rewrite_query_for_counting
+ *
+ * Rewrite query for counting duplicated tuples.
+ */
+static Query *
+rewrite_query_for_counting(Query *query, ParseState *pstate)
+{
+	TargetEntry *tle_count;
+	FuncCall *fn;
+	Node *node;
+
+	/* Add count(*) for counting distinct tuples in views */
+	fn = makeFuncCall(SystemFuncName("count"), NIL, COERCE_EXPLICIT_CALL, -1);
+	fn->agg_star = true;
+	if (!query->groupClause && !query->hasAggs)
+		query->groupClause = transformDistinctClause(NULL, &query->targetList, query->sortClause, false);
+
+	node = ParseFuncOrColumn(pstate, fn->funcname, NIL, NULL, fn, false, -1);
+
+	tle_count = makeTargetEntry((Expr *) node,
+								list_length(query->targetList) + 1,
+								pstrdup("__ivm_count__"),
+								false);
+	query->targetList = lappend(query->targetList, tle_count);
+	query->hasAggs = true;
+
+	return query;
+}
+
+/*
+ * calc_delta
+ *
+ * Calculate view deltas generated under the modification of a table specified
+ * by the RTE index.
+ */
+static void
+calc_delta(MV_TriggerTable *table, int rte_index, Query *query,
+			DestReceiver *dest_old, DestReceiver *dest_new,
+			TupleDesc *tupdesc_old, TupleDesc *tupdesc_new,
+			QueryEnvironment *queryEnv)
+{
+	ListCell *lc = list_nth_cell(query->rtable, rte_index - 1);
+	RangeTblEntry *rte = (RangeTblEntry *) lfirst(lc);
+
+	in_delta_calculation = true;
+
+	/* Generate old delta */
+	if (dest_old && list_length(table->old_tuplestores) > 0)
+	{
+		/* Replace the modified table with the old delta table and calculate the old view delta. */
+		lfirst(lc) = makeDeltaTable(rte, table, false, queryEnv);
+		refresh_matview_datafill(dest_old, query, queryEnv, tupdesc_old, "", false);
+	}
+
+	/* Generate new delta */
+	if (dest_new && list_length(table->new_tuplestores) > 0)
+	{
+		/* Replace the modified table with the new delta table and calculate the new view delta*/
+		lfirst(lc) = makeDeltaTable(rte, table, true, queryEnv);
+		refresh_matview_datafill(dest_new, query, queryEnv, tupdesc_new, "", false);
+	}
+
+	in_delta_calculation = false;
+}
+
+/*
+ * rewrite_query_for_postupdate_state
+ *
+ * Rewrite the query so that the specified base table's RTEs will represent
+ * "post-update" state of tables. This is called after the view delta
+ * calculation due to changes on this table finishes.
+ */
+static Query*
+rewrite_query_for_postupdate_state(Query *query, MV_TriggerTable *table, int rte_index)
+{
+	ListCell *lc = list_nth_cell(query->rtable, rte_index - 1);
+
+	/* Retore the original RTE */
+	lfirst(lc) = table->original_rte;
+
+	return query;
+}
+
+/*
+ * apply_delta
+ *
+ * Apply deltas to the materialized view. In outer join cases, this requires
+ * the view maintenance graph.
+ */
+static void
+apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *new_tuplestores,
+			TupleDesc tupdesc_old, TupleDesc tupdesc_new,
+			Query *query)
+{
+	StringInfoData querybuf;
+	StringInfoData target_list_buf;
+	Relation	matviewRel;
+	char	   *matviewname;
+	ListCell	*lc;
+	int			i;
+	List	   *keys = NIL;
+
+
+	/*
+	 * get names of the materialized view and delta tables
+	 */
+
+	matviewRel = table_open(matviewOid, NoLock);
+	matviewname = quote_qualified_identifier(get_namespace_name(RelationGetNamespace(matviewRel)),
+											 RelationGetRelationName(matviewRel));
+
+	/*
+	 * Build parts of the maintenance queries
+	 */
+
+	initStringInfo(&querybuf);
+	initStringInfo(&target_list_buf);
+
+	/* build string of target list */
+	for (i = 0; i < matviewRel->rd_att->natts; i++)
+	{
+		Form_pg_attribute attr = TupleDescAttr(matviewRel->rd_att, i);
+		char   *resname = NameStr(attr->attname);
+
+		if (i != 0)
+			appendStringInfo(&target_list_buf, ", ");
+		appendStringInfo(&target_list_buf, "%s", quote_qualified_identifier(NULL, resname));
+	}
+
+	i = 0;
+	foreach (lc, query->targetList)
+	{
+		TargetEntry *tle = (TargetEntry *) lfirst(lc);
+		Form_pg_attribute attr = TupleDescAttr(matviewRel->rd_att, i);
+
+		i++;
+
+		if (tle->resjunk)
+			continue;
+
+		keys = lappend(keys, attr);
+	}
+
+	/* Start maintaining the materialized view. */
+	OpenMatViewIncrementalMaintenance();
+
+	/* Open SPI context. */
+	if (SPI_connect() != SPI_OK_CONNECT)
+		elog(ERROR, "SPI_connect failed");
+
+	/* For tuple deletion */
+	if (old_tuplestores && tuplestore_tuple_count(old_tuplestores) > 0)
+	{
+		EphemeralNamedRelation enr = palloc(sizeof(EphemeralNamedRelationData));
+		int				rc;
+
+		/* convert tuplestores to ENR, and register for SPI */
+		enr->md.name = pstrdup(OLD_DELTA_ENRNAME);
+		enr->md.reliddesc = InvalidOid;
+		enr->md.tupdesc = tupdesc_old;
+		enr->md.enrtype = ENR_NAMED_TUPLESTORE;
+		enr->md.enrtuples = tuplestore_tuple_count(old_tuplestores);
+		enr->reldata = old_tuplestores;
+
+		rc = SPI_register_relation(enr);
+		if (rc != SPI_OK_REL_REGISTER)
+			elog(ERROR, "SPI_register failed");
+
+		apply_old_delta(matviewname, OLD_DELTA_ENRNAME, keys);
+
+	}
+	/* For tuple insertion */
+	if (new_tuplestores && tuplestore_tuple_count(new_tuplestores) > 0)
+	{
+		EphemeralNamedRelation enr = palloc(sizeof(EphemeralNamedRelationData));
+		int rc;
+
+		/* convert tuplestores to ENR, and register for SPI */
+		enr->md.name = pstrdup(NEW_DELTA_ENRNAME);
+		enr->md.reliddesc = InvalidOid;
+		enr->md.tupdesc = tupdesc_new;;
+		enr->md.enrtype = ENR_NAMED_TUPLESTORE;
+		enr->md.enrtuples = tuplestore_tuple_count(new_tuplestores);
+		enr->reldata = new_tuplestores;
+
+		rc = SPI_register_relation(enr);
+		if (rc != SPI_OK_REL_REGISTER)
+			elog(ERROR, "SPI_register failed");
+
+		/* apply new delta */
+		apply_new_delta(matviewname, NEW_DELTA_ENRNAME, &target_list_buf);
+	}
+
+	/* We're done maintaining the materialized view. */
+	CloseMatViewIncrementalMaintenance();
+
+	table_close(matviewRel, NoLock);
+
+	/* Close SPI context. */
+	if (SPI_finish() != SPI_OK_FINISH)
+		elog(ERROR, "SPI_finish failed");
+}
+
+/*
+ * apply_old_delta
+ *
+ * Execute a query for applying a delta table given by deltname_old
+ * which contains tuples to be deleted from to a materialized view given by
+ * matviewname.  This is used when counting is not required.
+ */
+static void
+apply_old_delta(const char *matviewname, const char *deltaname_old,
+				List *keys)
+{
+	StringInfoData	querybuf;
+	StringInfoData	keysbuf;
+	char   *match_cond;
+	ListCell *lc;
+
+	/* build WHERE condition for searching tuples to be deleted */
+	match_cond = get_matching_condition_string(keys);
+
+	/* build string of keys list */
+	initStringInfo(&keysbuf);
+	foreach (lc, keys)
+	{
+		Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc);
+		char   *resname = NameStr(attr->attname);
+		appendStringInfo(&keysbuf, "%s", quote_qualified_identifier("mv", resname));
+		if (lnext(keys, lc))
+			appendStringInfo(&keysbuf, ", ");
+	}
+
+	/* Search for matching tuples from the view and update or delete if found. */
+	initStringInfo(&querybuf);
+	appendStringInfo(&querybuf,
+	"DELETE FROM %s WHERE ctid IN ("
+		"SELECT tid FROM (SELECT pg_catalog.row_number() over (partition by %s) AS \"__ivm_row_number__\","
+								  "mv.ctid AS tid,"
+								  "diff.\"__ivm_count__\""
+						 "FROM %s AS mv, %s AS diff "
+						 "WHERE %s) v "
+					"WHERE v.\"__ivm_row_number__\" OPERATOR(pg_catalog.<=) v.\"__ivm_count__\")",
+					matviewname,
+					keysbuf.data,
+					matviewname, deltaname_old,
+					match_cond);
+
+	if (SPI_exec(querybuf.data, 0) != SPI_OK_DELETE)
+		elog(ERROR, "SPI_exec failed: %s", querybuf.data);
+}
+
+/*
+ * apply_new_delta
+ *
+ * Execute a query for applying a delta table given by deltname_new
+ * which contains tuples to be inserted into a materialized view given by
+ * matviewname.  This is used when counting is not required.
+ */
+static void
+apply_new_delta(const char *matviewname, const char *deltaname_new,
+				StringInfo target_list)
+{
+	StringInfoData	querybuf;
+
+	/* Search for matching tuples from the view and update or delete if found. */
+	initStringInfo(&querybuf);
+	appendStringInfo(&querybuf,
+					"INSERT INTO %s (%s) SELECT %s FROM ("
+						"SELECT diff.*, pg_catalog.generate_series(1, diff.\"__ivm_count__\")"
+							" AS __ivm_generate_series__ "
+						"FROM %s AS diff) AS v",
+					matviewname, target_list->data, target_list->data,
+					deltaname_new);
+
+	if (SPI_exec(querybuf.data, 0) != SPI_OK_INSERT)
+		elog(ERROR, "SPI_exec failed: %s", querybuf.data);
+}
+
+/*
+ * get_matching_condition_string
+ *
+ * Build a predicate string for looking for a tuple with given keys.
+ */
+static char *
+get_matching_condition_string(List *keys)
+{
+	StringInfoData match_cond;
+	ListCell	*lc;
+
+	/* If there is no key columns, the condition is always true. */
+	if (keys == NIL)
+		return "true";
+
+	initStringInfo(&match_cond);
+	foreach (lc, keys)
+	{
+		Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc);
+		char   *resname = NameStr(attr->attname);
+		char   *mv_resname = quote_qualified_identifier("mv", resname);
+		char   *diff_resname = quote_qualified_identifier("diff", resname);
+		Oid		typid = attr->atttypid;
+
+		/* Considering NULL values, we can not use simple = operator. */
+		appendStringInfo(&match_cond, "(");
+		generate_equal(&match_cond, typid, mv_resname, diff_resname);
+		appendStringInfo(&match_cond, " OR (%s IS NULL AND %s IS NULL))",
+						 mv_resname, diff_resname);
+
+		if (lnext(keys, lc))
+			appendStringInfo(&match_cond, " AND ");
+	}
+
+	return match_cond.data;
+}
+
+/*
+ * generate_equals
+ *
+ * Generate an equality clause using given operands' default equality
+ * operator.
+ */
+static void
+generate_equal(StringInfo querybuf, Oid opttype,
+			   const char *leftop, const char *rightop)
+{
+	TypeCacheEntry *typentry;
+
+	typentry = lookup_type_cache(opttype, TYPECACHE_EQ_OPR);
+	if (!OidIsValid(typentry->eq_opr))
+		ereport(ERROR,
+				(errcode(ERRCODE_UNDEFINED_FUNCTION),
+				 errmsg("could not identify an equality operator for type %s",
+						format_type_be_qualified(opttype))));
+
+	generate_operator_clause(querybuf,
+							 leftop, opttype,
+							 typentry->eq_opr,
+							 rightop, opttype);
+}
+
+/*
+ * mv_InitHashTables
+ */
+static void
+mv_InitHashTables(void)
+{
+	HASHCTL		ctl;
+
+	memset(&ctl, 0, sizeof(ctl));
+	ctl.keysize = sizeof(Oid);
+	ctl.entrysize = sizeof(MV_TriggerHashEntry);
+	mv_trigger_info = hash_create("MV trigger info",
+								 MV_INIT_QUERYHASHSIZE,
+								 &ctl, HASH_ELEM | HASH_BLOBS);
+
+	memset(&ctl, 0, sizeof(ctl));
+	ctl.keysize = sizeof(Oid);
+	ctl.entrysize = sizeof(DroppedImmvInfo);
+	dropped_immv = hash_create("Dropped IMMVs", 16,
+							   &ctl, HASH_ELEM | HASH_BLOBS);
+}
+
+/*
+ * AtAbort_IVM
+ *
+ * Clean up hash entries for all materialized views. This is called at
+ * (sub-)transaction abort. When the top-level transaction is aborted,
+ * InvalidSubTransactionId is set to subxid.
+ *
+ * Also, remove dropped IMMV information if it is aborted.
+ */
+void
+AtAbort_IVM(SubTransactionId subxid)
+{
+	HASH_SEQ_STATUS seq;
+
+	if (mv_trigger_info)
+	{
+		MV_TriggerHashEntry *entry;
+		hash_seq_init(&seq, mv_trigger_info);
+		while ((entry = hash_seq_search(&seq)) != NULL)
+			clean_up_IVM_hash_entry(entry, true, subxid);
+	}
+
+	if (dropped_immv)
+	{
+		DroppedImmvInfo *entry;
+		hash_seq_init(&seq, dropped_immv);
+		while ((entry = hash_seq_search(&seq)) != NULL)
+		{
+			if (subxid == InvalidSubTransactionId || subxid == entry->subxid)
+				hash_search(dropped_immv, (void *) &entry->immv_oid, HASH_REMOVE, NULL);
+		}
+	}
+
+	in_delta_calculation = false;
+}
+
+/*
+ * AtPreCommit_IVM
+ *
+ * Record the transaction ID that updated the view incrementally.
+ * Also, remove the entry for dropped IMMVs.
+ */
+void
+AtPreCommit_IVM(void)
+{
+	HASH_SEQ_STATUS seq;
+
+	if (mv_trigger_info)
+	{
+		MV_TriggerHashEntry *entry;
+
+		/*
+		 * Record the transaction ID that udpate the view incrementally,
+		 * and perform the final clean up of the entry.
+		 */
+		hash_seq_init(&seq, mv_trigger_info);
+		while ((entry = hash_seq_search(&seq)) != NULL)
+		{
+			setLastUpdateXid(entry->matview_id, GetTopFullTransactionId());
+			hash_search(mv_trigger_info, (void *) &entry->matview_id, HASH_REMOVE, NULL);
+		}
+	}
+
+	if (dropped_immv)
+	{
+		DroppedImmvInfo *entry;
+
+		LWLockAcquire(IvmControlLock, LW_EXCLUSIVE);
+		hash_seq_init(&seq, dropped_immv);
+		while ((entry = hash_seq_search(&seq)) != NULL)
+		{
+			hash_search(LastIvmUpdateHash, (void *) &entry->immv_oid, HASH_REMOVE, NULL);
+			hash_search(dropped_immv, (void *) &entry->immv_oid, HASH_REMOVE, NULL);
+		}
+		LWLockRelease(IvmControlLock);
+	}
+
+	in_delta_calculation = false;
+}
+
+/*
+ * clean_up_IVM_hash_entry
+ *
+ * Clean up tuple stores and hash entries for a materialized view after its
+ * maintenance finished. This is called at the end of table modifying query
+ * or (sub-)transaction abort. When the top-level transaction is aborted,
+ * InvalidSubTransactionId is set to subxid.
+ */
+static void
+clean_up_IVM_hash_entry(MV_TriggerHashEntry *entry, bool is_abort,
+						SubTransactionId subxid)
+{
+	bool found;
+	ListCell *lc;
+
+	/* clean up tuple stores */
+	foreach(lc, entry->tables)
+	{
+		MV_TriggerTable *table = (MV_TriggerTable *) lfirst(lc);
+
+		list_free(table->old_tuplestores);
+		list_free(table->new_tuplestores);
+		if (!is_abort)
+		{
+			ExecDropSingleTupleTableSlot(table->slot);
+			table_close(table->rel, NoLock);
+		}
+	}
+	list_free(entry->tables);
+	entry->tables = NIL;
+
+	if (is_abort)
+	{
+		bool	remove_entry = false;
+
+		/*
+		 * When the top-level transaction is aborted, remove all subxids.
+		 * When a sub-transaction is aborted, remove only its subxid.
+		 */
+		if (subxid == InvalidSubTransactionId)
+			remove_entry = true;
+		else
+		{
+			foreach(lc, entry->subxids)
+			{
+				if (lfirst_xid(lc) == subxid)
+				{
+					entry->subxids = list_delete_cell(entry->subxids, lc);
+					break;
+				}
+			}
+
+			/*
+			 * If all the subxid are removed, it means that the view was not
+			 * updated at all in this transaction.
+			 */
+			if (list_length(entry->subxids) == 0)
+				remove_entry = true;
+		}
+
+		/*
+		 * Remove entries of not updated views from the hash table.
+		 */
+		if (remove_entry)
+			hash_search(mv_trigger_info, (void *) &entry->matview_id, HASH_REMOVE, &found);
+	}
+	else
+	{
+		/* When the query sucsessully finished, unregister the snapshot */
+		UnregisterSnapshot(entry->snapshot);
+	}
+
+	entry->snapshot = InvalidSnapshot;
+}
+
+/*
+ * setLastUpdateXid
+ *
+ * Store the transaction ID that updated the view incremenally.
+ */
+static void
+setLastUpdateXid(Oid immv_oid, FullTransactionId xid)
+{
+	LastIvmUpdateEntry *entry;
+
+	LWLockAcquire(IvmControlLock, LW_EXCLUSIVE);
+	entry = (LastIvmUpdateEntry *) hash_search(LastIvmUpdateHash, (void *) &immv_oid, HASH_ENTER, NULL);
+	entry->oid = immv_oid;
+	entry->last_ivm_update = xid;
+	LWLockRelease(IvmControlLock);
+}
+
+/*
+ * getLastUpdateXid
+ *
+ * Get the most recent transaction ID that updated the view incrementally.
+ */
+static FullTransactionId
+getLastUpdateXid(Oid immv_oid)
+{
+	FullTransactionId xid = InvalidFullTransactionId;
+	LastIvmUpdateEntry *entry;
+	bool found;
+
+	LWLockAcquire(IvmControlLock, LW_SHARED);
+	entry = (LastIvmUpdateEntry *) hash_search(LastIvmUpdateHash, (void *) &immv_oid, HASH_FIND, &found);
+	LWLockRelease(IvmControlLock);
+	if (found)
+		xid = entry->last_ivm_update;
+
+	return xid;
+}
+
+void
+removeImmv(Oid immv_oid)
+{
+	DroppedImmvInfo *entry;
+
+	if (!dropped_immv)
+		mv_InitHashTables();
+
+	entry = (DroppedImmvInfo *) hash_search(dropped_immv, (void *) &immv_oid, HASH_ENTER, NULL);
+	entry->subxid = GetCurrentSubTransactionId();
+}
+
+/*
+ * isIvmName
+ *
+ * Check if this is a IVM hidden column from the name.
+ */
+bool
+isIvmName(const char *s)
+{
+	if (s)
+		return (strncmp(s, "__ivm_", 6) == 0);
+	return false;
+}
diff --git a/src/backend/commands/tablecmds.c b/src/backend/commands/tablecmds.c
index 95abaf4890c..95e974e1138 100644
--- a/src/backend/commands/tablecmds.c
+++ b/src/backend/commands/tablecmds.c
@@ -62,6 +62,7 @@
 #include "commands/defrem.h"
 #include "commands/event_trigger.h"
 #include "commands/extension.h"
+#include "commands/matview.h"
 #include "commands/repack.h"
 #include "commands/sequence.h"
 #include "commands/tablecmds.h"
@@ -1811,6 +1812,9 @@ RangeVarCallbackForDropRelation(const RangeVar *rel, Oid relOid, Oid oldRelOid,
 	state->actual_relkind = classform->relkind;
 	state->actual_relpersistence = classform->relpersistence;
 
+	if (classform->relkind == RELKIND_MATVIEW && classform->relisivm)
+		removeImmv(relOid);
+
 	/*
 	 * Both RELKIND_RELATION and RELKIND_PARTITIONED_TABLE are OBJECT_TABLE,
 	 * but RemoveRelations() can only pass one relkind for a given relation.
diff --git a/src/backend/utils/activity/wait_event_names.txt b/src/backend/utils/activity/wait_event_names.txt
index 560659f9568..d97c35eeef0 100644
--- a/src/backend/utils/activity/wait_event_names.txt
+++ b/src/backend/utils/activity/wait_event_names.txt
@@ -370,6 +370,7 @@ WaitLSN	"Waiting to read or update shared Wait-for-LSN state."
 LogicalDecodingControl	"Waiting to read or update logical decoding status information."
 DataChecksumsWorker	"Waiting for data checksums worker."
 AioWorkerControl	"Waiting to update AIO worker information."
+IvmControl	"Waiting for read or update IMMV information.."
 
 #
 # END OF PREDEFINED LWLOCKS (DO NOT CHANGE THIS LINE)
diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat
index 3cb84359adf..65a739af22a 100644
--- a/src/include/catalog/pg_proc.dat
+++ b/src/include/catalog/pg_proc.dat
@@ -12718,4 +12718,14 @@
   proname => 'hashoid8extended', prorettype => 'int8',
   proargtypes => 'oid8 int8', prosrc => 'hashoid8extended' },
 
+# IVM
+{ oid => '786', descr => 'ivm trigger (before)',
+  proname => 'IVM_immediate_before', provolatile => 'v', prorettype => 'trigger',
+  proargtypes => '', prosrc => 'IVM_immediate_before' },
+{ oid => '787', descr => 'ivm trigger (after)',
+  proname => 'IVM_immediate_maintenance', provolatile => 'v', prorettype => 'trigger',
+  proargtypes => '', prosrc => 'IVM_immediate_maintenance' },
+{ oid => '788', descr => 'ivm filetring ',
+  proname => 'ivm_visible_in_prestate', provolatile => 's', prorettype => 'bool',
+  proargtypes => 'oid tid oid', prosrc => 'ivm_visible_in_prestate' },
 ]
diff --git a/src/include/commands/createas.h b/src/include/commands/createas.h
index f895c67c0c2..c286ebcd70e 100644
--- a/src/include/commands/createas.h
+++ b/src/include/commands/createas.h
@@ -16,6 +16,7 @@
 
 #include "catalog/objectaddress.h"
 #include "nodes/params.h"
+#include "nodes/pathnodes.h"
 #include "parser/parse_node.h"
 #include "tcop/dest.h"
 #include "utils/queryenvironment.h"
@@ -25,6 +26,9 @@ extern ObjectAddress ExecCreateTableAs(ParseState *pstate, CreateTableAsStmt *st
 									   ParamListInfo params, QueryEnvironment *queryEnv,
 									   QueryCompletion *qc);
 
+extern void CreateIvmTriggersOnBaseTables(Query *qry, Oid matviewOid);
+extern void CreateIndexOnIMMV(Query *query, Relation matviewRel);
+
 extern int	GetIntoRelEFlags(IntoClause *intoClause);
 
 extern DestReceiver *CreateIntoRelDestReceiver(IntoClause *intoClause);
diff --git a/src/include/commands/matview.h b/src/include/commands/matview.h
index 738c731c1a9..f1dbfc052c5 100644
--- a/src/include/commands/matview.h
+++ b/src/include/commands/matview.h
@@ -15,6 +15,7 @@
 #define MATVIEW_H
 
 #include "catalog/objectaddress.h"
+#include "fmgr.h"
 #include "nodes/params.h"
 #include "nodes/parsenodes.h"
 #include "tcop/dest.h"
@@ -23,6 +24,8 @@
 
 extern void SetMatViewPopulatedState(Relation relation, bool newstate);
 
+extern void SetMatViewIVMState(Relation relation, bool newstate);
+
 extern ObjectAddress ExecRefreshMatView(RefreshMatViewStmt *stmt, const char *queryString,
 										QueryCompletion *qc);
 extern ObjectAddress RefreshMatViewByOid(Oid matviewOid, bool is_create, bool skipData,
@@ -33,4 +36,12 @@ extern DestReceiver *CreateTransientRelDestReceiver(Oid transientoid);
 
 extern bool MatViewIncrementalMaintenanceIsEnabled(void);
 
+extern Datum IVM_immediate_before(PG_FUNCTION_ARGS);
+extern Datum IVM_immediate_maintenance(PG_FUNCTION_ARGS);
+extern Datum IVM_visible_in_prestate(PG_FUNCTION_ARGS);
+extern void AtAbort_IVM(SubTransactionId subtxid);
+extern void AtPreCommit_IVM(void);
+extern void removeImmv(Oid immv_oid);
+extern bool isIvmName(const char *s);
+
 #endif							/* MATVIEW_H */
diff --git a/src/include/storage/lwlocklist.h b/src/include/storage/lwlocklist.h
index d7eb648bd27..756c63baf97 100644
--- a/src/include/storage/lwlocklist.h
+++ b/src/include/storage/lwlocklist.h
@@ -89,6 +89,7 @@ PG_LWLOCK(54, WaitLSN)
 PG_LWLOCK(55, LogicalDecodingControl)
 PG_LWLOCK(56, DataChecksumsWorker)
 PG_LWLOCK(57, AioWorkerControl)
+PG_LWLOCK(58, IvmControl)
 
 /*
  * There also exist several built-in LWLock tranches.  As with the predefined
diff --git a/src/include/storage/subsystemlist.h b/src/include/storage/subsystemlist.h
index 9ad619080be..481e15d00a1 100644
--- a/src/include/storage/subsystemlist.h
+++ b/src/include/storage/subsystemlist.h
@@ -88,3 +88,6 @@ PG_SHMEM_SUBSYSTEM(DataChecksumsShmemCallbacks)
 
 /* AIO subsystem. This delegates to the method-specific callbacks */
 PG_SHMEM_SUBSYSTEM(AioShmemCallbacks)
+
+/* Incremental View Maintenance */
+PG_SHMEM_SUBSYSTEM(IvmShmemCallbacks)
-- 
2.43.0


--Multipart=_Fri__3_Jul_2026_19_11_16_+0900_CskxSIu_iGcDMEyM
Content-Type: text/x-diff;
 name="v39-0005-Add-Incremental-View-Maintenance-support-to-psql.patch"
Content-Disposition: attachment;
 filename="v39-0005-Add-Incremental-View-Maintenance-support-to-psql.patch"
Content-Transfer-Encoding: 7bit



^ permalink  raw  reply  [nested|flat] 101+ messages in thread

* [PATCH v38 06/11] Add Incremental View Maintenance support
@ 2026-05-29 09:06  Yugo Nagata <[email protected]>
  0 siblings, 0 replies; 101+ messages in thread

From: Yugo Nagata @ 2026-05-29 09:06 UTC (permalink / raw)

In this implementation, AFTER triggers are used to collect
tuplestores containing transition table contents. When multiple tables
are changed, multiple AFTER triggers are invoked, then the final AFTER
trigger performs actual update of the matview. In addition, BEFORE
triggers are also used to handle global information for view
maintenance.

To calculate view deltas, we need both pre-state and post-state of base
tables. Post-update states are available in AFTER trigger, and pre-update
states can be calculated by removing inserted tuples and appending deleted
tuples. Insterted tuples are filtered using the snapshot taken before
table modification, and deleted tuples are contained in the old transition
table.

Incrementally Maintainable Materialized Views (IMMV) can contain
duplicated tuples.

This patch also allows self-join, simultaneous updates of more than
one base table, and multiple updates of the same base table.
---
 src/backend/access/transam/xact.c             |    8 +
 src/backend/commands/createas.c               |  709 +++++++
 src/backend/commands/matview.c                | 1835 ++++++++++++++++-
 src/backend/commands/tablecmds.c              |    4 +
 .../utils/activity/wait_event_names.txt       |    1 +
 src/include/catalog/pg_proc.dat               |   10 +
 src/include/commands/createas.h               |    4 +
 src/include/commands/matview.h                |   11 +
 src/include/storage/lwlocklist.h              |    1 +
 src/include/storage/subsystemlist.h           |    3 +
 10 files changed, 2548 insertions(+), 38 deletions(-)

diff --git a/src/backend/access/transam/xact.c b/src/backend/access/transam/xact.c
index 3a89149016f..0e6cb5493d2 100644
--- a/src/backend/access/transam/xact.c
+++ b/src/backend/access/transam/xact.c
@@ -37,6 +37,7 @@
 #include "catalog/pg_enum.h"
 #include "catalog/storage.h"
 #include "commands/async.h"
+#include "commands/matview.h"
 #include "commands/tablecmds.h"
 #include "commands/trigger.h"
 #include "common/pg_prng.h"
@@ -2322,6 +2323,9 @@ CommitTransaction(void)
 	CallXactCallbacks(is_parallel_worker ? XACT_EVENT_PARALLEL_PRE_COMMIT
 					  : XACT_EVENT_PRE_COMMIT);
 
+	/* Store the transaction ID that updated the view incrementally */
+	AtPreCommit_IVM();
+
 	/*
 	 * If this xact has started any unfinished parallel operation, clean up
 	 * its workers, warning about leaked resources.  (But we don't actually
@@ -2973,6 +2977,7 @@ AbortTransaction(void)
 	AtAbort_Notify();
 	AtEOXact_RelationMap(false, is_parallel_worker);
 	AtAbort_Twophase();
+	AtAbort_IVM(InvalidSubTransactionId);
 
 	/*
 	 * Advertise the fact that we aborted in pg_xact (assuming that we got as
@@ -5304,6 +5309,9 @@ AbortSubTransaction(void)
 
 	UnlockBuffers();
 
+	/* Clean up hash entries for incremental view maintenance */
+	AtAbort_IVM(s->subTransactionId);
+
 	/* Reset WAL record construction state */
 	XLogResetInsertion();
 
diff --git a/src/backend/commands/createas.c b/src/backend/commands/createas.c
index 6dbb831ca89..a499688b79d 100644
--- a/src/backend/commands/createas.c
+++ b/src/backend/commands/createas.c
@@ -29,18 +29,32 @@
 #include "access/tableam.h"
 #include "access/xact.h"
 #include "catalog/namespace.h"
+#include "catalog/index.h"
+#include "catalog/pg_am_d.h"
+#include "catalog/pg_constraint.h"
+#include "catalog/pg_inherits.h"
+#include "catalog/pg_trigger.h"
 #include "catalog/toasting.h"
 #include "commands/createas.h"
+#include "commands/defrem.h"
 #include "commands/matview.h"
 #include "commands/prepare.h"
 #include "commands/tablecmds.h"
+#include "commands/tablespace.h"
+#include "commands/trigger.h"
 #include "commands/view.h"
 #include "executor/execdesc.h"
 #include "executor/executor.h"
+#include "miscadmin.h"
 #include "nodes/makefuncs.h"
 #include "nodes/nodeFuncs.h"
 #include "nodes/queryjumble.h"
+#include "optimizer/optimizer.h"
+#include "optimizer/prep.h"
 #include "parser/analyze.h"
+#include "parser/parser.h"
+#include "parser/parsetree.h"
+#include "parser/parse_clause.h"
 #include "rewrite/rewriteHandler.h"
 #include "tcop/tcopprot.h"
 #include "utils/builtins.h"
@@ -70,6 +84,12 @@ static bool intorel_receive(TupleTableSlot *slot, DestReceiver *self);
 static void intorel_shutdown(DestReceiver *self);
 static void intorel_destroy(DestReceiver *self);
 
+static void CreateIvmTriggersOnBaseTablesRecurse(Query *qry, Node *node, Oid matviewOid,
+									 List **relids, bool ex_lock);
+static void CreateIvmTrigger(Oid relOid, Oid viewOid, int16 type, int16 timing, bool ex_lock);
+static void check_ivm_restriction(Node *node);
+static bool check_ivm_restriction_walker(Node *node, void *context);
+static Bitmapset *get_primary_key_attnos_from_query(Query *query, List **constraintList);
 
 /*
  * create_ctas_internal
@@ -277,6 +297,18 @@ ExecCreateTableAs(ParseState *pstate, CreateTableAsStmt *stmt,
 		into->skipData = true;
 	}
 
+	if (is_matview && into->ivm)
+	{
+		/* check if the query is supported in IMMV definition */
+		if (contain_mutable_functions((Node *) query))
+			ereport(ERROR,
+					(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+					 errmsg("mutable function is not supported on incrementally maintainable materialized view"),
+					 errhint("functions must be marked IMMUTABLE")));
+
+		check_ivm_restriction((Node *) query);
+	}
+
 	if (into->skipData)
 	{
 		/*
@@ -287,15 +319,36 @@ ExecCreateTableAs(ParseState *pstate, CreateTableAsStmt *stmt,
 		 */
 		address = create_ctas_nodata(query->targetList, into);
 
+		/*
+		 * For IVM, mark the matview before refresh so RelationIsIVM()
+		 * returns true inside RefreshMatViewByOid.
+		 */
+		if (is_matview && into->ivm)
+		{
+			Relation matviewRel = table_open(address.objectId, NoLock);
+
+			SetMatViewIVMState(matviewRel, true);
+			table_close(matviewRel, NoLock);
+			CommandCounterIncrement();
+		}
+
 		/*
 		 * For materialized views, reuse the REFRESH logic, which locks down
 		 * security-restricted operations and restricts the search_path.  This
 		 * reduces the chance that a subsequent refresh will fail.
 		 */
 		if (do_refresh)
+		{
 			RefreshMatViewByOid(address.objectId, true, false, false,
 								pstate->p_sourcetext, qc);
 
+			if (is_matview && into->ivm && IsolationUsesXactSnapshot())
+				ereport(WARNING,
+						(errmsg("inconsistent view can be created in isolation level SERIALIZABLE or REPEATABLE READ"),
+						 errdetail("The view may not include effects of a concurrent transaction."),
+						 errhint("The view with incremental maintenance should be created in isolation level READ COMMITTED, "
+								 "or refreshed manually to make sure the view is consistent.")));
+		}
 	}
 	else
 	{
@@ -635,3 +688,659 @@ intorel_destroy(DestReceiver *self)
 {
 	pfree(self);
 }
+
+/*
+ * CreateIvmTriggersOnBaseTables -- create IVM triggers on all base tables
+ */
+void
+CreateIvmTriggersOnBaseTables(Query *qry, Oid matviewOid)
+{
+	List   *relids = NIL;
+	bool	ex_lock = false;
+	RangeTblEntry *rte;
+
+	/* Immediately return if we don't have any base tables. */
+	if (list_length(qry->rtable) < 1)
+		return;
+
+	/*
+	 * If the view has more than one base tables, we need an exclusive lock
+	 * on the view so that the view would be maintained serially to avoid
+	 * the inconsistency that occurs when two base tables are modified in
+	 * concurrent transactions. However, if the view has only one table,
+	 * we can use a weaker lock.
+	 *
+	 * The type of lock should be determined here, because if we check the
+	 * view definition at maintenance time, we need to acquire a weaker lock,
+	 * and upgrading the lock level after this increases probability of
+	 * deadlock.
+	 */
+
+	rte = list_nth(qry->rtable, 0);
+	if (list_length(qry->rtable) > 1 || rte->rtekind != RTE_RELATION)
+		ex_lock = true;
+
+	CreateIvmTriggersOnBaseTablesRecurse(qry, (Node *)qry, matviewOid, &relids, ex_lock);
+
+	list_free(relids);
+}
+
+static void
+CreateIvmTriggersOnBaseTablesRecurse(Query *qry, Node *node, Oid matviewOid,
+									 List **relids, bool ex_lock)
+{
+	if (node == NULL)
+		return;
+
+	/* This can recurse, so check for excessive recursion */
+	check_stack_depth();
+
+	switch (nodeTag(node))
+	{
+		case T_Query:
+			{
+				Query *query = (Query *) node;
+
+				CreateIvmTriggersOnBaseTablesRecurse(qry, (Node *)query->jointree, matviewOid, relids, ex_lock);
+			}
+			break;
+
+		case T_RangeTblRef:
+			{
+				int			rti = ((RangeTblRef *) node)->rtindex;
+				RangeTblEntry *rte = rt_fetch(rti, qry->rtable);
+
+				if (rte->rtekind == RTE_RELATION && !list_member_oid(*relids, rte->relid))
+				{
+					CreateIvmTrigger(rte->relid, matviewOid, TRIGGER_TYPE_INSERT, TRIGGER_TYPE_BEFORE, ex_lock);
+					CreateIvmTrigger(rte->relid, matviewOid, TRIGGER_TYPE_DELETE, TRIGGER_TYPE_BEFORE, ex_lock);
+					CreateIvmTrigger(rte->relid, matviewOid, TRIGGER_TYPE_UPDATE, TRIGGER_TYPE_BEFORE, ex_lock);
+					CreateIvmTrigger(rte->relid, matviewOid, TRIGGER_TYPE_TRUNCATE, TRIGGER_TYPE_BEFORE, true);
+					CreateIvmTrigger(rte->relid, matviewOid, TRIGGER_TYPE_INSERT, TRIGGER_TYPE_AFTER, ex_lock);
+					CreateIvmTrigger(rte->relid, matviewOid, TRIGGER_TYPE_DELETE, TRIGGER_TYPE_AFTER, ex_lock);
+					CreateIvmTrigger(rte->relid, matviewOid, TRIGGER_TYPE_UPDATE, TRIGGER_TYPE_AFTER, ex_lock);
+					CreateIvmTrigger(rte->relid, matviewOid, TRIGGER_TYPE_TRUNCATE, TRIGGER_TYPE_AFTER, true);
+
+					*relids = lappend_oid(*relids, rte->relid);
+				}
+			}
+			break;
+
+		case T_FromExpr:
+			{
+				FromExpr   *f = (FromExpr *) node;
+				ListCell   *l;
+
+				foreach(l, f->fromlist)
+					CreateIvmTriggersOnBaseTablesRecurse(qry, lfirst(l), matviewOid, relids, ex_lock);
+			}
+			break;
+
+		case T_JoinExpr:
+			{
+				JoinExpr   *j = (JoinExpr *) node;
+
+				CreateIvmTriggersOnBaseTablesRecurse(qry, j->larg, matviewOid, relids, ex_lock);
+				CreateIvmTriggersOnBaseTablesRecurse(qry, j->rarg, matviewOid, relids, ex_lock);
+			}
+			break;
+
+		default:
+			elog(ERROR, "unrecognized node type: %d", (int) nodeTag(node));
+	}
+}
+
+/*
+ * CreateIvmTrigger -- create IVM trigger on a base table
+ */
+static void
+CreateIvmTrigger(Oid relOid, Oid viewOid, int16 type, int16 timing, bool ex_lock)
+{
+	ObjectAddress	refaddr;
+	ObjectAddress	address;
+	CreateTrigStmt *ivm_trigger;
+	List *transitionRels = NIL;
+
+	Assert(timing == TRIGGER_TYPE_BEFORE || timing == TRIGGER_TYPE_AFTER);
+
+	refaddr.classId = RelationRelationId;
+	refaddr.objectId = viewOid;
+	refaddr.objectSubId = 0;
+
+	ivm_trigger = makeNode(CreateTrigStmt);
+	ivm_trigger->relation = NULL;
+	ivm_trigger->row = false;
+
+	ivm_trigger->timing = timing;
+	ivm_trigger->events = type;
+
+	switch (type)
+	{
+		case TRIGGER_TYPE_INSERT:
+			ivm_trigger->trigname = (timing == TRIGGER_TYPE_BEFORE ? "IVM_trigger_ins_before" : "IVM_trigger_ins_after");
+			break;
+		case TRIGGER_TYPE_DELETE:
+			ivm_trigger->trigname = (timing == TRIGGER_TYPE_BEFORE ? "IVM_trigger_del_before" : "IVM_trigger_del_after");
+			break;
+		case TRIGGER_TYPE_UPDATE:
+			ivm_trigger->trigname = (timing == TRIGGER_TYPE_BEFORE ? "IVM_trigger_upd_before" : "IVM_trigger_upd_after");
+			break;
+		case TRIGGER_TYPE_TRUNCATE:
+			ivm_trigger->trigname = (timing == TRIGGER_TYPE_BEFORE ? "IVM_trigger_truncate_before" : "IVM_trigger_truncate_after");
+			break;
+		default:
+			elog(ERROR, "unsupported trigger type");
+	}
+
+	if (timing == TRIGGER_TYPE_AFTER)
+	{
+		if (type == TRIGGER_TYPE_INSERT || type == TRIGGER_TYPE_UPDATE)
+		{
+			TriggerTransition *n = makeNode(TriggerTransition);
+			n->name = "__ivm_newtable";
+			n->isNew = true;
+			n->isTable = true;
+
+			transitionRels = lappend(transitionRels, n);
+		}
+		if (type == TRIGGER_TYPE_DELETE || type == TRIGGER_TYPE_UPDATE)
+		{
+			TriggerTransition *n = makeNode(TriggerTransition);
+			n->name = "__ivm_oldtable";
+			n->isNew = false;
+			n->isTable = true;
+
+			transitionRels = lappend(transitionRels, n);
+		}
+	}
+
+	/*
+	 * XXX: When using DELETE or UPDATE, we must use exclusive lock for now
+	 * because apply_old_delta(_with_count) uses ctid to identify the tuple
+	 * to be deleted/deleted, but doesn't work in concurrent situations.
+	 *
+	 * If the view doesn't have aggregate, distinct, or tuple duplicate,
+	 * then it would work even in concurrent situations. However, we don't have
+	 * any way to guarantee the view has a unique key before opening the IMMV
+	 * at the maintenance time because users may drop the unique index.
+	 */
+
+	if (type == TRIGGER_TYPE_DELETE || type == TRIGGER_TYPE_UPDATE)
+		ex_lock = true;
+
+	ivm_trigger->funcname =
+		(timing == TRIGGER_TYPE_BEFORE ? SystemFuncName("IVM_immediate_before") : SystemFuncName("IVM_immediate_maintenance"));
+
+	ivm_trigger->columns = NIL;
+	ivm_trigger->transitionRels = transitionRels;
+	ivm_trigger->whenClause = NULL;
+	ivm_trigger->isconstraint = false;
+	ivm_trigger->deferrable = false;
+	ivm_trigger->initdeferred = false;
+	ivm_trigger->constrrel = NULL;
+	ivm_trigger->args = list_make2(
+		makeString(DatumGetPointer(DirectFunctionCall1(oidout, ObjectIdGetDatum(viewOid)))),
+		makeString(DatumGetPointer(DirectFunctionCall1(boolout, BoolGetDatum(ex_lock))))
+		);
+
+	address = CreateTrigger(ivm_trigger, NULL, relOid, InvalidOid, InvalidOid,
+						 InvalidOid, InvalidOid, InvalidOid, NULL, true, false);
+
+	recordDependencyOn(&address, &refaddr, DEPENDENCY_AUTO);
+
+	/* Make changes-so-far visible */
+	CommandCounterIncrement();
+}
+
+/*
+ * check_ivm_restriction --- look for specify nodes in the query tree
+ */
+static void
+check_ivm_restriction(Node *node)
+{
+	check_ivm_restriction_walker(node, NULL);
+}
+
+static bool
+check_ivm_restriction_walker(Node *node, void *context)
+{
+	if (node == NULL)
+		return false;
+
+	/*
+	 * We currently don't support Sub-Query.
+	 */
+	if (IsA(node, SubPlan) || IsA(node, SubLink))
+		ereport(ERROR,
+				(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+				 errmsg("subquery is not supported on incrementally maintainable materialized view")));
+
+	/* This can recurse, so check for excessive recursion */
+	check_stack_depth();
+
+	switch (nodeTag(node))
+	{
+		case T_Query:
+			{
+				Query *qry = (Query *)node;
+				ListCell   *lc;
+				List       *vars;
+
+				/* if contained CTE, return error */
+				if (qry->cteList != NIL)
+					ereport(ERROR,
+							(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+							 errmsg("CTE is not supported on incrementally maintainable materialized view")));
+				if (qry->havingQual != NULL)
+					ereport(ERROR,
+							(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+							 errmsg(" HAVING clause is not supported on incrementally maintainable materialized view")));
+				if (qry->sortClause != NIL)	/* There is a possibility that we don't need to return an error */
+					ereport(ERROR,
+							(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+							 errmsg("ORDER BY clause is not supported on incrementally maintainable materialized view")));
+				if (qry->limitOffset != NULL || qry->limitCount != NULL)
+					ereport(ERROR,
+							(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+							 errmsg("LIMIT/OFFSET clause is not supported on incrementally maintainable materialized view")));
+				if (qry->distinctClause)
+					ereport(ERROR,
+							(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+							 errmsg("DISTINCT is not supported on incrementally maintainable materialized view")));
+				if (qry->hasDistinctOn)
+					ereport(ERROR,
+							(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+							 errmsg("DISTINCT ON is not supported on incrementally maintainable materialized view")));
+				if (qry->hasWindowFuncs)
+					ereport(ERROR,
+							(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+							 errmsg("window functions are not supported on incrementally maintainable materialized view")));
+				if (qry->groupingSets != NIL)
+					ereport(ERROR,
+							(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+							 errmsg("GROUPING SETS, ROLLUP, or CUBE clauses is not supported on incrementally maintainable materialized view")));
+				if (qry->setOperations != NULL)
+					ereport(ERROR,
+							(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+							 errmsg("UNION/INTERSECT/EXCEPT statements are not supported on incrementally maintainable materialized view")));
+				if (list_length(qry->targetList) == 0)
+					ereport(ERROR,
+							(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+							 errmsg("empty target list is not supported on incrementally maintainable materialized view")));
+				if (qry->rowMarks != NIL)
+					ereport(ERROR,
+							(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+							 errmsg("FOR UPDATE/SHARE clause is not supported on incrementally maintainable materialized view")));
+
+				/* system column restrictions */
+				vars = pull_vars_of_level((Node *) qry, 0);
+				foreach(lc, vars)
+				{
+					if (IsA(lfirst(lc), Var))
+					{
+						Var *var = (Var *) lfirst(lc);
+						/* if system column, return error */
+						if (var->varattno < 0)
+							ereport(ERROR,
+									(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+									 errmsg("system column is not supported on incrementally maintainable materialized view")));
+					}
+				}
+
+				/* check if type in the target list had an equality operator */
+				foreach(lc, qry->targetList)
+				{
+					TargetEntry *tle = (TargetEntry *) lfirst(lc);
+					Oid             atttype = exprType((Node *) tle->expr);
+					Oid             opclass;
+
+					opclass = GetDefaultOpClass(atttype, BTREE_AM_OID);
+					if (!OidIsValid(opclass))
+						ereport(ERROR,
+								(errcode(ERRCODE_UNDEFINED_OBJECT),
+								 errmsg("data type %s has no default operator class for access method \"%s\"",
+									format_type_be(atttype), "btree")));
+				}
+
+				/* restrictions for rtable */
+				foreach(lc, qry->rtable)
+				{
+					RangeTblEntry *rte = (RangeTblEntry *) lfirst(lc);
+
+					if (rte->subquery)
+						ereport(ERROR,
+								(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+								 errmsg("subquery is not supported on incrementally maintainable materialized view")));
+
+					if (rte->tablesample != NULL)
+						ereport(ERROR,
+								(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+								 errmsg("TABLESAMPLE clause is not supported on incrementally maintainable materialized view")));
+
+					if (rte->relkind == RELKIND_PARTITIONED_TABLE)
+						ereport(ERROR,
+								(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+								 errmsg("partitioned table is not supported on incrementally maintainable materialized view")));
+
+					if (rte->relkind == RELKIND_RELATION && has_superclass(rte->relid))
+						ereport(ERROR,
+								(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+								 errmsg("partitions is not supported on incrementally maintainable materialized view")));
+
+					if (rte->relkind == RELKIND_RELATION && find_inheritance_children(rte->relid, NoLock) != NIL)
+						ereport(ERROR,
+								(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+								 errmsg("inheritance parent is not supported on incrementally maintainable materialized view")));
+
+					if (rte->relkind == RELKIND_FOREIGN_TABLE)
+						ereport(ERROR,
+								(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+								 errmsg("foreign table is not supported on incrementally maintainable materialized view")));
+
+					if (rte->relkind == RELKIND_VIEW ||
+						rte->relkind == RELKIND_MATVIEW)
+						ereport(ERROR,
+								(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+								 errmsg("VIEW or MATERIALIZED VIEW is not supported on incrementally maintainable materialized view")));
+
+					if (rte->rtekind == RTE_VALUES)
+						ereport(ERROR,
+								(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+								 errmsg("VALUES is not supported on incrementally maintainable materialized view")));
+
+				}
+
+				query_tree_walker(qry, check_ivm_restriction_walker, NULL, QTW_IGNORE_RANGE_TABLE);
+
+				break;
+			}
+		case T_TargetEntry:
+			{
+				TargetEntry *tle = (TargetEntry *)node;
+				if (isIvmName(tle->resname))
+						ereport(ERROR,
+								(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+								 errmsg("column name %s is not supported on incrementally maintainable materialized view", tle->resname)));
+
+				expression_tree_walker(node, check_ivm_restriction_walker, NULL);
+				break;
+			}
+		case T_JoinExpr:
+			{
+				JoinExpr *joinexpr = (JoinExpr *)node;
+
+				if (joinexpr->jointype > JOIN_INNER)
+						ereport(ERROR,
+								(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+								 errmsg("OUTER JOIN is not supported on incrementally maintainable materialized view")));
+
+				expression_tree_walker(node, check_ivm_restriction_walker, NULL);
+			}
+			break;
+		case T_Aggref:
+			ereport(ERROR,
+					(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+					 errmsg("aggregate function is not supported on incrementally maintainable materialized view")));
+			break;
+		default:
+			expression_tree_walker(node, check_ivm_restriction_walker, (void *) context);
+			break;
+	}
+	return false;
+}
+
+/*
+ * CreateIndexOnIMMV
+ *
+ * Create a unique index on incremental maintainable materialized view.
+ * If the view definition query has a GROUP BY clause, the index is created
+ * on the columns of GROUP BY expressions. Otherwise, if the view contains
+ * all primary key attributes of its base tables in the target list, the index
+ * is created on these attributes. In other cases, no index is created.
+ */
+void
+CreateIndexOnIMMV(Query *query, Relation matviewRel)
+{
+	ListCell *lc;
+	IndexStmt  *index;
+	ObjectAddress address;
+	List *constraintList = NIL;
+	char		idxname[NAMEDATALEN];
+	List	   *indexoidlist = RelationGetIndexList(matviewRel);
+	ListCell   *indexoidscan;
+	Bitmapset *key_attnos;
+
+	snprintf(idxname, sizeof(idxname), "%s_index", RelationGetRelationName(matviewRel));
+
+	index = makeNode(IndexStmt);
+
+	index->unique = true;
+	index->primary = false;
+	index->isconstraint = false;
+	index->deferrable = false;
+	index->initdeferred = false;
+	index->idxname = idxname;
+	index->relation =
+		makeRangeVar(get_namespace_name(RelationGetNamespace(matviewRel)),
+					 pstrdup(RelationGetRelationName(matviewRel)),
+					 -1);
+	index->accessMethod = DEFAULT_INDEX_TYPE;
+	index->options = NIL;
+	index->tableSpace = get_tablespace_name(matviewRel->rd_rel->reltablespace);
+	index->whereClause = NULL;
+	index->indexParams = NIL;
+	index->indexIncludingParams = NIL;
+	index->excludeOpNames = NIL;
+	index->idxcomment = NULL;
+	index->indexOid = InvalidOid;
+	index->oldNumber = InvalidRelFileNumber;
+	index->oldCreateSubid = InvalidSubTransactionId;
+	index->oldFirstRelfilelocatorSubid = InvalidSubTransactionId;
+	index->transformed = true;
+	index->concurrent = false;
+	index->if_not_exists = false;
+
+	/* create index on the base tables' primary key columns */
+	key_attnos = get_primary_key_attnos_from_query(query, &constraintList);
+	if (key_attnos)
+	{
+		foreach(lc, query->targetList)
+		{
+			TargetEntry *tle = (TargetEntry *) lfirst(lc);
+			Form_pg_attribute attr = TupleDescAttr(matviewRel->rd_att, tle->resno - 1);
+
+			if (bms_is_member(tle->resno - FirstLowInvalidHeapAttributeNumber, key_attnos))
+			{
+				IndexElem  *iparam;
+
+				iparam = makeNode(IndexElem);
+				iparam->name = pstrdup(NameStr(attr->attname));
+				iparam->expr = NULL;
+				iparam->indexcolname = NULL;
+				iparam->collation = NIL;
+				iparam->opclass = NIL;
+				iparam->opclassopts = NIL;
+				iparam->ordering = SORTBY_DEFAULT;
+				iparam->nulls_ordering = SORTBY_NULLS_DEFAULT;
+				index->indexParams = lappend(index->indexParams, iparam);
+			}
+		}
+	}
+	else
+	{
+		/* create no index, just notice that an appropriate index is necessary for efficient IVM */
+		ereport(NOTICE,
+				(errmsg("could not create an index on materialized view \"%s\" automatically",
+						RelationGetRelationName(matviewRel)),
+				 errdetail("This target list does not have all the primary key columns. "),
+				 errhint("Create an index on the materialized view for efficient incremental maintenance.")));
+		return;
+	}
+
+	/* If we have a compatible index, we don't need to create another. */
+	foreach(indexoidscan, indexoidlist)
+	{
+		Oid			indexoid = lfirst_oid(indexoidscan);
+		Relation	indexRel;
+		bool		hasCompatibleIndex = false;
+
+		indexRel = index_open(indexoid, AccessShareLock);
+
+		if (CheckIndexCompatible(indexRel->rd_id,
+								index->accessMethod,
+								index->indexParams,
+								index->excludeOpNames,
+								false))
+			hasCompatibleIndex = true;
+
+		index_close(indexRel, AccessShareLock);
+
+		if (hasCompatibleIndex)
+			return;
+	}
+
+	address = DefineIndex(NULL,
+						  RelationGetRelid(matviewRel),
+						  index,
+						  InvalidOid,
+						  InvalidOid,
+						  InvalidOid,
+						  -1,
+						  false, true, false, false, true);
+
+	ereport(NOTICE,
+			(errmsg("created index \"%s\" on materialized view \"%s\"",
+					idxname, RelationGetRelationName(matviewRel))));
+
+	/*
+	 * Make dependencies so that the index is dropped if any base tables'
+	 * primary key is dropped.
+	 */
+	foreach(lc, constraintList)
+	{
+		Oid constraintOid = lfirst_oid(lc);
+		ObjectAddress	refaddr;
+
+		refaddr.classId = ConstraintRelationId;
+		refaddr.objectId = constraintOid;
+		refaddr.objectSubId = 0;
+
+		recordDependencyOn(&address, &refaddr, DEPENDENCY_NORMAL);
+	}
+}
+
+
+/*
+ * get_primary_key_attnos_from_query
+ *
+ * Identify the columns in base tables' primary keys in the target list.
+ *
+ * Returns a Bitmapset of the column attnos of the primary key's columns of
+ * tables that used in the query.  The attnos are offset by
+ * FirstLowInvalidHeapAttributeNumber as same as get_primary_key_attnos.
+ *
+ * If any table has no primary key or any primary key's columns is not in
+ * the target list, return NULL.  We also return NULL if any pkey constraint
+ * is deferrable.
+ *
+ * constraintList is set to a list of the OIDs of the pkey constraints.
+ */
+static Bitmapset *
+get_primary_key_attnos_from_query(Query *query, List **constraintList)
+{
+	List *key_attnos_list = NIL;
+	ListCell *lc;
+	int i;
+	Bitmapset *keys = NULL;
+	Relids	rels_in_from;
+
+	/*
+	 * Collect primary key attributes from all tables used in query. The key attributes
+	 * sets for each table are stored in key_attnos_list in order by RTE index.
+	 */
+	foreach(lc, query->rtable)
+	{
+		RangeTblEntry *r = (RangeTblEntry*) lfirst(lc);
+		Bitmapset *key_attnos;
+		bool	has_no_pkey = false;
+
+		/* for tables, call get_primary_key_attnos */
+		if (r->rtekind == RTE_RELATION)
+		{
+			Oid constraintOid;
+			key_attnos = get_primary_key_attnos(r->relid, false, &constraintOid);
+			*constraintList = lappend_oid(*constraintList, constraintOid);
+			has_no_pkey = (key_attnos == NULL);
+		}
+		/*
+		 * Ignore join rels, because they are flatten later by
+		 * flatten_join_alias_vars(). Store NULL into key_attnos_list
+		 * as a dummy.
+		 */
+		 else if (r->rtekind == RTE_JOIN)
+		 {
+			key_attnos = NULL;
+		}
+		/* for other RTEs, store NULL into key_attnos_list */
+		else
+			has_no_pkey = true;
+
+		/*
+		 * If any table or subquery has no primary key or its pkey constraint is deferrable,
+		 * we cannot get key attributes for this query, so return NULL.
+		 */
+		if (has_no_pkey)
+			return NULL;
+
+		key_attnos_list = lappend(key_attnos_list, key_attnos);
+	}
+
+	/* Collect key attributes appearing in the target list */
+	i = 1;
+	foreach(lc, query->targetList)
+	{
+		TargetEntry *tle = (TargetEntry *) flatten_join_alias_vars(NULL, query, lfirst(lc));
+
+		if (IsA(tle->expr, Var))
+		{
+			Var *var = (Var*) tle->expr;
+			Bitmapset *key_attnos = list_nth(key_attnos_list, var->varno - 1);
+
+			/* check if this attribute is from a base table's primary key */
+			if (bms_is_member(var->varattno - FirstLowInvalidHeapAttributeNumber, key_attnos))
+			{
+				/*
+				 * Remove found key attributes from key_attnos_list, and add this
+				 * to the result list.
+				 */
+				key_attnos = bms_del_member(key_attnos, var->varattno - FirstLowInvalidHeapAttributeNumber);
+				if (bms_is_empty(key_attnos))
+				{
+					key_attnos_list = list_delete_nth_cell(key_attnos_list, var->varno - 1);
+					key_attnos_list = list_insert_nth(key_attnos_list, var->varno - 1, NULL);
+				}
+				keys = bms_add_member(keys, i - FirstLowInvalidHeapAttributeNumber);
+			}
+		}
+		i++;
+	}
+
+	/* Collect RTE indexes of relations appearing in the FROM clause */
+	rels_in_from = get_relids_in_jointree((Node *) query->jointree, false, false);
+
+	/*
+	 * Check if all key attributes of relations in FROM are appearing in the target
+	 * list.  If an attribute remains in key_attnos_list in spite of the table is used
+	 * in FROM clause, the target is missing this key attribute, so we return NULL.
+	 */
+	i = 1;
+	foreach(lc, key_attnos_list)
+	{
+		Bitmapset *bms = (Bitmapset *)lfirst(lc);
+		if (!bms_is_empty(bms) && bms_is_member(i, rels_in_from))
+			return NULL;
+		i++;
+	}
+
+	return keys;
+}
diff --git a/src/backend/commands/matview.c b/src/backend/commands/matview.c
index f7d8007f796..eaf39f80cd3 100644
--- a/src/backend/commands/matview.c
+++ b/src/backend/commands/matview.c
@@ -23,24 +23,36 @@
 #include "catalog/indexing.h"
 #include "catalog/namespace.h"
 #include "catalog/pg_am.h"
+#include "catalog/pg_depend.h"
+#include "catalog/pg_trigger.h"
 #include "catalog/pg_opclass.h"
 #include "commands/matview.h"
 #include "commands/repack.h"
 #include "commands/tablecmds.h"
 #include "commands/tablespace.h"
+#include "commands/createas.h"
 #include "executor/executor.h"
 #include "executor/spi.h"
+#include "executor/tstoreReceiver.h"
 #include "miscadmin.h"
+#include "nodes/makefuncs.h"
+#include "parser/analyze.h"
+#include "parser/parse_clause.h"
+#include "parser/parse_func.h"
+#include "parser/parse_relation.h"
 #include "pgstat.h"
 #include "rewrite/rewriteHandler.h"
+#include "rewrite/rowsecurity.h"
 #include "storage/lmgr.h"
+#include "storage/lwlock.h"
 #include "tcop/tcopprot.h"
 #include "utils/builtins.h"
+#include "utils/fmgroids.h"
 #include "utils/lsyscache.h"
 #include "utils/rel.h"
 #include "utils/snapmgr.h"
 #include "utils/syscache.h"
-
+#include "utils/typcache.h"
 
 typedef struct
 {
@@ -53,6 +65,97 @@ typedef struct
 	BulkInsertState bistate;	/* bulk insert state */
 } DR_transientrel;
 
+#define MV_INIT_QUERYHASHSIZE	16
+
+/*
+ * MV_TriggerHashEntry
+ *
+ * Hash entry for base tables on which IVM trigger is invoked
+ */
+typedef struct MV_TriggerHashEntry
+{
+	Oid	matview_id;			/* OID of the materialized view */
+	int	before_trig_count;	/* count of before triggers invoked */
+	int	after_trig_count;	/* count of after triggers invoked */
+
+	Snapshot	snapshot;	/* Snapshot just before table change */
+
+	List   *tables;		/* List of MV_TriggerTable */
+	bool	has_old;	/* tuples are deleted from any table? */
+	bool	has_new;	/* tuples are inserted into any table? */
+
+	/*
+	 * List of sub-transaction IDs that incrementally updated the view.
+	 * This list is maintained through a transaction, and an ID is removed
+	 * when a sub-transaction is aborted. If any ID is left when the
+	 * transaction is committed, this means the view is incrementally
+	 * updated in this transaction.
+	 */
+	List   *subxids;
+} MV_TriggerHashEntry;
+
+/*
+ * MV_TriggerTable
+ *
+ * IVM related data for tables on which the trigger is invoked.
+ */
+typedef struct MV_TriggerTable
+{
+	Oid		table_id;			/* OID of the modified table */
+	List   *old_tuplestores;	/* tuplestores for deleted tuples */
+	List   *new_tuplestores;	/* tuplestores for inserted tuples */
+
+	List   *rte_indexes;		/* List of RTE index of the modified table */
+	RangeTblEntry *original_rte;	/* the original RTE saved before rewriting query */
+
+	Relation	rel;			/* relation of the modified table */
+	TupleTableSlot *slot;		/* for checking visibility in the pre-state table */
+} MV_TriggerTable;
+
+typedef struct DroppedImmvInfo
+{
+	Oid					immv_oid;
+	SubTransactionId	subxid;
+} DroppedImmvInfo;
+
+static HTAB *mv_trigger_info = NULL;
+static HTAB *dropped_immv = NULL;
+
+static HTAB *LastIvmUpdateHash;
+
+#define LAST_IVM_UPDATE_HASH_SIZE 256
+
+static void IvmShmemRequest(void *arg);
+
+/* hash table entries */
+typedef struct LastIvmUpdateEntry
+{
+	Oid		oid;	/* hash key */
+	FullTransactionId	last_ivm_update;
+} LastIvmUpdateEntry;
+
+const ShmemCallbacks IvmShmemCallbacks = {
+	.request_fn = IvmShmemRequest,
+};
+
+static void
+IvmShmemRequest(void *arg)
+{
+	ShmemRequestHash(.name = "LastIvmUpdate hash",
+					 .nelems = LAST_IVM_UPDATE_HASH_SIZE,
+					 .ptr = &LastIvmUpdateHash,
+					 .hash_info.keysize = sizeof(Oid),
+					 .hash_info.entrysize = sizeof(LastIvmUpdateEntry),
+					 .hash_flags = HASH_ELEM | HASH_BLOBS,
+		);
+}
+
+static bool in_delta_calculation = false;
+
+/* ENR name for materialized view delta */
+#define NEW_DELTA_ENRNAME "new_delta"
+#define OLD_DELTA_ENRNAME "old_delta"
+
 static int	matview_maintenance_depth = 0;
 
 static void transientrel_startup(DestReceiver *self, int operation, TupleDesc typeinfo);
@@ -60,6 +163,8 @@ static bool transientrel_receive(TupleTableSlot *slot, DestReceiver *self);
 static void transientrel_shutdown(DestReceiver *self);
 static void transientrel_destroy(DestReceiver *self);
 static uint64 refresh_matview_datafill(DestReceiver *dest, Query *query,
+									   QueryEnvironment *queryEnv,
+									   TupleDesc *resultTupleDesc,
 									   const char *queryString, bool is_create);
 static void refresh_by_match_merge(Oid matviewOid, Oid tempOid, Oid relowner,
 								   int save_sec_context);
@@ -67,6 +172,41 @@ static void refresh_by_heap_swap(Oid matviewOid, Oid OIDNewHeap, char relpersist
 static bool is_usable_unique_index(Relation indexRel);
 static void OpenMatViewIncrementalMaintenance(void);
 static void CloseMatViewIncrementalMaintenance(void);
+static Query *get_matview_query(Relation matviewRel);
+
+static Query *rewrite_query_for_preupdate_state(Query *query, List *tables,
+								  ParseState *pstate, Oid matviewid);
+static void register_delta_ENRs(ParseState *pstate, Query *query, List *tables);
+static char *make_subquery_targetlist_from_table(MV_TriggerTable *table);
+static char *make_delta_enr_name(const char *prefix, Oid relid, int count);
+static RangeTblEntry *get_prestate_rte(RangeTblEntry *rte, MV_TriggerTable *table,
+				 QueryEnvironment *queryEnv, Oid matviewid);
+static RangeTblEntry *makeDeltaTable(RangeTblEntry *rte, MV_TriggerTable *table,
+									 bool is_new, QueryEnvironment *queryEnv);
+static Query *rewrite_query_for_counting(Query *query, ParseState *pstate);
+
+static void calc_delta(MV_TriggerTable *table, int rte_index, Query *query,
+			DestReceiver *dest_old, DestReceiver *dest_new,
+			TupleDesc *tupdesc_old, TupleDesc *tupdesc_new,
+			QueryEnvironment *queryEnv);
+static Query *rewrite_query_for_postupdate_state(Query *query, MV_TriggerTable *table, int rte_index);
+
+static void apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *new_tuplestores,
+			TupleDesc tupdesc_old, TupleDesc tupdesc_new,
+			Query *query);
+static void apply_old_delta(const char *matviewname, const char *deltaname_old,
+				List *keys);
+static void apply_new_delta(const char *matviewname, const char *deltaname_new,
+				StringInfo target_list);
+static char *get_matching_condition_string(List *keys);
+static void generate_equal(StringInfo querybuf, Oid opttype,
+			   const char *leftop, const char *rightop);
+
+static void mv_InitHashTables(void);
+static void clean_up_IVM_hash_entry(MV_TriggerHashEntry *entry, bool is_abort,
+									SubTransactionId subxid);
+static void setLastUpdateXid(Oid immv_oid, FullTransactionId xid);
+static FullTransactionId getLastUpdateXid(Oid immv_oid);
 
 /*
  * SetMatViewPopulatedState
@@ -108,6 +248,46 @@ SetMatViewPopulatedState(Relation relation, bool newstate)
 	CommandCounterIncrement();
 }
 
+/*
+ * SetMatViewIVMState
+ *		Mark a materialized view as IVM, or not.
+ *
+ * NOTE: caller must be holding an appropriate lock on the relation.
+ */
+void
+SetMatViewIVMState(Relation relation, bool newstate)
+{
+	Relation	pgrel;
+	HeapTuple	tuple;
+
+	Assert(relation->rd_rel->relkind == RELKIND_MATVIEW);
+
+	/*
+	 * Update relation's pg_class entry.  Crucial side-effect: other backends
+	 * (and this one too!) are sent SI message to make them rebuild relcache
+	 * entries.
+	 */
+	pgrel = table_open(RelationRelationId, RowExclusiveLock);
+	tuple = SearchSysCacheCopy1(RELOID,
+								ObjectIdGetDatum(RelationGetRelid(relation)));
+	if (!HeapTupleIsValid(tuple))
+		elog(ERROR, "cache lookup failed for relation %u",
+			 RelationGetRelid(relation));
+
+	((Form_pg_class) GETSTRUCT(tuple))->relisivm = newstate;
+
+	CatalogTupleUpdate(pgrel, &tuple->t_self, tuple);
+
+	heap_freetuple(tuple);
+	table_close(pgrel, RowExclusiveLock);
+
+	/*
+	 * Advance command counter to make the updated pg_class row locally
+	 * visible.
+	 */
+	CommandCounterIncrement();
+}
+
 /*
  * ExecRefreshMatView -- execute a REFRESH MATERIALIZED VIEW command
  *
@@ -166,8 +346,6 @@ RefreshMatViewByOid(Oid matviewOid, bool is_create, bool skipData,
 					QueryCompletion *qc)
 {
 	Relation	matviewRel;
-	RewriteRule *rule;
-	List	   *actions;
 	Query	   *dataQuery;
 	Oid			tableSpace;
 	Oid			relowner;
@@ -178,6 +356,7 @@ RefreshMatViewByOid(Oid matviewOid, bool is_create, bool skipData,
 	int			save_sec_context;
 	int			save_nestlevel;
 	ObjectAddress address;
+	bool oldPopulated;
 
 	matviewRel = table_open(matviewOid, NoLock);
 	relowner = matviewRel->rd_rel->relowner;
@@ -193,6 +372,8 @@ RefreshMatViewByOid(Oid matviewOid, bool is_create, bool skipData,
 	save_nestlevel = NewGUCNestLevel();
 	RestrictSearchPath();
 
+	oldPopulated = RelationIsPopulated(matviewRel);
+
 	/* Make sure it is a materialized view. */
 	if (matviewRel->rd_rel->relkind != RELKIND_MATVIEW)
 		ereport(ERROR,
@@ -213,32 +394,7 @@ RefreshMatViewByOid(Oid matviewOid, bool is_create, bool skipData,
 				 errmsg("%s options %s and %s cannot be used together",
 						"REFRESH", "CONCURRENTLY", "WITH NO DATA")));
 
-	/*
-	 * Check that everything is correct for a refresh. Problems at this point
-	 * are internal errors, so elog is sufficient.
-	 */
-	if (matviewRel->rd_rel->relhasrules == false ||
-		matviewRel->rd_rules->numLocks < 1)
-		elog(ERROR,
-			 "materialized view \"%s\" is missing rewrite information",
-			 RelationGetRelationName(matviewRel));
-
-	if (matviewRel->rd_rules->numLocks > 1)
-		elog(ERROR,
-			 "materialized view \"%s\" has too many rules",
-			 RelationGetRelationName(matviewRel));
-
-	rule = matviewRel->rd_rules->rules[0];
-	if (rule->event != CMD_SELECT || !(rule->isInstead))
-		elog(ERROR,
-			 "the rule for materialized view \"%s\" is not a SELECT INSTEAD OF rule",
-			 RelationGetRelationName(matviewRel));
-
-	actions = rule->actions;
-	if (list_length(actions) != 1)
-		elog(ERROR,
-			 "the rule for materialized view \"%s\" is not a single action",
-			 RelationGetRelationName(matviewRel));
+	dataQuery = get_matview_query(matviewRel);
 
 	/*
 	 * Check that there is a unique index with no WHERE clause on one or more
@@ -275,12 +431,6 @@ RefreshMatViewByOid(Oid matviewOid, bool is_create, bool skipData,
 					 errhint("Create a unique index with no WHERE clause on one or more columns of the materialized view.")));
 	}
 
-	/*
-	 * The stored query was rewritten at the time of the MV definition, but
-	 * has not been scribbled on by the planner.
-	 */
-	dataQuery = linitial_node(Query, actions);
-
 	/*
 	 * Check for active uses of the relation in the current transaction, such
 	 * as open scans.
@@ -310,6 +460,90 @@ RefreshMatViewByOid(Oid matviewOid, bool is_create, bool skipData,
 		relpersistence = matviewRel->rd_rel->relpersistence;
 	}
 
+	/* delete IMMV triggers. */
+	if (RelationIsIVM(matviewRel) && skipData)
+	{
+		Relation	tgRel;
+		Relation	depRel;
+		ScanKeyData key;
+		SysScanDesc scan;
+		HeapTuple	tup;
+		ObjectAddresses *immv_triggers;
+
+		immv_triggers = new_object_addresses();
+
+		tgRel = table_open(TriggerRelationId, RowExclusiveLock);
+		depRel = table_open(DependRelationId, RowExclusiveLock);
+
+		/* search triggers that depends on IMMV. */
+		ScanKeyInit(&key,
+					Anum_pg_depend_refobjid,
+					BTEqualStrategyNumber, F_OIDEQ,
+					ObjectIdGetDatum(matviewOid));
+		scan = systable_beginscan(depRel, DependReferenceIndexId, true,
+								  NULL, 1, &key);
+		while ((tup = systable_getnext(scan)) != NULL)
+		{
+			ObjectAddress obj;
+			Form_pg_depend foundDep = (Form_pg_depend) GETSTRUCT(tup);
+
+			if (foundDep->classid == TriggerRelationId)
+			{
+				HeapTuple	tgtup;
+				ScanKeyData tgkey[1];
+				SysScanDesc tgscan;
+				Form_pg_trigger tgform;
+
+				/* Find the trigger name. */
+				ScanKeyInit(&tgkey[0],
+							Anum_pg_trigger_oid,
+							BTEqualStrategyNumber, F_OIDEQ,
+							ObjectIdGetDatum(foundDep->objid));
+
+				tgscan = systable_beginscan(tgRel, TriggerOidIndexId, true,
+											NULL, 1, tgkey);
+				tgtup = systable_getnext(tgscan);
+				if (!HeapTupleIsValid(tgtup))
+					elog(ERROR, "could not find tuple for immv trigger %u", foundDep->objid);
+
+				tgform = (Form_pg_trigger) GETSTRUCT(tgtup);
+
+				/* If trigger is created by IMMV, delete it. */
+				if (strncmp(NameStr(tgform->tgname), "IVM_trigger_", 12) == 0)
+				{
+					obj.classId = foundDep->classid;
+					obj.objectId = foundDep->objid;
+					obj.objectSubId = foundDep->refobjsubid;
+					add_exact_object_address(&obj, immv_triggers);
+				}
+				systable_endscan(tgscan);
+			}
+		}
+		systable_endscan(scan);
+
+		performMultipleDeletions(immv_triggers, DROP_RESTRICT, PERFORM_DELETION_INTERNAL);
+
+		table_close(depRel, RowExclusiveLock);
+		table_close(tgRel, RowExclusiveLock);
+		free_object_addresses(immv_triggers);
+	}
+
+	/*
+	 * Create triggers on incremental maintainable materialized view
+	 * This argument should use 'dataQuery'. This needs to use a rewritten query,
+	 * because a sublink in jointree is not supported by this function.
+	 *
+	 * This is performed before generating data because we have to wait
+	 * concurrent transactions modifying a base table and then take a snapshot
+	 * to see changes by these transactions to make sure a consistent view
+	 * is created.
+	 */
+	if (RelationIsIVM(matviewRel) && !skipData && !oldPopulated)
+	{
+		CreateIvmTriggersOnBaseTables(dataQuery, matviewOid);
+		CreateIndexOnIMMV(dataQuery, matviewRel);
+	}
+
 	/*
 	 * Create the transient table that will receive the regenerated data. Lock
 	 * it against access by any other process until commit (by which time it
@@ -326,8 +560,43 @@ RefreshMatViewByOid(Oid matviewOid, bool is_create, bool skipData,
 		DestReceiver *dest;
 
 		dest = CreateTransientRelDestReceiver(OIDNewHeap);
-		processed = refresh_matview_datafill(dest, dataQuery, queryString,
-											 is_create);
+
+		if (RelationIsIVM(matviewRel))
+		{
+			/*
+			 * In READ COMMITTED, get and push the latest snapshot again to see the
+			 * results of concurrent transactions committed after the current
+			 * transaction started.
+			 */
+			if (!IsolationUsesXactSnapshot())
+				PushActiveSnapshot(GetTransactionSnapshot());
+
+			/*
+			 * If a concurrent transaction updated the view incrementally and was
+			 * committed before we acquired the lock, the results of refresh_immv could
+			 * be inconsistent. Therefore, we have to check the transaction ID of the
+			 * most recent update of the view, and if this was in progress at the
+			 * transaction start, raise an error to prevent anomalies.
+			 */
+			if (!is_create)
+			{
+				FullTransactionId xid;
+
+				xid = getLastUpdateXid(matviewOid);
+				if (XidInMVCCSnapshot(XidFromFullTransactionId(xid), GetActiveSnapshot()))
+					ereport(ERROR,
+							(errcode(ERRCODE_T_R_SERIALIZATION_FAILURE),
+							 errmsg("the materialized view is incrementally updated in concurrent transaction"),
+							 errhint("The transaction might succeed if retried.")));
+			}
+		}
+
+		processed = refresh_matview_datafill(dest, dataQuery, NULL, NULL,
+											 queryString, is_create);
+
+		/* Pop the original snapshot. */
+		if (RelationIsIVM(matviewRel) && !IsolationUsesXactSnapshot())
+			PopActiveSnapshot();
 	}
 
 	/* Make the matview match the newly generated data. */
@@ -402,6 +671,8 @@ RefreshMatViewByOid(Oid matviewOid, bool is_create, bool skipData,
  */
 static uint64
 refresh_matview_datafill(DestReceiver *dest, Query *query,
+						 QueryEnvironment *queryEnv,
+						 TupleDesc *resultTupleDesc,
 						 const char *queryString, bool is_create)
 {
 	List	   *rewritten;
@@ -439,7 +710,7 @@ refresh_matview_datafill(DestReceiver *dest, Query *query,
 	/* Create a QueryDesc, redirecting output to our tuple receiver */
 	queryDesc = CreateQueryDesc(plan, queryString,
 								GetActiveSnapshot(), InvalidSnapshot,
-								dest, NULL, NULL, 0);
+								dest, NULL, queryEnv ? queryEnv: NULL, 0);
 
 	/* call ExecutorStart to prepare the plan for execution */
 	ExecutorStart(queryDesc, 0);
@@ -449,6 +720,9 @@ refresh_matview_datafill(DestReceiver *dest, Query *query,
 
 	processed = queryDesc->estate->es_processed;
 
+	if (resultTupleDesc)
+		*resultTupleDesc = CreateTupleDescCopy(queryDesc->tupDesc);
+
 	/* and clean up */
 	ExecutorFinish(queryDesc);
 	ExecutorEnd(queryDesc);
@@ -967,3 +1241,1488 @@ CloseMatViewIncrementalMaintenance(void)
 	matview_maintenance_depth--;
 	Assert(matview_maintenance_depth >= 0);
 }
+
+/*
+ * get_matview_query - get the Query from a matview's _RETURN rule.
+ */
+static Query *
+get_matview_query(Relation matviewRel)
+{
+	RewriteRule *rule;
+	List * actions;
+
+	/*
+	 * Check that everything is correct for a refresh. Problems at this point
+	 * are internal errors, so elog is sufficient.
+	 */
+	if (matviewRel->rd_rel->relhasrules == false ||
+		matviewRel->rd_rules->numLocks < 1)
+		elog(ERROR,
+			 "materialized view \"%s\" is missing rewrite information",
+			 RelationGetRelationName(matviewRel));
+
+	if (matviewRel->rd_rules->numLocks > 1)
+		elog(ERROR,
+			 "materialized view \"%s\" has too many rules",
+			 RelationGetRelationName(matviewRel));
+
+	rule = matviewRel->rd_rules->rules[0];
+	if (rule->event != CMD_SELECT || !(rule->isInstead))
+		elog(ERROR,
+			 "the rule for materialized view \"%s\" is not a SELECT INSTEAD OF rule",
+			 RelationGetRelationName(matviewRel));
+
+	actions = rule->actions;
+	if (list_length(actions) != 1)
+		elog(ERROR,
+			 "the rule for materialized view \"%s\" is not a single action",
+			 RelationGetRelationName(matviewRel));
+
+	/*
+	 * The stored query was rewritten at the time of the MV definition, but
+	 * has not been scribbled on by the planner.
+	 */
+	return linitial_node(Query, actions);
+}
+
+
+/* ----------------------------------------------------
+ *		Incremental View Maintenance routines
+ * ---------------------------------------------------
+ */
+
+/*
+ * IVM_immediate_before
+ *
+ * IVM trigger function invoked before base table is modified. If this is
+ * invoked firstly in the same statement, we save the transaction id and the
+ * command id at that time.
+ */
+Datum
+IVM_immediate_before(PG_FUNCTION_ARGS)
+{
+	TriggerData *trigdata = (TriggerData *) fcinfo->context;
+	char	   *matviewOid_text = trigdata->tg_trigger->tgargs[0];
+	char	   *ex_lock_text = trigdata->tg_trigger->tgargs[1];
+	Oid			matviewOid;
+	MV_TriggerHashEntry *entry;
+	bool	found;
+	bool	ex_lock;
+
+	matviewOid = DatumGetObjectId(DirectFunctionCall1(oidin, CStringGetDatum(matviewOid_text)));
+	ex_lock = DatumGetBool(DirectFunctionCall1(boolin, CStringGetDatum(ex_lock_text)));
+
+	/* If the view has more than one tables, we have to use an exclusive lock. */
+	if (ex_lock)
+	{
+		FullTransactionId xid;
+
+		/*
+		 * Wait for concurrent transactions which update this materialized view at
+		 * READ COMMITED. This is needed to see changes committed in other
+		 * transactions. No wait and raise an error at REPEATABLE READ or
+		 * SERIALIZABLE to prevent update anomalies of matviews.
+		 * XXX: dead-lock is possible here.
+		 */
+		if (!IsolationUsesXactSnapshot())
+			LockRelationOid(matviewOid, ExclusiveLock);
+		else if (!ConditionalLockRelationOid(matviewOid, ExclusiveLock))
+		{
+			/* try to throw error by name; relation could be deleted... */
+			char	   *relname = get_rel_name(matviewOid);
+
+			if (!relname)
+				ereport(ERROR,
+						(errcode(ERRCODE_LOCK_NOT_AVAILABLE),
+						errmsg("could not obtain lock on materialized view during incremental maintenance")));
+
+			ereport(ERROR,
+					(errcode(ERRCODE_LOCK_NOT_AVAILABLE),
+					errmsg("could not obtain lock on materialized view \"%s\" during incremental maintenance",
+							relname)));
+		}
+
+		/*
+		 * Even if we can acquire an lock, a concurrent transaction could have
+		 * updated the view incrementally and been committed before we acquired
+		 * the lock. Therefore, we have to check the transaction ID of the most
+		 * recent update of the view, and if this was in progress at the
+		 * transaction start, raise an error to prevent anomalies.
+		 */
+		xid = getLastUpdateXid(matviewOid);
+		if (XidInMVCCSnapshot(XidFromFullTransactionId(xid), GetTransactionSnapshot()))
+			ereport(ERROR,
+					(errcode(ERRCODE_T_R_SERIALIZATION_FAILURE),
+					 errmsg("the materialized view is incrementally updated in concurrent transaction"),
+					 errhint("The transaction might succeed if retried.")));
+	}
+	else
+		LockRelationOid(matviewOid, RowExclusiveLock);
+
+	/*
+	 * On the first call initialize the hashtable
+	 */
+	if (!mv_trigger_info)
+		mv_InitHashTables();
+
+	entry = (MV_TriggerHashEntry *) hash_search(mv_trigger_info,
+											  (void *) &matviewOid,
+											  HASH_ENTER, &found);
+
+	/* On the first BEFORE to update the view, initialize trigger data */
+	if (!found || entry->snapshot == InvalidSnapshot)
+	{
+		Snapshot snapshot;
+
+		/*
+		 * Get a snapshot just before the table was modified for checking
+		 * tuple visibility in the pre-update state of the table.
+		 *
+		 * In READ COMMITTED, use the latest snapshot again to see the
+		 * results of concurrent transactions committed after the current
+		 * transaction started.
+		 */
+		if (IsolationUsesXactSnapshot())
+			snapshot = GetActiveSnapshot();
+		else
+			snapshot = GetTransactionSnapshot();
+
+		entry->matview_id = matviewOid;
+		entry->before_trig_count = 0;
+		entry->after_trig_count = 0;
+		entry->snapshot = RegisterSnapshot(snapshot);
+		entry->tables = NIL;
+		entry->has_old = false;
+		entry->has_new = false;
+
+		/*
+		 * If this is the first table modifying query in the transaction,
+		 * initialize the list of subxids.
+		 */
+		if (!found)
+			entry->subxids = NIL;
+	}
+
+	entry->before_trig_count++;
+
+	return PointerGetDatum(NULL);
+}
+
+/*
+ * IVM_immediate_maintenance
+ *
+ * IVM trigger function invoked after base table is modified.
+ * For each table, tuplestores of transition tables are collected.
+ * and after the last modification
+ */
+Datum
+IVM_immediate_maintenance(PG_FUNCTION_ARGS)
+{
+	TriggerData *trigdata = (TriggerData *) fcinfo->context;
+	Relation	rel;
+	Oid			relid;
+	Oid			matviewOid;
+	Query	   *query;
+	Query	   *rewritten = NULL;
+	char	   *matviewOid_text = trigdata->tg_trigger->tgargs[0];
+	Relation	matviewRel;
+	int old_depth = matview_maintenance_depth;
+	SubTransactionId subxid;
+
+	Oid			relowner;
+	Tuplestorestate *old_tuplestore = NULL;
+	Tuplestorestate *new_tuplestore = NULL;
+	DestReceiver *dest_new = NULL, *dest_old = NULL;
+	Oid			save_userid;
+	int			save_sec_context;
+	int			save_nestlevel;
+
+	MV_TriggerHashEntry *entry;
+	MV_TriggerTable		*table;
+	bool	found;
+
+	ParseState		 *pstate;
+	QueryEnvironment *queryEnv = create_queryEnv();
+	MemoryContext	oldcxt;
+	ListCell   *lc;
+	int			i;
+
+
+	/* Create a ParseState for rewriting the view definition query */
+	pstate = make_parsestate(NULL);
+	pstate->p_queryEnv = queryEnv;
+	pstate->p_expr_kind = EXPR_KIND_SELECT_TARGET;
+
+	rel = trigdata->tg_relation;
+	relid = rel->rd_id;
+
+	matviewOid = DatumGetObjectId(DirectFunctionCall1(oidin, CStringGetDatum(matviewOid_text)));
+
+	/*
+	 * On the first call initialize the hashtable
+	 */
+	if (!mv_trigger_info)
+		mv_InitHashTables();
+
+	/* get the entry for this materialized view */
+	entry = (MV_TriggerHashEntry *) hash_search(mv_trigger_info,
+											  (void *) &matviewOid,
+											  HASH_FIND, &found);
+	Assert (found && entry != NULL);
+	entry->after_trig_count++;
+
+	/* search the entry for the modified table and create new entry if not found */
+	found = false;
+	foreach(lc, entry->tables)
+	{
+		table = (MV_TriggerTable *) lfirst(lc);
+		if (table->table_id == relid)
+		{
+			found = true;
+			break;
+		}
+	}
+	if (!found)
+	{
+		oldcxt = MemoryContextSwitchTo(TopTransactionContext);
+
+		table = (MV_TriggerTable *) palloc0(sizeof(MV_TriggerTable));
+		table->table_id = relid;
+		table->old_tuplestores = NIL;
+		table->new_tuplestores = NIL;
+		table->rte_indexes = NIL;
+		table->slot = MakeSingleTupleTableSlot(RelationGetDescr(rel), table_slot_callbacks(rel));
+		/* We assume we have at least RowExclusiveLock on modified tables. */
+		table->rel = table_open(RelationGetRelid(rel), NoLock);
+		entry->tables = lappend(entry->tables, table);
+
+		MemoryContextSwitchTo(oldcxt);
+	}
+
+	/* Save the transition tables and make a request to not free immediately */
+	if (trigdata->tg_oldtable)
+	{
+		oldcxt = MemoryContextSwitchTo(TopTransactionContext);
+		table->old_tuplestores = lappend(table->old_tuplestores, trigdata->tg_oldtable);
+		entry->has_old = true;
+		MemoryContextSwitchTo(oldcxt);
+	}
+	if (trigdata->tg_newtable)
+	{
+		oldcxt = MemoryContextSwitchTo(TopTransactionContext);
+		table->new_tuplestores = lappend(table->new_tuplestores, trigdata->tg_newtable);
+		entry->has_new = true;
+		MemoryContextSwitchTo(oldcxt);
+	}
+	if (entry->has_new || entry->has_old)
+	{
+		CmdType cmd;
+
+		if (TRIGGER_FIRED_BY_INSERT(trigdata->tg_event))
+			cmd = CMD_INSERT;
+		else if (TRIGGER_FIRED_BY_DELETE(trigdata->tg_event))
+			cmd = CMD_DELETE;
+		else if (TRIGGER_FIRED_BY_UPDATE(trigdata->tg_event))
+			cmd = CMD_UPDATE;
+		else
+			elog(ERROR,"unsupported trigger type");
+
+		/* Prolong lifespan of transition tables to the end of the last AFTER trigger */
+		SetTransitionTablePreserved(relid, cmd);
+	}
+
+
+	/* If this is not the last AFTER trigger call, immediately exit. */
+	Assert (entry->before_trig_count >= entry->after_trig_count);
+	if (entry->before_trig_count != entry->after_trig_count)
+		return PointerGetDatum(NULL);
+
+	/*
+	 * If this is the last AFTER trigger call, continue and update the view.
+	 */
+
+	/* record the subxid that updated the view incrementally */
+	subxid = GetCurrentSubTransactionId();
+	if (!list_member_xid(entry->subxids, subxid))
+	{
+		oldcxt = MemoryContextSwitchTo(TopTransactionContext);
+		entry->subxids = lappend_xid(entry->subxids, subxid);
+		MemoryContextSwitchTo(oldcxt);
+	}
+
+	/*
+	 * Advance command counter to make the updated base table rows locally
+	 * visible.
+	 */
+	CommandCounterIncrement();
+
+	matviewRel = table_open(matviewOid, NoLock);
+
+	/* Make sure it is a materialized view. */
+	Assert(matviewRel->rd_rel->relkind == RELKIND_MATVIEW);
+
+	/*
+	 * In READ COMMITTED, get and push the latest snapshot again to see the
+	 * results of concurrent transactions committed after the current
+	 * transaction started.
+	 */
+	if (!IsolationUsesXactSnapshot())
+		PushActiveSnapshot(GetTransactionSnapshot());
+
+	/*
+	 * Check for active uses of the relation in the current transaction, such
+	 * as open scans.
+	 *
+	 * NB: We count on this to protect us against problems with refreshing the
+	 * data using TABLE_INSERT_FROZEN.
+	 */
+	CheckTableNotInUse(matviewRel, "refresh a materialized view incrementally");
+
+	/*
+	 * Switch to the owner's userid, so that any functions are run as that
+	 * user.  Also arrange to make GUC variable changes local to this command.
+	 * We will switch modes when we are about to execute user code.
+	 */
+	relowner = matviewRel->rd_rel->relowner;
+	GetUserIdAndSecContext(&save_userid, &save_sec_context);
+	SetUserIdAndSecContext(relowner,
+						   save_sec_context | SECURITY_RESTRICTED_OPERATION);
+	save_nestlevel = NewGUCNestLevel();
+
+	/* get view query*/
+	query = get_matview_query(matviewRel);
+
+	/*
+	 * When a base table is truncated, the view content will be empty if the
+	 * view definition query does not contain an aggregate without a GROUP clause.
+	 * Therefore, such views can be truncated.
+	 */
+	if (TRIGGER_FIRED_BY_TRUNCATE(trigdata->tg_event))
+	{
+		ExecuteTruncateGuts(list_make1(matviewRel), list_make1_oid(matviewOid),
+							NIL, DROP_RESTRICT, false, false);
+
+		/* Clean up hash entry and delete tuplestores */
+		clean_up_IVM_hash_entry(entry, false, InvalidSubTransactionId);
+
+		/* Pop the original snapshot. */
+		if (!IsolationUsesXactSnapshot())
+			PopActiveSnapshot();
+
+		table_close(matviewRel, NoLock);
+
+		/* Roll back any GUC changes */
+		AtEOXact_GUC(false, save_nestlevel);
+
+		/* Restore userid and security context */
+		SetUserIdAndSecContext(save_userid, save_sec_context);
+
+		return PointerGetDatum(NULL);
+	}
+
+	/*
+	 * rewrite query for calculating deltas
+	 */
+
+	rewritten = copyObject(query);
+
+	/* Replace resnames in a target list with materialized view's attnames */
+	i = 0;
+	foreach (lc, rewritten->targetList)
+	{
+		TargetEntry *tle = (TargetEntry *) lfirst(lc);
+		Form_pg_attribute attr = TupleDescAttr(matviewRel->rd_att, i);
+		char *resname = NameStr(attr->attname);
+
+		tle->resname = pstrdup(resname);
+		i++;
+	}
+
+	/* Set all tables in the query to pre-update state */
+	rewritten = rewrite_query_for_preupdate_state(rewritten, entry->tables,
+												  pstate, matviewOid);
+	/* Rewrite for counting duplicated tuples */
+	rewritten = rewrite_query_for_counting(rewritten, pstate);
+
+	/* Create tuplestores to store view deltas */
+	if (entry->has_old)
+	{
+		oldcxt = MemoryContextSwitchTo(TopTransactionContext);
+
+		old_tuplestore = tuplestore_begin_heap(false, false, work_mem);
+		dest_old = CreateDestReceiver(DestTuplestore);
+		SetTuplestoreDestReceiverParams(dest_old,
+									old_tuplestore,
+									TopTransactionContext,
+									false,
+									NULL,
+									NULL);
+
+		MemoryContextSwitchTo(oldcxt);
+	}
+	if (entry->has_new)
+	{
+		oldcxt = MemoryContextSwitchTo(TopTransactionContext);
+
+		new_tuplestore = tuplestore_begin_heap(false, false, work_mem);
+		dest_new = CreateDestReceiver(DestTuplestore);
+		SetTuplestoreDestReceiverParams(dest_new,
+									new_tuplestore,
+									TopTransactionContext,
+									false,
+									NULL,
+									NULL);
+		MemoryContextSwitchTo(oldcxt);
+	}
+
+	/* for all modified tables */
+	foreach(lc, entry->tables)
+	{
+		ListCell *lc2;
+
+		table = (MV_TriggerTable *) lfirst(lc);
+
+		/* loop for self-join */
+		foreach(lc2, table->rte_indexes)
+		{
+			int	rte_index = lfirst_int(lc2);
+			TupleDesc		tupdesc_old;
+			TupleDesc		tupdesc_new;
+
+			/* calculate delta tables */
+			calc_delta(table, rte_index, rewritten, dest_old, dest_new,
+					   &tupdesc_old, &tupdesc_new, queryEnv);
+
+			/* Set the table in the query to post-update state */
+			rewritten = rewrite_query_for_postupdate_state(rewritten, table, rte_index);
+
+			PG_TRY();
+			{
+				/* apply the delta tables to the materialized view */
+				apply_delta(matviewOid, old_tuplestore, new_tuplestore,
+							tupdesc_old, tupdesc_new, query);
+			}
+			PG_CATCH();
+			{
+				matview_maintenance_depth = old_depth;
+				PG_RE_THROW();
+			}
+			PG_END_TRY();
+
+			/* clear view delta tuplestores */
+			if (old_tuplestore)
+				tuplestore_clear(old_tuplestore);
+			if (new_tuplestore)
+				tuplestore_clear(new_tuplestore);
+		}
+	}
+
+	/* Clean up hash entry and delete tuplestores */
+	clean_up_IVM_hash_entry(entry, false, InvalidSubTransactionId);
+	if (old_tuplestore)
+	{
+		dest_old->rDestroy(dest_old);
+		tuplestore_end(old_tuplestore);
+	}
+	if (new_tuplestore)
+	{
+		dest_new->rDestroy(dest_new);
+		tuplestore_end(new_tuplestore);
+	}
+
+	/* Pop the original snapshot. */
+	if (!IsolationUsesXactSnapshot())
+		PopActiveSnapshot();
+
+	table_close(matviewRel, NoLock);
+
+	/* Roll back any GUC changes */
+	AtEOXact_GUC(false, save_nestlevel);
+
+	/* Restore userid and security context */
+	SetUserIdAndSecContext(save_userid, save_sec_context);
+
+	return PointerGetDatum(NULL);
+}
+
+/*
+ * rewrite_query_for_preupdate_state
+ *
+ * Rewrite the query so that base tables' RTEs will represent "pre-update"
+ * state of tables. This is necessary to calculate view delta after multiple
+ * tables are modified.
+ */
+static Query*
+rewrite_query_for_preupdate_state(Query *query, List *tables,
+								  ParseState *pstate, Oid matviewid)
+{
+	ListCell *lc;
+	int num_rte = list_length(query->rtable);
+	int i;
+
+
+	/* register delta ENRs */
+	register_delta_ENRs(pstate, query, tables);
+
+	/* XXX: Is necessary? Is this right timing? */
+	AcquireRewriteLocks(query, true, false);
+
+	i = 1;
+	foreach(lc, query->rtable)
+	{
+		RangeTblEntry *r = (RangeTblEntry*) lfirst(lc);
+
+		ListCell *lc2;
+		foreach(lc2, tables)
+		{
+			MV_TriggerTable *table = (MV_TriggerTable *) lfirst(lc2);
+			/*
+			 * if the modified table is found then replace the original RTE with
+			 * "pre-state" RTE and append its index to the list.
+			 */
+			if (r->relid == table->table_id)
+			{
+				List *securityQuals;
+				List *withCheckOptions;
+				bool  hasRowSecurity;
+				bool  hasSubLinks;
+
+				RangeTblEntry *rte_pre = get_prestate_rte(r, table, pstate->p_queryEnv, matviewid);
+
+				/*
+				 * Set a row security poslicies of the modified table to the subquery RTE which
+				 * represents the pre-update state of the table.
+				 */
+				get_row_security_policies(query, table->original_rte, i,
+										  &securityQuals, &withCheckOptions,
+										  &hasRowSecurity, &hasSubLinks);
+
+				if (hasRowSecurity)
+				{
+					query->hasRowSecurity = true;
+					rte_pre->security_barrier = true;
+				}
+				if (hasSubLinks)
+					query->hasSubLinks = true;
+
+				rte_pre->securityQuals = securityQuals;
+				lfirst(lc) = rte_pre;
+
+				table->rte_indexes = lappend_int(table->rte_indexes, i);
+				break;
+			}
+		}
+
+		/* finish the loop if we processed all RTE included in the original query */
+		if (i++ >= num_rte)
+			break;
+	}
+
+	return query;
+}
+
+/*
+ * register_delta_ENRs
+ *
+ * For all modified tables, make ENRs for their transition tables
+ * and register them to the queryEnv. ENR's RTEs are also appended
+ * into the list in query tree.
+ */
+static void
+register_delta_ENRs(ParseState *pstate, Query *query, List *tables)
+{
+	QueryEnvironment *queryEnv = pstate->p_queryEnv;
+	ListCell *lc;
+	RangeTblEntry	*rte;
+
+	foreach(lc, tables)
+	{
+		MV_TriggerTable *table = (MV_TriggerTable *) lfirst(lc);
+		ListCell *lc2;
+		int count;
+
+		count = 0;
+		foreach(lc2, table->old_tuplestores)
+		{
+			Tuplestorestate *oldtable = (Tuplestorestate *) lfirst(lc2);
+			EphemeralNamedRelation enr =
+				palloc(sizeof(EphemeralNamedRelationData));
+			ParseNamespaceItem *nsitem;
+
+			enr->md.name = make_delta_enr_name("old", table->table_id, count);
+			enr->md.reliddesc = table->table_id;
+			enr->md.tupdesc = NULL;
+			enr->md.enrtype = ENR_NAMED_TUPLESTORE;
+			enr->md.enrtuples = tuplestore_tuple_count(oldtable);
+			enr->reldata = oldtable;
+			register_ENR(queryEnv, enr);
+
+			nsitem = addRangeTableEntryForENR(pstate, makeRangeVar(NULL, enr->md.name, -1), true);
+			rte = nsitem->p_rte;
+
+			query->rtable = lappend(query->rtable, rte);
+
+			count++;
+		}
+
+		count = 0;
+		foreach(lc2, table->new_tuplestores)
+		{
+			Tuplestorestate *newtable = (Tuplestorestate *) lfirst(lc2);
+			EphemeralNamedRelation enr =
+				palloc(sizeof(EphemeralNamedRelationData));
+			ParseNamespaceItem *nsitem;
+
+			enr->md.name = make_delta_enr_name("new", table->table_id, count);
+			enr->md.reliddesc = table->table_id;
+			enr->md.tupdesc = NULL;
+			enr->md.enrtype = ENR_NAMED_TUPLESTORE;
+			enr->md.enrtuples = tuplestore_tuple_count(newtable);
+			enr->reldata = newtable;
+			register_ENR(queryEnv, enr);
+
+			nsitem = addRangeTableEntryForENR(pstate, makeRangeVar(NULL, enr->md.name, -1), true);
+			rte = nsitem->p_rte;
+
+			query->rtable = lappend(query->rtable, rte);
+
+			count++;
+		}
+	}
+}
+
+#define DatumGetItemPointer(X)	 ((ItemPointer) DatumGetPointer(X))
+#define PG_GETARG_ITEMPOINTER(n) DatumGetItemPointer(PG_GETARG_DATUM(n))
+
+/*
+ * ivm_visible_in_prestate
+ *
+ * Check visibility of a tuple specified by the tableoid and item pointer
+ * using the snapshot taken just before the table was modified.
+ */
+Datum
+ivm_visible_in_prestate(PG_FUNCTION_ARGS)
+{
+	Oid			tableoid = PG_GETARG_OID(0);
+	ItemPointer itemPtr = PG_GETARG_ITEMPOINTER(1);
+	Oid			matviewOid = PG_GETARG_OID(2);
+	MV_TriggerHashEntry *entry;
+	MV_TriggerTable		*table = NULL;
+	ListCell   *lc;
+	bool	found;
+	bool	result;
+
+	if (!in_delta_calculation)
+		ereport(ERROR,
+				(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+				 errmsg("ivm_visible_in_prestate can be called only in delta calculation")));
+
+	entry = (MV_TriggerHashEntry *) hash_search(mv_trigger_info,
+											  (void *) &matviewOid,
+											  HASH_FIND, &found);
+	Assert (found && entry != NULL);
+
+	foreach(lc, entry->tables)
+	{
+		table = (MV_TriggerTable *) lfirst(lc);
+		if (table->table_id == tableoid)
+			break;
+	}
+
+	Assert (table != NULL);
+
+	result = table_tuple_fetch_row_version(table->rel, itemPtr, entry->snapshot, table->slot);
+
+	PG_RETURN_BOOL(result);
+}
+
+/*
+ * get_prestate_rte
+ *
+ * Rewrite RTE of the modified table to a subquery which represents
+ * "pre-state" table. The original RTE is saved in table->rte_original.
+ */
+static RangeTblEntry*
+get_prestate_rte(RangeTblEntry *rte, MV_TriggerTable *table,
+				 QueryEnvironment *queryEnv, Oid matviewid)
+{
+	StringInfoData str;
+	RawStmt *raw;
+	Query *subquery;
+	ParseState *pstate;
+	char *relname;
+	static char *subquery_tl;
+	int i;
+
+	pstate = make_parsestate(NULL);
+	pstate->p_queryEnv = queryEnv;
+	pstate->p_expr_kind = EXPR_KIND_SELECT_TARGET;
+
+	relname = quote_qualified_identifier(
+					get_namespace_name(RelationGetNamespace(table->rel)),
+									   RelationGetRelationName(table->rel));
+
+	subquery_tl = make_subquery_targetlist_from_table(table);
+
+	/*
+	 * Filtering inserted row using the snapshot taken before the table
+	 * is modified. ctid is required for maintaining outer join views.
+	 */
+	initStringInfo(&str);
+	appendStringInfo(&str,
+		"SELECT %s FROM %s t"
+		" WHERE pg_catalog.ivm_visible_in_prestate(t.tableoid, t.ctid ,%d::pg_catalog.oid)",
+			subquery_tl, relname, matviewid);
+
+	/*
+	 * Re-add rows deleted from the old transition tables, excluding those
+	 * also present in the new transition tables.
+	 */
+	if (list_length(table->old_tuplestores) > 0)
+	{
+		appendStringInfo(&str," UNION ALL SELECT %s  FROM (",
+			subquery_tl);
+
+		for (i = 0; i < list_length(table->old_tuplestores); i++)
+		{
+			if (i != 0)
+				appendStringInfo(&str, " UNION ALL ");
+			appendStringInfo(&str," TABLE %s",
+				make_delta_enr_name("old", table->table_id, i));
+		}
+		for (i = 0; i < list_length(table->new_tuplestores); i++)
+		{
+			appendStringInfo(&str, " EXCEPT ALL ");
+			appendStringInfo(&str," TABLE %s",
+				make_delta_enr_name("new", table->table_id, i));
+		}
+		appendStringInfo(&str,")");
+	}
+
+	/* Get a subquery representing pre-state of the table */
+	raw = (RawStmt*)linitial(raw_parser(str.data, RAW_PARSE_DEFAULT));
+	subquery = transformStmt(pstate, raw->stmt);
+
+	/* save the original RTE */
+	table->original_rte = copyObject(rte);
+
+	rte->rtekind = RTE_SUBQUERY;
+	rte->subquery = subquery;
+	rte->security_barrier = false;
+
+	/* Clear fields that should not be set in a subquery RTE */
+	rte->relid = InvalidOid;
+	rte->relkind = 0;
+	rte->rellockmode = 0;
+	rte->tablesample = NULL;
+	rte->perminfoindex = 0;         /* no permission checking for this RTE */
+	rte->inh = false;			/* must not be set for a subquery */
+
+	return rte;
+}
+
+/*
+ * make_subquery_targetlist_from_table
+ *
+ * Make a targetlist string of a subquery representing a delta table or a
+ * pre-update state table. This subquery substitutes a modified table RTE
+ * in the view definition query during view maintenance. In the targetlist,
+ * column names appear in order of the table definition. However, for
+ * attribute numbers of vars in the query tree to reference columns of the
+ * subquery  correctly even though the table has a dropped column, put "null"
+ * as a dummy value at the position of a dropped column.
+ *
+ * We would also able to walk the query tree to rewrite varattnos, but
+ * crafting targetlist is more simple and reasonable.
+ */
+static char*
+make_subquery_targetlist_from_table(MV_TriggerTable *table)
+{
+	StringInfoData str;
+	TupleDesc	tupdesc;
+	int			i;
+
+	tupdesc = RelationGetDescr(table->rel);
+	initStringInfo(&str);
+	for (i = 0; i < tupdesc->natts; i++)
+	{
+		Form_pg_attribute attr = TupleDescAttr(tupdesc, i);
+
+		if (i > 0)
+			appendStringInfo(&str, ", ");
+
+		if (attr->attisdropped)
+			appendStringInfo(&str, "null");
+		else
+			appendStringInfo(&str, "%s", quote_identifier(NameStr(attr->attname)));
+	}
+
+	return str.data;
+}
+
+/*
+ * make_delta_enr_name
+ *
+ * Make a name for ENR of a transition table from the base table's oid.
+ * prefix will be "new" or "old" depending on its transition table kind..
+ */
+static char*
+make_delta_enr_name(const char *prefix, Oid relid, int count)
+{
+	char buf[NAMEDATALEN];
+	char *name;
+
+	snprintf(buf, NAMEDATALEN, "__ivm_%s_%u_%u", prefix, relid, count);
+	name = pstrdup(buf);
+
+	return name;
+}
+
+/*
+ * makeDeltaTable
+ *
+ * Make a RTE representing a delta of the specified table.
+ */
+static RangeTblEntry*
+makeDeltaTable(RangeTblEntry *rte, MV_TriggerTable *table,
+		   bool is_new, QueryEnvironment *queryEnv)
+{
+	StringInfoData str;
+	ParseState	*pstate;
+	RawStmt *raw;
+	Query *sub;
+	int		i;
+
+	const char *prefix_union = is_new ? "new" : "old";
+	const char *prefix_except = is_new ? "old" : "new";
+	int num_union = is_new ? list_length(table->new_tuplestores) : list_length(table->old_tuplestores);
+	int num_except = is_new ? list_length(table->old_tuplestores) : list_length(table->new_tuplestores);
+
+	/* the previous RTE must be a subquery which represents "pre-state" table */
+	Assert(rte->rtekind == RTE_SUBQUERY);
+
+	/* Create a ParseState for rewriting the view definition query */
+	pstate = make_parsestate(NULL);
+	pstate->p_queryEnv = queryEnv;
+	pstate->p_expr_kind = EXPR_KIND_NONE;
+
+	initStringInfo(&str);
+	appendStringInfo(&str,
+		" SELECT %s FROM ( ",
+		make_subquery_targetlist_from_table(table));
+
+	for (i = 0; i < num_union; i++)
+	{
+		if (i > 0)
+			appendStringInfo(&str, " UNION ALL ");
+
+		appendStringInfo(&str,
+			" TABLE  %s",
+			make_delta_enr_name(prefix_union, table->table_id, i));
+	}
+	for (i = 0; i < num_except; i++)
+	{
+		appendStringInfo(&str, " EXCEPT ALL ");
+
+		appendStringInfo(&str,
+			" TABLE  %s",
+			make_delta_enr_name(prefix_except, table->table_id, i));
+	}
+	appendStringInfo(&str,")");
+
+	raw = (RawStmt*)linitial(raw_parser(str.data, RAW_PARSE_DEFAULT));
+	sub = transformStmt(pstate, raw->stmt);
+
+	/*
+	 * Update the subquery so that it represent the combined transition
+	 * table.  Note that we leave the security_barrier and securityQuals
+	 * fields so that the subquery relation can be protected by the RLS
+	 * policy as same as the modified table.
+	 */
+	rte->rtekind = RTE_SUBQUERY;
+	rte->subquery = sub;
+
+	return rte;
+}
+
+/*
+ * rewrite_query_for_counting
+ *
+ * Rewrite query for counting duplicated tuples.
+ */
+static Query *
+rewrite_query_for_counting(Query *query, ParseState *pstate)
+{
+	TargetEntry *tle_count;
+	FuncCall *fn;
+	Node *node;
+
+	/* Add count(*) for counting distinct tuples in views */
+	fn = makeFuncCall(SystemFuncName("count"), NIL, COERCE_EXPLICIT_CALL, -1);
+	fn->agg_star = true;
+	if (!query->groupClause && !query->hasAggs)
+		query->groupClause = transformDistinctClause(NULL, &query->targetList, query->sortClause, false);
+
+	node = ParseFuncOrColumn(pstate, fn->funcname, NIL, NULL, fn, false, -1);
+
+	tle_count = makeTargetEntry((Expr *) node,
+								list_length(query->targetList) + 1,
+								pstrdup("__ivm_count__"),
+								false);
+	query->targetList = lappend(query->targetList, tle_count);
+	query->hasAggs = true;
+
+	return query;
+}
+
+/*
+ * calc_delta
+ *
+ * Calculate view deltas generated under the modification of a table specified
+ * by the RTE index.
+ */
+static void
+calc_delta(MV_TriggerTable *table, int rte_index, Query *query,
+			DestReceiver *dest_old, DestReceiver *dest_new,
+			TupleDesc *tupdesc_old, TupleDesc *tupdesc_new,
+			QueryEnvironment *queryEnv)
+{
+	ListCell *lc = list_nth_cell(query->rtable, rte_index - 1);
+	RangeTblEntry *rte = (RangeTblEntry *) lfirst(lc);
+
+	in_delta_calculation = true;
+
+	/* Generate old delta */
+	if (dest_old && list_length(table->old_tuplestores) > 0)
+	{
+		/* Replace the modified table with the old delta table and calculate the old view delta. */
+		lfirst(lc) = makeDeltaTable(rte, table, false, queryEnv);
+		refresh_matview_datafill(dest_old, query, queryEnv, tupdesc_old, "", false);
+	}
+
+	/* Generate new delta */
+	if (dest_new && list_length(table->new_tuplestores) > 0)
+	{
+		/* Replace the modified table with the new delta table and calculate the new view delta*/
+		lfirst(lc) = makeDeltaTable(rte, table, true, queryEnv);
+		refresh_matview_datafill(dest_new, query, queryEnv, tupdesc_new, "", false);
+	}
+
+	in_delta_calculation = false;
+}
+
+/*
+ * rewrite_query_for_postupdate_state
+ *
+ * Rewrite the query so that the specified base table's RTEs will represent
+ * "post-update" state of tables. This is called after the view delta
+ * calculation due to changes on this table finishes.
+ */
+static Query*
+rewrite_query_for_postupdate_state(Query *query, MV_TriggerTable *table, int rte_index)
+{
+	ListCell *lc = list_nth_cell(query->rtable, rte_index - 1);
+
+	/* Retore the original RTE */
+	lfirst(lc) = table->original_rte;
+
+	return query;
+}
+
+/*
+ * apply_delta
+ *
+ * Apply deltas to the materialized view. In outer join cases, this requires
+ * the view maintenance graph.
+ */
+static void
+apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *new_tuplestores,
+			TupleDesc tupdesc_old, TupleDesc tupdesc_new,
+			Query *query)
+{
+	StringInfoData querybuf;
+	StringInfoData target_list_buf;
+	Relation	matviewRel;
+	char	   *matviewname;
+	ListCell	*lc;
+	int			i;
+	List	   *keys = NIL;
+
+
+	/*
+	 * get names of the materialized view and delta tables
+	 */
+
+	matviewRel = table_open(matviewOid, NoLock);
+	matviewname = quote_qualified_identifier(get_namespace_name(RelationGetNamespace(matviewRel)),
+											 RelationGetRelationName(matviewRel));
+
+	/*
+	 * Build parts of the maintenance queries
+	 */
+
+	initStringInfo(&querybuf);
+	initStringInfo(&target_list_buf);
+
+	/* build string of target list */
+	for (i = 0; i < matviewRel->rd_att->natts; i++)
+	{
+		Form_pg_attribute attr = TupleDescAttr(matviewRel->rd_att, i);
+		char   *resname = NameStr(attr->attname);
+
+		if (i != 0)
+			appendStringInfo(&target_list_buf, ", ");
+		appendStringInfo(&target_list_buf, "%s", quote_qualified_identifier(NULL, resname));
+	}
+
+	i = 0;
+	foreach (lc, query->targetList)
+	{
+		TargetEntry *tle = (TargetEntry *) lfirst(lc);
+		Form_pg_attribute attr = TupleDescAttr(matviewRel->rd_att, i);
+
+		i++;
+
+		if (tle->resjunk)
+			continue;
+
+		keys = lappend(keys, attr);
+	}
+
+	/* Start maintaining the materialized view. */
+	OpenMatViewIncrementalMaintenance();
+
+	/* Open SPI context. */
+	if (SPI_connect() != SPI_OK_CONNECT)
+		elog(ERROR, "SPI_connect failed");
+
+	/* For tuple deletion */
+	if (old_tuplestores && tuplestore_tuple_count(old_tuplestores) > 0)
+	{
+		EphemeralNamedRelation enr = palloc(sizeof(EphemeralNamedRelationData));
+		int				rc;
+
+		/* convert tuplestores to ENR, and register for SPI */
+		enr->md.name = pstrdup(OLD_DELTA_ENRNAME);
+		enr->md.reliddesc = InvalidOid;
+		enr->md.tupdesc = tupdesc_old;
+		enr->md.enrtype = ENR_NAMED_TUPLESTORE;
+		enr->md.enrtuples = tuplestore_tuple_count(old_tuplestores);
+		enr->reldata = old_tuplestores;
+
+		rc = SPI_register_relation(enr);
+		if (rc != SPI_OK_REL_REGISTER)
+			elog(ERROR, "SPI_register failed");
+
+		apply_old_delta(matviewname, OLD_DELTA_ENRNAME, keys);
+
+	}
+	/* For tuple insertion */
+	if (new_tuplestores && tuplestore_tuple_count(new_tuplestores) > 0)
+	{
+		EphemeralNamedRelation enr = palloc(sizeof(EphemeralNamedRelationData));
+		int rc;
+
+		/* convert tuplestores to ENR, and register for SPI */
+		enr->md.name = pstrdup(NEW_DELTA_ENRNAME);
+		enr->md.reliddesc = InvalidOid;
+		enr->md.tupdesc = tupdesc_new;;
+		enr->md.enrtype = ENR_NAMED_TUPLESTORE;
+		enr->md.enrtuples = tuplestore_tuple_count(new_tuplestores);
+		enr->reldata = new_tuplestores;
+
+		rc = SPI_register_relation(enr);
+		if (rc != SPI_OK_REL_REGISTER)
+			elog(ERROR, "SPI_register failed");
+
+		/* apply new delta */
+		apply_new_delta(matviewname, NEW_DELTA_ENRNAME, &target_list_buf);
+	}
+
+	/* We're done maintaining the materialized view. */
+	CloseMatViewIncrementalMaintenance();
+
+	table_close(matviewRel, NoLock);
+
+	/* Close SPI context. */
+	if (SPI_finish() != SPI_OK_FINISH)
+		elog(ERROR, "SPI_finish failed");
+}
+
+/*
+ * apply_old_delta
+ *
+ * Execute a query for applying a delta table given by deltname_old
+ * which contains tuples to be deleted from to a materialized view given by
+ * matviewname.  This is used when counting is not required.
+ */
+static void
+apply_old_delta(const char *matviewname, const char *deltaname_old,
+				List *keys)
+{
+	StringInfoData	querybuf;
+	StringInfoData	keysbuf;
+	char   *match_cond;
+	ListCell *lc;
+
+	/* build WHERE condition for searching tuples to be deleted */
+	match_cond = get_matching_condition_string(keys);
+
+	/* build string of keys list */
+	initStringInfo(&keysbuf);
+	foreach (lc, keys)
+	{
+		Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc);
+		char   *resname = NameStr(attr->attname);
+		appendStringInfo(&keysbuf, "%s", quote_qualified_identifier("mv", resname));
+		if (lnext(keys, lc))
+			appendStringInfo(&keysbuf, ", ");
+	}
+
+	/* Search for matching tuples from the view and update or delete if found. */
+	initStringInfo(&querybuf);
+	appendStringInfo(&querybuf,
+	"DELETE FROM %s WHERE ctid IN ("
+		"SELECT tid FROM (SELECT pg_catalog.row_number() over (partition by %s) AS \"__ivm_row_number__\","
+								  "mv.ctid AS tid,"
+								  "diff.\"__ivm_count__\""
+						 "FROM %s AS mv, %s AS diff "
+						 "WHERE %s) v "
+					"WHERE v.\"__ivm_row_number__\" OPERATOR(pg_catalog.<=) v.\"__ivm_count__\")",
+					matviewname,
+					keysbuf.data,
+					matviewname, deltaname_old,
+					match_cond);
+
+	if (SPI_exec(querybuf.data, 0) != SPI_OK_DELETE)
+		elog(ERROR, "SPI_exec failed: %s", querybuf.data);
+}
+
+/*
+ * apply_new_delta
+ *
+ * Execute a query for applying a delta table given by deltname_new
+ * which contains tuples to be inserted into a materialized view given by
+ * matviewname.  This is used when counting is not required.
+ */
+static void
+apply_new_delta(const char *matviewname, const char *deltaname_new,
+				StringInfo target_list)
+{
+	StringInfoData	querybuf;
+
+	/* Search for matching tuples from the view and update or delete if found. */
+	initStringInfo(&querybuf);
+	appendStringInfo(&querybuf,
+					"INSERT INTO %s (%s) SELECT %s FROM ("
+						"SELECT diff.*, pg_catalog.generate_series(1, diff.\"__ivm_count__\")"
+							" AS __ivm_generate_series__ "
+						"FROM %s AS diff) AS v",
+					matviewname, target_list->data, target_list->data,
+					deltaname_new);
+
+	if (SPI_exec(querybuf.data, 0) != SPI_OK_INSERT)
+		elog(ERROR, "SPI_exec failed: %s", querybuf.data);
+}
+
+/*
+ * get_matching_condition_string
+ *
+ * Build a predicate string for looking for a tuple with given keys.
+ */
+static char *
+get_matching_condition_string(List *keys)
+{
+	StringInfoData match_cond;
+	ListCell	*lc;
+
+	/* If there is no key columns, the condition is always true. */
+	if (keys == NIL)
+		return "true";
+
+	initStringInfo(&match_cond);
+	foreach (lc, keys)
+	{
+		Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc);
+		char   *resname = NameStr(attr->attname);
+		char   *mv_resname = quote_qualified_identifier("mv", resname);
+		char   *diff_resname = quote_qualified_identifier("diff", resname);
+		Oid		typid = attr->atttypid;
+
+		/* Considering NULL values, we can not use simple = operator. */
+		appendStringInfo(&match_cond, "(");
+		generate_equal(&match_cond, typid, mv_resname, diff_resname);
+		appendStringInfo(&match_cond, " OR (%s IS NULL AND %s IS NULL))",
+						 mv_resname, diff_resname);
+
+		if (lnext(keys, lc))
+			appendStringInfo(&match_cond, " AND ");
+	}
+
+	return match_cond.data;
+}
+
+/*
+ * generate_equals
+ *
+ * Generate an equality clause using given operands' default equality
+ * operator.
+ */
+static void
+generate_equal(StringInfo querybuf, Oid opttype,
+			   const char *leftop, const char *rightop)
+{
+	TypeCacheEntry *typentry;
+
+	typentry = lookup_type_cache(opttype, TYPECACHE_EQ_OPR);
+	if (!OidIsValid(typentry->eq_opr))
+		ereport(ERROR,
+				(errcode(ERRCODE_UNDEFINED_FUNCTION),
+				 errmsg("could not identify an equality operator for type %s",
+						format_type_be_qualified(opttype))));
+
+	generate_operator_clause(querybuf,
+							 leftop, opttype,
+							 typentry->eq_opr,
+							 rightop, opttype);
+}
+
+/*
+ * mv_InitHashTables
+ */
+static void
+mv_InitHashTables(void)
+{
+	HASHCTL		ctl;
+
+	memset(&ctl, 0, sizeof(ctl));
+	ctl.keysize = sizeof(Oid);
+	ctl.entrysize = sizeof(MV_TriggerHashEntry);
+	mv_trigger_info = hash_create("MV trigger info",
+								 MV_INIT_QUERYHASHSIZE,
+								 &ctl, HASH_ELEM | HASH_BLOBS);
+
+	memset(&ctl, 0, sizeof(ctl));
+	ctl.keysize = sizeof(Oid);
+	ctl.entrysize = sizeof(DroppedImmvInfo);
+	dropped_immv = hash_create("Dropped IMMVs", 16,
+							   &ctl, HASH_ELEM | HASH_BLOBS);
+}
+
+/*
+ * AtAbort_IVM
+ *
+ * Clean up hash entries for all materialized views. This is called at
+ * (sub-)transaction abort. When the top-level transaction is aborted,
+ * InvalidSubTransactionId is set to subxid.
+ *
+ * Also, remove dropped IMMV information if it is aborted.
+ */
+void
+AtAbort_IVM(SubTransactionId subxid)
+{
+	HASH_SEQ_STATUS seq;
+
+	if (mv_trigger_info)
+	{
+		MV_TriggerHashEntry *entry;
+		hash_seq_init(&seq, mv_trigger_info);
+		while ((entry = hash_seq_search(&seq)) != NULL)
+			clean_up_IVM_hash_entry(entry, true, subxid);
+	}
+
+	if (dropped_immv)
+	{
+		DroppedImmvInfo *entry;
+		hash_seq_init(&seq, dropped_immv);
+		while ((entry = hash_seq_search(&seq)) != NULL)
+		{
+			if (subxid == InvalidSubTransactionId || subxid == entry->subxid)
+				hash_search(dropped_immv, (void *) &entry->immv_oid, HASH_REMOVE, NULL);
+		}
+	}
+
+	in_delta_calculation = false;
+}
+
+/*
+ * AtPreCommit_IVM
+ *
+ * Record the transaction ID that updated the view incrementally.
+ * Also, remove the entry for dropped IMMVs.
+ */
+void
+AtPreCommit_IVM(void)
+{
+	HASH_SEQ_STATUS seq;
+
+	if (mv_trigger_info)
+	{
+		MV_TriggerHashEntry *entry;
+
+		/*
+		 * Record the transaction ID that udpate the view incrementally,
+		 * and perform the final clean up of the entry.
+		 */
+		hash_seq_init(&seq, mv_trigger_info);
+		while ((entry = hash_seq_search(&seq)) != NULL)
+		{
+			setLastUpdateXid(entry->matview_id, GetTopFullTransactionId());
+			hash_search(mv_trigger_info, (void *) &entry->matview_id, HASH_REMOVE, NULL);
+		}
+	}
+
+	if (dropped_immv)
+	{
+		DroppedImmvInfo *entry;
+
+		LWLockAcquire(IvmControlLock, LW_EXCLUSIVE);
+		hash_seq_init(&seq, dropped_immv);
+		while ((entry = hash_seq_search(&seq)) != NULL)
+		{
+			hash_search(LastIvmUpdateHash, (void *) &entry->immv_oid, HASH_REMOVE, NULL);
+			hash_search(dropped_immv, (void *) &entry->immv_oid, HASH_REMOVE, NULL);
+		}
+		LWLockRelease(IvmControlLock);
+	}
+
+	in_delta_calculation = false;
+}
+
+/*
+ * clean_up_IVM_hash_entry
+ *
+ * Clean up tuple stores and hash entries for a materialized view after its
+ * maintenance finished. This is called at the end of table modifying query
+ * or (sub-)transaction abort. When the top-level transaction is aborted,
+ * InvalidSubTransactionId is set to subxid.
+ */
+static void
+clean_up_IVM_hash_entry(MV_TriggerHashEntry *entry, bool is_abort,
+						SubTransactionId subxid)
+{
+	bool found;
+	ListCell *lc;
+
+	/* clean up tuple stores */
+	foreach(lc, entry->tables)
+	{
+		MV_TriggerTable *table = (MV_TriggerTable *) lfirst(lc);
+
+		list_free(table->old_tuplestores);
+		list_free(table->new_tuplestores);
+		if (!is_abort)
+		{
+			ExecDropSingleTupleTableSlot(table->slot);
+			table_close(table->rel, NoLock);
+		}
+	}
+	list_free(entry->tables);
+	entry->tables = NIL;
+
+	if (is_abort)
+	{
+		bool	remove_entry = false;
+
+		/*
+		 * When the top-level transaction is aborted, remove all subxids.
+		 * When a sub-transaction is aborted, remove only its subxid.
+		 */
+		if (subxid == InvalidSubTransactionId)
+			remove_entry = true;
+		else
+		{
+			foreach(lc, entry->subxids)
+			{
+				if (lfirst_xid(lc) == subxid)
+				{
+					entry->subxids = list_delete_cell(entry->subxids, lc);
+					break;
+				}
+			}
+
+			/*
+			 * If all the subxid are removed, it means that the view was not
+			 * updated at all in this transaction.
+			 */
+			if (list_length(entry->subxids) == 0)
+				remove_entry = true;
+		}
+
+		/*
+		 * Remove entries of not updated views from the hash table.
+		 */
+		if (remove_entry)
+			hash_search(mv_trigger_info, (void *) &entry->matview_id, HASH_REMOVE, &found);
+	}
+	else
+	{
+		/* When the query sucsessully finished, unregister the snapshot */
+		UnregisterSnapshot(entry->snapshot);
+	}
+
+	entry->snapshot = InvalidSnapshot;
+}
+
+/*
+ * setLastUpdateXid
+ *
+ * Store the transaction ID that updated the view incremenally.
+ */
+static void
+setLastUpdateXid(Oid immv_oid, FullTransactionId xid)
+{
+	LastIvmUpdateEntry *entry;
+
+	LWLockAcquire(IvmControlLock, LW_EXCLUSIVE);
+	entry = (LastIvmUpdateEntry *) hash_search(LastIvmUpdateHash, (void *) &immv_oid, HASH_ENTER, NULL);
+	entry->oid = immv_oid;
+	entry->last_ivm_update = xid;
+	LWLockRelease(IvmControlLock);
+}
+
+/*
+ * getLastUpdateXid
+ *
+ * Get the most recent transaction ID that updated the view incrementally.
+ */
+static FullTransactionId
+getLastUpdateXid(Oid immv_oid)
+{
+	FullTransactionId xid = InvalidFullTransactionId;
+	LastIvmUpdateEntry *entry;
+	bool found;
+
+	LWLockAcquire(IvmControlLock, LW_SHARED);
+	entry = (LastIvmUpdateEntry *) hash_search(LastIvmUpdateHash, (void *) &immv_oid, HASH_FIND, &found);
+	LWLockRelease(IvmControlLock);
+	if (found)
+		xid = entry->last_ivm_update;
+
+	return xid;
+}
+
+void
+removeImmv(Oid immv_oid)
+{
+	DroppedImmvInfo *entry;
+
+	if (!dropped_immv)
+		mv_InitHashTables();
+
+	entry = (DroppedImmvInfo *) hash_search(dropped_immv, (void *) &immv_oid, HASH_ENTER, NULL);
+	entry->subxid = GetCurrentSubTransactionId();
+}
+
+/*
+ * isIvmName
+ *
+ * Check if this is a IVM hidden column from the name.
+ */
+bool
+isIvmName(const char *s)
+{
+	if (s)
+		return (strncmp(s, "__ivm_", 6) == 0);
+	return false;
+}
diff --git a/src/backend/commands/tablecmds.c b/src/backend/commands/tablecmds.c
index 472db112fa7..920b62d254d 100644
--- a/src/backend/commands/tablecmds.c
+++ b/src/backend/commands/tablecmds.c
@@ -62,6 +62,7 @@
 #include "commands/defrem.h"
 #include "commands/event_trigger.h"
 #include "commands/extension.h"
+#include "commands/matview.h"
 #include "commands/repack.h"
 #include "commands/sequence.h"
 #include "commands/tablecmds.h"
@@ -1811,6 +1812,9 @@ RangeVarCallbackForDropRelation(const RangeVar *rel, Oid relOid, Oid oldRelOid,
 	state->actual_relkind = classform->relkind;
 	state->actual_relpersistence = classform->relpersistence;
 
+	if (classform->relkind == RELKIND_MATVIEW && classform->relisivm)
+		removeImmv(relOid);
+
 	/*
 	 * Both RELKIND_RELATION and RELKIND_PARTITIONED_TABLE are OBJECT_TABLE,
 	 * but RemoveRelations() can only pass one relkind for a given relation.
diff --git a/src/backend/utils/activity/wait_event_names.txt b/src/backend/utils/activity/wait_event_names.txt
index 560659f9568..d97c35eeef0 100644
--- a/src/backend/utils/activity/wait_event_names.txt
+++ b/src/backend/utils/activity/wait_event_names.txt
@@ -370,6 +370,7 @@ WaitLSN	"Waiting to read or update shared Wait-for-LSN state."
 LogicalDecodingControl	"Waiting to read or update logical decoding status information."
 DataChecksumsWorker	"Waiting for data checksums worker."
 AioWorkerControl	"Waiting to update AIO worker information."
+IvmControl	"Waiting for read or update IMMV information.."
 
 #
 # END OF PREDEFINED LWLOCKS (DO NOT CHANGE THIS LINE)
diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat
index 73bb7fbb430..88399513f87 100644
--- a/src/include/catalog/pg_proc.dat
+++ b/src/include/catalog/pg_proc.dat
@@ -12698,4 +12698,14 @@
   proname => 'hashoid8extended', prorettype => 'int8',
   proargtypes => 'oid8 int8', prosrc => 'hashoid8extended' },
 
+# IVM
+{ oid => '786', descr => 'ivm trigger (before)',
+  proname => 'IVM_immediate_before', provolatile => 'v', prorettype => 'trigger',
+  proargtypes => '', prosrc => 'IVM_immediate_before' },
+{ oid => '787', descr => 'ivm trigger (after)',
+  proname => 'IVM_immediate_maintenance', provolatile => 'v', prorettype => 'trigger',
+  proargtypes => '', prosrc => 'IVM_immediate_maintenance' },
+{ oid => '788', descr => 'ivm filetring ',
+  proname => 'ivm_visible_in_prestate', provolatile => 's', prorettype => 'bool',
+  proargtypes => 'oid tid oid', prosrc => 'ivm_visible_in_prestate' },
 ]
diff --git a/src/include/commands/createas.h b/src/include/commands/createas.h
index f895c67c0c2..c286ebcd70e 100644
--- a/src/include/commands/createas.h
+++ b/src/include/commands/createas.h
@@ -16,6 +16,7 @@
 
 #include "catalog/objectaddress.h"
 #include "nodes/params.h"
+#include "nodes/pathnodes.h"
 #include "parser/parse_node.h"
 #include "tcop/dest.h"
 #include "utils/queryenvironment.h"
@@ -25,6 +26,9 @@ extern ObjectAddress ExecCreateTableAs(ParseState *pstate, CreateTableAsStmt *st
 									   ParamListInfo params, QueryEnvironment *queryEnv,
 									   QueryCompletion *qc);
 
+extern void CreateIvmTriggersOnBaseTables(Query *qry, Oid matviewOid);
+extern void CreateIndexOnIMMV(Query *query, Relation matviewRel);
+
 extern int	GetIntoRelEFlags(IntoClause *intoClause);
 
 extern DestReceiver *CreateIntoRelDestReceiver(IntoClause *intoClause);
diff --git a/src/include/commands/matview.h b/src/include/commands/matview.h
index 738c731c1a9..f1dbfc052c5 100644
--- a/src/include/commands/matview.h
+++ b/src/include/commands/matview.h
@@ -15,6 +15,7 @@
 #define MATVIEW_H
 
 #include "catalog/objectaddress.h"
+#include "fmgr.h"
 #include "nodes/params.h"
 #include "nodes/parsenodes.h"
 #include "tcop/dest.h"
@@ -23,6 +24,8 @@
 
 extern void SetMatViewPopulatedState(Relation relation, bool newstate);
 
+extern void SetMatViewIVMState(Relation relation, bool newstate);
+
 extern ObjectAddress ExecRefreshMatView(RefreshMatViewStmt *stmt, const char *queryString,
 										QueryCompletion *qc);
 extern ObjectAddress RefreshMatViewByOid(Oid matviewOid, bool is_create, bool skipData,
@@ -33,4 +36,12 @@ extern DestReceiver *CreateTransientRelDestReceiver(Oid transientoid);
 
 extern bool MatViewIncrementalMaintenanceIsEnabled(void);
 
+extern Datum IVM_immediate_before(PG_FUNCTION_ARGS);
+extern Datum IVM_immediate_maintenance(PG_FUNCTION_ARGS);
+extern Datum IVM_visible_in_prestate(PG_FUNCTION_ARGS);
+extern void AtAbort_IVM(SubTransactionId subtxid);
+extern void AtPreCommit_IVM(void);
+extern void removeImmv(Oid immv_oid);
+extern bool isIvmName(const char *s);
+
 #endif							/* MATVIEW_H */
diff --git a/src/include/storage/lwlocklist.h b/src/include/storage/lwlocklist.h
index d7eb648bd27..756c63baf97 100644
--- a/src/include/storage/lwlocklist.h
+++ b/src/include/storage/lwlocklist.h
@@ -89,6 +89,7 @@ PG_LWLOCK(54, WaitLSN)
 PG_LWLOCK(55, LogicalDecodingControl)
 PG_LWLOCK(56, DataChecksumsWorker)
 PG_LWLOCK(57, AioWorkerControl)
+PG_LWLOCK(58, IvmControl)
 
 /*
  * There also exist several built-in LWLock tranches.  As with the predefined
diff --git a/src/include/storage/subsystemlist.h b/src/include/storage/subsystemlist.h
index 9ad619080be..481e15d00a1 100644
--- a/src/include/storage/subsystemlist.h
+++ b/src/include/storage/subsystemlist.h
@@ -88,3 +88,6 @@ PG_SHMEM_SUBSYSTEM(DataChecksumsShmemCallbacks)
 
 /* AIO subsystem. This delegates to the method-specific callbacks */
 PG_SHMEM_SUBSYSTEM(AioShmemCallbacks)
+
+/* Incremental View Maintenance */
+PG_SHMEM_SUBSYSTEM(IvmShmemCallbacks)
-- 
2.43.0


--Multipart=_Wed__1_Jul_2026_00_04_01_+0900_OVSy2WWK_9aByzDJ
Content-Type: text/x-diff;
 name="v38-0005-Add-Incremental-View-Maintenance-support-to-psql.patch"
Content-Disposition: attachment;
 filename="v38-0005-Add-Incremental-View-Maintenance-support-to-psql.patch"
Content-Transfer-Encoding: 7bit



^ permalink  raw  reply  [nested|flat] 101+ messages in thread

* [PATCH v37 06/11] Add Incremental View Maintenance support
@ 2026-05-29 09:06  Yugo Nagata <[email protected]>
  0 siblings, 0 replies; 101+ messages in thread

From: Yugo Nagata @ 2026-05-29 09:06 UTC (permalink / raw)

In this implementation, AFTER triggers are used to collect
tuplestores containing transition table contents. When multiple tables
are changed, multiple AFTER triggers are invoked, then the final AFTER
trigger performs actual update of the matview. In addition, BEFORE
triggers are also used to handle global information for view
maintenance.

To calculate view deltas, we need both pre-state and post-state of base
tables. Post-update states are available in AFTER trigger, and pre-update
states can be calculated by removing inserted tuples and appending deleted
tuples. Insterted tuples are filtered using the snapshot taken before
table modification, and deleted tuples are contained in the old transition
table.

Incrementally Maintainable Materialized Views (IMMV) can contain
duplicated tuples.

This patch also allows self-join, simultaneous updates of more than
one base table, and multiple updates of the same base table.
---
 src/backend/access/transam/xact.c             |    8 +
 src/backend/commands/createas.c               |  709 +++++++
 src/backend/commands/matview.c                | 1835 ++++++++++++++++-
 src/backend/commands/tablecmds.c              |    4 +
 .../utils/activity/wait_event_names.txt       |    1 +
 src/include/catalog/pg_proc.dat               |   10 +
 src/include/commands/createas.h               |    4 +
 src/include/commands/matview.h                |   11 +
 src/include/storage/lwlocklist.h              |    1 +
 src/include/storage/subsystemlist.h           |    3 +
 10 files changed, 2548 insertions(+), 38 deletions(-)

diff --git a/src/backend/access/transam/xact.c b/src/backend/access/transam/xact.c
index 5586fbe5b07..302a4822d50 100644
--- a/src/backend/access/transam/xact.c
+++ b/src/backend/access/transam/xact.c
@@ -37,6 +37,7 @@
 #include "catalog/pg_enum.h"
 #include "catalog/storage.h"
 #include "commands/async.h"
+#include "commands/matview.h"
 #include "commands/tablecmds.h"
 #include "commands/trigger.h"
 #include "common/pg_prng.h"
@@ -2322,6 +2323,9 @@ CommitTransaction(void)
 	CallXactCallbacks(is_parallel_worker ? XACT_EVENT_PARALLEL_PRE_COMMIT
 					  : XACT_EVENT_PRE_COMMIT);
 
+	/* Store the transaction ID that updated the view incrementally */
+	AtPreCommit_IVM();
+
 	/*
 	 * If this xact has started any unfinished parallel operation, clean up
 	 * its workers, warning about leaked resources.  (But we don't actually
@@ -2971,6 +2975,7 @@ AbortTransaction(void)
 	AtAbort_Notify();
 	AtEOXact_RelationMap(false, is_parallel_worker);
 	AtAbort_Twophase();
+	AtAbort_IVM(InvalidSubTransactionId);
 
 	/*
 	 * Advertise the fact that we aborted in pg_xact (assuming that we got as
@@ -5301,6 +5306,9 @@ AbortSubTransaction(void)
 
 	UnlockBuffers();
 
+	/* Clean up hash entries for incremental view maintenance */
+	AtAbort_IVM(s->subTransactionId);
+
 	/* Reset WAL record construction state */
 	XLogResetInsertion();
 
diff --git a/src/backend/commands/createas.c b/src/backend/commands/createas.c
index 6dbb831ca89..a499688b79d 100644
--- a/src/backend/commands/createas.c
+++ b/src/backend/commands/createas.c
@@ -29,18 +29,32 @@
 #include "access/tableam.h"
 #include "access/xact.h"
 #include "catalog/namespace.h"
+#include "catalog/index.h"
+#include "catalog/pg_am_d.h"
+#include "catalog/pg_constraint.h"
+#include "catalog/pg_inherits.h"
+#include "catalog/pg_trigger.h"
 #include "catalog/toasting.h"
 #include "commands/createas.h"
+#include "commands/defrem.h"
 #include "commands/matview.h"
 #include "commands/prepare.h"
 #include "commands/tablecmds.h"
+#include "commands/tablespace.h"
+#include "commands/trigger.h"
 #include "commands/view.h"
 #include "executor/execdesc.h"
 #include "executor/executor.h"
+#include "miscadmin.h"
 #include "nodes/makefuncs.h"
 #include "nodes/nodeFuncs.h"
 #include "nodes/queryjumble.h"
+#include "optimizer/optimizer.h"
+#include "optimizer/prep.h"
 #include "parser/analyze.h"
+#include "parser/parser.h"
+#include "parser/parsetree.h"
+#include "parser/parse_clause.h"
 #include "rewrite/rewriteHandler.h"
 #include "tcop/tcopprot.h"
 #include "utils/builtins.h"
@@ -70,6 +84,12 @@ static bool intorel_receive(TupleTableSlot *slot, DestReceiver *self);
 static void intorel_shutdown(DestReceiver *self);
 static void intorel_destroy(DestReceiver *self);
 
+static void CreateIvmTriggersOnBaseTablesRecurse(Query *qry, Node *node, Oid matviewOid,
+									 List **relids, bool ex_lock);
+static void CreateIvmTrigger(Oid relOid, Oid viewOid, int16 type, int16 timing, bool ex_lock);
+static void check_ivm_restriction(Node *node);
+static bool check_ivm_restriction_walker(Node *node, void *context);
+static Bitmapset *get_primary_key_attnos_from_query(Query *query, List **constraintList);
 
 /*
  * create_ctas_internal
@@ -277,6 +297,18 @@ ExecCreateTableAs(ParseState *pstate, CreateTableAsStmt *stmt,
 		into->skipData = true;
 	}
 
+	if (is_matview && into->ivm)
+	{
+		/* check if the query is supported in IMMV definition */
+		if (contain_mutable_functions((Node *) query))
+			ereport(ERROR,
+					(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+					 errmsg("mutable function is not supported on incrementally maintainable materialized view"),
+					 errhint("functions must be marked IMMUTABLE")));
+
+		check_ivm_restriction((Node *) query);
+	}
+
 	if (into->skipData)
 	{
 		/*
@@ -287,15 +319,36 @@ ExecCreateTableAs(ParseState *pstate, CreateTableAsStmt *stmt,
 		 */
 		address = create_ctas_nodata(query->targetList, into);
 
+		/*
+		 * For IVM, mark the matview before refresh so RelationIsIVM()
+		 * returns true inside RefreshMatViewByOid.
+		 */
+		if (is_matview && into->ivm)
+		{
+			Relation matviewRel = table_open(address.objectId, NoLock);
+
+			SetMatViewIVMState(matviewRel, true);
+			table_close(matviewRel, NoLock);
+			CommandCounterIncrement();
+		}
+
 		/*
 		 * For materialized views, reuse the REFRESH logic, which locks down
 		 * security-restricted operations and restricts the search_path.  This
 		 * reduces the chance that a subsequent refresh will fail.
 		 */
 		if (do_refresh)
+		{
 			RefreshMatViewByOid(address.objectId, true, false, false,
 								pstate->p_sourcetext, qc);
 
+			if (is_matview && into->ivm && IsolationUsesXactSnapshot())
+				ereport(WARNING,
+						(errmsg("inconsistent view can be created in isolation level SERIALIZABLE or REPEATABLE READ"),
+						 errdetail("The view may not include effects of a concurrent transaction."),
+						 errhint("The view with incremental maintenance should be created in isolation level READ COMMITTED, "
+								 "or refreshed manually to make sure the view is consistent.")));
+		}
 	}
 	else
 	{
@@ -635,3 +688,659 @@ intorel_destroy(DestReceiver *self)
 {
 	pfree(self);
 }
+
+/*
+ * CreateIvmTriggersOnBaseTables -- create IVM triggers on all base tables
+ */
+void
+CreateIvmTriggersOnBaseTables(Query *qry, Oid matviewOid)
+{
+	List   *relids = NIL;
+	bool	ex_lock = false;
+	RangeTblEntry *rte;
+
+	/* Immediately return if we don't have any base tables. */
+	if (list_length(qry->rtable) < 1)
+		return;
+
+	/*
+	 * If the view has more than one base tables, we need an exclusive lock
+	 * on the view so that the view would be maintained serially to avoid
+	 * the inconsistency that occurs when two base tables are modified in
+	 * concurrent transactions. However, if the view has only one table,
+	 * we can use a weaker lock.
+	 *
+	 * The type of lock should be determined here, because if we check the
+	 * view definition at maintenance time, we need to acquire a weaker lock,
+	 * and upgrading the lock level after this increases probability of
+	 * deadlock.
+	 */
+
+	rte = list_nth(qry->rtable, 0);
+	if (list_length(qry->rtable) > 1 || rte->rtekind != RTE_RELATION)
+		ex_lock = true;
+
+	CreateIvmTriggersOnBaseTablesRecurse(qry, (Node *)qry, matviewOid, &relids, ex_lock);
+
+	list_free(relids);
+}
+
+static void
+CreateIvmTriggersOnBaseTablesRecurse(Query *qry, Node *node, Oid matviewOid,
+									 List **relids, bool ex_lock)
+{
+	if (node == NULL)
+		return;
+
+	/* This can recurse, so check for excessive recursion */
+	check_stack_depth();
+
+	switch (nodeTag(node))
+	{
+		case T_Query:
+			{
+				Query *query = (Query *) node;
+
+				CreateIvmTriggersOnBaseTablesRecurse(qry, (Node *)query->jointree, matviewOid, relids, ex_lock);
+			}
+			break;
+
+		case T_RangeTblRef:
+			{
+				int			rti = ((RangeTblRef *) node)->rtindex;
+				RangeTblEntry *rte = rt_fetch(rti, qry->rtable);
+
+				if (rte->rtekind == RTE_RELATION && !list_member_oid(*relids, rte->relid))
+				{
+					CreateIvmTrigger(rte->relid, matviewOid, TRIGGER_TYPE_INSERT, TRIGGER_TYPE_BEFORE, ex_lock);
+					CreateIvmTrigger(rte->relid, matviewOid, TRIGGER_TYPE_DELETE, TRIGGER_TYPE_BEFORE, ex_lock);
+					CreateIvmTrigger(rte->relid, matviewOid, TRIGGER_TYPE_UPDATE, TRIGGER_TYPE_BEFORE, ex_lock);
+					CreateIvmTrigger(rte->relid, matviewOid, TRIGGER_TYPE_TRUNCATE, TRIGGER_TYPE_BEFORE, true);
+					CreateIvmTrigger(rte->relid, matviewOid, TRIGGER_TYPE_INSERT, TRIGGER_TYPE_AFTER, ex_lock);
+					CreateIvmTrigger(rte->relid, matviewOid, TRIGGER_TYPE_DELETE, TRIGGER_TYPE_AFTER, ex_lock);
+					CreateIvmTrigger(rte->relid, matviewOid, TRIGGER_TYPE_UPDATE, TRIGGER_TYPE_AFTER, ex_lock);
+					CreateIvmTrigger(rte->relid, matviewOid, TRIGGER_TYPE_TRUNCATE, TRIGGER_TYPE_AFTER, true);
+
+					*relids = lappend_oid(*relids, rte->relid);
+				}
+			}
+			break;
+
+		case T_FromExpr:
+			{
+				FromExpr   *f = (FromExpr *) node;
+				ListCell   *l;
+
+				foreach(l, f->fromlist)
+					CreateIvmTriggersOnBaseTablesRecurse(qry, lfirst(l), matviewOid, relids, ex_lock);
+			}
+			break;
+
+		case T_JoinExpr:
+			{
+				JoinExpr   *j = (JoinExpr *) node;
+
+				CreateIvmTriggersOnBaseTablesRecurse(qry, j->larg, matviewOid, relids, ex_lock);
+				CreateIvmTriggersOnBaseTablesRecurse(qry, j->rarg, matviewOid, relids, ex_lock);
+			}
+			break;
+
+		default:
+			elog(ERROR, "unrecognized node type: %d", (int) nodeTag(node));
+	}
+}
+
+/*
+ * CreateIvmTrigger -- create IVM trigger on a base table
+ */
+static void
+CreateIvmTrigger(Oid relOid, Oid viewOid, int16 type, int16 timing, bool ex_lock)
+{
+	ObjectAddress	refaddr;
+	ObjectAddress	address;
+	CreateTrigStmt *ivm_trigger;
+	List *transitionRels = NIL;
+
+	Assert(timing == TRIGGER_TYPE_BEFORE || timing == TRIGGER_TYPE_AFTER);
+
+	refaddr.classId = RelationRelationId;
+	refaddr.objectId = viewOid;
+	refaddr.objectSubId = 0;
+
+	ivm_trigger = makeNode(CreateTrigStmt);
+	ivm_trigger->relation = NULL;
+	ivm_trigger->row = false;
+
+	ivm_trigger->timing = timing;
+	ivm_trigger->events = type;
+
+	switch (type)
+	{
+		case TRIGGER_TYPE_INSERT:
+			ivm_trigger->trigname = (timing == TRIGGER_TYPE_BEFORE ? "IVM_trigger_ins_before" : "IVM_trigger_ins_after");
+			break;
+		case TRIGGER_TYPE_DELETE:
+			ivm_trigger->trigname = (timing == TRIGGER_TYPE_BEFORE ? "IVM_trigger_del_before" : "IVM_trigger_del_after");
+			break;
+		case TRIGGER_TYPE_UPDATE:
+			ivm_trigger->trigname = (timing == TRIGGER_TYPE_BEFORE ? "IVM_trigger_upd_before" : "IVM_trigger_upd_after");
+			break;
+		case TRIGGER_TYPE_TRUNCATE:
+			ivm_trigger->trigname = (timing == TRIGGER_TYPE_BEFORE ? "IVM_trigger_truncate_before" : "IVM_trigger_truncate_after");
+			break;
+		default:
+			elog(ERROR, "unsupported trigger type");
+	}
+
+	if (timing == TRIGGER_TYPE_AFTER)
+	{
+		if (type == TRIGGER_TYPE_INSERT || type == TRIGGER_TYPE_UPDATE)
+		{
+			TriggerTransition *n = makeNode(TriggerTransition);
+			n->name = "__ivm_newtable";
+			n->isNew = true;
+			n->isTable = true;
+
+			transitionRels = lappend(transitionRels, n);
+		}
+		if (type == TRIGGER_TYPE_DELETE || type == TRIGGER_TYPE_UPDATE)
+		{
+			TriggerTransition *n = makeNode(TriggerTransition);
+			n->name = "__ivm_oldtable";
+			n->isNew = false;
+			n->isTable = true;
+
+			transitionRels = lappend(transitionRels, n);
+		}
+	}
+
+	/*
+	 * XXX: When using DELETE or UPDATE, we must use exclusive lock for now
+	 * because apply_old_delta(_with_count) uses ctid to identify the tuple
+	 * to be deleted/deleted, but doesn't work in concurrent situations.
+	 *
+	 * If the view doesn't have aggregate, distinct, or tuple duplicate,
+	 * then it would work even in concurrent situations. However, we don't have
+	 * any way to guarantee the view has a unique key before opening the IMMV
+	 * at the maintenance time because users may drop the unique index.
+	 */
+
+	if (type == TRIGGER_TYPE_DELETE || type == TRIGGER_TYPE_UPDATE)
+		ex_lock = true;
+
+	ivm_trigger->funcname =
+		(timing == TRIGGER_TYPE_BEFORE ? SystemFuncName("IVM_immediate_before") : SystemFuncName("IVM_immediate_maintenance"));
+
+	ivm_trigger->columns = NIL;
+	ivm_trigger->transitionRels = transitionRels;
+	ivm_trigger->whenClause = NULL;
+	ivm_trigger->isconstraint = false;
+	ivm_trigger->deferrable = false;
+	ivm_trigger->initdeferred = false;
+	ivm_trigger->constrrel = NULL;
+	ivm_trigger->args = list_make2(
+		makeString(DatumGetPointer(DirectFunctionCall1(oidout, ObjectIdGetDatum(viewOid)))),
+		makeString(DatumGetPointer(DirectFunctionCall1(boolout, BoolGetDatum(ex_lock))))
+		);
+
+	address = CreateTrigger(ivm_trigger, NULL, relOid, InvalidOid, InvalidOid,
+						 InvalidOid, InvalidOid, InvalidOid, NULL, true, false);
+
+	recordDependencyOn(&address, &refaddr, DEPENDENCY_AUTO);
+
+	/* Make changes-so-far visible */
+	CommandCounterIncrement();
+}
+
+/*
+ * check_ivm_restriction --- look for specify nodes in the query tree
+ */
+static void
+check_ivm_restriction(Node *node)
+{
+	check_ivm_restriction_walker(node, NULL);
+}
+
+static bool
+check_ivm_restriction_walker(Node *node, void *context)
+{
+	if (node == NULL)
+		return false;
+
+	/*
+	 * We currently don't support Sub-Query.
+	 */
+	if (IsA(node, SubPlan) || IsA(node, SubLink))
+		ereport(ERROR,
+				(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+				 errmsg("subquery is not supported on incrementally maintainable materialized view")));
+
+	/* This can recurse, so check for excessive recursion */
+	check_stack_depth();
+
+	switch (nodeTag(node))
+	{
+		case T_Query:
+			{
+				Query *qry = (Query *)node;
+				ListCell   *lc;
+				List       *vars;
+
+				/* if contained CTE, return error */
+				if (qry->cteList != NIL)
+					ereport(ERROR,
+							(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+							 errmsg("CTE is not supported on incrementally maintainable materialized view")));
+				if (qry->havingQual != NULL)
+					ereport(ERROR,
+							(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+							 errmsg(" HAVING clause is not supported on incrementally maintainable materialized view")));
+				if (qry->sortClause != NIL)	/* There is a possibility that we don't need to return an error */
+					ereport(ERROR,
+							(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+							 errmsg("ORDER BY clause is not supported on incrementally maintainable materialized view")));
+				if (qry->limitOffset != NULL || qry->limitCount != NULL)
+					ereport(ERROR,
+							(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+							 errmsg("LIMIT/OFFSET clause is not supported on incrementally maintainable materialized view")));
+				if (qry->distinctClause)
+					ereport(ERROR,
+							(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+							 errmsg("DISTINCT is not supported on incrementally maintainable materialized view")));
+				if (qry->hasDistinctOn)
+					ereport(ERROR,
+							(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+							 errmsg("DISTINCT ON is not supported on incrementally maintainable materialized view")));
+				if (qry->hasWindowFuncs)
+					ereport(ERROR,
+							(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+							 errmsg("window functions are not supported on incrementally maintainable materialized view")));
+				if (qry->groupingSets != NIL)
+					ereport(ERROR,
+							(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+							 errmsg("GROUPING SETS, ROLLUP, or CUBE clauses is not supported on incrementally maintainable materialized view")));
+				if (qry->setOperations != NULL)
+					ereport(ERROR,
+							(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+							 errmsg("UNION/INTERSECT/EXCEPT statements are not supported on incrementally maintainable materialized view")));
+				if (list_length(qry->targetList) == 0)
+					ereport(ERROR,
+							(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+							 errmsg("empty target list is not supported on incrementally maintainable materialized view")));
+				if (qry->rowMarks != NIL)
+					ereport(ERROR,
+							(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+							 errmsg("FOR UPDATE/SHARE clause is not supported on incrementally maintainable materialized view")));
+
+				/* system column restrictions */
+				vars = pull_vars_of_level((Node *) qry, 0);
+				foreach(lc, vars)
+				{
+					if (IsA(lfirst(lc), Var))
+					{
+						Var *var = (Var *) lfirst(lc);
+						/* if system column, return error */
+						if (var->varattno < 0)
+							ereport(ERROR,
+									(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+									 errmsg("system column is not supported on incrementally maintainable materialized view")));
+					}
+				}
+
+				/* check if type in the target list had an equality operator */
+				foreach(lc, qry->targetList)
+				{
+					TargetEntry *tle = (TargetEntry *) lfirst(lc);
+					Oid             atttype = exprType((Node *) tle->expr);
+					Oid             opclass;
+
+					opclass = GetDefaultOpClass(atttype, BTREE_AM_OID);
+					if (!OidIsValid(opclass))
+						ereport(ERROR,
+								(errcode(ERRCODE_UNDEFINED_OBJECT),
+								 errmsg("data type %s has no default operator class for access method \"%s\"",
+									format_type_be(atttype), "btree")));
+				}
+
+				/* restrictions for rtable */
+				foreach(lc, qry->rtable)
+				{
+					RangeTblEntry *rte = (RangeTblEntry *) lfirst(lc);
+
+					if (rte->subquery)
+						ereport(ERROR,
+								(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+								 errmsg("subquery is not supported on incrementally maintainable materialized view")));
+
+					if (rte->tablesample != NULL)
+						ereport(ERROR,
+								(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+								 errmsg("TABLESAMPLE clause is not supported on incrementally maintainable materialized view")));
+
+					if (rte->relkind == RELKIND_PARTITIONED_TABLE)
+						ereport(ERROR,
+								(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+								 errmsg("partitioned table is not supported on incrementally maintainable materialized view")));
+
+					if (rte->relkind == RELKIND_RELATION && has_superclass(rte->relid))
+						ereport(ERROR,
+								(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+								 errmsg("partitions is not supported on incrementally maintainable materialized view")));
+
+					if (rte->relkind == RELKIND_RELATION && find_inheritance_children(rte->relid, NoLock) != NIL)
+						ereport(ERROR,
+								(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+								 errmsg("inheritance parent is not supported on incrementally maintainable materialized view")));
+
+					if (rte->relkind == RELKIND_FOREIGN_TABLE)
+						ereport(ERROR,
+								(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+								 errmsg("foreign table is not supported on incrementally maintainable materialized view")));
+
+					if (rte->relkind == RELKIND_VIEW ||
+						rte->relkind == RELKIND_MATVIEW)
+						ereport(ERROR,
+								(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+								 errmsg("VIEW or MATERIALIZED VIEW is not supported on incrementally maintainable materialized view")));
+
+					if (rte->rtekind == RTE_VALUES)
+						ereport(ERROR,
+								(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+								 errmsg("VALUES is not supported on incrementally maintainable materialized view")));
+
+				}
+
+				query_tree_walker(qry, check_ivm_restriction_walker, NULL, QTW_IGNORE_RANGE_TABLE);
+
+				break;
+			}
+		case T_TargetEntry:
+			{
+				TargetEntry *tle = (TargetEntry *)node;
+				if (isIvmName(tle->resname))
+						ereport(ERROR,
+								(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+								 errmsg("column name %s is not supported on incrementally maintainable materialized view", tle->resname)));
+
+				expression_tree_walker(node, check_ivm_restriction_walker, NULL);
+				break;
+			}
+		case T_JoinExpr:
+			{
+				JoinExpr *joinexpr = (JoinExpr *)node;
+
+				if (joinexpr->jointype > JOIN_INNER)
+						ereport(ERROR,
+								(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+								 errmsg("OUTER JOIN is not supported on incrementally maintainable materialized view")));
+
+				expression_tree_walker(node, check_ivm_restriction_walker, NULL);
+			}
+			break;
+		case T_Aggref:
+			ereport(ERROR,
+					(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+					 errmsg("aggregate function is not supported on incrementally maintainable materialized view")));
+			break;
+		default:
+			expression_tree_walker(node, check_ivm_restriction_walker, (void *) context);
+			break;
+	}
+	return false;
+}
+
+/*
+ * CreateIndexOnIMMV
+ *
+ * Create a unique index on incremental maintainable materialized view.
+ * If the view definition query has a GROUP BY clause, the index is created
+ * on the columns of GROUP BY expressions. Otherwise, if the view contains
+ * all primary key attributes of its base tables in the target list, the index
+ * is created on these attributes. In other cases, no index is created.
+ */
+void
+CreateIndexOnIMMV(Query *query, Relation matviewRel)
+{
+	ListCell *lc;
+	IndexStmt  *index;
+	ObjectAddress address;
+	List *constraintList = NIL;
+	char		idxname[NAMEDATALEN];
+	List	   *indexoidlist = RelationGetIndexList(matviewRel);
+	ListCell   *indexoidscan;
+	Bitmapset *key_attnos;
+
+	snprintf(idxname, sizeof(idxname), "%s_index", RelationGetRelationName(matviewRel));
+
+	index = makeNode(IndexStmt);
+
+	index->unique = true;
+	index->primary = false;
+	index->isconstraint = false;
+	index->deferrable = false;
+	index->initdeferred = false;
+	index->idxname = idxname;
+	index->relation =
+		makeRangeVar(get_namespace_name(RelationGetNamespace(matviewRel)),
+					 pstrdup(RelationGetRelationName(matviewRel)),
+					 -1);
+	index->accessMethod = DEFAULT_INDEX_TYPE;
+	index->options = NIL;
+	index->tableSpace = get_tablespace_name(matviewRel->rd_rel->reltablespace);
+	index->whereClause = NULL;
+	index->indexParams = NIL;
+	index->indexIncludingParams = NIL;
+	index->excludeOpNames = NIL;
+	index->idxcomment = NULL;
+	index->indexOid = InvalidOid;
+	index->oldNumber = InvalidRelFileNumber;
+	index->oldCreateSubid = InvalidSubTransactionId;
+	index->oldFirstRelfilelocatorSubid = InvalidSubTransactionId;
+	index->transformed = true;
+	index->concurrent = false;
+	index->if_not_exists = false;
+
+	/* create index on the base tables' primary key columns */
+	key_attnos = get_primary_key_attnos_from_query(query, &constraintList);
+	if (key_attnos)
+	{
+		foreach(lc, query->targetList)
+		{
+			TargetEntry *tle = (TargetEntry *) lfirst(lc);
+			Form_pg_attribute attr = TupleDescAttr(matviewRel->rd_att, tle->resno - 1);
+
+			if (bms_is_member(tle->resno - FirstLowInvalidHeapAttributeNumber, key_attnos))
+			{
+				IndexElem  *iparam;
+
+				iparam = makeNode(IndexElem);
+				iparam->name = pstrdup(NameStr(attr->attname));
+				iparam->expr = NULL;
+				iparam->indexcolname = NULL;
+				iparam->collation = NIL;
+				iparam->opclass = NIL;
+				iparam->opclassopts = NIL;
+				iparam->ordering = SORTBY_DEFAULT;
+				iparam->nulls_ordering = SORTBY_NULLS_DEFAULT;
+				index->indexParams = lappend(index->indexParams, iparam);
+			}
+		}
+	}
+	else
+	{
+		/* create no index, just notice that an appropriate index is necessary for efficient IVM */
+		ereport(NOTICE,
+				(errmsg("could not create an index on materialized view \"%s\" automatically",
+						RelationGetRelationName(matviewRel)),
+				 errdetail("This target list does not have all the primary key columns. "),
+				 errhint("Create an index on the materialized view for efficient incremental maintenance.")));
+		return;
+	}
+
+	/* If we have a compatible index, we don't need to create another. */
+	foreach(indexoidscan, indexoidlist)
+	{
+		Oid			indexoid = lfirst_oid(indexoidscan);
+		Relation	indexRel;
+		bool		hasCompatibleIndex = false;
+
+		indexRel = index_open(indexoid, AccessShareLock);
+
+		if (CheckIndexCompatible(indexRel->rd_id,
+								index->accessMethod,
+								index->indexParams,
+								index->excludeOpNames,
+								false))
+			hasCompatibleIndex = true;
+
+		index_close(indexRel, AccessShareLock);
+
+		if (hasCompatibleIndex)
+			return;
+	}
+
+	address = DefineIndex(NULL,
+						  RelationGetRelid(matviewRel),
+						  index,
+						  InvalidOid,
+						  InvalidOid,
+						  InvalidOid,
+						  -1,
+						  false, true, false, false, true);
+
+	ereport(NOTICE,
+			(errmsg("created index \"%s\" on materialized view \"%s\"",
+					idxname, RelationGetRelationName(matviewRel))));
+
+	/*
+	 * Make dependencies so that the index is dropped if any base tables'
+	 * primary key is dropped.
+	 */
+	foreach(lc, constraintList)
+	{
+		Oid constraintOid = lfirst_oid(lc);
+		ObjectAddress	refaddr;
+
+		refaddr.classId = ConstraintRelationId;
+		refaddr.objectId = constraintOid;
+		refaddr.objectSubId = 0;
+
+		recordDependencyOn(&address, &refaddr, DEPENDENCY_NORMAL);
+	}
+}
+
+
+/*
+ * get_primary_key_attnos_from_query
+ *
+ * Identify the columns in base tables' primary keys in the target list.
+ *
+ * Returns a Bitmapset of the column attnos of the primary key's columns of
+ * tables that used in the query.  The attnos are offset by
+ * FirstLowInvalidHeapAttributeNumber as same as get_primary_key_attnos.
+ *
+ * If any table has no primary key or any primary key's columns is not in
+ * the target list, return NULL.  We also return NULL if any pkey constraint
+ * is deferrable.
+ *
+ * constraintList is set to a list of the OIDs of the pkey constraints.
+ */
+static Bitmapset *
+get_primary_key_attnos_from_query(Query *query, List **constraintList)
+{
+	List *key_attnos_list = NIL;
+	ListCell *lc;
+	int i;
+	Bitmapset *keys = NULL;
+	Relids	rels_in_from;
+
+	/*
+	 * Collect primary key attributes from all tables used in query. The key attributes
+	 * sets for each table are stored in key_attnos_list in order by RTE index.
+	 */
+	foreach(lc, query->rtable)
+	{
+		RangeTblEntry *r = (RangeTblEntry*) lfirst(lc);
+		Bitmapset *key_attnos;
+		bool	has_no_pkey = false;
+
+		/* for tables, call get_primary_key_attnos */
+		if (r->rtekind == RTE_RELATION)
+		{
+			Oid constraintOid;
+			key_attnos = get_primary_key_attnos(r->relid, false, &constraintOid);
+			*constraintList = lappend_oid(*constraintList, constraintOid);
+			has_no_pkey = (key_attnos == NULL);
+		}
+		/*
+		 * Ignore join rels, because they are flatten later by
+		 * flatten_join_alias_vars(). Store NULL into key_attnos_list
+		 * as a dummy.
+		 */
+		 else if (r->rtekind == RTE_JOIN)
+		 {
+			key_attnos = NULL;
+		}
+		/* for other RTEs, store NULL into key_attnos_list */
+		else
+			has_no_pkey = true;
+
+		/*
+		 * If any table or subquery has no primary key or its pkey constraint is deferrable,
+		 * we cannot get key attributes for this query, so return NULL.
+		 */
+		if (has_no_pkey)
+			return NULL;
+
+		key_attnos_list = lappend(key_attnos_list, key_attnos);
+	}
+
+	/* Collect key attributes appearing in the target list */
+	i = 1;
+	foreach(lc, query->targetList)
+	{
+		TargetEntry *tle = (TargetEntry *) flatten_join_alias_vars(NULL, query, lfirst(lc));
+
+		if (IsA(tle->expr, Var))
+		{
+			Var *var = (Var*) tle->expr;
+			Bitmapset *key_attnos = list_nth(key_attnos_list, var->varno - 1);
+
+			/* check if this attribute is from a base table's primary key */
+			if (bms_is_member(var->varattno - FirstLowInvalidHeapAttributeNumber, key_attnos))
+			{
+				/*
+				 * Remove found key attributes from key_attnos_list, and add this
+				 * to the result list.
+				 */
+				key_attnos = bms_del_member(key_attnos, var->varattno - FirstLowInvalidHeapAttributeNumber);
+				if (bms_is_empty(key_attnos))
+				{
+					key_attnos_list = list_delete_nth_cell(key_attnos_list, var->varno - 1);
+					key_attnos_list = list_insert_nth(key_attnos_list, var->varno - 1, NULL);
+				}
+				keys = bms_add_member(keys, i - FirstLowInvalidHeapAttributeNumber);
+			}
+		}
+		i++;
+	}
+
+	/* Collect RTE indexes of relations appearing in the FROM clause */
+	rels_in_from = get_relids_in_jointree((Node *) query->jointree, false, false);
+
+	/*
+	 * Check if all key attributes of relations in FROM are appearing in the target
+	 * list.  If an attribute remains in key_attnos_list in spite of the table is used
+	 * in FROM clause, the target is missing this key attribute, so we return NULL.
+	 */
+	i = 1;
+	foreach(lc, key_attnos_list)
+	{
+		Bitmapset *bms = (Bitmapset *)lfirst(lc);
+		if (!bms_is_empty(bms) && bms_is_member(i, rels_in_from))
+			return NULL;
+		i++;
+	}
+
+	return keys;
+}
diff --git a/src/backend/commands/matview.c b/src/backend/commands/matview.c
index f7d8007f796..eaf39f80cd3 100644
--- a/src/backend/commands/matview.c
+++ b/src/backend/commands/matview.c
@@ -23,24 +23,36 @@
 #include "catalog/indexing.h"
 #include "catalog/namespace.h"
 #include "catalog/pg_am.h"
+#include "catalog/pg_depend.h"
+#include "catalog/pg_trigger.h"
 #include "catalog/pg_opclass.h"
 #include "commands/matview.h"
 #include "commands/repack.h"
 #include "commands/tablecmds.h"
 #include "commands/tablespace.h"
+#include "commands/createas.h"
 #include "executor/executor.h"
 #include "executor/spi.h"
+#include "executor/tstoreReceiver.h"
 #include "miscadmin.h"
+#include "nodes/makefuncs.h"
+#include "parser/analyze.h"
+#include "parser/parse_clause.h"
+#include "parser/parse_func.h"
+#include "parser/parse_relation.h"
 #include "pgstat.h"
 #include "rewrite/rewriteHandler.h"
+#include "rewrite/rowsecurity.h"
 #include "storage/lmgr.h"
+#include "storage/lwlock.h"
 #include "tcop/tcopprot.h"
 #include "utils/builtins.h"
+#include "utils/fmgroids.h"
 #include "utils/lsyscache.h"
 #include "utils/rel.h"
 #include "utils/snapmgr.h"
 #include "utils/syscache.h"
-
+#include "utils/typcache.h"
 
 typedef struct
 {
@@ -53,6 +65,97 @@ typedef struct
 	BulkInsertState bistate;	/* bulk insert state */
 } DR_transientrel;
 
+#define MV_INIT_QUERYHASHSIZE	16
+
+/*
+ * MV_TriggerHashEntry
+ *
+ * Hash entry for base tables on which IVM trigger is invoked
+ */
+typedef struct MV_TriggerHashEntry
+{
+	Oid	matview_id;			/* OID of the materialized view */
+	int	before_trig_count;	/* count of before triggers invoked */
+	int	after_trig_count;	/* count of after triggers invoked */
+
+	Snapshot	snapshot;	/* Snapshot just before table change */
+
+	List   *tables;		/* List of MV_TriggerTable */
+	bool	has_old;	/* tuples are deleted from any table? */
+	bool	has_new;	/* tuples are inserted into any table? */
+
+	/*
+	 * List of sub-transaction IDs that incrementally updated the view.
+	 * This list is maintained through a transaction, and an ID is removed
+	 * when a sub-transaction is aborted. If any ID is left when the
+	 * transaction is committed, this means the view is incrementally
+	 * updated in this transaction.
+	 */
+	List   *subxids;
+} MV_TriggerHashEntry;
+
+/*
+ * MV_TriggerTable
+ *
+ * IVM related data for tables on which the trigger is invoked.
+ */
+typedef struct MV_TriggerTable
+{
+	Oid		table_id;			/* OID of the modified table */
+	List   *old_tuplestores;	/* tuplestores for deleted tuples */
+	List   *new_tuplestores;	/* tuplestores for inserted tuples */
+
+	List   *rte_indexes;		/* List of RTE index of the modified table */
+	RangeTblEntry *original_rte;	/* the original RTE saved before rewriting query */
+
+	Relation	rel;			/* relation of the modified table */
+	TupleTableSlot *slot;		/* for checking visibility in the pre-state table */
+} MV_TriggerTable;
+
+typedef struct DroppedImmvInfo
+{
+	Oid					immv_oid;
+	SubTransactionId	subxid;
+} DroppedImmvInfo;
+
+static HTAB *mv_trigger_info = NULL;
+static HTAB *dropped_immv = NULL;
+
+static HTAB *LastIvmUpdateHash;
+
+#define LAST_IVM_UPDATE_HASH_SIZE 256
+
+static void IvmShmemRequest(void *arg);
+
+/* hash table entries */
+typedef struct LastIvmUpdateEntry
+{
+	Oid		oid;	/* hash key */
+	FullTransactionId	last_ivm_update;
+} LastIvmUpdateEntry;
+
+const ShmemCallbacks IvmShmemCallbacks = {
+	.request_fn = IvmShmemRequest,
+};
+
+static void
+IvmShmemRequest(void *arg)
+{
+	ShmemRequestHash(.name = "LastIvmUpdate hash",
+					 .nelems = LAST_IVM_UPDATE_HASH_SIZE,
+					 .ptr = &LastIvmUpdateHash,
+					 .hash_info.keysize = sizeof(Oid),
+					 .hash_info.entrysize = sizeof(LastIvmUpdateEntry),
+					 .hash_flags = HASH_ELEM | HASH_BLOBS,
+		);
+}
+
+static bool in_delta_calculation = false;
+
+/* ENR name for materialized view delta */
+#define NEW_DELTA_ENRNAME "new_delta"
+#define OLD_DELTA_ENRNAME "old_delta"
+
 static int	matview_maintenance_depth = 0;
 
 static void transientrel_startup(DestReceiver *self, int operation, TupleDesc typeinfo);
@@ -60,6 +163,8 @@ static bool transientrel_receive(TupleTableSlot *slot, DestReceiver *self);
 static void transientrel_shutdown(DestReceiver *self);
 static void transientrel_destroy(DestReceiver *self);
 static uint64 refresh_matview_datafill(DestReceiver *dest, Query *query,
+									   QueryEnvironment *queryEnv,
+									   TupleDesc *resultTupleDesc,
 									   const char *queryString, bool is_create);
 static void refresh_by_match_merge(Oid matviewOid, Oid tempOid, Oid relowner,
 								   int save_sec_context);
@@ -67,6 +172,41 @@ static void refresh_by_heap_swap(Oid matviewOid, Oid OIDNewHeap, char relpersist
 static bool is_usable_unique_index(Relation indexRel);
 static void OpenMatViewIncrementalMaintenance(void);
 static void CloseMatViewIncrementalMaintenance(void);
+static Query *get_matview_query(Relation matviewRel);
+
+static Query *rewrite_query_for_preupdate_state(Query *query, List *tables,
+								  ParseState *pstate, Oid matviewid);
+static void register_delta_ENRs(ParseState *pstate, Query *query, List *tables);
+static char *make_subquery_targetlist_from_table(MV_TriggerTable *table);
+static char *make_delta_enr_name(const char *prefix, Oid relid, int count);
+static RangeTblEntry *get_prestate_rte(RangeTblEntry *rte, MV_TriggerTable *table,
+				 QueryEnvironment *queryEnv, Oid matviewid);
+static RangeTblEntry *makeDeltaTable(RangeTblEntry *rte, MV_TriggerTable *table,
+									 bool is_new, QueryEnvironment *queryEnv);
+static Query *rewrite_query_for_counting(Query *query, ParseState *pstate);
+
+static void calc_delta(MV_TriggerTable *table, int rte_index, Query *query,
+			DestReceiver *dest_old, DestReceiver *dest_new,
+			TupleDesc *tupdesc_old, TupleDesc *tupdesc_new,
+			QueryEnvironment *queryEnv);
+static Query *rewrite_query_for_postupdate_state(Query *query, MV_TriggerTable *table, int rte_index);
+
+static void apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *new_tuplestores,
+			TupleDesc tupdesc_old, TupleDesc tupdesc_new,
+			Query *query);
+static void apply_old_delta(const char *matviewname, const char *deltaname_old,
+				List *keys);
+static void apply_new_delta(const char *matviewname, const char *deltaname_new,
+				StringInfo target_list);
+static char *get_matching_condition_string(List *keys);
+static void generate_equal(StringInfo querybuf, Oid opttype,
+			   const char *leftop, const char *rightop);
+
+static void mv_InitHashTables(void);
+static void clean_up_IVM_hash_entry(MV_TriggerHashEntry *entry, bool is_abort,
+									SubTransactionId subxid);
+static void setLastUpdateXid(Oid immv_oid, FullTransactionId xid);
+static FullTransactionId getLastUpdateXid(Oid immv_oid);
 
 /*
  * SetMatViewPopulatedState
@@ -108,6 +248,46 @@ SetMatViewPopulatedState(Relation relation, bool newstate)
 	CommandCounterIncrement();
 }
 
+/*
+ * SetMatViewIVMState
+ *		Mark a materialized view as IVM, or not.
+ *
+ * NOTE: caller must be holding an appropriate lock on the relation.
+ */
+void
+SetMatViewIVMState(Relation relation, bool newstate)
+{
+	Relation	pgrel;
+	HeapTuple	tuple;
+
+	Assert(relation->rd_rel->relkind == RELKIND_MATVIEW);
+
+	/*
+	 * Update relation's pg_class entry.  Crucial side-effect: other backends
+	 * (and this one too!) are sent SI message to make them rebuild relcache
+	 * entries.
+	 */
+	pgrel = table_open(RelationRelationId, RowExclusiveLock);
+	tuple = SearchSysCacheCopy1(RELOID,
+								ObjectIdGetDatum(RelationGetRelid(relation)));
+	if (!HeapTupleIsValid(tuple))
+		elog(ERROR, "cache lookup failed for relation %u",
+			 RelationGetRelid(relation));
+
+	((Form_pg_class) GETSTRUCT(tuple))->relisivm = newstate;
+
+	CatalogTupleUpdate(pgrel, &tuple->t_self, tuple);
+
+	heap_freetuple(tuple);
+	table_close(pgrel, RowExclusiveLock);
+
+	/*
+	 * Advance command counter to make the updated pg_class row locally
+	 * visible.
+	 */
+	CommandCounterIncrement();
+}
+
 /*
  * ExecRefreshMatView -- execute a REFRESH MATERIALIZED VIEW command
  *
@@ -166,8 +346,6 @@ RefreshMatViewByOid(Oid matviewOid, bool is_create, bool skipData,
 					QueryCompletion *qc)
 {
 	Relation	matviewRel;
-	RewriteRule *rule;
-	List	   *actions;
 	Query	   *dataQuery;
 	Oid			tableSpace;
 	Oid			relowner;
@@ -178,6 +356,7 @@ RefreshMatViewByOid(Oid matviewOid, bool is_create, bool skipData,
 	int			save_sec_context;
 	int			save_nestlevel;
 	ObjectAddress address;
+	bool oldPopulated;
 
 	matviewRel = table_open(matviewOid, NoLock);
 	relowner = matviewRel->rd_rel->relowner;
@@ -193,6 +372,8 @@ RefreshMatViewByOid(Oid matviewOid, bool is_create, bool skipData,
 	save_nestlevel = NewGUCNestLevel();
 	RestrictSearchPath();
 
+	oldPopulated = RelationIsPopulated(matviewRel);
+
 	/* Make sure it is a materialized view. */
 	if (matviewRel->rd_rel->relkind != RELKIND_MATVIEW)
 		ereport(ERROR,
@@ -213,32 +394,7 @@ RefreshMatViewByOid(Oid matviewOid, bool is_create, bool skipData,
 				 errmsg("%s options %s and %s cannot be used together",
 						"REFRESH", "CONCURRENTLY", "WITH NO DATA")));
 
-	/*
-	 * Check that everything is correct for a refresh. Problems at this point
-	 * are internal errors, so elog is sufficient.
-	 */
-	if (matviewRel->rd_rel->relhasrules == false ||
-		matviewRel->rd_rules->numLocks < 1)
-		elog(ERROR,
-			 "materialized view \"%s\" is missing rewrite information",
-			 RelationGetRelationName(matviewRel));
-
-	if (matviewRel->rd_rules->numLocks > 1)
-		elog(ERROR,
-			 "materialized view \"%s\" has too many rules",
-			 RelationGetRelationName(matviewRel));
-
-	rule = matviewRel->rd_rules->rules[0];
-	if (rule->event != CMD_SELECT || !(rule->isInstead))
-		elog(ERROR,
-			 "the rule for materialized view \"%s\" is not a SELECT INSTEAD OF rule",
-			 RelationGetRelationName(matviewRel));
-
-	actions = rule->actions;
-	if (list_length(actions) != 1)
-		elog(ERROR,
-			 "the rule for materialized view \"%s\" is not a single action",
-			 RelationGetRelationName(matviewRel));
+	dataQuery = get_matview_query(matviewRel);
 
 	/*
 	 * Check that there is a unique index with no WHERE clause on one or more
@@ -275,12 +431,6 @@ RefreshMatViewByOid(Oid matviewOid, bool is_create, bool skipData,
 					 errhint("Create a unique index with no WHERE clause on one or more columns of the materialized view.")));
 	}
 
-	/*
-	 * The stored query was rewritten at the time of the MV definition, but
-	 * has not been scribbled on by the planner.
-	 */
-	dataQuery = linitial_node(Query, actions);
-
 	/*
 	 * Check for active uses of the relation in the current transaction, such
 	 * as open scans.
@@ -310,6 +460,90 @@ RefreshMatViewByOid(Oid matviewOid, bool is_create, bool skipData,
 		relpersistence = matviewRel->rd_rel->relpersistence;
 	}
 
+	/* delete IMMV triggers. */
+	if (RelationIsIVM(matviewRel) && skipData)
+	{
+		Relation	tgRel;
+		Relation	depRel;
+		ScanKeyData key;
+		SysScanDesc scan;
+		HeapTuple	tup;
+		ObjectAddresses *immv_triggers;
+
+		immv_triggers = new_object_addresses();
+
+		tgRel = table_open(TriggerRelationId, RowExclusiveLock);
+		depRel = table_open(DependRelationId, RowExclusiveLock);
+
+		/* search triggers that depends on IMMV. */
+		ScanKeyInit(&key,
+					Anum_pg_depend_refobjid,
+					BTEqualStrategyNumber, F_OIDEQ,
+					ObjectIdGetDatum(matviewOid));
+		scan = systable_beginscan(depRel, DependReferenceIndexId, true,
+								  NULL, 1, &key);
+		while ((tup = systable_getnext(scan)) != NULL)
+		{
+			ObjectAddress obj;
+			Form_pg_depend foundDep = (Form_pg_depend) GETSTRUCT(tup);
+
+			if (foundDep->classid == TriggerRelationId)
+			{
+				HeapTuple	tgtup;
+				ScanKeyData tgkey[1];
+				SysScanDesc tgscan;
+				Form_pg_trigger tgform;
+
+				/* Find the trigger name. */
+				ScanKeyInit(&tgkey[0],
+							Anum_pg_trigger_oid,
+							BTEqualStrategyNumber, F_OIDEQ,
+							ObjectIdGetDatum(foundDep->objid));
+
+				tgscan = systable_beginscan(tgRel, TriggerOidIndexId, true,
+											NULL, 1, tgkey);
+				tgtup = systable_getnext(tgscan);
+				if (!HeapTupleIsValid(tgtup))
+					elog(ERROR, "could not find tuple for immv trigger %u", foundDep->objid);
+
+				tgform = (Form_pg_trigger) GETSTRUCT(tgtup);
+
+				/* If trigger is created by IMMV, delete it. */
+				if (strncmp(NameStr(tgform->tgname), "IVM_trigger_", 12) == 0)
+				{
+					obj.classId = foundDep->classid;
+					obj.objectId = foundDep->objid;
+					obj.objectSubId = foundDep->refobjsubid;
+					add_exact_object_address(&obj, immv_triggers);
+				}
+				systable_endscan(tgscan);
+			}
+		}
+		systable_endscan(scan);
+
+		performMultipleDeletions(immv_triggers, DROP_RESTRICT, PERFORM_DELETION_INTERNAL);
+
+		table_close(depRel, RowExclusiveLock);
+		table_close(tgRel, RowExclusiveLock);
+		free_object_addresses(immv_triggers);
+	}
+
+	/*
+	 * Create triggers on incremental maintainable materialized view
+	 * This argument should use 'dataQuery'. This needs to use a rewritten query,
+	 * because a sublink in jointree is not supported by this function.
+	 *
+	 * This is performed before generating data because we have to wait
+	 * concurrent transactions modifying a base table and then take a snapshot
+	 * to see changes by these transactions to make sure a consistent view
+	 * is created.
+	 */
+	if (RelationIsIVM(matviewRel) && !skipData && !oldPopulated)
+	{
+		CreateIvmTriggersOnBaseTables(dataQuery, matviewOid);
+		CreateIndexOnIMMV(dataQuery, matviewRel);
+	}
+
 	/*
 	 * Create the transient table that will receive the regenerated data. Lock
 	 * it against access by any other process until commit (by which time it
@@ -326,8 +560,43 @@ RefreshMatViewByOid(Oid matviewOid, bool is_create, bool skipData,
 		DestReceiver *dest;
 
 		dest = CreateTransientRelDestReceiver(OIDNewHeap);
-		processed = refresh_matview_datafill(dest, dataQuery, queryString,
-											 is_create);
+
+		if (RelationIsIVM(matviewRel))
+		{
+			/*
+			 * In READ COMMITTED, get and push the latest snapshot again to see the
+			 * results of concurrent transactions committed after the current
+			 * transaction started.
+			 */
+			if (!IsolationUsesXactSnapshot())
+				PushActiveSnapshot(GetTransactionSnapshot());
+
+			/*
+			 * If a concurrent transaction updated the view incrementally and was
+			 * committed before we acquired the lock, the results of refresh_immv could
+			 * be inconsistent. Therefore, we have to check the transaction ID of the
+			 * most recent update of the view, and if this was in progress at the
+			 * transaction start, raise an error to prevent anomalies.
+			 */
+			if (!is_create)
+			{
+				FullTransactionId xid;
+
+				xid = getLastUpdateXid(matviewOid);
+				if (XidInMVCCSnapshot(XidFromFullTransactionId(xid), GetActiveSnapshot()))
+					ereport(ERROR,
+							(errcode(ERRCODE_T_R_SERIALIZATION_FAILURE),
+							 errmsg("the materialized view is incrementally updated in concurrent transaction"),
+							 errhint("The transaction might succeed if retried.")));
+			}
+		}
+
+		processed = refresh_matview_datafill(dest, dataQuery, NULL, NULL,
+											 queryString, is_create);
+
+		/* Pop the original snapshot. */
+		if (RelationIsIVM(matviewRel) && !IsolationUsesXactSnapshot())
+			PopActiveSnapshot();
 	}
 
 	/* Make the matview match the newly generated data. */
@@ -402,6 +671,8 @@ RefreshMatViewByOid(Oid matviewOid, bool is_create, bool skipData,
  */
 static uint64
 refresh_matview_datafill(DestReceiver *dest, Query *query,
+						 QueryEnvironment *queryEnv,
+						 TupleDesc *resultTupleDesc,
 						 const char *queryString, bool is_create)
 {
 	List	   *rewritten;
@@ -439,7 +710,7 @@ refresh_matview_datafill(DestReceiver *dest, Query *query,
 	/* Create a QueryDesc, redirecting output to our tuple receiver */
 	queryDesc = CreateQueryDesc(plan, queryString,
 								GetActiveSnapshot(), InvalidSnapshot,
-								dest, NULL, NULL, 0);
+								dest, NULL, queryEnv ? queryEnv: NULL, 0);
 
 	/* call ExecutorStart to prepare the plan for execution */
 	ExecutorStart(queryDesc, 0);
@@ -449,6 +720,9 @@ refresh_matview_datafill(DestReceiver *dest, Query *query,
 
 	processed = queryDesc->estate->es_processed;
 
+	if (resultTupleDesc)
+		*resultTupleDesc = CreateTupleDescCopy(queryDesc->tupDesc);
+
 	/* and clean up */
 	ExecutorFinish(queryDesc);
 	ExecutorEnd(queryDesc);
@@ -967,3 +1241,1488 @@ CloseMatViewIncrementalMaintenance(void)
 	matview_maintenance_depth--;
 	Assert(matview_maintenance_depth >= 0);
 }
+
+/*
+ * get_matview_query - get the Query from a matview's _RETURN rule.
+ */
+static Query *
+get_matview_query(Relation matviewRel)
+{
+	RewriteRule *rule;
+	List * actions;
+
+	/*
+	 * Check that everything is correct for a refresh. Problems at this point
+	 * are internal errors, so elog is sufficient.
+	 */
+	if (matviewRel->rd_rel->relhasrules == false ||
+		matviewRel->rd_rules->numLocks < 1)
+		elog(ERROR,
+			 "materialized view \"%s\" is missing rewrite information",
+			 RelationGetRelationName(matviewRel));
+
+	if (matviewRel->rd_rules->numLocks > 1)
+		elog(ERROR,
+			 "materialized view \"%s\" has too many rules",
+			 RelationGetRelationName(matviewRel));
+
+	rule = matviewRel->rd_rules->rules[0];
+	if (rule->event != CMD_SELECT || !(rule->isInstead))
+		elog(ERROR,
+			 "the rule for materialized view \"%s\" is not a SELECT INSTEAD OF rule",
+			 RelationGetRelationName(matviewRel));
+
+	actions = rule->actions;
+	if (list_length(actions) != 1)
+		elog(ERROR,
+			 "the rule for materialized view \"%s\" is not a single action",
+			 RelationGetRelationName(matviewRel));
+
+	/*
+	 * The stored query was rewritten at the time of the MV definition, but
+	 * has not been scribbled on by the planner.
+	 */
+	return linitial_node(Query, actions);
+}
+
+
+/* ----------------------------------------------------
+ *		Incremental View Maintenance routines
+ * ---------------------------------------------------
+ */
+
+/*
+ * IVM_immediate_before
+ *
+ * IVM trigger function invoked before base table is modified. If this is
+ * invoked firstly in the same statement, we save the transaction id and the
+ * command id at that time.
+ */
+Datum
+IVM_immediate_before(PG_FUNCTION_ARGS)
+{
+	TriggerData *trigdata = (TriggerData *) fcinfo->context;
+	char	   *matviewOid_text = trigdata->tg_trigger->tgargs[0];
+	char	   *ex_lock_text = trigdata->tg_trigger->tgargs[1];
+	Oid			matviewOid;
+	MV_TriggerHashEntry *entry;
+	bool	found;
+	bool	ex_lock;
+
+	matviewOid = DatumGetObjectId(DirectFunctionCall1(oidin, CStringGetDatum(matviewOid_text)));
+	ex_lock = DatumGetBool(DirectFunctionCall1(boolin, CStringGetDatum(ex_lock_text)));
+
+	/* If the view has more than one tables, we have to use an exclusive lock. */
+	if (ex_lock)
+	{
+		FullTransactionId xid;
+
+		/*
+		 * Wait for concurrent transactions which update this materialized view at
+		 * READ COMMITED. This is needed to see changes committed in other
+		 * transactions. No wait and raise an error at REPEATABLE READ or
+		 * SERIALIZABLE to prevent update anomalies of matviews.
+		 * XXX: dead-lock is possible here.
+		 */
+		if (!IsolationUsesXactSnapshot())
+			LockRelationOid(matviewOid, ExclusiveLock);
+		else if (!ConditionalLockRelationOid(matviewOid, ExclusiveLock))
+		{
+			/* try to throw error by name; relation could be deleted... */
+			char	   *relname = get_rel_name(matviewOid);
+
+			if (!relname)
+				ereport(ERROR,
+						(errcode(ERRCODE_LOCK_NOT_AVAILABLE),
+						errmsg("could not obtain lock on materialized view during incremental maintenance")));
+
+			ereport(ERROR,
+					(errcode(ERRCODE_LOCK_NOT_AVAILABLE),
+					errmsg("could not obtain lock on materialized view \"%s\" during incremental maintenance",
+							relname)));
+		}
+
+		/*
+		 * Even if we can acquire an lock, a concurrent transaction could have
+		 * updated the view incrementally and been committed before we acquired
+		 * the lock. Therefore, we have to check the transaction ID of the most
+		 * recent update of the view, and if this was in progress at the
+		 * transaction start, raise an error to prevent anomalies.
+		 */
+		xid = getLastUpdateXid(matviewOid);
+		if (XidInMVCCSnapshot(XidFromFullTransactionId(xid), GetTransactionSnapshot()))
+			ereport(ERROR,
+					(errcode(ERRCODE_T_R_SERIALIZATION_FAILURE),
+					 errmsg("the materialized view is incrementally updated in concurrent transaction"),
+					 errhint("The transaction might succeed if retried.")));
+	}
+	else
+		LockRelationOid(matviewOid, RowExclusiveLock);
+
+	/*
+	 * On the first call initialize the hashtable
+	 */
+	if (!mv_trigger_info)
+		mv_InitHashTables();
+
+	entry = (MV_TriggerHashEntry *) hash_search(mv_trigger_info,
+											  (void *) &matviewOid,
+											  HASH_ENTER, &found);
+
+	/* On the first BEFORE to update the view, initialize trigger data */
+	if (!found || entry->snapshot == InvalidSnapshot)
+	{
+		Snapshot snapshot;
+
+		/*
+		 * Get a snapshot just before the table was modified for checking
+		 * tuple visibility in the pre-update state of the table.
+		 *
+		 * In READ COMMITTED, use the latest snapshot again to see the
+		 * results of concurrent transactions committed after the current
+		 * transaction started.
+		 */
+		if (IsolationUsesXactSnapshot())
+			snapshot = GetActiveSnapshot();
+		else
+			snapshot = GetTransactionSnapshot();
+
+		entry->matview_id = matviewOid;
+		entry->before_trig_count = 0;
+		entry->after_trig_count = 0;
+		entry->snapshot = RegisterSnapshot(snapshot);
+		entry->tables = NIL;
+		entry->has_old = false;
+		entry->has_new = false;
+
+		/*
+		 * If this is the first table modifying query in the transaction,
+		 * initialize the list of subxids.
+		 */
+		if (!found)
+			entry->subxids = NIL;
+	}
+
+	entry->before_trig_count++;
+
+	return PointerGetDatum(NULL);
+}
+
+/*
+ * IVM_immediate_maintenance
+ *
+ * IVM trigger function invoked after base table is modified.
+ * For each table, tuplestores of transition tables are collected.
+ * and after the last modification
+ */
+Datum
+IVM_immediate_maintenance(PG_FUNCTION_ARGS)
+{
+	TriggerData *trigdata = (TriggerData *) fcinfo->context;
+	Relation	rel;
+	Oid			relid;
+	Oid			matviewOid;
+	Query	   *query;
+	Query	   *rewritten = NULL;
+	char	   *matviewOid_text = trigdata->tg_trigger->tgargs[0];
+	Relation	matviewRel;
+	int old_depth = matview_maintenance_depth;
+	SubTransactionId subxid;
+
+	Oid			relowner;
+	Tuplestorestate *old_tuplestore = NULL;
+	Tuplestorestate *new_tuplestore = NULL;
+	DestReceiver *dest_new = NULL, *dest_old = NULL;
+	Oid			save_userid;
+	int			save_sec_context;
+	int			save_nestlevel;
+
+	MV_TriggerHashEntry *entry;
+	MV_TriggerTable		*table;
+	bool	found;
+
+	ParseState		 *pstate;
+	QueryEnvironment *queryEnv = create_queryEnv();
+	MemoryContext	oldcxt;
+	ListCell   *lc;
+	int			i;
+
+
+	/* Create a ParseState for rewriting the view definition query */
+	pstate = make_parsestate(NULL);
+	pstate->p_queryEnv = queryEnv;
+	pstate->p_expr_kind = EXPR_KIND_SELECT_TARGET;
+
+	rel = trigdata->tg_relation;
+	relid = rel->rd_id;
+
+	matviewOid = DatumGetObjectId(DirectFunctionCall1(oidin, CStringGetDatum(matviewOid_text)));
+
+	/*
+	 * On the first call initialize the hashtable
+	 */
+	if (!mv_trigger_info)
+		mv_InitHashTables();
+
+	/* get the entry for this materialized view */
+	entry = (MV_TriggerHashEntry *) hash_search(mv_trigger_info,
+											  (void *) &matviewOid,
+											  HASH_FIND, &found);
+	Assert (found && entry != NULL);
+	entry->after_trig_count++;
+
+	/* search the entry for the modified table and create new entry if not found */
+	found = false;
+	foreach(lc, entry->tables)
+	{
+		table = (MV_TriggerTable *) lfirst(lc);
+		if (table->table_id == relid)
+		{
+			found = true;
+			break;
+		}
+	}
+	if (!found)
+	{
+		oldcxt = MemoryContextSwitchTo(TopTransactionContext);
+
+		table = (MV_TriggerTable *) palloc0(sizeof(MV_TriggerTable));
+		table->table_id = relid;
+		table->old_tuplestores = NIL;
+		table->new_tuplestores = NIL;
+		table->rte_indexes = NIL;
+		table->slot = MakeSingleTupleTableSlot(RelationGetDescr(rel), table_slot_callbacks(rel));
+		/* We assume we have at least RowExclusiveLock on modified tables. */
+		table->rel = table_open(RelationGetRelid(rel), NoLock);
+		entry->tables = lappend(entry->tables, table);
+
+		MemoryContextSwitchTo(oldcxt);
+	}
+
+	/* Save the transition tables and make a request to not free immediately */
+	if (trigdata->tg_oldtable)
+	{
+		oldcxt = MemoryContextSwitchTo(TopTransactionContext);
+		table->old_tuplestores = lappend(table->old_tuplestores, trigdata->tg_oldtable);
+		entry->has_old = true;
+		MemoryContextSwitchTo(oldcxt);
+	}
+	if (trigdata->tg_newtable)
+	{
+		oldcxt = MemoryContextSwitchTo(TopTransactionContext);
+		table->new_tuplestores = lappend(table->new_tuplestores, trigdata->tg_newtable);
+		entry->has_new = true;
+		MemoryContextSwitchTo(oldcxt);
+	}
+	if (entry->has_new || entry->has_old)
+	{
+		CmdType cmd;
+
+		if (TRIGGER_FIRED_BY_INSERT(trigdata->tg_event))
+			cmd = CMD_INSERT;
+		else if (TRIGGER_FIRED_BY_DELETE(trigdata->tg_event))
+			cmd = CMD_DELETE;
+		else if (TRIGGER_FIRED_BY_UPDATE(trigdata->tg_event))
+			cmd = CMD_UPDATE;
+		else
+			elog(ERROR,"unsupported trigger type");
+
+		/* Prolong lifespan of transition tables to the end of the last AFTER trigger */
+		SetTransitionTablePreserved(relid, cmd);
+	}
+
+
+	/* If this is not the last AFTER trigger call, immediately exit. */
+	Assert (entry->before_trig_count >= entry->after_trig_count);
+	if (entry->before_trig_count != entry->after_trig_count)
+		return PointerGetDatum(NULL);
+
+	/*
+	 * If this is the last AFTER trigger call, continue and update the view.
+	 */
+
+	/* record the subxid that updated the view incrementally */
+	subxid = GetCurrentSubTransactionId();
+	if (!list_member_xid(entry->subxids, subxid))
+	{
+		oldcxt = MemoryContextSwitchTo(TopTransactionContext);
+		entry->subxids = lappend_xid(entry->subxids, subxid);
+		MemoryContextSwitchTo(oldcxt);
+	}
+
+	/*
+	 * Advance command counter to make the updated base table rows locally
+	 * visible.
+	 */
+	CommandCounterIncrement();
+
+	matviewRel = table_open(matviewOid, NoLock);
+
+	/* Make sure it is a materialized view. */
+	Assert(matviewRel->rd_rel->relkind == RELKIND_MATVIEW);
+
+	/*
+	 * In READ COMMITTED, get and push the latest snapshot again to see the
+	 * results of concurrent transactions committed after the current
+	 * transaction started.
+	 */
+	if (!IsolationUsesXactSnapshot())
+		PushActiveSnapshot(GetTransactionSnapshot());
+
+	/*
+	 * Check for active uses of the relation in the current transaction, such
+	 * as open scans.
+	 *
+	 * NB: We count on this to protect us against problems with refreshing the
+	 * data using TABLE_INSERT_FROZEN.
+	 */
+	CheckTableNotInUse(matviewRel, "refresh a materialized view incrementally");
+
+	/*
+	 * Switch to the owner's userid, so that any functions are run as that
+	 * user.  Also arrange to make GUC variable changes local to this command.
+	 * We will switch modes when we are about to execute user code.
+	 */
+	relowner = matviewRel->rd_rel->relowner;
+	GetUserIdAndSecContext(&save_userid, &save_sec_context);
+	SetUserIdAndSecContext(relowner,
+						   save_sec_context | SECURITY_RESTRICTED_OPERATION);
+	save_nestlevel = NewGUCNestLevel();
+
+	/* get view query*/
+	query = get_matview_query(matviewRel);
+
+	/*
+	 * When a base table is truncated, the view content will be empty if the
+	 * view definition query does not contain an aggregate without a GROUP clause.
+	 * Therefore, such views can be truncated.
+	 */
+	if (TRIGGER_FIRED_BY_TRUNCATE(trigdata->tg_event))
+	{
+		ExecuteTruncateGuts(list_make1(matviewRel), list_make1_oid(matviewOid),
+							NIL, DROP_RESTRICT, false, false);
+
+		/* Clean up hash entry and delete tuplestores */
+		clean_up_IVM_hash_entry(entry, false, InvalidSubTransactionId);
+
+		/* Pop the original snapshot. */
+		if (!IsolationUsesXactSnapshot())
+			PopActiveSnapshot();
+
+		table_close(matviewRel, NoLock);
+
+		/* Roll back any GUC changes */
+		AtEOXact_GUC(false, save_nestlevel);
+
+		/* Restore userid and security context */
+		SetUserIdAndSecContext(save_userid, save_sec_context);
+
+		return PointerGetDatum(NULL);
+	}
+
+	/*
+	 * rewrite query for calculating deltas
+	 */
+
+	rewritten = copyObject(query);
+
+	/* Replace resnames in a target list with materialized view's attnames */
+	i = 0;
+	foreach (lc, rewritten->targetList)
+	{
+		TargetEntry *tle = (TargetEntry *) lfirst(lc);
+		Form_pg_attribute attr = TupleDescAttr(matviewRel->rd_att, i);
+		char *resname = NameStr(attr->attname);
+
+		tle->resname = pstrdup(resname);
+		i++;
+	}
+
+	/* Set all tables in the query to pre-update state */
+	rewritten = rewrite_query_for_preupdate_state(rewritten, entry->tables,
+												  pstate, matviewOid);
+	/* Rewrite for counting duplicated tuples */
+	rewritten = rewrite_query_for_counting(rewritten, pstate);
+
+	/* Create tuplestores to store view deltas */
+	if (entry->has_old)
+	{
+		oldcxt = MemoryContextSwitchTo(TopTransactionContext);
+
+		old_tuplestore = tuplestore_begin_heap(false, false, work_mem);
+		dest_old = CreateDestReceiver(DestTuplestore);
+		SetTuplestoreDestReceiverParams(dest_old,
+									old_tuplestore,
+									TopTransactionContext,
+									false,
+									NULL,
+									NULL);
+
+		MemoryContextSwitchTo(oldcxt);
+	}
+	if (entry->has_new)
+	{
+		oldcxt = MemoryContextSwitchTo(TopTransactionContext);
+
+		new_tuplestore = tuplestore_begin_heap(false, false, work_mem);
+		dest_new = CreateDestReceiver(DestTuplestore);
+		SetTuplestoreDestReceiverParams(dest_new,
+									new_tuplestore,
+									TopTransactionContext,
+									false,
+									NULL,
+									NULL);
+		MemoryContextSwitchTo(oldcxt);
+	}
+
+	/* for all modified tables */
+	foreach(lc, entry->tables)
+	{
+		ListCell *lc2;
+
+		table = (MV_TriggerTable *) lfirst(lc);
+
+		/* loop for self-join */
+		foreach(lc2, table->rte_indexes)
+		{
+			int	rte_index = lfirst_int(lc2);
+			TupleDesc		tupdesc_old;
+			TupleDesc		tupdesc_new;
+
+			/* calculate delta tables */
+			calc_delta(table, rte_index, rewritten, dest_old, dest_new,
+					   &tupdesc_old, &tupdesc_new, queryEnv);
+
+			/* Set the table in the query to post-update state */
+			rewritten = rewrite_query_for_postupdate_state(rewritten, table, rte_index);
+
+			PG_TRY();
+			{
+				/* apply the delta tables to the materialized view */
+				apply_delta(matviewOid, old_tuplestore, new_tuplestore,
+							tupdesc_old, tupdesc_new, query);
+			}
+			PG_CATCH();
+			{
+				matview_maintenance_depth = old_depth;
+				PG_RE_THROW();
+			}
+			PG_END_TRY();
+
+			/* clear view delta tuplestores */
+			if (old_tuplestore)
+				tuplestore_clear(old_tuplestore);
+			if (new_tuplestore)
+				tuplestore_clear(new_tuplestore);
+		}
+	}
+
+	/* Clean up hash entry and delete tuplestores */
+	clean_up_IVM_hash_entry(entry, false, InvalidSubTransactionId);
+	if (old_tuplestore)
+	{
+		dest_old->rDestroy(dest_old);
+		tuplestore_end(old_tuplestore);
+	}
+	if (new_tuplestore)
+	{
+		dest_new->rDestroy(dest_new);
+		tuplestore_end(new_tuplestore);
+	}
+
+	/* Pop the original snapshot. */
+	if (!IsolationUsesXactSnapshot())
+		PopActiveSnapshot();
+
+	table_close(matviewRel, NoLock);
+
+	/* Roll back any GUC changes */
+	AtEOXact_GUC(false, save_nestlevel);
+
+	/* Restore userid and security context */
+	SetUserIdAndSecContext(save_userid, save_sec_context);
+
+	return PointerGetDatum(NULL);
+}
+
+/*
+ * rewrite_query_for_preupdate_state
+ *
+ * Rewrite the query so that base tables' RTEs will represent "pre-update"
+ * state of tables. This is necessary to calculate view delta after multiple
+ * tables are modified.
+ */
+static Query*
+rewrite_query_for_preupdate_state(Query *query, List *tables,
+								  ParseState *pstate, Oid matviewid)
+{
+	ListCell *lc;
+	int num_rte = list_length(query->rtable);
+	int i;
+
+
+	/* register delta ENRs */
+	register_delta_ENRs(pstate, query, tables);
+
+	/* XXX: Is necessary? Is this right timing? */
+	AcquireRewriteLocks(query, true, false);
+
+	i = 1;
+	foreach(lc, query->rtable)
+	{
+		RangeTblEntry *r = (RangeTblEntry*) lfirst(lc);
+
+		ListCell *lc2;
+		foreach(lc2, tables)
+		{
+			MV_TriggerTable *table = (MV_TriggerTable *) lfirst(lc2);
+			/*
+			 * if the modified table is found then replace the original RTE with
+			 * "pre-state" RTE and append its index to the list.
+			 */
+			if (r->relid == table->table_id)
+			{
+				List *securityQuals;
+				List *withCheckOptions;
+				bool  hasRowSecurity;
+				bool  hasSubLinks;
+
+				RangeTblEntry *rte_pre = get_prestate_rte(r, table, pstate->p_queryEnv, matviewid);
+
+				/*
+				 * Set a row security poslicies of the modified table to the subquery RTE which
+				 * represents the pre-update state of the table.
+				 */
+				get_row_security_policies(query, table->original_rte, i,
+										  &securityQuals, &withCheckOptions,
+										  &hasRowSecurity, &hasSubLinks);
+
+				if (hasRowSecurity)
+				{
+					query->hasRowSecurity = true;
+					rte_pre->security_barrier = true;
+				}
+				if (hasSubLinks)
+					query->hasSubLinks = true;
+
+				rte_pre->securityQuals = securityQuals;
+				lfirst(lc) = rte_pre;
+
+				table->rte_indexes = lappend_int(table->rte_indexes, i);
+				break;
+			}
+		}
+
+		/* finish the loop if we processed all RTE included in the original query */
+		if (i++ >= num_rte)
+			break;
+	}
+
+	return query;
+}
+
+/*
+ * register_delta_ENRs
+ *
+ * For all modified tables, make ENRs for their transition tables
+ * and register them to the queryEnv. ENR's RTEs are also appended
+ * into the list in query tree.
+ */
+static void
+register_delta_ENRs(ParseState *pstate, Query *query, List *tables)
+{
+	QueryEnvironment *queryEnv = pstate->p_queryEnv;
+	ListCell *lc;
+	RangeTblEntry	*rte;
+
+	foreach(lc, tables)
+	{
+		MV_TriggerTable *table = (MV_TriggerTable *) lfirst(lc);
+		ListCell *lc2;
+		int count;
+
+		count = 0;
+		foreach(lc2, table->old_tuplestores)
+		{
+			Tuplestorestate *oldtable = (Tuplestorestate *) lfirst(lc2);
+			EphemeralNamedRelation enr =
+				palloc(sizeof(EphemeralNamedRelationData));
+			ParseNamespaceItem *nsitem;
+
+			enr->md.name = make_delta_enr_name("old", table->table_id, count);
+			enr->md.reliddesc = table->table_id;
+			enr->md.tupdesc = NULL;
+			enr->md.enrtype = ENR_NAMED_TUPLESTORE;
+			enr->md.enrtuples = tuplestore_tuple_count(oldtable);
+			enr->reldata = oldtable;
+			register_ENR(queryEnv, enr);
+
+			nsitem = addRangeTableEntryForENR(pstate, makeRangeVar(NULL, enr->md.name, -1), true);
+			rte = nsitem->p_rte;
+
+			query->rtable = lappend(query->rtable, rte);
+
+			count++;
+		}
+
+		count = 0;
+		foreach(lc2, table->new_tuplestores)
+		{
+			Tuplestorestate *newtable = (Tuplestorestate *) lfirst(lc2);
+			EphemeralNamedRelation enr =
+				palloc(sizeof(EphemeralNamedRelationData));
+			ParseNamespaceItem *nsitem;
+
+			enr->md.name = make_delta_enr_name("new", table->table_id, count);
+			enr->md.reliddesc = table->table_id;
+			enr->md.tupdesc = NULL;
+			enr->md.enrtype = ENR_NAMED_TUPLESTORE;
+			enr->md.enrtuples = tuplestore_tuple_count(newtable);
+			enr->reldata = newtable;
+			register_ENR(queryEnv, enr);
+
+			nsitem = addRangeTableEntryForENR(pstate, makeRangeVar(NULL, enr->md.name, -1), true);
+			rte = nsitem->p_rte;
+
+			query->rtable = lappend(query->rtable, rte);
+
+			count++;
+		}
+	}
+}
+
+#define DatumGetItemPointer(X)	 ((ItemPointer) DatumGetPointer(X))
+#define PG_GETARG_ITEMPOINTER(n) DatumGetItemPointer(PG_GETARG_DATUM(n))
+
+/*
+ * ivm_visible_in_prestate
+ *
+ * Check visibility of a tuple specified by the tableoid and item pointer
+ * using the snapshot taken just before the table was modified.
+ */
+Datum
+ivm_visible_in_prestate(PG_FUNCTION_ARGS)
+{
+	Oid			tableoid = PG_GETARG_OID(0);
+	ItemPointer itemPtr = PG_GETARG_ITEMPOINTER(1);
+	Oid			matviewOid = PG_GETARG_OID(2);
+	MV_TriggerHashEntry *entry;
+	MV_TriggerTable		*table = NULL;
+	ListCell   *lc;
+	bool	found;
+	bool	result;
+
+	if (!in_delta_calculation)
+		ereport(ERROR,
+				(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+				 errmsg("ivm_visible_in_prestate can be called only in delta calculation")));
+
+	entry = (MV_TriggerHashEntry *) hash_search(mv_trigger_info,
+											  (void *) &matviewOid,
+											  HASH_FIND, &found);
+	Assert (found && entry != NULL);
+
+	foreach(lc, entry->tables)
+	{
+		table = (MV_TriggerTable *) lfirst(lc);
+		if (table->table_id == tableoid)
+			break;
+	}
+
+	Assert (table != NULL);
+
+	result = table_tuple_fetch_row_version(table->rel, itemPtr, entry->snapshot, table->slot);
+
+	PG_RETURN_BOOL(result);
+}
+
+/*
+ * get_prestate_rte
+ *
+ * Rewrite RTE of the modified table to a subquery which represents
+ * "pre-state" table. The original RTE is saved in table->rte_original.
+ */
+static RangeTblEntry*
+get_prestate_rte(RangeTblEntry *rte, MV_TriggerTable *table,
+				 QueryEnvironment *queryEnv, Oid matviewid)
+{
+	StringInfoData str;
+	RawStmt *raw;
+	Query *subquery;
+	ParseState *pstate;
+	char *relname;
+	static char *subquery_tl;
+	int i;
+
+	pstate = make_parsestate(NULL);
+	pstate->p_queryEnv = queryEnv;
+	pstate->p_expr_kind = EXPR_KIND_SELECT_TARGET;
+
+	relname = quote_qualified_identifier(
+					get_namespace_name(RelationGetNamespace(table->rel)),
+									   RelationGetRelationName(table->rel));
+
+	subquery_tl = make_subquery_targetlist_from_table(table);
+
+	/*
+	 * Filtering inserted row using the snapshot taken before the table
+	 * is modified. ctid is required for maintaining outer join views.
+	 */
+	initStringInfo(&str);
+	appendStringInfo(&str,
+		"SELECT %s FROM %s t"
+		" WHERE pg_catalog.ivm_visible_in_prestate(t.tableoid, t.ctid ,%d::pg_catalog.oid)",
+			subquery_tl, relname, matviewid);
+
+	/*
+	 * Re-add rows deleted from the old transition tables, excluding those
+	 * also present in the new transition tables.
+	 */
+	if (list_length(table->old_tuplestores) > 0)
+	{
+		appendStringInfo(&str," UNION ALL SELECT %s  FROM (",
+			subquery_tl);
+
+		for (i = 0; i < list_length(table->old_tuplestores); i++)
+		{
+			if (i != 0)
+				appendStringInfo(&str, " UNION ALL ");
+			appendStringInfo(&str," TABLE %s",
+				make_delta_enr_name("old", table->table_id, i));
+		}
+		for (i = 0; i < list_length(table->new_tuplestores); i++)
+		{
+			appendStringInfo(&str, " EXCEPT ALL ");
+			appendStringInfo(&str," TABLE %s",
+				make_delta_enr_name("new", table->table_id, i));
+		}
+		appendStringInfo(&str,")");
+	}
+
+	/* Get a subquery representing pre-state of the table */
+	raw = (RawStmt*)linitial(raw_parser(str.data, RAW_PARSE_DEFAULT));
+	subquery = transformStmt(pstate, raw->stmt);
+
+	/* save the original RTE */
+	table->original_rte = copyObject(rte);
+
+	rte->rtekind = RTE_SUBQUERY;
+	rte->subquery = subquery;
+	rte->security_barrier = false;
+
+	/* Clear fields that should not be set in a subquery RTE */
+	rte->relid = InvalidOid;
+	rte->relkind = 0;
+	rte->rellockmode = 0;
+	rte->tablesample = NULL;
+	rte->perminfoindex = 0;         /* no permission checking for this RTE */
+	rte->inh = false;			/* must not be set for a subquery */
+
+	return rte;
+}
+
+/*
+ * make_subquery_targetlist_from_table
+ *
+ * Make a targetlist string of a subquery representing a delta table or a
+ * pre-update state table. This subquery substitutes a modified table RTE
+ * in the view definition query during view maintenance. In the targetlist,
+ * column names appear in order of the table definition. However, for
+ * attribute numbers of vars in the query tree to reference columns of the
+ * subquery  correctly even though the table has a dropped column, put "null"
+ * as a dummy value at the position of a dropped column.
+ *
+ * We would also able to walk the query tree to rewrite varattnos, but
+ * crafting targetlist is more simple and reasonable.
+ */
+static char*
+make_subquery_targetlist_from_table(MV_TriggerTable *table)
+{
+	StringInfoData str;
+	TupleDesc	tupdesc;
+	int			i;
+
+	tupdesc = RelationGetDescr(table->rel);
+	initStringInfo(&str);
+	for (i = 0; i < tupdesc->natts; i++)
+	{
+		Form_pg_attribute attr = TupleDescAttr(tupdesc, i);
+
+		if (i > 0)
+			appendStringInfo(&str, ", ");
+
+		if (attr->attisdropped)
+			appendStringInfo(&str, "null");
+		else
+			appendStringInfo(&str, "%s", quote_identifier(NameStr(attr->attname)));
+	}
+
+	return str.data;
+}
+
+/*
+ * make_delta_enr_name
+ *
+ * Make a name for ENR of a transition table from the base table's oid.
+ * prefix will be "new" or "old" depending on its transition table kind..
+ */
+static char*
+make_delta_enr_name(const char *prefix, Oid relid, int count)
+{
+	char buf[NAMEDATALEN];
+	char *name;
+
+	snprintf(buf, NAMEDATALEN, "__ivm_%s_%u_%u", prefix, relid, count);
+	name = pstrdup(buf);
+
+	return name;
+}
+
+/*
+ * makeDeltaTable
+ *
+ * Make a RTE representing a delta of the specified table.
+ */
+static RangeTblEntry*
+makeDeltaTable(RangeTblEntry *rte, MV_TriggerTable *table,
+		   bool is_new, QueryEnvironment *queryEnv)
+{
+	StringInfoData str;
+	ParseState	*pstate;
+	RawStmt *raw;
+	Query *sub;
+	int		i;
+
+	const char *prefix_union = is_new ? "new" : "old";
+	const char *prefix_except = is_new ? "old" : "new";
+	int num_union = is_new ? list_length(table->new_tuplestores) : list_length(table->old_tuplestores);
+	int num_except = is_new ? list_length(table->old_tuplestores) : list_length(table->new_tuplestores);
+
+	/* the previous RTE must be a subquery which represents "pre-state" table */
+	Assert(rte->rtekind == RTE_SUBQUERY);
+
+	/* Create a ParseState for rewriting the view definition query */
+	pstate = make_parsestate(NULL);
+	pstate->p_queryEnv = queryEnv;
+	pstate->p_expr_kind = EXPR_KIND_NONE;
+
+	initStringInfo(&str);
+	appendStringInfo(&str,
+		" SELECT %s FROM ( ",
+		make_subquery_targetlist_from_table(table));
+
+	for (i = 0; i < num_union; i++)
+	{
+		if (i > 0)
+			appendStringInfo(&str, " UNION ALL ");
+
+		appendStringInfo(&str,
+			" TABLE  %s",
+			make_delta_enr_name(prefix_union, table->table_id, i));
+	}
+	for (i = 0; i < num_except; i++)
+	{
+		appendStringInfo(&str, " EXCEPT ALL ");
+
+		appendStringInfo(&str,
+			" TABLE  %s",
+			make_delta_enr_name(prefix_except, table->table_id, i));
+	}
+	appendStringInfo(&str,")");
+
+	raw = (RawStmt*)linitial(raw_parser(str.data, RAW_PARSE_DEFAULT));
+	sub = transformStmt(pstate, raw->stmt);
+
+	/*
+	 * Update the subquery so that it represent the combined transition
+	 * table.  Note that we leave the security_barrier and securityQuals
+	 * fields so that the subquery relation can be protected by the RLS
+	 * policy as same as the modified table.
+	 */
+	rte->rtekind = RTE_SUBQUERY;
+	rte->subquery = sub;
+
+	return rte;
+}
+
+/*
+ * rewrite_query_for_counting
+ *
+ * Rewrite query for counting duplicated tuples.
+ */
+static Query *
+rewrite_query_for_counting(Query *query, ParseState *pstate)
+{
+	TargetEntry *tle_count;
+	FuncCall *fn;
+	Node *node;
+
+	/* Add count(*) for counting distinct tuples in views */
+	fn = makeFuncCall(SystemFuncName("count"), NIL, COERCE_EXPLICIT_CALL, -1);
+	fn->agg_star = true;
+	if (!query->groupClause && !query->hasAggs)
+		query->groupClause = transformDistinctClause(NULL, &query->targetList, query->sortClause, false);
+
+	node = ParseFuncOrColumn(pstate, fn->funcname, NIL, NULL, fn, false, -1);
+
+	tle_count = makeTargetEntry((Expr *) node,
+								list_length(query->targetList) + 1,
+								pstrdup("__ivm_count__"),
+								false);
+	query->targetList = lappend(query->targetList, tle_count);
+	query->hasAggs = true;
+
+	return query;
+}
+
+/*
+ * calc_delta
+ *
+ * Calculate view deltas generated under the modification of a table specified
+ * by the RTE index.
+ */
+static void
+calc_delta(MV_TriggerTable *table, int rte_index, Query *query,
+			DestReceiver *dest_old, DestReceiver *dest_new,
+			TupleDesc *tupdesc_old, TupleDesc *tupdesc_new,
+			QueryEnvironment *queryEnv)
+{
+	ListCell *lc = list_nth_cell(query->rtable, rte_index - 1);
+	RangeTblEntry *rte = (RangeTblEntry *) lfirst(lc);
+
+	in_delta_calculation = true;
+
+	/* Generate old delta */
+	if (dest_old && list_length(table->old_tuplestores) > 0)
+	{
+		/* Replace the modified table with the old delta table and calculate the old view delta. */
+		lfirst(lc) = makeDeltaTable(rte, table, false, queryEnv);
+		refresh_matview_datafill(dest_old, query, queryEnv, tupdesc_old, "", false);
+	}
+
+	/* Generate new delta */
+	if (dest_new && list_length(table->new_tuplestores) > 0)
+	{
+		/* Replace the modified table with the new delta table and calculate the new view delta*/
+		lfirst(lc) = makeDeltaTable(rte, table, true, queryEnv);
+		refresh_matview_datafill(dest_new, query, queryEnv, tupdesc_new, "", false);
+	}
+
+	in_delta_calculation = false;
+}
+
+/*
+ * rewrite_query_for_postupdate_state
+ *
+ * Rewrite the query so that the specified base table's RTEs will represent
+ * "post-update" state of tables. This is called after the view delta
+ * calculation due to changes on this table finishes.
+ */
+static Query*
+rewrite_query_for_postupdate_state(Query *query, MV_TriggerTable *table, int rte_index)
+{
+	ListCell *lc = list_nth_cell(query->rtable, rte_index - 1);
+
+	/* Retore the original RTE */
+	lfirst(lc) = table->original_rte;
+
+	return query;
+}
+
+/*
+ * apply_delta
+ *
+ * Apply deltas to the materialized view. In outer join cases, this requires
+ * the view maintenance graph.
+ */
+static void
+apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *new_tuplestores,
+			TupleDesc tupdesc_old, TupleDesc tupdesc_new,
+			Query *query)
+{
+	StringInfoData querybuf;
+	StringInfoData target_list_buf;
+	Relation	matviewRel;
+	char	   *matviewname;
+	ListCell	*lc;
+	int			i;
+	List	   *keys = NIL;
+
+
+	/*
+	 * get names of the materialized view and delta tables
+	 */
+
+	matviewRel = table_open(matviewOid, NoLock);
+	matviewname = quote_qualified_identifier(get_namespace_name(RelationGetNamespace(matviewRel)),
+											 RelationGetRelationName(matviewRel));
+
+	/*
+	 * Build parts of the maintenance queries
+	 */
+
+	initStringInfo(&querybuf);
+	initStringInfo(&target_list_buf);
+
+	/* build string of target list */
+	for (i = 0; i < matviewRel->rd_att->natts; i++)
+	{
+		Form_pg_attribute attr = TupleDescAttr(matviewRel->rd_att, i);
+		char   *resname = NameStr(attr->attname);
+
+		if (i != 0)
+			appendStringInfo(&target_list_buf, ", ");
+		appendStringInfo(&target_list_buf, "%s", quote_qualified_identifier(NULL, resname));
+	}
+
+	i = 0;
+	foreach (lc, query->targetList)
+	{
+		TargetEntry *tle = (TargetEntry *) lfirst(lc);
+		Form_pg_attribute attr = TupleDescAttr(matviewRel->rd_att, i);
+
+		i++;
+
+		if (tle->resjunk)
+			continue;
+
+		keys = lappend(keys, attr);
+	}
+
+	/* Start maintaining the materialized view. */
+	OpenMatViewIncrementalMaintenance();
+
+	/* Open SPI context. */
+	if (SPI_connect() != SPI_OK_CONNECT)
+		elog(ERROR, "SPI_connect failed");
+
+	/* For tuple deletion */
+	if (old_tuplestores && tuplestore_tuple_count(old_tuplestores) > 0)
+	{
+		EphemeralNamedRelation enr = palloc(sizeof(EphemeralNamedRelationData));
+		int				rc;
+
+		/* convert tuplestores to ENR, and register for SPI */
+		enr->md.name = pstrdup(OLD_DELTA_ENRNAME);
+		enr->md.reliddesc = InvalidOid;
+		enr->md.tupdesc = tupdesc_old;
+		enr->md.enrtype = ENR_NAMED_TUPLESTORE;
+		enr->md.enrtuples = tuplestore_tuple_count(old_tuplestores);
+		enr->reldata = old_tuplestores;
+
+		rc = SPI_register_relation(enr);
+		if (rc != SPI_OK_REL_REGISTER)
+			elog(ERROR, "SPI_register failed");
+
+		apply_old_delta(matviewname, OLD_DELTA_ENRNAME, keys);
+
+	}
+	/* For tuple insertion */
+	if (new_tuplestores && tuplestore_tuple_count(new_tuplestores) > 0)
+	{
+		EphemeralNamedRelation enr = palloc(sizeof(EphemeralNamedRelationData));
+		int rc;
+
+		/* convert tuplestores to ENR, and register for SPI */
+		enr->md.name = pstrdup(NEW_DELTA_ENRNAME);
+		enr->md.reliddesc = InvalidOid;
+		enr->md.tupdesc = tupdesc_new;;
+		enr->md.enrtype = ENR_NAMED_TUPLESTORE;
+		enr->md.enrtuples = tuplestore_tuple_count(new_tuplestores);
+		enr->reldata = new_tuplestores;
+
+		rc = SPI_register_relation(enr);
+		if (rc != SPI_OK_REL_REGISTER)
+			elog(ERROR, "SPI_register failed");
+
+		/* apply new delta */
+		apply_new_delta(matviewname, NEW_DELTA_ENRNAME, &target_list_buf);
+	}
+
+	/* We're done maintaining the materialized view. */
+	CloseMatViewIncrementalMaintenance();
+
+	table_close(matviewRel, NoLock);
+
+	/* Close SPI context. */
+	if (SPI_finish() != SPI_OK_FINISH)
+		elog(ERROR, "SPI_finish failed");
+}
+
+/*
+ * apply_old_delta
+ *
+ * Execute a query for applying a delta table given by deltname_old
+ * which contains tuples to be deleted from to a materialized view given by
+ * matviewname.  This is used when counting is not required.
+ */
+static void
+apply_old_delta(const char *matviewname, const char *deltaname_old,
+				List *keys)
+{
+	StringInfoData	querybuf;
+	StringInfoData	keysbuf;
+	char   *match_cond;
+	ListCell *lc;
+
+	/* build WHERE condition for searching tuples to be deleted */
+	match_cond = get_matching_condition_string(keys);
+
+	/* build string of keys list */
+	initStringInfo(&keysbuf);
+	foreach (lc, keys)
+	{
+		Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc);
+		char   *resname = NameStr(attr->attname);
+		appendStringInfo(&keysbuf, "%s", quote_qualified_identifier("mv", resname));
+		if (lnext(keys, lc))
+			appendStringInfo(&keysbuf, ", ");
+	}
+
+	/* Search for matching tuples from the view and update or delete if found. */
+	initStringInfo(&querybuf);
+	appendStringInfo(&querybuf,
+	"DELETE FROM %s WHERE ctid IN ("
+		"SELECT tid FROM (SELECT pg_catalog.row_number() over (partition by %s) AS \"__ivm_row_number__\","
+								  "mv.ctid AS tid,"
+								  "diff.\"__ivm_count__\""
+						 "FROM %s AS mv, %s AS diff "
+						 "WHERE %s) v "
+					"WHERE v.\"__ivm_row_number__\" OPERATOR(pg_catalog.<=) v.\"__ivm_count__\")",
+					matviewname,
+					keysbuf.data,
+					matviewname, deltaname_old,
+					match_cond);
+
+	if (SPI_exec(querybuf.data, 0) != SPI_OK_DELETE)
+		elog(ERROR, "SPI_exec failed: %s", querybuf.data);
+}
+
+/*
+ * apply_new_delta
+ *
+ * Execute a query for applying a delta table given by deltname_new
+ * which contains tuples to be inserted into a materialized view given by
+ * matviewname.  This is used when counting is not required.
+ */
+static void
+apply_new_delta(const char *matviewname, const char *deltaname_new,
+				StringInfo target_list)
+{
+	StringInfoData	querybuf;
+
+	/* Search for matching tuples from the view and update or delete if found. */
+	initStringInfo(&querybuf);
+	appendStringInfo(&querybuf,
+					"INSERT INTO %s (%s) SELECT %s FROM ("
+						"SELECT diff.*, pg_catalog.generate_series(1, diff.\"__ivm_count__\")"
+							" AS __ivm_generate_series__ "
+						"FROM %s AS diff) AS v",
+					matviewname, target_list->data, target_list->data,
+					deltaname_new);
+
+	if (SPI_exec(querybuf.data, 0) != SPI_OK_INSERT)
+		elog(ERROR, "SPI_exec failed: %s", querybuf.data);
+}
+
+/*
+ * get_matching_condition_string
+ *
+ * Build a predicate string for looking for a tuple with given keys.
+ */
+static char *
+get_matching_condition_string(List *keys)
+{
+	StringInfoData match_cond;
+	ListCell	*lc;
+
+	/* If there is no key columns, the condition is always true. */
+	if (keys == NIL)
+		return "true";
+
+	initStringInfo(&match_cond);
+	foreach (lc, keys)
+	{
+		Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc);
+		char   *resname = NameStr(attr->attname);
+		char   *mv_resname = quote_qualified_identifier("mv", resname);
+		char   *diff_resname = quote_qualified_identifier("diff", resname);
+		Oid		typid = attr->atttypid;
+
+		/* Considering NULL values, we can not use simple = operator. */
+		appendStringInfo(&match_cond, "(");
+		generate_equal(&match_cond, typid, mv_resname, diff_resname);
+		appendStringInfo(&match_cond, " OR (%s IS NULL AND %s IS NULL))",
+						 mv_resname, diff_resname);
+
+		if (lnext(keys, lc))
+			appendStringInfo(&match_cond, " AND ");
+	}
+
+	return match_cond.data;
+}
+
+/*
+ * generate_equals
+ *
+ * Generate an equality clause using given operands' default equality
+ * operator.
+ */
+static void
+generate_equal(StringInfo querybuf, Oid opttype,
+			   const char *leftop, const char *rightop)
+{
+	TypeCacheEntry *typentry;
+
+	typentry = lookup_type_cache(opttype, TYPECACHE_EQ_OPR);
+	if (!OidIsValid(typentry->eq_opr))
+		ereport(ERROR,
+				(errcode(ERRCODE_UNDEFINED_FUNCTION),
+				 errmsg("could not identify an equality operator for type %s",
+						format_type_be_qualified(opttype))));
+
+	generate_operator_clause(querybuf,
+							 leftop, opttype,
+							 typentry->eq_opr,
+							 rightop, opttype);
+}
+
+/*
+ * mv_InitHashTables
+ */
+static void
+mv_InitHashTables(void)
+{
+	HASHCTL		ctl;
+
+	memset(&ctl, 0, sizeof(ctl));
+	ctl.keysize = sizeof(Oid);
+	ctl.entrysize = sizeof(MV_TriggerHashEntry);
+	mv_trigger_info = hash_create("MV trigger info",
+								 MV_INIT_QUERYHASHSIZE,
+								 &ctl, HASH_ELEM | HASH_BLOBS);
+
+	memset(&ctl, 0, sizeof(ctl));
+	ctl.keysize = sizeof(Oid);
+	ctl.entrysize = sizeof(DroppedImmvInfo);
+	dropped_immv = hash_create("Dropped IMMVs", 16,
+							   &ctl, HASH_ELEM | HASH_BLOBS);
+}
+
+/*
+ * AtAbort_IVM
+ *
+ * Clean up hash entries for all materialized views. This is called at
+ * (sub-)transaction abort. When the top-level transaction is aborted,
+ * InvalidSubTransactionId is set to subxid.
+ *
+ * Also, remove dropped IMMV information if it is aborted.
+ */
+void
+AtAbort_IVM(SubTransactionId subxid)
+{
+	HASH_SEQ_STATUS seq;
+
+	if (mv_trigger_info)
+	{
+		MV_TriggerHashEntry *entry;
+		hash_seq_init(&seq, mv_trigger_info);
+		while ((entry = hash_seq_search(&seq)) != NULL)
+			clean_up_IVM_hash_entry(entry, true, subxid);
+	}
+
+	if (dropped_immv)
+	{
+		DroppedImmvInfo *entry;
+		hash_seq_init(&seq, dropped_immv);
+		while ((entry = hash_seq_search(&seq)) != NULL)
+		{
+			if (subxid == InvalidSubTransactionId || subxid == entry->subxid)
+				hash_search(dropped_immv, (void *) &entry->immv_oid, HASH_REMOVE, NULL);
+		}
+	}
+
+	in_delta_calculation = false;
+}
+
+/*
+ * AtPreCommit_IVM
+ *
+ * Record the transaction ID that updated the view incrementally.
+ * Also, remove the entry for dropped IMMVs.
+ */
+void
+AtPreCommit_IVM(void)
+{
+	HASH_SEQ_STATUS seq;
+
+	if (mv_trigger_info)
+	{
+		MV_TriggerHashEntry *entry;
+
+		/*
+		 * Record the transaction ID that udpate the view incrementally,
+		 * and perform the final clean up of the entry.
+		 */
+		hash_seq_init(&seq, mv_trigger_info);
+		while ((entry = hash_seq_search(&seq)) != NULL)
+		{
+			setLastUpdateXid(entry->matview_id, GetTopFullTransactionId());
+			hash_search(mv_trigger_info, (void *) &entry->matview_id, HASH_REMOVE, NULL);
+		}
+	}
+
+	if (dropped_immv)
+	{
+		DroppedImmvInfo *entry;
+
+		LWLockAcquire(IvmControlLock, LW_EXCLUSIVE);
+		hash_seq_init(&seq, dropped_immv);
+		while ((entry = hash_seq_search(&seq)) != NULL)
+		{
+			hash_search(LastIvmUpdateHash, (void *) &entry->immv_oid, HASH_REMOVE, NULL);
+			hash_search(dropped_immv, (void *) &entry->immv_oid, HASH_REMOVE, NULL);
+		}
+		LWLockRelease(IvmControlLock);
+	}
+
+	in_delta_calculation = false;
+}
+
+/*
+ * clean_up_IVM_hash_entry
+ *
+ * Clean up tuple stores and hash entries for a materialized view after its
+ * maintenance finished. This is called at the end of table modifying query
+ * or (sub-)transaction abort. When the top-level transaction is aborted,
+ * InvalidSubTransactionId is set to subxid.
+ */
+static void
+clean_up_IVM_hash_entry(MV_TriggerHashEntry *entry, bool is_abort,
+						SubTransactionId subxid)
+{
+	bool found;
+	ListCell *lc;
+
+	/* clean up tuple stores */
+	foreach(lc, entry->tables)
+	{
+		MV_TriggerTable *table = (MV_TriggerTable *) lfirst(lc);
+
+		list_free(table->old_tuplestores);
+		list_free(table->new_tuplestores);
+		if (!is_abort)
+		{
+			ExecDropSingleTupleTableSlot(table->slot);
+			table_close(table->rel, NoLock);
+		}
+	}
+	list_free(entry->tables);
+	entry->tables = NIL;
+
+	if (is_abort)
+	{
+		bool	remove_entry = false;
+
+		/*
+		 * When the top-level transaction is aborted, remove all subxids.
+		 * When a sub-transaction is aborted, remove only its subxid.
+		 */
+		if (subxid == InvalidSubTransactionId)
+			remove_entry = true;
+		else
+		{
+			foreach(lc, entry->subxids)
+			{
+				if (lfirst_xid(lc) == subxid)
+				{
+					entry->subxids = list_delete_cell(entry->subxids, lc);
+					break;
+				}
+			}
+
+			/*
+			 * If all the subxid are removed, it means that the view was not
+			 * updated at all in this transaction.
+			 */
+			if (list_length(entry->subxids) == 0)
+				remove_entry = true;
+		}
+
+		/*
+		 * Remove entries of not updated views from the hash table.
+		 */
+		if (remove_entry)
+			hash_search(mv_trigger_info, (void *) &entry->matview_id, HASH_REMOVE, &found);
+	}
+	else
+	{
+		/* When the query sucsessully finished, unregister the snapshot */
+		UnregisterSnapshot(entry->snapshot);
+	}
+
+	entry->snapshot = InvalidSnapshot;
+}
+
+/*
+ * setLastUpdateXid
+ *
+ * Store the transaction ID that updated the view incremenally.
+ */
+static void
+setLastUpdateXid(Oid immv_oid, FullTransactionId xid)
+{
+	LastIvmUpdateEntry *entry;
+
+	LWLockAcquire(IvmControlLock, LW_EXCLUSIVE);
+	entry = (LastIvmUpdateEntry *) hash_search(LastIvmUpdateHash, (void *) &immv_oid, HASH_ENTER, NULL);
+	entry->oid = immv_oid;
+	entry->last_ivm_update = xid;
+	LWLockRelease(IvmControlLock);
+}
+
+/*
+ * getLastUpdateXid
+ *
+ * Get the most recent transaction ID that updated the view incrementally.
+ */
+static FullTransactionId
+getLastUpdateXid(Oid immv_oid)
+{
+	FullTransactionId xid = InvalidFullTransactionId;
+	LastIvmUpdateEntry *entry;
+	bool found;
+
+	LWLockAcquire(IvmControlLock, LW_SHARED);
+	entry = (LastIvmUpdateEntry *) hash_search(LastIvmUpdateHash, (void *) &immv_oid, HASH_FIND, &found);
+	LWLockRelease(IvmControlLock);
+	if (found)
+		xid = entry->last_ivm_update;
+
+	return xid;
+}
+
+void
+removeImmv(Oid immv_oid)
+{
+	DroppedImmvInfo *entry;
+
+	if (!dropped_immv)
+		mv_InitHashTables();
+
+	entry = (DroppedImmvInfo *) hash_search(dropped_immv, (void *) &immv_oid, HASH_ENTER, NULL);
+	entry->subxid = GetCurrentSubTransactionId();
+}
+
+/*
+ * isIvmName
+ *
+ * Check if this is a IVM hidden column from the name.
+ */
+bool
+isIvmName(const char *s)
+{
+	if (s)
+		return (strncmp(s, "__ivm_", 6) == 0);
+	return false;
+}
diff --git a/src/backend/commands/tablecmds.c b/src/backend/commands/tablecmds.c
index a1845240a98..99bc709959a 100644
--- a/src/backend/commands/tablecmds.c
+++ b/src/backend/commands/tablecmds.c
@@ -62,6 +62,7 @@
 #include "commands/defrem.h"
 #include "commands/event_trigger.h"
 #include "commands/extension.h"
+#include "commands/matview.h"
 #include "commands/repack.h"
 #include "commands/sequence.h"
 #include "commands/tablecmds.h"
@@ -1804,6 +1805,9 @@ RangeVarCallbackForDropRelation(const RangeVar *rel, Oid relOid, Oid oldRelOid,
 	state->actual_relkind = classform->relkind;
 	state->actual_relpersistence = classform->relpersistence;
 
+	if (classform->relkind == RELKIND_MATVIEW && classform->relisivm)
+		removeImmv(relOid);
+
 	/*
 	 * Both RELKIND_RELATION and RELKIND_PARTITIONED_TABLE are OBJECT_TABLE,
 	 * but RemoveRelations() can only pass one relkind for a given relation.
diff --git a/src/backend/utils/activity/wait_event_names.txt b/src/backend/utils/activity/wait_event_names.txt
index 560659f9568..d97c35eeef0 100644
--- a/src/backend/utils/activity/wait_event_names.txt
+++ b/src/backend/utils/activity/wait_event_names.txt
@@ -370,6 +370,7 @@ WaitLSN	"Waiting to read or update shared Wait-for-LSN state."
 LogicalDecodingControl	"Waiting to read or update logical decoding status information."
 DataChecksumsWorker	"Waiting for data checksums worker."
 AioWorkerControl	"Waiting to update AIO worker information."
+IvmControl	"Waiting for read or update IMMV information.."
 
 #
 # END OF PREDEFINED LWLOCKS (DO NOT CHANGE THIS LINE)
diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat
index be157a5fbe9..b8722eea7a4 100644
--- a/src/include/catalog/pg_proc.dat
+++ b/src/include/catalog/pg_proc.dat
@@ -12693,4 +12693,14 @@
   proname => 'hashoid8extended', prorettype => 'int8',
   proargtypes => 'oid8 int8', prosrc => 'hashoid8extended' },
 
+# IVM
+{ oid => '786', descr => 'ivm trigger (before)',
+  proname => 'IVM_immediate_before', provolatile => 'v', prorettype => 'trigger',
+  proargtypes => '', prosrc => 'IVM_immediate_before' },
+{ oid => '787', descr => 'ivm trigger (after)',
+  proname => 'IVM_immediate_maintenance', provolatile => 'v', prorettype => 'trigger',
+  proargtypes => '', prosrc => 'IVM_immediate_maintenance' },
+{ oid => '788', descr => 'ivm filetring ',
+  proname => 'ivm_visible_in_prestate', provolatile => 's', prorettype => 'bool',
+  proargtypes => 'oid tid oid', prosrc => 'ivm_visible_in_prestate' },
 ]
diff --git a/src/include/commands/createas.h b/src/include/commands/createas.h
index f895c67c0c2..c286ebcd70e 100644
--- a/src/include/commands/createas.h
+++ b/src/include/commands/createas.h
@@ -16,6 +16,7 @@
 
 #include "catalog/objectaddress.h"
 #include "nodes/params.h"
+#include "nodes/pathnodes.h"
 #include "parser/parse_node.h"
 #include "tcop/dest.h"
 #include "utils/queryenvironment.h"
@@ -25,6 +26,9 @@ extern ObjectAddress ExecCreateTableAs(ParseState *pstate, CreateTableAsStmt *st
 									   ParamListInfo params, QueryEnvironment *queryEnv,
 									   QueryCompletion *qc);
 
+extern void CreateIvmTriggersOnBaseTables(Query *qry, Oid matviewOid);
+extern void CreateIndexOnIMMV(Query *query, Relation matviewRel);
+
 extern int	GetIntoRelEFlags(IntoClause *intoClause);
 
 extern DestReceiver *CreateIntoRelDestReceiver(IntoClause *intoClause);
diff --git a/src/include/commands/matview.h b/src/include/commands/matview.h
index 738c731c1a9..f1dbfc052c5 100644
--- a/src/include/commands/matview.h
+++ b/src/include/commands/matview.h
@@ -15,6 +15,7 @@
 #define MATVIEW_H
 
 #include "catalog/objectaddress.h"
+#include "fmgr.h"
 #include "nodes/params.h"
 #include "nodes/parsenodes.h"
 #include "tcop/dest.h"
@@ -23,6 +24,8 @@
 
 extern void SetMatViewPopulatedState(Relation relation, bool newstate);
 
+extern void SetMatViewIVMState(Relation relation, bool newstate);
+
 extern ObjectAddress ExecRefreshMatView(RefreshMatViewStmt *stmt, const char *queryString,
 										QueryCompletion *qc);
 extern ObjectAddress RefreshMatViewByOid(Oid matviewOid, bool is_create, bool skipData,
@@ -33,4 +36,12 @@ extern DestReceiver *CreateTransientRelDestReceiver(Oid transientoid);
 
 extern bool MatViewIncrementalMaintenanceIsEnabled(void);
 
+extern Datum IVM_immediate_before(PG_FUNCTION_ARGS);
+extern Datum IVM_immediate_maintenance(PG_FUNCTION_ARGS);
+extern Datum IVM_visible_in_prestate(PG_FUNCTION_ARGS);
+extern void AtAbort_IVM(SubTransactionId subtxid);
+extern void AtPreCommit_IVM(void);
+extern void removeImmv(Oid immv_oid);
+extern bool isIvmName(const char *s);
+
 #endif							/* MATVIEW_H */
diff --git a/src/include/storage/lwlocklist.h b/src/include/storage/lwlocklist.h
index d7eb648bd27..756c63baf97 100644
--- a/src/include/storage/lwlocklist.h
+++ b/src/include/storage/lwlocklist.h
@@ -89,6 +89,7 @@ PG_LWLOCK(54, WaitLSN)
 PG_LWLOCK(55, LogicalDecodingControl)
 PG_LWLOCK(56, DataChecksumsWorker)
 PG_LWLOCK(57, AioWorkerControl)
+PG_LWLOCK(58, IvmControl)
 
 /*
  * There also exist several built-in LWLock tranches.  As with the predefined
diff --git a/src/include/storage/subsystemlist.h b/src/include/storage/subsystemlist.h
index 9ad619080be..481e15d00a1 100644
--- a/src/include/storage/subsystemlist.h
+++ b/src/include/storage/subsystemlist.h
@@ -88,3 +88,6 @@ PG_SHMEM_SUBSYSTEM(DataChecksumsShmemCallbacks)
 
 /* AIO subsystem. This delegates to the method-specific callbacks */
 PG_SHMEM_SUBSYSTEM(AioShmemCallbacks)
+
+/* Incremental View Maintenance */
+PG_SHMEM_SUBSYSTEM(IvmShmemCallbacks)
-- 
2.43.0


--Multipart=_Fri__29_May_2026_23_14_17_+0900_Te0o73X2VqYK57Gd
Content-Type: text/x-diff;
 name="v37-0005-Add-Incremental-View-Maintenance-support-to-psql.patch"
Content-Disposition: attachment;
 filename="v37-0005-Add-Incremental-View-Maintenance-support-to-psql.patch"
Content-Transfer-Encoding: 7bit



^ permalink  raw  reply  [nested|flat] 101+ messages in thread

* [PATCH v37 06/11] Add Incremental View Maintenance support
@ 2026-05-29 09:06  Yugo Nagata <[email protected]>
  0 siblings, 0 replies; 101+ messages in thread

From: Yugo Nagata @ 2026-05-29 09:06 UTC (permalink / raw)

In this implementation, AFTER triggers are used to collect
tuplestores containing transition table contents. When multiple tables
are changed, multiple AFTER triggers are invoked, then the final AFTER
trigger performs actual update of the matview. In addition, BEFORE
triggers are also used to handle global information for view
maintenance.

To calculate view deltas, we need both pre-state and post-state of base
tables. Post-update states are available in AFTER trigger, and pre-update
states can be calculated by removing inserted tuples and appending deleted
tuples. Insterted tuples are filtered using the snapshot taken before
table modification, and deleted tuples are contained in the old transition
table.

Incrementally Maintainable Materialized Views (IMMV) can contain
duplicated tuples.

This patch also allows self-join, simultaneous updates of more than
one base table, and multiple updates of the same base table.
---
 src/backend/access/transam/xact.c             |    8 +
 src/backend/commands/createas.c               |  709 +++++++
 src/backend/commands/matview.c                | 1835 ++++++++++++++++-
 src/backend/commands/tablecmds.c              |    4 +
 .../utils/activity/wait_event_names.txt       |    1 +
 src/include/catalog/pg_proc.dat               |   10 +
 src/include/commands/createas.h               |    4 +
 src/include/commands/matview.h                |   11 +
 src/include/storage/lwlocklist.h              |    1 +
 src/include/storage/subsystemlist.h           |    3 +
 10 files changed, 2548 insertions(+), 38 deletions(-)

diff --git a/src/backend/access/transam/xact.c b/src/backend/access/transam/xact.c
index 5586fbe5b07..302a4822d50 100644
--- a/src/backend/access/transam/xact.c
+++ b/src/backend/access/transam/xact.c
@@ -37,6 +37,7 @@
 #include "catalog/pg_enum.h"
 #include "catalog/storage.h"
 #include "commands/async.h"
+#include "commands/matview.h"
 #include "commands/tablecmds.h"
 #include "commands/trigger.h"
 #include "common/pg_prng.h"
@@ -2322,6 +2323,9 @@ CommitTransaction(void)
 	CallXactCallbacks(is_parallel_worker ? XACT_EVENT_PARALLEL_PRE_COMMIT
 					  : XACT_EVENT_PRE_COMMIT);
 
+	/* Store the transaction ID that updated the view incrementally */
+	AtPreCommit_IVM();
+
 	/*
 	 * If this xact has started any unfinished parallel operation, clean up
 	 * its workers, warning about leaked resources.  (But we don't actually
@@ -2971,6 +2975,7 @@ AbortTransaction(void)
 	AtAbort_Notify();
 	AtEOXact_RelationMap(false, is_parallel_worker);
 	AtAbort_Twophase();
+	AtAbort_IVM(InvalidSubTransactionId);
 
 	/*
 	 * Advertise the fact that we aborted in pg_xact (assuming that we got as
@@ -5301,6 +5306,9 @@ AbortSubTransaction(void)
 
 	UnlockBuffers();
 
+	/* Clean up hash entries for incremental view maintenance */
+	AtAbort_IVM(s->subTransactionId);
+
 	/* Reset WAL record construction state */
 	XLogResetInsertion();
 
diff --git a/src/backend/commands/createas.c b/src/backend/commands/createas.c
index 6dbb831ca89..a499688b79d 100644
--- a/src/backend/commands/createas.c
+++ b/src/backend/commands/createas.c
@@ -29,18 +29,32 @@
 #include "access/tableam.h"
 #include "access/xact.h"
 #include "catalog/namespace.h"
+#include "catalog/index.h"
+#include "catalog/pg_am_d.h"
+#include "catalog/pg_constraint.h"
+#include "catalog/pg_inherits.h"
+#include "catalog/pg_trigger.h"
 #include "catalog/toasting.h"
 #include "commands/createas.h"
+#include "commands/defrem.h"
 #include "commands/matview.h"
 #include "commands/prepare.h"
 #include "commands/tablecmds.h"
+#include "commands/tablespace.h"
+#include "commands/trigger.h"
 #include "commands/view.h"
 #include "executor/execdesc.h"
 #include "executor/executor.h"
+#include "miscadmin.h"
 #include "nodes/makefuncs.h"
 #include "nodes/nodeFuncs.h"
 #include "nodes/queryjumble.h"
+#include "optimizer/optimizer.h"
+#include "optimizer/prep.h"
 #include "parser/analyze.h"
+#include "parser/parser.h"
+#include "parser/parsetree.h"
+#include "parser/parse_clause.h"
 #include "rewrite/rewriteHandler.h"
 #include "tcop/tcopprot.h"
 #include "utils/builtins.h"
@@ -70,6 +84,12 @@ static bool intorel_receive(TupleTableSlot *slot, DestReceiver *self);
 static void intorel_shutdown(DestReceiver *self);
 static void intorel_destroy(DestReceiver *self);
 
+static void CreateIvmTriggersOnBaseTablesRecurse(Query *qry, Node *node, Oid matviewOid,
+									 List **relids, bool ex_lock);
+static void CreateIvmTrigger(Oid relOid, Oid viewOid, int16 type, int16 timing, bool ex_lock);
+static void check_ivm_restriction(Node *node);
+static bool check_ivm_restriction_walker(Node *node, void *context);
+static Bitmapset *get_primary_key_attnos_from_query(Query *query, List **constraintList);
 
 /*
  * create_ctas_internal
@@ -277,6 +297,18 @@ ExecCreateTableAs(ParseState *pstate, CreateTableAsStmt *stmt,
 		into->skipData = true;
 	}
 
+	if (is_matview && into->ivm)
+	{
+		/* check if the query is supported in IMMV definition */
+		if (contain_mutable_functions((Node *) query))
+			ereport(ERROR,
+					(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+					 errmsg("mutable function is not supported on incrementally maintainable materialized view"),
+					 errhint("functions must be marked IMMUTABLE")));
+
+		check_ivm_restriction((Node *) query);
+	}
+
 	if (into->skipData)
 	{
 		/*
@@ -287,15 +319,36 @@ ExecCreateTableAs(ParseState *pstate, CreateTableAsStmt *stmt,
 		 */
 		address = create_ctas_nodata(query->targetList, into);
 
+		/*
+		 * For IVM, mark the matview before refresh so RelationIsIVM()
+		 * returns true inside RefreshMatViewByOid.
+		 */
+		if (is_matview && into->ivm)
+		{
+			Relation matviewRel = table_open(address.objectId, NoLock);
+
+			SetMatViewIVMState(matviewRel, true);
+			table_close(matviewRel, NoLock);
+			CommandCounterIncrement();
+		}
+
 		/*
 		 * For materialized views, reuse the REFRESH logic, which locks down
 		 * security-restricted operations and restricts the search_path.  This
 		 * reduces the chance that a subsequent refresh will fail.
 		 */
 		if (do_refresh)
+		{
 			RefreshMatViewByOid(address.objectId, true, false, false,
 								pstate->p_sourcetext, qc);
 
+			if (is_matview && into->ivm && IsolationUsesXactSnapshot())
+				ereport(WARNING,
+						(errmsg("inconsistent view can be created in isolation level SERIALIZABLE or REPEATABLE READ"),
+						 errdetail("The view may not include effects of a concurrent transaction."),
+						 errhint("The view with incremental maintenance should be created in isolation level READ COMMITTED, "
+								 "or refreshed manually to make sure the view is consistent.")));
+		}
 	}
 	else
 	{
@@ -635,3 +688,659 @@ intorel_destroy(DestReceiver *self)
 {
 	pfree(self);
 }
+
+/*
+ * CreateIvmTriggersOnBaseTables -- create IVM triggers on all base tables
+ */
+void
+CreateIvmTriggersOnBaseTables(Query *qry, Oid matviewOid)
+{
+	List   *relids = NIL;
+	bool	ex_lock = false;
+	RangeTblEntry *rte;
+
+	/* Immediately return if we don't have any base tables. */
+	if (list_length(qry->rtable) < 1)
+		return;
+
+	/*
+	 * If the view has more than one base tables, we need an exclusive lock
+	 * on the view so that the view would be maintained serially to avoid
+	 * the inconsistency that occurs when two base tables are modified in
+	 * concurrent transactions. However, if the view has only one table,
+	 * we can use a weaker lock.
+	 *
+	 * The type of lock should be determined here, because if we check the
+	 * view definition at maintenance time, we need to acquire a weaker lock,
+	 * and upgrading the lock level after this increases probability of
+	 * deadlock.
+	 */
+
+	rte = list_nth(qry->rtable, 0);
+	if (list_length(qry->rtable) > 1 || rte->rtekind != RTE_RELATION)
+		ex_lock = true;
+
+	CreateIvmTriggersOnBaseTablesRecurse(qry, (Node *)qry, matviewOid, &relids, ex_lock);
+
+	list_free(relids);
+}
+
+static void
+CreateIvmTriggersOnBaseTablesRecurse(Query *qry, Node *node, Oid matviewOid,
+									 List **relids, bool ex_lock)
+{
+	if (node == NULL)
+		return;
+
+	/* This can recurse, so check for excessive recursion */
+	check_stack_depth();
+
+	switch (nodeTag(node))
+	{
+		case T_Query:
+			{
+				Query *query = (Query *) node;
+
+				CreateIvmTriggersOnBaseTablesRecurse(qry, (Node *)query->jointree, matviewOid, relids, ex_lock);
+			}
+			break;
+
+		case T_RangeTblRef:
+			{
+				int			rti = ((RangeTblRef *) node)->rtindex;
+				RangeTblEntry *rte = rt_fetch(rti, qry->rtable);
+
+				if (rte->rtekind == RTE_RELATION && !list_member_oid(*relids, rte->relid))
+				{
+					CreateIvmTrigger(rte->relid, matviewOid, TRIGGER_TYPE_INSERT, TRIGGER_TYPE_BEFORE, ex_lock);
+					CreateIvmTrigger(rte->relid, matviewOid, TRIGGER_TYPE_DELETE, TRIGGER_TYPE_BEFORE, ex_lock);
+					CreateIvmTrigger(rte->relid, matviewOid, TRIGGER_TYPE_UPDATE, TRIGGER_TYPE_BEFORE, ex_lock);
+					CreateIvmTrigger(rte->relid, matviewOid, TRIGGER_TYPE_TRUNCATE, TRIGGER_TYPE_BEFORE, true);
+					CreateIvmTrigger(rte->relid, matviewOid, TRIGGER_TYPE_INSERT, TRIGGER_TYPE_AFTER, ex_lock);
+					CreateIvmTrigger(rte->relid, matviewOid, TRIGGER_TYPE_DELETE, TRIGGER_TYPE_AFTER, ex_lock);
+					CreateIvmTrigger(rte->relid, matviewOid, TRIGGER_TYPE_UPDATE, TRIGGER_TYPE_AFTER, ex_lock);
+					CreateIvmTrigger(rte->relid, matviewOid, TRIGGER_TYPE_TRUNCATE, TRIGGER_TYPE_AFTER, true);
+
+					*relids = lappend_oid(*relids, rte->relid);
+				}
+			}
+			break;
+
+		case T_FromExpr:
+			{
+				FromExpr   *f = (FromExpr *) node;
+				ListCell   *l;
+
+				foreach(l, f->fromlist)
+					CreateIvmTriggersOnBaseTablesRecurse(qry, lfirst(l), matviewOid, relids, ex_lock);
+			}
+			break;
+
+		case T_JoinExpr:
+			{
+				JoinExpr   *j = (JoinExpr *) node;
+
+				CreateIvmTriggersOnBaseTablesRecurse(qry, j->larg, matviewOid, relids, ex_lock);
+				CreateIvmTriggersOnBaseTablesRecurse(qry, j->rarg, matviewOid, relids, ex_lock);
+			}
+			break;
+
+		default:
+			elog(ERROR, "unrecognized node type: %d", (int) nodeTag(node));
+	}
+}
+
+/*
+ * CreateIvmTrigger -- create IVM trigger on a base table
+ */
+static void
+CreateIvmTrigger(Oid relOid, Oid viewOid, int16 type, int16 timing, bool ex_lock)
+{
+	ObjectAddress	refaddr;
+	ObjectAddress	address;
+	CreateTrigStmt *ivm_trigger;
+	List *transitionRels = NIL;
+
+	Assert(timing == TRIGGER_TYPE_BEFORE || timing == TRIGGER_TYPE_AFTER);
+
+	refaddr.classId = RelationRelationId;
+	refaddr.objectId = viewOid;
+	refaddr.objectSubId = 0;
+
+	ivm_trigger = makeNode(CreateTrigStmt);
+	ivm_trigger->relation = NULL;
+	ivm_trigger->row = false;
+
+	ivm_trigger->timing = timing;
+	ivm_trigger->events = type;
+
+	switch (type)
+	{
+		case TRIGGER_TYPE_INSERT:
+			ivm_trigger->trigname = (timing == TRIGGER_TYPE_BEFORE ? "IVM_trigger_ins_before" : "IVM_trigger_ins_after");
+			break;
+		case TRIGGER_TYPE_DELETE:
+			ivm_trigger->trigname = (timing == TRIGGER_TYPE_BEFORE ? "IVM_trigger_del_before" : "IVM_trigger_del_after");
+			break;
+		case TRIGGER_TYPE_UPDATE:
+			ivm_trigger->trigname = (timing == TRIGGER_TYPE_BEFORE ? "IVM_trigger_upd_before" : "IVM_trigger_upd_after");
+			break;
+		case TRIGGER_TYPE_TRUNCATE:
+			ivm_trigger->trigname = (timing == TRIGGER_TYPE_BEFORE ? "IVM_trigger_truncate_before" : "IVM_trigger_truncate_after");
+			break;
+		default:
+			elog(ERROR, "unsupported trigger type");
+	}
+
+	if (timing == TRIGGER_TYPE_AFTER)
+	{
+		if (type == TRIGGER_TYPE_INSERT || type == TRIGGER_TYPE_UPDATE)
+		{
+			TriggerTransition *n = makeNode(TriggerTransition);
+			n->name = "__ivm_newtable";
+			n->isNew = true;
+			n->isTable = true;
+
+			transitionRels = lappend(transitionRels, n);
+		}
+		if (type == TRIGGER_TYPE_DELETE || type == TRIGGER_TYPE_UPDATE)
+		{
+			TriggerTransition *n = makeNode(TriggerTransition);
+			n->name = "__ivm_oldtable";
+			n->isNew = false;
+			n->isTable = true;
+
+			transitionRels = lappend(transitionRels, n);
+		}
+	}
+
+	/*
+	 * XXX: When using DELETE or UPDATE, we must use exclusive lock for now
+	 * because apply_old_delta(_with_count) uses ctid to identify the tuple
+	 * to be deleted/deleted, but doesn't work in concurrent situations.
+	 *
+	 * If the view doesn't have aggregate, distinct, or tuple duplicate,
+	 * then it would work even in concurrent situations. However, we don't have
+	 * any way to guarantee the view has a unique key before opening the IMMV
+	 * at the maintenance time because users may drop the unique index.
+	 */
+
+	if (type == TRIGGER_TYPE_DELETE || type == TRIGGER_TYPE_UPDATE)
+		ex_lock = true;
+
+	ivm_trigger->funcname =
+		(timing == TRIGGER_TYPE_BEFORE ? SystemFuncName("IVM_immediate_before") : SystemFuncName("IVM_immediate_maintenance"));
+
+	ivm_trigger->columns = NIL;
+	ivm_trigger->transitionRels = transitionRels;
+	ivm_trigger->whenClause = NULL;
+	ivm_trigger->isconstraint = false;
+	ivm_trigger->deferrable = false;
+	ivm_trigger->initdeferred = false;
+	ivm_trigger->constrrel = NULL;
+	ivm_trigger->args = list_make2(
+		makeString(DatumGetPointer(DirectFunctionCall1(oidout, ObjectIdGetDatum(viewOid)))),
+		makeString(DatumGetPointer(DirectFunctionCall1(boolout, BoolGetDatum(ex_lock))))
+		);
+
+	address = CreateTrigger(ivm_trigger, NULL, relOid, InvalidOid, InvalidOid,
+						 InvalidOid, InvalidOid, InvalidOid, NULL, true, false);
+
+	recordDependencyOn(&address, &refaddr, DEPENDENCY_AUTO);
+
+	/* Make changes-so-far visible */
+	CommandCounterIncrement();
+}
+
+/*
+ * check_ivm_restriction --- look for specify nodes in the query tree
+ */
+static void
+check_ivm_restriction(Node *node)
+{
+	check_ivm_restriction_walker(node, NULL);
+}
+
+static bool
+check_ivm_restriction_walker(Node *node, void *context)
+{
+	if (node == NULL)
+		return false;
+
+	/*
+	 * We currently don't support Sub-Query.
+	 */
+	if (IsA(node, SubPlan) || IsA(node, SubLink))
+		ereport(ERROR,
+				(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+				 errmsg("subquery is not supported on incrementally maintainable materialized view")));
+
+	/* This can recurse, so check for excessive recursion */
+	check_stack_depth();
+
+	switch (nodeTag(node))
+	{
+		case T_Query:
+			{
+				Query *qry = (Query *)node;
+				ListCell   *lc;
+				List       *vars;
+
+				/* if contained CTE, return error */
+				if (qry->cteList != NIL)
+					ereport(ERROR,
+							(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+							 errmsg("CTE is not supported on incrementally maintainable materialized view")));
+				if (qry->havingQual != NULL)
+					ereport(ERROR,
+							(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+							 errmsg(" HAVING clause is not supported on incrementally maintainable materialized view")));
+				if (qry->sortClause != NIL)	/* There is a possibility that we don't need to return an error */
+					ereport(ERROR,
+							(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+							 errmsg("ORDER BY clause is not supported on incrementally maintainable materialized view")));
+				if (qry->limitOffset != NULL || qry->limitCount != NULL)
+					ereport(ERROR,
+							(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+							 errmsg("LIMIT/OFFSET clause is not supported on incrementally maintainable materialized view")));
+				if (qry->distinctClause)
+					ereport(ERROR,
+							(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+							 errmsg("DISTINCT is not supported on incrementally maintainable materialized view")));
+				if (qry->hasDistinctOn)
+					ereport(ERROR,
+							(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+							 errmsg("DISTINCT ON is not supported on incrementally maintainable materialized view")));
+				if (qry->hasWindowFuncs)
+					ereport(ERROR,
+							(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+							 errmsg("window functions are not supported on incrementally maintainable materialized view")));
+				if (qry->groupingSets != NIL)
+					ereport(ERROR,
+							(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+							 errmsg("GROUPING SETS, ROLLUP, or CUBE clauses is not supported on incrementally maintainable materialized view")));
+				if (qry->setOperations != NULL)
+					ereport(ERROR,
+							(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+							 errmsg("UNION/INTERSECT/EXCEPT statements are not supported on incrementally maintainable materialized view")));
+				if (list_length(qry->targetList) == 0)
+					ereport(ERROR,
+							(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+							 errmsg("empty target list is not supported on incrementally maintainable materialized view")));
+				if (qry->rowMarks != NIL)
+					ereport(ERROR,
+							(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+							 errmsg("FOR UPDATE/SHARE clause is not supported on incrementally maintainable materialized view")));
+
+				/* system column restrictions */
+				vars = pull_vars_of_level((Node *) qry, 0);
+				foreach(lc, vars)
+				{
+					if (IsA(lfirst(lc), Var))
+					{
+						Var *var = (Var *) lfirst(lc);
+						/* if system column, return error */
+						if (var->varattno < 0)
+							ereport(ERROR,
+									(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+									 errmsg("system column is not supported on incrementally maintainable materialized view")));
+					}
+				}
+
+				/* check if type in the target list had an equality operator */
+				foreach(lc, qry->targetList)
+				{
+					TargetEntry *tle = (TargetEntry *) lfirst(lc);
+					Oid             atttype = exprType((Node *) tle->expr);
+					Oid             opclass;
+
+					opclass = GetDefaultOpClass(atttype, BTREE_AM_OID);
+					if (!OidIsValid(opclass))
+						ereport(ERROR,
+								(errcode(ERRCODE_UNDEFINED_OBJECT),
+								 errmsg("data type %s has no default operator class for access method \"%s\"",
+									format_type_be(atttype), "btree")));
+				}
+
+				/* restrictions for rtable */
+				foreach(lc, qry->rtable)
+				{
+					RangeTblEntry *rte = (RangeTblEntry *) lfirst(lc);
+
+					if (rte->subquery)
+						ereport(ERROR,
+								(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+								 errmsg("subquery is not supported on incrementally maintainable materialized view")));
+
+					if (rte->tablesample != NULL)
+						ereport(ERROR,
+								(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+								 errmsg("TABLESAMPLE clause is not supported on incrementally maintainable materialized view")));
+
+					if (rte->relkind == RELKIND_PARTITIONED_TABLE)
+						ereport(ERROR,
+								(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+								 errmsg("partitioned table is not supported on incrementally maintainable materialized view")));
+
+					if (rte->relkind == RELKIND_RELATION && has_superclass(rte->relid))
+						ereport(ERROR,
+								(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+								 errmsg("partitions is not supported on incrementally maintainable materialized view")));
+
+					if (rte->relkind == RELKIND_RELATION && find_inheritance_children(rte->relid, NoLock) != NIL)
+						ereport(ERROR,
+								(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+								 errmsg("inheritance parent is not supported on incrementally maintainable materialized view")));
+
+					if (rte->relkind == RELKIND_FOREIGN_TABLE)
+						ereport(ERROR,
+								(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+								 errmsg("foreign table is not supported on incrementally maintainable materialized view")));
+
+					if (rte->relkind == RELKIND_VIEW ||
+						rte->relkind == RELKIND_MATVIEW)
+						ereport(ERROR,
+								(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+								 errmsg("VIEW or MATERIALIZED VIEW is not supported on incrementally maintainable materialized view")));
+
+					if (rte->rtekind == RTE_VALUES)
+						ereport(ERROR,
+								(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+								 errmsg("VALUES is not supported on incrementally maintainable materialized view")));
+
+				}
+
+				query_tree_walker(qry, check_ivm_restriction_walker, NULL, QTW_IGNORE_RANGE_TABLE);
+
+				break;
+			}
+		case T_TargetEntry:
+			{
+				TargetEntry *tle = (TargetEntry *)node;
+				if (isIvmName(tle->resname))
+						ereport(ERROR,
+								(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+								 errmsg("column name %s is not supported on incrementally maintainable materialized view", tle->resname)));
+
+				expression_tree_walker(node, check_ivm_restriction_walker, NULL);
+				break;
+			}
+		case T_JoinExpr:
+			{
+				JoinExpr *joinexpr = (JoinExpr *)node;
+
+				if (joinexpr->jointype > JOIN_INNER)
+						ereport(ERROR,
+								(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+								 errmsg("OUTER JOIN is not supported on incrementally maintainable materialized view")));
+
+				expression_tree_walker(node, check_ivm_restriction_walker, NULL);
+			}
+			break;
+		case T_Aggref:
+			ereport(ERROR,
+					(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+					 errmsg("aggregate function is not supported on incrementally maintainable materialized view")));
+			break;
+		default:
+			expression_tree_walker(node, check_ivm_restriction_walker, (void *) context);
+			break;
+	}
+	return false;
+}
+
+/*
+ * CreateIndexOnIMMV
+ *
+ * Create a unique index on incremental maintainable materialized view.
+ * If the view definition query has a GROUP BY clause, the index is created
+ * on the columns of GROUP BY expressions. Otherwise, if the view contains
+ * all primary key attributes of its base tables in the target list, the index
+ * is created on these attributes. In other cases, no index is created.
+ */
+void
+CreateIndexOnIMMV(Query *query, Relation matviewRel)
+{
+	ListCell *lc;
+	IndexStmt  *index;
+	ObjectAddress address;
+	List *constraintList = NIL;
+	char		idxname[NAMEDATALEN];
+	List	   *indexoidlist = RelationGetIndexList(matviewRel);
+	ListCell   *indexoidscan;
+	Bitmapset *key_attnos;
+
+	snprintf(idxname, sizeof(idxname), "%s_index", RelationGetRelationName(matviewRel));
+
+	index = makeNode(IndexStmt);
+
+	index->unique = true;
+	index->primary = false;
+	index->isconstraint = false;
+	index->deferrable = false;
+	index->initdeferred = false;
+	index->idxname = idxname;
+	index->relation =
+		makeRangeVar(get_namespace_name(RelationGetNamespace(matviewRel)),
+					 pstrdup(RelationGetRelationName(matviewRel)),
+					 -1);
+	index->accessMethod = DEFAULT_INDEX_TYPE;
+	index->options = NIL;
+	index->tableSpace = get_tablespace_name(matviewRel->rd_rel->reltablespace);
+	index->whereClause = NULL;
+	index->indexParams = NIL;
+	index->indexIncludingParams = NIL;
+	index->excludeOpNames = NIL;
+	index->idxcomment = NULL;
+	index->indexOid = InvalidOid;
+	index->oldNumber = InvalidRelFileNumber;
+	index->oldCreateSubid = InvalidSubTransactionId;
+	index->oldFirstRelfilelocatorSubid = InvalidSubTransactionId;
+	index->transformed = true;
+	index->concurrent = false;
+	index->if_not_exists = false;
+
+	/* create index on the base tables' primary key columns */
+	key_attnos = get_primary_key_attnos_from_query(query, &constraintList);
+	if (key_attnos)
+	{
+		foreach(lc, query->targetList)
+		{
+			TargetEntry *tle = (TargetEntry *) lfirst(lc);
+			Form_pg_attribute attr = TupleDescAttr(matviewRel->rd_att, tle->resno - 1);
+
+			if (bms_is_member(tle->resno - FirstLowInvalidHeapAttributeNumber, key_attnos))
+			{
+				IndexElem  *iparam;
+
+				iparam = makeNode(IndexElem);
+				iparam->name = pstrdup(NameStr(attr->attname));
+				iparam->expr = NULL;
+				iparam->indexcolname = NULL;
+				iparam->collation = NIL;
+				iparam->opclass = NIL;
+				iparam->opclassopts = NIL;
+				iparam->ordering = SORTBY_DEFAULT;
+				iparam->nulls_ordering = SORTBY_NULLS_DEFAULT;
+				index->indexParams = lappend(index->indexParams, iparam);
+			}
+		}
+	}
+	else
+	{
+		/* create no index, just notice that an appropriate index is necessary for efficient IVM */
+		ereport(NOTICE,
+				(errmsg("could not create an index on materialized view \"%s\" automatically",
+						RelationGetRelationName(matviewRel)),
+				 errdetail("This target list does not have all the primary key columns. "),
+				 errhint("Create an index on the materialized view for efficient incremental maintenance.")));
+		return;
+	}
+
+	/* If we have a compatible index, we don't need to create another. */
+	foreach(indexoidscan, indexoidlist)
+	{
+		Oid			indexoid = lfirst_oid(indexoidscan);
+		Relation	indexRel;
+		bool		hasCompatibleIndex = false;
+
+		indexRel = index_open(indexoid, AccessShareLock);
+
+		if (CheckIndexCompatible(indexRel->rd_id,
+								index->accessMethod,
+								index->indexParams,
+								index->excludeOpNames,
+								false))
+			hasCompatibleIndex = true;
+
+		index_close(indexRel, AccessShareLock);
+
+		if (hasCompatibleIndex)
+			return;
+	}
+
+	address = DefineIndex(NULL,
+						  RelationGetRelid(matviewRel),
+						  index,
+						  InvalidOid,
+						  InvalidOid,
+						  InvalidOid,
+						  -1,
+						  false, true, false, false, true);
+
+	ereport(NOTICE,
+			(errmsg("created index \"%s\" on materialized view \"%s\"",
+					idxname, RelationGetRelationName(matviewRel))));
+
+	/*
+	 * Make dependencies so that the index is dropped if any base tables'
+	 * primary key is dropped.
+	 */
+	foreach(lc, constraintList)
+	{
+		Oid constraintOid = lfirst_oid(lc);
+		ObjectAddress	refaddr;
+
+		refaddr.classId = ConstraintRelationId;
+		refaddr.objectId = constraintOid;
+		refaddr.objectSubId = 0;
+
+		recordDependencyOn(&address, &refaddr, DEPENDENCY_NORMAL);
+	}
+}
+
+
+/*
+ * get_primary_key_attnos_from_query
+ *
+ * Identify the columns in base tables' primary keys in the target list.
+ *
+ * Returns a Bitmapset of the column attnos of the primary key's columns of
+ * tables that used in the query.  The attnos are offset by
+ * FirstLowInvalidHeapAttributeNumber as same as get_primary_key_attnos.
+ *
+ * If any table has no primary key or any primary key's columns is not in
+ * the target list, return NULL.  We also return NULL if any pkey constraint
+ * is deferrable.
+ *
+ * constraintList is set to a list of the OIDs of the pkey constraints.
+ */
+static Bitmapset *
+get_primary_key_attnos_from_query(Query *query, List **constraintList)
+{
+	List *key_attnos_list = NIL;
+	ListCell *lc;
+	int i;
+	Bitmapset *keys = NULL;
+	Relids	rels_in_from;
+
+	/*
+	 * Collect primary key attributes from all tables used in query. The key attributes
+	 * sets for each table are stored in key_attnos_list in order by RTE index.
+	 */
+	foreach(lc, query->rtable)
+	{
+		RangeTblEntry *r = (RangeTblEntry*) lfirst(lc);
+		Bitmapset *key_attnos;
+		bool	has_no_pkey = false;
+
+		/* for tables, call get_primary_key_attnos */
+		if (r->rtekind == RTE_RELATION)
+		{
+			Oid constraintOid;
+			key_attnos = get_primary_key_attnos(r->relid, false, &constraintOid);
+			*constraintList = lappend_oid(*constraintList, constraintOid);
+			has_no_pkey = (key_attnos == NULL);
+		}
+		/*
+		 * Ignore join rels, because they are flatten later by
+		 * flatten_join_alias_vars(). Store NULL into key_attnos_list
+		 * as a dummy.
+		 */
+		 else if (r->rtekind == RTE_JOIN)
+		 {
+			key_attnos = NULL;
+		}
+		/* for other RTEs, store NULL into key_attnos_list */
+		else
+			has_no_pkey = true;
+
+		/*
+		 * If any table or subquery has no primary key or its pkey constraint is deferrable,
+		 * we cannot get key attributes for this query, so return NULL.
+		 */
+		if (has_no_pkey)
+			return NULL;
+
+		key_attnos_list = lappend(key_attnos_list, key_attnos);
+	}
+
+	/* Collect key attributes appearing in the target list */
+	i = 1;
+	foreach(lc, query->targetList)
+	{
+		TargetEntry *tle = (TargetEntry *) flatten_join_alias_vars(NULL, query, lfirst(lc));
+
+		if (IsA(tle->expr, Var))
+		{
+			Var *var = (Var*) tle->expr;
+			Bitmapset *key_attnos = list_nth(key_attnos_list, var->varno - 1);
+
+			/* check if this attribute is from a base table's primary key */
+			if (bms_is_member(var->varattno - FirstLowInvalidHeapAttributeNumber, key_attnos))
+			{
+				/*
+				 * Remove found key attributes from key_attnos_list, and add this
+				 * to the result list.
+				 */
+				key_attnos = bms_del_member(key_attnos, var->varattno - FirstLowInvalidHeapAttributeNumber);
+				if (bms_is_empty(key_attnos))
+				{
+					key_attnos_list = list_delete_nth_cell(key_attnos_list, var->varno - 1);
+					key_attnos_list = list_insert_nth(key_attnos_list, var->varno - 1, NULL);
+				}
+				keys = bms_add_member(keys, i - FirstLowInvalidHeapAttributeNumber);
+			}
+		}
+		i++;
+	}
+
+	/* Collect RTE indexes of relations appearing in the FROM clause */
+	rels_in_from = get_relids_in_jointree((Node *) query->jointree, false, false);
+
+	/*
+	 * Check if all key attributes of relations in FROM are appearing in the target
+	 * list.  If an attribute remains in key_attnos_list in spite of the table is used
+	 * in FROM clause, the target is missing this key attribute, so we return NULL.
+	 */
+	i = 1;
+	foreach(lc, key_attnos_list)
+	{
+		Bitmapset *bms = (Bitmapset *)lfirst(lc);
+		if (!bms_is_empty(bms) && bms_is_member(i, rels_in_from))
+			return NULL;
+		i++;
+	}
+
+	return keys;
+}
diff --git a/src/backend/commands/matview.c b/src/backend/commands/matview.c
index f7d8007f796..eaf39f80cd3 100644
--- a/src/backend/commands/matview.c
+++ b/src/backend/commands/matview.c
@@ -23,24 +23,36 @@
 #include "catalog/indexing.h"
 #include "catalog/namespace.h"
 #include "catalog/pg_am.h"
+#include "catalog/pg_depend.h"
+#include "catalog/pg_trigger.h"
 #include "catalog/pg_opclass.h"
 #include "commands/matview.h"
 #include "commands/repack.h"
 #include "commands/tablecmds.h"
 #include "commands/tablespace.h"
+#include "commands/createas.h"
 #include "executor/executor.h"
 #include "executor/spi.h"
+#include "executor/tstoreReceiver.h"
 #include "miscadmin.h"
+#include "nodes/makefuncs.h"
+#include "parser/analyze.h"
+#include "parser/parse_clause.h"
+#include "parser/parse_func.h"
+#include "parser/parse_relation.h"
 #include "pgstat.h"
 #include "rewrite/rewriteHandler.h"
+#include "rewrite/rowsecurity.h"
 #include "storage/lmgr.h"
+#include "storage/lwlock.h"
 #include "tcop/tcopprot.h"
 #include "utils/builtins.h"
+#include "utils/fmgroids.h"
 #include "utils/lsyscache.h"
 #include "utils/rel.h"
 #include "utils/snapmgr.h"
 #include "utils/syscache.h"
-
+#include "utils/typcache.h"
 
 typedef struct
 {
@@ -53,6 +65,97 @@ typedef struct
 	BulkInsertState bistate;	/* bulk insert state */
 } DR_transientrel;
 
+#define MV_INIT_QUERYHASHSIZE	16
+
+/*
+ * MV_TriggerHashEntry
+ *
+ * Hash entry for base tables on which IVM trigger is invoked
+ */
+typedef struct MV_TriggerHashEntry
+{
+	Oid	matview_id;			/* OID of the materialized view */
+	int	before_trig_count;	/* count of before triggers invoked */
+	int	after_trig_count;	/* count of after triggers invoked */
+
+	Snapshot	snapshot;	/* Snapshot just before table change */
+
+	List   *tables;		/* List of MV_TriggerTable */
+	bool	has_old;	/* tuples are deleted from any table? */
+	bool	has_new;	/* tuples are inserted into any table? */
+
+	/*
+	 * List of sub-transaction IDs that incrementally updated the view.
+	 * This list is maintained through a transaction, and an ID is removed
+	 * when a sub-transaction is aborted. If any ID is left when the
+	 * transaction is committed, this means the view is incrementally
+	 * updated in this transaction.
+	 */
+	List   *subxids;
+} MV_TriggerHashEntry;
+
+/*
+ * MV_TriggerTable
+ *
+ * IVM related data for tables on which the trigger is invoked.
+ */
+typedef struct MV_TriggerTable
+{
+	Oid		table_id;			/* OID of the modified table */
+	List   *old_tuplestores;	/* tuplestores for deleted tuples */
+	List   *new_tuplestores;	/* tuplestores for inserted tuples */
+
+	List   *rte_indexes;		/* List of RTE index of the modified table */
+	RangeTblEntry *original_rte;	/* the original RTE saved before rewriting query */
+
+	Relation	rel;			/* relation of the modified table */
+	TupleTableSlot *slot;		/* for checking visibility in the pre-state table */
+} MV_TriggerTable;
+
+typedef struct DroppedImmvInfo
+{
+	Oid					immv_oid;
+	SubTransactionId	subxid;
+} DroppedImmvInfo;
+
+static HTAB *mv_trigger_info = NULL;
+static HTAB *dropped_immv = NULL;
+
+static HTAB *LastIvmUpdateHash;
+
+#define LAST_IVM_UPDATE_HASH_SIZE 256
+
+static void IvmShmemRequest(void *arg);
+
+/* hash table entries */
+typedef struct LastIvmUpdateEntry
+{
+	Oid		oid;	/* hash key */
+	FullTransactionId	last_ivm_update;
+} LastIvmUpdateEntry;
+
+const ShmemCallbacks IvmShmemCallbacks = {
+	.request_fn = IvmShmemRequest,
+};
+
+static void
+IvmShmemRequest(void *arg)
+{
+	ShmemRequestHash(.name = "LastIvmUpdate hash",
+					 .nelems = LAST_IVM_UPDATE_HASH_SIZE,
+					 .ptr = &LastIvmUpdateHash,
+					 .hash_info.keysize = sizeof(Oid),
+					 .hash_info.entrysize = sizeof(LastIvmUpdateEntry),
+					 .hash_flags = HASH_ELEM | HASH_BLOBS,
+		);
+}
+
+static bool in_delta_calculation = false;
+
+/* ENR name for materialized view delta */
+#define NEW_DELTA_ENRNAME "new_delta"
+#define OLD_DELTA_ENRNAME "old_delta"
+
 static int	matview_maintenance_depth = 0;
 
 static void transientrel_startup(DestReceiver *self, int operation, TupleDesc typeinfo);
@@ -60,6 +163,8 @@ static bool transientrel_receive(TupleTableSlot *slot, DestReceiver *self);
 static void transientrel_shutdown(DestReceiver *self);
 static void transientrel_destroy(DestReceiver *self);
 static uint64 refresh_matview_datafill(DestReceiver *dest, Query *query,
+									   QueryEnvironment *queryEnv,
+									   TupleDesc *resultTupleDesc,
 									   const char *queryString, bool is_create);
 static void refresh_by_match_merge(Oid matviewOid, Oid tempOid, Oid relowner,
 								   int save_sec_context);
@@ -67,6 +172,41 @@ static void refresh_by_heap_swap(Oid matviewOid, Oid OIDNewHeap, char relpersist
 static bool is_usable_unique_index(Relation indexRel);
 static void OpenMatViewIncrementalMaintenance(void);
 static void CloseMatViewIncrementalMaintenance(void);
+static Query *get_matview_query(Relation matviewRel);
+
+static Query *rewrite_query_for_preupdate_state(Query *query, List *tables,
+								  ParseState *pstate, Oid matviewid);
+static void register_delta_ENRs(ParseState *pstate, Query *query, List *tables);
+static char *make_subquery_targetlist_from_table(MV_TriggerTable *table);
+static char *make_delta_enr_name(const char *prefix, Oid relid, int count);
+static RangeTblEntry *get_prestate_rte(RangeTblEntry *rte, MV_TriggerTable *table,
+				 QueryEnvironment *queryEnv, Oid matviewid);
+static RangeTblEntry *makeDeltaTable(RangeTblEntry *rte, MV_TriggerTable *table,
+									 bool is_new, QueryEnvironment *queryEnv);
+static Query *rewrite_query_for_counting(Query *query, ParseState *pstate);
+
+static void calc_delta(MV_TriggerTable *table, int rte_index, Query *query,
+			DestReceiver *dest_old, DestReceiver *dest_new,
+			TupleDesc *tupdesc_old, TupleDesc *tupdesc_new,
+			QueryEnvironment *queryEnv);
+static Query *rewrite_query_for_postupdate_state(Query *query, MV_TriggerTable *table, int rte_index);
+
+static void apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *new_tuplestores,
+			TupleDesc tupdesc_old, TupleDesc tupdesc_new,
+			Query *query);
+static void apply_old_delta(const char *matviewname, const char *deltaname_old,
+				List *keys);
+static void apply_new_delta(const char *matviewname, const char *deltaname_new,
+				StringInfo target_list);
+static char *get_matching_condition_string(List *keys);
+static void generate_equal(StringInfo querybuf, Oid opttype,
+			   const char *leftop, const char *rightop);
+
+static void mv_InitHashTables(void);
+static void clean_up_IVM_hash_entry(MV_TriggerHashEntry *entry, bool is_abort,
+									SubTransactionId subxid);
+static void setLastUpdateXid(Oid immv_oid, FullTransactionId xid);
+static FullTransactionId getLastUpdateXid(Oid immv_oid);
 
 /*
  * SetMatViewPopulatedState
@@ -108,6 +248,46 @@ SetMatViewPopulatedState(Relation relation, bool newstate)
 	CommandCounterIncrement();
 }
 
+/*
+ * SetMatViewIVMState
+ *		Mark a materialized view as IVM, or not.
+ *
+ * NOTE: caller must be holding an appropriate lock on the relation.
+ */
+void
+SetMatViewIVMState(Relation relation, bool newstate)
+{
+	Relation	pgrel;
+	HeapTuple	tuple;
+
+	Assert(relation->rd_rel->relkind == RELKIND_MATVIEW);
+
+	/*
+	 * Update relation's pg_class entry.  Crucial side-effect: other backends
+	 * (and this one too!) are sent SI message to make them rebuild relcache
+	 * entries.
+	 */
+	pgrel = table_open(RelationRelationId, RowExclusiveLock);
+	tuple = SearchSysCacheCopy1(RELOID,
+								ObjectIdGetDatum(RelationGetRelid(relation)));
+	if (!HeapTupleIsValid(tuple))
+		elog(ERROR, "cache lookup failed for relation %u",
+			 RelationGetRelid(relation));
+
+	((Form_pg_class) GETSTRUCT(tuple))->relisivm = newstate;
+
+	CatalogTupleUpdate(pgrel, &tuple->t_self, tuple);
+
+	heap_freetuple(tuple);
+	table_close(pgrel, RowExclusiveLock);
+
+	/*
+	 * Advance command counter to make the updated pg_class row locally
+	 * visible.
+	 */
+	CommandCounterIncrement();
+}
+
 /*
  * ExecRefreshMatView -- execute a REFRESH MATERIALIZED VIEW command
  *
@@ -166,8 +346,6 @@ RefreshMatViewByOid(Oid matviewOid, bool is_create, bool skipData,
 					QueryCompletion *qc)
 {
 	Relation	matviewRel;
-	RewriteRule *rule;
-	List	   *actions;
 	Query	   *dataQuery;
 	Oid			tableSpace;
 	Oid			relowner;
@@ -178,6 +356,7 @@ RefreshMatViewByOid(Oid matviewOid, bool is_create, bool skipData,
 	int			save_sec_context;
 	int			save_nestlevel;
 	ObjectAddress address;
+	bool oldPopulated;
 
 	matviewRel = table_open(matviewOid, NoLock);
 	relowner = matviewRel->rd_rel->relowner;
@@ -193,6 +372,8 @@ RefreshMatViewByOid(Oid matviewOid, bool is_create, bool skipData,
 	save_nestlevel = NewGUCNestLevel();
 	RestrictSearchPath();
 
+	oldPopulated = RelationIsPopulated(matviewRel);
+
 	/* Make sure it is a materialized view. */
 	if (matviewRel->rd_rel->relkind != RELKIND_MATVIEW)
 		ereport(ERROR,
@@ -213,32 +394,7 @@ RefreshMatViewByOid(Oid matviewOid, bool is_create, bool skipData,
 				 errmsg("%s options %s and %s cannot be used together",
 						"REFRESH", "CONCURRENTLY", "WITH NO DATA")));
 
-	/*
-	 * Check that everything is correct for a refresh. Problems at this point
-	 * are internal errors, so elog is sufficient.
-	 */
-	if (matviewRel->rd_rel->relhasrules == false ||
-		matviewRel->rd_rules->numLocks < 1)
-		elog(ERROR,
-			 "materialized view \"%s\" is missing rewrite information",
-			 RelationGetRelationName(matviewRel));
-
-	if (matviewRel->rd_rules->numLocks > 1)
-		elog(ERROR,
-			 "materialized view \"%s\" has too many rules",
-			 RelationGetRelationName(matviewRel));
-
-	rule = matviewRel->rd_rules->rules[0];
-	if (rule->event != CMD_SELECT || !(rule->isInstead))
-		elog(ERROR,
-			 "the rule for materialized view \"%s\" is not a SELECT INSTEAD OF rule",
-			 RelationGetRelationName(matviewRel));
-
-	actions = rule->actions;
-	if (list_length(actions) != 1)
-		elog(ERROR,
-			 "the rule for materialized view \"%s\" is not a single action",
-			 RelationGetRelationName(matviewRel));
+	dataQuery = get_matview_query(matviewRel);
 
 	/*
 	 * Check that there is a unique index with no WHERE clause on one or more
@@ -275,12 +431,6 @@ RefreshMatViewByOid(Oid matviewOid, bool is_create, bool skipData,
 					 errhint("Create a unique index with no WHERE clause on one or more columns of the materialized view.")));
 	}
 
-	/*
-	 * The stored query was rewritten at the time of the MV definition, but
-	 * has not been scribbled on by the planner.
-	 */
-	dataQuery = linitial_node(Query, actions);
-
 	/*
 	 * Check for active uses of the relation in the current transaction, such
 	 * as open scans.
@@ -310,6 +460,90 @@ RefreshMatViewByOid(Oid matviewOid, bool is_create, bool skipData,
 		relpersistence = matviewRel->rd_rel->relpersistence;
 	}
 
+	/* delete IMMV triggers. */
+	if (RelationIsIVM(matviewRel) && skipData)
+	{
+		Relation	tgRel;
+		Relation	depRel;
+		ScanKeyData key;
+		SysScanDesc scan;
+		HeapTuple	tup;
+		ObjectAddresses *immv_triggers;
+
+		immv_triggers = new_object_addresses();
+
+		tgRel = table_open(TriggerRelationId, RowExclusiveLock);
+		depRel = table_open(DependRelationId, RowExclusiveLock);
+
+		/* search triggers that depends on IMMV. */
+		ScanKeyInit(&key,
+					Anum_pg_depend_refobjid,
+					BTEqualStrategyNumber, F_OIDEQ,
+					ObjectIdGetDatum(matviewOid));
+		scan = systable_beginscan(depRel, DependReferenceIndexId, true,
+								  NULL, 1, &key);
+		while ((tup = systable_getnext(scan)) != NULL)
+		{
+			ObjectAddress obj;
+			Form_pg_depend foundDep = (Form_pg_depend) GETSTRUCT(tup);
+
+			if (foundDep->classid == TriggerRelationId)
+			{
+				HeapTuple	tgtup;
+				ScanKeyData tgkey[1];
+				SysScanDesc tgscan;
+				Form_pg_trigger tgform;
+
+				/* Find the trigger name. */
+				ScanKeyInit(&tgkey[0],
+							Anum_pg_trigger_oid,
+							BTEqualStrategyNumber, F_OIDEQ,
+							ObjectIdGetDatum(foundDep->objid));
+
+				tgscan = systable_beginscan(tgRel, TriggerOidIndexId, true,
+											NULL, 1, tgkey);
+				tgtup = systable_getnext(tgscan);
+				if (!HeapTupleIsValid(tgtup))
+					elog(ERROR, "could not find tuple for immv trigger %u", foundDep->objid);
+
+				tgform = (Form_pg_trigger) GETSTRUCT(tgtup);
+
+				/* If trigger is created by IMMV, delete it. */
+				if (strncmp(NameStr(tgform->tgname), "IVM_trigger_", 12) == 0)
+				{
+					obj.classId = foundDep->classid;
+					obj.objectId = foundDep->objid;
+					obj.objectSubId = foundDep->refobjsubid;
+					add_exact_object_address(&obj, immv_triggers);
+				}
+				systable_endscan(tgscan);
+			}
+		}
+		systable_endscan(scan);
+
+		performMultipleDeletions(immv_triggers, DROP_RESTRICT, PERFORM_DELETION_INTERNAL);
+
+		table_close(depRel, RowExclusiveLock);
+		table_close(tgRel, RowExclusiveLock);
+		free_object_addresses(immv_triggers);
+	}
+
+	/*
+	 * Create triggers on incremental maintainable materialized view
+	 * This argument should use 'dataQuery'. This needs to use a rewritten query,
+	 * because a sublink in jointree is not supported by this function.
+	 *
+	 * This is performed before generating data because we have to wait
+	 * concurrent transactions modifying a base table and then take a snapshot
+	 * to see changes by these transactions to make sure a consistent view
+	 * is created.
+	 */
+	if (RelationIsIVM(matviewRel) && !skipData && !oldPopulated)
+	{
+		CreateIvmTriggersOnBaseTables(dataQuery, matviewOid);
+		CreateIndexOnIMMV(dataQuery, matviewRel);
+	}
+
 	/*
 	 * Create the transient table that will receive the regenerated data. Lock
 	 * it against access by any other process until commit (by which time it
@@ -326,8 +560,43 @@ RefreshMatViewByOid(Oid matviewOid, bool is_create, bool skipData,
 		DestReceiver *dest;
 
 		dest = CreateTransientRelDestReceiver(OIDNewHeap);
-		processed = refresh_matview_datafill(dest, dataQuery, queryString,
-											 is_create);
+
+		if (RelationIsIVM(matviewRel))
+		{
+			/*
+			 * In READ COMMITTED, get and push the latest snapshot again to see the
+			 * results of concurrent transactions committed after the current
+			 * transaction started.
+			 */
+			if (!IsolationUsesXactSnapshot())
+				PushActiveSnapshot(GetTransactionSnapshot());
+
+			/*
+			 * If a concurrent transaction updated the view incrementally and was
+			 * committed before we acquired the lock, the results of refresh_immv could
+			 * be inconsistent. Therefore, we have to check the transaction ID of the
+			 * most recent update of the view, and if this was in progress at the
+			 * transaction start, raise an error to prevent anomalies.
+			 */
+			if (!is_create)
+			{
+				FullTransactionId xid;
+
+				xid = getLastUpdateXid(matviewOid);
+				if (XidInMVCCSnapshot(XidFromFullTransactionId(xid), GetActiveSnapshot()))
+					ereport(ERROR,
+							(errcode(ERRCODE_T_R_SERIALIZATION_FAILURE),
+							 errmsg("the materialized view is incrementally updated in concurrent transaction"),
+							 errhint("The transaction might succeed if retried.")));
+			}
+		}
+
+		processed = refresh_matview_datafill(dest, dataQuery, NULL, NULL,
+											 queryString, is_create);
+
+		/* Pop the original snapshot. */
+		if (RelationIsIVM(matviewRel) && !IsolationUsesXactSnapshot())
+			PopActiveSnapshot();
 	}
 
 	/* Make the matview match the newly generated data. */
@@ -402,6 +671,8 @@ RefreshMatViewByOid(Oid matviewOid, bool is_create, bool skipData,
  */
 static uint64
 refresh_matview_datafill(DestReceiver *dest, Query *query,
+						 QueryEnvironment *queryEnv,
+						 TupleDesc *resultTupleDesc,
 						 const char *queryString, bool is_create)
 {
 	List	   *rewritten;
@@ -439,7 +710,7 @@ refresh_matview_datafill(DestReceiver *dest, Query *query,
 	/* Create a QueryDesc, redirecting output to our tuple receiver */
 	queryDesc = CreateQueryDesc(plan, queryString,
 								GetActiveSnapshot(), InvalidSnapshot,
-								dest, NULL, NULL, 0);
+								dest, NULL, queryEnv ? queryEnv: NULL, 0);
 
 	/* call ExecutorStart to prepare the plan for execution */
 	ExecutorStart(queryDesc, 0);
@@ -449,6 +720,9 @@ refresh_matview_datafill(DestReceiver *dest, Query *query,
 
 	processed = queryDesc->estate->es_processed;
 
+	if (resultTupleDesc)
+		*resultTupleDesc = CreateTupleDescCopy(queryDesc->tupDesc);
+
 	/* and clean up */
 	ExecutorFinish(queryDesc);
 	ExecutorEnd(queryDesc);
@@ -967,3 +1241,1488 @@ CloseMatViewIncrementalMaintenance(void)
 	matview_maintenance_depth--;
 	Assert(matview_maintenance_depth >= 0);
 }
+
+/*
+ * get_matview_query - get the Query from a matview's _RETURN rule.
+ */
+static Query *
+get_matview_query(Relation matviewRel)
+{
+	RewriteRule *rule;
+	List * actions;
+
+	/*
+	 * Check that everything is correct for a refresh. Problems at this point
+	 * are internal errors, so elog is sufficient.
+	 */
+	if (matviewRel->rd_rel->relhasrules == false ||
+		matviewRel->rd_rules->numLocks < 1)
+		elog(ERROR,
+			 "materialized view \"%s\" is missing rewrite information",
+			 RelationGetRelationName(matviewRel));
+
+	if (matviewRel->rd_rules->numLocks > 1)
+		elog(ERROR,
+			 "materialized view \"%s\" has too many rules",
+			 RelationGetRelationName(matviewRel));
+
+	rule = matviewRel->rd_rules->rules[0];
+	if (rule->event != CMD_SELECT || !(rule->isInstead))
+		elog(ERROR,
+			 "the rule for materialized view \"%s\" is not a SELECT INSTEAD OF rule",
+			 RelationGetRelationName(matviewRel));
+
+	actions = rule->actions;
+	if (list_length(actions) != 1)
+		elog(ERROR,
+			 "the rule for materialized view \"%s\" is not a single action",
+			 RelationGetRelationName(matviewRel));
+
+	/*
+	 * The stored query was rewritten at the time of the MV definition, but
+	 * has not been scribbled on by the planner.
+	 */
+	return linitial_node(Query, actions);
+}
+
+
+/* ----------------------------------------------------
+ *		Incremental View Maintenance routines
+ * ---------------------------------------------------
+ */
+
+/*
+ * IVM_immediate_before
+ *
+ * IVM trigger function invoked before base table is modified. If this is
+ * invoked firstly in the same statement, we save the transaction id and the
+ * command id at that time.
+ */
+Datum
+IVM_immediate_before(PG_FUNCTION_ARGS)
+{
+	TriggerData *trigdata = (TriggerData *) fcinfo->context;
+	char	   *matviewOid_text = trigdata->tg_trigger->tgargs[0];
+	char	   *ex_lock_text = trigdata->tg_trigger->tgargs[1];
+	Oid			matviewOid;
+	MV_TriggerHashEntry *entry;
+	bool	found;
+	bool	ex_lock;
+
+	matviewOid = DatumGetObjectId(DirectFunctionCall1(oidin, CStringGetDatum(matviewOid_text)));
+	ex_lock = DatumGetBool(DirectFunctionCall1(boolin, CStringGetDatum(ex_lock_text)));
+
+	/* If the view has more than one tables, we have to use an exclusive lock. */
+	if (ex_lock)
+	{
+		FullTransactionId xid;
+
+		/*
+		 * Wait for concurrent transactions which update this materialized view at
+		 * READ COMMITED. This is needed to see changes committed in other
+		 * transactions. No wait and raise an error at REPEATABLE READ or
+		 * SERIALIZABLE to prevent update anomalies of matviews.
+		 * XXX: dead-lock is possible here.
+		 */
+		if (!IsolationUsesXactSnapshot())
+			LockRelationOid(matviewOid, ExclusiveLock);
+		else if (!ConditionalLockRelationOid(matviewOid, ExclusiveLock))
+		{
+			/* try to throw error by name; relation could be deleted... */
+			char	   *relname = get_rel_name(matviewOid);
+
+			if (!relname)
+				ereport(ERROR,
+						(errcode(ERRCODE_LOCK_NOT_AVAILABLE),
+						errmsg("could not obtain lock on materialized view during incremental maintenance")));
+
+			ereport(ERROR,
+					(errcode(ERRCODE_LOCK_NOT_AVAILABLE),
+					errmsg("could not obtain lock on materialized view \"%s\" during incremental maintenance",
+							relname)));
+		}
+
+		/*
+		 * Even if we can acquire an lock, a concurrent transaction could have
+		 * updated the view incrementally and been committed before we acquired
+		 * the lock. Therefore, we have to check the transaction ID of the most
+		 * recent update of the view, and if this was in progress at the
+		 * transaction start, raise an error to prevent anomalies.
+		 */
+		xid = getLastUpdateXid(matviewOid);
+		if (XidInMVCCSnapshot(XidFromFullTransactionId(xid), GetTransactionSnapshot()))
+			ereport(ERROR,
+					(errcode(ERRCODE_T_R_SERIALIZATION_FAILURE),
+					 errmsg("the materialized view is incrementally updated in concurrent transaction"),
+					 errhint("The transaction might succeed if retried.")));
+	}
+	else
+		LockRelationOid(matviewOid, RowExclusiveLock);
+
+	/*
+	 * On the first call initialize the hashtable
+	 */
+	if (!mv_trigger_info)
+		mv_InitHashTables();
+
+	entry = (MV_TriggerHashEntry *) hash_search(mv_trigger_info,
+											  (void *) &matviewOid,
+											  HASH_ENTER, &found);
+
+	/* On the first BEFORE to update the view, initialize trigger data */
+	if (!found || entry->snapshot == InvalidSnapshot)
+	{
+		Snapshot snapshot;
+
+		/*
+		 * Get a snapshot just before the table was modified for checking
+		 * tuple visibility in the pre-update state of the table.
+		 *
+		 * In READ COMMITTED, use the latest snapshot again to see the
+		 * results of concurrent transactions committed after the current
+		 * transaction started.
+		 */
+		if (IsolationUsesXactSnapshot())
+			snapshot = GetActiveSnapshot();
+		else
+			snapshot = GetTransactionSnapshot();
+
+		entry->matview_id = matviewOid;
+		entry->before_trig_count = 0;
+		entry->after_trig_count = 0;
+		entry->snapshot = RegisterSnapshot(snapshot);
+		entry->tables = NIL;
+		entry->has_old = false;
+		entry->has_new = false;
+
+		/*
+		 * If this is the first table modifying query in the transaction,
+		 * initialize the list of subxids.
+		 */
+		if (!found)
+			entry->subxids = NIL;
+	}
+
+	entry->before_trig_count++;
+
+	return PointerGetDatum(NULL);
+}
+
+/*
+ * IVM_immediate_maintenance
+ *
+ * IVM trigger function invoked after base table is modified.
+ * For each table, tuplestores of transition tables are collected.
+ * and after the last modification
+ */
+Datum
+IVM_immediate_maintenance(PG_FUNCTION_ARGS)
+{
+	TriggerData *trigdata = (TriggerData *) fcinfo->context;
+	Relation	rel;
+	Oid			relid;
+	Oid			matviewOid;
+	Query	   *query;
+	Query	   *rewritten = NULL;
+	char	   *matviewOid_text = trigdata->tg_trigger->tgargs[0];
+	Relation	matviewRel;
+	int old_depth = matview_maintenance_depth;
+	SubTransactionId subxid;
+
+	Oid			relowner;
+	Tuplestorestate *old_tuplestore = NULL;
+	Tuplestorestate *new_tuplestore = NULL;
+	DestReceiver *dest_new = NULL, *dest_old = NULL;
+	Oid			save_userid;
+	int			save_sec_context;
+	int			save_nestlevel;
+
+	MV_TriggerHashEntry *entry;
+	MV_TriggerTable		*table;
+	bool	found;
+
+	ParseState		 *pstate;
+	QueryEnvironment *queryEnv = create_queryEnv();
+	MemoryContext	oldcxt;
+	ListCell   *lc;
+	int			i;
+
+
+	/* Create a ParseState for rewriting the view definition query */
+	pstate = make_parsestate(NULL);
+	pstate->p_queryEnv = queryEnv;
+	pstate->p_expr_kind = EXPR_KIND_SELECT_TARGET;
+
+	rel = trigdata->tg_relation;
+	relid = rel->rd_id;
+
+	matviewOid = DatumGetObjectId(DirectFunctionCall1(oidin, CStringGetDatum(matviewOid_text)));
+
+	/*
+	 * On the first call initialize the hashtable
+	 */
+	if (!mv_trigger_info)
+		mv_InitHashTables();
+
+	/* get the entry for this materialized view */
+	entry = (MV_TriggerHashEntry *) hash_search(mv_trigger_info,
+											  (void *) &matviewOid,
+											  HASH_FIND, &found);
+	Assert (found && entry != NULL);
+	entry->after_trig_count++;
+
+	/* search the entry for the modified table and create new entry if not found */
+	found = false;
+	foreach(lc, entry->tables)
+	{
+		table = (MV_TriggerTable *) lfirst(lc);
+		if (table->table_id == relid)
+		{
+			found = true;
+			break;
+		}
+	}
+	if (!found)
+	{
+		oldcxt = MemoryContextSwitchTo(TopTransactionContext);
+
+		table = (MV_TriggerTable *) palloc0(sizeof(MV_TriggerTable));
+		table->table_id = relid;
+		table->old_tuplestores = NIL;
+		table->new_tuplestores = NIL;
+		table->rte_indexes = NIL;
+		table->slot = MakeSingleTupleTableSlot(RelationGetDescr(rel), table_slot_callbacks(rel));
+		/* We assume we have at least RowExclusiveLock on modified tables. */
+		table->rel = table_open(RelationGetRelid(rel), NoLock);
+		entry->tables = lappend(entry->tables, table);
+
+		MemoryContextSwitchTo(oldcxt);
+	}
+
+	/* Save the transition tables and make a request to not free immediately */
+	if (trigdata->tg_oldtable)
+	{
+		oldcxt = MemoryContextSwitchTo(TopTransactionContext);
+		table->old_tuplestores = lappend(table->old_tuplestores, trigdata->tg_oldtable);
+		entry->has_old = true;
+		MemoryContextSwitchTo(oldcxt);
+	}
+	if (trigdata->tg_newtable)
+	{
+		oldcxt = MemoryContextSwitchTo(TopTransactionContext);
+		table->new_tuplestores = lappend(table->new_tuplestores, trigdata->tg_newtable);
+		entry->has_new = true;
+		MemoryContextSwitchTo(oldcxt);
+	}
+	if (entry->has_new || entry->has_old)
+	{
+		CmdType cmd;
+
+		if (TRIGGER_FIRED_BY_INSERT(trigdata->tg_event))
+			cmd = CMD_INSERT;
+		else if (TRIGGER_FIRED_BY_DELETE(trigdata->tg_event))
+			cmd = CMD_DELETE;
+		else if (TRIGGER_FIRED_BY_UPDATE(trigdata->tg_event))
+			cmd = CMD_UPDATE;
+		else
+			elog(ERROR,"unsupported trigger type");
+
+		/* Prolong lifespan of transition tables to the end of the last AFTER trigger */
+		SetTransitionTablePreserved(relid, cmd);
+	}
+
+
+	/* If this is not the last AFTER trigger call, immediately exit. */
+	Assert (entry->before_trig_count >= entry->after_trig_count);
+	if (entry->before_trig_count != entry->after_trig_count)
+		return PointerGetDatum(NULL);
+
+	/*
+	 * If this is the last AFTER trigger call, continue and update the view.
+	 */
+
+	/* record the subxid that updated the view incrementally */
+	subxid = GetCurrentSubTransactionId();
+	if (!list_member_xid(entry->subxids, subxid))
+	{
+		oldcxt = MemoryContextSwitchTo(TopTransactionContext);
+		entry->subxids = lappend_xid(entry->subxids, subxid);
+		MemoryContextSwitchTo(oldcxt);
+	}
+
+	/*
+	 * Advance command counter to make the updated base table rows locally
+	 * visible.
+	 */
+	CommandCounterIncrement();
+
+	matviewRel = table_open(matviewOid, NoLock);
+
+	/* Make sure it is a materialized view. */
+	Assert(matviewRel->rd_rel->relkind == RELKIND_MATVIEW);
+
+	/*
+	 * In READ COMMITTED, get and push the latest snapshot again to see the
+	 * results of concurrent transactions committed after the current
+	 * transaction started.
+	 */
+	if (!IsolationUsesXactSnapshot())
+		PushActiveSnapshot(GetTransactionSnapshot());
+
+	/*
+	 * Check for active uses of the relation in the current transaction, such
+	 * as open scans.
+	 *
+	 * NB: We count on this to protect us against problems with refreshing the
+	 * data using TABLE_INSERT_FROZEN.
+	 */
+	CheckTableNotInUse(matviewRel, "refresh a materialized view incrementally");
+
+	/*
+	 * Switch to the owner's userid, so that any functions are run as that
+	 * user.  Also arrange to make GUC variable changes local to this command.
+	 * We will switch modes when we are about to execute user code.
+	 */
+	relowner = matviewRel->rd_rel->relowner;
+	GetUserIdAndSecContext(&save_userid, &save_sec_context);
+	SetUserIdAndSecContext(relowner,
+						   save_sec_context | SECURITY_RESTRICTED_OPERATION);
+	save_nestlevel = NewGUCNestLevel();
+
+	/* get view query*/
+	query = get_matview_query(matviewRel);
+
+	/*
+	 * When a base table is truncated, the view content will be empty if the
+	 * view definition query does not contain an aggregate without a GROUP clause.
+	 * Therefore, such views can be truncated.
+	 */
+	if (TRIGGER_FIRED_BY_TRUNCATE(trigdata->tg_event))
+	{
+		ExecuteTruncateGuts(list_make1(matviewRel), list_make1_oid(matviewOid),
+							NIL, DROP_RESTRICT, false, false);
+
+		/* Clean up hash entry and delete tuplestores */
+		clean_up_IVM_hash_entry(entry, false, InvalidSubTransactionId);
+
+		/* Pop the original snapshot. */
+		if (!IsolationUsesXactSnapshot())
+			PopActiveSnapshot();
+
+		table_close(matviewRel, NoLock);
+
+		/* Roll back any GUC changes */
+		AtEOXact_GUC(false, save_nestlevel);
+
+		/* Restore userid and security context */
+		SetUserIdAndSecContext(save_userid, save_sec_context);
+
+		return PointerGetDatum(NULL);
+	}
+
+	/*
+	 * rewrite query for calculating deltas
+	 */
+
+	rewritten = copyObject(query);
+
+	/* Replace resnames in a target list with materialized view's attnames */
+	i = 0;
+	foreach (lc, rewritten->targetList)
+	{
+		TargetEntry *tle = (TargetEntry *) lfirst(lc);
+		Form_pg_attribute attr = TupleDescAttr(matviewRel->rd_att, i);
+		char *resname = NameStr(attr->attname);
+
+		tle->resname = pstrdup(resname);
+		i++;
+	}
+
+	/* Set all tables in the query to pre-update state */
+	rewritten = rewrite_query_for_preupdate_state(rewritten, entry->tables,
+												  pstate, matviewOid);
+	/* Rewrite for counting duplicated tuples */
+	rewritten = rewrite_query_for_counting(rewritten, pstate);
+
+	/* Create tuplestores to store view deltas */
+	if (entry->has_old)
+	{
+		oldcxt = MemoryContextSwitchTo(TopTransactionContext);
+
+		old_tuplestore = tuplestore_begin_heap(false, false, work_mem);
+		dest_old = CreateDestReceiver(DestTuplestore);
+		SetTuplestoreDestReceiverParams(dest_old,
+									old_tuplestore,
+									TopTransactionContext,
+									false,
+									NULL,
+									NULL);
+
+		MemoryContextSwitchTo(oldcxt);
+	}
+	if (entry->has_new)
+	{
+		oldcxt = MemoryContextSwitchTo(TopTransactionContext);
+
+		new_tuplestore = tuplestore_begin_heap(false, false, work_mem);
+		dest_new = CreateDestReceiver(DestTuplestore);
+		SetTuplestoreDestReceiverParams(dest_new,
+									new_tuplestore,
+									TopTransactionContext,
+									false,
+									NULL,
+									NULL);
+		MemoryContextSwitchTo(oldcxt);
+	}
+
+	/* for all modified tables */
+	foreach(lc, entry->tables)
+	{
+		ListCell *lc2;
+
+		table = (MV_TriggerTable *) lfirst(lc);
+
+		/* loop for self-join */
+		foreach(lc2, table->rte_indexes)
+		{
+			int	rte_index = lfirst_int(lc2);
+			TupleDesc		tupdesc_old;
+			TupleDesc		tupdesc_new;
+
+			/* calculate delta tables */
+			calc_delta(table, rte_index, rewritten, dest_old, dest_new,
+					   &tupdesc_old, &tupdesc_new, queryEnv);
+
+			/* Set the table in the query to post-update state */
+			rewritten = rewrite_query_for_postupdate_state(rewritten, table, rte_index);
+
+			PG_TRY();
+			{
+				/* apply the delta tables to the materialized view */
+				apply_delta(matviewOid, old_tuplestore, new_tuplestore,
+							tupdesc_old, tupdesc_new, query);
+			}
+			PG_CATCH();
+			{
+				matview_maintenance_depth = old_depth;
+				PG_RE_THROW();
+			}
+			PG_END_TRY();
+
+			/* clear view delta tuplestores */
+			if (old_tuplestore)
+				tuplestore_clear(old_tuplestore);
+			if (new_tuplestore)
+				tuplestore_clear(new_tuplestore);
+		}
+	}
+
+	/* Clean up hash entry and delete tuplestores */
+	clean_up_IVM_hash_entry(entry, false, InvalidSubTransactionId);
+	if (old_tuplestore)
+	{
+		dest_old->rDestroy(dest_old);
+		tuplestore_end(old_tuplestore);
+	}
+	if (new_tuplestore)
+	{
+		dest_new->rDestroy(dest_new);
+		tuplestore_end(new_tuplestore);
+	}
+
+	/* Pop the original snapshot. */
+	if (!IsolationUsesXactSnapshot())
+		PopActiveSnapshot();
+
+	table_close(matviewRel, NoLock);
+
+	/* Roll back any GUC changes */
+	AtEOXact_GUC(false, save_nestlevel);
+
+	/* Restore userid and security context */
+	SetUserIdAndSecContext(save_userid, save_sec_context);
+
+	return PointerGetDatum(NULL);
+}
+
+/*
+ * rewrite_query_for_preupdate_state
+ *
+ * Rewrite the query so that base tables' RTEs will represent "pre-update"
+ * state of tables. This is necessary to calculate view delta after multiple
+ * tables are modified.
+ */
+static Query*
+rewrite_query_for_preupdate_state(Query *query, List *tables,
+								  ParseState *pstate, Oid matviewid)
+{
+	ListCell *lc;
+	int num_rte = list_length(query->rtable);
+	int i;
+
+
+	/* register delta ENRs */
+	register_delta_ENRs(pstate, query, tables);
+
+	/* XXX: Is necessary? Is this right timing? */
+	AcquireRewriteLocks(query, true, false);
+
+	i = 1;
+	foreach(lc, query->rtable)
+	{
+		RangeTblEntry *r = (RangeTblEntry*) lfirst(lc);
+
+		ListCell *lc2;
+		foreach(lc2, tables)
+		{
+			MV_TriggerTable *table = (MV_TriggerTable *) lfirst(lc2);
+			/*
+			 * if the modified table is found then replace the original RTE with
+			 * "pre-state" RTE and append its index to the list.
+			 */
+			if (r->relid == table->table_id)
+			{
+				List *securityQuals;
+				List *withCheckOptions;
+				bool  hasRowSecurity;
+				bool  hasSubLinks;
+
+				RangeTblEntry *rte_pre = get_prestate_rte(r, table, pstate->p_queryEnv, matviewid);
+
+				/*
+				 * Set a row security poslicies of the modified table to the subquery RTE which
+				 * represents the pre-update state of the table.
+				 */
+				get_row_security_policies(query, table->original_rte, i,
+										  &securityQuals, &withCheckOptions,
+										  &hasRowSecurity, &hasSubLinks);
+
+				if (hasRowSecurity)
+				{
+					query->hasRowSecurity = true;
+					rte_pre->security_barrier = true;
+				}
+				if (hasSubLinks)
+					query->hasSubLinks = true;
+
+				rte_pre->securityQuals = securityQuals;
+				lfirst(lc) = rte_pre;
+
+				table->rte_indexes = lappend_int(table->rte_indexes, i);
+				break;
+			}
+		}
+
+		/* finish the loop if we processed all RTE included in the original query */
+		if (i++ >= num_rte)
+			break;
+	}
+
+	return query;
+}
+
+/*
+ * register_delta_ENRs
+ *
+ * For all modified tables, make ENRs for their transition tables
+ * and register them to the queryEnv. ENR's RTEs are also appended
+ * into the list in query tree.
+ */
+static void
+register_delta_ENRs(ParseState *pstate, Query *query, List *tables)
+{
+	QueryEnvironment *queryEnv = pstate->p_queryEnv;
+	ListCell *lc;
+	RangeTblEntry	*rte;
+
+	foreach(lc, tables)
+	{
+		MV_TriggerTable *table = (MV_TriggerTable *) lfirst(lc);
+		ListCell *lc2;
+		int count;
+
+		count = 0;
+		foreach(lc2, table->old_tuplestores)
+		{
+			Tuplestorestate *oldtable = (Tuplestorestate *) lfirst(lc2);
+			EphemeralNamedRelation enr =
+				palloc(sizeof(EphemeralNamedRelationData));
+			ParseNamespaceItem *nsitem;
+
+			enr->md.name = make_delta_enr_name("old", table->table_id, count);
+			enr->md.reliddesc = table->table_id;
+			enr->md.tupdesc = NULL;
+			enr->md.enrtype = ENR_NAMED_TUPLESTORE;
+			enr->md.enrtuples = tuplestore_tuple_count(oldtable);
+			enr->reldata = oldtable;
+			register_ENR(queryEnv, enr);
+
+			nsitem = addRangeTableEntryForENR(pstate, makeRangeVar(NULL, enr->md.name, -1), true);
+			rte = nsitem->p_rte;
+
+			query->rtable = lappend(query->rtable, rte);
+
+			count++;
+		}
+
+		count = 0;
+		foreach(lc2, table->new_tuplestores)
+		{
+			Tuplestorestate *newtable = (Tuplestorestate *) lfirst(lc2);
+			EphemeralNamedRelation enr =
+				palloc(sizeof(EphemeralNamedRelationData));
+			ParseNamespaceItem *nsitem;
+
+			enr->md.name = make_delta_enr_name("new", table->table_id, count);
+			enr->md.reliddesc = table->table_id;
+			enr->md.tupdesc = NULL;
+			enr->md.enrtype = ENR_NAMED_TUPLESTORE;
+			enr->md.enrtuples = tuplestore_tuple_count(newtable);
+			enr->reldata = newtable;
+			register_ENR(queryEnv, enr);
+
+			nsitem = addRangeTableEntryForENR(pstate, makeRangeVar(NULL, enr->md.name, -1), true);
+			rte = nsitem->p_rte;
+
+			query->rtable = lappend(query->rtable, rte);
+
+			count++;
+		}
+	}
+}
+
+#define DatumGetItemPointer(X)	 ((ItemPointer) DatumGetPointer(X))
+#define PG_GETARG_ITEMPOINTER(n) DatumGetItemPointer(PG_GETARG_DATUM(n))
+
+/*
+ * ivm_visible_in_prestate
+ *
+ * Check visibility of a tuple specified by the tableoid and item pointer
+ * using the snapshot taken just before the table was modified.
+ */
+Datum
+ivm_visible_in_prestate(PG_FUNCTION_ARGS)
+{
+	Oid			tableoid = PG_GETARG_OID(0);
+	ItemPointer itemPtr = PG_GETARG_ITEMPOINTER(1);
+	Oid			matviewOid = PG_GETARG_OID(2);
+	MV_TriggerHashEntry *entry;
+	MV_TriggerTable		*table = NULL;
+	ListCell   *lc;
+	bool	found;
+	bool	result;
+
+	if (!in_delta_calculation)
+		ereport(ERROR,
+				(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+				 errmsg("ivm_visible_in_prestate can be called only in delta calculation")));
+
+	entry = (MV_TriggerHashEntry *) hash_search(mv_trigger_info,
+											  (void *) &matviewOid,
+											  HASH_FIND, &found);
+	Assert (found && entry != NULL);
+
+	foreach(lc, entry->tables)
+	{
+		table = (MV_TriggerTable *) lfirst(lc);
+		if (table->table_id == tableoid)
+			break;
+	}
+
+	Assert (table != NULL);
+
+	result = table_tuple_fetch_row_version(table->rel, itemPtr, entry->snapshot, table->slot);
+
+	PG_RETURN_BOOL(result);
+}
+
+/*
+ * get_prestate_rte
+ *
+ * Rewrite RTE of the modified table to a subquery which represents
+ * "pre-state" table. The original RTE is saved in table->rte_original.
+ */
+static RangeTblEntry*
+get_prestate_rte(RangeTblEntry *rte, MV_TriggerTable *table,
+				 QueryEnvironment *queryEnv, Oid matviewid)
+{
+	StringInfoData str;
+	RawStmt *raw;
+	Query *subquery;
+	ParseState *pstate;
+	char *relname;
+	static char *subquery_tl;
+	int i;
+
+	pstate = make_parsestate(NULL);
+	pstate->p_queryEnv = queryEnv;
+	pstate->p_expr_kind = EXPR_KIND_SELECT_TARGET;
+
+	relname = quote_qualified_identifier(
+					get_namespace_name(RelationGetNamespace(table->rel)),
+									   RelationGetRelationName(table->rel));
+
+	subquery_tl = make_subquery_targetlist_from_table(table);
+
+	/*
+	 * Filtering inserted row using the snapshot taken before the table
+	 * is modified. ctid is required for maintaining outer join views.
+	 */
+	initStringInfo(&str);
+	appendStringInfo(&str,
+		"SELECT %s FROM %s t"
+		" WHERE pg_catalog.ivm_visible_in_prestate(t.tableoid, t.ctid ,%d::pg_catalog.oid)",
+			subquery_tl, relname, matviewid);
+
+	/*
+	 * Re-add rows deleted from the old transition tables, excluding those
+	 * also present in the new transition tables.
+	 */
+	if (list_length(table->old_tuplestores) > 0)
+	{
+		appendStringInfo(&str," UNION ALL SELECT %s  FROM (",
+			subquery_tl);
+
+		for (i = 0; i < list_length(table->old_tuplestores); i++)
+		{
+			if (i != 0)
+				appendStringInfo(&str, " UNION ALL ");
+			appendStringInfo(&str," TABLE %s",
+				make_delta_enr_name("old", table->table_id, i));
+		}
+		for (i = 0; i < list_length(table->new_tuplestores); i++)
+		{
+			appendStringInfo(&str, " EXCEPT ALL ");
+			appendStringInfo(&str," TABLE %s",
+				make_delta_enr_name("new", table->table_id, i));
+		}
+		appendStringInfo(&str,")");
+	}
+
+	/* Get a subquery representing pre-state of the table */
+	raw = (RawStmt*)linitial(raw_parser(str.data, RAW_PARSE_DEFAULT));
+	subquery = transformStmt(pstate, raw->stmt);
+
+	/* save the original RTE */
+	table->original_rte = copyObject(rte);
+
+	rte->rtekind = RTE_SUBQUERY;
+	rte->subquery = subquery;
+	rte->security_barrier = false;
+
+	/* Clear fields that should not be set in a subquery RTE */
+	rte->relid = InvalidOid;
+	rte->relkind = 0;
+	rte->rellockmode = 0;
+	rte->tablesample = NULL;
+	rte->perminfoindex = 0;         /* no permission checking for this RTE */
+	rte->inh = false;			/* must not be set for a subquery */
+
+	return rte;
+}
+
+/*
+ * make_subquery_targetlist_from_table
+ *
+ * Make a targetlist string of a subquery representing a delta table or a
+ * pre-update state table. This subquery substitutes a modified table RTE
+ * in the view definition query during view maintenance. In the targetlist,
+ * column names appear in order of the table definition. However, for
+ * attribute numbers of vars in the query tree to reference columns of the
+ * subquery  correctly even though the table has a dropped column, put "null"
+ * as a dummy value at the position of a dropped column.
+ *
+ * We would also able to walk the query tree to rewrite varattnos, but
+ * crafting targetlist is more simple and reasonable.
+ */
+static char*
+make_subquery_targetlist_from_table(MV_TriggerTable *table)
+{
+	StringInfoData str;
+	TupleDesc	tupdesc;
+	int			i;
+
+	tupdesc = RelationGetDescr(table->rel);
+	initStringInfo(&str);
+	for (i = 0; i < tupdesc->natts; i++)
+	{
+		Form_pg_attribute attr = TupleDescAttr(tupdesc, i);
+
+		if (i > 0)
+			appendStringInfo(&str, ", ");
+
+		if (attr->attisdropped)
+			appendStringInfo(&str, "null");
+		else
+			appendStringInfo(&str, "%s", quote_identifier(NameStr(attr->attname)));
+	}
+
+	return str.data;
+}
+
+/*
+ * make_delta_enr_name
+ *
+ * Make a name for ENR of a transition table from the base table's oid.
+ * prefix will be "new" or "old" depending on its transition table kind..
+ */
+static char*
+make_delta_enr_name(const char *prefix, Oid relid, int count)
+{
+	char buf[NAMEDATALEN];
+	char *name;
+
+	snprintf(buf, NAMEDATALEN, "__ivm_%s_%u_%u", prefix, relid, count);
+	name = pstrdup(buf);
+
+	return name;
+}
+
+/*
+ * makeDeltaTable
+ *
+ * Make a RTE representing a delta of the specified table.
+ */
+static RangeTblEntry*
+makeDeltaTable(RangeTblEntry *rte, MV_TriggerTable *table,
+		   bool is_new, QueryEnvironment *queryEnv)
+{
+	StringInfoData str;
+	ParseState	*pstate;
+	RawStmt *raw;
+	Query *sub;
+	int		i;
+
+	const char *prefix_union = is_new ? "new" : "old";
+	const char *prefix_except = is_new ? "old" : "new";
+	int num_union = is_new ? list_length(table->new_tuplestores) : list_length(table->old_tuplestores);
+	int num_except = is_new ? list_length(table->old_tuplestores) : list_length(table->new_tuplestores);
+
+	/* the previous RTE must be a subquery which represents "pre-state" table */
+	Assert(rte->rtekind == RTE_SUBQUERY);
+
+	/* Create a ParseState for rewriting the view definition query */
+	pstate = make_parsestate(NULL);
+	pstate->p_queryEnv = queryEnv;
+	pstate->p_expr_kind = EXPR_KIND_NONE;
+
+	initStringInfo(&str);
+	appendStringInfo(&str,
+		" SELECT %s FROM ( ",
+		make_subquery_targetlist_from_table(table));
+
+	for (i = 0; i < num_union; i++)
+	{
+		if (i > 0)
+			appendStringInfo(&str, " UNION ALL ");
+
+		appendStringInfo(&str,
+			" TABLE  %s",
+			make_delta_enr_name(prefix_union, table->table_id, i));
+	}
+	for (i = 0; i < num_except; i++)
+	{
+		appendStringInfo(&str, " EXCEPT ALL ");
+
+		appendStringInfo(&str,
+			" TABLE  %s",
+			make_delta_enr_name(prefix_except, table->table_id, i));
+	}
+	appendStringInfo(&str,")");
+
+	raw = (RawStmt*)linitial(raw_parser(str.data, RAW_PARSE_DEFAULT));
+	sub = transformStmt(pstate, raw->stmt);
+
+	/*
+	 * Update the subquery so that it represent the combined transition
+	 * table.  Note that we leave the security_barrier and securityQuals
+	 * fields so that the subquery relation can be protected by the RLS
+	 * policy as same as the modified table.
+	 */
+	rte->rtekind = RTE_SUBQUERY;
+	rte->subquery = sub;
+
+	return rte;
+}
+
+/*
+ * rewrite_query_for_counting
+ *
+ * Rewrite query for counting duplicated tuples.
+ */
+static Query *
+rewrite_query_for_counting(Query *query, ParseState *pstate)
+{
+	TargetEntry *tle_count;
+	FuncCall *fn;
+	Node *node;
+
+	/* Add count(*) for counting distinct tuples in views */
+	fn = makeFuncCall(SystemFuncName("count"), NIL, COERCE_EXPLICIT_CALL, -1);
+	fn->agg_star = true;
+	if (!query->groupClause && !query->hasAggs)
+		query->groupClause = transformDistinctClause(NULL, &query->targetList, query->sortClause, false);
+
+	node = ParseFuncOrColumn(pstate, fn->funcname, NIL, NULL, fn, false, -1);
+
+	tle_count = makeTargetEntry((Expr *) node,
+								list_length(query->targetList) + 1,
+								pstrdup("__ivm_count__"),
+								false);
+	query->targetList = lappend(query->targetList, tle_count);
+	query->hasAggs = true;
+
+	return query;
+}
+
+/*
+ * calc_delta
+ *
+ * Calculate view deltas generated under the modification of a table specified
+ * by the RTE index.
+ */
+static void
+calc_delta(MV_TriggerTable *table, int rte_index, Query *query,
+			DestReceiver *dest_old, DestReceiver *dest_new,
+			TupleDesc *tupdesc_old, TupleDesc *tupdesc_new,
+			QueryEnvironment *queryEnv)
+{
+	ListCell *lc = list_nth_cell(query->rtable, rte_index - 1);
+	RangeTblEntry *rte = (RangeTblEntry *) lfirst(lc);
+
+	in_delta_calculation = true;
+
+	/* Generate old delta */
+	if (dest_old && list_length(table->old_tuplestores) > 0)
+	{
+		/* Replace the modified table with the old delta table and calculate the old view delta. */
+		lfirst(lc) = makeDeltaTable(rte, table, false, queryEnv);
+		refresh_matview_datafill(dest_old, query, queryEnv, tupdesc_old, "", false);
+	}
+
+	/* Generate new delta */
+	if (dest_new && list_length(table->new_tuplestores) > 0)
+	{
+		/* Replace the modified table with the new delta table and calculate the new view delta*/
+		lfirst(lc) = makeDeltaTable(rte, table, true, queryEnv);
+		refresh_matview_datafill(dest_new, query, queryEnv, tupdesc_new, "", false);
+	}
+
+	in_delta_calculation = false;
+}
+
+/*
+ * rewrite_query_for_postupdate_state
+ *
+ * Rewrite the query so that the specified base table's RTEs will represent
+ * "post-update" state of tables. This is called after the view delta
+ * calculation due to changes on this table finishes.
+ */
+static Query*
+rewrite_query_for_postupdate_state(Query *query, MV_TriggerTable *table, int rte_index)
+{
+	ListCell *lc = list_nth_cell(query->rtable, rte_index - 1);
+
+	/* Retore the original RTE */
+	lfirst(lc) = table->original_rte;
+
+	return query;
+}
+
+/*
+ * apply_delta
+ *
+ * Apply deltas to the materialized view. In outer join cases, this requires
+ * the view maintenance graph.
+ */
+static void
+apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *new_tuplestores,
+			TupleDesc tupdesc_old, TupleDesc tupdesc_new,
+			Query *query)
+{
+	StringInfoData querybuf;
+	StringInfoData target_list_buf;
+	Relation	matviewRel;
+	char	   *matviewname;
+	ListCell	*lc;
+	int			i;
+	List	   *keys = NIL;
+
+
+	/*
+	 * get names of the materialized view and delta tables
+	 */
+
+	matviewRel = table_open(matviewOid, NoLock);
+	matviewname = quote_qualified_identifier(get_namespace_name(RelationGetNamespace(matviewRel)),
+											 RelationGetRelationName(matviewRel));
+
+	/*
+	 * Build parts of the maintenance queries
+	 */
+
+	initStringInfo(&querybuf);
+	initStringInfo(&target_list_buf);
+
+	/* build string of target list */
+	for (i = 0; i < matviewRel->rd_att->natts; i++)
+	{
+		Form_pg_attribute attr = TupleDescAttr(matviewRel->rd_att, i);
+		char   *resname = NameStr(attr->attname);
+
+		if (i != 0)
+			appendStringInfo(&target_list_buf, ", ");
+		appendStringInfo(&target_list_buf, "%s", quote_qualified_identifier(NULL, resname));
+	}
+
+	i = 0;
+	foreach (lc, query->targetList)
+	{
+		TargetEntry *tle = (TargetEntry *) lfirst(lc);
+		Form_pg_attribute attr = TupleDescAttr(matviewRel->rd_att, i);
+
+		i++;
+
+		if (tle->resjunk)
+			continue;
+
+		keys = lappend(keys, attr);
+	}
+
+	/* Start maintaining the materialized view. */
+	OpenMatViewIncrementalMaintenance();
+
+	/* Open SPI context. */
+	if (SPI_connect() != SPI_OK_CONNECT)
+		elog(ERROR, "SPI_connect failed");
+
+	/* For tuple deletion */
+	if (old_tuplestores && tuplestore_tuple_count(old_tuplestores) > 0)
+	{
+		EphemeralNamedRelation enr = palloc(sizeof(EphemeralNamedRelationData));
+		int				rc;
+
+		/* convert tuplestores to ENR, and register for SPI */
+		enr->md.name = pstrdup(OLD_DELTA_ENRNAME);
+		enr->md.reliddesc = InvalidOid;
+		enr->md.tupdesc = tupdesc_old;
+		enr->md.enrtype = ENR_NAMED_TUPLESTORE;
+		enr->md.enrtuples = tuplestore_tuple_count(old_tuplestores);
+		enr->reldata = old_tuplestores;
+
+		rc = SPI_register_relation(enr);
+		if (rc != SPI_OK_REL_REGISTER)
+			elog(ERROR, "SPI_register failed");
+
+		apply_old_delta(matviewname, OLD_DELTA_ENRNAME, keys);
+
+	}
+	/* For tuple insertion */
+	if (new_tuplestores && tuplestore_tuple_count(new_tuplestores) > 0)
+	{
+		EphemeralNamedRelation enr = palloc(sizeof(EphemeralNamedRelationData));
+		int rc;
+
+		/* convert tuplestores to ENR, and register for SPI */
+		enr->md.name = pstrdup(NEW_DELTA_ENRNAME);
+		enr->md.reliddesc = InvalidOid;
+		enr->md.tupdesc = tupdesc_new;;
+		enr->md.enrtype = ENR_NAMED_TUPLESTORE;
+		enr->md.enrtuples = tuplestore_tuple_count(new_tuplestores);
+		enr->reldata = new_tuplestores;
+
+		rc = SPI_register_relation(enr);
+		if (rc != SPI_OK_REL_REGISTER)
+			elog(ERROR, "SPI_register failed");
+
+		/* apply new delta */
+		apply_new_delta(matviewname, NEW_DELTA_ENRNAME, &target_list_buf);
+	}
+
+	/* We're done maintaining the materialized view. */
+	CloseMatViewIncrementalMaintenance();
+
+	table_close(matviewRel, NoLock);
+
+	/* Close SPI context. */
+	if (SPI_finish() != SPI_OK_FINISH)
+		elog(ERROR, "SPI_finish failed");
+}
+
+/*
+ * apply_old_delta
+ *
+ * Execute a query for applying a delta table given by deltname_old
+ * which contains tuples to be deleted from to a materialized view given by
+ * matviewname.  This is used when counting is not required.
+ */
+static void
+apply_old_delta(const char *matviewname, const char *deltaname_old,
+				List *keys)
+{
+	StringInfoData	querybuf;
+	StringInfoData	keysbuf;
+	char   *match_cond;
+	ListCell *lc;
+
+	/* build WHERE condition for searching tuples to be deleted */
+	match_cond = get_matching_condition_string(keys);
+
+	/* build string of keys list */
+	initStringInfo(&keysbuf);
+	foreach (lc, keys)
+	{
+		Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc);
+		char   *resname = NameStr(attr->attname);
+		appendStringInfo(&keysbuf, "%s", quote_qualified_identifier("mv", resname));
+		if (lnext(keys, lc))
+			appendStringInfo(&keysbuf, ", ");
+	}
+
+	/* Search for matching tuples from the view and update or delete if found. */
+	initStringInfo(&querybuf);
+	appendStringInfo(&querybuf,
+	"DELETE FROM %s WHERE ctid IN ("
+		"SELECT tid FROM (SELECT pg_catalog.row_number() over (partition by %s) AS \"__ivm_row_number__\","
+								  "mv.ctid AS tid,"
+								  "diff.\"__ivm_count__\""
+						 "FROM %s AS mv, %s AS diff "
+						 "WHERE %s) v "
+					"WHERE v.\"__ivm_row_number__\" OPERATOR(pg_catalog.<=) v.\"__ivm_count__\")",
+					matviewname,
+					keysbuf.data,
+					matviewname, deltaname_old,
+					match_cond);
+
+	if (SPI_exec(querybuf.data, 0) != SPI_OK_DELETE)
+		elog(ERROR, "SPI_exec failed: %s", querybuf.data);
+}
+
+/*
+ * apply_new_delta
+ *
+ * Execute a query for applying a delta table given by deltname_new
+ * which contains tuples to be inserted into a materialized view given by
+ * matviewname.  This is used when counting is not required.
+ */
+static void
+apply_new_delta(const char *matviewname, const char *deltaname_new,
+				StringInfo target_list)
+{
+	StringInfoData	querybuf;
+
+	/* Search for matching tuples from the view and update or delete if found. */
+	initStringInfo(&querybuf);
+	appendStringInfo(&querybuf,
+					"INSERT INTO %s (%s) SELECT %s FROM ("
+						"SELECT diff.*, pg_catalog.generate_series(1, diff.\"__ivm_count__\")"
+							" AS __ivm_generate_series__ "
+						"FROM %s AS diff) AS v",
+					matviewname, target_list->data, target_list->data,
+					deltaname_new);
+
+	if (SPI_exec(querybuf.data, 0) != SPI_OK_INSERT)
+		elog(ERROR, "SPI_exec failed: %s", querybuf.data);
+}
+
+/*
+ * get_matching_condition_string
+ *
+ * Build a predicate string for looking for a tuple with given keys.
+ */
+static char *
+get_matching_condition_string(List *keys)
+{
+	StringInfoData match_cond;
+	ListCell	*lc;
+
+	/* If there is no key columns, the condition is always true. */
+	if (keys == NIL)
+		return "true";
+
+	initStringInfo(&match_cond);
+	foreach (lc, keys)
+	{
+		Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc);
+		char   *resname = NameStr(attr->attname);
+		char   *mv_resname = quote_qualified_identifier("mv", resname);
+		char   *diff_resname = quote_qualified_identifier("diff", resname);
+		Oid		typid = attr->atttypid;
+
+		/* Considering NULL values, we can not use simple = operator. */
+		appendStringInfo(&match_cond, "(");
+		generate_equal(&match_cond, typid, mv_resname, diff_resname);
+		appendStringInfo(&match_cond, " OR (%s IS NULL AND %s IS NULL))",
+						 mv_resname, diff_resname);
+
+		if (lnext(keys, lc))
+			appendStringInfo(&match_cond, " AND ");
+	}
+
+	return match_cond.data;
+}
+
+/*
+ * generate_equals
+ *
+ * Generate an equality clause using given operands' default equality
+ * operator.
+ */
+static void
+generate_equal(StringInfo querybuf, Oid opttype,
+			   const char *leftop, const char *rightop)
+{
+	TypeCacheEntry *typentry;
+
+	typentry = lookup_type_cache(opttype, TYPECACHE_EQ_OPR);
+	if (!OidIsValid(typentry->eq_opr))
+		ereport(ERROR,
+				(errcode(ERRCODE_UNDEFINED_FUNCTION),
+				 errmsg("could not identify an equality operator for type %s",
+						format_type_be_qualified(opttype))));
+
+	generate_operator_clause(querybuf,
+							 leftop, opttype,
+							 typentry->eq_opr,
+							 rightop, opttype);
+}
+
+/*
+ * mv_InitHashTables
+ */
+static void
+mv_InitHashTables(void)
+{
+	HASHCTL		ctl;
+
+	memset(&ctl, 0, sizeof(ctl));
+	ctl.keysize = sizeof(Oid);
+	ctl.entrysize = sizeof(MV_TriggerHashEntry);
+	mv_trigger_info = hash_create("MV trigger info",
+								 MV_INIT_QUERYHASHSIZE,
+								 &ctl, HASH_ELEM | HASH_BLOBS);
+
+	memset(&ctl, 0, sizeof(ctl));
+	ctl.keysize = sizeof(Oid);
+	ctl.entrysize = sizeof(DroppedImmvInfo);
+	dropped_immv = hash_create("Dropped IMMVs", 16,
+							   &ctl, HASH_ELEM | HASH_BLOBS);
+}
+
+/*
+ * AtAbort_IVM
+ *
+ * Clean up hash entries for all materialized views. This is called at
+ * (sub-)transaction abort. When the top-level transaction is aborted,
+ * InvalidSubTransactionId is set to subxid.
+ *
+ * Also, remove dropped IMMV information if it is aborted.
+ */
+void
+AtAbort_IVM(SubTransactionId subxid)
+{
+	HASH_SEQ_STATUS seq;
+
+	if (mv_trigger_info)
+	{
+		MV_TriggerHashEntry *entry;
+		hash_seq_init(&seq, mv_trigger_info);
+		while ((entry = hash_seq_search(&seq)) != NULL)
+			clean_up_IVM_hash_entry(entry, true, subxid);
+	}
+
+	if (dropped_immv)
+	{
+		DroppedImmvInfo *entry;
+		hash_seq_init(&seq, dropped_immv);
+		while ((entry = hash_seq_search(&seq)) != NULL)
+		{
+			if (subxid == InvalidSubTransactionId || subxid == entry->subxid)
+				hash_search(dropped_immv, (void *) &entry->immv_oid, HASH_REMOVE, NULL);
+		}
+	}
+
+	in_delta_calculation = false;
+}
+
+/*
+ * AtPreCommit_IVM
+ *
+ * Record the transaction ID that updated the view incrementally.
+ * Also, remove the entry for dropped IMMVs.
+ */
+void
+AtPreCommit_IVM(void)
+{
+	HASH_SEQ_STATUS seq;
+
+	if (mv_trigger_info)
+	{
+		MV_TriggerHashEntry *entry;
+
+		/*
+		 * Record the transaction ID that udpate the view incrementally,
+		 * and perform the final clean up of the entry.
+		 */
+		hash_seq_init(&seq, mv_trigger_info);
+		while ((entry = hash_seq_search(&seq)) != NULL)
+		{
+			setLastUpdateXid(entry->matview_id, GetTopFullTransactionId());
+			hash_search(mv_trigger_info, (void *) &entry->matview_id, HASH_REMOVE, NULL);
+		}
+	}
+
+	if (dropped_immv)
+	{
+		DroppedImmvInfo *entry;
+
+		LWLockAcquire(IvmControlLock, LW_EXCLUSIVE);
+		hash_seq_init(&seq, dropped_immv);
+		while ((entry = hash_seq_search(&seq)) != NULL)
+		{
+			hash_search(LastIvmUpdateHash, (void *) &entry->immv_oid, HASH_REMOVE, NULL);
+			hash_search(dropped_immv, (void *) &entry->immv_oid, HASH_REMOVE, NULL);
+		}
+		LWLockRelease(IvmControlLock);
+	}
+
+	in_delta_calculation = false;
+}
+
+/*
+ * clean_up_IVM_hash_entry
+ *
+ * Clean up tuple stores and hash entries for a materialized view after its
+ * maintenance finished. This is called at the end of table modifying query
+ * or (sub-)transaction abort. When the top-level transaction is aborted,
+ * InvalidSubTransactionId is set to subxid.
+ */
+static void
+clean_up_IVM_hash_entry(MV_TriggerHashEntry *entry, bool is_abort,
+						SubTransactionId subxid)
+{
+	bool found;
+	ListCell *lc;
+
+	/* clean up tuple stores */
+	foreach(lc, entry->tables)
+	{
+		MV_TriggerTable *table = (MV_TriggerTable *) lfirst(lc);
+
+		list_free(table->old_tuplestores);
+		list_free(table->new_tuplestores);
+		if (!is_abort)
+		{
+			ExecDropSingleTupleTableSlot(table->slot);
+			table_close(table->rel, NoLock);
+		}
+	}
+	list_free(entry->tables);
+	entry->tables = NIL;
+
+	if (is_abort)
+	{
+		bool	remove_entry = false;
+
+		/*
+		 * When the top-level transaction is aborted, remove all subxids.
+		 * When a sub-transaction is aborted, remove only its subxid.
+		 */
+		if (subxid == InvalidSubTransactionId)
+			remove_entry = true;
+		else
+		{
+			foreach(lc, entry->subxids)
+			{
+				if (lfirst_xid(lc) == subxid)
+				{
+					entry->subxids = list_delete_cell(entry->subxids, lc);
+					break;
+				}
+			}
+
+			/*
+			 * If all the subxid are removed, it means that the view was not
+			 * updated at all in this transaction.
+			 */
+			if (list_length(entry->subxids) == 0)
+				remove_entry = true;
+		}
+
+		/*
+		 * Remove entries of not updated views from the hash table.
+		 */
+		if (remove_entry)
+			hash_search(mv_trigger_info, (void *) &entry->matview_id, HASH_REMOVE, &found);
+	}
+	else
+	{
+		/* When the query sucsessully finished, unregister the snapshot */
+		UnregisterSnapshot(entry->snapshot);
+	}
+
+	entry->snapshot = InvalidSnapshot;
+}
+
+/*
+ * setLastUpdateXid
+ *
+ * Store the transaction ID that updated the view incremenally.
+ */
+static void
+setLastUpdateXid(Oid immv_oid, FullTransactionId xid)
+{
+	LastIvmUpdateEntry *entry;
+
+	LWLockAcquire(IvmControlLock, LW_EXCLUSIVE);
+	entry = (LastIvmUpdateEntry *) hash_search(LastIvmUpdateHash, (void *) &immv_oid, HASH_ENTER, NULL);
+	entry->oid = immv_oid;
+	entry->last_ivm_update = xid;
+	LWLockRelease(IvmControlLock);
+}
+
+/*
+ * getLastUpdateXid
+ *
+ * Get the most recent transaction ID that updated the view incrementally.
+ */
+static FullTransactionId
+getLastUpdateXid(Oid immv_oid)
+{
+	FullTransactionId xid = InvalidFullTransactionId;
+	LastIvmUpdateEntry *entry;
+	bool found;
+
+	LWLockAcquire(IvmControlLock, LW_SHARED);
+	entry = (LastIvmUpdateEntry *) hash_search(LastIvmUpdateHash, (void *) &immv_oid, HASH_FIND, &found);
+	LWLockRelease(IvmControlLock);
+	if (found)
+		xid = entry->last_ivm_update;
+
+	return xid;
+}
+
+void
+removeImmv(Oid immv_oid)
+{
+	DroppedImmvInfo *entry;
+
+	if (!dropped_immv)
+		mv_InitHashTables();
+
+	entry = (DroppedImmvInfo *) hash_search(dropped_immv, (void *) &immv_oid, HASH_ENTER, NULL);
+	entry->subxid = GetCurrentSubTransactionId();
+}
+
+/*
+ * isIvmName
+ *
+ * Check if this is a IVM hidden column from the name.
+ */
+bool
+isIvmName(const char *s)
+{
+	if (s)
+		return (strncmp(s, "__ivm_", 6) == 0);
+	return false;
+}
diff --git a/src/backend/commands/tablecmds.c b/src/backend/commands/tablecmds.c
index a1845240a98..99bc709959a 100644
--- a/src/backend/commands/tablecmds.c
+++ b/src/backend/commands/tablecmds.c
@@ -62,6 +62,7 @@
 #include "commands/defrem.h"
 #include "commands/event_trigger.h"
 #include "commands/extension.h"
+#include "commands/matview.h"
 #include "commands/repack.h"
 #include "commands/sequence.h"
 #include "commands/tablecmds.h"
@@ -1804,6 +1805,9 @@ RangeVarCallbackForDropRelation(const RangeVar *rel, Oid relOid, Oid oldRelOid,
 	state->actual_relkind = classform->relkind;
 	state->actual_relpersistence = classform->relpersistence;
 
+	if (classform->relkind == RELKIND_MATVIEW && classform->relisivm)
+		removeImmv(relOid);
+
 	/*
 	 * Both RELKIND_RELATION and RELKIND_PARTITIONED_TABLE are OBJECT_TABLE,
 	 * but RemoveRelations() can only pass one relkind for a given relation.
diff --git a/src/backend/utils/activity/wait_event_names.txt b/src/backend/utils/activity/wait_event_names.txt
index 560659f9568..d97c35eeef0 100644
--- a/src/backend/utils/activity/wait_event_names.txt
+++ b/src/backend/utils/activity/wait_event_names.txt
@@ -370,6 +370,7 @@ WaitLSN	"Waiting to read or update shared Wait-for-LSN state."
 LogicalDecodingControl	"Waiting to read or update logical decoding status information."
 DataChecksumsWorker	"Waiting for data checksums worker."
 AioWorkerControl	"Waiting to update AIO worker information."
+IvmControl	"Waiting for read or update IMMV information.."
 
 #
 # END OF PREDEFINED LWLOCKS (DO NOT CHANGE THIS LINE)
diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat
index be157a5fbe9..b8722eea7a4 100644
--- a/src/include/catalog/pg_proc.dat
+++ b/src/include/catalog/pg_proc.dat
@@ -12693,4 +12693,14 @@
   proname => 'hashoid8extended', prorettype => 'int8',
   proargtypes => 'oid8 int8', prosrc => 'hashoid8extended' },
 
+# IVM
+{ oid => '786', descr => 'ivm trigger (before)',
+  proname => 'IVM_immediate_before', provolatile => 'v', prorettype => 'trigger',
+  proargtypes => '', prosrc => 'IVM_immediate_before' },
+{ oid => '787', descr => 'ivm trigger (after)',
+  proname => 'IVM_immediate_maintenance', provolatile => 'v', prorettype => 'trigger',
+  proargtypes => '', prosrc => 'IVM_immediate_maintenance' },
+{ oid => '788', descr => 'ivm filetring ',
+  proname => 'ivm_visible_in_prestate', provolatile => 's', prorettype => 'bool',
+  proargtypes => 'oid tid oid', prosrc => 'ivm_visible_in_prestate' },
 ]
diff --git a/src/include/commands/createas.h b/src/include/commands/createas.h
index f895c67c0c2..c286ebcd70e 100644
--- a/src/include/commands/createas.h
+++ b/src/include/commands/createas.h
@@ -16,6 +16,7 @@
 
 #include "catalog/objectaddress.h"
 #include "nodes/params.h"
+#include "nodes/pathnodes.h"
 #include "parser/parse_node.h"
 #include "tcop/dest.h"
 #include "utils/queryenvironment.h"
@@ -25,6 +26,9 @@ extern ObjectAddress ExecCreateTableAs(ParseState *pstate, CreateTableAsStmt *st
 									   ParamListInfo params, QueryEnvironment *queryEnv,
 									   QueryCompletion *qc);
 
+extern void CreateIvmTriggersOnBaseTables(Query *qry, Oid matviewOid);
+extern void CreateIndexOnIMMV(Query *query, Relation matviewRel);
+
 extern int	GetIntoRelEFlags(IntoClause *intoClause);
 
 extern DestReceiver *CreateIntoRelDestReceiver(IntoClause *intoClause);
diff --git a/src/include/commands/matview.h b/src/include/commands/matview.h
index 738c731c1a9..f1dbfc052c5 100644
--- a/src/include/commands/matview.h
+++ b/src/include/commands/matview.h
@@ -15,6 +15,7 @@
 #define MATVIEW_H
 
 #include "catalog/objectaddress.h"
+#include "fmgr.h"
 #include "nodes/params.h"
 #include "nodes/parsenodes.h"
 #include "tcop/dest.h"
@@ -23,6 +24,8 @@
 
 extern void SetMatViewPopulatedState(Relation relation, bool newstate);
 
+extern void SetMatViewIVMState(Relation relation, bool newstate);
+
 extern ObjectAddress ExecRefreshMatView(RefreshMatViewStmt *stmt, const char *queryString,
 										QueryCompletion *qc);
 extern ObjectAddress RefreshMatViewByOid(Oid matviewOid, bool is_create, bool skipData,
@@ -33,4 +36,12 @@ extern DestReceiver *CreateTransientRelDestReceiver(Oid transientoid);
 
 extern bool MatViewIncrementalMaintenanceIsEnabled(void);
 
+extern Datum IVM_immediate_before(PG_FUNCTION_ARGS);
+extern Datum IVM_immediate_maintenance(PG_FUNCTION_ARGS);
+extern Datum IVM_visible_in_prestate(PG_FUNCTION_ARGS);
+extern void AtAbort_IVM(SubTransactionId subtxid);
+extern void AtPreCommit_IVM(void);
+extern void removeImmv(Oid immv_oid);
+extern bool isIvmName(const char *s);
+
 #endif							/* MATVIEW_H */
diff --git a/src/include/storage/lwlocklist.h b/src/include/storage/lwlocklist.h
index d7eb648bd27..756c63baf97 100644
--- a/src/include/storage/lwlocklist.h
+++ b/src/include/storage/lwlocklist.h
@@ -89,6 +89,7 @@ PG_LWLOCK(54, WaitLSN)
 PG_LWLOCK(55, LogicalDecodingControl)
 PG_LWLOCK(56, DataChecksumsWorker)
 PG_LWLOCK(57, AioWorkerControl)
+PG_LWLOCK(58, IvmControl)
 
 /*
  * There also exist several built-in LWLock tranches.  As with the predefined
diff --git a/src/include/storage/subsystemlist.h b/src/include/storage/subsystemlist.h
index 9ad619080be..481e15d00a1 100644
--- a/src/include/storage/subsystemlist.h
+++ b/src/include/storage/subsystemlist.h
@@ -88,3 +88,6 @@ PG_SHMEM_SUBSYSTEM(DataChecksumsShmemCallbacks)
 
 /* AIO subsystem. This delegates to the method-specific callbacks */
 PG_SHMEM_SUBSYSTEM(AioShmemCallbacks)
+
+/* Incremental View Maintenance */
+PG_SHMEM_SUBSYSTEM(IvmShmemCallbacks)
-- 
2.43.0


--Multipart=_Fri__29_May_2026_23_14_17_+0900_Te0o73X2VqYK57Gd
Content-Type: text/x-diff;
 name="v37-0005-Add-Incremental-View-Maintenance-support-to-psql.patch"
Content-Disposition: attachment;
 filename="v37-0005-Add-Incremental-View-Maintenance-support-to-psql.patch"
Content-Transfer-Encoding: 7bit



^ permalink  raw  reply  [nested|flat] 101+ messages in thread

* [PATCH v38 06/11] Add Incremental View Maintenance support
@ 2026-05-29 09:06  Yugo Nagata <[email protected]>
  0 siblings, 0 replies; 101+ messages in thread

From: Yugo Nagata @ 2026-05-29 09:06 UTC (permalink / raw)

In this implementation, AFTER triggers are used to collect
tuplestores containing transition table contents. When multiple tables
are changed, multiple AFTER triggers are invoked, then the final AFTER
trigger performs actual update of the matview. In addition, BEFORE
triggers are also used to handle global information for view
maintenance.

To calculate view deltas, we need both pre-state and post-state of base
tables. Post-update states are available in AFTER trigger, and pre-update
states can be calculated by removing inserted tuples and appending deleted
tuples. Insterted tuples are filtered using the snapshot taken before
table modification, and deleted tuples are contained in the old transition
table.

Incrementally Maintainable Materialized Views (IMMV) can contain
duplicated tuples.

This patch also allows self-join, simultaneous updates of more than
one base table, and multiple updates of the same base table.
---
 src/backend/access/transam/xact.c             |    8 +
 src/backend/commands/createas.c               |  709 +++++++
 src/backend/commands/matview.c                | 1835 ++++++++++++++++-
 src/backend/commands/tablecmds.c              |    4 +
 .../utils/activity/wait_event_names.txt       |    1 +
 src/include/catalog/pg_proc.dat               |   10 +
 src/include/commands/createas.h               |    4 +
 src/include/commands/matview.h                |   11 +
 src/include/storage/lwlocklist.h              |    1 +
 src/include/storage/subsystemlist.h           |    3 +
 10 files changed, 2548 insertions(+), 38 deletions(-)

diff --git a/src/backend/access/transam/xact.c b/src/backend/access/transam/xact.c
index 3a89149016f..0e6cb5493d2 100644
--- a/src/backend/access/transam/xact.c
+++ b/src/backend/access/transam/xact.c
@@ -37,6 +37,7 @@
 #include "catalog/pg_enum.h"
 #include "catalog/storage.h"
 #include "commands/async.h"
+#include "commands/matview.h"
 #include "commands/tablecmds.h"
 #include "commands/trigger.h"
 #include "common/pg_prng.h"
@@ -2322,6 +2323,9 @@ CommitTransaction(void)
 	CallXactCallbacks(is_parallel_worker ? XACT_EVENT_PARALLEL_PRE_COMMIT
 					  : XACT_EVENT_PRE_COMMIT);
 
+	/* Store the transaction ID that updated the view incrementally */
+	AtPreCommit_IVM();
+
 	/*
 	 * If this xact has started any unfinished parallel operation, clean up
 	 * its workers, warning about leaked resources.  (But we don't actually
@@ -2973,6 +2977,7 @@ AbortTransaction(void)
 	AtAbort_Notify();
 	AtEOXact_RelationMap(false, is_parallel_worker);
 	AtAbort_Twophase();
+	AtAbort_IVM(InvalidSubTransactionId);
 
 	/*
 	 * Advertise the fact that we aborted in pg_xact (assuming that we got as
@@ -5304,6 +5309,9 @@ AbortSubTransaction(void)
 
 	UnlockBuffers();
 
+	/* Clean up hash entries for incremental view maintenance */
+	AtAbort_IVM(s->subTransactionId);
+
 	/* Reset WAL record construction state */
 	XLogResetInsertion();
 
diff --git a/src/backend/commands/createas.c b/src/backend/commands/createas.c
index 6dbb831ca89..a499688b79d 100644
--- a/src/backend/commands/createas.c
+++ b/src/backend/commands/createas.c
@@ -29,18 +29,32 @@
 #include "access/tableam.h"
 #include "access/xact.h"
 #include "catalog/namespace.h"
+#include "catalog/index.h"
+#include "catalog/pg_am_d.h"
+#include "catalog/pg_constraint.h"
+#include "catalog/pg_inherits.h"
+#include "catalog/pg_trigger.h"
 #include "catalog/toasting.h"
 #include "commands/createas.h"
+#include "commands/defrem.h"
 #include "commands/matview.h"
 #include "commands/prepare.h"
 #include "commands/tablecmds.h"
+#include "commands/tablespace.h"
+#include "commands/trigger.h"
 #include "commands/view.h"
 #include "executor/execdesc.h"
 #include "executor/executor.h"
+#include "miscadmin.h"
 #include "nodes/makefuncs.h"
 #include "nodes/nodeFuncs.h"
 #include "nodes/queryjumble.h"
+#include "optimizer/optimizer.h"
+#include "optimizer/prep.h"
 #include "parser/analyze.h"
+#include "parser/parser.h"
+#include "parser/parsetree.h"
+#include "parser/parse_clause.h"
 #include "rewrite/rewriteHandler.h"
 #include "tcop/tcopprot.h"
 #include "utils/builtins.h"
@@ -70,6 +84,12 @@ static bool intorel_receive(TupleTableSlot *slot, DestReceiver *self);
 static void intorel_shutdown(DestReceiver *self);
 static void intorel_destroy(DestReceiver *self);
 
+static void CreateIvmTriggersOnBaseTablesRecurse(Query *qry, Node *node, Oid matviewOid,
+									 List **relids, bool ex_lock);
+static void CreateIvmTrigger(Oid relOid, Oid viewOid, int16 type, int16 timing, bool ex_lock);
+static void check_ivm_restriction(Node *node);
+static bool check_ivm_restriction_walker(Node *node, void *context);
+static Bitmapset *get_primary_key_attnos_from_query(Query *query, List **constraintList);
 
 /*
  * create_ctas_internal
@@ -277,6 +297,18 @@ ExecCreateTableAs(ParseState *pstate, CreateTableAsStmt *stmt,
 		into->skipData = true;
 	}
 
+	if (is_matview && into->ivm)
+	{
+		/* check if the query is supported in IMMV definition */
+		if (contain_mutable_functions((Node *) query))
+			ereport(ERROR,
+					(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+					 errmsg("mutable function is not supported on incrementally maintainable materialized view"),
+					 errhint("functions must be marked IMMUTABLE")));
+
+		check_ivm_restriction((Node *) query);
+	}
+
 	if (into->skipData)
 	{
 		/*
@@ -287,15 +319,36 @@ ExecCreateTableAs(ParseState *pstate, CreateTableAsStmt *stmt,
 		 */
 		address = create_ctas_nodata(query->targetList, into);
 
+		/*
+		 * For IVM, mark the matview before refresh so RelationIsIVM()
+		 * returns true inside RefreshMatViewByOid.
+		 */
+		if (is_matview && into->ivm)
+		{
+			Relation matviewRel = table_open(address.objectId, NoLock);
+
+			SetMatViewIVMState(matviewRel, true);
+			table_close(matviewRel, NoLock);
+			CommandCounterIncrement();
+		}
+
 		/*
 		 * For materialized views, reuse the REFRESH logic, which locks down
 		 * security-restricted operations and restricts the search_path.  This
 		 * reduces the chance that a subsequent refresh will fail.
 		 */
 		if (do_refresh)
+		{
 			RefreshMatViewByOid(address.objectId, true, false, false,
 								pstate->p_sourcetext, qc);
 
+			if (is_matview && into->ivm && IsolationUsesXactSnapshot())
+				ereport(WARNING,
+						(errmsg("inconsistent view can be created in isolation level SERIALIZABLE or REPEATABLE READ"),
+						 errdetail("The view may not include effects of a concurrent transaction."),
+						 errhint("The view with incremental maintenance should be created in isolation level READ COMMITTED, "
+								 "or refreshed manually to make sure the view is consistent.")));
+		}
 	}
 	else
 	{
@@ -635,3 +688,659 @@ intorel_destroy(DestReceiver *self)
 {
 	pfree(self);
 }
+
+/*
+ * CreateIvmTriggersOnBaseTables -- create IVM triggers on all base tables
+ */
+void
+CreateIvmTriggersOnBaseTables(Query *qry, Oid matviewOid)
+{
+	List   *relids = NIL;
+	bool	ex_lock = false;
+	RangeTblEntry *rte;
+
+	/* Immediately return if we don't have any base tables. */
+	if (list_length(qry->rtable) < 1)
+		return;
+
+	/*
+	 * If the view has more than one base tables, we need an exclusive lock
+	 * on the view so that the view would be maintained serially to avoid
+	 * the inconsistency that occurs when two base tables are modified in
+	 * concurrent transactions. However, if the view has only one table,
+	 * we can use a weaker lock.
+	 *
+	 * The type of lock should be determined here, because if we check the
+	 * view definition at maintenance time, we need to acquire a weaker lock,
+	 * and upgrading the lock level after this increases probability of
+	 * deadlock.
+	 */
+
+	rte = list_nth(qry->rtable, 0);
+	if (list_length(qry->rtable) > 1 || rte->rtekind != RTE_RELATION)
+		ex_lock = true;
+
+	CreateIvmTriggersOnBaseTablesRecurse(qry, (Node *)qry, matviewOid, &relids, ex_lock);
+
+	list_free(relids);
+}
+
+static void
+CreateIvmTriggersOnBaseTablesRecurse(Query *qry, Node *node, Oid matviewOid,
+									 List **relids, bool ex_lock)
+{
+	if (node == NULL)
+		return;
+
+	/* This can recurse, so check for excessive recursion */
+	check_stack_depth();
+
+	switch (nodeTag(node))
+	{
+		case T_Query:
+			{
+				Query *query = (Query *) node;
+
+				CreateIvmTriggersOnBaseTablesRecurse(qry, (Node *)query->jointree, matviewOid, relids, ex_lock);
+			}
+			break;
+
+		case T_RangeTblRef:
+			{
+				int			rti = ((RangeTblRef *) node)->rtindex;
+				RangeTblEntry *rte = rt_fetch(rti, qry->rtable);
+
+				if (rte->rtekind == RTE_RELATION && !list_member_oid(*relids, rte->relid))
+				{
+					CreateIvmTrigger(rte->relid, matviewOid, TRIGGER_TYPE_INSERT, TRIGGER_TYPE_BEFORE, ex_lock);
+					CreateIvmTrigger(rte->relid, matviewOid, TRIGGER_TYPE_DELETE, TRIGGER_TYPE_BEFORE, ex_lock);
+					CreateIvmTrigger(rte->relid, matviewOid, TRIGGER_TYPE_UPDATE, TRIGGER_TYPE_BEFORE, ex_lock);
+					CreateIvmTrigger(rte->relid, matviewOid, TRIGGER_TYPE_TRUNCATE, TRIGGER_TYPE_BEFORE, true);
+					CreateIvmTrigger(rte->relid, matviewOid, TRIGGER_TYPE_INSERT, TRIGGER_TYPE_AFTER, ex_lock);
+					CreateIvmTrigger(rte->relid, matviewOid, TRIGGER_TYPE_DELETE, TRIGGER_TYPE_AFTER, ex_lock);
+					CreateIvmTrigger(rte->relid, matviewOid, TRIGGER_TYPE_UPDATE, TRIGGER_TYPE_AFTER, ex_lock);
+					CreateIvmTrigger(rte->relid, matviewOid, TRIGGER_TYPE_TRUNCATE, TRIGGER_TYPE_AFTER, true);
+
+					*relids = lappend_oid(*relids, rte->relid);
+				}
+			}
+			break;
+
+		case T_FromExpr:
+			{
+				FromExpr   *f = (FromExpr *) node;
+				ListCell   *l;
+
+				foreach(l, f->fromlist)
+					CreateIvmTriggersOnBaseTablesRecurse(qry, lfirst(l), matviewOid, relids, ex_lock);
+			}
+			break;
+
+		case T_JoinExpr:
+			{
+				JoinExpr   *j = (JoinExpr *) node;
+
+				CreateIvmTriggersOnBaseTablesRecurse(qry, j->larg, matviewOid, relids, ex_lock);
+				CreateIvmTriggersOnBaseTablesRecurse(qry, j->rarg, matviewOid, relids, ex_lock);
+			}
+			break;
+
+		default:
+			elog(ERROR, "unrecognized node type: %d", (int) nodeTag(node));
+	}
+}
+
+/*
+ * CreateIvmTrigger -- create IVM trigger on a base table
+ */
+static void
+CreateIvmTrigger(Oid relOid, Oid viewOid, int16 type, int16 timing, bool ex_lock)
+{
+	ObjectAddress	refaddr;
+	ObjectAddress	address;
+	CreateTrigStmt *ivm_trigger;
+	List *transitionRels = NIL;
+
+	Assert(timing == TRIGGER_TYPE_BEFORE || timing == TRIGGER_TYPE_AFTER);
+
+	refaddr.classId = RelationRelationId;
+	refaddr.objectId = viewOid;
+	refaddr.objectSubId = 0;
+
+	ivm_trigger = makeNode(CreateTrigStmt);
+	ivm_trigger->relation = NULL;
+	ivm_trigger->row = false;
+
+	ivm_trigger->timing = timing;
+	ivm_trigger->events = type;
+
+	switch (type)
+	{
+		case TRIGGER_TYPE_INSERT:
+			ivm_trigger->trigname = (timing == TRIGGER_TYPE_BEFORE ? "IVM_trigger_ins_before" : "IVM_trigger_ins_after");
+			break;
+		case TRIGGER_TYPE_DELETE:
+			ivm_trigger->trigname = (timing == TRIGGER_TYPE_BEFORE ? "IVM_trigger_del_before" : "IVM_trigger_del_after");
+			break;
+		case TRIGGER_TYPE_UPDATE:
+			ivm_trigger->trigname = (timing == TRIGGER_TYPE_BEFORE ? "IVM_trigger_upd_before" : "IVM_trigger_upd_after");
+			break;
+		case TRIGGER_TYPE_TRUNCATE:
+			ivm_trigger->trigname = (timing == TRIGGER_TYPE_BEFORE ? "IVM_trigger_truncate_before" : "IVM_trigger_truncate_after");
+			break;
+		default:
+			elog(ERROR, "unsupported trigger type");
+	}
+
+	if (timing == TRIGGER_TYPE_AFTER)
+	{
+		if (type == TRIGGER_TYPE_INSERT || type == TRIGGER_TYPE_UPDATE)
+		{
+			TriggerTransition *n = makeNode(TriggerTransition);
+			n->name = "__ivm_newtable";
+			n->isNew = true;
+			n->isTable = true;
+
+			transitionRels = lappend(transitionRels, n);
+		}
+		if (type == TRIGGER_TYPE_DELETE || type == TRIGGER_TYPE_UPDATE)
+		{
+			TriggerTransition *n = makeNode(TriggerTransition);
+			n->name = "__ivm_oldtable";
+			n->isNew = false;
+			n->isTable = true;
+
+			transitionRels = lappend(transitionRels, n);
+		}
+	}
+
+	/*
+	 * XXX: When using DELETE or UPDATE, we must use exclusive lock for now
+	 * because apply_old_delta(_with_count) uses ctid to identify the tuple
+	 * to be deleted/deleted, but doesn't work in concurrent situations.
+	 *
+	 * If the view doesn't have aggregate, distinct, or tuple duplicate,
+	 * then it would work even in concurrent situations. However, we don't have
+	 * any way to guarantee the view has a unique key before opening the IMMV
+	 * at the maintenance time because users may drop the unique index.
+	 */
+
+	if (type == TRIGGER_TYPE_DELETE || type == TRIGGER_TYPE_UPDATE)
+		ex_lock = true;
+
+	ivm_trigger->funcname =
+		(timing == TRIGGER_TYPE_BEFORE ? SystemFuncName("IVM_immediate_before") : SystemFuncName("IVM_immediate_maintenance"));
+
+	ivm_trigger->columns = NIL;
+	ivm_trigger->transitionRels = transitionRels;
+	ivm_trigger->whenClause = NULL;
+	ivm_trigger->isconstraint = false;
+	ivm_trigger->deferrable = false;
+	ivm_trigger->initdeferred = false;
+	ivm_trigger->constrrel = NULL;
+	ivm_trigger->args = list_make2(
+		makeString(DatumGetPointer(DirectFunctionCall1(oidout, ObjectIdGetDatum(viewOid)))),
+		makeString(DatumGetPointer(DirectFunctionCall1(boolout, BoolGetDatum(ex_lock))))
+		);
+
+	address = CreateTrigger(ivm_trigger, NULL, relOid, InvalidOid, InvalidOid,
+						 InvalidOid, InvalidOid, InvalidOid, NULL, true, false);
+
+	recordDependencyOn(&address, &refaddr, DEPENDENCY_AUTO);
+
+	/* Make changes-so-far visible */
+	CommandCounterIncrement();
+}
+
+/*
+ * check_ivm_restriction --- look for specify nodes in the query tree
+ */
+static void
+check_ivm_restriction(Node *node)
+{
+	check_ivm_restriction_walker(node, NULL);
+}
+
+static bool
+check_ivm_restriction_walker(Node *node, void *context)
+{
+	if (node == NULL)
+		return false;
+
+	/*
+	 * We currently don't support Sub-Query.
+	 */
+	if (IsA(node, SubPlan) || IsA(node, SubLink))
+		ereport(ERROR,
+				(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+				 errmsg("subquery is not supported on incrementally maintainable materialized view")));
+
+	/* This can recurse, so check for excessive recursion */
+	check_stack_depth();
+
+	switch (nodeTag(node))
+	{
+		case T_Query:
+			{
+				Query *qry = (Query *)node;
+				ListCell   *lc;
+				List       *vars;
+
+				/* if contained CTE, return error */
+				if (qry->cteList != NIL)
+					ereport(ERROR,
+							(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+							 errmsg("CTE is not supported on incrementally maintainable materialized view")));
+				if (qry->havingQual != NULL)
+					ereport(ERROR,
+							(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+							 errmsg(" HAVING clause is not supported on incrementally maintainable materialized view")));
+				if (qry->sortClause != NIL)	/* There is a possibility that we don't need to return an error */
+					ereport(ERROR,
+							(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+							 errmsg("ORDER BY clause is not supported on incrementally maintainable materialized view")));
+				if (qry->limitOffset != NULL || qry->limitCount != NULL)
+					ereport(ERROR,
+							(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+							 errmsg("LIMIT/OFFSET clause is not supported on incrementally maintainable materialized view")));
+				if (qry->distinctClause)
+					ereport(ERROR,
+							(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+							 errmsg("DISTINCT is not supported on incrementally maintainable materialized view")));
+				if (qry->hasDistinctOn)
+					ereport(ERROR,
+							(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+							 errmsg("DISTINCT ON is not supported on incrementally maintainable materialized view")));
+				if (qry->hasWindowFuncs)
+					ereport(ERROR,
+							(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+							 errmsg("window functions are not supported on incrementally maintainable materialized view")));
+				if (qry->groupingSets != NIL)
+					ereport(ERROR,
+							(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+							 errmsg("GROUPING SETS, ROLLUP, or CUBE clauses is not supported on incrementally maintainable materialized view")));
+				if (qry->setOperations != NULL)
+					ereport(ERROR,
+							(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+							 errmsg("UNION/INTERSECT/EXCEPT statements are not supported on incrementally maintainable materialized view")));
+				if (list_length(qry->targetList) == 0)
+					ereport(ERROR,
+							(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+							 errmsg("empty target list is not supported on incrementally maintainable materialized view")));
+				if (qry->rowMarks != NIL)
+					ereport(ERROR,
+							(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+							 errmsg("FOR UPDATE/SHARE clause is not supported on incrementally maintainable materialized view")));
+
+				/* system column restrictions */
+				vars = pull_vars_of_level((Node *) qry, 0);
+				foreach(lc, vars)
+				{
+					if (IsA(lfirst(lc), Var))
+					{
+						Var *var = (Var *) lfirst(lc);
+						/* if system column, return error */
+						if (var->varattno < 0)
+							ereport(ERROR,
+									(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+									 errmsg("system column is not supported on incrementally maintainable materialized view")));
+					}
+				}
+
+				/* check if type in the target list had an equality operator */
+				foreach(lc, qry->targetList)
+				{
+					TargetEntry *tle = (TargetEntry *) lfirst(lc);
+					Oid             atttype = exprType((Node *) tle->expr);
+					Oid             opclass;
+
+					opclass = GetDefaultOpClass(atttype, BTREE_AM_OID);
+					if (!OidIsValid(opclass))
+						ereport(ERROR,
+								(errcode(ERRCODE_UNDEFINED_OBJECT),
+								 errmsg("data type %s has no default operator class for access method \"%s\"",
+									format_type_be(atttype), "btree")));
+				}
+
+				/* restrictions for rtable */
+				foreach(lc, qry->rtable)
+				{
+					RangeTblEntry *rte = (RangeTblEntry *) lfirst(lc);
+
+					if (rte->subquery)
+						ereport(ERROR,
+								(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+								 errmsg("subquery is not supported on incrementally maintainable materialized view")));
+
+					if (rte->tablesample != NULL)
+						ereport(ERROR,
+								(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+								 errmsg("TABLESAMPLE clause is not supported on incrementally maintainable materialized view")));
+
+					if (rte->relkind == RELKIND_PARTITIONED_TABLE)
+						ereport(ERROR,
+								(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+								 errmsg("partitioned table is not supported on incrementally maintainable materialized view")));
+
+					if (rte->relkind == RELKIND_RELATION && has_superclass(rte->relid))
+						ereport(ERROR,
+								(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+								 errmsg("partitions is not supported on incrementally maintainable materialized view")));
+
+					if (rte->relkind == RELKIND_RELATION && find_inheritance_children(rte->relid, NoLock) != NIL)
+						ereport(ERROR,
+								(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+								 errmsg("inheritance parent is not supported on incrementally maintainable materialized view")));
+
+					if (rte->relkind == RELKIND_FOREIGN_TABLE)
+						ereport(ERROR,
+								(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+								 errmsg("foreign table is not supported on incrementally maintainable materialized view")));
+
+					if (rte->relkind == RELKIND_VIEW ||
+						rte->relkind == RELKIND_MATVIEW)
+						ereport(ERROR,
+								(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+								 errmsg("VIEW or MATERIALIZED VIEW is not supported on incrementally maintainable materialized view")));
+
+					if (rte->rtekind == RTE_VALUES)
+						ereport(ERROR,
+								(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+								 errmsg("VALUES is not supported on incrementally maintainable materialized view")));
+
+				}
+
+				query_tree_walker(qry, check_ivm_restriction_walker, NULL, QTW_IGNORE_RANGE_TABLE);
+
+				break;
+			}
+		case T_TargetEntry:
+			{
+				TargetEntry *tle = (TargetEntry *)node;
+				if (isIvmName(tle->resname))
+						ereport(ERROR,
+								(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+								 errmsg("column name %s is not supported on incrementally maintainable materialized view", tle->resname)));
+
+				expression_tree_walker(node, check_ivm_restriction_walker, NULL);
+				break;
+			}
+		case T_JoinExpr:
+			{
+				JoinExpr *joinexpr = (JoinExpr *)node;
+
+				if (joinexpr->jointype > JOIN_INNER)
+						ereport(ERROR,
+								(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+								 errmsg("OUTER JOIN is not supported on incrementally maintainable materialized view")));
+
+				expression_tree_walker(node, check_ivm_restriction_walker, NULL);
+			}
+			break;
+		case T_Aggref:
+			ereport(ERROR,
+					(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+					 errmsg("aggregate function is not supported on incrementally maintainable materialized view")));
+			break;
+		default:
+			expression_tree_walker(node, check_ivm_restriction_walker, (void *) context);
+			break;
+	}
+	return false;
+}
+
+/*
+ * CreateIndexOnIMMV
+ *
+ * Create a unique index on incremental maintainable materialized view.
+ * If the view definition query has a GROUP BY clause, the index is created
+ * on the columns of GROUP BY expressions. Otherwise, if the view contains
+ * all primary key attributes of its base tables in the target list, the index
+ * is created on these attributes. In other cases, no index is created.
+ */
+void
+CreateIndexOnIMMV(Query *query, Relation matviewRel)
+{
+	ListCell *lc;
+	IndexStmt  *index;
+	ObjectAddress address;
+	List *constraintList = NIL;
+	char		idxname[NAMEDATALEN];
+	List	   *indexoidlist = RelationGetIndexList(matviewRel);
+	ListCell   *indexoidscan;
+	Bitmapset *key_attnos;
+
+	snprintf(idxname, sizeof(idxname), "%s_index", RelationGetRelationName(matviewRel));
+
+	index = makeNode(IndexStmt);
+
+	index->unique = true;
+	index->primary = false;
+	index->isconstraint = false;
+	index->deferrable = false;
+	index->initdeferred = false;
+	index->idxname = idxname;
+	index->relation =
+		makeRangeVar(get_namespace_name(RelationGetNamespace(matviewRel)),
+					 pstrdup(RelationGetRelationName(matviewRel)),
+					 -1);
+	index->accessMethod = DEFAULT_INDEX_TYPE;
+	index->options = NIL;
+	index->tableSpace = get_tablespace_name(matviewRel->rd_rel->reltablespace);
+	index->whereClause = NULL;
+	index->indexParams = NIL;
+	index->indexIncludingParams = NIL;
+	index->excludeOpNames = NIL;
+	index->idxcomment = NULL;
+	index->indexOid = InvalidOid;
+	index->oldNumber = InvalidRelFileNumber;
+	index->oldCreateSubid = InvalidSubTransactionId;
+	index->oldFirstRelfilelocatorSubid = InvalidSubTransactionId;
+	index->transformed = true;
+	index->concurrent = false;
+	index->if_not_exists = false;
+
+	/* create index on the base tables' primary key columns */
+	key_attnos = get_primary_key_attnos_from_query(query, &constraintList);
+	if (key_attnos)
+	{
+		foreach(lc, query->targetList)
+		{
+			TargetEntry *tle = (TargetEntry *) lfirst(lc);
+			Form_pg_attribute attr = TupleDescAttr(matviewRel->rd_att, tle->resno - 1);
+
+			if (bms_is_member(tle->resno - FirstLowInvalidHeapAttributeNumber, key_attnos))
+			{
+				IndexElem  *iparam;
+
+				iparam = makeNode(IndexElem);
+				iparam->name = pstrdup(NameStr(attr->attname));
+				iparam->expr = NULL;
+				iparam->indexcolname = NULL;
+				iparam->collation = NIL;
+				iparam->opclass = NIL;
+				iparam->opclassopts = NIL;
+				iparam->ordering = SORTBY_DEFAULT;
+				iparam->nulls_ordering = SORTBY_NULLS_DEFAULT;
+				index->indexParams = lappend(index->indexParams, iparam);
+			}
+		}
+	}
+	else
+	{
+		/* create no index, just notice that an appropriate index is necessary for efficient IVM */
+		ereport(NOTICE,
+				(errmsg("could not create an index on materialized view \"%s\" automatically",
+						RelationGetRelationName(matviewRel)),
+				 errdetail("This target list does not have all the primary key columns. "),
+				 errhint("Create an index on the materialized view for efficient incremental maintenance.")));
+		return;
+	}
+
+	/* If we have a compatible index, we don't need to create another. */
+	foreach(indexoidscan, indexoidlist)
+	{
+		Oid			indexoid = lfirst_oid(indexoidscan);
+		Relation	indexRel;
+		bool		hasCompatibleIndex = false;
+
+		indexRel = index_open(indexoid, AccessShareLock);
+
+		if (CheckIndexCompatible(indexRel->rd_id,
+								index->accessMethod,
+								index->indexParams,
+								index->excludeOpNames,
+								false))
+			hasCompatibleIndex = true;
+
+		index_close(indexRel, AccessShareLock);
+
+		if (hasCompatibleIndex)
+			return;
+	}
+
+	address = DefineIndex(NULL,
+						  RelationGetRelid(matviewRel),
+						  index,
+						  InvalidOid,
+						  InvalidOid,
+						  InvalidOid,
+						  -1,
+						  false, true, false, false, true);
+
+	ereport(NOTICE,
+			(errmsg("created index \"%s\" on materialized view \"%s\"",
+					idxname, RelationGetRelationName(matviewRel))));
+
+	/*
+	 * Make dependencies so that the index is dropped if any base tables'
+	 * primary key is dropped.
+	 */
+	foreach(lc, constraintList)
+	{
+		Oid constraintOid = lfirst_oid(lc);
+		ObjectAddress	refaddr;
+
+		refaddr.classId = ConstraintRelationId;
+		refaddr.objectId = constraintOid;
+		refaddr.objectSubId = 0;
+
+		recordDependencyOn(&address, &refaddr, DEPENDENCY_NORMAL);
+	}
+}
+
+
+/*
+ * get_primary_key_attnos_from_query
+ *
+ * Identify the columns in base tables' primary keys in the target list.
+ *
+ * Returns a Bitmapset of the column attnos of the primary key's columns of
+ * tables that used in the query.  The attnos are offset by
+ * FirstLowInvalidHeapAttributeNumber as same as get_primary_key_attnos.
+ *
+ * If any table has no primary key or any primary key's columns is not in
+ * the target list, return NULL.  We also return NULL if any pkey constraint
+ * is deferrable.
+ *
+ * constraintList is set to a list of the OIDs of the pkey constraints.
+ */
+static Bitmapset *
+get_primary_key_attnos_from_query(Query *query, List **constraintList)
+{
+	List *key_attnos_list = NIL;
+	ListCell *lc;
+	int i;
+	Bitmapset *keys = NULL;
+	Relids	rels_in_from;
+
+	/*
+	 * Collect primary key attributes from all tables used in query. The key attributes
+	 * sets for each table are stored in key_attnos_list in order by RTE index.
+	 */
+	foreach(lc, query->rtable)
+	{
+		RangeTblEntry *r = (RangeTblEntry*) lfirst(lc);
+		Bitmapset *key_attnos;
+		bool	has_no_pkey = false;
+
+		/* for tables, call get_primary_key_attnos */
+		if (r->rtekind == RTE_RELATION)
+		{
+			Oid constraintOid;
+			key_attnos = get_primary_key_attnos(r->relid, false, &constraintOid);
+			*constraintList = lappend_oid(*constraintList, constraintOid);
+			has_no_pkey = (key_attnos == NULL);
+		}
+		/*
+		 * Ignore join rels, because they are flatten later by
+		 * flatten_join_alias_vars(). Store NULL into key_attnos_list
+		 * as a dummy.
+		 */
+		 else if (r->rtekind == RTE_JOIN)
+		 {
+			key_attnos = NULL;
+		}
+		/* for other RTEs, store NULL into key_attnos_list */
+		else
+			has_no_pkey = true;
+
+		/*
+		 * If any table or subquery has no primary key or its pkey constraint is deferrable,
+		 * we cannot get key attributes for this query, so return NULL.
+		 */
+		if (has_no_pkey)
+			return NULL;
+
+		key_attnos_list = lappend(key_attnos_list, key_attnos);
+	}
+
+	/* Collect key attributes appearing in the target list */
+	i = 1;
+	foreach(lc, query->targetList)
+	{
+		TargetEntry *tle = (TargetEntry *) flatten_join_alias_vars(NULL, query, lfirst(lc));
+
+		if (IsA(tle->expr, Var))
+		{
+			Var *var = (Var*) tle->expr;
+			Bitmapset *key_attnos = list_nth(key_attnos_list, var->varno - 1);
+
+			/* check if this attribute is from a base table's primary key */
+			if (bms_is_member(var->varattno - FirstLowInvalidHeapAttributeNumber, key_attnos))
+			{
+				/*
+				 * Remove found key attributes from key_attnos_list, and add this
+				 * to the result list.
+				 */
+				key_attnos = bms_del_member(key_attnos, var->varattno - FirstLowInvalidHeapAttributeNumber);
+				if (bms_is_empty(key_attnos))
+				{
+					key_attnos_list = list_delete_nth_cell(key_attnos_list, var->varno - 1);
+					key_attnos_list = list_insert_nth(key_attnos_list, var->varno - 1, NULL);
+				}
+				keys = bms_add_member(keys, i - FirstLowInvalidHeapAttributeNumber);
+			}
+		}
+		i++;
+	}
+
+	/* Collect RTE indexes of relations appearing in the FROM clause */
+	rels_in_from = get_relids_in_jointree((Node *) query->jointree, false, false);
+
+	/*
+	 * Check if all key attributes of relations in FROM are appearing in the target
+	 * list.  If an attribute remains in key_attnos_list in spite of the table is used
+	 * in FROM clause, the target is missing this key attribute, so we return NULL.
+	 */
+	i = 1;
+	foreach(lc, key_attnos_list)
+	{
+		Bitmapset *bms = (Bitmapset *)lfirst(lc);
+		if (!bms_is_empty(bms) && bms_is_member(i, rels_in_from))
+			return NULL;
+		i++;
+	}
+
+	return keys;
+}
diff --git a/src/backend/commands/matview.c b/src/backend/commands/matview.c
index f7d8007f796..eaf39f80cd3 100644
--- a/src/backend/commands/matview.c
+++ b/src/backend/commands/matview.c
@@ -23,24 +23,36 @@
 #include "catalog/indexing.h"
 #include "catalog/namespace.h"
 #include "catalog/pg_am.h"
+#include "catalog/pg_depend.h"
+#include "catalog/pg_trigger.h"
 #include "catalog/pg_opclass.h"
 #include "commands/matview.h"
 #include "commands/repack.h"
 #include "commands/tablecmds.h"
 #include "commands/tablespace.h"
+#include "commands/createas.h"
 #include "executor/executor.h"
 #include "executor/spi.h"
+#include "executor/tstoreReceiver.h"
 #include "miscadmin.h"
+#include "nodes/makefuncs.h"
+#include "parser/analyze.h"
+#include "parser/parse_clause.h"
+#include "parser/parse_func.h"
+#include "parser/parse_relation.h"
 #include "pgstat.h"
 #include "rewrite/rewriteHandler.h"
+#include "rewrite/rowsecurity.h"
 #include "storage/lmgr.h"
+#include "storage/lwlock.h"
 #include "tcop/tcopprot.h"
 #include "utils/builtins.h"
+#include "utils/fmgroids.h"
 #include "utils/lsyscache.h"
 #include "utils/rel.h"
 #include "utils/snapmgr.h"
 #include "utils/syscache.h"
-
+#include "utils/typcache.h"
 
 typedef struct
 {
@@ -53,6 +65,97 @@ typedef struct
 	BulkInsertState bistate;	/* bulk insert state */
 } DR_transientrel;
 
+#define MV_INIT_QUERYHASHSIZE	16
+
+/*
+ * MV_TriggerHashEntry
+ *
+ * Hash entry for base tables on which IVM trigger is invoked
+ */
+typedef struct MV_TriggerHashEntry
+{
+	Oid	matview_id;			/* OID of the materialized view */
+	int	before_trig_count;	/* count of before triggers invoked */
+	int	after_trig_count;	/* count of after triggers invoked */
+
+	Snapshot	snapshot;	/* Snapshot just before table change */
+
+	List   *tables;		/* List of MV_TriggerTable */
+	bool	has_old;	/* tuples are deleted from any table? */
+	bool	has_new;	/* tuples are inserted into any table? */
+
+	/*
+	 * List of sub-transaction IDs that incrementally updated the view.
+	 * This list is maintained through a transaction, and an ID is removed
+	 * when a sub-transaction is aborted. If any ID is left when the
+	 * transaction is committed, this means the view is incrementally
+	 * updated in this transaction.
+	 */
+	List   *subxids;
+} MV_TriggerHashEntry;
+
+/*
+ * MV_TriggerTable
+ *
+ * IVM related data for tables on which the trigger is invoked.
+ */
+typedef struct MV_TriggerTable
+{
+	Oid		table_id;			/* OID of the modified table */
+	List   *old_tuplestores;	/* tuplestores for deleted tuples */
+	List   *new_tuplestores;	/* tuplestores for inserted tuples */
+
+	List   *rte_indexes;		/* List of RTE index of the modified table */
+	RangeTblEntry *original_rte;	/* the original RTE saved before rewriting query */
+
+	Relation	rel;			/* relation of the modified table */
+	TupleTableSlot *slot;		/* for checking visibility in the pre-state table */
+} MV_TriggerTable;
+
+typedef struct DroppedImmvInfo
+{
+	Oid					immv_oid;
+	SubTransactionId	subxid;
+} DroppedImmvInfo;
+
+static HTAB *mv_trigger_info = NULL;
+static HTAB *dropped_immv = NULL;
+
+static HTAB *LastIvmUpdateHash;
+
+#define LAST_IVM_UPDATE_HASH_SIZE 256
+
+static void IvmShmemRequest(void *arg);
+
+/* hash table entries */
+typedef struct LastIvmUpdateEntry
+{
+	Oid		oid;	/* hash key */
+	FullTransactionId	last_ivm_update;
+} LastIvmUpdateEntry;
+
+const ShmemCallbacks IvmShmemCallbacks = {
+	.request_fn = IvmShmemRequest,
+};
+
+static void
+IvmShmemRequest(void *arg)
+{
+	ShmemRequestHash(.name = "LastIvmUpdate hash",
+					 .nelems = LAST_IVM_UPDATE_HASH_SIZE,
+					 .ptr = &LastIvmUpdateHash,
+					 .hash_info.keysize = sizeof(Oid),
+					 .hash_info.entrysize = sizeof(LastIvmUpdateEntry),
+					 .hash_flags = HASH_ELEM | HASH_BLOBS,
+		);
+}
+
+static bool in_delta_calculation = false;
+
+/* ENR name for materialized view delta */
+#define NEW_DELTA_ENRNAME "new_delta"
+#define OLD_DELTA_ENRNAME "old_delta"
+
 static int	matview_maintenance_depth = 0;
 
 static void transientrel_startup(DestReceiver *self, int operation, TupleDesc typeinfo);
@@ -60,6 +163,8 @@ static bool transientrel_receive(TupleTableSlot *slot, DestReceiver *self);
 static void transientrel_shutdown(DestReceiver *self);
 static void transientrel_destroy(DestReceiver *self);
 static uint64 refresh_matview_datafill(DestReceiver *dest, Query *query,
+									   QueryEnvironment *queryEnv,
+									   TupleDesc *resultTupleDesc,
 									   const char *queryString, bool is_create);
 static void refresh_by_match_merge(Oid matviewOid, Oid tempOid, Oid relowner,
 								   int save_sec_context);
@@ -67,6 +172,41 @@ static void refresh_by_heap_swap(Oid matviewOid, Oid OIDNewHeap, char relpersist
 static bool is_usable_unique_index(Relation indexRel);
 static void OpenMatViewIncrementalMaintenance(void);
 static void CloseMatViewIncrementalMaintenance(void);
+static Query *get_matview_query(Relation matviewRel);
+
+static Query *rewrite_query_for_preupdate_state(Query *query, List *tables,
+								  ParseState *pstate, Oid matviewid);
+static void register_delta_ENRs(ParseState *pstate, Query *query, List *tables);
+static char *make_subquery_targetlist_from_table(MV_TriggerTable *table);
+static char *make_delta_enr_name(const char *prefix, Oid relid, int count);
+static RangeTblEntry *get_prestate_rte(RangeTblEntry *rte, MV_TriggerTable *table,
+				 QueryEnvironment *queryEnv, Oid matviewid);
+static RangeTblEntry *makeDeltaTable(RangeTblEntry *rte, MV_TriggerTable *table,
+									 bool is_new, QueryEnvironment *queryEnv);
+static Query *rewrite_query_for_counting(Query *query, ParseState *pstate);
+
+static void calc_delta(MV_TriggerTable *table, int rte_index, Query *query,
+			DestReceiver *dest_old, DestReceiver *dest_new,
+			TupleDesc *tupdesc_old, TupleDesc *tupdesc_new,
+			QueryEnvironment *queryEnv);
+static Query *rewrite_query_for_postupdate_state(Query *query, MV_TriggerTable *table, int rte_index);
+
+static void apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *new_tuplestores,
+			TupleDesc tupdesc_old, TupleDesc tupdesc_new,
+			Query *query);
+static void apply_old_delta(const char *matviewname, const char *deltaname_old,
+				List *keys);
+static void apply_new_delta(const char *matviewname, const char *deltaname_new,
+				StringInfo target_list);
+static char *get_matching_condition_string(List *keys);
+static void generate_equal(StringInfo querybuf, Oid opttype,
+			   const char *leftop, const char *rightop);
+
+static void mv_InitHashTables(void);
+static void clean_up_IVM_hash_entry(MV_TriggerHashEntry *entry, bool is_abort,
+									SubTransactionId subxid);
+static void setLastUpdateXid(Oid immv_oid, FullTransactionId xid);
+static FullTransactionId getLastUpdateXid(Oid immv_oid);
 
 /*
  * SetMatViewPopulatedState
@@ -108,6 +248,46 @@ SetMatViewPopulatedState(Relation relation, bool newstate)
 	CommandCounterIncrement();
 }
 
+/*
+ * SetMatViewIVMState
+ *		Mark a materialized view as IVM, or not.
+ *
+ * NOTE: caller must be holding an appropriate lock on the relation.
+ */
+void
+SetMatViewIVMState(Relation relation, bool newstate)
+{
+	Relation	pgrel;
+	HeapTuple	tuple;
+
+	Assert(relation->rd_rel->relkind == RELKIND_MATVIEW);
+
+	/*
+	 * Update relation's pg_class entry.  Crucial side-effect: other backends
+	 * (and this one too!) are sent SI message to make them rebuild relcache
+	 * entries.
+	 */
+	pgrel = table_open(RelationRelationId, RowExclusiveLock);
+	tuple = SearchSysCacheCopy1(RELOID,
+								ObjectIdGetDatum(RelationGetRelid(relation)));
+	if (!HeapTupleIsValid(tuple))
+		elog(ERROR, "cache lookup failed for relation %u",
+			 RelationGetRelid(relation));
+
+	((Form_pg_class) GETSTRUCT(tuple))->relisivm = newstate;
+
+	CatalogTupleUpdate(pgrel, &tuple->t_self, tuple);
+
+	heap_freetuple(tuple);
+	table_close(pgrel, RowExclusiveLock);
+
+	/*
+	 * Advance command counter to make the updated pg_class row locally
+	 * visible.
+	 */
+	CommandCounterIncrement();
+}
+
 /*
  * ExecRefreshMatView -- execute a REFRESH MATERIALIZED VIEW command
  *
@@ -166,8 +346,6 @@ RefreshMatViewByOid(Oid matviewOid, bool is_create, bool skipData,
 					QueryCompletion *qc)
 {
 	Relation	matviewRel;
-	RewriteRule *rule;
-	List	   *actions;
 	Query	   *dataQuery;
 	Oid			tableSpace;
 	Oid			relowner;
@@ -178,6 +356,7 @@ RefreshMatViewByOid(Oid matviewOid, bool is_create, bool skipData,
 	int			save_sec_context;
 	int			save_nestlevel;
 	ObjectAddress address;
+	bool oldPopulated;
 
 	matviewRel = table_open(matviewOid, NoLock);
 	relowner = matviewRel->rd_rel->relowner;
@@ -193,6 +372,8 @@ RefreshMatViewByOid(Oid matviewOid, bool is_create, bool skipData,
 	save_nestlevel = NewGUCNestLevel();
 	RestrictSearchPath();
 
+	oldPopulated = RelationIsPopulated(matviewRel);
+
 	/* Make sure it is a materialized view. */
 	if (matviewRel->rd_rel->relkind != RELKIND_MATVIEW)
 		ereport(ERROR,
@@ -213,32 +394,7 @@ RefreshMatViewByOid(Oid matviewOid, bool is_create, bool skipData,
 				 errmsg("%s options %s and %s cannot be used together",
 						"REFRESH", "CONCURRENTLY", "WITH NO DATA")));
 
-	/*
-	 * Check that everything is correct for a refresh. Problems at this point
-	 * are internal errors, so elog is sufficient.
-	 */
-	if (matviewRel->rd_rel->relhasrules == false ||
-		matviewRel->rd_rules->numLocks < 1)
-		elog(ERROR,
-			 "materialized view \"%s\" is missing rewrite information",
-			 RelationGetRelationName(matviewRel));
-
-	if (matviewRel->rd_rules->numLocks > 1)
-		elog(ERROR,
-			 "materialized view \"%s\" has too many rules",
-			 RelationGetRelationName(matviewRel));
-
-	rule = matviewRel->rd_rules->rules[0];
-	if (rule->event != CMD_SELECT || !(rule->isInstead))
-		elog(ERROR,
-			 "the rule for materialized view \"%s\" is not a SELECT INSTEAD OF rule",
-			 RelationGetRelationName(matviewRel));
-
-	actions = rule->actions;
-	if (list_length(actions) != 1)
-		elog(ERROR,
-			 "the rule for materialized view \"%s\" is not a single action",
-			 RelationGetRelationName(matviewRel));
+	dataQuery = get_matview_query(matviewRel);
 
 	/*
 	 * Check that there is a unique index with no WHERE clause on one or more
@@ -275,12 +431,6 @@ RefreshMatViewByOid(Oid matviewOid, bool is_create, bool skipData,
 					 errhint("Create a unique index with no WHERE clause on one or more columns of the materialized view.")));
 	}
 
-	/*
-	 * The stored query was rewritten at the time of the MV definition, but
-	 * has not been scribbled on by the planner.
-	 */
-	dataQuery = linitial_node(Query, actions);
-
 	/*
 	 * Check for active uses of the relation in the current transaction, such
 	 * as open scans.
@@ -310,6 +460,90 @@ RefreshMatViewByOid(Oid matviewOid, bool is_create, bool skipData,
 		relpersistence = matviewRel->rd_rel->relpersistence;
 	}
 
+	/* delete IMMV triggers. */
+	if (RelationIsIVM(matviewRel) && skipData)
+	{
+		Relation	tgRel;
+		Relation	depRel;
+		ScanKeyData key;
+		SysScanDesc scan;
+		HeapTuple	tup;
+		ObjectAddresses *immv_triggers;
+
+		immv_triggers = new_object_addresses();
+
+		tgRel = table_open(TriggerRelationId, RowExclusiveLock);
+		depRel = table_open(DependRelationId, RowExclusiveLock);
+
+		/* search triggers that depends on IMMV. */
+		ScanKeyInit(&key,
+					Anum_pg_depend_refobjid,
+					BTEqualStrategyNumber, F_OIDEQ,
+					ObjectIdGetDatum(matviewOid));
+		scan = systable_beginscan(depRel, DependReferenceIndexId, true,
+								  NULL, 1, &key);
+		while ((tup = systable_getnext(scan)) != NULL)
+		{
+			ObjectAddress obj;
+			Form_pg_depend foundDep = (Form_pg_depend) GETSTRUCT(tup);
+
+			if (foundDep->classid == TriggerRelationId)
+			{
+				HeapTuple	tgtup;
+				ScanKeyData tgkey[1];
+				SysScanDesc tgscan;
+				Form_pg_trigger tgform;
+
+				/* Find the trigger name. */
+				ScanKeyInit(&tgkey[0],
+							Anum_pg_trigger_oid,
+							BTEqualStrategyNumber, F_OIDEQ,
+							ObjectIdGetDatum(foundDep->objid));
+
+				tgscan = systable_beginscan(tgRel, TriggerOidIndexId, true,
+											NULL, 1, tgkey);
+				tgtup = systable_getnext(tgscan);
+				if (!HeapTupleIsValid(tgtup))
+					elog(ERROR, "could not find tuple for immv trigger %u", foundDep->objid);
+
+				tgform = (Form_pg_trigger) GETSTRUCT(tgtup);
+
+				/* If trigger is created by IMMV, delete it. */
+				if (strncmp(NameStr(tgform->tgname), "IVM_trigger_", 12) == 0)
+				{
+					obj.classId = foundDep->classid;
+					obj.objectId = foundDep->objid;
+					obj.objectSubId = foundDep->refobjsubid;
+					add_exact_object_address(&obj, immv_triggers);
+				}
+				systable_endscan(tgscan);
+			}
+		}
+		systable_endscan(scan);
+
+		performMultipleDeletions(immv_triggers, DROP_RESTRICT, PERFORM_DELETION_INTERNAL);
+
+		table_close(depRel, RowExclusiveLock);
+		table_close(tgRel, RowExclusiveLock);
+		free_object_addresses(immv_triggers);
+	}
+
+	/*
+	 * Create triggers on incremental maintainable materialized view
+	 * This argument should use 'dataQuery'. This needs to use a rewritten query,
+	 * because a sublink in jointree is not supported by this function.
+	 *
+	 * This is performed before generating data because we have to wait
+	 * concurrent transactions modifying a base table and then take a snapshot
+	 * to see changes by these transactions to make sure a consistent view
+	 * is created.
+	 */
+	if (RelationIsIVM(matviewRel) && !skipData && !oldPopulated)
+	{
+		CreateIvmTriggersOnBaseTables(dataQuery, matviewOid);
+		CreateIndexOnIMMV(dataQuery, matviewRel);
+	}
+
 	/*
 	 * Create the transient table that will receive the regenerated data. Lock
 	 * it against access by any other process until commit (by which time it
@@ -326,8 +560,43 @@ RefreshMatViewByOid(Oid matviewOid, bool is_create, bool skipData,
 		DestReceiver *dest;
 
 		dest = CreateTransientRelDestReceiver(OIDNewHeap);
-		processed = refresh_matview_datafill(dest, dataQuery, queryString,
-											 is_create);
+
+		if (RelationIsIVM(matviewRel))
+		{
+			/*
+			 * In READ COMMITTED, get and push the latest snapshot again to see the
+			 * results of concurrent transactions committed after the current
+			 * transaction started.
+			 */
+			if (!IsolationUsesXactSnapshot())
+				PushActiveSnapshot(GetTransactionSnapshot());
+
+			/*
+			 * If a concurrent transaction updated the view incrementally and was
+			 * committed before we acquired the lock, the results of refresh_immv could
+			 * be inconsistent. Therefore, we have to check the transaction ID of the
+			 * most recent update of the view, and if this was in progress at the
+			 * transaction start, raise an error to prevent anomalies.
+			 */
+			if (!is_create)
+			{
+				FullTransactionId xid;
+
+				xid = getLastUpdateXid(matviewOid);
+				if (XidInMVCCSnapshot(XidFromFullTransactionId(xid), GetActiveSnapshot()))
+					ereport(ERROR,
+							(errcode(ERRCODE_T_R_SERIALIZATION_FAILURE),
+							 errmsg("the materialized view is incrementally updated in concurrent transaction"),
+							 errhint("The transaction might succeed if retried.")));
+			}
+		}
+
+		processed = refresh_matview_datafill(dest, dataQuery, NULL, NULL,
+											 queryString, is_create);
+
+		/* Pop the original snapshot. */
+		if (RelationIsIVM(matviewRel) && !IsolationUsesXactSnapshot())
+			PopActiveSnapshot();
 	}
 
 	/* Make the matview match the newly generated data. */
@@ -402,6 +671,8 @@ RefreshMatViewByOid(Oid matviewOid, bool is_create, bool skipData,
  */
 static uint64
 refresh_matview_datafill(DestReceiver *dest, Query *query,
+						 QueryEnvironment *queryEnv,
+						 TupleDesc *resultTupleDesc,
 						 const char *queryString, bool is_create)
 {
 	List	   *rewritten;
@@ -439,7 +710,7 @@ refresh_matview_datafill(DestReceiver *dest, Query *query,
 	/* Create a QueryDesc, redirecting output to our tuple receiver */
 	queryDesc = CreateQueryDesc(plan, queryString,
 								GetActiveSnapshot(), InvalidSnapshot,
-								dest, NULL, NULL, 0);
+								dest, NULL, queryEnv ? queryEnv: NULL, 0);
 
 	/* call ExecutorStart to prepare the plan for execution */
 	ExecutorStart(queryDesc, 0);
@@ -449,6 +720,9 @@ refresh_matview_datafill(DestReceiver *dest, Query *query,
 
 	processed = queryDesc->estate->es_processed;
 
+	if (resultTupleDesc)
+		*resultTupleDesc = CreateTupleDescCopy(queryDesc->tupDesc);
+
 	/* and clean up */
 	ExecutorFinish(queryDesc);
 	ExecutorEnd(queryDesc);
@@ -967,3 +1241,1488 @@ CloseMatViewIncrementalMaintenance(void)
 	matview_maintenance_depth--;
 	Assert(matview_maintenance_depth >= 0);
 }
+
+/*
+ * get_matview_query - get the Query from a matview's _RETURN rule.
+ */
+static Query *
+get_matview_query(Relation matviewRel)
+{
+	RewriteRule *rule;
+	List * actions;
+
+	/*
+	 * Check that everything is correct for a refresh. Problems at this point
+	 * are internal errors, so elog is sufficient.
+	 */
+	if (matviewRel->rd_rel->relhasrules == false ||
+		matviewRel->rd_rules->numLocks < 1)
+		elog(ERROR,
+			 "materialized view \"%s\" is missing rewrite information",
+			 RelationGetRelationName(matviewRel));
+
+	if (matviewRel->rd_rules->numLocks > 1)
+		elog(ERROR,
+			 "materialized view \"%s\" has too many rules",
+			 RelationGetRelationName(matviewRel));
+
+	rule = matviewRel->rd_rules->rules[0];
+	if (rule->event != CMD_SELECT || !(rule->isInstead))
+		elog(ERROR,
+			 "the rule for materialized view \"%s\" is not a SELECT INSTEAD OF rule",
+			 RelationGetRelationName(matviewRel));
+
+	actions = rule->actions;
+	if (list_length(actions) != 1)
+		elog(ERROR,
+			 "the rule for materialized view \"%s\" is not a single action",
+			 RelationGetRelationName(matviewRel));
+
+	/*
+	 * The stored query was rewritten at the time of the MV definition, but
+	 * has not been scribbled on by the planner.
+	 */
+	return linitial_node(Query, actions);
+}
+
+
+/* ----------------------------------------------------
+ *		Incremental View Maintenance routines
+ * ---------------------------------------------------
+ */
+
+/*
+ * IVM_immediate_before
+ *
+ * IVM trigger function invoked before base table is modified. If this is
+ * invoked firstly in the same statement, we save the transaction id and the
+ * command id at that time.
+ */
+Datum
+IVM_immediate_before(PG_FUNCTION_ARGS)
+{
+	TriggerData *trigdata = (TriggerData *) fcinfo->context;
+	char	   *matviewOid_text = trigdata->tg_trigger->tgargs[0];
+	char	   *ex_lock_text = trigdata->tg_trigger->tgargs[1];
+	Oid			matviewOid;
+	MV_TriggerHashEntry *entry;
+	bool	found;
+	bool	ex_lock;
+
+	matviewOid = DatumGetObjectId(DirectFunctionCall1(oidin, CStringGetDatum(matviewOid_text)));
+	ex_lock = DatumGetBool(DirectFunctionCall1(boolin, CStringGetDatum(ex_lock_text)));
+
+	/* If the view has more than one tables, we have to use an exclusive lock. */
+	if (ex_lock)
+	{
+		FullTransactionId xid;
+
+		/*
+		 * Wait for concurrent transactions which update this materialized view at
+		 * READ COMMITED. This is needed to see changes committed in other
+		 * transactions. No wait and raise an error at REPEATABLE READ or
+		 * SERIALIZABLE to prevent update anomalies of matviews.
+		 * XXX: dead-lock is possible here.
+		 */
+		if (!IsolationUsesXactSnapshot())
+			LockRelationOid(matviewOid, ExclusiveLock);
+		else if (!ConditionalLockRelationOid(matviewOid, ExclusiveLock))
+		{
+			/* try to throw error by name; relation could be deleted... */
+			char	   *relname = get_rel_name(matviewOid);
+
+			if (!relname)
+				ereport(ERROR,
+						(errcode(ERRCODE_LOCK_NOT_AVAILABLE),
+						errmsg("could not obtain lock on materialized view during incremental maintenance")));
+
+			ereport(ERROR,
+					(errcode(ERRCODE_LOCK_NOT_AVAILABLE),
+					errmsg("could not obtain lock on materialized view \"%s\" during incremental maintenance",
+							relname)));
+		}
+
+		/*
+		 * Even if we can acquire an lock, a concurrent transaction could have
+		 * updated the view incrementally and been committed before we acquired
+		 * the lock. Therefore, we have to check the transaction ID of the most
+		 * recent update of the view, and if this was in progress at the
+		 * transaction start, raise an error to prevent anomalies.
+		 */
+		xid = getLastUpdateXid(matviewOid);
+		if (XidInMVCCSnapshot(XidFromFullTransactionId(xid), GetTransactionSnapshot()))
+			ereport(ERROR,
+					(errcode(ERRCODE_T_R_SERIALIZATION_FAILURE),
+					 errmsg("the materialized view is incrementally updated in concurrent transaction"),
+					 errhint("The transaction might succeed if retried.")));
+	}
+	else
+		LockRelationOid(matviewOid, RowExclusiveLock);
+
+	/*
+	 * On the first call initialize the hashtable
+	 */
+	if (!mv_trigger_info)
+		mv_InitHashTables();
+
+	entry = (MV_TriggerHashEntry *) hash_search(mv_trigger_info,
+											  (void *) &matviewOid,
+											  HASH_ENTER, &found);
+
+	/* On the first BEFORE to update the view, initialize trigger data */
+	if (!found || entry->snapshot == InvalidSnapshot)
+	{
+		Snapshot snapshot;
+
+		/*
+		 * Get a snapshot just before the table was modified for checking
+		 * tuple visibility in the pre-update state of the table.
+		 *
+		 * In READ COMMITTED, use the latest snapshot again to see the
+		 * results of concurrent transactions committed after the current
+		 * transaction started.
+		 */
+		if (IsolationUsesXactSnapshot())
+			snapshot = GetActiveSnapshot();
+		else
+			snapshot = GetTransactionSnapshot();
+
+		entry->matview_id = matviewOid;
+		entry->before_trig_count = 0;
+		entry->after_trig_count = 0;
+		entry->snapshot = RegisterSnapshot(snapshot);
+		entry->tables = NIL;
+		entry->has_old = false;
+		entry->has_new = false;
+
+		/*
+		 * If this is the first table modifying query in the transaction,
+		 * initialize the list of subxids.
+		 */
+		if (!found)
+			entry->subxids = NIL;
+	}
+
+	entry->before_trig_count++;
+
+	return PointerGetDatum(NULL);
+}
+
+/*
+ * IVM_immediate_maintenance
+ *
+ * IVM trigger function invoked after base table is modified.
+ * For each table, tuplestores of transition tables are collected.
+ * and after the last modification
+ */
+Datum
+IVM_immediate_maintenance(PG_FUNCTION_ARGS)
+{
+	TriggerData *trigdata = (TriggerData *) fcinfo->context;
+	Relation	rel;
+	Oid			relid;
+	Oid			matviewOid;
+	Query	   *query;
+	Query	   *rewritten = NULL;
+	char	   *matviewOid_text = trigdata->tg_trigger->tgargs[0];
+	Relation	matviewRel;
+	int old_depth = matview_maintenance_depth;
+	SubTransactionId subxid;
+
+	Oid			relowner;
+	Tuplestorestate *old_tuplestore = NULL;
+	Tuplestorestate *new_tuplestore = NULL;
+	DestReceiver *dest_new = NULL, *dest_old = NULL;
+	Oid			save_userid;
+	int			save_sec_context;
+	int			save_nestlevel;
+
+	MV_TriggerHashEntry *entry;
+	MV_TriggerTable		*table;
+	bool	found;
+
+	ParseState		 *pstate;
+	QueryEnvironment *queryEnv = create_queryEnv();
+	MemoryContext	oldcxt;
+	ListCell   *lc;
+	int			i;
+
+
+	/* Create a ParseState for rewriting the view definition query */
+	pstate = make_parsestate(NULL);
+	pstate->p_queryEnv = queryEnv;
+	pstate->p_expr_kind = EXPR_KIND_SELECT_TARGET;
+
+	rel = trigdata->tg_relation;
+	relid = rel->rd_id;
+
+	matviewOid = DatumGetObjectId(DirectFunctionCall1(oidin, CStringGetDatum(matviewOid_text)));
+
+	/*
+	 * On the first call initialize the hashtable
+	 */
+	if (!mv_trigger_info)
+		mv_InitHashTables();
+
+	/* get the entry for this materialized view */
+	entry = (MV_TriggerHashEntry *) hash_search(mv_trigger_info,
+											  (void *) &matviewOid,
+											  HASH_FIND, &found);
+	Assert (found && entry != NULL);
+	entry->after_trig_count++;
+
+	/* search the entry for the modified table and create new entry if not found */
+	found = false;
+	foreach(lc, entry->tables)
+	{
+		table = (MV_TriggerTable *) lfirst(lc);
+		if (table->table_id == relid)
+		{
+			found = true;
+			break;
+		}
+	}
+	if (!found)
+	{
+		oldcxt = MemoryContextSwitchTo(TopTransactionContext);
+
+		table = (MV_TriggerTable *) palloc0(sizeof(MV_TriggerTable));
+		table->table_id = relid;
+		table->old_tuplestores = NIL;
+		table->new_tuplestores = NIL;
+		table->rte_indexes = NIL;
+		table->slot = MakeSingleTupleTableSlot(RelationGetDescr(rel), table_slot_callbacks(rel));
+		/* We assume we have at least RowExclusiveLock on modified tables. */
+		table->rel = table_open(RelationGetRelid(rel), NoLock);
+		entry->tables = lappend(entry->tables, table);
+
+		MemoryContextSwitchTo(oldcxt);
+	}
+
+	/* Save the transition tables and make a request to not free immediately */
+	if (trigdata->tg_oldtable)
+	{
+		oldcxt = MemoryContextSwitchTo(TopTransactionContext);
+		table->old_tuplestores = lappend(table->old_tuplestores, trigdata->tg_oldtable);
+		entry->has_old = true;
+		MemoryContextSwitchTo(oldcxt);
+	}
+	if (trigdata->tg_newtable)
+	{
+		oldcxt = MemoryContextSwitchTo(TopTransactionContext);
+		table->new_tuplestores = lappend(table->new_tuplestores, trigdata->tg_newtable);
+		entry->has_new = true;
+		MemoryContextSwitchTo(oldcxt);
+	}
+	if (entry->has_new || entry->has_old)
+	{
+		CmdType cmd;
+
+		if (TRIGGER_FIRED_BY_INSERT(trigdata->tg_event))
+			cmd = CMD_INSERT;
+		else if (TRIGGER_FIRED_BY_DELETE(trigdata->tg_event))
+			cmd = CMD_DELETE;
+		else if (TRIGGER_FIRED_BY_UPDATE(trigdata->tg_event))
+			cmd = CMD_UPDATE;
+		else
+			elog(ERROR,"unsupported trigger type");
+
+		/* Prolong lifespan of transition tables to the end of the last AFTER trigger */
+		SetTransitionTablePreserved(relid, cmd);
+	}
+
+
+	/* If this is not the last AFTER trigger call, immediately exit. */
+	Assert (entry->before_trig_count >= entry->after_trig_count);
+	if (entry->before_trig_count != entry->after_trig_count)
+		return PointerGetDatum(NULL);
+
+	/*
+	 * If this is the last AFTER trigger call, continue and update the view.
+	 */
+
+	/* record the subxid that updated the view incrementally */
+	subxid = GetCurrentSubTransactionId();
+	if (!list_member_xid(entry->subxids, subxid))
+	{
+		oldcxt = MemoryContextSwitchTo(TopTransactionContext);
+		entry->subxids = lappend_xid(entry->subxids, subxid);
+		MemoryContextSwitchTo(oldcxt);
+	}
+
+	/*
+	 * Advance command counter to make the updated base table rows locally
+	 * visible.
+	 */
+	CommandCounterIncrement();
+
+	matviewRel = table_open(matviewOid, NoLock);
+
+	/* Make sure it is a materialized view. */
+	Assert(matviewRel->rd_rel->relkind == RELKIND_MATVIEW);
+
+	/*
+	 * In READ COMMITTED, get and push the latest snapshot again to see the
+	 * results of concurrent transactions committed after the current
+	 * transaction started.
+	 */
+	if (!IsolationUsesXactSnapshot())
+		PushActiveSnapshot(GetTransactionSnapshot());
+
+	/*
+	 * Check for active uses of the relation in the current transaction, such
+	 * as open scans.
+	 *
+	 * NB: We count on this to protect us against problems with refreshing the
+	 * data using TABLE_INSERT_FROZEN.
+	 */
+	CheckTableNotInUse(matviewRel, "refresh a materialized view incrementally");
+
+	/*
+	 * Switch to the owner's userid, so that any functions are run as that
+	 * user.  Also arrange to make GUC variable changes local to this command.
+	 * We will switch modes when we are about to execute user code.
+	 */
+	relowner = matviewRel->rd_rel->relowner;
+	GetUserIdAndSecContext(&save_userid, &save_sec_context);
+	SetUserIdAndSecContext(relowner,
+						   save_sec_context | SECURITY_RESTRICTED_OPERATION);
+	save_nestlevel = NewGUCNestLevel();
+
+	/* get view query*/
+	query = get_matview_query(matviewRel);
+
+	/*
+	 * When a base table is truncated, the view content will be empty if the
+	 * view definition query does not contain an aggregate without a GROUP clause.
+	 * Therefore, such views can be truncated.
+	 */
+	if (TRIGGER_FIRED_BY_TRUNCATE(trigdata->tg_event))
+	{
+		ExecuteTruncateGuts(list_make1(matviewRel), list_make1_oid(matviewOid),
+							NIL, DROP_RESTRICT, false, false);
+
+		/* Clean up hash entry and delete tuplestores */
+		clean_up_IVM_hash_entry(entry, false, InvalidSubTransactionId);
+
+		/* Pop the original snapshot. */
+		if (!IsolationUsesXactSnapshot())
+			PopActiveSnapshot();
+
+		table_close(matviewRel, NoLock);
+
+		/* Roll back any GUC changes */
+		AtEOXact_GUC(false, save_nestlevel);
+
+		/* Restore userid and security context */
+		SetUserIdAndSecContext(save_userid, save_sec_context);
+
+		return PointerGetDatum(NULL);
+	}
+
+	/*
+	 * rewrite query for calculating deltas
+	 */
+
+	rewritten = copyObject(query);
+
+	/* Replace resnames in a target list with materialized view's attnames */
+	i = 0;
+	foreach (lc, rewritten->targetList)
+	{
+		TargetEntry *tle = (TargetEntry *) lfirst(lc);
+		Form_pg_attribute attr = TupleDescAttr(matviewRel->rd_att, i);
+		char *resname = NameStr(attr->attname);
+
+		tle->resname = pstrdup(resname);
+		i++;
+	}
+
+	/* Set all tables in the query to pre-update state */
+	rewritten = rewrite_query_for_preupdate_state(rewritten, entry->tables,
+												  pstate, matviewOid);
+	/* Rewrite for counting duplicated tuples */
+	rewritten = rewrite_query_for_counting(rewritten, pstate);
+
+	/* Create tuplestores to store view deltas */
+	if (entry->has_old)
+	{
+		oldcxt = MemoryContextSwitchTo(TopTransactionContext);
+
+		old_tuplestore = tuplestore_begin_heap(false, false, work_mem);
+		dest_old = CreateDestReceiver(DestTuplestore);
+		SetTuplestoreDestReceiverParams(dest_old,
+									old_tuplestore,
+									TopTransactionContext,
+									false,
+									NULL,
+									NULL);
+
+		MemoryContextSwitchTo(oldcxt);
+	}
+	if (entry->has_new)
+	{
+		oldcxt = MemoryContextSwitchTo(TopTransactionContext);
+
+		new_tuplestore = tuplestore_begin_heap(false, false, work_mem);
+		dest_new = CreateDestReceiver(DestTuplestore);
+		SetTuplestoreDestReceiverParams(dest_new,
+									new_tuplestore,
+									TopTransactionContext,
+									false,
+									NULL,
+									NULL);
+		MemoryContextSwitchTo(oldcxt);
+	}
+
+	/* for all modified tables */
+	foreach(lc, entry->tables)
+	{
+		ListCell *lc2;
+
+		table = (MV_TriggerTable *) lfirst(lc);
+
+		/* loop for self-join */
+		foreach(lc2, table->rte_indexes)
+		{
+			int	rte_index = lfirst_int(lc2);
+			TupleDesc		tupdesc_old;
+			TupleDesc		tupdesc_new;
+
+			/* calculate delta tables */
+			calc_delta(table, rte_index, rewritten, dest_old, dest_new,
+					   &tupdesc_old, &tupdesc_new, queryEnv);
+
+			/* Set the table in the query to post-update state */
+			rewritten = rewrite_query_for_postupdate_state(rewritten, table, rte_index);
+
+			PG_TRY();
+			{
+				/* apply the delta tables to the materialized view */
+				apply_delta(matviewOid, old_tuplestore, new_tuplestore,
+							tupdesc_old, tupdesc_new, query);
+			}
+			PG_CATCH();
+			{
+				matview_maintenance_depth = old_depth;
+				PG_RE_THROW();
+			}
+			PG_END_TRY();
+
+			/* clear view delta tuplestores */
+			if (old_tuplestore)
+				tuplestore_clear(old_tuplestore);
+			if (new_tuplestore)
+				tuplestore_clear(new_tuplestore);
+		}
+	}
+
+	/* Clean up hash entry and delete tuplestores */
+	clean_up_IVM_hash_entry(entry, false, InvalidSubTransactionId);
+	if (old_tuplestore)
+	{
+		dest_old->rDestroy(dest_old);
+		tuplestore_end(old_tuplestore);
+	}
+	if (new_tuplestore)
+	{
+		dest_new->rDestroy(dest_new);
+		tuplestore_end(new_tuplestore);
+	}
+
+	/* Pop the original snapshot. */
+	if (!IsolationUsesXactSnapshot())
+		PopActiveSnapshot();
+
+	table_close(matviewRel, NoLock);
+
+	/* Roll back any GUC changes */
+	AtEOXact_GUC(false, save_nestlevel);
+
+	/* Restore userid and security context */
+	SetUserIdAndSecContext(save_userid, save_sec_context);
+
+	return PointerGetDatum(NULL);
+}
+
+/*
+ * rewrite_query_for_preupdate_state
+ *
+ * Rewrite the query so that base tables' RTEs will represent "pre-update"
+ * state of tables. This is necessary to calculate view delta after multiple
+ * tables are modified.
+ */
+static Query*
+rewrite_query_for_preupdate_state(Query *query, List *tables,
+								  ParseState *pstate, Oid matviewid)
+{
+	ListCell *lc;
+	int num_rte = list_length(query->rtable);
+	int i;
+
+
+	/* register delta ENRs */
+	register_delta_ENRs(pstate, query, tables);
+
+	/* XXX: Is necessary? Is this right timing? */
+	AcquireRewriteLocks(query, true, false);
+
+	i = 1;
+	foreach(lc, query->rtable)
+	{
+		RangeTblEntry *r = (RangeTblEntry*) lfirst(lc);
+
+		ListCell *lc2;
+		foreach(lc2, tables)
+		{
+			MV_TriggerTable *table = (MV_TriggerTable *) lfirst(lc2);
+			/*
+			 * if the modified table is found then replace the original RTE with
+			 * "pre-state" RTE and append its index to the list.
+			 */
+			if (r->relid == table->table_id)
+			{
+				List *securityQuals;
+				List *withCheckOptions;
+				bool  hasRowSecurity;
+				bool  hasSubLinks;
+
+				RangeTblEntry *rte_pre = get_prestate_rte(r, table, pstate->p_queryEnv, matviewid);
+
+				/*
+				 * Set a row security poslicies of the modified table to the subquery RTE which
+				 * represents the pre-update state of the table.
+				 */
+				get_row_security_policies(query, table->original_rte, i,
+										  &securityQuals, &withCheckOptions,
+										  &hasRowSecurity, &hasSubLinks);
+
+				if (hasRowSecurity)
+				{
+					query->hasRowSecurity = true;
+					rte_pre->security_barrier = true;
+				}
+				if (hasSubLinks)
+					query->hasSubLinks = true;
+
+				rte_pre->securityQuals = securityQuals;
+				lfirst(lc) = rte_pre;
+
+				table->rte_indexes = lappend_int(table->rte_indexes, i);
+				break;
+			}
+		}
+
+		/* finish the loop if we processed all RTE included in the original query */
+		if (i++ >= num_rte)
+			break;
+	}
+
+	return query;
+}
+
+/*
+ * register_delta_ENRs
+ *
+ * For all modified tables, make ENRs for their transition tables
+ * and register them to the queryEnv. ENR's RTEs are also appended
+ * into the list in query tree.
+ */
+static void
+register_delta_ENRs(ParseState *pstate, Query *query, List *tables)
+{
+	QueryEnvironment *queryEnv = pstate->p_queryEnv;
+	ListCell *lc;
+	RangeTblEntry	*rte;
+
+	foreach(lc, tables)
+	{
+		MV_TriggerTable *table = (MV_TriggerTable *) lfirst(lc);
+		ListCell *lc2;
+		int count;
+
+		count = 0;
+		foreach(lc2, table->old_tuplestores)
+		{
+			Tuplestorestate *oldtable = (Tuplestorestate *) lfirst(lc2);
+			EphemeralNamedRelation enr =
+				palloc(sizeof(EphemeralNamedRelationData));
+			ParseNamespaceItem *nsitem;
+
+			enr->md.name = make_delta_enr_name("old", table->table_id, count);
+			enr->md.reliddesc = table->table_id;
+			enr->md.tupdesc = NULL;
+			enr->md.enrtype = ENR_NAMED_TUPLESTORE;
+			enr->md.enrtuples = tuplestore_tuple_count(oldtable);
+			enr->reldata = oldtable;
+			register_ENR(queryEnv, enr);
+
+			nsitem = addRangeTableEntryForENR(pstate, makeRangeVar(NULL, enr->md.name, -1), true);
+			rte = nsitem->p_rte;
+
+			query->rtable = lappend(query->rtable, rte);
+
+			count++;
+		}
+
+		count = 0;
+		foreach(lc2, table->new_tuplestores)
+		{
+			Tuplestorestate *newtable = (Tuplestorestate *) lfirst(lc2);
+			EphemeralNamedRelation enr =
+				palloc(sizeof(EphemeralNamedRelationData));
+			ParseNamespaceItem *nsitem;
+
+			enr->md.name = make_delta_enr_name("new", table->table_id, count);
+			enr->md.reliddesc = table->table_id;
+			enr->md.tupdesc = NULL;
+			enr->md.enrtype = ENR_NAMED_TUPLESTORE;
+			enr->md.enrtuples = tuplestore_tuple_count(newtable);
+			enr->reldata = newtable;
+			register_ENR(queryEnv, enr);
+
+			nsitem = addRangeTableEntryForENR(pstate, makeRangeVar(NULL, enr->md.name, -1), true);
+			rte = nsitem->p_rte;
+
+			query->rtable = lappend(query->rtable, rte);
+
+			count++;
+		}
+	}
+}
+
+#define DatumGetItemPointer(X)	 ((ItemPointer) DatumGetPointer(X))
+#define PG_GETARG_ITEMPOINTER(n) DatumGetItemPointer(PG_GETARG_DATUM(n))
+
+/*
+ * ivm_visible_in_prestate
+ *
+ * Check visibility of a tuple specified by the tableoid and item pointer
+ * using the snapshot taken just before the table was modified.
+ */
+Datum
+ivm_visible_in_prestate(PG_FUNCTION_ARGS)
+{
+	Oid			tableoid = PG_GETARG_OID(0);
+	ItemPointer itemPtr = PG_GETARG_ITEMPOINTER(1);
+	Oid			matviewOid = PG_GETARG_OID(2);
+	MV_TriggerHashEntry *entry;
+	MV_TriggerTable		*table = NULL;
+	ListCell   *lc;
+	bool	found;
+	bool	result;
+
+	if (!in_delta_calculation)
+		ereport(ERROR,
+				(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+				 errmsg("ivm_visible_in_prestate can be called only in delta calculation")));
+
+	entry = (MV_TriggerHashEntry *) hash_search(mv_trigger_info,
+											  (void *) &matviewOid,
+											  HASH_FIND, &found);
+	Assert (found && entry != NULL);
+
+	foreach(lc, entry->tables)
+	{
+		table = (MV_TriggerTable *) lfirst(lc);
+		if (table->table_id == tableoid)
+			break;
+	}
+
+	Assert (table != NULL);
+
+	result = table_tuple_fetch_row_version(table->rel, itemPtr, entry->snapshot, table->slot);
+
+	PG_RETURN_BOOL(result);
+}
+
+/*
+ * get_prestate_rte
+ *
+ * Rewrite RTE of the modified table to a subquery which represents
+ * "pre-state" table. The original RTE is saved in table->rte_original.
+ */
+static RangeTblEntry*
+get_prestate_rte(RangeTblEntry *rte, MV_TriggerTable *table,
+				 QueryEnvironment *queryEnv, Oid matviewid)
+{
+	StringInfoData str;
+	RawStmt *raw;
+	Query *subquery;
+	ParseState *pstate;
+	char *relname;
+	static char *subquery_tl;
+	int i;
+
+	pstate = make_parsestate(NULL);
+	pstate->p_queryEnv = queryEnv;
+	pstate->p_expr_kind = EXPR_KIND_SELECT_TARGET;
+
+	relname = quote_qualified_identifier(
+					get_namespace_name(RelationGetNamespace(table->rel)),
+									   RelationGetRelationName(table->rel));
+
+	subquery_tl = make_subquery_targetlist_from_table(table);
+
+	/*
+	 * Filtering inserted row using the snapshot taken before the table
+	 * is modified. ctid is required for maintaining outer join views.
+	 */
+	initStringInfo(&str);
+	appendStringInfo(&str,
+		"SELECT %s FROM %s t"
+		" WHERE pg_catalog.ivm_visible_in_prestate(t.tableoid, t.ctid ,%d::pg_catalog.oid)",
+			subquery_tl, relname, matviewid);
+
+	/*
+	 * Re-add rows deleted from the old transition tables, excluding those
+	 * also present in the new transition tables.
+	 */
+	if (list_length(table->old_tuplestores) > 0)
+	{
+		appendStringInfo(&str," UNION ALL SELECT %s  FROM (",
+			subquery_tl);
+
+		for (i = 0; i < list_length(table->old_tuplestores); i++)
+		{
+			if (i != 0)
+				appendStringInfo(&str, " UNION ALL ");
+			appendStringInfo(&str," TABLE %s",
+				make_delta_enr_name("old", table->table_id, i));
+		}
+		for (i = 0; i < list_length(table->new_tuplestores); i++)
+		{
+			appendStringInfo(&str, " EXCEPT ALL ");
+			appendStringInfo(&str," TABLE %s",
+				make_delta_enr_name("new", table->table_id, i));
+		}
+		appendStringInfo(&str,")");
+	}
+
+	/* Get a subquery representing pre-state of the table */
+	raw = (RawStmt*)linitial(raw_parser(str.data, RAW_PARSE_DEFAULT));
+	subquery = transformStmt(pstate, raw->stmt);
+
+	/* save the original RTE */
+	table->original_rte = copyObject(rte);
+
+	rte->rtekind = RTE_SUBQUERY;
+	rte->subquery = subquery;
+	rte->security_barrier = false;
+
+	/* Clear fields that should not be set in a subquery RTE */
+	rte->relid = InvalidOid;
+	rte->relkind = 0;
+	rte->rellockmode = 0;
+	rte->tablesample = NULL;
+	rte->perminfoindex = 0;         /* no permission checking for this RTE */
+	rte->inh = false;			/* must not be set for a subquery */
+
+	return rte;
+}
+
+/*
+ * make_subquery_targetlist_from_table
+ *
+ * Make a targetlist string of a subquery representing a delta table or a
+ * pre-update state table. This subquery substitutes a modified table RTE
+ * in the view definition query during view maintenance. In the targetlist,
+ * column names appear in order of the table definition. However, for
+ * attribute numbers of vars in the query tree to reference columns of the
+ * subquery  correctly even though the table has a dropped column, put "null"
+ * as a dummy value at the position of a dropped column.
+ *
+ * We would also able to walk the query tree to rewrite varattnos, but
+ * crafting targetlist is more simple and reasonable.
+ */
+static char*
+make_subquery_targetlist_from_table(MV_TriggerTable *table)
+{
+	StringInfoData str;
+	TupleDesc	tupdesc;
+	int			i;
+
+	tupdesc = RelationGetDescr(table->rel);
+	initStringInfo(&str);
+	for (i = 0; i < tupdesc->natts; i++)
+	{
+		Form_pg_attribute attr = TupleDescAttr(tupdesc, i);
+
+		if (i > 0)
+			appendStringInfo(&str, ", ");
+
+		if (attr->attisdropped)
+			appendStringInfo(&str, "null");
+		else
+			appendStringInfo(&str, "%s", quote_identifier(NameStr(attr->attname)));
+	}
+
+	return str.data;
+}
+
+/*
+ * make_delta_enr_name
+ *
+ * Make a name for ENR of a transition table from the base table's oid.
+ * prefix will be "new" or "old" depending on its transition table kind..
+ */
+static char*
+make_delta_enr_name(const char *prefix, Oid relid, int count)
+{
+	char buf[NAMEDATALEN];
+	char *name;
+
+	snprintf(buf, NAMEDATALEN, "__ivm_%s_%u_%u", prefix, relid, count);
+	name = pstrdup(buf);
+
+	return name;
+}
+
+/*
+ * makeDeltaTable
+ *
+ * Make a RTE representing a delta of the specified table.
+ */
+static RangeTblEntry*
+makeDeltaTable(RangeTblEntry *rte, MV_TriggerTable *table,
+		   bool is_new, QueryEnvironment *queryEnv)
+{
+	StringInfoData str;
+	ParseState	*pstate;
+	RawStmt *raw;
+	Query *sub;
+	int		i;
+
+	const char *prefix_union = is_new ? "new" : "old";
+	const char *prefix_except = is_new ? "old" : "new";
+	int num_union = is_new ? list_length(table->new_tuplestores) : list_length(table->old_tuplestores);
+	int num_except = is_new ? list_length(table->old_tuplestores) : list_length(table->new_tuplestores);
+
+	/* the previous RTE must be a subquery which represents "pre-state" table */
+	Assert(rte->rtekind == RTE_SUBQUERY);
+
+	/* Create a ParseState for rewriting the view definition query */
+	pstate = make_parsestate(NULL);
+	pstate->p_queryEnv = queryEnv;
+	pstate->p_expr_kind = EXPR_KIND_NONE;
+
+	initStringInfo(&str);
+	appendStringInfo(&str,
+		" SELECT %s FROM ( ",
+		make_subquery_targetlist_from_table(table));
+
+	for (i = 0; i < num_union; i++)
+	{
+		if (i > 0)
+			appendStringInfo(&str, " UNION ALL ");
+
+		appendStringInfo(&str,
+			" TABLE  %s",
+			make_delta_enr_name(prefix_union, table->table_id, i));
+	}
+	for (i = 0; i < num_except; i++)
+	{
+		appendStringInfo(&str, " EXCEPT ALL ");
+
+		appendStringInfo(&str,
+			" TABLE  %s",
+			make_delta_enr_name(prefix_except, table->table_id, i));
+	}
+	appendStringInfo(&str,")");
+
+	raw = (RawStmt*)linitial(raw_parser(str.data, RAW_PARSE_DEFAULT));
+	sub = transformStmt(pstate, raw->stmt);
+
+	/*
+	 * Update the subquery so that it represent the combined transition
+	 * table.  Note that we leave the security_barrier and securityQuals
+	 * fields so that the subquery relation can be protected by the RLS
+	 * policy as same as the modified table.
+	 */
+	rte->rtekind = RTE_SUBQUERY;
+	rte->subquery = sub;
+
+	return rte;
+}
+
+/*
+ * rewrite_query_for_counting
+ *
+ * Rewrite query for counting duplicated tuples.
+ */
+static Query *
+rewrite_query_for_counting(Query *query, ParseState *pstate)
+{
+	TargetEntry *tle_count;
+	FuncCall *fn;
+	Node *node;
+
+	/* Add count(*) for counting distinct tuples in views */
+	fn = makeFuncCall(SystemFuncName("count"), NIL, COERCE_EXPLICIT_CALL, -1);
+	fn->agg_star = true;
+	if (!query->groupClause && !query->hasAggs)
+		query->groupClause = transformDistinctClause(NULL, &query->targetList, query->sortClause, false);
+
+	node = ParseFuncOrColumn(pstate, fn->funcname, NIL, NULL, fn, false, -1);
+
+	tle_count = makeTargetEntry((Expr *) node,
+								list_length(query->targetList) + 1,
+								pstrdup("__ivm_count__"),
+								false);
+	query->targetList = lappend(query->targetList, tle_count);
+	query->hasAggs = true;
+
+	return query;
+}
+
+/*
+ * calc_delta
+ *
+ * Calculate view deltas generated under the modification of a table specified
+ * by the RTE index.
+ */
+static void
+calc_delta(MV_TriggerTable *table, int rte_index, Query *query,
+			DestReceiver *dest_old, DestReceiver *dest_new,
+			TupleDesc *tupdesc_old, TupleDesc *tupdesc_new,
+			QueryEnvironment *queryEnv)
+{
+	ListCell *lc = list_nth_cell(query->rtable, rte_index - 1);
+	RangeTblEntry *rte = (RangeTblEntry *) lfirst(lc);
+
+	in_delta_calculation = true;
+
+	/* Generate old delta */
+	if (dest_old && list_length(table->old_tuplestores) > 0)
+	{
+		/* Replace the modified table with the old delta table and calculate the old view delta. */
+		lfirst(lc) = makeDeltaTable(rte, table, false, queryEnv);
+		refresh_matview_datafill(dest_old, query, queryEnv, tupdesc_old, "", false);
+	}
+
+	/* Generate new delta */
+	if (dest_new && list_length(table->new_tuplestores) > 0)
+	{
+		/* Replace the modified table with the new delta table and calculate the new view delta*/
+		lfirst(lc) = makeDeltaTable(rte, table, true, queryEnv);
+		refresh_matview_datafill(dest_new, query, queryEnv, tupdesc_new, "", false);
+	}
+
+	in_delta_calculation = false;
+}
+
+/*
+ * rewrite_query_for_postupdate_state
+ *
+ * Rewrite the query so that the specified base table's RTEs will represent
+ * "post-update" state of tables. This is called after the view delta
+ * calculation due to changes on this table finishes.
+ */
+static Query*
+rewrite_query_for_postupdate_state(Query *query, MV_TriggerTable *table, int rte_index)
+{
+	ListCell *lc = list_nth_cell(query->rtable, rte_index - 1);
+
+	/* Retore the original RTE */
+	lfirst(lc) = table->original_rte;
+
+	return query;
+}
+
+/*
+ * apply_delta
+ *
+ * Apply deltas to the materialized view. In outer join cases, this requires
+ * the view maintenance graph.
+ */
+static void
+apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *new_tuplestores,
+			TupleDesc tupdesc_old, TupleDesc tupdesc_new,
+			Query *query)
+{
+	StringInfoData querybuf;
+	StringInfoData target_list_buf;
+	Relation	matviewRel;
+	char	   *matviewname;
+	ListCell	*lc;
+	int			i;
+	List	   *keys = NIL;
+
+
+	/*
+	 * get names of the materialized view and delta tables
+	 */
+
+	matviewRel = table_open(matviewOid, NoLock);
+	matviewname = quote_qualified_identifier(get_namespace_name(RelationGetNamespace(matviewRel)),
+											 RelationGetRelationName(matviewRel));
+
+	/*
+	 * Build parts of the maintenance queries
+	 */
+
+	initStringInfo(&querybuf);
+	initStringInfo(&target_list_buf);
+
+	/* build string of target list */
+	for (i = 0; i < matviewRel->rd_att->natts; i++)
+	{
+		Form_pg_attribute attr = TupleDescAttr(matviewRel->rd_att, i);
+		char   *resname = NameStr(attr->attname);
+
+		if (i != 0)
+			appendStringInfo(&target_list_buf, ", ");
+		appendStringInfo(&target_list_buf, "%s", quote_qualified_identifier(NULL, resname));
+	}
+
+	i = 0;
+	foreach (lc, query->targetList)
+	{
+		TargetEntry *tle = (TargetEntry *) lfirst(lc);
+		Form_pg_attribute attr = TupleDescAttr(matviewRel->rd_att, i);
+
+		i++;
+
+		if (tle->resjunk)
+			continue;
+
+		keys = lappend(keys, attr);
+	}
+
+	/* Start maintaining the materialized view. */
+	OpenMatViewIncrementalMaintenance();
+
+	/* Open SPI context. */
+	if (SPI_connect() != SPI_OK_CONNECT)
+		elog(ERROR, "SPI_connect failed");
+
+	/* For tuple deletion */
+	if (old_tuplestores && tuplestore_tuple_count(old_tuplestores) > 0)
+	{
+		EphemeralNamedRelation enr = palloc(sizeof(EphemeralNamedRelationData));
+		int				rc;
+
+		/* convert tuplestores to ENR, and register for SPI */
+		enr->md.name = pstrdup(OLD_DELTA_ENRNAME);
+		enr->md.reliddesc = InvalidOid;
+		enr->md.tupdesc = tupdesc_old;
+		enr->md.enrtype = ENR_NAMED_TUPLESTORE;
+		enr->md.enrtuples = tuplestore_tuple_count(old_tuplestores);
+		enr->reldata = old_tuplestores;
+
+		rc = SPI_register_relation(enr);
+		if (rc != SPI_OK_REL_REGISTER)
+			elog(ERROR, "SPI_register failed");
+
+		apply_old_delta(matviewname, OLD_DELTA_ENRNAME, keys);
+
+	}
+	/* For tuple insertion */
+	if (new_tuplestores && tuplestore_tuple_count(new_tuplestores) > 0)
+	{
+		EphemeralNamedRelation enr = palloc(sizeof(EphemeralNamedRelationData));
+		int rc;
+
+		/* convert tuplestores to ENR, and register for SPI */
+		enr->md.name = pstrdup(NEW_DELTA_ENRNAME);
+		enr->md.reliddesc = InvalidOid;
+		enr->md.tupdesc = tupdesc_new;;
+		enr->md.enrtype = ENR_NAMED_TUPLESTORE;
+		enr->md.enrtuples = tuplestore_tuple_count(new_tuplestores);
+		enr->reldata = new_tuplestores;
+
+		rc = SPI_register_relation(enr);
+		if (rc != SPI_OK_REL_REGISTER)
+			elog(ERROR, "SPI_register failed");
+
+		/* apply new delta */
+		apply_new_delta(matviewname, NEW_DELTA_ENRNAME, &target_list_buf);
+	}
+
+	/* We're done maintaining the materialized view. */
+	CloseMatViewIncrementalMaintenance();
+
+	table_close(matviewRel, NoLock);
+
+	/* Close SPI context. */
+	if (SPI_finish() != SPI_OK_FINISH)
+		elog(ERROR, "SPI_finish failed");
+}
+
+/*
+ * apply_old_delta
+ *
+ * Execute a query for applying a delta table given by deltname_old
+ * which contains tuples to be deleted from to a materialized view given by
+ * matviewname.  This is used when counting is not required.
+ */
+static void
+apply_old_delta(const char *matviewname, const char *deltaname_old,
+				List *keys)
+{
+	StringInfoData	querybuf;
+	StringInfoData	keysbuf;
+	char   *match_cond;
+	ListCell *lc;
+
+	/* build WHERE condition for searching tuples to be deleted */
+	match_cond = get_matching_condition_string(keys);
+
+	/* build string of keys list */
+	initStringInfo(&keysbuf);
+	foreach (lc, keys)
+	{
+		Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc);
+		char   *resname = NameStr(attr->attname);
+		appendStringInfo(&keysbuf, "%s", quote_qualified_identifier("mv", resname));
+		if (lnext(keys, lc))
+			appendStringInfo(&keysbuf, ", ");
+	}
+
+	/* Search for matching tuples from the view and update or delete if found. */
+	initStringInfo(&querybuf);
+	appendStringInfo(&querybuf,
+	"DELETE FROM %s WHERE ctid IN ("
+		"SELECT tid FROM (SELECT pg_catalog.row_number() over (partition by %s) AS \"__ivm_row_number__\","
+								  "mv.ctid AS tid,"
+								  "diff.\"__ivm_count__\""
+						 "FROM %s AS mv, %s AS diff "
+						 "WHERE %s) v "
+					"WHERE v.\"__ivm_row_number__\" OPERATOR(pg_catalog.<=) v.\"__ivm_count__\")",
+					matviewname,
+					keysbuf.data,
+					matviewname, deltaname_old,
+					match_cond);
+
+	if (SPI_exec(querybuf.data, 0) != SPI_OK_DELETE)
+		elog(ERROR, "SPI_exec failed: %s", querybuf.data);
+}
+
+/*
+ * apply_new_delta
+ *
+ * Execute a query for applying a delta table given by deltname_new
+ * which contains tuples to be inserted into a materialized view given by
+ * matviewname.  This is used when counting is not required.
+ */
+static void
+apply_new_delta(const char *matviewname, const char *deltaname_new,
+				StringInfo target_list)
+{
+	StringInfoData	querybuf;
+
+	/* Search for matching tuples from the view and update or delete if found. */
+	initStringInfo(&querybuf);
+	appendStringInfo(&querybuf,
+					"INSERT INTO %s (%s) SELECT %s FROM ("
+						"SELECT diff.*, pg_catalog.generate_series(1, diff.\"__ivm_count__\")"
+							" AS __ivm_generate_series__ "
+						"FROM %s AS diff) AS v",
+					matviewname, target_list->data, target_list->data,
+					deltaname_new);
+
+	if (SPI_exec(querybuf.data, 0) != SPI_OK_INSERT)
+		elog(ERROR, "SPI_exec failed: %s", querybuf.data);
+}
+
+/*
+ * get_matching_condition_string
+ *
+ * Build a predicate string for looking for a tuple with given keys.
+ */
+static char *
+get_matching_condition_string(List *keys)
+{
+	StringInfoData match_cond;
+	ListCell	*lc;
+
+	/* If there is no key columns, the condition is always true. */
+	if (keys == NIL)
+		return "true";
+
+	initStringInfo(&match_cond);
+	foreach (lc, keys)
+	{
+		Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc);
+		char   *resname = NameStr(attr->attname);
+		char   *mv_resname = quote_qualified_identifier("mv", resname);
+		char   *diff_resname = quote_qualified_identifier("diff", resname);
+		Oid		typid = attr->atttypid;
+
+		/* Considering NULL values, we can not use simple = operator. */
+		appendStringInfo(&match_cond, "(");
+		generate_equal(&match_cond, typid, mv_resname, diff_resname);
+		appendStringInfo(&match_cond, " OR (%s IS NULL AND %s IS NULL))",
+						 mv_resname, diff_resname);
+
+		if (lnext(keys, lc))
+			appendStringInfo(&match_cond, " AND ");
+	}
+
+	return match_cond.data;
+}
+
+/*
+ * generate_equals
+ *
+ * Generate an equality clause using given operands' default equality
+ * operator.
+ */
+static void
+generate_equal(StringInfo querybuf, Oid opttype,
+			   const char *leftop, const char *rightop)
+{
+	TypeCacheEntry *typentry;
+
+	typentry = lookup_type_cache(opttype, TYPECACHE_EQ_OPR);
+	if (!OidIsValid(typentry->eq_opr))
+		ereport(ERROR,
+				(errcode(ERRCODE_UNDEFINED_FUNCTION),
+				 errmsg("could not identify an equality operator for type %s",
+						format_type_be_qualified(opttype))));
+
+	generate_operator_clause(querybuf,
+							 leftop, opttype,
+							 typentry->eq_opr,
+							 rightop, opttype);
+}
+
+/*
+ * mv_InitHashTables
+ */
+static void
+mv_InitHashTables(void)
+{
+	HASHCTL		ctl;
+
+	memset(&ctl, 0, sizeof(ctl));
+	ctl.keysize = sizeof(Oid);
+	ctl.entrysize = sizeof(MV_TriggerHashEntry);
+	mv_trigger_info = hash_create("MV trigger info",
+								 MV_INIT_QUERYHASHSIZE,
+								 &ctl, HASH_ELEM | HASH_BLOBS);
+
+	memset(&ctl, 0, sizeof(ctl));
+	ctl.keysize = sizeof(Oid);
+	ctl.entrysize = sizeof(DroppedImmvInfo);
+	dropped_immv = hash_create("Dropped IMMVs", 16,
+							   &ctl, HASH_ELEM | HASH_BLOBS);
+}
+
+/*
+ * AtAbort_IVM
+ *
+ * Clean up hash entries for all materialized views. This is called at
+ * (sub-)transaction abort. When the top-level transaction is aborted,
+ * InvalidSubTransactionId is set to subxid.
+ *
+ * Also, remove dropped IMMV information if it is aborted.
+ */
+void
+AtAbort_IVM(SubTransactionId subxid)
+{
+	HASH_SEQ_STATUS seq;
+
+	if (mv_trigger_info)
+	{
+		MV_TriggerHashEntry *entry;
+		hash_seq_init(&seq, mv_trigger_info);
+		while ((entry = hash_seq_search(&seq)) != NULL)
+			clean_up_IVM_hash_entry(entry, true, subxid);
+	}
+
+	if (dropped_immv)
+	{
+		DroppedImmvInfo *entry;
+		hash_seq_init(&seq, dropped_immv);
+		while ((entry = hash_seq_search(&seq)) != NULL)
+		{
+			if (subxid == InvalidSubTransactionId || subxid == entry->subxid)
+				hash_search(dropped_immv, (void *) &entry->immv_oid, HASH_REMOVE, NULL);
+		}
+	}
+
+	in_delta_calculation = false;
+}
+
+/*
+ * AtPreCommit_IVM
+ *
+ * Record the transaction ID that updated the view incrementally.
+ * Also, remove the entry for dropped IMMVs.
+ */
+void
+AtPreCommit_IVM(void)
+{
+	HASH_SEQ_STATUS seq;
+
+	if (mv_trigger_info)
+	{
+		MV_TriggerHashEntry *entry;
+
+		/*
+		 * Record the transaction ID that udpate the view incrementally,
+		 * and perform the final clean up of the entry.
+		 */
+		hash_seq_init(&seq, mv_trigger_info);
+		while ((entry = hash_seq_search(&seq)) != NULL)
+		{
+			setLastUpdateXid(entry->matview_id, GetTopFullTransactionId());
+			hash_search(mv_trigger_info, (void *) &entry->matview_id, HASH_REMOVE, NULL);
+		}
+	}
+
+	if (dropped_immv)
+	{
+		DroppedImmvInfo *entry;
+
+		LWLockAcquire(IvmControlLock, LW_EXCLUSIVE);
+		hash_seq_init(&seq, dropped_immv);
+		while ((entry = hash_seq_search(&seq)) != NULL)
+		{
+			hash_search(LastIvmUpdateHash, (void *) &entry->immv_oid, HASH_REMOVE, NULL);
+			hash_search(dropped_immv, (void *) &entry->immv_oid, HASH_REMOVE, NULL);
+		}
+		LWLockRelease(IvmControlLock);
+	}
+
+	in_delta_calculation = false;
+}
+
+/*
+ * clean_up_IVM_hash_entry
+ *
+ * Clean up tuple stores and hash entries for a materialized view after its
+ * maintenance finished. This is called at the end of table modifying query
+ * or (sub-)transaction abort. When the top-level transaction is aborted,
+ * InvalidSubTransactionId is set to subxid.
+ */
+static void
+clean_up_IVM_hash_entry(MV_TriggerHashEntry *entry, bool is_abort,
+						SubTransactionId subxid)
+{
+	bool found;
+	ListCell *lc;
+
+	/* clean up tuple stores */
+	foreach(lc, entry->tables)
+	{
+		MV_TriggerTable *table = (MV_TriggerTable *) lfirst(lc);
+
+		list_free(table->old_tuplestores);
+		list_free(table->new_tuplestores);
+		if (!is_abort)
+		{
+			ExecDropSingleTupleTableSlot(table->slot);
+			table_close(table->rel, NoLock);
+		}
+	}
+	list_free(entry->tables);
+	entry->tables = NIL;
+
+	if (is_abort)
+	{
+		bool	remove_entry = false;
+
+		/*
+		 * When the top-level transaction is aborted, remove all subxids.
+		 * When a sub-transaction is aborted, remove only its subxid.
+		 */
+		if (subxid == InvalidSubTransactionId)
+			remove_entry = true;
+		else
+		{
+			foreach(lc, entry->subxids)
+			{
+				if (lfirst_xid(lc) == subxid)
+				{
+					entry->subxids = list_delete_cell(entry->subxids, lc);
+					break;
+				}
+			}
+
+			/*
+			 * If all the subxid are removed, it means that the view was not
+			 * updated at all in this transaction.
+			 */
+			if (list_length(entry->subxids) == 0)
+				remove_entry = true;
+		}
+
+		/*
+		 * Remove entries of not updated views from the hash table.
+		 */
+		if (remove_entry)
+			hash_search(mv_trigger_info, (void *) &entry->matview_id, HASH_REMOVE, &found);
+	}
+	else
+	{
+		/* When the query sucsessully finished, unregister the snapshot */
+		UnregisterSnapshot(entry->snapshot);
+	}
+
+	entry->snapshot = InvalidSnapshot;
+}
+
+/*
+ * setLastUpdateXid
+ *
+ * Store the transaction ID that updated the view incremenally.
+ */
+static void
+setLastUpdateXid(Oid immv_oid, FullTransactionId xid)
+{
+	LastIvmUpdateEntry *entry;
+
+	LWLockAcquire(IvmControlLock, LW_EXCLUSIVE);
+	entry = (LastIvmUpdateEntry *) hash_search(LastIvmUpdateHash, (void *) &immv_oid, HASH_ENTER, NULL);
+	entry->oid = immv_oid;
+	entry->last_ivm_update = xid;
+	LWLockRelease(IvmControlLock);
+}
+
+/*
+ * getLastUpdateXid
+ *
+ * Get the most recent transaction ID that updated the view incrementally.
+ */
+static FullTransactionId
+getLastUpdateXid(Oid immv_oid)
+{
+	FullTransactionId xid = InvalidFullTransactionId;
+	LastIvmUpdateEntry *entry;
+	bool found;
+
+	LWLockAcquire(IvmControlLock, LW_SHARED);
+	entry = (LastIvmUpdateEntry *) hash_search(LastIvmUpdateHash, (void *) &immv_oid, HASH_FIND, &found);
+	LWLockRelease(IvmControlLock);
+	if (found)
+		xid = entry->last_ivm_update;
+
+	return xid;
+}
+
+void
+removeImmv(Oid immv_oid)
+{
+	DroppedImmvInfo *entry;
+
+	if (!dropped_immv)
+		mv_InitHashTables();
+
+	entry = (DroppedImmvInfo *) hash_search(dropped_immv, (void *) &immv_oid, HASH_ENTER, NULL);
+	entry->subxid = GetCurrentSubTransactionId();
+}
+
+/*
+ * isIvmName
+ *
+ * Check if this is a IVM hidden column from the name.
+ */
+bool
+isIvmName(const char *s)
+{
+	if (s)
+		return (strncmp(s, "__ivm_", 6) == 0);
+	return false;
+}
diff --git a/src/backend/commands/tablecmds.c b/src/backend/commands/tablecmds.c
index 472db112fa7..920b62d254d 100644
--- a/src/backend/commands/tablecmds.c
+++ b/src/backend/commands/tablecmds.c
@@ -62,6 +62,7 @@
 #include "commands/defrem.h"
 #include "commands/event_trigger.h"
 #include "commands/extension.h"
+#include "commands/matview.h"
 #include "commands/repack.h"
 #include "commands/sequence.h"
 #include "commands/tablecmds.h"
@@ -1811,6 +1812,9 @@ RangeVarCallbackForDropRelation(const RangeVar *rel, Oid relOid, Oid oldRelOid,
 	state->actual_relkind = classform->relkind;
 	state->actual_relpersistence = classform->relpersistence;
 
+	if (classform->relkind == RELKIND_MATVIEW && classform->relisivm)
+		removeImmv(relOid);
+
 	/*
 	 * Both RELKIND_RELATION and RELKIND_PARTITIONED_TABLE are OBJECT_TABLE,
 	 * but RemoveRelations() can only pass one relkind for a given relation.
diff --git a/src/backend/utils/activity/wait_event_names.txt b/src/backend/utils/activity/wait_event_names.txt
index 560659f9568..d97c35eeef0 100644
--- a/src/backend/utils/activity/wait_event_names.txt
+++ b/src/backend/utils/activity/wait_event_names.txt
@@ -370,6 +370,7 @@ WaitLSN	"Waiting to read or update shared Wait-for-LSN state."
 LogicalDecodingControl	"Waiting to read or update logical decoding status information."
 DataChecksumsWorker	"Waiting for data checksums worker."
 AioWorkerControl	"Waiting to update AIO worker information."
+IvmControl	"Waiting for read or update IMMV information.."
 
 #
 # END OF PREDEFINED LWLOCKS (DO NOT CHANGE THIS LINE)
diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat
index 73bb7fbb430..88399513f87 100644
--- a/src/include/catalog/pg_proc.dat
+++ b/src/include/catalog/pg_proc.dat
@@ -12698,4 +12698,14 @@
   proname => 'hashoid8extended', prorettype => 'int8',
   proargtypes => 'oid8 int8', prosrc => 'hashoid8extended' },
 
+# IVM
+{ oid => '786', descr => 'ivm trigger (before)',
+  proname => 'IVM_immediate_before', provolatile => 'v', prorettype => 'trigger',
+  proargtypes => '', prosrc => 'IVM_immediate_before' },
+{ oid => '787', descr => 'ivm trigger (after)',
+  proname => 'IVM_immediate_maintenance', provolatile => 'v', prorettype => 'trigger',
+  proargtypes => '', prosrc => 'IVM_immediate_maintenance' },
+{ oid => '788', descr => 'ivm filetring ',
+  proname => 'ivm_visible_in_prestate', provolatile => 's', prorettype => 'bool',
+  proargtypes => 'oid tid oid', prosrc => 'ivm_visible_in_prestate' },
 ]
diff --git a/src/include/commands/createas.h b/src/include/commands/createas.h
index f895c67c0c2..c286ebcd70e 100644
--- a/src/include/commands/createas.h
+++ b/src/include/commands/createas.h
@@ -16,6 +16,7 @@
 
 #include "catalog/objectaddress.h"
 #include "nodes/params.h"
+#include "nodes/pathnodes.h"
 #include "parser/parse_node.h"
 #include "tcop/dest.h"
 #include "utils/queryenvironment.h"
@@ -25,6 +26,9 @@ extern ObjectAddress ExecCreateTableAs(ParseState *pstate, CreateTableAsStmt *st
 									   ParamListInfo params, QueryEnvironment *queryEnv,
 									   QueryCompletion *qc);
 
+extern void CreateIvmTriggersOnBaseTables(Query *qry, Oid matviewOid);
+extern void CreateIndexOnIMMV(Query *query, Relation matviewRel);
+
 extern int	GetIntoRelEFlags(IntoClause *intoClause);
 
 extern DestReceiver *CreateIntoRelDestReceiver(IntoClause *intoClause);
diff --git a/src/include/commands/matview.h b/src/include/commands/matview.h
index 738c731c1a9..f1dbfc052c5 100644
--- a/src/include/commands/matview.h
+++ b/src/include/commands/matview.h
@@ -15,6 +15,7 @@
 #define MATVIEW_H
 
 #include "catalog/objectaddress.h"
+#include "fmgr.h"
 #include "nodes/params.h"
 #include "nodes/parsenodes.h"
 #include "tcop/dest.h"
@@ -23,6 +24,8 @@
 
 extern void SetMatViewPopulatedState(Relation relation, bool newstate);
 
+extern void SetMatViewIVMState(Relation relation, bool newstate);
+
 extern ObjectAddress ExecRefreshMatView(RefreshMatViewStmt *stmt, const char *queryString,
 										QueryCompletion *qc);
 extern ObjectAddress RefreshMatViewByOid(Oid matviewOid, bool is_create, bool skipData,
@@ -33,4 +36,12 @@ extern DestReceiver *CreateTransientRelDestReceiver(Oid transientoid);
 
 extern bool MatViewIncrementalMaintenanceIsEnabled(void);
 
+extern Datum IVM_immediate_before(PG_FUNCTION_ARGS);
+extern Datum IVM_immediate_maintenance(PG_FUNCTION_ARGS);
+extern Datum IVM_visible_in_prestate(PG_FUNCTION_ARGS);
+extern void AtAbort_IVM(SubTransactionId subtxid);
+extern void AtPreCommit_IVM(void);
+extern void removeImmv(Oid immv_oid);
+extern bool isIvmName(const char *s);
+
 #endif							/* MATVIEW_H */
diff --git a/src/include/storage/lwlocklist.h b/src/include/storage/lwlocklist.h
index d7eb648bd27..756c63baf97 100644
--- a/src/include/storage/lwlocklist.h
+++ b/src/include/storage/lwlocklist.h
@@ -89,6 +89,7 @@ PG_LWLOCK(54, WaitLSN)
 PG_LWLOCK(55, LogicalDecodingControl)
 PG_LWLOCK(56, DataChecksumsWorker)
 PG_LWLOCK(57, AioWorkerControl)
+PG_LWLOCK(58, IvmControl)
 
 /*
  * There also exist several built-in LWLock tranches.  As with the predefined
diff --git a/src/include/storage/subsystemlist.h b/src/include/storage/subsystemlist.h
index 9ad619080be..481e15d00a1 100644
--- a/src/include/storage/subsystemlist.h
+++ b/src/include/storage/subsystemlist.h
@@ -88,3 +88,6 @@ PG_SHMEM_SUBSYSTEM(DataChecksumsShmemCallbacks)
 
 /* AIO subsystem. This delegates to the method-specific callbacks */
 PG_SHMEM_SUBSYSTEM(AioShmemCallbacks)
+
+/* Incremental View Maintenance */
+PG_SHMEM_SUBSYSTEM(IvmShmemCallbacks)
-- 
2.43.0


--Multipart=_Wed__1_Jul_2026_00_04_01_+0900_OVSy2WWK_9aByzDJ
Content-Type: text/x-diff;
 name="v38-0005-Add-Incremental-View-Maintenance-support-to-psql.patch"
Content-Disposition: attachment;
 filename="v38-0005-Add-Incremental-View-Maintenance-support-to-psql.patch"
Content-Transfer-Encoding: 7bit



^ permalink  raw  reply  [nested|flat] 101+ messages in thread

* [PATCH v38 06/11] Add Incremental View Maintenance support
@ 2026-05-29 09:06  Yugo Nagata <[email protected]>
  0 siblings, 0 replies; 101+ messages in thread

From: Yugo Nagata @ 2026-05-29 09:06 UTC (permalink / raw)

In this implementation, AFTER triggers are used to collect
tuplestores containing transition table contents. When multiple tables
are changed, multiple AFTER triggers are invoked, then the final AFTER
trigger performs actual update of the matview. In addition, BEFORE
triggers are also used to handle global information for view
maintenance.

To calculate view deltas, we need both pre-state and post-state of base
tables. Post-update states are available in AFTER trigger, and pre-update
states can be calculated by removing inserted tuples and appending deleted
tuples. Insterted tuples are filtered using the snapshot taken before
table modification, and deleted tuples are contained in the old transition
table.

Incrementally Maintainable Materialized Views (IMMV) can contain
duplicated tuples.

This patch also allows self-join, simultaneous updates of more than
one base table, and multiple updates of the same base table.
---
 src/backend/access/transam/xact.c             |    8 +
 src/backend/commands/createas.c               |  709 +++++++
 src/backend/commands/matview.c                | 1835 ++++++++++++++++-
 src/backend/commands/tablecmds.c              |    4 +
 .../utils/activity/wait_event_names.txt       |    1 +
 src/include/catalog/pg_proc.dat               |   10 +
 src/include/commands/createas.h               |    4 +
 src/include/commands/matview.h                |   11 +
 src/include/storage/lwlocklist.h              |    1 +
 src/include/storage/subsystemlist.h           |    3 +
 10 files changed, 2548 insertions(+), 38 deletions(-)

diff --git a/src/backend/access/transam/xact.c b/src/backend/access/transam/xact.c
index 3a89149016f..0e6cb5493d2 100644
--- a/src/backend/access/transam/xact.c
+++ b/src/backend/access/transam/xact.c
@@ -37,6 +37,7 @@
 #include "catalog/pg_enum.h"
 #include "catalog/storage.h"
 #include "commands/async.h"
+#include "commands/matview.h"
 #include "commands/tablecmds.h"
 #include "commands/trigger.h"
 #include "common/pg_prng.h"
@@ -2322,6 +2323,9 @@ CommitTransaction(void)
 	CallXactCallbacks(is_parallel_worker ? XACT_EVENT_PARALLEL_PRE_COMMIT
 					  : XACT_EVENT_PRE_COMMIT);
 
+	/* Store the transaction ID that updated the view incrementally */
+	AtPreCommit_IVM();
+
 	/*
 	 * If this xact has started any unfinished parallel operation, clean up
 	 * its workers, warning about leaked resources.  (But we don't actually
@@ -2973,6 +2977,7 @@ AbortTransaction(void)
 	AtAbort_Notify();
 	AtEOXact_RelationMap(false, is_parallel_worker);
 	AtAbort_Twophase();
+	AtAbort_IVM(InvalidSubTransactionId);
 
 	/*
 	 * Advertise the fact that we aborted in pg_xact (assuming that we got as
@@ -5304,6 +5309,9 @@ AbortSubTransaction(void)
 
 	UnlockBuffers();
 
+	/* Clean up hash entries for incremental view maintenance */
+	AtAbort_IVM(s->subTransactionId);
+
 	/* Reset WAL record construction state */
 	XLogResetInsertion();
 
diff --git a/src/backend/commands/createas.c b/src/backend/commands/createas.c
index 6dbb831ca89..a499688b79d 100644
--- a/src/backend/commands/createas.c
+++ b/src/backend/commands/createas.c
@@ -29,18 +29,32 @@
 #include "access/tableam.h"
 #include "access/xact.h"
 #include "catalog/namespace.h"
+#include "catalog/index.h"
+#include "catalog/pg_am_d.h"
+#include "catalog/pg_constraint.h"
+#include "catalog/pg_inherits.h"
+#include "catalog/pg_trigger.h"
 #include "catalog/toasting.h"
 #include "commands/createas.h"
+#include "commands/defrem.h"
 #include "commands/matview.h"
 #include "commands/prepare.h"
 #include "commands/tablecmds.h"
+#include "commands/tablespace.h"
+#include "commands/trigger.h"
 #include "commands/view.h"
 #include "executor/execdesc.h"
 #include "executor/executor.h"
+#include "miscadmin.h"
 #include "nodes/makefuncs.h"
 #include "nodes/nodeFuncs.h"
 #include "nodes/queryjumble.h"
+#include "optimizer/optimizer.h"
+#include "optimizer/prep.h"
 #include "parser/analyze.h"
+#include "parser/parser.h"
+#include "parser/parsetree.h"
+#include "parser/parse_clause.h"
 #include "rewrite/rewriteHandler.h"
 #include "tcop/tcopprot.h"
 #include "utils/builtins.h"
@@ -70,6 +84,12 @@ static bool intorel_receive(TupleTableSlot *slot, DestReceiver *self);
 static void intorel_shutdown(DestReceiver *self);
 static void intorel_destroy(DestReceiver *self);
 
+static void CreateIvmTriggersOnBaseTablesRecurse(Query *qry, Node *node, Oid matviewOid,
+									 List **relids, bool ex_lock);
+static void CreateIvmTrigger(Oid relOid, Oid viewOid, int16 type, int16 timing, bool ex_lock);
+static void check_ivm_restriction(Node *node);
+static bool check_ivm_restriction_walker(Node *node, void *context);
+static Bitmapset *get_primary_key_attnos_from_query(Query *query, List **constraintList);
 
 /*
  * create_ctas_internal
@@ -277,6 +297,18 @@ ExecCreateTableAs(ParseState *pstate, CreateTableAsStmt *stmt,
 		into->skipData = true;
 	}
 
+	if (is_matview && into->ivm)
+	{
+		/* check if the query is supported in IMMV definition */
+		if (contain_mutable_functions((Node *) query))
+			ereport(ERROR,
+					(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+					 errmsg("mutable function is not supported on incrementally maintainable materialized view"),
+					 errhint("functions must be marked IMMUTABLE")));
+
+		check_ivm_restriction((Node *) query);
+	}
+
 	if (into->skipData)
 	{
 		/*
@@ -287,15 +319,36 @@ ExecCreateTableAs(ParseState *pstate, CreateTableAsStmt *stmt,
 		 */
 		address = create_ctas_nodata(query->targetList, into);
 
+		/*
+		 * For IVM, mark the matview before refresh so RelationIsIVM()
+		 * returns true inside RefreshMatViewByOid.
+		 */
+		if (is_matview && into->ivm)
+		{
+			Relation matviewRel = table_open(address.objectId, NoLock);
+
+			SetMatViewIVMState(matviewRel, true);
+			table_close(matviewRel, NoLock);
+			CommandCounterIncrement();
+		}
+
 		/*
 		 * For materialized views, reuse the REFRESH logic, which locks down
 		 * security-restricted operations and restricts the search_path.  This
 		 * reduces the chance that a subsequent refresh will fail.
 		 */
 		if (do_refresh)
+		{
 			RefreshMatViewByOid(address.objectId, true, false, false,
 								pstate->p_sourcetext, qc);
 
+			if (is_matview && into->ivm && IsolationUsesXactSnapshot())
+				ereport(WARNING,
+						(errmsg("inconsistent view can be created in isolation level SERIALIZABLE or REPEATABLE READ"),
+						 errdetail("The view may not include effects of a concurrent transaction."),
+						 errhint("The view with incremental maintenance should be created in isolation level READ COMMITTED, "
+								 "or refreshed manually to make sure the view is consistent.")));
+		}
 	}
 	else
 	{
@@ -635,3 +688,659 @@ intorel_destroy(DestReceiver *self)
 {
 	pfree(self);
 }
+
+/*
+ * CreateIvmTriggersOnBaseTables -- create IVM triggers on all base tables
+ */
+void
+CreateIvmTriggersOnBaseTables(Query *qry, Oid matviewOid)
+{
+	List   *relids = NIL;
+	bool	ex_lock = false;
+	RangeTblEntry *rte;
+
+	/* Immediately return if we don't have any base tables. */
+	if (list_length(qry->rtable) < 1)
+		return;
+
+	/*
+	 * If the view has more than one base tables, we need an exclusive lock
+	 * on the view so that the view would be maintained serially to avoid
+	 * the inconsistency that occurs when two base tables are modified in
+	 * concurrent transactions. However, if the view has only one table,
+	 * we can use a weaker lock.
+	 *
+	 * The type of lock should be determined here, because if we check the
+	 * view definition at maintenance time, we need to acquire a weaker lock,
+	 * and upgrading the lock level after this increases probability of
+	 * deadlock.
+	 */
+
+	rte = list_nth(qry->rtable, 0);
+	if (list_length(qry->rtable) > 1 || rte->rtekind != RTE_RELATION)
+		ex_lock = true;
+
+	CreateIvmTriggersOnBaseTablesRecurse(qry, (Node *)qry, matviewOid, &relids, ex_lock);
+
+	list_free(relids);
+}
+
+static void
+CreateIvmTriggersOnBaseTablesRecurse(Query *qry, Node *node, Oid matviewOid,
+									 List **relids, bool ex_lock)
+{
+	if (node == NULL)
+		return;
+
+	/* This can recurse, so check for excessive recursion */
+	check_stack_depth();
+
+	switch (nodeTag(node))
+	{
+		case T_Query:
+			{
+				Query *query = (Query *) node;
+
+				CreateIvmTriggersOnBaseTablesRecurse(qry, (Node *)query->jointree, matviewOid, relids, ex_lock);
+			}
+			break;
+
+		case T_RangeTblRef:
+			{
+				int			rti = ((RangeTblRef *) node)->rtindex;
+				RangeTblEntry *rte = rt_fetch(rti, qry->rtable);
+
+				if (rte->rtekind == RTE_RELATION && !list_member_oid(*relids, rte->relid))
+				{
+					CreateIvmTrigger(rte->relid, matviewOid, TRIGGER_TYPE_INSERT, TRIGGER_TYPE_BEFORE, ex_lock);
+					CreateIvmTrigger(rte->relid, matviewOid, TRIGGER_TYPE_DELETE, TRIGGER_TYPE_BEFORE, ex_lock);
+					CreateIvmTrigger(rte->relid, matviewOid, TRIGGER_TYPE_UPDATE, TRIGGER_TYPE_BEFORE, ex_lock);
+					CreateIvmTrigger(rte->relid, matviewOid, TRIGGER_TYPE_TRUNCATE, TRIGGER_TYPE_BEFORE, true);
+					CreateIvmTrigger(rte->relid, matviewOid, TRIGGER_TYPE_INSERT, TRIGGER_TYPE_AFTER, ex_lock);
+					CreateIvmTrigger(rte->relid, matviewOid, TRIGGER_TYPE_DELETE, TRIGGER_TYPE_AFTER, ex_lock);
+					CreateIvmTrigger(rte->relid, matviewOid, TRIGGER_TYPE_UPDATE, TRIGGER_TYPE_AFTER, ex_lock);
+					CreateIvmTrigger(rte->relid, matviewOid, TRIGGER_TYPE_TRUNCATE, TRIGGER_TYPE_AFTER, true);
+
+					*relids = lappend_oid(*relids, rte->relid);
+				}
+			}
+			break;
+
+		case T_FromExpr:
+			{
+				FromExpr   *f = (FromExpr *) node;
+				ListCell   *l;
+
+				foreach(l, f->fromlist)
+					CreateIvmTriggersOnBaseTablesRecurse(qry, lfirst(l), matviewOid, relids, ex_lock);
+			}
+			break;
+
+		case T_JoinExpr:
+			{
+				JoinExpr   *j = (JoinExpr *) node;
+
+				CreateIvmTriggersOnBaseTablesRecurse(qry, j->larg, matviewOid, relids, ex_lock);
+				CreateIvmTriggersOnBaseTablesRecurse(qry, j->rarg, matviewOid, relids, ex_lock);
+			}
+			break;
+
+		default:
+			elog(ERROR, "unrecognized node type: %d", (int) nodeTag(node));
+	}
+}
+
+/*
+ * CreateIvmTrigger -- create IVM trigger on a base table
+ */
+static void
+CreateIvmTrigger(Oid relOid, Oid viewOid, int16 type, int16 timing, bool ex_lock)
+{
+	ObjectAddress	refaddr;
+	ObjectAddress	address;
+	CreateTrigStmt *ivm_trigger;
+	List *transitionRels = NIL;
+
+	Assert(timing == TRIGGER_TYPE_BEFORE || timing == TRIGGER_TYPE_AFTER);
+
+	refaddr.classId = RelationRelationId;
+	refaddr.objectId = viewOid;
+	refaddr.objectSubId = 0;
+
+	ivm_trigger = makeNode(CreateTrigStmt);
+	ivm_trigger->relation = NULL;
+	ivm_trigger->row = false;
+
+	ivm_trigger->timing = timing;
+	ivm_trigger->events = type;
+
+	switch (type)
+	{
+		case TRIGGER_TYPE_INSERT:
+			ivm_trigger->trigname = (timing == TRIGGER_TYPE_BEFORE ? "IVM_trigger_ins_before" : "IVM_trigger_ins_after");
+			break;
+		case TRIGGER_TYPE_DELETE:
+			ivm_trigger->trigname = (timing == TRIGGER_TYPE_BEFORE ? "IVM_trigger_del_before" : "IVM_trigger_del_after");
+			break;
+		case TRIGGER_TYPE_UPDATE:
+			ivm_trigger->trigname = (timing == TRIGGER_TYPE_BEFORE ? "IVM_trigger_upd_before" : "IVM_trigger_upd_after");
+			break;
+		case TRIGGER_TYPE_TRUNCATE:
+			ivm_trigger->trigname = (timing == TRIGGER_TYPE_BEFORE ? "IVM_trigger_truncate_before" : "IVM_trigger_truncate_after");
+			break;
+		default:
+			elog(ERROR, "unsupported trigger type");
+	}
+
+	if (timing == TRIGGER_TYPE_AFTER)
+	{
+		if (type == TRIGGER_TYPE_INSERT || type == TRIGGER_TYPE_UPDATE)
+		{
+			TriggerTransition *n = makeNode(TriggerTransition);
+			n->name = "__ivm_newtable";
+			n->isNew = true;
+			n->isTable = true;
+
+			transitionRels = lappend(transitionRels, n);
+		}
+		if (type == TRIGGER_TYPE_DELETE || type == TRIGGER_TYPE_UPDATE)
+		{
+			TriggerTransition *n = makeNode(TriggerTransition);
+			n->name = "__ivm_oldtable";
+			n->isNew = false;
+			n->isTable = true;
+
+			transitionRels = lappend(transitionRels, n);
+		}
+	}
+
+	/*
+	 * XXX: When using DELETE or UPDATE, we must use exclusive lock for now
+	 * because apply_old_delta(_with_count) uses ctid to identify the tuple
+	 * to be deleted/deleted, but doesn't work in concurrent situations.
+	 *
+	 * If the view doesn't have aggregate, distinct, or tuple duplicate,
+	 * then it would work even in concurrent situations. However, we don't have
+	 * any way to guarantee the view has a unique key before opening the IMMV
+	 * at the maintenance time because users may drop the unique index.
+	 */
+
+	if (type == TRIGGER_TYPE_DELETE || type == TRIGGER_TYPE_UPDATE)
+		ex_lock = true;
+
+	ivm_trigger->funcname =
+		(timing == TRIGGER_TYPE_BEFORE ? SystemFuncName("IVM_immediate_before") : SystemFuncName("IVM_immediate_maintenance"));
+
+	ivm_trigger->columns = NIL;
+	ivm_trigger->transitionRels = transitionRels;
+	ivm_trigger->whenClause = NULL;
+	ivm_trigger->isconstraint = false;
+	ivm_trigger->deferrable = false;
+	ivm_trigger->initdeferred = false;
+	ivm_trigger->constrrel = NULL;
+	ivm_trigger->args = list_make2(
+		makeString(DatumGetPointer(DirectFunctionCall1(oidout, ObjectIdGetDatum(viewOid)))),
+		makeString(DatumGetPointer(DirectFunctionCall1(boolout, BoolGetDatum(ex_lock))))
+		);
+
+	address = CreateTrigger(ivm_trigger, NULL, relOid, InvalidOid, InvalidOid,
+						 InvalidOid, InvalidOid, InvalidOid, NULL, true, false);
+
+	recordDependencyOn(&address, &refaddr, DEPENDENCY_AUTO);
+
+	/* Make changes-so-far visible */
+	CommandCounterIncrement();
+}
+
+/*
+ * check_ivm_restriction --- look for specify nodes in the query tree
+ */
+static void
+check_ivm_restriction(Node *node)
+{
+	check_ivm_restriction_walker(node, NULL);
+}
+
+static bool
+check_ivm_restriction_walker(Node *node, void *context)
+{
+	if (node == NULL)
+		return false;
+
+	/*
+	 * We currently don't support Sub-Query.
+	 */
+	if (IsA(node, SubPlan) || IsA(node, SubLink))
+		ereport(ERROR,
+				(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+				 errmsg("subquery is not supported on incrementally maintainable materialized view")));
+
+	/* This can recurse, so check for excessive recursion */
+	check_stack_depth();
+
+	switch (nodeTag(node))
+	{
+		case T_Query:
+			{
+				Query *qry = (Query *)node;
+				ListCell   *lc;
+				List       *vars;
+
+				/* if contained CTE, return error */
+				if (qry->cteList != NIL)
+					ereport(ERROR,
+							(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+							 errmsg("CTE is not supported on incrementally maintainable materialized view")));
+				if (qry->havingQual != NULL)
+					ereport(ERROR,
+							(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+							 errmsg(" HAVING clause is not supported on incrementally maintainable materialized view")));
+				if (qry->sortClause != NIL)	/* There is a possibility that we don't need to return an error */
+					ereport(ERROR,
+							(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+							 errmsg("ORDER BY clause is not supported on incrementally maintainable materialized view")));
+				if (qry->limitOffset != NULL || qry->limitCount != NULL)
+					ereport(ERROR,
+							(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+							 errmsg("LIMIT/OFFSET clause is not supported on incrementally maintainable materialized view")));
+				if (qry->distinctClause)
+					ereport(ERROR,
+							(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+							 errmsg("DISTINCT is not supported on incrementally maintainable materialized view")));
+				if (qry->hasDistinctOn)
+					ereport(ERROR,
+							(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+							 errmsg("DISTINCT ON is not supported on incrementally maintainable materialized view")));
+				if (qry->hasWindowFuncs)
+					ereport(ERROR,
+							(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+							 errmsg("window functions are not supported on incrementally maintainable materialized view")));
+				if (qry->groupingSets != NIL)
+					ereport(ERROR,
+							(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+							 errmsg("GROUPING SETS, ROLLUP, or CUBE clauses is not supported on incrementally maintainable materialized view")));
+				if (qry->setOperations != NULL)
+					ereport(ERROR,
+							(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+							 errmsg("UNION/INTERSECT/EXCEPT statements are not supported on incrementally maintainable materialized view")));
+				if (list_length(qry->targetList) == 0)
+					ereport(ERROR,
+							(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+							 errmsg("empty target list is not supported on incrementally maintainable materialized view")));
+				if (qry->rowMarks != NIL)
+					ereport(ERROR,
+							(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+							 errmsg("FOR UPDATE/SHARE clause is not supported on incrementally maintainable materialized view")));
+
+				/* system column restrictions */
+				vars = pull_vars_of_level((Node *) qry, 0);
+				foreach(lc, vars)
+				{
+					if (IsA(lfirst(lc), Var))
+					{
+						Var *var = (Var *) lfirst(lc);
+						/* if system column, return error */
+						if (var->varattno < 0)
+							ereport(ERROR,
+									(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+									 errmsg("system column is not supported on incrementally maintainable materialized view")));
+					}
+				}
+
+				/* check if type in the target list had an equality operator */
+				foreach(lc, qry->targetList)
+				{
+					TargetEntry *tle = (TargetEntry *) lfirst(lc);
+					Oid             atttype = exprType((Node *) tle->expr);
+					Oid             opclass;
+
+					opclass = GetDefaultOpClass(atttype, BTREE_AM_OID);
+					if (!OidIsValid(opclass))
+						ereport(ERROR,
+								(errcode(ERRCODE_UNDEFINED_OBJECT),
+								 errmsg("data type %s has no default operator class for access method \"%s\"",
+									format_type_be(atttype), "btree")));
+				}
+
+				/* restrictions for rtable */
+				foreach(lc, qry->rtable)
+				{
+					RangeTblEntry *rte = (RangeTblEntry *) lfirst(lc);
+
+					if (rte->subquery)
+						ereport(ERROR,
+								(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+								 errmsg("subquery is not supported on incrementally maintainable materialized view")));
+
+					if (rte->tablesample != NULL)
+						ereport(ERROR,
+								(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+								 errmsg("TABLESAMPLE clause is not supported on incrementally maintainable materialized view")));
+
+					if (rte->relkind == RELKIND_PARTITIONED_TABLE)
+						ereport(ERROR,
+								(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+								 errmsg("partitioned table is not supported on incrementally maintainable materialized view")));
+
+					if (rte->relkind == RELKIND_RELATION && has_superclass(rte->relid))
+						ereport(ERROR,
+								(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+								 errmsg("partitions is not supported on incrementally maintainable materialized view")));
+
+					if (rte->relkind == RELKIND_RELATION && find_inheritance_children(rte->relid, NoLock) != NIL)
+						ereport(ERROR,
+								(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+								 errmsg("inheritance parent is not supported on incrementally maintainable materialized view")));
+
+					if (rte->relkind == RELKIND_FOREIGN_TABLE)
+						ereport(ERROR,
+								(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+								 errmsg("foreign table is not supported on incrementally maintainable materialized view")));
+
+					if (rte->relkind == RELKIND_VIEW ||
+						rte->relkind == RELKIND_MATVIEW)
+						ereport(ERROR,
+								(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+								 errmsg("VIEW or MATERIALIZED VIEW is not supported on incrementally maintainable materialized view")));
+
+					if (rte->rtekind == RTE_VALUES)
+						ereport(ERROR,
+								(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+								 errmsg("VALUES is not supported on incrementally maintainable materialized view")));
+
+				}
+
+				query_tree_walker(qry, check_ivm_restriction_walker, NULL, QTW_IGNORE_RANGE_TABLE);
+
+				break;
+			}
+		case T_TargetEntry:
+			{
+				TargetEntry *tle = (TargetEntry *)node;
+				if (isIvmName(tle->resname))
+						ereport(ERROR,
+								(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+								 errmsg("column name %s is not supported on incrementally maintainable materialized view", tle->resname)));
+
+				expression_tree_walker(node, check_ivm_restriction_walker, NULL);
+				break;
+			}
+		case T_JoinExpr:
+			{
+				JoinExpr *joinexpr = (JoinExpr *)node;
+
+				if (joinexpr->jointype > JOIN_INNER)
+						ereport(ERROR,
+								(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+								 errmsg("OUTER JOIN is not supported on incrementally maintainable materialized view")));
+
+				expression_tree_walker(node, check_ivm_restriction_walker, NULL);
+			}
+			break;
+		case T_Aggref:
+			ereport(ERROR,
+					(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+					 errmsg("aggregate function is not supported on incrementally maintainable materialized view")));
+			break;
+		default:
+			expression_tree_walker(node, check_ivm_restriction_walker, (void *) context);
+			break;
+	}
+	return false;
+}
+
+/*
+ * CreateIndexOnIMMV
+ *
+ * Create a unique index on incremental maintainable materialized view.
+ * If the view definition query has a GROUP BY clause, the index is created
+ * on the columns of GROUP BY expressions. Otherwise, if the view contains
+ * all primary key attributes of its base tables in the target list, the index
+ * is created on these attributes. In other cases, no index is created.
+ */
+void
+CreateIndexOnIMMV(Query *query, Relation matviewRel)
+{
+	ListCell *lc;
+	IndexStmt  *index;
+	ObjectAddress address;
+	List *constraintList = NIL;
+	char		idxname[NAMEDATALEN];
+	List	   *indexoidlist = RelationGetIndexList(matviewRel);
+	ListCell   *indexoidscan;
+	Bitmapset *key_attnos;
+
+	snprintf(idxname, sizeof(idxname), "%s_index", RelationGetRelationName(matviewRel));
+
+	index = makeNode(IndexStmt);
+
+	index->unique = true;
+	index->primary = false;
+	index->isconstraint = false;
+	index->deferrable = false;
+	index->initdeferred = false;
+	index->idxname = idxname;
+	index->relation =
+		makeRangeVar(get_namespace_name(RelationGetNamespace(matviewRel)),
+					 pstrdup(RelationGetRelationName(matviewRel)),
+					 -1);
+	index->accessMethod = DEFAULT_INDEX_TYPE;
+	index->options = NIL;
+	index->tableSpace = get_tablespace_name(matviewRel->rd_rel->reltablespace);
+	index->whereClause = NULL;
+	index->indexParams = NIL;
+	index->indexIncludingParams = NIL;
+	index->excludeOpNames = NIL;
+	index->idxcomment = NULL;
+	index->indexOid = InvalidOid;
+	index->oldNumber = InvalidRelFileNumber;
+	index->oldCreateSubid = InvalidSubTransactionId;
+	index->oldFirstRelfilelocatorSubid = InvalidSubTransactionId;
+	index->transformed = true;
+	index->concurrent = false;
+	index->if_not_exists = false;
+
+	/* create index on the base tables' primary key columns */
+	key_attnos = get_primary_key_attnos_from_query(query, &constraintList);
+	if (key_attnos)
+	{
+		foreach(lc, query->targetList)
+		{
+			TargetEntry *tle = (TargetEntry *) lfirst(lc);
+			Form_pg_attribute attr = TupleDescAttr(matviewRel->rd_att, tle->resno - 1);
+
+			if (bms_is_member(tle->resno - FirstLowInvalidHeapAttributeNumber, key_attnos))
+			{
+				IndexElem  *iparam;
+
+				iparam = makeNode(IndexElem);
+				iparam->name = pstrdup(NameStr(attr->attname));
+				iparam->expr = NULL;
+				iparam->indexcolname = NULL;
+				iparam->collation = NIL;
+				iparam->opclass = NIL;
+				iparam->opclassopts = NIL;
+				iparam->ordering = SORTBY_DEFAULT;
+				iparam->nulls_ordering = SORTBY_NULLS_DEFAULT;
+				index->indexParams = lappend(index->indexParams, iparam);
+			}
+		}
+	}
+	else
+	{
+		/* create no index, just notice that an appropriate index is necessary for efficient IVM */
+		ereport(NOTICE,
+				(errmsg("could not create an index on materialized view \"%s\" automatically",
+						RelationGetRelationName(matviewRel)),
+				 errdetail("This target list does not have all the primary key columns. "),
+				 errhint("Create an index on the materialized view for efficient incremental maintenance.")));
+		return;
+	}
+
+	/* If we have a compatible index, we don't need to create another. */
+	foreach(indexoidscan, indexoidlist)
+	{
+		Oid			indexoid = lfirst_oid(indexoidscan);
+		Relation	indexRel;
+		bool		hasCompatibleIndex = false;
+
+		indexRel = index_open(indexoid, AccessShareLock);
+
+		if (CheckIndexCompatible(indexRel->rd_id,
+								index->accessMethod,
+								index->indexParams,
+								index->excludeOpNames,
+								false))
+			hasCompatibleIndex = true;
+
+		index_close(indexRel, AccessShareLock);
+
+		if (hasCompatibleIndex)
+			return;
+	}
+
+	address = DefineIndex(NULL,
+						  RelationGetRelid(matviewRel),
+						  index,
+						  InvalidOid,
+						  InvalidOid,
+						  InvalidOid,
+						  -1,
+						  false, true, false, false, true);
+
+	ereport(NOTICE,
+			(errmsg("created index \"%s\" on materialized view \"%s\"",
+					idxname, RelationGetRelationName(matviewRel))));
+
+	/*
+	 * Make dependencies so that the index is dropped if any base tables'
+	 * primary key is dropped.
+	 */
+	foreach(lc, constraintList)
+	{
+		Oid constraintOid = lfirst_oid(lc);
+		ObjectAddress	refaddr;
+
+		refaddr.classId = ConstraintRelationId;
+		refaddr.objectId = constraintOid;
+		refaddr.objectSubId = 0;
+
+		recordDependencyOn(&address, &refaddr, DEPENDENCY_NORMAL);
+	}
+}
+
+
+/*
+ * get_primary_key_attnos_from_query
+ *
+ * Identify the columns in base tables' primary keys in the target list.
+ *
+ * Returns a Bitmapset of the column attnos of the primary key's columns of
+ * tables that used in the query.  The attnos are offset by
+ * FirstLowInvalidHeapAttributeNumber as same as get_primary_key_attnos.
+ *
+ * If any table has no primary key or any primary key's columns is not in
+ * the target list, return NULL.  We also return NULL if any pkey constraint
+ * is deferrable.
+ *
+ * constraintList is set to a list of the OIDs of the pkey constraints.
+ */
+static Bitmapset *
+get_primary_key_attnos_from_query(Query *query, List **constraintList)
+{
+	List *key_attnos_list = NIL;
+	ListCell *lc;
+	int i;
+	Bitmapset *keys = NULL;
+	Relids	rels_in_from;
+
+	/*
+	 * Collect primary key attributes from all tables used in query. The key attributes
+	 * sets for each table are stored in key_attnos_list in order by RTE index.
+	 */
+	foreach(lc, query->rtable)
+	{
+		RangeTblEntry *r = (RangeTblEntry*) lfirst(lc);
+		Bitmapset *key_attnos;
+		bool	has_no_pkey = false;
+
+		/* for tables, call get_primary_key_attnos */
+		if (r->rtekind == RTE_RELATION)
+		{
+			Oid constraintOid;
+			key_attnos = get_primary_key_attnos(r->relid, false, &constraintOid);
+			*constraintList = lappend_oid(*constraintList, constraintOid);
+			has_no_pkey = (key_attnos == NULL);
+		}
+		/*
+		 * Ignore join rels, because they are flatten later by
+		 * flatten_join_alias_vars(). Store NULL into key_attnos_list
+		 * as a dummy.
+		 */
+		 else if (r->rtekind == RTE_JOIN)
+		 {
+			key_attnos = NULL;
+		}
+		/* for other RTEs, store NULL into key_attnos_list */
+		else
+			has_no_pkey = true;
+
+		/*
+		 * If any table or subquery has no primary key or its pkey constraint is deferrable,
+		 * we cannot get key attributes for this query, so return NULL.
+		 */
+		if (has_no_pkey)
+			return NULL;
+
+		key_attnos_list = lappend(key_attnos_list, key_attnos);
+	}
+
+	/* Collect key attributes appearing in the target list */
+	i = 1;
+	foreach(lc, query->targetList)
+	{
+		TargetEntry *tle = (TargetEntry *) flatten_join_alias_vars(NULL, query, lfirst(lc));
+
+		if (IsA(tle->expr, Var))
+		{
+			Var *var = (Var*) tle->expr;
+			Bitmapset *key_attnos = list_nth(key_attnos_list, var->varno - 1);
+
+			/* check if this attribute is from a base table's primary key */
+			if (bms_is_member(var->varattno - FirstLowInvalidHeapAttributeNumber, key_attnos))
+			{
+				/*
+				 * Remove found key attributes from key_attnos_list, and add this
+				 * to the result list.
+				 */
+				key_attnos = bms_del_member(key_attnos, var->varattno - FirstLowInvalidHeapAttributeNumber);
+				if (bms_is_empty(key_attnos))
+				{
+					key_attnos_list = list_delete_nth_cell(key_attnos_list, var->varno - 1);
+					key_attnos_list = list_insert_nth(key_attnos_list, var->varno - 1, NULL);
+				}
+				keys = bms_add_member(keys, i - FirstLowInvalidHeapAttributeNumber);
+			}
+		}
+		i++;
+	}
+
+	/* Collect RTE indexes of relations appearing in the FROM clause */
+	rels_in_from = get_relids_in_jointree((Node *) query->jointree, false, false);
+
+	/*
+	 * Check if all key attributes of relations in FROM are appearing in the target
+	 * list.  If an attribute remains in key_attnos_list in spite of the table is used
+	 * in FROM clause, the target is missing this key attribute, so we return NULL.
+	 */
+	i = 1;
+	foreach(lc, key_attnos_list)
+	{
+		Bitmapset *bms = (Bitmapset *)lfirst(lc);
+		if (!bms_is_empty(bms) && bms_is_member(i, rels_in_from))
+			return NULL;
+		i++;
+	}
+
+	return keys;
+}
diff --git a/src/backend/commands/matview.c b/src/backend/commands/matview.c
index f7d8007f796..eaf39f80cd3 100644
--- a/src/backend/commands/matview.c
+++ b/src/backend/commands/matview.c
@@ -23,24 +23,36 @@
 #include "catalog/indexing.h"
 #include "catalog/namespace.h"
 #include "catalog/pg_am.h"
+#include "catalog/pg_depend.h"
+#include "catalog/pg_trigger.h"
 #include "catalog/pg_opclass.h"
 #include "commands/matview.h"
 #include "commands/repack.h"
 #include "commands/tablecmds.h"
 #include "commands/tablespace.h"
+#include "commands/createas.h"
 #include "executor/executor.h"
 #include "executor/spi.h"
+#include "executor/tstoreReceiver.h"
 #include "miscadmin.h"
+#include "nodes/makefuncs.h"
+#include "parser/analyze.h"
+#include "parser/parse_clause.h"
+#include "parser/parse_func.h"
+#include "parser/parse_relation.h"
 #include "pgstat.h"
 #include "rewrite/rewriteHandler.h"
+#include "rewrite/rowsecurity.h"
 #include "storage/lmgr.h"
+#include "storage/lwlock.h"
 #include "tcop/tcopprot.h"
 #include "utils/builtins.h"
+#include "utils/fmgroids.h"
 #include "utils/lsyscache.h"
 #include "utils/rel.h"
 #include "utils/snapmgr.h"
 #include "utils/syscache.h"
-
+#include "utils/typcache.h"
 
 typedef struct
 {
@@ -53,6 +65,97 @@ typedef struct
 	BulkInsertState bistate;	/* bulk insert state */
 } DR_transientrel;
 
+#define MV_INIT_QUERYHASHSIZE	16
+
+/*
+ * MV_TriggerHashEntry
+ *
+ * Hash entry for base tables on which IVM trigger is invoked
+ */
+typedef struct MV_TriggerHashEntry
+{
+	Oid	matview_id;			/* OID of the materialized view */
+	int	before_trig_count;	/* count of before triggers invoked */
+	int	after_trig_count;	/* count of after triggers invoked */
+
+	Snapshot	snapshot;	/* Snapshot just before table change */
+
+	List   *tables;		/* List of MV_TriggerTable */
+	bool	has_old;	/* tuples are deleted from any table? */
+	bool	has_new;	/* tuples are inserted into any table? */
+
+	/*
+	 * List of sub-transaction IDs that incrementally updated the view.
+	 * This list is maintained through a transaction, and an ID is removed
+	 * when a sub-transaction is aborted. If any ID is left when the
+	 * transaction is committed, this means the view is incrementally
+	 * updated in this transaction.
+	 */
+	List   *subxids;
+} MV_TriggerHashEntry;
+
+/*
+ * MV_TriggerTable
+ *
+ * IVM related data for tables on which the trigger is invoked.
+ */
+typedef struct MV_TriggerTable
+{
+	Oid		table_id;			/* OID of the modified table */
+	List   *old_tuplestores;	/* tuplestores for deleted tuples */
+	List   *new_tuplestores;	/* tuplestores for inserted tuples */
+
+	List   *rte_indexes;		/* List of RTE index of the modified table */
+	RangeTblEntry *original_rte;	/* the original RTE saved before rewriting query */
+
+	Relation	rel;			/* relation of the modified table */
+	TupleTableSlot *slot;		/* for checking visibility in the pre-state table */
+} MV_TriggerTable;
+
+typedef struct DroppedImmvInfo
+{
+	Oid					immv_oid;
+	SubTransactionId	subxid;
+} DroppedImmvInfo;
+
+static HTAB *mv_trigger_info = NULL;
+static HTAB *dropped_immv = NULL;
+
+static HTAB *LastIvmUpdateHash;
+
+#define LAST_IVM_UPDATE_HASH_SIZE 256
+
+static void IvmShmemRequest(void *arg);
+
+/* hash table entries */
+typedef struct LastIvmUpdateEntry
+{
+	Oid		oid;	/* hash key */
+	FullTransactionId	last_ivm_update;
+} LastIvmUpdateEntry;
+
+const ShmemCallbacks IvmShmemCallbacks = {
+	.request_fn = IvmShmemRequest,
+};
+
+static void
+IvmShmemRequest(void *arg)
+{
+	ShmemRequestHash(.name = "LastIvmUpdate hash",
+					 .nelems = LAST_IVM_UPDATE_HASH_SIZE,
+					 .ptr = &LastIvmUpdateHash,
+					 .hash_info.keysize = sizeof(Oid),
+					 .hash_info.entrysize = sizeof(LastIvmUpdateEntry),
+					 .hash_flags = HASH_ELEM | HASH_BLOBS,
+		);
+}
+
+static bool in_delta_calculation = false;
+
+/* ENR name for materialized view delta */
+#define NEW_DELTA_ENRNAME "new_delta"
+#define OLD_DELTA_ENRNAME "old_delta"
+
 static int	matview_maintenance_depth = 0;
 
 static void transientrel_startup(DestReceiver *self, int operation, TupleDesc typeinfo);
@@ -60,6 +163,8 @@ static bool transientrel_receive(TupleTableSlot *slot, DestReceiver *self);
 static void transientrel_shutdown(DestReceiver *self);
 static void transientrel_destroy(DestReceiver *self);
 static uint64 refresh_matview_datafill(DestReceiver *dest, Query *query,
+									   QueryEnvironment *queryEnv,
+									   TupleDesc *resultTupleDesc,
 									   const char *queryString, bool is_create);
 static void refresh_by_match_merge(Oid matviewOid, Oid tempOid, Oid relowner,
 								   int save_sec_context);
@@ -67,6 +172,41 @@ static void refresh_by_heap_swap(Oid matviewOid, Oid OIDNewHeap, char relpersist
 static bool is_usable_unique_index(Relation indexRel);
 static void OpenMatViewIncrementalMaintenance(void);
 static void CloseMatViewIncrementalMaintenance(void);
+static Query *get_matview_query(Relation matviewRel);
+
+static Query *rewrite_query_for_preupdate_state(Query *query, List *tables,
+								  ParseState *pstate, Oid matviewid);
+static void register_delta_ENRs(ParseState *pstate, Query *query, List *tables);
+static char *make_subquery_targetlist_from_table(MV_TriggerTable *table);
+static char *make_delta_enr_name(const char *prefix, Oid relid, int count);
+static RangeTblEntry *get_prestate_rte(RangeTblEntry *rte, MV_TriggerTable *table,
+				 QueryEnvironment *queryEnv, Oid matviewid);
+static RangeTblEntry *makeDeltaTable(RangeTblEntry *rte, MV_TriggerTable *table,
+									 bool is_new, QueryEnvironment *queryEnv);
+static Query *rewrite_query_for_counting(Query *query, ParseState *pstate);
+
+static void calc_delta(MV_TriggerTable *table, int rte_index, Query *query,
+			DestReceiver *dest_old, DestReceiver *dest_new,
+			TupleDesc *tupdesc_old, TupleDesc *tupdesc_new,
+			QueryEnvironment *queryEnv);
+static Query *rewrite_query_for_postupdate_state(Query *query, MV_TriggerTable *table, int rte_index);
+
+static void apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *new_tuplestores,
+			TupleDesc tupdesc_old, TupleDesc tupdesc_new,
+			Query *query);
+static void apply_old_delta(const char *matviewname, const char *deltaname_old,
+				List *keys);
+static void apply_new_delta(const char *matviewname, const char *deltaname_new,
+				StringInfo target_list);
+static char *get_matching_condition_string(List *keys);
+static void generate_equal(StringInfo querybuf, Oid opttype,
+			   const char *leftop, const char *rightop);
+
+static void mv_InitHashTables(void);
+static void clean_up_IVM_hash_entry(MV_TriggerHashEntry *entry, bool is_abort,
+									SubTransactionId subxid);
+static void setLastUpdateXid(Oid immv_oid, FullTransactionId xid);
+static FullTransactionId getLastUpdateXid(Oid immv_oid);
 
 /*
  * SetMatViewPopulatedState
@@ -108,6 +248,46 @@ SetMatViewPopulatedState(Relation relation, bool newstate)
 	CommandCounterIncrement();
 }
 
+/*
+ * SetMatViewIVMState
+ *		Mark a materialized view as IVM, or not.
+ *
+ * NOTE: caller must be holding an appropriate lock on the relation.
+ */
+void
+SetMatViewIVMState(Relation relation, bool newstate)
+{
+	Relation	pgrel;
+	HeapTuple	tuple;
+
+	Assert(relation->rd_rel->relkind == RELKIND_MATVIEW);
+
+	/*
+	 * Update relation's pg_class entry.  Crucial side-effect: other backends
+	 * (and this one too!) are sent SI message to make them rebuild relcache
+	 * entries.
+	 */
+	pgrel = table_open(RelationRelationId, RowExclusiveLock);
+	tuple = SearchSysCacheCopy1(RELOID,
+								ObjectIdGetDatum(RelationGetRelid(relation)));
+	if (!HeapTupleIsValid(tuple))
+		elog(ERROR, "cache lookup failed for relation %u",
+			 RelationGetRelid(relation));
+
+	((Form_pg_class) GETSTRUCT(tuple))->relisivm = newstate;
+
+	CatalogTupleUpdate(pgrel, &tuple->t_self, tuple);
+
+	heap_freetuple(tuple);
+	table_close(pgrel, RowExclusiveLock);
+
+	/*
+	 * Advance command counter to make the updated pg_class row locally
+	 * visible.
+	 */
+	CommandCounterIncrement();
+}
+
 /*
  * ExecRefreshMatView -- execute a REFRESH MATERIALIZED VIEW command
  *
@@ -166,8 +346,6 @@ RefreshMatViewByOid(Oid matviewOid, bool is_create, bool skipData,
 					QueryCompletion *qc)
 {
 	Relation	matviewRel;
-	RewriteRule *rule;
-	List	   *actions;
 	Query	   *dataQuery;
 	Oid			tableSpace;
 	Oid			relowner;
@@ -178,6 +356,7 @@ RefreshMatViewByOid(Oid matviewOid, bool is_create, bool skipData,
 	int			save_sec_context;
 	int			save_nestlevel;
 	ObjectAddress address;
+	bool oldPopulated;
 
 	matviewRel = table_open(matviewOid, NoLock);
 	relowner = matviewRel->rd_rel->relowner;
@@ -193,6 +372,8 @@ RefreshMatViewByOid(Oid matviewOid, bool is_create, bool skipData,
 	save_nestlevel = NewGUCNestLevel();
 	RestrictSearchPath();
 
+	oldPopulated = RelationIsPopulated(matviewRel);
+
 	/* Make sure it is a materialized view. */
 	if (matviewRel->rd_rel->relkind != RELKIND_MATVIEW)
 		ereport(ERROR,
@@ -213,32 +394,7 @@ RefreshMatViewByOid(Oid matviewOid, bool is_create, bool skipData,
 				 errmsg("%s options %s and %s cannot be used together",
 						"REFRESH", "CONCURRENTLY", "WITH NO DATA")));
 
-	/*
-	 * Check that everything is correct for a refresh. Problems at this point
-	 * are internal errors, so elog is sufficient.
-	 */
-	if (matviewRel->rd_rel->relhasrules == false ||
-		matviewRel->rd_rules->numLocks < 1)
-		elog(ERROR,
-			 "materialized view \"%s\" is missing rewrite information",
-			 RelationGetRelationName(matviewRel));
-
-	if (matviewRel->rd_rules->numLocks > 1)
-		elog(ERROR,
-			 "materialized view \"%s\" has too many rules",
-			 RelationGetRelationName(matviewRel));
-
-	rule = matviewRel->rd_rules->rules[0];
-	if (rule->event != CMD_SELECT || !(rule->isInstead))
-		elog(ERROR,
-			 "the rule for materialized view \"%s\" is not a SELECT INSTEAD OF rule",
-			 RelationGetRelationName(matviewRel));
-
-	actions = rule->actions;
-	if (list_length(actions) != 1)
-		elog(ERROR,
-			 "the rule for materialized view \"%s\" is not a single action",
-			 RelationGetRelationName(matviewRel));
+	dataQuery = get_matview_query(matviewRel);
 
 	/*
 	 * Check that there is a unique index with no WHERE clause on one or more
@@ -275,12 +431,6 @@ RefreshMatViewByOid(Oid matviewOid, bool is_create, bool skipData,
 					 errhint("Create a unique index with no WHERE clause on one or more columns of the materialized view.")));
 	}
 
-	/*
-	 * The stored query was rewritten at the time of the MV definition, but
-	 * has not been scribbled on by the planner.
-	 */
-	dataQuery = linitial_node(Query, actions);
-
 	/*
 	 * Check for active uses of the relation in the current transaction, such
 	 * as open scans.
@@ -310,6 +460,90 @@ RefreshMatViewByOid(Oid matviewOid, bool is_create, bool skipData,
 		relpersistence = matviewRel->rd_rel->relpersistence;
 	}
 
+	/* delete IMMV triggers. */
+	if (RelationIsIVM(matviewRel) && skipData)
+	{
+		Relation	tgRel;
+		Relation	depRel;
+		ScanKeyData key;
+		SysScanDesc scan;
+		HeapTuple	tup;
+		ObjectAddresses *immv_triggers;
+
+		immv_triggers = new_object_addresses();
+
+		tgRel = table_open(TriggerRelationId, RowExclusiveLock);
+		depRel = table_open(DependRelationId, RowExclusiveLock);
+
+		/* search triggers that depends on IMMV. */
+		ScanKeyInit(&key,
+					Anum_pg_depend_refobjid,
+					BTEqualStrategyNumber, F_OIDEQ,
+					ObjectIdGetDatum(matviewOid));
+		scan = systable_beginscan(depRel, DependReferenceIndexId, true,
+								  NULL, 1, &key);
+		while ((tup = systable_getnext(scan)) != NULL)
+		{
+			ObjectAddress obj;
+			Form_pg_depend foundDep = (Form_pg_depend) GETSTRUCT(tup);
+
+			if (foundDep->classid == TriggerRelationId)
+			{
+				HeapTuple	tgtup;
+				ScanKeyData tgkey[1];
+				SysScanDesc tgscan;
+				Form_pg_trigger tgform;
+
+				/* Find the trigger name. */
+				ScanKeyInit(&tgkey[0],
+							Anum_pg_trigger_oid,
+							BTEqualStrategyNumber, F_OIDEQ,
+							ObjectIdGetDatum(foundDep->objid));
+
+				tgscan = systable_beginscan(tgRel, TriggerOidIndexId, true,
+											NULL, 1, tgkey);
+				tgtup = systable_getnext(tgscan);
+				if (!HeapTupleIsValid(tgtup))
+					elog(ERROR, "could not find tuple for immv trigger %u", foundDep->objid);
+
+				tgform = (Form_pg_trigger) GETSTRUCT(tgtup);
+
+				/* If trigger is created by IMMV, delete it. */
+				if (strncmp(NameStr(tgform->tgname), "IVM_trigger_", 12) == 0)
+				{
+					obj.classId = foundDep->classid;
+					obj.objectId = foundDep->objid;
+					obj.objectSubId = foundDep->refobjsubid;
+					add_exact_object_address(&obj, immv_triggers);
+				}
+				systable_endscan(tgscan);
+			}
+		}
+		systable_endscan(scan);
+
+		performMultipleDeletions(immv_triggers, DROP_RESTRICT, PERFORM_DELETION_INTERNAL);
+
+		table_close(depRel, RowExclusiveLock);
+		table_close(tgRel, RowExclusiveLock);
+		free_object_addresses(immv_triggers);
+	}
+
+	/*
+	 * Create triggers on incremental maintainable materialized view
+	 * This argument should use 'dataQuery'. This needs to use a rewritten query,
+	 * because a sublink in jointree is not supported by this function.
+	 *
+	 * This is performed before generating data because we have to wait
+	 * concurrent transactions modifying a base table and then take a snapshot
+	 * to see changes by these transactions to make sure a consistent view
+	 * is created.
+	 */
+	if (RelationIsIVM(matviewRel) && !skipData && !oldPopulated)
+	{
+		CreateIvmTriggersOnBaseTables(dataQuery, matviewOid);
+		CreateIndexOnIMMV(dataQuery, matviewRel);
+	}
+
 	/*
 	 * Create the transient table that will receive the regenerated data. Lock
 	 * it against access by any other process until commit (by which time it
@@ -326,8 +560,43 @@ RefreshMatViewByOid(Oid matviewOid, bool is_create, bool skipData,
 		DestReceiver *dest;
 
 		dest = CreateTransientRelDestReceiver(OIDNewHeap);
-		processed = refresh_matview_datafill(dest, dataQuery, queryString,
-											 is_create);
+
+		if (RelationIsIVM(matviewRel))
+		{
+			/*
+			 * In READ COMMITTED, get and push the latest snapshot again to see the
+			 * results of concurrent transactions committed after the current
+			 * transaction started.
+			 */
+			if (!IsolationUsesXactSnapshot())
+				PushActiveSnapshot(GetTransactionSnapshot());
+
+			/*
+			 * If a concurrent transaction updated the view incrementally and was
+			 * committed before we acquired the lock, the results of refresh_immv could
+			 * be inconsistent. Therefore, we have to check the transaction ID of the
+			 * most recent update of the view, and if this was in progress at the
+			 * transaction start, raise an error to prevent anomalies.
+			 */
+			if (!is_create)
+			{
+				FullTransactionId xid;
+
+				xid = getLastUpdateXid(matviewOid);
+				if (XidInMVCCSnapshot(XidFromFullTransactionId(xid), GetActiveSnapshot()))
+					ereport(ERROR,
+							(errcode(ERRCODE_T_R_SERIALIZATION_FAILURE),
+							 errmsg("the materialized view is incrementally updated in concurrent transaction"),
+							 errhint("The transaction might succeed if retried.")));
+			}
+		}
+
+		processed = refresh_matview_datafill(dest, dataQuery, NULL, NULL,
+											 queryString, is_create);
+
+		/* Pop the original snapshot. */
+		if (RelationIsIVM(matviewRel) && !IsolationUsesXactSnapshot())
+			PopActiveSnapshot();
 	}
 
 	/* Make the matview match the newly generated data. */
@@ -402,6 +671,8 @@ RefreshMatViewByOid(Oid matviewOid, bool is_create, bool skipData,
  */
 static uint64
 refresh_matview_datafill(DestReceiver *dest, Query *query,
+						 QueryEnvironment *queryEnv,
+						 TupleDesc *resultTupleDesc,
 						 const char *queryString, bool is_create)
 {
 	List	   *rewritten;
@@ -439,7 +710,7 @@ refresh_matview_datafill(DestReceiver *dest, Query *query,
 	/* Create a QueryDesc, redirecting output to our tuple receiver */
 	queryDesc = CreateQueryDesc(plan, queryString,
 								GetActiveSnapshot(), InvalidSnapshot,
-								dest, NULL, NULL, 0);
+								dest, NULL, queryEnv ? queryEnv: NULL, 0);
 
 	/* call ExecutorStart to prepare the plan for execution */
 	ExecutorStart(queryDesc, 0);
@@ -449,6 +720,9 @@ refresh_matview_datafill(DestReceiver *dest, Query *query,
 
 	processed = queryDesc->estate->es_processed;
 
+	if (resultTupleDesc)
+		*resultTupleDesc = CreateTupleDescCopy(queryDesc->tupDesc);
+
 	/* and clean up */
 	ExecutorFinish(queryDesc);
 	ExecutorEnd(queryDesc);
@@ -967,3 +1241,1488 @@ CloseMatViewIncrementalMaintenance(void)
 	matview_maintenance_depth--;
 	Assert(matview_maintenance_depth >= 0);
 }
+
+/*
+ * get_matview_query - get the Query from a matview's _RETURN rule.
+ */
+static Query *
+get_matview_query(Relation matviewRel)
+{
+	RewriteRule *rule;
+	List * actions;
+
+	/*
+	 * Check that everything is correct for a refresh. Problems at this point
+	 * are internal errors, so elog is sufficient.
+	 */
+	if (matviewRel->rd_rel->relhasrules == false ||
+		matviewRel->rd_rules->numLocks < 1)
+		elog(ERROR,
+			 "materialized view \"%s\" is missing rewrite information",
+			 RelationGetRelationName(matviewRel));
+
+	if (matviewRel->rd_rules->numLocks > 1)
+		elog(ERROR,
+			 "materialized view \"%s\" has too many rules",
+			 RelationGetRelationName(matviewRel));
+
+	rule = matviewRel->rd_rules->rules[0];
+	if (rule->event != CMD_SELECT || !(rule->isInstead))
+		elog(ERROR,
+			 "the rule for materialized view \"%s\" is not a SELECT INSTEAD OF rule",
+			 RelationGetRelationName(matviewRel));
+
+	actions = rule->actions;
+	if (list_length(actions) != 1)
+		elog(ERROR,
+			 "the rule for materialized view \"%s\" is not a single action",
+			 RelationGetRelationName(matviewRel));
+
+	/*
+	 * The stored query was rewritten at the time of the MV definition, but
+	 * has not been scribbled on by the planner.
+	 */
+	return linitial_node(Query, actions);
+}
+
+
+/* ----------------------------------------------------
+ *		Incremental View Maintenance routines
+ * ---------------------------------------------------
+ */
+
+/*
+ * IVM_immediate_before
+ *
+ * IVM trigger function invoked before base table is modified. If this is
+ * invoked firstly in the same statement, we save the transaction id and the
+ * command id at that time.
+ */
+Datum
+IVM_immediate_before(PG_FUNCTION_ARGS)
+{
+	TriggerData *trigdata = (TriggerData *) fcinfo->context;
+	char	   *matviewOid_text = trigdata->tg_trigger->tgargs[0];
+	char	   *ex_lock_text = trigdata->tg_trigger->tgargs[1];
+	Oid			matviewOid;
+	MV_TriggerHashEntry *entry;
+	bool	found;
+	bool	ex_lock;
+
+	matviewOid = DatumGetObjectId(DirectFunctionCall1(oidin, CStringGetDatum(matviewOid_text)));
+	ex_lock = DatumGetBool(DirectFunctionCall1(boolin, CStringGetDatum(ex_lock_text)));
+
+	/* If the view has more than one tables, we have to use an exclusive lock. */
+	if (ex_lock)
+	{
+		FullTransactionId xid;
+
+		/*
+		 * Wait for concurrent transactions which update this materialized view at
+		 * READ COMMITED. This is needed to see changes committed in other
+		 * transactions. No wait and raise an error at REPEATABLE READ or
+		 * SERIALIZABLE to prevent update anomalies of matviews.
+		 * XXX: dead-lock is possible here.
+		 */
+		if (!IsolationUsesXactSnapshot())
+			LockRelationOid(matviewOid, ExclusiveLock);
+		else if (!ConditionalLockRelationOid(matviewOid, ExclusiveLock))
+		{
+			/* try to throw error by name; relation could be deleted... */
+			char	   *relname = get_rel_name(matviewOid);
+
+			if (!relname)
+				ereport(ERROR,
+						(errcode(ERRCODE_LOCK_NOT_AVAILABLE),
+						errmsg("could not obtain lock on materialized view during incremental maintenance")));
+
+			ereport(ERROR,
+					(errcode(ERRCODE_LOCK_NOT_AVAILABLE),
+					errmsg("could not obtain lock on materialized view \"%s\" during incremental maintenance",
+							relname)));
+		}
+
+		/*
+		 * Even if we can acquire an lock, a concurrent transaction could have
+		 * updated the view incrementally and been committed before we acquired
+		 * the lock. Therefore, we have to check the transaction ID of the most
+		 * recent update of the view, and if this was in progress at the
+		 * transaction start, raise an error to prevent anomalies.
+		 */
+		xid = getLastUpdateXid(matviewOid);
+		if (XidInMVCCSnapshot(XidFromFullTransactionId(xid), GetTransactionSnapshot()))
+			ereport(ERROR,
+					(errcode(ERRCODE_T_R_SERIALIZATION_FAILURE),
+					 errmsg("the materialized view is incrementally updated in concurrent transaction"),
+					 errhint("The transaction might succeed if retried.")));
+	}
+	else
+		LockRelationOid(matviewOid, RowExclusiveLock);
+
+	/*
+	 * On the first call initialize the hashtable
+	 */
+	if (!mv_trigger_info)
+		mv_InitHashTables();
+
+	entry = (MV_TriggerHashEntry *) hash_search(mv_trigger_info,
+											  (void *) &matviewOid,
+											  HASH_ENTER, &found);
+
+	/* On the first BEFORE to update the view, initialize trigger data */
+	if (!found || entry->snapshot == InvalidSnapshot)
+	{
+		Snapshot snapshot;
+
+		/*
+		 * Get a snapshot just before the table was modified for checking
+		 * tuple visibility in the pre-update state of the table.
+		 *
+		 * In READ COMMITTED, use the latest snapshot again to see the
+		 * results of concurrent transactions committed after the current
+		 * transaction started.
+		 */
+		if (IsolationUsesXactSnapshot())
+			snapshot = GetActiveSnapshot();
+		else
+			snapshot = GetTransactionSnapshot();
+
+		entry->matview_id = matviewOid;
+		entry->before_trig_count = 0;
+		entry->after_trig_count = 0;
+		entry->snapshot = RegisterSnapshot(snapshot);
+		entry->tables = NIL;
+		entry->has_old = false;
+		entry->has_new = false;
+
+		/*
+		 * If this is the first table modifying query in the transaction,
+		 * initialize the list of subxids.
+		 */
+		if (!found)
+			entry->subxids = NIL;
+	}
+
+	entry->before_trig_count++;
+
+	return PointerGetDatum(NULL);
+}
+
+/*
+ * IVM_immediate_maintenance
+ *
+ * IVM trigger function invoked after base table is modified.
+ * For each table, tuplestores of transition tables are collected.
+ * and after the last modification
+ */
+Datum
+IVM_immediate_maintenance(PG_FUNCTION_ARGS)
+{
+	TriggerData *trigdata = (TriggerData *) fcinfo->context;
+	Relation	rel;
+	Oid			relid;
+	Oid			matviewOid;
+	Query	   *query;
+	Query	   *rewritten = NULL;
+	char	   *matviewOid_text = trigdata->tg_trigger->tgargs[0];
+	Relation	matviewRel;
+	int old_depth = matview_maintenance_depth;
+	SubTransactionId subxid;
+
+	Oid			relowner;
+	Tuplestorestate *old_tuplestore = NULL;
+	Tuplestorestate *new_tuplestore = NULL;
+	DestReceiver *dest_new = NULL, *dest_old = NULL;
+	Oid			save_userid;
+	int			save_sec_context;
+	int			save_nestlevel;
+
+	MV_TriggerHashEntry *entry;
+	MV_TriggerTable		*table;
+	bool	found;
+
+	ParseState		 *pstate;
+	QueryEnvironment *queryEnv = create_queryEnv();
+	MemoryContext	oldcxt;
+	ListCell   *lc;
+	int			i;
+
+
+	/* Create a ParseState for rewriting the view definition query */
+	pstate = make_parsestate(NULL);
+	pstate->p_queryEnv = queryEnv;
+	pstate->p_expr_kind = EXPR_KIND_SELECT_TARGET;
+
+	rel = trigdata->tg_relation;
+	relid = rel->rd_id;
+
+	matviewOid = DatumGetObjectId(DirectFunctionCall1(oidin, CStringGetDatum(matviewOid_text)));
+
+	/*
+	 * On the first call initialize the hashtable
+	 */
+	if (!mv_trigger_info)
+		mv_InitHashTables();
+
+	/* get the entry for this materialized view */
+	entry = (MV_TriggerHashEntry *) hash_search(mv_trigger_info,
+											  (void *) &matviewOid,
+											  HASH_FIND, &found);
+	Assert (found && entry != NULL);
+	entry->after_trig_count++;
+
+	/* search the entry for the modified table and create new entry if not found */
+	found = false;
+	foreach(lc, entry->tables)
+	{
+		table = (MV_TriggerTable *) lfirst(lc);
+		if (table->table_id == relid)
+		{
+			found = true;
+			break;
+		}
+	}
+	if (!found)
+	{
+		oldcxt = MemoryContextSwitchTo(TopTransactionContext);
+
+		table = (MV_TriggerTable *) palloc0(sizeof(MV_TriggerTable));
+		table->table_id = relid;
+		table->old_tuplestores = NIL;
+		table->new_tuplestores = NIL;
+		table->rte_indexes = NIL;
+		table->slot = MakeSingleTupleTableSlot(RelationGetDescr(rel), table_slot_callbacks(rel));
+		/* We assume we have at least RowExclusiveLock on modified tables. */
+		table->rel = table_open(RelationGetRelid(rel), NoLock);
+		entry->tables = lappend(entry->tables, table);
+
+		MemoryContextSwitchTo(oldcxt);
+	}
+
+	/* Save the transition tables and make a request to not free immediately */
+	if (trigdata->tg_oldtable)
+	{
+		oldcxt = MemoryContextSwitchTo(TopTransactionContext);
+		table->old_tuplestores = lappend(table->old_tuplestores, trigdata->tg_oldtable);
+		entry->has_old = true;
+		MemoryContextSwitchTo(oldcxt);
+	}
+	if (trigdata->tg_newtable)
+	{
+		oldcxt = MemoryContextSwitchTo(TopTransactionContext);
+		table->new_tuplestores = lappend(table->new_tuplestores, trigdata->tg_newtable);
+		entry->has_new = true;
+		MemoryContextSwitchTo(oldcxt);
+	}
+	if (entry->has_new || entry->has_old)
+	{
+		CmdType cmd;
+
+		if (TRIGGER_FIRED_BY_INSERT(trigdata->tg_event))
+			cmd = CMD_INSERT;
+		else if (TRIGGER_FIRED_BY_DELETE(trigdata->tg_event))
+			cmd = CMD_DELETE;
+		else if (TRIGGER_FIRED_BY_UPDATE(trigdata->tg_event))
+			cmd = CMD_UPDATE;
+		else
+			elog(ERROR,"unsupported trigger type");
+
+		/* Prolong lifespan of transition tables to the end of the last AFTER trigger */
+		SetTransitionTablePreserved(relid, cmd);
+	}
+
+
+	/* If this is not the last AFTER trigger call, immediately exit. */
+	Assert (entry->before_trig_count >= entry->after_trig_count);
+	if (entry->before_trig_count != entry->after_trig_count)
+		return PointerGetDatum(NULL);
+
+	/*
+	 * If this is the last AFTER trigger call, continue and update the view.
+	 */
+
+	/* record the subxid that updated the view incrementally */
+	subxid = GetCurrentSubTransactionId();
+	if (!list_member_xid(entry->subxids, subxid))
+	{
+		oldcxt = MemoryContextSwitchTo(TopTransactionContext);
+		entry->subxids = lappend_xid(entry->subxids, subxid);
+		MemoryContextSwitchTo(oldcxt);
+	}
+
+	/*
+	 * Advance command counter to make the updated base table rows locally
+	 * visible.
+	 */
+	CommandCounterIncrement();
+
+	matviewRel = table_open(matviewOid, NoLock);
+
+	/* Make sure it is a materialized view. */
+	Assert(matviewRel->rd_rel->relkind == RELKIND_MATVIEW);
+
+	/*
+	 * In READ COMMITTED, get and push the latest snapshot again to see the
+	 * results of concurrent transactions committed after the current
+	 * transaction started.
+	 */
+	if (!IsolationUsesXactSnapshot())
+		PushActiveSnapshot(GetTransactionSnapshot());
+
+	/*
+	 * Check for active uses of the relation in the current transaction, such
+	 * as open scans.
+	 *
+	 * NB: We count on this to protect us against problems with refreshing the
+	 * data using TABLE_INSERT_FROZEN.
+	 */
+	CheckTableNotInUse(matviewRel, "refresh a materialized view incrementally");
+
+	/*
+	 * Switch to the owner's userid, so that any functions are run as that
+	 * user.  Also arrange to make GUC variable changes local to this command.
+	 * We will switch modes when we are about to execute user code.
+	 */
+	relowner = matviewRel->rd_rel->relowner;
+	GetUserIdAndSecContext(&save_userid, &save_sec_context);
+	SetUserIdAndSecContext(relowner,
+						   save_sec_context | SECURITY_RESTRICTED_OPERATION);
+	save_nestlevel = NewGUCNestLevel();
+
+	/* get view query*/
+	query = get_matview_query(matviewRel);
+
+	/*
+	 * When a base table is truncated, the view content will be empty if the
+	 * view definition query does not contain an aggregate without a GROUP clause.
+	 * Therefore, such views can be truncated.
+	 */
+	if (TRIGGER_FIRED_BY_TRUNCATE(trigdata->tg_event))
+	{
+		ExecuteTruncateGuts(list_make1(matviewRel), list_make1_oid(matviewOid),
+							NIL, DROP_RESTRICT, false, false);
+
+		/* Clean up hash entry and delete tuplestores */
+		clean_up_IVM_hash_entry(entry, false, InvalidSubTransactionId);
+
+		/* Pop the original snapshot. */
+		if (!IsolationUsesXactSnapshot())
+			PopActiveSnapshot();
+
+		table_close(matviewRel, NoLock);
+
+		/* Roll back any GUC changes */
+		AtEOXact_GUC(false, save_nestlevel);
+
+		/* Restore userid and security context */
+		SetUserIdAndSecContext(save_userid, save_sec_context);
+
+		return PointerGetDatum(NULL);
+	}
+
+	/*
+	 * rewrite query for calculating deltas
+	 */
+
+	rewritten = copyObject(query);
+
+	/* Replace resnames in a target list with materialized view's attnames */
+	i = 0;
+	foreach (lc, rewritten->targetList)
+	{
+		TargetEntry *tle = (TargetEntry *) lfirst(lc);
+		Form_pg_attribute attr = TupleDescAttr(matviewRel->rd_att, i);
+		char *resname = NameStr(attr->attname);
+
+		tle->resname = pstrdup(resname);
+		i++;
+	}
+
+	/* Set all tables in the query to pre-update state */
+	rewritten = rewrite_query_for_preupdate_state(rewritten, entry->tables,
+												  pstate, matviewOid);
+	/* Rewrite for counting duplicated tuples */
+	rewritten = rewrite_query_for_counting(rewritten, pstate);
+
+	/* Create tuplestores to store view deltas */
+	if (entry->has_old)
+	{
+		oldcxt = MemoryContextSwitchTo(TopTransactionContext);
+
+		old_tuplestore = tuplestore_begin_heap(false, false, work_mem);
+		dest_old = CreateDestReceiver(DestTuplestore);
+		SetTuplestoreDestReceiverParams(dest_old,
+									old_tuplestore,
+									TopTransactionContext,
+									false,
+									NULL,
+									NULL);
+
+		MemoryContextSwitchTo(oldcxt);
+	}
+	if (entry->has_new)
+	{
+		oldcxt = MemoryContextSwitchTo(TopTransactionContext);
+
+		new_tuplestore = tuplestore_begin_heap(false, false, work_mem);
+		dest_new = CreateDestReceiver(DestTuplestore);
+		SetTuplestoreDestReceiverParams(dest_new,
+									new_tuplestore,
+									TopTransactionContext,
+									false,
+									NULL,
+									NULL);
+		MemoryContextSwitchTo(oldcxt);
+	}
+
+	/* for all modified tables */
+	foreach(lc, entry->tables)
+	{
+		ListCell *lc2;
+
+		table = (MV_TriggerTable *) lfirst(lc);
+
+		/* loop for self-join */
+		foreach(lc2, table->rte_indexes)
+		{
+			int	rte_index = lfirst_int(lc2);
+			TupleDesc		tupdesc_old;
+			TupleDesc		tupdesc_new;
+
+			/* calculate delta tables */
+			calc_delta(table, rte_index, rewritten, dest_old, dest_new,
+					   &tupdesc_old, &tupdesc_new, queryEnv);
+
+			/* Set the table in the query to post-update state */
+			rewritten = rewrite_query_for_postupdate_state(rewritten, table, rte_index);
+
+			PG_TRY();
+			{
+				/* apply the delta tables to the materialized view */
+				apply_delta(matviewOid, old_tuplestore, new_tuplestore,
+							tupdesc_old, tupdesc_new, query);
+			}
+			PG_CATCH();
+			{
+				matview_maintenance_depth = old_depth;
+				PG_RE_THROW();
+			}
+			PG_END_TRY();
+
+			/* clear view delta tuplestores */
+			if (old_tuplestore)
+				tuplestore_clear(old_tuplestore);
+			if (new_tuplestore)
+				tuplestore_clear(new_tuplestore);
+		}
+	}
+
+	/* Clean up hash entry and delete tuplestores */
+	clean_up_IVM_hash_entry(entry, false, InvalidSubTransactionId);
+	if (old_tuplestore)
+	{
+		dest_old->rDestroy(dest_old);
+		tuplestore_end(old_tuplestore);
+	}
+	if (new_tuplestore)
+	{
+		dest_new->rDestroy(dest_new);
+		tuplestore_end(new_tuplestore);
+	}
+
+	/* Pop the original snapshot. */
+	if (!IsolationUsesXactSnapshot())
+		PopActiveSnapshot();
+
+	table_close(matviewRel, NoLock);
+
+	/* Roll back any GUC changes */
+	AtEOXact_GUC(false, save_nestlevel);
+
+	/* Restore userid and security context */
+	SetUserIdAndSecContext(save_userid, save_sec_context);
+
+	return PointerGetDatum(NULL);
+}
+
+/*
+ * rewrite_query_for_preupdate_state
+ *
+ * Rewrite the query so that base tables' RTEs will represent "pre-update"
+ * state of tables. This is necessary to calculate view delta after multiple
+ * tables are modified.
+ */
+static Query*
+rewrite_query_for_preupdate_state(Query *query, List *tables,
+								  ParseState *pstate, Oid matviewid)
+{
+	ListCell *lc;
+	int num_rte = list_length(query->rtable);
+	int i;
+
+
+	/* register delta ENRs */
+	register_delta_ENRs(pstate, query, tables);
+
+	/* XXX: Is necessary? Is this right timing? */
+	AcquireRewriteLocks(query, true, false);
+
+	i = 1;
+	foreach(lc, query->rtable)
+	{
+		RangeTblEntry *r = (RangeTblEntry*) lfirst(lc);
+
+		ListCell *lc2;
+		foreach(lc2, tables)
+		{
+			MV_TriggerTable *table = (MV_TriggerTable *) lfirst(lc2);
+			/*
+			 * if the modified table is found then replace the original RTE with
+			 * "pre-state" RTE and append its index to the list.
+			 */
+			if (r->relid == table->table_id)
+			{
+				List *securityQuals;
+				List *withCheckOptions;
+				bool  hasRowSecurity;
+				bool  hasSubLinks;
+
+				RangeTblEntry *rte_pre = get_prestate_rte(r, table, pstate->p_queryEnv, matviewid);
+
+				/*
+				 * Set a row security poslicies of the modified table to the subquery RTE which
+				 * represents the pre-update state of the table.
+				 */
+				get_row_security_policies(query, table->original_rte, i,
+										  &securityQuals, &withCheckOptions,
+										  &hasRowSecurity, &hasSubLinks);
+
+				if (hasRowSecurity)
+				{
+					query->hasRowSecurity = true;
+					rte_pre->security_barrier = true;
+				}
+				if (hasSubLinks)
+					query->hasSubLinks = true;
+
+				rte_pre->securityQuals = securityQuals;
+				lfirst(lc) = rte_pre;
+
+				table->rte_indexes = lappend_int(table->rte_indexes, i);
+				break;
+			}
+		}
+
+		/* finish the loop if we processed all RTE included in the original query */
+		if (i++ >= num_rte)
+			break;
+	}
+
+	return query;
+}
+
+/*
+ * register_delta_ENRs
+ *
+ * For all modified tables, make ENRs for their transition tables
+ * and register them to the queryEnv. ENR's RTEs are also appended
+ * into the list in query tree.
+ */
+static void
+register_delta_ENRs(ParseState *pstate, Query *query, List *tables)
+{
+	QueryEnvironment *queryEnv = pstate->p_queryEnv;
+	ListCell *lc;
+	RangeTblEntry	*rte;
+
+	foreach(lc, tables)
+	{
+		MV_TriggerTable *table = (MV_TriggerTable *) lfirst(lc);
+		ListCell *lc2;
+		int count;
+
+		count = 0;
+		foreach(lc2, table->old_tuplestores)
+		{
+			Tuplestorestate *oldtable = (Tuplestorestate *) lfirst(lc2);
+			EphemeralNamedRelation enr =
+				palloc(sizeof(EphemeralNamedRelationData));
+			ParseNamespaceItem *nsitem;
+
+			enr->md.name = make_delta_enr_name("old", table->table_id, count);
+			enr->md.reliddesc = table->table_id;
+			enr->md.tupdesc = NULL;
+			enr->md.enrtype = ENR_NAMED_TUPLESTORE;
+			enr->md.enrtuples = tuplestore_tuple_count(oldtable);
+			enr->reldata = oldtable;
+			register_ENR(queryEnv, enr);
+
+			nsitem = addRangeTableEntryForENR(pstate, makeRangeVar(NULL, enr->md.name, -1), true);
+			rte = nsitem->p_rte;
+
+			query->rtable = lappend(query->rtable, rte);
+
+			count++;
+		}
+
+		count = 0;
+		foreach(lc2, table->new_tuplestores)
+		{
+			Tuplestorestate *newtable = (Tuplestorestate *) lfirst(lc2);
+			EphemeralNamedRelation enr =
+				palloc(sizeof(EphemeralNamedRelationData));
+			ParseNamespaceItem *nsitem;
+
+			enr->md.name = make_delta_enr_name("new", table->table_id, count);
+			enr->md.reliddesc = table->table_id;
+			enr->md.tupdesc = NULL;
+			enr->md.enrtype = ENR_NAMED_TUPLESTORE;
+			enr->md.enrtuples = tuplestore_tuple_count(newtable);
+			enr->reldata = newtable;
+			register_ENR(queryEnv, enr);
+
+			nsitem = addRangeTableEntryForENR(pstate, makeRangeVar(NULL, enr->md.name, -1), true);
+			rte = nsitem->p_rte;
+
+			query->rtable = lappend(query->rtable, rte);
+
+			count++;
+		}
+	}
+}
+
+#define DatumGetItemPointer(X)	 ((ItemPointer) DatumGetPointer(X))
+#define PG_GETARG_ITEMPOINTER(n) DatumGetItemPointer(PG_GETARG_DATUM(n))
+
+/*
+ * ivm_visible_in_prestate
+ *
+ * Check visibility of a tuple specified by the tableoid and item pointer
+ * using the snapshot taken just before the table was modified.
+ */
+Datum
+ivm_visible_in_prestate(PG_FUNCTION_ARGS)
+{
+	Oid			tableoid = PG_GETARG_OID(0);
+	ItemPointer itemPtr = PG_GETARG_ITEMPOINTER(1);
+	Oid			matviewOid = PG_GETARG_OID(2);
+	MV_TriggerHashEntry *entry;
+	MV_TriggerTable		*table = NULL;
+	ListCell   *lc;
+	bool	found;
+	bool	result;
+
+	if (!in_delta_calculation)
+		ereport(ERROR,
+				(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+				 errmsg("ivm_visible_in_prestate can be called only in delta calculation")));
+
+	entry = (MV_TriggerHashEntry *) hash_search(mv_trigger_info,
+											  (void *) &matviewOid,
+											  HASH_FIND, &found);
+	Assert (found && entry != NULL);
+
+	foreach(lc, entry->tables)
+	{
+		table = (MV_TriggerTable *) lfirst(lc);
+		if (table->table_id == tableoid)
+			break;
+	}
+
+	Assert (table != NULL);
+
+	result = table_tuple_fetch_row_version(table->rel, itemPtr, entry->snapshot, table->slot);
+
+	PG_RETURN_BOOL(result);
+}
+
+/*
+ * get_prestate_rte
+ *
+ * Rewrite RTE of the modified table to a subquery which represents
+ * "pre-state" table. The original RTE is saved in table->rte_original.
+ */
+static RangeTblEntry*
+get_prestate_rte(RangeTblEntry *rte, MV_TriggerTable *table,
+				 QueryEnvironment *queryEnv, Oid matviewid)
+{
+	StringInfoData str;
+	RawStmt *raw;
+	Query *subquery;
+	ParseState *pstate;
+	char *relname;
+	static char *subquery_tl;
+	int i;
+
+	pstate = make_parsestate(NULL);
+	pstate->p_queryEnv = queryEnv;
+	pstate->p_expr_kind = EXPR_KIND_SELECT_TARGET;
+
+	relname = quote_qualified_identifier(
+					get_namespace_name(RelationGetNamespace(table->rel)),
+									   RelationGetRelationName(table->rel));
+
+	subquery_tl = make_subquery_targetlist_from_table(table);
+
+	/*
+	 * Filtering inserted row using the snapshot taken before the table
+	 * is modified. ctid is required for maintaining outer join views.
+	 */
+	initStringInfo(&str);
+	appendStringInfo(&str,
+		"SELECT %s FROM %s t"
+		" WHERE pg_catalog.ivm_visible_in_prestate(t.tableoid, t.ctid ,%d::pg_catalog.oid)",
+			subquery_tl, relname, matviewid);
+
+	/*
+	 * Re-add rows deleted from the old transition tables, excluding those
+	 * also present in the new transition tables.
+	 */
+	if (list_length(table->old_tuplestores) > 0)
+	{
+		appendStringInfo(&str," UNION ALL SELECT %s  FROM (",
+			subquery_tl);
+
+		for (i = 0; i < list_length(table->old_tuplestores); i++)
+		{
+			if (i != 0)
+				appendStringInfo(&str, " UNION ALL ");
+			appendStringInfo(&str," TABLE %s",
+				make_delta_enr_name("old", table->table_id, i));
+		}
+		for (i = 0; i < list_length(table->new_tuplestores); i++)
+		{
+			appendStringInfo(&str, " EXCEPT ALL ");
+			appendStringInfo(&str," TABLE %s",
+				make_delta_enr_name("new", table->table_id, i));
+		}
+		appendStringInfo(&str,")");
+	}
+
+	/* Get a subquery representing pre-state of the table */
+	raw = (RawStmt*)linitial(raw_parser(str.data, RAW_PARSE_DEFAULT));
+	subquery = transformStmt(pstate, raw->stmt);
+
+	/* save the original RTE */
+	table->original_rte = copyObject(rte);
+
+	rte->rtekind = RTE_SUBQUERY;
+	rte->subquery = subquery;
+	rte->security_barrier = false;
+
+	/* Clear fields that should not be set in a subquery RTE */
+	rte->relid = InvalidOid;
+	rte->relkind = 0;
+	rte->rellockmode = 0;
+	rte->tablesample = NULL;
+	rte->perminfoindex = 0;         /* no permission checking for this RTE */
+	rte->inh = false;			/* must not be set for a subquery */
+
+	return rte;
+}
+
+/*
+ * make_subquery_targetlist_from_table
+ *
+ * Make a targetlist string of a subquery representing a delta table or a
+ * pre-update state table. This subquery substitutes a modified table RTE
+ * in the view definition query during view maintenance. In the targetlist,
+ * column names appear in order of the table definition. However, for
+ * attribute numbers of vars in the query tree to reference columns of the
+ * subquery  correctly even though the table has a dropped column, put "null"
+ * as a dummy value at the position of a dropped column.
+ *
+ * We would also able to walk the query tree to rewrite varattnos, but
+ * crafting targetlist is more simple and reasonable.
+ */
+static char*
+make_subquery_targetlist_from_table(MV_TriggerTable *table)
+{
+	StringInfoData str;
+	TupleDesc	tupdesc;
+	int			i;
+
+	tupdesc = RelationGetDescr(table->rel);
+	initStringInfo(&str);
+	for (i = 0; i < tupdesc->natts; i++)
+	{
+		Form_pg_attribute attr = TupleDescAttr(tupdesc, i);
+
+		if (i > 0)
+			appendStringInfo(&str, ", ");
+
+		if (attr->attisdropped)
+			appendStringInfo(&str, "null");
+		else
+			appendStringInfo(&str, "%s", quote_identifier(NameStr(attr->attname)));
+	}
+
+	return str.data;
+}
+
+/*
+ * make_delta_enr_name
+ *
+ * Make a name for ENR of a transition table from the base table's oid.
+ * prefix will be "new" or "old" depending on its transition table kind..
+ */
+static char*
+make_delta_enr_name(const char *prefix, Oid relid, int count)
+{
+	char buf[NAMEDATALEN];
+	char *name;
+
+	snprintf(buf, NAMEDATALEN, "__ivm_%s_%u_%u", prefix, relid, count);
+	name = pstrdup(buf);
+
+	return name;
+}
+
+/*
+ * makeDeltaTable
+ *
+ * Make a RTE representing a delta of the specified table.
+ */
+static RangeTblEntry*
+makeDeltaTable(RangeTblEntry *rte, MV_TriggerTable *table,
+		   bool is_new, QueryEnvironment *queryEnv)
+{
+	StringInfoData str;
+	ParseState	*pstate;
+	RawStmt *raw;
+	Query *sub;
+	int		i;
+
+	const char *prefix_union = is_new ? "new" : "old";
+	const char *prefix_except = is_new ? "old" : "new";
+	int num_union = is_new ? list_length(table->new_tuplestores) : list_length(table->old_tuplestores);
+	int num_except = is_new ? list_length(table->old_tuplestores) : list_length(table->new_tuplestores);
+
+	/* the previous RTE must be a subquery which represents "pre-state" table */
+	Assert(rte->rtekind == RTE_SUBQUERY);
+
+	/* Create a ParseState for rewriting the view definition query */
+	pstate = make_parsestate(NULL);
+	pstate->p_queryEnv = queryEnv;
+	pstate->p_expr_kind = EXPR_KIND_NONE;
+
+	initStringInfo(&str);
+	appendStringInfo(&str,
+		" SELECT %s FROM ( ",
+		make_subquery_targetlist_from_table(table));
+
+	for (i = 0; i < num_union; i++)
+	{
+		if (i > 0)
+			appendStringInfo(&str, " UNION ALL ");
+
+		appendStringInfo(&str,
+			" TABLE  %s",
+			make_delta_enr_name(prefix_union, table->table_id, i));
+	}
+	for (i = 0; i < num_except; i++)
+	{
+		appendStringInfo(&str, " EXCEPT ALL ");
+
+		appendStringInfo(&str,
+			" TABLE  %s",
+			make_delta_enr_name(prefix_except, table->table_id, i));
+	}
+	appendStringInfo(&str,")");
+
+	raw = (RawStmt*)linitial(raw_parser(str.data, RAW_PARSE_DEFAULT));
+	sub = transformStmt(pstate, raw->stmt);
+
+	/*
+	 * Update the subquery so that it represent the combined transition
+	 * table.  Note that we leave the security_barrier and securityQuals
+	 * fields so that the subquery relation can be protected by the RLS
+	 * policy as same as the modified table.
+	 */
+	rte->rtekind = RTE_SUBQUERY;
+	rte->subquery = sub;
+
+	return rte;
+}
+
+/*
+ * rewrite_query_for_counting
+ *
+ * Rewrite query for counting duplicated tuples.
+ */
+static Query *
+rewrite_query_for_counting(Query *query, ParseState *pstate)
+{
+	TargetEntry *tle_count;
+	FuncCall *fn;
+	Node *node;
+
+	/* Add count(*) for counting distinct tuples in views */
+	fn = makeFuncCall(SystemFuncName("count"), NIL, COERCE_EXPLICIT_CALL, -1);
+	fn->agg_star = true;
+	if (!query->groupClause && !query->hasAggs)
+		query->groupClause = transformDistinctClause(NULL, &query->targetList, query->sortClause, false);
+
+	node = ParseFuncOrColumn(pstate, fn->funcname, NIL, NULL, fn, false, -1);
+
+	tle_count = makeTargetEntry((Expr *) node,
+								list_length(query->targetList) + 1,
+								pstrdup("__ivm_count__"),
+								false);
+	query->targetList = lappend(query->targetList, tle_count);
+	query->hasAggs = true;
+
+	return query;
+}
+
+/*
+ * calc_delta
+ *
+ * Calculate view deltas generated under the modification of a table specified
+ * by the RTE index.
+ */
+static void
+calc_delta(MV_TriggerTable *table, int rte_index, Query *query,
+			DestReceiver *dest_old, DestReceiver *dest_new,
+			TupleDesc *tupdesc_old, TupleDesc *tupdesc_new,
+			QueryEnvironment *queryEnv)
+{
+	ListCell *lc = list_nth_cell(query->rtable, rte_index - 1);
+	RangeTblEntry *rte = (RangeTblEntry *) lfirst(lc);
+
+	in_delta_calculation = true;
+
+	/* Generate old delta */
+	if (dest_old && list_length(table->old_tuplestores) > 0)
+	{
+		/* Replace the modified table with the old delta table and calculate the old view delta. */
+		lfirst(lc) = makeDeltaTable(rte, table, false, queryEnv);
+		refresh_matview_datafill(dest_old, query, queryEnv, tupdesc_old, "", false);
+	}
+
+	/* Generate new delta */
+	if (dest_new && list_length(table->new_tuplestores) > 0)
+	{
+		/* Replace the modified table with the new delta table and calculate the new view delta*/
+		lfirst(lc) = makeDeltaTable(rte, table, true, queryEnv);
+		refresh_matview_datafill(dest_new, query, queryEnv, tupdesc_new, "", false);
+	}
+
+	in_delta_calculation = false;
+}
+
+/*
+ * rewrite_query_for_postupdate_state
+ *
+ * Rewrite the query so that the specified base table's RTEs will represent
+ * "post-update" state of tables. This is called after the view delta
+ * calculation due to changes on this table finishes.
+ */
+static Query*
+rewrite_query_for_postupdate_state(Query *query, MV_TriggerTable *table, int rte_index)
+{
+	ListCell *lc = list_nth_cell(query->rtable, rte_index - 1);
+
+	/* Retore the original RTE */
+	lfirst(lc) = table->original_rte;
+
+	return query;
+}
+
+/*
+ * apply_delta
+ *
+ * Apply deltas to the materialized view. In outer join cases, this requires
+ * the view maintenance graph.
+ */
+static void
+apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *new_tuplestores,
+			TupleDesc tupdesc_old, TupleDesc tupdesc_new,
+			Query *query)
+{
+	StringInfoData querybuf;
+	StringInfoData target_list_buf;
+	Relation	matviewRel;
+	char	   *matviewname;
+	ListCell	*lc;
+	int			i;
+	List	   *keys = NIL;
+
+
+	/*
+	 * get names of the materialized view and delta tables
+	 */
+
+	matviewRel = table_open(matviewOid, NoLock);
+	matviewname = quote_qualified_identifier(get_namespace_name(RelationGetNamespace(matviewRel)),
+											 RelationGetRelationName(matviewRel));
+
+	/*
+	 * Build parts of the maintenance queries
+	 */
+
+	initStringInfo(&querybuf);
+	initStringInfo(&target_list_buf);
+
+	/* build string of target list */
+	for (i = 0; i < matviewRel->rd_att->natts; i++)
+	{
+		Form_pg_attribute attr = TupleDescAttr(matviewRel->rd_att, i);
+		char   *resname = NameStr(attr->attname);
+
+		if (i != 0)
+			appendStringInfo(&target_list_buf, ", ");
+		appendStringInfo(&target_list_buf, "%s", quote_qualified_identifier(NULL, resname));
+	}
+
+	i = 0;
+	foreach (lc, query->targetList)
+	{
+		TargetEntry *tle = (TargetEntry *) lfirst(lc);
+		Form_pg_attribute attr = TupleDescAttr(matviewRel->rd_att, i);
+
+		i++;
+
+		if (tle->resjunk)
+			continue;
+
+		keys = lappend(keys, attr);
+	}
+
+	/* Start maintaining the materialized view. */
+	OpenMatViewIncrementalMaintenance();
+
+	/* Open SPI context. */
+	if (SPI_connect() != SPI_OK_CONNECT)
+		elog(ERROR, "SPI_connect failed");
+
+	/* For tuple deletion */
+	if (old_tuplestores && tuplestore_tuple_count(old_tuplestores) > 0)
+	{
+		EphemeralNamedRelation enr = palloc(sizeof(EphemeralNamedRelationData));
+		int				rc;
+
+		/* convert tuplestores to ENR, and register for SPI */
+		enr->md.name = pstrdup(OLD_DELTA_ENRNAME);
+		enr->md.reliddesc = InvalidOid;
+		enr->md.tupdesc = tupdesc_old;
+		enr->md.enrtype = ENR_NAMED_TUPLESTORE;
+		enr->md.enrtuples = tuplestore_tuple_count(old_tuplestores);
+		enr->reldata = old_tuplestores;
+
+		rc = SPI_register_relation(enr);
+		if (rc != SPI_OK_REL_REGISTER)
+			elog(ERROR, "SPI_register failed");
+
+		apply_old_delta(matviewname, OLD_DELTA_ENRNAME, keys);
+
+	}
+	/* For tuple insertion */
+	if (new_tuplestores && tuplestore_tuple_count(new_tuplestores) > 0)
+	{
+		EphemeralNamedRelation enr = palloc(sizeof(EphemeralNamedRelationData));
+		int rc;
+
+		/* convert tuplestores to ENR, and register for SPI */
+		enr->md.name = pstrdup(NEW_DELTA_ENRNAME);
+		enr->md.reliddesc = InvalidOid;
+		enr->md.tupdesc = tupdesc_new;;
+		enr->md.enrtype = ENR_NAMED_TUPLESTORE;
+		enr->md.enrtuples = tuplestore_tuple_count(new_tuplestores);
+		enr->reldata = new_tuplestores;
+
+		rc = SPI_register_relation(enr);
+		if (rc != SPI_OK_REL_REGISTER)
+			elog(ERROR, "SPI_register failed");
+
+		/* apply new delta */
+		apply_new_delta(matviewname, NEW_DELTA_ENRNAME, &target_list_buf);
+	}
+
+	/* We're done maintaining the materialized view. */
+	CloseMatViewIncrementalMaintenance();
+
+	table_close(matviewRel, NoLock);
+
+	/* Close SPI context. */
+	if (SPI_finish() != SPI_OK_FINISH)
+		elog(ERROR, "SPI_finish failed");
+}
+
+/*
+ * apply_old_delta
+ *
+ * Execute a query for applying a delta table given by deltname_old
+ * which contains tuples to be deleted from to a materialized view given by
+ * matviewname.  This is used when counting is not required.
+ */
+static void
+apply_old_delta(const char *matviewname, const char *deltaname_old,
+				List *keys)
+{
+	StringInfoData	querybuf;
+	StringInfoData	keysbuf;
+	char   *match_cond;
+	ListCell *lc;
+
+	/* build WHERE condition for searching tuples to be deleted */
+	match_cond = get_matching_condition_string(keys);
+
+	/* build string of keys list */
+	initStringInfo(&keysbuf);
+	foreach (lc, keys)
+	{
+		Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc);
+		char   *resname = NameStr(attr->attname);
+		appendStringInfo(&keysbuf, "%s", quote_qualified_identifier("mv", resname));
+		if (lnext(keys, lc))
+			appendStringInfo(&keysbuf, ", ");
+	}
+
+	/* Search for matching tuples from the view and update or delete if found. */
+	initStringInfo(&querybuf);
+	appendStringInfo(&querybuf,
+	"DELETE FROM %s WHERE ctid IN ("
+		"SELECT tid FROM (SELECT pg_catalog.row_number() over (partition by %s) AS \"__ivm_row_number__\","
+								  "mv.ctid AS tid,"
+								  "diff.\"__ivm_count__\""
+						 "FROM %s AS mv, %s AS diff "
+						 "WHERE %s) v "
+					"WHERE v.\"__ivm_row_number__\" OPERATOR(pg_catalog.<=) v.\"__ivm_count__\")",
+					matviewname,
+					keysbuf.data,
+					matviewname, deltaname_old,
+					match_cond);
+
+	if (SPI_exec(querybuf.data, 0) != SPI_OK_DELETE)
+		elog(ERROR, "SPI_exec failed: %s", querybuf.data);
+}
+
+/*
+ * apply_new_delta
+ *
+ * Execute a query for applying a delta table given by deltname_new
+ * which contains tuples to be inserted into a materialized view given by
+ * matviewname.  This is used when counting is not required.
+ */
+static void
+apply_new_delta(const char *matviewname, const char *deltaname_new,
+				StringInfo target_list)
+{
+	StringInfoData	querybuf;
+
+	/* Search for matching tuples from the view and update or delete if found. */
+	initStringInfo(&querybuf);
+	appendStringInfo(&querybuf,
+					"INSERT INTO %s (%s) SELECT %s FROM ("
+						"SELECT diff.*, pg_catalog.generate_series(1, diff.\"__ivm_count__\")"
+							" AS __ivm_generate_series__ "
+						"FROM %s AS diff) AS v",
+					matviewname, target_list->data, target_list->data,
+					deltaname_new);
+
+	if (SPI_exec(querybuf.data, 0) != SPI_OK_INSERT)
+		elog(ERROR, "SPI_exec failed: %s", querybuf.data);
+}
+
+/*
+ * get_matching_condition_string
+ *
+ * Build a predicate string for looking for a tuple with given keys.
+ */
+static char *
+get_matching_condition_string(List *keys)
+{
+	StringInfoData match_cond;
+	ListCell	*lc;
+
+	/* If there is no key columns, the condition is always true. */
+	if (keys == NIL)
+		return "true";
+
+	initStringInfo(&match_cond);
+	foreach (lc, keys)
+	{
+		Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc);
+		char   *resname = NameStr(attr->attname);
+		char   *mv_resname = quote_qualified_identifier("mv", resname);
+		char   *diff_resname = quote_qualified_identifier("diff", resname);
+		Oid		typid = attr->atttypid;
+
+		/* Considering NULL values, we can not use simple = operator. */
+		appendStringInfo(&match_cond, "(");
+		generate_equal(&match_cond, typid, mv_resname, diff_resname);
+		appendStringInfo(&match_cond, " OR (%s IS NULL AND %s IS NULL))",
+						 mv_resname, diff_resname);
+
+		if (lnext(keys, lc))
+			appendStringInfo(&match_cond, " AND ");
+	}
+
+	return match_cond.data;
+}
+
+/*
+ * generate_equals
+ *
+ * Generate an equality clause using given operands' default equality
+ * operator.
+ */
+static void
+generate_equal(StringInfo querybuf, Oid opttype,
+			   const char *leftop, const char *rightop)
+{
+	TypeCacheEntry *typentry;
+
+	typentry = lookup_type_cache(opttype, TYPECACHE_EQ_OPR);
+	if (!OidIsValid(typentry->eq_opr))
+		ereport(ERROR,
+				(errcode(ERRCODE_UNDEFINED_FUNCTION),
+				 errmsg("could not identify an equality operator for type %s",
+						format_type_be_qualified(opttype))));
+
+	generate_operator_clause(querybuf,
+							 leftop, opttype,
+							 typentry->eq_opr,
+							 rightop, opttype);
+}
+
+/*
+ * mv_InitHashTables
+ */
+static void
+mv_InitHashTables(void)
+{
+	HASHCTL		ctl;
+
+	memset(&ctl, 0, sizeof(ctl));
+	ctl.keysize = sizeof(Oid);
+	ctl.entrysize = sizeof(MV_TriggerHashEntry);
+	mv_trigger_info = hash_create("MV trigger info",
+								 MV_INIT_QUERYHASHSIZE,
+								 &ctl, HASH_ELEM | HASH_BLOBS);
+
+	memset(&ctl, 0, sizeof(ctl));
+	ctl.keysize = sizeof(Oid);
+	ctl.entrysize = sizeof(DroppedImmvInfo);
+	dropped_immv = hash_create("Dropped IMMVs", 16,
+							   &ctl, HASH_ELEM | HASH_BLOBS);
+}
+
+/*
+ * AtAbort_IVM
+ *
+ * Clean up hash entries for all materialized views. This is called at
+ * (sub-)transaction abort. When the top-level transaction is aborted,
+ * InvalidSubTransactionId is set to subxid.
+ *
+ * Also, remove dropped IMMV information if it is aborted.
+ */
+void
+AtAbort_IVM(SubTransactionId subxid)
+{
+	HASH_SEQ_STATUS seq;
+
+	if (mv_trigger_info)
+	{
+		MV_TriggerHashEntry *entry;
+		hash_seq_init(&seq, mv_trigger_info);
+		while ((entry = hash_seq_search(&seq)) != NULL)
+			clean_up_IVM_hash_entry(entry, true, subxid);
+	}
+
+	if (dropped_immv)
+	{
+		DroppedImmvInfo *entry;
+		hash_seq_init(&seq, dropped_immv);
+		while ((entry = hash_seq_search(&seq)) != NULL)
+		{
+			if (subxid == InvalidSubTransactionId || subxid == entry->subxid)
+				hash_search(dropped_immv, (void *) &entry->immv_oid, HASH_REMOVE, NULL);
+		}
+	}
+
+	in_delta_calculation = false;
+}
+
+/*
+ * AtPreCommit_IVM
+ *
+ * Record the transaction ID that updated the view incrementally.
+ * Also, remove the entry for dropped IMMVs.
+ */
+void
+AtPreCommit_IVM(void)
+{
+	HASH_SEQ_STATUS seq;
+
+	if (mv_trigger_info)
+	{
+		MV_TriggerHashEntry *entry;
+
+		/*
+		 * Record the transaction ID that udpate the view incrementally,
+		 * and perform the final clean up of the entry.
+		 */
+		hash_seq_init(&seq, mv_trigger_info);
+		while ((entry = hash_seq_search(&seq)) != NULL)
+		{
+			setLastUpdateXid(entry->matview_id, GetTopFullTransactionId());
+			hash_search(mv_trigger_info, (void *) &entry->matview_id, HASH_REMOVE, NULL);
+		}
+	}
+
+	if (dropped_immv)
+	{
+		DroppedImmvInfo *entry;
+
+		LWLockAcquire(IvmControlLock, LW_EXCLUSIVE);
+		hash_seq_init(&seq, dropped_immv);
+		while ((entry = hash_seq_search(&seq)) != NULL)
+		{
+			hash_search(LastIvmUpdateHash, (void *) &entry->immv_oid, HASH_REMOVE, NULL);
+			hash_search(dropped_immv, (void *) &entry->immv_oid, HASH_REMOVE, NULL);
+		}
+		LWLockRelease(IvmControlLock);
+	}
+
+	in_delta_calculation = false;
+}
+
+/*
+ * clean_up_IVM_hash_entry
+ *
+ * Clean up tuple stores and hash entries for a materialized view after its
+ * maintenance finished. This is called at the end of table modifying query
+ * or (sub-)transaction abort. When the top-level transaction is aborted,
+ * InvalidSubTransactionId is set to subxid.
+ */
+static void
+clean_up_IVM_hash_entry(MV_TriggerHashEntry *entry, bool is_abort,
+						SubTransactionId subxid)
+{
+	bool found;
+	ListCell *lc;
+
+	/* clean up tuple stores */
+	foreach(lc, entry->tables)
+	{
+		MV_TriggerTable *table = (MV_TriggerTable *) lfirst(lc);
+
+		list_free(table->old_tuplestores);
+		list_free(table->new_tuplestores);
+		if (!is_abort)
+		{
+			ExecDropSingleTupleTableSlot(table->slot);
+			table_close(table->rel, NoLock);
+		}
+	}
+	list_free(entry->tables);
+	entry->tables = NIL;
+
+	if (is_abort)
+	{
+		bool	remove_entry = false;
+
+		/*
+		 * When the top-level transaction is aborted, remove all subxids.
+		 * When a sub-transaction is aborted, remove only its subxid.
+		 */
+		if (subxid == InvalidSubTransactionId)
+			remove_entry = true;
+		else
+		{
+			foreach(lc, entry->subxids)
+			{
+				if (lfirst_xid(lc) == subxid)
+				{
+					entry->subxids = list_delete_cell(entry->subxids, lc);
+					break;
+				}
+			}
+
+			/*
+			 * If all the subxid are removed, it means that the view was not
+			 * updated at all in this transaction.
+			 */
+			if (list_length(entry->subxids) == 0)
+				remove_entry = true;
+		}
+
+		/*
+		 * Remove entries of not updated views from the hash table.
+		 */
+		if (remove_entry)
+			hash_search(mv_trigger_info, (void *) &entry->matview_id, HASH_REMOVE, &found);
+	}
+	else
+	{
+		/* When the query sucsessully finished, unregister the snapshot */
+		UnregisterSnapshot(entry->snapshot);
+	}
+
+	entry->snapshot = InvalidSnapshot;
+}
+
+/*
+ * setLastUpdateXid
+ *
+ * Store the transaction ID that updated the view incremenally.
+ */
+static void
+setLastUpdateXid(Oid immv_oid, FullTransactionId xid)
+{
+	LastIvmUpdateEntry *entry;
+
+	LWLockAcquire(IvmControlLock, LW_EXCLUSIVE);
+	entry = (LastIvmUpdateEntry *) hash_search(LastIvmUpdateHash, (void *) &immv_oid, HASH_ENTER, NULL);
+	entry->oid = immv_oid;
+	entry->last_ivm_update = xid;
+	LWLockRelease(IvmControlLock);
+}
+
+/*
+ * getLastUpdateXid
+ *
+ * Get the most recent transaction ID that updated the view incrementally.
+ */
+static FullTransactionId
+getLastUpdateXid(Oid immv_oid)
+{
+	FullTransactionId xid = InvalidFullTransactionId;
+	LastIvmUpdateEntry *entry;
+	bool found;
+
+	LWLockAcquire(IvmControlLock, LW_SHARED);
+	entry = (LastIvmUpdateEntry *) hash_search(LastIvmUpdateHash, (void *) &immv_oid, HASH_FIND, &found);
+	LWLockRelease(IvmControlLock);
+	if (found)
+		xid = entry->last_ivm_update;
+
+	return xid;
+}
+
+void
+removeImmv(Oid immv_oid)
+{
+	DroppedImmvInfo *entry;
+
+	if (!dropped_immv)
+		mv_InitHashTables();
+
+	entry = (DroppedImmvInfo *) hash_search(dropped_immv, (void *) &immv_oid, HASH_ENTER, NULL);
+	entry->subxid = GetCurrentSubTransactionId();
+}
+
+/*
+ * isIvmName
+ *
+ * Check if this is a IVM hidden column from the name.
+ */
+bool
+isIvmName(const char *s)
+{
+	if (s)
+		return (strncmp(s, "__ivm_", 6) == 0);
+	return false;
+}
diff --git a/src/backend/commands/tablecmds.c b/src/backend/commands/tablecmds.c
index 472db112fa7..920b62d254d 100644
--- a/src/backend/commands/tablecmds.c
+++ b/src/backend/commands/tablecmds.c
@@ -62,6 +62,7 @@
 #include "commands/defrem.h"
 #include "commands/event_trigger.h"
 #include "commands/extension.h"
+#include "commands/matview.h"
 #include "commands/repack.h"
 #include "commands/sequence.h"
 #include "commands/tablecmds.h"
@@ -1811,6 +1812,9 @@ RangeVarCallbackForDropRelation(const RangeVar *rel, Oid relOid, Oid oldRelOid,
 	state->actual_relkind = classform->relkind;
 	state->actual_relpersistence = classform->relpersistence;
 
+	if (classform->relkind == RELKIND_MATVIEW && classform->relisivm)
+		removeImmv(relOid);
+
 	/*
 	 * Both RELKIND_RELATION and RELKIND_PARTITIONED_TABLE are OBJECT_TABLE,
 	 * but RemoveRelations() can only pass one relkind for a given relation.
diff --git a/src/backend/utils/activity/wait_event_names.txt b/src/backend/utils/activity/wait_event_names.txt
index 560659f9568..d97c35eeef0 100644
--- a/src/backend/utils/activity/wait_event_names.txt
+++ b/src/backend/utils/activity/wait_event_names.txt
@@ -370,6 +370,7 @@ WaitLSN	"Waiting to read or update shared Wait-for-LSN state."
 LogicalDecodingControl	"Waiting to read or update logical decoding status information."
 DataChecksumsWorker	"Waiting for data checksums worker."
 AioWorkerControl	"Waiting to update AIO worker information."
+IvmControl	"Waiting for read or update IMMV information.."
 
 #
 # END OF PREDEFINED LWLOCKS (DO NOT CHANGE THIS LINE)
diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat
index 73bb7fbb430..88399513f87 100644
--- a/src/include/catalog/pg_proc.dat
+++ b/src/include/catalog/pg_proc.dat
@@ -12698,4 +12698,14 @@
   proname => 'hashoid8extended', prorettype => 'int8',
   proargtypes => 'oid8 int8', prosrc => 'hashoid8extended' },
 
+# IVM
+{ oid => '786', descr => 'ivm trigger (before)',
+  proname => 'IVM_immediate_before', provolatile => 'v', prorettype => 'trigger',
+  proargtypes => '', prosrc => 'IVM_immediate_before' },
+{ oid => '787', descr => 'ivm trigger (after)',
+  proname => 'IVM_immediate_maintenance', provolatile => 'v', prorettype => 'trigger',
+  proargtypes => '', prosrc => 'IVM_immediate_maintenance' },
+{ oid => '788', descr => 'ivm filetring ',
+  proname => 'ivm_visible_in_prestate', provolatile => 's', prorettype => 'bool',
+  proargtypes => 'oid tid oid', prosrc => 'ivm_visible_in_prestate' },
 ]
diff --git a/src/include/commands/createas.h b/src/include/commands/createas.h
index f895c67c0c2..c286ebcd70e 100644
--- a/src/include/commands/createas.h
+++ b/src/include/commands/createas.h
@@ -16,6 +16,7 @@
 
 #include "catalog/objectaddress.h"
 #include "nodes/params.h"
+#include "nodes/pathnodes.h"
 #include "parser/parse_node.h"
 #include "tcop/dest.h"
 #include "utils/queryenvironment.h"
@@ -25,6 +26,9 @@ extern ObjectAddress ExecCreateTableAs(ParseState *pstate, CreateTableAsStmt *st
 									   ParamListInfo params, QueryEnvironment *queryEnv,
 									   QueryCompletion *qc);
 
+extern void CreateIvmTriggersOnBaseTables(Query *qry, Oid matviewOid);
+extern void CreateIndexOnIMMV(Query *query, Relation matviewRel);
+
 extern int	GetIntoRelEFlags(IntoClause *intoClause);
 
 extern DestReceiver *CreateIntoRelDestReceiver(IntoClause *intoClause);
diff --git a/src/include/commands/matview.h b/src/include/commands/matview.h
index 738c731c1a9..f1dbfc052c5 100644
--- a/src/include/commands/matview.h
+++ b/src/include/commands/matview.h
@@ -15,6 +15,7 @@
 #define MATVIEW_H
 
 #include "catalog/objectaddress.h"
+#include "fmgr.h"
 #include "nodes/params.h"
 #include "nodes/parsenodes.h"
 #include "tcop/dest.h"
@@ -23,6 +24,8 @@
 
 extern void SetMatViewPopulatedState(Relation relation, bool newstate);
 
+extern void SetMatViewIVMState(Relation relation, bool newstate);
+
 extern ObjectAddress ExecRefreshMatView(RefreshMatViewStmt *stmt, const char *queryString,
 										QueryCompletion *qc);
 extern ObjectAddress RefreshMatViewByOid(Oid matviewOid, bool is_create, bool skipData,
@@ -33,4 +36,12 @@ extern DestReceiver *CreateTransientRelDestReceiver(Oid transientoid);
 
 extern bool MatViewIncrementalMaintenanceIsEnabled(void);
 
+extern Datum IVM_immediate_before(PG_FUNCTION_ARGS);
+extern Datum IVM_immediate_maintenance(PG_FUNCTION_ARGS);
+extern Datum IVM_visible_in_prestate(PG_FUNCTION_ARGS);
+extern void AtAbort_IVM(SubTransactionId subtxid);
+extern void AtPreCommit_IVM(void);
+extern void removeImmv(Oid immv_oid);
+extern bool isIvmName(const char *s);
+
 #endif							/* MATVIEW_H */
diff --git a/src/include/storage/lwlocklist.h b/src/include/storage/lwlocklist.h
index d7eb648bd27..756c63baf97 100644
--- a/src/include/storage/lwlocklist.h
+++ b/src/include/storage/lwlocklist.h
@@ -89,6 +89,7 @@ PG_LWLOCK(54, WaitLSN)
 PG_LWLOCK(55, LogicalDecodingControl)
 PG_LWLOCK(56, DataChecksumsWorker)
 PG_LWLOCK(57, AioWorkerControl)
+PG_LWLOCK(58, IvmControl)
 
 /*
  * There also exist several built-in LWLock tranches.  As with the predefined
diff --git a/src/include/storage/subsystemlist.h b/src/include/storage/subsystemlist.h
index 9ad619080be..481e15d00a1 100644
--- a/src/include/storage/subsystemlist.h
+++ b/src/include/storage/subsystemlist.h
@@ -88,3 +88,6 @@ PG_SHMEM_SUBSYSTEM(DataChecksumsShmemCallbacks)
 
 /* AIO subsystem. This delegates to the method-specific callbacks */
 PG_SHMEM_SUBSYSTEM(AioShmemCallbacks)
+
+/* Incremental View Maintenance */
+PG_SHMEM_SUBSYSTEM(IvmShmemCallbacks)
-- 
2.43.0


--Multipart=_Wed__1_Jul_2026_00_04_01_+0900_OVSy2WWK_9aByzDJ
Content-Type: text/x-diff;
 name="v38-0005-Add-Incremental-View-Maintenance-support-to-psql.patch"
Content-Disposition: attachment;
 filename="v38-0005-Add-Incremental-View-Maintenance-support-to-psql.patch"
Content-Transfer-Encoding: 7bit



^ permalink  raw  reply  [nested|flat] 101+ messages in thread

* [PATCH v39 6/8] Add Incremental View Maintenance support
@ 2026-05-29 09:06  Yugo Nagata <[email protected]>
  0 siblings, 0 replies; 101+ messages in thread

From: Yugo Nagata @ 2026-05-29 09:06 UTC (permalink / raw)

In this implementation, AFTER triggers are used to collect
tuplestores containing transition table contents. When multiple tables
are changed, multiple AFTER triggers are invoked, then the final AFTER
trigger performs actual update of the matview. In addition, BEFORE
triggers are also used to handle global information for view
maintenance.

To calculate view deltas, we need both pre-state and post-state of base
tables. Post-update states are available in AFTER trigger, and pre-update
states can be calculated by removing inserted tuples and appending deleted
tuples. Insterted tuples are filtered using the snapshot taken before
table modification, and deleted tuples are contained in the old transition
table.

Incrementally Maintainable Materialized Views (IMMV) can contain
duplicated tuples.

This patch also allows self-join, simultaneous updates of more than
one base table, and multiple updates of the same base table.
---
 src/backend/access/transam/xact.c             |    8 +
 src/backend/commands/createas.c               |  709 +++++++
 src/backend/commands/matview.c                | 1835 ++++++++++++++++-
 src/backend/commands/tablecmds.c              |    4 +
 .../utils/activity/wait_event_names.txt       |    1 +
 src/include/catalog/pg_proc.dat               |   10 +
 src/include/commands/createas.h               |    4 +
 src/include/commands/matview.h                |   11 +
 src/include/storage/lwlocklist.h              |    1 +
 src/include/storage/subsystemlist.h           |    3 +
 10 files changed, 2548 insertions(+), 38 deletions(-)

diff --git a/src/backend/access/transam/xact.c b/src/backend/access/transam/xact.c
index 3a89149016f..0e6cb5493d2 100644
--- a/src/backend/access/transam/xact.c
+++ b/src/backend/access/transam/xact.c
@@ -37,6 +37,7 @@
 #include "catalog/pg_enum.h"
 #include "catalog/storage.h"
 #include "commands/async.h"
+#include "commands/matview.h"
 #include "commands/tablecmds.h"
 #include "commands/trigger.h"
 #include "common/pg_prng.h"
@@ -2322,6 +2323,9 @@ CommitTransaction(void)
 	CallXactCallbacks(is_parallel_worker ? XACT_EVENT_PARALLEL_PRE_COMMIT
 					  : XACT_EVENT_PRE_COMMIT);
 
+	/* Store the transaction ID that updated the view incrementally */
+	AtPreCommit_IVM();
+
 	/*
 	 * If this xact has started any unfinished parallel operation, clean up
 	 * its workers, warning about leaked resources.  (But we don't actually
@@ -2973,6 +2977,7 @@ AbortTransaction(void)
 	AtAbort_Notify();
 	AtEOXact_RelationMap(false, is_parallel_worker);
 	AtAbort_Twophase();
+	AtAbort_IVM(InvalidSubTransactionId);
 
 	/*
 	 * Advertise the fact that we aborted in pg_xact (assuming that we got as
@@ -5304,6 +5309,9 @@ AbortSubTransaction(void)
 
 	UnlockBuffers();
 
+	/* Clean up hash entries for incremental view maintenance */
+	AtAbort_IVM(s->subTransactionId);
+
 	/* Reset WAL record construction state */
 	XLogResetInsertion();
 
diff --git a/src/backend/commands/createas.c b/src/backend/commands/createas.c
index 6dbb831ca89..a499688b79d 100644
--- a/src/backend/commands/createas.c
+++ b/src/backend/commands/createas.c
@@ -29,18 +29,32 @@
 #include "access/tableam.h"
 #include "access/xact.h"
 #include "catalog/namespace.h"
+#include "catalog/index.h"
+#include "catalog/pg_am_d.h"
+#include "catalog/pg_constraint.h"
+#include "catalog/pg_inherits.h"
+#include "catalog/pg_trigger.h"
 #include "catalog/toasting.h"
 #include "commands/createas.h"
+#include "commands/defrem.h"
 #include "commands/matview.h"
 #include "commands/prepare.h"
 #include "commands/tablecmds.h"
+#include "commands/tablespace.h"
+#include "commands/trigger.h"
 #include "commands/view.h"
 #include "executor/execdesc.h"
 #include "executor/executor.h"
+#include "miscadmin.h"
 #include "nodes/makefuncs.h"
 #include "nodes/nodeFuncs.h"
 #include "nodes/queryjumble.h"
+#include "optimizer/optimizer.h"
+#include "optimizer/prep.h"
 #include "parser/analyze.h"
+#include "parser/parser.h"
+#include "parser/parsetree.h"
+#include "parser/parse_clause.h"
 #include "rewrite/rewriteHandler.h"
 #include "tcop/tcopprot.h"
 #include "utils/builtins.h"
@@ -70,6 +84,12 @@ static bool intorel_receive(TupleTableSlot *slot, DestReceiver *self);
 static void intorel_shutdown(DestReceiver *self);
 static void intorel_destroy(DestReceiver *self);
 
+static void CreateIvmTriggersOnBaseTablesRecurse(Query *qry, Node *node, Oid matviewOid,
+									 List **relids, bool ex_lock);
+static void CreateIvmTrigger(Oid relOid, Oid viewOid, int16 type, int16 timing, bool ex_lock);
+static void check_ivm_restriction(Node *node);
+static bool check_ivm_restriction_walker(Node *node, void *context);
+static Bitmapset *get_primary_key_attnos_from_query(Query *query, List **constraintList);
 
 /*
  * create_ctas_internal
@@ -277,6 +297,18 @@ ExecCreateTableAs(ParseState *pstate, CreateTableAsStmt *stmt,
 		into->skipData = true;
 	}
 
+	if (is_matview && into->ivm)
+	{
+		/* check if the query is supported in IMMV definition */
+		if (contain_mutable_functions((Node *) query))
+			ereport(ERROR,
+					(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+					 errmsg("mutable function is not supported on incrementally maintainable materialized view"),
+					 errhint("functions must be marked IMMUTABLE")));
+
+		check_ivm_restriction((Node *) query);
+	}
+
 	if (into->skipData)
 	{
 		/*
@@ -287,15 +319,36 @@ ExecCreateTableAs(ParseState *pstate, CreateTableAsStmt *stmt,
 		 */
 		address = create_ctas_nodata(query->targetList, into);
 
+		/*
+		 * For IVM, mark the matview before refresh so RelationIsIVM()
+		 * returns true inside RefreshMatViewByOid.
+		 */
+		if (is_matview && into->ivm)
+		{
+			Relation matviewRel = table_open(address.objectId, NoLock);
+
+			SetMatViewIVMState(matviewRel, true);
+			table_close(matviewRel, NoLock);
+			CommandCounterIncrement();
+		}
+
 		/*
 		 * For materialized views, reuse the REFRESH logic, which locks down
 		 * security-restricted operations and restricts the search_path.  This
 		 * reduces the chance that a subsequent refresh will fail.
 		 */
 		if (do_refresh)
+		{
 			RefreshMatViewByOid(address.objectId, true, false, false,
 								pstate->p_sourcetext, qc);
 
+			if (is_matview && into->ivm && IsolationUsesXactSnapshot())
+				ereport(WARNING,
+						(errmsg("inconsistent view can be created in isolation level SERIALIZABLE or REPEATABLE READ"),
+						 errdetail("The view may not include effects of a concurrent transaction."),
+						 errhint("The view with incremental maintenance should be created in isolation level READ COMMITTED, "
+								 "or refreshed manually to make sure the view is consistent.")));
+		}
 	}
 	else
 	{
@@ -635,3 +688,659 @@ intorel_destroy(DestReceiver *self)
 {
 	pfree(self);
 }
+
+/*
+ * CreateIvmTriggersOnBaseTables -- create IVM triggers on all base tables
+ */
+void
+CreateIvmTriggersOnBaseTables(Query *qry, Oid matviewOid)
+{
+	List   *relids = NIL;
+	bool	ex_lock = false;
+	RangeTblEntry *rte;
+
+	/* Immediately return if we don't have any base tables. */
+	if (list_length(qry->rtable) < 1)
+		return;
+
+	/*
+	 * If the view has more than one base tables, we need an exclusive lock
+	 * on the view so that the view would be maintained serially to avoid
+	 * the inconsistency that occurs when two base tables are modified in
+	 * concurrent transactions. However, if the view has only one table,
+	 * we can use a weaker lock.
+	 *
+	 * The type of lock should be determined here, because if we check the
+	 * view definition at maintenance time, we need to acquire a weaker lock,
+	 * and upgrading the lock level after this increases probability of
+	 * deadlock.
+	 */
+
+	rte = list_nth(qry->rtable, 0);
+	if (list_length(qry->rtable) > 1 || rte->rtekind != RTE_RELATION)
+		ex_lock = true;
+
+	CreateIvmTriggersOnBaseTablesRecurse(qry, (Node *)qry, matviewOid, &relids, ex_lock);
+
+	list_free(relids);
+}
+
+static void
+CreateIvmTriggersOnBaseTablesRecurse(Query *qry, Node *node, Oid matviewOid,
+									 List **relids, bool ex_lock)
+{
+	if (node == NULL)
+		return;
+
+	/* This can recurse, so check for excessive recursion */
+	check_stack_depth();
+
+	switch (nodeTag(node))
+	{
+		case T_Query:
+			{
+				Query *query = (Query *) node;
+
+				CreateIvmTriggersOnBaseTablesRecurse(qry, (Node *)query->jointree, matviewOid, relids, ex_lock);
+			}
+			break;
+
+		case T_RangeTblRef:
+			{
+				int			rti = ((RangeTblRef *) node)->rtindex;
+				RangeTblEntry *rte = rt_fetch(rti, qry->rtable);
+
+				if (rte->rtekind == RTE_RELATION && !list_member_oid(*relids, rte->relid))
+				{
+					CreateIvmTrigger(rte->relid, matviewOid, TRIGGER_TYPE_INSERT, TRIGGER_TYPE_BEFORE, ex_lock);
+					CreateIvmTrigger(rte->relid, matviewOid, TRIGGER_TYPE_DELETE, TRIGGER_TYPE_BEFORE, ex_lock);
+					CreateIvmTrigger(rte->relid, matviewOid, TRIGGER_TYPE_UPDATE, TRIGGER_TYPE_BEFORE, ex_lock);
+					CreateIvmTrigger(rte->relid, matviewOid, TRIGGER_TYPE_TRUNCATE, TRIGGER_TYPE_BEFORE, true);
+					CreateIvmTrigger(rte->relid, matviewOid, TRIGGER_TYPE_INSERT, TRIGGER_TYPE_AFTER, ex_lock);
+					CreateIvmTrigger(rte->relid, matviewOid, TRIGGER_TYPE_DELETE, TRIGGER_TYPE_AFTER, ex_lock);
+					CreateIvmTrigger(rte->relid, matviewOid, TRIGGER_TYPE_UPDATE, TRIGGER_TYPE_AFTER, ex_lock);
+					CreateIvmTrigger(rte->relid, matviewOid, TRIGGER_TYPE_TRUNCATE, TRIGGER_TYPE_AFTER, true);
+
+					*relids = lappend_oid(*relids, rte->relid);
+				}
+			}
+			break;
+
+		case T_FromExpr:
+			{
+				FromExpr   *f = (FromExpr *) node;
+				ListCell   *l;
+
+				foreach(l, f->fromlist)
+					CreateIvmTriggersOnBaseTablesRecurse(qry, lfirst(l), matviewOid, relids, ex_lock);
+			}
+			break;
+
+		case T_JoinExpr:
+			{
+				JoinExpr   *j = (JoinExpr *) node;
+
+				CreateIvmTriggersOnBaseTablesRecurse(qry, j->larg, matviewOid, relids, ex_lock);
+				CreateIvmTriggersOnBaseTablesRecurse(qry, j->rarg, matviewOid, relids, ex_lock);
+			}
+			break;
+
+		default:
+			elog(ERROR, "unrecognized node type: %d", (int) nodeTag(node));
+	}
+}
+
+/*
+ * CreateIvmTrigger -- create IVM trigger on a base table
+ */
+static void
+CreateIvmTrigger(Oid relOid, Oid viewOid, int16 type, int16 timing, bool ex_lock)
+{
+	ObjectAddress	refaddr;
+	ObjectAddress	address;
+	CreateTrigStmt *ivm_trigger;
+	List *transitionRels = NIL;
+
+	Assert(timing == TRIGGER_TYPE_BEFORE || timing == TRIGGER_TYPE_AFTER);
+
+	refaddr.classId = RelationRelationId;
+	refaddr.objectId = viewOid;
+	refaddr.objectSubId = 0;
+
+	ivm_trigger = makeNode(CreateTrigStmt);
+	ivm_trigger->relation = NULL;
+	ivm_trigger->row = false;
+
+	ivm_trigger->timing = timing;
+	ivm_trigger->events = type;
+
+	switch (type)
+	{
+		case TRIGGER_TYPE_INSERT:
+			ivm_trigger->trigname = (timing == TRIGGER_TYPE_BEFORE ? "IVM_trigger_ins_before" : "IVM_trigger_ins_after");
+			break;
+		case TRIGGER_TYPE_DELETE:
+			ivm_trigger->trigname = (timing == TRIGGER_TYPE_BEFORE ? "IVM_trigger_del_before" : "IVM_trigger_del_after");
+			break;
+		case TRIGGER_TYPE_UPDATE:
+			ivm_trigger->trigname = (timing == TRIGGER_TYPE_BEFORE ? "IVM_trigger_upd_before" : "IVM_trigger_upd_after");
+			break;
+		case TRIGGER_TYPE_TRUNCATE:
+			ivm_trigger->trigname = (timing == TRIGGER_TYPE_BEFORE ? "IVM_trigger_truncate_before" : "IVM_trigger_truncate_after");
+			break;
+		default:
+			elog(ERROR, "unsupported trigger type");
+	}
+
+	if (timing == TRIGGER_TYPE_AFTER)
+	{
+		if (type == TRIGGER_TYPE_INSERT || type == TRIGGER_TYPE_UPDATE)
+		{
+			TriggerTransition *n = makeNode(TriggerTransition);
+			n->name = "__ivm_newtable";
+			n->isNew = true;
+			n->isTable = true;
+
+			transitionRels = lappend(transitionRels, n);
+		}
+		if (type == TRIGGER_TYPE_DELETE || type == TRIGGER_TYPE_UPDATE)
+		{
+			TriggerTransition *n = makeNode(TriggerTransition);
+			n->name = "__ivm_oldtable";
+			n->isNew = false;
+			n->isTable = true;
+
+			transitionRels = lappend(transitionRels, n);
+		}
+	}
+
+	/*
+	 * XXX: When using DELETE or UPDATE, we must use exclusive lock for now
+	 * because apply_old_delta(_with_count) uses ctid to identify the tuple
+	 * to be deleted/deleted, but doesn't work in concurrent situations.
+	 *
+	 * If the view doesn't have aggregate, distinct, or tuple duplicate,
+	 * then it would work even in concurrent situations. However, we don't have
+	 * any way to guarantee the view has a unique key before opening the IMMV
+	 * at the maintenance time because users may drop the unique index.
+	 */
+
+	if (type == TRIGGER_TYPE_DELETE || type == TRIGGER_TYPE_UPDATE)
+		ex_lock = true;
+
+	ivm_trigger->funcname =
+		(timing == TRIGGER_TYPE_BEFORE ? SystemFuncName("IVM_immediate_before") : SystemFuncName("IVM_immediate_maintenance"));
+
+	ivm_trigger->columns = NIL;
+	ivm_trigger->transitionRels = transitionRels;
+	ivm_trigger->whenClause = NULL;
+	ivm_trigger->isconstraint = false;
+	ivm_trigger->deferrable = false;
+	ivm_trigger->initdeferred = false;
+	ivm_trigger->constrrel = NULL;
+	ivm_trigger->args = list_make2(
+		makeString(DatumGetPointer(DirectFunctionCall1(oidout, ObjectIdGetDatum(viewOid)))),
+		makeString(DatumGetPointer(DirectFunctionCall1(boolout, BoolGetDatum(ex_lock))))
+		);
+
+	address = CreateTrigger(ivm_trigger, NULL, relOid, InvalidOid, InvalidOid,
+						 InvalidOid, InvalidOid, InvalidOid, NULL, true, false);
+
+	recordDependencyOn(&address, &refaddr, DEPENDENCY_AUTO);
+
+	/* Make changes-so-far visible */
+	CommandCounterIncrement();
+}
+
+/*
+ * check_ivm_restriction --- look for specify nodes in the query tree
+ */
+static void
+check_ivm_restriction(Node *node)
+{
+	check_ivm_restriction_walker(node, NULL);
+}
+
+static bool
+check_ivm_restriction_walker(Node *node, void *context)
+{
+	if (node == NULL)
+		return false;
+
+	/*
+	 * We currently don't support Sub-Query.
+	 */
+	if (IsA(node, SubPlan) || IsA(node, SubLink))
+		ereport(ERROR,
+				(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+				 errmsg("subquery is not supported on incrementally maintainable materialized view")));
+
+	/* This can recurse, so check for excessive recursion */
+	check_stack_depth();
+
+	switch (nodeTag(node))
+	{
+		case T_Query:
+			{
+				Query *qry = (Query *)node;
+				ListCell   *lc;
+				List       *vars;
+
+				/* if contained CTE, return error */
+				if (qry->cteList != NIL)
+					ereport(ERROR,
+							(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+							 errmsg("CTE is not supported on incrementally maintainable materialized view")));
+				if (qry->havingQual != NULL)
+					ereport(ERROR,
+							(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+							 errmsg(" HAVING clause is not supported on incrementally maintainable materialized view")));
+				if (qry->sortClause != NIL)	/* There is a possibility that we don't need to return an error */
+					ereport(ERROR,
+							(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+							 errmsg("ORDER BY clause is not supported on incrementally maintainable materialized view")));
+				if (qry->limitOffset != NULL || qry->limitCount != NULL)
+					ereport(ERROR,
+							(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+							 errmsg("LIMIT/OFFSET clause is not supported on incrementally maintainable materialized view")));
+				if (qry->distinctClause)
+					ereport(ERROR,
+							(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+							 errmsg("DISTINCT is not supported on incrementally maintainable materialized view")));
+				if (qry->hasDistinctOn)
+					ereport(ERROR,
+							(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+							 errmsg("DISTINCT ON is not supported on incrementally maintainable materialized view")));
+				if (qry->hasWindowFuncs)
+					ereport(ERROR,
+							(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+							 errmsg("window functions are not supported on incrementally maintainable materialized view")));
+				if (qry->groupingSets != NIL)
+					ereport(ERROR,
+							(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+							 errmsg("GROUPING SETS, ROLLUP, or CUBE clauses is not supported on incrementally maintainable materialized view")));
+				if (qry->setOperations != NULL)
+					ereport(ERROR,
+							(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+							 errmsg("UNION/INTERSECT/EXCEPT statements are not supported on incrementally maintainable materialized view")));
+				if (list_length(qry->targetList) == 0)
+					ereport(ERROR,
+							(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+							 errmsg("empty target list is not supported on incrementally maintainable materialized view")));
+				if (qry->rowMarks != NIL)
+					ereport(ERROR,
+							(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+							 errmsg("FOR UPDATE/SHARE clause is not supported on incrementally maintainable materialized view")));
+
+				/* system column restrictions */
+				vars = pull_vars_of_level((Node *) qry, 0);
+				foreach(lc, vars)
+				{
+					if (IsA(lfirst(lc), Var))
+					{
+						Var *var = (Var *) lfirst(lc);
+						/* if system column, return error */
+						if (var->varattno < 0)
+							ereport(ERROR,
+									(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+									 errmsg("system column is not supported on incrementally maintainable materialized view")));
+					}
+				}
+
+				/* check if type in the target list had an equality operator */
+				foreach(lc, qry->targetList)
+				{
+					TargetEntry *tle = (TargetEntry *) lfirst(lc);
+					Oid             atttype = exprType((Node *) tle->expr);
+					Oid             opclass;
+
+					opclass = GetDefaultOpClass(atttype, BTREE_AM_OID);
+					if (!OidIsValid(opclass))
+						ereport(ERROR,
+								(errcode(ERRCODE_UNDEFINED_OBJECT),
+								 errmsg("data type %s has no default operator class for access method \"%s\"",
+									format_type_be(atttype), "btree")));
+				}
+
+				/* restrictions for rtable */
+				foreach(lc, qry->rtable)
+				{
+					RangeTblEntry *rte = (RangeTblEntry *) lfirst(lc);
+
+					if (rte->subquery)
+						ereport(ERROR,
+								(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+								 errmsg("subquery is not supported on incrementally maintainable materialized view")));
+
+					if (rte->tablesample != NULL)
+						ereport(ERROR,
+								(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+								 errmsg("TABLESAMPLE clause is not supported on incrementally maintainable materialized view")));
+
+					if (rte->relkind == RELKIND_PARTITIONED_TABLE)
+						ereport(ERROR,
+								(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+								 errmsg("partitioned table is not supported on incrementally maintainable materialized view")));
+
+					if (rte->relkind == RELKIND_RELATION && has_superclass(rte->relid))
+						ereport(ERROR,
+								(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+								 errmsg("partitions is not supported on incrementally maintainable materialized view")));
+
+					if (rte->relkind == RELKIND_RELATION && find_inheritance_children(rte->relid, NoLock) != NIL)
+						ereport(ERROR,
+								(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+								 errmsg("inheritance parent is not supported on incrementally maintainable materialized view")));
+
+					if (rte->relkind == RELKIND_FOREIGN_TABLE)
+						ereport(ERROR,
+								(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+								 errmsg("foreign table is not supported on incrementally maintainable materialized view")));
+
+					if (rte->relkind == RELKIND_VIEW ||
+						rte->relkind == RELKIND_MATVIEW)
+						ereport(ERROR,
+								(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+								 errmsg("VIEW or MATERIALIZED VIEW is not supported on incrementally maintainable materialized view")));
+
+					if (rte->rtekind == RTE_VALUES)
+						ereport(ERROR,
+								(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+								 errmsg("VALUES is not supported on incrementally maintainable materialized view")));
+
+				}
+
+				query_tree_walker(qry, check_ivm_restriction_walker, NULL, QTW_IGNORE_RANGE_TABLE);
+
+				break;
+			}
+		case T_TargetEntry:
+			{
+				TargetEntry *tle = (TargetEntry *)node;
+				if (isIvmName(tle->resname))
+						ereport(ERROR,
+								(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+								 errmsg("column name %s is not supported on incrementally maintainable materialized view", tle->resname)));
+
+				expression_tree_walker(node, check_ivm_restriction_walker, NULL);
+				break;
+			}
+		case T_JoinExpr:
+			{
+				JoinExpr *joinexpr = (JoinExpr *)node;
+
+				if (joinexpr->jointype > JOIN_INNER)
+						ereport(ERROR,
+								(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+								 errmsg("OUTER JOIN is not supported on incrementally maintainable materialized view")));
+
+				expression_tree_walker(node, check_ivm_restriction_walker, NULL);
+			}
+			break;
+		case T_Aggref:
+			ereport(ERROR,
+					(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+					 errmsg("aggregate function is not supported on incrementally maintainable materialized view")));
+			break;
+		default:
+			expression_tree_walker(node, check_ivm_restriction_walker, (void *) context);
+			break;
+	}
+	return false;
+}
+
+/*
+ * CreateIndexOnIMMV
+ *
+ * Create a unique index on incremental maintainable materialized view.
+ * If the view definition query has a GROUP BY clause, the index is created
+ * on the columns of GROUP BY expressions. Otherwise, if the view contains
+ * all primary key attributes of its base tables in the target list, the index
+ * is created on these attributes. In other cases, no index is created.
+ */
+void
+CreateIndexOnIMMV(Query *query, Relation matviewRel)
+{
+	ListCell *lc;
+	IndexStmt  *index;
+	ObjectAddress address;
+	List *constraintList = NIL;
+	char		idxname[NAMEDATALEN];
+	List	   *indexoidlist = RelationGetIndexList(matviewRel);
+	ListCell   *indexoidscan;
+	Bitmapset *key_attnos;
+
+	snprintf(idxname, sizeof(idxname), "%s_index", RelationGetRelationName(matviewRel));
+
+	index = makeNode(IndexStmt);
+
+	index->unique = true;
+	index->primary = false;
+	index->isconstraint = false;
+	index->deferrable = false;
+	index->initdeferred = false;
+	index->idxname = idxname;
+	index->relation =
+		makeRangeVar(get_namespace_name(RelationGetNamespace(matviewRel)),
+					 pstrdup(RelationGetRelationName(matviewRel)),
+					 -1);
+	index->accessMethod = DEFAULT_INDEX_TYPE;
+	index->options = NIL;
+	index->tableSpace = get_tablespace_name(matviewRel->rd_rel->reltablespace);
+	index->whereClause = NULL;
+	index->indexParams = NIL;
+	index->indexIncludingParams = NIL;
+	index->excludeOpNames = NIL;
+	index->idxcomment = NULL;
+	index->indexOid = InvalidOid;
+	index->oldNumber = InvalidRelFileNumber;
+	index->oldCreateSubid = InvalidSubTransactionId;
+	index->oldFirstRelfilelocatorSubid = InvalidSubTransactionId;
+	index->transformed = true;
+	index->concurrent = false;
+	index->if_not_exists = false;
+
+	/* create index on the base tables' primary key columns */
+	key_attnos = get_primary_key_attnos_from_query(query, &constraintList);
+	if (key_attnos)
+	{
+		foreach(lc, query->targetList)
+		{
+			TargetEntry *tle = (TargetEntry *) lfirst(lc);
+			Form_pg_attribute attr = TupleDescAttr(matviewRel->rd_att, tle->resno - 1);
+
+			if (bms_is_member(tle->resno - FirstLowInvalidHeapAttributeNumber, key_attnos))
+			{
+				IndexElem  *iparam;
+
+				iparam = makeNode(IndexElem);
+				iparam->name = pstrdup(NameStr(attr->attname));
+				iparam->expr = NULL;
+				iparam->indexcolname = NULL;
+				iparam->collation = NIL;
+				iparam->opclass = NIL;
+				iparam->opclassopts = NIL;
+				iparam->ordering = SORTBY_DEFAULT;
+				iparam->nulls_ordering = SORTBY_NULLS_DEFAULT;
+				index->indexParams = lappend(index->indexParams, iparam);
+			}
+		}
+	}
+	else
+	{
+		/* create no index, just notice that an appropriate index is necessary for efficient IVM */
+		ereport(NOTICE,
+				(errmsg("could not create an index on materialized view \"%s\" automatically",
+						RelationGetRelationName(matviewRel)),
+				 errdetail("This target list does not have all the primary key columns. "),
+				 errhint("Create an index on the materialized view for efficient incremental maintenance.")));
+		return;
+	}
+
+	/* If we have a compatible index, we don't need to create another. */
+	foreach(indexoidscan, indexoidlist)
+	{
+		Oid			indexoid = lfirst_oid(indexoidscan);
+		Relation	indexRel;
+		bool		hasCompatibleIndex = false;
+
+		indexRel = index_open(indexoid, AccessShareLock);
+
+		if (CheckIndexCompatible(indexRel->rd_id,
+								index->accessMethod,
+								index->indexParams,
+								index->excludeOpNames,
+								false))
+			hasCompatibleIndex = true;
+
+		index_close(indexRel, AccessShareLock);
+
+		if (hasCompatibleIndex)
+			return;
+	}
+
+	address = DefineIndex(NULL,
+						  RelationGetRelid(matviewRel),
+						  index,
+						  InvalidOid,
+						  InvalidOid,
+						  InvalidOid,
+						  -1,
+						  false, true, false, false, true);
+
+	ereport(NOTICE,
+			(errmsg("created index \"%s\" on materialized view \"%s\"",
+					idxname, RelationGetRelationName(matviewRel))));
+
+	/*
+	 * Make dependencies so that the index is dropped if any base tables'
+	 * primary key is dropped.
+	 */
+	foreach(lc, constraintList)
+	{
+		Oid constraintOid = lfirst_oid(lc);
+		ObjectAddress	refaddr;
+
+		refaddr.classId = ConstraintRelationId;
+		refaddr.objectId = constraintOid;
+		refaddr.objectSubId = 0;
+
+		recordDependencyOn(&address, &refaddr, DEPENDENCY_NORMAL);
+	}
+}
+
+
+/*
+ * get_primary_key_attnos_from_query
+ *
+ * Identify the columns in base tables' primary keys in the target list.
+ *
+ * Returns a Bitmapset of the column attnos of the primary key's columns of
+ * tables that used in the query.  The attnos are offset by
+ * FirstLowInvalidHeapAttributeNumber as same as get_primary_key_attnos.
+ *
+ * If any table has no primary key or any primary key's columns is not in
+ * the target list, return NULL.  We also return NULL if any pkey constraint
+ * is deferrable.
+ *
+ * constraintList is set to a list of the OIDs of the pkey constraints.
+ */
+static Bitmapset *
+get_primary_key_attnos_from_query(Query *query, List **constraintList)
+{
+	List *key_attnos_list = NIL;
+	ListCell *lc;
+	int i;
+	Bitmapset *keys = NULL;
+	Relids	rels_in_from;
+
+	/*
+	 * Collect primary key attributes from all tables used in query. The key attributes
+	 * sets for each table are stored in key_attnos_list in order by RTE index.
+	 */
+	foreach(lc, query->rtable)
+	{
+		RangeTblEntry *r = (RangeTblEntry*) lfirst(lc);
+		Bitmapset *key_attnos;
+		bool	has_no_pkey = false;
+
+		/* for tables, call get_primary_key_attnos */
+		if (r->rtekind == RTE_RELATION)
+		{
+			Oid constraintOid;
+			key_attnos = get_primary_key_attnos(r->relid, false, &constraintOid);
+			*constraintList = lappend_oid(*constraintList, constraintOid);
+			has_no_pkey = (key_attnos == NULL);
+		}
+		/*
+		 * Ignore join rels, because they are flatten later by
+		 * flatten_join_alias_vars(). Store NULL into key_attnos_list
+		 * as a dummy.
+		 */
+		 else if (r->rtekind == RTE_JOIN)
+		 {
+			key_attnos = NULL;
+		}
+		/* for other RTEs, store NULL into key_attnos_list */
+		else
+			has_no_pkey = true;
+
+		/*
+		 * If any table or subquery has no primary key or its pkey constraint is deferrable,
+		 * we cannot get key attributes for this query, so return NULL.
+		 */
+		if (has_no_pkey)
+			return NULL;
+
+		key_attnos_list = lappend(key_attnos_list, key_attnos);
+	}
+
+	/* Collect key attributes appearing in the target list */
+	i = 1;
+	foreach(lc, query->targetList)
+	{
+		TargetEntry *tle = (TargetEntry *) flatten_join_alias_vars(NULL, query, lfirst(lc));
+
+		if (IsA(tle->expr, Var))
+		{
+			Var *var = (Var*) tle->expr;
+			Bitmapset *key_attnos = list_nth(key_attnos_list, var->varno - 1);
+
+			/* check if this attribute is from a base table's primary key */
+			if (bms_is_member(var->varattno - FirstLowInvalidHeapAttributeNumber, key_attnos))
+			{
+				/*
+				 * Remove found key attributes from key_attnos_list, and add this
+				 * to the result list.
+				 */
+				key_attnos = bms_del_member(key_attnos, var->varattno - FirstLowInvalidHeapAttributeNumber);
+				if (bms_is_empty(key_attnos))
+				{
+					key_attnos_list = list_delete_nth_cell(key_attnos_list, var->varno - 1);
+					key_attnos_list = list_insert_nth(key_attnos_list, var->varno - 1, NULL);
+				}
+				keys = bms_add_member(keys, i - FirstLowInvalidHeapAttributeNumber);
+			}
+		}
+		i++;
+	}
+
+	/* Collect RTE indexes of relations appearing in the FROM clause */
+	rels_in_from = get_relids_in_jointree((Node *) query->jointree, false, false);
+
+	/*
+	 * Check if all key attributes of relations in FROM are appearing in the target
+	 * list.  If an attribute remains in key_attnos_list in spite of the table is used
+	 * in FROM clause, the target is missing this key attribute, so we return NULL.
+	 */
+	i = 1;
+	foreach(lc, key_attnos_list)
+	{
+		Bitmapset *bms = (Bitmapset *)lfirst(lc);
+		if (!bms_is_empty(bms) && bms_is_member(i, rels_in_from))
+			return NULL;
+		i++;
+	}
+
+	return keys;
+}
diff --git a/src/backend/commands/matview.c b/src/backend/commands/matview.c
index f7d8007f796..eaf39f80cd3 100644
--- a/src/backend/commands/matview.c
+++ b/src/backend/commands/matview.c
@@ -23,24 +23,36 @@
 #include "catalog/indexing.h"
 #include "catalog/namespace.h"
 #include "catalog/pg_am.h"
+#include "catalog/pg_depend.h"
+#include "catalog/pg_trigger.h"
 #include "catalog/pg_opclass.h"
 #include "commands/matview.h"
 #include "commands/repack.h"
 #include "commands/tablecmds.h"
 #include "commands/tablespace.h"
+#include "commands/createas.h"
 #include "executor/executor.h"
 #include "executor/spi.h"
+#include "executor/tstoreReceiver.h"
 #include "miscadmin.h"
+#include "nodes/makefuncs.h"
+#include "parser/analyze.h"
+#include "parser/parse_clause.h"
+#include "parser/parse_func.h"
+#include "parser/parse_relation.h"
 #include "pgstat.h"
 #include "rewrite/rewriteHandler.h"
+#include "rewrite/rowsecurity.h"
 #include "storage/lmgr.h"
+#include "storage/lwlock.h"
 #include "tcop/tcopprot.h"
 #include "utils/builtins.h"
+#include "utils/fmgroids.h"
 #include "utils/lsyscache.h"
 #include "utils/rel.h"
 #include "utils/snapmgr.h"
 #include "utils/syscache.h"
-
+#include "utils/typcache.h"
 
 typedef struct
 {
@@ -53,6 +65,97 @@ typedef struct
 	BulkInsertState bistate;	/* bulk insert state */
 } DR_transientrel;
 
+#define MV_INIT_QUERYHASHSIZE	16
+
+/*
+ * MV_TriggerHashEntry
+ *
+ * Hash entry for base tables on which IVM trigger is invoked
+ */
+typedef struct MV_TriggerHashEntry
+{
+	Oid	matview_id;			/* OID of the materialized view */
+	int	before_trig_count;	/* count of before triggers invoked */
+	int	after_trig_count;	/* count of after triggers invoked */
+
+	Snapshot	snapshot;	/* Snapshot just before table change */
+
+	List   *tables;		/* List of MV_TriggerTable */
+	bool	has_old;	/* tuples are deleted from any table? */
+	bool	has_new;	/* tuples are inserted into any table? */
+
+	/*
+	 * List of sub-transaction IDs that incrementally updated the view.
+	 * This list is maintained through a transaction, and an ID is removed
+	 * when a sub-transaction is aborted. If any ID is left when the
+	 * transaction is committed, this means the view is incrementally
+	 * updated in this transaction.
+	 */
+	List   *subxids;
+} MV_TriggerHashEntry;
+
+/*
+ * MV_TriggerTable
+ *
+ * IVM related data for tables on which the trigger is invoked.
+ */
+typedef struct MV_TriggerTable
+{
+	Oid		table_id;			/* OID of the modified table */
+	List   *old_tuplestores;	/* tuplestores for deleted tuples */
+	List   *new_tuplestores;	/* tuplestores for inserted tuples */
+
+	List   *rte_indexes;		/* List of RTE index of the modified table */
+	RangeTblEntry *original_rte;	/* the original RTE saved before rewriting query */
+
+	Relation	rel;			/* relation of the modified table */
+	TupleTableSlot *slot;		/* for checking visibility in the pre-state table */
+} MV_TriggerTable;
+
+typedef struct DroppedImmvInfo
+{
+	Oid					immv_oid;
+	SubTransactionId	subxid;
+} DroppedImmvInfo;
+
+static HTAB *mv_trigger_info = NULL;
+static HTAB *dropped_immv = NULL;
+
+static HTAB *LastIvmUpdateHash;
+
+#define LAST_IVM_UPDATE_HASH_SIZE 256
+
+static void IvmShmemRequest(void *arg);
+
+/* hash table entries */
+typedef struct LastIvmUpdateEntry
+{
+	Oid		oid;	/* hash key */
+	FullTransactionId	last_ivm_update;
+} LastIvmUpdateEntry;
+
+const ShmemCallbacks IvmShmemCallbacks = {
+	.request_fn = IvmShmemRequest,
+};
+
+static void
+IvmShmemRequest(void *arg)
+{
+	ShmemRequestHash(.name = "LastIvmUpdate hash",
+					 .nelems = LAST_IVM_UPDATE_HASH_SIZE,
+					 .ptr = &LastIvmUpdateHash,
+					 .hash_info.keysize = sizeof(Oid),
+					 .hash_info.entrysize = sizeof(LastIvmUpdateEntry),
+					 .hash_flags = HASH_ELEM | HASH_BLOBS,
+		);
+}
+
+static bool in_delta_calculation = false;
+
+/* ENR name for materialized view delta */
+#define NEW_DELTA_ENRNAME "new_delta"
+#define OLD_DELTA_ENRNAME "old_delta"
+
 static int	matview_maintenance_depth = 0;
 
 static void transientrel_startup(DestReceiver *self, int operation, TupleDesc typeinfo);
@@ -60,6 +163,8 @@ static bool transientrel_receive(TupleTableSlot *slot, DestReceiver *self);
 static void transientrel_shutdown(DestReceiver *self);
 static void transientrel_destroy(DestReceiver *self);
 static uint64 refresh_matview_datafill(DestReceiver *dest, Query *query,
+									   QueryEnvironment *queryEnv,
+									   TupleDesc *resultTupleDesc,
 									   const char *queryString, bool is_create);
 static void refresh_by_match_merge(Oid matviewOid, Oid tempOid, Oid relowner,
 								   int save_sec_context);
@@ -67,6 +172,41 @@ static void refresh_by_heap_swap(Oid matviewOid, Oid OIDNewHeap, char relpersist
 static bool is_usable_unique_index(Relation indexRel);
 static void OpenMatViewIncrementalMaintenance(void);
 static void CloseMatViewIncrementalMaintenance(void);
+static Query *get_matview_query(Relation matviewRel);
+
+static Query *rewrite_query_for_preupdate_state(Query *query, List *tables,
+								  ParseState *pstate, Oid matviewid);
+static void register_delta_ENRs(ParseState *pstate, Query *query, List *tables);
+static char *make_subquery_targetlist_from_table(MV_TriggerTable *table);
+static char *make_delta_enr_name(const char *prefix, Oid relid, int count);
+static RangeTblEntry *get_prestate_rte(RangeTblEntry *rte, MV_TriggerTable *table,
+				 QueryEnvironment *queryEnv, Oid matviewid);
+static RangeTblEntry *makeDeltaTable(RangeTblEntry *rte, MV_TriggerTable *table,
+									 bool is_new, QueryEnvironment *queryEnv);
+static Query *rewrite_query_for_counting(Query *query, ParseState *pstate);
+
+static void calc_delta(MV_TriggerTable *table, int rte_index, Query *query,
+			DestReceiver *dest_old, DestReceiver *dest_new,
+			TupleDesc *tupdesc_old, TupleDesc *tupdesc_new,
+			QueryEnvironment *queryEnv);
+static Query *rewrite_query_for_postupdate_state(Query *query, MV_TriggerTable *table, int rte_index);
+
+static void apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *new_tuplestores,
+			TupleDesc tupdesc_old, TupleDesc tupdesc_new,
+			Query *query);
+static void apply_old_delta(const char *matviewname, const char *deltaname_old,
+				List *keys);
+static void apply_new_delta(const char *matviewname, const char *deltaname_new,
+				StringInfo target_list);
+static char *get_matching_condition_string(List *keys);
+static void generate_equal(StringInfo querybuf, Oid opttype,
+			   const char *leftop, const char *rightop);
+
+static void mv_InitHashTables(void);
+static void clean_up_IVM_hash_entry(MV_TriggerHashEntry *entry, bool is_abort,
+									SubTransactionId subxid);
+static void setLastUpdateXid(Oid immv_oid, FullTransactionId xid);
+static FullTransactionId getLastUpdateXid(Oid immv_oid);
 
 /*
  * SetMatViewPopulatedState
@@ -108,6 +248,46 @@ SetMatViewPopulatedState(Relation relation, bool newstate)
 	CommandCounterIncrement();
 }
 
+/*
+ * SetMatViewIVMState
+ *		Mark a materialized view as IVM, or not.
+ *
+ * NOTE: caller must be holding an appropriate lock on the relation.
+ */
+void
+SetMatViewIVMState(Relation relation, bool newstate)
+{
+	Relation	pgrel;
+	HeapTuple	tuple;
+
+	Assert(relation->rd_rel->relkind == RELKIND_MATVIEW);
+
+	/*
+	 * Update relation's pg_class entry.  Crucial side-effect: other backends
+	 * (and this one too!) are sent SI message to make them rebuild relcache
+	 * entries.
+	 */
+	pgrel = table_open(RelationRelationId, RowExclusiveLock);
+	tuple = SearchSysCacheCopy1(RELOID,
+								ObjectIdGetDatum(RelationGetRelid(relation)));
+	if (!HeapTupleIsValid(tuple))
+		elog(ERROR, "cache lookup failed for relation %u",
+			 RelationGetRelid(relation));
+
+	((Form_pg_class) GETSTRUCT(tuple))->relisivm = newstate;
+
+	CatalogTupleUpdate(pgrel, &tuple->t_self, tuple);
+
+	heap_freetuple(tuple);
+	table_close(pgrel, RowExclusiveLock);
+
+	/*
+	 * Advance command counter to make the updated pg_class row locally
+	 * visible.
+	 */
+	CommandCounterIncrement();
+}
+
 /*
  * ExecRefreshMatView -- execute a REFRESH MATERIALIZED VIEW command
  *
@@ -166,8 +346,6 @@ RefreshMatViewByOid(Oid matviewOid, bool is_create, bool skipData,
 					QueryCompletion *qc)
 {
 	Relation	matviewRel;
-	RewriteRule *rule;
-	List	   *actions;
 	Query	   *dataQuery;
 	Oid			tableSpace;
 	Oid			relowner;
@@ -178,6 +356,7 @@ RefreshMatViewByOid(Oid matviewOid, bool is_create, bool skipData,
 	int			save_sec_context;
 	int			save_nestlevel;
 	ObjectAddress address;
+	bool oldPopulated;
 
 	matviewRel = table_open(matviewOid, NoLock);
 	relowner = matviewRel->rd_rel->relowner;
@@ -193,6 +372,8 @@ RefreshMatViewByOid(Oid matviewOid, bool is_create, bool skipData,
 	save_nestlevel = NewGUCNestLevel();
 	RestrictSearchPath();
 
+	oldPopulated = RelationIsPopulated(matviewRel);
+
 	/* Make sure it is a materialized view. */
 	if (matviewRel->rd_rel->relkind != RELKIND_MATVIEW)
 		ereport(ERROR,
@@ -213,32 +394,7 @@ RefreshMatViewByOid(Oid matviewOid, bool is_create, bool skipData,
 				 errmsg("%s options %s and %s cannot be used together",
 						"REFRESH", "CONCURRENTLY", "WITH NO DATA")));
 
-	/*
-	 * Check that everything is correct for a refresh. Problems at this point
-	 * are internal errors, so elog is sufficient.
-	 */
-	if (matviewRel->rd_rel->relhasrules == false ||
-		matviewRel->rd_rules->numLocks < 1)
-		elog(ERROR,
-			 "materialized view \"%s\" is missing rewrite information",
-			 RelationGetRelationName(matviewRel));
-
-	if (matviewRel->rd_rules->numLocks > 1)
-		elog(ERROR,
-			 "materialized view \"%s\" has too many rules",
-			 RelationGetRelationName(matviewRel));
-
-	rule = matviewRel->rd_rules->rules[0];
-	if (rule->event != CMD_SELECT || !(rule->isInstead))
-		elog(ERROR,
-			 "the rule for materialized view \"%s\" is not a SELECT INSTEAD OF rule",
-			 RelationGetRelationName(matviewRel));
-
-	actions = rule->actions;
-	if (list_length(actions) != 1)
-		elog(ERROR,
-			 "the rule for materialized view \"%s\" is not a single action",
-			 RelationGetRelationName(matviewRel));
+	dataQuery = get_matview_query(matviewRel);
 
 	/*
 	 * Check that there is a unique index with no WHERE clause on one or more
@@ -275,12 +431,6 @@ RefreshMatViewByOid(Oid matviewOid, bool is_create, bool skipData,
 					 errhint("Create a unique index with no WHERE clause on one or more columns of the materialized view.")));
 	}
 
-	/*
-	 * The stored query was rewritten at the time of the MV definition, but
-	 * has not been scribbled on by the planner.
-	 */
-	dataQuery = linitial_node(Query, actions);
-
 	/*
 	 * Check for active uses of the relation in the current transaction, such
 	 * as open scans.
@@ -310,6 +460,90 @@ RefreshMatViewByOid(Oid matviewOid, bool is_create, bool skipData,
 		relpersistence = matviewRel->rd_rel->relpersistence;
 	}
 
+	/* delete IMMV triggers. */
+	if (RelationIsIVM(matviewRel) && skipData)
+	{
+		Relation	tgRel;
+		Relation	depRel;
+		ScanKeyData key;
+		SysScanDesc scan;
+		HeapTuple	tup;
+		ObjectAddresses *immv_triggers;
+
+		immv_triggers = new_object_addresses();
+
+		tgRel = table_open(TriggerRelationId, RowExclusiveLock);
+		depRel = table_open(DependRelationId, RowExclusiveLock);
+
+		/* search triggers that depends on IMMV. */
+		ScanKeyInit(&key,
+					Anum_pg_depend_refobjid,
+					BTEqualStrategyNumber, F_OIDEQ,
+					ObjectIdGetDatum(matviewOid));
+		scan = systable_beginscan(depRel, DependReferenceIndexId, true,
+								  NULL, 1, &key);
+		while ((tup = systable_getnext(scan)) != NULL)
+		{
+			ObjectAddress obj;
+			Form_pg_depend foundDep = (Form_pg_depend) GETSTRUCT(tup);
+
+			if (foundDep->classid == TriggerRelationId)
+			{
+				HeapTuple	tgtup;
+				ScanKeyData tgkey[1];
+				SysScanDesc tgscan;
+				Form_pg_trigger tgform;
+
+				/* Find the trigger name. */
+				ScanKeyInit(&tgkey[0],
+							Anum_pg_trigger_oid,
+							BTEqualStrategyNumber, F_OIDEQ,
+							ObjectIdGetDatum(foundDep->objid));
+
+				tgscan = systable_beginscan(tgRel, TriggerOidIndexId, true,
+											NULL, 1, tgkey);
+				tgtup = systable_getnext(tgscan);
+				if (!HeapTupleIsValid(tgtup))
+					elog(ERROR, "could not find tuple for immv trigger %u", foundDep->objid);
+
+				tgform = (Form_pg_trigger) GETSTRUCT(tgtup);
+
+				/* If trigger is created by IMMV, delete it. */
+				if (strncmp(NameStr(tgform->tgname), "IVM_trigger_", 12) == 0)
+				{
+					obj.classId = foundDep->classid;
+					obj.objectId = foundDep->objid;
+					obj.objectSubId = foundDep->refobjsubid;
+					add_exact_object_address(&obj, immv_triggers);
+				}
+				systable_endscan(tgscan);
+			}
+		}
+		systable_endscan(scan);
+
+		performMultipleDeletions(immv_triggers, DROP_RESTRICT, PERFORM_DELETION_INTERNAL);
+
+		table_close(depRel, RowExclusiveLock);
+		table_close(tgRel, RowExclusiveLock);
+		free_object_addresses(immv_triggers);
+	}
+
+	/*
+	 * Create triggers on incremental maintainable materialized view
+	 * This argument should use 'dataQuery'. This needs to use a rewritten query,
+	 * because a sublink in jointree is not supported by this function.
+	 *
+	 * This is performed before generating data because we have to wait
+	 * concurrent transactions modifying a base table and then take a snapshot
+	 * to see changes by these transactions to make sure a consistent view
+	 * is created.
+	 */
+	if (RelationIsIVM(matviewRel) && !skipData && !oldPopulated)
+	{
+		CreateIvmTriggersOnBaseTables(dataQuery, matviewOid);
+		CreateIndexOnIMMV(dataQuery, matviewRel);
+	}
+
 	/*
 	 * Create the transient table that will receive the regenerated data. Lock
 	 * it against access by any other process until commit (by which time it
@@ -326,8 +560,43 @@ RefreshMatViewByOid(Oid matviewOid, bool is_create, bool skipData,
 		DestReceiver *dest;
 
 		dest = CreateTransientRelDestReceiver(OIDNewHeap);
-		processed = refresh_matview_datafill(dest, dataQuery, queryString,
-											 is_create);
+
+		if (RelationIsIVM(matviewRel))
+		{
+			/*
+			 * In READ COMMITTED, get and push the latest snapshot again to see the
+			 * results of concurrent transactions committed after the current
+			 * transaction started.
+			 */
+			if (!IsolationUsesXactSnapshot())
+				PushActiveSnapshot(GetTransactionSnapshot());
+
+			/*
+			 * If a concurrent transaction updated the view incrementally and was
+			 * committed before we acquired the lock, the results of refresh_immv could
+			 * be inconsistent. Therefore, we have to check the transaction ID of the
+			 * most recent update of the view, and if this was in progress at the
+			 * transaction start, raise an error to prevent anomalies.
+			 */
+			if (!is_create)
+			{
+				FullTransactionId xid;
+
+				xid = getLastUpdateXid(matviewOid);
+				if (XidInMVCCSnapshot(XidFromFullTransactionId(xid), GetActiveSnapshot()))
+					ereport(ERROR,
+							(errcode(ERRCODE_T_R_SERIALIZATION_FAILURE),
+							 errmsg("the materialized view is incrementally updated in concurrent transaction"),
+							 errhint("The transaction might succeed if retried.")));
+			}
+		}
+
+		processed = refresh_matview_datafill(dest, dataQuery, NULL, NULL,
+											 queryString, is_create);
+
+		/* Pop the original snapshot. */
+		if (RelationIsIVM(matviewRel) && !IsolationUsesXactSnapshot())
+			PopActiveSnapshot();
 	}
 
 	/* Make the matview match the newly generated data. */
@@ -402,6 +671,8 @@ RefreshMatViewByOid(Oid matviewOid, bool is_create, bool skipData,
  */
 static uint64
 refresh_matview_datafill(DestReceiver *dest, Query *query,
+						 QueryEnvironment *queryEnv,
+						 TupleDesc *resultTupleDesc,
 						 const char *queryString, bool is_create)
 {
 	List	   *rewritten;
@@ -439,7 +710,7 @@ refresh_matview_datafill(DestReceiver *dest, Query *query,
 	/* Create a QueryDesc, redirecting output to our tuple receiver */
 	queryDesc = CreateQueryDesc(plan, queryString,
 								GetActiveSnapshot(), InvalidSnapshot,
-								dest, NULL, NULL, 0);
+								dest, NULL, queryEnv ? queryEnv: NULL, 0);
 
 	/* call ExecutorStart to prepare the plan for execution */
 	ExecutorStart(queryDesc, 0);
@@ -449,6 +720,9 @@ refresh_matview_datafill(DestReceiver *dest, Query *query,
 
 	processed = queryDesc->estate->es_processed;
 
+	if (resultTupleDesc)
+		*resultTupleDesc = CreateTupleDescCopy(queryDesc->tupDesc);
+
 	/* and clean up */
 	ExecutorFinish(queryDesc);
 	ExecutorEnd(queryDesc);
@@ -967,3 +1241,1488 @@ CloseMatViewIncrementalMaintenance(void)
 	matview_maintenance_depth--;
 	Assert(matview_maintenance_depth >= 0);
 }
+
+/*
+ * get_matview_query - get the Query from a matview's _RETURN rule.
+ */
+static Query *
+get_matview_query(Relation matviewRel)
+{
+	RewriteRule *rule;
+	List * actions;
+
+	/*
+	 * Check that everything is correct for a refresh. Problems at this point
+	 * are internal errors, so elog is sufficient.
+	 */
+	if (matviewRel->rd_rel->relhasrules == false ||
+		matviewRel->rd_rules->numLocks < 1)
+		elog(ERROR,
+			 "materialized view \"%s\" is missing rewrite information",
+			 RelationGetRelationName(matviewRel));
+
+	if (matviewRel->rd_rules->numLocks > 1)
+		elog(ERROR,
+			 "materialized view \"%s\" has too many rules",
+			 RelationGetRelationName(matviewRel));
+
+	rule = matviewRel->rd_rules->rules[0];
+	if (rule->event != CMD_SELECT || !(rule->isInstead))
+		elog(ERROR,
+			 "the rule for materialized view \"%s\" is not a SELECT INSTEAD OF rule",
+			 RelationGetRelationName(matviewRel));
+
+	actions = rule->actions;
+	if (list_length(actions) != 1)
+		elog(ERROR,
+			 "the rule for materialized view \"%s\" is not a single action",
+			 RelationGetRelationName(matviewRel));
+
+	/*
+	 * The stored query was rewritten at the time of the MV definition, but
+	 * has not been scribbled on by the planner.
+	 */
+	return linitial_node(Query, actions);
+}
+
+
+/* ----------------------------------------------------
+ *		Incremental View Maintenance routines
+ * ---------------------------------------------------
+ */
+
+/*
+ * IVM_immediate_before
+ *
+ * IVM trigger function invoked before base table is modified. If this is
+ * invoked firstly in the same statement, we save the transaction id and the
+ * command id at that time.
+ */
+Datum
+IVM_immediate_before(PG_FUNCTION_ARGS)
+{
+	TriggerData *trigdata = (TriggerData *) fcinfo->context;
+	char	   *matviewOid_text = trigdata->tg_trigger->tgargs[0];
+	char	   *ex_lock_text = trigdata->tg_trigger->tgargs[1];
+	Oid			matviewOid;
+	MV_TriggerHashEntry *entry;
+	bool	found;
+	bool	ex_lock;
+
+	matviewOid = DatumGetObjectId(DirectFunctionCall1(oidin, CStringGetDatum(matviewOid_text)));
+	ex_lock = DatumGetBool(DirectFunctionCall1(boolin, CStringGetDatum(ex_lock_text)));
+
+	/* If the view has more than one tables, we have to use an exclusive lock. */
+	if (ex_lock)
+	{
+		FullTransactionId xid;
+
+		/*
+		 * Wait for concurrent transactions which update this materialized view at
+		 * READ COMMITED. This is needed to see changes committed in other
+		 * transactions. No wait and raise an error at REPEATABLE READ or
+		 * SERIALIZABLE to prevent update anomalies of matviews.
+		 * XXX: dead-lock is possible here.
+		 */
+		if (!IsolationUsesXactSnapshot())
+			LockRelationOid(matviewOid, ExclusiveLock);
+		else if (!ConditionalLockRelationOid(matviewOid, ExclusiveLock))
+		{
+			/* try to throw error by name; relation could be deleted... */
+			char	   *relname = get_rel_name(matviewOid);
+
+			if (!relname)
+				ereport(ERROR,
+						(errcode(ERRCODE_LOCK_NOT_AVAILABLE),
+						errmsg("could not obtain lock on materialized view during incremental maintenance")));
+
+			ereport(ERROR,
+					(errcode(ERRCODE_LOCK_NOT_AVAILABLE),
+					errmsg("could not obtain lock on materialized view \"%s\" during incremental maintenance",
+							relname)));
+		}
+
+		/*
+		 * Even if we can acquire an lock, a concurrent transaction could have
+		 * updated the view incrementally and been committed before we acquired
+		 * the lock. Therefore, we have to check the transaction ID of the most
+		 * recent update of the view, and if this was in progress at the
+		 * transaction start, raise an error to prevent anomalies.
+		 */
+		xid = getLastUpdateXid(matviewOid);
+		if (XidInMVCCSnapshot(XidFromFullTransactionId(xid), GetTransactionSnapshot()))
+			ereport(ERROR,
+					(errcode(ERRCODE_T_R_SERIALIZATION_FAILURE),
+					 errmsg("the materialized view is incrementally updated in concurrent transaction"),
+					 errhint("The transaction might succeed if retried.")));
+	}
+	else
+		LockRelationOid(matviewOid, RowExclusiveLock);
+
+	/*
+	 * On the first call initialize the hashtable
+	 */
+	if (!mv_trigger_info)
+		mv_InitHashTables();
+
+	entry = (MV_TriggerHashEntry *) hash_search(mv_trigger_info,
+											  (void *) &matviewOid,
+											  HASH_ENTER, &found);
+
+	/* On the first BEFORE to update the view, initialize trigger data */
+	if (!found || entry->snapshot == InvalidSnapshot)
+	{
+		Snapshot snapshot;
+
+		/*
+		 * Get a snapshot just before the table was modified for checking
+		 * tuple visibility in the pre-update state of the table.
+		 *
+		 * In READ COMMITTED, use the latest snapshot again to see the
+		 * results of concurrent transactions committed after the current
+		 * transaction started.
+		 */
+		if (IsolationUsesXactSnapshot())
+			snapshot = GetActiveSnapshot();
+		else
+			snapshot = GetTransactionSnapshot();
+
+		entry->matview_id = matviewOid;
+		entry->before_trig_count = 0;
+		entry->after_trig_count = 0;
+		entry->snapshot = RegisterSnapshot(snapshot);
+		entry->tables = NIL;
+		entry->has_old = false;
+		entry->has_new = false;
+
+		/*
+		 * If this is the first table modifying query in the transaction,
+		 * initialize the list of subxids.
+		 */
+		if (!found)
+			entry->subxids = NIL;
+	}
+
+	entry->before_trig_count++;
+
+	return PointerGetDatum(NULL);
+}
+
+/*
+ * IVM_immediate_maintenance
+ *
+ * IVM trigger function invoked after base table is modified.
+ * For each table, tuplestores of transition tables are collected.
+ * and after the last modification
+ */
+Datum
+IVM_immediate_maintenance(PG_FUNCTION_ARGS)
+{
+	TriggerData *trigdata = (TriggerData *) fcinfo->context;
+	Relation	rel;
+	Oid			relid;
+	Oid			matviewOid;
+	Query	   *query;
+	Query	   *rewritten = NULL;
+	char	   *matviewOid_text = trigdata->tg_trigger->tgargs[0];
+	Relation	matviewRel;
+	int old_depth = matview_maintenance_depth;
+	SubTransactionId subxid;
+
+	Oid			relowner;
+	Tuplestorestate *old_tuplestore = NULL;
+	Tuplestorestate *new_tuplestore = NULL;
+	DestReceiver *dest_new = NULL, *dest_old = NULL;
+	Oid			save_userid;
+	int			save_sec_context;
+	int			save_nestlevel;
+
+	MV_TriggerHashEntry *entry;
+	MV_TriggerTable		*table;
+	bool	found;
+
+	ParseState		 *pstate;
+	QueryEnvironment *queryEnv = create_queryEnv();
+	MemoryContext	oldcxt;
+	ListCell   *lc;
+	int			i;
+
+
+	/* Create a ParseState for rewriting the view definition query */
+	pstate = make_parsestate(NULL);
+	pstate->p_queryEnv = queryEnv;
+	pstate->p_expr_kind = EXPR_KIND_SELECT_TARGET;
+
+	rel = trigdata->tg_relation;
+	relid = rel->rd_id;
+
+	matviewOid = DatumGetObjectId(DirectFunctionCall1(oidin, CStringGetDatum(matviewOid_text)));
+
+	/*
+	 * On the first call initialize the hashtable
+	 */
+	if (!mv_trigger_info)
+		mv_InitHashTables();
+
+	/* get the entry for this materialized view */
+	entry = (MV_TriggerHashEntry *) hash_search(mv_trigger_info,
+											  (void *) &matviewOid,
+											  HASH_FIND, &found);
+	Assert (found && entry != NULL);
+	entry->after_trig_count++;
+
+	/* search the entry for the modified table and create new entry if not found */
+	found = false;
+	foreach(lc, entry->tables)
+	{
+		table = (MV_TriggerTable *) lfirst(lc);
+		if (table->table_id == relid)
+		{
+			found = true;
+			break;
+		}
+	}
+	if (!found)
+	{
+		oldcxt = MemoryContextSwitchTo(TopTransactionContext);
+
+		table = (MV_TriggerTable *) palloc0(sizeof(MV_TriggerTable));
+		table->table_id = relid;
+		table->old_tuplestores = NIL;
+		table->new_tuplestores = NIL;
+		table->rte_indexes = NIL;
+		table->slot = MakeSingleTupleTableSlot(RelationGetDescr(rel), table_slot_callbacks(rel));
+		/* We assume we have at least RowExclusiveLock on modified tables. */
+		table->rel = table_open(RelationGetRelid(rel), NoLock);
+		entry->tables = lappend(entry->tables, table);
+
+		MemoryContextSwitchTo(oldcxt);
+	}
+
+	/* Save the transition tables and make a request to not free immediately */
+	if (trigdata->tg_oldtable)
+	{
+		oldcxt = MemoryContextSwitchTo(TopTransactionContext);
+		table->old_tuplestores = lappend(table->old_tuplestores, trigdata->tg_oldtable);
+		entry->has_old = true;
+		MemoryContextSwitchTo(oldcxt);
+	}
+	if (trigdata->tg_newtable)
+	{
+		oldcxt = MemoryContextSwitchTo(TopTransactionContext);
+		table->new_tuplestores = lappend(table->new_tuplestores, trigdata->tg_newtable);
+		entry->has_new = true;
+		MemoryContextSwitchTo(oldcxt);
+	}
+	if (entry->has_new || entry->has_old)
+	{
+		CmdType cmd;
+
+		if (TRIGGER_FIRED_BY_INSERT(trigdata->tg_event))
+			cmd = CMD_INSERT;
+		else if (TRIGGER_FIRED_BY_DELETE(trigdata->tg_event))
+			cmd = CMD_DELETE;
+		else if (TRIGGER_FIRED_BY_UPDATE(trigdata->tg_event))
+			cmd = CMD_UPDATE;
+		else
+			elog(ERROR,"unsupported trigger type");
+
+		/* Prolong lifespan of transition tables to the end of the last AFTER trigger */
+		SetTransitionTablePreserved(relid, cmd);
+	}
+
+
+	/* If this is not the last AFTER trigger call, immediately exit. */
+	Assert (entry->before_trig_count >= entry->after_trig_count);
+	if (entry->before_trig_count != entry->after_trig_count)
+		return PointerGetDatum(NULL);
+
+	/*
+	 * If this is the last AFTER trigger call, continue and update the view.
+	 */
+
+	/* record the subxid that updated the view incrementally */
+	subxid = GetCurrentSubTransactionId();
+	if (!list_member_xid(entry->subxids, subxid))
+	{
+		oldcxt = MemoryContextSwitchTo(TopTransactionContext);
+		entry->subxids = lappend_xid(entry->subxids, subxid);
+		MemoryContextSwitchTo(oldcxt);
+	}
+
+	/*
+	 * Advance command counter to make the updated base table rows locally
+	 * visible.
+	 */
+	CommandCounterIncrement();
+
+	matviewRel = table_open(matviewOid, NoLock);
+
+	/* Make sure it is a materialized view. */
+	Assert(matviewRel->rd_rel->relkind == RELKIND_MATVIEW);
+
+	/*
+	 * In READ COMMITTED, get and push the latest snapshot again to see the
+	 * results of concurrent transactions committed after the current
+	 * transaction started.
+	 */
+	if (!IsolationUsesXactSnapshot())
+		PushActiveSnapshot(GetTransactionSnapshot());
+
+	/*
+	 * Check for active uses of the relation in the current transaction, such
+	 * as open scans.
+	 *
+	 * NB: We count on this to protect us against problems with refreshing the
+	 * data using TABLE_INSERT_FROZEN.
+	 */
+	CheckTableNotInUse(matviewRel, "refresh a materialized view incrementally");
+
+	/*
+	 * Switch to the owner's userid, so that any functions are run as that
+	 * user.  Also arrange to make GUC variable changes local to this command.
+	 * We will switch modes when we are about to execute user code.
+	 */
+	relowner = matviewRel->rd_rel->relowner;
+	GetUserIdAndSecContext(&save_userid, &save_sec_context);
+	SetUserIdAndSecContext(relowner,
+						   save_sec_context | SECURITY_RESTRICTED_OPERATION);
+	save_nestlevel = NewGUCNestLevel();
+
+	/* get view query*/
+	query = get_matview_query(matviewRel);
+
+	/*
+	 * When a base table is truncated, the view content will be empty if the
+	 * view definition query does not contain an aggregate without a GROUP clause.
+	 * Therefore, such views can be truncated.
+	 */
+	if (TRIGGER_FIRED_BY_TRUNCATE(trigdata->tg_event))
+	{
+		ExecuteTruncateGuts(list_make1(matviewRel), list_make1_oid(matviewOid),
+							NIL, DROP_RESTRICT, false, false);
+
+		/* Clean up hash entry and delete tuplestores */
+		clean_up_IVM_hash_entry(entry, false, InvalidSubTransactionId);
+
+		/* Pop the original snapshot. */
+		if (!IsolationUsesXactSnapshot())
+			PopActiveSnapshot();
+
+		table_close(matviewRel, NoLock);
+
+		/* Roll back any GUC changes */
+		AtEOXact_GUC(false, save_nestlevel);
+
+		/* Restore userid and security context */
+		SetUserIdAndSecContext(save_userid, save_sec_context);
+
+		return PointerGetDatum(NULL);
+	}
+
+	/*
+	 * rewrite query for calculating deltas
+	 */
+
+	rewritten = copyObject(query);
+
+	/* Replace resnames in a target list with materialized view's attnames */
+	i = 0;
+	foreach (lc, rewritten->targetList)
+	{
+		TargetEntry *tle = (TargetEntry *) lfirst(lc);
+		Form_pg_attribute attr = TupleDescAttr(matviewRel->rd_att, i);
+		char *resname = NameStr(attr->attname);
+
+		tle->resname = pstrdup(resname);
+		i++;
+	}
+
+	/* Set all tables in the query to pre-update state */
+	rewritten = rewrite_query_for_preupdate_state(rewritten, entry->tables,
+												  pstate, matviewOid);
+	/* Rewrite for counting duplicated tuples */
+	rewritten = rewrite_query_for_counting(rewritten, pstate);
+
+	/* Create tuplestores to store view deltas */
+	if (entry->has_old)
+	{
+		oldcxt = MemoryContextSwitchTo(TopTransactionContext);
+
+		old_tuplestore = tuplestore_begin_heap(false, false, work_mem);
+		dest_old = CreateDestReceiver(DestTuplestore);
+		SetTuplestoreDestReceiverParams(dest_old,
+									old_tuplestore,
+									TopTransactionContext,
+									false,
+									NULL,
+									NULL);
+
+		MemoryContextSwitchTo(oldcxt);
+	}
+	if (entry->has_new)
+	{
+		oldcxt = MemoryContextSwitchTo(TopTransactionContext);
+
+		new_tuplestore = tuplestore_begin_heap(false, false, work_mem);
+		dest_new = CreateDestReceiver(DestTuplestore);
+		SetTuplestoreDestReceiverParams(dest_new,
+									new_tuplestore,
+									TopTransactionContext,
+									false,
+									NULL,
+									NULL);
+		MemoryContextSwitchTo(oldcxt);
+	}
+
+	/* for all modified tables */
+	foreach(lc, entry->tables)
+	{
+		ListCell *lc2;
+
+		table = (MV_TriggerTable *) lfirst(lc);
+
+		/* loop for self-join */
+		foreach(lc2, table->rte_indexes)
+		{
+			int	rte_index = lfirst_int(lc2);
+			TupleDesc		tupdesc_old;
+			TupleDesc		tupdesc_new;
+
+			/* calculate delta tables */
+			calc_delta(table, rte_index, rewritten, dest_old, dest_new,
+					   &tupdesc_old, &tupdesc_new, queryEnv);
+
+			/* Set the table in the query to post-update state */
+			rewritten = rewrite_query_for_postupdate_state(rewritten, table, rte_index);
+
+			PG_TRY();
+			{
+				/* apply the delta tables to the materialized view */
+				apply_delta(matviewOid, old_tuplestore, new_tuplestore,
+							tupdesc_old, tupdesc_new, query);
+			}
+			PG_CATCH();
+			{
+				matview_maintenance_depth = old_depth;
+				PG_RE_THROW();
+			}
+			PG_END_TRY();
+
+			/* clear view delta tuplestores */
+			if (old_tuplestore)
+				tuplestore_clear(old_tuplestore);
+			if (new_tuplestore)
+				tuplestore_clear(new_tuplestore);
+		}
+	}
+
+	/* Clean up hash entry and delete tuplestores */
+	clean_up_IVM_hash_entry(entry, false, InvalidSubTransactionId);
+	if (old_tuplestore)
+	{
+		dest_old->rDestroy(dest_old);
+		tuplestore_end(old_tuplestore);
+	}
+	if (new_tuplestore)
+	{
+		dest_new->rDestroy(dest_new);
+		tuplestore_end(new_tuplestore);
+	}
+
+	/* Pop the original snapshot. */
+	if (!IsolationUsesXactSnapshot())
+		PopActiveSnapshot();
+
+	table_close(matviewRel, NoLock);
+
+	/* Roll back any GUC changes */
+	AtEOXact_GUC(false, save_nestlevel);
+
+	/* Restore userid and security context */
+	SetUserIdAndSecContext(save_userid, save_sec_context);
+
+	return PointerGetDatum(NULL);
+}
+
+/*
+ * rewrite_query_for_preupdate_state
+ *
+ * Rewrite the query so that base tables' RTEs will represent "pre-update"
+ * state of tables. This is necessary to calculate view delta after multiple
+ * tables are modified.
+ */
+static Query*
+rewrite_query_for_preupdate_state(Query *query, List *tables,
+								  ParseState *pstate, Oid matviewid)
+{
+	ListCell *lc;
+	int num_rte = list_length(query->rtable);
+	int i;
+
+
+	/* register delta ENRs */
+	register_delta_ENRs(pstate, query, tables);
+
+	/* XXX: Is necessary? Is this right timing? */
+	AcquireRewriteLocks(query, true, false);
+
+	i = 1;
+	foreach(lc, query->rtable)
+	{
+		RangeTblEntry *r = (RangeTblEntry*) lfirst(lc);
+
+		ListCell *lc2;
+		foreach(lc2, tables)
+		{
+			MV_TriggerTable *table = (MV_TriggerTable *) lfirst(lc2);
+			/*
+			 * if the modified table is found then replace the original RTE with
+			 * "pre-state" RTE and append its index to the list.
+			 */
+			if (r->relid == table->table_id)
+			{
+				List *securityQuals;
+				List *withCheckOptions;
+				bool  hasRowSecurity;
+				bool  hasSubLinks;
+
+				RangeTblEntry *rte_pre = get_prestate_rte(r, table, pstate->p_queryEnv, matviewid);
+
+				/*
+				 * Set a row security poslicies of the modified table to the subquery RTE which
+				 * represents the pre-update state of the table.
+				 */
+				get_row_security_policies(query, table->original_rte, i,
+										  &securityQuals, &withCheckOptions,
+										  &hasRowSecurity, &hasSubLinks);
+
+				if (hasRowSecurity)
+				{
+					query->hasRowSecurity = true;
+					rte_pre->security_barrier = true;
+				}
+				if (hasSubLinks)
+					query->hasSubLinks = true;
+
+				rte_pre->securityQuals = securityQuals;
+				lfirst(lc) = rte_pre;
+
+				table->rte_indexes = lappend_int(table->rte_indexes, i);
+				break;
+			}
+		}
+
+		/* finish the loop if we processed all RTE included in the original query */
+		if (i++ >= num_rte)
+			break;
+	}
+
+	return query;
+}
+
+/*
+ * register_delta_ENRs
+ *
+ * For all modified tables, make ENRs for their transition tables
+ * and register them to the queryEnv. ENR's RTEs are also appended
+ * into the list in query tree.
+ */
+static void
+register_delta_ENRs(ParseState *pstate, Query *query, List *tables)
+{
+	QueryEnvironment *queryEnv = pstate->p_queryEnv;
+	ListCell *lc;
+	RangeTblEntry	*rte;
+
+	foreach(lc, tables)
+	{
+		MV_TriggerTable *table = (MV_TriggerTable *) lfirst(lc);
+		ListCell *lc2;
+		int count;
+
+		count = 0;
+		foreach(lc2, table->old_tuplestores)
+		{
+			Tuplestorestate *oldtable = (Tuplestorestate *) lfirst(lc2);
+			EphemeralNamedRelation enr =
+				palloc(sizeof(EphemeralNamedRelationData));
+			ParseNamespaceItem *nsitem;
+
+			enr->md.name = make_delta_enr_name("old", table->table_id, count);
+			enr->md.reliddesc = table->table_id;
+			enr->md.tupdesc = NULL;
+			enr->md.enrtype = ENR_NAMED_TUPLESTORE;
+			enr->md.enrtuples = tuplestore_tuple_count(oldtable);
+			enr->reldata = oldtable;
+			register_ENR(queryEnv, enr);
+
+			nsitem = addRangeTableEntryForENR(pstate, makeRangeVar(NULL, enr->md.name, -1), true);
+			rte = nsitem->p_rte;
+
+			query->rtable = lappend(query->rtable, rte);
+
+			count++;
+		}
+
+		count = 0;
+		foreach(lc2, table->new_tuplestores)
+		{
+			Tuplestorestate *newtable = (Tuplestorestate *) lfirst(lc2);
+			EphemeralNamedRelation enr =
+				palloc(sizeof(EphemeralNamedRelationData));
+			ParseNamespaceItem *nsitem;
+
+			enr->md.name = make_delta_enr_name("new", table->table_id, count);
+			enr->md.reliddesc = table->table_id;
+			enr->md.tupdesc = NULL;
+			enr->md.enrtype = ENR_NAMED_TUPLESTORE;
+			enr->md.enrtuples = tuplestore_tuple_count(newtable);
+			enr->reldata = newtable;
+			register_ENR(queryEnv, enr);
+
+			nsitem = addRangeTableEntryForENR(pstate, makeRangeVar(NULL, enr->md.name, -1), true);
+			rte = nsitem->p_rte;
+
+			query->rtable = lappend(query->rtable, rte);
+
+			count++;
+		}
+	}
+}
+
+#define DatumGetItemPointer(X)	 ((ItemPointer) DatumGetPointer(X))
+#define PG_GETARG_ITEMPOINTER(n) DatumGetItemPointer(PG_GETARG_DATUM(n))
+
+/*
+ * ivm_visible_in_prestate
+ *
+ * Check visibility of a tuple specified by the tableoid and item pointer
+ * using the snapshot taken just before the table was modified.
+ */
+Datum
+ivm_visible_in_prestate(PG_FUNCTION_ARGS)
+{
+	Oid			tableoid = PG_GETARG_OID(0);
+	ItemPointer itemPtr = PG_GETARG_ITEMPOINTER(1);
+	Oid			matviewOid = PG_GETARG_OID(2);
+	MV_TriggerHashEntry *entry;
+	MV_TriggerTable		*table = NULL;
+	ListCell   *lc;
+	bool	found;
+	bool	result;
+
+	if (!in_delta_calculation)
+		ereport(ERROR,
+				(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+				 errmsg("ivm_visible_in_prestate can be called only in delta calculation")));
+
+	entry = (MV_TriggerHashEntry *) hash_search(mv_trigger_info,
+											  (void *) &matviewOid,
+											  HASH_FIND, &found);
+	Assert (found && entry != NULL);
+
+	foreach(lc, entry->tables)
+	{
+		table = (MV_TriggerTable *) lfirst(lc);
+		if (table->table_id == tableoid)
+			break;
+	}
+
+	Assert (table != NULL);
+
+	result = table_tuple_fetch_row_version(table->rel, itemPtr, entry->snapshot, table->slot);
+
+	PG_RETURN_BOOL(result);
+}
+
+/*
+ * get_prestate_rte
+ *
+ * Rewrite RTE of the modified table to a subquery which represents
+ * "pre-state" table. The original RTE is saved in table->rte_original.
+ */
+static RangeTblEntry*
+get_prestate_rte(RangeTblEntry *rte, MV_TriggerTable *table,
+				 QueryEnvironment *queryEnv, Oid matviewid)
+{
+	StringInfoData str;
+	RawStmt *raw;
+	Query *subquery;
+	ParseState *pstate;
+	char *relname;
+	static char *subquery_tl;
+	int i;
+
+	pstate = make_parsestate(NULL);
+	pstate->p_queryEnv = queryEnv;
+	pstate->p_expr_kind = EXPR_KIND_SELECT_TARGET;
+
+	relname = quote_qualified_identifier(
+					get_namespace_name(RelationGetNamespace(table->rel)),
+									   RelationGetRelationName(table->rel));
+
+	subquery_tl = make_subquery_targetlist_from_table(table);
+
+	/*
+	 * Filtering inserted row using the snapshot taken before the table
+	 * is modified. ctid is required for maintaining outer join views.
+	 */
+	initStringInfo(&str);
+	appendStringInfo(&str,
+		"SELECT %s FROM %s t"
+		" WHERE pg_catalog.ivm_visible_in_prestate(t.tableoid, t.ctid ,%d::pg_catalog.oid)",
+			subquery_tl, relname, matviewid);
+
+	/*
+	 * Re-add rows deleted from the old transition tables, excluding those
+	 * also present in the new transition tables.
+	 */
+	if (list_length(table->old_tuplestores) > 0)
+	{
+		appendStringInfo(&str," UNION ALL SELECT %s  FROM (",
+			subquery_tl);
+
+		for (i = 0; i < list_length(table->old_tuplestores); i++)
+		{
+			if (i != 0)
+				appendStringInfo(&str, " UNION ALL ");
+			appendStringInfo(&str," TABLE %s",
+				make_delta_enr_name("old", table->table_id, i));
+		}
+		for (i = 0; i < list_length(table->new_tuplestores); i++)
+		{
+			appendStringInfo(&str, " EXCEPT ALL ");
+			appendStringInfo(&str," TABLE %s",
+				make_delta_enr_name("new", table->table_id, i));
+		}
+		appendStringInfo(&str,")");
+	}
+
+	/* Get a subquery representing pre-state of the table */
+	raw = (RawStmt*)linitial(raw_parser(str.data, RAW_PARSE_DEFAULT));
+	subquery = transformStmt(pstate, raw->stmt);
+
+	/* save the original RTE */
+	table->original_rte = copyObject(rte);
+
+	rte->rtekind = RTE_SUBQUERY;
+	rte->subquery = subquery;
+	rte->security_barrier = false;
+
+	/* Clear fields that should not be set in a subquery RTE */
+	rte->relid = InvalidOid;
+	rte->relkind = 0;
+	rte->rellockmode = 0;
+	rte->tablesample = NULL;
+	rte->perminfoindex = 0;         /* no permission checking for this RTE */
+	rte->inh = false;			/* must not be set for a subquery */
+
+	return rte;
+}
+
+/*
+ * make_subquery_targetlist_from_table
+ *
+ * Make a targetlist string of a subquery representing a delta table or a
+ * pre-update state table. This subquery substitutes a modified table RTE
+ * in the view definition query during view maintenance. In the targetlist,
+ * column names appear in order of the table definition. However, for
+ * attribute numbers of vars in the query tree to reference columns of the
+ * subquery  correctly even though the table has a dropped column, put "null"
+ * as a dummy value at the position of a dropped column.
+ *
+ * We would also able to walk the query tree to rewrite varattnos, but
+ * crafting targetlist is more simple and reasonable.
+ */
+static char*
+make_subquery_targetlist_from_table(MV_TriggerTable *table)
+{
+	StringInfoData str;
+	TupleDesc	tupdesc;
+	int			i;
+
+	tupdesc = RelationGetDescr(table->rel);
+	initStringInfo(&str);
+	for (i = 0; i < tupdesc->natts; i++)
+	{
+		Form_pg_attribute attr = TupleDescAttr(tupdesc, i);
+
+		if (i > 0)
+			appendStringInfo(&str, ", ");
+
+		if (attr->attisdropped)
+			appendStringInfo(&str, "null");
+		else
+			appendStringInfo(&str, "%s", quote_identifier(NameStr(attr->attname)));
+	}
+
+	return str.data;
+}
+
+/*
+ * make_delta_enr_name
+ *
+ * Make a name for ENR of a transition table from the base table's oid.
+ * prefix will be "new" or "old" depending on its transition table kind..
+ */
+static char*
+make_delta_enr_name(const char *prefix, Oid relid, int count)
+{
+	char buf[NAMEDATALEN];
+	char *name;
+
+	snprintf(buf, NAMEDATALEN, "__ivm_%s_%u_%u", prefix, relid, count);
+	name = pstrdup(buf);
+
+	return name;
+}
+
+/*
+ * makeDeltaTable
+ *
+ * Make a RTE representing a delta of the specified table.
+ */
+static RangeTblEntry*
+makeDeltaTable(RangeTblEntry *rte, MV_TriggerTable *table,
+		   bool is_new, QueryEnvironment *queryEnv)
+{
+	StringInfoData str;
+	ParseState	*pstate;
+	RawStmt *raw;
+	Query *sub;
+	int		i;
+
+	const char *prefix_union = is_new ? "new" : "old";
+	const char *prefix_except = is_new ? "old" : "new";
+	int num_union = is_new ? list_length(table->new_tuplestores) : list_length(table->old_tuplestores);
+	int num_except = is_new ? list_length(table->old_tuplestores) : list_length(table->new_tuplestores);
+
+	/* the previous RTE must be a subquery which represents "pre-state" table */
+	Assert(rte->rtekind == RTE_SUBQUERY);
+
+	/* Create a ParseState for rewriting the view definition query */
+	pstate = make_parsestate(NULL);
+	pstate->p_queryEnv = queryEnv;
+	pstate->p_expr_kind = EXPR_KIND_NONE;
+
+	initStringInfo(&str);
+	appendStringInfo(&str,
+		" SELECT %s FROM ( ",
+		make_subquery_targetlist_from_table(table));
+
+	for (i = 0; i < num_union; i++)
+	{
+		if (i > 0)
+			appendStringInfo(&str, " UNION ALL ");
+
+		appendStringInfo(&str,
+			" TABLE  %s",
+			make_delta_enr_name(prefix_union, table->table_id, i));
+	}
+	for (i = 0; i < num_except; i++)
+	{
+		appendStringInfo(&str, " EXCEPT ALL ");
+
+		appendStringInfo(&str,
+			" TABLE  %s",
+			make_delta_enr_name(prefix_except, table->table_id, i));
+	}
+	appendStringInfo(&str,")");
+
+	raw = (RawStmt*)linitial(raw_parser(str.data, RAW_PARSE_DEFAULT));
+	sub = transformStmt(pstate, raw->stmt);
+
+	/*
+	 * Update the subquery so that it represent the combined transition
+	 * table.  Note that we leave the security_barrier and securityQuals
+	 * fields so that the subquery relation can be protected by the RLS
+	 * policy as same as the modified table.
+	 */
+	rte->rtekind = RTE_SUBQUERY;
+	rte->subquery = sub;
+
+	return rte;
+}
+
+/*
+ * rewrite_query_for_counting
+ *
+ * Rewrite query for counting duplicated tuples.
+ */
+static Query *
+rewrite_query_for_counting(Query *query, ParseState *pstate)
+{
+	TargetEntry *tle_count;
+	FuncCall *fn;
+	Node *node;
+
+	/* Add count(*) for counting distinct tuples in views */
+	fn = makeFuncCall(SystemFuncName("count"), NIL, COERCE_EXPLICIT_CALL, -1);
+	fn->agg_star = true;
+	if (!query->groupClause && !query->hasAggs)
+		query->groupClause = transformDistinctClause(NULL, &query->targetList, query->sortClause, false);
+
+	node = ParseFuncOrColumn(pstate, fn->funcname, NIL, NULL, fn, false, -1);
+
+	tle_count = makeTargetEntry((Expr *) node,
+								list_length(query->targetList) + 1,
+								pstrdup("__ivm_count__"),
+								false);
+	query->targetList = lappend(query->targetList, tle_count);
+	query->hasAggs = true;
+
+	return query;
+}
+
+/*
+ * calc_delta
+ *
+ * Calculate view deltas generated under the modification of a table specified
+ * by the RTE index.
+ */
+static void
+calc_delta(MV_TriggerTable *table, int rte_index, Query *query,
+			DestReceiver *dest_old, DestReceiver *dest_new,
+			TupleDesc *tupdesc_old, TupleDesc *tupdesc_new,
+			QueryEnvironment *queryEnv)
+{
+	ListCell *lc = list_nth_cell(query->rtable, rte_index - 1);
+	RangeTblEntry *rte = (RangeTblEntry *) lfirst(lc);
+
+	in_delta_calculation = true;
+
+	/* Generate old delta */
+	if (dest_old && list_length(table->old_tuplestores) > 0)
+	{
+		/* Replace the modified table with the old delta table and calculate the old view delta. */
+		lfirst(lc) = makeDeltaTable(rte, table, false, queryEnv);
+		refresh_matview_datafill(dest_old, query, queryEnv, tupdesc_old, "", false);
+	}
+
+	/* Generate new delta */
+	if (dest_new && list_length(table->new_tuplestores) > 0)
+	{
+		/* Replace the modified table with the new delta table and calculate the new view delta*/
+		lfirst(lc) = makeDeltaTable(rte, table, true, queryEnv);
+		refresh_matview_datafill(dest_new, query, queryEnv, tupdesc_new, "", false);
+	}
+
+	in_delta_calculation = false;
+}
+
+/*
+ * rewrite_query_for_postupdate_state
+ *
+ * Rewrite the query so that the specified base table's RTEs will represent
+ * "post-update" state of tables. This is called after the view delta
+ * calculation due to changes on this table finishes.
+ */
+static Query*
+rewrite_query_for_postupdate_state(Query *query, MV_TriggerTable *table, int rte_index)
+{
+	ListCell *lc = list_nth_cell(query->rtable, rte_index - 1);
+
+	/* Retore the original RTE */
+	lfirst(lc) = table->original_rte;
+
+	return query;
+}
+
+/*
+ * apply_delta
+ *
+ * Apply deltas to the materialized view. In outer join cases, this requires
+ * the view maintenance graph.
+ */
+static void
+apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *new_tuplestores,
+			TupleDesc tupdesc_old, TupleDesc tupdesc_new,
+			Query *query)
+{
+	StringInfoData querybuf;
+	StringInfoData target_list_buf;
+	Relation	matviewRel;
+	char	   *matviewname;
+	ListCell	*lc;
+	int			i;
+	List	   *keys = NIL;
+
+
+	/*
+	 * get names of the materialized view and delta tables
+	 */
+
+	matviewRel = table_open(matviewOid, NoLock);
+	matviewname = quote_qualified_identifier(get_namespace_name(RelationGetNamespace(matviewRel)),
+											 RelationGetRelationName(matviewRel));
+
+	/*
+	 * Build parts of the maintenance queries
+	 */
+
+	initStringInfo(&querybuf);
+	initStringInfo(&target_list_buf);
+
+	/* build string of target list */
+	for (i = 0; i < matviewRel->rd_att->natts; i++)
+	{
+		Form_pg_attribute attr = TupleDescAttr(matviewRel->rd_att, i);
+		char   *resname = NameStr(attr->attname);
+
+		if (i != 0)
+			appendStringInfo(&target_list_buf, ", ");
+		appendStringInfo(&target_list_buf, "%s", quote_qualified_identifier(NULL, resname));
+	}
+
+	i = 0;
+	foreach (lc, query->targetList)
+	{
+		TargetEntry *tle = (TargetEntry *) lfirst(lc);
+		Form_pg_attribute attr = TupleDescAttr(matviewRel->rd_att, i);
+
+		i++;
+
+		if (tle->resjunk)
+			continue;
+
+		keys = lappend(keys, attr);
+	}
+
+	/* Start maintaining the materialized view. */
+	OpenMatViewIncrementalMaintenance();
+
+	/* Open SPI context. */
+	if (SPI_connect() != SPI_OK_CONNECT)
+		elog(ERROR, "SPI_connect failed");
+
+	/* For tuple deletion */
+	if (old_tuplestores && tuplestore_tuple_count(old_tuplestores) > 0)
+	{
+		EphemeralNamedRelation enr = palloc(sizeof(EphemeralNamedRelationData));
+		int				rc;
+
+		/* convert tuplestores to ENR, and register for SPI */
+		enr->md.name = pstrdup(OLD_DELTA_ENRNAME);
+		enr->md.reliddesc = InvalidOid;
+		enr->md.tupdesc = tupdesc_old;
+		enr->md.enrtype = ENR_NAMED_TUPLESTORE;
+		enr->md.enrtuples = tuplestore_tuple_count(old_tuplestores);
+		enr->reldata = old_tuplestores;
+
+		rc = SPI_register_relation(enr);
+		if (rc != SPI_OK_REL_REGISTER)
+			elog(ERROR, "SPI_register failed");
+
+		apply_old_delta(matviewname, OLD_DELTA_ENRNAME, keys);
+
+	}
+	/* For tuple insertion */
+	if (new_tuplestores && tuplestore_tuple_count(new_tuplestores) > 0)
+	{
+		EphemeralNamedRelation enr = palloc(sizeof(EphemeralNamedRelationData));
+		int rc;
+
+		/* convert tuplestores to ENR, and register for SPI */
+		enr->md.name = pstrdup(NEW_DELTA_ENRNAME);
+		enr->md.reliddesc = InvalidOid;
+		enr->md.tupdesc = tupdesc_new;;
+		enr->md.enrtype = ENR_NAMED_TUPLESTORE;
+		enr->md.enrtuples = tuplestore_tuple_count(new_tuplestores);
+		enr->reldata = new_tuplestores;
+
+		rc = SPI_register_relation(enr);
+		if (rc != SPI_OK_REL_REGISTER)
+			elog(ERROR, "SPI_register failed");
+
+		/* apply new delta */
+		apply_new_delta(matviewname, NEW_DELTA_ENRNAME, &target_list_buf);
+	}
+
+	/* We're done maintaining the materialized view. */
+	CloseMatViewIncrementalMaintenance();
+
+	table_close(matviewRel, NoLock);
+
+	/* Close SPI context. */
+	if (SPI_finish() != SPI_OK_FINISH)
+		elog(ERROR, "SPI_finish failed");
+}
+
+/*
+ * apply_old_delta
+ *
+ * Execute a query for applying a delta table given by deltname_old
+ * which contains tuples to be deleted from to a materialized view given by
+ * matviewname.  This is used when counting is not required.
+ */
+static void
+apply_old_delta(const char *matviewname, const char *deltaname_old,
+				List *keys)
+{
+	StringInfoData	querybuf;
+	StringInfoData	keysbuf;
+	char   *match_cond;
+	ListCell *lc;
+
+	/* build WHERE condition for searching tuples to be deleted */
+	match_cond = get_matching_condition_string(keys);
+
+	/* build string of keys list */
+	initStringInfo(&keysbuf);
+	foreach (lc, keys)
+	{
+		Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc);
+		char   *resname = NameStr(attr->attname);
+		appendStringInfo(&keysbuf, "%s", quote_qualified_identifier("mv", resname));
+		if (lnext(keys, lc))
+			appendStringInfo(&keysbuf, ", ");
+	}
+
+	/* Search for matching tuples from the view and update or delete if found. */
+	initStringInfo(&querybuf);
+	appendStringInfo(&querybuf,
+	"DELETE FROM %s WHERE ctid IN ("
+		"SELECT tid FROM (SELECT pg_catalog.row_number() over (partition by %s) AS \"__ivm_row_number__\","
+								  "mv.ctid AS tid,"
+								  "diff.\"__ivm_count__\""
+						 "FROM %s AS mv, %s AS diff "
+						 "WHERE %s) v "
+					"WHERE v.\"__ivm_row_number__\" OPERATOR(pg_catalog.<=) v.\"__ivm_count__\")",
+					matviewname,
+					keysbuf.data,
+					matviewname, deltaname_old,
+					match_cond);
+
+	if (SPI_exec(querybuf.data, 0) != SPI_OK_DELETE)
+		elog(ERROR, "SPI_exec failed: %s", querybuf.data);
+}
+
+/*
+ * apply_new_delta
+ *
+ * Execute a query for applying a delta table given by deltname_new
+ * which contains tuples to be inserted into a materialized view given by
+ * matviewname.  This is used when counting is not required.
+ */
+static void
+apply_new_delta(const char *matviewname, const char *deltaname_new,
+				StringInfo target_list)
+{
+	StringInfoData	querybuf;
+
+	/* Search for matching tuples from the view and update or delete if found. */
+	initStringInfo(&querybuf);
+	appendStringInfo(&querybuf,
+					"INSERT INTO %s (%s) SELECT %s FROM ("
+						"SELECT diff.*, pg_catalog.generate_series(1, diff.\"__ivm_count__\")"
+							" AS __ivm_generate_series__ "
+						"FROM %s AS diff) AS v",
+					matviewname, target_list->data, target_list->data,
+					deltaname_new);
+
+	if (SPI_exec(querybuf.data, 0) != SPI_OK_INSERT)
+		elog(ERROR, "SPI_exec failed: %s", querybuf.data);
+}
+
+/*
+ * get_matching_condition_string
+ *
+ * Build a predicate string for looking for a tuple with given keys.
+ */
+static char *
+get_matching_condition_string(List *keys)
+{
+	StringInfoData match_cond;
+	ListCell	*lc;
+
+	/* If there is no key columns, the condition is always true. */
+	if (keys == NIL)
+		return "true";
+
+	initStringInfo(&match_cond);
+	foreach (lc, keys)
+	{
+		Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc);
+		char   *resname = NameStr(attr->attname);
+		char   *mv_resname = quote_qualified_identifier("mv", resname);
+		char   *diff_resname = quote_qualified_identifier("diff", resname);
+		Oid		typid = attr->atttypid;
+
+		/* Considering NULL values, we can not use simple = operator. */
+		appendStringInfo(&match_cond, "(");
+		generate_equal(&match_cond, typid, mv_resname, diff_resname);
+		appendStringInfo(&match_cond, " OR (%s IS NULL AND %s IS NULL))",
+						 mv_resname, diff_resname);
+
+		if (lnext(keys, lc))
+			appendStringInfo(&match_cond, " AND ");
+	}
+
+	return match_cond.data;
+}
+
+/*
+ * generate_equals
+ *
+ * Generate an equality clause using given operands' default equality
+ * operator.
+ */
+static void
+generate_equal(StringInfo querybuf, Oid opttype,
+			   const char *leftop, const char *rightop)
+{
+	TypeCacheEntry *typentry;
+
+	typentry = lookup_type_cache(opttype, TYPECACHE_EQ_OPR);
+	if (!OidIsValid(typentry->eq_opr))
+		ereport(ERROR,
+				(errcode(ERRCODE_UNDEFINED_FUNCTION),
+				 errmsg("could not identify an equality operator for type %s",
+						format_type_be_qualified(opttype))));
+
+	generate_operator_clause(querybuf,
+							 leftop, opttype,
+							 typentry->eq_opr,
+							 rightop, opttype);
+}
+
+/*
+ * mv_InitHashTables
+ */
+static void
+mv_InitHashTables(void)
+{
+	HASHCTL		ctl;
+
+	memset(&ctl, 0, sizeof(ctl));
+	ctl.keysize = sizeof(Oid);
+	ctl.entrysize = sizeof(MV_TriggerHashEntry);
+	mv_trigger_info = hash_create("MV trigger info",
+								 MV_INIT_QUERYHASHSIZE,
+								 &ctl, HASH_ELEM | HASH_BLOBS);
+
+	memset(&ctl, 0, sizeof(ctl));
+	ctl.keysize = sizeof(Oid);
+	ctl.entrysize = sizeof(DroppedImmvInfo);
+	dropped_immv = hash_create("Dropped IMMVs", 16,
+							   &ctl, HASH_ELEM | HASH_BLOBS);
+}
+
+/*
+ * AtAbort_IVM
+ *
+ * Clean up hash entries for all materialized views. This is called at
+ * (sub-)transaction abort. When the top-level transaction is aborted,
+ * InvalidSubTransactionId is set to subxid.
+ *
+ * Also, remove dropped IMMV information if it is aborted.
+ */
+void
+AtAbort_IVM(SubTransactionId subxid)
+{
+	HASH_SEQ_STATUS seq;
+
+	if (mv_trigger_info)
+	{
+		MV_TriggerHashEntry *entry;
+		hash_seq_init(&seq, mv_trigger_info);
+		while ((entry = hash_seq_search(&seq)) != NULL)
+			clean_up_IVM_hash_entry(entry, true, subxid);
+	}
+
+	if (dropped_immv)
+	{
+		DroppedImmvInfo *entry;
+		hash_seq_init(&seq, dropped_immv);
+		while ((entry = hash_seq_search(&seq)) != NULL)
+		{
+			if (subxid == InvalidSubTransactionId || subxid == entry->subxid)
+				hash_search(dropped_immv, (void *) &entry->immv_oid, HASH_REMOVE, NULL);
+		}
+	}
+
+	in_delta_calculation = false;
+}
+
+/*
+ * AtPreCommit_IVM
+ *
+ * Record the transaction ID that updated the view incrementally.
+ * Also, remove the entry for dropped IMMVs.
+ */
+void
+AtPreCommit_IVM(void)
+{
+	HASH_SEQ_STATUS seq;
+
+	if (mv_trigger_info)
+	{
+		MV_TriggerHashEntry *entry;
+
+		/*
+		 * Record the transaction ID that udpate the view incrementally,
+		 * and perform the final clean up of the entry.
+		 */
+		hash_seq_init(&seq, mv_trigger_info);
+		while ((entry = hash_seq_search(&seq)) != NULL)
+		{
+			setLastUpdateXid(entry->matview_id, GetTopFullTransactionId());
+			hash_search(mv_trigger_info, (void *) &entry->matview_id, HASH_REMOVE, NULL);
+		}
+	}
+
+	if (dropped_immv)
+	{
+		DroppedImmvInfo *entry;
+
+		LWLockAcquire(IvmControlLock, LW_EXCLUSIVE);
+		hash_seq_init(&seq, dropped_immv);
+		while ((entry = hash_seq_search(&seq)) != NULL)
+		{
+			hash_search(LastIvmUpdateHash, (void *) &entry->immv_oid, HASH_REMOVE, NULL);
+			hash_search(dropped_immv, (void *) &entry->immv_oid, HASH_REMOVE, NULL);
+		}
+		LWLockRelease(IvmControlLock);
+	}
+
+	in_delta_calculation = false;
+}
+
+/*
+ * clean_up_IVM_hash_entry
+ *
+ * Clean up tuple stores and hash entries for a materialized view after its
+ * maintenance finished. This is called at the end of table modifying query
+ * or (sub-)transaction abort. When the top-level transaction is aborted,
+ * InvalidSubTransactionId is set to subxid.
+ */
+static void
+clean_up_IVM_hash_entry(MV_TriggerHashEntry *entry, bool is_abort,
+						SubTransactionId subxid)
+{
+	bool found;
+	ListCell *lc;
+
+	/* clean up tuple stores */
+	foreach(lc, entry->tables)
+	{
+		MV_TriggerTable *table = (MV_TriggerTable *) lfirst(lc);
+
+		list_free(table->old_tuplestores);
+		list_free(table->new_tuplestores);
+		if (!is_abort)
+		{
+			ExecDropSingleTupleTableSlot(table->slot);
+			table_close(table->rel, NoLock);
+		}
+	}
+	list_free(entry->tables);
+	entry->tables = NIL;
+
+	if (is_abort)
+	{
+		bool	remove_entry = false;
+
+		/*
+		 * When the top-level transaction is aborted, remove all subxids.
+		 * When a sub-transaction is aborted, remove only its subxid.
+		 */
+		if (subxid == InvalidSubTransactionId)
+			remove_entry = true;
+		else
+		{
+			foreach(lc, entry->subxids)
+			{
+				if (lfirst_xid(lc) == subxid)
+				{
+					entry->subxids = list_delete_cell(entry->subxids, lc);
+					break;
+				}
+			}
+
+			/*
+			 * If all the subxid are removed, it means that the view was not
+			 * updated at all in this transaction.
+			 */
+			if (list_length(entry->subxids) == 0)
+				remove_entry = true;
+		}
+
+		/*
+		 * Remove entries of not updated views from the hash table.
+		 */
+		if (remove_entry)
+			hash_search(mv_trigger_info, (void *) &entry->matview_id, HASH_REMOVE, &found);
+	}
+	else
+	{
+		/* When the query sucsessully finished, unregister the snapshot */
+		UnregisterSnapshot(entry->snapshot);
+	}
+
+	entry->snapshot = InvalidSnapshot;
+}
+
+/*
+ * setLastUpdateXid
+ *
+ * Store the transaction ID that updated the view incremenally.
+ */
+static void
+setLastUpdateXid(Oid immv_oid, FullTransactionId xid)
+{
+	LastIvmUpdateEntry *entry;
+
+	LWLockAcquire(IvmControlLock, LW_EXCLUSIVE);
+	entry = (LastIvmUpdateEntry *) hash_search(LastIvmUpdateHash, (void *) &immv_oid, HASH_ENTER, NULL);
+	entry->oid = immv_oid;
+	entry->last_ivm_update = xid;
+	LWLockRelease(IvmControlLock);
+}
+
+/*
+ * getLastUpdateXid
+ *
+ * Get the most recent transaction ID that updated the view incrementally.
+ */
+static FullTransactionId
+getLastUpdateXid(Oid immv_oid)
+{
+	FullTransactionId xid = InvalidFullTransactionId;
+	LastIvmUpdateEntry *entry;
+	bool found;
+
+	LWLockAcquire(IvmControlLock, LW_SHARED);
+	entry = (LastIvmUpdateEntry *) hash_search(LastIvmUpdateHash, (void *) &immv_oid, HASH_FIND, &found);
+	LWLockRelease(IvmControlLock);
+	if (found)
+		xid = entry->last_ivm_update;
+
+	return xid;
+}
+
+void
+removeImmv(Oid immv_oid)
+{
+	DroppedImmvInfo *entry;
+
+	if (!dropped_immv)
+		mv_InitHashTables();
+
+	entry = (DroppedImmvInfo *) hash_search(dropped_immv, (void *) &immv_oid, HASH_ENTER, NULL);
+	entry->subxid = GetCurrentSubTransactionId();
+}
+
+/*
+ * isIvmName
+ *
+ * Check if this is a IVM hidden column from the name.
+ */
+bool
+isIvmName(const char *s)
+{
+	if (s)
+		return (strncmp(s, "__ivm_", 6) == 0);
+	return false;
+}
diff --git a/src/backend/commands/tablecmds.c b/src/backend/commands/tablecmds.c
index 95abaf4890c..95e974e1138 100644
--- a/src/backend/commands/tablecmds.c
+++ b/src/backend/commands/tablecmds.c
@@ -62,6 +62,7 @@
 #include "commands/defrem.h"
 #include "commands/event_trigger.h"
 #include "commands/extension.h"
+#include "commands/matview.h"
 #include "commands/repack.h"
 #include "commands/sequence.h"
 #include "commands/tablecmds.h"
@@ -1811,6 +1812,9 @@ RangeVarCallbackForDropRelation(const RangeVar *rel, Oid relOid, Oid oldRelOid,
 	state->actual_relkind = classform->relkind;
 	state->actual_relpersistence = classform->relpersistence;
 
+	if (classform->relkind == RELKIND_MATVIEW && classform->relisivm)
+		removeImmv(relOid);
+
 	/*
 	 * Both RELKIND_RELATION and RELKIND_PARTITIONED_TABLE are OBJECT_TABLE,
 	 * but RemoveRelations() can only pass one relkind for a given relation.
diff --git a/src/backend/utils/activity/wait_event_names.txt b/src/backend/utils/activity/wait_event_names.txt
index 560659f9568..d97c35eeef0 100644
--- a/src/backend/utils/activity/wait_event_names.txt
+++ b/src/backend/utils/activity/wait_event_names.txt
@@ -370,6 +370,7 @@ WaitLSN	"Waiting to read or update shared Wait-for-LSN state."
 LogicalDecodingControl	"Waiting to read or update logical decoding status information."
 DataChecksumsWorker	"Waiting for data checksums worker."
 AioWorkerControl	"Waiting to update AIO worker information."
+IvmControl	"Waiting for read or update IMMV information.."
 
 #
 # END OF PREDEFINED LWLOCKS (DO NOT CHANGE THIS LINE)
diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat
index 3cb84359adf..65a739af22a 100644
--- a/src/include/catalog/pg_proc.dat
+++ b/src/include/catalog/pg_proc.dat
@@ -12718,4 +12718,14 @@
   proname => 'hashoid8extended', prorettype => 'int8',
   proargtypes => 'oid8 int8', prosrc => 'hashoid8extended' },
 
+# IVM
+{ oid => '786', descr => 'ivm trigger (before)',
+  proname => 'IVM_immediate_before', provolatile => 'v', prorettype => 'trigger',
+  proargtypes => '', prosrc => 'IVM_immediate_before' },
+{ oid => '787', descr => 'ivm trigger (after)',
+  proname => 'IVM_immediate_maintenance', provolatile => 'v', prorettype => 'trigger',
+  proargtypes => '', prosrc => 'IVM_immediate_maintenance' },
+{ oid => '788', descr => 'ivm filetring ',
+  proname => 'ivm_visible_in_prestate', provolatile => 's', prorettype => 'bool',
+  proargtypes => 'oid tid oid', prosrc => 'ivm_visible_in_prestate' },
 ]
diff --git a/src/include/commands/createas.h b/src/include/commands/createas.h
index f895c67c0c2..c286ebcd70e 100644
--- a/src/include/commands/createas.h
+++ b/src/include/commands/createas.h
@@ -16,6 +16,7 @@
 
 #include "catalog/objectaddress.h"
 #include "nodes/params.h"
+#include "nodes/pathnodes.h"
 #include "parser/parse_node.h"
 #include "tcop/dest.h"
 #include "utils/queryenvironment.h"
@@ -25,6 +26,9 @@ extern ObjectAddress ExecCreateTableAs(ParseState *pstate, CreateTableAsStmt *st
 									   ParamListInfo params, QueryEnvironment *queryEnv,
 									   QueryCompletion *qc);
 
+extern void CreateIvmTriggersOnBaseTables(Query *qry, Oid matviewOid);
+extern void CreateIndexOnIMMV(Query *query, Relation matviewRel);
+
 extern int	GetIntoRelEFlags(IntoClause *intoClause);
 
 extern DestReceiver *CreateIntoRelDestReceiver(IntoClause *intoClause);
diff --git a/src/include/commands/matview.h b/src/include/commands/matview.h
index 738c731c1a9..f1dbfc052c5 100644
--- a/src/include/commands/matview.h
+++ b/src/include/commands/matview.h
@@ -15,6 +15,7 @@
 #define MATVIEW_H
 
 #include "catalog/objectaddress.h"
+#include "fmgr.h"
 #include "nodes/params.h"
 #include "nodes/parsenodes.h"
 #include "tcop/dest.h"
@@ -23,6 +24,8 @@
 
 extern void SetMatViewPopulatedState(Relation relation, bool newstate);
 
+extern void SetMatViewIVMState(Relation relation, bool newstate);
+
 extern ObjectAddress ExecRefreshMatView(RefreshMatViewStmt *stmt, const char *queryString,
 										QueryCompletion *qc);
 extern ObjectAddress RefreshMatViewByOid(Oid matviewOid, bool is_create, bool skipData,
@@ -33,4 +36,12 @@ extern DestReceiver *CreateTransientRelDestReceiver(Oid transientoid);
 
 extern bool MatViewIncrementalMaintenanceIsEnabled(void);
 
+extern Datum IVM_immediate_before(PG_FUNCTION_ARGS);
+extern Datum IVM_immediate_maintenance(PG_FUNCTION_ARGS);
+extern Datum IVM_visible_in_prestate(PG_FUNCTION_ARGS);
+extern void AtAbort_IVM(SubTransactionId subtxid);
+extern void AtPreCommit_IVM(void);
+extern void removeImmv(Oid immv_oid);
+extern bool isIvmName(const char *s);
+
 #endif							/* MATVIEW_H */
diff --git a/src/include/storage/lwlocklist.h b/src/include/storage/lwlocklist.h
index d7eb648bd27..756c63baf97 100644
--- a/src/include/storage/lwlocklist.h
+++ b/src/include/storage/lwlocklist.h
@@ -89,6 +89,7 @@ PG_LWLOCK(54, WaitLSN)
 PG_LWLOCK(55, LogicalDecodingControl)
 PG_LWLOCK(56, DataChecksumsWorker)
 PG_LWLOCK(57, AioWorkerControl)
+PG_LWLOCK(58, IvmControl)
 
 /*
  * There also exist several built-in LWLock tranches.  As with the predefined
diff --git a/src/include/storage/subsystemlist.h b/src/include/storage/subsystemlist.h
index 9ad619080be..481e15d00a1 100644
--- a/src/include/storage/subsystemlist.h
+++ b/src/include/storage/subsystemlist.h
@@ -88,3 +88,6 @@ PG_SHMEM_SUBSYSTEM(DataChecksumsShmemCallbacks)
 
 /* AIO subsystem. This delegates to the method-specific callbacks */
 PG_SHMEM_SUBSYSTEM(AioShmemCallbacks)
+
+/* Incremental View Maintenance */
+PG_SHMEM_SUBSYSTEM(IvmShmemCallbacks)
-- 
2.43.0


--Multipart=_Fri__3_Jul_2026_19_11_16_+0900_CskxSIu_iGcDMEyM
Content-Type: text/x-diff;
 name="v39-0005-Add-Incremental-View-Maintenance-support-to-psql.patch"
Content-Disposition: attachment;
 filename="v39-0005-Add-Incremental-View-Maintenance-support-to-psql.patch"
Content-Transfer-Encoding: 7bit



^ permalink  raw  reply  [nested|flat] 101+ messages in thread


end of thread, other threads:[~2026-05-29 09:06 UTC | newest]

Thread overview: 101+ messages (download: mbox mbox.gz follow: Atom feed)
-- links below jump to the message on this page --
2017-12-21 08:33 [PATCH 4/6] TAP test for the slot limit feature Kyotaro Horiguchi <[email protected]>
2017-12-21 08:33 [PATCH 4/6] TAP test for the slot limit feature Kyotaro Horiguchi <[email protected]>
2017-12-21 08:33 [PATCH 4/6] TAP test for the slot limit feature Kyotaro Horiguchi <[email protected]>
2017-12-21 08:33 [PATCH 4/6] TAP test for the slot limit feature Kyotaro Horiguchi <[email protected]>
2019-12-20 01:21 [PATCH v29 05/11] Add Incremental View Maintenance support to psql Yugo Nagata <[email protected]>
2019-12-20 01:21 [PATCH v31 05/11] Add Incremental View Maintenance support to psql Yugo Nagata <[email protected]>
2019-12-20 01:21 [PATCH v30 05/11] Add Incremental View Maintenance support to psql Yugo Nagata <[email protected]>
2019-12-20 01:21 [PATCH v24 06/15] Add Incremental View Maintenance support to psql Yugo Nagata <[email protected]>
2019-12-20 01:21 [PATCH v29 05/11] Add Incremental View Maintenance support to psql Yugo Nagata <[email protected]>
2019-12-20 01:21 [PATCH v29 05/11] Add Incremental View Maintenance support to psql Yugo Nagata <[email protected]>
2019-12-20 01:21 [PATCH v29 05/11] Add Incremental View Maintenance support to psql Yugo Nagata <[email protected]>
2019-12-20 01:21 [PATCH v30 05/11] Add Incremental View Maintenance support to psql Yugo Nagata <[email protected]>
2019-12-20 01:21 [PATCH v27 5/9] Add Incremental View Maintenance support to psql Yugo Nagata <[email protected]>
2019-12-20 01:21 [PATCH v25 06/15] Add Incremental View Maintenance support to psql Yugo Nagata <[email protected]>
2019-12-20 01:21 [PATCH v32 05/11] Add Incremental View Maintenance support to psql Yugo Nagata <[email protected]>
2019-12-20 01:21 [PATCH v26 06/10] Add Incremental View Maintenance support to psql Yugo Nagata <[email protected]>
2019-12-20 01:21 [PATCH v23 06/15] Add Incremental View Maintenance support to psql Yugo Nagata <[email protected]>
2019-12-20 01:21 [PATCH v24 06/15] Add Incremental View Maintenance support to psql Yugo Nagata <[email protected]>
2019-12-20 01:21 [PATCH v28 05/11] Add Incremental View Maintenance support to psql Yugo Nagata <[email protected]>
2019-12-20 01:21 [PATCH v30 05/11] Add Incremental View Maintenance support to psql Yugo Nagata <[email protected]>
2019-12-20 01:21 [PATCH v27 5/9] Add Incremental View Maintenance support to psql Yugo Nagata <[email protected]>
2020-11-11 08:01 [PATCH v24 05/15] Add Incremental View Maintenance support to pg_dump Yugo Nagata <[email protected]>
2020-11-11 08:01 [PATCH v24 05/15] Add Incremental View Maintenance support to pg_dump Yugo Nagata <[email protected]>
2020-11-11 08:01 [PATCH v37 04/11] Add Incremental View Maintenance support to pg_dump Yugo Nagata <[email protected]>
2020-11-11 08:01 [PATCH v38 04/11] Add Incremental View Maintenance support to pg_dump Yugo Nagata <[email protected]>
2020-11-11 08:01 [PATCH v38 04/11] Add Incremental View Maintenance support to pg_dump Yugo Nagata <[email protected]>
2020-11-11 08:01 [PATCH v39 4/8] Add Incremental View Maintenance support to pg_dump Yugo Nagata <[email protected]>
2020-11-11 08:01 [PATCH v38 04/11] Add Incremental View Maintenance support to pg_dump Yugo Nagata <[email protected]>
2020-11-11 08:01 [PATCH v29 04/11] Add Incremental View Maintenance support to pg_dump Yugo Nagata <[email protected]>
2020-11-11 08:01 [PATCH v29 04/11] Add Incremental View Maintenance support to pg_dump Yugo Nagata <[email protected]>
2020-11-11 08:01 [PATCH v31 04/11] Add Incremental View Maintenance support to pg_dump Yugo Nagata <[email protected]>
2020-11-11 08:01 [PATCH v39 4/8] Add Incremental View Maintenance support to pg_dump Yugo Nagata <[email protected]>
2020-11-11 08:01 [PATCH v27 4/9] Add Incremental View Maintenance support to pg_dump Yugo Nagata <[email protected]>
2020-11-11 08:01 [PATCH v25 05/15] Add Incremental View Maintenance support to pg_dump Yugo Nagata <[email protected]>
2020-11-11 08:01 [PATCH v30 04/11] Add Incremental View Maintenance support to pg_dump Yugo Nagata <[email protected]>
2020-11-11 08:01 [PATCH v30 04/11] Add Incremental View Maintenance support to pg_dump Yugo Nagata <[email protected]>
2020-11-11 08:01 [PATCH v29 04/11] Add Incremental View Maintenance support to pg_dump Yugo Nagata <[email protected]>
2020-11-11 08:01 [PATCH v30 04/11] Add Incremental View Maintenance support to pg_dump Yugo Nagata <[email protected]>
2020-11-11 08:01 [PATCH v26 05/10] Add Incremental View Maintenance support to pg_dump Yugo Nagata <[email protected]>
2020-11-11 08:01 [PATCH v27 4/9] Add Incremental View Maintenance support to pg_dump Yugo Nagata <[email protected]>
2020-11-11 08:01 [PATCH v28 04/11] Add Incremental View Maintenance support to pg_dump Yugo Nagata <[email protected]>
2020-11-11 08:01 [PATCH v37 04/11] Add Incremental View Maintenance support to pg_dump Yugo Nagata <[email protected]>
2020-11-11 08:01 [PATCH v29 04/11] Add Incremental View Maintenance support to pg_dump Yugo Nagata <[email protected]>
2020-11-11 08:01 [PATCH v39 4/8] Add Incremental View Maintenance support to pg_dump Yugo Nagata <[email protected]>
2020-11-11 08:01 [PATCH v23 05/15] Add Incremental View Maintenance support to pg_dump Yugo Nagata <[email protected]>
2020-11-11 08:01 [PATCH v37 04/11] Add Incremental View Maintenance support to pg_dump Yugo Nagata <[email protected]>
2020-11-11 08:01 [PATCH v32 04/11] Add Incremental View Maintenance support to pg_dump Yugo Nagata <[email protected]>
2020-12-22 09:40 [PATCH v25 07/15] Add Incremental View Maintenance support Yugo Nagata <[email protected]>
2020-12-22 09:40 [PATCH v24 07/15] Add Incremental View Maintenance support Yugo Nagata <[email protected]>
2020-12-22 09:40 [PATCH v26 07/10] Add Incremental View Maintenance support Yugo Nagata <[email protected]>
2020-12-22 09:40 [PATCH v23 07/15] Add Incremental View Maintenance support Yugo Nagata <[email protected]>
2020-12-22 09:40 [PATCH v24 07/15] Add Incremental View Maintenance support Yugo Nagata <[email protected]>
2022-04-21 02:58 [PATCH v27 6/9] Add Incremental View Maintenance support Yugo Nagata <[email protected]>
2022-04-21 02:58 [PATCH v27 6/9] Add Incremental View Maintenance support Yugo Nagata <[email protected]>
2023-05-31 09:59 [PATCH v29 06/11] Add Incremental View Maintenance support Yugo Nagata <[email protected]>
2023-05-31 09:59 [PATCH v29 06/11] Add Incremental View Maintenance support Yugo Nagata <[email protected]>
2023-05-31 09:59 [PATCH v30 06/11] Add Incremental View Maintenance support Yugo Nagata <[email protected]>
2023-05-31 09:59 [PATCH v29 06/11] Add Incremental View Maintenance support Yugo Nagata <[email protected]>
2023-05-31 09:59 [PATCH v30 06/11] Add Incremental View Maintenance support Yugo Nagata <[email protected]>
2023-05-31 09:59 [PATCH v28 06/11] Add Incremental View Maintenance support Yugo Nagata <[email protected]>
2023-05-31 09:59 [PATCH v31 06/11] Add Incremental View Maintenance support Yugo Nagata <[email protected]>
2023-05-31 09:59 [PATCH v32 06/11] Add Incremental View Maintenance support Yugo Nagata <[email protected]>
2023-05-31 09:59 [PATCH v30 06/11] Add Incremental View Maintenance support Yugo Nagata <[email protected]>
2023-05-31 09:59 [PATCH v30 06/11] Add Incremental View Maintenance support Yugo Nagata <[email protected]>
2024-07-03 05:30 Re: Conflict Detection and Resolution shveta malik <[email protected]>
2024-07-03 05:59 ` Re: Conflict Detection and Resolution Dilip Kumar <[email protected]>
2024-07-03 07:00   ` Re: Conflict Detection and Resolution Amit Kapila <[email protected]>
2024-07-03 08:46     ` Re: Conflict Detection and Resolution Dilip Kumar <[email protected]>
2024-07-03 10:05       ` Re: Conflict Detection and Resolution Amit Kapila <[email protected]>
2024-07-03 10:34         ` Re: Conflict Detection and Resolution Dilip Kumar <[email protected]>
2024-07-03 11:17           ` Re: Conflict Detection and Resolution Amit Kapila <[email protected]>
2024-07-03 11:36             ` Re: Conflict Detection and Resolution Dilip Kumar <[email protected]>
2024-07-04 12:07               ` Re: Conflict Detection and Resolution Amit Kapila <[email protected]>
2024-07-05 06:27                 ` Re: Conflict Detection and Resolution Dilip Kumar <[email protected]>
2024-07-05 06:52                   ` Re: Conflict Detection and Resolution Nisha Moond <[email protected]>
2024-07-05 08:53                   ` Re: Conflict Detection and Resolution Amit Kapila <[email protected]>
2024-07-05 11:41                     ` Re: Conflict Detection and Resolution Dilip Kumar <[email protected]>
2024-07-03 10:39         ` Re: Conflict Detection and Resolution shveta malik <[email protected]>
2024-07-04 04:01     ` Re: Conflict Detection and Resolution shveta malik <[email protected]>
2024-07-03 10:32   ` Re: Conflict Detection and Resolution shveta malik <[email protected]>
2024-07-03 10:42     ` Re: Conflict Detection and Resolution Dilip Kumar <[email protected]>
2024-07-03 11:38       ` Re: Conflict Detection and Resolution shveta malik <[email protected]>
2024-07-03 11:52         ` Re: Conflict Detection and Resolution Dilip Kumar <[email protected]>
2026-05-29 09:05 [PATCH v37 05/11] Add Incremental View Maintenance support to psql Yugo Nagata <[email protected]>
2026-05-29 09:05 [PATCH v38 05/11] Add Incremental View Maintenance support to psql Yugo Nagata <[email protected]>
2026-05-29 09:05 [PATCH v38 05/11] Add Incremental View Maintenance support to psql Yugo Nagata <[email protected]>
2026-05-29 09:05 [PATCH v38 05/11] Add Incremental View Maintenance support to psql Yugo Nagata <[email protected]>
2026-05-29 09:05 [PATCH v37 05/11] Add Incremental View Maintenance support to psql Yugo Nagata <[email protected]>
2026-05-29 09:05 [PATCH v39 5/8] Add Incremental View Maintenance support to psql Yugo Nagata <[email protected]>
2026-05-29 09:05 [PATCH v39 5/8] Add Incremental View Maintenance support to psql Yugo Nagata <[email protected]>
2026-05-29 09:05 [PATCH v37 05/11] Add Incremental View Maintenance support to psql Yugo Nagata <[email protected]>
2026-05-29 09:05 [PATCH v39 5/8] Add Incremental View Maintenance support to psql Yugo Nagata <[email protected]>
2026-05-29 09:06 [PATCH v37 06/11] Add Incremental View Maintenance support Yugo Nagata <[email protected]>
2026-05-29 09:06 [PATCH v38 06/11] Add Incremental View Maintenance support Yugo Nagata <[email protected]>
2026-05-29 09:06 [PATCH v38 06/11] Add Incremental View Maintenance support Yugo Nagata <[email protected]>
2026-05-29 09:06 [PATCH v37 06/11] Add Incremental View Maintenance support Yugo Nagata <[email protected]>
2026-05-29 09:06 [PATCH v39 6/8] Add Incremental View Maintenance support Yugo Nagata <[email protected]>
2026-05-29 09:06 [PATCH v37 06/11] Add Incremental View Maintenance support Yugo Nagata <[email protected]>
2026-05-29 09:06 [PATCH v39 6/8] Add Incremental View Maintenance support Yugo Nagata <[email protected]>
2026-05-29 09:06 [PATCH v39 6/8] Add Incremental View Maintenance support Yugo Nagata <[email protected]>
2026-05-29 09:06 [PATCH v38 06/11] Add Incremental View Maintenance support Yugo Nagata <[email protected]>

This inbox is served by agora; see mirroring instructions
for how to clone and mirror all data and code used for this inbox