agora inbox for [email protected]  

help / color / mirror / Atom feed

[PATCH v2 4/4] Change force_parallel_mode to a DEVELOPER GUC, and remove it from sample config..
150+ messages / 3 participants
[nested] [flat]

* [PATCH v2 4/4] Change force_parallel_mode to a DEVELOPER GUC, and remove it from sample config..
@ 2021-04-04 00:24  Justin Pryzby <[email protected]>
  0 siblings, 0 replies; 150+ messages in thread

From: Justin Pryzby @ 2021-04-04 00:24 UTC (permalink / raw)

..to help avoid users finding this option and changing it in hopes that it'll
make their queries faster, but without reading the documentation or
understanding what it does.
---
 doc/src/sgml/config.sgml                      | 90 +++++++++----------
 src/backend/utils/misc/guc.c                  |  2 +-
 src/backend/utils/misc/postgresql.conf.sample |  1 -
 3 files changed, 46 insertions(+), 47 deletions(-)

diff --git a/doc/src/sgml/config.sgml b/doc/src/sgml/config.sgml
index eb154cd669..4568a5c5a0 100644
--- a/doc/src/sgml/config.sgml
+++ b/doc/src/sgml/config.sgml
@@ -5912,51 +5912,6 @@ SELECT * FROM parent WHERE key = 2400;
       </listitem>
      </varlistentry>
 
-     <varlistentry id="guc-force-parallel-mode" xreflabel="force_parallel_mode">
-      <term><varname>force_parallel_mode</varname> (<type>enum</type>)
-      <indexterm>
-       <primary><varname>force_parallel_mode</varname> configuration parameter</primary>
-      </indexterm>
-      </term>
-      <listitem>
-       <para>
-        Allows the use of parallel queries for testing purposes even in cases
-        where no performance benefit is expected.
-        The allowed values of <varname>force_parallel_mode</varname> are
-        <literal>off</literal> (use parallel mode only when it is expected to improve
-        performance), <literal>on</literal> (force parallel query for all queries
-        for which it is thought to be safe), and <literal>regress</literal> (like
-        <literal>on</literal>, but with additional behavior changes as explained
-        below).
-       </para>
-
-       <para>
-        More specifically, setting this value to <literal>on</literal> will add
-        a <literal>Gather</literal> node to the top of any query plan for which this
-        appears to be safe, so that the query runs inside of a parallel worker.
-        Even when a parallel worker is not available or cannot be used,
-        operations such as starting a subtransaction that would be prohibited
-        in a parallel query context will be prohibited unless the planner
-        believes that this will cause the query to fail.  If failures or
-        unexpected results occur when this option is set, some functions used
-        by the query may need to be marked <literal>PARALLEL UNSAFE</literal>
-        (or, possibly, <literal>PARALLEL RESTRICTED</literal>).
-       </para>
-
-       <para>
-        Setting this value to <literal>regress</literal> has all of the same effects
-        as setting it to <literal>on</literal> plus some additional effects that are
-        intended to facilitate automated regression testing.  Normally,
-        messages from a parallel worker include a context line indicating that,
-        but a setting of <literal>regress</literal> suppresses this line so that the
-        output is the same as in non-parallel execution.  Also,
-        the <literal>Gather</literal> nodes added to plans by this setting are hidden
-        in <literal>EXPLAIN</literal> output so that the output matches what
-        would be obtained if this setting were turned <literal>off</literal>.
-       </para>
-      </listitem>
-     </varlistentry>
-
      <varlistentry id="guc-plan-cache_mode" xreflabel="plan_cache_mode">
       <term><varname>plan_cache_mode</varname> (<type>enum</type>)
       <indexterm>
@@ -10462,6 +10417,51 @@ dynamic_library_path = 'C:\tools\postgresql;H:\my_project\lib;$libdir'
       </listitem>
      </varlistentry>
 
+     <varlistentry id="guc-force-parallel-mode" xreflabel="force_parallel_mode">
+      <term><varname>force_parallel_mode</varname> (<type>enum</type>)
+      <indexterm>
+       <primary><varname>force_parallel_mode</varname> configuration parameter</primary>
+      </indexterm>
+      </term>
+      <listitem>
+       <para>
+        Allows the use of parallel queries for testing purposes even in cases
+        where no performance benefit is expected.
+        The allowed values of <varname>force_parallel_mode</varname> are
+        <literal>off</literal> (use parallel mode only when it is expected to improve
+        performance), <literal>on</literal> (force parallel query for all queries
+        for which it is thought to be safe), and <literal>regress</literal> (like
+        <literal>on</literal>, but with additional behavior changes as explained
+        below).
+       </para>
+
+       <para>
+        More specifically, setting this value to <literal>on</literal> will add
+        a <literal>Gather</literal> node to the top of any query plan for which this
+        appears to be safe, so that the query runs inside of a parallel worker.
+        Even when a parallel worker is not available or cannot be used,
+        operations such as starting a subtransaction that would be prohibited
+        in a parallel query context will be prohibited unless the planner
+        believes that this will cause the query to fail.  If failures or
+        unexpected results occur when this option is set, some functions used
+        by the query may need to be marked <literal>PARALLEL UNSAFE</literal>
+        (or, possibly, <literal>PARALLEL RESTRICTED</literal>).
+       </para>
+
+       <para>
+        Setting this value to <literal>regress</literal> has all of the same effects
+        as setting it to <literal>on</literal> plus some additional effects that are
+        intended to facilitate automated regression testing.  Normally,
+        messages from a parallel worker include a context line indicating that,
+        but a setting of <literal>regress</literal> suppresses this line so that the
+        output is the same as in non-parallel execution.  Also,
+        the <literal>Gather</literal> nodes added to plans by this setting are hidden
+        in <literal>EXPLAIN</literal> output so that the output matches what
+        would be obtained if this setting were turned <literal>off</literal>.
+       </para>
+      </listitem>
+     </varlistentry>
+
      <varlistentry id="guc-ignore-system-indexes" xreflabel="ignore_system_indexes">
       <term><varname>ignore_system_indexes</varname> (<type>boolean</type>)
       <indexterm>
diff --git a/src/backend/utils/misc/guc.c b/src/backend/utils/misc/guc.c
index 2b9583cc77..598813da2d 100644
--- a/src/backend/utils/misc/guc.c
+++ b/src/backend/utils/misc/guc.c
@@ -4922,7 +4922,7 @@ static struct config_enum ConfigureNamesEnum[] =
 	},
 
 	{
-		{"force_parallel_mode", PGC_USERSET, QUERY_TUNING_OTHER,
+		{"force_parallel_mode", PGC_USERSET, DEVELOPER_OPTIONS,
 			gettext_noop("Forces use of parallel query facilities."),
 			gettext_noop("If possible, run query using a parallel worker and with parallel restrictions."),
 			GUC_EXPLAIN
diff --git a/src/backend/utils/misc/postgresql.conf.sample b/src/backend/utils/misc/postgresql.conf.sample
index cc9edc410f..a38fe18886 100644
--- a/src/backend/utils/misc/postgresql.conf.sample
+++ b/src/backend/utils/misc/postgresql.conf.sample
@@ -421,7 +421,6 @@
 #from_collapse_limit = 8
 #join_collapse_limit = 8		# 1 disables collapsing of explicit
 					# JOIN clauses
-#force_parallel_mode = off
 #jit = on				# allow JIT compilation
 #plan_cache_mode = auto			# auto, force_generic_plan or
 					# force_custom_plan
-- 
2.17.0


--0eh6TmSyL6TZE2Uz--





^ permalink  raw  reply  [nested|flat] 150+ messages in thread

* [PATCH v3 3/3] Change force_parallel_mode to a DEVELOPER GUC, and remove it from sample config..
@ 2021-04-04 00:24  Justin Pryzby <[email protected]>
  0 siblings, 0 replies; 150+ messages in thread

From: Justin Pryzby @ 2021-04-04 00:24 UTC (permalink / raw)

..to discourage users from changing this option in hopes that it'll make their
queries faster, but without reading the documentation or understanding what it
does.
---
 doc/src/sgml/config.sgml                      | 96 ++++++++++---------
 src/backend/utils/misc/guc.c                  |  2 +-
 src/backend/utils/misc/postgresql.conf.sample |  1 -
 3 files changed, 50 insertions(+), 49 deletions(-)

diff --git a/doc/src/sgml/config.sgml b/doc/src/sgml/config.sgml
index f749fe9ce7..a7350c6ddc 100644
--- a/doc/src/sgml/config.sgml
+++ b/doc/src/sgml/config.sgml
@@ -5912,51 +5912,6 @@ SELECT * FROM parent WHERE key = 2400;
       </listitem>
      </varlistentry>
 
-     <varlistentry id="guc-force-parallel-mode" xreflabel="force_parallel_mode">
-      <term><varname>force_parallel_mode</varname> (<type>enum</type>)
-      <indexterm>
-       <primary><varname>force_parallel_mode</varname> configuration parameter</primary>
-      </indexterm>
-      </term>
-      <listitem>
-       <para>
-        Allows the use of parallel queries for testing purposes even in cases
-        where no performance benefit is expected.
-        The allowed values of <varname>force_parallel_mode</varname> are
-        <literal>off</literal> (use parallel mode only when it is expected to improve
-        performance), <literal>on</literal> (force parallel query for all queries
-        for which it is thought to be safe), and <literal>regress</literal> (like
-        <literal>on</literal>, but with additional behavior changes as explained
-        below).
-       </para>
-
-       <para>
-        More specifically, setting this value to <literal>on</literal> will add
-        a <literal>Gather</literal> node to the top of any query plan for which this
-        appears to be safe, so that the query runs inside of a parallel worker.
-        Even when a parallel worker is not available or cannot be used,
-        operations such as starting a subtransaction that would be prohibited
-        in a parallel query context will be prohibited unless the planner
-        believes that this will cause the query to fail.  If failures or
-        unexpected results occur when this option is set, some functions used
-        by the query may need to be marked <literal>PARALLEL UNSAFE</literal>
-        (or, possibly, <literal>PARALLEL RESTRICTED</literal>).
-       </para>
-
-       <para>
-        Setting this value to <literal>regress</literal> has all of the same effects
-        as setting it to <literal>on</literal> plus some additional effects that are
-        intended to facilitate automated regression testing.  Normally,
-        messages from a parallel worker include a context line indicating that,
-        but a setting of <literal>regress</literal> suppresses this line so that the
-        output is the same as in non-parallel execution.  Also,
-        the <literal>Gather</literal> nodes added to plans by this setting are hidden
-        in <literal>EXPLAIN</literal> output so that the output matches what
-        would be obtained if this setting were turned <literal>off</literal>.
-       </para>
-      </listitem>
-     </varlistentry>
-
      <varlistentry id="guc-plan-cache_mode" xreflabel="plan_cache_mode">
       <term><varname>plan_cache_mode</varname> (<type>enum</type>)
       <indexterm>
@@ -10374,8 +10329,10 @@ dynamic_library_path = 'C:\tools\postgresql;H:\my_project\lib;$libdir'
     <title>Developer Options</title>
 
     <para>
-     The following parameters are intended for work on the
-     <productname>PostgreSQL</productname> source code, and in some cases
+     The following parameters are intended for development with
+     <productname>PostgreSQL</productname>.  Some of them are useful while
+     writing SQL queries, some of them are useful when
+     working on the source code of PostgreSQL itself, and
      to assist with recovery of severely damaged databases.  There
      should be no reason to use them on a production database.
      As such, they have been excluded from the sample
@@ -10464,6 +10421,51 @@ dynamic_library_path = 'C:\tools\postgresql;H:\my_project\lib;$libdir'
       </listitem>
      </varlistentry>
 
+     <varlistentry id="guc-force-parallel-mode" xreflabel="force_parallel_mode">
+      <term><varname>force_parallel_mode</varname> (<type>enum</type>)
+      <indexterm>
+       <primary><varname>force_parallel_mode</varname> configuration parameter</primary>
+      </indexterm>
+      </term>
+      <listitem>
+       <para>
+        Allows the use of parallel queries for testing purposes even in cases
+        where no performance benefit is expected.
+        The allowed values of <varname>force_parallel_mode</varname> are
+        <literal>off</literal> (use parallel mode only when it is expected to improve
+        performance), <literal>on</literal> (force parallel query for all queries
+        for which it is thought to be safe), and <literal>regress</literal> (like
+        <literal>on</literal>, but with additional behavior changes as explained
+        below).
+       </para>
+
+       <para>
+        More specifically, setting this value to <literal>on</literal> will add
+        a <literal>Gather</literal> node to the top of any query plan for which this
+        appears to be safe, so that the query runs inside of a parallel worker.
+        Even when a parallel worker is not available or cannot be used,
+        operations such as starting a subtransaction that would be prohibited
+        in a parallel query context will be prohibited unless the planner
+        believes that this will cause the query to fail.  If failures or
+        unexpected results occur when this option is set, some functions used
+        by the query may need to be marked <literal>PARALLEL UNSAFE</literal>
+        (or, possibly, <literal>PARALLEL RESTRICTED</literal>).
+       </para>
+
+       <para>
+        Setting this value to <literal>regress</literal> has all of the same effects
+        as setting it to <literal>on</literal> plus some additional effects that are
+        intended to facilitate automated regression testing.  Normally,
+        messages from a parallel worker include a context line indicating that,
+        but a setting of <literal>regress</literal> suppresses this line so that the
+        output is the same as in non-parallel execution.  Also,
+        the <literal>Gather</literal> nodes added to plans by this setting are hidden
+        in <literal>EXPLAIN</literal> output so that the output matches what
+        would be obtained if this setting were turned <literal>off</literal>.
+       </para>
+      </listitem>
+     </varlistentry>
+
      <varlistentry id="guc-ignore-system-indexes" xreflabel="ignore_system_indexes">
       <term><varname>ignore_system_indexes</varname> (<type>boolean</type>)
       <indexterm>
diff --git a/src/backend/utils/misc/guc.c b/src/backend/utils/misc/guc.c
index a3c2ebbc53..b8738561e6 100644
--- a/src/backend/utils/misc/guc.c
+++ b/src/backend/utils/misc/guc.c
@@ -4922,7 +4922,7 @@ static struct config_enum ConfigureNamesEnum[] =
 	},
 
 	{
-		{"force_parallel_mode", PGC_USERSET, QUERY_TUNING_OTHER,
+		{"force_parallel_mode", PGC_USERSET, DEVELOPER_OPTIONS,
 			gettext_noop("Forces use of parallel query facilities."),
 			gettext_noop("If possible, run query using a parallel worker and with parallel restrictions."),
 			GUC_EXPLAIN
diff --git a/src/backend/utils/misc/postgresql.conf.sample b/src/backend/utils/misc/postgresql.conf.sample
index 2f6dd014a8..0f7f49b949 100644
--- a/src/backend/utils/misc/postgresql.conf.sample
+++ b/src/backend/utils/misc/postgresql.conf.sample
@@ -421,7 +421,6 @@
 #from_collapse_limit = 8
 #join_collapse_limit = 8		# 1 disables collapsing of explicit
 					# JOIN clauses
-#force_parallel_mode = off
 #jit = on				# allow JIT compilation
 #plan_cache_mode = auto			# auto, force_generic_plan or
 					# force_custom_plan
-- 
2.17.0


--oC1+HKm2/end4ao3--





^ permalink  raw  reply  [nested|flat] 150+ messages in thread

* [PATCH 4/4] Change force_parallel_mode to a DEVELOPER GUC, and remove it from sample config..
@ 2021-04-04 00:24  Justin Pryzby <[email protected]>
  0 siblings, 0 replies; 150+ messages in thread

From: Justin Pryzby @ 2021-04-04 00:24 UTC (permalink / raw)

..to help avoid users finding this option and changing it in hopes that it'll
make their queries faster, but without reading the documentation or
understanding what it does.
---
 doc/src/sgml/config.sgml                      | 90 +++++++++----------
 src/backend/utils/misc/guc.c                  |  2 +-
 src/backend/utils/misc/postgresql.conf.sample |  1 -
 3 files changed, 46 insertions(+), 47 deletions(-)

diff --git a/doc/src/sgml/config.sgml b/doc/src/sgml/config.sgml
index c4d5126c2a..5c7c5a39ca 100644
--- a/doc/src/sgml/config.sgml
+++ b/doc/src/sgml/config.sgml
@@ -5788,51 +5788,6 @@ SELECT * FROM parent WHERE key = 2400;
       </listitem>
      </varlistentry>
 
-     <varlistentry id="guc-force-parallel-mode" xreflabel="force_parallel_mode">
-      <term><varname>force_parallel_mode</varname> (<type>enum</type>)
-      <indexterm>
-       <primary><varname>force_parallel_mode</varname> configuration parameter</primary>
-      </indexterm>
-      </term>
-      <listitem>
-       <para>
-        Allows the use of parallel queries for testing purposes even in cases
-        where no performance benefit is expected.
-        The allowed values of <varname>force_parallel_mode</varname> are
-        <literal>off</literal> (use parallel mode only when it is expected to improve
-        performance), <literal>on</literal> (force parallel query for all queries
-        for which it is thought to be safe), and <literal>regress</literal> (like
-        <literal>on</literal>, but with additional behavior changes as explained
-        below).
-       </para>
-
-       <para>
-        More specifically, setting this value to <literal>on</literal> will add
-        a <literal>Gather</literal> node to the top of any query plan for which this
-        appears to be safe, so that the query runs inside of a parallel worker.
-        Even when a parallel worker is not available or cannot be used,
-        operations such as starting a subtransaction that would be prohibited
-        in a parallel query context will be prohibited unless the planner
-        believes that this will cause the query to fail.  If failures or
-        unexpected results occur when this option is set, some functions used
-        by the query may need to be marked <literal>PARALLEL UNSAFE</literal>
-        (or, possibly, <literal>PARALLEL RESTRICTED</literal>).
-       </para>
-
-       <para>
-        Setting this value to <literal>regress</literal> has all of the same effects
-        as setting it to <literal>on</literal> plus some additional effects that are
-        intended to facilitate automated regression testing.  Normally,
-        messages from a parallel worker include a context line indicating that,
-        but a setting of <literal>regress</literal> suppresses this line so that the
-        output is the same as in non-parallel execution.  Also,
-        the <literal>Gather</literal> nodes added to plans by this setting are hidden
-        in <literal>EXPLAIN</literal> output so that the output matches what
-        would be obtained if this setting were turned <literal>off</literal>.
-       </para>
-      </listitem>
-     </varlistentry>
-
      <varlistentry id="guc-plan-cache_mode" xreflabel="plan_cache_mode">
       <term><varname>plan_cache_mode</varname> (<type>enum</type>)
       <indexterm>
@@ -10231,6 +10186,51 @@ dynamic_library_path = 'C:\tools\postgresql;H:\my_project\lib;$libdir'
       </listitem>
      </varlistentry>
 
+     <varlistentry id="guc-force-parallel-mode" xreflabel="force_parallel_mode">
+      <term><varname>force_parallel_mode</varname> (<type>enum</type>)
+      <indexterm>
+       <primary><varname>force_parallel_mode</varname> configuration parameter</primary>
+      </indexterm>
+      </term>
+      <listitem>
+       <para>
+        Allows the use of parallel queries for testing purposes even in cases
+        where no performance benefit is expected.
+        The allowed values of <varname>force_parallel_mode</varname> are
+        <literal>off</literal> (use parallel mode only when it is expected to improve
+        performance), <literal>on</literal> (force parallel query for all queries
+        for which it is thought to be safe), and <literal>regress</literal> (like
+        <literal>on</literal>, but with additional behavior changes as explained
+        below).
+       </para>
+
+       <para>
+        More specifically, setting this value to <literal>on</literal> will add
+        a <literal>Gather</literal> node to the top of any query plan for which this
+        appears to be safe, so that the query runs inside of a parallel worker.
+        Even when a parallel worker is not available or cannot be used,
+        operations such as starting a subtransaction that would be prohibited
+        in a parallel query context will be prohibited unless the planner
+        believes that this will cause the query to fail.  If failures or
+        unexpected results occur when this option is set, some functions used
+        by the query may need to be marked <literal>PARALLEL UNSAFE</literal>
+        (or, possibly, <literal>PARALLEL RESTRICTED</literal>).
+       </para>
+
+       <para>
+        Setting this value to <literal>regress</literal> has all of the same effects
+        as setting it to <literal>on</literal> plus some additional effects that are
+        intended to facilitate automated regression testing.  Normally,
+        messages from a parallel worker include a context line indicating that,
+        but a setting of <literal>regress</literal> suppresses this line so that the
+        output is the same as in non-parallel execution.  Also,
+        the <literal>Gather</literal> nodes added to plans by this setting are hidden
+        in <literal>EXPLAIN</literal> output so that the output matches what
+        would be obtained if this setting were turned <literal>off</literal>.
+       </para>
+      </listitem>
+     </varlistentry>
+
      <varlistentry id="guc-ignore-system-indexes" xreflabel="ignore_system_indexes">
       <term><varname>ignore_system_indexes</varname> (<type>boolean</type>)
       <indexterm>
diff --git a/src/backend/utils/misc/guc.c b/src/backend/utils/misc/guc.c
index 27287599ad..06de7c0308 100644
--- a/src/backend/utils/misc/guc.c
+++ b/src/backend/utils/misc/guc.c
@@ -4840,7 +4840,7 @@ static struct config_enum ConfigureNamesEnum[] =
 	},
 
 	{
-		{"force_parallel_mode", PGC_USERSET, QUERY_TUNING_OTHER,
+		{"force_parallel_mode", PGC_USERSET, DEVELOPER_OPTIONS,
 			gettext_noop("Forces use of parallel query facilities."),
 			gettext_noop("If possible, run query using a parallel worker and with parallel restrictions."),
 			GUC_EXPLAIN
diff --git a/src/backend/utils/misc/postgresql.conf.sample b/src/backend/utils/misc/postgresql.conf.sample
index 52c4373a79..50faa50462 100644
--- a/src/backend/utils/misc/postgresql.conf.sample
+++ b/src/backend/utils/misc/postgresql.conf.sample
@@ -415,7 +415,6 @@
 #from_collapse_limit = 8
 #join_collapse_limit = 8		# 1 disables collapsing of explicit
 					# JOIN clauses
-#force_parallel_mode = off
 #jit = on				# allow JIT compilation
 #plan_cache_mode = auto			# auto, force_generic_plan or
 					# force_custom_plan
-- 
2.17.0


--GyRA7555PLgSTuth--





^ permalink  raw  reply  [nested|flat] 150+ messages in thread

* [PATCH v29 07/11] Add DISTINCT support for IVM
@ 2023-05-31 10:08  Yugo Nagata <[email protected]>
  0 siblings, 0 replies; 150+ messages in thread

From: Yugo Nagata @ 2023-05-31 10:08 UTC (permalink / raw)

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/commands/createas.c     | 141 ++++++++++++++++++++------
 src/backend/commands/indexcmds.c    |  40 ++++++++
 src/backend/commands/matview.c      | 148 ++++++++++++++++++++++++++--
 src/backend/commands/tablecmds.c    |   9 ++
 src/backend/parser/parse_relation.c |  18 +++-
 src/backend/rewrite/rewriteDefine.c |   3 +-
 src/include/commands/createas.h     |   2 +
 src/include/nodes/parsenodes.h      |   1 +
 8 files changed, 317 insertions(+), 45 deletions(-)

diff --git a/src/backend/commands/createas.c b/src/backend/commands/createas.c
index 415f110516..076f35ee6b 100644
--- a/src/backend/commands/createas.c
+++ b/src/backend/commands/createas.c
@@ -53,6 +53,7 @@
 #include "parser/parser.h"
 #include "parser/parsetree.h"
 #include "parser/parse_clause.h"
+#include "parser/parse_func.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/smgr.h"
 #include "tcop/tcopprot.h"
@@ -309,6 +310,9 @@ ExecCreateTableAs(ParseState *pstate, CreateTableAsStmt *stmt,
 					 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)
@@ -413,6 +417,49 @@ ExecCreateTableAs(ParseState *pstate, CreateTableAsStmt *stmt,
 	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;
+
+	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)
+	{
+		TargetEntry *tle;
+
+		rewritten->groupClause = transformDistinctClause(NULL, &rewritten->targetList, rewritten->sortClause, false);
+
+		fn = makeFuncCall(SystemFuncName("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
  *
@@ -536,7 +583,8 @@ intorel_startup(DestReceiver *self, int operation, TupleDesc typeinfo)
 		ColumnDef  *col;
 		char	   *colname;
 
-		if (lc)
+		/* Don't override hidden columns added for IVM */
+		if (lc && !isIvmName(NameStr(attribute->attname)))
 		{
 			colname = strVal(lfirst(lc));
 			lc = lnext(into->colNames, lc);
@@ -940,10 +988,6 @@ check_ivm_restriction_walker(Node *node, void *context)
 					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),
@@ -1090,12 +1134,18 @@ CreateIndexOnIMMV(Query *query, Relation matviewRel)
 	char		idxname[NAMEDATALEN];
 	List	   *indexoidlist = RelationGetIndexList(matviewRel);
 	ListCell   *indexoidscan;
-	Bitmapset *key_attnos;
 
 	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;
@@ -1122,41 +1172,68 @@ CreateIndexOnIMMV(Query *query, Relation matviewRel)
 	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)
+	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);
-
-			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);
-			}
+			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;
+		Bitmapset *key_attnos;
+
+		/* 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, "
+							   "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. */
diff --git a/src/backend/commands/indexcmds.c b/src/backend/commands/indexcmds.c
index ab8b81b302..4811a1c8df 100644
--- a/src/backend/commands/indexcmds.c
+++ b/src/backend/commands/indexcmds.c
@@ -38,6 +38,7 @@
 #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"
@@ -1104,6 +1105,45 @@ DefineIndex(Oid tableId,
 	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 (int 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 39305f3c49..aa518f20ef 100644
--- a/src/backend/commands/matview.c
+++ b/src/backend/commands/matview.c
@@ -152,11 +152,15 @@ static Query *rewrite_query_for_postupdate_state(Query *query, MV_TriggerTable *
 
 static void apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *new_tuplestores,
 			TupleDesc tupdesc_old, TupleDesc tupdesc_new,
-			Query *query);
+			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);
@@ -271,6 +275,7 @@ ExecRefreshMatView(RefreshMatViewStmt *stmt, const char *queryString,
 	Oid			matviewOid;
 	Relation	matviewRel;
 	Query	   *dataQuery;
+	Query	   *viewQuery;
 	Oid			tableSpace;
 	Oid			relowner;
 	Oid			OIDNewHeap;
@@ -330,8 +335,13 @@ ExecRefreshMatView(RefreshMatViewStmt *stmt, const char *queryString,
 						"CONCURRENTLY", "WITH NO DATA")));
 
 
-	dataQuery = get_matview_query(matviewRel);
+	viewQuery = get_matview_query(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
@@ -511,8 +521,8 @@ ExecRefreshMatView(RefreshMatViewStmt *stmt, const char *queryString,
 
 	if (!stmt->skipData && RelationIsIVM(matviewRel) && !oldPopulated)
 	{
-		CreateIndexOnIMMV(dataQuery, matviewRel);
-		CreateIvmTriggersOnBaseTables(dataQuery, matviewOid);
+		CreateIndexOnIMMV(viewQuery, matviewRel);
+		CreateIvmTriggersOnBaseTables(viewQuery, matviewOid);
 	}
 
 	table_close(matviewRel, NoLock);
@@ -1512,6 +1522,13 @@ IVM_immediate_maintenance(PG_FUNCTION_ARGS)
 			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,
@@ -1524,7 +1541,8 @@ IVM_immediate_maintenance(PG_FUNCTION_ARGS)
 			{
 				/* apply the delta tables to the materialized view */
 				apply_delta(matviewOid, old_tuplestore, new_tuplestore,
-							tupdesc_old, tupdesc_new, query);
+							tupdesc_old, tupdesc_new, query, use_count,
+							count_colname);
 			}
 			PG_CATCH();
 			{
@@ -1997,7 +2015,7 @@ rewrite_query_for_postupdate_state(Query *query, MV_TriggerTable *table, int rte
 static void
 apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *new_tuplestores,
 			TupleDesc tupdesc_old, TupleDesc tupdesc_new,
-			Query *query)
+			Query *query, bool use_count, char *count_colname)
 {
 	StringInfoData querybuf;
 	StringInfoData target_list_buf;
@@ -2073,7 +2091,12 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n
 		if (rc != SPI_OK_REL_REGISTER)
 			elog(ERROR, "SPI_register failed");
 
-		apply_old_delta(matviewname, OLD_DELTA_ENRNAME, keys);
+		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 */
@@ -2095,7 +2118,11 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n
 			elog(ERROR, "SPI_register failed");
 
 		/* apply new delta */
-		apply_new_delta(matviewname, NEW_DELTA_ENRNAME, &target_list_buf);
+		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. */
@@ -2108,6 +2135,51 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n
 		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
  *
@@ -2157,6 +2229,66 @@ apply_old_delta(const char *matviewname, const char *deltaname_old,
 		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 exist */
+						"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
  *
diff --git a/src/backend/commands/tablecmds.c b/src/backend/commands/tablecmds.c
index 47c900445c..adbd768e0d 100644
--- a/src/backend/commands/tablecmds.c
+++ b/src/backend/commands/tablecmds.c
@@ -53,6 +53,7 @@
 #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"
@@ -3673,6 +3674,14 @@ 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/parser/parse_relation.c b/src/backend/parser/parse_relation.c
index 864ea9b0d5..c257440414 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"
 
 
 /*
@@ -97,7 +98,7 @@ 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 rte_visible_if_lateral(ParseState *pstate, RangeTblEntry *rte);
 static bool rte_visible_if_qualified(ParseState *pstate, RangeTblEntry *rte);
@@ -1502,6 +1503,7 @@ 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
@@ -1587,6 +1589,7 @@ 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
@@ -2758,7 +2761,7 @@ 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)
 					{
@@ -3026,7 +3029,7 @@ 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);
 }
 
@@ -3043,7 +3046,7 @@ 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;
@@ -3056,6 +3059,9 @@ 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)
@@ -3218,6 +3224,10 @@ 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 e36fc72e1e..f6dc7ba202 100644
--- a/src/backend/rewrite/rewriteDefine.c
+++ b/src/backend/rewrite/rewriteDefine.c
@@ -621,7 +621,8 @@ 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/commands/createas.h b/src/include/commands/createas.h
index 09a64fa2e5..76a7873ebf 100644
--- a/src/include/commands/createas.h
+++ b/src/include/commands/createas.h
@@ -29,6 +29,8 @@ extern ObjectAddress ExecCreateTableAs(ParseState *pstate, CreateTableAsStmt *st
 extern void CreateIvmTriggersOnBaseTables(Query *qry, Oid matviewOid);
 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/nodes/parsenodes.h b/src/include/nodes/parsenodes.h
index fef4c714b8..1a2b8fa09e 100644
--- a/src/include/nodes/parsenodes.h
+++ b/src/include/nodes/parsenodes.h
@@ -1073,6 +1073,7 @@ typedef struct RangeTblEntry
 	int			rellockmode;	/* lock level that query requires on the rel */
 	struct TableSampleClause *tablesample;	/* sampling info, or NULL */
 	Index		perminfoindex;
+	bool		relisivm;
 
 	/*
 	 * Fields valid for a subquery RTE (else NULL):
-- 
2.25.1


--Multipart=_Mon__28_Aug_2023_16_05_30_+0900_b1OvQD_3A3ZMTGvj
Content-Type: text/x-diff;
 name="v29-0008-Add-aggregates-support-in-IVM.patch"
Content-Disposition: attachment;
 filename="v29-0008-Add-aggregates-support-in-IVM.patch"
Content-Transfer-Encoding: quoted-printable



^ permalink  raw  reply  [nested|flat] 150+ messages in thread

* [PATCH v8] using indexscan to speedup add not null constraints
@ 2025-10-20 05:29  jian he <[email protected]>
  0 siblings, 0 replies; 150+ messages in thread

From: jian he @ 2025-10-20 05:29 UTC (permalink / raw)

This patch tries to use index_beginscan() / index_getnext() / index_endscan()
mentioned in [1] to speedup adding not-null constraints to the existing table.

The main logic happens in phase3 ATRewriteTable
1. collect all not-null constraints.
2. For each not-null constraint, check whether there is a corresponding index
available for validation. If not, then can not use indexscan to verify not-null
constraints.
3. If any of the following conditions are true
  * table scan or rewrite is required,
  * table wasn't locked with `AccessExclusiveLock`
  * the NOT NULL constraint applies to a virtual generated column
 then index scan cannot be used for fast validation.
4. If all conditions are satisfied, attempt to use indexscan to verify
whether the column contains any NULL values.

concurrency concern:
ALTER TABLE SET NOT NULL will take an ACCESS EXCLUSIVE lock, so there is less
variant of racing issue can occur?  to prove accurate, I wrote some isolation
tests. see[2]

performance:
demo:
case when: %20 percent values are NULL and have been deleted from heap but they
still on the index.

drop table if exists t;
create unlogged table t(a int, b int) with (autovacuum_enabled = off, vacuum_index_cleanup=off);
insert into t select case when g % 5 = 0 then null else g end, g+1
from generate_series(1,1_000_000) g;
create index t_idx_a on t(a);
delete from t where a is null;

alter table t alter column a drop not null;
alter table t add constraint t1 not null a;

the above two statement running several times:
patch Time:: 1.084  ms
master Time: 12.045 ms

references:
[1] https://postgr.es/m/CA%2BTgmoa5NKz8iGW_9v7wz%3D-%2BzQFu%3DE4SZoaTaU1znLaEXRYp-Q%40mail.gmail.com
[2] https://postgr.es/m/900056D1-32DF-4927-8251-3E0C0DC407FD%40anarazel.de
discussion: https://postgr.es/m/CACJufxFiW=4k1is=F1J=r-Cx1RuByXQPUrWB331U47rSnGz+hw@mail.gmail.com
commitfest entry: https://commitfest.postgresql.org/patch/5444
---
 src/backend/commands/tablecmds.c              | 116 +++++++++-
 src/backend/executor/execIndexing.c           | 213 ++++++++++++++++++
 src/include/executor/executor.h               |   2 +
 .../expected/indexscan-check-notnull.out      |  97 ++++++++
 src/test/isolation/isolation_schedule         |   1 +
 .../specs/indexscan-check-notnull.spec        |  45 ++++
 src/test/modules/test_misc/meson.build        |   1 +
 .../t/011_indexscan_validate_notnull.pl       | 163 ++++++++++++++
 8 files changed, 632 insertions(+), 6 deletions(-)
 create mode 100644 src/test/isolation/expected/indexscan-check-notnull.out
 create mode 100644 src/test/isolation/specs/indexscan-check-notnull.spec
 create mode 100644 src/test/modules/test_misc/t/011_indexscan_validate_notnull.pl

diff --git a/src/backend/commands/tablecmds.c b/src/backend/commands/tablecmds.c
index f976c0e5c7e..2af06630b35 100644
--- a/src/backend/commands/tablecmds.c
+++ b/src/backend/commands/tablecmds.c
@@ -210,16 +210,19 @@ typedef struct AlteredTableInfo
 	List	   *changedStatisticsDefs;	/* string definitions of same */
 } AlteredTableInfo;
 
-/* Struct describing one new constraint to check in Phase 3 scan */
-/* Note: new not-null constraints are handled elsewhere */
+/*
+ * Struct describing one new constraint to check in Phase 3 scan. Note: new
+ * not-null constraints are handled here too.
+*/
 typedef struct NewConstraint
 {
 	char	   *name;			/* Constraint name, or NULL if none */
-	ConstrType	contype;		/* CHECK or FOREIGN */
+	ConstrType	contype;		/* CHECK or FOREIGN or NOT NULL */
 	Oid			refrelid;		/* PK rel, if FOREIGN */
 	Oid			refindid;		/* OID of PK's index, if FOREIGN */
 	bool		conwithperiod;	/* Whether the new FOREIGN KEY uses PERIOD */
 	Oid			conid;			/* OID of pg_constraint entry, if FOREIGN */
+	int			attnum;			/* NOT NULL constraint attribute number */
 	Node	   *qual;			/* Check expr or CONSTR_FOREIGN Constraint */
 	ExprState  *qualstate;		/* Execution state for CHECK expr */
 } NewConstraint;
@@ -6217,6 +6220,9 @@ ATRewriteTable(AlteredTableInfo *tab, Oid OIDNewHeap)
 				needscan = true;
 				con->qualstate = ExecPrepareExpr((Expr *) expand_generated_columns_in_expr(con->qual, oldrel, 1), estate);
 				break;
+			case CONSTR_NOTNULL:
+				/* Nothing to do here */
+				break;
 			case CONSTR_FOREIGN:
 				/* Nothing to do here */
 				break;
@@ -6270,10 +6276,69 @@ ATRewriteTable(AlteredTableInfo *tab, Oid OIDNewHeap)
 														wholeatt->attnum);
 			}
 		}
-		if (notnull_attrs || notnull_virtual_attrs)
-			needscan = true;
 	}
 
+	/*-
+	 * If we have to verify new not-null constraints and don't have any other
+	 * reason to fully scan the table, then we can use indexes to test for
+	 * absence of NULL values instead of scanning.  The following conditions
+	 * must be met:
+	 * - we're operating on a regular table
+	 * - we hold AccessExclusiveLock on the table
+	 * - no not-null constraint covers a virtual generated column,
+	 *   because no indexes can be created on them
+	 */
+	if (!needscan &&
+		newrel == NULL &&
+		tab->verify_new_notnull &&
+		notnull_virtual_attrs == NIL &&
+		oldrel->rd_rel->relkind == RELKIND_RELATION &&
+		CheckRelationLockedByMe(oldrel, AccessExclusiveLock, false))
+	{
+		List	   *notnull_attnums = NIL;
+
+		Assert(!tab->rewrite);
+
+		foreach(l, tab->constraints)
+		{
+			Form_pg_attribute attr;
+			NewConstraint *con = lfirst(l);
+
+			if (con->contype != CONSTR_NOTNULL)
+				continue;
+
+			attr = TupleDescAttr(newTupDesc, con->attnum - 1);
+
+			Assert(attr->attnotnull);
+			Assert(attr->attnum == con->attnum);
+
+			if (attr->attgenerated == ATTRIBUTE_GENERATED_VIRTUAL)
+			{
+				needscan = true;
+				break;
+			}
+
+			notnull_attnums = lappend_int(notnull_attnums, attr->attnum);
+		}
+
+		/*
+		 * Validate new NOT NULL constraints, unless we need a scan for other
+		 * reasons, because we can validate them cheaply there, and doing it
+		 * also here would be a waste of cycles.
+		 */
+		if (notnull_attnums != NIL && !needscan)
+		{
+			if (!index_check_notnull(oldrel, notnull_attnums))
+				needscan = true;
+			else
+				ereport(DEBUG1,
+						errmsg_internal("all new not-null constraints on relation \"%s\" have been validated by using index scan",
+										RelationGetRelationName(oldrel)));
+		}
+	}
+	else if (notnull_attrs || notnull_virtual_attrs)
+		needscan = true;
+
 	if (newrel || needscan)
 	{
 		ExprContext *econtext;
@@ -7949,6 +8014,7 @@ ATExecSetNotNull(List **wqueue, Relation rel, char *conName, char *colName,
 	CookedConstraint *ccon;
 	List	   *cooked;
 	bool		is_no_inherit = false;
+	AlteredTableInfo *tab = NULL;
 
 	/* Guard against stack overflow due to overly deep inheritance tree. */
 	check_stack_depth();
@@ -8073,10 +8139,32 @@ ATExecSetNotNull(List **wqueue, Relation rel, char *conName, char *colName,
 	constraint->is_no_inherit = is_no_inherit;
 	constraint->conname = conName;
 
+	tab = ATGetQueueEntry(wqueue, rel);
+
 	/* and do it */
 	cooked = AddRelationNewConstraints(rel, NIL, list_make1(constraint),
 									   false, !recursing, false, NULL);
 	ccon = linitial(cooked);
+
+	Assert(ccon->contype == CONSTR_NOTNULL);
+
+	/*
+	 * We may use indexscan to vertify not-null constraint in Phase3.  Add the
+	 * to-be-validated not-null constraint to Phase 3's queue.
+	 */
+	if (!ccon->skip_validation)
+	{
+		NewConstraint *newcon;
+
+		newcon = (NewConstraint *) palloc0(sizeof(NewConstraint));
+
+		newcon->name = ccon->name;
+		newcon->contype = ccon->contype;
+		newcon->attnum = ccon->attnum;
+
+		tab->constraints = lappend(tab->constraints, newcon);
+	}
+
 	ObjectAddressSet(address, ConstraintRelationId, ccon->conoid);
 
 	InvokeObjectPostAlterHook(RelationRelationId,
@@ -9983,13 +10071,15 @@ ATAddCheckNNConstraint(List **wqueue, AlteredTableInfo *tab, Relation rel,
 	{
 		CookedConstraint *ccon = (CookedConstraint *) lfirst(lcon);
 
-		if (!ccon->skip_validation && ccon->contype != CONSTR_NOTNULL)
+		if (!ccon->skip_validation)
 		{
 			NewConstraint *newcon;
 
 			newcon = palloc0_object(NewConstraint);
 			newcon->name = ccon->name;
 			newcon->contype = ccon->contype;
+			if (ccon->contype == CONSTR_NOTNULL)
+				newcon->attnum = ccon->attnum;
 			newcon->qual = ccon->expr;
 
 			tab->constraints = lappend(tab->constraints, newcon);
@@ -13258,6 +13348,7 @@ QueueNNConstraintValidation(List **wqueue, Relation conrel, Relation rel,
 	List	   *children = NIL;
 	AttrNumber	attnum;
 	char	   *colname;
+	NewConstraint *newcon;
 
 	con = (Form_pg_constraint) GETSTRUCT(contuple);
 	Assert(con->contype == CONSTRAINT_NOTNULL);
@@ -13321,7 +13412,20 @@ QueueNNConstraintValidation(List **wqueue, Relation conrel, Relation rel,
 	/* Set attnotnull appropriately without queueing another validation */
 	set_attnotnull(NULL, rel, attnum, true, false);
 
+	/*
+	 * Queue validation for phase 3.
+	 *
+	 * ALTER TABLE SET NOT NULL will add NOT NULL constraint to
+	 * AlteredTableInfo->constraints, for consistency, do the same here.
+	 */
+	newcon = (NewConstraint *) palloc0(sizeof(NewConstraint));
+	newcon->name = colname;
+	newcon->contype = CONSTR_NOTNULL;
+	newcon->attnum = attnum;
+
+	/* Find or create work queue entry for this table */
 	tab = ATGetQueueEntry(wqueue, rel);
+	tab->constraints = lappend(tab->constraints, newcon);
 	tab->verify_new_notnull = true;
 
 	/*
diff --git a/src/backend/executor/execIndexing.c b/src/backend/executor/execIndexing.c
index 6ae0f959592..88694ce0335 100644
--- a/src/backend/executor/execIndexing.c
+++ b/src/backend/executor/execIndexing.c
@@ -108,12 +108,15 @@
 
 #include "access/genam.h"
 #include "access/relscan.h"
+#include "access/table.h"
 #include "access/tableam.h"
 #include "access/xact.h"
 #include "catalog/index.h"
+#include "catalog/pg_am_d.h"
 #include "executor/executor.h"
 #include "nodes/nodeFuncs.h"
 #include "storage/lmgr.h"
+#include "utils/fmgroids.h"
 #include "utils/injection_point.h"
 #include "utils/multirangetypes.h"
 #include "utils/rangetypes.h"
@@ -146,6 +149,7 @@ static bool index_expression_changed_walker(Node *node,
 											Bitmapset *allUpdatedCols);
 static void ExecWithoutOverlapsNotEmpty(Relation rel, NameData attname, Datum attval,
 										char typtype, Oid atttypid);
+static bool index_check_notnull_internal(Relation relation, List *attnums, List *idxs);
 
 /* ----------------------------------------------------------------
  *		ExecOpenIndices
@@ -1178,3 +1182,212 @@ ExecWithoutOverlapsNotEmpty(Relation rel, NameData attname, Datum attval, char t
 				 errmsg("empty WITHOUT OVERLAPS value found in column \"%s\" in relation \"%s\"",
 						NameStr(attname), RelationGetRelationName(rel))));
 }
+
+/*
+ * notnull_attnums: list of attribute numbers of all new not-null constraints.
+ *
+ * First check whether the relation has a suitable index for each not-null
+ * attribute, then using indexscan mechanism to verify that *all* attributes on
+ * notnull_attnums are indeed not null.
+ *
+ * Returning true means all new not-null constraints have been verified, no
+ * need an extra scan to verify newly added not-null constraints.
+ */
+bool
+index_check_notnull(Relation relation, List *notnull_attnums)
+{
+	Relation	pg_index;
+	Relation	index_rel;
+	SysScanDesc indscan;
+	ScanKeyData skey;
+	HeapTuple	htup;
+	TupleDesc	tupdesc;
+	Form_pg_attribute attr;
+	List	   *idxs = NIL;
+	List	   *attnums = NIL;
+
+	tupdesc = RelationGetDescr(relation);
+
+	/* Prepare to scan pg_index for entries having indrelid = this rel */
+	ScanKeyInit(&skey,
+				Anum_pg_index_indrelid,
+				BTEqualStrategyNumber, F_OIDEQ,
+				ObjectIdGetDatum(RelationGetRelid(relation)));
+
+	pg_index = table_open(IndexRelationId, AccessShareLock);
+	indscan = systable_beginscan(pg_index, IndexIndrelidIndexId, true,
+								 NULL, 1, &skey);
+
+	while (HeapTupleIsValid(htup = systable_getnext(indscan)))
+	{
+		Form_pg_index index = (Form_pg_index) GETSTRUCT(htup);
+
+		/*
+		 * we can only use non-deferred, validated, and alive btree index to
+		 * validate not-null constraints
+		 */
+		if (!index->indimmediate || !index->indisvalid || !index->indislive)
+			continue;
+
+		/* can not use expression index or partial index too */
+		if (!heap_attisnull(htup, Anum_pg_index_indexprs, NULL) ||
+			!heap_attisnull(htup, Anum_pg_index_indpred, NULL))
+			continue;
+
+		index_rel = index_open(index->indexrelid, AccessShareLock);
+
+		/* can only apply to btree index */
+		if (index_rel->rd_rel->relam != BTREE_AM_OID)
+		{
+			index_close(index_rel, AccessShareLock);
+			continue;
+		}
+
+		/* collect index attnums while loop */
+		for (int i = 0; i < index->indnkeyatts; i++)
+		{
+			attr = TupleDescAttr(tupdesc, (index->indkey.values[i] - 1));
+
+			if (attr->attisdropped)
+				continue;
+
+			if (list_member_int(notnull_attnums, attr->attnum) &&
+				!list_member_int(attnums, attr->attnum))
+			{
+				attnums = lappend_int(attnums, attr->attnum);
+				idxs = lappend_oid(idxs, index->indexrelid);
+			}
+		}
+		index_close(index_rel, NoLock);
+	}
+	systable_endscan(indscan);
+	table_close(pg_index, AccessShareLock);
+
+	if (attnums == NIL)
+		return false;
+
+	/*
+	 * every not-null constraint requires an index for indexscan.  If no such
+	 * index exists, we need to use regular table scan to validate not-null
+	 * constraints.
+	 */
+	foreach_int(attno, notnull_attnums)
+	{
+		if (!list_member_int(attnums, attno))
+			return false;
+	}
+
+	return index_check_notnull_internal(relation, attnums, idxs);
+}
+
+/*
+ * Use indexscan mechanism to fast verify each attribute in "attnums" are
+ * not-null or not.
+ */
+static bool
+index_check_notnull_internal(Relation relation, List *attnums, List *idxs)
+{
+	EState	   *estate;
+	ExprContext *econtext;
+	TupleTableSlot *existing_slot;
+	bool		all_not_null = true;
+	ListCell   *lc,
+			   *lc2;
+
+	/*
+	 * Need an EState for slot to hold the current tuple.
+	 */
+	estate = CreateExecutorState();
+	econtext = GetPerTupleExprContext(estate);
+
+	forboth(lc, attnums, lc2, idxs)
+	{
+		SnapshotData DirtySnapshot;
+		IndexScanDesc index_scan;
+		ScanKeyData scankeys[INDEX_MAX_KEYS];
+		IndexInfo  *indexInfo;
+		AttrNumber	sk_attno = -1;
+		Relation	index;
+		int			indnkeyatts;
+
+		AttrNumber	attno = lfirst_int(lc);
+		Oid			indexoid = lfirst_oid(lc2);
+
+		existing_slot = table_slot_create(relation, NULL);
+
+		/* Arrange for econtext's scan tuple to be the tuple under test */
+		econtext->ecxt_scantuple = existing_slot;
+
+		index = index_open(indexoid, NoLock);
+
+		indexInfo = BuildIndexInfo(index);
+		indnkeyatts = IndexRelationGetNumberOfKeyAttributes(index);
+
+		/*
+		 * Search the tuples that are in the index for any violations,
+		 * including tuples that aren't visible yet.
+		 */
+		InitDirtySnapshot(DirtySnapshot);
+
+		for (int i = 0; i < indnkeyatts; i++)
+		{
+			if (indexInfo->ii_IndexAttrNumbers[i] == attno)
+			{
+				sk_attno = i + 1;
+				break;
+			}
+		}
+
+		if (sk_attno == -1)
+			elog(ERROR, "cache lookup failed for attribute number %d on index %u", indexoid, attno);
+
+		for (int i = 0; i < indnkeyatts; i++)
+		{
+			/* set up an IS NULL scan key so that we ignore not nulls */
+			ScanKeyEntryInitialize(&scankeys[i],
+								   SK_ISNULL | SK_SEARCHNULL,
+								   sk_attno,	/* index col to scan */
+								   InvalidStrategy, /* no strategy */
+								   InvalidOid,	/* no strategy subtype */
+								   InvalidOid,	/* no collation */
+								   InvalidOid,	/* no reg proc for this */
+								   (Datum) 0);	/* constant */
+		}
+
+		index_scan = index_beginscan(relation, index, &DirtySnapshot, NULL, indnkeyatts, 0);
+		index_rescan(index_scan, scankeys, indnkeyatts, NULL, 0);
+
+		while (index_getnext_slot(index_scan, ForwardScanDirection, existing_slot))
+		{
+			Datum		values[INDEX_MAX_KEYS];
+			bool		nulls[INDEX_MAX_KEYS];
+
+			/*
+			 * Extract the index column values and isnull flags from the
+			 * existing tuple.
+			 */
+			FormIndexDatum(indexInfo, existing_slot, estate, values, nulls);
+
+			if (nulls[sk_attno - 1])
+			{
+				all_not_null = false;
+				break;
+			}
+		}
+
+		index_endscan(index_scan);
+		index_close(index, NoLock);
+		ExecDropSingleTupleTableSlot(existing_slot);
+
+		/* exit earlier */
+		if (!all_not_null)
+		{
+			FreeExecutorState(estate);
+			return false;
+		}
+	}
+
+	FreeExecutorState(estate);
+
+	return true;
+}
diff --git a/src/include/executor/executor.h b/src/include/executor/executor.h
index 5929aabc353..7f24caeeafb 100644
--- a/src/include/executor/executor.h
+++ b/src/include/executor/executor.h
@@ -756,6 +756,8 @@ extern void check_exclusion_constraint(Relation heap, Relation index,
 									   const Datum *values, const bool *isnull,
 									   EState *estate, bool newIndex);
 
+extern bool index_check_notnull(Relation relation, List *notnull_attnums);
+
 /*
  * prototypes from functions in execReplication.c
  */
diff --git a/src/test/isolation/expected/indexscan-check-notnull.out b/src/test/isolation/expected/indexscan-check-notnull.out
new file mode 100644
index 00000000000..c6a652e2518
--- /dev/null
+++ b/src/test/isolation/expected/indexscan-check-notnull.out
@@ -0,0 +1,97 @@
+Parsed test spec with 2 sessions
+
+starting permutation: s1_b1 s2_b1 s1_d1 s2_a1 s1_c1 s2_c1 s1_q1
+step s1_b1: BEGIN ISOLATION LEVEL REPEATABLE READ;
+step s2_b1: BEGIN ISOLATION LEVEL REPEATABLE READ;
+step s1_d1: DELETE FROM t;
+step s2_a1: ALTER TABLE t ADD CONSTRAINT t1_nn NOT NULL a; <waiting ...>
+step s1_c1: COMMIT;
+step s2_a1: <... completed>
+step s2_c1: COMMIT;
+step s1_q1: SELECT conname, conrelid::regclass, contype, convalidated
+              FROM pg_constraint WHERE conname = 't1_nn';
+
+conname|conrelid|contype|convalidated
+-------+--------+-------+------------
+t1_nn  |t       |n      |t           
+(1 row)
+
+
+starting permutation: s1_b2 s2_b1 s1_d1 s2_a1 s1_c1 s2_c1 s1_q1
+step s1_b2: BEGIN;
+step s2_b1: BEGIN ISOLATION LEVEL REPEATABLE READ;
+step s1_d1: DELETE FROM t;
+step s2_a1: ALTER TABLE t ADD CONSTRAINT t1_nn NOT NULL a; <waiting ...>
+step s1_c1: COMMIT;
+step s2_a1: <... completed>
+step s2_c1: COMMIT;
+step s1_q1: SELECT conname, conrelid::regclass, contype, convalidated
+              FROM pg_constraint WHERE conname = 't1_nn';
+
+conname|conrelid|contype|convalidated
+-------+--------+-------+------------
+t1_nn  |t       |n      |t           
+(1 row)
+
+
+starting permutation: s1_b1 s2_b2 s1_d1 s2_a1 s1_c1 s2_c1 s1_q1
+step s1_b1: BEGIN ISOLATION LEVEL REPEATABLE READ;
+step s2_b2: BEGIN;
+step s1_d1: DELETE FROM t;
+step s2_a1: ALTER TABLE t ADD CONSTRAINT t1_nn NOT NULL a; <waiting ...>
+step s1_c1: COMMIT;
+step s2_a1: <... completed>
+step s2_c1: COMMIT;
+step s1_q1: SELECT conname, conrelid::regclass, contype, convalidated
+              FROM pg_constraint WHERE conname = 't1_nn';
+
+conname|conrelid|contype|convalidated
+-------+--------+-------+------------
+t1_nn  |t       |n      |t           
+(1 row)
+
+
+starting permutation: s1_b1 s2_b1 s2_a1 s1_r1 s2_r1
+step s1_b1: BEGIN ISOLATION LEVEL REPEATABLE READ;
+step s2_b1: BEGIN ISOLATION LEVEL REPEATABLE READ;
+step s2_a1: ALTER TABLE t ADD CONSTRAINT t1_nn NOT NULL a;
+ERROR:  column "a" of relation "t" contains null values
+step s1_r1: ROLLBACK;
+step s2_r1: ROLLBACK;
+
+starting permutation: s1_b1 s2_b2 s2_d1 s1_d1 s2_r1 s1_a1 s1_q1 s1_r1
+step s1_b1: BEGIN ISOLATION LEVEL REPEATABLE READ;
+step s2_b2: BEGIN;
+step s2_d1: DROP INDEX t_ab_idx;
+step s1_d1: DELETE FROM t; <waiting ...>
+step s2_r1: ROLLBACK;
+step s1_d1: <... completed>
+step s1_a1: ALTER TABLE t ADD CONSTRAINT t1_nn NOT NULL a;
+step s1_q1: SELECT conname, conrelid::regclass, contype, convalidated
+              FROM pg_constraint WHERE conname = 't1_nn';
+
+conname|conrelid|contype|convalidated
+-------+--------+-------+------------
+t1_nn  |t       |n      |t           
+(1 row)
+
+step s1_r1: ROLLBACK;
+
+starting permutation: s1_b2 s2_b1 s1_d1 s2_d1 s1_s0 s1_a1 s1_c1 s2_c1 s1_q1
+step s1_b2: BEGIN;
+step s2_b1: BEGIN ISOLATION LEVEL REPEATABLE READ;
+step s1_d1: DELETE FROM t;
+step s2_d1: DROP INDEX t_ab_idx; <waiting ...>
+step s1_s0: SAVEPOINT s0;
+step s1_a1: ALTER TABLE t ADD CONSTRAINT t1_nn NOT NULL a;
+step s1_c1: COMMIT;
+step s2_d1: <... completed>
+step s2_c1: COMMIT;
+step s1_q1: SELECT conname, conrelid::regclass, contype, convalidated
+              FROM pg_constraint WHERE conname = 't1_nn';
+
+conname|conrelid|contype|convalidated
+-------+--------+-------+------------
+t1_nn  |t       |n      |t           
+(1 row)
+
diff --git a/src/test/isolation/isolation_schedule b/src/test/isolation/isolation_schedule
index 01ff1c6586f..7ce6bbcaf89 100644
--- a/src/test/isolation/isolation_schedule
+++ b/src/test/isolation/isolation_schedule
@@ -58,6 +58,7 @@ test: merge-delete
 test: merge-update
 test: merge-match-recheck
 test: merge-join
+test: indexscan-check-notnull
 test: delete-abort-savept
 test: delete-abort-savept-2
 test: aborted-keyrevoke
diff --git a/src/test/isolation/specs/indexscan-check-notnull.spec b/src/test/isolation/specs/indexscan-check-notnull.spec
new file mode 100644
index 00000000000..05b4488550c
--- /dev/null
+++ b/src/test/isolation/specs/indexscan-check-notnull.spec
@@ -0,0 +1,45 @@
+
+#
+# using indexscan to check a column not-null constraint
+# is satisfied or not.
+#
+
+setup
+{
+  CREATE TABLE t (a int, b int);
+  CREATE INDEX t_ab_idx on t(a,b);
+  INSERT INTO t values (null, 1);
+  INSERT INTO t SELECT x, x*10 FROM generate_series(1,3) g(x);
+}
+
+teardown
+{
+  DROP TABLE t;
+}
+
+session s1
+step s1_b1  { BEGIN ISOLATION LEVEL REPEATABLE READ; }
+step s1_b2  { BEGIN; }
+step s1_d1  { DELETE FROM t;}
+step s1_s0  { SAVEPOINT s0;}
+step s1_a1  { ALTER TABLE t ADD CONSTRAINT t1_nn NOT NULL a;}
+step s1_q1  { SELECT conname, conrelid::regclass, contype, convalidated
+              FROM pg_constraint WHERE conname = 't1_nn';
+            }
+step s1_r1  { ROLLBACK; }
+step s1_c1  { COMMIT; }
+
+session s2
+step s2_b1  { BEGIN ISOLATION LEVEL REPEATABLE READ; }
+step s2_b2  { BEGIN; }
+step s2_a1  { ALTER TABLE t ADD CONSTRAINT t1_nn NOT NULL a;}
+step s2_d1  { DROP INDEX t_ab_idx;}
+step s2_r1  { ROLLBACK; }
+step s2_c1  { COMMIT; }
+
+permutation s1_b1 s2_b1 s1_d1 s2_a1 s1_c1 s2_c1 s1_q1
+permutation s1_b2 s2_b1 s1_d1 s2_a1 s1_c1 s2_c1 s1_q1
+permutation s1_b1 s2_b2 s1_d1 s2_a1 s1_c1 s2_c1 s1_q1
+permutation s1_b1 s2_b1 s2_a1 s1_r1 s2_r1
+permutation s1_b1 s2_b2 s2_d1 s1_d1 s2_r1 s1_a1 s1_q1 s1_r1
+permutation s1_b2 s2_b1 s1_d1 s2_d1 s1_s0 s1_a1 s1_c1 s2_c1 s1_q1
diff --git a/src/test/modules/test_misc/meson.build b/src/test/modules/test_misc/meson.build
index 6e8db1621a7..56faf359b29 100644
--- a/src/test/modules/test_misc/meson.build
+++ b/src/test/modules/test_misc/meson.build
@@ -19,6 +19,7 @@ tests += {
       't/008_replslot_single_user.pl',
       't/009_log_temp_files.pl',
       't/010_index_concurrently_upsert.pl',
+      't/011_indexscan_validate_notnull.pl',
     ],
     # The injection points are cluster-wide, so disable installcheck
     'runningcheck': false,
diff --git a/src/test/modules/test_misc/t/011_indexscan_validate_notnull.pl b/src/test/modules/test_misc/t/011_indexscan_validate_notnull.pl
new file mode 100644
index 00000000000..a3f3cb409b6
--- /dev/null
+++ b/src/test/modules/test_misc/t/011_indexscan_validate_notnull.pl
@@ -0,0 +1,163 @@
+# Copyright (c) 2025, PostgreSQL Global Development Group
+
+# Verify that indexscan mechanism can speedup ALTER TABLE ADD NOT NULL
+
+
+use strict;
+use warnings FATAL => 'all';
+use PostgreSQL::Test::Cluster;
+use PostgreSQL::Test::Utils;
+use Test::More;
+
+# Initialize a test cluster
+my $node = PostgreSQL::Test::Cluster->new('primary');
+$node->init();
+# Turn message level up to DEBUG1 so that we get the messages we want to see
+$node->append_conf('postgresql.conf', 'client_min_messages = DEBUG1');
+$node->start;
+
+# Run a SQL command and return psql's stderr (including debug messages)
+sub run_sql_command
+{
+	my $sql = shift;
+	my $stderr;
+
+	$node->psql(
+		'postgres',
+		$sql,
+		stderr => \$stderr,
+		on_error_die => 1,
+		on_error_stop => 1);
+	return $stderr;
+}
+
+# Check whether result of run_sql_command shows that we did a verify pass
+sub is_table_verified
+{
+	my $output = shift;
+	return index($output, 'DEBUG:  verifying table') != -1;
+}
+
+# Check whether result of run_sql_command shows that we did a verify pass
+sub is_indexscan_veritify_notnull
+{
+	my $output = shift;
+	return index($output, 'DEBUG:  all new not-null constraints on relation') != -1;
+}
+
+my $output;
+
+note "test alter table SET NOT NULL using indexscan with partitioned table";
+
+run_sql_command(
+    'CREATE TABLE tp (a int, b int, c int, d int ) PARTITION BY range(a);
+     CREATE TABLE tpp1 partition of tp for values from ( 1 ) to (10);
+     CREATE TABLE tpp2 partition of tp for values from ( 10 ) to (21);
+     INSERT INTO tp select g, g + 10, g + 15, g + random(min=>1::int, max=>10::int) from generate_series(1,19) g;
+     CREATE INDEX ON tp(b); ');
+
+$output = run_sql_command('ALTER TABLE tp ALTER COLUMN b SET NOT NULL;');
+ok(is_indexscan_veritify_notnull($output),
+	'column b will use indexscan to verify not-null status, no need scan table');
+ok( $output =~
+	  m/all new not-null constraints on relation "tpp1" have been validated by using index scan/,
+	'all newly added constraints proved by indexscan');
+
+run_sql_command(
+	'ALTER TABLE tp ALTER COLUMN b DROP NOT NULL;');
+
+# use indexes on partitions to fast vertifing not-null should be ok
+$output = run_sql_command('ALTER TABLE tpp1 ALTER COLUMN b SET NOT NULL;');
+ok(is_indexscan_veritify_notnull($output), 'use indexscan to validate column b not-null will not scan table');
+ok(!is_table_verified($output), 'no table scan for pp1');
+ok( $output =~
+	  m/all new not-null constraints on relation "tpp1" have been validated by using index scan/,
+	'all newly added constraints proved by indexscan');
+
+$output = run_sql_command('ALTER TABLE tpp2 ALTER COLUMN b SET NOT NULL;');
+ok(is_indexscan_veritify_notnull($output), 'use indexscan to validate column b not-null, will not scan table');
+ok(!is_table_verified($output), 'no table scan for tpp2');
+ok( $output =~
+	  m/all new not-null constraints on relation "tpp2" have been validated by using index scan/,
+	'all newly added constraints proved by indexscan');
+
+run_sql_command(
+	'ALTER TABLE tp ALTER COLUMN b DROP NOT NULL;');
+
+# table rewrite then can not use indexscan to verify not-null constraint
+$output = run_sql_command(
+	'ALTER TABLE tp ALTER COLUMN b SET NOT NULL, ALTER COLUMN b SET DATA TYPE bigint;'
+);
+ok(!is_table_verified($output), 'no table scan for tp');
+ok(!is_indexscan_veritify_notnull($output), 'table tp will rewrite, can not use indexscan to verify not-null constraints on it');
+
+# test using indexscan with multiple not-null constraints
+run_sql_command(
+    'ALTER TABLE tp ALTER COLUMN b DROP NOT NULL;
+	 CREATE INDEX ON tp(c);
+	 CREATE INDEX ON tp(d); ');
+
+# one column can use indexscan, another can not, so can not use indexscan to verify not-null
+$output = run_sql_command(
+	'ALTER TABLE tp ALTER COLUMN a SET NOT NULL, ADD CONSTRAINT c_nn NOT NULL c');
+ok(is_table_verified($output), 'table scan for tp');
+ok(!is_indexscan_veritify_notnull($output), 'can not use indexscan to verify not-null constraints on table tp');
+
+# all columns have index on it
+# use indexscan to verify multiple not-null constraints should just fine
+$output = run_sql_command(
+	'ALTER TABLE tp ALTER COLUMN d SET NOT NULL, ADD CONSTRAINT c_nn NOT NULL c, ALTER COLUMN b SET NOT NULL;');
+ok(!is_table_verified($output), 'no table scan for tp');
+ok(is_indexscan_veritify_notnull($output),
+	'using indexscan to verify not-null constraints on column b, c, d, no need table scan');
+
+# test with non-partitioned table and other non-Btree index.
+run_sql_command(
+    'CREATE TABLE t1(f1 INT, f2 int, f3 int,f4 int, f5 int);
+     INSERT INTO t1 select g, g+1, g+2, g+3, g+4 from generate_series(1, 100) g;
+     CREATE INDEX t1_f1_f2_idx ON t1(f1,f2);
+     CREATE UNIQUE INDEX t1_f3idx ON t1(f3);
+     CREATE INDEX t1_f3f4idx ON t1(f3) include(f4);
+     CREATE INDEX hash_f5_idx ON t1 USING hash (f5 int4_ops); ');
+
+# ALTER TABLE VALIDATE CONSTRAINT can not use indexscan,
+# because it only hold ShareUpdateExclusiveLock lock.
+run_sql_command('ALTER TABLE t1 ADD CONSTRAINT nn_t1_f2 NOT NULL f2 NOT VALID;');
+
+$output = run_sql_command(
+	'ALTER TABLE t1 VALIDATE CONSTRAINT nn_t1_f2;'
+);
+ok(!is_indexscan_veritify_notnull($output), 'can not use indexscan for ALTER TABLE VALIDATE CONSTRAINT command');
+run_sql_command('ALTER TABLE t1 DROP CONSTRAINT nn_t1_f2;');
+
+$output = run_sql_command(
+	'ALTER TABLE t1 ALTER COLUMN f1 SET NOT NULL, ALTER f1 type bigint;'
+);
+ok(!is_indexscan_veritify_notnull($output), 'table t1 will rewrite, can not use indexscan to validate not-null constraints on t1');
+
+run_sql_command('ALTER TABLE t1 ALTER COLUMN f1 DROP NOT NULL;');
+run_sql_command('ALTER TABLE t1 ADD CONSTRAINT nn NOT NULL f1, ALTER f1 type bigint;');
+
+# can use indexscan mechanism to fast add multiple not-null constraints
+$output = run_sql_command(
+	'ALTER TABLE t1 ALTER COLUMN f2 SET NOT NULL, ALTER COLUMN f1 SET NOT NULL;'
+);
+ok( $output =~
+	  m/all new not-null constraints on relation "t1" have been validated by using index scan/,
+	'all not-null constraints are validated by indexscan');
+
+# using indexscan mechanism to fast add a not-null can only apply to key columns, not include column
+$output = run_sql_command(
+	'ALTER TABLE t1 ADD CONSTRAINT nnf4 NOT NULL f4;'
+);
+ok(!is_indexscan_veritify_notnull($output), 'can not use indexscan to validate not-null constraint on t1');
+
+# if index is not btree index then cannot use indexscan mechanism to fast add not-null constraint
+$output = run_sql_command(
+	'ALTER TABLE t1 ADD CONSTRAINT nn_f5 NOT NULL f5;'
+);
+ok(!is_indexscan_veritify_notnull($output), 'can not use indexscan to validate not-null constraints on t1');
+
+$node->stop('fast');
+
+done_testing();
-- 
2.47.3


--xpkr6zhfzd3fjt76--





^ permalink  raw  reply  [nested|flat] 150+ messages in thread

* [PATCH v8] using indexscan to speedup add not null constraints
@ 2025-10-20 05:29  jian he <[email protected]>
  0 siblings, 0 replies; 150+ messages in thread

From: jian he @ 2025-10-20 05:29 UTC (permalink / raw)

This patch tries to use index_beginscan() / index_getnext() / index_endscan()
mentioned in [1] to speedup adding not-null constraints to the existing table.

The main logic happens in phase3 ATRewriteTable
1. collect all not-null constraints.
2. For each not-null constraint, check whether there is a corresponding index
available for validation. If not, then can not use indexscan to verify not-null
constraints.
3. If any of the following conditions are true
  * table scan or rewrite is required,
  * table wasn't locked with `AccessExclusiveLock`
  * the NOT NULL constraint applies to a virtual generated column
 then index scan cannot be used for fast validation.
4. If all conditions are satisfied, attempt to use indexscan to verify
whether the column contains any NULL values.

concurrency concern:
ALTER TABLE SET NOT NULL will take an ACCESS EXCLUSIVE lock, so there is less
variant of racing issue can occur?  to prove accurate, I wrote some isolation
tests. see[2]

performance:
demo:
case when: %20 percent values are NULL and have been deleted from heap but they
still on the index.

drop table if exists t;
create unlogged table t(a int, b int) with (autovacuum_enabled = off, vacuum_index_cleanup=off);
insert into t select case when g % 5 = 0 then null else g end, g+1
from generate_series(1,1_000_000) g;
create index t_idx_a on t(a);
delete from t where a is null;

alter table t alter column a drop not null;
alter table t add constraint t1 not null a;

the above two statement running several times:
patch Time:: 1.084  ms
master Time: 12.045 ms

references:
[1] https://postgr.es/m/CA%2BTgmoa5NKz8iGW_9v7wz%3D-%2BzQFu%3DE4SZoaTaU1znLaEXRYp-Q%40mail.gmail.com
[2] https://postgr.es/m/900056D1-32DF-4927-8251-3E0C0DC407FD%40anarazel.de
discussion: https://postgr.es/m/CACJufxFiW=4k1is=F1J=r-Cx1RuByXQPUrWB331U47rSnGz+hw@mail.gmail.com
commitfest entry: https://commitfest.postgresql.org/patch/5444
---
 src/backend/commands/tablecmds.c              | 116 +++++++++-
 src/backend/executor/execIndexing.c           | 213 ++++++++++++++++++
 src/include/executor/executor.h               |   2 +
 .../expected/indexscan-check-notnull.out      |  97 ++++++++
 src/test/isolation/isolation_schedule         |   1 +
 .../specs/indexscan-check-notnull.spec        |  45 ++++
 src/test/modules/test_misc/meson.build        |   1 +
 .../t/011_indexscan_validate_notnull.pl       | 163 ++++++++++++++
 8 files changed, 632 insertions(+), 6 deletions(-)
 create mode 100644 src/test/isolation/expected/indexscan-check-notnull.out
 create mode 100644 src/test/isolation/specs/indexscan-check-notnull.spec
 create mode 100644 src/test/modules/test_misc/t/011_indexscan_validate_notnull.pl

diff --git a/src/backend/commands/tablecmds.c b/src/backend/commands/tablecmds.c
index f976c0e5c7e..2af06630b35 100644
--- a/src/backend/commands/tablecmds.c
+++ b/src/backend/commands/tablecmds.c
@@ -210,16 +210,19 @@ typedef struct AlteredTableInfo
 	List	   *changedStatisticsDefs;	/* string definitions of same */
 } AlteredTableInfo;
 
-/* Struct describing one new constraint to check in Phase 3 scan */
-/* Note: new not-null constraints are handled elsewhere */
+/*
+ * Struct describing one new constraint to check in Phase 3 scan. Note: new
+ * not-null constraints are handled here too.
+*/
 typedef struct NewConstraint
 {
 	char	   *name;			/* Constraint name, or NULL if none */
-	ConstrType	contype;		/* CHECK or FOREIGN */
+	ConstrType	contype;		/* CHECK or FOREIGN or NOT NULL */
 	Oid			refrelid;		/* PK rel, if FOREIGN */
 	Oid			refindid;		/* OID of PK's index, if FOREIGN */
 	bool		conwithperiod;	/* Whether the new FOREIGN KEY uses PERIOD */
 	Oid			conid;			/* OID of pg_constraint entry, if FOREIGN */
+	int			attnum;			/* NOT NULL constraint attribute number */
 	Node	   *qual;			/* Check expr or CONSTR_FOREIGN Constraint */
 	ExprState  *qualstate;		/* Execution state for CHECK expr */
 } NewConstraint;
@@ -6217,6 +6220,9 @@ ATRewriteTable(AlteredTableInfo *tab, Oid OIDNewHeap)
 				needscan = true;
 				con->qualstate = ExecPrepareExpr((Expr *) expand_generated_columns_in_expr(con->qual, oldrel, 1), estate);
 				break;
+			case CONSTR_NOTNULL:
+				/* Nothing to do here */
+				break;
 			case CONSTR_FOREIGN:
 				/* Nothing to do here */
 				break;
@@ -6270,10 +6276,69 @@ ATRewriteTable(AlteredTableInfo *tab, Oid OIDNewHeap)
 														wholeatt->attnum);
 			}
 		}
-		if (notnull_attrs || notnull_virtual_attrs)
-			needscan = true;
 	}
 
+	/*-
+	 * If we have to verify new not-null constraints and don't have any other
+	 * reason to fully scan the table, then we can use indexes to test for
+	 * absence of NULL values instead of scanning.  The following conditions
+	 * must be met:
+	 * - we're operating on a regular table
+	 * - we hold AccessExclusiveLock on the table
+	 * - no not-null constraint covers a virtual generated column,
+	 *   because no indexes can be created on them
+	 */
+	if (!needscan &&
+		newrel == NULL &&
+		tab->verify_new_notnull &&
+		notnull_virtual_attrs == NIL &&
+		oldrel->rd_rel->relkind == RELKIND_RELATION &&
+		CheckRelationLockedByMe(oldrel, AccessExclusiveLock, false))
+	{
+		List	   *notnull_attnums = NIL;
+
+		Assert(!tab->rewrite);
+
+		foreach(l, tab->constraints)
+		{
+			Form_pg_attribute attr;
+			NewConstraint *con = lfirst(l);
+
+			if (con->contype != CONSTR_NOTNULL)
+				continue;
+
+			attr = TupleDescAttr(newTupDesc, con->attnum - 1);
+
+			Assert(attr->attnotnull);
+			Assert(attr->attnum == con->attnum);
+
+			if (attr->attgenerated == ATTRIBUTE_GENERATED_VIRTUAL)
+			{
+				needscan = true;
+				break;
+			}
+
+			notnull_attnums = lappend_int(notnull_attnums, attr->attnum);
+		}
+
+		/*
+		 * Validate new NOT NULL constraints, unless we need a scan for other
+		 * reasons, because we can validate them cheaply there, and doing it
+		 * also here would be a waste of cycles.
+		 */
+		if (notnull_attnums != NIL && !needscan)
+		{
+			if (!index_check_notnull(oldrel, notnull_attnums))
+				needscan = true;
+			else
+				ereport(DEBUG1,
+						errmsg_internal("all new not-null constraints on relation \"%s\" have been validated by using index scan",
+										RelationGetRelationName(oldrel)));
+		}
+	}
+	else if (notnull_attrs || notnull_virtual_attrs)
+		needscan = true;
+
 	if (newrel || needscan)
 	{
 		ExprContext *econtext;
@@ -7949,6 +8014,7 @@ ATExecSetNotNull(List **wqueue, Relation rel, char *conName, char *colName,
 	CookedConstraint *ccon;
 	List	   *cooked;
 	bool		is_no_inherit = false;
+	AlteredTableInfo *tab = NULL;
 
 	/* Guard against stack overflow due to overly deep inheritance tree. */
 	check_stack_depth();
@@ -8073,10 +8139,32 @@ ATExecSetNotNull(List **wqueue, Relation rel, char *conName, char *colName,
 	constraint->is_no_inherit = is_no_inherit;
 	constraint->conname = conName;
 
+	tab = ATGetQueueEntry(wqueue, rel);
+
 	/* and do it */
 	cooked = AddRelationNewConstraints(rel, NIL, list_make1(constraint),
 									   false, !recursing, false, NULL);
 	ccon = linitial(cooked);
+
+	Assert(ccon->contype == CONSTR_NOTNULL);
+
+	/*
+	 * We may use indexscan to vertify not-null constraint in Phase3.  Add the
+	 * to-be-validated not-null constraint to Phase 3's queue.
+	 */
+	if (!ccon->skip_validation)
+	{
+		NewConstraint *newcon;
+
+		newcon = (NewConstraint *) palloc0(sizeof(NewConstraint));
+
+		newcon->name = ccon->name;
+		newcon->contype = ccon->contype;
+		newcon->attnum = ccon->attnum;
+
+		tab->constraints = lappend(tab->constraints, newcon);
+	}
+
 	ObjectAddressSet(address, ConstraintRelationId, ccon->conoid);
 
 	InvokeObjectPostAlterHook(RelationRelationId,
@@ -9983,13 +10071,15 @@ ATAddCheckNNConstraint(List **wqueue, AlteredTableInfo *tab, Relation rel,
 	{
 		CookedConstraint *ccon = (CookedConstraint *) lfirst(lcon);
 
-		if (!ccon->skip_validation && ccon->contype != CONSTR_NOTNULL)
+		if (!ccon->skip_validation)
 		{
 			NewConstraint *newcon;
 
 			newcon = palloc0_object(NewConstraint);
 			newcon->name = ccon->name;
 			newcon->contype = ccon->contype;
+			if (ccon->contype == CONSTR_NOTNULL)
+				newcon->attnum = ccon->attnum;
 			newcon->qual = ccon->expr;
 
 			tab->constraints = lappend(tab->constraints, newcon);
@@ -13258,6 +13348,7 @@ QueueNNConstraintValidation(List **wqueue, Relation conrel, Relation rel,
 	List	   *children = NIL;
 	AttrNumber	attnum;
 	char	   *colname;
+	NewConstraint *newcon;
 
 	con = (Form_pg_constraint) GETSTRUCT(contuple);
 	Assert(con->contype == CONSTRAINT_NOTNULL);
@@ -13321,7 +13412,20 @@ QueueNNConstraintValidation(List **wqueue, Relation conrel, Relation rel,
 	/* Set attnotnull appropriately without queueing another validation */
 	set_attnotnull(NULL, rel, attnum, true, false);
 
+	/*
+	 * Queue validation for phase 3.
+	 *
+	 * ALTER TABLE SET NOT NULL will add NOT NULL constraint to
+	 * AlteredTableInfo->constraints, for consistency, do the same here.
+	 */
+	newcon = (NewConstraint *) palloc0(sizeof(NewConstraint));
+	newcon->name = colname;
+	newcon->contype = CONSTR_NOTNULL;
+	newcon->attnum = attnum;
+
+	/* Find or create work queue entry for this table */
 	tab = ATGetQueueEntry(wqueue, rel);
+	tab->constraints = lappend(tab->constraints, newcon);
 	tab->verify_new_notnull = true;
 
 	/*
diff --git a/src/backend/executor/execIndexing.c b/src/backend/executor/execIndexing.c
index 6ae0f959592..88694ce0335 100644
--- a/src/backend/executor/execIndexing.c
+++ b/src/backend/executor/execIndexing.c
@@ -108,12 +108,15 @@
 
 #include "access/genam.h"
 #include "access/relscan.h"
+#include "access/table.h"
 #include "access/tableam.h"
 #include "access/xact.h"
 #include "catalog/index.h"
+#include "catalog/pg_am_d.h"
 #include "executor/executor.h"
 #include "nodes/nodeFuncs.h"
 #include "storage/lmgr.h"
+#include "utils/fmgroids.h"
 #include "utils/injection_point.h"
 #include "utils/multirangetypes.h"
 #include "utils/rangetypes.h"
@@ -146,6 +149,7 @@ static bool index_expression_changed_walker(Node *node,
 											Bitmapset *allUpdatedCols);
 static void ExecWithoutOverlapsNotEmpty(Relation rel, NameData attname, Datum attval,
 										char typtype, Oid atttypid);
+static bool index_check_notnull_internal(Relation relation, List *attnums, List *idxs);
 
 /* ----------------------------------------------------------------
  *		ExecOpenIndices
@@ -1178,3 +1182,212 @@ ExecWithoutOverlapsNotEmpty(Relation rel, NameData attname, Datum attval, char t
 				 errmsg("empty WITHOUT OVERLAPS value found in column \"%s\" in relation \"%s\"",
 						NameStr(attname), RelationGetRelationName(rel))));
 }
+
+/*
+ * notnull_attnums: list of attribute numbers of all new not-null constraints.
+ *
+ * First check whether the relation has a suitable index for each not-null
+ * attribute, then using indexscan mechanism to verify that *all* attributes on
+ * notnull_attnums are indeed not null.
+ *
+ * Returning true means all new not-null constraints have been verified, no
+ * need an extra scan to verify newly added not-null constraints.
+ */
+bool
+index_check_notnull(Relation relation, List *notnull_attnums)
+{
+	Relation	pg_index;
+	Relation	index_rel;
+	SysScanDesc indscan;
+	ScanKeyData skey;
+	HeapTuple	htup;
+	TupleDesc	tupdesc;
+	Form_pg_attribute attr;
+	List	   *idxs = NIL;
+	List	   *attnums = NIL;
+
+	tupdesc = RelationGetDescr(relation);
+
+	/* Prepare to scan pg_index for entries having indrelid = this rel */
+	ScanKeyInit(&skey,
+				Anum_pg_index_indrelid,
+				BTEqualStrategyNumber, F_OIDEQ,
+				ObjectIdGetDatum(RelationGetRelid(relation)));
+
+	pg_index = table_open(IndexRelationId, AccessShareLock);
+	indscan = systable_beginscan(pg_index, IndexIndrelidIndexId, true,
+								 NULL, 1, &skey);
+
+	while (HeapTupleIsValid(htup = systable_getnext(indscan)))
+	{
+		Form_pg_index index = (Form_pg_index) GETSTRUCT(htup);
+
+		/*
+		 * we can only use non-deferred, validated, and alive btree index to
+		 * validate not-null constraints
+		 */
+		if (!index->indimmediate || !index->indisvalid || !index->indislive)
+			continue;
+
+		/* can not use expression index or partial index too */
+		if (!heap_attisnull(htup, Anum_pg_index_indexprs, NULL) ||
+			!heap_attisnull(htup, Anum_pg_index_indpred, NULL))
+			continue;
+
+		index_rel = index_open(index->indexrelid, AccessShareLock);
+
+		/* can only apply to btree index */
+		if (index_rel->rd_rel->relam != BTREE_AM_OID)
+		{
+			index_close(index_rel, AccessShareLock);
+			continue;
+		}
+
+		/* collect index attnums while loop */
+		for (int i = 0; i < index->indnkeyatts; i++)
+		{
+			attr = TupleDescAttr(tupdesc, (index->indkey.values[i] - 1));
+
+			if (attr->attisdropped)
+				continue;
+
+			if (list_member_int(notnull_attnums, attr->attnum) &&
+				!list_member_int(attnums, attr->attnum))
+			{
+				attnums = lappend_int(attnums, attr->attnum);
+				idxs = lappend_oid(idxs, index->indexrelid);
+			}
+		}
+		index_close(index_rel, NoLock);
+	}
+	systable_endscan(indscan);
+	table_close(pg_index, AccessShareLock);
+
+	if (attnums == NIL)
+		return false;
+
+	/*
+	 * every not-null constraint requires an index for indexscan.  If no such
+	 * index exists, we need to use regular table scan to validate not-null
+	 * constraints.
+	 */
+	foreach_int(attno, notnull_attnums)
+	{
+		if (!list_member_int(attnums, attno))
+			return false;
+	}
+
+	return index_check_notnull_internal(relation, attnums, idxs);
+}
+
+/*
+ * Use indexscan mechanism to fast verify each attribute in "attnums" are
+ * not-null or not.
+ */
+static bool
+index_check_notnull_internal(Relation relation, List *attnums, List *idxs)
+{
+	EState	   *estate;
+	ExprContext *econtext;
+	TupleTableSlot *existing_slot;
+	bool		all_not_null = true;
+	ListCell   *lc,
+			   *lc2;
+
+	/*
+	 * Need an EState for slot to hold the current tuple.
+	 */
+	estate = CreateExecutorState();
+	econtext = GetPerTupleExprContext(estate);
+
+	forboth(lc, attnums, lc2, idxs)
+	{
+		SnapshotData DirtySnapshot;
+		IndexScanDesc index_scan;
+		ScanKeyData scankeys[INDEX_MAX_KEYS];
+		IndexInfo  *indexInfo;
+		AttrNumber	sk_attno = -1;
+		Relation	index;
+		int			indnkeyatts;
+
+		AttrNumber	attno = lfirst_int(lc);
+		Oid			indexoid = lfirst_oid(lc2);
+
+		existing_slot = table_slot_create(relation, NULL);
+
+		/* Arrange for econtext's scan tuple to be the tuple under test */
+		econtext->ecxt_scantuple = existing_slot;
+
+		index = index_open(indexoid, NoLock);
+
+		indexInfo = BuildIndexInfo(index);
+		indnkeyatts = IndexRelationGetNumberOfKeyAttributes(index);
+
+		/*
+		 * Search the tuples that are in the index for any violations,
+		 * including tuples that aren't visible yet.
+		 */
+		InitDirtySnapshot(DirtySnapshot);
+
+		for (int i = 0; i < indnkeyatts; i++)
+		{
+			if (indexInfo->ii_IndexAttrNumbers[i] == attno)
+			{
+				sk_attno = i + 1;
+				break;
+			}
+		}
+
+		if (sk_attno == -1)
+			elog(ERROR, "cache lookup failed for attribute number %d on index %u", indexoid, attno);
+
+		for (int i = 0; i < indnkeyatts; i++)
+		{
+			/* set up an IS NULL scan key so that we ignore not nulls */
+			ScanKeyEntryInitialize(&scankeys[i],
+								   SK_ISNULL | SK_SEARCHNULL,
+								   sk_attno,	/* index col to scan */
+								   InvalidStrategy, /* no strategy */
+								   InvalidOid,	/* no strategy subtype */
+								   InvalidOid,	/* no collation */
+								   InvalidOid,	/* no reg proc for this */
+								   (Datum) 0);	/* constant */
+		}
+
+		index_scan = index_beginscan(relation, index, &DirtySnapshot, NULL, indnkeyatts, 0);
+		index_rescan(index_scan, scankeys, indnkeyatts, NULL, 0);
+
+		while (index_getnext_slot(index_scan, ForwardScanDirection, existing_slot))
+		{
+			Datum		values[INDEX_MAX_KEYS];
+			bool		nulls[INDEX_MAX_KEYS];
+
+			/*
+			 * Extract the index column values and isnull flags from the
+			 * existing tuple.
+			 */
+			FormIndexDatum(indexInfo, existing_slot, estate, values, nulls);
+
+			if (nulls[sk_attno - 1])
+			{
+				all_not_null = false;
+				break;
+			}
+		}
+
+		index_endscan(index_scan);
+		index_close(index, NoLock);
+		ExecDropSingleTupleTableSlot(existing_slot);
+
+		/* exit earlier */
+		if (!all_not_null)
+		{
+			FreeExecutorState(estate);
+			return false;
+		}
+	}
+
+	FreeExecutorState(estate);
+
+	return true;
+}
diff --git a/src/include/executor/executor.h b/src/include/executor/executor.h
index 5929aabc353..7f24caeeafb 100644
--- a/src/include/executor/executor.h
+++ b/src/include/executor/executor.h
@@ -756,6 +756,8 @@ extern void check_exclusion_constraint(Relation heap, Relation index,
 									   const Datum *values, const bool *isnull,
 									   EState *estate, bool newIndex);
 
+extern bool index_check_notnull(Relation relation, List *notnull_attnums);
+
 /*
  * prototypes from functions in execReplication.c
  */
diff --git a/src/test/isolation/expected/indexscan-check-notnull.out b/src/test/isolation/expected/indexscan-check-notnull.out
new file mode 100644
index 00000000000..c6a652e2518
--- /dev/null
+++ b/src/test/isolation/expected/indexscan-check-notnull.out
@@ -0,0 +1,97 @@
+Parsed test spec with 2 sessions
+
+starting permutation: s1_b1 s2_b1 s1_d1 s2_a1 s1_c1 s2_c1 s1_q1
+step s1_b1: BEGIN ISOLATION LEVEL REPEATABLE READ;
+step s2_b1: BEGIN ISOLATION LEVEL REPEATABLE READ;
+step s1_d1: DELETE FROM t;
+step s2_a1: ALTER TABLE t ADD CONSTRAINT t1_nn NOT NULL a; <waiting ...>
+step s1_c1: COMMIT;
+step s2_a1: <... completed>
+step s2_c1: COMMIT;
+step s1_q1: SELECT conname, conrelid::regclass, contype, convalidated
+              FROM pg_constraint WHERE conname = 't1_nn';
+
+conname|conrelid|contype|convalidated
+-------+--------+-------+------------
+t1_nn  |t       |n      |t           
+(1 row)
+
+
+starting permutation: s1_b2 s2_b1 s1_d1 s2_a1 s1_c1 s2_c1 s1_q1
+step s1_b2: BEGIN;
+step s2_b1: BEGIN ISOLATION LEVEL REPEATABLE READ;
+step s1_d1: DELETE FROM t;
+step s2_a1: ALTER TABLE t ADD CONSTRAINT t1_nn NOT NULL a; <waiting ...>
+step s1_c1: COMMIT;
+step s2_a1: <... completed>
+step s2_c1: COMMIT;
+step s1_q1: SELECT conname, conrelid::regclass, contype, convalidated
+              FROM pg_constraint WHERE conname = 't1_nn';
+
+conname|conrelid|contype|convalidated
+-------+--------+-------+------------
+t1_nn  |t       |n      |t           
+(1 row)
+
+
+starting permutation: s1_b1 s2_b2 s1_d1 s2_a1 s1_c1 s2_c1 s1_q1
+step s1_b1: BEGIN ISOLATION LEVEL REPEATABLE READ;
+step s2_b2: BEGIN;
+step s1_d1: DELETE FROM t;
+step s2_a1: ALTER TABLE t ADD CONSTRAINT t1_nn NOT NULL a; <waiting ...>
+step s1_c1: COMMIT;
+step s2_a1: <... completed>
+step s2_c1: COMMIT;
+step s1_q1: SELECT conname, conrelid::regclass, contype, convalidated
+              FROM pg_constraint WHERE conname = 't1_nn';
+
+conname|conrelid|contype|convalidated
+-------+--------+-------+------------
+t1_nn  |t       |n      |t           
+(1 row)
+
+
+starting permutation: s1_b1 s2_b1 s2_a1 s1_r1 s2_r1
+step s1_b1: BEGIN ISOLATION LEVEL REPEATABLE READ;
+step s2_b1: BEGIN ISOLATION LEVEL REPEATABLE READ;
+step s2_a1: ALTER TABLE t ADD CONSTRAINT t1_nn NOT NULL a;
+ERROR:  column "a" of relation "t" contains null values
+step s1_r1: ROLLBACK;
+step s2_r1: ROLLBACK;
+
+starting permutation: s1_b1 s2_b2 s2_d1 s1_d1 s2_r1 s1_a1 s1_q1 s1_r1
+step s1_b1: BEGIN ISOLATION LEVEL REPEATABLE READ;
+step s2_b2: BEGIN;
+step s2_d1: DROP INDEX t_ab_idx;
+step s1_d1: DELETE FROM t; <waiting ...>
+step s2_r1: ROLLBACK;
+step s1_d1: <... completed>
+step s1_a1: ALTER TABLE t ADD CONSTRAINT t1_nn NOT NULL a;
+step s1_q1: SELECT conname, conrelid::regclass, contype, convalidated
+              FROM pg_constraint WHERE conname = 't1_nn';
+
+conname|conrelid|contype|convalidated
+-------+--------+-------+------------
+t1_nn  |t       |n      |t           
+(1 row)
+
+step s1_r1: ROLLBACK;
+
+starting permutation: s1_b2 s2_b1 s1_d1 s2_d1 s1_s0 s1_a1 s1_c1 s2_c1 s1_q1
+step s1_b2: BEGIN;
+step s2_b1: BEGIN ISOLATION LEVEL REPEATABLE READ;
+step s1_d1: DELETE FROM t;
+step s2_d1: DROP INDEX t_ab_idx; <waiting ...>
+step s1_s0: SAVEPOINT s0;
+step s1_a1: ALTER TABLE t ADD CONSTRAINT t1_nn NOT NULL a;
+step s1_c1: COMMIT;
+step s2_d1: <... completed>
+step s2_c1: COMMIT;
+step s1_q1: SELECT conname, conrelid::regclass, contype, convalidated
+              FROM pg_constraint WHERE conname = 't1_nn';
+
+conname|conrelid|contype|convalidated
+-------+--------+-------+------------
+t1_nn  |t       |n      |t           
+(1 row)
+
diff --git a/src/test/isolation/isolation_schedule b/src/test/isolation/isolation_schedule
index 01ff1c6586f..7ce6bbcaf89 100644
--- a/src/test/isolation/isolation_schedule
+++ b/src/test/isolation/isolation_schedule
@@ -58,6 +58,7 @@ test: merge-delete
 test: merge-update
 test: merge-match-recheck
 test: merge-join
+test: indexscan-check-notnull
 test: delete-abort-savept
 test: delete-abort-savept-2
 test: aborted-keyrevoke
diff --git a/src/test/isolation/specs/indexscan-check-notnull.spec b/src/test/isolation/specs/indexscan-check-notnull.spec
new file mode 100644
index 00000000000..05b4488550c
--- /dev/null
+++ b/src/test/isolation/specs/indexscan-check-notnull.spec
@@ -0,0 +1,45 @@
+
+#
+# using indexscan to check a column not-null constraint
+# is satisfied or not.
+#
+
+setup
+{
+  CREATE TABLE t (a int, b int);
+  CREATE INDEX t_ab_idx on t(a,b);
+  INSERT INTO t values (null, 1);
+  INSERT INTO t SELECT x, x*10 FROM generate_series(1,3) g(x);
+}
+
+teardown
+{
+  DROP TABLE t;
+}
+
+session s1
+step s1_b1  { BEGIN ISOLATION LEVEL REPEATABLE READ; }
+step s1_b2  { BEGIN; }
+step s1_d1  { DELETE FROM t;}
+step s1_s0  { SAVEPOINT s0;}
+step s1_a1  { ALTER TABLE t ADD CONSTRAINT t1_nn NOT NULL a;}
+step s1_q1  { SELECT conname, conrelid::regclass, contype, convalidated
+              FROM pg_constraint WHERE conname = 't1_nn';
+            }
+step s1_r1  { ROLLBACK; }
+step s1_c1  { COMMIT; }
+
+session s2
+step s2_b1  { BEGIN ISOLATION LEVEL REPEATABLE READ; }
+step s2_b2  { BEGIN; }
+step s2_a1  { ALTER TABLE t ADD CONSTRAINT t1_nn NOT NULL a;}
+step s2_d1  { DROP INDEX t_ab_idx;}
+step s2_r1  { ROLLBACK; }
+step s2_c1  { COMMIT; }
+
+permutation s1_b1 s2_b1 s1_d1 s2_a1 s1_c1 s2_c1 s1_q1
+permutation s1_b2 s2_b1 s1_d1 s2_a1 s1_c1 s2_c1 s1_q1
+permutation s1_b1 s2_b2 s1_d1 s2_a1 s1_c1 s2_c1 s1_q1
+permutation s1_b1 s2_b1 s2_a1 s1_r1 s2_r1
+permutation s1_b1 s2_b2 s2_d1 s1_d1 s2_r1 s1_a1 s1_q1 s1_r1
+permutation s1_b2 s2_b1 s1_d1 s2_d1 s1_s0 s1_a1 s1_c1 s2_c1 s1_q1
diff --git a/src/test/modules/test_misc/meson.build b/src/test/modules/test_misc/meson.build
index 6e8db1621a7..56faf359b29 100644
--- a/src/test/modules/test_misc/meson.build
+++ b/src/test/modules/test_misc/meson.build
@@ -19,6 +19,7 @@ tests += {
       't/008_replslot_single_user.pl',
       't/009_log_temp_files.pl',
       't/010_index_concurrently_upsert.pl',
+      't/011_indexscan_validate_notnull.pl',
     ],
     # The injection points are cluster-wide, so disable installcheck
     'runningcheck': false,
diff --git a/src/test/modules/test_misc/t/011_indexscan_validate_notnull.pl b/src/test/modules/test_misc/t/011_indexscan_validate_notnull.pl
new file mode 100644
index 00000000000..a3f3cb409b6
--- /dev/null
+++ b/src/test/modules/test_misc/t/011_indexscan_validate_notnull.pl
@@ -0,0 +1,163 @@
+# Copyright (c) 2025, PostgreSQL Global Development Group
+
+# Verify that indexscan mechanism can speedup ALTER TABLE ADD NOT NULL
+
+
+use strict;
+use warnings FATAL => 'all';
+use PostgreSQL::Test::Cluster;
+use PostgreSQL::Test::Utils;
+use Test::More;
+
+# Initialize a test cluster
+my $node = PostgreSQL::Test::Cluster->new('primary');
+$node->init();
+# Turn message level up to DEBUG1 so that we get the messages we want to see
+$node->append_conf('postgresql.conf', 'client_min_messages = DEBUG1');
+$node->start;
+
+# Run a SQL command and return psql's stderr (including debug messages)
+sub run_sql_command
+{
+	my $sql = shift;
+	my $stderr;
+
+	$node->psql(
+		'postgres',
+		$sql,
+		stderr => \$stderr,
+		on_error_die => 1,
+		on_error_stop => 1);
+	return $stderr;
+}
+
+# Check whether result of run_sql_command shows that we did a verify pass
+sub is_table_verified
+{
+	my $output = shift;
+	return index($output, 'DEBUG:  verifying table') != -1;
+}
+
+# Check whether result of run_sql_command shows that we did a verify pass
+sub is_indexscan_veritify_notnull
+{
+	my $output = shift;
+	return index($output, 'DEBUG:  all new not-null constraints on relation') != -1;
+}
+
+my $output;
+
+note "test alter table SET NOT NULL using indexscan with partitioned table";
+
+run_sql_command(
+    'CREATE TABLE tp (a int, b int, c int, d int ) PARTITION BY range(a);
+     CREATE TABLE tpp1 partition of tp for values from ( 1 ) to (10);
+     CREATE TABLE tpp2 partition of tp for values from ( 10 ) to (21);
+     INSERT INTO tp select g, g + 10, g + 15, g + random(min=>1::int, max=>10::int) from generate_series(1,19) g;
+     CREATE INDEX ON tp(b); ');
+
+$output = run_sql_command('ALTER TABLE tp ALTER COLUMN b SET NOT NULL;');
+ok(is_indexscan_veritify_notnull($output),
+	'column b will use indexscan to verify not-null status, no need scan table');
+ok( $output =~
+	  m/all new not-null constraints on relation "tpp1" have been validated by using index scan/,
+	'all newly added constraints proved by indexscan');
+
+run_sql_command(
+	'ALTER TABLE tp ALTER COLUMN b DROP NOT NULL;');
+
+# use indexes on partitions to fast vertifing not-null should be ok
+$output = run_sql_command('ALTER TABLE tpp1 ALTER COLUMN b SET NOT NULL;');
+ok(is_indexscan_veritify_notnull($output), 'use indexscan to validate column b not-null will not scan table');
+ok(!is_table_verified($output), 'no table scan for pp1');
+ok( $output =~
+	  m/all new not-null constraints on relation "tpp1" have been validated by using index scan/,
+	'all newly added constraints proved by indexscan');
+
+$output = run_sql_command('ALTER TABLE tpp2 ALTER COLUMN b SET NOT NULL;');
+ok(is_indexscan_veritify_notnull($output), 'use indexscan to validate column b not-null, will not scan table');
+ok(!is_table_verified($output), 'no table scan for tpp2');
+ok( $output =~
+	  m/all new not-null constraints on relation "tpp2" have been validated by using index scan/,
+	'all newly added constraints proved by indexscan');
+
+run_sql_command(
+	'ALTER TABLE tp ALTER COLUMN b DROP NOT NULL;');
+
+# table rewrite then can not use indexscan to verify not-null constraint
+$output = run_sql_command(
+	'ALTER TABLE tp ALTER COLUMN b SET NOT NULL, ALTER COLUMN b SET DATA TYPE bigint;'
+);
+ok(!is_table_verified($output), 'no table scan for tp');
+ok(!is_indexscan_veritify_notnull($output), 'table tp will rewrite, can not use indexscan to verify not-null constraints on it');
+
+# test using indexscan with multiple not-null constraints
+run_sql_command(
+    'ALTER TABLE tp ALTER COLUMN b DROP NOT NULL;
+	 CREATE INDEX ON tp(c);
+	 CREATE INDEX ON tp(d); ');
+
+# one column can use indexscan, another can not, so can not use indexscan to verify not-null
+$output = run_sql_command(
+	'ALTER TABLE tp ALTER COLUMN a SET NOT NULL, ADD CONSTRAINT c_nn NOT NULL c');
+ok(is_table_verified($output), 'table scan for tp');
+ok(!is_indexscan_veritify_notnull($output), 'can not use indexscan to verify not-null constraints on table tp');
+
+# all columns have index on it
+# use indexscan to verify multiple not-null constraints should just fine
+$output = run_sql_command(
+	'ALTER TABLE tp ALTER COLUMN d SET NOT NULL, ADD CONSTRAINT c_nn NOT NULL c, ALTER COLUMN b SET NOT NULL;');
+ok(!is_table_verified($output), 'no table scan for tp');
+ok(is_indexscan_veritify_notnull($output),
+	'using indexscan to verify not-null constraints on column b, c, d, no need table scan');
+
+# test with non-partitioned table and other non-Btree index.
+run_sql_command(
+    'CREATE TABLE t1(f1 INT, f2 int, f3 int,f4 int, f5 int);
+     INSERT INTO t1 select g, g+1, g+2, g+3, g+4 from generate_series(1, 100) g;
+     CREATE INDEX t1_f1_f2_idx ON t1(f1,f2);
+     CREATE UNIQUE INDEX t1_f3idx ON t1(f3);
+     CREATE INDEX t1_f3f4idx ON t1(f3) include(f4);
+     CREATE INDEX hash_f5_idx ON t1 USING hash (f5 int4_ops); ');
+
+# ALTER TABLE VALIDATE CONSTRAINT can not use indexscan,
+# because it only hold ShareUpdateExclusiveLock lock.
+run_sql_command('ALTER TABLE t1 ADD CONSTRAINT nn_t1_f2 NOT NULL f2 NOT VALID;');
+
+$output = run_sql_command(
+	'ALTER TABLE t1 VALIDATE CONSTRAINT nn_t1_f2;'
+);
+ok(!is_indexscan_veritify_notnull($output), 'can not use indexscan for ALTER TABLE VALIDATE CONSTRAINT command');
+run_sql_command('ALTER TABLE t1 DROP CONSTRAINT nn_t1_f2;');
+
+$output = run_sql_command(
+	'ALTER TABLE t1 ALTER COLUMN f1 SET NOT NULL, ALTER f1 type bigint;'
+);
+ok(!is_indexscan_veritify_notnull($output), 'table t1 will rewrite, can not use indexscan to validate not-null constraints on t1');
+
+run_sql_command('ALTER TABLE t1 ALTER COLUMN f1 DROP NOT NULL;');
+run_sql_command('ALTER TABLE t1 ADD CONSTRAINT nn NOT NULL f1, ALTER f1 type bigint;');
+
+# can use indexscan mechanism to fast add multiple not-null constraints
+$output = run_sql_command(
+	'ALTER TABLE t1 ALTER COLUMN f2 SET NOT NULL, ALTER COLUMN f1 SET NOT NULL;'
+);
+ok( $output =~
+	  m/all new not-null constraints on relation "t1" have been validated by using index scan/,
+	'all not-null constraints are validated by indexscan');
+
+# using indexscan mechanism to fast add a not-null can only apply to key columns, not include column
+$output = run_sql_command(
+	'ALTER TABLE t1 ADD CONSTRAINT nnf4 NOT NULL f4;'
+);
+ok(!is_indexscan_veritify_notnull($output), 'can not use indexscan to validate not-null constraint on t1');
+
+# if index is not btree index then cannot use indexscan mechanism to fast add not-null constraint
+$output = run_sql_command(
+	'ALTER TABLE t1 ADD CONSTRAINT nn_f5 NOT NULL f5;'
+);
+ok(!is_indexscan_veritify_notnull($output), 'can not use indexscan to validate not-null constraints on t1');
+
+$node->stop('fast');
+
+done_testing();
-- 
2.47.3


--xpkr6zhfzd3fjt76--





^ permalink  raw  reply  [nested|flat] 150+ messages in thread

* [PATCH v8] using indexscan to speedup add not null constraints
@ 2025-10-20 05:29  jian he <[email protected]>
  0 siblings, 0 replies; 150+ messages in thread

From: jian he @ 2025-10-20 05:29 UTC (permalink / raw)

This patch tries to use index_beginscan() / index_getnext() / index_endscan()
mentioned in [1] to speedup adding not-null constraints to the existing table.

The main logic happens in phase3 ATRewriteTable
1. collect all not-null constraints.
2. For each not-null constraint, check whether there is a corresponding index
available for validation. If not, then can not use indexscan to verify not-null
constraints.
3. If any of the following conditions are true
  * table scan or rewrite is required,
  * table wasn't locked with `AccessExclusiveLock`
  * the NOT NULL constraint applies to a virtual generated column
 then index scan cannot be used for fast validation.
4. If all conditions are satisfied, attempt to use indexscan to verify
whether the column contains any NULL values.

concurrency concern:
ALTER TABLE SET NOT NULL will take an ACCESS EXCLUSIVE lock, so there is less
variant of racing issue can occur?  to prove accurate, I wrote some isolation
tests. see[2]

performance:
demo:
case when: %20 percent values are NULL and have been deleted from heap but they
still on the index.

drop table if exists t;
create unlogged table t(a int, b int) with (autovacuum_enabled = off, vacuum_index_cleanup=off);
insert into t select case when g % 5 = 0 then null else g end, g+1
from generate_series(1,1_000_000) g;
create index t_idx_a on t(a);
delete from t where a is null;

alter table t alter column a drop not null;
alter table t add constraint t1 not null a;

the above two statement running several times:
patch Time:: 1.084  ms
master Time: 12.045 ms

references:
[1] https://postgr.es/m/CA%2BTgmoa5NKz8iGW_9v7wz%3D-%2BzQFu%3DE4SZoaTaU1znLaEXRYp-Q%40mail.gmail.com
[2] https://postgr.es/m/900056D1-32DF-4927-8251-3E0C0DC407FD%40anarazel.de
discussion: https://postgr.es/m/CACJufxFiW=4k1is=F1J=r-Cx1RuByXQPUrWB331U47rSnGz+hw@mail.gmail.com
commitfest entry: https://commitfest.postgresql.org/patch/5444
---
 src/backend/commands/tablecmds.c              | 116 +++++++++-
 src/backend/executor/execIndexing.c           | 213 ++++++++++++++++++
 src/include/executor/executor.h               |   2 +
 .../expected/indexscan-check-notnull.out      |  97 ++++++++
 src/test/isolation/isolation_schedule         |   1 +
 .../specs/indexscan-check-notnull.spec        |  45 ++++
 src/test/modules/test_misc/meson.build        |   1 +
 .../t/011_indexscan_validate_notnull.pl       | 163 ++++++++++++++
 8 files changed, 632 insertions(+), 6 deletions(-)
 create mode 100644 src/test/isolation/expected/indexscan-check-notnull.out
 create mode 100644 src/test/isolation/specs/indexscan-check-notnull.spec
 create mode 100644 src/test/modules/test_misc/t/011_indexscan_validate_notnull.pl

diff --git a/src/backend/commands/tablecmds.c b/src/backend/commands/tablecmds.c
index f976c0e5c7e..2af06630b35 100644
--- a/src/backend/commands/tablecmds.c
+++ b/src/backend/commands/tablecmds.c
@@ -210,16 +210,19 @@ typedef struct AlteredTableInfo
 	List	   *changedStatisticsDefs;	/* string definitions of same */
 } AlteredTableInfo;
 
-/* Struct describing one new constraint to check in Phase 3 scan */
-/* Note: new not-null constraints are handled elsewhere */
+/*
+ * Struct describing one new constraint to check in Phase 3 scan. Note: new
+ * not-null constraints are handled here too.
+*/
 typedef struct NewConstraint
 {
 	char	   *name;			/* Constraint name, or NULL if none */
-	ConstrType	contype;		/* CHECK or FOREIGN */
+	ConstrType	contype;		/* CHECK or FOREIGN or NOT NULL */
 	Oid			refrelid;		/* PK rel, if FOREIGN */
 	Oid			refindid;		/* OID of PK's index, if FOREIGN */
 	bool		conwithperiod;	/* Whether the new FOREIGN KEY uses PERIOD */
 	Oid			conid;			/* OID of pg_constraint entry, if FOREIGN */
+	int			attnum;			/* NOT NULL constraint attribute number */
 	Node	   *qual;			/* Check expr or CONSTR_FOREIGN Constraint */
 	ExprState  *qualstate;		/* Execution state for CHECK expr */
 } NewConstraint;
@@ -6217,6 +6220,9 @@ ATRewriteTable(AlteredTableInfo *tab, Oid OIDNewHeap)
 				needscan = true;
 				con->qualstate = ExecPrepareExpr((Expr *) expand_generated_columns_in_expr(con->qual, oldrel, 1), estate);
 				break;
+			case CONSTR_NOTNULL:
+				/* Nothing to do here */
+				break;
 			case CONSTR_FOREIGN:
 				/* Nothing to do here */
 				break;
@@ -6270,10 +6276,69 @@ ATRewriteTable(AlteredTableInfo *tab, Oid OIDNewHeap)
 														wholeatt->attnum);
 			}
 		}
-		if (notnull_attrs || notnull_virtual_attrs)
-			needscan = true;
 	}
 
+	/*-
+	 * If we have to verify new not-null constraints and don't have any other
+	 * reason to fully scan the table, then we can use indexes to test for
+	 * absence of NULL values instead of scanning.  The following conditions
+	 * must be met:
+	 * - we're operating on a regular table
+	 * - we hold AccessExclusiveLock on the table
+	 * - no not-null constraint covers a virtual generated column,
+	 *   because no indexes can be created on them
+	 */
+	if (!needscan &&
+		newrel == NULL &&
+		tab->verify_new_notnull &&
+		notnull_virtual_attrs == NIL &&
+		oldrel->rd_rel->relkind == RELKIND_RELATION &&
+		CheckRelationLockedByMe(oldrel, AccessExclusiveLock, false))
+	{
+		List	   *notnull_attnums = NIL;
+
+		Assert(!tab->rewrite);
+
+		foreach(l, tab->constraints)
+		{
+			Form_pg_attribute attr;
+			NewConstraint *con = lfirst(l);
+
+			if (con->contype != CONSTR_NOTNULL)
+				continue;
+
+			attr = TupleDescAttr(newTupDesc, con->attnum - 1);
+
+			Assert(attr->attnotnull);
+			Assert(attr->attnum == con->attnum);
+
+			if (attr->attgenerated == ATTRIBUTE_GENERATED_VIRTUAL)
+			{
+				needscan = true;
+				break;
+			}
+
+			notnull_attnums = lappend_int(notnull_attnums, attr->attnum);
+		}
+
+		/*
+		 * Validate new NOT NULL constraints, unless we need a scan for other
+		 * reasons, because we can validate them cheaply there, and doing it
+		 * also here would be a waste of cycles.
+		 */
+		if (notnull_attnums != NIL && !needscan)
+		{
+			if (!index_check_notnull(oldrel, notnull_attnums))
+				needscan = true;
+			else
+				ereport(DEBUG1,
+						errmsg_internal("all new not-null constraints on relation \"%s\" have been validated by using index scan",
+										RelationGetRelationName(oldrel)));
+		}
+	}
+	else if (notnull_attrs || notnull_virtual_attrs)
+		needscan = true;
+
 	if (newrel || needscan)
 	{
 		ExprContext *econtext;
@@ -7949,6 +8014,7 @@ ATExecSetNotNull(List **wqueue, Relation rel, char *conName, char *colName,
 	CookedConstraint *ccon;
 	List	   *cooked;
 	bool		is_no_inherit = false;
+	AlteredTableInfo *tab = NULL;
 
 	/* Guard against stack overflow due to overly deep inheritance tree. */
 	check_stack_depth();
@@ -8073,10 +8139,32 @@ ATExecSetNotNull(List **wqueue, Relation rel, char *conName, char *colName,
 	constraint->is_no_inherit = is_no_inherit;
 	constraint->conname = conName;
 
+	tab = ATGetQueueEntry(wqueue, rel);
+
 	/* and do it */
 	cooked = AddRelationNewConstraints(rel, NIL, list_make1(constraint),
 									   false, !recursing, false, NULL);
 	ccon = linitial(cooked);
+
+	Assert(ccon->contype == CONSTR_NOTNULL);
+
+	/*
+	 * We may use indexscan to vertify not-null constraint in Phase3.  Add the
+	 * to-be-validated not-null constraint to Phase 3's queue.
+	 */
+	if (!ccon->skip_validation)
+	{
+		NewConstraint *newcon;
+
+		newcon = (NewConstraint *) palloc0(sizeof(NewConstraint));
+
+		newcon->name = ccon->name;
+		newcon->contype = ccon->contype;
+		newcon->attnum = ccon->attnum;
+
+		tab->constraints = lappend(tab->constraints, newcon);
+	}
+
 	ObjectAddressSet(address, ConstraintRelationId, ccon->conoid);
 
 	InvokeObjectPostAlterHook(RelationRelationId,
@@ -9983,13 +10071,15 @@ ATAddCheckNNConstraint(List **wqueue, AlteredTableInfo *tab, Relation rel,
 	{
 		CookedConstraint *ccon = (CookedConstraint *) lfirst(lcon);
 
-		if (!ccon->skip_validation && ccon->contype != CONSTR_NOTNULL)
+		if (!ccon->skip_validation)
 		{
 			NewConstraint *newcon;
 
 			newcon = palloc0_object(NewConstraint);
 			newcon->name = ccon->name;
 			newcon->contype = ccon->contype;
+			if (ccon->contype == CONSTR_NOTNULL)
+				newcon->attnum = ccon->attnum;
 			newcon->qual = ccon->expr;
 
 			tab->constraints = lappend(tab->constraints, newcon);
@@ -13258,6 +13348,7 @@ QueueNNConstraintValidation(List **wqueue, Relation conrel, Relation rel,
 	List	   *children = NIL;
 	AttrNumber	attnum;
 	char	   *colname;
+	NewConstraint *newcon;
 
 	con = (Form_pg_constraint) GETSTRUCT(contuple);
 	Assert(con->contype == CONSTRAINT_NOTNULL);
@@ -13321,7 +13412,20 @@ QueueNNConstraintValidation(List **wqueue, Relation conrel, Relation rel,
 	/* Set attnotnull appropriately without queueing another validation */
 	set_attnotnull(NULL, rel, attnum, true, false);
 
+	/*
+	 * Queue validation for phase 3.
+	 *
+	 * ALTER TABLE SET NOT NULL will add NOT NULL constraint to
+	 * AlteredTableInfo->constraints, for consistency, do the same here.
+	 */
+	newcon = (NewConstraint *) palloc0(sizeof(NewConstraint));
+	newcon->name = colname;
+	newcon->contype = CONSTR_NOTNULL;
+	newcon->attnum = attnum;
+
+	/* Find or create work queue entry for this table */
 	tab = ATGetQueueEntry(wqueue, rel);
+	tab->constraints = lappend(tab->constraints, newcon);
 	tab->verify_new_notnull = true;
 
 	/*
diff --git a/src/backend/executor/execIndexing.c b/src/backend/executor/execIndexing.c
index 6ae0f959592..88694ce0335 100644
--- a/src/backend/executor/execIndexing.c
+++ b/src/backend/executor/execIndexing.c
@@ -108,12 +108,15 @@
 
 #include "access/genam.h"
 #include "access/relscan.h"
+#include "access/table.h"
 #include "access/tableam.h"
 #include "access/xact.h"
 #include "catalog/index.h"
+#include "catalog/pg_am_d.h"
 #include "executor/executor.h"
 #include "nodes/nodeFuncs.h"
 #include "storage/lmgr.h"
+#include "utils/fmgroids.h"
 #include "utils/injection_point.h"
 #include "utils/multirangetypes.h"
 #include "utils/rangetypes.h"
@@ -146,6 +149,7 @@ static bool index_expression_changed_walker(Node *node,
 											Bitmapset *allUpdatedCols);
 static void ExecWithoutOverlapsNotEmpty(Relation rel, NameData attname, Datum attval,
 										char typtype, Oid atttypid);
+static bool index_check_notnull_internal(Relation relation, List *attnums, List *idxs);
 
 /* ----------------------------------------------------------------
  *		ExecOpenIndices
@@ -1178,3 +1182,212 @@ ExecWithoutOverlapsNotEmpty(Relation rel, NameData attname, Datum attval, char t
 				 errmsg("empty WITHOUT OVERLAPS value found in column \"%s\" in relation \"%s\"",
 						NameStr(attname), RelationGetRelationName(rel))));
 }
+
+/*
+ * notnull_attnums: list of attribute numbers of all new not-null constraints.
+ *
+ * First check whether the relation has a suitable index for each not-null
+ * attribute, then using indexscan mechanism to verify that *all* attributes on
+ * notnull_attnums are indeed not null.
+ *
+ * Returning true means all new not-null constraints have been verified, no
+ * need an extra scan to verify newly added not-null constraints.
+ */
+bool
+index_check_notnull(Relation relation, List *notnull_attnums)
+{
+	Relation	pg_index;
+	Relation	index_rel;
+	SysScanDesc indscan;
+	ScanKeyData skey;
+	HeapTuple	htup;
+	TupleDesc	tupdesc;
+	Form_pg_attribute attr;
+	List	   *idxs = NIL;
+	List	   *attnums = NIL;
+
+	tupdesc = RelationGetDescr(relation);
+
+	/* Prepare to scan pg_index for entries having indrelid = this rel */
+	ScanKeyInit(&skey,
+				Anum_pg_index_indrelid,
+				BTEqualStrategyNumber, F_OIDEQ,
+				ObjectIdGetDatum(RelationGetRelid(relation)));
+
+	pg_index = table_open(IndexRelationId, AccessShareLock);
+	indscan = systable_beginscan(pg_index, IndexIndrelidIndexId, true,
+								 NULL, 1, &skey);
+
+	while (HeapTupleIsValid(htup = systable_getnext(indscan)))
+	{
+		Form_pg_index index = (Form_pg_index) GETSTRUCT(htup);
+
+		/*
+		 * we can only use non-deferred, validated, and alive btree index to
+		 * validate not-null constraints
+		 */
+		if (!index->indimmediate || !index->indisvalid || !index->indislive)
+			continue;
+
+		/* can not use expression index or partial index too */
+		if (!heap_attisnull(htup, Anum_pg_index_indexprs, NULL) ||
+			!heap_attisnull(htup, Anum_pg_index_indpred, NULL))
+			continue;
+
+		index_rel = index_open(index->indexrelid, AccessShareLock);
+
+		/* can only apply to btree index */
+		if (index_rel->rd_rel->relam != BTREE_AM_OID)
+		{
+			index_close(index_rel, AccessShareLock);
+			continue;
+		}
+
+		/* collect index attnums while loop */
+		for (int i = 0; i < index->indnkeyatts; i++)
+		{
+			attr = TupleDescAttr(tupdesc, (index->indkey.values[i] - 1));
+
+			if (attr->attisdropped)
+				continue;
+
+			if (list_member_int(notnull_attnums, attr->attnum) &&
+				!list_member_int(attnums, attr->attnum))
+			{
+				attnums = lappend_int(attnums, attr->attnum);
+				idxs = lappend_oid(idxs, index->indexrelid);
+			}
+		}
+		index_close(index_rel, NoLock);
+	}
+	systable_endscan(indscan);
+	table_close(pg_index, AccessShareLock);
+
+	if (attnums == NIL)
+		return false;
+
+	/*
+	 * every not-null constraint requires an index for indexscan.  If no such
+	 * index exists, we need to use regular table scan to validate not-null
+	 * constraints.
+	 */
+	foreach_int(attno, notnull_attnums)
+	{
+		if (!list_member_int(attnums, attno))
+			return false;
+	}
+
+	return index_check_notnull_internal(relation, attnums, idxs);
+}
+
+/*
+ * Use indexscan mechanism to fast verify each attribute in "attnums" are
+ * not-null or not.
+ */
+static bool
+index_check_notnull_internal(Relation relation, List *attnums, List *idxs)
+{
+	EState	   *estate;
+	ExprContext *econtext;
+	TupleTableSlot *existing_slot;
+	bool		all_not_null = true;
+	ListCell   *lc,
+			   *lc2;
+
+	/*
+	 * Need an EState for slot to hold the current tuple.
+	 */
+	estate = CreateExecutorState();
+	econtext = GetPerTupleExprContext(estate);
+
+	forboth(lc, attnums, lc2, idxs)
+	{
+		SnapshotData DirtySnapshot;
+		IndexScanDesc index_scan;
+		ScanKeyData scankeys[INDEX_MAX_KEYS];
+		IndexInfo  *indexInfo;
+		AttrNumber	sk_attno = -1;
+		Relation	index;
+		int			indnkeyatts;
+
+		AttrNumber	attno = lfirst_int(lc);
+		Oid			indexoid = lfirst_oid(lc2);
+
+		existing_slot = table_slot_create(relation, NULL);
+
+		/* Arrange for econtext's scan tuple to be the tuple under test */
+		econtext->ecxt_scantuple = existing_slot;
+
+		index = index_open(indexoid, NoLock);
+
+		indexInfo = BuildIndexInfo(index);
+		indnkeyatts = IndexRelationGetNumberOfKeyAttributes(index);
+
+		/*
+		 * Search the tuples that are in the index for any violations,
+		 * including tuples that aren't visible yet.
+		 */
+		InitDirtySnapshot(DirtySnapshot);
+
+		for (int i = 0; i < indnkeyatts; i++)
+		{
+			if (indexInfo->ii_IndexAttrNumbers[i] == attno)
+			{
+				sk_attno = i + 1;
+				break;
+			}
+		}
+
+		if (sk_attno == -1)
+			elog(ERROR, "cache lookup failed for attribute number %d on index %u", indexoid, attno);
+
+		for (int i = 0; i < indnkeyatts; i++)
+		{
+			/* set up an IS NULL scan key so that we ignore not nulls */
+			ScanKeyEntryInitialize(&scankeys[i],
+								   SK_ISNULL | SK_SEARCHNULL,
+								   sk_attno,	/* index col to scan */
+								   InvalidStrategy, /* no strategy */
+								   InvalidOid,	/* no strategy subtype */
+								   InvalidOid,	/* no collation */
+								   InvalidOid,	/* no reg proc for this */
+								   (Datum) 0);	/* constant */
+		}
+
+		index_scan = index_beginscan(relation, index, &DirtySnapshot, NULL, indnkeyatts, 0);
+		index_rescan(index_scan, scankeys, indnkeyatts, NULL, 0);
+
+		while (index_getnext_slot(index_scan, ForwardScanDirection, existing_slot))
+		{
+			Datum		values[INDEX_MAX_KEYS];
+			bool		nulls[INDEX_MAX_KEYS];
+
+			/*
+			 * Extract the index column values and isnull flags from the
+			 * existing tuple.
+			 */
+			FormIndexDatum(indexInfo, existing_slot, estate, values, nulls);
+
+			if (nulls[sk_attno - 1])
+			{
+				all_not_null = false;
+				break;
+			}
+		}
+
+		index_endscan(index_scan);
+		index_close(index, NoLock);
+		ExecDropSingleTupleTableSlot(existing_slot);
+
+		/* exit earlier */
+		if (!all_not_null)
+		{
+			FreeExecutorState(estate);
+			return false;
+		}
+	}
+
+	FreeExecutorState(estate);
+
+	return true;
+}
diff --git a/src/include/executor/executor.h b/src/include/executor/executor.h
index 5929aabc353..7f24caeeafb 100644
--- a/src/include/executor/executor.h
+++ b/src/include/executor/executor.h
@@ -756,6 +756,8 @@ extern void check_exclusion_constraint(Relation heap, Relation index,
 									   const Datum *values, const bool *isnull,
 									   EState *estate, bool newIndex);
 
+extern bool index_check_notnull(Relation relation, List *notnull_attnums);
+
 /*
  * prototypes from functions in execReplication.c
  */
diff --git a/src/test/isolation/expected/indexscan-check-notnull.out b/src/test/isolation/expected/indexscan-check-notnull.out
new file mode 100644
index 00000000000..c6a652e2518
--- /dev/null
+++ b/src/test/isolation/expected/indexscan-check-notnull.out
@@ -0,0 +1,97 @@
+Parsed test spec with 2 sessions
+
+starting permutation: s1_b1 s2_b1 s1_d1 s2_a1 s1_c1 s2_c1 s1_q1
+step s1_b1: BEGIN ISOLATION LEVEL REPEATABLE READ;
+step s2_b1: BEGIN ISOLATION LEVEL REPEATABLE READ;
+step s1_d1: DELETE FROM t;
+step s2_a1: ALTER TABLE t ADD CONSTRAINT t1_nn NOT NULL a; <waiting ...>
+step s1_c1: COMMIT;
+step s2_a1: <... completed>
+step s2_c1: COMMIT;
+step s1_q1: SELECT conname, conrelid::regclass, contype, convalidated
+              FROM pg_constraint WHERE conname = 't1_nn';
+
+conname|conrelid|contype|convalidated
+-------+--------+-------+------------
+t1_nn  |t       |n      |t           
+(1 row)
+
+
+starting permutation: s1_b2 s2_b1 s1_d1 s2_a1 s1_c1 s2_c1 s1_q1
+step s1_b2: BEGIN;
+step s2_b1: BEGIN ISOLATION LEVEL REPEATABLE READ;
+step s1_d1: DELETE FROM t;
+step s2_a1: ALTER TABLE t ADD CONSTRAINT t1_nn NOT NULL a; <waiting ...>
+step s1_c1: COMMIT;
+step s2_a1: <... completed>
+step s2_c1: COMMIT;
+step s1_q1: SELECT conname, conrelid::regclass, contype, convalidated
+              FROM pg_constraint WHERE conname = 't1_nn';
+
+conname|conrelid|contype|convalidated
+-------+--------+-------+------------
+t1_nn  |t       |n      |t           
+(1 row)
+
+
+starting permutation: s1_b1 s2_b2 s1_d1 s2_a1 s1_c1 s2_c1 s1_q1
+step s1_b1: BEGIN ISOLATION LEVEL REPEATABLE READ;
+step s2_b2: BEGIN;
+step s1_d1: DELETE FROM t;
+step s2_a1: ALTER TABLE t ADD CONSTRAINT t1_nn NOT NULL a; <waiting ...>
+step s1_c1: COMMIT;
+step s2_a1: <... completed>
+step s2_c1: COMMIT;
+step s1_q1: SELECT conname, conrelid::regclass, contype, convalidated
+              FROM pg_constraint WHERE conname = 't1_nn';
+
+conname|conrelid|contype|convalidated
+-------+--------+-------+------------
+t1_nn  |t       |n      |t           
+(1 row)
+
+
+starting permutation: s1_b1 s2_b1 s2_a1 s1_r1 s2_r1
+step s1_b1: BEGIN ISOLATION LEVEL REPEATABLE READ;
+step s2_b1: BEGIN ISOLATION LEVEL REPEATABLE READ;
+step s2_a1: ALTER TABLE t ADD CONSTRAINT t1_nn NOT NULL a;
+ERROR:  column "a" of relation "t" contains null values
+step s1_r1: ROLLBACK;
+step s2_r1: ROLLBACK;
+
+starting permutation: s1_b1 s2_b2 s2_d1 s1_d1 s2_r1 s1_a1 s1_q1 s1_r1
+step s1_b1: BEGIN ISOLATION LEVEL REPEATABLE READ;
+step s2_b2: BEGIN;
+step s2_d1: DROP INDEX t_ab_idx;
+step s1_d1: DELETE FROM t; <waiting ...>
+step s2_r1: ROLLBACK;
+step s1_d1: <... completed>
+step s1_a1: ALTER TABLE t ADD CONSTRAINT t1_nn NOT NULL a;
+step s1_q1: SELECT conname, conrelid::regclass, contype, convalidated
+              FROM pg_constraint WHERE conname = 't1_nn';
+
+conname|conrelid|contype|convalidated
+-------+--------+-------+------------
+t1_nn  |t       |n      |t           
+(1 row)
+
+step s1_r1: ROLLBACK;
+
+starting permutation: s1_b2 s2_b1 s1_d1 s2_d1 s1_s0 s1_a1 s1_c1 s2_c1 s1_q1
+step s1_b2: BEGIN;
+step s2_b1: BEGIN ISOLATION LEVEL REPEATABLE READ;
+step s1_d1: DELETE FROM t;
+step s2_d1: DROP INDEX t_ab_idx; <waiting ...>
+step s1_s0: SAVEPOINT s0;
+step s1_a1: ALTER TABLE t ADD CONSTRAINT t1_nn NOT NULL a;
+step s1_c1: COMMIT;
+step s2_d1: <... completed>
+step s2_c1: COMMIT;
+step s1_q1: SELECT conname, conrelid::regclass, contype, convalidated
+              FROM pg_constraint WHERE conname = 't1_nn';
+
+conname|conrelid|contype|convalidated
+-------+--------+-------+------------
+t1_nn  |t       |n      |t           
+(1 row)
+
diff --git a/src/test/isolation/isolation_schedule b/src/test/isolation/isolation_schedule
index 01ff1c6586f..7ce6bbcaf89 100644
--- a/src/test/isolation/isolation_schedule
+++ b/src/test/isolation/isolation_schedule
@@ -58,6 +58,7 @@ test: merge-delete
 test: merge-update
 test: merge-match-recheck
 test: merge-join
+test: indexscan-check-notnull
 test: delete-abort-savept
 test: delete-abort-savept-2
 test: aborted-keyrevoke
diff --git a/src/test/isolation/specs/indexscan-check-notnull.spec b/src/test/isolation/specs/indexscan-check-notnull.spec
new file mode 100644
index 00000000000..05b4488550c
--- /dev/null
+++ b/src/test/isolation/specs/indexscan-check-notnull.spec
@@ -0,0 +1,45 @@
+
+#
+# using indexscan to check a column not-null constraint
+# is satisfied or not.
+#
+
+setup
+{
+  CREATE TABLE t (a int, b int);
+  CREATE INDEX t_ab_idx on t(a,b);
+  INSERT INTO t values (null, 1);
+  INSERT INTO t SELECT x, x*10 FROM generate_series(1,3) g(x);
+}
+
+teardown
+{
+  DROP TABLE t;
+}
+
+session s1
+step s1_b1  { BEGIN ISOLATION LEVEL REPEATABLE READ; }
+step s1_b2  { BEGIN; }
+step s1_d1  { DELETE FROM t;}
+step s1_s0  { SAVEPOINT s0;}
+step s1_a1  { ALTER TABLE t ADD CONSTRAINT t1_nn NOT NULL a;}
+step s1_q1  { SELECT conname, conrelid::regclass, contype, convalidated
+              FROM pg_constraint WHERE conname = 't1_nn';
+            }
+step s1_r1  { ROLLBACK; }
+step s1_c1  { COMMIT; }
+
+session s2
+step s2_b1  { BEGIN ISOLATION LEVEL REPEATABLE READ; }
+step s2_b2  { BEGIN; }
+step s2_a1  { ALTER TABLE t ADD CONSTRAINT t1_nn NOT NULL a;}
+step s2_d1  { DROP INDEX t_ab_idx;}
+step s2_r1  { ROLLBACK; }
+step s2_c1  { COMMIT; }
+
+permutation s1_b1 s2_b1 s1_d1 s2_a1 s1_c1 s2_c1 s1_q1
+permutation s1_b2 s2_b1 s1_d1 s2_a1 s1_c1 s2_c1 s1_q1
+permutation s1_b1 s2_b2 s1_d1 s2_a1 s1_c1 s2_c1 s1_q1
+permutation s1_b1 s2_b1 s2_a1 s1_r1 s2_r1
+permutation s1_b1 s2_b2 s2_d1 s1_d1 s2_r1 s1_a1 s1_q1 s1_r1
+permutation s1_b2 s2_b1 s1_d1 s2_d1 s1_s0 s1_a1 s1_c1 s2_c1 s1_q1
diff --git a/src/test/modules/test_misc/meson.build b/src/test/modules/test_misc/meson.build
index 6e8db1621a7..56faf359b29 100644
--- a/src/test/modules/test_misc/meson.build
+++ b/src/test/modules/test_misc/meson.build
@@ -19,6 +19,7 @@ tests += {
       't/008_replslot_single_user.pl',
       't/009_log_temp_files.pl',
       't/010_index_concurrently_upsert.pl',
+      't/011_indexscan_validate_notnull.pl',
     ],
     # The injection points are cluster-wide, so disable installcheck
     'runningcheck': false,
diff --git a/src/test/modules/test_misc/t/011_indexscan_validate_notnull.pl b/src/test/modules/test_misc/t/011_indexscan_validate_notnull.pl
new file mode 100644
index 00000000000..a3f3cb409b6
--- /dev/null
+++ b/src/test/modules/test_misc/t/011_indexscan_validate_notnull.pl
@@ -0,0 +1,163 @@
+# Copyright (c) 2025, PostgreSQL Global Development Group
+
+# Verify that indexscan mechanism can speedup ALTER TABLE ADD NOT NULL
+
+
+use strict;
+use warnings FATAL => 'all';
+use PostgreSQL::Test::Cluster;
+use PostgreSQL::Test::Utils;
+use Test::More;
+
+# Initialize a test cluster
+my $node = PostgreSQL::Test::Cluster->new('primary');
+$node->init();
+# Turn message level up to DEBUG1 so that we get the messages we want to see
+$node->append_conf('postgresql.conf', 'client_min_messages = DEBUG1');
+$node->start;
+
+# Run a SQL command and return psql's stderr (including debug messages)
+sub run_sql_command
+{
+	my $sql = shift;
+	my $stderr;
+
+	$node->psql(
+		'postgres',
+		$sql,
+		stderr => \$stderr,
+		on_error_die => 1,
+		on_error_stop => 1);
+	return $stderr;
+}
+
+# Check whether result of run_sql_command shows that we did a verify pass
+sub is_table_verified
+{
+	my $output = shift;
+	return index($output, 'DEBUG:  verifying table') != -1;
+}
+
+# Check whether result of run_sql_command shows that we did a verify pass
+sub is_indexscan_veritify_notnull
+{
+	my $output = shift;
+	return index($output, 'DEBUG:  all new not-null constraints on relation') != -1;
+}
+
+my $output;
+
+note "test alter table SET NOT NULL using indexscan with partitioned table";
+
+run_sql_command(
+    'CREATE TABLE tp (a int, b int, c int, d int ) PARTITION BY range(a);
+     CREATE TABLE tpp1 partition of tp for values from ( 1 ) to (10);
+     CREATE TABLE tpp2 partition of tp for values from ( 10 ) to (21);
+     INSERT INTO tp select g, g + 10, g + 15, g + random(min=>1::int, max=>10::int) from generate_series(1,19) g;
+     CREATE INDEX ON tp(b); ');
+
+$output = run_sql_command('ALTER TABLE tp ALTER COLUMN b SET NOT NULL;');
+ok(is_indexscan_veritify_notnull($output),
+	'column b will use indexscan to verify not-null status, no need scan table');
+ok( $output =~
+	  m/all new not-null constraints on relation "tpp1" have been validated by using index scan/,
+	'all newly added constraints proved by indexscan');
+
+run_sql_command(
+	'ALTER TABLE tp ALTER COLUMN b DROP NOT NULL;');
+
+# use indexes on partitions to fast vertifing not-null should be ok
+$output = run_sql_command('ALTER TABLE tpp1 ALTER COLUMN b SET NOT NULL;');
+ok(is_indexscan_veritify_notnull($output), 'use indexscan to validate column b not-null will not scan table');
+ok(!is_table_verified($output), 'no table scan for pp1');
+ok( $output =~
+	  m/all new not-null constraints on relation "tpp1" have been validated by using index scan/,
+	'all newly added constraints proved by indexscan');
+
+$output = run_sql_command('ALTER TABLE tpp2 ALTER COLUMN b SET NOT NULL;');
+ok(is_indexscan_veritify_notnull($output), 'use indexscan to validate column b not-null, will not scan table');
+ok(!is_table_verified($output), 'no table scan for tpp2');
+ok( $output =~
+	  m/all new not-null constraints on relation "tpp2" have been validated by using index scan/,
+	'all newly added constraints proved by indexscan');
+
+run_sql_command(
+	'ALTER TABLE tp ALTER COLUMN b DROP NOT NULL;');
+
+# table rewrite then can not use indexscan to verify not-null constraint
+$output = run_sql_command(
+	'ALTER TABLE tp ALTER COLUMN b SET NOT NULL, ALTER COLUMN b SET DATA TYPE bigint;'
+);
+ok(!is_table_verified($output), 'no table scan for tp');
+ok(!is_indexscan_veritify_notnull($output), 'table tp will rewrite, can not use indexscan to verify not-null constraints on it');
+
+# test using indexscan with multiple not-null constraints
+run_sql_command(
+    'ALTER TABLE tp ALTER COLUMN b DROP NOT NULL;
+	 CREATE INDEX ON tp(c);
+	 CREATE INDEX ON tp(d); ');
+
+# one column can use indexscan, another can not, so can not use indexscan to verify not-null
+$output = run_sql_command(
+	'ALTER TABLE tp ALTER COLUMN a SET NOT NULL, ADD CONSTRAINT c_nn NOT NULL c');
+ok(is_table_verified($output), 'table scan for tp');
+ok(!is_indexscan_veritify_notnull($output), 'can not use indexscan to verify not-null constraints on table tp');
+
+# all columns have index on it
+# use indexscan to verify multiple not-null constraints should just fine
+$output = run_sql_command(
+	'ALTER TABLE tp ALTER COLUMN d SET NOT NULL, ADD CONSTRAINT c_nn NOT NULL c, ALTER COLUMN b SET NOT NULL;');
+ok(!is_table_verified($output), 'no table scan for tp');
+ok(is_indexscan_veritify_notnull($output),
+	'using indexscan to verify not-null constraints on column b, c, d, no need table scan');
+
+# test with non-partitioned table and other non-Btree index.
+run_sql_command(
+    'CREATE TABLE t1(f1 INT, f2 int, f3 int,f4 int, f5 int);
+     INSERT INTO t1 select g, g+1, g+2, g+3, g+4 from generate_series(1, 100) g;
+     CREATE INDEX t1_f1_f2_idx ON t1(f1,f2);
+     CREATE UNIQUE INDEX t1_f3idx ON t1(f3);
+     CREATE INDEX t1_f3f4idx ON t1(f3) include(f4);
+     CREATE INDEX hash_f5_idx ON t1 USING hash (f5 int4_ops); ');
+
+# ALTER TABLE VALIDATE CONSTRAINT can not use indexscan,
+# because it only hold ShareUpdateExclusiveLock lock.
+run_sql_command('ALTER TABLE t1 ADD CONSTRAINT nn_t1_f2 NOT NULL f2 NOT VALID;');
+
+$output = run_sql_command(
+	'ALTER TABLE t1 VALIDATE CONSTRAINT nn_t1_f2;'
+);
+ok(!is_indexscan_veritify_notnull($output), 'can not use indexscan for ALTER TABLE VALIDATE CONSTRAINT command');
+run_sql_command('ALTER TABLE t1 DROP CONSTRAINT nn_t1_f2;');
+
+$output = run_sql_command(
+	'ALTER TABLE t1 ALTER COLUMN f1 SET NOT NULL, ALTER f1 type bigint;'
+);
+ok(!is_indexscan_veritify_notnull($output), 'table t1 will rewrite, can not use indexscan to validate not-null constraints on t1');
+
+run_sql_command('ALTER TABLE t1 ALTER COLUMN f1 DROP NOT NULL;');
+run_sql_command('ALTER TABLE t1 ADD CONSTRAINT nn NOT NULL f1, ALTER f1 type bigint;');
+
+# can use indexscan mechanism to fast add multiple not-null constraints
+$output = run_sql_command(
+	'ALTER TABLE t1 ALTER COLUMN f2 SET NOT NULL, ALTER COLUMN f1 SET NOT NULL;'
+);
+ok( $output =~
+	  m/all new not-null constraints on relation "t1" have been validated by using index scan/,
+	'all not-null constraints are validated by indexscan');
+
+# using indexscan mechanism to fast add a not-null can only apply to key columns, not include column
+$output = run_sql_command(
+	'ALTER TABLE t1 ADD CONSTRAINT nnf4 NOT NULL f4;'
+);
+ok(!is_indexscan_veritify_notnull($output), 'can not use indexscan to validate not-null constraint on t1');
+
+# if index is not btree index then cannot use indexscan mechanism to fast add not-null constraint
+$output = run_sql_command(
+	'ALTER TABLE t1 ADD CONSTRAINT nn_f5 NOT NULL f5;'
+);
+ok(!is_indexscan_veritify_notnull($output), 'can not use indexscan to validate not-null constraints on t1');
+
+$node->stop('fast');
+
+done_testing();
-- 
2.47.3


--xpkr6zhfzd3fjt76--





^ permalink  raw  reply  [nested|flat] 150+ messages in thread

* [PATCH v8] using indexscan to speedup add not null constraints
@ 2025-10-20 05:29  jian he <[email protected]>
  0 siblings, 0 replies; 150+ messages in thread

From: jian he @ 2025-10-20 05:29 UTC (permalink / raw)

This patch tries to use index_beginscan() / index_getnext() / index_endscan()
mentioned in [1] to speedup adding not-null constraints to the existing table.

The main logic happens in phase3 ATRewriteTable
1. collect all not-null constraints.
2. For each not-null constraint, check whether there is a corresponding index
available for validation. If not, then can not use indexscan to verify not-null
constraints.
3. If any of the following conditions are true
  * table scan or rewrite is required,
  * table wasn't locked with `AccessExclusiveLock`
  * the NOT NULL constraint applies to a virtual generated column
 then index scan cannot be used for fast validation.
4. If all conditions are satisfied, attempt to use indexscan to verify
whether the column contains any NULL values.

concurrency concern:
ALTER TABLE SET NOT NULL will take an ACCESS EXCLUSIVE lock, so there is less
variant of racing issue can occur?  to prove accurate, I wrote some isolation
tests. see[2]

performance:
demo:
case when: %20 percent values are NULL and have been deleted from heap but they
still on the index.

drop table if exists t;
create unlogged table t(a int, b int) with (autovacuum_enabled = off, vacuum_index_cleanup=off);
insert into t select case when g % 5 = 0 then null else g end, g+1
from generate_series(1,1_000_000) g;
create index t_idx_a on t(a);
delete from t where a is null;

alter table t alter column a drop not null;
alter table t add constraint t1 not null a;

the above two statement running several times:
patch Time:: 1.084  ms
master Time: 12.045 ms

references:
[1] https://postgr.es/m/CA%2BTgmoa5NKz8iGW_9v7wz%3D-%2BzQFu%3DE4SZoaTaU1znLaEXRYp-Q%40mail.gmail.com
[2] https://postgr.es/m/900056D1-32DF-4927-8251-3E0C0DC407FD%40anarazel.de
discussion: https://postgr.es/m/CACJufxFiW=4k1is=F1J=r-Cx1RuByXQPUrWB331U47rSnGz+hw@mail.gmail.com
commitfest entry: https://commitfest.postgresql.org/patch/5444
---
 src/backend/commands/tablecmds.c              | 116 +++++++++-
 src/backend/executor/execIndexing.c           | 213 ++++++++++++++++++
 src/include/executor/executor.h               |   2 +
 .../expected/indexscan-check-notnull.out      |  97 ++++++++
 src/test/isolation/isolation_schedule         |   1 +
 .../specs/indexscan-check-notnull.spec        |  45 ++++
 src/test/modules/test_misc/meson.build        |   1 +
 .../t/011_indexscan_validate_notnull.pl       | 163 ++++++++++++++
 8 files changed, 632 insertions(+), 6 deletions(-)
 create mode 100644 src/test/isolation/expected/indexscan-check-notnull.out
 create mode 100644 src/test/isolation/specs/indexscan-check-notnull.spec
 create mode 100644 src/test/modules/test_misc/t/011_indexscan_validate_notnull.pl

diff --git a/src/backend/commands/tablecmds.c b/src/backend/commands/tablecmds.c
index f976c0e5c7e..2af06630b35 100644
--- a/src/backend/commands/tablecmds.c
+++ b/src/backend/commands/tablecmds.c
@@ -210,16 +210,19 @@ typedef struct AlteredTableInfo
 	List	   *changedStatisticsDefs;	/* string definitions of same */
 } AlteredTableInfo;
 
-/* Struct describing one new constraint to check in Phase 3 scan */
-/* Note: new not-null constraints are handled elsewhere */
+/*
+ * Struct describing one new constraint to check in Phase 3 scan. Note: new
+ * not-null constraints are handled here too.
+*/
 typedef struct NewConstraint
 {
 	char	   *name;			/* Constraint name, or NULL if none */
-	ConstrType	contype;		/* CHECK or FOREIGN */
+	ConstrType	contype;		/* CHECK or FOREIGN or NOT NULL */
 	Oid			refrelid;		/* PK rel, if FOREIGN */
 	Oid			refindid;		/* OID of PK's index, if FOREIGN */
 	bool		conwithperiod;	/* Whether the new FOREIGN KEY uses PERIOD */
 	Oid			conid;			/* OID of pg_constraint entry, if FOREIGN */
+	int			attnum;			/* NOT NULL constraint attribute number */
 	Node	   *qual;			/* Check expr or CONSTR_FOREIGN Constraint */
 	ExprState  *qualstate;		/* Execution state for CHECK expr */
 } NewConstraint;
@@ -6217,6 +6220,9 @@ ATRewriteTable(AlteredTableInfo *tab, Oid OIDNewHeap)
 				needscan = true;
 				con->qualstate = ExecPrepareExpr((Expr *) expand_generated_columns_in_expr(con->qual, oldrel, 1), estate);
 				break;
+			case CONSTR_NOTNULL:
+				/* Nothing to do here */
+				break;
 			case CONSTR_FOREIGN:
 				/* Nothing to do here */
 				break;
@@ -6270,10 +6276,69 @@ ATRewriteTable(AlteredTableInfo *tab, Oid OIDNewHeap)
 														wholeatt->attnum);
 			}
 		}
-		if (notnull_attrs || notnull_virtual_attrs)
-			needscan = true;
 	}
 
+	/*-
+	 * If we have to verify new not-null constraints and don't have any other
+	 * reason to fully scan the table, then we can use indexes to test for
+	 * absence of NULL values instead of scanning.  The following conditions
+	 * must be met:
+	 * - we're operating on a regular table
+	 * - we hold AccessExclusiveLock on the table
+	 * - no not-null constraint covers a virtual generated column,
+	 *   because no indexes can be created on them
+	 */
+	if (!needscan &&
+		newrel == NULL &&
+		tab->verify_new_notnull &&
+		notnull_virtual_attrs == NIL &&
+		oldrel->rd_rel->relkind == RELKIND_RELATION &&
+		CheckRelationLockedByMe(oldrel, AccessExclusiveLock, false))
+	{
+		List	   *notnull_attnums = NIL;
+
+		Assert(!tab->rewrite);
+
+		foreach(l, tab->constraints)
+		{
+			Form_pg_attribute attr;
+			NewConstraint *con = lfirst(l);
+
+			if (con->contype != CONSTR_NOTNULL)
+				continue;
+
+			attr = TupleDescAttr(newTupDesc, con->attnum - 1);
+
+			Assert(attr->attnotnull);
+			Assert(attr->attnum == con->attnum);
+
+			if (attr->attgenerated == ATTRIBUTE_GENERATED_VIRTUAL)
+			{
+				needscan = true;
+				break;
+			}
+
+			notnull_attnums = lappend_int(notnull_attnums, attr->attnum);
+		}
+
+		/*
+		 * Validate new NOT NULL constraints, unless we need a scan for other
+		 * reasons, because we can validate them cheaply there, and doing it
+		 * also here would be a waste of cycles.
+		 */
+		if (notnull_attnums != NIL && !needscan)
+		{
+			if (!index_check_notnull(oldrel, notnull_attnums))
+				needscan = true;
+			else
+				ereport(DEBUG1,
+						errmsg_internal("all new not-null constraints on relation \"%s\" have been validated by using index scan",
+										RelationGetRelationName(oldrel)));
+		}
+	}
+	else if (notnull_attrs || notnull_virtual_attrs)
+		needscan = true;
+
 	if (newrel || needscan)
 	{
 		ExprContext *econtext;
@@ -7949,6 +8014,7 @@ ATExecSetNotNull(List **wqueue, Relation rel, char *conName, char *colName,
 	CookedConstraint *ccon;
 	List	   *cooked;
 	bool		is_no_inherit = false;
+	AlteredTableInfo *tab = NULL;
 
 	/* Guard against stack overflow due to overly deep inheritance tree. */
 	check_stack_depth();
@@ -8073,10 +8139,32 @@ ATExecSetNotNull(List **wqueue, Relation rel, char *conName, char *colName,
 	constraint->is_no_inherit = is_no_inherit;
 	constraint->conname = conName;
 
+	tab = ATGetQueueEntry(wqueue, rel);
+
 	/* and do it */
 	cooked = AddRelationNewConstraints(rel, NIL, list_make1(constraint),
 									   false, !recursing, false, NULL);
 	ccon = linitial(cooked);
+
+	Assert(ccon->contype == CONSTR_NOTNULL);
+
+	/*
+	 * We may use indexscan to vertify not-null constraint in Phase3.  Add the
+	 * to-be-validated not-null constraint to Phase 3's queue.
+	 */
+	if (!ccon->skip_validation)
+	{
+		NewConstraint *newcon;
+
+		newcon = (NewConstraint *) palloc0(sizeof(NewConstraint));
+
+		newcon->name = ccon->name;
+		newcon->contype = ccon->contype;
+		newcon->attnum = ccon->attnum;
+
+		tab->constraints = lappend(tab->constraints, newcon);
+	}
+
 	ObjectAddressSet(address, ConstraintRelationId, ccon->conoid);
 
 	InvokeObjectPostAlterHook(RelationRelationId,
@@ -9983,13 +10071,15 @@ ATAddCheckNNConstraint(List **wqueue, AlteredTableInfo *tab, Relation rel,
 	{
 		CookedConstraint *ccon = (CookedConstraint *) lfirst(lcon);
 
-		if (!ccon->skip_validation && ccon->contype != CONSTR_NOTNULL)
+		if (!ccon->skip_validation)
 		{
 			NewConstraint *newcon;
 
 			newcon = palloc0_object(NewConstraint);
 			newcon->name = ccon->name;
 			newcon->contype = ccon->contype;
+			if (ccon->contype == CONSTR_NOTNULL)
+				newcon->attnum = ccon->attnum;
 			newcon->qual = ccon->expr;
 
 			tab->constraints = lappend(tab->constraints, newcon);
@@ -13258,6 +13348,7 @@ QueueNNConstraintValidation(List **wqueue, Relation conrel, Relation rel,
 	List	   *children = NIL;
 	AttrNumber	attnum;
 	char	   *colname;
+	NewConstraint *newcon;
 
 	con = (Form_pg_constraint) GETSTRUCT(contuple);
 	Assert(con->contype == CONSTRAINT_NOTNULL);
@@ -13321,7 +13412,20 @@ QueueNNConstraintValidation(List **wqueue, Relation conrel, Relation rel,
 	/* Set attnotnull appropriately without queueing another validation */
 	set_attnotnull(NULL, rel, attnum, true, false);
 
+	/*
+	 * Queue validation for phase 3.
+	 *
+	 * ALTER TABLE SET NOT NULL will add NOT NULL constraint to
+	 * AlteredTableInfo->constraints, for consistency, do the same here.
+	 */
+	newcon = (NewConstraint *) palloc0(sizeof(NewConstraint));
+	newcon->name = colname;
+	newcon->contype = CONSTR_NOTNULL;
+	newcon->attnum = attnum;
+
+	/* Find or create work queue entry for this table */
 	tab = ATGetQueueEntry(wqueue, rel);
+	tab->constraints = lappend(tab->constraints, newcon);
 	tab->verify_new_notnull = true;
 
 	/*
diff --git a/src/backend/executor/execIndexing.c b/src/backend/executor/execIndexing.c
index 6ae0f959592..88694ce0335 100644
--- a/src/backend/executor/execIndexing.c
+++ b/src/backend/executor/execIndexing.c
@@ -108,12 +108,15 @@
 
 #include "access/genam.h"
 #include "access/relscan.h"
+#include "access/table.h"
 #include "access/tableam.h"
 #include "access/xact.h"
 #include "catalog/index.h"
+#include "catalog/pg_am_d.h"
 #include "executor/executor.h"
 #include "nodes/nodeFuncs.h"
 #include "storage/lmgr.h"
+#include "utils/fmgroids.h"
 #include "utils/injection_point.h"
 #include "utils/multirangetypes.h"
 #include "utils/rangetypes.h"
@@ -146,6 +149,7 @@ static bool index_expression_changed_walker(Node *node,
 											Bitmapset *allUpdatedCols);
 static void ExecWithoutOverlapsNotEmpty(Relation rel, NameData attname, Datum attval,
 										char typtype, Oid atttypid);
+static bool index_check_notnull_internal(Relation relation, List *attnums, List *idxs);
 
 /* ----------------------------------------------------------------
  *		ExecOpenIndices
@@ -1178,3 +1182,212 @@ ExecWithoutOverlapsNotEmpty(Relation rel, NameData attname, Datum attval, char t
 				 errmsg("empty WITHOUT OVERLAPS value found in column \"%s\" in relation \"%s\"",
 						NameStr(attname), RelationGetRelationName(rel))));
 }
+
+/*
+ * notnull_attnums: list of attribute numbers of all new not-null constraints.
+ *
+ * First check whether the relation has a suitable index for each not-null
+ * attribute, then using indexscan mechanism to verify that *all* attributes on
+ * notnull_attnums are indeed not null.
+ *
+ * Returning true means all new not-null constraints have been verified, no
+ * need an extra scan to verify newly added not-null constraints.
+ */
+bool
+index_check_notnull(Relation relation, List *notnull_attnums)
+{
+	Relation	pg_index;
+	Relation	index_rel;
+	SysScanDesc indscan;
+	ScanKeyData skey;
+	HeapTuple	htup;
+	TupleDesc	tupdesc;
+	Form_pg_attribute attr;
+	List	   *idxs = NIL;
+	List	   *attnums = NIL;
+
+	tupdesc = RelationGetDescr(relation);
+
+	/* Prepare to scan pg_index for entries having indrelid = this rel */
+	ScanKeyInit(&skey,
+				Anum_pg_index_indrelid,
+				BTEqualStrategyNumber, F_OIDEQ,
+				ObjectIdGetDatum(RelationGetRelid(relation)));
+
+	pg_index = table_open(IndexRelationId, AccessShareLock);
+	indscan = systable_beginscan(pg_index, IndexIndrelidIndexId, true,
+								 NULL, 1, &skey);
+
+	while (HeapTupleIsValid(htup = systable_getnext(indscan)))
+	{
+		Form_pg_index index = (Form_pg_index) GETSTRUCT(htup);
+
+		/*
+		 * we can only use non-deferred, validated, and alive btree index to
+		 * validate not-null constraints
+		 */
+		if (!index->indimmediate || !index->indisvalid || !index->indislive)
+			continue;
+
+		/* can not use expression index or partial index too */
+		if (!heap_attisnull(htup, Anum_pg_index_indexprs, NULL) ||
+			!heap_attisnull(htup, Anum_pg_index_indpred, NULL))
+			continue;
+
+		index_rel = index_open(index->indexrelid, AccessShareLock);
+
+		/* can only apply to btree index */
+		if (index_rel->rd_rel->relam != BTREE_AM_OID)
+		{
+			index_close(index_rel, AccessShareLock);
+			continue;
+		}
+
+		/* collect index attnums while loop */
+		for (int i = 0; i < index->indnkeyatts; i++)
+		{
+			attr = TupleDescAttr(tupdesc, (index->indkey.values[i] - 1));
+
+			if (attr->attisdropped)
+				continue;
+
+			if (list_member_int(notnull_attnums, attr->attnum) &&
+				!list_member_int(attnums, attr->attnum))
+			{
+				attnums = lappend_int(attnums, attr->attnum);
+				idxs = lappend_oid(idxs, index->indexrelid);
+			}
+		}
+		index_close(index_rel, NoLock);
+	}
+	systable_endscan(indscan);
+	table_close(pg_index, AccessShareLock);
+
+	if (attnums == NIL)
+		return false;
+
+	/*
+	 * every not-null constraint requires an index for indexscan.  If no such
+	 * index exists, we need to use regular table scan to validate not-null
+	 * constraints.
+	 */
+	foreach_int(attno, notnull_attnums)
+	{
+		if (!list_member_int(attnums, attno))
+			return false;
+	}
+
+	return index_check_notnull_internal(relation, attnums, idxs);
+}
+
+/*
+ * Use indexscan mechanism to fast verify each attribute in "attnums" are
+ * not-null or not.
+ */
+static bool
+index_check_notnull_internal(Relation relation, List *attnums, List *idxs)
+{
+	EState	   *estate;
+	ExprContext *econtext;
+	TupleTableSlot *existing_slot;
+	bool		all_not_null = true;
+	ListCell   *lc,
+			   *lc2;
+
+	/*
+	 * Need an EState for slot to hold the current tuple.
+	 */
+	estate = CreateExecutorState();
+	econtext = GetPerTupleExprContext(estate);
+
+	forboth(lc, attnums, lc2, idxs)
+	{
+		SnapshotData DirtySnapshot;
+		IndexScanDesc index_scan;
+		ScanKeyData scankeys[INDEX_MAX_KEYS];
+		IndexInfo  *indexInfo;
+		AttrNumber	sk_attno = -1;
+		Relation	index;
+		int			indnkeyatts;
+
+		AttrNumber	attno = lfirst_int(lc);
+		Oid			indexoid = lfirst_oid(lc2);
+
+		existing_slot = table_slot_create(relation, NULL);
+
+		/* Arrange for econtext's scan tuple to be the tuple under test */
+		econtext->ecxt_scantuple = existing_slot;
+
+		index = index_open(indexoid, NoLock);
+
+		indexInfo = BuildIndexInfo(index);
+		indnkeyatts = IndexRelationGetNumberOfKeyAttributes(index);
+
+		/*
+		 * Search the tuples that are in the index for any violations,
+		 * including tuples that aren't visible yet.
+		 */
+		InitDirtySnapshot(DirtySnapshot);
+
+		for (int i = 0; i < indnkeyatts; i++)
+		{
+			if (indexInfo->ii_IndexAttrNumbers[i] == attno)
+			{
+				sk_attno = i + 1;
+				break;
+			}
+		}
+
+		if (sk_attno == -1)
+			elog(ERROR, "cache lookup failed for attribute number %d on index %u", indexoid, attno);
+
+		for (int i = 0; i < indnkeyatts; i++)
+		{
+			/* set up an IS NULL scan key so that we ignore not nulls */
+			ScanKeyEntryInitialize(&scankeys[i],
+								   SK_ISNULL | SK_SEARCHNULL,
+								   sk_attno,	/* index col to scan */
+								   InvalidStrategy, /* no strategy */
+								   InvalidOid,	/* no strategy subtype */
+								   InvalidOid,	/* no collation */
+								   InvalidOid,	/* no reg proc for this */
+								   (Datum) 0);	/* constant */
+		}
+
+		index_scan = index_beginscan(relation, index, &DirtySnapshot, NULL, indnkeyatts, 0);
+		index_rescan(index_scan, scankeys, indnkeyatts, NULL, 0);
+
+		while (index_getnext_slot(index_scan, ForwardScanDirection, existing_slot))
+		{
+			Datum		values[INDEX_MAX_KEYS];
+			bool		nulls[INDEX_MAX_KEYS];
+
+			/*
+			 * Extract the index column values and isnull flags from the
+			 * existing tuple.
+			 */
+			FormIndexDatum(indexInfo, existing_slot, estate, values, nulls);
+
+			if (nulls[sk_attno - 1])
+			{
+				all_not_null = false;
+				break;
+			}
+		}
+
+		index_endscan(index_scan);
+		index_close(index, NoLock);
+		ExecDropSingleTupleTableSlot(existing_slot);
+
+		/* exit earlier */
+		if (!all_not_null)
+		{
+			FreeExecutorState(estate);
+			return false;
+		}
+	}
+
+	FreeExecutorState(estate);
+
+	return true;
+}
diff --git a/src/include/executor/executor.h b/src/include/executor/executor.h
index 5929aabc353..7f24caeeafb 100644
--- a/src/include/executor/executor.h
+++ b/src/include/executor/executor.h
@@ -756,6 +756,8 @@ extern void check_exclusion_constraint(Relation heap, Relation index,
 									   const Datum *values, const bool *isnull,
 									   EState *estate, bool newIndex);
 
+extern bool index_check_notnull(Relation relation, List *notnull_attnums);
+
 /*
  * prototypes from functions in execReplication.c
  */
diff --git a/src/test/isolation/expected/indexscan-check-notnull.out b/src/test/isolation/expected/indexscan-check-notnull.out
new file mode 100644
index 00000000000..c6a652e2518
--- /dev/null
+++ b/src/test/isolation/expected/indexscan-check-notnull.out
@@ -0,0 +1,97 @@
+Parsed test spec with 2 sessions
+
+starting permutation: s1_b1 s2_b1 s1_d1 s2_a1 s1_c1 s2_c1 s1_q1
+step s1_b1: BEGIN ISOLATION LEVEL REPEATABLE READ;
+step s2_b1: BEGIN ISOLATION LEVEL REPEATABLE READ;
+step s1_d1: DELETE FROM t;
+step s2_a1: ALTER TABLE t ADD CONSTRAINT t1_nn NOT NULL a; <waiting ...>
+step s1_c1: COMMIT;
+step s2_a1: <... completed>
+step s2_c1: COMMIT;
+step s1_q1: SELECT conname, conrelid::regclass, contype, convalidated
+              FROM pg_constraint WHERE conname = 't1_nn';
+
+conname|conrelid|contype|convalidated
+-------+--------+-------+------------
+t1_nn  |t       |n      |t           
+(1 row)
+
+
+starting permutation: s1_b2 s2_b1 s1_d1 s2_a1 s1_c1 s2_c1 s1_q1
+step s1_b2: BEGIN;
+step s2_b1: BEGIN ISOLATION LEVEL REPEATABLE READ;
+step s1_d1: DELETE FROM t;
+step s2_a1: ALTER TABLE t ADD CONSTRAINT t1_nn NOT NULL a; <waiting ...>
+step s1_c1: COMMIT;
+step s2_a1: <... completed>
+step s2_c1: COMMIT;
+step s1_q1: SELECT conname, conrelid::regclass, contype, convalidated
+              FROM pg_constraint WHERE conname = 't1_nn';
+
+conname|conrelid|contype|convalidated
+-------+--------+-------+------------
+t1_nn  |t       |n      |t           
+(1 row)
+
+
+starting permutation: s1_b1 s2_b2 s1_d1 s2_a1 s1_c1 s2_c1 s1_q1
+step s1_b1: BEGIN ISOLATION LEVEL REPEATABLE READ;
+step s2_b2: BEGIN;
+step s1_d1: DELETE FROM t;
+step s2_a1: ALTER TABLE t ADD CONSTRAINT t1_nn NOT NULL a; <waiting ...>
+step s1_c1: COMMIT;
+step s2_a1: <... completed>
+step s2_c1: COMMIT;
+step s1_q1: SELECT conname, conrelid::regclass, contype, convalidated
+              FROM pg_constraint WHERE conname = 't1_nn';
+
+conname|conrelid|contype|convalidated
+-------+--------+-------+------------
+t1_nn  |t       |n      |t           
+(1 row)
+
+
+starting permutation: s1_b1 s2_b1 s2_a1 s1_r1 s2_r1
+step s1_b1: BEGIN ISOLATION LEVEL REPEATABLE READ;
+step s2_b1: BEGIN ISOLATION LEVEL REPEATABLE READ;
+step s2_a1: ALTER TABLE t ADD CONSTRAINT t1_nn NOT NULL a;
+ERROR:  column "a" of relation "t" contains null values
+step s1_r1: ROLLBACK;
+step s2_r1: ROLLBACK;
+
+starting permutation: s1_b1 s2_b2 s2_d1 s1_d1 s2_r1 s1_a1 s1_q1 s1_r1
+step s1_b1: BEGIN ISOLATION LEVEL REPEATABLE READ;
+step s2_b2: BEGIN;
+step s2_d1: DROP INDEX t_ab_idx;
+step s1_d1: DELETE FROM t; <waiting ...>
+step s2_r1: ROLLBACK;
+step s1_d1: <... completed>
+step s1_a1: ALTER TABLE t ADD CONSTRAINT t1_nn NOT NULL a;
+step s1_q1: SELECT conname, conrelid::regclass, contype, convalidated
+              FROM pg_constraint WHERE conname = 't1_nn';
+
+conname|conrelid|contype|convalidated
+-------+--------+-------+------------
+t1_nn  |t       |n      |t           
+(1 row)
+
+step s1_r1: ROLLBACK;
+
+starting permutation: s1_b2 s2_b1 s1_d1 s2_d1 s1_s0 s1_a1 s1_c1 s2_c1 s1_q1
+step s1_b2: BEGIN;
+step s2_b1: BEGIN ISOLATION LEVEL REPEATABLE READ;
+step s1_d1: DELETE FROM t;
+step s2_d1: DROP INDEX t_ab_idx; <waiting ...>
+step s1_s0: SAVEPOINT s0;
+step s1_a1: ALTER TABLE t ADD CONSTRAINT t1_nn NOT NULL a;
+step s1_c1: COMMIT;
+step s2_d1: <... completed>
+step s2_c1: COMMIT;
+step s1_q1: SELECT conname, conrelid::regclass, contype, convalidated
+              FROM pg_constraint WHERE conname = 't1_nn';
+
+conname|conrelid|contype|convalidated
+-------+--------+-------+------------
+t1_nn  |t       |n      |t           
+(1 row)
+
diff --git a/src/test/isolation/isolation_schedule b/src/test/isolation/isolation_schedule
index 01ff1c6586f..7ce6bbcaf89 100644
--- a/src/test/isolation/isolation_schedule
+++ b/src/test/isolation/isolation_schedule
@@ -58,6 +58,7 @@ test: merge-delete
 test: merge-update
 test: merge-match-recheck
 test: merge-join
+test: indexscan-check-notnull
 test: delete-abort-savept
 test: delete-abort-savept-2
 test: aborted-keyrevoke
diff --git a/src/test/isolation/specs/indexscan-check-notnull.spec b/src/test/isolation/specs/indexscan-check-notnull.spec
new file mode 100644
index 00000000000..05b4488550c
--- /dev/null
+++ b/src/test/isolation/specs/indexscan-check-notnull.spec
@@ -0,0 +1,45 @@
+
+#
+# using indexscan to check a column not-null constraint
+# is satisfied or not.
+#
+
+setup
+{
+  CREATE TABLE t (a int, b int);
+  CREATE INDEX t_ab_idx on t(a,b);
+  INSERT INTO t values (null, 1);
+  INSERT INTO t SELECT x, x*10 FROM generate_series(1,3) g(x);
+}
+
+teardown
+{
+  DROP TABLE t;
+}
+
+session s1
+step s1_b1  { BEGIN ISOLATION LEVEL REPEATABLE READ; }
+step s1_b2  { BEGIN; }
+step s1_d1  { DELETE FROM t;}
+step s1_s0  { SAVEPOINT s0;}
+step s1_a1  { ALTER TABLE t ADD CONSTRAINT t1_nn NOT NULL a;}
+step s1_q1  { SELECT conname, conrelid::regclass, contype, convalidated
+              FROM pg_constraint WHERE conname = 't1_nn';
+            }
+step s1_r1  { ROLLBACK; }
+step s1_c1  { COMMIT; }
+
+session s2
+step s2_b1  { BEGIN ISOLATION LEVEL REPEATABLE READ; }
+step s2_b2  { BEGIN; }
+step s2_a1  { ALTER TABLE t ADD CONSTRAINT t1_nn NOT NULL a;}
+step s2_d1  { DROP INDEX t_ab_idx;}
+step s2_r1  { ROLLBACK; }
+step s2_c1  { COMMIT; }
+
+permutation s1_b1 s2_b1 s1_d1 s2_a1 s1_c1 s2_c1 s1_q1
+permutation s1_b2 s2_b1 s1_d1 s2_a1 s1_c1 s2_c1 s1_q1
+permutation s1_b1 s2_b2 s1_d1 s2_a1 s1_c1 s2_c1 s1_q1
+permutation s1_b1 s2_b1 s2_a1 s1_r1 s2_r1
+permutation s1_b1 s2_b2 s2_d1 s1_d1 s2_r1 s1_a1 s1_q1 s1_r1
+permutation s1_b2 s2_b1 s1_d1 s2_d1 s1_s0 s1_a1 s1_c1 s2_c1 s1_q1
diff --git a/src/test/modules/test_misc/meson.build b/src/test/modules/test_misc/meson.build
index 6e8db1621a7..56faf359b29 100644
--- a/src/test/modules/test_misc/meson.build
+++ b/src/test/modules/test_misc/meson.build
@@ -19,6 +19,7 @@ tests += {
       't/008_replslot_single_user.pl',
       't/009_log_temp_files.pl',
       't/010_index_concurrently_upsert.pl',
+      't/011_indexscan_validate_notnull.pl',
     ],
     # The injection points are cluster-wide, so disable installcheck
     'runningcheck': false,
diff --git a/src/test/modules/test_misc/t/011_indexscan_validate_notnull.pl b/src/test/modules/test_misc/t/011_indexscan_validate_notnull.pl
new file mode 100644
index 00000000000..a3f3cb409b6
--- /dev/null
+++ b/src/test/modules/test_misc/t/011_indexscan_validate_notnull.pl
@@ -0,0 +1,163 @@
+# Copyright (c) 2025, PostgreSQL Global Development Group
+
+# Verify that indexscan mechanism can speedup ALTER TABLE ADD NOT NULL
+
+
+use strict;
+use warnings FATAL => 'all';
+use PostgreSQL::Test::Cluster;
+use PostgreSQL::Test::Utils;
+use Test::More;
+
+# Initialize a test cluster
+my $node = PostgreSQL::Test::Cluster->new('primary');
+$node->init();
+# Turn message level up to DEBUG1 so that we get the messages we want to see
+$node->append_conf('postgresql.conf', 'client_min_messages = DEBUG1');
+$node->start;
+
+# Run a SQL command and return psql's stderr (including debug messages)
+sub run_sql_command
+{
+	my $sql = shift;
+	my $stderr;
+
+	$node->psql(
+		'postgres',
+		$sql,
+		stderr => \$stderr,
+		on_error_die => 1,
+		on_error_stop => 1);
+	return $stderr;
+}
+
+# Check whether result of run_sql_command shows that we did a verify pass
+sub is_table_verified
+{
+	my $output = shift;
+	return index($output, 'DEBUG:  verifying table') != -1;
+}
+
+# Check whether result of run_sql_command shows that we did a verify pass
+sub is_indexscan_veritify_notnull
+{
+	my $output = shift;
+	return index($output, 'DEBUG:  all new not-null constraints on relation') != -1;
+}
+
+my $output;
+
+note "test alter table SET NOT NULL using indexscan with partitioned table";
+
+run_sql_command(
+    'CREATE TABLE tp (a int, b int, c int, d int ) PARTITION BY range(a);
+     CREATE TABLE tpp1 partition of tp for values from ( 1 ) to (10);
+     CREATE TABLE tpp2 partition of tp for values from ( 10 ) to (21);
+     INSERT INTO tp select g, g + 10, g + 15, g + random(min=>1::int, max=>10::int) from generate_series(1,19) g;
+     CREATE INDEX ON tp(b); ');
+
+$output = run_sql_command('ALTER TABLE tp ALTER COLUMN b SET NOT NULL;');
+ok(is_indexscan_veritify_notnull($output),
+	'column b will use indexscan to verify not-null status, no need scan table');
+ok( $output =~
+	  m/all new not-null constraints on relation "tpp1" have been validated by using index scan/,
+	'all newly added constraints proved by indexscan');
+
+run_sql_command(
+	'ALTER TABLE tp ALTER COLUMN b DROP NOT NULL;');
+
+# use indexes on partitions to fast vertifing not-null should be ok
+$output = run_sql_command('ALTER TABLE tpp1 ALTER COLUMN b SET NOT NULL;');
+ok(is_indexscan_veritify_notnull($output), 'use indexscan to validate column b not-null will not scan table');
+ok(!is_table_verified($output), 'no table scan for pp1');
+ok( $output =~
+	  m/all new not-null constraints on relation "tpp1" have been validated by using index scan/,
+	'all newly added constraints proved by indexscan');
+
+$output = run_sql_command('ALTER TABLE tpp2 ALTER COLUMN b SET NOT NULL;');
+ok(is_indexscan_veritify_notnull($output), 'use indexscan to validate column b not-null, will not scan table');
+ok(!is_table_verified($output), 'no table scan for tpp2');
+ok( $output =~
+	  m/all new not-null constraints on relation "tpp2" have been validated by using index scan/,
+	'all newly added constraints proved by indexscan');
+
+run_sql_command(
+	'ALTER TABLE tp ALTER COLUMN b DROP NOT NULL;');
+
+# table rewrite then can not use indexscan to verify not-null constraint
+$output = run_sql_command(
+	'ALTER TABLE tp ALTER COLUMN b SET NOT NULL, ALTER COLUMN b SET DATA TYPE bigint;'
+);
+ok(!is_table_verified($output), 'no table scan for tp');
+ok(!is_indexscan_veritify_notnull($output), 'table tp will rewrite, can not use indexscan to verify not-null constraints on it');
+
+# test using indexscan with multiple not-null constraints
+run_sql_command(
+    'ALTER TABLE tp ALTER COLUMN b DROP NOT NULL;
+	 CREATE INDEX ON tp(c);
+	 CREATE INDEX ON tp(d); ');
+
+# one column can use indexscan, another can not, so can not use indexscan to verify not-null
+$output = run_sql_command(
+	'ALTER TABLE tp ALTER COLUMN a SET NOT NULL, ADD CONSTRAINT c_nn NOT NULL c');
+ok(is_table_verified($output), 'table scan for tp');
+ok(!is_indexscan_veritify_notnull($output), 'can not use indexscan to verify not-null constraints on table tp');
+
+# all columns have index on it
+# use indexscan to verify multiple not-null constraints should just fine
+$output = run_sql_command(
+	'ALTER TABLE tp ALTER COLUMN d SET NOT NULL, ADD CONSTRAINT c_nn NOT NULL c, ALTER COLUMN b SET NOT NULL;');
+ok(!is_table_verified($output), 'no table scan for tp');
+ok(is_indexscan_veritify_notnull($output),
+	'using indexscan to verify not-null constraints on column b, c, d, no need table scan');
+
+# test with non-partitioned table and other non-Btree index.
+run_sql_command(
+    'CREATE TABLE t1(f1 INT, f2 int, f3 int,f4 int, f5 int);
+     INSERT INTO t1 select g, g+1, g+2, g+3, g+4 from generate_series(1, 100) g;
+     CREATE INDEX t1_f1_f2_idx ON t1(f1,f2);
+     CREATE UNIQUE INDEX t1_f3idx ON t1(f3);
+     CREATE INDEX t1_f3f4idx ON t1(f3) include(f4);
+     CREATE INDEX hash_f5_idx ON t1 USING hash (f5 int4_ops); ');
+
+# ALTER TABLE VALIDATE CONSTRAINT can not use indexscan,
+# because it only hold ShareUpdateExclusiveLock lock.
+run_sql_command('ALTER TABLE t1 ADD CONSTRAINT nn_t1_f2 NOT NULL f2 NOT VALID;');
+
+$output = run_sql_command(
+	'ALTER TABLE t1 VALIDATE CONSTRAINT nn_t1_f2;'
+);
+ok(!is_indexscan_veritify_notnull($output), 'can not use indexscan for ALTER TABLE VALIDATE CONSTRAINT command');
+run_sql_command('ALTER TABLE t1 DROP CONSTRAINT nn_t1_f2;');
+
+$output = run_sql_command(
+	'ALTER TABLE t1 ALTER COLUMN f1 SET NOT NULL, ALTER f1 type bigint;'
+);
+ok(!is_indexscan_veritify_notnull($output), 'table t1 will rewrite, can not use indexscan to validate not-null constraints on t1');
+
+run_sql_command('ALTER TABLE t1 ALTER COLUMN f1 DROP NOT NULL;');
+run_sql_command('ALTER TABLE t1 ADD CONSTRAINT nn NOT NULL f1, ALTER f1 type bigint;');
+
+# can use indexscan mechanism to fast add multiple not-null constraints
+$output = run_sql_command(
+	'ALTER TABLE t1 ALTER COLUMN f2 SET NOT NULL, ALTER COLUMN f1 SET NOT NULL;'
+);
+ok( $output =~
+	  m/all new not-null constraints on relation "t1" have been validated by using index scan/,
+	'all not-null constraints are validated by indexscan');
+
+# using indexscan mechanism to fast add a not-null can only apply to key columns, not include column
+$output = run_sql_command(
+	'ALTER TABLE t1 ADD CONSTRAINT nnf4 NOT NULL f4;'
+);
+ok(!is_indexscan_veritify_notnull($output), 'can not use indexscan to validate not-null constraint on t1');
+
+# if index is not btree index then cannot use indexscan mechanism to fast add not-null constraint
+$output = run_sql_command(
+	'ALTER TABLE t1 ADD CONSTRAINT nn_f5 NOT NULL f5;'
+);
+ok(!is_indexscan_veritify_notnull($output), 'can not use indexscan to validate not-null constraints on t1');
+
+$node->stop('fast');
+
+done_testing();
-- 
2.47.3


--xpkr6zhfzd3fjt76--





^ permalink  raw  reply  [nested|flat] 150+ messages in thread

* [PATCH v8] using indexscan to speedup add not null constraints
@ 2025-10-20 05:29  jian he <[email protected]>
  0 siblings, 0 replies; 150+ messages in thread

From: jian he @ 2025-10-20 05:29 UTC (permalink / raw)

This patch tries to use index_beginscan() / index_getnext() / index_endscan()
mentioned in [1] to speedup adding not-null constraints to the existing table.

The main logic happens in phase3 ATRewriteTable
1. collect all not-null constraints.
2. For each not-null constraint, check whether there is a corresponding index
available for validation. If not, then can not use indexscan to verify not-null
constraints.
3. If any of the following conditions are true
  * table scan or rewrite is required,
  * table wasn't locked with `AccessExclusiveLock`
  * the NOT NULL constraint applies to a virtual generated column
 then index scan cannot be used for fast validation.
4. If all conditions are satisfied, attempt to use indexscan to verify
whether the column contains any NULL values.

concurrency concern:
ALTER TABLE SET NOT NULL will take an ACCESS EXCLUSIVE lock, so there is less
variant of racing issue can occur?  to prove accurate, I wrote some isolation
tests. see[2]

performance:
demo:
case when: %20 percent values are NULL and have been deleted from heap but they
still on the index.

drop table if exists t;
create unlogged table t(a int, b int) with (autovacuum_enabled = off, vacuum_index_cleanup=off);
insert into t select case when g % 5 = 0 then null else g end, g+1
from generate_series(1,1_000_000) g;
create index t_idx_a on t(a);
delete from t where a is null;

alter table t alter column a drop not null;
alter table t add constraint t1 not null a;

the above two statement running several times:
patch Time:: 1.084  ms
master Time: 12.045 ms

references:
[1] https://postgr.es/m/CA%2BTgmoa5NKz8iGW_9v7wz%3D-%2BzQFu%3DE4SZoaTaU1znLaEXRYp-Q%40mail.gmail.com
[2] https://postgr.es/m/900056D1-32DF-4927-8251-3E0C0DC407FD%40anarazel.de
discussion: https://postgr.es/m/CACJufxFiW=4k1is=F1J=r-Cx1RuByXQPUrWB331U47rSnGz+hw@mail.gmail.com
commitfest entry: https://commitfest.postgresql.org/patch/5444
---
 src/backend/commands/tablecmds.c              | 116 +++++++++-
 src/backend/executor/execIndexing.c           | 213 ++++++++++++++++++
 src/include/executor/executor.h               |   2 +
 .../expected/indexscan-check-notnull.out      |  97 ++++++++
 src/test/isolation/isolation_schedule         |   1 +
 .../specs/indexscan-check-notnull.spec        |  45 ++++
 src/test/modules/test_misc/meson.build        |   1 +
 .../t/011_indexscan_validate_notnull.pl       | 163 ++++++++++++++
 8 files changed, 632 insertions(+), 6 deletions(-)
 create mode 100644 src/test/isolation/expected/indexscan-check-notnull.out
 create mode 100644 src/test/isolation/specs/indexscan-check-notnull.spec
 create mode 100644 src/test/modules/test_misc/t/011_indexscan_validate_notnull.pl

diff --git a/src/backend/commands/tablecmds.c b/src/backend/commands/tablecmds.c
index f976c0e5c7e..2af06630b35 100644
--- a/src/backend/commands/tablecmds.c
+++ b/src/backend/commands/tablecmds.c
@@ -210,16 +210,19 @@ typedef struct AlteredTableInfo
 	List	   *changedStatisticsDefs;	/* string definitions of same */
 } AlteredTableInfo;
 
-/* Struct describing one new constraint to check in Phase 3 scan */
-/* Note: new not-null constraints are handled elsewhere */
+/*
+ * Struct describing one new constraint to check in Phase 3 scan. Note: new
+ * not-null constraints are handled here too.
+*/
 typedef struct NewConstraint
 {
 	char	   *name;			/* Constraint name, or NULL if none */
-	ConstrType	contype;		/* CHECK or FOREIGN */
+	ConstrType	contype;		/* CHECK or FOREIGN or NOT NULL */
 	Oid			refrelid;		/* PK rel, if FOREIGN */
 	Oid			refindid;		/* OID of PK's index, if FOREIGN */
 	bool		conwithperiod;	/* Whether the new FOREIGN KEY uses PERIOD */
 	Oid			conid;			/* OID of pg_constraint entry, if FOREIGN */
+	int			attnum;			/* NOT NULL constraint attribute number */
 	Node	   *qual;			/* Check expr or CONSTR_FOREIGN Constraint */
 	ExprState  *qualstate;		/* Execution state for CHECK expr */
 } NewConstraint;
@@ -6217,6 +6220,9 @@ ATRewriteTable(AlteredTableInfo *tab, Oid OIDNewHeap)
 				needscan = true;
 				con->qualstate = ExecPrepareExpr((Expr *) expand_generated_columns_in_expr(con->qual, oldrel, 1), estate);
 				break;
+			case CONSTR_NOTNULL:
+				/* Nothing to do here */
+				break;
 			case CONSTR_FOREIGN:
 				/* Nothing to do here */
 				break;
@@ -6270,10 +6276,69 @@ ATRewriteTable(AlteredTableInfo *tab, Oid OIDNewHeap)
 														wholeatt->attnum);
 			}
 		}
-		if (notnull_attrs || notnull_virtual_attrs)
-			needscan = true;
 	}
 
+	/*-
+	 * If we have to verify new not-null constraints and don't have any other
+	 * reason to fully scan the table, then we can use indexes to test for
+	 * absence of NULL values instead of scanning.  The following conditions
+	 * must be met:
+	 * - we're operating on a regular table
+	 * - we hold AccessExclusiveLock on the table
+	 * - no not-null constraint covers a virtual generated column,
+	 *   because no indexes can be created on them
+	 */
+	if (!needscan &&
+		newrel == NULL &&
+		tab->verify_new_notnull &&
+		notnull_virtual_attrs == NIL &&
+		oldrel->rd_rel->relkind == RELKIND_RELATION &&
+		CheckRelationLockedByMe(oldrel, AccessExclusiveLock, false))
+	{
+		List	   *notnull_attnums = NIL;
+
+		Assert(!tab->rewrite);
+
+		foreach(l, tab->constraints)
+		{
+			Form_pg_attribute attr;
+			NewConstraint *con = lfirst(l);
+
+			if (con->contype != CONSTR_NOTNULL)
+				continue;
+
+			attr = TupleDescAttr(newTupDesc, con->attnum - 1);
+
+			Assert(attr->attnotnull);
+			Assert(attr->attnum == con->attnum);
+
+			if (attr->attgenerated == ATTRIBUTE_GENERATED_VIRTUAL)
+			{
+				needscan = true;
+				break;
+			}
+
+			notnull_attnums = lappend_int(notnull_attnums, attr->attnum);
+		}
+
+		/*
+		 * Validate new NOT NULL constraints, unless we need a scan for other
+		 * reasons, because we can validate them cheaply there, and doing it
+		 * also here would be a waste of cycles.
+		 */
+		if (notnull_attnums != NIL && !needscan)
+		{
+			if (!index_check_notnull(oldrel, notnull_attnums))
+				needscan = true;
+			else
+				ereport(DEBUG1,
+						errmsg_internal("all new not-null constraints on relation \"%s\" have been validated by using index scan",
+										RelationGetRelationName(oldrel)));
+		}
+	}
+	else if (notnull_attrs || notnull_virtual_attrs)
+		needscan = true;
+
 	if (newrel || needscan)
 	{
 		ExprContext *econtext;
@@ -7949,6 +8014,7 @@ ATExecSetNotNull(List **wqueue, Relation rel, char *conName, char *colName,
 	CookedConstraint *ccon;
 	List	   *cooked;
 	bool		is_no_inherit = false;
+	AlteredTableInfo *tab = NULL;
 
 	/* Guard against stack overflow due to overly deep inheritance tree. */
 	check_stack_depth();
@@ -8073,10 +8139,32 @@ ATExecSetNotNull(List **wqueue, Relation rel, char *conName, char *colName,
 	constraint->is_no_inherit = is_no_inherit;
 	constraint->conname = conName;
 
+	tab = ATGetQueueEntry(wqueue, rel);
+
 	/* and do it */
 	cooked = AddRelationNewConstraints(rel, NIL, list_make1(constraint),
 									   false, !recursing, false, NULL);
 	ccon = linitial(cooked);
+
+	Assert(ccon->contype == CONSTR_NOTNULL);
+
+	/*
+	 * We may use indexscan to vertify not-null constraint in Phase3.  Add the
+	 * to-be-validated not-null constraint to Phase 3's queue.
+	 */
+	if (!ccon->skip_validation)
+	{
+		NewConstraint *newcon;
+
+		newcon = (NewConstraint *) palloc0(sizeof(NewConstraint));
+
+		newcon->name = ccon->name;
+		newcon->contype = ccon->contype;
+		newcon->attnum = ccon->attnum;
+
+		tab->constraints = lappend(tab->constraints, newcon);
+	}
+
 	ObjectAddressSet(address, ConstraintRelationId, ccon->conoid);
 
 	InvokeObjectPostAlterHook(RelationRelationId,
@@ -9983,13 +10071,15 @@ ATAddCheckNNConstraint(List **wqueue, AlteredTableInfo *tab, Relation rel,
 	{
 		CookedConstraint *ccon = (CookedConstraint *) lfirst(lcon);
 
-		if (!ccon->skip_validation && ccon->contype != CONSTR_NOTNULL)
+		if (!ccon->skip_validation)
 		{
 			NewConstraint *newcon;
 
 			newcon = palloc0_object(NewConstraint);
 			newcon->name = ccon->name;
 			newcon->contype = ccon->contype;
+			if (ccon->contype == CONSTR_NOTNULL)
+				newcon->attnum = ccon->attnum;
 			newcon->qual = ccon->expr;
 
 			tab->constraints = lappend(tab->constraints, newcon);
@@ -13258,6 +13348,7 @@ QueueNNConstraintValidation(List **wqueue, Relation conrel, Relation rel,
 	List	   *children = NIL;
 	AttrNumber	attnum;
 	char	   *colname;
+	NewConstraint *newcon;
 
 	con = (Form_pg_constraint) GETSTRUCT(contuple);
 	Assert(con->contype == CONSTRAINT_NOTNULL);
@@ -13321,7 +13412,20 @@ QueueNNConstraintValidation(List **wqueue, Relation conrel, Relation rel,
 	/* Set attnotnull appropriately without queueing another validation */
 	set_attnotnull(NULL, rel, attnum, true, false);
 
+	/*
+	 * Queue validation for phase 3.
+	 *
+	 * ALTER TABLE SET NOT NULL will add NOT NULL constraint to
+	 * AlteredTableInfo->constraints, for consistency, do the same here.
+	 */
+	newcon = (NewConstraint *) palloc0(sizeof(NewConstraint));
+	newcon->name = colname;
+	newcon->contype = CONSTR_NOTNULL;
+	newcon->attnum = attnum;
+
+	/* Find or create work queue entry for this table */
 	tab = ATGetQueueEntry(wqueue, rel);
+	tab->constraints = lappend(tab->constraints, newcon);
 	tab->verify_new_notnull = true;
 
 	/*
diff --git a/src/backend/executor/execIndexing.c b/src/backend/executor/execIndexing.c
index 6ae0f959592..88694ce0335 100644
--- a/src/backend/executor/execIndexing.c
+++ b/src/backend/executor/execIndexing.c
@@ -108,12 +108,15 @@
 
 #include "access/genam.h"
 #include "access/relscan.h"
+#include "access/table.h"
 #include "access/tableam.h"
 #include "access/xact.h"
 #include "catalog/index.h"
+#include "catalog/pg_am_d.h"
 #include "executor/executor.h"
 #include "nodes/nodeFuncs.h"
 #include "storage/lmgr.h"
+#include "utils/fmgroids.h"
 #include "utils/injection_point.h"
 #include "utils/multirangetypes.h"
 #include "utils/rangetypes.h"
@@ -146,6 +149,7 @@ static bool index_expression_changed_walker(Node *node,
 											Bitmapset *allUpdatedCols);
 static void ExecWithoutOverlapsNotEmpty(Relation rel, NameData attname, Datum attval,
 										char typtype, Oid atttypid);
+static bool index_check_notnull_internal(Relation relation, List *attnums, List *idxs);
 
 /* ----------------------------------------------------------------
  *		ExecOpenIndices
@@ -1178,3 +1182,212 @@ ExecWithoutOverlapsNotEmpty(Relation rel, NameData attname, Datum attval, char t
 				 errmsg("empty WITHOUT OVERLAPS value found in column \"%s\" in relation \"%s\"",
 						NameStr(attname), RelationGetRelationName(rel))));
 }
+
+/*
+ * notnull_attnums: list of attribute numbers of all new not-null constraints.
+ *
+ * First check whether the relation has a suitable index for each not-null
+ * attribute, then using indexscan mechanism to verify that *all* attributes on
+ * notnull_attnums are indeed not null.
+ *
+ * Returning true means all new not-null constraints have been verified, no
+ * need an extra scan to verify newly added not-null constraints.
+ */
+bool
+index_check_notnull(Relation relation, List *notnull_attnums)
+{
+	Relation	pg_index;
+	Relation	index_rel;
+	SysScanDesc indscan;
+	ScanKeyData skey;
+	HeapTuple	htup;
+	TupleDesc	tupdesc;
+	Form_pg_attribute attr;
+	List	   *idxs = NIL;
+	List	   *attnums = NIL;
+
+	tupdesc = RelationGetDescr(relation);
+
+	/* Prepare to scan pg_index for entries having indrelid = this rel */
+	ScanKeyInit(&skey,
+				Anum_pg_index_indrelid,
+				BTEqualStrategyNumber, F_OIDEQ,
+				ObjectIdGetDatum(RelationGetRelid(relation)));
+
+	pg_index = table_open(IndexRelationId, AccessShareLock);
+	indscan = systable_beginscan(pg_index, IndexIndrelidIndexId, true,
+								 NULL, 1, &skey);
+
+	while (HeapTupleIsValid(htup = systable_getnext(indscan)))
+	{
+		Form_pg_index index = (Form_pg_index) GETSTRUCT(htup);
+
+		/*
+		 * we can only use non-deferred, validated, and alive btree index to
+		 * validate not-null constraints
+		 */
+		if (!index->indimmediate || !index->indisvalid || !index->indislive)
+			continue;
+
+		/* can not use expression index or partial index too */
+		if (!heap_attisnull(htup, Anum_pg_index_indexprs, NULL) ||
+			!heap_attisnull(htup, Anum_pg_index_indpred, NULL))
+			continue;
+
+		index_rel = index_open(index->indexrelid, AccessShareLock);
+
+		/* can only apply to btree index */
+		if (index_rel->rd_rel->relam != BTREE_AM_OID)
+		{
+			index_close(index_rel, AccessShareLock);
+			continue;
+		}
+
+		/* collect index attnums while loop */
+		for (int i = 0; i < index->indnkeyatts; i++)
+		{
+			attr = TupleDescAttr(tupdesc, (index->indkey.values[i] - 1));
+
+			if (attr->attisdropped)
+				continue;
+
+			if (list_member_int(notnull_attnums, attr->attnum) &&
+				!list_member_int(attnums, attr->attnum))
+			{
+				attnums = lappend_int(attnums, attr->attnum);
+				idxs = lappend_oid(idxs, index->indexrelid);
+			}
+		}
+		index_close(index_rel, NoLock);
+	}
+	systable_endscan(indscan);
+	table_close(pg_index, AccessShareLock);
+
+	if (attnums == NIL)
+		return false;
+
+	/*
+	 * every not-null constraint requires an index for indexscan.  If no such
+	 * index exists, we need to use regular table scan to validate not-null
+	 * constraints.
+	 */
+	foreach_int(attno, notnull_attnums)
+	{
+		if (!list_member_int(attnums, attno))
+			return false;
+	}
+
+	return index_check_notnull_internal(relation, attnums, idxs);
+}
+
+/*
+ * Use indexscan mechanism to fast verify each attribute in "attnums" are
+ * not-null or not.
+ */
+static bool
+index_check_notnull_internal(Relation relation, List *attnums, List *idxs)
+{
+	EState	   *estate;
+	ExprContext *econtext;
+	TupleTableSlot *existing_slot;
+	bool		all_not_null = true;
+	ListCell   *lc,
+			   *lc2;
+
+	/*
+	 * Need an EState for slot to hold the current tuple.
+	 */
+	estate = CreateExecutorState();
+	econtext = GetPerTupleExprContext(estate);
+
+	forboth(lc, attnums, lc2, idxs)
+	{
+		SnapshotData DirtySnapshot;
+		IndexScanDesc index_scan;
+		ScanKeyData scankeys[INDEX_MAX_KEYS];
+		IndexInfo  *indexInfo;
+		AttrNumber	sk_attno = -1;
+		Relation	index;
+		int			indnkeyatts;
+
+		AttrNumber	attno = lfirst_int(lc);
+		Oid			indexoid = lfirst_oid(lc2);
+
+		existing_slot = table_slot_create(relation, NULL);
+
+		/* Arrange for econtext's scan tuple to be the tuple under test */
+		econtext->ecxt_scantuple = existing_slot;
+
+		index = index_open(indexoid, NoLock);
+
+		indexInfo = BuildIndexInfo(index);
+		indnkeyatts = IndexRelationGetNumberOfKeyAttributes(index);
+
+		/*
+		 * Search the tuples that are in the index for any violations,
+		 * including tuples that aren't visible yet.
+		 */
+		InitDirtySnapshot(DirtySnapshot);
+
+		for (int i = 0; i < indnkeyatts; i++)
+		{
+			if (indexInfo->ii_IndexAttrNumbers[i] == attno)
+			{
+				sk_attno = i + 1;
+				break;
+			}
+		}
+
+		if (sk_attno == -1)
+			elog(ERROR, "cache lookup failed for attribute number %d on index %u", indexoid, attno);
+
+		for (int i = 0; i < indnkeyatts; i++)
+		{
+			/* set up an IS NULL scan key so that we ignore not nulls */
+			ScanKeyEntryInitialize(&scankeys[i],
+								   SK_ISNULL | SK_SEARCHNULL,
+								   sk_attno,	/* index col to scan */
+								   InvalidStrategy, /* no strategy */
+								   InvalidOid,	/* no strategy subtype */
+								   InvalidOid,	/* no collation */
+								   InvalidOid,	/* no reg proc for this */
+								   (Datum) 0);	/* constant */
+		}
+
+		index_scan = index_beginscan(relation, index, &DirtySnapshot, NULL, indnkeyatts, 0);
+		index_rescan(index_scan, scankeys, indnkeyatts, NULL, 0);
+
+		while (index_getnext_slot(index_scan, ForwardScanDirection, existing_slot))
+		{
+			Datum		values[INDEX_MAX_KEYS];
+			bool		nulls[INDEX_MAX_KEYS];
+
+			/*
+			 * Extract the index column values and isnull flags from the
+			 * existing tuple.
+			 */
+			FormIndexDatum(indexInfo, existing_slot, estate, values, nulls);
+
+			if (nulls[sk_attno - 1])
+			{
+				all_not_null = false;
+				break;
+			}
+		}
+
+		index_endscan(index_scan);
+		index_close(index, NoLock);
+		ExecDropSingleTupleTableSlot(existing_slot);
+
+		/* exit earlier */
+		if (!all_not_null)
+		{
+			FreeExecutorState(estate);
+			return false;
+		}
+	}
+
+	FreeExecutorState(estate);
+
+	return true;
+}
diff --git a/src/include/executor/executor.h b/src/include/executor/executor.h
index 5929aabc353..7f24caeeafb 100644
--- a/src/include/executor/executor.h
+++ b/src/include/executor/executor.h
@@ -756,6 +756,8 @@ extern void check_exclusion_constraint(Relation heap, Relation index,
 									   const Datum *values, const bool *isnull,
 									   EState *estate, bool newIndex);
 
+extern bool index_check_notnull(Relation relation, List *notnull_attnums);
+
 /*
  * prototypes from functions in execReplication.c
  */
diff --git a/src/test/isolation/expected/indexscan-check-notnull.out b/src/test/isolation/expected/indexscan-check-notnull.out
new file mode 100644
index 00000000000..c6a652e2518
--- /dev/null
+++ b/src/test/isolation/expected/indexscan-check-notnull.out
@@ -0,0 +1,97 @@
+Parsed test spec with 2 sessions
+
+starting permutation: s1_b1 s2_b1 s1_d1 s2_a1 s1_c1 s2_c1 s1_q1
+step s1_b1: BEGIN ISOLATION LEVEL REPEATABLE READ;
+step s2_b1: BEGIN ISOLATION LEVEL REPEATABLE READ;
+step s1_d1: DELETE FROM t;
+step s2_a1: ALTER TABLE t ADD CONSTRAINT t1_nn NOT NULL a; <waiting ...>
+step s1_c1: COMMIT;
+step s2_a1: <... completed>
+step s2_c1: COMMIT;
+step s1_q1: SELECT conname, conrelid::regclass, contype, convalidated
+              FROM pg_constraint WHERE conname = 't1_nn';
+
+conname|conrelid|contype|convalidated
+-------+--------+-------+------------
+t1_nn  |t       |n      |t           
+(1 row)
+
+
+starting permutation: s1_b2 s2_b1 s1_d1 s2_a1 s1_c1 s2_c1 s1_q1
+step s1_b2: BEGIN;
+step s2_b1: BEGIN ISOLATION LEVEL REPEATABLE READ;
+step s1_d1: DELETE FROM t;
+step s2_a1: ALTER TABLE t ADD CONSTRAINT t1_nn NOT NULL a; <waiting ...>
+step s1_c1: COMMIT;
+step s2_a1: <... completed>
+step s2_c1: COMMIT;
+step s1_q1: SELECT conname, conrelid::regclass, contype, convalidated
+              FROM pg_constraint WHERE conname = 't1_nn';
+
+conname|conrelid|contype|convalidated
+-------+--------+-------+------------
+t1_nn  |t       |n      |t           
+(1 row)
+
+
+starting permutation: s1_b1 s2_b2 s1_d1 s2_a1 s1_c1 s2_c1 s1_q1
+step s1_b1: BEGIN ISOLATION LEVEL REPEATABLE READ;
+step s2_b2: BEGIN;
+step s1_d1: DELETE FROM t;
+step s2_a1: ALTER TABLE t ADD CONSTRAINT t1_nn NOT NULL a; <waiting ...>
+step s1_c1: COMMIT;
+step s2_a1: <... completed>
+step s2_c1: COMMIT;
+step s1_q1: SELECT conname, conrelid::regclass, contype, convalidated
+              FROM pg_constraint WHERE conname = 't1_nn';
+
+conname|conrelid|contype|convalidated
+-------+--------+-------+------------
+t1_nn  |t       |n      |t           
+(1 row)
+
+
+starting permutation: s1_b1 s2_b1 s2_a1 s1_r1 s2_r1
+step s1_b1: BEGIN ISOLATION LEVEL REPEATABLE READ;
+step s2_b1: BEGIN ISOLATION LEVEL REPEATABLE READ;
+step s2_a1: ALTER TABLE t ADD CONSTRAINT t1_nn NOT NULL a;
+ERROR:  column "a" of relation "t" contains null values
+step s1_r1: ROLLBACK;
+step s2_r1: ROLLBACK;
+
+starting permutation: s1_b1 s2_b2 s2_d1 s1_d1 s2_r1 s1_a1 s1_q1 s1_r1
+step s1_b1: BEGIN ISOLATION LEVEL REPEATABLE READ;
+step s2_b2: BEGIN;
+step s2_d1: DROP INDEX t_ab_idx;
+step s1_d1: DELETE FROM t; <waiting ...>
+step s2_r1: ROLLBACK;
+step s1_d1: <... completed>
+step s1_a1: ALTER TABLE t ADD CONSTRAINT t1_nn NOT NULL a;
+step s1_q1: SELECT conname, conrelid::regclass, contype, convalidated
+              FROM pg_constraint WHERE conname = 't1_nn';
+
+conname|conrelid|contype|convalidated
+-------+--------+-------+------------
+t1_nn  |t       |n      |t           
+(1 row)
+
+step s1_r1: ROLLBACK;
+
+starting permutation: s1_b2 s2_b1 s1_d1 s2_d1 s1_s0 s1_a1 s1_c1 s2_c1 s1_q1
+step s1_b2: BEGIN;
+step s2_b1: BEGIN ISOLATION LEVEL REPEATABLE READ;
+step s1_d1: DELETE FROM t;
+step s2_d1: DROP INDEX t_ab_idx; <waiting ...>
+step s1_s0: SAVEPOINT s0;
+step s1_a1: ALTER TABLE t ADD CONSTRAINT t1_nn NOT NULL a;
+step s1_c1: COMMIT;
+step s2_d1: <... completed>
+step s2_c1: COMMIT;
+step s1_q1: SELECT conname, conrelid::regclass, contype, convalidated
+              FROM pg_constraint WHERE conname = 't1_nn';
+
+conname|conrelid|contype|convalidated
+-------+--------+-------+------------
+t1_nn  |t       |n      |t           
+(1 row)
+
diff --git a/src/test/isolation/isolation_schedule b/src/test/isolation/isolation_schedule
index 01ff1c6586f..7ce6bbcaf89 100644
--- a/src/test/isolation/isolation_schedule
+++ b/src/test/isolation/isolation_schedule
@@ -58,6 +58,7 @@ test: merge-delete
 test: merge-update
 test: merge-match-recheck
 test: merge-join
+test: indexscan-check-notnull
 test: delete-abort-savept
 test: delete-abort-savept-2
 test: aborted-keyrevoke
diff --git a/src/test/isolation/specs/indexscan-check-notnull.spec b/src/test/isolation/specs/indexscan-check-notnull.spec
new file mode 100644
index 00000000000..05b4488550c
--- /dev/null
+++ b/src/test/isolation/specs/indexscan-check-notnull.spec
@@ -0,0 +1,45 @@
+
+#
+# using indexscan to check a column not-null constraint
+# is satisfied or not.
+#
+
+setup
+{
+  CREATE TABLE t (a int, b int);
+  CREATE INDEX t_ab_idx on t(a,b);
+  INSERT INTO t values (null, 1);
+  INSERT INTO t SELECT x, x*10 FROM generate_series(1,3) g(x);
+}
+
+teardown
+{
+  DROP TABLE t;
+}
+
+session s1
+step s1_b1  { BEGIN ISOLATION LEVEL REPEATABLE READ; }
+step s1_b2  { BEGIN; }
+step s1_d1  { DELETE FROM t;}
+step s1_s0  { SAVEPOINT s0;}
+step s1_a1  { ALTER TABLE t ADD CONSTRAINT t1_nn NOT NULL a;}
+step s1_q1  { SELECT conname, conrelid::regclass, contype, convalidated
+              FROM pg_constraint WHERE conname = 't1_nn';
+            }
+step s1_r1  { ROLLBACK; }
+step s1_c1  { COMMIT; }
+
+session s2
+step s2_b1  { BEGIN ISOLATION LEVEL REPEATABLE READ; }
+step s2_b2  { BEGIN; }
+step s2_a1  { ALTER TABLE t ADD CONSTRAINT t1_nn NOT NULL a;}
+step s2_d1  { DROP INDEX t_ab_idx;}
+step s2_r1  { ROLLBACK; }
+step s2_c1  { COMMIT; }
+
+permutation s1_b1 s2_b1 s1_d1 s2_a1 s1_c1 s2_c1 s1_q1
+permutation s1_b2 s2_b1 s1_d1 s2_a1 s1_c1 s2_c1 s1_q1
+permutation s1_b1 s2_b2 s1_d1 s2_a1 s1_c1 s2_c1 s1_q1
+permutation s1_b1 s2_b1 s2_a1 s1_r1 s2_r1
+permutation s1_b1 s2_b2 s2_d1 s1_d1 s2_r1 s1_a1 s1_q1 s1_r1
+permutation s1_b2 s2_b1 s1_d1 s2_d1 s1_s0 s1_a1 s1_c1 s2_c1 s1_q1
diff --git a/src/test/modules/test_misc/meson.build b/src/test/modules/test_misc/meson.build
index 6e8db1621a7..56faf359b29 100644
--- a/src/test/modules/test_misc/meson.build
+++ b/src/test/modules/test_misc/meson.build
@@ -19,6 +19,7 @@ tests += {
       't/008_replslot_single_user.pl',
       't/009_log_temp_files.pl',
       't/010_index_concurrently_upsert.pl',
+      't/011_indexscan_validate_notnull.pl',
     ],
     # The injection points are cluster-wide, so disable installcheck
     'runningcheck': false,
diff --git a/src/test/modules/test_misc/t/011_indexscan_validate_notnull.pl b/src/test/modules/test_misc/t/011_indexscan_validate_notnull.pl
new file mode 100644
index 00000000000..a3f3cb409b6
--- /dev/null
+++ b/src/test/modules/test_misc/t/011_indexscan_validate_notnull.pl
@@ -0,0 +1,163 @@
+# Copyright (c) 2025, PostgreSQL Global Development Group
+
+# Verify that indexscan mechanism can speedup ALTER TABLE ADD NOT NULL
+
+
+use strict;
+use warnings FATAL => 'all';
+use PostgreSQL::Test::Cluster;
+use PostgreSQL::Test::Utils;
+use Test::More;
+
+# Initialize a test cluster
+my $node = PostgreSQL::Test::Cluster->new('primary');
+$node->init();
+# Turn message level up to DEBUG1 so that we get the messages we want to see
+$node->append_conf('postgresql.conf', 'client_min_messages = DEBUG1');
+$node->start;
+
+# Run a SQL command and return psql's stderr (including debug messages)
+sub run_sql_command
+{
+	my $sql = shift;
+	my $stderr;
+
+	$node->psql(
+		'postgres',
+		$sql,
+		stderr => \$stderr,
+		on_error_die => 1,
+		on_error_stop => 1);
+	return $stderr;
+}
+
+# Check whether result of run_sql_command shows that we did a verify pass
+sub is_table_verified
+{
+	my $output = shift;
+	return index($output, 'DEBUG:  verifying table') != -1;
+}
+
+# Check whether result of run_sql_command shows that we did a verify pass
+sub is_indexscan_veritify_notnull
+{
+	my $output = shift;
+	return index($output, 'DEBUG:  all new not-null constraints on relation') != -1;
+}
+
+my $output;
+
+note "test alter table SET NOT NULL using indexscan with partitioned table";
+
+run_sql_command(
+    'CREATE TABLE tp (a int, b int, c int, d int ) PARTITION BY range(a);
+     CREATE TABLE tpp1 partition of tp for values from ( 1 ) to (10);
+     CREATE TABLE tpp2 partition of tp for values from ( 10 ) to (21);
+     INSERT INTO tp select g, g + 10, g + 15, g + random(min=>1::int, max=>10::int) from generate_series(1,19) g;
+     CREATE INDEX ON tp(b); ');
+
+$output = run_sql_command('ALTER TABLE tp ALTER COLUMN b SET NOT NULL;');
+ok(is_indexscan_veritify_notnull($output),
+	'column b will use indexscan to verify not-null status, no need scan table');
+ok( $output =~
+	  m/all new not-null constraints on relation "tpp1" have been validated by using index scan/,
+	'all newly added constraints proved by indexscan');
+
+run_sql_command(
+	'ALTER TABLE tp ALTER COLUMN b DROP NOT NULL;');
+
+# use indexes on partitions to fast vertifing not-null should be ok
+$output = run_sql_command('ALTER TABLE tpp1 ALTER COLUMN b SET NOT NULL;');
+ok(is_indexscan_veritify_notnull($output), 'use indexscan to validate column b not-null will not scan table');
+ok(!is_table_verified($output), 'no table scan for pp1');
+ok( $output =~
+	  m/all new not-null constraints on relation "tpp1" have been validated by using index scan/,
+	'all newly added constraints proved by indexscan');
+
+$output = run_sql_command('ALTER TABLE tpp2 ALTER COLUMN b SET NOT NULL;');
+ok(is_indexscan_veritify_notnull($output), 'use indexscan to validate column b not-null, will not scan table');
+ok(!is_table_verified($output), 'no table scan for tpp2');
+ok( $output =~
+	  m/all new not-null constraints on relation "tpp2" have been validated by using index scan/,
+	'all newly added constraints proved by indexscan');
+
+run_sql_command(
+	'ALTER TABLE tp ALTER COLUMN b DROP NOT NULL;');
+
+# table rewrite then can not use indexscan to verify not-null constraint
+$output = run_sql_command(
+	'ALTER TABLE tp ALTER COLUMN b SET NOT NULL, ALTER COLUMN b SET DATA TYPE bigint;'
+);
+ok(!is_table_verified($output), 'no table scan for tp');
+ok(!is_indexscan_veritify_notnull($output), 'table tp will rewrite, can not use indexscan to verify not-null constraints on it');
+
+# test using indexscan with multiple not-null constraints
+run_sql_command(
+    'ALTER TABLE tp ALTER COLUMN b DROP NOT NULL;
+	 CREATE INDEX ON tp(c);
+	 CREATE INDEX ON tp(d); ');
+
+# one column can use indexscan, another can not, so can not use indexscan to verify not-null
+$output = run_sql_command(
+	'ALTER TABLE tp ALTER COLUMN a SET NOT NULL, ADD CONSTRAINT c_nn NOT NULL c');
+ok(is_table_verified($output), 'table scan for tp');
+ok(!is_indexscan_veritify_notnull($output), 'can not use indexscan to verify not-null constraints on table tp');
+
+# all columns have index on it
+# use indexscan to verify multiple not-null constraints should just fine
+$output = run_sql_command(
+	'ALTER TABLE tp ALTER COLUMN d SET NOT NULL, ADD CONSTRAINT c_nn NOT NULL c, ALTER COLUMN b SET NOT NULL;');
+ok(!is_table_verified($output), 'no table scan for tp');
+ok(is_indexscan_veritify_notnull($output),
+	'using indexscan to verify not-null constraints on column b, c, d, no need table scan');
+
+# test with non-partitioned table and other non-Btree index.
+run_sql_command(
+    'CREATE TABLE t1(f1 INT, f2 int, f3 int,f4 int, f5 int);
+     INSERT INTO t1 select g, g+1, g+2, g+3, g+4 from generate_series(1, 100) g;
+     CREATE INDEX t1_f1_f2_idx ON t1(f1,f2);
+     CREATE UNIQUE INDEX t1_f3idx ON t1(f3);
+     CREATE INDEX t1_f3f4idx ON t1(f3) include(f4);
+     CREATE INDEX hash_f5_idx ON t1 USING hash (f5 int4_ops); ');
+
+# ALTER TABLE VALIDATE CONSTRAINT can not use indexscan,
+# because it only hold ShareUpdateExclusiveLock lock.
+run_sql_command('ALTER TABLE t1 ADD CONSTRAINT nn_t1_f2 NOT NULL f2 NOT VALID;');
+
+$output = run_sql_command(
+	'ALTER TABLE t1 VALIDATE CONSTRAINT nn_t1_f2;'
+);
+ok(!is_indexscan_veritify_notnull($output), 'can not use indexscan for ALTER TABLE VALIDATE CONSTRAINT command');
+run_sql_command('ALTER TABLE t1 DROP CONSTRAINT nn_t1_f2;');
+
+$output = run_sql_command(
+	'ALTER TABLE t1 ALTER COLUMN f1 SET NOT NULL, ALTER f1 type bigint;'
+);
+ok(!is_indexscan_veritify_notnull($output), 'table t1 will rewrite, can not use indexscan to validate not-null constraints on t1');
+
+run_sql_command('ALTER TABLE t1 ALTER COLUMN f1 DROP NOT NULL;');
+run_sql_command('ALTER TABLE t1 ADD CONSTRAINT nn NOT NULL f1, ALTER f1 type bigint;');
+
+# can use indexscan mechanism to fast add multiple not-null constraints
+$output = run_sql_command(
+	'ALTER TABLE t1 ALTER COLUMN f2 SET NOT NULL, ALTER COLUMN f1 SET NOT NULL;'
+);
+ok( $output =~
+	  m/all new not-null constraints on relation "t1" have been validated by using index scan/,
+	'all not-null constraints are validated by indexscan');
+
+# using indexscan mechanism to fast add a not-null can only apply to key columns, not include column
+$output = run_sql_command(
+	'ALTER TABLE t1 ADD CONSTRAINT nnf4 NOT NULL f4;'
+);
+ok(!is_indexscan_veritify_notnull($output), 'can not use indexscan to validate not-null constraint on t1');
+
+# if index is not btree index then cannot use indexscan mechanism to fast add not-null constraint
+$output = run_sql_command(
+	'ALTER TABLE t1 ADD CONSTRAINT nn_f5 NOT NULL f5;'
+);
+ok(!is_indexscan_veritify_notnull($output), 'can not use indexscan to validate not-null constraints on t1');
+
+$node->stop('fast');
+
+done_testing();
-- 
2.47.3


--xpkr6zhfzd3fjt76--





^ permalink  raw  reply  [nested|flat] 150+ messages in thread

* [PATCH v8] using indexscan to speedup add not null constraints
@ 2025-10-20 05:29  jian he <[email protected]>
  0 siblings, 0 replies; 150+ messages in thread

From: jian he @ 2025-10-20 05:29 UTC (permalink / raw)

This patch tries to use index_beginscan() / index_getnext() / index_endscan()
mentioned in [1] to speedup adding not-null constraints to the existing table.

The main logic happens in phase3 ATRewriteTable
1. collect all not-null constraints.
2. For each not-null constraint, check whether there is a corresponding index
available for validation. If not, then can not use indexscan to verify not-null
constraints.
3. If any of the following conditions are true
  * table scan or rewrite is required,
  * table wasn't locked with `AccessExclusiveLock`
  * the NOT NULL constraint applies to a virtual generated column
 then index scan cannot be used for fast validation.
4. If all conditions are satisfied, attempt to use indexscan to verify
whether the column contains any NULL values.

concurrency concern:
ALTER TABLE SET NOT NULL will take an ACCESS EXCLUSIVE lock, so there is less
variant of racing issue can occur?  to prove accurate, I wrote some isolation
tests. see[2]

performance:
demo:
case when: %20 percent values are NULL and have been deleted from heap but they
still on the index.

drop table if exists t;
create unlogged table t(a int, b int) with (autovacuum_enabled = off, vacuum_index_cleanup=off);
insert into t select case when g % 5 = 0 then null else g end, g+1
from generate_series(1,1_000_000) g;
create index t_idx_a on t(a);
delete from t where a is null;

alter table t alter column a drop not null;
alter table t add constraint t1 not null a;

the above two statement running several times:
patch Time:: 1.084  ms
master Time: 12.045 ms

references:
[1] https://postgr.es/m/CA%2BTgmoa5NKz8iGW_9v7wz%3D-%2BzQFu%3DE4SZoaTaU1znLaEXRYp-Q%40mail.gmail.com
[2] https://postgr.es/m/900056D1-32DF-4927-8251-3E0C0DC407FD%40anarazel.de
discussion: https://postgr.es/m/CACJufxFiW=4k1is=F1J=r-Cx1RuByXQPUrWB331U47rSnGz+hw@mail.gmail.com
commitfest entry: https://commitfest.postgresql.org/patch/5444
---
 src/backend/commands/tablecmds.c              | 116 +++++++++-
 src/backend/executor/execIndexing.c           | 213 ++++++++++++++++++
 src/include/executor/executor.h               |   2 +
 .../expected/indexscan-check-notnull.out      |  97 ++++++++
 src/test/isolation/isolation_schedule         |   1 +
 .../specs/indexscan-check-notnull.spec        |  45 ++++
 src/test/modules/test_misc/meson.build        |   1 +
 .../t/011_indexscan_validate_notnull.pl       | 163 ++++++++++++++
 8 files changed, 632 insertions(+), 6 deletions(-)
 create mode 100644 src/test/isolation/expected/indexscan-check-notnull.out
 create mode 100644 src/test/isolation/specs/indexscan-check-notnull.spec
 create mode 100644 src/test/modules/test_misc/t/011_indexscan_validate_notnull.pl

diff --git a/src/backend/commands/tablecmds.c b/src/backend/commands/tablecmds.c
index f976c0e5c7e..2af06630b35 100644
--- a/src/backend/commands/tablecmds.c
+++ b/src/backend/commands/tablecmds.c
@@ -210,16 +210,19 @@ typedef struct AlteredTableInfo
 	List	   *changedStatisticsDefs;	/* string definitions of same */
 } AlteredTableInfo;
 
-/* Struct describing one new constraint to check in Phase 3 scan */
-/* Note: new not-null constraints are handled elsewhere */
+/*
+ * Struct describing one new constraint to check in Phase 3 scan. Note: new
+ * not-null constraints are handled here too.
+*/
 typedef struct NewConstraint
 {
 	char	   *name;			/* Constraint name, or NULL if none */
-	ConstrType	contype;		/* CHECK or FOREIGN */
+	ConstrType	contype;		/* CHECK or FOREIGN or NOT NULL */
 	Oid			refrelid;		/* PK rel, if FOREIGN */
 	Oid			refindid;		/* OID of PK's index, if FOREIGN */
 	bool		conwithperiod;	/* Whether the new FOREIGN KEY uses PERIOD */
 	Oid			conid;			/* OID of pg_constraint entry, if FOREIGN */
+	int			attnum;			/* NOT NULL constraint attribute number */
 	Node	   *qual;			/* Check expr or CONSTR_FOREIGN Constraint */
 	ExprState  *qualstate;		/* Execution state for CHECK expr */
 } NewConstraint;
@@ -6217,6 +6220,9 @@ ATRewriteTable(AlteredTableInfo *tab, Oid OIDNewHeap)
 				needscan = true;
 				con->qualstate = ExecPrepareExpr((Expr *) expand_generated_columns_in_expr(con->qual, oldrel, 1), estate);
 				break;
+			case CONSTR_NOTNULL:
+				/* Nothing to do here */
+				break;
 			case CONSTR_FOREIGN:
 				/* Nothing to do here */
 				break;
@@ -6270,10 +6276,69 @@ ATRewriteTable(AlteredTableInfo *tab, Oid OIDNewHeap)
 														wholeatt->attnum);
 			}
 		}
-		if (notnull_attrs || notnull_virtual_attrs)
-			needscan = true;
 	}
 
+	/*-
+	 * If we have to verify new not-null constraints and don't have any other
+	 * reason to fully scan the table, then we can use indexes to test for
+	 * absence of NULL values instead of scanning.  The following conditions
+	 * must be met:
+	 * - we're operating on a regular table
+	 * - we hold AccessExclusiveLock on the table
+	 * - no not-null constraint covers a virtual generated column,
+	 *   because no indexes can be created on them
+	 */
+	if (!needscan &&
+		newrel == NULL &&
+		tab->verify_new_notnull &&
+		notnull_virtual_attrs == NIL &&
+		oldrel->rd_rel->relkind == RELKIND_RELATION &&
+		CheckRelationLockedByMe(oldrel, AccessExclusiveLock, false))
+	{
+		List	   *notnull_attnums = NIL;
+
+		Assert(!tab->rewrite);
+
+		foreach(l, tab->constraints)
+		{
+			Form_pg_attribute attr;
+			NewConstraint *con = lfirst(l);
+
+			if (con->contype != CONSTR_NOTNULL)
+				continue;
+
+			attr = TupleDescAttr(newTupDesc, con->attnum - 1);
+
+			Assert(attr->attnotnull);
+			Assert(attr->attnum == con->attnum);
+
+			if (attr->attgenerated == ATTRIBUTE_GENERATED_VIRTUAL)
+			{
+				needscan = true;
+				break;
+			}
+
+			notnull_attnums = lappend_int(notnull_attnums, attr->attnum);
+		}
+
+		/*
+		 * Validate new NOT NULL constraints, unless we need a scan for other
+		 * reasons, because we can validate them cheaply there, and doing it
+		 * also here would be a waste of cycles.
+		 */
+		if (notnull_attnums != NIL && !needscan)
+		{
+			if (!index_check_notnull(oldrel, notnull_attnums))
+				needscan = true;
+			else
+				ereport(DEBUG1,
+						errmsg_internal("all new not-null constraints on relation \"%s\" have been validated by using index scan",
+										RelationGetRelationName(oldrel)));
+		}
+	}
+	else if (notnull_attrs || notnull_virtual_attrs)
+		needscan = true;
+
 	if (newrel || needscan)
 	{
 		ExprContext *econtext;
@@ -7949,6 +8014,7 @@ ATExecSetNotNull(List **wqueue, Relation rel, char *conName, char *colName,
 	CookedConstraint *ccon;
 	List	   *cooked;
 	bool		is_no_inherit = false;
+	AlteredTableInfo *tab = NULL;
 
 	/* Guard against stack overflow due to overly deep inheritance tree. */
 	check_stack_depth();
@@ -8073,10 +8139,32 @@ ATExecSetNotNull(List **wqueue, Relation rel, char *conName, char *colName,
 	constraint->is_no_inherit = is_no_inherit;
 	constraint->conname = conName;
 
+	tab = ATGetQueueEntry(wqueue, rel);
+
 	/* and do it */
 	cooked = AddRelationNewConstraints(rel, NIL, list_make1(constraint),
 									   false, !recursing, false, NULL);
 	ccon = linitial(cooked);
+
+	Assert(ccon->contype == CONSTR_NOTNULL);
+
+	/*
+	 * We may use indexscan to vertify not-null constraint in Phase3.  Add the
+	 * to-be-validated not-null constraint to Phase 3's queue.
+	 */
+	if (!ccon->skip_validation)
+	{
+		NewConstraint *newcon;
+
+		newcon = (NewConstraint *) palloc0(sizeof(NewConstraint));
+
+		newcon->name = ccon->name;
+		newcon->contype = ccon->contype;
+		newcon->attnum = ccon->attnum;
+
+		tab->constraints = lappend(tab->constraints, newcon);
+	}
+
 	ObjectAddressSet(address, ConstraintRelationId, ccon->conoid);
 
 	InvokeObjectPostAlterHook(RelationRelationId,
@@ -9983,13 +10071,15 @@ ATAddCheckNNConstraint(List **wqueue, AlteredTableInfo *tab, Relation rel,
 	{
 		CookedConstraint *ccon = (CookedConstraint *) lfirst(lcon);
 
-		if (!ccon->skip_validation && ccon->contype != CONSTR_NOTNULL)
+		if (!ccon->skip_validation)
 		{
 			NewConstraint *newcon;
 
 			newcon = palloc0_object(NewConstraint);
 			newcon->name = ccon->name;
 			newcon->contype = ccon->contype;
+			if (ccon->contype == CONSTR_NOTNULL)
+				newcon->attnum = ccon->attnum;
 			newcon->qual = ccon->expr;
 
 			tab->constraints = lappend(tab->constraints, newcon);
@@ -13258,6 +13348,7 @@ QueueNNConstraintValidation(List **wqueue, Relation conrel, Relation rel,
 	List	   *children = NIL;
 	AttrNumber	attnum;
 	char	   *colname;
+	NewConstraint *newcon;
 
 	con = (Form_pg_constraint) GETSTRUCT(contuple);
 	Assert(con->contype == CONSTRAINT_NOTNULL);
@@ -13321,7 +13412,20 @@ QueueNNConstraintValidation(List **wqueue, Relation conrel, Relation rel,
 	/* Set attnotnull appropriately without queueing another validation */
 	set_attnotnull(NULL, rel, attnum, true, false);
 
+	/*
+	 * Queue validation for phase 3.
+	 *
+	 * ALTER TABLE SET NOT NULL will add NOT NULL constraint to
+	 * AlteredTableInfo->constraints, for consistency, do the same here.
+	 */
+	newcon = (NewConstraint *) palloc0(sizeof(NewConstraint));
+	newcon->name = colname;
+	newcon->contype = CONSTR_NOTNULL;
+	newcon->attnum = attnum;
+
+	/* Find or create work queue entry for this table */
 	tab = ATGetQueueEntry(wqueue, rel);
+	tab->constraints = lappend(tab->constraints, newcon);
 	tab->verify_new_notnull = true;
 
 	/*
diff --git a/src/backend/executor/execIndexing.c b/src/backend/executor/execIndexing.c
index 6ae0f959592..88694ce0335 100644
--- a/src/backend/executor/execIndexing.c
+++ b/src/backend/executor/execIndexing.c
@@ -108,12 +108,15 @@
 
 #include "access/genam.h"
 #include "access/relscan.h"
+#include "access/table.h"
 #include "access/tableam.h"
 #include "access/xact.h"
 #include "catalog/index.h"
+#include "catalog/pg_am_d.h"
 #include "executor/executor.h"
 #include "nodes/nodeFuncs.h"
 #include "storage/lmgr.h"
+#include "utils/fmgroids.h"
 #include "utils/injection_point.h"
 #include "utils/multirangetypes.h"
 #include "utils/rangetypes.h"
@@ -146,6 +149,7 @@ static bool index_expression_changed_walker(Node *node,
 											Bitmapset *allUpdatedCols);
 static void ExecWithoutOverlapsNotEmpty(Relation rel, NameData attname, Datum attval,
 										char typtype, Oid atttypid);
+static bool index_check_notnull_internal(Relation relation, List *attnums, List *idxs);
 
 /* ----------------------------------------------------------------
  *		ExecOpenIndices
@@ -1178,3 +1182,212 @@ ExecWithoutOverlapsNotEmpty(Relation rel, NameData attname, Datum attval, char t
 				 errmsg("empty WITHOUT OVERLAPS value found in column \"%s\" in relation \"%s\"",
 						NameStr(attname), RelationGetRelationName(rel))));
 }
+
+/*
+ * notnull_attnums: list of attribute numbers of all new not-null constraints.
+ *
+ * First check whether the relation has a suitable index for each not-null
+ * attribute, then using indexscan mechanism to verify that *all* attributes on
+ * notnull_attnums are indeed not null.
+ *
+ * Returning true means all new not-null constraints have been verified, no
+ * need an extra scan to verify newly added not-null constraints.
+ */
+bool
+index_check_notnull(Relation relation, List *notnull_attnums)
+{
+	Relation	pg_index;
+	Relation	index_rel;
+	SysScanDesc indscan;
+	ScanKeyData skey;
+	HeapTuple	htup;
+	TupleDesc	tupdesc;
+	Form_pg_attribute attr;
+	List	   *idxs = NIL;
+	List	   *attnums = NIL;
+
+	tupdesc = RelationGetDescr(relation);
+
+	/* Prepare to scan pg_index for entries having indrelid = this rel */
+	ScanKeyInit(&skey,
+				Anum_pg_index_indrelid,
+				BTEqualStrategyNumber, F_OIDEQ,
+				ObjectIdGetDatum(RelationGetRelid(relation)));
+
+	pg_index = table_open(IndexRelationId, AccessShareLock);
+	indscan = systable_beginscan(pg_index, IndexIndrelidIndexId, true,
+								 NULL, 1, &skey);
+
+	while (HeapTupleIsValid(htup = systable_getnext(indscan)))
+	{
+		Form_pg_index index = (Form_pg_index) GETSTRUCT(htup);
+
+		/*
+		 * we can only use non-deferred, validated, and alive btree index to
+		 * validate not-null constraints
+		 */
+		if (!index->indimmediate || !index->indisvalid || !index->indislive)
+			continue;
+
+		/* can not use expression index or partial index too */
+		if (!heap_attisnull(htup, Anum_pg_index_indexprs, NULL) ||
+			!heap_attisnull(htup, Anum_pg_index_indpred, NULL))
+			continue;
+
+		index_rel = index_open(index->indexrelid, AccessShareLock);
+
+		/* can only apply to btree index */
+		if (index_rel->rd_rel->relam != BTREE_AM_OID)
+		{
+			index_close(index_rel, AccessShareLock);
+			continue;
+		}
+
+		/* collect index attnums while loop */
+		for (int i = 0; i < index->indnkeyatts; i++)
+		{
+			attr = TupleDescAttr(tupdesc, (index->indkey.values[i] - 1));
+
+			if (attr->attisdropped)
+				continue;
+
+			if (list_member_int(notnull_attnums, attr->attnum) &&
+				!list_member_int(attnums, attr->attnum))
+			{
+				attnums = lappend_int(attnums, attr->attnum);
+				idxs = lappend_oid(idxs, index->indexrelid);
+			}
+		}
+		index_close(index_rel, NoLock);
+	}
+	systable_endscan(indscan);
+	table_close(pg_index, AccessShareLock);
+
+	if (attnums == NIL)
+		return false;
+
+	/*
+	 * every not-null constraint requires an index for indexscan.  If no such
+	 * index exists, we need to use regular table scan to validate not-null
+	 * constraints.
+	 */
+	foreach_int(attno, notnull_attnums)
+	{
+		if (!list_member_int(attnums, attno))
+			return false;
+	}
+
+	return index_check_notnull_internal(relation, attnums, idxs);
+}
+
+/*
+ * Use indexscan mechanism to fast verify each attribute in "attnums" are
+ * not-null or not.
+ */
+static bool
+index_check_notnull_internal(Relation relation, List *attnums, List *idxs)
+{
+	EState	   *estate;
+	ExprContext *econtext;
+	TupleTableSlot *existing_slot;
+	bool		all_not_null = true;
+	ListCell   *lc,
+			   *lc2;
+
+	/*
+	 * Need an EState for slot to hold the current tuple.
+	 */
+	estate = CreateExecutorState();
+	econtext = GetPerTupleExprContext(estate);
+
+	forboth(lc, attnums, lc2, idxs)
+	{
+		SnapshotData DirtySnapshot;
+		IndexScanDesc index_scan;
+		ScanKeyData scankeys[INDEX_MAX_KEYS];
+		IndexInfo  *indexInfo;
+		AttrNumber	sk_attno = -1;
+		Relation	index;
+		int			indnkeyatts;
+
+		AttrNumber	attno = lfirst_int(lc);
+		Oid			indexoid = lfirst_oid(lc2);
+
+		existing_slot = table_slot_create(relation, NULL);
+
+		/* Arrange for econtext's scan tuple to be the tuple under test */
+		econtext->ecxt_scantuple = existing_slot;
+
+		index = index_open(indexoid, NoLock);
+
+		indexInfo = BuildIndexInfo(index);
+		indnkeyatts = IndexRelationGetNumberOfKeyAttributes(index);
+
+		/*
+		 * Search the tuples that are in the index for any violations,
+		 * including tuples that aren't visible yet.
+		 */
+		InitDirtySnapshot(DirtySnapshot);
+
+		for (int i = 0; i < indnkeyatts; i++)
+		{
+			if (indexInfo->ii_IndexAttrNumbers[i] == attno)
+			{
+				sk_attno = i + 1;
+				break;
+			}
+		}
+
+		if (sk_attno == -1)
+			elog(ERROR, "cache lookup failed for attribute number %d on index %u", indexoid, attno);
+
+		for (int i = 0; i < indnkeyatts; i++)
+		{
+			/* set up an IS NULL scan key so that we ignore not nulls */
+			ScanKeyEntryInitialize(&scankeys[i],
+								   SK_ISNULL | SK_SEARCHNULL,
+								   sk_attno,	/* index col to scan */
+								   InvalidStrategy, /* no strategy */
+								   InvalidOid,	/* no strategy subtype */
+								   InvalidOid,	/* no collation */
+								   InvalidOid,	/* no reg proc for this */
+								   (Datum) 0);	/* constant */
+		}
+
+		index_scan = index_beginscan(relation, index, &DirtySnapshot, NULL, indnkeyatts, 0);
+		index_rescan(index_scan, scankeys, indnkeyatts, NULL, 0);
+
+		while (index_getnext_slot(index_scan, ForwardScanDirection, existing_slot))
+		{
+			Datum		values[INDEX_MAX_KEYS];
+			bool		nulls[INDEX_MAX_KEYS];
+
+			/*
+			 * Extract the index column values and isnull flags from the
+			 * existing tuple.
+			 */
+			FormIndexDatum(indexInfo, existing_slot, estate, values, nulls);
+
+			if (nulls[sk_attno - 1])
+			{
+				all_not_null = false;
+				break;
+			}
+		}
+
+		index_endscan(index_scan);
+		index_close(index, NoLock);
+		ExecDropSingleTupleTableSlot(existing_slot);
+
+		/* exit earlier */
+		if (!all_not_null)
+		{
+			FreeExecutorState(estate);
+			return false;
+		}
+	}
+
+	FreeExecutorState(estate);
+
+	return true;
+}
diff --git a/src/include/executor/executor.h b/src/include/executor/executor.h
index 5929aabc353..7f24caeeafb 100644
--- a/src/include/executor/executor.h
+++ b/src/include/executor/executor.h
@@ -756,6 +756,8 @@ extern void check_exclusion_constraint(Relation heap, Relation index,
 									   const Datum *values, const bool *isnull,
 									   EState *estate, bool newIndex);
 
+extern bool index_check_notnull(Relation relation, List *notnull_attnums);
+
 /*
  * prototypes from functions in execReplication.c
  */
diff --git a/src/test/isolation/expected/indexscan-check-notnull.out b/src/test/isolation/expected/indexscan-check-notnull.out
new file mode 100644
index 00000000000..c6a652e2518
--- /dev/null
+++ b/src/test/isolation/expected/indexscan-check-notnull.out
@@ -0,0 +1,97 @@
+Parsed test spec with 2 sessions
+
+starting permutation: s1_b1 s2_b1 s1_d1 s2_a1 s1_c1 s2_c1 s1_q1
+step s1_b1: BEGIN ISOLATION LEVEL REPEATABLE READ;
+step s2_b1: BEGIN ISOLATION LEVEL REPEATABLE READ;
+step s1_d1: DELETE FROM t;
+step s2_a1: ALTER TABLE t ADD CONSTRAINT t1_nn NOT NULL a; <waiting ...>
+step s1_c1: COMMIT;
+step s2_a1: <... completed>
+step s2_c1: COMMIT;
+step s1_q1: SELECT conname, conrelid::regclass, contype, convalidated
+              FROM pg_constraint WHERE conname = 't1_nn';
+
+conname|conrelid|contype|convalidated
+-------+--------+-------+------------
+t1_nn  |t       |n      |t           
+(1 row)
+
+
+starting permutation: s1_b2 s2_b1 s1_d1 s2_a1 s1_c1 s2_c1 s1_q1
+step s1_b2: BEGIN;
+step s2_b1: BEGIN ISOLATION LEVEL REPEATABLE READ;
+step s1_d1: DELETE FROM t;
+step s2_a1: ALTER TABLE t ADD CONSTRAINT t1_nn NOT NULL a; <waiting ...>
+step s1_c1: COMMIT;
+step s2_a1: <... completed>
+step s2_c1: COMMIT;
+step s1_q1: SELECT conname, conrelid::regclass, contype, convalidated
+              FROM pg_constraint WHERE conname = 't1_nn';
+
+conname|conrelid|contype|convalidated
+-------+--------+-------+------------
+t1_nn  |t       |n      |t           
+(1 row)
+
+
+starting permutation: s1_b1 s2_b2 s1_d1 s2_a1 s1_c1 s2_c1 s1_q1
+step s1_b1: BEGIN ISOLATION LEVEL REPEATABLE READ;
+step s2_b2: BEGIN;
+step s1_d1: DELETE FROM t;
+step s2_a1: ALTER TABLE t ADD CONSTRAINT t1_nn NOT NULL a; <waiting ...>
+step s1_c1: COMMIT;
+step s2_a1: <... completed>
+step s2_c1: COMMIT;
+step s1_q1: SELECT conname, conrelid::regclass, contype, convalidated
+              FROM pg_constraint WHERE conname = 't1_nn';
+
+conname|conrelid|contype|convalidated
+-------+--------+-------+------------
+t1_nn  |t       |n      |t           
+(1 row)
+
+
+starting permutation: s1_b1 s2_b1 s2_a1 s1_r1 s2_r1
+step s1_b1: BEGIN ISOLATION LEVEL REPEATABLE READ;
+step s2_b1: BEGIN ISOLATION LEVEL REPEATABLE READ;
+step s2_a1: ALTER TABLE t ADD CONSTRAINT t1_nn NOT NULL a;
+ERROR:  column "a" of relation "t" contains null values
+step s1_r1: ROLLBACK;
+step s2_r1: ROLLBACK;
+
+starting permutation: s1_b1 s2_b2 s2_d1 s1_d1 s2_r1 s1_a1 s1_q1 s1_r1
+step s1_b1: BEGIN ISOLATION LEVEL REPEATABLE READ;
+step s2_b2: BEGIN;
+step s2_d1: DROP INDEX t_ab_idx;
+step s1_d1: DELETE FROM t; <waiting ...>
+step s2_r1: ROLLBACK;
+step s1_d1: <... completed>
+step s1_a1: ALTER TABLE t ADD CONSTRAINT t1_nn NOT NULL a;
+step s1_q1: SELECT conname, conrelid::regclass, contype, convalidated
+              FROM pg_constraint WHERE conname = 't1_nn';
+
+conname|conrelid|contype|convalidated
+-------+--------+-------+------------
+t1_nn  |t       |n      |t           
+(1 row)
+
+step s1_r1: ROLLBACK;
+
+starting permutation: s1_b2 s2_b1 s1_d1 s2_d1 s1_s0 s1_a1 s1_c1 s2_c1 s1_q1
+step s1_b2: BEGIN;
+step s2_b1: BEGIN ISOLATION LEVEL REPEATABLE READ;
+step s1_d1: DELETE FROM t;
+step s2_d1: DROP INDEX t_ab_idx; <waiting ...>
+step s1_s0: SAVEPOINT s0;
+step s1_a1: ALTER TABLE t ADD CONSTRAINT t1_nn NOT NULL a;
+step s1_c1: COMMIT;
+step s2_d1: <... completed>
+step s2_c1: COMMIT;
+step s1_q1: SELECT conname, conrelid::regclass, contype, convalidated
+              FROM pg_constraint WHERE conname = 't1_nn';
+
+conname|conrelid|contype|convalidated
+-------+--------+-------+------------
+t1_nn  |t       |n      |t           
+(1 row)
+
diff --git a/src/test/isolation/isolation_schedule b/src/test/isolation/isolation_schedule
index 01ff1c6586f..7ce6bbcaf89 100644
--- a/src/test/isolation/isolation_schedule
+++ b/src/test/isolation/isolation_schedule
@@ -58,6 +58,7 @@ test: merge-delete
 test: merge-update
 test: merge-match-recheck
 test: merge-join
+test: indexscan-check-notnull
 test: delete-abort-savept
 test: delete-abort-savept-2
 test: aborted-keyrevoke
diff --git a/src/test/isolation/specs/indexscan-check-notnull.spec b/src/test/isolation/specs/indexscan-check-notnull.spec
new file mode 100644
index 00000000000..05b4488550c
--- /dev/null
+++ b/src/test/isolation/specs/indexscan-check-notnull.spec
@@ -0,0 +1,45 @@
+
+#
+# using indexscan to check a column not-null constraint
+# is satisfied or not.
+#
+
+setup
+{
+  CREATE TABLE t (a int, b int);
+  CREATE INDEX t_ab_idx on t(a,b);
+  INSERT INTO t values (null, 1);
+  INSERT INTO t SELECT x, x*10 FROM generate_series(1,3) g(x);
+}
+
+teardown
+{
+  DROP TABLE t;
+}
+
+session s1
+step s1_b1  { BEGIN ISOLATION LEVEL REPEATABLE READ; }
+step s1_b2  { BEGIN; }
+step s1_d1  { DELETE FROM t;}
+step s1_s0  { SAVEPOINT s0;}
+step s1_a1  { ALTER TABLE t ADD CONSTRAINT t1_nn NOT NULL a;}
+step s1_q1  { SELECT conname, conrelid::regclass, contype, convalidated
+              FROM pg_constraint WHERE conname = 't1_nn';
+            }
+step s1_r1  { ROLLBACK; }
+step s1_c1  { COMMIT; }
+
+session s2
+step s2_b1  { BEGIN ISOLATION LEVEL REPEATABLE READ; }
+step s2_b2  { BEGIN; }
+step s2_a1  { ALTER TABLE t ADD CONSTRAINT t1_nn NOT NULL a;}
+step s2_d1  { DROP INDEX t_ab_idx;}
+step s2_r1  { ROLLBACK; }
+step s2_c1  { COMMIT; }
+
+permutation s1_b1 s2_b1 s1_d1 s2_a1 s1_c1 s2_c1 s1_q1
+permutation s1_b2 s2_b1 s1_d1 s2_a1 s1_c1 s2_c1 s1_q1
+permutation s1_b1 s2_b2 s1_d1 s2_a1 s1_c1 s2_c1 s1_q1
+permutation s1_b1 s2_b1 s2_a1 s1_r1 s2_r1
+permutation s1_b1 s2_b2 s2_d1 s1_d1 s2_r1 s1_a1 s1_q1 s1_r1
+permutation s1_b2 s2_b1 s1_d1 s2_d1 s1_s0 s1_a1 s1_c1 s2_c1 s1_q1
diff --git a/src/test/modules/test_misc/meson.build b/src/test/modules/test_misc/meson.build
index 6e8db1621a7..56faf359b29 100644
--- a/src/test/modules/test_misc/meson.build
+++ b/src/test/modules/test_misc/meson.build
@@ -19,6 +19,7 @@ tests += {
       't/008_replslot_single_user.pl',
       't/009_log_temp_files.pl',
       't/010_index_concurrently_upsert.pl',
+      't/011_indexscan_validate_notnull.pl',
     ],
     # The injection points are cluster-wide, so disable installcheck
     'runningcheck': false,
diff --git a/src/test/modules/test_misc/t/011_indexscan_validate_notnull.pl b/src/test/modules/test_misc/t/011_indexscan_validate_notnull.pl
new file mode 100644
index 00000000000..a3f3cb409b6
--- /dev/null
+++ b/src/test/modules/test_misc/t/011_indexscan_validate_notnull.pl
@@ -0,0 +1,163 @@
+# Copyright (c) 2025, PostgreSQL Global Development Group
+
+# Verify that indexscan mechanism can speedup ALTER TABLE ADD NOT NULL
+
+
+use strict;
+use warnings FATAL => 'all';
+use PostgreSQL::Test::Cluster;
+use PostgreSQL::Test::Utils;
+use Test::More;
+
+# Initialize a test cluster
+my $node = PostgreSQL::Test::Cluster->new('primary');
+$node->init();
+# Turn message level up to DEBUG1 so that we get the messages we want to see
+$node->append_conf('postgresql.conf', 'client_min_messages = DEBUG1');
+$node->start;
+
+# Run a SQL command and return psql's stderr (including debug messages)
+sub run_sql_command
+{
+	my $sql = shift;
+	my $stderr;
+
+	$node->psql(
+		'postgres',
+		$sql,
+		stderr => \$stderr,
+		on_error_die => 1,
+		on_error_stop => 1);
+	return $stderr;
+}
+
+# Check whether result of run_sql_command shows that we did a verify pass
+sub is_table_verified
+{
+	my $output = shift;
+	return index($output, 'DEBUG:  verifying table') != -1;
+}
+
+# Check whether result of run_sql_command shows that we did a verify pass
+sub is_indexscan_veritify_notnull
+{
+	my $output = shift;
+	return index($output, 'DEBUG:  all new not-null constraints on relation') != -1;
+}
+
+my $output;
+
+note "test alter table SET NOT NULL using indexscan with partitioned table";
+
+run_sql_command(
+    'CREATE TABLE tp (a int, b int, c int, d int ) PARTITION BY range(a);
+     CREATE TABLE tpp1 partition of tp for values from ( 1 ) to (10);
+     CREATE TABLE tpp2 partition of tp for values from ( 10 ) to (21);
+     INSERT INTO tp select g, g + 10, g + 15, g + random(min=>1::int, max=>10::int) from generate_series(1,19) g;
+     CREATE INDEX ON tp(b); ');
+
+$output = run_sql_command('ALTER TABLE tp ALTER COLUMN b SET NOT NULL;');
+ok(is_indexscan_veritify_notnull($output),
+	'column b will use indexscan to verify not-null status, no need scan table');
+ok( $output =~
+	  m/all new not-null constraints on relation "tpp1" have been validated by using index scan/,
+	'all newly added constraints proved by indexscan');
+
+run_sql_command(
+	'ALTER TABLE tp ALTER COLUMN b DROP NOT NULL;');
+
+# use indexes on partitions to fast vertifing not-null should be ok
+$output = run_sql_command('ALTER TABLE tpp1 ALTER COLUMN b SET NOT NULL;');
+ok(is_indexscan_veritify_notnull($output), 'use indexscan to validate column b not-null will not scan table');
+ok(!is_table_verified($output), 'no table scan for pp1');
+ok( $output =~
+	  m/all new not-null constraints on relation "tpp1" have been validated by using index scan/,
+	'all newly added constraints proved by indexscan');
+
+$output = run_sql_command('ALTER TABLE tpp2 ALTER COLUMN b SET NOT NULL;');
+ok(is_indexscan_veritify_notnull($output), 'use indexscan to validate column b not-null, will not scan table');
+ok(!is_table_verified($output), 'no table scan for tpp2');
+ok( $output =~
+	  m/all new not-null constraints on relation "tpp2" have been validated by using index scan/,
+	'all newly added constraints proved by indexscan');
+
+run_sql_command(
+	'ALTER TABLE tp ALTER COLUMN b DROP NOT NULL;');
+
+# table rewrite then can not use indexscan to verify not-null constraint
+$output = run_sql_command(
+	'ALTER TABLE tp ALTER COLUMN b SET NOT NULL, ALTER COLUMN b SET DATA TYPE bigint;'
+);
+ok(!is_table_verified($output), 'no table scan for tp');
+ok(!is_indexscan_veritify_notnull($output), 'table tp will rewrite, can not use indexscan to verify not-null constraints on it');
+
+# test using indexscan with multiple not-null constraints
+run_sql_command(
+    'ALTER TABLE tp ALTER COLUMN b DROP NOT NULL;
+	 CREATE INDEX ON tp(c);
+	 CREATE INDEX ON tp(d); ');
+
+# one column can use indexscan, another can not, so can not use indexscan to verify not-null
+$output = run_sql_command(
+	'ALTER TABLE tp ALTER COLUMN a SET NOT NULL, ADD CONSTRAINT c_nn NOT NULL c');
+ok(is_table_verified($output), 'table scan for tp');
+ok(!is_indexscan_veritify_notnull($output), 'can not use indexscan to verify not-null constraints on table tp');
+
+# all columns have index on it
+# use indexscan to verify multiple not-null constraints should just fine
+$output = run_sql_command(
+	'ALTER TABLE tp ALTER COLUMN d SET NOT NULL, ADD CONSTRAINT c_nn NOT NULL c, ALTER COLUMN b SET NOT NULL;');
+ok(!is_table_verified($output), 'no table scan for tp');
+ok(is_indexscan_veritify_notnull($output),
+	'using indexscan to verify not-null constraints on column b, c, d, no need table scan');
+
+# test with non-partitioned table and other non-Btree index.
+run_sql_command(
+    'CREATE TABLE t1(f1 INT, f2 int, f3 int,f4 int, f5 int);
+     INSERT INTO t1 select g, g+1, g+2, g+3, g+4 from generate_series(1, 100) g;
+     CREATE INDEX t1_f1_f2_idx ON t1(f1,f2);
+     CREATE UNIQUE INDEX t1_f3idx ON t1(f3);
+     CREATE INDEX t1_f3f4idx ON t1(f3) include(f4);
+     CREATE INDEX hash_f5_idx ON t1 USING hash (f5 int4_ops); ');
+
+# ALTER TABLE VALIDATE CONSTRAINT can not use indexscan,
+# because it only hold ShareUpdateExclusiveLock lock.
+run_sql_command('ALTER TABLE t1 ADD CONSTRAINT nn_t1_f2 NOT NULL f2 NOT VALID;');
+
+$output = run_sql_command(
+	'ALTER TABLE t1 VALIDATE CONSTRAINT nn_t1_f2;'
+);
+ok(!is_indexscan_veritify_notnull($output), 'can not use indexscan for ALTER TABLE VALIDATE CONSTRAINT command');
+run_sql_command('ALTER TABLE t1 DROP CONSTRAINT nn_t1_f2;');
+
+$output = run_sql_command(
+	'ALTER TABLE t1 ALTER COLUMN f1 SET NOT NULL, ALTER f1 type bigint;'
+);
+ok(!is_indexscan_veritify_notnull($output), 'table t1 will rewrite, can not use indexscan to validate not-null constraints on t1');
+
+run_sql_command('ALTER TABLE t1 ALTER COLUMN f1 DROP NOT NULL;');
+run_sql_command('ALTER TABLE t1 ADD CONSTRAINT nn NOT NULL f1, ALTER f1 type bigint;');
+
+# can use indexscan mechanism to fast add multiple not-null constraints
+$output = run_sql_command(
+	'ALTER TABLE t1 ALTER COLUMN f2 SET NOT NULL, ALTER COLUMN f1 SET NOT NULL;'
+);
+ok( $output =~
+	  m/all new not-null constraints on relation "t1" have been validated by using index scan/,
+	'all not-null constraints are validated by indexscan');
+
+# using indexscan mechanism to fast add a not-null can only apply to key columns, not include column
+$output = run_sql_command(
+	'ALTER TABLE t1 ADD CONSTRAINT nnf4 NOT NULL f4;'
+);
+ok(!is_indexscan_veritify_notnull($output), 'can not use indexscan to validate not-null constraint on t1');
+
+# if index is not btree index then cannot use indexscan mechanism to fast add not-null constraint
+$output = run_sql_command(
+	'ALTER TABLE t1 ADD CONSTRAINT nn_f5 NOT NULL f5;'
+);
+ok(!is_indexscan_veritify_notnull($output), 'can not use indexscan to validate not-null constraints on t1');
+
+$node->stop('fast');
+
+done_testing();
-- 
2.47.3


--xpkr6zhfzd3fjt76--





^ permalink  raw  reply  [nested|flat] 150+ messages in thread

* [PATCH v8] using indexscan to speedup add not null constraints
@ 2025-10-20 05:29  jian he <[email protected]>
  0 siblings, 0 replies; 150+ messages in thread

From: jian he @ 2025-10-20 05:29 UTC (permalink / raw)

This patch tries to use index_beginscan() / index_getnext() / index_endscan()
mentioned in [1] to speedup adding not-null constraints to the existing table.

The main logic happens in phase3 ATRewriteTable
1. collect all not-null constraints.
2. For each not-null constraint, check whether there is a corresponding index
available for validation. If not, then can not use indexscan to verify not-null
constraints.
3. If any of the following conditions are true
  * table scan or rewrite is required,
  * table wasn't locked with `AccessExclusiveLock`
  * the NOT NULL constraint applies to a virtual generated column
 then index scan cannot be used for fast validation.
4. If all conditions are satisfied, attempt to use indexscan to verify
whether the column contains any NULL values.

concurrency concern:
ALTER TABLE SET NOT NULL will take an ACCESS EXCLUSIVE lock, so there is less
variant of racing issue can occur?  to prove accurate, I wrote some isolation
tests. see[2]

performance:
demo:
case when: %20 percent values are NULL and have been deleted from heap but they
still on the index.

drop table if exists t;
create unlogged table t(a int, b int) with (autovacuum_enabled = off, vacuum_index_cleanup=off);
insert into t select case when g % 5 = 0 then null else g end, g+1
from generate_series(1,1_000_000) g;
create index t_idx_a on t(a);
delete from t where a is null;

alter table t alter column a drop not null;
alter table t add constraint t1 not null a;

the above two statement running several times:
patch Time:: 1.084  ms
master Time: 12.045 ms

references:
[1] https://postgr.es/m/CA%2BTgmoa5NKz8iGW_9v7wz%3D-%2BzQFu%3DE4SZoaTaU1znLaEXRYp-Q%40mail.gmail.com
[2] https://postgr.es/m/900056D1-32DF-4927-8251-3E0C0DC407FD%40anarazel.de
discussion: https://postgr.es/m/CACJufxFiW=4k1is=F1J=r-Cx1RuByXQPUrWB331U47rSnGz+hw@mail.gmail.com
commitfest entry: https://commitfest.postgresql.org/patch/5444
---
 src/backend/commands/tablecmds.c              | 116 +++++++++-
 src/backend/executor/execIndexing.c           | 213 ++++++++++++++++++
 src/include/executor/executor.h               |   2 +
 .../expected/indexscan-check-notnull.out      |  97 ++++++++
 src/test/isolation/isolation_schedule         |   1 +
 .../specs/indexscan-check-notnull.spec        |  45 ++++
 src/test/modules/test_misc/meson.build        |   1 +
 .../t/011_indexscan_validate_notnull.pl       | 163 ++++++++++++++
 8 files changed, 632 insertions(+), 6 deletions(-)
 create mode 100644 src/test/isolation/expected/indexscan-check-notnull.out
 create mode 100644 src/test/isolation/specs/indexscan-check-notnull.spec
 create mode 100644 src/test/modules/test_misc/t/011_indexscan_validate_notnull.pl

diff --git a/src/backend/commands/tablecmds.c b/src/backend/commands/tablecmds.c
index f976c0e5c7e..2af06630b35 100644
--- a/src/backend/commands/tablecmds.c
+++ b/src/backend/commands/tablecmds.c
@@ -210,16 +210,19 @@ typedef struct AlteredTableInfo
 	List	   *changedStatisticsDefs;	/* string definitions of same */
 } AlteredTableInfo;
 
-/* Struct describing one new constraint to check in Phase 3 scan */
-/* Note: new not-null constraints are handled elsewhere */
+/*
+ * Struct describing one new constraint to check in Phase 3 scan. Note: new
+ * not-null constraints are handled here too.
+*/
 typedef struct NewConstraint
 {
 	char	   *name;			/* Constraint name, or NULL if none */
-	ConstrType	contype;		/* CHECK or FOREIGN */
+	ConstrType	contype;		/* CHECK or FOREIGN or NOT NULL */
 	Oid			refrelid;		/* PK rel, if FOREIGN */
 	Oid			refindid;		/* OID of PK's index, if FOREIGN */
 	bool		conwithperiod;	/* Whether the new FOREIGN KEY uses PERIOD */
 	Oid			conid;			/* OID of pg_constraint entry, if FOREIGN */
+	int			attnum;			/* NOT NULL constraint attribute number */
 	Node	   *qual;			/* Check expr or CONSTR_FOREIGN Constraint */
 	ExprState  *qualstate;		/* Execution state for CHECK expr */
 } NewConstraint;
@@ -6217,6 +6220,9 @@ ATRewriteTable(AlteredTableInfo *tab, Oid OIDNewHeap)
 				needscan = true;
 				con->qualstate = ExecPrepareExpr((Expr *) expand_generated_columns_in_expr(con->qual, oldrel, 1), estate);
 				break;
+			case CONSTR_NOTNULL:
+				/* Nothing to do here */
+				break;
 			case CONSTR_FOREIGN:
 				/* Nothing to do here */
 				break;
@@ -6270,10 +6276,69 @@ ATRewriteTable(AlteredTableInfo *tab, Oid OIDNewHeap)
 														wholeatt->attnum);
 			}
 		}
-		if (notnull_attrs || notnull_virtual_attrs)
-			needscan = true;
 	}
 
+	/*-
+	 * If we have to verify new not-null constraints and don't have any other
+	 * reason to fully scan the table, then we can use indexes to test for
+	 * absence of NULL values instead of scanning.  The following conditions
+	 * must be met:
+	 * - we're operating on a regular table
+	 * - we hold AccessExclusiveLock on the table
+	 * - no not-null constraint covers a virtual generated column,
+	 *   because no indexes can be created on them
+	 */
+	if (!needscan &&
+		newrel == NULL &&
+		tab->verify_new_notnull &&
+		notnull_virtual_attrs == NIL &&
+		oldrel->rd_rel->relkind == RELKIND_RELATION &&
+		CheckRelationLockedByMe(oldrel, AccessExclusiveLock, false))
+	{
+		List	   *notnull_attnums = NIL;
+
+		Assert(!tab->rewrite);
+
+		foreach(l, tab->constraints)
+		{
+			Form_pg_attribute attr;
+			NewConstraint *con = lfirst(l);
+
+			if (con->contype != CONSTR_NOTNULL)
+				continue;
+
+			attr = TupleDescAttr(newTupDesc, con->attnum - 1);
+
+			Assert(attr->attnotnull);
+			Assert(attr->attnum == con->attnum);
+
+			if (attr->attgenerated == ATTRIBUTE_GENERATED_VIRTUAL)
+			{
+				needscan = true;
+				break;
+			}
+
+			notnull_attnums = lappend_int(notnull_attnums, attr->attnum);
+		}
+
+		/*
+		 * Validate new NOT NULL constraints, unless we need a scan for other
+		 * reasons, because we can validate them cheaply there, and doing it
+		 * also here would be a waste of cycles.
+		 */
+		if (notnull_attnums != NIL && !needscan)
+		{
+			if (!index_check_notnull(oldrel, notnull_attnums))
+				needscan = true;
+			else
+				ereport(DEBUG1,
+						errmsg_internal("all new not-null constraints on relation \"%s\" have been validated by using index scan",
+										RelationGetRelationName(oldrel)));
+		}
+	}
+	else if (notnull_attrs || notnull_virtual_attrs)
+		needscan = true;
+
 	if (newrel || needscan)
 	{
 		ExprContext *econtext;
@@ -7949,6 +8014,7 @@ ATExecSetNotNull(List **wqueue, Relation rel, char *conName, char *colName,
 	CookedConstraint *ccon;
 	List	   *cooked;
 	bool		is_no_inherit = false;
+	AlteredTableInfo *tab = NULL;
 
 	/* Guard against stack overflow due to overly deep inheritance tree. */
 	check_stack_depth();
@@ -8073,10 +8139,32 @@ ATExecSetNotNull(List **wqueue, Relation rel, char *conName, char *colName,
 	constraint->is_no_inherit = is_no_inherit;
 	constraint->conname = conName;
 
+	tab = ATGetQueueEntry(wqueue, rel);
+
 	/* and do it */
 	cooked = AddRelationNewConstraints(rel, NIL, list_make1(constraint),
 									   false, !recursing, false, NULL);
 	ccon = linitial(cooked);
+
+	Assert(ccon->contype == CONSTR_NOTNULL);
+
+	/*
+	 * We may use indexscan to vertify not-null constraint in Phase3.  Add the
+	 * to-be-validated not-null constraint to Phase 3's queue.
+	 */
+	if (!ccon->skip_validation)
+	{
+		NewConstraint *newcon;
+
+		newcon = (NewConstraint *) palloc0(sizeof(NewConstraint));
+
+		newcon->name = ccon->name;
+		newcon->contype = ccon->contype;
+		newcon->attnum = ccon->attnum;
+
+		tab->constraints = lappend(tab->constraints, newcon);
+	}
+
 	ObjectAddressSet(address, ConstraintRelationId, ccon->conoid);
 
 	InvokeObjectPostAlterHook(RelationRelationId,
@@ -9983,13 +10071,15 @@ ATAddCheckNNConstraint(List **wqueue, AlteredTableInfo *tab, Relation rel,
 	{
 		CookedConstraint *ccon = (CookedConstraint *) lfirst(lcon);
 
-		if (!ccon->skip_validation && ccon->contype != CONSTR_NOTNULL)
+		if (!ccon->skip_validation)
 		{
 			NewConstraint *newcon;
 
 			newcon = palloc0_object(NewConstraint);
 			newcon->name = ccon->name;
 			newcon->contype = ccon->contype;
+			if (ccon->contype == CONSTR_NOTNULL)
+				newcon->attnum = ccon->attnum;
 			newcon->qual = ccon->expr;
 
 			tab->constraints = lappend(tab->constraints, newcon);
@@ -13258,6 +13348,7 @@ QueueNNConstraintValidation(List **wqueue, Relation conrel, Relation rel,
 	List	   *children = NIL;
 	AttrNumber	attnum;
 	char	   *colname;
+	NewConstraint *newcon;
 
 	con = (Form_pg_constraint) GETSTRUCT(contuple);
 	Assert(con->contype == CONSTRAINT_NOTNULL);
@@ -13321,7 +13412,20 @@ QueueNNConstraintValidation(List **wqueue, Relation conrel, Relation rel,
 	/* Set attnotnull appropriately without queueing another validation */
 	set_attnotnull(NULL, rel, attnum, true, false);
 
+	/*
+	 * Queue validation for phase 3.
+	 *
+	 * ALTER TABLE SET NOT NULL will add NOT NULL constraint to
+	 * AlteredTableInfo->constraints, for consistency, do the same here.
+	 */
+	newcon = (NewConstraint *) palloc0(sizeof(NewConstraint));
+	newcon->name = colname;
+	newcon->contype = CONSTR_NOTNULL;
+	newcon->attnum = attnum;
+
+	/* Find or create work queue entry for this table */
 	tab = ATGetQueueEntry(wqueue, rel);
+	tab->constraints = lappend(tab->constraints, newcon);
 	tab->verify_new_notnull = true;
 
 	/*
diff --git a/src/backend/executor/execIndexing.c b/src/backend/executor/execIndexing.c
index 6ae0f959592..88694ce0335 100644
--- a/src/backend/executor/execIndexing.c
+++ b/src/backend/executor/execIndexing.c
@@ -108,12 +108,15 @@
 
 #include "access/genam.h"
 #include "access/relscan.h"
+#include "access/table.h"
 #include "access/tableam.h"
 #include "access/xact.h"
 #include "catalog/index.h"
+#include "catalog/pg_am_d.h"
 #include "executor/executor.h"
 #include "nodes/nodeFuncs.h"
 #include "storage/lmgr.h"
+#include "utils/fmgroids.h"
 #include "utils/injection_point.h"
 #include "utils/multirangetypes.h"
 #include "utils/rangetypes.h"
@@ -146,6 +149,7 @@ static bool index_expression_changed_walker(Node *node,
 											Bitmapset *allUpdatedCols);
 static void ExecWithoutOverlapsNotEmpty(Relation rel, NameData attname, Datum attval,
 										char typtype, Oid atttypid);
+static bool index_check_notnull_internal(Relation relation, List *attnums, List *idxs);
 
 /* ----------------------------------------------------------------
  *		ExecOpenIndices
@@ -1178,3 +1182,212 @@ ExecWithoutOverlapsNotEmpty(Relation rel, NameData attname, Datum attval, char t
 				 errmsg("empty WITHOUT OVERLAPS value found in column \"%s\" in relation \"%s\"",
 						NameStr(attname), RelationGetRelationName(rel))));
 }
+
+/*
+ * notnull_attnums: list of attribute numbers of all new not-null constraints.
+ *
+ * First check whether the relation has a suitable index for each not-null
+ * attribute, then using indexscan mechanism to verify that *all* attributes on
+ * notnull_attnums are indeed not null.
+ *
+ * Returning true means all new not-null constraints have been verified, no
+ * need an extra scan to verify newly added not-null constraints.
+ */
+bool
+index_check_notnull(Relation relation, List *notnull_attnums)
+{
+	Relation	pg_index;
+	Relation	index_rel;
+	SysScanDesc indscan;
+	ScanKeyData skey;
+	HeapTuple	htup;
+	TupleDesc	tupdesc;
+	Form_pg_attribute attr;
+	List	   *idxs = NIL;
+	List	   *attnums = NIL;
+
+	tupdesc = RelationGetDescr(relation);
+
+	/* Prepare to scan pg_index for entries having indrelid = this rel */
+	ScanKeyInit(&skey,
+				Anum_pg_index_indrelid,
+				BTEqualStrategyNumber, F_OIDEQ,
+				ObjectIdGetDatum(RelationGetRelid(relation)));
+
+	pg_index = table_open(IndexRelationId, AccessShareLock);
+	indscan = systable_beginscan(pg_index, IndexIndrelidIndexId, true,
+								 NULL, 1, &skey);
+
+	while (HeapTupleIsValid(htup = systable_getnext(indscan)))
+	{
+		Form_pg_index index = (Form_pg_index) GETSTRUCT(htup);
+
+		/*
+		 * we can only use non-deferred, validated, and alive btree index to
+		 * validate not-null constraints
+		 */
+		if (!index->indimmediate || !index->indisvalid || !index->indislive)
+			continue;
+
+		/* can not use expression index or partial index too */
+		if (!heap_attisnull(htup, Anum_pg_index_indexprs, NULL) ||
+			!heap_attisnull(htup, Anum_pg_index_indpred, NULL))
+			continue;
+
+		index_rel = index_open(index->indexrelid, AccessShareLock);
+
+		/* can only apply to btree index */
+		if (index_rel->rd_rel->relam != BTREE_AM_OID)
+		{
+			index_close(index_rel, AccessShareLock);
+			continue;
+		}
+
+		/* collect index attnums while loop */
+		for (int i = 0; i < index->indnkeyatts; i++)
+		{
+			attr = TupleDescAttr(tupdesc, (index->indkey.values[i] - 1));
+
+			if (attr->attisdropped)
+				continue;
+
+			if (list_member_int(notnull_attnums, attr->attnum) &&
+				!list_member_int(attnums, attr->attnum))
+			{
+				attnums = lappend_int(attnums, attr->attnum);
+				idxs = lappend_oid(idxs, index->indexrelid);
+			}
+		}
+		index_close(index_rel, NoLock);
+	}
+	systable_endscan(indscan);
+	table_close(pg_index, AccessShareLock);
+
+	if (attnums == NIL)
+		return false;
+
+	/*
+	 * every not-null constraint requires an index for indexscan.  If no such
+	 * index exists, we need to use regular table scan to validate not-null
+	 * constraints.
+	 */
+	foreach_int(attno, notnull_attnums)
+	{
+		if (!list_member_int(attnums, attno))
+			return false;
+	}
+
+	return index_check_notnull_internal(relation, attnums, idxs);
+}
+
+/*
+ * Use indexscan mechanism to fast verify each attribute in "attnums" are
+ * not-null or not.
+ */
+static bool
+index_check_notnull_internal(Relation relation, List *attnums, List *idxs)
+{
+	EState	   *estate;
+	ExprContext *econtext;
+	TupleTableSlot *existing_slot;
+	bool		all_not_null = true;
+	ListCell   *lc,
+			   *lc2;
+
+	/*
+	 * Need an EState for slot to hold the current tuple.
+	 */
+	estate = CreateExecutorState();
+	econtext = GetPerTupleExprContext(estate);
+
+	forboth(lc, attnums, lc2, idxs)
+	{
+		SnapshotData DirtySnapshot;
+		IndexScanDesc index_scan;
+		ScanKeyData scankeys[INDEX_MAX_KEYS];
+		IndexInfo  *indexInfo;
+		AttrNumber	sk_attno = -1;
+		Relation	index;
+		int			indnkeyatts;
+
+		AttrNumber	attno = lfirst_int(lc);
+		Oid			indexoid = lfirst_oid(lc2);
+
+		existing_slot = table_slot_create(relation, NULL);
+
+		/* Arrange for econtext's scan tuple to be the tuple under test */
+		econtext->ecxt_scantuple = existing_slot;
+
+		index = index_open(indexoid, NoLock);
+
+		indexInfo = BuildIndexInfo(index);
+		indnkeyatts = IndexRelationGetNumberOfKeyAttributes(index);
+
+		/*
+		 * Search the tuples that are in the index for any violations,
+		 * including tuples that aren't visible yet.
+		 */
+		InitDirtySnapshot(DirtySnapshot);
+
+		for (int i = 0; i < indnkeyatts; i++)
+		{
+			if (indexInfo->ii_IndexAttrNumbers[i] == attno)
+			{
+				sk_attno = i + 1;
+				break;
+			}
+		}
+
+		if (sk_attno == -1)
+			elog(ERROR, "cache lookup failed for attribute number %d on index %u", indexoid, attno);
+
+		for (int i = 0; i < indnkeyatts; i++)
+		{
+			/* set up an IS NULL scan key so that we ignore not nulls */
+			ScanKeyEntryInitialize(&scankeys[i],
+								   SK_ISNULL | SK_SEARCHNULL,
+								   sk_attno,	/* index col to scan */
+								   InvalidStrategy, /* no strategy */
+								   InvalidOid,	/* no strategy subtype */
+								   InvalidOid,	/* no collation */
+								   InvalidOid,	/* no reg proc for this */
+								   (Datum) 0);	/* constant */
+		}
+
+		index_scan = index_beginscan(relation, index, &DirtySnapshot, NULL, indnkeyatts, 0);
+		index_rescan(index_scan, scankeys, indnkeyatts, NULL, 0);
+
+		while (index_getnext_slot(index_scan, ForwardScanDirection, existing_slot))
+		{
+			Datum		values[INDEX_MAX_KEYS];
+			bool		nulls[INDEX_MAX_KEYS];
+
+			/*
+			 * Extract the index column values and isnull flags from the
+			 * existing tuple.
+			 */
+			FormIndexDatum(indexInfo, existing_slot, estate, values, nulls);
+
+			if (nulls[sk_attno - 1])
+			{
+				all_not_null = false;
+				break;
+			}
+		}
+
+		index_endscan(index_scan);
+		index_close(index, NoLock);
+		ExecDropSingleTupleTableSlot(existing_slot);
+
+		/* exit earlier */
+		if (!all_not_null)
+		{
+			FreeExecutorState(estate);
+			return false;
+		}
+	}
+
+	FreeExecutorState(estate);
+
+	return true;
+}
diff --git a/src/include/executor/executor.h b/src/include/executor/executor.h
index 5929aabc353..7f24caeeafb 100644
--- a/src/include/executor/executor.h
+++ b/src/include/executor/executor.h
@@ -756,6 +756,8 @@ extern void check_exclusion_constraint(Relation heap, Relation index,
 									   const Datum *values, const bool *isnull,
 									   EState *estate, bool newIndex);
 
+extern bool index_check_notnull(Relation relation, List *notnull_attnums);
+
 /*
  * prototypes from functions in execReplication.c
  */
diff --git a/src/test/isolation/expected/indexscan-check-notnull.out b/src/test/isolation/expected/indexscan-check-notnull.out
new file mode 100644
index 00000000000..c6a652e2518
--- /dev/null
+++ b/src/test/isolation/expected/indexscan-check-notnull.out
@@ -0,0 +1,97 @@
+Parsed test spec with 2 sessions
+
+starting permutation: s1_b1 s2_b1 s1_d1 s2_a1 s1_c1 s2_c1 s1_q1
+step s1_b1: BEGIN ISOLATION LEVEL REPEATABLE READ;
+step s2_b1: BEGIN ISOLATION LEVEL REPEATABLE READ;
+step s1_d1: DELETE FROM t;
+step s2_a1: ALTER TABLE t ADD CONSTRAINT t1_nn NOT NULL a; <waiting ...>
+step s1_c1: COMMIT;
+step s2_a1: <... completed>
+step s2_c1: COMMIT;
+step s1_q1: SELECT conname, conrelid::regclass, contype, convalidated
+              FROM pg_constraint WHERE conname = 't1_nn';
+
+conname|conrelid|contype|convalidated
+-------+--------+-------+------------
+t1_nn  |t       |n      |t           
+(1 row)
+
+
+starting permutation: s1_b2 s2_b1 s1_d1 s2_a1 s1_c1 s2_c1 s1_q1
+step s1_b2: BEGIN;
+step s2_b1: BEGIN ISOLATION LEVEL REPEATABLE READ;
+step s1_d1: DELETE FROM t;
+step s2_a1: ALTER TABLE t ADD CONSTRAINT t1_nn NOT NULL a; <waiting ...>
+step s1_c1: COMMIT;
+step s2_a1: <... completed>
+step s2_c1: COMMIT;
+step s1_q1: SELECT conname, conrelid::regclass, contype, convalidated
+              FROM pg_constraint WHERE conname = 't1_nn';
+
+conname|conrelid|contype|convalidated
+-------+--------+-------+------------
+t1_nn  |t       |n      |t           
+(1 row)
+
+
+starting permutation: s1_b1 s2_b2 s1_d1 s2_a1 s1_c1 s2_c1 s1_q1
+step s1_b1: BEGIN ISOLATION LEVEL REPEATABLE READ;
+step s2_b2: BEGIN;
+step s1_d1: DELETE FROM t;
+step s2_a1: ALTER TABLE t ADD CONSTRAINT t1_nn NOT NULL a; <waiting ...>
+step s1_c1: COMMIT;
+step s2_a1: <... completed>
+step s2_c1: COMMIT;
+step s1_q1: SELECT conname, conrelid::regclass, contype, convalidated
+              FROM pg_constraint WHERE conname = 't1_nn';
+
+conname|conrelid|contype|convalidated
+-------+--------+-------+------------
+t1_nn  |t       |n      |t           
+(1 row)
+
+
+starting permutation: s1_b1 s2_b1 s2_a1 s1_r1 s2_r1
+step s1_b1: BEGIN ISOLATION LEVEL REPEATABLE READ;
+step s2_b1: BEGIN ISOLATION LEVEL REPEATABLE READ;
+step s2_a1: ALTER TABLE t ADD CONSTRAINT t1_nn NOT NULL a;
+ERROR:  column "a" of relation "t" contains null values
+step s1_r1: ROLLBACK;
+step s2_r1: ROLLBACK;
+
+starting permutation: s1_b1 s2_b2 s2_d1 s1_d1 s2_r1 s1_a1 s1_q1 s1_r1
+step s1_b1: BEGIN ISOLATION LEVEL REPEATABLE READ;
+step s2_b2: BEGIN;
+step s2_d1: DROP INDEX t_ab_idx;
+step s1_d1: DELETE FROM t; <waiting ...>
+step s2_r1: ROLLBACK;
+step s1_d1: <... completed>
+step s1_a1: ALTER TABLE t ADD CONSTRAINT t1_nn NOT NULL a;
+step s1_q1: SELECT conname, conrelid::regclass, contype, convalidated
+              FROM pg_constraint WHERE conname = 't1_nn';
+
+conname|conrelid|contype|convalidated
+-------+--------+-------+------------
+t1_nn  |t       |n      |t           
+(1 row)
+
+step s1_r1: ROLLBACK;
+
+starting permutation: s1_b2 s2_b1 s1_d1 s2_d1 s1_s0 s1_a1 s1_c1 s2_c1 s1_q1
+step s1_b2: BEGIN;
+step s2_b1: BEGIN ISOLATION LEVEL REPEATABLE READ;
+step s1_d1: DELETE FROM t;
+step s2_d1: DROP INDEX t_ab_idx; <waiting ...>
+step s1_s0: SAVEPOINT s0;
+step s1_a1: ALTER TABLE t ADD CONSTRAINT t1_nn NOT NULL a;
+step s1_c1: COMMIT;
+step s2_d1: <... completed>
+step s2_c1: COMMIT;
+step s1_q1: SELECT conname, conrelid::regclass, contype, convalidated
+              FROM pg_constraint WHERE conname = 't1_nn';
+
+conname|conrelid|contype|convalidated
+-------+--------+-------+------------
+t1_nn  |t       |n      |t           
+(1 row)
+
diff --git a/src/test/isolation/isolation_schedule b/src/test/isolation/isolation_schedule
index 01ff1c6586f..7ce6bbcaf89 100644
--- a/src/test/isolation/isolation_schedule
+++ b/src/test/isolation/isolation_schedule
@@ -58,6 +58,7 @@ test: merge-delete
 test: merge-update
 test: merge-match-recheck
 test: merge-join
+test: indexscan-check-notnull
 test: delete-abort-savept
 test: delete-abort-savept-2
 test: aborted-keyrevoke
diff --git a/src/test/isolation/specs/indexscan-check-notnull.spec b/src/test/isolation/specs/indexscan-check-notnull.spec
new file mode 100644
index 00000000000..05b4488550c
--- /dev/null
+++ b/src/test/isolation/specs/indexscan-check-notnull.spec
@@ -0,0 +1,45 @@
+
+#
+# using indexscan to check a column not-null constraint
+# is satisfied or not.
+#
+
+setup
+{
+  CREATE TABLE t (a int, b int);
+  CREATE INDEX t_ab_idx on t(a,b);
+  INSERT INTO t values (null, 1);
+  INSERT INTO t SELECT x, x*10 FROM generate_series(1,3) g(x);
+}
+
+teardown
+{
+  DROP TABLE t;
+}
+
+session s1
+step s1_b1  { BEGIN ISOLATION LEVEL REPEATABLE READ; }
+step s1_b2  { BEGIN; }
+step s1_d1  { DELETE FROM t;}
+step s1_s0  { SAVEPOINT s0;}
+step s1_a1  { ALTER TABLE t ADD CONSTRAINT t1_nn NOT NULL a;}
+step s1_q1  { SELECT conname, conrelid::regclass, contype, convalidated
+              FROM pg_constraint WHERE conname = 't1_nn';
+            }
+step s1_r1  { ROLLBACK; }
+step s1_c1  { COMMIT; }
+
+session s2
+step s2_b1  { BEGIN ISOLATION LEVEL REPEATABLE READ; }
+step s2_b2  { BEGIN; }
+step s2_a1  { ALTER TABLE t ADD CONSTRAINT t1_nn NOT NULL a;}
+step s2_d1  { DROP INDEX t_ab_idx;}
+step s2_r1  { ROLLBACK; }
+step s2_c1  { COMMIT; }
+
+permutation s1_b1 s2_b1 s1_d1 s2_a1 s1_c1 s2_c1 s1_q1
+permutation s1_b2 s2_b1 s1_d1 s2_a1 s1_c1 s2_c1 s1_q1
+permutation s1_b1 s2_b2 s1_d1 s2_a1 s1_c1 s2_c1 s1_q1
+permutation s1_b1 s2_b1 s2_a1 s1_r1 s2_r1
+permutation s1_b1 s2_b2 s2_d1 s1_d1 s2_r1 s1_a1 s1_q1 s1_r1
+permutation s1_b2 s2_b1 s1_d1 s2_d1 s1_s0 s1_a1 s1_c1 s2_c1 s1_q1
diff --git a/src/test/modules/test_misc/meson.build b/src/test/modules/test_misc/meson.build
index 6e8db1621a7..56faf359b29 100644
--- a/src/test/modules/test_misc/meson.build
+++ b/src/test/modules/test_misc/meson.build
@@ -19,6 +19,7 @@ tests += {
       't/008_replslot_single_user.pl',
       't/009_log_temp_files.pl',
       't/010_index_concurrently_upsert.pl',
+      't/011_indexscan_validate_notnull.pl',
     ],
     # The injection points are cluster-wide, so disable installcheck
     'runningcheck': false,
diff --git a/src/test/modules/test_misc/t/011_indexscan_validate_notnull.pl b/src/test/modules/test_misc/t/011_indexscan_validate_notnull.pl
new file mode 100644
index 00000000000..a3f3cb409b6
--- /dev/null
+++ b/src/test/modules/test_misc/t/011_indexscan_validate_notnull.pl
@@ -0,0 +1,163 @@
+# Copyright (c) 2025, PostgreSQL Global Development Group
+
+# Verify that indexscan mechanism can speedup ALTER TABLE ADD NOT NULL
+
+
+use strict;
+use warnings FATAL => 'all';
+use PostgreSQL::Test::Cluster;
+use PostgreSQL::Test::Utils;
+use Test::More;
+
+# Initialize a test cluster
+my $node = PostgreSQL::Test::Cluster->new('primary');
+$node->init();
+# Turn message level up to DEBUG1 so that we get the messages we want to see
+$node->append_conf('postgresql.conf', 'client_min_messages = DEBUG1');
+$node->start;
+
+# Run a SQL command and return psql's stderr (including debug messages)
+sub run_sql_command
+{
+	my $sql = shift;
+	my $stderr;
+
+	$node->psql(
+		'postgres',
+		$sql,
+		stderr => \$stderr,
+		on_error_die => 1,
+		on_error_stop => 1);
+	return $stderr;
+}
+
+# Check whether result of run_sql_command shows that we did a verify pass
+sub is_table_verified
+{
+	my $output = shift;
+	return index($output, 'DEBUG:  verifying table') != -1;
+}
+
+# Check whether result of run_sql_command shows that we did a verify pass
+sub is_indexscan_veritify_notnull
+{
+	my $output = shift;
+	return index($output, 'DEBUG:  all new not-null constraints on relation') != -1;
+}
+
+my $output;
+
+note "test alter table SET NOT NULL using indexscan with partitioned table";
+
+run_sql_command(
+    'CREATE TABLE tp (a int, b int, c int, d int ) PARTITION BY range(a);
+     CREATE TABLE tpp1 partition of tp for values from ( 1 ) to (10);
+     CREATE TABLE tpp2 partition of tp for values from ( 10 ) to (21);
+     INSERT INTO tp select g, g + 10, g + 15, g + random(min=>1::int, max=>10::int) from generate_series(1,19) g;
+     CREATE INDEX ON tp(b); ');
+
+$output = run_sql_command('ALTER TABLE tp ALTER COLUMN b SET NOT NULL;');
+ok(is_indexscan_veritify_notnull($output),
+	'column b will use indexscan to verify not-null status, no need scan table');
+ok( $output =~
+	  m/all new not-null constraints on relation "tpp1" have been validated by using index scan/,
+	'all newly added constraints proved by indexscan');
+
+run_sql_command(
+	'ALTER TABLE tp ALTER COLUMN b DROP NOT NULL;');
+
+# use indexes on partitions to fast vertifing not-null should be ok
+$output = run_sql_command('ALTER TABLE tpp1 ALTER COLUMN b SET NOT NULL;');
+ok(is_indexscan_veritify_notnull($output), 'use indexscan to validate column b not-null will not scan table');
+ok(!is_table_verified($output), 'no table scan for pp1');
+ok( $output =~
+	  m/all new not-null constraints on relation "tpp1" have been validated by using index scan/,
+	'all newly added constraints proved by indexscan');
+
+$output = run_sql_command('ALTER TABLE tpp2 ALTER COLUMN b SET NOT NULL;');
+ok(is_indexscan_veritify_notnull($output), 'use indexscan to validate column b not-null, will not scan table');
+ok(!is_table_verified($output), 'no table scan for tpp2');
+ok( $output =~
+	  m/all new not-null constraints on relation "tpp2" have been validated by using index scan/,
+	'all newly added constraints proved by indexscan');
+
+run_sql_command(
+	'ALTER TABLE tp ALTER COLUMN b DROP NOT NULL;');
+
+# table rewrite then can not use indexscan to verify not-null constraint
+$output = run_sql_command(
+	'ALTER TABLE tp ALTER COLUMN b SET NOT NULL, ALTER COLUMN b SET DATA TYPE bigint;'
+);
+ok(!is_table_verified($output), 'no table scan for tp');
+ok(!is_indexscan_veritify_notnull($output), 'table tp will rewrite, can not use indexscan to verify not-null constraints on it');
+
+# test using indexscan with multiple not-null constraints
+run_sql_command(
+    'ALTER TABLE tp ALTER COLUMN b DROP NOT NULL;
+	 CREATE INDEX ON tp(c);
+	 CREATE INDEX ON tp(d); ');
+
+# one column can use indexscan, another can not, so can not use indexscan to verify not-null
+$output = run_sql_command(
+	'ALTER TABLE tp ALTER COLUMN a SET NOT NULL, ADD CONSTRAINT c_nn NOT NULL c');
+ok(is_table_verified($output), 'table scan for tp');
+ok(!is_indexscan_veritify_notnull($output), 'can not use indexscan to verify not-null constraints on table tp');
+
+# all columns have index on it
+# use indexscan to verify multiple not-null constraints should just fine
+$output = run_sql_command(
+	'ALTER TABLE tp ALTER COLUMN d SET NOT NULL, ADD CONSTRAINT c_nn NOT NULL c, ALTER COLUMN b SET NOT NULL;');
+ok(!is_table_verified($output), 'no table scan for tp');
+ok(is_indexscan_veritify_notnull($output),
+	'using indexscan to verify not-null constraints on column b, c, d, no need table scan');
+
+# test with non-partitioned table and other non-Btree index.
+run_sql_command(
+    'CREATE TABLE t1(f1 INT, f2 int, f3 int,f4 int, f5 int);
+     INSERT INTO t1 select g, g+1, g+2, g+3, g+4 from generate_series(1, 100) g;
+     CREATE INDEX t1_f1_f2_idx ON t1(f1,f2);
+     CREATE UNIQUE INDEX t1_f3idx ON t1(f3);
+     CREATE INDEX t1_f3f4idx ON t1(f3) include(f4);
+     CREATE INDEX hash_f5_idx ON t1 USING hash (f5 int4_ops); ');
+
+# ALTER TABLE VALIDATE CONSTRAINT can not use indexscan,
+# because it only hold ShareUpdateExclusiveLock lock.
+run_sql_command('ALTER TABLE t1 ADD CONSTRAINT nn_t1_f2 NOT NULL f2 NOT VALID;');
+
+$output = run_sql_command(
+	'ALTER TABLE t1 VALIDATE CONSTRAINT nn_t1_f2;'
+);
+ok(!is_indexscan_veritify_notnull($output), 'can not use indexscan for ALTER TABLE VALIDATE CONSTRAINT command');
+run_sql_command('ALTER TABLE t1 DROP CONSTRAINT nn_t1_f2;');
+
+$output = run_sql_command(
+	'ALTER TABLE t1 ALTER COLUMN f1 SET NOT NULL, ALTER f1 type bigint;'
+);
+ok(!is_indexscan_veritify_notnull($output), 'table t1 will rewrite, can not use indexscan to validate not-null constraints on t1');
+
+run_sql_command('ALTER TABLE t1 ALTER COLUMN f1 DROP NOT NULL;');
+run_sql_command('ALTER TABLE t1 ADD CONSTRAINT nn NOT NULL f1, ALTER f1 type bigint;');
+
+# can use indexscan mechanism to fast add multiple not-null constraints
+$output = run_sql_command(
+	'ALTER TABLE t1 ALTER COLUMN f2 SET NOT NULL, ALTER COLUMN f1 SET NOT NULL;'
+);
+ok( $output =~
+	  m/all new not-null constraints on relation "t1" have been validated by using index scan/,
+	'all not-null constraints are validated by indexscan');
+
+# using indexscan mechanism to fast add a not-null can only apply to key columns, not include column
+$output = run_sql_command(
+	'ALTER TABLE t1 ADD CONSTRAINT nnf4 NOT NULL f4;'
+);
+ok(!is_indexscan_veritify_notnull($output), 'can not use indexscan to validate not-null constraint on t1');
+
+# if index is not btree index then cannot use indexscan mechanism to fast add not-null constraint
+$output = run_sql_command(
+	'ALTER TABLE t1 ADD CONSTRAINT nn_f5 NOT NULL f5;'
+);
+ok(!is_indexscan_veritify_notnull($output), 'can not use indexscan to validate not-null constraints on t1');
+
+$node->stop('fast');
+
+done_testing();
-- 
2.47.3


--xpkr6zhfzd3fjt76--





^ permalink  raw  reply  [nested|flat] 150+ messages in thread

* [PATCH v8] using indexscan to speedup add not null constraints
@ 2025-10-20 05:29  jian he <[email protected]>
  0 siblings, 0 replies; 150+ messages in thread

From: jian he @ 2025-10-20 05:29 UTC (permalink / raw)

This patch tries to use index_beginscan() / index_getnext() / index_endscan()
mentioned in [1] to speedup adding not-null constraints to the existing table.

The main logic happens in phase3 ATRewriteTable
1. collect all not-null constraints.
2. For each not-null constraint, check whether there is a corresponding index
available for validation. If not, then can not use indexscan to verify not-null
constraints.
3. If any of the following conditions are true
  * table scan or rewrite is required,
  * table wasn't locked with `AccessExclusiveLock`
  * the NOT NULL constraint applies to a virtual generated column
 then index scan cannot be used for fast validation.
4. If all conditions are satisfied, attempt to use indexscan to verify
whether the column contains any NULL values.

concurrency concern:
ALTER TABLE SET NOT NULL will take an ACCESS EXCLUSIVE lock, so there is less
variant of racing issue can occur?  to prove accurate, I wrote some isolation
tests. see[2]

performance:
demo:
case when: %20 percent values are NULL and have been deleted from heap but they
still on the index.

drop table if exists t;
create unlogged table t(a int, b int) with (autovacuum_enabled = off, vacuum_index_cleanup=off);
insert into t select case when g % 5 = 0 then null else g end, g+1
from generate_series(1,1_000_000) g;
create index t_idx_a on t(a);
delete from t where a is null;

alter table t alter column a drop not null;
alter table t add constraint t1 not null a;

the above two statement running several times:
patch Time:: 1.084  ms
master Time: 12.045 ms

references:
[1] https://postgr.es/m/CA%2BTgmoa5NKz8iGW_9v7wz%3D-%2BzQFu%3DE4SZoaTaU1znLaEXRYp-Q%40mail.gmail.com
[2] https://postgr.es/m/900056D1-32DF-4927-8251-3E0C0DC407FD%40anarazel.de
discussion: https://postgr.es/m/CACJufxFiW=4k1is=F1J=r-Cx1RuByXQPUrWB331U47rSnGz+hw@mail.gmail.com
commitfest entry: https://commitfest.postgresql.org/patch/5444
---
 src/backend/commands/tablecmds.c              | 116 +++++++++-
 src/backend/executor/execIndexing.c           | 213 ++++++++++++++++++
 src/include/executor/executor.h               |   2 +
 .../expected/indexscan-check-notnull.out      |  97 ++++++++
 src/test/isolation/isolation_schedule         |   1 +
 .../specs/indexscan-check-notnull.spec        |  45 ++++
 src/test/modules/test_misc/meson.build        |   1 +
 .../t/011_indexscan_validate_notnull.pl       | 163 ++++++++++++++
 8 files changed, 632 insertions(+), 6 deletions(-)
 create mode 100644 src/test/isolation/expected/indexscan-check-notnull.out
 create mode 100644 src/test/isolation/specs/indexscan-check-notnull.spec
 create mode 100644 src/test/modules/test_misc/t/011_indexscan_validate_notnull.pl

diff --git a/src/backend/commands/tablecmds.c b/src/backend/commands/tablecmds.c
index f976c0e5c7e..2af06630b35 100644
--- a/src/backend/commands/tablecmds.c
+++ b/src/backend/commands/tablecmds.c
@@ -210,16 +210,19 @@ typedef struct AlteredTableInfo
 	List	   *changedStatisticsDefs;	/* string definitions of same */
 } AlteredTableInfo;
 
-/* Struct describing one new constraint to check in Phase 3 scan */
-/* Note: new not-null constraints are handled elsewhere */
+/*
+ * Struct describing one new constraint to check in Phase 3 scan. Note: new
+ * not-null constraints are handled here too.
+*/
 typedef struct NewConstraint
 {
 	char	   *name;			/* Constraint name, or NULL if none */
-	ConstrType	contype;		/* CHECK or FOREIGN */
+	ConstrType	contype;		/* CHECK or FOREIGN or NOT NULL */
 	Oid			refrelid;		/* PK rel, if FOREIGN */
 	Oid			refindid;		/* OID of PK's index, if FOREIGN */
 	bool		conwithperiod;	/* Whether the new FOREIGN KEY uses PERIOD */
 	Oid			conid;			/* OID of pg_constraint entry, if FOREIGN */
+	int			attnum;			/* NOT NULL constraint attribute number */
 	Node	   *qual;			/* Check expr or CONSTR_FOREIGN Constraint */
 	ExprState  *qualstate;		/* Execution state for CHECK expr */
 } NewConstraint;
@@ -6217,6 +6220,9 @@ ATRewriteTable(AlteredTableInfo *tab, Oid OIDNewHeap)
 				needscan = true;
 				con->qualstate = ExecPrepareExpr((Expr *) expand_generated_columns_in_expr(con->qual, oldrel, 1), estate);
 				break;
+			case CONSTR_NOTNULL:
+				/* Nothing to do here */
+				break;
 			case CONSTR_FOREIGN:
 				/* Nothing to do here */
 				break;
@@ -6270,10 +6276,69 @@ ATRewriteTable(AlteredTableInfo *tab, Oid OIDNewHeap)
 														wholeatt->attnum);
 			}
 		}
-		if (notnull_attrs || notnull_virtual_attrs)
-			needscan = true;
 	}
 
+	/*-
+	 * If we have to verify new not-null constraints and don't have any other
+	 * reason to fully scan the table, then we can use indexes to test for
+	 * absence of NULL values instead of scanning.  The following conditions
+	 * must be met:
+	 * - we're operating on a regular table
+	 * - we hold AccessExclusiveLock on the table
+	 * - no not-null constraint covers a virtual generated column,
+	 *   because no indexes can be created on them
+	 */
+	if (!needscan &&
+		newrel == NULL &&
+		tab->verify_new_notnull &&
+		notnull_virtual_attrs == NIL &&
+		oldrel->rd_rel->relkind == RELKIND_RELATION &&
+		CheckRelationLockedByMe(oldrel, AccessExclusiveLock, false))
+	{
+		List	   *notnull_attnums = NIL;
+
+		Assert(!tab->rewrite);
+
+		foreach(l, tab->constraints)
+		{
+			Form_pg_attribute attr;
+			NewConstraint *con = lfirst(l);
+
+			if (con->contype != CONSTR_NOTNULL)
+				continue;
+
+			attr = TupleDescAttr(newTupDesc, con->attnum - 1);
+
+			Assert(attr->attnotnull);
+			Assert(attr->attnum == con->attnum);
+
+			if (attr->attgenerated == ATTRIBUTE_GENERATED_VIRTUAL)
+			{
+				needscan = true;
+				break;
+			}
+
+			notnull_attnums = lappend_int(notnull_attnums, attr->attnum);
+		}
+
+		/*
+		 * Validate new NOT NULL constraints, unless we need a scan for other
+		 * reasons, because we can validate them cheaply there, and doing it
+		 * also here would be a waste of cycles.
+		 */
+		if (notnull_attnums != NIL && !needscan)
+		{
+			if (!index_check_notnull(oldrel, notnull_attnums))
+				needscan = true;
+			else
+				ereport(DEBUG1,
+						errmsg_internal("all new not-null constraints on relation \"%s\" have been validated by using index scan",
+										RelationGetRelationName(oldrel)));
+		}
+	}
+	else if (notnull_attrs || notnull_virtual_attrs)
+		needscan = true;
+
 	if (newrel || needscan)
 	{
 		ExprContext *econtext;
@@ -7949,6 +8014,7 @@ ATExecSetNotNull(List **wqueue, Relation rel, char *conName, char *colName,
 	CookedConstraint *ccon;
 	List	   *cooked;
 	bool		is_no_inherit = false;
+	AlteredTableInfo *tab = NULL;
 
 	/* Guard against stack overflow due to overly deep inheritance tree. */
 	check_stack_depth();
@@ -8073,10 +8139,32 @@ ATExecSetNotNull(List **wqueue, Relation rel, char *conName, char *colName,
 	constraint->is_no_inherit = is_no_inherit;
 	constraint->conname = conName;
 
+	tab = ATGetQueueEntry(wqueue, rel);
+
 	/* and do it */
 	cooked = AddRelationNewConstraints(rel, NIL, list_make1(constraint),
 									   false, !recursing, false, NULL);
 	ccon = linitial(cooked);
+
+	Assert(ccon->contype == CONSTR_NOTNULL);
+
+	/*
+	 * We may use indexscan to vertify not-null constraint in Phase3.  Add the
+	 * to-be-validated not-null constraint to Phase 3's queue.
+	 */
+	if (!ccon->skip_validation)
+	{
+		NewConstraint *newcon;
+
+		newcon = (NewConstraint *) palloc0(sizeof(NewConstraint));
+
+		newcon->name = ccon->name;
+		newcon->contype = ccon->contype;
+		newcon->attnum = ccon->attnum;
+
+		tab->constraints = lappend(tab->constraints, newcon);
+	}
+
 	ObjectAddressSet(address, ConstraintRelationId, ccon->conoid);
 
 	InvokeObjectPostAlterHook(RelationRelationId,
@@ -9983,13 +10071,15 @@ ATAddCheckNNConstraint(List **wqueue, AlteredTableInfo *tab, Relation rel,
 	{
 		CookedConstraint *ccon = (CookedConstraint *) lfirst(lcon);
 
-		if (!ccon->skip_validation && ccon->contype != CONSTR_NOTNULL)
+		if (!ccon->skip_validation)
 		{
 			NewConstraint *newcon;
 
 			newcon = palloc0_object(NewConstraint);
 			newcon->name = ccon->name;
 			newcon->contype = ccon->contype;
+			if (ccon->contype == CONSTR_NOTNULL)
+				newcon->attnum = ccon->attnum;
 			newcon->qual = ccon->expr;
 
 			tab->constraints = lappend(tab->constraints, newcon);
@@ -13258,6 +13348,7 @@ QueueNNConstraintValidation(List **wqueue, Relation conrel, Relation rel,
 	List	   *children = NIL;
 	AttrNumber	attnum;
 	char	   *colname;
+	NewConstraint *newcon;
 
 	con = (Form_pg_constraint) GETSTRUCT(contuple);
 	Assert(con->contype == CONSTRAINT_NOTNULL);
@@ -13321,7 +13412,20 @@ QueueNNConstraintValidation(List **wqueue, Relation conrel, Relation rel,
 	/* Set attnotnull appropriately without queueing another validation */
 	set_attnotnull(NULL, rel, attnum, true, false);
 
+	/*
+	 * Queue validation for phase 3.
+	 *
+	 * ALTER TABLE SET NOT NULL will add NOT NULL constraint to
+	 * AlteredTableInfo->constraints, for consistency, do the same here.
+	 */
+	newcon = (NewConstraint *) palloc0(sizeof(NewConstraint));
+	newcon->name = colname;
+	newcon->contype = CONSTR_NOTNULL;
+	newcon->attnum = attnum;
+
+	/* Find or create work queue entry for this table */
 	tab = ATGetQueueEntry(wqueue, rel);
+	tab->constraints = lappend(tab->constraints, newcon);
 	tab->verify_new_notnull = true;
 
 	/*
diff --git a/src/backend/executor/execIndexing.c b/src/backend/executor/execIndexing.c
index 6ae0f959592..88694ce0335 100644
--- a/src/backend/executor/execIndexing.c
+++ b/src/backend/executor/execIndexing.c
@@ -108,12 +108,15 @@
 
 #include "access/genam.h"
 #include "access/relscan.h"
+#include "access/table.h"
 #include "access/tableam.h"
 #include "access/xact.h"
 #include "catalog/index.h"
+#include "catalog/pg_am_d.h"
 #include "executor/executor.h"
 #include "nodes/nodeFuncs.h"
 #include "storage/lmgr.h"
+#include "utils/fmgroids.h"
 #include "utils/injection_point.h"
 #include "utils/multirangetypes.h"
 #include "utils/rangetypes.h"
@@ -146,6 +149,7 @@ static bool index_expression_changed_walker(Node *node,
 											Bitmapset *allUpdatedCols);
 static void ExecWithoutOverlapsNotEmpty(Relation rel, NameData attname, Datum attval,
 										char typtype, Oid atttypid);
+static bool index_check_notnull_internal(Relation relation, List *attnums, List *idxs);
 
 /* ----------------------------------------------------------------
  *		ExecOpenIndices
@@ -1178,3 +1182,212 @@ ExecWithoutOverlapsNotEmpty(Relation rel, NameData attname, Datum attval, char t
 				 errmsg("empty WITHOUT OVERLAPS value found in column \"%s\" in relation \"%s\"",
 						NameStr(attname), RelationGetRelationName(rel))));
 }
+
+/*
+ * notnull_attnums: list of attribute numbers of all new not-null constraints.
+ *
+ * First check whether the relation has a suitable index for each not-null
+ * attribute, then using indexscan mechanism to verify that *all* attributes on
+ * notnull_attnums are indeed not null.
+ *
+ * Returning true means all new not-null constraints have been verified, no
+ * need an extra scan to verify newly added not-null constraints.
+ */
+bool
+index_check_notnull(Relation relation, List *notnull_attnums)
+{
+	Relation	pg_index;
+	Relation	index_rel;
+	SysScanDesc indscan;
+	ScanKeyData skey;
+	HeapTuple	htup;
+	TupleDesc	tupdesc;
+	Form_pg_attribute attr;
+	List	   *idxs = NIL;
+	List	   *attnums = NIL;
+
+	tupdesc = RelationGetDescr(relation);
+
+	/* Prepare to scan pg_index for entries having indrelid = this rel */
+	ScanKeyInit(&skey,
+				Anum_pg_index_indrelid,
+				BTEqualStrategyNumber, F_OIDEQ,
+				ObjectIdGetDatum(RelationGetRelid(relation)));
+
+	pg_index = table_open(IndexRelationId, AccessShareLock);
+	indscan = systable_beginscan(pg_index, IndexIndrelidIndexId, true,
+								 NULL, 1, &skey);
+
+	while (HeapTupleIsValid(htup = systable_getnext(indscan)))
+	{
+		Form_pg_index index = (Form_pg_index) GETSTRUCT(htup);
+
+		/*
+		 * we can only use non-deferred, validated, and alive btree index to
+		 * validate not-null constraints
+		 */
+		if (!index->indimmediate || !index->indisvalid || !index->indislive)
+			continue;
+
+		/* can not use expression index or partial index too */
+		if (!heap_attisnull(htup, Anum_pg_index_indexprs, NULL) ||
+			!heap_attisnull(htup, Anum_pg_index_indpred, NULL))
+			continue;
+
+		index_rel = index_open(index->indexrelid, AccessShareLock);
+
+		/* can only apply to btree index */
+		if (index_rel->rd_rel->relam != BTREE_AM_OID)
+		{
+			index_close(index_rel, AccessShareLock);
+			continue;
+		}
+
+		/* collect index attnums while loop */
+		for (int i = 0; i < index->indnkeyatts; i++)
+		{
+			attr = TupleDescAttr(tupdesc, (index->indkey.values[i] - 1));
+
+			if (attr->attisdropped)
+				continue;
+
+			if (list_member_int(notnull_attnums, attr->attnum) &&
+				!list_member_int(attnums, attr->attnum))
+			{
+				attnums = lappend_int(attnums, attr->attnum);
+				idxs = lappend_oid(idxs, index->indexrelid);
+			}
+		}
+		index_close(index_rel, NoLock);
+	}
+	systable_endscan(indscan);
+	table_close(pg_index, AccessShareLock);
+
+	if (attnums == NIL)
+		return false;
+
+	/*
+	 * every not-null constraint requires an index for indexscan.  If no such
+	 * index exists, we need to use regular table scan to validate not-null
+	 * constraints.
+	 */
+	foreach_int(attno, notnull_attnums)
+	{
+		if (!list_member_int(attnums, attno))
+			return false;
+	}
+
+	return index_check_notnull_internal(relation, attnums, idxs);
+}
+
+/*
+ * Use indexscan mechanism to fast verify each attribute in "attnums" are
+ * not-null or not.
+ */
+static bool
+index_check_notnull_internal(Relation relation, List *attnums, List *idxs)
+{
+	EState	   *estate;
+	ExprContext *econtext;
+	TupleTableSlot *existing_slot;
+	bool		all_not_null = true;
+	ListCell   *lc,
+			   *lc2;
+
+	/*
+	 * Need an EState for slot to hold the current tuple.
+	 */
+	estate = CreateExecutorState();
+	econtext = GetPerTupleExprContext(estate);
+
+	forboth(lc, attnums, lc2, idxs)
+	{
+		SnapshotData DirtySnapshot;
+		IndexScanDesc index_scan;
+		ScanKeyData scankeys[INDEX_MAX_KEYS];
+		IndexInfo  *indexInfo;
+		AttrNumber	sk_attno = -1;
+		Relation	index;
+		int			indnkeyatts;
+
+		AttrNumber	attno = lfirst_int(lc);
+		Oid			indexoid = lfirst_oid(lc2);
+
+		existing_slot = table_slot_create(relation, NULL);
+
+		/* Arrange for econtext's scan tuple to be the tuple under test */
+		econtext->ecxt_scantuple = existing_slot;
+
+		index = index_open(indexoid, NoLock);
+
+		indexInfo = BuildIndexInfo(index);
+		indnkeyatts = IndexRelationGetNumberOfKeyAttributes(index);
+
+		/*
+		 * Search the tuples that are in the index for any violations,
+		 * including tuples that aren't visible yet.
+		 */
+		InitDirtySnapshot(DirtySnapshot);
+
+		for (int i = 0; i < indnkeyatts; i++)
+		{
+			if (indexInfo->ii_IndexAttrNumbers[i] == attno)
+			{
+				sk_attno = i + 1;
+				break;
+			}
+		}
+
+		if (sk_attno == -1)
+			elog(ERROR, "cache lookup failed for attribute number %d on index %u", indexoid, attno);
+
+		for (int i = 0; i < indnkeyatts; i++)
+		{
+			/* set up an IS NULL scan key so that we ignore not nulls */
+			ScanKeyEntryInitialize(&scankeys[i],
+								   SK_ISNULL | SK_SEARCHNULL,
+								   sk_attno,	/* index col to scan */
+								   InvalidStrategy, /* no strategy */
+								   InvalidOid,	/* no strategy subtype */
+								   InvalidOid,	/* no collation */
+								   InvalidOid,	/* no reg proc for this */
+								   (Datum) 0);	/* constant */
+		}
+
+		index_scan = index_beginscan(relation, index, &DirtySnapshot, NULL, indnkeyatts, 0);
+		index_rescan(index_scan, scankeys, indnkeyatts, NULL, 0);
+
+		while (index_getnext_slot(index_scan, ForwardScanDirection, existing_slot))
+		{
+			Datum		values[INDEX_MAX_KEYS];
+			bool		nulls[INDEX_MAX_KEYS];
+
+			/*
+			 * Extract the index column values and isnull flags from the
+			 * existing tuple.
+			 */
+			FormIndexDatum(indexInfo, existing_slot, estate, values, nulls);
+
+			if (nulls[sk_attno - 1])
+			{
+				all_not_null = false;
+				break;
+			}
+		}
+
+		index_endscan(index_scan);
+		index_close(index, NoLock);
+		ExecDropSingleTupleTableSlot(existing_slot);
+
+		/* exit earlier */
+		if (!all_not_null)
+		{
+			FreeExecutorState(estate);
+			return false;
+		}
+	}
+
+	FreeExecutorState(estate);
+
+	return true;
+}
diff --git a/src/include/executor/executor.h b/src/include/executor/executor.h
index 5929aabc353..7f24caeeafb 100644
--- a/src/include/executor/executor.h
+++ b/src/include/executor/executor.h
@@ -756,6 +756,8 @@ extern void check_exclusion_constraint(Relation heap, Relation index,
 									   const Datum *values, const bool *isnull,
 									   EState *estate, bool newIndex);
 
+extern bool index_check_notnull(Relation relation, List *notnull_attnums);
+
 /*
  * prototypes from functions in execReplication.c
  */
diff --git a/src/test/isolation/expected/indexscan-check-notnull.out b/src/test/isolation/expected/indexscan-check-notnull.out
new file mode 100644
index 00000000000..c6a652e2518
--- /dev/null
+++ b/src/test/isolation/expected/indexscan-check-notnull.out
@@ -0,0 +1,97 @@
+Parsed test spec with 2 sessions
+
+starting permutation: s1_b1 s2_b1 s1_d1 s2_a1 s1_c1 s2_c1 s1_q1
+step s1_b1: BEGIN ISOLATION LEVEL REPEATABLE READ;
+step s2_b1: BEGIN ISOLATION LEVEL REPEATABLE READ;
+step s1_d1: DELETE FROM t;
+step s2_a1: ALTER TABLE t ADD CONSTRAINT t1_nn NOT NULL a; <waiting ...>
+step s1_c1: COMMIT;
+step s2_a1: <... completed>
+step s2_c1: COMMIT;
+step s1_q1: SELECT conname, conrelid::regclass, contype, convalidated
+              FROM pg_constraint WHERE conname = 't1_nn';
+
+conname|conrelid|contype|convalidated
+-------+--------+-------+------------
+t1_nn  |t       |n      |t           
+(1 row)
+
+
+starting permutation: s1_b2 s2_b1 s1_d1 s2_a1 s1_c1 s2_c1 s1_q1
+step s1_b2: BEGIN;
+step s2_b1: BEGIN ISOLATION LEVEL REPEATABLE READ;
+step s1_d1: DELETE FROM t;
+step s2_a1: ALTER TABLE t ADD CONSTRAINT t1_nn NOT NULL a; <waiting ...>
+step s1_c1: COMMIT;
+step s2_a1: <... completed>
+step s2_c1: COMMIT;
+step s1_q1: SELECT conname, conrelid::regclass, contype, convalidated
+              FROM pg_constraint WHERE conname = 't1_nn';
+
+conname|conrelid|contype|convalidated
+-------+--------+-------+------------
+t1_nn  |t       |n      |t           
+(1 row)
+
+
+starting permutation: s1_b1 s2_b2 s1_d1 s2_a1 s1_c1 s2_c1 s1_q1
+step s1_b1: BEGIN ISOLATION LEVEL REPEATABLE READ;
+step s2_b2: BEGIN;
+step s1_d1: DELETE FROM t;
+step s2_a1: ALTER TABLE t ADD CONSTRAINT t1_nn NOT NULL a; <waiting ...>
+step s1_c1: COMMIT;
+step s2_a1: <... completed>
+step s2_c1: COMMIT;
+step s1_q1: SELECT conname, conrelid::regclass, contype, convalidated
+              FROM pg_constraint WHERE conname = 't1_nn';
+
+conname|conrelid|contype|convalidated
+-------+--------+-------+------------
+t1_nn  |t       |n      |t           
+(1 row)
+
+
+starting permutation: s1_b1 s2_b1 s2_a1 s1_r1 s2_r1
+step s1_b1: BEGIN ISOLATION LEVEL REPEATABLE READ;
+step s2_b1: BEGIN ISOLATION LEVEL REPEATABLE READ;
+step s2_a1: ALTER TABLE t ADD CONSTRAINT t1_nn NOT NULL a;
+ERROR:  column "a" of relation "t" contains null values
+step s1_r1: ROLLBACK;
+step s2_r1: ROLLBACK;
+
+starting permutation: s1_b1 s2_b2 s2_d1 s1_d1 s2_r1 s1_a1 s1_q1 s1_r1
+step s1_b1: BEGIN ISOLATION LEVEL REPEATABLE READ;
+step s2_b2: BEGIN;
+step s2_d1: DROP INDEX t_ab_idx;
+step s1_d1: DELETE FROM t; <waiting ...>
+step s2_r1: ROLLBACK;
+step s1_d1: <... completed>
+step s1_a1: ALTER TABLE t ADD CONSTRAINT t1_nn NOT NULL a;
+step s1_q1: SELECT conname, conrelid::regclass, contype, convalidated
+              FROM pg_constraint WHERE conname = 't1_nn';
+
+conname|conrelid|contype|convalidated
+-------+--------+-------+------------
+t1_nn  |t       |n      |t           
+(1 row)
+
+step s1_r1: ROLLBACK;
+
+starting permutation: s1_b2 s2_b1 s1_d1 s2_d1 s1_s0 s1_a1 s1_c1 s2_c1 s1_q1
+step s1_b2: BEGIN;
+step s2_b1: BEGIN ISOLATION LEVEL REPEATABLE READ;
+step s1_d1: DELETE FROM t;
+step s2_d1: DROP INDEX t_ab_idx; <waiting ...>
+step s1_s0: SAVEPOINT s0;
+step s1_a1: ALTER TABLE t ADD CONSTRAINT t1_nn NOT NULL a;
+step s1_c1: COMMIT;
+step s2_d1: <... completed>
+step s2_c1: COMMIT;
+step s1_q1: SELECT conname, conrelid::regclass, contype, convalidated
+              FROM pg_constraint WHERE conname = 't1_nn';
+
+conname|conrelid|contype|convalidated
+-------+--------+-------+------------
+t1_nn  |t       |n      |t           
+(1 row)
+
diff --git a/src/test/isolation/isolation_schedule b/src/test/isolation/isolation_schedule
index 01ff1c6586f..7ce6bbcaf89 100644
--- a/src/test/isolation/isolation_schedule
+++ b/src/test/isolation/isolation_schedule
@@ -58,6 +58,7 @@ test: merge-delete
 test: merge-update
 test: merge-match-recheck
 test: merge-join
+test: indexscan-check-notnull
 test: delete-abort-savept
 test: delete-abort-savept-2
 test: aborted-keyrevoke
diff --git a/src/test/isolation/specs/indexscan-check-notnull.spec b/src/test/isolation/specs/indexscan-check-notnull.spec
new file mode 100644
index 00000000000..05b4488550c
--- /dev/null
+++ b/src/test/isolation/specs/indexscan-check-notnull.spec
@@ -0,0 +1,45 @@
+
+#
+# using indexscan to check a column not-null constraint
+# is satisfied or not.
+#
+
+setup
+{
+  CREATE TABLE t (a int, b int);
+  CREATE INDEX t_ab_idx on t(a,b);
+  INSERT INTO t values (null, 1);
+  INSERT INTO t SELECT x, x*10 FROM generate_series(1,3) g(x);
+}
+
+teardown
+{
+  DROP TABLE t;
+}
+
+session s1
+step s1_b1  { BEGIN ISOLATION LEVEL REPEATABLE READ; }
+step s1_b2  { BEGIN; }
+step s1_d1  { DELETE FROM t;}
+step s1_s0  { SAVEPOINT s0;}
+step s1_a1  { ALTER TABLE t ADD CONSTRAINT t1_nn NOT NULL a;}
+step s1_q1  { SELECT conname, conrelid::regclass, contype, convalidated
+              FROM pg_constraint WHERE conname = 't1_nn';
+            }
+step s1_r1  { ROLLBACK; }
+step s1_c1  { COMMIT; }
+
+session s2
+step s2_b1  { BEGIN ISOLATION LEVEL REPEATABLE READ; }
+step s2_b2  { BEGIN; }
+step s2_a1  { ALTER TABLE t ADD CONSTRAINT t1_nn NOT NULL a;}
+step s2_d1  { DROP INDEX t_ab_idx;}
+step s2_r1  { ROLLBACK; }
+step s2_c1  { COMMIT; }
+
+permutation s1_b1 s2_b1 s1_d1 s2_a1 s1_c1 s2_c1 s1_q1
+permutation s1_b2 s2_b1 s1_d1 s2_a1 s1_c1 s2_c1 s1_q1
+permutation s1_b1 s2_b2 s1_d1 s2_a1 s1_c1 s2_c1 s1_q1
+permutation s1_b1 s2_b1 s2_a1 s1_r1 s2_r1
+permutation s1_b1 s2_b2 s2_d1 s1_d1 s2_r1 s1_a1 s1_q1 s1_r1
+permutation s1_b2 s2_b1 s1_d1 s2_d1 s1_s0 s1_a1 s1_c1 s2_c1 s1_q1
diff --git a/src/test/modules/test_misc/meson.build b/src/test/modules/test_misc/meson.build
index 6e8db1621a7..56faf359b29 100644
--- a/src/test/modules/test_misc/meson.build
+++ b/src/test/modules/test_misc/meson.build
@@ -19,6 +19,7 @@ tests += {
       't/008_replslot_single_user.pl',
       't/009_log_temp_files.pl',
       't/010_index_concurrently_upsert.pl',
+      't/011_indexscan_validate_notnull.pl',
     ],
     # The injection points are cluster-wide, so disable installcheck
     'runningcheck': false,
diff --git a/src/test/modules/test_misc/t/011_indexscan_validate_notnull.pl b/src/test/modules/test_misc/t/011_indexscan_validate_notnull.pl
new file mode 100644
index 00000000000..a3f3cb409b6
--- /dev/null
+++ b/src/test/modules/test_misc/t/011_indexscan_validate_notnull.pl
@@ -0,0 +1,163 @@
+# Copyright (c) 2025, PostgreSQL Global Development Group
+
+# Verify that indexscan mechanism can speedup ALTER TABLE ADD NOT NULL
+
+
+use strict;
+use warnings FATAL => 'all';
+use PostgreSQL::Test::Cluster;
+use PostgreSQL::Test::Utils;
+use Test::More;
+
+# Initialize a test cluster
+my $node = PostgreSQL::Test::Cluster->new('primary');
+$node->init();
+# Turn message level up to DEBUG1 so that we get the messages we want to see
+$node->append_conf('postgresql.conf', 'client_min_messages = DEBUG1');
+$node->start;
+
+# Run a SQL command and return psql's stderr (including debug messages)
+sub run_sql_command
+{
+	my $sql = shift;
+	my $stderr;
+
+	$node->psql(
+		'postgres',
+		$sql,
+		stderr => \$stderr,
+		on_error_die => 1,
+		on_error_stop => 1);
+	return $stderr;
+}
+
+# Check whether result of run_sql_command shows that we did a verify pass
+sub is_table_verified
+{
+	my $output = shift;
+	return index($output, 'DEBUG:  verifying table') != -1;
+}
+
+# Check whether result of run_sql_command shows that we did a verify pass
+sub is_indexscan_veritify_notnull
+{
+	my $output = shift;
+	return index($output, 'DEBUG:  all new not-null constraints on relation') != -1;
+}
+
+my $output;
+
+note "test alter table SET NOT NULL using indexscan with partitioned table";
+
+run_sql_command(
+    'CREATE TABLE tp (a int, b int, c int, d int ) PARTITION BY range(a);
+     CREATE TABLE tpp1 partition of tp for values from ( 1 ) to (10);
+     CREATE TABLE tpp2 partition of tp for values from ( 10 ) to (21);
+     INSERT INTO tp select g, g + 10, g + 15, g + random(min=>1::int, max=>10::int) from generate_series(1,19) g;
+     CREATE INDEX ON tp(b); ');
+
+$output = run_sql_command('ALTER TABLE tp ALTER COLUMN b SET NOT NULL;');
+ok(is_indexscan_veritify_notnull($output),
+	'column b will use indexscan to verify not-null status, no need scan table');
+ok( $output =~
+	  m/all new not-null constraints on relation "tpp1" have been validated by using index scan/,
+	'all newly added constraints proved by indexscan');
+
+run_sql_command(
+	'ALTER TABLE tp ALTER COLUMN b DROP NOT NULL;');
+
+# use indexes on partitions to fast vertifing not-null should be ok
+$output = run_sql_command('ALTER TABLE tpp1 ALTER COLUMN b SET NOT NULL;');
+ok(is_indexscan_veritify_notnull($output), 'use indexscan to validate column b not-null will not scan table');
+ok(!is_table_verified($output), 'no table scan for pp1');
+ok( $output =~
+	  m/all new not-null constraints on relation "tpp1" have been validated by using index scan/,
+	'all newly added constraints proved by indexscan');
+
+$output = run_sql_command('ALTER TABLE tpp2 ALTER COLUMN b SET NOT NULL;');
+ok(is_indexscan_veritify_notnull($output), 'use indexscan to validate column b not-null, will not scan table');
+ok(!is_table_verified($output), 'no table scan for tpp2');
+ok( $output =~
+	  m/all new not-null constraints on relation "tpp2" have been validated by using index scan/,
+	'all newly added constraints proved by indexscan');
+
+run_sql_command(
+	'ALTER TABLE tp ALTER COLUMN b DROP NOT NULL;');
+
+# table rewrite then can not use indexscan to verify not-null constraint
+$output = run_sql_command(
+	'ALTER TABLE tp ALTER COLUMN b SET NOT NULL, ALTER COLUMN b SET DATA TYPE bigint;'
+);
+ok(!is_table_verified($output), 'no table scan for tp');
+ok(!is_indexscan_veritify_notnull($output), 'table tp will rewrite, can not use indexscan to verify not-null constraints on it');
+
+# test using indexscan with multiple not-null constraints
+run_sql_command(
+    'ALTER TABLE tp ALTER COLUMN b DROP NOT NULL;
+	 CREATE INDEX ON tp(c);
+	 CREATE INDEX ON tp(d); ');
+
+# one column can use indexscan, another can not, so can not use indexscan to verify not-null
+$output = run_sql_command(
+	'ALTER TABLE tp ALTER COLUMN a SET NOT NULL, ADD CONSTRAINT c_nn NOT NULL c');
+ok(is_table_verified($output), 'table scan for tp');
+ok(!is_indexscan_veritify_notnull($output), 'can not use indexscan to verify not-null constraints on table tp');
+
+# all columns have index on it
+# use indexscan to verify multiple not-null constraints should just fine
+$output = run_sql_command(
+	'ALTER TABLE tp ALTER COLUMN d SET NOT NULL, ADD CONSTRAINT c_nn NOT NULL c, ALTER COLUMN b SET NOT NULL;');
+ok(!is_table_verified($output), 'no table scan for tp');
+ok(is_indexscan_veritify_notnull($output),
+	'using indexscan to verify not-null constraints on column b, c, d, no need table scan');
+
+# test with non-partitioned table and other non-Btree index.
+run_sql_command(
+    'CREATE TABLE t1(f1 INT, f2 int, f3 int,f4 int, f5 int);
+     INSERT INTO t1 select g, g+1, g+2, g+3, g+4 from generate_series(1, 100) g;
+     CREATE INDEX t1_f1_f2_idx ON t1(f1,f2);
+     CREATE UNIQUE INDEX t1_f3idx ON t1(f3);
+     CREATE INDEX t1_f3f4idx ON t1(f3) include(f4);
+     CREATE INDEX hash_f5_idx ON t1 USING hash (f5 int4_ops); ');
+
+# ALTER TABLE VALIDATE CONSTRAINT can not use indexscan,
+# because it only hold ShareUpdateExclusiveLock lock.
+run_sql_command('ALTER TABLE t1 ADD CONSTRAINT nn_t1_f2 NOT NULL f2 NOT VALID;');
+
+$output = run_sql_command(
+	'ALTER TABLE t1 VALIDATE CONSTRAINT nn_t1_f2;'
+);
+ok(!is_indexscan_veritify_notnull($output), 'can not use indexscan for ALTER TABLE VALIDATE CONSTRAINT command');
+run_sql_command('ALTER TABLE t1 DROP CONSTRAINT nn_t1_f2;');
+
+$output = run_sql_command(
+	'ALTER TABLE t1 ALTER COLUMN f1 SET NOT NULL, ALTER f1 type bigint;'
+);
+ok(!is_indexscan_veritify_notnull($output), 'table t1 will rewrite, can not use indexscan to validate not-null constraints on t1');
+
+run_sql_command('ALTER TABLE t1 ALTER COLUMN f1 DROP NOT NULL;');
+run_sql_command('ALTER TABLE t1 ADD CONSTRAINT nn NOT NULL f1, ALTER f1 type bigint;');
+
+# can use indexscan mechanism to fast add multiple not-null constraints
+$output = run_sql_command(
+	'ALTER TABLE t1 ALTER COLUMN f2 SET NOT NULL, ALTER COLUMN f1 SET NOT NULL;'
+);
+ok( $output =~
+	  m/all new not-null constraints on relation "t1" have been validated by using index scan/,
+	'all not-null constraints are validated by indexscan');
+
+# using indexscan mechanism to fast add a not-null can only apply to key columns, not include column
+$output = run_sql_command(
+	'ALTER TABLE t1 ADD CONSTRAINT nnf4 NOT NULL f4;'
+);
+ok(!is_indexscan_veritify_notnull($output), 'can not use indexscan to validate not-null constraint on t1');
+
+# if index is not btree index then cannot use indexscan mechanism to fast add not-null constraint
+$output = run_sql_command(
+	'ALTER TABLE t1 ADD CONSTRAINT nn_f5 NOT NULL f5;'
+);
+ok(!is_indexscan_veritify_notnull($output), 'can not use indexscan to validate not-null constraints on t1');
+
+$node->stop('fast');
+
+done_testing();
-- 
2.47.3


--xpkr6zhfzd3fjt76--





^ permalink  raw  reply  [nested|flat] 150+ messages in thread

* [PATCH v8] using indexscan to speedup add not null constraints
@ 2025-10-20 05:29  jian he <[email protected]>
  0 siblings, 0 replies; 150+ messages in thread

From: jian he @ 2025-10-20 05:29 UTC (permalink / raw)

This patch tries to use index_beginscan() / index_getnext() / index_endscan()
mentioned in [1] to speedup adding not-null constraints to the existing table.

The main logic happens in phase3 ATRewriteTable
1. collect all not-null constraints.
2. For each not-null constraint, check whether there is a corresponding index
available for validation. If not, then can not use indexscan to verify not-null
constraints.
3. If any of the following conditions are true
  * table scan or rewrite is required,
  * table wasn't locked with `AccessExclusiveLock`
  * the NOT NULL constraint applies to a virtual generated column
 then index scan cannot be used for fast validation.
4. If all conditions are satisfied, attempt to use indexscan to verify
whether the column contains any NULL values.

concurrency concern:
ALTER TABLE SET NOT NULL will take an ACCESS EXCLUSIVE lock, so there is less
variant of racing issue can occur?  to prove accurate, I wrote some isolation
tests. see[2]

performance:
demo:
case when: %20 percent values are NULL and have been deleted from heap but they
still on the index.

drop table if exists t;
create unlogged table t(a int, b int) with (autovacuum_enabled = off, vacuum_index_cleanup=off);
insert into t select case when g % 5 = 0 then null else g end, g+1
from generate_series(1,1_000_000) g;
create index t_idx_a on t(a);
delete from t where a is null;

alter table t alter column a drop not null;
alter table t add constraint t1 not null a;

the above two statement running several times:
patch Time:: 1.084  ms
master Time: 12.045 ms

references:
[1] https://postgr.es/m/CA%2BTgmoa5NKz8iGW_9v7wz%3D-%2BzQFu%3DE4SZoaTaU1znLaEXRYp-Q%40mail.gmail.com
[2] https://postgr.es/m/900056D1-32DF-4927-8251-3E0C0DC407FD%40anarazel.de
discussion: https://postgr.es/m/CACJufxFiW=4k1is=F1J=r-Cx1RuByXQPUrWB331U47rSnGz+hw@mail.gmail.com
commitfest entry: https://commitfest.postgresql.org/patch/5444
---
 src/backend/commands/tablecmds.c              | 116 +++++++++-
 src/backend/executor/execIndexing.c           | 213 ++++++++++++++++++
 src/include/executor/executor.h               |   2 +
 .../expected/indexscan-check-notnull.out      |  97 ++++++++
 src/test/isolation/isolation_schedule         |   1 +
 .../specs/indexscan-check-notnull.spec        |  45 ++++
 src/test/modules/test_misc/meson.build        |   1 +
 .../t/011_indexscan_validate_notnull.pl       | 163 ++++++++++++++
 8 files changed, 632 insertions(+), 6 deletions(-)
 create mode 100644 src/test/isolation/expected/indexscan-check-notnull.out
 create mode 100644 src/test/isolation/specs/indexscan-check-notnull.spec
 create mode 100644 src/test/modules/test_misc/t/011_indexscan_validate_notnull.pl

diff --git a/src/backend/commands/tablecmds.c b/src/backend/commands/tablecmds.c
index f976c0e5c7e..2af06630b35 100644
--- a/src/backend/commands/tablecmds.c
+++ b/src/backend/commands/tablecmds.c
@@ -210,16 +210,19 @@ typedef struct AlteredTableInfo
 	List	   *changedStatisticsDefs;	/* string definitions of same */
 } AlteredTableInfo;
 
-/* Struct describing one new constraint to check in Phase 3 scan */
-/* Note: new not-null constraints are handled elsewhere */
+/*
+ * Struct describing one new constraint to check in Phase 3 scan. Note: new
+ * not-null constraints are handled here too.
+*/
 typedef struct NewConstraint
 {
 	char	   *name;			/* Constraint name, or NULL if none */
-	ConstrType	contype;		/* CHECK or FOREIGN */
+	ConstrType	contype;		/* CHECK or FOREIGN or NOT NULL */
 	Oid			refrelid;		/* PK rel, if FOREIGN */
 	Oid			refindid;		/* OID of PK's index, if FOREIGN */
 	bool		conwithperiod;	/* Whether the new FOREIGN KEY uses PERIOD */
 	Oid			conid;			/* OID of pg_constraint entry, if FOREIGN */
+	int			attnum;			/* NOT NULL constraint attribute number */
 	Node	   *qual;			/* Check expr or CONSTR_FOREIGN Constraint */
 	ExprState  *qualstate;		/* Execution state for CHECK expr */
 } NewConstraint;
@@ -6217,6 +6220,9 @@ ATRewriteTable(AlteredTableInfo *tab, Oid OIDNewHeap)
 				needscan = true;
 				con->qualstate = ExecPrepareExpr((Expr *) expand_generated_columns_in_expr(con->qual, oldrel, 1), estate);
 				break;
+			case CONSTR_NOTNULL:
+				/* Nothing to do here */
+				break;
 			case CONSTR_FOREIGN:
 				/* Nothing to do here */
 				break;
@@ -6270,10 +6276,69 @@ ATRewriteTable(AlteredTableInfo *tab, Oid OIDNewHeap)
 														wholeatt->attnum);
 			}
 		}
-		if (notnull_attrs || notnull_virtual_attrs)
-			needscan = true;
 	}
 
+	/*-
+	 * If we have to verify new not-null constraints and don't have any other
+	 * reason to fully scan the table, then we can use indexes to test for
+	 * absence of NULL values instead of scanning.  The following conditions
+	 * must be met:
+	 * - we're operating on a regular table
+	 * - we hold AccessExclusiveLock on the table
+	 * - no not-null constraint covers a virtual generated column,
+	 *   because no indexes can be created on them
+	 */
+	if (!needscan &&
+		newrel == NULL &&
+		tab->verify_new_notnull &&
+		notnull_virtual_attrs == NIL &&
+		oldrel->rd_rel->relkind == RELKIND_RELATION &&
+		CheckRelationLockedByMe(oldrel, AccessExclusiveLock, false))
+	{
+		List	   *notnull_attnums = NIL;
+
+		Assert(!tab->rewrite);
+
+		foreach(l, tab->constraints)
+		{
+			Form_pg_attribute attr;
+			NewConstraint *con = lfirst(l);
+
+			if (con->contype != CONSTR_NOTNULL)
+				continue;
+
+			attr = TupleDescAttr(newTupDesc, con->attnum - 1);
+
+			Assert(attr->attnotnull);
+			Assert(attr->attnum == con->attnum);
+
+			if (attr->attgenerated == ATTRIBUTE_GENERATED_VIRTUAL)
+			{
+				needscan = true;
+				break;
+			}
+
+			notnull_attnums = lappend_int(notnull_attnums, attr->attnum);
+		}
+
+		/*
+		 * Validate new NOT NULL constraints, unless we need a scan for other
+		 * reasons, because we can validate them cheaply there, and doing it
+		 * also here would be a waste of cycles.
+		 */
+		if (notnull_attnums != NIL && !needscan)
+		{
+			if (!index_check_notnull(oldrel, notnull_attnums))
+				needscan = true;
+			else
+				ereport(DEBUG1,
+						errmsg_internal("all new not-null constraints on relation \"%s\" have been validated by using index scan",
+										RelationGetRelationName(oldrel)));
+		}
+	}
+	else if (notnull_attrs || notnull_virtual_attrs)
+		needscan = true;
+
 	if (newrel || needscan)
 	{
 		ExprContext *econtext;
@@ -7949,6 +8014,7 @@ ATExecSetNotNull(List **wqueue, Relation rel, char *conName, char *colName,
 	CookedConstraint *ccon;
 	List	   *cooked;
 	bool		is_no_inherit = false;
+	AlteredTableInfo *tab = NULL;
 
 	/* Guard against stack overflow due to overly deep inheritance tree. */
 	check_stack_depth();
@@ -8073,10 +8139,32 @@ ATExecSetNotNull(List **wqueue, Relation rel, char *conName, char *colName,
 	constraint->is_no_inherit = is_no_inherit;
 	constraint->conname = conName;
 
+	tab = ATGetQueueEntry(wqueue, rel);
+
 	/* and do it */
 	cooked = AddRelationNewConstraints(rel, NIL, list_make1(constraint),
 									   false, !recursing, false, NULL);
 	ccon = linitial(cooked);
+
+	Assert(ccon->contype == CONSTR_NOTNULL);
+
+	/*
+	 * We may use indexscan to vertify not-null constraint in Phase3.  Add the
+	 * to-be-validated not-null constraint to Phase 3's queue.
+	 */
+	if (!ccon->skip_validation)
+	{
+		NewConstraint *newcon;
+
+		newcon = (NewConstraint *) palloc0(sizeof(NewConstraint));
+
+		newcon->name = ccon->name;
+		newcon->contype = ccon->contype;
+		newcon->attnum = ccon->attnum;
+
+		tab->constraints = lappend(tab->constraints, newcon);
+	}
+
 	ObjectAddressSet(address, ConstraintRelationId, ccon->conoid);
 
 	InvokeObjectPostAlterHook(RelationRelationId,
@@ -9983,13 +10071,15 @@ ATAddCheckNNConstraint(List **wqueue, AlteredTableInfo *tab, Relation rel,
 	{
 		CookedConstraint *ccon = (CookedConstraint *) lfirst(lcon);
 
-		if (!ccon->skip_validation && ccon->contype != CONSTR_NOTNULL)
+		if (!ccon->skip_validation)
 		{
 			NewConstraint *newcon;
 
 			newcon = palloc0_object(NewConstraint);
 			newcon->name = ccon->name;
 			newcon->contype = ccon->contype;
+			if (ccon->contype == CONSTR_NOTNULL)
+				newcon->attnum = ccon->attnum;
 			newcon->qual = ccon->expr;
 
 			tab->constraints = lappend(tab->constraints, newcon);
@@ -13258,6 +13348,7 @@ QueueNNConstraintValidation(List **wqueue, Relation conrel, Relation rel,
 	List	   *children = NIL;
 	AttrNumber	attnum;
 	char	   *colname;
+	NewConstraint *newcon;
 
 	con = (Form_pg_constraint) GETSTRUCT(contuple);
 	Assert(con->contype == CONSTRAINT_NOTNULL);
@@ -13321,7 +13412,20 @@ QueueNNConstraintValidation(List **wqueue, Relation conrel, Relation rel,
 	/* Set attnotnull appropriately without queueing another validation */
 	set_attnotnull(NULL, rel, attnum, true, false);
 
+	/*
+	 * Queue validation for phase 3.
+	 *
+	 * ALTER TABLE SET NOT NULL will add NOT NULL constraint to
+	 * AlteredTableInfo->constraints, for consistency, do the same here.
+	 */
+	newcon = (NewConstraint *) palloc0(sizeof(NewConstraint));
+	newcon->name = colname;
+	newcon->contype = CONSTR_NOTNULL;
+	newcon->attnum = attnum;
+
+	/* Find or create work queue entry for this table */
 	tab = ATGetQueueEntry(wqueue, rel);
+	tab->constraints = lappend(tab->constraints, newcon);
 	tab->verify_new_notnull = true;
 
 	/*
diff --git a/src/backend/executor/execIndexing.c b/src/backend/executor/execIndexing.c
index 6ae0f959592..88694ce0335 100644
--- a/src/backend/executor/execIndexing.c
+++ b/src/backend/executor/execIndexing.c
@@ -108,12 +108,15 @@
 
 #include "access/genam.h"
 #include "access/relscan.h"
+#include "access/table.h"
 #include "access/tableam.h"
 #include "access/xact.h"
 #include "catalog/index.h"
+#include "catalog/pg_am_d.h"
 #include "executor/executor.h"
 #include "nodes/nodeFuncs.h"
 #include "storage/lmgr.h"
+#include "utils/fmgroids.h"
 #include "utils/injection_point.h"
 #include "utils/multirangetypes.h"
 #include "utils/rangetypes.h"
@@ -146,6 +149,7 @@ static bool index_expression_changed_walker(Node *node,
 											Bitmapset *allUpdatedCols);
 static void ExecWithoutOverlapsNotEmpty(Relation rel, NameData attname, Datum attval,
 										char typtype, Oid atttypid);
+static bool index_check_notnull_internal(Relation relation, List *attnums, List *idxs);
 
 /* ----------------------------------------------------------------
  *		ExecOpenIndices
@@ -1178,3 +1182,212 @@ ExecWithoutOverlapsNotEmpty(Relation rel, NameData attname, Datum attval, char t
 				 errmsg("empty WITHOUT OVERLAPS value found in column \"%s\" in relation \"%s\"",
 						NameStr(attname), RelationGetRelationName(rel))));
 }
+
+/*
+ * notnull_attnums: list of attribute numbers of all new not-null constraints.
+ *
+ * First check whether the relation has a suitable index for each not-null
+ * attribute, then using indexscan mechanism to verify that *all* attributes on
+ * notnull_attnums are indeed not null.
+ *
+ * Returning true means all new not-null constraints have been verified, no
+ * need an extra scan to verify newly added not-null constraints.
+ */
+bool
+index_check_notnull(Relation relation, List *notnull_attnums)
+{
+	Relation	pg_index;
+	Relation	index_rel;
+	SysScanDesc indscan;
+	ScanKeyData skey;
+	HeapTuple	htup;
+	TupleDesc	tupdesc;
+	Form_pg_attribute attr;
+	List	   *idxs = NIL;
+	List	   *attnums = NIL;
+
+	tupdesc = RelationGetDescr(relation);
+
+	/* Prepare to scan pg_index for entries having indrelid = this rel */
+	ScanKeyInit(&skey,
+				Anum_pg_index_indrelid,
+				BTEqualStrategyNumber, F_OIDEQ,
+				ObjectIdGetDatum(RelationGetRelid(relation)));
+
+	pg_index = table_open(IndexRelationId, AccessShareLock);
+	indscan = systable_beginscan(pg_index, IndexIndrelidIndexId, true,
+								 NULL, 1, &skey);
+
+	while (HeapTupleIsValid(htup = systable_getnext(indscan)))
+	{
+		Form_pg_index index = (Form_pg_index) GETSTRUCT(htup);
+
+		/*
+		 * we can only use non-deferred, validated, and alive btree index to
+		 * validate not-null constraints
+		 */
+		if (!index->indimmediate || !index->indisvalid || !index->indislive)
+			continue;
+
+		/* can not use expression index or partial index too */
+		if (!heap_attisnull(htup, Anum_pg_index_indexprs, NULL) ||
+			!heap_attisnull(htup, Anum_pg_index_indpred, NULL))
+			continue;
+
+		index_rel = index_open(index->indexrelid, AccessShareLock);
+
+		/* can only apply to btree index */
+		if (index_rel->rd_rel->relam != BTREE_AM_OID)
+		{
+			index_close(index_rel, AccessShareLock);
+			continue;
+		}
+
+		/* collect index attnums while loop */
+		for (int i = 0; i < index->indnkeyatts; i++)
+		{
+			attr = TupleDescAttr(tupdesc, (index->indkey.values[i] - 1));
+
+			if (attr->attisdropped)
+				continue;
+
+			if (list_member_int(notnull_attnums, attr->attnum) &&
+				!list_member_int(attnums, attr->attnum))
+			{
+				attnums = lappend_int(attnums, attr->attnum);
+				idxs = lappend_oid(idxs, index->indexrelid);
+			}
+		}
+		index_close(index_rel, NoLock);
+	}
+	systable_endscan(indscan);
+	table_close(pg_index, AccessShareLock);
+
+	if (attnums == NIL)
+		return false;
+
+	/*
+	 * every not-null constraint requires an index for indexscan.  If no such
+	 * index exists, we need to use regular table scan to validate not-null
+	 * constraints.
+	 */
+	foreach_int(attno, notnull_attnums)
+	{
+		if (!list_member_int(attnums, attno))
+			return false;
+	}
+
+	return index_check_notnull_internal(relation, attnums, idxs);
+}
+
+/*
+ * Use indexscan mechanism to fast verify each attribute in "attnums" are
+ * not-null or not.
+ */
+static bool
+index_check_notnull_internal(Relation relation, List *attnums, List *idxs)
+{
+	EState	   *estate;
+	ExprContext *econtext;
+	TupleTableSlot *existing_slot;
+	bool		all_not_null = true;
+	ListCell   *lc,
+			   *lc2;
+
+	/*
+	 * Need an EState for slot to hold the current tuple.
+	 */
+	estate = CreateExecutorState();
+	econtext = GetPerTupleExprContext(estate);
+
+	forboth(lc, attnums, lc2, idxs)
+	{
+		SnapshotData DirtySnapshot;
+		IndexScanDesc index_scan;
+		ScanKeyData scankeys[INDEX_MAX_KEYS];
+		IndexInfo  *indexInfo;
+		AttrNumber	sk_attno = -1;
+		Relation	index;
+		int			indnkeyatts;
+
+		AttrNumber	attno = lfirst_int(lc);
+		Oid			indexoid = lfirst_oid(lc2);
+
+		existing_slot = table_slot_create(relation, NULL);
+
+		/* Arrange for econtext's scan tuple to be the tuple under test */
+		econtext->ecxt_scantuple = existing_slot;
+
+		index = index_open(indexoid, NoLock);
+
+		indexInfo = BuildIndexInfo(index);
+		indnkeyatts = IndexRelationGetNumberOfKeyAttributes(index);
+
+		/*
+		 * Search the tuples that are in the index for any violations,
+		 * including tuples that aren't visible yet.
+		 */
+		InitDirtySnapshot(DirtySnapshot);
+
+		for (int i = 0; i < indnkeyatts; i++)
+		{
+			if (indexInfo->ii_IndexAttrNumbers[i] == attno)
+			{
+				sk_attno = i + 1;
+				break;
+			}
+		}
+
+		if (sk_attno == -1)
+			elog(ERROR, "cache lookup failed for attribute number %d on index %u", indexoid, attno);
+
+		for (int i = 0; i < indnkeyatts; i++)
+		{
+			/* set up an IS NULL scan key so that we ignore not nulls */
+			ScanKeyEntryInitialize(&scankeys[i],
+								   SK_ISNULL | SK_SEARCHNULL,
+								   sk_attno,	/* index col to scan */
+								   InvalidStrategy, /* no strategy */
+								   InvalidOid,	/* no strategy subtype */
+								   InvalidOid,	/* no collation */
+								   InvalidOid,	/* no reg proc for this */
+								   (Datum) 0);	/* constant */
+		}
+
+		index_scan = index_beginscan(relation, index, &DirtySnapshot, NULL, indnkeyatts, 0);
+		index_rescan(index_scan, scankeys, indnkeyatts, NULL, 0);
+
+		while (index_getnext_slot(index_scan, ForwardScanDirection, existing_slot))
+		{
+			Datum		values[INDEX_MAX_KEYS];
+			bool		nulls[INDEX_MAX_KEYS];
+
+			/*
+			 * Extract the index column values and isnull flags from the
+			 * existing tuple.
+			 */
+			FormIndexDatum(indexInfo, existing_slot, estate, values, nulls);
+
+			if (nulls[sk_attno - 1])
+			{
+				all_not_null = false;
+				break;
+			}
+		}
+
+		index_endscan(index_scan);
+		index_close(index, NoLock);
+		ExecDropSingleTupleTableSlot(existing_slot);
+
+		/* exit earlier */
+		if (!all_not_null)
+		{
+			FreeExecutorState(estate);
+			return false;
+		}
+	}
+
+	FreeExecutorState(estate);
+
+	return true;
+}
diff --git a/src/include/executor/executor.h b/src/include/executor/executor.h
index 5929aabc353..7f24caeeafb 100644
--- a/src/include/executor/executor.h
+++ b/src/include/executor/executor.h
@@ -756,6 +756,8 @@ extern void check_exclusion_constraint(Relation heap, Relation index,
 									   const Datum *values, const bool *isnull,
 									   EState *estate, bool newIndex);
 
+extern bool index_check_notnull(Relation relation, List *notnull_attnums);
+
 /*
  * prototypes from functions in execReplication.c
  */
diff --git a/src/test/isolation/expected/indexscan-check-notnull.out b/src/test/isolation/expected/indexscan-check-notnull.out
new file mode 100644
index 00000000000..c6a652e2518
--- /dev/null
+++ b/src/test/isolation/expected/indexscan-check-notnull.out
@@ -0,0 +1,97 @@
+Parsed test spec with 2 sessions
+
+starting permutation: s1_b1 s2_b1 s1_d1 s2_a1 s1_c1 s2_c1 s1_q1
+step s1_b1: BEGIN ISOLATION LEVEL REPEATABLE READ;
+step s2_b1: BEGIN ISOLATION LEVEL REPEATABLE READ;
+step s1_d1: DELETE FROM t;
+step s2_a1: ALTER TABLE t ADD CONSTRAINT t1_nn NOT NULL a; <waiting ...>
+step s1_c1: COMMIT;
+step s2_a1: <... completed>
+step s2_c1: COMMIT;
+step s1_q1: SELECT conname, conrelid::regclass, contype, convalidated
+              FROM pg_constraint WHERE conname = 't1_nn';
+
+conname|conrelid|contype|convalidated
+-------+--------+-------+------------
+t1_nn  |t       |n      |t           
+(1 row)
+
+
+starting permutation: s1_b2 s2_b1 s1_d1 s2_a1 s1_c1 s2_c1 s1_q1
+step s1_b2: BEGIN;
+step s2_b1: BEGIN ISOLATION LEVEL REPEATABLE READ;
+step s1_d1: DELETE FROM t;
+step s2_a1: ALTER TABLE t ADD CONSTRAINT t1_nn NOT NULL a; <waiting ...>
+step s1_c1: COMMIT;
+step s2_a1: <... completed>
+step s2_c1: COMMIT;
+step s1_q1: SELECT conname, conrelid::regclass, contype, convalidated
+              FROM pg_constraint WHERE conname = 't1_nn';
+
+conname|conrelid|contype|convalidated
+-------+--------+-------+------------
+t1_nn  |t       |n      |t           
+(1 row)
+
+
+starting permutation: s1_b1 s2_b2 s1_d1 s2_a1 s1_c1 s2_c1 s1_q1
+step s1_b1: BEGIN ISOLATION LEVEL REPEATABLE READ;
+step s2_b2: BEGIN;
+step s1_d1: DELETE FROM t;
+step s2_a1: ALTER TABLE t ADD CONSTRAINT t1_nn NOT NULL a; <waiting ...>
+step s1_c1: COMMIT;
+step s2_a1: <... completed>
+step s2_c1: COMMIT;
+step s1_q1: SELECT conname, conrelid::regclass, contype, convalidated
+              FROM pg_constraint WHERE conname = 't1_nn';
+
+conname|conrelid|contype|convalidated
+-------+--------+-------+------------
+t1_nn  |t       |n      |t           
+(1 row)
+
+
+starting permutation: s1_b1 s2_b1 s2_a1 s1_r1 s2_r1
+step s1_b1: BEGIN ISOLATION LEVEL REPEATABLE READ;
+step s2_b1: BEGIN ISOLATION LEVEL REPEATABLE READ;
+step s2_a1: ALTER TABLE t ADD CONSTRAINT t1_nn NOT NULL a;
+ERROR:  column "a" of relation "t" contains null values
+step s1_r1: ROLLBACK;
+step s2_r1: ROLLBACK;
+
+starting permutation: s1_b1 s2_b2 s2_d1 s1_d1 s2_r1 s1_a1 s1_q1 s1_r1
+step s1_b1: BEGIN ISOLATION LEVEL REPEATABLE READ;
+step s2_b2: BEGIN;
+step s2_d1: DROP INDEX t_ab_idx;
+step s1_d1: DELETE FROM t; <waiting ...>
+step s2_r1: ROLLBACK;
+step s1_d1: <... completed>
+step s1_a1: ALTER TABLE t ADD CONSTRAINT t1_nn NOT NULL a;
+step s1_q1: SELECT conname, conrelid::regclass, contype, convalidated
+              FROM pg_constraint WHERE conname = 't1_nn';
+
+conname|conrelid|contype|convalidated
+-------+--------+-------+------------
+t1_nn  |t       |n      |t           
+(1 row)
+
+step s1_r1: ROLLBACK;
+
+starting permutation: s1_b2 s2_b1 s1_d1 s2_d1 s1_s0 s1_a1 s1_c1 s2_c1 s1_q1
+step s1_b2: BEGIN;
+step s2_b1: BEGIN ISOLATION LEVEL REPEATABLE READ;
+step s1_d1: DELETE FROM t;
+step s2_d1: DROP INDEX t_ab_idx; <waiting ...>
+step s1_s0: SAVEPOINT s0;
+step s1_a1: ALTER TABLE t ADD CONSTRAINT t1_nn NOT NULL a;
+step s1_c1: COMMIT;
+step s2_d1: <... completed>
+step s2_c1: COMMIT;
+step s1_q1: SELECT conname, conrelid::regclass, contype, convalidated
+              FROM pg_constraint WHERE conname = 't1_nn';
+
+conname|conrelid|contype|convalidated
+-------+--------+-------+------------
+t1_nn  |t       |n      |t           
+(1 row)
+
diff --git a/src/test/isolation/isolation_schedule b/src/test/isolation/isolation_schedule
index 01ff1c6586f..7ce6bbcaf89 100644
--- a/src/test/isolation/isolation_schedule
+++ b/src/test/isolation/isolation_schedule
@@ -58,6 +58,7 @@ test: merge-delete
 test: merge-update
 test: merge-match-recheck
 test: merge-join
+test: indexscan-check-notnull
 test: delete-abort-savept
 test: delete-abort-savept-2
 test: aborted-keyrevoke
diff --git a/src/test/isolation/specs/indexscan-check-notnull.spec b/src/test/isolation/specs/indexscan-check-notnull.spec
new file mode 100644
index 00000000000..05b4488550c
--- /dev/null
+++ b/src/test/isolation/specs/indexscan-check-notnull.spec
@@ -0,0 +1,45 @@
+
+#
+# using indexscan to check a column not-null constraint
+# is satisfied or not.
+#
+
+setup
+{
+  CREATE TABLE t (a int, b int);
+  CREATE INDEX t_ab_idx on t(a,b);
+  INSERT INTO t values (null, 1);
+  INSERT INTO t SELECT x, x*10 FROM generate_series(1,3) g(x);
+}
+
+teardown
+{
+  DROP TABLE t;
+}
+
+session s1
+step s1_b1  { BEGIN ISOLATION LEVEL REPEATABLE READ; }
+step s1_b2  { BEGIN; }
+step s1_d1  { DELETE FROM t;}
+step s1_s0  { SAVEPOINT s0;}
+step s1_a1  { ALTER TABLE t ADD CONSTRAINT t1_nn NOT NULL a;}
+step s1_q1  { SELECT conname, conrelid::regclass, contype, convalidated
+              FROM pg_constraint WHERE conname = 't1_nn';
+            }
+step s1_r1  { ROLLBACK; }
+step s1_c1  { COMMIT; }
+
+session s2
+step s2_b1  { BEGIN ISOLATION LEVEL REPEATABLE READ; }
+step s2_b2  { BEGIN; }
+step s2_a1  { ALTER TABLE t ADD CONSTRAINT t1_nn NOT NULL a;}
+step s2_d1  { DROP INDEX t_ab_idx;}
+step s2_r1  { ROLLBACK; }
+step s2_c1  { COMMIT; }
+
+permutation s1_b1 s2_b1 s1_d1 s2_a1 s1_c1 s2_c1 s1_q1
+permutation s1_b2 s2_b1 s1_d1 s2_a1 s1_c1 s2_c1 s1_q1
+permutation s1_b1 s2_b2 s1_d1 s2_a1 s1_c1 s2_c1 s1_q1
+permutation s1_b1 s2_b1 s2_a1 s1_r1 s2_r1
+permutation s1_b1 s2_b2 s2_d1 s1_d1 s2_r1 s1_a1 s1_q1 s1_r1
+permutation s1_b2 s2_b1 s1_d1 s2_d1 s1_s0 s1_a1 s1_c1 s2_c1 s1_q1
diff --git a/src/test/modules/test_misc/meson.build b/src/test/modules/test_misc/meson.build
index 6e8db1621a7..56faf359b29 100644
--- a/src/test/modules/test_misc/meson.build
+++ b/src/test/modules/test_misc/meson.build
@@ -19,6 +19,7 @@ tests += {
       't/008_replslot_single_user.pl',
       't/009_log_temp_files.pl',
       't/010_index_concurrently_upsert.pl',
+      't/011_indexscan_validate_notnull.pl',
     ],
     # The injection points are cluster-wide, so disable installcheck
     'runningcheck': false,
diff --git a/src/test/modules/test_misc/t/011_indexscan_validate_notnull.pl b/src/test/modules/test_misc/t/011_indexscan_validate_notnull.pl
new file mode 100644
index 00000000000..a3f3cb409b6
--- /dev/null
+++ b/src/test/modules/test_misc/t/011_indexscan_validate_notnull.pl
@@ -0,0 +1,163 @@
+# Copyright (c) 2025, PostgreSQL Global Development Group
+
+# Verify that indexscan mechanism can speedup ALTER TABLE ADD NOT NULL
+
+
+use strict;
+use warnings FATAL => 'all';
+use PostgreSQL::Test::Cluster;
+use PostgreSQL::Test::Utils;
+use Test::More;
+
+# Initialize a test cluster
+my $node = PostgreSQL::Test::Cluster->new('primary');
+$node->init();
+# Turn message level up to DEBUG1 so that we get the messages we want to see
+$node->append_conf('postgresql.conf', 'client_min_messages = DEBUG1');
+$node->start;
+
+# Run a SQL command and return psql's stderr (including debug messages)
+sub run_sql_command
+{
+	my $sql = shift;
+	my $stderr;
+
+	$node->psql(
+		'postgres',
+		$sql,
+		stderr => \$stderr,
+		on_error_die => 1,
+		on_error_stop => 1);
+	return $stderr;
+}
+
+# Check whether result of run_sql_command shows that we did a verify pass
+sub is_table_verified
+{
+	my $output = shift;
+	return index($output, 'DEBUG:  verifying table') != -1;
+}
+
+# Check whether result of run_sql_command shows that we did a verify pass
+sub is_indexscan_veritify_notnull
+{
+	my $output = shift;
+	return index($output, 'DEBUG:  all new not-null constraints on relation') != -1;
+}
+
+my $output;
+
+note "test alter table SET NOT NULL using indexscan with partitioned table";
+
+run_sql_command(
+    'CREATE TABLE tp (a int, b int, c int, d int ) PARTITION BY range(a);
+     CREATE TABLE tpp1 partition of tp for values from ( 1 ) to (10);
+     CREATE TABLE tpp2 partition of tp for values from ( 10 ) to (21);
+     INSERT INTO tp select g, g + 10, g + 15, g + random(min=>1::int, max=>10::int) from generate_series(1,19) g;
+     CREATE INDEX ON tp(b); ');
+
+$output = run_sql_command('ALTER TABLE tp ALTER COLUMN b SET NOT NULL;');
+ok(is_indexscan_veritify_notnull($output),
+	'column b will use indexscan to verify not-null status, no need scan table');
+ok( $output =~
+	  m/all new not-null constraints on relation "tpp1" have been validated by using index scan/,
+	'all newly added constraints proved by indexscan');
+
+run_sql_command(
+	'ALTER TABLE tp ALTER COLUMN b DROP NOT NULL;');
+
+# use indexes on partitions to fast vertifing not-null should be ok
+$output = run_sql_command('ALTER TABLE tpp1 ALTER COLUMN b SET NOT NULL;');
+ok(is_indexscan_veritify_notnull($output), 'use indexscan to validate column b not-null will not scan table');
+ok(!is_table_verified($output), 'no table scan for pp1');
+ok( $output =~
+	  m/all new not-null constraints on relation "tpp1" have been validated by using index scan/,
+	'all newly added constraints proved by indexscan');
+
+$output = run_sql_command('ALTER TABLE tpp2 ALTER COLUMN b SET NOT NULL;');
+ok(is_indexscan_veritify_notnull($output), 'use indexscan to validate column b not-null, will not scan table');
+ok(!is_table_verified($output), 'no table scan for tpp2');
+ok( $output =~
+	  m/all new not-null constraints on relation "tpp2" have been validated by using index scan/,
+	'all newly added constraints proved by indexscan');
+
+run_sql_command(
+	'ALTER TABLE tp ALTER COLUMN b DROP NOT NULL;');
+
+# table rewrite then can not use indexscan to verify not-null constraint
+$output = run_sql_command(
+	'ALTER TABLE tp ALTER COLUMN b SET NOT NULL, ALTER COLUMN b SET DATA TYPE bigint;'
+);
+ok(!is_table_verified($output), 'no table scan for tp');
+ok(!is_indexscan_veritify_notnull($output), 'table tp will rewrite, can not use indexscan to verify not-null constraints on it');
+
+# test using indexscan with multiple not-null constraints
+run_sql_command(
+    'ALTER TABLE tp ALTER COLUMN b DROP NOT NULL;
+	 CREATE INDEX ON tp(c);
+	 CREATE INDEX ON tp(d); ');
+
+# one column can use indexscan, another can not, so can not use indexscan to verify not-null
+$output = run_sql_command(
+	'ALTER TABLE tp ALTER COLUMN a SET NOT NULL, ADD CONSTRAINT c_nn NOT NULL c');
+ok(is_table_verified($output), 'table scan for tp');
+ok(!is_indexscan_veritify_notnull($output), 'can not use indexscan to verify not-null constraints on table tp');
+
+# all columns have index on it
+# use indexscan to verify multiple not-null constraints should just fine
+$output = run_sql_command(
+	'ALTER TABLE tp ALTER COLUMN d SET NOT NULL, ADD CONSTRAINT c_nn NOT NULL c, ALTER COLUMN b SET NOT NULL;');
+ok(!is_table_verified($output), 'no table scan for tp');
+ok(is_indexscan_veritify_notnull($output),
+	'using indexscan to verify not-null constraints on column b, c, d, no need table scan');
+
+# test with non-partitioned table and other non-Btree index.
+run_sql_command(
+    'CREATE TABLE t1(f1 INT, f2 int, f3 int,f4 int, f5 int);
+     INSERT INTO t1 select g, g+1, g+2, g+3, g+4 from generate_series(1, 100) g;
+     CREATE INDEX t1_f1_f2_idx ON t1(f1,f2);
+     CREATE UNIQUE INDEX t1_f3idx ON t1(f3);
+     CREATE INDEX t1_f3f4idx ON t1(f3) include(f4);
+     CREATE INDEX hash_f5_idx ON t1 USING hash (f5 int4_ops); ');
+
+# ALTER TABLE VALIDATE CONSTRAINT can not use indexscan,
+# because it only hold ShareUpdateExclusiveLock lock.
+run_sql_command('ALTER TABLE t1 ADD CONSTRAINT nn_t1_f2 NOT NULL f2 NOT VALID;');
+
+$output = run_sql_command(
+	'ALTER TABLE t1 VALIDATE CONSTRAINT nn_t1_f2;'
+);
+ok(!is_indexscan_veritify_notnull($output), 'can not use indexscan for ALTER TABLE VALIDATE CONSTRAINT command');
+run_sql_command('ALTER TABLE t1 DROP CONSTRAINT nn_t1_f2;');
+
+$output = run_sql_command(
+	'ALTER TABLE t1 ALTER COLUMN f1 SET NOT NULL, ALTER f1 type bigint;'
+);
+ok(!is_indexscan_veritify_notnull($output), 'table t1 will rewrite, can not use indexscan to validate not-null constraints on t1');
+
+run_sql_command('ALTER TABLE t1 ALTER COLUMN f1 DROP NOT NULL;');
+run_sql_command('ALTER TABLE t1 ADD CONSTRAINT nn NOT NULL f1, ALTER f1 type bigint;');
+
+# can use indexscan mechanism to fast add multiple not-null constraints
+$output = run_sql_command(
+	'ALTER TABLE t1 ALTER COLUMN f2 SET NOT NULL, ALTER COLUMN f1 SET NOT NULL;'
+);
+ok( $output =~
+	  m/all new not-null constraints on relation "t1" have been validated by using index scan/,
+	'all not-null constraints are validated by indexscan');
+
+# using indexscan mechanism to fast add a not-null can only apply to key columns, not include column
+$output = run_sql_command(
+	'ALTER TABLE t1 ADD CONSTRAINT nnf4 NOT NULL f4;'
+);
+ok(!is_indexscan_veritify_notnull($output), 'can not use indexscan to validate not-null constraint on t1');
+
+# if index is not btree index then cannot use indexscan mechanism to fast add not-null constraint
+$output = run_sql_command(
+	'ALTER TABLE t1 ADD CONSTRAINT nn_f5 NOT NULL f5;'
+);
+ok(!is_indexscan_veritify_notnull($output), 'can not use indexscan to validate not-null constraints on t1');
+
+$node->stop('fast');
+
+done_testing();
-- 
2.47.3


--xpkr6zhfzd3fjt76--





^ permalink  raw  reply  [nested|flat] 150+ messages in thread

* [PATCH v8] using indexscan to speedup add not null constraints
@ 2025-10-20 05:29  jian he <[email protected]>
  0 siblings, 0 replies; 150+ messages in thread

From: jian he @ 2025-10-20 05:29 UTC (permalink / raw)

This patch tries to use index_beginscan() / index_getnext() / index_endscan()
mentioned in [1] to speedup adding not-null constraints to the existing table.

The main logic happens in phase3 ATRewriteTable
1. collect all not-null constraints.
2. For each not-null constraint, check whether there is a corresponding index
available for validation. If not, then can not use indexscan to verify not-null
constraints.
3. If any of the following conditions are true
  * table scan or rewrite is required,
  * table wasn't locked with `AccessExclusiveLock`
  * the NOT NULL constraint applies to a virtual generated column
 then index scan cannot be used for fast validation.
4. If all conditions are satisfied, attempt to use indexscan to verify
whether the column contains any NULL values.

concurrency concern:
ALTER TABLE SET NOT NULL will take an ACCESS EXCLUSIVE lock, so there is less
variant of racing issue can occur?  to prove accurate, I wrote some isolation
tests. see[2]

performance:
demo:
case when: %20 percent values are NULL and have been deleted from heap but they
still on the index.

drop table if exists t;
create unlogged table t(a int, b int) with (autovacuum_enabled = off, vacuum_index_cleanup=off);
insert into t select case when g % 5 = 0 then null else g end, g+1
from generate_series(1,1_000_000) g;
create index t_idx_a on t(a);
delete from t where a is null;

alter table t alter column a drop not null;
alter table t add constraint t1 not null a;

the above two statement running several times:
patch Time:: 1.084  ms
master Time: 12.045 ms

references:
[1] https://postgr.es/m/CA%2BTgmoa5NKz8iGW_9v7wz%3D-%2BzQFu%3DE4SZoaTaU1znLaEXRYp-Q%40mail.gmail.com
[2] https://postgr.es/m/900056D1-32DF-4927-8251-3E0C0DC407FD%40anarazel.de
discussion: https://postgr.es/m/CACJufxFiW=4k1is=F1J=r-Cx1RuByXQPUrWB331U47rSnGz+hw@mail.gmail.com
commitfest entry: https://commitfest.postgresql.org/patch/5444
---
 src/backend/commands/tablecmds.c              | 116 +++++++++-
 src/backend/executor/execIndexing.c           | 213 ++++++++++++++++++
 src/include/executor/executor.h               |   2 +
 .../expected/indexscan-check-notnull.out      |  97 ++++++++
 src/test/isolation/isolation_schedule         |   1 +
 .../specs/indexscan-check-notnull.spec        |  45 ++++
 src/test/modules/test_misc/meson.build        |   1 +
 .../t/011_indexscan_validate_notnull.pl       | 163 ++++++++++++++
 8 files changed, 632 insertions(+), 6 deletions(-)
 create mode 100644 src/test/isolation/expected/indexscan-check-notnull.out
 create mode 100644 src/test/isolation/specs/indexscan-check-notnull.spec
 create mode 100644 src/test/modules/test_misc/t/011_indexscan_validate_notnull.pl

diff --git a/src/backend/commands/tablecmds.c b/src/backend/commands/tablecmds.c
index f976c0e5c7e..2af06630b35 100644
--- a/src/backend/commands/tablecmds.c
+++ b/src/backend/commands/tablecmds.c
@@ -210,16 +210,19 @@ typedef struct AlteredTableInfo
 	List	   *changedStatisticsDefs;	/* string definitions of same */
 } AlteredTableInfo;
 
-/* Struct describing one new constraint to check in Phase 3 scan */
-/* Note: new not-null constraints are handled elsewhere */
+/*
+ * Struct describing one new constraint to check in Phase 3 scan. Note: new
+ * not-null constraints are handled here too.
+*/
 typedef struct NewConstraint
 {
 	char	   *name;			/* Constraint name, or NULL if none */
-	ConstrType	contype;		/* CHECK or FOREIGN */
+	ConstrType	contype;		/* CHECK or FOREIGN or NOT NULL */
 	Oid			refrelid;		/* PK rel, if FOREIGN */
 	Oid			refindid;		/* OID of PK's index, if FOREIGN */
 	bool		conwithperiod;	/* Whether the new FOREIGN KEY uses PERIOD */
 	Oid			conid;			/* OID of pg_constraint entry, if FOREIGN */
+	int			attnum;			/* NOT NULL constraint attribute number */
 	Node	   *qual;			/* Check expr or CONSTR_FOREIGN Constraint */
 	ExprState  *qualstate;		/* Execution state for CHECK expr */
 } NewConstraint;
@@ -6217,6 +6220,9 @@ ATRewriteTable(AlteredTableInfo *tab, Oid OIDNewHeap)
 				needscan = true;
 				con->qualstate = ExecPrepareExpr((Expr *) expand_generated_columns_in_expr(con->qual, oldrel, 1), estate);
 				break;
+			case CONSTR_NOTNULL:
+				/* Nothing to do here */
+				break;
 			case CONSTR_FOREIGN:
 				/* Nothing to do here */
 				break;
@@ -6270,10 +6276,69 @@ ATRewriteTable(AlteredTableInfo *tab, Oid OIDNewHeap)
 														wholeatt->attnum);
 			}
 		}
-		if (notnull_attrs || notnull_virtual_attrs)
-			needscan = true;
 	}
 
+	/*-
+	 * If we have to verify new not-null constraints and don't have any other
+	 * reason to fully scan the table, then we can use indexes to test for
+	 * absence of NULL values instead of scanning.  The following conditions
+	 * must be met:
+	 * - we're operating on a regular table
+	 * - we hold AccessExclusiveLock on the table
+	 * - no not-null constraint covers a virtual generated column,
+	 *   because no indexes can be created on them
+	 */
+	if (!needscan &&
+		newrel == NULL &&
+		tab->verify_new_notnull &&
+		notnull_virtual_attrs == NIL &&
+		oldrel->rd_rel->relkind == RELKIND_RELATION &&
+		CheckRelationLockedByMe(oldrel, AccessExclusiveLock, false))
+	{
+		List	   *notnull_attnums = NIL;
+
+		Assert(!tab->rewrite);
+
+		foreach(l, tab->constraints)
+		{
+			Form_pg_attribute attr;
+			NewConstraint *con = lfirst(l);
+
+			if (con->contype != CONSTR_NOTNULL)
+				continue;
+
+			attr = TupleDescAttr(newTupDesc, con->attnum - 1);
+
+			Assert(attr->attnotnull);
+			Assert(attr->attnum == con->attnum);
+
+			if (attr->attgenerated == ATTRIBUTE_GENERATED_VIRTUAL)
+			{
+				needscan = true;
+				break;
+			}
+
+			notnull_attnums = lappend_int(notnull_attnums, attr->attnum);
+		}
+
+		/*
+		 * Validate new NOT NULL constraints, unless we need a scan for other
+		 * reasons, because we can validate them cheaply there, and doing it
+		 * also here would be a waste of cycles.
+		 */
+		if (notnull_attnums != NIL && !needscan)
+		{
+			if (!index_check_notnull(oldrel, notnull_attnums))
+				needscan = true;
+			else
+				ereport(DEBUG1,
+						errmsg_internal("all new not-null constraints on relation \"%s\" have been validated by using index scan",
+										RelationGetRelationName(oldrel)));
+		}
+	}
+	else if (notnull_attrs || notnull_virtual_attrs)
+		needscan = true;
+
 	if (newrel || needscan)
 	{
 		ExprContext *econtext;
@@ -7949,6 +8014,7 @@ ATExecSetNotNull(List **wqueue, Relation rel, char *conName, char *colName,
 	CookedConstraint *ccon;
 	List	   *cooked;
 	bool		is_no_inherit = false;
+	AlteredTableInfo *tab = NULL;
 
 	/* Guard against stack overflow due to overly deep inheritance tree. */
 	check_stack_depth();
@@ -8073,10 +8139,32 @@ ATExecSetNotNull(List **wqueue, Relation rel, char *conName, char *colName,
 	constraint->is_no_inherit = is_no_inherit;
 	constraint->conname = conName;
 
+	tab = ATGetQueueEntry(wqueue, rel);
+
 	/* and do it */
 	cooked = AddRelationNewConstraints(rel, NIL, list_make1(constraint),
 									   false, !recursing, false, NULL);
 	ccon = linitial(cooked);
+
+	Assert(ccon->contype == CONSTR_NOTNULL);
+
+	/*
+	 * We may use indexscan to vertify not-null constraint in Phase3.  Add the
+	 * to-be-validated not-null constraint to Phase 3's queue.
+	 */
+	if (!ccon->skip_validation)
+	{
+		NewConstraint *newcon;
+
+		newcon = (NewConstraint *) palloc0(sizeof(NewConstraint));
+
+		newcon->name = ccon->name;
+		newcon->contype = ccon->contype;
+		newcon->attnum = ccon->attnum;
+
+		tab->constraints = lappend(tab->constraints, newcon);
+	}
+
 	ObjectAddressSet(address, ConstraintRelationId, ccon->conoid);
 
 	InvokeObjectPostAlterHook(RelationRelationId,
@@ -9983,13 +10071,15 @@ ATAddCheckNNConstraint(List **wqueue, AlteredTableInfo *tab, Relation rel,
 	{
 		CookedConstraint *ccon = (CookedConstraint *) lfirst(lcon);
 
-		if (!ccon->skip_validation && ccon->contype != CONSTR_NOTNULL)
+		if (!ccon->skip_validation)
 		{
 			NewConstraint *newcon;
 
 			newcon = palloc0_object(NewConstraint);
 			newcon->name = ccon->name;
 			newcon->contype = ccon->contype;
+			if (ccon->contype == CONSTR_NOTNULL)
+				newcon->attnum = ccon->attnum;
 			newcon->qual = ccon->expr;
 
 			tab->constraints = lappend(tab->constraints, newcon);
@@ -13258,6 +13348,7 @@ QueueNNConstraintValidation(List **wqueue, Relation conrel, Relation rel,
 	List	   *children = NIL;
 	AttrNumber	attnum;
 	char	   *colname;
+	NewConstraint *newcon;
 
 	con = (Form_pg_constraint) GETSTRUCT(contuple);
 	Assert(con->contype == CONSTRAINT_NOTNULL);
@@ -13321,7 +13412,20 @@ QueueNNConstraintValidation(List **wqueue, Relation conrel, Relation rel,
 	/* Set attnotnull appropriately without queueing another validation */
 	set_attnotnull(NULL, rel, attnum, true, false);
 
+	/*
+	 * Queue validation for phase 3.
+	 *
+	 * ALTER TABLE SET NOT NULL will add NOT NULL constraint to
+	 * AlteredTableInfo->constraints, for consistency, do the same here.
+	 */
+	newcon = (NewConstraint *) palloc0(sizeof(NewConstraint));
+	newcon->name = colname;
+	newcon->contype = CONSTR_NOTNULL;
+	newcon->attnum = attnum;
+
+	/* Find or create work queue entry for this table */
 	tab = ATGetQueueEntry(wqueue, rel);
+	tab->constraints = lappend(tab->constraints, newcon);
 	tab->verify_new_notnull = true;
 
 	/*
diff --git a/src/backend/executor/execIndexing.c b/src/backend/executor/execIndexing.c
index 6ae0f959592..88694ce0335 100644
--- a/src/backend/executor/execIndexing.c
+++ b/src/backend/executor/execIndexing.c
@@ -108,12 +108,15 @@
 
 #include "access/genam.h"
 #include "access/relscan.h"
+#include "access/table.h"
 #include "access/tableam.h"
 #include "access/xact.h"
 #include "catalog/index.h"
+#include "catalog/pg_am_d.h"
 #include "executor/executor.h"
 #include "nodes/nodeFuncs.h"
 #include "storage/lmgr.h"
+#include "utils/fmgroids.h"
 #include "utils/injection_point.h"
 #include "utils/multirangetypes.h"
 #include "utils/rangetypes.h"
@@ -146,6 +149,7 @@ static bool index_expression_changed_walker(Node *node,
 											Bitmapset *allUpdatedCols);
 static void ExecWithoutOverlapsNotEmpty(Relation rel, NameData attname, Datum attval,
 										char typtype, Oid atttypid);
+static bool index_check_notnull_internal(Relation relation, List *attnums, List *idxs);
 
 /* ----------------------------------------------------------------
  *		ExecOpenIndices
@@ -1178,3 +1182,212 @@ ExecWithoutOverlapsNotEmpty(Relation rel, NameData attname, Datum attval, char t
 				 errmsg("empty WITHOUT OVERLAPS value found in column \"%s\" in relation \"%s\"",
 						NameStr(attname), RelationGetRelationName(rel))));
 }
+
+/*
+ * notnull_attnums: list of attribute numbers of all new not-null constraints.
+ *
+ * First check whether the relation has a suitable index for each not-null
+ * attribute, then using indexscan mechanism to verify that *all* attributes on
+ * notnull_attnums are indeed not null.
+ *
+ * Returning true means all new not-null constraints have been verified, no
+ * need an extra scan to verify newly added not-null constraints.
+ */
+bool
+index_check_notnull(Relation relation, List *notnull_attnums)
+{
+	Relation	pg_index;
+	Relation	index_rel;
+	SysScanDesc indscan;
+	ScanKeyData skey;
+	HeapTuple	htup;
+	TupleDesc	tupdesc;
+	Form_pg_attribute attr;
+	List	   *idxs = NIL;
+	List	   *attnums = NIL;
+
+	tupdesc = RelationGetDescr(relation);
+
+	/* Prepare to scan pg_index for entries having indrelid = this rel */
+	ScanKeyInit(&skey,
+				Anum_pg_index_indrelid,
+				BTEqualStrategyNumber, F_OIDEQ,
+				ObjectIdGetDatum(RelationGetRelid(relation)));
+
+	pg_index = table_open(IndexRelationId, AccessShareLock);
+	indscan = systable_beginscan(pg_index, IndexIndrelidIndexId, true,
+								 NULL, 1, &skey);
+
+	while (HeapTupleIsValid(htup = systable_getnext(indscan)))
+	{
+		Form_pg_index index = (Form_pg_index) GETSTRUCT(htup);
+
+		/*
+		 * we can only use non-deferred, validated, and alive btree index to
+		 * validate not-null constraints
+		 */
+		if (!index->indimmediate || !index->indisvalid || !index->indislive)
+			continue;
+
+		/* can not use expression index or partial index too */
+		if (!heap_attisnull(htup, Anum_pg_index_indexprs, NULL) ||
+			!heap_attisnull(htup, Anum_pg_index_indpred, NULL))
+			continue;
+
+		index_rel = index_open(index->indexrelid, AccessShareLock);
+
+		/* can only apply to btree index */
+		if (index_rel->rd_rel->relam != BTREE_AM_OID)
+		{
+			index_close(index_rel, AccessShareLock);
+			continue;
+		}
+
+		/* collect index attnums while loop */
+		for (int i = 0; i < index->indnkeyatts; i++)
+		{
+			attr = TupleDescAttr(tupdesc, (index->indkey.values[i] - 1));
+
+			if (attr->attisdropped)
+				continue;
+
+			if (list_member_int(notnull_attnums, attr->attnum) &&
+				!list_member_int(attnums, attr->attnum))
+			{
+				attnums = lappend_int(attnums, attr->attnum);
+				idxs = lappend_oid(idxs, index->indexrelid);
+			}
+		}
+		index_close(index_rel, NoLock);
+	}
+	systable_endscan(indscan);
+	table_close(pg_index, AccessShareLock);
+
+	if (attnums == NIL)
+		return false;
+
+	/*
+	 * every not-null constraint requires an index for indexscan.  If no such
+	 * index exists, we need to use regular table scan to validate not-null
+	 * constraints.
+	 */
+	foreach_int(attno, notnull_attnums)
+	{
+		if (!list_member_int(attnums, attno))
+			return false;
+	}
+
+	return index_check_notnull_internal(relation, attnums, idxs);
+}
+
+/*
+ * Use indexscan mechanism to fast verify each attribute in "attnums" are
+ * not-null or not.
+ */
+static bool
+index_check_notnull_internal(Relation relation, List *attnums, List *idxs)
+{
+	EState	   *estate;
+	ExprContext *econtext;
+	TupleTableSlot *existing_slot;
+	bool		all_not_null = true;
+	ListCell   *lc,
+			   *lc2;
+
+	/*
+	 * Need an EState for slot to hold the current tuple.
+	 */
+	estate = CreateExecutorState();
+	econtext = GetPerTupleExprContext(estate);
+
+	forboth(lc, attnums, lc2, idxs)
+	{
+		SnapshotData DirtySnapshot;
+		IndexScanDesc index_scan;
+		ScanKeyData scankeys[INDEX_MAX_KEYS];
+		IndexInfo  *indexInfo;
+		AttrNumber	sk_attno = -1;
+		Relation	index;
+		int			indnkeyatts;
+
+		AttrNumber	attno = lfirst_int(lc);
+		Oid			indexoid = lfirst_oid(lc2);
+
+		existing_slot = table_slot_create(relation, NULL);
+
+		/* Arrange for econtext's scan tuple to be the tuple under test */
+		econtext->ecxt_scantuple = existing_slot;
+
+		index = index_open(indexoid, NoLock);
+
+		indexInfo = BuildIndexInfo(index);
+		indnkeyatts = IndexRelationGetNumberOfKeyAttributes(index);
+
+		/*
+		 * Search the tuples that are in the index for any violations,
+		 * including tuples that aren't visible yet.
+		 */
+		InitDirtySnapshot(DirtySnapshot);
+
+		for (int i = 0; i < indnkeyatts; i++)
+		{
+			if (indexInfo->ii_IndexAttrNumbers[i] == attno)
+			{
+				sk_attno = i + 1;
+				break;
+			}
+		}
+
+		if (sk_attno == -1)
+			elog(ERROR, "cache lookup failed for attribute number %d on index %u", indexoid, attno);
+
+		for (int i = 0; i < indnkeyatts; i++)
+		{
+			/* set up an IS NULL scan key so that we ignore not nulls */
+			ScanKeyEntryInitialize(&scankeys[i],
+								   SK_ISNULL | SK_SEARCHNULL,
+								   sk_attno,	/* index col to scan */
+								   InvalidStrategy, /* no strategy */
+								   InvalidOid,	/* no strategy subtype */
+								   InvalidOid,	/* no collation */
+								   InvalidOid,	/* no reg proc for this */
+								   (Datum) 0);	/* constant */
+		}
+
+		index_scan = index_beginscan(relation, index, &DirtySnapshot, NULL, indnkeyatts, 0);
+		index_rescan(index_scan, scankeys, indnkeyatts, NULL, 0);
+
+		while (index_getnext_slot(index_scan, ForwardScanDirection, existing_slot))
+		{
+			Datum		values[INDEX_MAX_KEYS];
+			bool		nulls[INDEX_MAX_KEYS];
+
+			/*
+			 * Extract the index column values and isnull flags from the
+			 * existing tuple.
+			 */
+			FormIndexDatum(indexInfo, existing_slot, estate, values, nulls);
+
+			if (nulls[sk_attno - 1])
+			{
+				all_not_null = false;
+				break;
+			}
+		}
+
+		index_endscan(index_scan);
+		index_close(index, NoLock);
+		ExecDropSingleTupleTableSlot(existing_slot);
+
+		/* exit earlier */
+		if (!all_not_null)
+		{
+			FreeExecutorState(estate);
+			return false;
+		}
+	}
+
+	FreeExecutorState(estate);
+
+	return true;
+}
diff --git a/src/include/executor/executor.h b/src/include/executor/executor.h
index 5929aabc353..7f24caeeafb 100644
--- a/src/include/executor/executor.h
+++ b/src/include/executor/executor.h
@@ -756,6 +756,8 @@ extern void check_exclusion_constraint(Relation heap, Relation index,
 									   const Datum *values, const bool *isnull,
 									   EState *estate, bool newIndex);
 
+extern bool index_check_notnull(Relation relation, List *notnull_attnums);
+
 /*
  * prototypes from functions in execReplication.c
  */
diff --git a/src/test/isolation/expected/indexscan-check-notnull.out b/src/test/isolation/expected/indexscan-check-notnull.out
new file mode 100644
index 00000000000..c6a652e2518
--- /dev/null
+++ b/src/test/isolation/expected/indexscan-check-notnull.out
@@ -0,0 +1,97 @@
+Parsed test spec with 2 sessions
+
+starting permutation: s1_b1 s2_b1 s1_d1 s2_a1 s1_c1 s2_c1 s1_q1
+step s1_b1: BEGIN ISOLATION LEVEL REPEATABLE READ;
+step s2_b1: BEGIN ISOLATION LEVEL REPEATABLE READ;
+step s1_d1: DELETE FROM t;
+step s2_a1: ALTER TABLE t ADD CONSTRAINT t1_nn NOT NULL a; <waiting ...>
+step s1_c1: COMMIT;
+step s2_a1: <... completed>
+step s2_c1: COMMIT;
+step s1_q1: SELECT conname, conrelid::regclass, contype, convalidated
+              FROM pg_constraint WHERE conname = 't1_nn';
+
+conname|conrelid|contype|convalidated
+-------+--------+-------+------------
+t1_nn  |t       |n      |t           
+(1 row)
+
+
+starting permutation: s1_b2 s2_b1 s1_d1 s2_a1 s1_c1 s2_c1 s1_q1
+step s1_b2: BEGIN;
+step s2_b1: BEGIN ISOLATION LEVEL REPEATABLE READ;
+step s1_d1: DELETE FROM t;
+step s2_a1: ALTER TABLE t ADD CONSTRAINT t1_nn NOT NULL a; <waiting ...>
+step s1_c1: COMMIT;
+step s2_a1: <... completed>
+step s2_c1: COMMIT;
+step s1_q1: SELECT conname, conrelid::regclass, contype, convalidated
+              FROM pg_constraint WHERE conname = 't1_nn';
+
+conname|conrelid|contype|convalidated
+-------+--------+-------+------------
+t1_nn  |t       |n      |t           
+(1 row)
+
+
+starting permutation: s1_b1 s2_b2 s1_d1 s2_a1 s1_c1 s2_c1 s1_q1
+step s1_b1: BEGIN ISOLATION LEVEL REPEATABLE READ;
+step s2_b2: BEGIN;
+step s1_d1: DELETE FROM t;
+step s2_a1: ALTER TABLE t ADD CONSTRAINT t1_nn NOT NULL a; <waiting ...>
+step s1_c1: COMMIT;
+step s2_a1: <... completed>
+step s2_c1: COMMIT;
+step s1_q1: SELECT conname, conrelid::regclass, contype, convalidated
+              FROM pg_constraint WHERE conname = 't1_nn';
+
+conname|conrelid|contype|convalidated
+-------+--------+-------+------------
+t1_nn  |t       |n      |t           
+(1 row)
+
+
+starting permutation: s1_b1 s2_b1 s2_a1 s1_r1 s2_r1
+step s1_b1: BEGIN ISOLATION LEVEL REPEATABLE READ;
+step s2_b1: BEGIN ISOLATION LEVEL REPEATABLE READ;
+step s2_a1: ALTER TABLE t ADD CONSTRAINT t1_nn NOT NULL a;
+ERROR:  column "a" of relation "t" contains null values
+step s1_r1: ROLLBACK;
+step s2_r1: ROLLBACK;
+
+starting permutation: s1_b1 s2_b2 s2_d1 s1_d1 s2_r1 s1_a1 s1_q1 s1_r1
+step s1_b1: BEGIN ISOLATION LEVEL REPEATABLE READ;
+step s2_b2: BEGIN;
+step s2_d1: DROP INDEX t_ab_idx;
+step s1_d1: DELETE FROM t; <waiting ...>
+step s2_r1: ROLLBACK;
+step s1_d1: <... completed>
+step s1_a1: ALTER TABLE t ADD CONSTRAINT t1_nn NOT NULL a;
+step s1_q1: SELECT conname, conrelid::regclass, contype, convalidated
+              FROM pg_constraint WHERE conname = 't1_nn';
+
+conname|conrelid|contype|convalidated
+-------+--------+-------+------------
+t1_nn  |t       |n      |t           
+(1 row)
+
+step s1_r1: ROLLBACK;
+
+starting permutation: s1_b2 s2_b1 s1_d1 s2_d1 s1_s0 s1_a1 s1_c1 s2_c1 s1_q1
+step s1_b2: BEGIN;
+step s2_b1: BEGIN ISOLATION LEVEL REPEATABLE READ;
+step s1_d1: DELETE FROM t;
+step s2_d1: DROP INDEX t_ab_idx; <waiting ...>
+step s1_s0: SAVEPOINT s0;
+step s1_a1: ALTER TABLE t ADD CONSTRAINT t1_nn NOT NULL a;
+step s1_c1: COMMIT;
+step s2_d1: <... completed>
+step s2_c1: COMMIT;
+step s1_q1: SELECT conname, conrelid::regclass, contype, convalidated
+              FROM pg_constraint WHERE conname = 't1_nn';
+
+conname|conrelid|contype|convalidated
+-------+--------+-------+------------
+t1_nn  |t       |n      |t           
+(1 row)
+
diff --git a/src/test/isolation/isolation_schedule b/src/test/isolation/isolation_schedule
index 01ff1c6586f..7ce6bbcaf89 100644
--- a/src/test/isolation/isolation_schedule
+++ b/src/test/isolation/isolation_schedule
@@ -58,6 +58,7 @@ test: merge-delete
 test: merge-update
 test: merge-match-recheck
 test: merge-join
+test: indexscan-check-notnull
 test: delete-abort-savept
 test: delete-abort-savept-2
 test: aborted-keyrevoke
diff --git a/src/test/isolation/specs/indexscan-check-notnull.spec b/src/test/isolation/specs/indexscan-check-notnull.spec
new file mode 100644
index 00000000000..05b4488550c
--- /dev/null
+++ b/src/test/isolation/specs/indexscan-check-notnull.spec
@@ -0,0 +1,45 @@
+
+#
+# using indexscan to check a column not-null constraint
+# is satisfied or not.
+#
+
+setup
+{
+  CREATE TABLE t (a int, b int);
+  CREATE INDEX t_ab_idx on t(a,b);
+  INSERT INTO t values (null, 1);
+  INSERT INTO t SELECT x, x*10 FROM generate_series(1,3) g(x);
+}
+
+teardown
+{
+  DROP TABLE t;
+}
+
+session s1
+step s1_b1  { BEGIN ISOLATION LEVEL REPEATABLE READ; }
+step s1_b2  { BEGIN; }
+step s1_d1  { DELETE FROM t;}
+step s1_s0  { SAVEPOINT s0;}
+step s1_a1  { ALTER TABLE t ADD CONSTRAINT t1_nn NOT NULL a;}
+step s1_q1  { SELECT conname, conrelid::regclass, contype, convalidated
+              FROM pg_constraint WHERE conname = 't1_nn';
+            }
+step s1_r1  { ROLLBACK; }
+step s1_c1  { COMMIT; }
+
+session s2
+step s2_b1  { BEGIN ISOLATION LEVEL REPEATABLE READ; }
+step s2_b2  { BEGIN; }
+step s2_a1  { ALTER TABLE t ADD CONSTRAINT t1_nn NOT NULL a;}
+step s2_d1  { DROP INDEX t_ab_idx;}
+step s2_r1  { ROLLBACK; }
+step s2_c1  { COMMIT; }
+
+permutation s1_b1 s2_b1 s1_d1 s2_a1 s1_c1 s2_c1 s1_q1
+permutation s1_b2 s2_b1 s1_d1 s2_a1 s1_c1 s2_c1 s1_q1
+permutation s1_b1 s2_b2 s1_d1 s2_a1 s1_c1 s2_c1 s1_q1
+permutation s1_b1 s2_b1 s2_a1 s1_r1 s2_r1
+permutation s1_b1 s2_b2 s2_d1 s1_d1 s2_r1 s1_a1 s1_q1 s1_r1
+permutation s1_b2 s2_b1 s1_d1 s2_d1 s1_s0 s1_a1 s1_c1 s2_c1 s1_q1
diff --git a/src/test/modules/test_misc/meson.build b/src/test/modules/test_misc/meson.build
index 6e8db1621a7..56faf359b29 100644
--- a/src/test/modules/test_misc/meson.build
+++ b/src/test/modules/test_misc/meson.build
@@ -19,6 +19,7 @@ tests += {
       't/008_replslot_single_user.pl',
       't/009_log_temp_files.pl',
       't/010_index_concurrently_upsert.pl',
+      't/011_indexscan_validate_notnull.pl',
     ],
     # The injection points are cluster-wide, so disable installcheck
     'runningcheck': false,
diff --git a/src/test/modules/test_misc/t/011_indexscan_validate_notnull.pl b/src/test/modules/test_misc/t/011_indexscan_validate_notnull.pl
new file mode 100644
index 00000000000..a3f3cb409b6
--- /dev/null
+++ b/src/test/modules/test_misc/t/011_indexscan_validate_notnull.pl
@@ -0,0 +1,163 @@
+# Copyright (c) 2025, PostgreSQL Global Development Group
+
+# Verify that indexscan mechanism can speedup ALTER TABLE ADD NOT NULL
+
+
+use strict;
+use warnings FATAL => 'all';
+use PostgreSQL::Test::Cluster;
+use PostgreSQL::Test::Utils;
+use Test::More;
+
+# Initialize a test cluster
+my $node = PostgreSQL::Test::Cluster->new('primary');
+$node->init();
+# Turn message level up to DEBUG1 so that we get the messages we want to see
+$node->append_conf('postgresql.conf', 'client_min_messages = DEBUG1');
+$node->start;
+
+# Run a SQL command and return psql's stderr (including debug messages)
+sub run_sql_command
+{
+	my $sql = shift;
+	my $stderr;
+
+	$node->psql(
+		'postgres',
+		$sql,
+		stderr => \$stderr,
+		on_error_die => 1,
+		on_error_stop => 1);
+	return $stderr;
+}
+
+# Check whether result of run_sql_command shows that we did a verify pass
+sub is_table_verified
+{
+	my $output = shift;
+	return index($output, 'DEBUG:  verifying table') != -1;
+}
+
+# Check whether result of run_sql_command shows that we did a verify pass
+sub is_indexscan_veritify_notnull
+{
+	my $output = shift;
+	return index($output, 'DEBUG:  all new not-null constraints on relation') != -1;
+}
+
+my $output;
+
+note "test alter table SET NOT NULL using indexscan with partitioned table";
+
+run_sql_command(
+    'CREATE TABLE tp (a int, b int, c int, d int ) PARTITION BY range(a);
+     CREATE TABLE tpp1 partition of tp for values from ( 1 ) to (10);
+     CREATE TABLE tpp2 partition of tp for values from ( 10 ) to (21);
+     INSERT INTO tp select g, g + 10, g + 15, g + random(min=>1::int, max=>10::int) from generate_series(1,19) g;
+     CREATE INDEX ON tp(b); ');
+
+$output = run_sql_command('ALTER TABLE tp ALTER COLUMN b SET NOT NULL;');
+ok(is_indexscan_veritify_notnull($output),
+	'column b will use indexscan to verify not-null status, no need scan table');
+ok( $output =~
+	  m/all new not-null constraints on relation "tpp1" have been validated by using index scan/,
+	'all newly added constraints proved by indexscan');
+
+run_sql_command(
+	'ALTER TABLE tp ALTER COLUMN b DROP NOT NULL;');
+
+# use indexes on partitions to fast vertifing not-null should be ok
+$output = run_sql_command('ALTER TABLE tpp1 ALTER COLUMN b SET NOT NULL;');
+ok(is_indexscan_veritify_notnull($output), 'use indexscan to validate column b not-null will not scan table');
+ok(!is_table_verified($output), 'no table scan for pp1');
+ok( $output =~
+	  m/all new not-null constraints on relation "tpp1" have been validated by using index scan/,
+	'all newly added constraints proved by indexscan');
+
+$output = run_sql_command('ALTER TABLE tpp2 ALTER COLUMN b SET NOT NULL;');
+ok(is_indexscan_veritify_notnull($output), 'use indexscan to validate column b not-null, will not scan table');
+ok(!is_table_verified($output), 'no table scan for tpp2');
+ok( $output =~
+	  m/all new not-null constraints on relation "tpp2" have been validated by using index scan/,
+	'all newly added constraints proved by indexscan');
+
+run_sql_command(
+	'ALTER TABLE tp ALTER COLUMN b DROP NOT NULL;');
+
+# table rewrite then can not use indexscan to verify not-null constraint
+$output = run_sql_command(
+	'ALTER TABLE tp ALTER COLUMN b SET NOT NULL, ALTER COLUMN b SET DATA TYPE bigint;'
+);
+ok(!is_table_verified($output), 'no table scan for tp');
+ok(!is_indexscan_veritify_notnull($output), 'table tp will rewrite, can not use indexscan to verify not-null constraints on it');
+
+# test using indexscan with multiple not-null constraints
+run_sql_command(
+    'ALTER TABLE tp ALTER COLUMN b DROP NOT NULL;
+	 CREATE INDEX ON tp(c);
+	 CREATE INDEX ON tp(d); ');
+
+# one column can use indexscan, another can not, so can not use indexscan to verify not-null
+$output = run_sql_command(
+	'ALTER TABLE tp ALTER COLUMN a SET NOT NULL, ADD CONSTRAINT c_nn NOT NULL c');
+ok(is_table_verified($output), 'table scan for tp');
+ok(!is_indexscan_veritify_notnull($output), 'can not use indexscan to verify not-null constraints on table tp');
+
+# all columns have index on it
+# use indexscan to verify multiple not-null constraints should just fine
+$output = run_sql_command(
+	'ALTER TABLE tp ALTER COLUMN d SET NOT NULL, ADD CONSTRAINT c_nn NOT NULL c, ALTER COLUMN b SET NOT NULL;');
+ok(!is_table_verified($output), 'no table scan for tp');
+ok(is_indexscan_veritify_notnull($output),
+	'using indexscan to verify not-null constraints on column b, c, d, no need table scan');
+
+# test with non-partitioned table and other non-Btree index.
+run_sql_command(
+    'CREATE TABLE t1(f1 INT, f2 int, f3 int,f4 int, f5 int);
+     INSERT INTO t1 select g, g+1, g+2, g+3, g+4 from generate_series(1, 100) g;
+     CREATE INDEX t1_f1_f2_idx ON t1(f1,f2);
+     CREATE UNIQUE INDEX t1_f3idx ON t1(f3);
+     CREATE INDEX t1_f3f4idx ON t1(f3) include(f4);
+     CREATE INDEX hash_f5_idx ON t1 USING hash (f5 int4_ops); ');
+
+# ALTER TABLE VALIDATE CONSTRAINT can not use indexscan,
+# because it only hold ShareUpdateExclusiveLock lock.
+run_sql_command('ALTER TABLE t1 ADD CONSTRAINT nn_t1_f2 NOT NULL f2 NOT VALID;');
+
+$output = run_sql_command(
+	'ALTER TABLE t1 VALIDATE CONSTRAINT nn_t1_f2;'
+);
+ok(!is_indexscan_veritify_notnull($output), 'can not use indexscan for ALTER TABLE VALIDATE CONSTRAINT command');
+run_sql_command('ALTER TABLE t1 DROP CONSTRAINT nn_t1_f2;');
+
+$output = run_sql_command(
+	'ALTER TABLE t1 ALTER COLUMN f1 SET NOT NULL, ALTER f1 type bigint;'
+);
+ok(!is_indexscan_veritify_notnull($output), 'table t1 will rewrite, can not use indexscan to validate not-null constraints on t1');
+
+run_sql_command('ALTER TABLE t1 ALTER COLUMN f1 DROP NOT NULL;');
+run_sql_command('ALTER TABLE t1 ADD CONSTRAINT nn NOT NULL f1, ALTER f1 type bigint;');
+
+# can use indexscan mechanism to fast add multiple not-null constraints
+$output = run_sql_command(
+	'ALTER TABLE t1 ALTER COLUMN f2 SET NOT NULL, ALTER COLUMN f1 SET NOT NULL;'
+);
+ok( $output =~
+	  m/all new not-null constraints on relation "t1" have been validated by using index scan/,
+	'all not-null constraints are validated by indexscan');
+
+# using indexscan mechanism to fast add a not-null can only apply to key columns, not include column
+$output = run_sql_command(
+	'ALTER TABLE t1 ADD CONSTRAINT nnf4 NOT NULL f4;'
+);
+ok(!is_indexscan_veritify_notnull($output), 'can not use indexscan to validate not-null constraint on t1');
+
+# if index is not btree index then cannot use indexscan mechanism to fast add not-null constraint
+$output = run_sql_command(
+	'ALTER TABLE t1 ADD CONSTRAINT nn_f5 NOT NULL f5;'
+);
+ok(!is_indexscan_veritify_notnull($output), 'can not use indexscan to validate not-null constraints on t1');
+
+$node->stop('fast');
+
+done_testing();
-- 
2.47.3


--xpkr6zhfzd3fjt76--





^ permalink  raw  reply  [nested|flat] 150+ messages in thread

* [PATCH v8] using indexscan to speedup add not null constraints
@ 2025-10-20 05:29  jian he <[email protected]>
  0 siblings, 0 replies; 150+ messages in thread

From: jian he @ 2025-10-20 05:29 UTC (permalink / raw)

This patch tries to use index_beginscan() / index_getnext() / index_endscan()
mentioned in [1] to speedup adding not-null constraints to the existing table.

The main logic happens in phase3 ATRewriteTable
1. collect all not-null constraints.
2. For each not-null constraint, check whether there is a corresponding index
available for validation. If not, then can not use indexscan to verify not-null
constraints.
3. If any of the following conditions are true
  * table scan or rewrite is required,
  * table wasn't locked with `AccessExclusiveLock`
  * the NOT NULL constraint applies to a virtual generated column
 then index scan cannot be used for fast validation.
4. If all conditions are satisfied, attempt to use indexscan to verify
whether the column contains any NULL values.

concurrency concern:
ALTER TABLE SET NOT NULL will take an ACCESS EXCLUSIVE lock, so there is less
variant of racing issue can occur?  to prove accurate, I wrote some isolation
tests. see[2]

performance:
demo:
case when: %20 percent values are NULL and have been deleted from heap but they
still on the index.

drop table if exists t;
create unlogged table t(a int, b int) with (autovacuum_enabled = off, vacuum_index_cleanup=off);
insert into t select case when g % 5 = 0 then null else g end, g+1
from generate_series(1,1_000_000) g;
create index t_idx_a on t(a);
delete from t where a is null;

alter table t alter column a drop not null;
alter table t add constraint t1 not null a;

the above two statement running several times:
patch Time:: 1.084  ms
master Time: 12.045 ms

references:
[1] https://postgr.es/m/CA%2BTgmoa5NKz8iGW_9v7wz%3D-%2BzQFu%3DE4SZoaTaU1znLaEXRYp-Q%40mail.gmail.com
[2] https://postgr.es/m/900056D1-32DF-4927-8251-3E0C0DC407FD%40anarazel.de
discussion: https://postgr.es/m/CACJufxFiW=4k1is=F1J=r-Cx1RuByXQPUrWB331U47rSnGz+hw@mail.gmail.com
commitfest entry: https://commitfest.postgresql.org/patch/5444
---
 src/backend/commands/tablecmds.c              | 116 +++++++++-
 src/backend/executor/execIndexing.c           | 213 ++++++++++++++++++
 src/include/executor/executor.h               |   2 +
 .../expected/indexscan-check-notnull.out      |  97 ++++++++
 src/test/isolation/isolation_schedule         |   1 +
 .../specs/indexscan-check-notnull.spec        |  45 ++++
 src/test/modules/test_misc/meson.build        |   1 +
 .../t/011_indexscan_validate_notnull.pl       | 163 ++++++++++++++
 8 files changed, 632 insertions(+), 6 deletions(-)
 create mode 100644 src/test/isolation/expected/indexscan-check-notnull.out
 create mode 100644 src/test/isolation/specs/indexscan-check-notnull.spec
 create mode 100644 src/test/modules/test_misc/t/011_indexscan_validate_notnull.pl

diff --git a/src/backend/commands/tablecmds.c b/src/backend/commands/tablecmds.c
index f976c0e5c7e..2af06630b35 100644
--- a/src/backend/commands/tablecmds.c
+++ b/src/backend/commands/tablecmds.c
@@ -210,16 +210,19 @@ typedef struct AlteredTableInfo
 	List	   *changedStatisticsDefs;	/* string definitions of same */
 } AlteredTableInfo;
 
-/* Struct describing one new constraint to check in Phase 3 scan */
-/* Note: new not-null constraints are handled elsewhere */
+/*
+ * Struct describing one new constraint to check in Phase 3 scan. Note: new
+ * not-null constraints are handled here too.
+*/
 typedef struct NewConstraint
 {
 	char	   *name;			/* Constraint name, or NULL if none */
-	ConstrType	contype;		/* CHECK or FOREIGN */
+	ConstrType	contype;		/* CHECK or FOREIGN or NOT NULL */
 	Oid			refrelid;		/* PK rel, if FOREIGN */
 	Oid			refindid;		/* OID of PK's index, if FOREIGN */
 	bool		conwithperiod;	/* Whether the new FOREIGN KEY uses PERIOD */
 	Oid			conid;			/* OID of pg_constraint entry, if FOREIGN */
+	int			attnum;			/* NOT NULL constraint attribute number */
 	Node	   *qual;			/* Check expr or CONSTR_FOREIGN Constraint */
 	ExprState  *qualstate;		/* Execution state for CHECK expr */
 } NewConstraint;
@@ -6217,6 +6220,9 @@ ATRewriteTable(AlteredTableInfo *tab, Oid OIDNewHeap)
 				needscan = true;
 				con->qualstate = ExecPrepareExpr((Expr *) expand_generated_columns_in_expr(con->qual, oldrel, 1), estate);
 				break;
+			case CONSTR_NOTNULL:
+				/* Nothing to do here */
+				break;
 			case CONSTR_FOREIGN:
 				/* Nothing to do here */
 				break;
@@ -6270,10 +6276,69 @@ ATRewriteTable(AlteredTableInfo *tab, Oid OIDNewHeap)
 														wholeatt->attnum);
 			}
 		}
-		if (notnull_attrs || notnull_virtual_attrs)
-			needscan = true;
 	}
 
+	/*-
+	 * If we have to verify new not-null constraints and don't have any other
+	 * reason to fully scan the table, then we can use indexes to test for
+	 * absence of NULL values instead of scanning.  The following conditions
+	 * must be met:
+	 * - we're operating on a regular table
+	 * - we hold AccessExclusiveLock on the table
+	 * - no not-null constraint covers a virtual generated column,
+	 *   because no indexes can be created on them
+	 */
+	if (!needscan &&
+		newrel == NULL &&
+		tab->verify_new_notnull &&
+		notnull_virtual_attrs == NIL &&
+		oldrel->rd_rel->relkind == RELKIND_RELATION &&
+		CheckRelationLockedByMe(oldrel, AccessExclusiveLock, false))
+	{
+		List	   *notnull_attnums = NIL;
+
+		Assert(!tab->rewrite);
+
+		foreach(l, tab->constraints)
+		{
+			Form_pg_attribute attr;
+			NewConstraint *con = lfirst(l);
+
+			if (con->contype != CONSTR_NOTNULL)
+				continue;
+
+			attr = TupleDescAttr(newTupDesc, con->attnum - 1);
+
+			Assert(attr->attnotnull);
+			Assert(attr->attnum == con->attnum);
+
+			if (attr->attgenerated == ATTRIBUTE_GENERATED_VIRTUAL)
+			{
+				needscan = true;
+				break;
+			}
+
+			notnull_attnums = lappend_int(notnull_attnums, attr->attnum);
+		}
+
+		/*
+		 * Validate new NOT NULL constraints, unless we need a scan for other
+		 * reasons, because we can validate them cheaply there, and doing it
+		 * also here would be a waste of cycles.
+		 */
+		if (notnull_attnums != NIL && !needscan)
+		{
+			if (!index_check_notnull(oldrel, notnull_attnums))
+				needscan = true;
+			else
+				ereport(DEBUG1,
+						errmsg_internal("all new not-null constraints on relation \"%s\" have been validated by using index scan",
+										RelationGetRelationName(oldrel)));
+		}
+	}
+	else if (notnull_attrs || notnull_virtual_attrs)
+		needscan = true;
+
 	if (newrel || needscan)
 	{
 		ExprContext *econtext;
@@ -7949,6 +8014,7 @@ ATExecSetNotNull(List **wqueue, Relation rel, char *conName, char *colName,
 	CookedConstraint *ccon;
 	List	   *cooked;
 	bool		is_no_inherit = false;
+	AlteredTableInfo *tab = NULL;
 
 	/* Guard against stack overflow due to overly deep inheritance tree. */
 	check_stack_depth();
@@ -8073,10 +8139,32 @@ ATExecSetNotNull(List **wqueue, Relation rel, char *conName, char *colName,
 	constraint->is_no_inherit = is_no_inherit;
 	constraint->conname = conName;
 
+	tab = ATGetQueueEntry(wqueue, rel);
+
 	/* and do it */
 	cooked = AddRelationNewConstraints(rel, NIL, list_make1(constraint),
 									   false, !recursing, false, NULL);
 	ccon = linitial(cooked);
+
+	Assert(ccon->contype == CONSTR_NOTNULL);
+
+	/*
+	 * We may use indexscan to vertify not-null constraint in Phase3.  Add the
+	 * to-be-validated not-null constraint to Phase 3's queue.
+	 */
+	if (!ccon->skip_validation)
+	{
+		NewConstraint *newcon;
+
+		newcon = (NewConstraint *) palloc0(sizeof(NewConstraint));
+
+		newcon->name = ccon->name;
+		newcon->contype = ccon->contype;
+		newcon->attnum = ccon->attnum;
+
+		tab->constraints = lappend(tab->constraints, newcon);
+	}
+
 	ObjectAddressSet(address, ConstraintRelationId, ccon->conoid);
 
 	InvokeObjectPostAlterHook(RelationRelationId,
@@ -9983,13 +10071,15 @@ ATAddCheckNNConstraint(List **wqueue, AlteredTableInfo *tab, Relation rel,
 	{
 		CookedConstraint *ccon = (CookedConstraint *) lfirst(lcon);
 
-		if (!ccon->skip_validation && ccon->contype != CONSTR_NOTNULL)
+		if (!ccon->skip_validation)
 		{
 			NewConstraint *newcon;
 
 			newcon = palloc0_object(NewConstraint);
 			newcon->name = ccon->name;
 			newcon->contype = ccon->contype;
+			if (ccon->contype == CONSTR_NOTNULL)
+				newcon->attnum = ccon->attnum;
 			newcon->qual = ccon->expr;
 
 			tab->constraints = lappend(tab->constraints, newcon);
@@ -13258,6 +13348,7 @@ QueueNNConstraintValidation(List **wqueue, Relation conrel, Relation rel,
 	List	   *children = NIL;
 	AttrNumber	attnum;
 	char	   *colname;
+	NewConstraint *newcon;
 
 	con = (Form_pg_constraint) GETSTRUCT(contuple);
 	Assert(con->contype == CONSTRAINT_NOTNULL);
@@ -13321,7 +13412,20 @@ QueueNNConstraintValidation(List **wqueue, Relation conrel, Relation rel,
 	/* Set attnotnull appropriately without queueing another validation */
 	set_attnotnull(NULL, rel, attnum, true, false);
 
+	/*
+	 * Queue validation for phase 3.
+	 *
+	 * ALTER TABLE SET NOT NULL will add NOT NULL constraint to
+	 * AlteredTableInfo->constraints, for consistency, do the same here.
+	 */
+	newcon = (NewConstraint *) palloc0(sizeof(NewConstraint));
+	newcon->name = colname;
+	newcon->contype = CONSTR_NOTNULL;
+	newcon->attnum = attnum;
+
+	/* Find or create work queue entry for this table */
 	tab = ATGetQueueEntry(wqueue, rel);
+	tab->constraints = lappend(tab->constraints, newcon);
 	tab->verify_new_notnull = true;
 
 	/*
diff --git a/src/backend/executor/execIndexing.c b/src/backend/executor/execIndexing.c
index 6ae0f959592..88694ce0335 100644
--- a/src/backend/executor/execIndexing.c
+++ b/src/backend/executor/execIndexing.c
@@ -108,12 +108,15 @@
 
 #include "access/genam.h"
 #include "access/relscan.h"
+#include "access/table.h"
 #include "access/tableam.h"
 #include "access/xact.h"
 #include "catalog/index.h"
+#include "catalog/pg_am_d.h"
 #include "executor/executor.h"
 #include "nodes/nodeFuncs.h"
 #include "storage/lmgr.h"
+#include "utils/fmgroids.h"
 #include "utils/injection_point.h"
 #include "utils/multirangetypes.h"
 #include "utils/rangetypes.h"
@@ -146,6 +149,7 @@ static bool index_expression_changed_walker(Node *node,
 											Bitmapset *allUpdatedCols);
 static void ExecWithoutOverlapsNotEmpty(Relation rel, NameData attname, Datum attval,
 										char typtype, Oid atttypid);
+static bool index_check_notnull_internal(Relation relation, List *attnums, List *idxs);
 
 /* ----------------------------------------------------------------
  *		ExecOpenIndices
@@ -1178,3 +1182,212 @@ ExecWithoutOverlapsNotEmpty(Relation rel, NameData attname, Datum attval, char t
 				 errmsg("empty WITHOUT OVERLAPS value found in column \"%s\" in relation \"%s\"",
 						NameStr(attname), RelationGetRelationName(rel))));
 }
+
+/*
+ * notnull_attnums: list of attribute numbers of all new not-null constraints.
+ *
+ * First check whether the relation has a suitable index for each not-null
+ * attribute, then using indexscan mechanism to verify that *all* attributes on
+ * notnull_attnums are indeed not null.
+ *
+ * Returning true means all new not-null constraints have been verified, no
+ * need an extra scan to verify newly added not-null constraints.
+ */
+bool
+index_check_notnull(Relation relation, List *notnull_attnums)
+{
+	Relation	pg_index;
+	Relation	index_rel;
+	SysScanDesc indscan;
+	ScanKeyData skey;
+	HeapTuple	htup;
+	TupleDesc	tupdesc;
+	Form_pg_attribute attr;
+	List	   *idxs = NIL;
+	List	   *attnums = NIL;
+
+	tupdesc = RelationGetDescr(relation);
+
+	/* Prepare to scan pg_index for entries having indrelid = this rel */
+	ScanKeyInit(&skey,
+				Anum_pg_index_indrelid,
+				BTEqualStrategyNumber, F_OIDEQ,
+				ObjectIdGetDatum(RelationGetRelid(relation)));
+
+	pg_index = table_open(IndexRelationId, AccessShareLock);
+	indscan = systable_beginscan(pg_index, IndexIndrelidIndexId, true,
+								 NULL, 1, &skey);
+
+	while (HeapTupleIsValid(htup = systable_getnext(indscan)))
+	{
+		Form_pg_index index = (Form_pg_index) GETSTRUCT(htup);
+
+		/*
+		 * we can only use non-deferred, validated, and alive btree index to
+		 * validate not-null constraints
+		 */
+		if (!index->indimmediate || !index->indisvalid || !index->indislive)
+			continue;
+
+		/* can not use expression index or partial index too */
+		if (!heap_attisnull(htup, Anum_pg_index_indexprs, NULL) ||
+			!heap_attisnull(htup, Anum_pg_index_indpred, NULL))
+			continue;
+
+		index_rel = index_open(index->indexrelid, AccessShareLock);
+
+		/* can only apply to btree index */
+		if (index_rel->rd_rel->relam != BTREE_AM_OID)
+		{
+			index_close(index_rel, AccessShareLock);
+			continue;
+		}
+
+		/* collect index attnums while loop */
+		for (int i = 0; i < index->indnkeyatts; i++)
+		{
+			attr = TupleDescAttr(tupdesc, (index->indkey.values[i] - 1));
+
+			if (attr->attisdropped)
+				continue;
+
+			if (list_member_int(notnull_attnums, attr->attnum) &&
+				!list_member_int(attnums, attr->attnum))
+			{
+				attnums = lappend_int(attnums, attr->attnum);
+				idxs = lappend_oid(idxs, index->indexrelid);
+			}
+		}
+		index_close(index_rel, NoLock);
+	}
+	systable_endscan(indscan);
+	table_close(pg_index, AccessShareLock);
+
+	if (attnums == NIL)
+		return false;
+
+	/*
+	 * every not-null constraint requires an index for indexscan.  If no such
+	 * index exists, we need to use regular table scan to validate not-null
+	 * constraints.
+	 */
+	foreach_int(attno, notnull_attnums)
+	{
+		if (!list_member_int(attnums, attno))
+			return false;
+	}
+
+	return index_check_notnull_internal(relation, attnums, idxs);
+}
+
+/*
+ * Use indexscan mechanism to fast verify each attribute in "attnums" are
+ * not-null or not.
+ */
+static bool
+index_check_notnull_internal(Relation relation, List *attnums, List *idxs)
+{
+	EState	   *estate;
+	ExprContext *econtext;
+	TupleTableSlot *existing_slot;
+	bool		all_not_null = true;
+	ListCell   *lc,
+			   *lc2;
+
+	/*
+	 * Need an EState for slot to hold the current tuple.
+	 */
+	estate = CreateExecutorState();
+	econtext = GetPerTupleExprContext(estate);
+
+	forboth(lc, attnums, lc2, idxs)
+	{
+		SnapshotData DirtySnapshot;
+		IndexScanDesc index_scan;
+		ScanKeyData scankeys[INDEX_MAX_KEYS];
+		IndexInfo  *indexInfo;
+		AttrNumber	sk_attno = -1;
+		Relation	index;
+		int			indnkeyatts;
+
+		AttrNumber	attno = lfirst_int(lc);
+		Oid			indexoid = lfirst_oid(lc2);
+
+		existing_slot = table_slot_create(relation, NULL);
+
+		/* Arrange for econtext's scan tuple to be the tuple under test */
+		econtext->ecxt_scantuple = existing_slot;
+
+		index = index_open(indexoid, NoLock);
+
+		indexInfo = BuildIndexInfo(index);
+		indnkeyatts = IndexRelationGetNumberOfKeyAttributes(index);
+
+		/*
+		 * Search the tuples that are in the index for any violations,
+		 * including tuples that aren't visible yet.
+		 */
+		InitDirtySnapshot(DirtySnapshot);
+
+		for (int i = 0; i < indnkeyatts; i++)
+		{
+			if (indexInfo->ii_IndexAttrNumbers[i] == attno)
+			{
+				sk_attno = i + 1;
+				break;
+			}
+		}
+
+		if (sk_attno == -1)
+			elog(ERROR, "cache lookup failed for attribute number %d on index %u", indexoid, attno);
+
+		for (int i = 0; i < indnkeyatts; i++)
+		{
+			/* set up an IS NULL scan key so that we ignore not nulls */
+			ScanKeyEntryInitialize(&scankeys[i],
+								   SK_ISNULL | SK_SEARCHNULL,
+								   sk_attno,	/* index col to scan */
+								   InvalidStrategy, /* no strategy */
+								   InvalidOid,	/* no strategy subtype */
+								   InvalidOid,	/* no collation */
+								   InvalidOid,	/* no reg proc for this */
+								   (Datum) 0);	/* constant */
+		}
+
+		index_scan = index_beginscan(relation, index, &DirtySnapshot, NULL, indnkeyatts, 0);
+		index_rescan(index_scan, scankeys, indnkeyatts, NULL, 0);
+
+		while (index_getnext_slot(index_scan, ForwardScanDirection, existing_slot))
+		{
+			Datum		values[INDEX_MAX_KEYS];
+			bool		nulls[INDEX_MAX_KEYS];
+
+			/*
+			 * Extract the index column values and isnull flags from the
+			 * existing tuple.
+			 */
+			FormIndexDatum(indexInfo, existing_slot, estate, values, nulls);
+
+			if (nulls[sk_attno - 1])
+			{
+				all_not_null = false;
+				break;
+			}
+		}
+
+		index_endscan(index_scan);
+		index_close(index, NoLock);
+		ExecDropSingleTupleTableSlot(existing_slot);
+
+		/* exit earlier */
+		if (!all_not_null)
+		{
+			FreeExecutorState(estate);
+			return false;
+		}
+	}
+
+	FreeExecutorState(estate);
+
+	return true;
+}
diff --git a/src/include/executor/executor.h b/src/include/executor/executor.h
index 5929aabc353..7f24caeeafb 100644
--- a/src/include/executor/executor.h
+++ b/src/include/executor/executor.h
@@ -756,6 +756,8 @@ extern void check_exclusion_constraint(Relation heap, Relation index,
 									   const Datum *values, const bool *isnull,
 									   EState *estate, bool newIndex);
 
+extern bool index_check_notnull(Relation relation, List *notnull_attnums);
+
 /*
  * prototypes from functions in execReplication.c
  */
diff --git a/src/test/isolation/expected/indexscan-check-notnull.out b/src/test/isolation/expected/indexscan-check-notnull.out
new file mode 100644
index 00000000000..c6a652e2518
--- /dev/null
+++ b/src/test/isolation/expected/indexscan-check-notnull.out
@@ -0,0 +1,97 @@
+Parsed test spec with 2 sessions
+
+starting permutation: s1_b1 s2_b1 s1_d1 s2_a1 s1_c1 s2_c1 s1_q1
+step s1_b1: BEGIN ISOLATION LEVEL REPEATABLE READ;
+step s2_b1: BEGIN ISOLATION LEVEL REPEATABLE READ;
+step s1_d1: DELETE FROM t;
+step s2_a1: ALTER TABLE t ADD CONSTRAINT t1_nn NOT NULL a; <waiting ...>
+step s1_c1: COMMIT;
+step s2_a1: <... completed>
+step s2_c1: COMMIT;
+step s1_q1: SELECT conname, conrelid::regclass, contype, convalidated
+              FROM pg_constraint WHERE conname = 't1_nn';
+
+conname|conrelid|contype|convalidated
+-------+--------+-------+------------
+t1_nn  |t       |n      |t           
+(1 row)
+
+
+starting permutation: s1_b2 s2_b1 s1_d1 s2_a1 s1_c1 s2_c1 s1_q1
+step s1_b2: BEGIN;
+step s2_b1: BEGIN ISOLATION LEVEL REPEATABLE READ;
+step s1_d1: DELETE FROM t;
+step s2_a1: ALTER TABLE t ADD CONSTRAINT t1_nn NOT NULL a; <waiting ...>
+step s1_c1: COMMIT;
+step s2_a1: <... completed>
+step s2_c1: COMMIT;
+step s1_q1: SELECT conname, conrelid::regclass, contype, convalidated
+              FROM pg_constraint WHERE conname = 't1_nn';
+
+conname|conrelid|contype|convalidated
+-------+--------+-------+------------
+t1_nn  |t       |n      |t           
+(1 row)
+
+
+starting permutation: s1_b1 s2_b2 s1_d1 s2_a1 s1_c1 s2_c1 s1_q1
+step s1_b1: BEGIN ISOLATION LEVEL REPEATABLE READ;
+step s2_b2: BEGIN;
+step s1_d1: DELETE FROM t;
+step s2_a1: ALTER TABLE t ADD CONSTRAINT t1_nn NOT NULL a; <waiting ...>
+step s1_c1: COMMIT;
+step s2_a1: <... completed>
+step s2_c1: COMMIT;
+step s1_q1: SELECT conname, conrelid::regclass, contype, convalidated
+              FROM pg_constraint WHERE conname = 't1_nn';
+
+conname|conrelid|contype|convalidated
+-------+--------+-------+------------
+t1_nn  |t       |n      |t           
+(1 row)
+
+
+starting permutation: s1_b1 s2_b1 s2_a1 s1_r1 s2_r1
+step s1_b1: BEGIN ISOLATION LEVEL REPEATABLE READ;
+step s2_b1: BEGIN ISOLATION LEVEL REPEATABLE READ;
+step s2_a1: ALTER TABLE t ADD CONSTRAINT t1_nn NOT NULL a;
+ERROR:  column "a" of relation "t" contains null values
+step s1_r1: ROLLBACK;
+step s2_r1: ROLLBACK;
+
+starting permutation: s1_b1 s2_b2 s2_d1 s1_d1 s2_r1 s1_a1 s1_q1 s1_r1
+step s1_b1: BEGIN ISOLATION LEVEL REPEATABLE READ;
+step s2_b2: BEGIN;
+step s2_d1: DROP INDEX t_ab_idx;
+step s1_d1: DELETE FROM t; <waiting ...>
+step s2_r1: ROLLBACK;
+step s1_d1: <... completed>
+step s1_a1: ALTER TABLE t ADD CONSTRAINT t1_nn NOT NULL a;
+step s1_q1: SELECT conname, conrelid::regclass, contype, convalidated
+              FROM pg_constraint WHERE conname = 't1_nn';
+
+conname|conrelid|contype|convalidated
+-------+--------+-------+------------
+t1_nn  |t       |n      |t           
+(1 row)
+
+step s1_r1: ROLLBACK;
+
+starting permutation: s1_b2 s2_b1 s1_d1 s2_d1 s1_s0 s1_a1 s1_c1 s2_c1 s1_q1
+step s1_b2: BEGIN;
+step s2_b1: BEGIN ISOLATION LEVEL REPEATABLE READ;
+step s1_d1: DELETE FROM t;
+step s2_d1: DROP INDEX t_ab_idx; <waiting ...>
+step s1_s0: SAVEPOINT s0;
+step s1_a1: ALTER TABLE t ADD CONSTRAINT t1_nn NOT NULL a;
+step s1_c1: COMMIT;
+step s2_d1: <... completed>
+step s2_c1: COMMIT;
+step s1_q1: SELECT conname, conrelid::regclass, contype, convalidated
+              FROM pg_constraint WHERE conname = 't1_nn';
+
+conname|conrelid|contype|convalidated
+-------+--------+-------+------------
+t1_nn  |t       |n      |t           
+(1 row)
+
diff --git a/src/test/isolation/isolation_schedule b/src/test/isolation/isolation_schedule
index 01ff1c6586f..7ce6bbcaf89 100644
--- a/src/test/isolation/isolation_schedule
+++ b/src/test/isolation/isolation_schedule
@@ -58,6 +58,7 @@ test: merge-delete
 test: merge-update
 test: merge-match-recheck
 test: merge-join
+test: indexscan-check-notnull
 test: delete-abort-savept
 test: delete-abort-savept-2
 test: aborted-keyrevoke
diff --git a/src/test/isolation/specs/indexscan-check-notnull.spec b/src/test/isolation/specs/indexscan-check-notnull.spec
new file mode 100644
index 00000000000..05b4488550c
--- /dev/null
+++ b/src/test/isolation/specs/indexscan-check-notnull.spec
@@ -0,0 +1,45 @@
+
+#
+# using indexscan to check a column not-null constraint
+# is satisfied or not.
+#
+
+setup
+{
+  CREATE TABLE t (a int, b int);
+  CREATE INDEX t_ab_idx on t(a,b);
+  INSERT INTO t values (null, 1);
+  INSERT INTO t SELECT x, x*10 FROM generate_series(1,3) g(x);
+}
+
+teardown
+{
+  DROP TABLE t;
+}
+
+session s1
+step s1_b1  { BEGIN ISOLATION LEVEL REPEATABLE READ; }
+step s1_b2  { BEGIN; }
+step s1_d1  { DELETE FROM t;}
+step s1_s0  { SAVEPOINT s0;}
+step s1_a1  { ALTER TABLE t ADD CONSTRAINT t1_nn NOT NULL a;}
+step s1_q1  { SELECT conname, conrelid::regclass, contype, convalidated
+              FROM pg_constraint WHERE conname = 't1_nn';
+            }
+step s1_r1  { ROLLBACK; }
+step s1_c1  { COMMIT; }
+
+session s2
+step s2_b1  { BEGIN ISOLATION LEVEL REPEATABLE READ; }
+step s2_b2  { BEGIN; }
+step s2_a1  { ALTER TABLE t ADD CONSTRAINT t1_nn NOT NULL a;}
+step s2_d1  { DROP INDEX t_ab_idx;}
+step s2_r1  { ROLLBACK; }
+step s2_c1  { COMMIT; }
+
+permutation s1_b1 s2_b1 s1_d1 s2_a1 s1_c1 s2_c1 s1_q1
+permutation s1_b2 s2_b1 s1_d1 s2_a1 s1_c1 s2_c1 s1_q1
+permutation s1_b1 s2_b2 s1_d1 s2_a1 s1_c1 s2_c1 s1_q1
+permutation s1_b1 s2_b1 s2_a1 s1_r1 s2_r1
+permutation s1_b1 s2_b2 s2_d1 s1_d1 s2_r1 s1_a1 s1_q1 s1_r1
+permutation s1_b2 s2_b1 s1_d1 s2_d1 s1_s0 s1_a1 s1_c1 s2_c1 s1_q1
diff --git a/src/test/modules/test_misc/meson.build b/src/test/modules/test_misc/meson.build
index 6e8db1621a7..56faf359b29 100644
--- a/src/test/modules/test_misc/meson.build
+++ b/src/test/modules/test_misc/meson.build
@@ -19,6 +19,7 @@ tests += {
       't/008_replslot_single_user.pl',
       't/009_log_temp_files.pl',
       't/010_index_concurrently_upsert.pl',
+      't/011_indexscan_validate_notnull.pl',
     ],
     # The injection points are cluster-wide, so disable installcheck
     'runningcheck': false,
diff --git a/src/test/modules/test_misc/t/011_indexscan_validate_notnull.pl b/src/test/modules/test_misc/t/011_indexscan_validate_notnull.pl
new file mode 100644
index 00000000000..a3f3cb409b6
--- /dev/null
+++ b/src/test/modules/test_misc/t/011_indexscan_validate_notnull.pl
@@ -0,0 +1,163 @@
+# Copyright (c) 2025, PostgreSQL Global Development Group
+
+# Verify that indexscan mechanism can speedup ALTER TABLE ADD NOT NULL
+
+
+use strict;
+use warnings FATAL => 'all';
+use PostgreSQL::Test::Cluster;
+use PostgreSQL::Test::Utils;
+use Test::More;
+
+# Initialize a test cluster
+my $node = PostgreSQL::Test::Cluster->new('primary');
+$node->init();
+# Turn message level up to DEBUG1 so that we get the messages we want to see
+$node->append_conf('postgresql.conf', 'client_min_messages = DEBUG1');
+$node->start;
+
+# Run a SQL command and return psql's stderr (including debug messages)
+sub run_sql_command
+{
+	my $sql = shift;
+	my $stderr;
+
+	$node->psql(
+		'postgres',
+		$sql,
+		stderr => \$stderr,
+		on_error_die => 1,
+		on_error_stop => 1);
+	return $stderr;
+}
+
+# Check whether result of run_sql_command shows that we did a verify pass
+sub is_table_verified
+{
+	my $output = shift;
+	return index($output, 'DEBUG:  verifying table') != -1;
+}
+
+# Check whether result of run_sql_command shows that we did a verify pass
+sub is_indexscan_veritify_notnull
+{
+	my $output = shift;
+	return index($output, 'DEBUG:  all new not-null constraints on relation') != -1;
+}
+
+my $output;
+
+note "test alter table SET NOT NULL using indexscan with partitioned table";
+
+run_sql_command(
+    'CREATE TABLE tp (a int, b int, c int, d int ) PARTITION BY range(a);
+     CREATE TABLE tpp1 partition of tp for values from ( 1 ) to (10);
+     CREATE TABLE tpp2 partition of tp for values from ( 10 ) to (21);
+     INSERT INTO tp select g, g + 10, g + 15, g + random(min=>1::int, max=>10::int) from generate_series(1,19) g;
+     CREATE INDEX ON tp(b); ');
+
+$output = run_sql_command('ALTER TABLE tp ALTER COLUMN b SET NOT NULL;');
+ok(is_indexscan_veritify_notnull($output),
+	'column b will use indexscan to verify not-null status, no need scan table');
+ok( $output =~
+	  m/all new not-null constraints on relation "tpp1" have been validated by using index scan/,
+	'all newly added constraints proved by indexscan');
+
+run_sql_command(
+	'ALTER TABLE tp ALTER COLUMN b DROP NOT NULL;');
+
+# use indexes on partitions to fast vertifing not-null should be ok
+$output = run_sql_command('ALTER TABLE tpp1 ALTER COLUMN b SET NOT NULL;');
+ok(is_indexscan_veritify_notnull($output), 'use indexscan to validate column b not-null will not scan table');
+ok(!is_table_verified($output), 'no table scan for pp1');
+ok( $output =~
+	  m/all new not-null constraints on relation "tpp1" have been validated by using index scan/,
+	'all newly added constraints proved by indexscan');
+
+$output = run_sql_command('ALTER TABLE tpp2 ALTER COLUMN b SET NOT NULL;');
+ok(is_indexscan_veritify_notnull($output), 'use indexscan to validate column b not-null, will not scan table');
+ok(!is_table_verified($output), 'no table scan for tpp2');
+ok( $output =~
+	  m/all new not-null constraints on relation "tpp2" have been validated by using index scan/,
+	'all newly added constraints proved by indexscan');
+
+run_sql_command(
+	'ALTER TABLE tp ALTER COLUMN b DROP NOT NULL;');
+
+# table rewrite then can not use indexscan to verify not-null constraint
+$output = run_sql_command(
+	'ALTER TABLE tp ALTER COLUMN b SET NOT NULL, ALTER COLUMN b SET DATA TYPE bigint;'
+);
+ok(!is_table_verified($output), 'no table scan for tp');
+ok(!is_indexscan_veritify_notnull($output), 'table tp will rewrite, can not use indexscan to verify not-null constraints on it');
+
+# test using indexscan with multiple not-null constraints
+run_sql_command(
+    'ALTER TABLE tp ALTER COLUMN b DROP NOT NULL;
+	 CREATE INDEX ON tp(c);
+	 CREATE INDEX ON tp(d); ');
+
+# one column can use indexscan, another can not, so can not use indexscan to verify not-null
+$output = run_sql_command(
+	'ALTER TABLE tp ALTER COLUMN a SET NOT NULL, ADD CONSTRAINT c_nn NOT NULL c');
+ok(is_table_verified($output), 'table scan for tp');
+ok(!is_indexscan_veritify_notnull($output), 'can not use indexscan to verify not-null constraints on table tp');
+
+# all columns have index on it
+# use indexscan to verify multiple not-null constraints should just fine
+$output = run_sql_command(
+	'ALTER TABLE tp ALTER COLUMN d SET NOT NULL, ADD CONSTRAINT c_nn NOT NULL c, ALTER COLUMN b SET NOT NULL;');
+ok(!is_table_verified($output), 'no table scan for tp');
+ok(is_indexscan_veritify_notnull($output),
+	'using indexscan to verify not-null constraints on column b, c, d, no need table scan');
+
+# test with non-partitioned table and other non-Btree index.
+run_sql_command(
+    'CREATE TABLE t1(f1 INT, f2 int, f3 int,f4 int, f5 int);
+     INSERT INTO t1 select g, g+1, g+2, g+3, g+4 from generate_series(1, 100) g;
+     CREATE INDEX t1_f1_f2_idx ON t1(f1,f2);
+     CREATE UNIQUE INDEX t1_f3idx ON t1(f3);
+     CREATE INDEX t1_f3f4idx ON t1(f3) include(f4);
+     CREATE INDEX hash_f5_idx ON t1 USING hash (f5 int4_ops); ');
+
+# ALTER TABLE VALIDATE CONSTRAINT can not use indexscan,
+# because it only hold ShareUpdateExclusiveLock lock.
+run_sql_command('ALTER TABLE t1 ADD CONSTRAINT nn_t1_f2 NOT NULL f2 NOT VALID;');
+
+$output = run_sql_command(
+	'ALTER TABLE t1 VALIDATE CONSTRAINT nn_t1_f2;'
+);
+ok(!is_indexscan_veritify_notnull($output), 'can not use indexscan for ALTER TABLE VALIDATE CONSTRAINT command');
+run_sql_command('ALTER TABLE t1 DROP CONSTRAINT nn_t1_f2;');
+
+$output = run_sql_command(
+	'ALTER TABLE t1 ALTER COLUMN f1 SET NOT NULL, ALTER f1 type bigint;'
+);
+ok(!is_indexscan_veritify_notnull($output), 'table t1 will rewrite, can not use indexscan to validate not-null constraints on t1');
+
+run_sql_command('ALTER TABLE t1 ALTER COLUMN f1 DROP NOT NULL;');
+run_sql_command('ALTER TABLE t1 ADD CONSTRAINT nn NOT NULL f1, ALTER f1 type bigint;');
+
+# can use indexscan mechanism to fast add multiple not-null constraints
+$output = run_sql_command(
+	'ALTER TABLE t1 ALTER COLUMN f2 SET NOT NULL, ALTER COLUMN f1 SET NOT NULL;'
+);
+ok( $output =~
+	  m/all new not-null constraints on relation "t1" have been validated by using index scan/,
+	'all not-null constraints are validated by indexscan');
+
+# using indexscan mechanism to fast add a not-null can only apply to key columns, not include column
+$output = run_sql_command(
+	'ALTER TABLE t1 ADD CONSTRAINT nnf4 NOT NULL f4;'
+);
+ok(!is_indexscan_veritify_notnull($output), 'can not use indexscan to validate not-null constraint on t1');
+
+# if index is not btree index then cannot use indexscan mechanism to fast add not-null constraint
+$output = run_sql_command(
+	'ALTER TABLE t1 ADD CONSTRAINT nn_f5 NOT NULL f5;'
+);
+ok(!is_indexscan_veritify_notnull($output), 'can not use indexscan to validate not-null constraints on t1');
+
+$node->stop('fast');
+
+done_testing();
-- 
2.47.3


--xpkr6zhfzd3fjt76--





^ permalink  raw  reply  [nested|flat] 150+ messages in thread