Date: Tue, 12 Mar 2024 22:07:17 -0500
From: Nathan Bossart <nathandbossart@gmail.com>
To: Yugo NAGATA <nagata@sraoss.co.jp>
Cc: jian he <jian.universality@gmail.com>, Sergei Kornilov <sk@zsrv.org>,
	Nikita Malakhov <hukutoc@gmail.com>, pgsql-hackers@postgresql.org
Subject: Re: pg_column_toast_chunk_id: a function to get a chunk ID of a
 TOASTed value
Message-ID: <20240313030717.GA2507890@nathanxps13>
References: 
 <CACJufxGpqVg9j_Fb7aBRwricx1ZTV+vEQfUmwuVpNhrRyvcAdA@mail.gmail.com>
 <20240201134524.d647b3d185e5252162eb0436@sraoss.co.jp>
 <CACJufxHyDKcB+34JUDFJubO7GkLNNjZXxbf9jSnSdqVKS8T9+g@mail.gmail.com>
 <20240205162823.6c705517ca6898e482b69b9e@sraoss.co.jp>
 <20240307225617.GA615950@nathanxps13>
 <20240308153155.4c4b2fee3ed1431203e41016@sraoss.co.jp>
 <20240308221758.GB1060542@nathanxps13>
 <20240309115718.deb9209b7f53883cc8e1b4b3@sraoss.co.jp>
 <20240309145028.GB1111406@nathanxps13>
 <20240312155119.9341cfd76f2732ac93ecb6a4@sraoss.co.jp>
MIME-Version: 1.0
Content-Type: multipart/mixed; boundary="IJpNTDwzlM2Ie8A6"
Content-Disposition: inline
In-Reply-To: <20240312155119.9341cfd76f2732ac93ecb6a4@sraoss.co.jp>
Archived-At: 
 <https://www.postgresql.org/message-id/20240313030717.GA2507890%40nathanxps13>
Precedence: bulk


--IJpNTDwzlM2Ie8A6
Content-Type: text/plain; charset=us-ascii
Content-Disposition: inline

I did some light editing to prepare this for commit.

-- 
Nathan Bossart
Amazon Web Services: https://aws.amazon.com

--IJpNTDwzlM2Ie8A6
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v10-0001-Add-pg_column_toast_chunk_id.patch"

From 38c78bd92a7b4d4600e6f0dbe58283c21ea87d50 Mon Sep 17 00:00:00 2001
From: Nathan Bossart <nathan@postgresql.org>
Date: Tue, 12 Mar 2024 22:04:25 -0500
Subject: [PATCH v10 1/1] Add pg_column_toast_chunk_id().

This function returns the chunk_id of an on-disk TOASTed value, or
NULL if the value is un-TOASTed or not on-disk.  This is useful for
identifying which values are actually TOASTed and for investigating
"unexpected chunk number" errors.

XXX: REQUIRES CATVERSION BUMP

Author: Yugo Nagata
Reviewed-by: Jian He
Discussion: https://postgr.es/m/20230329105507.d764497456eeac1ca491b5bd%40sraoss.co.jp
---
 doc/src/sgml/func.sgml                       | 17 ++++++++
 src/backend/utils/adt/varlena.c              | 41 ++++++++++++++++++++
 src/include/catalog/pg_proc.dat              |  3 ++
 src/test/regress/expected/misc_functions.out | 16 ++++++++
 src/test/regress/sql/misc_functions.sql      | 12 ++++++
 5 files changed, 89 insertions(+)

diff --git a/doc/src/sgml/func.sgml b/doc/src/sgml/func.sgml
index 0bb7aeb40e..fe9c1a38b9 100644
--- a/doc/src/sgml/func.sgml
+++ b/doc/src/sgml/func.sgml
@@ -28552,6 +28552,23 @@ postgres=# SELECT '0/0'::pg_lsn + pd.segment_number * ps.setting::int + :offset
        </para></entry>
       </row>
 
+      <row>
+       <entry role="func_table_entry"><para role="func_signature">
+        <indexterm>
+         <primary>pg_column_toast_chunk_id</primary>
+        </indexterm>
+        <function>pg_column_toast_chunk_id</function> ( <type>"any"</type> )
+        <returnvalue>oid</returnvalue>
+       </para>
+       <para>
+        Shows the <structfield>chunk_id</structfield> of an on-disk
+        <acronym>TOAST</acronym>ed value.  Returns <literal>NULL</literal>
+        if the value is un-<acronym>TOAST</acronym>ed or not on-disk.  See
+        <xref linkend="storage-toast"/> for more information about
+        <acronym>TOAST</acronym>.
+       </para></entry>
+      </row>
+
       <row>
        <entry role="func_table_entry"><para role="func_signature">
         <indexterm>
diff --git a/src/backend/utils/adt/varlena.c b/src/backend/utils/adt/varlena.c
index 543afb66e5..8d28dd42ce 100644
--- a/src/backend/utils/adt/varlena.c
+++ b/src/backend/utils/adt/varlena.c
@@ -5105,6 +5105,47 @@ pg_column_compression(PG_FUNCTION_ARGS)
 	PG_RETURN_TEXT_P(cstring_to_text(result));
 }
 
+/*
+ * Return the chunk_id of the on-disk TOASTed value.  Return NULL if the value
+ * is un-TOASTed or not on-disk.
+ */
+Datum
+pg_column_toast_chunk_id(PG_FUNCTION_ARGS)
+{
+	int			typlen;
+	struct varlena *attr;
+	struct varatt_external toast_pointer;
+
+	/* On first call, get the input type's typlen, and save at *fn_extra */
+	if (fcinfo->flinfo->fn_extra == NULL)
+	{
+		/* Lookup the datatype of the supplied argument */
+		Oid			argtypeid = get_fn_expr_argtype(fcinfo->flinfo, 0);
+
+		typlen = get_typlen(argtypeid);
+		if (typlen == 0)		/* should not happen */
+			elog(ERROR, "cache lookup failed for type %u", argtypeid);
+
+		fcinfo->flinfo->fn_extra = MemoryContextAlloc(fcinfo->flinfo->fn_mcxt,
+													  sizeof(int));
+		*((int *) fcinfo->flinfo->fn_extra) = typlen;
+	}
+	else
+		typlen = *((int *) fcinfo->flinfo->fn_extra);
+
+	if (typlen != -1)
+		PG_RETURN_NULL();
+
+	attr = (struct varlena *) DatumGetPointer(PG_GETARG_DATUM(0));
+
+	if (!VARATT_IS_EXTERNAL_ONDISK(attr))
+		PG_RETURN_NULL();
+
+	VARATT_EXTERNAL_GET_POINTER(toast_pointer, attr);
+
+	PG_RETURN_OID(toast_pointer.va_valueid);
+}
+
 /*
  * string_agg - Concatenates values and returns string.
  *
diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat
index 291ed876fc..443ca854a6 100644
--- a/src/include/catalog/pg_proc.dat
+++ b/src/include/catalog/pg_proc.dat
@@ -7447,6 +7447,9 @@
 { oid => '2121', descr => 'compression method for the compressed datum',
   proname => 'pg_column_compression', provolatile => 's', prorettype => 'text',
   proargtypes => 'any', prosrc => 'pg_column_compression' },
+{ oid => '8393', descr => 'chunk ID of on-disk TOASTed value',
+  proname => 'pg_column_toast_chunk_id', provolatile => 's', prorettype => 'oid',
+  proargtypes => 'any', prosrc => 'pg_column_toast_chunk_id' },
 { oid => '2322',
   descr => 'total disk space usage for the specified tablespace',
   proname => 'pg_tablespace_size', provolatile => 'v', prorettype => 'int8',
diff --git a/src/test/regress/expected/misc_functions.out b/src/test/regress/expected/misc_functions.out
index d5f61dfad9..e0ba9fdafa 100644
--- a/src/test/regress/expected/misc_functions.out
+++ b/src/test/regress/expected/misc_functions.out
@@ -703,3 +703,19 @@ SELECT has_function_privilege('regress_current_logfile',
 (1 row)
 
 DROP ROLE regress_current_logfile;
+-- pg_column_toast_chunk_id
+CREATE TABLE test_chunk_id (a TEXT, b TEXT STORAGE EXTERNAL);
+INSERT INTO test_chunk_id VALUES ('x', repeat('x', 8192));
+SELECT t.relname AS toastrel FROM pg_class c
+  LEFT JOIN pg_class t ON c.reltoastrelid = t.oid
+  WHERE c.relname = 'test_chunk_id'
+\gset
+SELECT pg_column_toast_chunk_id(a) IS NULL,
+  pg_column_toast_chunk_id(b) IN (SELECT chunk_id FROM pg_toast.:toastrel)
+  FROM test_chunk_id;
+ ?column? | ?column? 
+----------+----------
+ t        | t
+(1 row)
+
+DROP TABLE test_chunk_id;
diff --git a/src/test/regress/sql/misc_functions.sql b/src/test/regress/sql/misc_functions.sql
index 928b04db7f..ff5ed5edde 100644
--- a/src/test/regress/sql/misc_functions.sql
+++ b/src/test/regress/sql/misc_functions.sql
@@ -265,3 +265,15 @@ GRANT pg_monitor TO regress_current_logfile;
 SELECT has_function_privilege('regress_current_logfile',
   'pg_current_logfile()', 'EXECUTE');
 DROP ROLE regress_current_logfile;
+
+-- pg_column_toast_chunk_id
+CREATE TABLE test_chunk_id (a TEXT, b TEXT STORAGE EXTERNAL);
+INSERT INTO test_chunk_id VALUES ('x', repeat('x', 8192));
+SELECT t.relname AS toastrel FROM pg_class c
+  LEFT JOIN pg_class t ON c.reltoastrelid = t.oid
+  WHERE c.relname = 'test_chunk_id'
+\gset
+SELECT pg_column_toast_chunk_id(a) IS NULL,
+  pg_column_toast_chunk_id(b) IN (SELECT chunk_id FROM pg_toast.:toastrel)
+  FROM test_chunk_id;
+DROP TABLE test_chunk_id;
-- 
2.25.1


--IJpNTDwzlM2Ie8A6--