Add support for multiple kinds of external toast datums.

To that end, support tags rather than lengths for external datums. As an example of how this can be used, add support or "indirect" tuples which point to some externally allocated memory containing a toast tuple. Similar infrastructure could be used for other purposes, including, perhaps, support for alternative compression algorithms. Andres Freund, reviewed by Hitoshi Harada and myself
12 years ago · 3682025015
parent 148326b994
commit 3682025015
10 changed files with 472 additions and 43 deletions
--- a/src/backend/access/heap/tuptoaster.c
+++ b/src/backend/access/heap/tuptoaster.c
@ -44,9 +44,6 @@

 #undef TOAST_DEBUG

-/* Size of an EXTERNAL datum that contains a standard TOAST pointer */
-#define TOAST_POINTER_SIZE (VARHDRSZ_EXTERNAL + sizeof(struct varatt_external))
-
 /*
 * Testing whether an externally-stored value is compressed now requires
 * comparing extsize (the actual length of the external data) to rawsize
@ -87,11 +84,11 @@ static struct varlena *toast_fetch_datum_slice(struct varlena * attr,
 * heap_tuple_fetch_attr -
 *
 *	Public entry point to get back a toasted value from
- *	external storage (possibly still in compressed format).
+ *	external source (possibly still in compressed format).
 *
 * This will return a datum that contains all the data internally, ie, not
- * relying on external storage, but it can still be compressed or have a short
- * header.
+ * relying on external storage or memory, but it can still be compressed or
+ * have a short header.
 ----------
 */
 struct varlena *
@ -99,13 +96,35 @@ heap_tuple_fetch_attr(struct varlena * attr)
 {
 	struct varlena *result;

-	if (VARATT_IS_EXTERNAL(attr))
+	if (VARATT_IS_EXTERNAL_ONDISK(attr))
 	{
 		/*
 		 * This is an external stored plain value
 		 */
 		result = toast_fetch_datum(attr);
 	}
+	else if (VARATT_IS_EXTERNAL_INDIRECT(attr))
+	{
+		/*
+		 * copy into the caller's memory context. That's not required in all
+		 * cases but sufficient for now since this is mainly used when we need
+		 * to persist a Datum for unusually long time, like in a HOLD cursor.
+		 */
+		struct varatt_indirect redirect;
+		VARATT_EXTERNAL_GET_POINTER(redirect, attr);
+		attr = (struct varlena *)redirect.pointer;
+
+		/* nested indirect Datums aren't allowed */
+		Assert(!VARATT_IS_EXTERNAL_INDIRECT(attr));
+
+		/* doesn't make much sense, but better handle it */
+		if (VARATT_IS_EXTERNAL_ONDISK(attr))
+			return heap_tuple_fetch_attr(attr);
+
+		/* copy datum verbatim */
+		result = (struct varlena *) palloc(VARSIZE_ANY(attr));
+		memcpy(result, attr, VARSIZE_ANY(attr));
+	}
 	else
 	{
 		/*
@ -128,7 +147,7 @@ heap_tuple_fetch_attr(struct varlena * attr)
 struct varlena *
 heap_tuple_untoast_attr(struct varlena * attr)
 {
-	if (VARATT_IS_EXTERNAL(attr))
+	if (VARATT_IS_EXTERNAL_ONDISK(attr))
 	{
 		/*
 		 * This is an externally stored datum --- fetch it back from there
@ -145,6 +164,17 @@ heap_tuple_untoast_attr(struct varlena * attr)
 			pfree(tmp);
 		}
 	}
+	else if (VARATT_IS_EXTERNAL_INDIRECT(attr))
+	{
+		struct varatt_indirect redirect;
+		VARATT_EXTERNAL_GET_POINTER(redirect, attr);
+		attr = (struct varlena *)redirect.pointer;
+
+		/* nested indirect Datums aren't allowed */
+		Assert(!VARATT_IS_EXTERNAL_INDIRECT(attr));
+
+		attr = heap_tuple_untoast_attr(attr);
+	}
 	else if (VARATT_IS_COMPRESSED(attr))
 	{
 		/*
@ -191,7 +221,7 @@ heap_tuple_untoast_attr_slice(struct varlena * attr,
 	char	   *attrdata;
 	int32		attrsize;

-	if (VARATT_IS_EXTERNAL(attr))
+	if (VARATT_IS_EXTERNAL_ONDISK(attr))
 	{
 		struct varatt_external toast_pointer;

@ -204,6 +234,17 @@ heap_tuple_untoast_attr_slice(struct varlena * attr,
 		/* fetch it back (compressed marker will get set automatically) */
 		preslice = toast_fetch_datum(attr);
 	}
+	else if (VARATT_IS_EXTERNAL_INDIRECT(attr))
+	{
+		struct varatt_indirect redirect;
+		VARATT_EXTERNAL_GET_POINTER(redirect, attr);
+
+		/* nested indirect Datums aren't allowed */
+		Assert(!VARATT_IS_EXTERNAL_INDIRECT(redirect.pointer));
+
+		return heap_tuple_untoast_attr_slice(redirect.pointer,
+											 sliceoffset, slicelength);
+	}
 	else
 		preslice = attr;

@ -267,7 +308,7 @@ toast_raw_datum_size(Datum value)
 	struct varlena *attr = (struct varlena *) DatumGetPointer(value);
 	Size		result;

-	if (VARATT_IS_EXTERNAL(attr))
+	if (VARATT_IS_EXTERNAL_ONDISK(attr))
 	{
 		/* va_rawsize is the size of the original datum -- including header */
 		struct varatt_external toast_pointer;
@ -275,6 +316,16 @@ toast_raw_datum_size(Datum value)
 		VARATT_EXTERNAL_GET_POINTER(toast_pointer, attr);
 		result = toast_pointer.va_rawsize;
 	}
+	else if (VARATT_IS_EXTERNAL_INDIRECT(attr))
+	{
+		struct varatt_indirect toast_pointer;
+		VARATT_EXTERNAL_GET_POINTER(toast_pointer, attr);
+
+		/* nested indirect Datums aren't allowed */
+		Assert(!VARATT_IS_EXTERNAL_INDIRECT(toast_pointer.pointer));
+
+		return toast_raw_datum_size(PointerGetDatum(toast_pointer.pointer));
+	}
 	else if (VARATT_IS_COMPRESSED(attr))
 	{
 		/* here, va_rawsize is just the payload size */
@ -308,7 +359,7 @@ toast_datum_size(Datum value)
 	struct varlena *attr = (struct varlena *) DatumGetPointer(value);
 	Size		result;

-	if (VARATT_IS_EXTERNAL(attr))
+	if (VARATT_IS_EXTERNAL_ONDISK(attr))
 	{
 		/*
 		 * Attribute is stored externally - return the extsize whether
@ -320,6 +371,16 @@ toast_datum_size(Datum value)
 		VARATT_EXTERNAL_GET_POINTER(toast_pointer, attr);
 		result = toast_pointer.va_extsize;
 	}
+	else if (VARATT_IS_EXTERNAL_INDIRECT(attr))
+	{
+		struct varatt_indirect toast_pointer;
+		VARATT_EXTERNAL_GET_POINTER(toast_pointer, attr);
+
+		/* nested indirect Datums aren't allowed */
+		Assert(!VARATT_IS_EXTERNAL_INDIRECT(attr));
+
+		return toast_datum_size(PointerGetDatum(toast_pointer.pointer));
+	}
 	else if (VARATT_IS_SHORT(attr))
 	{
 		result = VARSIZE_SHORT(attr);
@ -387,8 +448,12 @@ toast_delete(Relation rel, HeapTuple oldtup)
 		{
 			Datum		value = toast_values[i];

-			if (!toast_isnull[i] && VARATT_IS_EXTERNAL(PointerGetDatum(value)))
+			if (toast_isnull[i])
+				continue;
+			else if (VARATT_IS_EXTERNAL_ONDISK(PointerGetDatum(value)))
 				toast_delete_datum(rel, value);
+			else if (VARATT_IS_EXTERNAL_INDIRECT(PointerGetDatum(value)))
+				elog(ERROR, "attempt to delete tuple containing indirect datums");
 		}
 	}
 }
@ -490,13 +555,13 @@ toast_insert_or_update(Relation rel, HeapTuple newtup, HeapTuple oldtup,
 			new_value = (struct varlena *) DatumGetPointer(toast_values[i]);

 			/*
-			 * If the old value is an external stored one, check if it has
-			 * changed so we have to delete it later.
+			 * If the old value is stored on disk, check if it has changed so
+			 * we have to delete it later.
 			 */
 			if (att[i]->attlen == -1 && !toast_oldisnull[i] &&
-				VARATT_IS_EXTERNAL(old_value))
+				VARATT_IS_EXTERNAL_ONDISK(old_value))
 			{
-				if (toast_isnull[i] || !VARATT_IS_EXTERNAL(new_value) ||
+				if (toast_isnull[i] || !VARATT_IS_EXTERNAL_ONDISK(new_value) ||
 					memcmp((char *) old_value, (char *) new_value,
 						   VARSIZE_EXTERNAL(old_value)) != 0)
 				{
@ -1258,6 +1323,8 @@ toast_save_datum(Relation rel, Datum value,
 	int32		data_todo;
 	Pointer		dval = DatumGetPointer(value);

+	Assert(!VARATT_IS_EXTERNAL(value));
+
 	/*
 	 * Open the toast relation and its index.  We can use the index to check
 	 * uniqueness of the OID we assign to the toasted item, even though it has
@ -1341,7 +1408,7 @@ toast_save_datum(Relation rel, Datum value,
 		{
 			struct varatt_external old_toast_pointer;

-			Assert(VARATT_IS_EXTERNAL(oldexternal));
+			Assert(VARATT_IS_EXTERNAL_ONDISK(oldexternal));
 			/* Must copy to access aligned fields */
 			VARATT_EXTERNAL_GET_POINTER(old_toast_pointer, oldexternal);
 			if (old_toast_pointer.va_toastrelid == rel->rd_toastoid)
@ -1456,7 +1523,7 @@ toast_save_datum(Relation rel, Datum value,
 	 * Create the TOAST pointer value that we'll return
 	 */
 	result = (struct varlena *) palloc(TOAST_POINTER_SIZE);
-	SET_VARSIZE_EXTERNAL(result, TOAST_POINTER_SIZE);
+	SET_VARTAG_EXTERNAL(result, VARTAG_ONDISK);
 	memcpy(VARDATA_EXTERNAL(result), &toast_pointer, sizeof(toast_pointer));

 	return PointerGetDatum(result);
@ -1480,7 +1547,7 @@ toast_delete_datum(Relation rel, Datum value)
 	SysScanDesc toastscan;
 	HeapTuple	toasttup;

-	if (!VARATT_IS_EXTERNAL(attr))
+	if (!VARATT_IS_EXTERNAL_ONDISK(attr))
 		return;

 	/* Must copy to access aligned fields */
@ -1608,6 +1675,9 @@ toast_fetch_datum(struct varlena * attr)
 	char	   *chunkdata;
 	int32		chunksize;

+	if (VARATT_IS_EXTERNAL_INDIRECT(attr))
+		elog(ERROR, "shouldn't be called for indirect tuples");
+
 	/* Must copy to access aligned fields */
 	VARATT_EXTERNAL_GET_POINTER(toast_pointer, attr);

@ -1775,7 +1845,7 @@ toast_fetch_datum_slice(struct varlena * attr, int32 sliceoffset, int32 length)
 	int32		chcpystrt;
 	int32		chcpyend;

-	Assert(VARATT_IS_EXTERNAL(attr));
+	Assert(VARATT_IS_EXTERNAL_ONDISK(attr));

 	/* Must copy to access aligned fields */
 	VARATT_EXTERNAL_GET_POINTER(toast_pointer, attr);
--- a/src/include/access/tuptoaster.h
+++ b/src/include/access/tuptoaster.h
@ -94,6 +94,11 @@
 	 sizeof(int32) -									\
 	 VARHDRSZ)

+/* Size of an EXTERNAL datum that contains a standard TOAST pointer */
+#define TOAST_POINTER_SIZE (VARHDRSZ_EXTERNAL + sizeof(struct varatt_external))
+
+/* Size of an indirect datum that contains an indirect TOAST pointer */
+#define INDIRECT_POINTER_SIZE (VARHDRSZ_EXTERNAL + sizeof(struct varatt_indirect))

 /* ----------
 * toast_insert_or_update -
--- a/src/include/postgres.h
+++ b/src/include/postgres.h
@ -54,23 +54,53 @@
 */

 /*
- * struct varatt_external is a "TOAST pointer", that is, the information
- * needed to fetch a stored-out-of-line Datum.	The data is compressed
- * if and only if va_extsize < va_rawsize - VARHDRSZ.  This struct must not
- * contain any padding, because we sometimes compare pointers using memcmp.
+ * struct varatt_external is a "TOAST pointer", that is, the information needed
+ * to fetch a Datum stored in an out-of-line on-disk Datum. The data is
+ * compressed if and only if va_extsize < va_rawsize - VARHDRSZ.  This struct
+ * must not contain any padding, because we sometimes compare pointers using
+ * memcmp.
 *
 * Note that this information is stored unaligned within actual tuples, so
 * you need to memcpy from the tuple into a local struct variable before
 * you can look at these fields!  (The reason we use memcmp is to avoid
 * having to do that just to detect equality of two TOAST pointers...)
 */
-struct varatt_external
+typedef struct varatt_external
 {
 	int32		va_rawsize;		/* Original data size (includes header) */
 	int32		va_extsize;		/* External saved size (doesn't) */
 	Oid			va_valueid;		/* Unique ID of value within TOAST table */
 	Oid			va_toastrelid;	/* RelID of TOAST table containing it */
-};
+} varatt_external;
+
+/*
+ * Out-of-line Datum thats stored in memory in contrast to varatt_external
+ * pointers which points to data in an external toast relation.
+ *
+ * Note that just as varatt_external's this is stored unaligned within the
+ * tuple.
+ */
+typedef struct varatt_indirect
+{
+	struct varlena *pointer;	/* Pointer to in-memory varlena */
+} varatt_indirect;
+
+
+/*
+ * Type of external toast datum stored. The peculiar value for VARTAG_ONDISK
+ * comes from the requirement for on-disk compatibility with the older
+ * definitions of varattrib_1b_e where v_tag was named va_len_1be...
+ */
+typedef enum vartag_external
+{
+	VARTAG_INDIRECT = 1,
+	VARTAG_ONDISK = 18
+} vartag_external;
+
+#define VARTAG_SIZE(tag) \
+	((tag) == VARTAG_INDIRECT ? sizeof(varatt_indirect) :		\
+	 (tag) == VARTAG_ONDISK ? sizeof(varatt_external) : \
+	 TrapMacro(true, "unknown vartag"))

 /*
 * These structs describe the header of a varlena object that may have been
@ -102,11 +132,12 @@ typedef struct
 	char		va_data[1];		/* Data begins here */
 } varattrib_1b;

+/* inline portion of a short varlena pointing to an external resource */
 typedef struct
 {
 	uint8		va_header;		/* Always 0x80 or 0x01 */
-	uint8		va_len_1be;		/* Physical length of datum */
-	char		va_data[1];		/* Data (for now always a TOAST pointer) */
+	uint8		va_tag;			/* Type of datum */
+	char		va_data[1];		/* Data (of the type indicated by va_tag) */
 } varattrib_1b_e;

 /*
@ -130,6 +161,9 @@ typedef struct
 * first byte.	Also, it is not possible for a 1-byte length word to be zero;
 * this lets us disambiguate alignment padding bytes from the start of an
 * unaligned datum.  (We now *require* pad bytes to be filled with zero!)
+ *
+ * In TOAST datums the tag field in varattrib_1b_e is used to discern whether
+ * its an indirection pointer or more commonly an on-disk tuple.
 */

 /*
@ -161,8 +195,8 @@ typedef struct
 	(((varattrib_4b *) (PTR))->va_4byte.va_header & 0x3FFFFFFF)
 #define VARSIZE_1B(PTR) \
 	(((varattrib_1b *) (PTR))->va_header & 0x7F)
-#define VARSIZE_1B_E(PTR) \
-	(((varattrib_1b_e *) (PTR))->va_len_1be)
+#define VARTAG_1B_E(PTR) \
+	(((varattrib_1b_e *) (PTR))->va_tag)

 #define SET_VARSIZE_4B(PTR,len) \
 	(((varattrib_4b *) (PTR))->va_4byte.va_header = (len) & 0x3FFFFFFF)
@ -170,9 +204,9 @@ typedef struct
 	(((varattrib_4b *) (PTR))->va_4byte.va_header = ((len) & 0x3FFFFFFF) | 0x40000000)
 #define SET_VARSIZE_1B(PTR,len) \
 	(((varattrib_1b *) (PTR))->va_header = (len) | 0x80)
-#define SET_VARSIZE_1B_E(PTR,len) \
+#define SET_VARTAG_1B_E(PTR,tag) \
 	(((varattrib_1b_e *) (PTR))->va_header = 0x80, \
-	 ((varattrib_1b_e *) (PTR))->va_len_1be = (len))
+	 ((varattrib_1b_e *) (PTR))->va_tag = (tag))
 #else							/* !WORDS_BIGENDIAN */

 #define VARATT_IS_4B(PTR) \
@ -193,8 +227,8 @@ typedef struct
 	((((varattrib_4b *) (PTR))->va_4byte.va_header >> 2) & 0x3FFFFFFF)
 #define VARSIZE_1B(PTR) \
 	((((varattrib_1b *) (PTR))->va_header >> 1) & 0x7F)
-#define VARSIZE_1B_E(PTR) \
-	(((varattrib_1b_e *) (PTR))->va_len_1be)
+#define VARTAG_1B_E(PTR) \
+	(((varattrib_1b_e *) (PTR))->va_tag)

 #define SET_VARSIZE_4B(PTR,len) \
 	(((varattrib_4b *) (PTR))->va_4byte.va_header = (((uint32) (len)) << 2))
@ -202,12 +236,12 @@ typedef struct
 	(((varattrib_4b *) (PTR))->va_4byte.va_header = (((uint32) (len)) << 2) | 0x02)
 #define SET_VARSIZE_1B(PTR,len) \
 	(((varattrib_1b *) (PTR))->va_header = (((uint8) (len)) << 1) | 0x01)
-#define SET_VARSIZE_1B_E(PTR,len) \
+#define SET_VARTAG_1B_E(PTR,tag) \
 	(((varattrib_1b_e *) (PTR))->va_header = 0x01, \
-	 ((varattrib_1b_e *) (PTR))->va_len_1be = (len))
+	 ((varattrib_1b_e *) (PTR))->va_tag = (tag))
 #endif   /* WORDS_BIGENDIAN */

-#define VARHDRSZ_SHORT			1
+#define VARHDRSZ_SHORT			offsetof(varattrib_1b, va_data)
 #define VARATT_SHORT_MAX		0x7F
 #define VARATT_CAN_MAKE_SHORT(PTR) \
 	(VARATT_IS_4B_U(PTR) && \
@ -215,7 +249,7 @@ typedef struct
 #define VARATT_CONVERTED_SHORT_SIZE(PTR) \
 	(VARSIZE(PTR) - VARHDRSZ + VARHDRSZ_SHORT)

-#define VARHDRSZ_EXTERNAL		2
+#define VARHDRSZ_EXTERNAL		offsetof(varattrib_1b_e, va_data)

 #define VARDATA_4B(PTR)		(((varattrib_4b *) (PTR))->va_4byte.va_data)
 #define VARDATA_4B_C(PTR)	(((varattrib_4b *) (PTR))->va_compressed.va_data)
@ -249,26 +283,32 @@ typedef struct
 #define VARSIZE_SHORT(PTR)					VARSIZE_1B(PTR)
 #define VARDATA_SHORT(PTR)					VARDATA_1B(PTR)

-#define VARSIZE_EXTERNAL(PTR)				VARSIZE_1B_E(PTR)
+#define VARTAG_EXTERNAL(PTR)				VARTAG_1B_E(PTR)
+#define VARSIZE_EXTERNAL(PTR)				(VARHDRSZ_EXTERNAL + VARTAG_SIZE(VARTAG_EXTERNAL(PTR)))
 #define VARDATA_EXTERNAL(PTR)				VARDATA_1B_E(PTR)

 #define VARATT_IS_COMPRESSED(PTR)			VARATT_IS_4B_C(PTR)
 #define VARATT_IS_EXTERNAL(PTR)				VARATT_IS_1B_E(PTR)
+#define VARATT_IS_EXTERNAL_ONDISK(PTR) \
+	(VARATT_IS_EXTERNAL(PTR) && VARTAG_EXTERNAL(PTR) == VARTAG_ONDISK)
+#define VARATT_IS_EXTERNAL_INDIRECT(PTR) \
+	(VARATT_IS_EXTERNAL(PTR) && VARTAG_EXTERNAL(PTR) == VARTAG_INDIRECT)
 #define VARATT_IS_SHORT(PTR)				VARATT_IS_1B(PTR)
 #define VARATT_IS_EXTENDED(PTR)				(!VARATT_IS_4B_U(PTR))

 #define SET_VARSIZE(PTR, len)				SET_VARSIZE_4B(PTR, len)
 #define SET_VARSIZE_SHORT(PTR, len)			SET_VARSIZE_1B(PTR, len)
 #define SET_VARSIZE_COMPRESSED(PTR, len)	SET_VARSIZE_4B_C(PTR, len)
-#define SET_VARSIZE_EXTERNAL(PTR, len)		SET_VARSIZE_1B_E(PTR, len)
+
+#define SET_VARTAG_EXTERNAL(PTR, tag)		SET_VARTAG_1B_E(PTR, tag)

 #define VARSIZE_ANY(PTR) \
-	(VARATT_IS_1B_E(PTR) ? VARSIZE_1B_E(PTR) : \
+	(VARATT_IS_1B_E(PTR) ? VARSIZE_EXTERNAL(PTR) : \
 	 (VARATT_IS_1B(PTR) ? VARSIZE_1B(PTR) : \
 	  VARSIZE_4B(PTR)))

 #define VARSIZE_ANY_EXHDR(PTR) \
-	(VARATT_IS_1B_E(PTR) ? VARSIZE_1B_E(PTR)-VARHDRSZ_EXTERNAL : \
+	(VARATT_IS_1B_E(PTR) ? VARSIZE_EXTERNAL(PTR)-VARHDRSZ_EXTERNAL : \
 	 (VARATT_IS_1B(PTR) ? VARSIZE_1B(PTR)-VARHDRSZ_SHORT : \
 	  VARSIZE_4B(PTR)-VARHDRSZ))

--- a/src/test/regress/expected/indirect_toast.out
+++ b/src/test/regress/expected/indirect_toast.out
@ -0,0 +1,151 @@
+CREATE TABLE toasttest(descr text, cnt int DEFAULT 0, f1 text, f2 text);
+INSERT INTO toasttest(descr, f1, f2) VALUES('two-compressed', repeat('1234567890',1000), repeat('1234567890',1000));
+INSERT INTO toasttest(descr, f1, f2) VALUES('two-toasted', repeat('1234567890',30000), repeat('1234567890',50000));
+INSERT INTO toasttest(descr, f1, f2) VALUES('one-compressed,one-null', NULL, repeat('1234567890',1000));
+INSERT INTO toasttest(descr, f1, f2) VALUES('one-toasted,one-null', NULL, repeat('1234567890',50000));
+-- check whether indirect tuples works on the most basic level
+SELECT descr, substring(make_tuple_indirect(toasttest)::text, 1, 200) FROM toasttest;
+          descr          |                                                                                                substring                                                                                                 
+-------------------------+----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------
+ two-compressed          | (two-compressed,0,12345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012
+ two-toasted             | (two-toasted,0,12345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345
+ one-compressed,one-null | ("one-compressed,one-null",0,,12345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890
+ one-toasted,one-null    | ("one-toasted,one-null",0,,12345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123
+(4 rows)
+
+-- modification without changing varlenas
+UPDATE toasttest SET cnt = cnt +1 RETURNING substring(toasttest::text, 1, 200);
+                                                                                                substring                                                                                                 
+----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------
+ (two-compressed,1,12345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012
+ (two-toasted,1,12345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345
+ ("one-compressed,one-null",1,,12345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890
+ ("one-toasted,one-null",1,,12345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123
+(4 rows)
+
+-- modification without modifying asigned value
+UPDATE toasttest SET cnt = cnt +1, f1 = f1 RETURNING substring(toasttest::text, 1, 200);
+                                                                                                substring                                                                                                 
+----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------
+ (two-compressed,2,12345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012
+ (two-toasted,2,12345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345
+ ("one-compressed,one-null",2,,12345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890
+ ("one-toasted,one-null",2,,12345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123
+(4 rows)
+
+-- modification modifying, but effectively not changing
+UPDATE toasttest SET cnt = cnt +1, f1 = f1||'' RETURNING substring(toasttest::text, 1, 200);
+                                                                                                substring                                                                                                 
+----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------
+ (two-compressed,3,12345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012
+ (two-toasted,3,12345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345
+ ("one-compressed,one-null",3,,12345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890
+ ("one-toasted,one-null",3,,12345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123
+(4 rows)
+
+UPDATE toasttest SET cnt = cnt +1, f1 = '-'||f1||'-' RETURNING substring(toasttest::text, 1, 200);
+                                                                                                substring                                                                                                 
+----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------
+ (two-compressed,4,-1234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901
+ (two-toasted,4,-1234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234
+ ("one-compressed,one-null",4,,12345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890
+ ("one-toasted,one-null",4,,12345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123
+(4 rows)
+
+SELECT substring(toasttest::text, 1, 200) FROM toasttest;
+                                                                                                substring                                                                                                 
+----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------
+ (two-compressed,4,-1234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901
+ (two-toasted,4,-1234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234
+ ("one-compressed,one-null",4,,12345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890
+ ("one-toasted,one-null",4,,12345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123
+(4 rows)
+
+-- check we didn't screw with main/toast tuple visiblity
+VACUUM FREEZE toasttest;
+SELECT substring(toasttest::text, 1, 200) FROM toasttest;
+                                                                                                substring                                                                                                 
+----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------
+ (two-compressed,4,-1234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901
+ (two-toasted,4,-1234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234
+ ("one-compressed,one-null",4,,12345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890
+ ("one-toasted,one-null",4,,12345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123
+(4 rows)
+
+-- now create a trigger that forces all Datums to be indirect ones
+CREATE FUNCTION update_using_indirect()
+        RETURNS trigger
+        LANGUAGE plpgsql AS $$
+BEGIN
+    NEW := make_tuple_indirect(NEW);
+    RETURN NEW;
+END$$;
+CREATE TRIGGER toasttest_update_indirect
+        BEFORE INSERT OR UPDATE
+        ON toasttest
+        FOR EACH ROW
+        EXECUTE PROCEDURE update_using_indirect();
+-- modification without changing varlenas
+UPDATE toasttest SET cnt = cnt +1 RETURNING substring(toasttest::text, 1, 200);
+                                                                                                substring                                                                                                 
+----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------
+ (two-compressed,5,-1234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901
+ (two-toasted,5,-1234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234
+ ("one-compressed,one-null",5,,12345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890
+ ("one-toasted,one-null",5,,12345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123
+(4 rows)
+
+-- modification without modifying asigned value
+UPDATE toasttest SET cnt = cnt +1, f1 = f1 RETURNING substring(toasttest::text, 1, 200);
+                                                                                                substring                                                                                                 
+----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------
+ (two-compressed,6,-1234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901
+ (two-toasted,6,-1234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234
+ ("one-compressed,one-null",6,,12345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890
+ ("one-toasted,one-null",6,,12345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123
+(4 rows)
+
+-- modification modifying, but effectively not changing
+UPDATE toasttest SET cnt = cnt +1, f1 = f1||'' RETURNING substring(toasttest::text, 1, 200);
+                                                                                                substring                                                                                                 
+----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------
+ (two-compressed,7,-1234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901
+ (two-toasted,7,-1234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234
+ ("one-compressed,one-null",7,,12345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890
+ ("one-toasted,one-null",7,,12345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123
+(4 rows)
+
+UPDATE toasttest SET cnt = cnt +1, f1 = '-'||f1||'-' RETURNING substring(toasttest::text, 1, 200);
+                                                                                                substring                                                                                                 
+----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------
+ (two-compressed,8,--123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890
+ (two-toasted,8,--123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123
+ ("one-compressed,one-null",8,,12345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890
+ ("one-toasted,one-null",8,,12345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123
+(4 rows)
+
+INSERT INTO toasttest(descr, f1, f2) VALUES('one-toasted,one-null, via indirect', repeat('1234567890',30000), NULL);
+SELECT substring(toasttest::text, 1, 200) FROM toasttest;
+                                                                                                substring                                                                                                 
+----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------
+ (two-compressed,8,--123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890
+ (two-toasted,8,--123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123
+ ("one-compressed,one-null",8,,12345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890
+ ("one-toasted,one-null",8,,12345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123
+ ("one-toasted,one-null, via indirect",0,1234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890
+(5 rows)
+
+-- check we didn't screw with main/toast tuple visiblity
+VACUUM FREEZE toasttest;
+SELECT substring(toasttest::text, 1, 200) FROM toasttest;
+                                                                                                substring                                                                                                 
+----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------
+ (two-compressed,8,--123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890
+ (two-toasted,8,--123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123
+ ("one-compressed,one-null",8,,12345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890
+ ("one-toasted,one-null",8,,12345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123
+ ("one-toasted,one-null, via indirect",0,1234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890
+(5 rows)
+
+DROP TABLE toasttest;
+DROP FUNCTION update_using_indirect();
--- a/src/test/regress/input/create_function_1.source
+++ b/src/test/regress/input/create_function_1.source
@ -52,6 +52,11 @@ CREATE FUNCTION set_ttdummy (int4)
        AS '@libdir@/regress@DLSUFFIX@'
        LANGUAGE C STRICT;

+CREATE FUNCTION make_tuple_indirect (record)
+        RETURNS record
+        AS '@libdir@/regress@DLSUFFIX@'
+        LANGUAGE C STRICT;
+
 -- Things that shouldn't work:

 CREATE FUNCTION test1 (int) RETURNS int LANGUAGE SQL
--- a/src/test/regress/output/create_function_1.source
+++ b/src/test/regress/output/create_function_1.source
@ -47,6 +47,10 @@ CREATE FUNCTION set_ttdummy (int4)
        RETURNS int4
        AS '@libdir@/regress@DLSUFFIX@'
        LANGUAGE C STRICT;
+CREATE FUNCTION make_tuple_indirect (record)
+        RETURNS record
+        AS '@libdir@/regress@DLSUFFIX@'
+        LANGUAGE C STRICT;
 -- Things that shouldn't work:
 CREATE FUNCTION test1 (int) RETURNS int LANGUAGE SQL
    AS 'SELECT ''not an integer'';';
--- a/src/test/regress/parallel_schedule
+++ b/src/test/regress/parallel_schedule
@ -98,7 +98,7 @@ test: event_trigger
 # ----------
 # Another group of parallel tests
 # ----------
-test: select_views portals_p2 foreign_key cluster dependency guc bitmapops combocid tsearch tsdicts foreign_data window xmlmap functional_deps advisory_lock json
+test: select_views portals_p2 foreign_key cluster dependency guc bitmapops combocid tsearch tsdicts foreign_data window xmlmap functional_deps advisory_lock json indirect_toast

 # ----------
 # Another group of parallel tests
--- a/src/test/regress/regress.c
+++ b/src/test/regress/regress.c
@ -7,7 +7,9 @@
 #include <float.h>
 #include <math.h>

+#include "access/htup_details.h"
 #include "access/transam.h"
+#include "access/tuptoaster.h"
 #include "access/xact.h"
 #include "catalog/pg_type.h"
 #include "commands/sequence.h"
@ -17,6 +19,8 @@
 #include "utils/builtins.h"
 #include "utils/geo_decls.h"
 #include "utils/rel.h"
+#include "utils/typcache.h"
+#include "utils/memutils.h"


 #define P_MAXDIG 12
@ -35,6 +39,7 @@ extern char *reverse_name(char *string);
 extern int	oldstyle_length(int n, text *t);
 extern Datum int44in(PG_FUNCTION_ARGS);
 extern Datum int44out(PG_FUNCTION_ARGS);
+extern Datum make_tuple_indirect(PG_FUNCTION_ARGS);

 #ifdef PG_MODULE_MAGIC
 PG_MODULE_MAGIC;
@ -737,3 +742,90 @@ int44out(PG_FUNCTION_ARGS)
 	*--walk = '\0';
 	PG_RETURN_CSTRING(result);
 }
+
+PG_FUNCTION_INFO_V1(make_tuple_indirect);
+Datum
+make_tuple_indirect(PG_FUNCTION_ARGS)
+{
+	HeapTupleHeader rec = PG_GETARG_HEAPTUPLEHEADER(0);
+	HeapTupleData tuple;
+	int			ncolumns;
+	Datum	   *values;
+	bool	   *nulls;
+
+	Oid			tupType;
+	int32		tupTypmod;
+	TupleDesc	tupdesc;
+
+	HeapTuple	newtup;
+
+	int			i;
+
+	MemoryContext old_context;
+
+	/* Extract type info from the tuple itself */
+	tupType = HeapTupleHeaderGetTypeId(rec);
+	tupTypmod = HeapTupleHeaderGetTypMod(rec);
+	tupdesc = lookup_rowtype_tupdesc(tupType, tupTypmod);
+	ncolumns = tupdesc->natts;
+
+	/* Build a temporary HeapTuple control structure */
+	tuple.t_len = HeapTupleHeaderGetDatumLength(rec);
+	ItemPointerSetInvalid(&(tuple.t_self));
+	tuple.t_tableOid = InvalidOid;
+	tuple.t_data = rec;
+
+	values = (Datum *) palloc(ncolumns * sizeof(Datum));
+	nulls = (bool *) palloc(ncolumns * sizeof(bool));
+
+	heap_deform_tuple(&tuple, tupdesc, values, nulls);
+
+	old_context = MemoryContextSwitchTo(TopTransactionContext);
+
+	for (i = 0; i < ncolumns; i++)
+	{
+		struct varlena *attr;
+		struct varlena *new_attr;
+		struct varatt_indirect redirect_pointer;
+
+		/* only work on existing, not-null varlenas */
+		if (tupdesc->attrs[i]->attisdropped ||
+			nulls[i] ||
+			tupdesc->attrs[i]->attlen != -1)
+			continue;
+
+		attr = (struct varlena *) DatumGetPointer(values[i]);
+
+		/* don't recursively indirect */
+		if (VARATT_IS_EXTERNAL_INDIRECT(attr))
+			continue;
+
+		/* copy datum, so it still lives later */
+		if (VARATT_IS_EXTERNAL_ONDISK(attr))
+			attr = heap_tuple_fetch_attr(attr);
+		else
+		{
+			struct varlena *oldattr = attr;
+			attr = palloc0(VARSIZE_ANY(oldattr));
+			memcpy(attr, oldattr, VARSIZE_ANY(oldattr));
+		}
+
+		/* build indirection Datum */
+		new_attr = (struct varlena *) palloc0(INDIRECT_POINTER_SIZE);
+		redirect_pointer.pointer = attr;
+		SET_VARTAG_EXTERNAL(new_attr, VARTAG_INDIRECT);
+		memcpy(VARDATA_EXTERNAL(new_attr), &redirect_pointer,
+			   sizeof(redirect_pointer));
+
+		values[i] = PointerGetDatum(new_attr);
+	}
+
+	newtup = heap_form_tuple(tupdesc, values, nulls);
+	pfree(values);
+	pfree(nulls);
+	ReleaseTupleDesc(tupdesc);
+
+	MemoryContextSwitchTo(old_context);
+
+	PG_RETURN_HEAPTUPLEHEADER(newtup->t_data);
+}
--- a/src/test/regress/serial_schedule
+++ b/src/test/regress/serial_schedule
@ -117,6 +117,7 @@ test: xmlmap
 test: functional_deps
 test: advisory_lock
 test: json
+test: indirect_toast
 test: plancache
 test: limit
 test: plpgsql
--- a/src/test/regress/sql/indirect_toast.sql
+++ b/src/test/regress/sql/indirect_toast.sql
@ -0,0 +1,61 @@
+CREATE TABLE toasttest(descr text, cnt int DEFAULT 0, f1 text, f2 text);
+
+INSERT INTO toasttest(descr, f1, f2) VALUES('two-compressed', repeat('1234567890',1000), repeat('1234567890',1000));
+INSERT INTO toasttest(descr, f1, f2) VALUES('two-toasted', repeat('1234567890',30000), repeat('1234567890',50000));
+INSERT INTO toasttest(descr, f1, f2) VALUES('one-compressed,one-null', NULL, repeat('1234567890',1000));
+INSERT INTO toasttest(descr, f1, f2) VALUES('one-toasted,one-null', NULL, repeat('1234567890',50000));
+
+-- check whether indirect tuples works on the most basic level
+SELECT descr, substring(make_tuple_indirect(toasttest)::text, 1, 200) FROM toasttest;
+
+-- modification without changing varlenas
+UPDATE toasttest SET cnt = cnt +1 RETURNING substring(toasttest::text, 1, 200);
+
+-- modification without modifying asigned value
+UPDATE toasttest SET cnt = cnt +1, f1 = f1 RETURNING substring(toasttest::text, 1, 200);
+
+-- modification modifying, but effectively not changing
+UPDATE toasttest SET cnt = cnt +1, f1 = f1||'' RETURNING substring(toasttest::text, 1, 200);
+
+UPDATE toasttest SET cnt = cnt +1, f1 = '-'||f1||'-' RETURNING substring(toasttest::text, 1, 200);
+
+SELECT substring(toasttest::text, 1, 200) FROM toasttest;
+-- check we didn't screw with main/toast tuple visiblity
+VACUUM FREEZE toasttest;
+SELECT substring(toasttest::text, 1, 200) FROM toasttest;
+
+-- now create a trigger that forces all Datums to be indirect ones
+CREATE FUNCTION update_using_indirect()
+        RETURNS trigger
+        LANGUAGE plpgsql AS $$
+BEGIN
+    NEW := make_tuple_indirect(NEW);
+    RETURN NEW;
+END$$;
+
+CREATE TRIGGER toasttest_update_indirect
+        BEFORE INSERT OR UPDATE
+        ON toasttest
+        FOR EACH ROW
+        EXECUTE PROCEDURE update_using_indirect();
+
+-- modification without changing varlenas
+UPDATE toasttest SET cnt = cnt +1 RETURNING substring(toasttest::text, 1, 200);
+
+-- modification without modifying asigned value
+UPDATE toasttest SET cnt = cnt +1, f1 = f1 RETURNING substring(toasttest::text, 1, 200);
+
+-- modification modifying, but effectively not changing
+UPDATE toasttest SET cnt = cnt +1, f1 = f1||'' RETURNING substring(toasttest::text, 1, 200);
+
+UPDATE toasttest SET cnt = cnt +1, f1 = '-'||f1||'-' RETURNING substring(toasttest::text, 1, 200);
+
+INSERT INTO toasttest(descr, f1, f2) VALUES('one-toasted,one-null, via indirect', repeat('1234567890',30000), NULL);
+
+SELECT substring(toasttest::text, 1, 200) FROM toasttest;
+-- check we didn't screw with main/toast tuple visiblity
+VACUUM FREEZE toasttest;
+SELECT substring(toasttest::text, 1, 200) FROM toasttest;
+
+DROP TABLE toasttest;
+DROP FUNCTION update_using_indirect();