Support "expanded" objects, particularly arrays, for better performance.

This patch introduces the ability for complex datatypes to have an
in-memory representation that is different from their on-disk format.
On-disk formats are typically optimized for minimal size, and in any case
they can't contain pointers, so they are often not well-suited for
computation.  Now a datatype can invent an "expanded" in-memory format
that is better suited for its operations, and then pass that around among
the C functions that operate on the datatype.  There are also provisions
(rudimentary as yet) to allow an expanded object to be modified in-place
under suitable conditions, so that operations like assignment to an element
of an array need not involve copying the entire array.

The initial application for this feature is arrays, but it is not hard
to foresee using it for other container types like JSON, XML and hstore.
I have hopes that it will be useful to PostGIS as well.

In this initial implementation, a few heuristics have been hard-wired
into plpgsql to improve performance for arrays that are stored in
plpgsql variables.  We would like to generalize those hacks so that
other datatypes can obtain similar improvements, but figuring out some
appropriate APIs is left as a task for future work.  (The heuristics
themselves are probably not optimal yet, either, as they sometimes
force expansion of arrays that would be better left alone.)

Preliminary performance testing shows impressive speed gains for plpgsql
functions that do element-by-element access or update of large arrays.
There are other cases that get a little slower, as a result of added array
format conversions; but we can hope to improve anything that's annoyingly
bad.  In any case most applications should see a net win.

Tom Lane, reviewed by Andres Freund

1 files changed, 30 insertions, 0 deletions

diff --git a/src/include/postgres.h b/src/include/postgres.h
index be37313fa5a..ccf1605455e 100644
--- a/src/include/postgres.h
+++ b/src/include/postgres.h
@@ -88,6 +88,23 @@ typedef struct varatt_indirect
 }	varatt_indirect;
 
 /*
+ * struct varatt_expanded is a "TOAST pointer" representing an out-of-line
+ * Datum that is stored in memory, in some type-specific, not necessarily
+ * physically contiguous format that is convenient for computation not
+ * storage.  APIs for this, in particular the definition of struct
+ * ExpandedObjectHeader, are in src/include/utils/expandeddatum.h.
+ *
+ * Note that just as for struct varatt_external, this struct is stored
+ * unaligned within any containing tuple.
+ */
+typedef struct ExpandedObjectHeader ExpandedObjectHeader;
+
+typedef struct varatt_expanded
+{
+	ExpandedObjectHeader *eohptr;
+} varatt_expanded;
+
+/*
  * Type tag for the various sorts of "TOAST pointer" datums.  The peculiar
  * value for VARTAG_ONDISK comes from a requirement for on-disk compatibility
  * with a previous notion that the tag field was the pointer datum's length.
@@ -95,11 +112,18 @@ typedef struct varatt_indirect
 typedef enum vartag_external
 {
 	VARTAG_INDIRECT = 1,
+	VARTAG_EXPANDED_RO = 2,
+	VARTAG_EXPANDED_RW = 3,
 	VARTAG_ONDISK = 18
 } vartag_external;
 
+/* this test relies on the specific tag values above */
+#define VARTAG_IS_EXPANDED(tag) \
+	(((tag) & ~1) == VARTAG_EXPANDED_RO)
+
 #define VARTAG_SIZE(tag) \
 	((tag) == VARTAG_INDIRECT ? sizeof(varatt_indirect) : \
+	 VARTAG_IS_EXPANDED(tag) ? sizeof(varatt_expanded) : \
 	 (tag) == VARTAG_ONDISK ? sizeof(varatt_external) : \
 	 TrapMacro(true, "unrecognized TOAST vartag"))
 
@@ -294,6 +318,12 @@ typedef struct
 	(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_EXTERNAL_EXPANDED_RO(PTR) \
+	(VARATT_IS_EXTERNAL(PTR) && VARTAG_EXTERNAL(PTR) == VARTAG_EXPANDED_RO)
+#define VARATT_IS_EXTERNAL_EXPANDED_RW(PTR) \
+	(VARATT_IS_EXTERNAL(PTR) && VARTAG_EXTERNAL(PTR) == VARTAG_EXPANDED_RW)
+#define VARATT_IS_EXTERNAL_EXPANDED(PTR) \
+	(VARATT_IS_EXTERNAL(PTR) && VARTAG_IS_EXPANDED(VARTAG_EXTERNAL(PTR)))
 #define VARATT_IS_SHORT(PTR)				VARATT_IS_1B(PTR)
 #define VARATT_IS_EXTENDED(PTR)				(!VARATT_IS_4B_U(PTR))