Add sortsupport for gist_btree opclasses, for faster index builds.

Commit 16fa9b2 introduced a faster way to build GiST indexes, by
sorting all the data. This commit adds the sortsupport functions needed
to make use of that feature for btree_gist.

Author: Andrey Borodin
Discussion: https://www.postgresql.org/message-id/[email protected]

Author: hlinnaka

contrib/btree_gist/Makefile

@@ -32,7 +32,7 @@ EXTENSION = btree_gist
 DATA = btree_gist--1.0--1.1.sql \
        btree_gist--1.1--1.2.sql btree_gist--1.2.sql btree_gist--1.2--1.3.sql \
        btree_gist--1.3--1.4.sql btree_gist--1.4--1.5.sql \
-       btree_gist--1.5--1.6.sql
+       btree_gist--1.5--1.6.sql btree_gist--1.6--1.7.sql
 PGFILEDESC = "btree_gist - B-tree equivalent GiST operator classes"
 
 REGRESS = init int2 int4 int8 float4 float8 cash oid timestamp timestamptz \

contrib/btree_gist/btree_bit.c

@@ -19,6 +19,7 @@ PG_FUNCTION_INFO_V1(gbt_bit_picksplit);
 PG_FUNCTION_INFO_V1(gbt_bit_consistent);
 PG_FUNCTION_INFO_V1(gbt_bit_penalty);
 PG_FUNCTION_INFO_V1(gbt_bit_same);
+PG_FUNCTION_INFO_V1(gbt_bit_sortsupport);
 
 
 /* define for comparison */
@@ -209,3 +210,27 @@ gbt_bit_penalty(PG_FUNCTION_ARGS)
 	PG_RETURN_POINTER(gbt_var_penalty(result, o, n, PG_GET_COLLATION(),
 									  &tinfo, fcinfo->flinfo));
 }
+
+static int
+gbt_bit_sort_build_cmp(Datum a, Datum b, SortSupport ssup)
+{
+	/* Use byteacmp(), like gbt_bitcmp() does */
+	return DatumGetInt32(DirectFunctionCall2(byteacmp,
+											 PointerGetDatum(a),
+											 PointerGetDatum(b)));
+}
+
+/*
+ * Sort support routine for fast GiST index build by sorting.
+ */
+Datum
+gbt_bit_sortsupport(PG_FUNCTION_ARGS)
+{
+	SortSupport ssup = (SortSupport) PG_GETARG_POINTER(0);
+
+	ssup->comparator = gbt_bit_sort_build_cmp;
+	ssup->abbrev_converter = NULL;
+	ssup->abbrev_abort = NULL;
+	ssup->abbrev_full_comparator = NULL;
+	PG_RETURN_VOID();
+}

contrib/btree_gist/btree_bytea.c

@@ -18,6 +18,7 @@ PG_FUNCTION_INFO_V1(gbt_bytea_picksplit);
 PG_FUNCTION_INFO_V1(gbt_bytea_consistent);
 PG_FUNCTION_INFO_V1(gbt_bytea_penalty);
 PG_FUNCTION_INFO_V1(gbt_bytea_same);
+PG_FUNCTION_INFO_V1(gbt_bytea_sortsupport);
 
 
 /* define for comparison */
@@ -87,7 +88,7 @@ static const gbtree_vinfo tinfo =
 
 
 /**************************************************
- * Text ops
+ * Bytea ops
  **************************************************/
 
 
@@ -168,3 +169,26 @@ gbt_bytea_penalty(PG_FUNCTION_ARGS)
 	PG_RETURN_POINTER(gbt_var_penalty(result, o, n, PG_GET_COLLATION(),
 									  &tinfo, fcinfo->flinfo));
 }
+
+static int
+gbt_bytea_sort_build_cmp(Datum a, Datum b, SortSupport ssup)
+{
+	return DatumGetInt32(DirectFunctionCall2(byteacmp,
+											 PointerGetDatum(a),
+											 PointerGetDatum(b)));
+}
+
+/*
+ * Sort support routine for fast GiST index build by sorting.
+ */
+Datum
+gbt_bytea_sortsupport(PG_FUNCTION_ARGS)
+{
+	SortSupport ssup = (SortSupport) PG_GETARG_POINTER(0);
+
+	ssup->comparator = gbt_bytea_sort_build_cmp;
+	ssup->abbrev_converter = NULL;
+	ssup->abbrev_abort = NULL;
+	ssup->abbrev_full_comparator = NULL;
+	PG_RETURN_VOID();
+}

contrib/btree_gist/btree_cash.c

@@ -25,6 +25,7 @@ PG_FUNCTION_INFO_V1(gbt_cash_consistent);
 PG_FUNCTION_INFO_V1(gbt_cash_distance);
 PG_FUNCTION_INFO_V1(gbt_cash_penalty);
 PG_FUNCTION_INFO_V1(gbt_cash_same);
+PG_FUNCTION_INFO_V1(gbt_cash_sortsupport);
 
 static bool
 gbt_cashgt(const void *a, const void *b, FmgrInfo *flinfo)
@@ -216,3 +217,82 @@ gbt_cash_same(PG_FUNCTION_ARGS)
 	*result = gbt_num_same((void *) b1, (void *) b2, &tinfo, fcinfo->flinfo);
 	PG_RETURN_POINTER(result);
 }
+
+static int
+gbt_cash_sort_build_cmp(Datum a, Datum b, SortSupport ssup)
+{
+	cashKEY    *ia = (cashKEY *) DatumGetPointer(a);
+	cashKEY    *ib = (cashKEY *) DatumGetPointer(b);
+
+	/* for leaf items we expect lower == upper */
+	Assert(ia->lower == ia->upper);
+	Assert(ib->lower == ib->upper);
+
+	if (ia->lower == ib->lower)
+		return 0;
+
+	return (ia->lower > ib->lower) ? 1 : -1;
+}
+
+static Datum
+gbt_cash_abbrev_convert(Datum original, SortSupport ssup)
+{
+	cashKEY    *b1 = (cashKEY *) DatumGetPointer(original);
+	int64		z = b1->lower;
+
+#if SIZEOF_DATUM == 8
+	return Int64GetDatum(z);
+#else
+	return Int32GetDatum(z >> 32);
+#endif
+}
+
+static int
+gbt_cash_cmp_abbrev(Datum z1, Datum z2, SortSupport ssup)
+{
+#if SIZEOF_DATUM == 8
+	int64		a = DatumGetInt64(z1);
+	int64		b = DatumGetInt64(z2);
+#else
+	int32		a = DatumGetInt32(z1);
+	int32		b = DatumGetInt32(z2);
+#endif
+
+	if (a > b)
+		return 1;
+	else if (a < b)
+		return -1;
+	else
+		return 0;
+}
+
+/*
+ * We never consider aborting the abbreviation.
+ */
+static bool
+gbt_cash_abbrev_abort(int memtupcount, SortSupport ssup)
+{
+	return false;
+}
+
+/*
+ * Sort support routine for fast GiST index build by sorting.
+ */
+Datum
+gbt_cash_sortsupport(PG_FUNCTION_ARGS)
+{
+	SortSupport ssup = (SortSupport) PG_GETARG_POINTER(0);
+
+	if (ssup->abbreviate)
+	{
+		ssup->comparator = gbt_cash_cmp_abbrev;
+		ssup->abbrev_converter = gbt_cash_abbrev_convert;
+		ssup->abbrev_abort = gbt_cash_abbrev_abort;
+		ssup->abbrev_full_comparator = gbt_cash_sort_build_cmp;
+	}
+	else
+	{
+		ssup->comparator = gbt_cash_sort_build_cmp;
+	}
+	PG_RETURN_VOID();
+}

contrib/btree_gist/btree_date.c

@@ -25,6 +25,7 @@ PG_FUNCTION_INFO_V1(gbt_date_consistent);
 PG_FUNCTION_INFO_V1(gbt_date_distance);
 PG_FUNCTION_INFO_V1(gbt_date_penalty);
 PG_FUNCTION_INFO_V1(gbt_date_same);
+PG_FUNCTION_INFO_V1(gbt_date_sortsupport);
 
 static bool
 gbt_dategt(const void *a, const void *b, FmgrInfo *flinfo)
@@ -257,3 +258,29 @@ gbt_date_same(PG_FUNCTION_ARGS)
 	*result = gbt_num_same((void *) b1, (void *) b2, &tinfo, fcinfo->flinfo);
 	PG_RETURN_POINTER(result);
 }
+
+static int
+gbt_date_sort_build_cmp(Datum a, Datum b, SortSupport ssup)
+{
+	dateKEY    *ia = (dateKEY *) PointerGetDatum(a);
+	dateKEY    *ib = (dateKEY *) PointerGetDatum(b);
+
+	return DatumGetInt32(DirectFunctionCall2(date_cmp,
+											 DateADTGetDatum(ia->lower),
+											 DateADTGetDatum(ib->lower)));
+}
+
+/*
+ * Sort support routine for fast GiST index build by sorting.
+ */
+Datum
+gbt_date_sortsupport(PG_FUNCTION_ARGS)
+{
+	SortSupport ssup = (SortSupport) PG_GETARG_POINTER(0);
+
+	ssup->comparator = gbt_date_sort_build_cmp;
+	ssup->abbrev_converter = NULL;
+	ssup->abbrev_abort = NULL;
+	ssup->abbrev_full_comparator = NULL;
+	PG_RETURN_VOID();
+}

contrib/btree_gist/btree_enum.c

@@ -26,6 +26,7 @@ PG_FUNCTION_INFO_V1(gbt_enum_picksplit);
 PG_FUNCTION_INFO_V1(gbt_enum_consistent);
 PG_FUNCTION_INFO_V1(gbt_enum_penalty);
 PG_FUNCTION_INFO_V1(gbt_enum_same);
+PG_FUNCTION_INFO_V1(gbt_enum_sortsupport);
 
 
 static bool
@@ -183,3 +184,72 @@ gbt_enum_same(PG_FUNCTION_ARGS)
 	*result = gbt_num_same((void *) b1, (void *) b2, &tinfo, fcinfo->flinfo);
 	PG_RETURN_POINTER(result);
 }
+
+static int
+gbt_enum_sort_build_cmp(Datum a, Datum b, SortSupport ssup)
+{
+	oidKEY	   *ia = (oidKEY *) DatumGetPointer(a);
+	oidKEY	   *ib = (oidKEY *) DatumGetPointer(b);
+
+	/* for leaf items we expect lower == upper */
+	Assert(ia->lower == ia->upper);
+	Assert(ib->lower == ib->upper);
+
+	if (ia->lower == ib->lower)
+		return 0;
+
+	return (ia->lower > ib->lower) ? 1 : -1;
+}
+
+static Datum
+gbt_enum_abbrev_convert(Datum original, SortSupport ssup)
+{
+	oidKEY	   *b1 = (oidKEY *) DatumGetPointer(original);
+
+	return ObjectIdGetDatum(b1->lower);
+}
+
+static int
+gbt_enum_cmp_abbrev(Datum z1, Datum z2, SortSupport ssup)
+{
+	Oid			a = DatumGetObjectId(z1);
+	Oid			b = DatumGetObjectId(z2);
+
+	if (a > b)
+		return 1;
+	else if (a < b)
+		return -1;
+	else
+		return 0;
+}
+
+/*
+ * We never consider aborting the abbreviation.
+ */
+static bool
+gbt_enum_abbrev_abort(int memtupcount, SortSupport ssup)
+{
+	return false;
+}
+
+/*
+ * Sort support routine for fast GiST index build by sorting.
+ */
+Datum
+gbt_enum_sortsupport(PG_FUNCTION_ARGS)
+{
+	SortSupport ssup = (SortSupport) PG_GETARG_POINTER(0);
+
+	if (ssup->abbreviate)
+	{
+		ssup->comparator = gbt_enum_cmp_abbrev;
+		ssup->abbrev_converter = gbt_enum_abbrev_convert;
+		ssup->abbrev_abort = gbt_enum_abbrev_abort;
+		ssup->abbrev_full_comparator = gbt_enum_sort_build_cmp;
+	}
+	else
+	{
+		ssup->comparator = gbt_enum_sort_build_cmp;
+	}
+	PG_RETURN_VOID();
+}

contrib/btree_gist/btree_float4.c

@@ -23,6 +23,7 @@ PG_FUNCTION_INFO_V1(gbt_float4_consistent);
 PG_FUNCTION_INFO_V1(gbt_float4_distance);
 PG_FUNCTION_INFO_V1(gbt_float4_penalty);
 PG_FUNCTION_INFO_V1(gbt_float4_same);
+PG_FUNCTION_INFO_V1(gbt_float4_sortsupport);
 
 static bool
 gbt_float4gt(const void *a, const void *b, FmgrInfo *flinfo)
@@ -209,3 +210,73 @@ gbt_float4_same(PG_FUNCTION_ARGS)
 	*result = gbt_num_same((void *) b1, (void *) b2, &tinfo, fcinfo->flinfo);
 	PG_RETURN_POINTER(result);
 }
+
+
+static int
+gbt_float4_sort_build_cmp(Datum a, Datum b, SortSupport ssup)
+{
+	float4KEY  *ia = (float4KEY *) DatumGetPointer(a);
+	float4KEY  *ib = (float4KEY *) DatumGetPointer(b);
+
+	/* for leaf items we expect lower == upper */
+	Assert(ia->lower == ia->upper);
+	Assert(ib->lower == ib->upper);
+
+	if (ia->lower == ib->lower)
+		return 0;
+
+	return (ia->lower > ib->lower) ? 1 : -1;
+}
+
+static Datum
+gbt_float4_abbrev_convert(Datum original, SortSupport ssup)
+{
+	float4KEY  *b1 = (float4KEY *) DatumGetPointer(original);
+
+	return Float4GetDatum(b1->lower);
+}
+
+static int
+gbt_float4_cmp_abbrev(Datum z1, Datum z2, SortSupport ssup)
+{
+	float4		a = DatumGetFloat4(z1);
+	float4		b = DatumGetFloat4(z2);
+
+	if (a > b)
+		return 1;
+	else if (a < b)
+		return -1;
+	else
+		return 0;
+}
+
+/*
+ * We never consider aborting the abbreviation.
+ */
+static bool
+gbt_float4_abbrev_abort(int memtupcount, SortSupport ssup)
+{
+	return false;
+}
+
+/*
+ * Sort support routine for fast GiST index build by sorting.
+ */
+Datum
+gbt_float4_sortsupport(PG_FUNCTION_ARGS)
+{
+	SortSupport ssup = (SortSupport) PG_GETARG_POINTER(0);
+
+	if (ssup->abbreviate)
+	{
+		ssup->comparator = gbt_float4_cmp_abbrev;
+		ssup->abbrev_converter = gbt_float4_abbrev_convert;
+		ssup->abbrev_abort = gbt_float4_abbrev_abort;
+		ssup->abbrev_full_comparator = gbt_float4_sort_build_cmp;
+	}
+	else
+	{
+		ssup->comparator = gbt_float4_sort_build_cmp;
+	}
+	PG_RETURN_VOID();
+}