pgbench: Function to generate random permutations.

This adds a new function, permute(), that generates pseudorandom
permutations of arbitrary sizes. This can be used to randomly shuffle
a set of values to remove unwanted correlations. For example,
permuting the output from a non-uniform random distribution so that
all the most common values aren't collocated, allowing more realistic
tests to be performed.

Formerly, hash() was recommended for this purpose, but that suffers
from collisions that might alter the distribution, so recommend
permute() for this purpose instead.

Fabien Coelho and Hironobu Suzuki, with additional hacking be me.
Reviewed by Thomas Munro, Alvaro Herrera and Muhammad Usama.

Discussion: https://postgr.es/m/alpine.DEB.2.21.1807280944370.5142@lancre

1 files changed, 17 insertions, 0 deletions

diff --git a/src/bin/pgbench/exprparse.y b/src/bin/pgbench/exprparse.y
index 4d529ea5500..56f75ccd253 100644
--- a/src/bin/pgbench/exprparse.y
+++ b/src/bin/pgbench/exprparse.y
@@ -19,6 +19,7 @@
 #define PGBENCH_NARGS_VARIABLE	(-1)
 #define PGBENCH_NARGS_CASE		(-2)
 #define PGBENCH_NARGS_HASH		(-3)
+#define PGBENCH_NARGS_PERMUTE	(-4)
 
 PgBenchExpr *expr_parse_result;
 
@@ -370,6 +371,9 @@ static const struct
 	{
 		"hash_fnv1a", PGBENCH_NARGS_HASH, PGBENCH_HASH_FNV1A
 	},
+	{
+		"permute", PGBENCH_NARGS_PERMUTE, PGBENCH_PERMUTE
+	},
 	/* keep as last array element */
 	{
 		NULL, 0, 0
@@ -482,6 +486,19 @@ make_func(yyscan_t yyscanner, int fnumber, PgBenchExprList *args)
 			}
 			break;
 
+		/* pseudorandom permutation function with optional seed argument */
+		case PGBENCH_NARGS_PERMUTE:
+			if (len < 2 || len > 3)
+				expr_yyerror_more(yyscanner, "unexpected number of arguments",
+								  PGBENCH_FUNCTIONS[fnumber].fname);
+
+			if (len == 2)
+			{
+				PgBenchExpr *var = make_variable("default_seed");
+				args = make_elist(var, args);
+			}
+			break;
+
 		/* common case: positive arguments number */
 		default:
 			Assert(PGBENCH_FUNCTIONS[fnumber].nargs >= 0);