pgbench-64-v5.patch

diff --git a/contrib/pgbench/pgbench.c b/contrib/pgbench/pgbench.c
index 55ca1e8..5b9b582 100644
--- a/contrib/pgbench/pgbench.c
+++ b/contrib/pgbench/pgbench.c
@@ -60,6 +60,8 @@
 #define INT64_MAX	INT64CONST(0x7FFFFFFFFFFFFFFF)
 #endif
 
+#define MAX_RANDOM_VALUE64	INT64_MAX
+
 /*
  * Multi-platform pthread implementations
  */
@@ -364,15 +366,84 @@ usage(const char *progname)
 		   progname, progname);
 }
 
+/*
+ * strtoint64 -- convert a string to 64-bit integer
+ *
+ * This function is a modified version of scanint8() from
+ * src/backend/utils/adt/int8.c.
+ *
+ */
+static int64
+strtoint64(const char *str)
+{
+	const char *ptr = str;
+	int64		result = 0;
+	int			sign = 1;
+
+	/*
+	 * Do our own scan, rather than relying on sscanf which might be broken
+	 * for long long.
+	 */
+
+	/* skip leading spaces */
+	while (*ptr && isspace((unsigned char) *ptr))
+		ptr++;
+
+	/* handle sign */
+	if (*ptr == '-')
+	{
+		ptr++;
+
+		/*
+		 * Do an explicit check for INT64_MIN.	Ugly though this is, it's
+		 * cleaner than trying to get the loop below to handle it portably.
+		 */
+		if (strncmp(ptr, "9223372036854775808", 19) == 0)
+		{
+			result = -INT64CONST(0x7fffffffffffffff) - 1;
+			ptr += 19;
+			goto gotdigits;
+		}
+		sign = -1;
+	}
+	else if (*ptr == '+')
+		ptr++;
+
+	/* require at least one digit */
+	if (!isdigit((unsigned char) *ptr))
+		fprintf(stderr, "invalid input syntax for integer: \"%s\"\n", str);
+
+	/* process digits */
+	while (*ptr && isdigit((unsigned char) *ptr))
+	{
+		int64		tmp = result * 10 + (*ptr++ - '0');
+
+		if ((tmp / 10) != result)		/* overflow? */
+			fprintf(stderr, "value \"%s\" is out of range for type bigint\n", str);
+		result = tmp;
+	}
+
+gotdigits:
+
+	/* allow trailing whitespace, but not other trailing chars */
+	while (*ptr != '\0' && isspace((unsigned char) *ptr))
+		ptr++;
+
+	if (*ptr != '\0')
+		fprintf(stderr, "invalid input syntax for integer: \"%s\"\n", str);
+
+	return ((sign < 0) ? -result : result);
+}
+
 /* random number generator: uniform distribution from min to max inclusive */
-static int
-getrand(int min, int max)
+static int64
+getrand(int64 min, int64 max)
 {
 	/*
 	 * Odd coding is so that min and max have approximately the same chance of
 	 * being selected as do numbers between them.
 	 */
-	return min + (int) (((max - min + 1) * (double) random()) / (MAX_RANDOM_VALUE + 1.0));
+	return min + (int64) (((max - min + 1) * (double) random()) / (MAX_RANDOM_VALUE + 1.0));
 }
 
 /* call PQexec() and exit() on failure */
@@ -887,7 +958,7 @@ top:
 		if (commands[st->state] == NULL)
 		{
 			st->state = 0;
-			st->use_file = getrand(0, num_files - 1);
+			st->use_file = (int) getrand(0, num_files - 1);
 			commands = sql_files[st->use_file];
 		}
 	}
@@ -1007,7 +1078,7 @@ top:
 		if (pg_strcasecmp(argv[0], "setrandom") == 0)
 		{
 			char	   *var;
-			int			min,
+			int64		min,
 						max;
 			char		res[64];
 
@@ -1019,15 +1090,15 @@ top:
 					st->ecnt++;
 					return true;
 				}
-				min = atoi(var);
+				min = strtoint64(var);
 			}
 			else
-				min = atoi(argv[2]);
+				min = strtoint64(argv[2]);
 
 #ifdef NOT_USED
 			if (min < 0)
 			{
-				fprintf(stderr, "%s: invalid minimum number %d\n", argv[0], min);
+				fprintf(stderr, "%s: invalid minimum number " INT64_FORMAT "\n", argv[0], min);
 				st->ecnt++;
 				return;
 			}
@@ -1041,22 +1112,22 @@ top:
 					st->ecnt++;
 					return true;
 				}
-				max = atoi(var);
+				max = strtoint64(var);
 			}
 			else
-				max = atoi(argv[3]);
+				max = strtoint64(argv[3]);
 
-			if (max < min || max > MAX_RANDOM_VALUE)
+			if (max < min || max > MAX_RANDOM_VALUE64)
 			{
-				fprintf(stderr, "%s: invalid maximum number %d\n", argv[0], max);
+				fprintf(stderr, "%s: invalid maximum number " INT64_FORMAT "\n", argv[0], max);
 				st->ecnt++;
 				return true;
 			}
 
 #ifdef DEBUG
-			printf("min: %d max: %d random: %d\n", min, max, getrand(min, max));
+			printf("min: " INT64_FORMAT " max: " INT64_FORMAT " random: " INT64_FORMAT "\n", min, max, getrand(min, max));
 #endif
-			snprintf(res, sizeof(res), "%d", getrand(min, max));
+			snprintf(res, sizeof(res), INT64_FORMAT, getrand(min, max));
 
 			if (!putVariable(st, argv[0], argv[1], res))
 			{
@@ -1069,7 +1140,7 @@ top:
 		else if (pg_strcasecmp(argv[0], "set") == 0)
 		{
 			char	   *var;
-			int			ope1,
+			int64		ope1,
 						ope2;
 			char		res[64];
 
@@ -1081,13 +1152,13 @@ top:
 					st->ecnt++;
 					return true;
 				}
-				ope1 = atoi(var);
+				ope1 = strtoint64(var);
 			}
 			else
-				ope1 = atoi(argv[2]);
+				ope1 = strtoint64(argv[2]);
 
 			if (argc < 5)
-				snprintf(res, sizeof(res), "%d", ope1);
+				snprintf(res, sizeof(res), INT64_FORMAT, ope1);
 			else
 			{
 				if (*argv[4] == ':')
@@ -1098,17 +1169,17 @@ top:
 						st->ecnt++;
 						return true;
 					}
-					ope2 = atoi(var);
+					ope2 = strtoint64(var);
 				}
 				else
-					ope2 = atoi(argv[4]);
+					ope2 = strtoint64(argv[4]);
 
 				if (strcmp(argv[3], "+") == 0)
-					snprintf(res, sizeof(res), "%d", ope1 + ope2);
+					snprintf(res, sizeof(res), INT64_FORMAT, ope1 + ope2);
 				else if (strcmp(argv[3], "-") == 0)
-					snprintf(res, sizeof(res), "%d", ope1 - ope2);
+					snprintf(res, sizeof(res), INT64_FORMAT, ope1 - ope2);
 				else if (strcmp(argv[3], "*") == 0)
-					snprintf(res, sizeof(res), "%d", ope1 * ope2);
+					snprintf(res, sizeof(res), INT64_FORMAT, ope1 * ope2);
 				else if (strcmp(argv[3], "/") == 0)
 				{
 					if (ope2 == 0)
@@ -1117,7 +1188,7 @@ top:
 						st->ecnt++;
 						return true;
 					}
-					snprintf(res, sizeof(res), "%d", ope1 / ope2);
+					snprintf(res, sizeof(res), INT64_FORMAT, ope1 / ope2);
 				}
 				else
 				{
@@ -1239,9 +1310,9 @@ init(void)
 		"drop table if exists pgbench_tellers",
 		"create table pgbench_tellers(tid int not null,bid int,tbalance int,filler char(84)) with (fillfactor=%d)",
 		"drop table if exists pgbench_accounts",
-		"create table pgbench_accounts(aid int not null,bid int,abalance int,filler char(84)) with (fillfactor=%d)",
+		"create table pgbench_accounts(aid %s not null,bid int,abalance int,filler char(84)) with (fillfactor=%d)",
 		"drop table if exists pgbench_history",
-		"create table pgbench_history(tid int,bid int,aid int,delta int,mtime timestamp,filler char(22))"
+		"create table pgbench_history(tid int,bid int,aid %s,delta int,mtime timestamp,filler char(22))"
 	};
 	static char *DDLAFTERs[] = {
 		"alter table pgbench_branches add primary key (bid)",
@@ -1253,6 +1324,7 @@ init(void)
 	PGresult   *res;
 	char		sql[256];
 	int			i;
+	int64		k;
 
 	if ((con = doConnect()) == NULL)
 		exit(1);
@@ -1263,8 +1335,7 @@ init(void)
 		 * set fillfactor for branches, tellers and accounts tables
 		 */
 		if ((strstr(DDLs[i], "create table pgbench_branches") == DDLs[i]) ||
-			(strstr(DDLs[i], "create table pgbench_tellers") == DDLs[i]) ||
-			(strstr(DDLs[i], "create table pgbench_accounts") == DDLs[i]))
+			(strstr(DDLs[i], "create table pgbench_tellers") == DDLs[i]))
 		{
 			char		ddl_stmt[128];
 
@@ -1272,6 +1343,36 @@ init(void)
 			executeStatement(con, ddl_stmt);
 			continue;
 		}
+		else if (strstr(DDLs[i], "create table pgbench_accounts") == DDLs[i])
+		{
+			char		ddl_stmt[128];
+
+			/*
+			 * Use bigint columns in cases where scale factor is bigger
+			 * than 20000, which gives an account number around the upper
+			 * limit the range for a regular integer (just over 2 billion).
+			 * For smaller scale factors, we still use int columns, to keep
+			 * results more like those given by earlier versions of pgbench.
+			 */
+			if (scale >= 20000)
+				snprintf(ddl_stmt, 128, DDLs[i], "bigint", fillfactor);
+			else
+				snprintf(ddl_stmt, 128, DDLs[i], "int", fillfactor);
+			executeStatement(con, ddl_stmt);
+			continue;
+		}
+		else if (strstr(DDLs[i], "create table pgbench_history") == DDLs[i])
+		{
+			char		ddl_stmt[128];
+
+			/* The accounts value in the history table needs a matching size */
+			if (scale >= 20000)
+				snprintf(ddl_stmt, 128, DDLs[i], "bigint");
+			else
+				snprintf(ddl_stmt, 128, DDLs[i], "int");
+			executeStatement(con, ddl_stmt);
+			continue;
+		}
 		else
 			executeStatement(con, DDLs[i]);
 	}
@@ -1309,11 +1410,11 @@ init(void)
 	}
 	PQclear(res);
 
-	for (i = 0; i < naccounts * scale; i++)
+	for (k = 0; k < (int64) naccounts * scale; k++)
 	{
-		int			j = i + 1;
+		int64			j = k + 1;
 
-		snprintf(sql, 256, "%d\t%d\t%d\t\n", j, i / naccounts + 1, 0);
+		snprintf(sql, 256, INT64_FORMAT "\t" INT64_FORMAT "\t%d\t\n", j, k / naccounts + 1, 0);
 		if (PQputline(con, sql))
 		{
 			fprintf(stderr, "PQputline failed\n");
@@ -1321,7 +1422,7 @@ init(void)
 		}
 
 		if (j % 10000 == 0)
-			fprintf(stderr, "%d tuples done.\n", j);
+			fprintf(stderr, INT64_FORMAT " tuples done.\n", j);
 	}
 	if (PQputline(con, "\\.\n"))
 	{
diff --git a/doc/src/sgml/pgbench.sgml b/doc/src/sgml/pgbench.sgml
index a33ac17..05c9794 100644
--- a/doc/src/sgml/pgbench.sgml
+++ b/doc/src/sgml/pgbench.sgml
@@ -155,6 +155,10 @@ pgbench <optional> <replaceable>options</> </optional> <replaceable>dbname</>
         Multiply the number of rows generated by the scale factor.
         For example, <literal>-s 100</> will create 10,000,000 rows
         in the <structname>pgbench_accounts</> table. Default is 1.
+        When the scale is 20,000 or larger, the columns used to
+        hold account identifiers will switch to using larger integers,
+        in order to be big enough to hold the range of account
+        identifiers.
        </para>
       </listitem>
      </varlistentry>
@@ -769,6 +773,19 @@ statement latencies in milliseconds:
    instances concurrently, on several client machines, against the same
    database server.
   </para>
+
+  <para>
+   The random number generation done by <application>pgbench</> is limited
+   the accuracy of the underlying operating system numeric library.  Typically
+   this provides range of approximately 1 billion values.  There will
+   be a billion rows in the <structname>pgbench_accounts</> table once the
+   database scale is increased to 10,000 or above.  When creating large
+   databases above or even near this scale, you should expect that the
+   distribution of rows selected by random operations will no longer be
+   as evenly distributed, relative to when the program is running against a
+   smaller database.
+  </para>
+ 
  </sect2>
 
 </sect1>