Fix portability problem in pgbench.

tglsfdc · tglsfdc · commit e6c3ba7fbfd5 · 2019-01-24T11:31:54.000-05:00
The pgbench regression test supposed that srandom() with a specific value would result in deterministic output from random(), as required by POSIX. It emerges however that OpenBSD is too smart to be constrained by mere standards, so their random() emits nondeterministic output anyway. While a workaround does exist, what seems like a better fix is to stop relying on the platform's srandom()/random() altogether, so that what you get from --random-seed=N is not merely deterministic but platform independent. Hence, use a separate pg_jrand48() random sequence in place of random(). Also adjust the regression test case that's supposed to detect nondeterminism so that it's more likely to detect it; the original choice of random_zipfian parameter tended to produce the same output all the time even if the underlying behavior wasn't deterministic. In passing, improve pgbench's docs about random_zipfian(). Back-patch to v11 where this code was introduced. Fabien Coelho and Tom Lane Discussion: https://postgr.es/m/4615.1547792324@sss.pgh.pa.us
diff --git a/doc/src/sgml/ref/pgbench.sgml b/doc/src/sgml/ref/pgbench.sgml
@@ -1604,15 +1604,24 @@ f(x) = PHI(2.0 * parameter * (x - mu) / (max - min + 1)) /
       in (1, 1000), a rejection method is used, based on
       "Non-Uniform Random Variate Generation", Luc Devroye, p. 550-551,
       Springer 1986. The distribution is not defined when the parameter's
-      value is 1.0. The drawing performance is poor for parameter values
+      value is 1.0. The function's performance is poor for parameter values
       close and above 1.0 and on a small range.
      </para>
      <para>
-      <replaceable>parameter</replaceable>
-      defines how skewed the distribution is. The larger the <replaceable>parameter</replaceable>, the more
-      frequently values to the beginning of the interval are drawn.
+      <replaceable>parameter</replaceable> defines how skewed the distribution
+      is. The larger the <replaceable>parameter</replaceable>, the more
+      frequently values closer to the beginning of the interval are drawn.
       The closer to 0 <replaceable>parameter</replaceable> is,
-      the flatter (more uniform) the access distribution.
+      the flatter (more uniform) the output distribution.
+      The distribution is such that, assuming the range starts from 1,
+      the ratio of the probability of drawing <replaceable>k</replaceable>
+      versus drawing <replaceable>k+1</replaceable> is
+      <literal>((<replaceable>k</replaceable>+1)/<replaceable>k</replaceable>)**<replaceable>parameter</replaceable></literal>.
+      For example, <literal>random_zipfian(1, ..., 2.5)</literal> produces
+      the value <literal>1</literal> about <literal>(2/1)**2.5 =
+      5.66</literal> times more frequently than <literal>2</literal>, which
+      itself is produced <literal>(3/2)*2.5 = 2.76</literal> times more
+      frequently than <literal>3</literal>, and so on.
      </para>
     </listitem>
    </itemizedlist>
diff --git a/src/bin/pgbench/pgbench.c b/src/bin/pgbench/pgbench.c
@@ -185,7 +185,7 @@ int64		latency_limit = 0;
 char	   *tablespace = NULL;
 char	   *index_tablespace = NULL;
 
-/* random seed used when calling srandom() */
+/* random seed used to initialize base_random_sequence */
 int64		random_seed = -1;
 
 /*
@@ -287,6 +287,9 @@ typedef struct RandomState
 	unsigned short xseed[3];
 } RandomState;
 
+/* Various random sequences are initialized from this one. */
+static RandomState base_random_sequence;
+
 /*
  * Connection state machine states.
  */
@@ -833,16 +836,28 @@ strtodouble(const char *str, bool errorOK, double *dv)
 
 /*
  * Initialize a random state struct.
+ *
+ * We derive the seed from base_random_sequence, which must be set up already.
  */
 static void
 initRandomState(RandomState *random_state)
 {
-	random_state->xseed[0] = random();
-	random_state->xseed[1] = random();
-	random_state->xseed[2] = random();
+	random_state->xseed[0] = (unsigned short)
+		(pg_jrand48(base_random_sequence.xseed) & 0xFFFF);
+	random_state->xseed[1] = (unsigned short)
+		(pg_jrand48(base_random_sequence.xseed) & 0xFFFF);
+	random_state->xseed[2] = (unsigned short)
+		(pg_jrand48(base_random_sequence.xseed) & 0xFFFF);
 }
 
-/* random number generator: uniform distribution from min to max inclusive */
+/*
+ * Random number generator: uniform distribution from min to max inclusive.
+ *
+ * Although the limits are expressed as int64, you can't generate the full
+ * int64 range in one call, because the difference of the limits mustn't
+ * overflow int64.  In practice it's unwise to ask for more than an int32
+ * range, because of the limited precision of pg_erand48().
+ */
 static int64
 getrand(RandomState *random_state, int64 min, int64 max)
 {
@@ -5126,20 +5141,22 @@ printResults(TState *threads, StatsData *total, instr_time total_time,
 	}
 }
 
-/* call srandom based on some seed. NULL triggers the default behavior. */
+/*
+ * Set up a random seed according to seed parameter (NULL means default),
+ * and initialize base_random_sequence for use in initializing other sequences.
+ */
 static bool
 set_random_seed(const char *seed)
 {
-	/* srandom expects an unsigned int */
-	unsigned int iseed;
+	uint64		iseed;
 
 	if (seed == NULL || strcmp(seed, "time") == 0)
 	{
 		/* rely on current time */
 		instr_time	now;
 
 		INSTR_TIME_SET_CURRENT(now);
-		iseed = (unsigned int) INSTR_TIME_GET_MICROSEC(now);
+		iseed = (uint64) INSTR_TIME_GET_MICROSEC(now);
 	}
 	else if (strcmp(seed, "rand") == 0)
 	{
@@ -5155,7 +5172,7 @@ set_random_seed(const char *seed)
 		/* parse seed unsigned int value */
 		char		garbage;
 
-		if (sscanf(seed, "%u%c", &iseed, &garbage) != 1)
+		if (sscanf(seed, UINT64_FORMAT "%c", &iseed, &garbage) != 1)
 		{
 			fprintf(stderr,
 					"unrecognized random seed option \"%s\": expecting an unsigned integer, \"time\" or \"rand\"\n",
@@ -5165,10 +5182,14 @@ set_random_seed(const char *seed)
 	}
 
 	if (seed != NULL)
-		fprintf(stderr, "setting random seed to %u\n", iseed);
-	srandom(iseed);
-	/* no precision loss: 32 bit unsigned int cast to 64 bit int */
+		fprintf(stderr, "setting random seed to " UINT64_FORMAT "\n", iseed);
 	random_seed = iseed;
+
+	/* Fill base_random_sequence with low-order bits of seed */
+	base_random_sequence.xseed[0] = iseed & 0xFFFF;
+	base_random_sequence.xseed[1] = (iseed >> 16) & 0xFFFF;
+	base_random_sequence.xseed[2] = (iseed >> 32) & 0xFFFF;
+
 	return true;
 }
 
@@ -5862,10 +5883,9 @@ main(int argc, char **argv)
 	/* set default seed for hash functions */
 	if (lookupVariable(&state[0], "default_seed") == NULL)
 	{
-		uint64		seed = ((uint64) (random() & 0xFFFF) << 48) |
-		((uint64) (random() & 0xFFFF) << 32) |
-		((uint64) (random() & 0xFFFF) << 16) |
-		(uint64) (random() & 0xFFFF);
+		uint64		seed =
+		((uint64) pg_jrand48(base_random_sequence.xseed) & 0xFFFFFFFF) |
+		(((uint64) pg_jrand48(base_random_sequence.xseed) & 0xFFFFFFFF) << 32);
 
 		for (i = 0; i < nclients; i++)
 			if (!putVariableInt(&state[i], "startup", "default_seed", (int64) seed))
diff --git a/src/bin/pgbench/t/001_pgbench_with_server.pl b/src/bin/pgbench/t/001_pgbench_with_server.pl
@@ -259,11 +259,11 @@ sub pgbench
 	[
 		qr{setting random seed to 5432\b},
 
-		# After explicit seeding, the four * random checks (1-3,20) should be
-		# deterministic, but not necessarily portable.
-		qr{command=1.: int 1\d\b},        # uniform random: 12 on linux
-		qr{command=2.: int 1\d\d\b},      # exponential random: 106 on linux
-		qr{command=3.: int 1\d\d\d\b},    # gaussian random: 1462 on linux
+		# After explicit seeding, the four random checks (1-3,20) are
+		# deterministic
+		qr{command=1.: int 13\b},      # uniform random
+		qr{command=2.: int 116\b},     # exponential random
+		qr{command=3.: int 1498\b},    # gaussian random
 		qr{command=4.: int 4\b},
 		qr{command=5.: int 5\b},
 		qr{command=6.: int 6\b},
@@ -276,7 +276,7 @@ sub pgbench
 		qr{command=15.: double 15\b},
 		qr{command=16.: double 16\b},
 		qr{command=17.: double 17\b},
-		qr{command=20.: int \d\b},    # zipfian random: 1 on linux
+		qr{command=20.: int 1\b},      # zipfian random
 		qr{command=21.: double -27\b},
 		qr{command=22.: double 1024\b},
 		qr{command=23.: double 1\b},
@@ -471,7 +471,7 @@ sub pgbench
 \set ur random(1000, 1999)
 \set er random_exponential(2000, 2999, 2.0)
 \set gr random_gaussian(3000, 3999, 3.0)
-\set zr random_zipfian(4000, 4999, 2.5)
+\set zr random_zipfian(4000, 4999, 1.5)
 INSERT INTO seeded_random(seed, rand, val) VALUES
   (:random_seed, 'uniform', :ur),
   (:random_seed, 'exponential', :er),
