pgbench-sampling-v3.diff

diff --git a/contrib/pgbench/pgbench.c b/contrib/pgbench/pgbench.c
index 00cab73..578aeb3 100644
--- a/contrib/pgbench/pgbench.c
+++ b/contrib/pgbench/pgbench.c
@@ -130,6 +130,11 @@ int			foreign_keys = 0;
 int			unlogged_tables = 0;
 
 /*
+ * use log sampling (rate => 1 = 100%, 0 = don't use)
+ */
+double		use_sample_rate = 0.0;
+
+/*
  * tablespace selection
  */
 char	   *tablespace = NULL;
@@ -364,6 +369,8 @@ usage(void)
 		   "  -f FILENAME  read transaction script from FILENAME\n"
 		   "  -j NUM       number of threads (default: 1)\n"
 		   "  -l           write transaction times to log file\n"
+		   "  --sampling-rate NUM\n"
+		   "               sampling rate of the log (e.g. 0.01 for 1%% sample)\n"
 		   "  -M simple|extended|prepared\n"
 		   "               protocol for submitting queries to server (default: simple)\n"
 		   "  -n           do not run VACUUM before tests\n"
@@ -877,21 +884,26 @@ top:
 			instr_time	diff;
 			double		usec;
 
-			INSTR_TIME_SET_CURRENT(now);
-			diff = now;
-			INSTR_TIME_SUBTRACT(diff, st->txn_begin);
-			usec = (double) INSTR_TIME_GET_MICROSEC(diff);
+			/* either no sampling or is within the sample */
+			if ((use_sample_rate == 0.0) || (pg_erand48(thread->random_state) <= use_sample_rate))
+			{
+
+				INSTR_TIME_SET_CURRENT(now);
+				diff = now;
+				INSTR_TIME_SUBTRACT(diff, st->txn_begin);
+				usec = (double) INSTR_TIME_GET_MICROSEC(diff);
 
 #ifndef WIN32
-			/* This is more than we really ought to know about instr_time */
-			fprintf(logfile, "%d %d %.0f %d %ld %ld\n",
-					st->id, st->cnt, usec, st->use_file,
-					(long) now.tv_sec, (long) now.tv_usec);
+				/* This is more than we really ought to know about instr_time */
+				fprintf(logfile, "%d %d %.0f %d %ld %ld\n",
+						st->id, st->cnt, usec, st->use_file,
+						(long) now.tv_sec, (long) now.tv_usec);
 #else
-			/* On Windows, instr_time doesn't provide a timestamp anyway */
-			fprintf(logfile, "%d %d %.0f %d 0 0\n",
-					st->id, st->cnt, usec, st->use_file);
+				/* On Windows, instr_time doesn't provide a timestamp anyway */
+				fprintf(logfile, "%d %d %.0f %d 0 0\n",
+						st->id, st->cnt, usec, st->use_file);
 #endif
+			}
 		}
 
 		if (commands[st->state]->type == SQL_COMMAND)
@@ -1918,6 +1930,7 @@ main(int argc, char **argv)
 		{"index-tablespace", required_argument, NULL, 3},
 		{"tablespace", required_argument, NULL, 2},
 		{"unlogged-tables", no_argument, &unlogged_tables, 1},
+		{"sampling-rate", required_argument, NULL, 4},
 		{NULL, 0, NULL, 0}
 	};
 
@@ -2123,6 +2136,14 @@ main(int argc, char **argv)
 			case 3:				/* index-tablespace */
 				index_tablespace = optarg;
 				break;
+			case 4:
+				use_sample_rate = atof(optarg)/100;
+				if (use_sample_rate <= 0.0 || use_sample_rate > 1.0)
+				{
+					fprintf(stderr, "invalid sampling rate: %f\n", use_sample_rate);
+					exit(1);
+				}
+				break;
 			default:
 				fprintf(stderr, _("Try \"%s --help\" for more information.\n"), progname);
 				exit(1);
@@ -2158,6 +2179,12 @@ main(int argc, char **argv)
 		exit(1);
 	}
 
+	/* --sampling-rate may be used only with -l */
+	if (use_sample_rate > 0 && (! use_log)) {
+		fprintf(stderr, "log sampling rate is allowed only when logging transactions\n");
+		exit(1);
+	}
+
 	/*
 	 * is_latencies only works with multiple threads in thread-based
 	 * implementations, not fork-based ones, because it supposes that the
diff --git a/doc/src/sgml/pgbench.sgml b/doc/src/sgml/pgbench.sgml
index 437fcea..67b21aa 100644
--- a/doc/src/sgml/pgbench.sgml
+++ b/doc/src/sgml/pgbench.sgml
@@ -317,6 +317,22 @@ pgbench <optional> <replaceable>options</> </optional> <replaceable>dbname</>
      </varlistentry>
 
      <varlistentry>
+      <term><option>--sampling-rate</option> <replaceable>rate</></term>
+      <listitem>
+       <para>
+        Sampling rate, used when writing data into the log in percent. 100 means all
+        transactions will be logged, 1 means only 1% of the transactions will be logged.
+        This may also be a float, e.g. 12.5 means 12.5% will be sampled.
+       </para>
+       <para>
+        Be careful when processing the log file - e.g. when computing tps values, you
+        need to multiply the numbers accordingly (e.g. with 1% sample you'll get 1/100
+        of the actual tps).
+       </para>
+      </listitem>
+     </varlistentry>
+
+     <varlistentry>
       <term><option>-M</option> <replaceable>querymode</></term>
       <listitem>
        <para>