sample_rate-3.patch

commit 26e30f7506ccdbca6a2d5c2d4942bd9985c3c9bc
Author: anayrat <adrien.nayrat@anayrat.info>
Date:   Wed May 30 20:27:54 2018 +0200

    Add a new GUC, log_sample_rate, to log a fraction of queries.

diff --git a/doc/src/sgml/config.sgml b/doc/src/sgml/config.sgml
index 7bfbc87109..e4f7cb9c09 100644
--- a/doc/src/sgml/config.sgml
+++ b/doc/src/sgml/config.sgml
@@ -5190,6 +5190,25 @@ local0.*    /var/log/postgresql
        </listitem>
       </varlistentry>
 
+     <varlistentry id="guc-log-sample-rate" xreflabel="log_sample_rate">
+      <term><varname>log_sample_rate</varname> (<type>real</type>)
+      <indexterm>
+       <primary><varname>log_sample_rate</varname> configuration parameter</primary>
+      </indexterm>
+      </term>
+       <listitem>
+        <para>
+         Causes logging a fraction of the statements when log_min_duration_statement
+         is used. The default is 1, meaning log all statements longer than
+         log_min_duration_statement. Setting this to zero disable logging, same
+         as setting log_min_duration_statement to Minus-one.
+         Using log_sample_rate less than 1 can be helpful to log a sample of short
+         queries when the traffic is to important to log all queries (for example,
+         if you want queries parameters).
+        </para>
+       </listitem>
+      </varlistentry>
+
      </variablelist>
 
     <para>
diff --git a/src/backend/tcop/postgres.c b/src/backend/tcop/postgres.c
index f4133953be..0197161ad1 100644
--- a/src/backend/tcop/postgres.c
+++ b/src/backend/tcop/postgres.c
@@ -2115,7 +2115,8 @@ check_log_statement(List *stmt_list)
 
 /*
  * check_log_duration
- *		Determine whether current command's duration should be logged
+ *		Determine whether current command's duration should be logged.
+ *		If log_sample_rate < 1.0, log only a sample.
  *
  * Returns:
  *		0 if no logging is needed
@@ -2147,11 +2148,16 @@ check_log_duration(char *msec_str, bool was_logged)
 		 * This odd-looking test for log_min_duration_statement being exceeded
 		 * is designed to avoid integer overflow with very long durations:
 		 * don't compute secs * 1000 until we've verified it will fit in int.
+		 * Do not log if log_sample_rate = 0.
+		 * Log a sample if log_sample_rate <= 1 and avoid unecessary random()
+		 * call if log_sample_rate = 1.
 		 */
 		exceeded = (log_min_duration_statement == 0 ||
 					(log_min_duration_statement > 0 &&
 					 (secs > log_min_duration_statement / 1000 ||
-					  secs * 1000 + msecs >= log_min_duration_statement)));
+					  secs * 1000 + msecs >= log_min_duration_statement))) &&
+				   log_sample_rate != 0 && (log_sample_rate == 1 ||
+				   random() <= log_sample_rate * MAX_RANDOM_VALUE);
 
 		if (exceeded || log_duration)
 		{
diff --git a/src/backend/utils/misc/guc.c b/src/backend/utils/misc/guc.c
index 859ef931e7..c1ff5e71c8 100644
--- a/src/backend/utils/misc/guc.c
+++ b/src/backend/utils/misc/guc.c
@@ -455,6 +455,7 @@ int			log_min_messages = WARNING;
 int			client_min_messages = NOTICE;
 int			log_min_duration_statement = -1;
 int			log_temp_files = -1;
+double 		log_sample_rate = 1.0;
 int			trace_recovery_messages = LOG;
 
 int			temp_file_limit = -1;
@@ -3257,6 +3258,17 @@ static struct config_real ConfigureNamesReal[] =
 		NULL, NULL, NULL
 	},
 
+	{
+		{"log_sample_rate", PGC_SUSET, LOGGING_WHEN,
+			gettext_noop("Fraction of statements to log."),
+			gettext_noop("1.0 log all statements."),
+			NULL
+		},
+		&log_sample_rate,
+		1.0, 0.0, 1.0,
+		NULL, NULL, NULL
+	},
+
 	/* End-of-list marker */
 	{
 		{NULL, 0, 0, NULL, NULL}, NULL, 0.0, 0.0, 0.0, NULL, NULL, NULL
diff --git a/src/backend/utils/misc/postgresql.conf.sample b/src/backend/utils/misc/postgresql.conf.sample
index 9e39baf466..3f9a016003 100644
--- a/src/backend/utils/misc/postgresql.conf.sample
+++ b/src/backend/utils/misc/postgresql.conf.sample
@@ -447,6 +447,8 @@
 					# statements running at least this number
 					# of milliseconds
 
+#log_sample_rate = 1  # Fraction of logged statements. 1 means log all
+					# statements.
 
 # - What to Log -
 
diff --git a/src/include/utils/guc.h b/src/include/utils/guc.h
index f462eabe59..f50a0d1f1b 100644
--- a/src/include/utils/guc.h
+++ b/src/include/utils/guc.h
@@ -252,6 +252,7 @@ extern PGDLLIMPORT int log_min_messages;
 extern PGDLLIMPORT int client_min_messages;
 extern int	log_min_duration_statement;
 extern int	log_temp_files;
+extern double	log_sample_rate;
 
 extern int	temp_file_limit;