Allow setting sample ratio for auto_explain

New configuration parameter auto_explain.sample_ratio makes it
possible to log just a fraction of the queries meeting the configured
threshold, to reduce the amount of logging.

Author: Craig Ringer and Julien Rouhaud
Review: Petr Jelinek

2 files changed, 46 insertions, 3 deletions

diff --git a/contrib/auto_explain/auto_explain.c b/contrib/auto_explain/auto_explain.c
index 0950e18f6d..76d1831567 100644
--- a/contrib/auto_explain/auto_explain.c
+++ b/contrib/auto_explain/auto_explain.c
@@ -29,6 +29,7 @@ static bool auto_explain_log_triggers = false;
 static bool auto_explain_log_timing = true;
 static int	auto_explain_log_format = EXPLAIN_FORMAT_TEXT;
 static bool auto_explain_log_nested_statements = false;
+static double auto_explain_sample_ratio = 1;
 
 static const struct config_enum_entry format_options[] = {
 	{"text", EXPLAIN_FORMAT_TEXT, false},
@@ -47,6 +48,9 @@ static ExecutorRun_hook_type prev_ExecutorRun = NULL;
 static ExecutorFinish_hook_type prev_ExecutorFinish = NULL;
 static ExecutorEnd_hook_type prev_ExecutorEnd = NULL;
 
+/* Is the current query sampled, per backend */
+static bool current_query_sampled = true;
+
 #define auto_explain_enabled() \
 	(auto_explain_log_min_duration >= 0 && \
 	 (nesting_level == 0 || auto_explain_log_nested_statements))
@@ -159,6 +163,19 @@ _PG_init(void)
 							 NULL,
 							 NULL);
 
+	DefineCustomRealVariable("auto_explain.sample_ratio",
+							 "Fraction of queries to process.",
+							NULL,
+							&auto_explain_sample_ratio,
+							1.0,
+							0.0,
+							1.0,
+							PGC_SUSET,
+							0,
+							NULL,
+							NULL,
+							NULL);
+
 	EmitWarningsOnPlaceholders("auto_explain");
 
 	/* Install hooks. */
@@ -191,7 +208,15 @@ _PG_fini(void)
 static void
 explain_ExecutorStart(QueryDesc *queryDesc, int eflags)
 {
-	if (auto_explain_enabled())
+	/*
+	 * For ratio sampling, randomly choose top-level statement. Either
+	 * all nested statements will be explained or none will.
+	 */
+	if (auto_explain_log_min_duration >= 0 && nesting_level == 0)
+		current_query_sampled = (random() < auto_explain_sample_ratio *
+				MAX_RANDOM_VALUE);
+
+	if (auto_explain_enabled() && current_query_sampled)
 	{
 		/* Enable per-node instrumentation iff log_analyze is required. */
 		if (auto_explain_log_analyze && (eflags & EXEC_FLAG_EXPLAIN_ONLY) == 0)
@@ -210,7 +235,7 @@ explain_ExecutorStart(QueryDesc *queryDesc, int eflags)
 	else
 		standard_ExecutorStart(queryDesc, eflags);
 
-	if (auto_explain_enabled())
+	if (auto_explain_enabled() && current_query_sampled)
 	{
 		/*
 		 * Set up to track total elapsed time in ExecutorRun.  Make sure the
@@ -280,7 +305,7 @@ explain_ExecutorFinish(QueryDesc *queryDesc)
 static void
 explain_ExecutorEnd(QueryDesc *queryDesc)
 {
-	if (queryDesc->totaltime && auto_explain_enabled())
+	if (queryDesc->totaltime && auto_explain_enabled() && current_query_sampled)
 	{
 		double		msec;
 
diff --git a/doc/src/sgml/auto-explain.sgml b/doc/src/sgml/auto-explain.sgml
index d527208271..6f1bde0d17 100644
--- a/doc/src/sgml/auto-explain.sgml
+++ b/doc/src/sgml/auto-explain.sgml
@@ -203,6 +203,24 @@ LOAD 'auto_explain';
      </para>
     </listitem>
    </varlistentry>
+
+   <varlistentry>
+    <term>
+     <varname>auto_explain.sample_ratio</varname> (<type>real</type>)
+     <indexterm>
+      <primary><varname>auto_explain.sample_ratio</> configuration parameter</primary>
+     </indexterm>
+    </term>
+    <listitem>
+     <para>
+      <varname>auto_explain.sample_ratio</varname> (<type>floating point</type>)
+      causes auto_explain to only explain a fraction of the statements in each
+      session.  The default is 1, meaning explain all the queries.  In case
+      of nested statements, either all will be explained or none. Only
+      superusers can change this setting.
+     </para>
+    </listitem>
+   </varlistentry>
   </variablelist>
 
   <para>