From: Justin Pryzby <pryzbyj@telsasoft.com>
Date: Fri, 13 Mar 2020 22:03:06 -0500
Subject: [PATCH v1 2/2] Include the leader PID in logfile

See also: b025f32e0b, which adds the leader PID to pg_stat_activity
---
 doc/src/sgml/config.sgml                      |  8 +++-
 src/backend/utils/error/elog.c                | 47 +++++++++++++++++++
 src/backend/utils/misc/postgresql.conf.sample |  1 +
 3 files changed, 55 insertions(+), 1 deletion(-)

diff --git a/doc/src/sgml/config.sgml b/doc/src/sgml/config.sgml
index fc0e2c00c3..d53b62e2df 100644
--- a/doc/src/sgml/config.sgml
+++ b/doc/src/sgml/config.sgml
@@ -6487,6 +6487,11 @@ local0.*    /var/log/postgresql
              <entry>Process ID</entry>
              <entry>no</entry>
             </row>
+            <row>
+             <entry><literal>%k</literal></entry>
+             <entry>Leader PID for a parallel process, NULL otherwise</entry>
+             <entry>yes</entry>
+            </row>
             <row>
              <entry><literal>%t</literal></entry>
              <entry>Time stamp without milliseconds</entry>
@@ -6777,7 +6782,7 @@ log_line_prefix = '%m [%p] %q%u@%d/%a '
         character count of the error position therein,
         location of the error in the PostgreSQL source code
         (if <varname>log_error_verbosity</varname> is set to <literal>verbose</literal>),
-        application name, and backend type.
+        application name, backend type, and leader PID.
         Here is a sample table definition for storing CSV-format log output:
 
 <programlisting>
@@ -6807,6 +6812,7 @@ CREATE TABLE postgres_log
   location text,
   application_name text,
   backend_type text,
+  leader_pid integer,
   PRIMARY KEY (session_id, session_line_num)
 );
 </programlisting>
diff --git a/src/backend/utils/error/elog.c b/src/backend/utils/error/elog.c
index 62eef7b71f..e6b3caf414 100644
--- a/src/backend/utils/error/elog.c
+++ b/src/backend/utils/error/elog.c
@@ -77,6 +77,7 @@
 #include "postmaster/syslogger.h"
 #include "storage/ipc.h"
 #include "storage/proc.h"
+#include "storage/procarray.h"
 #include "tcop/tcopprot.h"
 #include "utils/guc.h"
 #include "utils/memutils.h"
@@ -177,6 +178,7 @@ static void write_console(const char *line, int len);
 static void setup_formatted_log_time(void);
 static void setup_formatted_start_time(void);
 static const char *process_log_prefix_padding(const char *p, int *padding);
+static pid_t get_leader_pid();
 static void log_line_prefix(StringInfo buf, ErrorData *edata);
 static void write_csvlog(ErrorData *edata);
 static void send_message_to_server_log(ErrorData *edata);
@@ -2402,6 +2404,24 @@ process_log_prefix_padding(const char *p, int *ppadding)
 	return p;
 }
 
+/* Return PID of leader, or InvalidPid if not a parallel worker */
+static pid_t
+get_leader_pid()
+{
+	PGPROC	*proc;
+	pid_t	leader_pid = InvalidPid;
+
+	if (MyBackendType != B_BG_WORKER)
+		return InvalidPid;
+
+	LWLockAcquire(ProcArrayLock, LW_SHARED);
+	proc = BackendPidGetProcWithLock(MyProcPid);
+	if (proc && proc->lockGroupLeader)
+		leader_pid = proc->lockGroupLeader->pid;
+	LWLockRelease(ProcArrayLock);
+	return leader_pid;
+}
+
 /*
  * Format tag info for log lines; append to the provided buffer.
  */
@@ -2413,6 +2433,10 @@ log_line_prefix(StringInfo buf, ErrorData *edata)
 
 	/* has counter been reset in current process? */
 	static int	log_my_pid = 0;
+
+	/* Leader PID is retrieved only once per process after forking from postmaster */
+	static pid_t	leader_pid = InvalidPid;
+
 	int			padding;
 	const char *p;
 
@@ -2427,6 +2451,7 @@ log_line_prefix(StringInfo buf, ErrorData *edata)
 		log_line_number = 0;
 		log_my_pid = MyProcPid;
 		formatted_start_time[0] = '\0';
+		leader_pid = get_leader_pid();
 	}
 	log_line_number++;
 
@@ -2560,6 +2585,18 @@ log_line_prefix(StringInfo buf, ErrorData *edata)
 				else
 					appendStringInfo(buf, "%d", MyProcPid);
 				break;
+
+			case 'k':
+				if (!MyProcPort)
+					; /* Do nothing */
+				else if (leader_pid == InvalidPid)
+					; /* Do nothing */
+				else if (padding != 0)
+					appendStringInfo(buf, "%*d", padding, leader_pid);
+				else
+					appendStringInfo(buf, "%d", leader_pid);
+				break;
+
 			case 'l':
 				if (padding != 0)
 					appendStringInfo(buf, "%*ld", padding, log_line_number);
@@ -2768,6 +2805,9 @@ write_csvlog(ErrorData *edata)
 	/* has counter been reset in current process? */
 	static int	log_my_pid = 0;
 
+	/* Leader PID is retrieved only once per process after forking from postmaster */
+	static pid_t	leader_pid = InvalidPid;
+
 	/*
 	 * This is one of the few places where we'd rather not inherit a static
 	 * variable's value from the postmaster.  But since we will, reset it when
@@ -2778,6 +2818,7 @@ write_csvlog(ErrorData *edata)
 		log_line_number = 0;
 		log_my_pid = MyProcPid;
 		formatted_start_time[0] = '\0';
+		leader_pid = get_leader_pid();
 	}
 	log_line_number++;
 
@@ -2948,6 +2989,12 @@ write_csvlog(ErrorData *edata)
 	else
 		appendCSVLiteral(&buf, GetBackendTypeDesc(MyBackendType));
 
+	appendStringInfoChar(&buf, ',');
+
+	/* leader PID */
+	if (MyProcPort && leader_pid != InvalidPid)
+		appendStringInfo(&buf, "%d", leader_pid);
+
 	appendStringInfoChar(&buf, '\n');
 
 	/* If in the syslogger process, try to write messages direct to file */
diff --git a/src/backend/utils/misc/postgresql.conf.sample b/src/backend/utils/misc/postgresql.conf.sample
index c0e9531f9c..32fc4b18e6 100644
--- a/src/backend/utils/misc/postgresql.conf.sample
+++ b/src/backend/utils/misc/postgresql.conf.sample
@@ -530,6 +530,7 @@
 					#   %r = remote host and port
 					#   %h = remote host
 					#   %p = process ID
+					#   %k = leader PID
 					#   %t = timestamp without milliseconds
 					#   %m = timestamp with milliseconds
 					#   %n = timestamp with milliseconds (as a Unix epoch)
-- 
2.17.0


--QTprm0S8XgL7H0Dt--