On systems that have setsid(2) (which should be just about everything except

Windows), arrange for each postmaster child process to be its own process
group leader, and deliver signals SIGINT, SIGTERM, SIGQUIT to the whole
process group not only the direct child process.  This provides saner behavior
for archive and recovery scripts; in particular, it's possible to shut down a
warm-standby recovery server using "pg_ctl stop -m immediate", since delivery
of SIGQUIT to the startup subprocess will result in killing the waiting
recovery_command.  Also, this makes Query Cancel and statement_timeout apply
to scripts being run from backends via system().  (There is no support in the
core backend for that, but it's widely done using untrusted PLs.)  Per gripe
from Stephen Harris and subsequent discussion.

6 files changed, 156 insertions, 40 deletions

diff --git a/src/backend/postmaster/autovacuum.c b/src/backend/postmaster/autovacuum.c
index 11552c9464..8a44f7fa57 100644
--- a/src/backend/postmaster/autovacuum.c
+++ b/src/backend/postmaster/autovacuum.c
@@ -10,7 +10,7 @@
  *
  *
  * IDENTIFICATION
- *	  $PostgreSQL: pgsql/src/backend/postmaster/autovacuum.c,v 1.28 2006/11/05 22:42:09 tgl Exp $
+ *	  $PostgreSQL: pgsql/src/backend/postmaster/autovacuum.c,v 1.29 2006/11/21 20:59:52 tgl Exp $
  *
  *-------------------------------------------------------------------------
  */
@@ -244,6 +244,17 @@ AutoVacMain(int argc, char *argv[])
 	SetProcessingMode(InitProcessing);
 
 	/*
+	 * If possible, make this process a group leader, so that the postmaster
+	 * can signal any child processes too.  (autovacuum probably never has
+	 * any child processes, but for consistency we make all postmaster
+	 * child processes do this.)
+	 */
+#ifdef HAVE_SETSID
+	if (setsid() < 0)
+		elog(FATAL, "setsid() failed: %m");
+#endif
+
+	/*
 	 * Set up signal handlers.	We operate on databases much like a regular
 	 * backend, so we use the same signal handling.  See equivalent code in
 	 * tcop/postgres.c.
diff --git a/src/backend/postmaster/bgwriter.c b/src/backend/postmaster/bgwriter.c
index f2cb3ff68d..5aa378ae70 100644
--- a/src/backend/postmaster/bgwriter.c
+++ b/src/backend/postmaster/bgwriter.c
@@ -37,7 +37,7 @@
  *
  *
  * IDENTIFICATION
- *	  $PostgreSQL: pgsql/src/backend/postmaster/bgwriter.c,v 1.30 2006/11/21 00:49:55 tgl Exp $
+ *	  $PostgreSQL: pgsql/src/backend/postmaster/bgwriter.c,v 1.31 2006/11/21 20:59:52 tgl Exp $
  *
  *-------------------------------------------------------------------------
  */
@@ -45,6 +45,7 @@
 
 #include <signal.h>
 #include <time.h>
+#include <unistd.h>
 
 #include "access/xlog_internal.h"
 #include "libpq/pqsignal.h"
@@ -171,6 +172,17 @@ BackgroundWriterMain(void)
 	am_bg_writer = true;
 
 	/*
+	 * If possible, make this process a group leader, so that the postmaster
+	 * can signal any child processes too.  (bgwriter probably never has
+	 * any child processes, but for consistency we make all postmaster
+	 * child processes do this.)
+	 */
+#ifdef HAVE_SETSID
+	if (setsid() < 0)
+		elog(FATAL, "setsid() failed: %m");
+#endif
+
+	/*
 	 * Properly accept or ignore signals the postmaster might send us
 	 *
 	 * Note: we deliberately ignore SIGTERM, because during a standard Unix
diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c
index a40bf47b3a..ba8a396c2e 100644
--- a/src/backend/postmaster/pgarch.c
+++ b/src/backend/postmaster/pgarch.c
@@ -19,7 +19,7 @@
  *
  *
  * IDENTIFICATION
- *	  $PostgreSQL: pgsql/src/backend/postmaster/pgarch.c,v 1.26 2006/11/10 22:32:20 tgl Exp $
+ *	  $PostgreSQL: pgsql/src/backend/postmaster/pgarch.c,v 1.27 2006/11/21 20:59:52 tgl Exp $
  *
  *-------------------------------------------------------------------------
  */
@@ -29,6 +29,7 @@
 #include <signal.h>
 #include <time.h>
 #include <sys/time.h>
+#include <sys/wait.h>
 #include <unistd.h>
 
 #include "access/xlog_internal.h"
@@ -223,6 +224,15 @@ PgArchiverMain(int argc, char *argv[])
 	MyProcPid = getpid();		/* reset MyProcPid */
 
 	/*
+	 * If possible, make this process a group leader, so that the postmaster
+	 * can signal any child processes too.
+	 */
+#ifdef HAVE_SETSID
+	if (setsid() < 0)
+		elog(FATAL, "setsid() failed: %m");
+#endif
+
+	/*
 	 * Ignore all signals usually bound to some action in the postmaster,
 	 * except for SIGHUP, SIGUSR1 and SIGQUIT.
 	 */
@@ -456,9 +466,22 @@ pgarch_archiveXlog(char *xlog)
 	rc = system(xlogarchcmd);
 	if (rc != 0)
 	{
-		ereport(LOG,
+		/*
+		 * If either the shell itself, or a called command, died on a signal,
+		 * abort the archiver.  We do this because system() ignores SIGINT and
+		 * SIGQUIT while waiting; so a signal is very likely something that
+		 * should have interrupted us too.  If we overreact it's no big deal,
+		 * the postmaster will just start the archiver again.
+		 *
+		 * Per the Single Unix Spec, shells report exit status > 128 when
+		 * a called command died on a signal.
+		 */
+		bool	signaled = WIFSIGNALED(rc) || WEXITSTATUS(rc) > 128;
+
+		ereport(signaled ? FATAL : LOG,
 				(errmsg("archive command \"%s\" failed: return code %d",
 						xlogarchcmd, rc)));
+
 		return false;
 	}
 	ereport(LOG,
diff --git a/src/backend/postmaster/pgstat.c b/src/backend/postmaster/pgstat.c
index db4a57b017..19a694caf3 100644
--- a/src/backend/postmaster/pgstat.c
+++ b/src/backend/postmaster/pgstat.c
@@ -13,7 +13,7 @@
  *
  *	Copyright (c) 2001-2006, PostgreSQL Global Development Group
  *
- *	$PostgreSQL: pgsql/src/backend/postmaster/pgstat.c,v 1.139 2006/10/04 00:29:56 momjian Exp $
+ *	$PostgreSQL: pgsql/src/backend/postmaster/pgstat.c,v 1.140 2006/11/21 20:59:52 tgl Exp $
  * ----------
  */
 #include "postgres.h"
@@ -1614,6 +1614,17 @@ PgstatCollectorMain(int argc, char *argv[])
 	MyProcPid = getpid();		/* reset MyProcPid */
 
 	/*
+	 * If possible, make this process a group leader, so that the postmaster
+	 * can signal any child processes too.  (pgstat probably never has
+	 * any child processes, but for consistency we make all postmaster
+	 * child processes do this.)
+	 */
+#ifdef HAVE_SETSID
+	if (setsid() < 0)
+		elog(FATAL, "setsid() failed: %m");
+#endif
+
+	/*
 	 * Ignore all signals usually bound to some action in the postmaster,
 	 * except SIGQUIT and SIGALRM.
 	 */
diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c
index 9d7b6065f4..07b5a9d854 100644
--- a/src/backend/postmaster/postmaster.c
+++ b/src/backend/postmaster/postmaster.c
@@ -37,7 +37,7 @@
  *
  *
  * IDENTIFICATION
- *	  $PostgreSQL: pgsql/src/backend/postmaster/postmaster.c,v 1.502 2006/11/21 00:49:55 tgl Exp $
+ *	  $PostgreSQL: pgsql/src/backend/postmaster/postmaster.c,v 1.503 2006/11/21 20:59:52 tgl Exp $
  *
  * NOTES
  *
@@ -268,6 +268,7 @@ static void report_fork_failure_to_client(Port *port, int errnum);
 static enum CAC_state canAcceptConnections(void);
 static long PostmasterRandom(void);
 static void RandomSalt(char *cryptSalt, char *md5Salt);
+static void signal_child(pid_t pid, int signal);
 static void SignalChildren(int signal);
 static int	CountChildren(void);
 static bool CreateOptsFile(int argc, char *argv[], char *fullprogname);
@@ -1229,7 +1230,7 @@ ServerLoop(void)
 			BgWriterPID = StartBackgroundWriter();
 			/* If shutdown is pending, set it going */
 			if (Shutdown > NoShutdown && BgWriterPID != 0)
-				kill(BgWriterPID, SIGUSR2);
+				signal_child(BgWriterPID, SIGUSR2);
 		}
 
 		/*
@@ -1639,7 +1640,7 @@ processCancelRequest(Port *port, void *pkt)
 				ereport(DEBUG2,
 						(errmsg_internal("processing cancel request: sending SIGINT to process %d",
 										 backendPID)));
-				kill(bp->pid, SIGINT);
+				signal_child(bp->pid, SIGINT);
 			}
 			else
 				/* Right PID, wrong key: no way, Jose */
@@ -1813,13 +1814,13 @@ SIGHUP_handler(SIGNAL_ARGS)
 		ProcessConfigFile(PGC_SIGHUP);
 		SignalChildren(SIGHUP);
 		if (BgWriterPID != 0)
-			kill(BgWriterPID, SIGHUP);
+			signal_child(BgWriterPID, SIGHUP);
 		if (AutoVacPID != 0)
-			kill(AutoVacPID, SIGHUP);
+			signal_child(AutoVacPID, SIGHUP);
 		if (PgArchPID != 0)
-			kill(PgArchPID, SIGHUP);
+			signal_child(PgArchPID, SIGHUP);
 		if (SysLoggerPID != 0)
-			kill(SysLoggerPID, SIGHUP);
+			signal_child(SysLoggerPID, SIGHUP);
 		/* PgStatPID does not currently need SIGHUP */
 
 		/* Reload authentication config files too */
@@ -1873,7 +1874,7 @@ pmdie(SIGNAL_ARGS)
 			if (AutoVacPID != 0)
 			{
 				/* Use statement cancel to shut it down */
-				kill(AutoVacPID, SIGINT);
+				signal_child(AutoVacPID, SIGINT);
 				break;			/* let reaper() handle this */
 			}
 
@@ -1890,13 +1891,13 @@ pmdie(SIGNAL_ARGS)
 				BgWriterPID = StartBackgroundWriter();
 			/* And tell it to shut down */
 			if (BgWriterPID != 0)
-				kill(BgWriterPID, SIGUSR2);
+				signal_child(BgWriterPID, SIGUSR2);
 			/* Tell pgarch to shut down too; nothing left for it to do */
 			if (PgArchPID != 0)
-				kill(PgArchPID, SIGQUIT);
+				signal_child(PgArchPID, SIGQUIT);
 			/* Tell pgstat to shut down too; nothing left for it to do */
 			if (PgStatPID != 0)
-				kill(PgStatPID, SIGQUIT);
+				signal_child(PgStatPID, SIGQUIT);
 			break;
 
 		case SIGINT:
@@ -1921,7 +1922,7 @@ pmdie(SIGNAL_ARGS)
 							(errmsg("aborting any active transactions")));
 					SignalChildren(SIGTERM);
 					if (AutoVacPID != 0)
-						kill(AutoVacPID, SIGTERM);
+						signal_child(AutoVacPID, SIGTERM);
 					/* reaper() does the rest */
 				}
 				break;
@@ -1940,13 +1941,13 @@ pmdie(SIGNAL_ARGS)
 				BgWriterPID = StartBackgroundWriter();
 			/* And tell it to shut down */
 			if (BgWriterPID != 0)
-				kill(BgWriterPID, SIGUSR2);
+				signal_child(BgWriterPID, SIGUSR2);
 			/* Tell pgarch to shut down too; nothing left for it to do */
 			if (PgArchPID != 0)
-				kill(PgArchPID, SIGQUIT);
+				signal_child(PgArchPID, SIGQUIT);
 			/* Tell pgstat to shut down too; nothing left for it to do */
 			if (PgStatPID != 0)
-				kill(PgStatPID, SIGQUIT);
+				signal_child(PgStatPID, SIGQUIT);
 			break;
 
 		case SIGQUIT:
@@ -1960,15 +1961,15 @@ pmdie(SIGNAL_ARGS)
 			ereport(LOG,
 					(errmsg("received immediate shutdown request")));
 			if (StartupPID != 0)
-				kill(StartupPID, SIGQUIT);
+				signal_child(StartupPID, SIGQUIT);
 			if (BgWriterPID != 0)
-				kill(BgWriterPID, SIGQUIT);
+				signal_child(BgWriterPID, SIGQUIT);
 			if (AutoVacPID != 0)
-				kill(AutoVacPID, SIGQUIT);
+				signal_child(AutoVacPID, SIGQUIT);
 			if (PgArchPID != 0)
-				kill(PgArchPID, SIGQUIT);
+				signal_child(PgArchPID, SIGQUIT);
 			if (PgStatPID != 0)
-				kill(PgStatPID, SIGQUIT);
+				signal_child(PgStatPID, SIGQUIT);
 			if (DLGetHead(BackendList))
 				SignalChildren(SIGQUIT);
 			ExitPostmaster(0);
@@ -2065,7 +2066,7 @@ reaper(SIGNAL_ARGS)
 			 * (We could, but don't, try to start autovacuum here.)
 			 */
 			if (Shutdown > NoShutdown && BgWriterPID != 0)
-				kill(BgWriterPID, SIGUSR2);
+				signal_child(BgWriterPID, SIGUSR2);
 			else if (Shutdown == NoShutdown)
 			{
 				if (XLogArchivingActive() && PgArchPID == 0)
@@ -2207,13 +2208,13 @@ reaper(SIGNAL_ARGS)
 			BgWriterPID = StartBackgroundWriter();
 		/* And tell it to shut down */
 		if (BgWriterPID != 0)
-			kill(BgWriterPID, SIGUSR2);
+			signal_child(BgWriterPID, SIGUSR2);
 		/* Tell pgarch to shut down too; nothing left for it to do */
 		if (PgArchPID != 0)
-			kill(PgArchPID, SIGQUIT);
+			signal_child(PgArchPID, SIGQUIT);
 		/* Tell pgstat to shut down too; nothing left for it to do */
 		if (PgStatPID != 0)
-			kill(PgStatPID, SIGQUIT);
+			signal_child(PgStatPID, SIGQUIT);
 	}
 
 reaper_done:
@@ -2324,7 +2325,7 @@ HandleChildCrash(int pid, int exitstatus, const char *procname)
 						(errmsg_internal("sending %s to process %d",
 										 (SendStop ? "SIGSTOP" : "SIGQUIT"),
 										 (int) bp->pid)));
-				kill(bp->pid, (SendStop ? SIGSTOP : SIGQUIT));
+				signal_child(bp->pid, (SendStop ? SIGSTOP : SIGQUIT));
 			}
 		}
 	}
@@ -2338,7 +2339,7 @@ HandleChildCrash(int pid, int exitstatus, const char *procname)
 				(errmsg_internal("sending %s to process %d",
 								 (SendStop ? "SIGSTOP" : "SIGQUIT"),
 								 (int) BgWriterPID)));
-		kill(BgWriterPID, (SendStop ? SIGSTOP : SIGQUIT));
+		signal_child(BgWriterPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
 	/* Take care of the autovacuum daemon too */
@@ -2350,7 +2351,7 @@ HandleChildCrash(int pid, int exitstatus, const char *procname)
 				(errmsg_internal("sending %s to process %d",
 								 (SendStop ? "SIGSTOP" : "SIGQUIT"),
 								 (int) AutoVacPID)));
-		kill(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT));
+		signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
 	/* Force a power-cycle of the pgarch process too */
@@ -2361,7 +2362,7 @@ HandleChildCrash(int pid, int exitstatus, const char *procname)
 				(errmsg_internal("sending %s to process %d",
 								 "SIGQUIT",
 								 (int) PgArchPID)));
-		kill(PgArchPID, SIGQUIT);
+		signal_child(PgArchPID, SIGQUIT);
 	}
 
 	/* Force a power-cycle of the pgstat process too */
@@ -2372,7 +2373,7 @@ HandleChildCrash(int pid, int exitstatus, const char *procname)
 				(errmsg_internal("sending %s to process %d",
 								 "SIGQUIT",
 								 (int) PgStatPID)));
-		kill(PgStatPID, SIGQUIT);
+		signal_child(PgStatPID, SIGQUIT);
 	}
 
 	/* We do NOT restart the syslogger */
@@ -2416,6 +2417,43 @@ LogChildExit(int lev, const char *procname, int pid, int exitstatus)
 }
 
 /*
+ * Send a signal to a postmaster child process
+ *
+ * On systems that have setsid(), each child process sets itself up as a
+ * process group leader.  For signals that are generally interpreted in the
+ * appropriate fashion, we signal the entire process group not just the
+ * direct child process.  This allows us to, for example, SIGQUIT a blocked
+ * archive_recovery script, or SIGINT a script being run by a backend via
+ * system().
+ *
+ * There is a race condition for recently-forked children: they might not
+ * have executed setsid() yet.  So we signal the child directly as well as
+ * the group.  We assume such a child will handle the signal before trying
+ * to spawn any grandchild processes.  We also assume that signaling the
+ * child twice will not cause any problems.
+ */
+static void
+signal_child(pid_t pid, int signal)
+{
+	if (kill(pid, signal) < 0)
+		elog(DEBUG3, "kill(%ld,%d) failed: %m", (long) pid, signal);
+#ifdef HAVE_SETSID
+	switch (signal)
+	{
+		case SIGINT:
+		case SIGTERM:
+		case SIGQUIT:
+		case SIGSTOP:
+			if (kill(-pid, signal) < 0)
+				elog(DEBUG3, "kill(%ld,%d) failed: %m", (long) (-pid), signal);
+			break;
+		default:
+			break;
+	}
+#endif
+}
+
+/*
  * Send a signal to all backend children (but NOT special children)
  */
 static void
@@ -2430,7 +2468,7 @@ SignalChildren(int signal)
 		ereport(DEBUG4,
 				(errmsg_internal("sending signal %d to process %d",
 								 signal, (int) bp->pid)));
-		kill(bp->pid, signal);
+		signal_child(bp->pid, signal);
 	}
 }
 
@@ -2641,7 +2679,17 @@ BackendInitialize(Port *port)
 	whereToSendOutput = DestRemote;		/* now safe to ereport to client */
 
 	/*
-	 * We arrange for a simple exit(0) if we receive SIGTERM or SIGQUIT during
+	 * If possible, make this process a group leader, so that the postmaster
+	 * can signal any child processes too.  (We do this now on the off chance
+	 * that something might spawn a child process during authentication.)
+	 */
+#ifdef HAVE_SETSID
+	if (setsid() < 0)
+		elog(FATAL, "setsid() failed: %m");
+#endif
+
+	/*
+	 * We arrange for a simple exit(1) if we receive SIGTERM or SIGQUIT during
 	 * any client authentication related communication. Otherwise the
 	 * postmaster cannot shutdown the database FAST or IMMED cleanly if a
 	 * buggy client blocks a backend during authentication.
@@ -3413,7 +3461,7 @@ sigusr1_handler(SIGNAL_ARGS)
 		{
 			SignalChildren(SIGUSR1);
 			if (AutoVacPID != 0)
-				kill(AutoVacPID, SIGUSR1);
+				signal_child(AutoVacPID, SIGUSR1);
 		}
 	}
 
@@ -3424,14 +3472,14 @@ sigusr1_handler(SIGNAL_ARGS)
 		 * Send SIGUSR1 to archiver process, to wake it up and begin archiving
 		 * next transaction log file.
 		 */
-		kill(PgArchPID, SIGUSR1);
+		signal_child(PgArchPID, SIGUSR1);
 	}
 
 	if (CheckPostmasterSignal(PMSIGNAL_ROTATE_LOGFILE) &&
 		SysLoggerPID != 0)
 	{
 		/* Tell syslogger to rotate logfile */
-		kill(SysLoggerPID, SIGUSR1);
+		signal_child(SysLoggerPID, SIGUSR1);
 	}
 
 	if (CheckPostmasterSignal(PMSIGNAL_START_AUTOVAC))
diff --git a/src/backend/postmaster/syslogger.c b/src/backend/postmaster/syslogger.c
index 23ff158fc6..3968018382 100644
--- a/src/backend/postmaster/syslogger.c
+++ b/src/backend/postmaster/syslogger.c
@@ -18,7 +18,7 @@
  *
  *
  * IDENTIFICATION
- *	  $PostgreSQL: pgsql/src/backend/postmaster/syslogger.c,v 1.28 2006/07/16 20:17:04 tgl Exp $
+ *	  $PostgreSQL: pgsql/src/backend/postmaster/syslogger.c,v 1.29 2006/11/21 20:59:52 tgl Exp $
  *
  *-------------------------------------------------------------------------
  */
@@ -183,6 +183,17 @@ SysLoggerMain(int argc, char *argv[])
 #endif
 
 	/*
+	 * If possible, make this process a group leader, so that the postmaster
+	 * can signal any child processes too.  (syslogger probably never has
+	 * any child processes, but for consistency we make all postmaster
+	 * child processes do this.)
+	 */
+#ifdef HAVE_SETSID
+	if (setsid() < 0)
+		elog(FATAL, "setsid() failed: %m");
+#endif
+
+	/*
 	 * Properly accept or ignore signals the postmaster might send us
 	 *
 	 * Note: we ignore all termination signals, and instead exit only when all