Cosmetic adjustments for postmaster's handling of checkpointer.

tglsfdc · tglsfdc · commit d0c231d13224 · 2012-05-11T17:46:37.000-04:00
Correct some comments, order some operations a bit more consistently.
No functional changes.
diff --git a/src/backend/postmaster/bgwriter.c b/src/backend/postmaster/bgwriter.c
@@ -15,9 +15,9 @@
  * The bgwriter is started by the postmaster as soon as the startup subprocess
  * finishes, or as soon as recovery begins if we are doing archive recovery.
  * It remains alive until the postmaster commands it to terminate.
- * Normal termination is by SIGUSR2, which instructs the bgwriter to exit(0).
- * Emergency termination is by SIGQUIT; like any
- * backend, the bgwriter will simply abort and exit on SIGQUIT.
+ * Normal termination is by SIGTERM, which instructs the bgwriter to exit(0).
+ * Emergency termination is by SIGQUIT; like any backend, the bgwriter will
+ * simply abort and exit on SIGQUIT.
  *
  * If the bgwriter exits unexpectedly, the postmaster treats that the same
  * as a backend crash: shared memory may be corrupted, so remaining backends
diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c
@@ -239,13 +239,13 @@ static bool RecoveryError = false;		/* T if WAL recovery failed */
  * hot standby during archive recovery.
  *
  * When the startup process is ready to start archive recovery, it signals the
- * postmaster, and we switch to PM_RECOVERY state. The background writer is
- * launched, while the startup process continues applying WAL.	If Hot Standby
- * is enabled, then, after reaching a consistent point in WAL redo, startup
- * process signals us again, and we switch to PM_HOT_STANDBY state and
- * begin accepting connections to perform read-only queries.  When archive
- * recovery is finished, the startup process exits with exit code 0 and we
- * switch to PM_RUN state.
+ * postmaster, and we switch to PM_RECOVERY state. The background writer and
+ * checkpointer are launched, while the startup process continues applying WAL.
+ * If Hot Standby is enabled, then, after reaching a consistent point in WAL
+ * redo, startup process signals us again, and we switch to PM_HOT_STANDBY
+ * state and begin accepting connections to perform read-only queries.  When
+ * archive recovery is finished, the startup process exits with exit code 0
+ * and we switch to PM_RUN state.
  *
  * Normal child backends can only be launched when we are in PM_RUN or
  * PM_HOT_STANDBY state.  (We also allow launch of normal
@@ -1038,7 +1038,7 @@ PostmasterMain(int argc, char *argv[])
 	 * handling setup of child processes.  See tcop/postgres.c,
 	 * bootstrap/bootstrap.c, postmaster/bgwriter.c, postmaster/walwriter.c,
 	 * postmaster/autovacuum.c, postmaster/pgarch.c, postmaster/pgstat.c,
-	 * postmaster/syslogger.c and postmaster/checkpointer.c
+	 * postmaster/syslogger.c and postmaster/checkpointer.c.
 	 */
 	pqinitmask();
 	PG_SETMASK(&BlockSig);
@@ -1373,10 +1373,10 @@ ServerLoop(void)
 		/*
 		 * If no background writer process is running, and we are not in a
 		 * state that prevents it, start one.  It doesn't matter if this
-		 * fails, we'll just try again later.
+		 * fails, we'll just try again later.  Likewise for the checkpointer.
 		 */
 		if (pmState == PM_RUN || pmState == PM_RECOVERY ||
-			 pmState == PM_HOT_STANDBY)
+			pmState == PM_HOT_STANDBY)
 		{
 			if (BgWriterPID == 0)
 				BgWriterPID = StartBackgroundWriter();
@@ -1386,7 +1386,8 @@ ServerLoop(void)
 
 		/*
 		 * Likewise, if we have lost the walwriter process, try to start a new
-		 * one.
+		 * one.  But this is needed only in normal operation (else we cannot
+		 * be writing any new WAL).
 		 */
 		if (WalWriterPID == 0 && pmState == PM_RUN)
 			WalWriterPID = StartWalWriter();
@@ -2131,11 +2132,12 @@ pmdie(SIGNAL_ARGS)
 				/* and the autovac launcher too */
 				if (AutoVacPID != 0)
 					signal_child(AutoVacPID, SIGTERM);
+				/* and the bgwriter too */
+				if (BgWriterPID != 0)
+					signal_child(BgWriterPID, SIGTERM);
 				/* and the walwriter too */
 				if (WalWriterPID != 0)
 					signal_child(WalWriterPID, SIGTERM);
-				if (BgWriterPID != 0)
-					signal_child(BgWriterPID, SIGTERM);
 
 				/*
 				 * If we're in recovery, we can't kill the startup process
@@ -2174,13 +2176,17 @@ pmdie(SIGNAL_ARGS)
 
 			if (StartupPID != 0)
 				signal_child(StartupPID, SIGTERM);
-			if (WalReceiverPID != 0)
-				signal_child(WalReceiverPID, SIGTERM);
 			if (BgWriterPID != 0)
 				signal_child(BgWriterPID, SIGTERM);
+			if (WalReceiverPID != 0)
+				signal_child(WalReceiverPID, SIGTERM);
 			if (pmState == PM_RECOVERY)
 			{
-				/* only checkpointer is active in this state */
+				/*
+				 * Only startup, bgwriter, and checkpointer should be active
+				 * in this state; we just signaled the first two, and we don't
+				 * want to kill checkpointer yet.
+				 */
 				pmState = PM_WAIT_BACKENDS;
 			}
 			else if (pmState == PM_RUN ||
@@ -2362,21 +2368,21 @@ reaper(SIGNAL_ARGS)
 			}
 
 			/*
-			 * Crank up background tasks, if we didn't do that already
+			 * Crank up the background tasks, if we didn't do that already
 			 * when we entered consistent recovery state.  It doesn't matter
 			 * if this fails, we'll just try again later.
 			 */
 			if (BgWriterPID == 0)
 				BgWriterPID = StartBackgroundWriter();
 			if (CheckpointerPID == 0)
 				CheckpointerPID = StartCheckpointer();
+			if (WalWriterPID == 0)
+				WalWriterPID = StartWalWriter();
 
 			/*
 			 * Likewise, start other special children as needed.  In a restart
 			 * situation, some of them may be alive already.
 			 */
-			if (WalWriterPID == 0)
-				WalWriterPID = StartWalWriter();
 			if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0)
 				AutoVacPID = StartAutoVacLauncher();
 			if (XLogArchivingActive() && PgArchPID == 0)
@@ -2392,7 +2398,9 @@ reaper(SIGNAL_ARGS)
 		}
 
 		/*
-		 * Was it the bgwriter?
+		 * Was it the bgwriter?  Normal exit can be ignored; we'll start a
+		 * new one at the next iteration of the postmaster's main loop, if
+		 * necessary.  Any other exit condition is treated as a crash.
 		 */
 		if (pid == BgWriterPID)
 		{
@@ -4228,13 +4236,13 @@ sigusr1_handler(SIGNAL_ARGS)
 		FatalError = false;
 
 		/*
-		 * Crank up the background writers.	It doesn't matter if this fails,
+		 * Crank up the background tasks.  It doesn't matter if this fails,
 		 * we'll just try again later.
 		 */
-		Assert(CheckpointerPID == 0);
-		CheckpointerPID = StartCheckpointer();
 		Assert(BgWriterPID == 0);
 		BgWriterPID = StartBackgroundWriter();
+		Assert(CheckpointerPID == 0);
+		CheckpointerPID = StartCheckpointer();
 
 		pmState = PM_RECOVERY;
 	}
