Add some simple support and documentation for using process-specific oom_adj

settings to prevent the postmaster from being OOM-killed on Linux systems.

Alex Hunsaker and Tom Lane

src/backend/postmaster/fork_process.c

@@ -7,12 +7,14 @@
  * Copyright (c) 1996-2010, PostgreSQL Global Development Group
  *
  * IDENTIFICATION
- *	  $PostgreSQL: pgsql/src/backend/postmaster/fork_process.c,v 1.10 2010/01/02 16:57:50 momjian Exp $
+ *	  $PostgreSQL: pgsql/src/backend/postmaster/fork_process.c,v 1.11 2010/01/11 18:39:32 tgl Exp $
  */
 #include "postgres.h"
 #include "postmaster/fork_process.h"
 
+#include <fcntl.h>
 #include <time.h>
+#include <sys/stat.h>
 #include <sys/time.h>
 #include <unistd.h>
 
@@ -60,6 +62,38 @@ fork_process(void)
 		setitimer(ITIMER_PROF, &prof_itimer, NULL);
 #endif
 
+		/*
+		 * By default, Linux tends to kill the postmaster in out-of-memory
+		 * situations, because it blames the postmaster for the sum of child
+		 * process sizes *including shared memory*.  (This is unbelievably
+		 * stupid, but the kernel hackers seem uninterested in improving it.)
+		 * Therefore it's often a good idea to protect the postmaster by
+		 * setting its oom_adj value negative (which has to be done in a
+		 * root-owned startup script).  If you just do that much, all child
+		 * processes will also be protected against OOM kill, which might not
+		 * be desirable.  You can then choose to build with LINUX_OOM_ADJ
+		 * #defined to 0, or some other value that you want child processes
+		 * to adopt here.
+		 */
+#ifdef LINUX_OOM_ADJ
+		{
+			/*
+			 * Use open() not stdio, to ensure we control the open flags.
+			 * Some Linux security environments reject anything but O_WRONLY.
+			 */
+			int		fd = open("/proc/self/oom_adj", O_WRONLY, 0);
+
+			/* We ignore all errors */
+			if (fd >= 0)
+			{
+				char	buf[16];
+
+				snprintf(buf, sizeof(buf), "%d\n", LINUX_OOM_ADJ);
+				(void) write(fd, buf, strlen(buf));
+				close(fd);
+			}
+		}
+#endif /* LINUX_OOM_ADJ */
 	}
 
 	return result;