Try to log current the query string when a backend crashes.

To avoid minimize risk inside the postmaster, we subject this feature
to a number of significant limitations.  We very much wish to avoid
doing any complex processing inside the postmaster, due to the
posssibility that the crashed backend has completely corrupted shared
memory.  To that end, no encoding conversion is done; instead, we just
replace anything that doesn't look like an ASCII character with a
question mark.  We limit the amount of data copied to 1024 characters,
and carefully sanity check the source of that data.  While these
restrictions would doubtless be unacceptable in a general-purpose
logging facility, even this limited facility seems like an improvement
over the status quo ante.

Marti Raudsepp, reviewed by PDXPUG and myself

1 files changed, 17 insertions, 5 deletions

diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c
index dd7493cf9d..5476975f76 100644
--- a/src/backend/postmaster/postmaster.c
+++ b/src/backend/postmaster/postmaster.c
@@ -2777,6 +2777,13 @@ HandleChildCrash(int pid, int exitstatus, const char *procname)
 static void
 LogChildExit(int lev, const char *procname, int pid, int exitstatus)
 {
+	char		activity_buffer[1024]; /* default track_activity_query_size */
+	const char *activity;
+
+	activity = pgstat_get_crashed_backend_activity(pid,
+												   activity_buffer,
+												   sizeof(activity_buffer));
+
 	if (WIFEXITED(exitstatus))
 		ereport(lev,
 
@@ -2784,7 +2791,8 @@ LogChildExit(int lev, const char *procname, int pid, int exitstatus)
 		  translator: %s is a noun phrase describing a child process, such as
 		  "server process" */
 				(errmsg("%s (PID %d) exited with exit code %d",
-						procname, pid, WEXITSTATUS(exitstatus))));
+						procname, pid, WEXITSTATUS(exitstatus)),
+				 errdetail("Running query: %s", activity)));
 	else if (WIFSIGNALED(exitstatus))
 #if defined(WIN32)
 		ereport(lev,
@@ -2794,7 +2802,8 @@ LogChildExit(int lev, const char *procname, int pid, int exitstatus)
 		  "server process" */
 				(errmsg("%s (PID %d) was terminated by exception 0x%X",
 						procname, pid, WTERMSIG(exitstatus)),
-				 errhint("See C include file \"ntstatus.h\" for a description of the hexadecimal value.")));
+				 errhint("See C include file \"ntstatus.h\" for a description of the hexadecimal value."),
+				 errdetail("Running query: %s", activity)));
 #elif defined(HAVE_DECL_SYS_SIGLIST) && HAVE_DECL_SYS_SIGLIST
 	ereport(lev,
 
@@ -2804,7 +2813,8 @@ LogChildExit(int lev, const char *procname, int pid, int exitstatus)
 			(errmsg("%s (PID %d) was terminated by signal %d: %s",
 					procname, pid, WTERMSIG(exitstatus),
 					WTERMSIG(exitstatus) < NSIG ?
-					sys_siglist[WTERMSIG(exitstatus)] : "(unknown)")));
+					sys_siglist[WTERMSIG(exitstatus)] : "(unknown)"),
+			 errdetail("Running query: %s", activity)));
 #else
 		ereport(lev,
 
@@ -2812,7 +2822,8 @@ LogChildExit(int lev, const char *procname, int pid, int exitstatus)
 		  translator: %s is a noun phrase describing a child process, such as
 		  "server process" */
 				(errmsg("%s (PID %d) was terminated by signal %d",
-						procname, pid, WTERMSIG(exitstatus))));
+						procname, pid, WTERMSIG(exitstatus)),
+				 errdetail("Running query: %s", activity)));
 #endif
 	else
 		ereport(lev,
@@ -2821,7 +2832,8 @@ LogChildExit(int lev, const char *procname, int pid, int exitstatus)
 		  translator: %s is a noun phrase describing a child process, such as
 		  "server process" */
 				(errmsg("%s (PID %d) exited with unrecognized status %d",
-						procname, pid, exitstatus)));
+						procname, pid, exitstatus),
+				 errdetail("Running query: %s", activity)));
 }
 
 /*