pg_waldump: Emit stats summary when interrupted by SIGINT

michaelpq · michaelpq · commit f2c52eeba919 · 2021-12-02T13:52:16.000+09:00
Previously, pg_waldump would not display its statistics summary if it got interrupted by SIGINT (or say a simple Ctrl+C). It gains with this commit a signal handler for SIGINT, trapping the signal to exit at the earliest convenience to allow a display of the stats summary before exiting. This makes the reports more interactive, similarly to strace -c. This new behavior makes the combination of the options --stats and --follow much more useful, so as the user will get a report for any invocation of pg_waldump in such a case. Information about the LSN range of the stats computed is added as a header to the report displayed. This implementation comes from a suggestion by Álvaro Herrera and myself, following a complaint by the author of this patch about --stats and --follow not being useful together originally. As documented, this is not supported on Windows, though its support would be possible by catching the terminal events associated to Ctrl+C, for example (this may require a more centralized implementation, as other tools could benefit from a common API). Author: Bharath Rupireddy Discussion: https://postgr.es/m/CALj2ACUUx3PcK2z9h0_m7vehreZAUbcmOky9WSEpe8TofhV=PQ@mail.gmail.com
diff --git a/doc/src/sgml/ref/pg_waldump.sgml b/doc/src/sgml/ref/pg_waldump.sgml
@@ -202,6 +202,15 @@ PostgreSQL documentation
         full-page images) instead of individual records. Optionally
         generate statistics per-record instead of per-rmgr.
        </para>
+
+       <para>
+        If <application>pg_waldump</application> is terminated by signal
+        <systemitem>SIGINT</systemitem>
+        (<keycombo action="simul"><keycap>Control</keycap><keycap>C</keycap></keycombo>,
+        the summary of the statistics computed is displayed up to the
+        termination point. This operation is not supported on
+        <productname>Windows</productname>.
+       </para>
       </listitem>
      </varlistentry>
 
diff --git a/src/bin/pg_waldump/pg_waldump.c b/src/bin/pg_waldump/pg_waldump.c
@@ -13,6 +13,7 @@
 #include "postgres.h"
 
 #include <dirent.h>
+#include <signal.h>
 #include <sys/stat.h>
 #include <unistd.h>
 
@@ -28,6 +29,7 @@
 static const char *progname;
 
 static int	WalSegSz;
+static volatile sig_atomic_t time_to_stop = false;
 
 typedef struct XLogDumpPrivate
 {
@@ -67,12 +69,27 @@ typedef struct Stats
 typedef struct XLogDumpStats
 {
 	uint64		count;
+	XLogRecPtr	startptr;
+	XLogRecPtr	endptr;
 	Stats		rmgr_stats[RM_NEXT_ID];
 	Stats		record_stats[RM_NEXT_ID][MAX_XLINFO_TYPES];
 } XLogDumpStats;
 
 #define fatal_error(...) do { pg_log_fatal(__VA_ARGS__); exit(EXIT_FAILURE); } while(0)
 
+/*
+ * When sigint is called, just tell the system to exit at the next possible
+ * moment.
+ */
+#ifndef WIN32
+
+static void
+sigint_handler(int signum)
+{
+	time_to_stop = true;
+}
+#endif
+
 static void
 print_rmgr_list(void)
 {
@@ -632,6 +649,12 @@ XLogDumpDisplayStats(XLogDumpConfig *config, XLogDumpStats *stats)
 	double		rec_len_pct,
 				fpi_len_pct;
 
+	/*
+	 * Leave if no stats have been computed yet, as tracked by the end LSN.
+	 */
+	if (XLogRecPtrIsInvalid(stats->endptr))
+		return;
+
 	/*
 	 * Each row shows its percentages of the total, so make a first pass to
 	 * calculate column totals.
@@ -645,6 +668,9 @@ XLogDumpDisplayStats(XLogDumpConfig *config, XLogDumpStats *stats)
 	}
 	total_len = total_rec_len + total_fpi_len;
 
+	printf("WAL statistics between %X/%X and %X/%X:\n",
+		   LSN_FORMAT_ARGS(stats->startptr), LSN_FORMAT_ARGS(stats->endptr));
+
 	/*
 	 * 27 is strlen("Transaction/COMMIT_PREPARED"), 20 is strlen(2^64), 8 is
 	 * strlen("(100.00%)")
@@ -794,6 +820,10 @@ main(int argc, char **argv)
 	int			option;
 	int			optindex = 0;
 
+#ifndef WIN32
+	pqsignal(SIGINT, sigint_handler);
+#endif
+
 	pg_logging_init(argv[0]);
 	set_pglocale_pgservice(argv[0], PG_TEXTDOMAIN("pg_waldump"));
 	progname = get_progname(argv[0]);
@@ -833,6 +863,9 @@ main(int argc, char **argv)
 	config.stats = false;
 	config.stats_per_record = false;
 
+	stats.startptr = InvalidXLogRecPtr;
+	stats.endptr = InvalidXLogRecPtr;
+
 	if (argc <= 1)
 	{
 		pg_log_error("no arguments specified");
@@ -1084,8 +1117,17 @@ main(int argc, char **argv)
 			   LSN_FORMAT_ARGS(first_record),
 			   (uint32) (first_record - private.startptr));
 
+	if (config.stats == true && !config.quiet)
+		stats.startptr = first_record;
+
 	for (;;)
 	{
+		if (time_to_stop)
+		{
+			/* We've been Ctrl-C'ed, so leave */
+			break;
+		}
+
 		/* try to read the next record */
 		record = XLogReadRecord(xlogreader_state, &errormsg);
 		if (!record)
@@ -1112,7 +1154,10 @@ main(int argc, char **argv)
 		if (!config.quiet)
 		{
 			if (config.stats == true)
+			{
 				XLogDumpCountRecord(&config, &stats, xlogreader_state);
+				stats.endptr = xlogreader_state->EndRecPtr;
+			}
 			else
 				XLogDumpDisplayRecord(&config, xlogreader_state);
 		}
@@ -1127,6 +1172,9 @@ main(int argc, char **argv)
 	if (config.stats == true && !config.quiet)
 		XLogDumpDisplayStats(&config, &stats);
 
+	if (time_to_stop)
+		exit(0);
+
 	if (errormsg)
 		fatal_error("error in WAL record at %X/%X: %s",
 					LSN_FORMAT_ARGS(xlogreader_state->ReadRecPtr),
