agora inbox for [email protected]  

help / color / mirror / Atom feed

[PATCH v2 1/1] Lower default value of autovacuum_worker_slots in initdb as needed.
265+ messages / 2 participants
[nested] [flat]

* [PATCH v2 1/1] Lower default value of autovacuum_worker_slots in initdb as needed.
@ 2025-01-06 23:14  Nathan Bossart <[email protected]>
  0 siblings, 0 replies; 265+ messages in thread

From: Nathan Bossart @ 2025-01-06 23:14 UTC (permalink / raw)

---
 doc/src/sgml/config.sgml                      |  5 +--
 src/backend/utils/misc/guc_tables.c           |  2 +-
 src/backend/utils/misc/postgresql.conf.sample |  2 +-
 src/bin/initdb/initdb.c                       | 34 +++++++++++++++----
 4 files changed, 33 insertions(+), 10 deletions(-)

diff --git a/doc/src/sgml/config.sgml b/doc/src/sgml/config.sgml
index 740ff5d5044..a47c4dbfcb2 100644
--- a/doc/src/sgml/config.sgml
+++ b/doc/src/sgml/config.sgml
@@ -8639,8 +8639,9 @@ COPY postgres_log FROM '/full/path/to/logfile.csv' WITH csv;
       <listitem>
        <para>
         Specifies the number of backend slots to reserve for autovacuum worker
-        processes.  The default is 16.  This parameter can only be set at server
-        start.
+        processes.  The default is typically 12 slots, but might be less if
+        your kernel settings will not support it (as determined during initdb).
+        This parameter can only be set at server start.
        </para>
        <para>
         When changing this value, consider also adjusting
diff --git a/src/backend/utils/misc/guc_tables.c b/src/backend/utils/misc/guc_tables.c
index c9d8cd796a8..8781495a622 100644
--- a/src/backend/utils/misc/guc_tables.c
+++ b/src/backend/utils/misc/guc_tables.c
@@ -3472,7 +3472,7 @@ struct config_int ConfigureNamesInt[] =
 			NULL
 		},
 		&autovacuum_worker_slots,
-		16, 1, MAX_BACKENDS,
+		12, 1, MAX_BACKENDS,
 		NULL, NULL, NULL
 	},
 	{
diff --git a/src/backend/utils/misc/postgresql.conf.sample b/src/backend/utils/misc/postgresql.conf.sample
index b2bc43383db..3405ca0e726 100644
--- a/src/backend/utils/misc/postgresql.conf.sample
+++ b/src/backend/utils/misc/postgresql.conf.sample
@@ -661,7 +661,7 @@
 
 #autovacuum = on			# Enable autovacuum subprocess?  'on'
 					# requires track_counts to also be on.
-autovacuum_worker_slots = 16	# autovacuum worker slots to allocate
+autovacuum_worker_slots = 12	# autovacuum worker slots to allocate
 					# (change requires restart)
 #autovacuum_max_workers = 3		# max number of autovacuum subprocesses
 #autovacuum_naptime = 1min		# time between autovacuum runs
diff --git a/src/bin/initdb/initdb.c b/src/bin/initdb/initdb.c
index 4e4b7ede190..b5023484771 100644
--- a/src/bin/initdb/initdb.c
+++ b/src/bin/initdb/initdb.c
@@ -196,6 +196,7 @@ static char *pgdata_native;
 
 /* defaults */
 static int	n_connections = 10;
+static int	n_av_slots = 12;
 static int	n_buffers = 50;
 static const char *dynamic_shared_memory_type = NULL;
 static const char *default_timezone = NULL;
@@ -273,7 +274,8 @@ static void check_input(char *path);
 static void write_version_file(const char *extrapath);
 static void set_null_conf(void);
 static void test_config_settings(void);
-static bool test_specific_config_settings(int test_conns, int test_buffs);
+static bool test_specific_config_settings(int test_conns, int test_av_slots,
+										  int test_buffs);
 static void setup_config(void);
 static void bootstrap_template1(void);
 static void setup_auth(FILE *cmdfd);
@@ -1118,6 +1120,12 @@ test_config_settings(void)
 	 */
 #define MIN_BUFS_FOR_CONNS(nconns)	((nconns) * 10)
 
+	/*
+	 * This macro defines the default value of autovacuum_worker_slots we want
+	 * for a given max_connections value.
+	 */
+#define AV_SLOTS_FOR_CONNS(nconns)	((nconns) / 8)
+
 	static const int trial_conns[] = {
 		100, 50, 40, 30, 25
 	};
@@ -1145,7 +1153,8 @@ test_config_settings(void)
 
 	/*
 	 * Probe for max_connections before shared_buffers, since it is subject to
-	 * more constraints than shared_buffers.
+	 * more constraints than shared_buffers.  We also choose the default
+	 * autovacuum_worker_slots here.
 	 */
 	printf(_("selecting default \"max_connections\" ... "));
 	fflush(stdout);
@@ -1154,8 +1163,9 @@ test_config_settings(void)
 	{
 		test_conns = trial_conns[i];
 		test_buffs = MIN_BUFS_FOR_CONNS(test_conns);
+		n_av_slots = AV_SLOTS_FOR_CONNS(test_conns);
 
-		if (test_specific_config_settings(test_conns, test_buffs))
+		if (test_specific_config_settings(test_conns, n_av_slots, test_buffs))
 		{
 			ok_buffers = test_buffs;
 			break;
@@ -1167,6 +1177,13 @@ test_config_settings(void)
 
 	printf("%d\n", n_connections);
 
+	/*
+	 * We chose the default for autovacuum_worker_slots during the
+	 * max_connections tests above, but we print a progress message anyway.
+	 */
+	printf(_("selecting default \"autovacuum_worker_slots\" ... %d\n"),
+		   n_av_slots);
+
 	printf(_("selecting default \"shared_buffers\" ... "));
 	fflush(stdout);
 
@@ -1180,7 +1197,7 @@ test_config_settings(void)
 			break;
 		}
 
-		if (test_specific_config_settings(n_connections, test_buffs))
+		if (test_specific_config_settings(n_connections, n_av_slots, test_buffs))
 			break;
 	}
 	n_buffers = test_buffs;
@@ -1200,7 +1217,7 @@ test_config_settings(void)
  * Test a specific combination of configuration settings.
  */
 static bool
-test_specific_config_settings(int test_conns, int test_buffs)
+test_specific_config_settings(int test_conns, int test_av_slots, int test_buffs)
 {
 	PQExpBufferData cmd;
 	_stringlist *gnames,
@@ -1213,10 +1230,11 @@ test_specific_config_settings(int test_conns, int test_buffs)
 	printfPQExpBuffer(&cmd,
 					  "\"%s\" --check %s %s "
 					  "-c max_connections=%d "
+					  "-c autovacuum_worker_slots=%d "
 					  "-c shared_buffers=%d "
 					  "-c dynamic_shared_memory_type=%s",
 					  backend_exec, boot_options, extra_options,
-					  test_conns, test_buffs,
+					  test_conns, test_av_slots, test_buffs,
 					  dynamic_shared_memory_type);
 
 	/* Add any user-given setting overrides */
@@ -1280,6 +1298,10 @@ setup_config(void)
 	conflines = replace_guc_value(conflines, "max_connections",
 								  repltok, false);
 
+	snprintf(repltok, sizeof(repltok), "%d", n_av_slots);
+	conflines = replace_guc_value(conflines, "autovacuum_worker_slots",
+								  repltok, false);
+
 	if ((n_buffers * (BLCKSZ / 1024)) % 1024 == 0)
 		snprintf(repltok, sizeof(repltok), "%dMB",
 				 (n_buffers * (BLCKSZ / 1024)) / 1024);
-- 
2.39.5 (Apple Git-154)


--Pf5SPdkAJilNBD4g--





^ permalink  raw  reply  [nested|flat] 265+ messages in thread

* [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source
@ 2025-07-27 15:48  Lukas Fittl <[email protected]>
  0 siblings, 0 replies; 265+ messages in thread

From: Lukas Fittl @ 2025-07-27 15:48 UTC (permalink / raw)

In passing also reduce the per-loop overhead caused by repeated divisions
in INSTR_TIME_GET_NANOSEC when the ticks variable has become very large,
instead diff first and then turn it into nanosecs.
---
 src/bin/pg_test_timing/pg_test_timing.c | 59 +++++++++++++++++++------
 src/include/portability/instr_time.h    | 30 ++++++++-----
 2 files changed, 65 insertions(+), 24 deletions(-)

diff --git a/src/bin/pg_test_timing/pg_test_timing.c b/src/bin/pg_test_timing/pg_test_timing.c
index a5621251afc..b77ef2063b6 100644
--- a/src/bin/pg_test_timing/pg_test_timing.c
+++ b/src/bin/pg_test_timing/pg_test_timing.c
@@ -16,6 +16,7 @@ static const char *progname;
 
 static unsigned int test_duration = 3;
 static double max_rprct = 99.99;
+static bool fast_timing = false;
 
 /* record duration in powers of 2 nanoseconds */
 static long long int histogram[32];
@@ -56,6 +57,7 @@ handle_args(int argc, char *argv[])
 	static struct option long_options[] = {
 		{"duration", required_argument, NULL, 'd'},
 		{"cutoff", required_argument, NULL, 'c'},
+		{"fast", no_argument, NULL, 'f'},
 		{NULL, 0, NULL, 0}
 	};
 
@@ -68,7 +70,7 @@ handle_args(int argc, char *argv[])
 	{
 		if (strcmp(argv[1], "--help") == 0 || strcmp(argv[1], "-?") == 0)
 		{
-			printf(_("Usage: %s [-d DURATION] [-c CUTOFF]\n"), progname);
+			printf(_("Usage: %s [-d DURATION] [-c CUTOFF] [--fast]\n"), progname);
 			exit(0);
 		}
 		if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0)
@@ -78,7 +80,7 @@ handle_args(int argc, char *argv[])
 		}
 	}
 
-	while ((option = getopt_long(argc, argv, "d:c:",
+	while ((option = getopt_long(argc, argv, "d:c:f:",
 								 long_options, &optindex)) != -1)
 	{
 		switch (option)
@@ -125,6 +127,10 @@ handle_args(int argc, char *argv[])
 				}
 				break;
 
+			case 'f':
+				fast_timing = true;
+				break;
+
 			default:
 				fprintf(stderr, _("Try \"%s --help\" for more information.\n"),
 						progname);
@@ -155,11 +161,31 @@ test_timing(unsigned int duration)
 	uint64		total_time;
 	int64		time_elapsed = 0;
 	uint64		loop_count = 0;
-	uint64		prev,
-				cur;
 	instr_time	start_time,
 				end_time,
-				temp;
+				prev,
+				cur;
+	char	   *time_source = NULL;
+	bool		fast_timing_used = false;
+
+	INSTR_TIME_INITIALIZE();
+
+#if !defined(WIN32) && defined(__x86_64__) && defined(__linux__)
+	if (fast_timing && has_rdtsc)
+	{
+		time_source = "RDTSC";
+		fast_timing_used = true;
+	}
+	else if (has_rdtscp)
+		time_source = "RDTSCP";
+	else
+		time_source = PG_INSTR_CLOCK_NAME;
+#else
+	time_source = PG_INSTR_CLOCK_NAME;
+#endif
+	if (fast_timing && !fast_timing_used)
+		printf(_("Warning: Fast timing requested, but not available - regular timing source will be used\n"));
+	printf(_("Time source: %s\n"), time_source);
 
 	/*
 	 * Pre-zero the statistics data structures.  They're already zero by
@@ -173,8 +199,11 @@ test_timing(unsigned int duration)
 
 	total_time = duration > 0 ? duration * INT64CONST(1000000000) : 0;
 
-	INSTR_TIME_SET_CURRENT(start_time);
-	cur = INSTR_TIME_GET_NANOSEC(start_time);
+	if (fast_timing)
+		INSTR_TIME_SET_CURRENT_FAST(start_time);
+	else
+		INSTR_TIME_SET_CURRENT(start_time);
+	cur = start_time;
 
 	while (time_elapsed < total_time)
 	{
@@ -182,9 +211,11 @@ test_timing(unsigned int duration)
 					bits;
 
 		prev = cur;
-		INSTR_TIME_SET_CURRENT(temp);
-		cur = INSTR_TIME_GET_NANOSEC(temp);
-		diff = cur - prev;
+		if (fast_timing)
+			INSTR_TIME_SET_CURRENT_FAST(cur);
+		else
+			INSTR_TIME_SET_CURRENT(cur);
+		diff = INSTR_TIME_DIFF_NANOSEC(cur, prev);
 
 		/* Did time go backwards? */
 		if (unlikely(diff < 0))
@@ -217,11 +248,13 @@ test_timing(unsigned int duration)
 			largest_diff_count++;
 
 		loop_count++;
-		INSTR_TIME_SUBTRACT(temp, start_time);
-		time_elapsed = INSTR_TIME_GET_NANOSEC(temp);
+		time_elapsed = INSTR_TIME_DIFF_NANOSEC(cur, start_time);
 	}
 
-	INSTR_TIME_SET_CURRENT(end_time);
+	if (fast_timing)
+		INSTR_TIME_SET_CURRENT_FAST(end_time);
+	else
+		INSTR_TIME_SET_CURRENT(end_time);
 
 	INSTR_TIME_SUBTRACT(end_time, start_time);
 
diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h
index e2e339a0c4f..f02296f1026 100644
--- a/src/include/portability/instr_time.h
+++ b/src/include/portability/instr_time.h
@@ -112,10 +112,13 @@ extern int64 max_ticks_no_overflow;
  */
 #if defined(__darwin__) && defined(CLOCK_MONOTONIC_RAW)
 #define PG_INSTR_CLOCK	CLOCK_MONOTONIC_RAW
+#define PG_INSTR_CLOCK_NAME	"clock_gettime (CLOCK_MONOTONIC_RAW)"
 #elif defined(CLOCK_MONOTONIC)
 #define PG_INSTR_CLOCK	CLOCK_MONOTONIC
+#define PG_INSTR_CLOCK_NAME	"clock_gettime (CLOCK_MONOTONIC)"
 #else
 #define PG_INSTR_CLOCK	CLOCK_REALTIME
+#define PG_INSTR_CLOCK_NAME	"clock_gettime (CLOCK_REALTIME)"
 #endif
 
 #if defined(__x86_64__) && defined(__linux__)
@@ -174,7 +177,7 @@ pg_get_ticks(void)
 }
 
 static inline int64_t
-pg_ticks_to_ns(instr_time t)
+pg_ticks_to_ns(int64 ticks)
 {
 	/*
 	 * Would multiplication overflow? If so perform computation in two parts.
@@ -183,7 +186,7 @@ pg_ticks_to_ns(instr_time t)
 	 */
 	int64		ns = 0;
 
-	if (unlikely(t.ticks > max_ticks_no_overflow))
+	if (unlikely(ticks > max_ticks_no_overflow))
 	{
 		/*
 		 * Compute how often the maximum number of ticks fits completely into
@@ -192,7 +195,7 @@ pg_ticks_to_ns(instr_time t)
 		 * value. In a 2nd step we adjust the number of elapsed ticks and
 		 * convert the remaining ticks.
 		 */
-		int64		count = t.ticks / max_ticks_no_overflow;
+		int64		count = ticks / max_ticks_no_overflow;
 		int64		max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION;
 
 		ns = max_ns * count;
@@ -201,11 +204,11 @@ pg_ticks_to_ns(instr_time t)
 		 * Subtract the ticks that we now already accounted for, so that they
 		 * don't get counted twice.
 		 */
-		t.ticks -= count * max_ticks_no_overflow;
-		Assert(t.ticks >= 0);
+		ticks -= count * max_ticks_no_overflow;
+		Assert(ticks >= 0);
 	}
 
-	ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION;
+	ns += ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION;
 	return ns;
 }
 
@@ -226,14 +229,14 @@ pg_initialize_get_ticks()
 #define INSTR_TIME_SET_CURRENT(t) \
 	((t) = pg_get_ticks())
 
-#define INSTR_TIME_GET_NANOSEC(t) \
-	pg_ticks_to_ns(t)
-
+#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \
+	(pg_ticks_to_ns(ticks))
 
 #else							/* WIN32 */
 
 
 /* Use QueryPerformanceCounter() */
+#define PG_INSTR_CLOCK_NAME	"QueryPerformanceCounter"
 
 /* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */
 static inline instr_time
@@ -265,8 +268,8 @@ GetTimerFrequency(void)
 #define INSTR_TIME_SET_CURRENT(t) \
 	((t) = pg_query_performance_counter())
 
-#define INSTR_TIME_GET_NANOSEC(t) \
-	((int64) ((t).ticks * ((double) NS_PER_S / GetTimerFrequency())))
+#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \
+	((int64) ((ticks) * ((double) NS_PER_S / GetTimerFrequency())))
 
 #endif							/* WIN32 */
 
@@ -285,9 +288,14 @@ GetTimerFrequency(void)
 #define INSTR_TIME_SUBTRACT(x,y) \
 	((x).ticks -= (y).ticks)
 
+#define INSTR_TIME_DIFF_NANOSEC(x,y) \
+	(INSTR_TIME_TICKS_TO_NANOSEC((x).ticks - (y).ticks))
+
 #define INSTR_TIME_ACCUM_DIFF(x,y,z) \
 	((x).ticks += (y).ticks - (z).ticks)
 
+#define INSTR_TIME_GET_NANOSEC(t) \
+	(INSTR_TIME_TICKS_TO_NANOSEC((t).ticks))
 
 #define INSTR_TIME_GET_DOUBLE(t) \
 	((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S)
-- 
2.47.3


--vtqqtrpooseurzip--





^ permalink  raw  reply  [nested|flat] 265+ messages in thread

* [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source
@ 2025-07-27 15:48  Lukas Fittl <[email protected]>
  0 siblings, 0 replies; 265+ messages in thread

From: Lukas Fittl @ 2025-07-27 15:48 UTC (permalink / raw)

In passing also reduce the per-loop overhead caused by repeated divisions
in INSTR_TIME_GET_NANOSEC when the ticks variable has become very large,
instead diff first and then turn it into nanosecs.
---
 src/bin/pg_test_timing/pg_test_timing.c | 59 +++++++++++++++++++------
 src/include/portability/instr_time.h    | 30 ++++++++-----
 2 files changed, 65 insertions(+), 24 deletions(-)

diff --git a/src/bin/pg_test_timing/pg_test_timing.c b/src/bin/pg_test_timing/pg_test_timing.c
index a5621251afc..b77ef2063b6 100644
--- a/src/bin/pg_test_timing/pg_test_timing.c
+++ b/src/bin/pg_test_timing/pg_test_timing.c
@@ -16,6 +16,7 @@ static const char *progname;
 
 static unsigned int test_duration = 3;
 static double max_rprct = 99.99;
+static bool fast_timing = false;
 
 /* record duration in powers of 2 nanoseconds */
 static long long int histogram[32];
@@ -56,6 +57,7 @@ handle_args(int argc, char *argv[])
 	static struct option long_options[] = {
 		{"duration", required_argument, NULL, 'd'},
 		{"cutoff", required_argument, NULL, 'c'},
+		{"fast", no_argument, NULL, 'f'},
 		{NULL, 0, NULL, 0}
 	};
 
@@ -68,7 +70,7 @@ handle_args(int argc, char *argv[])
 	{
 		if (strcmp(argv[1], "--help") == 0 || strcmp(argv[1], "-?") == 0)
 		{
-			printf(_("Usage: %s [-d DURATION] [-c CUTOFF]\n"), progname);
+			printf(_("Usage: %s [-d DURATION] [-c CUTOFF] [--fast]\n"), progname);
 			exit(0);
 		}
 		if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0)
@@ -78,7 +80,7 @@ handle_args(int argc, char *argv[])
 		}
 	}
 
-	while ((option = getopt_long(argc, argv, "d:c:",
+	while ((option = getopt_long(argc, argv, "d:c:f:",
 								 long_options, &optindex)) != -1)
 	{
 		switch (option)
@@ -125,6 +127,10 @@ handle_args(int argc, char *argv[])
 				}
 				break;
 
+			case 'f':
+				fast_timing = true;
+				break;
+
 			default:
 				fprintf(stderr, _("Try \"%s --help\" for more information.\n"),
 						progname);
@@ -155,11 +161,31 @@ test_timing(unsigned int duration)
 	uint64		total_time;
 	int64		time_elapsed = 0;
 	uint64		loop_count = 0;
-	uint64		prev,
-				cur;
 	instr_time	start_time,
 				end_time,
-				temp;
+				prev,
+				cur;
+	char	   *time_source = NULL;
+	bool		fast_timing_used = false;
+
+	INSTR_TIME_INITIALIZE();
+
+#if !defined(WIN32) && defined(__x86_64__) && defined(__linux__)
+	if (fast_timing && has_rdtsc)
+	{
+		time_source = "RDTSC";
+		fast_timing_used = true;
+	}
+	else if (has_rdtscp)
+		time_source = "RDTSCP";
+	else
+		time_source = PG_INSTR_CLOCK_NAME;
+#else
+	time_source = PG_INSTR_CLOCK_NAME;
+#endif
+	if (fast_timing && !fast_timing_used)
+		printf(_("Warning: Fast timing requested, but not available - regular timing source will be used\n"));
+	printf(_("Time source: %s\n"), time_source);
 
 	/*
 	 * Pre-zero the statistics data structures.  They're already zero by
@@ -173,8 +199,11 @@ test_timing(unsigned int duration)
 
 	total_time = duration > 0 ? duration * INT64CONST(1000000000) : 0;
 
-	INSTR_TIME_SET_CURRENT(start_time);
-	cur = INSTR_TIME_GET_NANOSEC(start_time);
+	if (fast_timing)
+		INSTR_TIME_SET_CURRENT_FAST(start_time);
+	else
+		INSTR_TIME_SET_CURRENT(start_time);
+	cur = start_time;
 
 	while (time_elapsed < total_time)
 	{
@@ -182,9 +211,11 @@ test_timing(unsigned int duration)
 					bits;
 
 		prev = cur;
-		INSTR_TIME_SET_CURRENT(temp);
-		cur = INSTR_TIME_GET_NANOSEC(temp);
-		diff = cur - prev;
+		if (fast_timing)
+			INSTR_TIME_SET_CURRENT_FAST(cur);
+		else
+			INSTR_TIME_SET_CURRENT(cur);
+		diff = INSTR_TIME_DIFF_NANOSEC(cur, prev);
 
 		/* Did time go backwards? */
 		if (unlikely(diff < 0))
@@ -217,11 +248,13 @@ test_timing(unsigned int duration)
 			largest_diff_count++;
 
 		loop_count++;
-		INSTR_TIME_SUBTRACT(temp, start_time);
-		time_elapsed = INSTR_TIME_GET_NANOSEC(temp);
+		time_elapsed = INSTR_TIME_DIFF_NANOSEC(cur, start_time);
 	}
 
-	INSTR_TIME_SET_CURRENT(end_time);
+	if (fast_timing)
+		INSTR_TIME_SET_CURRENT_FAST(end_time);
+	else
+		INSTR_TIME_SET_CURRENT(end_time);
 
 	INSTR_TIME_SUBTRACT(end_time, start_time);
 
diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h
index e2e339a0c4f..f02296f1026 100644
--- a/src/include/portability/instr_time.h
+++ b/src/include/portability/instr_time.h
@@ -112,10 +112,13 @@ extern int64 max_ticks_no_overflow;
  */
 #if defined(__darwin__) && defined(CLOCK_MONOTONIC_RAW)
 #define PG_INSTR_CLOCK	CLOCK_MONOTONIC_RAW
+#define PG_INSTR_CLOCK_NAME	"clock_gettime (CLOCK_MONOTONIC_RAW)"
 #elif defined(CLOCK_MONOTONIC)
 #define PG_INSTR_CLOCK	CLOCK_MONOTONIC
+#define PG_INSTR_CLOCK_NAME	"clock_gettime (CLOCK_MONOTONIC)"
 #else
 #define PG_INSTR_CLOCK	CLOCK_REALTIME
+#define PG_INSTR_CLOCK_NAME	"clock_gettime (CLOCK_REALTIME)"
 #endif
 
 #if defined(__x86_64__) && defined(__linux__)
@@ -174,7 +177,7 @@ pg_get_ticks(void)
 }
 
 static inline int64_t
-pg_ticks_to_ns(instr_time t)
+pg_ticks_to_ns(int64 ticks)
 {
 	/*
 	 * Would multiplication overflow? If so perform computation in two parts.
@@ -183,7 +186,7 @@ pg_ticks_to_ns(instr_time t)
 	 */
 	int64		ns = 0;
 
-	if (unlikely(t.ticks > max_ticks_no_overflow))
+	if (unlikely(ticks > max_ticks_no_overflow))
 	{
 		/*
 		 * Compute how often the maximum number of ticks fits completely into
@@ -192,7 +195,7 @@ pg_ticks_to_ns(instr_time t)
 		 * value. In a 2nd step we adjust the number of elapsed ticks and
 		 * convert the remaining ticks.
 		 */
-		int64		count = t.ticks / max_ticks_no_overflow;
+		int64		count = ticks / max_ticks_no_overflow;
 		int64		max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION;
 
 		ns = max_ns * count;
@@ -201,11 +204,11 @@ pg_ticks_to_ns(instr_time t)
 		 * Subtract the ticks that we now already accounted for, so that they
 		 * don't get counted twice.
 		 */
-		t.ticks -= count * max_ticks_no_overflow;
-		Assert(t.ticks >= 0);
+		ticks -= count * max_ticks_no_overflow;
+		Assert(ticks >= 0);
 	}
 
-	ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION;
+	ns += ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION;
 	return ns;
 }
 
@@ -226,14 +229,14 @@ pg_initialize_get_ticks()
 #define INSTR_TIME_SET_CURRENT(t) \
 	((t) = pg_get_ticks())
 
-#define INSTR_TIME_GET_NANOSEC(t) \
-	pg_ticks_to_ns(t)
-
+#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \
+	(pg_ticks_to_ns(ticks))
 
 #else							/* WIN32 */
 
 
 /* Use QueryPerformanceCounter() */
+#define PG_INSTR_CLOCK_NAME	"QueryPerformanceCounter"
 
 /* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */
 static inline instr_time
@@ -265,8 +268,8 @@ GetTimerFrequency(void)
 #define INSTR_TIME_SET_CURRENT(t) \
 	((t) = pg_query_performance_counter())
 
-#define INSTR_TIME_GET_NANOSEC(t) \
-	((int64) ((t).ticks * ((double) NS_PER_S / GetTimerFrequency())))
+#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \
+	((int64) ((ticks) * ((double) NS_PER_S / GetTimerFrequency())))
 
 #endif							/* WIN32 */
 
@@ -285,9 +288,14 @@ GetTimerFrequency(void)
 #define INSTR_TIME_SUBTRACT(x,y) \
 	((x).ticks -= (y).ticks)
 
+#define INSTR_TIME_DIFF_NANOSEC(x,y) \
+	(INSTR_TIME_TICKS_TO_NANOSEC((x).ticks - (y).ticks))
+
 #define INSTR_TIME_ACCUM_DIFF(x,y,z) \
 	((x).ticks += (y).ticks - (z).ticks)
 
+#define INSTR_TIME_GET_NANOSEC(t) \
+	(INSTR_TIME_TICKS_TO_NANOSEC((t).ticks))
 
 #define INSTR_TIME_GET_DOUBLE(t) \
 	((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S)
-- 
2.47.3


--vtqqtrpooseurzip--





^ permalink  raw  reply  [nested|flat] 265+ messages in thread

* [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source
@ 2025-07-27 15:48  Lukas Fittl <[email protected]>
  0 siblings, 0 replies; 265+ messages in thread

From: Lukas Fittl @ 2025-07-27 15:48 UTC (permalink / raw)

In passing also reduce the per-loop overhead caused by repeated divisions
in INSTR_TIME_GET_NANOSEC when the ticks variable has become very large,
instead diff first and then turn it into nanosecs.
---
 src/bin/pg_test_timing/pg_test_timing.c | 59 +++++++++++++++++++------
 src/include/portability/instr_time.h    | 30 ++++++++-----
 2 files changed, 65 insertions(+), 24 deletions(-)

diff --git a/src/bin/pg_test_timing/pg_test_timing.c b/src/bin/pg_test_timing/pg_test_timing.c
index a5621251afc..b77ef2063b6 100644
--- a/src/bin/pg_test_timing/pg_test_timing.c
+++ b/src/bin/pg_test_timing/pg_test_timing.c
@@ -16,6 +16,7 @@ static const char *progname;
 
 static unsigned int test_duration = 3;
 static double max_rprct = 99.99;
+static bool fast_timing = false;
 
 /* record duration in powers of 2 nanoseconds */
 static long long int histogram[32];
@@ -56,6 +57,7 @@ handle_args(int argc, char *argv[])
 	static struct option long_options[] = {
 		{"duration", required_argument, NULL, 'd'},
 		{"cutoff", required_argument, NULL, 'c'},
+		{"fast", no_argument, NULL, 'f'},
 		{NULL, 0, NULL, 0}
 	};
 
@@ -68,7 +70,7 @@ handle_args(int argc, char *argv[])
 	{
 		if (strcmp(argv[1], "--help") == 0 || strcmp(argv[1], "-?") == 0)
 		{
-			printf(_("Usage: %s [-d DURATION] [-c CUTOFF]\n"), progname);
+			printf(_("Usage: %s [-d DURATION] [-c CUTOFF] [--fast]\n"), progname);
 			exit(0);
 		}
 		if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0)
@@ -78,7 +80,7 @@ handle_args(int argc, char *argv[])
 		}
 	}
 
-	while ((option = getopt_long(argc, argv, "d:c:",
+	while ((option = getopt_long(argc, argv, "d:c:f:",
 								 long_options, &optindex)) != -1)
 	{
 		switch (option)
@@ -125,6 +127,10 @@ handle_args(int argc, char *argv[])
 				}
 				break;
 
+			case 'f':
+				fast_timing = true;
+				break;
+
 			default:
 				fprintf(stderr, _("Try \"%s --help\" for more information.\n"),
 						progname);
@@ -155,11 +161,31 @@ test_timing(unsigned int duration)
 	uint64		total_time;
 	int64		time_elapsed = 0;
 	uint64		loop_count = 0;
-	uint64		prev,
-				cur;
 	instr_time	start_time,
 				end_time,
-				temp;
+				prev,
+				cur;
+	char	   *time_source = NULL;
+	bool		fast_timing_used = false;
+
+	INSTR_TIME_INITIALIZE();
+
+#if !defined(WIN32) && defined(__x86_64__) && defined(__linux__)
+	if (fast_timing && has_rdtsc)
+	{
+		time_source = "RDTSC";
+		fast_timing_used = true;
+	}
+	else if (has_rdtscp)
+		time_source = "RDTSCP";
+	else
+		time_source = PG_INSTR_CLOCK_NAME;
+#else
+	time_source = PG_INSTR_CLOCK_NAME;
+#endif
+	if (fast_timing && !fast_timing_used)
+		printf(_("Warning: Fast timing requested, but not available - regular timing source will be used\n"));
+	printf(_("Time source: %s\n"), time_source);
 
 	/*
 	 * Pre-zero the statistics data structures.  They're already zero by
@@ -173,8 +199,11 @@ test_timing(unsigned int duration)
 
 	total_time = duration > 0 ? duration * INT64CONST(1000000000) : 0;
 
-	INSTR_TIME_SET_CURRENT(start_time);
-	cur = INSTR_TIME_GET_NANOSEC(start_time);
+	if (fast_timing)
+		INSTR_TIME_SET_CURRENT_FAST(start_time);
+	else
+		INSTR_TIME_SET_CURRENT(start_time);
+	cur = start_time;
 
 	while (time_elapsed < total_time)
 	{
@@ -182,9 +211,11 @@ test_timing(unsigned int duration)
 					bits;
 
 		prev = cur;
-		INSTR_TIME_SET_CURRENT(temp);
-		cur = INSTR_TIME_GET_NANOSEC(temp);
-		diff = cur - prev;
+		if (fast_timing)
+			INSTR_TIME_SET_CURRENT_FAST(cur);
+		else
+			INSTR_TIME_SET_CURRENT(cur);
+		diff = INSTR_TIME_DIFF_NANOSEC(cur, prev);
 
 		/* Did time go backwards? */
 		if (unlikely(diff < 0))
@@ -217,11 +248,13 @@ test_timing(unsigned int duration)
 			largest_diff_count++;
 
 		loop_count++;
-		INSTR_TIME_SUBTRACT(temp, start_time);
-		time_elapsed = INSTR_TIME_GET_NANOSEC(temp);
+		time_elapsed = INSTR_TIME_DIFF_NANOSEC(cur, start_time);
 	}
 
-	INSTR_TIME_SET_CURRENT(end_time);
+	if (fast_timing)
+		INSTR_TIME_SET_CURRENT_FAST(end_time);
+	else
+		INSTR_TIME_SET_CURRENT(end_time);
 
 	INSTR_TIME_SUBTRACT(end_time, start_time);
 
diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h
index e2e339a0c4f..f02296f1026 100644
--- a/src/include/portability/instr_time.h
+++ b/src/include/portability/instr_time.h
@@ -112,10 +112,13 @@ extern int64 max_ticks_no_overflow;
  */
 #if defined(__darwin__) && defined(CLOCK_MONOTONIC_RAW)
 #define PG_INSTR_CLOCK	CLOCK_MONOTONIC_RAW
+#define PG_INSTR_CLOCK_NAME	"clock_gettime (CLOCK_MONOTONIC_RAW)"
 #elif defined(CLOCK_MONOTONIC)
 #define PG_INSTR_CLOCK	CLOCK_MONOTONIC
+#define PG_INSTR_CLOCK_NAME	"clock_gettime (CLOCK_MONOTONIC)"
 #else
 #define PG_INSTR_CLOCK	CLOCK_REALTIME
+#define PG_INSTR_CLOCK_NAME	"clock_gettime (CLOCK_REALTIME)"
 #endif
 
 #if defined(__x86_64__) && defined(__linux__)
@@ -174,7 +177,7 @@ pg_get_ticks(void)
 }
 
 static inline int64_t
-pg_ticks_to_ns(instr_time t)
+pg_ticks_to_ns(int64 ticks)
 {
 	/*
 	 * Would multiplication overflow? If so perform computation in two parts.
@@ -183,7 +186,7 @@ pg_ticks_to_ns(instr_time t)
 	 */
 	int64		ns = 0;
 
-	if (unlikely(t.ticks > max_ticks_no_overflow))
+	if (unlikely(ticks > max_ticks_no_overflow))
 	{
 		/*
 		 * Compute how often the maximum number of ticks fits completely into
@@ -192,7 +195,7 @@ pg_ticks_to_ns(instr_time t)
 		 * value. In a 2nd step we adjust the number of elapsed ticks and
 		 * convert the remaining ticks.
 		 */
-		int64		count = t.ticks / max_ticks_no_overflow;
+		int64		count = ticks / max_ticks_no_overflow;
 		int64		max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION;
 
 		ns = max_ns * count;
@@ -201,11 +204,11 @@ pg_ticks_to_ns(instr_time t)
 		 * Subtract the ticks that we now already accounted for, so that they
 		 * don't get counted twice.
 		 */
-		t.ticks -= count * max_ticks_no_overflow;
-		Assert(t.ticks >= 0);
+		ticks -= count * max_ticks_no_overflow;
+		Assert(ticks >= 0);
 	}
 
-	ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION;
+	ns += ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION;
 	return ns;
 }
 
@@ -226,14 +229,14 @@ pg_initialize_get_ticks()
 #define INSTR_TIME_SET_CURRENT(t) \
 	((t) = pg_get_ticks())
 
-#define INSTR_TIME_GET_NANOSEC(t) \
-	pg_ticks_to_ns(t)
-
+#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \
+	(pg_ticks_to_ns(ticks))
 
 #else							/* WIN32 */
 
 
 /* Use QueryPerformanceCounter() */
+#define PG_INSTR_CLOCK_NAME	"QueryPerformanceCounter"
 
 /* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */
 static inline instr_time
@@ -265,8 +268,8 @@ GetTimerFrequency(void)
 #define INSTR_TIME_SET_CURRENT(t) \
 	((t) = pg_query_performance_counter())
 
-#define INSTR_TIME_GET_NANOSEC(t) \
-	((int64) ((t).ticks * ((double) NS_PER_S / GetTimerFrequency())))
+#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \
+	((int64) ((ticks) * ((double) NS_PER_S / GetTimerFrequency())))
 
 #endif							/* WIN32 */
 
@@ -285,9 +288,14 @@ GetTimerFrequency(void)
 #define INSTR_TIME_SUBTRACT(x,y) \
 	((x).ticks -= (y).ticks)
 
+#define INSTR_TIME_DIFF_NANOSEC(x,y) \
+	(INSTR_TIME_TICKS_TO_NANOSEC((x).ticks - (y).ticks))
+
 #define INSTR_TIME_ACCUM_DIFF(x,y,z) \
 	((x).ticks += (y).ticks - (z).ticks)
 
+#define INSTR_TIME_GET_NANOSEC(t) \
+	(INSTR_TIME_TICKS_TO_NANOSEC((t).ticks))
 
 #define INSTR_TIME_GET_DOUBLE(t) \
 	((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S)
-- 
2.47.3


--vtqqtrpooseurzip--





^ permalink  raw  reply  [nested|flat] 265+ messages in thread

* [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source
@ 2025-07-27 15:48  Lukas Fittl <[email protected]>
  0 siblings, 0 replies; 265+ messages in thread

From: Lukas Fittl @ 2025-07-27 15:48 UTC (permalink / raw)

In passing also reduce the per-loop overhead caused by repeated divisions
in INSTR_TIME_GET_NANOSEC when the ticks variable has become very large,
instead diff first and then turn it into nanosecs.
---
 src/bin/pg_test_timing/pg_test_timing.c | 59 +++++++++++++++++++------
 src/include/portability/instr_time.h    | 30 ++++++++-----
 2 files changed, 65 insertions(+), 24 deletions(-)

diff --git a/src/bin/pg_test_timing/pg_test_timing.c b/src/bin/pg_test_timing/pg_test_timing.c
index a5621251afc..b77ef2063b6 100644
--- a/src/bin/pg_test_timing/pg_test_timing.c
+++ b/src/bin/pg_test_timing/pg_test_timing.c
@@ -16,6 +16,7 @@ static const char *progname;
 
 static unsigned int test_duration = 3;
 static double max_rprct = 99.99;
+static bool fast_timing = false;
 
 /* record duration in powers of 2 nanoseconds */
 static long long int histogram[32];
@@ -56,6 +57,7 @@ handle_args(int argc, char *argv[])
 	static struct option long_options[] = {
 		{"duration", required_argument, NULL, 'd'},
 		{"cutoff", required_argument, NULL, 'c'},
+		{"fast", no_argument, NULL, 'f'},
 		{NULL, 0, NULL, 0}
 	};
 
@@ -68,7 +70,7 @@ handle_args(int argc, char *argv[])
 	{
 		if (strcmp(argv[1], "--help") == 0 || strcmp(argv[1], "-?") == 0)
 		{
-			printf(_("Usage: %s [-d DURATION] [-c CUTOFF]\n"), progname);
+			printf(_("Usage: %s [-d DURATION] [-c CUTOFF] [--fast]\n"), progname);
 			exit(0);
 		}
 		if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0)
@@ -78,7 +80,7 @@ handle_args(int argc, char *argv[])
 		}
 	}
 
-	while ((option = getopt_long(argc, argv, "d:c:",
+	while ((option = getopt_long(argc, argv, "d:c:f:",
 								 long_options, &optindex)) != -1)
 	{
 		switch (option)
@@ -125,6 +127,10 @@ handle_args(int argc, char *argv[])
 				}
 				break;
 
+			case 'f':
+				fast_timing = true;
+				break;
+
 			default:
 				fprintf(stderr, _("Try \"%s --help\" for more information.\n"),
 						progname);
@@ -155,11 +161,31 @@ test_timing(unsigned int duration)
 	uint64		total_time;
 	int64		time_elapsed = 0;
 	uint64		loop_count = 0;
-	uint64		prev,
-				cur;
 	instr_time	start_time,
 				end_time,
-				temp;
+				prev,
+				cur;
+	char	   *time_source = NULL;
+	bool		fast_timing_used = false;
+
+	INSTR_TIME_INITIALIZE();
+
+#if !defined(WIN32) && defined(__x86_64__) && defined(__linux__)
+	if (fast_timing && has_rdtsc)
+	{
+		time_source = "RDTSC";
+		fast_timing_used = true;
+	}
+	else if (has_rdtscp)
+		time_source = "RDTSCP";
+	else
+		time_source = PG_INSTR_CLOCK_NAME;
+#else
+	time_source = PG_INSTR_CLOCK_NAME;
+#endif
+	if (fast_timing && !fast_timing_used)
+		printf(_("Warning: Fast timing requested, but not available - regular timing source will be used\n"));
+	printf(_("Time source: %s\n"), time_source);
 
 	/*
 	 * Pre-zero the statistics data structures.  They're already zero by
@@ -173,8 +199,11 @@ test_timing(unsigned int duration)
 
 	total_time = duration > 0 ? duration * INT64CONST(1000000000) : 0;
 
-	INSTR_TIME_SET_CURRENT(start_time);
-	cur = INSTR_TIME_GET_NANOSEC(start_time);
+	if (fast_timing)
+		INSTR_TIME_SET_CURRENT_FAST(start_time);
+	else
+		INSTR_TIME_SET_CURRENT(start_time);
+	cur = start_time;
 
 	while (time_elapsed < total_time)
 	{
@@ -182,9 +211,11 @@ test_timing(unsigned int duration)
 					bits;
 
 		prev = cur;
-		INSTR_TIME_SET_CURRENT(temp);
-		cur = INSTR_TIME_GET_NANOSEC(temp);
-		diff = cur - prev;
+		if (fast_timing)
+			INSTR_TIME_SET_CURRENT_FAST(cur);
+		else
+			INSTR_TIME_SET_CURRENT(cur);
+		diff = INSTR_TIME_DIFF_NANOSEC(cur, prev);
 
 		/* Did time go backwards? */
 		if (unlikely(diff < 0))
@@ -217,11 +248,13 @@ test_timing(unsigned int duration)
 			largest_diff_count++;
 
 		loop_count++;
-		INSTR_TIME_SUBTRACT(temp, start_time);
-		time_elapsed = INSTR_TIME_GET_NANOSEC(temp);
+		time_elapsed = INSTR_TIME_DIFF_NANOSEC(cur, start_time);
 	}
 
-	INSTR_TIME_SET_CURRENT(end_time);
+	if (fast_timing)
+		INSTR_TIME_SET_CURRENT_FAST(end_time);
+	else
+		INSTR_TIME_SET_CURRENT(end_time);
 
 	INSTR_TIME_SUBTRACT(end_time, start_time);
 
diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h
index e2e339a0c4f..f02296f1026 100644
--- a/src/include/portability/instr_time.h
+++ b/src/include/portability/instr_time.h
@@ -112,10 +112,13 @@ extern int64 max_ticks_no_overflow;
  */
 #if defined(__darwin__) && defined(CLOCK_MONOTONIC_RAW)
 #define PG_INSTR_CLOCK	CLOCK_MONOTONIC_RAW
+#define PG_INSTR_CLOCK_NAME	"clock_gettime (CLOCK_MONOTONIC_RAW)"
 #elif defined(CLOCK_MONOTONIC)
 #define PG_INSTR_CLOCK	CLOCK_MONOTONIC
+#define PG_INSTR_CLOCK_NAME	"clock_gettime (CLOCK_MONOTONIC)"
 #else
 #define PG_INSTR_CLOCK	CLOCK_REALTIME
+#define PG_INSTR_CLOCK_NAME	"clock_gettime (CLOCK_REALTIME)"
 #endif
 
 #if defined(__x86_64__) && defined(__linux__)
@@ -174,7 +177,7 @@ pg_get_ticks(void)
 }
 
 static inline int64_t
-pg_ticks_to_ns(instr_time t)
+pg_ticks_to_ns(int64 ticks)
 {
 	/*
 	 * Would multiplication overflow? If so perform computation in two parts.
@@ -183,7 +186,7 @@ pg_ticks_to_ns(instr_time t)
 	 */
 	int64		ns = 0;
 
-	if (unlikely(t.ticks > max_ticks_no_overflow))
+	if (unlikely(ticks > max_ticks_no_overflow))
 	{
 		/*
 		 * Compute how often the maximum number of ticks fits completely into
@@ -192,7 +195,7 @@ pg_ticks_to_ns(instr_time t)
 		 * value. In a 2nd step we adjust the number of elapsed ticks and
 		 * convert the remaining ticks.
 		 */
-		int64		count = t.ticks / max_ticks_no_overflow;
+		int64		count = ticks / max_ticks_no_overflow;
 		int64		max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION;
 
 		ns = max_ns * count;
@@ -201,11 +204,11 @@ pg_ticks_to_ns(instr_time t)
 		 * Subtract the ticks that we now already accounted for, so that they
 		 * don't get counted twice.
 		 */
-		t.ticks -= count * max_ticks_no_overflow;
-		Assert(t.ticks >= 0);
+		ticks -= count * max_ticks_no_overflow;
+		Assert(ticks >= 0);
 	}
 
-	ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION;
+	ns += ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION;
 	return ns;
 }
 
@@ -226,14 +229,14 @@ pg_initialize_get_ticks()
 #define INSTR_TIME_SET_CURRENT(t) \
 	((t) = pg_get_ticks())
 
-#define INSTR_TIME_GET_NANOSEC(t) \
-	pg_ticks_to_ns(t)
-
+#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \
+	(pg_ticks_to_ns(ticks))
 
 #else							/* WIN32 */
 
 
 /* Use QueryPerformanceCounter() */
+#define PG_INSTR_CLOCK_NAME	"QueryPerformanceCounter"
 
 /* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */
 static inline instr_time
@@ -265,8 +268,8 @@ GetTimerFrequency(void)
 #define INSTR_TIME_SET_CURRENT(t) \
 	((t) = pg_query_performance_counter())
 
-#define INSTR_TIME_GET_NANOSEC(t) \
-	((int64) ((t).ticks * ((double) NS_PER_S / GetTimerFrequency())))
+#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \
+	((int64) ((ticks) * ((double) NS_PER_S / GetTimerFrequency())))
 
 #endif							/* WIN32 */
 
@@ -285,9 +288,14 @@ GetTimerFrequency(void)
 #define INSTR_TIME_SUBTRACT(x,y) \
 	((x).ticks -= (y).ticks)
 
+#define INSTR_TIME_DIFF_NANOSEC(x,y) \
+	(INSTR_TIME_TICKS_TO_NANOSEC((x).ticks - (y).ticks))
+
 #define INSTR_TIME_ACCUM_DIFF(x,y,z) \
 	((x).ticks += (y).ticks - (z).ticks)
 
+#define INSTR_TIME_GET_NANOSEC(t) \
+	(INSTR_TIME_TICKS_TO_NANOSEC((t).ticks))
 
 #define INSTR_TIME_GET_DOUBLE(t) \
 	((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S)
-- 
2.47.3


--vtqqtrpooseurzip--





^ permalink  raw  reply  [nested|flat] 265+ messages in thread

* [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source
@ 2025-07-27 15:48  Lukas Fittl <[email protected]>
  0 siblings, 0 replies; 265+ messages in thread

From: Lukas Fittl @ 2025-07-27 15:48 UTC (permalink / raw)

In passing also reduce the per-loop overhead caused by repeated divisions
in INSTR_TIME_GET_NANOSEC when the ticks variable has become very large,
instead diff first and then turn it into nanosecs.
---
 src/bin/pg_test_timing/pg_test_timing.c | 59 +++++++++++++++++++------
 src/include/portability/instr_time.h    | 30 ++++++++-----
 2 files changed, 65 insertions(+), 24 deletions(-)

diff --git a/src/bin/pg_test_timing/pg_test_timing.c b/src/bin/pg_test_timing/pg_test_timing.c
index a5621251afc..b77ef2063b6 100644
--- a/src/bin/pg_test_timing/pg_test_timing.c
+++ b/src/bin/pg_test_timing/pg_test_timing.c
@@ -16,6 +16,7 @@ static const char *progname;
 
 static unsigned int test_duration = 3;
 static double max_rprct = 99.99;
+static bool fast_timing = false;
 
 /* record duration in powers of 2 nanoseconds */
 static long long int histogram[32];
@@ -56,6 +57,7 @@ handle_args(int argc, char *argv[])
 	static struct option long_options[] = {
 		{"duration", required_argument, NULL, 'd'},
 		{"cutoff", required_argument, NULL, 'c'},
+		{"fast", no_argument, NULL, 'f'},
 		{NULL, 0, NULL, 0}
 	};
 
@@ -68,7 +70,7 @@ handle_args(int argc, char *argv[])
 	{
 		if (strcmp(argv[1], "--help") == 0 || strcmp(argv[1], "-?") == 0)
 		{
-			printf(_("Usage: %s [-d DURATION] [-c CUTOFF]\n"), progname);
+			printf(_("Usage: %s [-d DURATION] [-c CUTOFF] [--fast]\n"), progname);
 			exit(0);
 		}
 		if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0)
@@ -78,7 +80,7 @@ handle_args(int argc, char *argv[])
 		}
 	}
 
-	while ((option = getopt_long(argc, argv, "d:c:",
+	while ((option = getopt_long(argc, argv, "d:c:f:",
 								 long_options, &optindex)) != -1)
 	{
 		switch (option)
@@ -125,6 +127,10 @@ handle_args(int argc, char *argv[])
 				}
 				break;
 
+			case 'f':
+				fast_timing = true;
+				break;
+
 			default:
 				fprintf(stderr, _("Try \"%s --help\" for more information.\n"),
 						progname);
@@ -155,11 +161,31 @@ test_timing(unsigned int duration)
 	uint64		total_time;
 	int64		time_elapsed = 0;
 	uint64		loop_count = 0;
-	uint64		prev,
-				cur;
 	instr_time	start_time,
 				end_time,
-				temp;
+				prev,
+				cur;
+	char	   *time_source = NULL;
+	bool		fast_timing_used = false;
+
+	INSTR_TIME_INITIALIZE();
+
+#if !defined(WIN32) && defined(__x86_64__) && defined(__linux__)
+	if (fast_timing && has_rdtsc)
+	{
+		time_source = "RDTSC";
+		fast_timing_used = true;
+	}
+	else if (has_rdtscp)
+		time_source = "RDTSCP";
+	else
+		time_source = PG_INSTR_CLOCK_NAME;
+#else
+	time_source = PG_INSTR_CLOCK_NAME;
+#endif
+	if (fast_timing && !fast_timing_used)
+		printf(_("Warning: Fast timing requested, but not available - regular timing source will be used\n"));
+	printf(_("Time source: %s\n"), time_source);
 
 	/*
 	 * Pre-zero the statistics data structures.  They're already zero by
@@ -173,8 +199,11 @@ test_timing(unsigned int duration)
 
 	total_time = duration > 0 ? duration * INT64CONST(1000000000) : 0;
 
-	INSTR_TIME_SET_CURRENT(start_time);
-	cur = INSTR_TIME_GET_NANOSEC(start_time);
+	if (fast_timing)
+		INSTR_TIME_SET_CURRENT_FAST(start_time);
+	else
+		INSTR_TIME_SET_CURRENT(start_time);
+	cur = start_time;
 
 	while (time_elapsed < total_time)
 	{
@@ -182,9 +211,11 @@ test_timing(unsigned int duration)
 					bits;
 
 		prev = cur;
-		INSTR_TIME_SET_CURRENT(temp);
-		cur = INSTR_TIME_GET_NANOSEC(temp);
-		diff = cur - prev;
+		if (fast_timing)
+			INSTR_TIME_SET_CURRENT_FAST(cur);
+		else
+			INSTR_TIME_SET_CURRENT(cur);
+		diff = INSTR_TIME_DIFF_NANOSEC(cur, prev);
 
 		/* Did time go backwards? */
 		if (unlikely(diff < 0))
@@ -217,11 +248,13 @@ test_timing(unsigned int duration)
 			largest_diff_count++;
 
 		loop_count++;
-		INSTR_TIME_SUBTRACT(temp, start_time);
-		time_elapsed = INSTR_TIME_GET_NANOSEC(temp);
+		time_elapsed = INSTR_TIME_DIFF_NANOSEC(cur, start_time);
 	}
 
-	INSTR_TIME_SET_CURRENT(end_time);
+	if (fast_timing)
+		INSTR_TIME_SET_CURRENT_FAST(end_time);
+	else
+		INSTR_TIME_SET_CURRENT(end_time);
 
 	INSTR_TIME_SUBTRACT(end_time, start_time);
 
diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h
index e2e339a0c4f..f02296f1026 100644
--- a/src/include/portability/instr_time.h
+++ b/src/include/portability/instr_time.h
@@ -112,10 +112,13 @@ extern int64 max_ticks_no_overflow;
  */
 #if defined(__darwin__) && defined(CLOCK_MONOTONIC_RAW)
 #define PG_INSTR_CLOCK	CLOCK_MONOTONIC_RAW
+#define PG_INSTR_CLOCK_NAME	"clock_gettime (CLOCK_MONOTONIC_RAW)"
 #elif defined(CLOCK_MONOTONIC)
 #define PG_INSTR_CLOCK	CLOCK_MONOTONIC
+#define PG_INSTR_CLOCK_NAME	"clock_gettime (CLOCK_MONOTONIC)"
 #else
 #define PG_INSTR_CLOCK	CLOCK_REALTIME
+#define PG_INSTR_CLOCK_NAME	"clock_gettime (CLOCK_REALTIME)"
 #endif
 
 #if defined(__x86_64__) && defined(__linux__)
@@ -174,7 +177,7 @@ pg_get_ticks(void)
 }
 
 static inline int64_t
-pg_ticks_to_ns(instr_time t)
+pg_ticks_to_ns(int64 ticks)
 {
 	/*
 	 * Would multiplication overflow? If so perform computation in two parts.
@@ -183,7 +186,7 @@ pg_ticks_to_ns(instr_time t)
 	 */
 	int64		ns = 0;
 
-	if (unlikely(t.ticks > max_ticks_no_overflow))
+	if (unlikely(ticks > max_ticks_no_overflow))
 	{
 		/*
 		 * Compute how often the maximum number of ticks fits completely into
@@ -192,7 +195,7 @@ pg_ticks_to_ns(instr_time t)
 		 * value. In a 2nd step we adjust the number of elapsed ticks and
 		 * convert the remaining ticks.
 		 */
-		int64		count = t.ticks / max_ticks_no_overflow;
+		int64		count = ticks / max_ticks_no_overflow;
 		int64		max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION;
 
 		ns = max_ns * count;
@@ -201,11 +204,11 @@ pg_ticks_to_ns(instr_time t)
 		 * Subtract the ticks that we now already accounted for, so that they
 		 * don't get counted twice.
 		 */
-		t.ticks -= count * max_ticks_no_overflow;
-		Assert(t.ticks >= 0);
+		ticks -= count * max_ticks_no_overflow;
+		Assert(ticks >= 0);
 	}
 
-	ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION;
+	ns += ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION;
 	return ns;
 }
 
@@ -226,14 +229,14 @@ pg_initialize_get_ticks()
 #define INSTR_TIME_SET_CURRENT(t) \
 	((t) = pg_get_ticks())
 
-#define INSTR_TIME_GET_NANOSEC(t) \
-	pg_ticks_to_ns(t)
-
+#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \
+	(pg_ticks_to_ns(ticks))
 
 #else							/* WIN32 */
 
 
 /* Use QueryPerformanceCounter() */
+#define PG_INSTR_CLOCK_NAME	"QueryPerformanceCounter"
 
 /* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */
 static inline instr_time
@@ -265,8 +268,8 @@ GetTimerFrequency(void)
 #define INSTR_TIME_SET_CURRENT(t) \
 	((t) = pg_query_performance_counter())
 
-#define INSTR_TIME_GET_NANOSEC(t) \
-	((int64) ((t).ticks * ((double) NS_PER_S / GetTimerFrequency())))
+#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \
+	((int64) ((ticks) * ((double) NS_PER_S / GetTimerFrequency())))
 
 #endif							/* WIN32 */
 
@@ -285,9 +288,14 @@ GetTimerFrequency(void)
 #define INSTR_TIME_SUBTRACT(x,y) \
 	((x).ticks -= (y).ticks)
 
+#define INSTR_TIME_DIFF_NANOSEC(x,y) \
+	(INSTR_TIME_TICKS_TO_NANOSEC((x).ticks - (y).ticks))
+
 #define INSTR_TIME_ACCUM_DIFF(x,y,z) \
 	((x).ticks += (y).ticks - (z).ticks)
 
+#define INSTR_TIME_GET_NANOSEC(t) \
+	(INSTR_TIME_TICKS_TO_NANOSEC((t).ticks))
 
 #define INSTR_TIME_GET_DOUBLE(t) \
 	((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S)
-- 
2.47.3


--vtqqtrpooseurzip--





^ permalink  raw  reply  [nested|flat] 265+ messages in thread

* [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source
@ 2025-07-27 15:48  Lukas Fittl <[email protected]>
  0 siblings, 0 replies; 265+ messages in thread

From: Lukas Fittl @ 2025-07-27 15:48 UTC (permalink / raw)

In passing also reduce the per-loop overhead caused by repeated divisions
in INSTR_TIME_GET_NANOSEC when the ticks variable has become very large,
instead diff first and then turn it into nanosecs.
---
 src/bin/pg_test_timing/pg_test_timing.c | 59 +++++++++++++++++++------
 src/include/portability/instr_time.h    | 30 ++++++++-----
 2 files changed, 65 insertions(+), 24 deletions(-)

diff --git a/src/bin/pg_test_timing/pg_test_timing.c b/src/bin/pg_test_timing/pg_test_timing.c
index a5621251afc..b77ef2063b6 100644
--- a/src/bin/pg_test_timing/pg_test_timing.c
+++ b/src/bin/pg_test_timing/pg_test_timing.c
@@ -16,6 +16,7 @@ static const char *progname;
 
 static unsigned int test_duration = 3;
 static double max_rprct = 99.99;
+static bool fast_timing = false;
 
 /* record duration in powers of 2 nanoseconds */
 static long long int histogram[32];
@@ -56,6 +57,7 @@ handle_args(int argc, char *argv[])
 	static struct option long_options[] = {
 		{"duration", required_argument, NULL, 'd'},
 		{"cutoff", required_argument, NULL, 'c'},
+		{"fast", no_argument, NULL, 'f'},
 		{NULL, 0, NULL, 0}
 	};
 
@@ -68,7 +70,7 @@ handle_args(int argc, char *argv[])
 	{
 		if (strcmp(argv[1], "--help") == 0 || strcmp(argv[1], "-?") == 0)
 		{
-			printf(_("Usage: %s [-d DURATION] [-c CUTOFF]\n"), progname);
+			printf(_("Usage: %s [-d DURATION] [-c CUTOFF] [--fast]\n"), progname);
 			exit(0);
 		}
 		if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0)
@@ -78,7 +80,7 @@ handle_args(int argc, char *argv[])
 		}
 	}
 
-	while ((option = getopt_long(argc, argv, "d:c:",
+	while ((option = getopt_long(argc, argv, "d:c:f:",
 								 long_options, &optindex)) != -1)
 	{
 		switch (option)
@@ -125,6 +127,10 @@ handle_args(int argc, char *argv[])
 				}
 				break;
 
+			case 'f':
+				fast_timing = true;
+				break;
+
 			default:
 				fprintf(stderr, _("Try \"%s --help\" for more information.\n"),
 						progname);
@@ -155,11 +161,31 @@ test_timing(unsigned int duration)
 	uint64		total_time;
 	int64		time_elapsed = 0;
 	uint64		loop_count = 0;
-	uint64		prev,
-				cur;
 	instr_time	start_time,
 				end_time,
-				temp;
+				prev,
+				cur;
+	char	   *time_source = NULL;
+	bool		fast_timing_used = false;
+
+	INSTR_TIME_INITIALIZE();
+
+#if !defined(WIN32) && defined(__x86_64__) && defined(__linux__)
+	if (fast_timing && has_rdtsc)
+	{
+		time_source = "RDTSC";
+		fast_timing_used = true;
+	}
+	else if (has_rdtscp)
+		time_source = "RDTSCP";
+	else
+		time_source = PG_INSTR_CLOCK_NAME;
+#else
+	time_source = PG_INSTR_CLOCK_NAME;
+#endif
+	if (fast_timing && !fast_timing_used)
+		printf(_("Warning: Fast timing requested, but not available - regular timing source will be used\n"));
+	printf(_("Time source: %s\n"), time_source);
 
 	/*
 	 * Pre-zero the statistics data structures.  They're already zero by
@@ -173,8 +199,11 @@ test_timing(unsigned int duration)
 
 	total_time = duration > 0 ? duration * INT64CONST(1000000000) : 0;
 
-	INSTR_TIME_SET_CURRENT(start_time);
-	cur = INSTR_TIME_GET_NANOSEC(start_time);
+	if (fast_timing)
+		INSTR_TIME_SET_CURRENT_FAST(start_time);
+	else
+		INSTR_TIME_SET_CURRENT(start_time);
+	cur = start_time;
 
 	while (time_elapsed < total_time)
 	{
@@ -182,9 +211,11 @@ test_timing(unsigned int duration)
 					bits;
 
 		prev = cur;
-		INSTR_TIME_SET_CURRENT(temp);
-		cur = INSTR_TIME_GET_NANOSEC(temp);
-		diff = cur - prev;
+		if (fast_timing)
+			INSTR_TIME_SET_CURRENT_FAST(cur);
+		else
+			INSTR_TIME_SET_CURRENT(cur);
+		diff = INSTR_TIME_DIFF_NANOSEC(cur, prev);
 
 		/* Did time go backwards? */
 		if (unlikely(diff < 0))
@@ -217,11 +248,13 @@ test_timing(unsigned int duration)
 			largest_diff_count++;
 
 		loop_count++;
-		INSTR_TIME_SUBTRACT(temp, start_time);
-		time_elapsed = INSTR_TIME_GET_NANOSEC(temp);
+		time_elapsed = INSTR_TIME_DIFF_NANOSEC(cur, start_time);
 	}
 
-	INSTR_TIME_SET_CURRENT(end_time);
+	if (fast_timing)
+		INSTR_TIME_SET_CURRENT_FAST(end_time);
+	else
+		INSTR_TIME_SET_CURRENT(end_time);
 
 	INSTR_TIME_SUBTRACT(end_time, start_time);
 
diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h
index e2e339a0c4f..f02296f1026 100644
--- a/src/include/portability/instr_time.h
+++ b/src/include/portability/instr_time.h
@@ -112,10 +112,13 @@ extern int64 max_ticks_no_overflow;
  */
 #if defined(__darwin__) && defined(CLOCK_MONOTONIC_RAW)
 #define PG_INSTR_CLOCK	CLOCK_MONOTONIC_RAW
+#define PG_INSTR_CLOCK_NAME	"clock_gettime (CLOCK_MONOTONIC_RAW)"
 #elif defined(CLOCK_MONOTONIC)
 #define PG_INSTR_CLOCK	CLOCK_MONOTONIC
+#define PG_INSTR_CLOCK_NAME	"clock_gettime (CLOCK_MONOTONIC)"
 #else
 #define PG_INSTR_CLOCK	CLOCK_REALTIME
+#define PG_INSTR_CLOCK_NAME	"clock_gettime (CLOCK_REALTIME)"
 #endif
 
 #if defined(__x86_64__) && defined(__linux__)
@@ -174,7 +177,7 @@ pg_get_ticks(void)
 }
 
 static inline int64_t
-pg_ticks_to_ns(instr_time t)
+pg_ticks_to_ns(int64 ticks)
 {
 	/*
 	 * Would multiplication overflow? If so perform computation in two parts.
@@ -183,7 +186,7 @@ pg_ticks_to_ns(instr_time t)
 	 */
 	int64		ns = 0;
 
-	if (unlikely(t.ticks > max_ticks_no_overflow))
+	if (unlikely(ticks > max_ticks_no_overflow))
 	{
 		/*
 		 * Compute how often the maximum number of ticks fits completely into
@@ -192,7 +195,7 @@ pg_ticks_to_ns(instr_time t)
 		 * value. In a 2nd step we adjust the number of elapsed ticks and
 		 * convert the remaining ticks.
 		 */
-		int64		count = t.ticks / max_ticks_no_overflow;
+		int64		count = ticks / max_ticks_no_overflow;
 		int64		max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION;
 
 		ns = max_ns * count;
@@ -201,11 +204,11 @@ pg_ticks_to_ns(instr_time t)
 		 * Subtract the ticks that we now already accounted for, so that they
 		 * don't get counted twice.
 		 */
-		t.ticks -= count * max_ticks_no_overflow;
-		Assert(t.ticks >= 0);
+		ticks -= count * max_ticks_no_overflow;
+		Assert(ticks >= 0);
 	}
 
-	ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION;
+	ns += ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION;
 	return ns;
 }
 
@@ -226,14 +229,14 @@ pg_initialize_get_ticks()
 #define INSTR_TIME_SET_CURRENT(t) \
 	((t) = pg_get_ticks())
 
-#define INSTR_TIME_GET_NANOSEC(t) \
-	pg_ticks_to_ns(t)
-
+#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \
+	(pg_ticks_to_ns(ticks))
 
 #else							/* WIN32 */
 
 
 /* Use QueryPerformanceCounter() */
+#define PG_INSTR_CLOCK_NAME	"QueryPerformanceCounter"
 
 /* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */
 static inline instr_time
@@ -265,8 +268,8 @@ GetTimerFrequency(void)
 #define INSTR_TIME_SET_CURRENT(t) \
 	((t) = pg_query_performance_counter())
 
-#define INSTR_TIME_GET_NANOSEC(t) \
-	((int64) ((t).ticks * ((double) NS_PER_S / GetTimerFrequency())))
+#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \
+	((int64) ((ticks) * ((double) NS_PER_S / GetTimerFrequency())))
 
 #endif							/* WIN32 */
 
@@ -285,9 +288,14 @@ GetTimerFrequency(void)
 #define INSTR_TIME_SUBTRACT(x,y) \
 	((x).ticks -= (y).ticks)
 
+#define INSTR_TIME_DIFF_NANOSEC(x,y) \
+	(INSTR_TIME_TICKS_TO_NANOSEC((x).ticks - (y).ticks))
+
 #define INSTR_TIME_ACCUM_DIFF(x,y,z) \
 	((x).ticks += (y).ticks - (z).ticks)
 
+#define INSTR_TIME_GET_NANOSEC(t) \
+	(INSTR_TIME_TICKS_TO_NANOSEC((t).ticks))
 
 #define INSTR_TIME_GET_DOUBLE(t) \
 	((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S)
-- 
2.47.3


--vtqqtrpooseurzip--





^ permalink  raw  reply  [nested|flat] 265+ messages in thread

* [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source
@ 2025-07-27 15:48  Lukas Fittl <[email protected]>
  0 siblings, 0 replies; 265+ messages in thread

From: Lukas Fittl @ 2025-07-27 15:48 UTC (permalink / raw)

In passing also reduce the per-loop overhead caused by repeated divisions
in INSTR_TIME_GET_NANOSEC when the ticks variable has become very large,
instead diff first and then turn it into nanosecs.
---
 src/bin/pg_test_timing/pg_test_timing.c | 59 +++++++++++++++++++------
 src/include/portability/instr_time.h    | 30 ++++++++-----
 2 files changed, 65 insertions(+), 24 deletions(-)

diff --git a/src/bin/pg_test_timing/pg_test_timing.c b/src/bin/pg_test_timing/pg_test_timing.c
index a5621251afc..b77ef2063b6 100644
--- a/src/bin/pg_test_timing/pg_test_timing.c
+++ b/src/bin/pg_test_timing/pg_test_timing.c
@@ -16,6 +16,7 @@ static const char *progname;
 
 static unsigned int test_duration = 3;
 static double max_rprct = 99.99;
+static bool fast_timing = false;
 
 /* record duration in powers of 2 nanoseconds */
 static long long int histogram[32];
@@ -56,6 +57,7 @@ handle_args(int argc, char *argv[])
 	static struct option long_options[] = {
 		{"duration", required_argument, NULL, 'd'},
 		{"cutoff", required_argument, NULL, 'c'},
+		{"fast", no_argument, NULL, 'f'},
 		{NULL, 0, NULL, 0}
 	};
 
@@ -68,7 +70,7 @@ handle_args(int argc, char *argv[])
 	{
 		if (strcmp(argv[1], "--help") == 0 || strcmp(argv[1], "-?") == 0)
 		{
-			printf(_("Usage: %s [-d DURATION] [-c CUTOFF]\n"), progname);
+			printf(_("Usage: %s [-d DURATION] [-c CUTOFF] [--fast]\n"), progname);
 			exit(0);
 		}
 		if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0)
@@ -78,7 +80,7 @@ handle_args(int argc, char *argv[])
 		}
 	}
 
-	while ((option = getopt_long(argc, argv, "d:c:",
+	while ((option = getopt_long(argc, argv, "d:c:f:",
 								 long_options, &optindex)) != -1)
 	{
 		switch (option)
@@ -125,6 +127,10 @@ handle_args(int argc, char *argv[])
 				}
 				break;
 
+			case 'f':
+				fast_timing = true;
+				break;
+
 			default:
 				fprintf(stderr, _("Try \"%s --help\" for more information.\n"),
 						progname);
@@ -155,11 +161,31 @@ test_timing(unsigned int duration)
 	uint64		total_time;
 	int64		time_elapsed = 0;
 	uint64		loop_count = 0;
-	uint64		prev,
-				cur;
 	instr_time	start_time,
 				end_time,
-				temp;
+				prev,
+				cur;
+	char	   *time_source = NULL;
+	bool		fast_timing_used = false;
+
+	INSTR_TIME_INITIALIZE();
+
+#if !defined(WIN32) && defined(__x86_64__) && defined(__linux__)
+	if (fast_timing && has_rdtsc)
+	{
+		time_source = "RDTSC";
+		fast_timing_used = true;
+	}
+	else if (has_rdtscp)
+		time_source = "RDTSCP";
+	else
+		time_source = PG_INSTR_CLOCK_NAME;
+#else
+	time_source = PG_INSTR_CLOCK_NAME;
+#endif
+	if (fast_timing && !fast_timing_used)
+		printf(_("Warning: Fast timing requested, but not available - regular timing source will be used\n"));
+	printf(_("Time source: %s\n"), time_source);
 
 	/*
 	 * Pre-zero the statistics data structures.  They're already zero by
@@ -173,8 +199,11 @@ test_timing(unsigned int duration)
 
 	total_time = duration > 0 ? duration * INT64CONST(1000000000) : 0;
 
-	INSTR_TIME_SET_CURRENT(start_time);
-	cur = INSTR_TIME_GET_NANOSEC(start_time);
+	if (fast_timing)
+		INSTR_TIME_SET_CURRENT_FAST(start_time);
+	else
+		INSTR_TIME_SET_CURRENT(start_time);
+	cur = start_time;
 
 	while (time_elapsed < total_time)
 	{
@@ -182,9 +211,11 @@ test_timing(unsigned int duration)
 					bits;
 
 		prev = cur;
-		INSTR_TIME_SET_CURRENT(temp);
-		cur = INSTR_TIME_GET_NANOSEC(temp);
-		diff = cur - prev;
+		if (fast_timing)
+			INSTR_TIME_SET_CURRENT_FAST(cur);
+		else
+			INSTR_TIME_SET_CURRENT(cur);
+		diff = INSTR_TIME_DIFF_NANOSEC(cur, prev);
 
 		/* Did time go backwards? */
 		if (unlikely(diff < 0))
@@ -217,11 +248,13 @@ test_timing(unsigned int duration)
 			largest_diff_count++;
 
 		loop_count++;
-		INSTR_TIME_SUBTRACT(temp, start_time);
-		time_elapsed = INSTR_TIME_GET_NANOSEC(temp);
+		time_elapsed = INSTR_TIME_DIFF_NANOSEC(cur, start_time);
 	}
 
-	INSTR_TIME_SET_CURRENT(end_time);
+	if (fast_timing)
+		INSTR_TIME_SET_CURRENT_FAST(end_time);
+	else
+		INSTR_TIME_SET_CURRENT(end_time);
 
 	INSTR_TIME_SUBTRACT(end_time, start_time);
 
diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h
index e2e339a0c4f..f02296f1026 100644
--- a/src/include/portability/instr_time.h
+++ b/src/include/portability/instr_time.h
@@ -112,10 +112,13 @@ extern int64 max_ticks_no_overflow;
  */
 #if defined(__darwin__) && defined(CLOCK_MONOTONIC_RAW)
 #define PG_INSTR_CLOCK	CLOCK_MONOTONIC_RAW
+#define PG_INSTR_CLOCK_NAME	"clock_gettime (CLOCK_MONOTONIC_RAW)"
 #elif defined(CLOCK_MONOTONIC)
 #define PG_INSTR_CLOCK	CLOCK_MONOTONIC
+#define PG_INSTR_CLOCK_NAME	"clock_gettime (CLOCK_MONOTONIC)"
 #else
 #define PG_INSTR_CLOCK	CLOCK_REALTIME
+#define PG_INSTR_CLOCK_NAME	"clock_gettime (CLOCK_REALTIME)"
 #endif
 
 #if defined(__x86_64__) && defined(__linux__)
@@ -174,7 +177,7 @@ pg_get_ticks(void)
 }
 
 static inline int64_t
-pg_ticks_to_ns(instr_time t)
+pg_ticks_to_ns(int64 ticks)
 {
 	/*
 	 * Would multiplication overflow? If so perform computation in two parts.
@@ -183,7 +186,7 @@ pg_ticks_to_ns(instr_time t)
 	 */
 	int64		ns = 0;
 
-	if (unlikely(t.ticks > max_ticks_no_overflow))
+	if (unlikely(ticks > max_ticks_no_overflow))
 	{
 		/*
 		 * Compute how often the maximum number of ticks fits completely into
@@ -192,7 +195,7 @@ pg_ticks_to_ns(instr_time t)
 		 * value. In a 2nd step we adjust the number of elapsed ticks and
 		 * convert the remaining ticks.
 		 */
-		int64		count = t.ticks / max_ticks_no_overflow;
+		int64		count = ticks / max_ticks_no_overflow;
 		int64		max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION;
 
 		ns = max_ns * count;
@@ -201,11 +204,11 @@ pg_ticks_to_ns(instr_time t)
 		 * Subtract the ticks that we now already accounted for, so that they
 		 * don't get counted twice.
 		 */
-		t.ticks -= count * max_ticks_no_overflow;
-		Assert(t.ticks >= 0);
+		ticks -= count * max_ticks_no_overflow;
+		Assert(ticks >= 0);
 	}
 
-	ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION;
+	ns += ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION;
 	return ns;
 }
 
@@ -226,14 +229,14 @@ pg_initialize_get_ticks()
 #define INSTR_TIME_SET_CURRENT(t) \
 	((t) = pg_get_ticks())
 
-#define INSTR_TIME_GET_NANOSEC(t) \
-	pg_ticks_to_ns(t)
-
+#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \
+	(pg_ticks_to_ns(ticks))
 
 #else							/* WIN32 */
 
 
 /* Use QueryPerformanceCounter() */
+#define PG_INSTR_CLOCK_NAME	"QueryPerformanceCounter"
 
 /* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */
 static inline instr_time
@@ -265,8 +268,8 @@ GetTimerFrequency(void)
 #define INSTR_TIME_SET_CURRENT(t) \
 	((t) = pg_query_performance_counter())
 
-#define INSTR_TIME_GET_NANOSEC(t) \
-	((int64) ((t).ticks * ((double) NS_PER_S / GetTimerFrequency())))
+#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \
+	((int64) ((ticks) * ((double) NS_PER_S / GetTimerFrequency())))
 
 #endif							/* WIN32 */
 
@@ -285,9 +288,14 @@ GetTimerFrequency(void)
 #define INSTR_TIME_SUBTRACT(x,y) \
 	((x).ticks -= (y).ticks)
 
+#define INSTR_TIME_DIFF_NANOSEC(x,y) \
+	(INSTR_TIME_TICKS_TO_NANOSEC((x).ticks - (y).ticks))
+
 #define INSTR_TIME_ACCUM_DIFF(x,y,z) \
 	((x).ticks += (y).ticks - (z).ticks)
 
+#define INSTR_TIME_GET_NANOSEC(t) \
+	(INSTR_TIME_TICKS_TO_NANOSEC((t).ticks))
 
 #define INSTR_TIME_GET_DOUBLE(t) \
 	((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S)
-- 
2.47.3


--vtqqtrpooseurzip--





^ permalink  raw  reply  [nested|flat] 265+ messages in thread

* [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source
@ 2025-07-27 15:48  Lukas Fittl <[email protected]>
  0 siblings, 0 replies; 265+ messages in thread

From: Lukas Fittl @ 2025-07-27 15:48 UTC (permalink / raw)

In passing also reduce the per-loop overhead caused by repeated divisions
in INSTR_TIME_GET_NANOSEC when the ticks variable has become very large,
instead diff first and then turn it into nanosecs.
---
 src/bin/pg_test_timing/pg_test_timing.c | 59 +++++++++++++++++++------
 src/include/portability/instr_time.h    | 30 ++++++++-----
 2 files changed, 65 insertions(+), 24 deletions(-)

diff --git a/src/bin/pg_test_timing/pg_test_timing.c b/src/bin/pg_test_timing/pg_test_timing.c
index a5621251afc..b77ef2063b6 100644
--- a/src/bin/pg_test_timing/pg_test_timing.c
+++ b/src/bin/pg_test_timing/pg_test_timing.c
@@ -16,6 +16,7 @@ static const char *progname;
 
 static unsigned int test_duration = 3;
 static double max_rprct = 99.99;
+static bool fast_timing = false;
 
 /* record duration in powers of 2 nanoseconds */
 static long long int histogram[32];
@@ -56,6 +57,7 @@ handle_args(int argc, char *argv[])
 	static struct option long_options[] = {
 		{"duration", required_argument, NULL, 'd'},
 		{"cutoff", required_argument, NULL, 'c'},
+		{"fast", no_argument, NULL, 'f'},
 		{NULL, 0, NULL, 0}
 	};
 
@@ -68,7 +70,7 @@ handle_args(int argc, char *argv[])
 	{
 		if (strcmp(argv[1], "--help") == 0 || strcmp(argv[1], "-?") == 0)
 		{
-			printf(_("Usage: %s [-d DURATION] [-c CUTOFF]\n"), progname);
+			printf(_("Usage: %s [-d DURATION] [-c CUTOFF] [--fast]\n"), progname);
 			exit(0);
 		}
 		if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0)
@@ -78,7 +80,7 @@ handle_args(int argc, char *argv[])
 		}
 	}
 
-	while ((option = getopt_long(argc, argv, "d:c:",
+	while ((option = getopt_long(argc, argv, "d:c:f:",
 								 long_options, &optindex)) != -1)
 	{
 		switch (option)
@@ -125,6 +127,10 @@ handle_args(int argc, char *argv[])
 				}
 				break;
 
+			case 'f':
+				fast_timing = true;
+				break;
+
 			default:
 				fprintf(stderr, _("Try \"%s --help\" for more information.\n"),
 						progname);
@@ -155,11 +161,31 @@ test_timing(unsigned int duration)
 	uint64		total_time;
 	int64		time_elapsed = 0;
 	uint64		loop_count = 0;
-	uint64		prev,
-				cur;
 	instr_time	start_time,
 				end_time,
-				temp;
+				prev,
+				cur;
+	char	   *time_source = NULL;
+	bool		fast_timing_used = false;
+
+	INSTR_TIME_INITIALIZE();
+
+#if !defined(WIN32) && defined(__x86_64__) && defined(__linux__)
+	if (fast_timing && has_rdtsc)
+	{
+		time_source = "RDTSC";
+		fast_timing_used = true;
+	}
+	else if (has_rdtscp)
+		time_source = "RDTSCP";
+	else
+		time_source = PG_INSTR_CLOCK_NAME;
+#else
+	time_source = PG_INSTR_CLOCK_NAME;
+#endif
+	if (fast_timing && !fast_timing_used)
+		printf(_("Warning: Fast timing requested, but not available - regular timing source will be used\n"));
+	printf(_("Time source: %s\n"), time_source);
 
 	/*
 	 * Pre-zero the statistics data structures.  They're already zero by
@@ -173,8 +199,11 @@ test_timing(unsigned int duration)
 
 	total_time = duration > 0 ? duration * INT64CONST(1000000000) : 0;
 
-	INSTR_TIME_SET_CURRENT(start_time);
-	cur = INSTR_TIME_GET_NANOSEC(start_time);
+	if (fast_timing)
+		INSTR_TIME_SET_CURRENT_FAST(start_time);
+	else
+		INSTR_TIME_SET_CURRENT(start_time);
+	cur = start_time;
 
 	while (time_elapsed < total_time)
 	{
@@ -182,9 +211,11 @@ test_timing(unsigned int duration)
 					bits;
 
 		prev = cur;
-		INSTR_TIME_SET_CURRENT(temp);
-		cur = INSTR_TIME_GET_NANOSEC(temp);
-		diff = cur - prev;
+		if (fast_timing)
+			INSTR_TIME_SET_CURRENT_FAST(cur);
+		else
+			INSTR_TIME_SET_CURRENT(cur);
+		diff = INSTR_TIME_DIFF_NANOSEC(cur, prev);
 
 		/* Did time go backwards? */
 		if (unlikely(diff < 0))
@@ -217,11 +248,13 @@ test_timing(unsigned int duration)
 			largest_diff_count++;
 
 		loop_count++;
-		INSTR_TIME_SUBTRACT(temp, start_time);
-		time_elapsed = INSTR_TIME_GET_NANOSEC(temp);
+		time_elapsed = INSTR_TIME_DIFF_NANOSEC(cur, start_time);
 	}
 
-	INSTR_TIME_SET_CURRENT(end_time);
+	if (fast_timing)
+		INSTR_TIME_SET_CURRENT_FAST(end_time);
+	else
+		INSTR_TIME_SET_CURRENT(end_time);
 
 	INSTR_TIME_SUBTRACT(end_time, start_time);
 
diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h
index e2e339a0c4f..f02296f1026 100644
--- a/src/include/portability/instr_time.h
+++ b/src/include/portability/instr_time.h
@@ -112,10 +112,13 @@ extern int64 max_ticks_no_overflow;
  */
 #if defined(__darwin__) && defined(CLOCK_MONOTONIC_RAW)
 #define PG_INSTR_CLOCK	CLOCK_MONOTONIC_RAW
+#define PG_INSTR_CLOCK_NAME	"clock_gettime (CLOCK_MONOTONIC_RAW)"
 #elif defined(CLOCK_MONOTONIC)
 #define PG_INSTR_CLOCK	CLOCK_MONOTONIC
+#define PG_INSTR_CLOCK_NAME	"clock_gettime (CLOCK_MONOTONIC)"
 #else
 #define PG_INSTR_CLOCK	CLOCK_REALTIME
+#define PG_INSTR_CLOCK_NAME	"clock_gettime (CLOCK_REALTIME)"
 #endif
 
 #if defined(__x86_64__) && defined(__linux__)
@@ -174,7 +177,7 @@ pg_get_ticks(void)
 }
 
 static inline int64_t
-pg_ticks_to_ns(instr_time t)
+pg_ticks_to_ns(int64 ticks)
 {
 	/*
 	 * Would multiplication overflow? If so perform computation in two parts.
@@ -183,7 +186,7 @@ pg_ticks_to_ns(instr_time t)
 	 */
 	int64		ns = 0;
 
-	if (unlikely(t.ticks > max_ticks_no_overflow))
+	if (unlikely(ticks > max_ticks_no_overflow))
 	{
 		/*
 		 * Compute how often the maximum number of ticks fits completely into
@@ -192,7 +195,7 @@ pg_ticks_to_ns(instr_time t)
 		 * value. In a 2nd step we adjust the number of elapsed ticks and
 		 * convert the remaining ticks.
 		 */
-		int64		count = t.ticks / max_ticks_no_overflow;
+		int64		count = ticks / max_ticks_no_overflow;
 		int64		max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION;
 
 		ns = max_ns * count;
@@ -201,11 +204,11 @@ pg_ticks_to_ns(instr_time t)
 		 * Subtract the ticks that we now already accounted for, so that they
 		 * don't get counted twice.
 		 */
-		t.ticks -= count * max_ticks_no_overflow;
-		Assert(t.ticks >= 0);
+		ticks -= count * max_ticks_no_overflow;
+		Assert(ticks >= 0);
 	}
 
-	ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION;
+	ns += ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION;
 	return ns;
 }
 
@@ -226,14 +229,14 @@ pg_initialize_get_ticks()
 #define INSTR_TIME_SET_CURRENT(t) \
 	((t) = pg_get_ticks())
 
-#define INSTR_TIME_GET_NANOSEC(t) \
-	pg_ticks_to_ns(t)
-
+#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \
+	(pg_ticks_to_ns(ticks))
 
 #else							/* WIN32 */
 
 
 /* Use QueryPerformanceCounter() */
+#define PG_INSTR_CLOCK_NAME	"QueryPerformanceCounter"
 
 /* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */
 static inline instr_time
@@ -265,8 +268,8 @@ GetTimerFrequency(void)
 #define INSTR_TIME_SET_CURRENT(t) \
 	((t) = pg_query_performance_counter())
 
-#define INSTR_TIME_GET_NANOSEC(t) \
-	((int64) ((t).ticks * ((double) NS_PER_S / GetTimerFrequency())))
+#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \
+	((int64) ((ticks) * ((double) NS_PER_S / GetTimerFrequency())))
 
 #endif							/* WIN32 */
 
@@ -285,9 +288,14 @@ GetTimerFrequency(void)
 #define INSTR_TIME_SUBTRACT(x,y) \
 	((x).ticks -= (y).ticks)
 
+#define INSTR_TIME_DIFF_NANOSEC(x,y) \
+	(INSTR_TIME_TICKS_TO_NANOSEC((x).ticks - (y).ticks))
+
 #define INSTR_TIME_ACCUM_DIFF(x,y,z) \
 	((x).ticks += (y).ticks - (z).ticks)
 
+#define INSTR_TIME_GET_NANOSEC(t) \
+	(INSTR_TIME_TICKS_TO_NANOSEC((t).ticks))
 
 #define INSTR_TIME_GET_DOUBLE(t) \
 	((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S)
-- 
2.47.3


--vtqqtrpooseurzip--





^ permalink  raw  reply  [nested|flat] 265+ messages in thread

* [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source
@ 2025-07-27 15:48  Lukas Fittl <[email protected]>
  0 siblings, 0 replies; 265+ messages in thread

From: Lukas Fittl @ 2025-07-27 15:48 UTC (permalink / raw)

In passing also reduce the per-loop overhead caused by repeated divisions
in INSTR_TIME_GET_NANOSEC when the ticks variable has become very large,
instead diff first and then turn it into nanosecs.
---
 src/bin/pg_test_timing/pg_test_timing.c | 59 +++++++++++++++++++------
 src/include/portability/instr_time.h    | 30 ++++++++-----
 2 files changed, 65 insertions(+), 24 deletions(-)

diff --git a/src/bin/pg_test_timing/pg_test_timing.c b/src/bin/pg_test_timing/pg_test_timing.c
index a5621251afc..b77ef2063b6 100644
--- a/src/bin/pg_test_timing/pg_test_timing.c
+++ b/src/bin/pg_test_timing/pg_test_timing.c
@@ -16,6 +16,7 @@ static const char *progname;
 
 static unsigned int test_duration = 3;
 static double max_rprct = 99.99;
+static bool fast_timing = false;
 
 /* record duration in powers of 2 nanoseconds */
 static long long int histogram[32];
@@ -56,6 +57,7 @@ handle_args(int argc, char *argv[])
 	static struct option long_options[] = {
 		{"duration", required_argument, NULL, 'd'},
 		{"cutoff", required_argument, NULL, 'c'},
+		{"fast", no_argument, NULL, 'f'},
 		{NULL, 0, NULL, 0}
 	};
 
@@ -68,7 +70,7 @@ handle_args(int argc, char *argv[])
 	{
 		if (strcmp(argv[1], "--help") == 0 || strcmp(argv[1], "-?") == 0)
 		{
-			printf(_("Usage: %s [-d DURATION] [-c CUTOFF]\n"), progname);
+			printf(_("Usage: %s [-d DURATION] [-c CUTOFF] [--fast]\n"), progname);
 			exit(0);
 		}
 		if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0)
@@ -78,7 +80,7 @@ handle_args(int argc, char *argv[])
 		}
 	}
 
-	while ((option = getopt_long(argc, argv, "d:c:",
+	while ((option = getopt_long(argc, argv, "d:c:f:",
 								 long_options, &optindex)) != -1)
 	{
 		switch (option)
@@ -125,6 +127,10 @@ handle_args(int argc, char *argv[])
 				}
 				break;
 
+			case 'f':
+				fast_timing = true;
+				break;
+
 			default:
 				fprintf(stderr, _("Try \"%s --help\" for more information.\n"),
 						progname);
@@ -155,11 +161,31 @@ test_timing(unsigned int duration)
 	uint64		total_time;
 	int64		time_elapsed = 0;
 	uint64		loop_count = 0;
-	uint64		prev,
-				cur;
 	instr_time	start_time,
 				end_time,
-				temp;
+				prev,
+				cur;
+	char	   *time_source = NULL;
+	bool		fast_timing_used = false;
+
+	INSTR_TIME_INITIALIZE();
+
+#if !defined(WIN32) && defined(__x86_64__) && defined(__linux__)
+	if (fast_timing && has_rdtsc)
+	{
+		time_source = "RDTSC";
+		fast_timing_used = true;
+	}
+	else if (has_rdtscp)
+		time_source = "RDTSCP";
+	else
+		time_source = PG_INSTR_CLOCK_NAME;
+#else
+	time_source = PG_INSTR_CLOCK_NAME;
+#endif
+	if (fast_timing && !fast_timing_used)
+		printf(_("Warning: Fast timing requested, but not available - regular timing source will be used\n"));
+	printf(_("Time source: %s\n"), time_source);
 
 	/*
 	 * Pre-zero the statistics data structures.  They're already zero by
@@ -173,8 +199,11 @@ test_timing(unsigned int duration)
 
 	total_time = duration > 0 ? duration * INT64CONST(1000000000) : 0;
 
-	INSTR_TIME_SET_CURRENT(start_time);
-	cur = INSTR_TIME_GET_NANOSEC(start_time);
+	if (fast_timing)
+		INSTR_TIME_SET_CURRENT_FAST(start_time);
+	else
+		INSTR_TIME_SET_CURRENT(start_time);
+	cur = start_time;
 
 	while (time_elapsed < total_time)
 	{
@@ -182,9 +211,11 @@ test_timing(unsigned int duration)
 					bits;
 
 		prev = cur;
-		INSTR_TIME_SET_CURRENT(temp);
-		cur = INSTR_TIME_GET_NANOSEC(temp);
-		diff = cur - prev;
+		if (fast_timing)
+			INSTR_TIME_SET_CURRENT_FAST(cur);
+		else
+			INSTR_TIME_SET_CURRENT(cur);
+		diff = INSTR_TIME_DIFF_NANOSEC(cur, prev);
 
 		/* Did time go backwards? */
 		if (unlikely(diff < 0))
@@ -217,11 +248,13 @@ test_timing(unsigned int duration)
 			largest_diff_count++;
 
 		loop_count++;
-		INSTR_TIME_SUBTRACT(temp, start_time);
-		time_elapsed = INSTR_TIME_GET_NANOSEC(temp);
+		time_elapsed = INSTR_TIME_DIFF_NANOSEC(cur, start_time);
 	}
 
-	INSTR_TIME_SET_CURRENT(end_time);
+	if (fast_timing)
+		INSTR_TIME_SET_CURRENT_FAST(end_time);
+	else
+		INSTR_TIME_SET_CURRENT(end_time);
 
 	INSTR_TIME_SUBTRACT(end_time, start_time);
 
diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h
index e2e339a0c4f..f02296f1026 100644
--- a/src/include/portability/instr_time.h
+++ b/src/include/portability/instr_time.h
@@ -112,10 +112,13 @@ extern int64 max_ticks_no_overflow;
  */
 #if defined(__darwin__) && defined(CLOCK_MONOTONIC_RAW)
 #define PG_INSTR_CLOCK	CLOCK_MONOTONIC_RAW
+#define PG_INSTR_CLOCK_NAME	"clock_gettime (CLOCK_MONOTONIC_RAW)"
 #elif defined(CLOCK_MONOTONIC)
 #define PG_INSTR_CLOCK	CLOCK_MONOTONIC
+#define PG_INSTR_CLOCK_NAME	"clock_gettime (CLOCK_MONOTONIC)"
 #else
 #define PG_INSTR_CLOCK	CLOCK_REALTIME
+#define PG_INSTR_CLOCK_NAME	"clock_gettime (CLOCK_REALTIME)"
 #endif
 
 #if defined(__x86_64__) && defined(__linux__)
@@ -174,7 +177,7 @@ pg_get_ticks(void)
 }
 
 static inline int64_t
-pg_ticks_to_ns(instr_time t)
+pg_ticks_to_ns(int64 ticks)
 {
 	/*
 	 * Would multiplication overflow? If so perform computation in two parts.
@@ -183,7 +186,7 @@ pg_ticks_to_ns(instr_time t)
 	 */
 	int64		ns = 0;
 
-	if (unlikely(t.ticks > max_ticks_no_overflow))
+	if (unlikely(ticks > max_ticks_no_overflow))
 	{
 		/*
 		 * Compute how often the maximum number of ticks fits completely into
@@ -192,7 +195,7 @@ pg_ticks_to_ns(instr_time t)
 		 * value. In a 2nd step we adjust the number of elapsed ticks and
 		 * convert the remaining ticks.
 		 */
-		int64		count = t.ticks / max_ticks_no_overflow;
+		int64		count = ticks / max_ticks_no_overflow;
 		int64		max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION;
 
 		ns = max_ns * count;
@@ -201,11 +204,11 @@ pg_ticks_to_ns(instr_time t)
 		 * Subtract the ticks that we now already accounted for, so that they
 		 * don't get counted twice.
 		 */
-		t.ticks -= count * max_ticks_no_overflow;
-		Assert(t.ticks >= 0);
+		ticks -= count * max_ticks_no_overflow;
+		Assert(ticks >= 0);
 	}
 
-	ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION;
+	ns += ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION;
 	return ns;
 }
 
@@ -226,14 +229,14 @@ pg_initialize_get_ticks()
 #define INSTR_TIME_SET_CURRENT(t) \
 	((t) = pg_get_ticks())
 
-#define INSTR_TIME_GET_NANOSEC(t) \
-	pg_ticks_to_ns(t)
-
+#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \
+	(pg_ticks_to_ns(ticks))
 
 #else							/* WIN32 */
 
 
 /* Use QueryPerformanceCounter() */
+#define PG_INSTR_CLOCK_NAME	"QueryPerformanceCounter"
 
 /* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */
 static inline instr_time
@@ -265,8 +268,8 @@ GetTimerFrequency(void)
 #define INSTR_TIME_SET_CURRENT(t) \
 	((t) = pg_query_performance_counter())
 
-#define INSTR_TIME_GET_NANOSEC(t) \
-	((int64) ((t).ticks * ((double) NS_PER_S / GetTimerFrequency())))
+#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \
+	((int64) ((ticks) * ((double) NS_PER_S / GetTimerFrequency())))
 
 #endif							/* WIN32 */
 
@@ -285,9 +288,14 @@ GetTimerFrequency(void)
 #define INSTR_TIME_SUBTRACT(x,y) \
 	((x).ticks -= (y).ticks)
 
+#define INSTR_TIME_DIFF_NANOSEC(x,y) \
+	(INSTR_TIME_TICKS_TO_NANOSEC((x).ticks - (y).ticks))
+
 #define INSTR_TIME_ACCUM_DIFF(x,y,z) \
 	((x).ticks += (y).ticks - (z).ticks)
 
+#define INSTR_TIME_GET_NANOSEC(t) \
+	(INSTR_TIME_TICKS_TO_NANOSEC((t).ticks))
 
 #define INSTR_TIME_GET_DOUBLE(t) \
 	((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S)
-- 
2.47.3


--vtqqtrpooseurzip--





^ permalink  raw  reply  [nested|flat] 265+ messages in thread

* [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source
@ 2025-07-27 15:48  Lukas Fittl <[email protected]>
  0 siblings, 0 replies; 265+ messages in thread

From: Lukas Fittl @ 2025-07-27 15:48 UTC (permalink / raw)

In passing also reduce the per-loop overhead caused by repeated divisions
in INSTR_TIME_GET_NANOSEC when the ticks variable has become very large,
instead diff first and then turn it into nanosecs.
---
 src/bin/pg_test_timing/pg_test_timing.c | 59 +++++++++++++++++++------
 src/include/portability/instr_time.h    | 30 ++++++++-----
 2 files changed, 65 insertions(+), 24 deletions(-)

diff --git a/src/bin/pg_test_timing/pg_test_timing.c b/src/bin/pg_test_timing/pg_test_timing.c
index a5621251afc..b77ef2063b6 100644
--- a/src/bin/pg_test_timing/pg_test_timing.c
+++ b/src/bin/pg_test_timing/pg_test_timing.c
@@ -16,6 +16,7 @@ static const char *progname;
 
 static unsigned int test_duration = 3;
 static double max_rprct = 99.99;
+static bool fast_timing = false;
 
 /* record duration in powers of 2 nanoseconds */
 static long long int histogram[32];
@@ -56,6 +57,7 @@ handle_args(int argc, char *argv[])
 	static struct option long_options[] = {
 		{"duration", required_argument, NULL, 'd'},
 		{"cutoff", required_argument, NULL, 'c'},
+		{"fast", no_argument, NULL, 'f'},
 		{NULL, 0, NULL, 0}
 	};
 
@@ -68,7 +70,7 @@ handle_args(int argc, char *argv[])
 	{
 		if (strcmp(argv[1], "--help") == 0 || strcmp(argv[1], "-?") == 0)
 		{
-			printf(_("Usage: %s [-d DURATION] [-c CUTOFF]\n"), progname);
+			printf(_("Usage: %s [-d DURATION] [-c CUTOFF] [--fast]\n"), progname);
 			exit(0);
 		}
 		if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0)
@@ -78,7 +80,7 @@ handle_args(int argc, char *argv[])
 		}
 	}
 
-	while ((option = getopt_long(argc, argv, "d:c:",
+	while ((option = getopt_long(argc, argv, "d:c:f:",
 								 long_options, &optindex)) != -1)
 	{
 		switch (option)
@@ -125,6 +127,10 @@ handle_args(int argc, char *argv[])
 				}
 				break;
 
+			case 'f':
+				fast_timing = true;
+				break;
+
 			default:
 				fprintf(stderr, _("Try \"%s --help\" for more information.\n"),
 						progname);
@@ -155,11 +161,31 @@ test_timing(unsigned int duration)
 	uint64		total_time;
 	int64		time_elapsed = 0;
 	uint64		loop_count = 0;
-	uint64		prev,
-				cur;
 	instr_time	start_time,
 				end_time,
-				temp;
+				prev,
+				cur;
+	char	   *time_source = NULL;
+	bool		fast_timing_used = false;
+
+	INSTR_TIME_INITIALIZE();
+
+#if !defined(WIN32) && defined(__x86_64__) && defined(__linux__)
+	if (fast_timing && has_rdtsc)
+	{
+		time_source = "RDTSC";
+		fast_timing_used = true;
+	}
+	else if (has_rdtscp)
+		time_source = "RDTSCP";
+	else
+		time_source = PG_INSTR_CLOCK_NAME;
+#else
+	time_source = PG_INSTR_CLOCK_NAME;
+#endif
+	if (fast_timing && !fast_timing_used)
+		printf(_("Warning: Fast timing requested, but not available - regular timing source will be used\n"));
+	printf(_("Time source: %s\n"), time_source);
 
 	/*
 	 * Pre-zero the statistics data structures.  They're already zero by
@@ -173,8 +199,11 @@ test_timing(unsigned int duration)
 
 	total_time = duration > 0 ? duration * INT64CONST(1000000000) : 0;
 
-	INSTR_TIME_SET_CURRENT(start_time);
-	cur = INSTR_TIME_GET_NANOSEC(start_time);
+	if (fast_timing)
+		INSTR_TIME_SET_CURRENT_FAST(start_time);
+	else
+		INSTR_TIME_SET_CURRENT(start_time);
+	cur = start_time;
 
 	while (time_elapsed < total_time)
 	{
@@ -182,9 +211,11 @@ test_timing(unsigned int duration)
 					bits;
 
 		prev = cur;
-		INSTR_TIME_SET_CURRENT(temp);
-		cur = INSTR_TIME_GET_NANOSEC(temp);
-		diff = cur - prev;
+		if (fast_timing)
+			INSTR_TIME_SET_CURRENT_FAST(cur);
+		else
+			INSTR_TIME_SET_CURRENT(cur);
+		diff = INSTR_TIME_DIFF_NANOSEC(cur, prev);
 
 		/* Did time go backwards? */
 		if (unlikely(diff < 0))
@@ -217,11 +248,13 @@ test_timing(unsigned int duration)
 			largest_diff_count++;
 
 		loop_count++;
-		INSTR_TIME_SUBTRACT(temp, start_time);
-		time_elapsed = INSTR_TIME_GET_NANOSEC(temp);
+		time_elapsed = INSTR_TIME_DIFF_NANOSEC(cur, start_time);
 	}
 
-	INSTR_TIME_SET_CURRENT(end_time);
+	if (fast_timing)
+		INSTR_TIME_SET_CURRENT_FAST(end_time);
+	else
+		INSTR_TIME_SET_CURRENT(end_time);
 
 	INSTR_TIME_SUBTRACT(end_time, start_time);
 
diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h
index e2e339a0c4f..f02296f1026 100644
--- a/src/include/portability/instr_time.h
+++ b/src/include/portability/instr_time.h
@@ -112,10 +112,13 @@ extern int64 max_ticks_no_overflow;
  */
 #if defined(__darwin__) && defined(CLOCK_MONOTONIC_RAW)
 #define PG_INSTR_CLOCK	CLOCK_MONOTONIC_RAW
+#define PG_INSTR_CLOCK_NAME	"clock_gettime (CLOCK_MONOTONIC_RAW)"
 #elif defined(CLOCK_MONOTONIC)
 #define PG_INSTR_CLOCK	CLOCK_MONOTONIC
+#define PG_INSTR_CLOCK_NAME	"clock_gettime (CLOCK_MONOTONIC)"
 #else
 #define PG_INSTR_CLOCK	CLOCK_REALTIME
+#define PG_INSTR_CLOCK_NAME	"clock_gettime (CLOCK_REALTIME)"
 #endif
 
 #if defined(__x86_64__) && defined(__linux__)
@@ -174,7 +177,7 @@ pg_get_ticks(void)
 }
 
 static inline int64_t
-pg_ticks_to_ns(instr_time t)
+pg_ticks_to_ns(int64 ticks)
 {
 	/*
 	 * Would multiplication overflow? If so perform computation in two parts.
@@ -183,7 +186,7 @@ pg_ticks_to_ns(instr_time t)
 	 */
 	int64		ns = 0;
 
-	if (unlikely(t.ticks > max_ticks_no_overflow))
+	if (unlikely(ticks > max_ticks_no_overflow))
 	{
 		/*
 		 * Compute how often the maximum number of ticks fits completely into
@@ -192,7 +195,7 @@ pg_ticks_to_ns(instr_time t)
 		 * value. In a 2nd step we adjust the number of elapsed ticks and
 		 * convert the remaining ticks.
 		 */
-		int64		count = t.ticks / max_ticks_no_overflow;
+		int64		count = ticks / max_ticks_no_overflow;
 		int64		max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION;
 
 		ns = max_ns * count;
@@ -201,11 +204,11 @@ pg_ticks_to_ns(instr_time t)
 		 * Subtract the ticks that we now already accounted for, so that they
 		 * don't get counted twice.
 		 */
-		t.ticks -= count * max_ticks_no_overflow;
-		Assert(t.ticks >= 0);
+		ticks -= count * max_ticks_no_overflow;
+		Assert(ticks >= 0);
 	}
 
-	ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION;
+	ns += ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION;
 	return ns;
 }
 
@@ -226,14 +229,14 @@ pg_initialize_get_ticks()
 #define INSTR_TIME_SET_CURRENT(t) \
 	((t) = pg_get_ticks())
 
-#define INSTR_TIME_GET_NANOSEC(t) \
-	pg_ticks_to_ns(t)
-
+#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \
+	(pg_ticks_to_ns(ticks))
 
 #else							/* WIN32 */
 
 
 /* Use QueryPerformanceCounter() */
+#define PG_INSTR_CLOCK_NAME	"QueryPerformanceCounter"
 
 /* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */
 static inline instr_time
@@ -265,8 +268,8 @@ GetTimerFrequency(void)
 #define INSTR_TIME_SET_CURRENT(t) \
 	((t) = pg_query_performance_counter())
 
-#define INSTR_TIME_GET_NANOSEC(t) \
-	((int64) ((t).ticks * ((double) NS_PER_S / GetTimerFrequency())))
+#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \
+	((int64) ((ticks) * ((double) NS_PER_S / GetTimerFrequency())))
 
 #endif							/* WIN32 */
 
@@ -285,9 +288,14 @@ GetTimerFrequency(void)
 #define INSTR_TIME_SUBTRACT(x,y) \
 	((x).ticks -= (y).ticks)
 
+#define INSTR_TIME_DIFF_NANOSEC(x,y) \
+	(INSTR_TIME_TICKS_TO_NANOSEC((x).ticks - (y).ticks))
+
 #define INSTR_TIME_ACCUM_DIFF(x,y,z) \
 	((x).ticks += (y).ticks - (z).ticks)
 
+#define INSTR_TIME_GET_NANOSEC(t) \
+	(INSTR_TIME_TICKS_TO_NANOSEC((t).ticks))
 
 #define INSTR_TIME_GET_DOUBLE(t) \
 	((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S)
-- 
2.47.3


--vtqqtrpooseurzip--





^ permalink  raw  reply  [nested|flat] 265+ messages in thread

* [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source
@ 2025-07-27 15:48  Lukas Fittl <[email protected]>
  0 siblings, 0 replies; 265+ messages in thread

From: Lukas Fittl @ 2025-07-27 15:48 UTC (permalink / raw)

In passing also reduce the per-loop overhead caused by repeated divisions
in INSTR_TIME_GET_NANOSEC when the ticks variable has become very large,
instead diff first and then turn it into nanosecs.
---
 src/bin/pg_test_timing/pg_test_timing.c | 59 +++++++++++++++++++------
 src/include/portability/instr_time.h    | 30 ++++++++-----
 2 files changed, 65 insertions(+), 24 deletions(-)

diff --git a/src/bin/pg_test_timing/pg_test_timing.c b/src/bin/pg_test_timing/pg_test_timing.c
index a5621251afc..b77ef2063b6 100644
--- a/src/bin/pg_test_timing/pg_test_timing.c
+++ b/src/bin/pg_test_timing/pg_test_timing.c
@@ -16,6 +16,7 @@ static const char *progname;
 
 static unsigned int test_duration = 3;
 static double max_rprct = 99.99;
+static bool fast_timing = false;
 
 /* record duration in powers of 2 nanoseconds */
 static long long int histogram[32];
@@ -56,6 +57,7 @@ handle_args(int argc, char *argv[])
 	static struct option long_options[] = {
 		{"duration", required_argument, NULL, 'd'},
 		{"cutoff", required_argument, NULL, 'c'},
+		{"fast", no_argument, NULL, 'f'},
 		{NULL, 0, NULL, 0}
 	};
 
@@ -68,7 +70,7 @@ handle_args(int argc, char *argv[])
 	{
 		if (strcmp(argv[1], "--help") == 0 || strcmp(argv[1], "-?") == 0)
 		{
-			printf(_("Usage: %s [-d DURATION] [-c CUTOFF]\n"), progname);
+			printf(_("Usage: %s [-d DURATION] [-c CUTOFF] [--fast]\n"), progname);
 			exit(0);
 		}
 		if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0)
@@ -78,7 +80,7 @@ handle_args(int argc, char *argv[])
 		}
 	}
 
-	while ((option = getopt_long(argc, argv, "d:c:",
+	while ((option = getopt_long(argc, argv, "d:c:f:",
 								 long_options, &optindex)) != -1)
 	{
 		switch (option)
@@ -125,6 +127,10 @@ handle_args(int argc, char *argv[])
 				}
 				break;
 
+			case 'f':
+				fast_timing = true;
+				break;
+
 			default:
 				fprintf(stderr, _("Try \"%s --help\" for more information.\n"),
 						progname);
@@ -155,11 +161,31 @@ test_timing(unsigned int duration)
 	uint64		total_time;
 	int64		time_elapsed = 0;
 	uint64		loop_count = 0;
-	uint64		prev,
-				cur;
 	instr_time	start_time,
 				end_time,
-				temp;
+				prev,
+				cur;
+	char	   *time_source = NULL;
+	bool		fast_timing_used = false;
+
+	INSTR_TIME_INITIALIZE();
+
+#if !defined(WIN32) && defined(__x86_64__) && defined(__linux__)
+	if (fast_timing && has_rdtsc)
+	{
+		time_source = "RDTSC";
+		fast_timing_used = true;
+	}
+	else if (has_rdtscp)
+		time_source = "RDTSCP";
+	else
+		time_source = PG_INSTR_CLOCK_NAME;
+#else
+	time_source = PG_INSTR_CLOCK_NAME;
+#endif
+	if (fast_timing && !fast_timing_used)
+		printf(_("Warning: Fast timing requested, but not available - regular timing source will be used\n"));
+	printf(_("Time source: %s\n"), time_source);
 
 	/*
 	 * Pre-zero the statistics data structures.  They're already zero by
@@ -173,8 +199,11 @@ test_timing(unsigned int duration)
 
 	total_time = duration > 0 ? duration * INT64CONST(1000000000) : 0;
 
-	INSTR_TIME_SET_CURRENT(start_time);
-	cur = INSTR_TIME_GET_NANOSEC(start_time);
+	if (fast_timing)
+		INSTR_TIME_SET_CURRENT_FAST(start_time);
+	else
+		INSTR_TIME_SET_CURRENT(start_time);
+	cur = start_time;
 
 	while (time_elapsed < total_time)
 	{
@@ -182,9 +211,11 @@ test_timing(unsigned int duration)
 					bits;
 
 		prev = cur;
-		INSTR_TIME_SET_CURRENT(temp);
-		cur = INSTR_TIME_GET_NANOSEC(temp);
-		diff = cur - prev;
+		if (fast_timing)
+			INSTR_TIME_SET_CURRENT_FAST(cur);
+		else
+			INSTR_TIME_SET_CURRENT(cur);
+		diff = INSTR_TIME_DIFF_NANOSEC(cur, prev);
 
 		/* Did time go backwards? */
 		if (unlikely(diff < 0))
@@ -217,11 +248,13 @@ test_timing(unsigned int duration)
 			largest_diff_count++;
 
 		loop_count++;
-		INSTR_TIME_SUBTRACT(temp, start_time);
-		time_elapsed = INSTR_TIME_GET_NANOSEC(temp);
+		time_elapsed = INSTR_TIME_DIFF_NANOSEC(cur, start_time);
 	}
 
-	INSTR_TIME_SET_CURRENT(end_time);
+	if (fast_timing)
+		INSTR_TIME_SET_CURRENT_FAST(end_time);
+	else
+		INSTR_TIME_SET_CURRENT(end_time);
 
 	INSTR_TIME_SUBTRACT(end_time, start_time);
 
diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h
index e2e339a0c4f..f02296f1026 100644
--- a/src/include/portability/instr_time.h
+++ b/src/include/portability/instr_time.h
@@ -112,10 +112,13 @@ extern int64 max_ticks_no_overflow;
  */
 #if defined(__darwin__) && defined(CLOCK_MONOTONIC_RAW)
 #define PG_INSTR_CLOCK	CLOCK_MONOTONIC_RAW
+#define PG_INSTR_CLOCK_NAME	"clock_gettime (CLOCK_MONOTONIC_RAW)"
 #elif defined(CLOCK_MONOTONIC)
 #define PG_INSTR_CLOCK	CLOCK_MONOTONIC
+#define PG_INSTR_CLOCK_NAME	"clock_gettime (CLOCK_MONOTONIC)"
 #else
 #define PG_INSTR_CLOCK	CLOCK_REALTIME
+#define PG_INSTR_CLOCK_NAME	"clock_gettime (CLOCK_REALTIME)"
 #endif
 
 #if defined(__x86_64__) && defined(__linux__)
@@ -174,7 +177,7 @@ pg_get_ticks(void)
 }
 
 static inline int64_t
-pg_ticks_to_ns(instr_time t)
+pg_ticks_to_ns(int64 ticks)
 {
 	/*
 	 * Would multiplication overflow? If so perform computation in two parts.
@@ -183,7 +186,7 @@ pg_ticks_to_ns(instr_time t)
 	 */
 	int64		ns = 0;
 
-	if (unlikely(t.ticks > max_ticks_no_overflow))
+	if (unlikely(ticks > max_ticks_no_overflow))
 	{
 		/*
 		 * Compute how often the maximum number of ticks fits completely into
@@ -192,7 +195,7 @@ pg_ticks_to_ns(instr_time t)
 		 * value. In a 2nd step we adjust the number of elapsed ticks and
 		 * convert the remaining ticks.
 		 */
-		int64		count = t.ticks / max_ticks_no_overflow;
+		int64		count = ticks / max_ticks_no_overflow;
 		int64		max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION;
 
 		ns = max_ns * count;
@@ -201,11 +204,11 @@ pg_ticks_to_ns(instr_time t)
 		 * Subtract the ticks that we now already accounted for, so that they
 		 * don't get counted twice.
 		 */
-		t.ticks -= count * max_ticks_no_overflow;
-		Assert(t.ticks >= 0);
+		ticks -= count * max_ticks_no_overflow;
+		Assert(ticks >= 0);
 	}
 
-	ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION;
+	ns += ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION;
 	return ns;
 }
 
@@ -226,14 +229,14 @@ pg_initialize_get_ticks()
 #define INSTR_TIME_SET_CURRENT(t) \
 	((t) = pg_get_ticks())
 
-#define INSTR_TIME_GET_NANOSEC(t) \
-	pg_ticks_to_ns(t)
-
+#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \
+	(pg_ticks_to_ns(ticks))
 
 #else							/* WIN32 */
 
 
 /* Use QueryPerformanceCounter() */
+#define PG_INSTR_CLOCK_NAME	"QueryPerformanceCounter"
 
 /* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */
 static inline instr_time
@@ -265,8 +268,8 @@ GetTimerFrequency(void)
 #define INSTR_TIME_SET_CURRENT(t) \
 	((t) = pg_query_performance_counter())
 
-#define INSTR_TIME_GET_NANOSEC(t) \
-	((int64) ((t).ticks * ((double) NS_PER_S / GetTimerFrequency())))
+#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \
+	((int64) ((ticks) * ((double) NS_PER_S / GetTimerFrequency())))
 
 #endif							/* WIN32 */
 
@@ -285,9 +288,14 @@ GetTimerFrequency(void)
 #define INSTR_TIME_SUBTRACT(x,y) \
 	((x).ticks -= (y).ticks)
 
+#define INSTR_TIME_DIFF_NANOSEC(x,y) \
+	(INSTR_TIME_TICKS_TO_NANOSEC((x).ticks - (y).ticks))
+
 #define INSTR_TIME_ACCUM_DIFF(x,y,z) \
 	((x).ticks += (y).ticks - (z).ticks)
 
+#define INSTR_TIME_GET_NANOSEC(t) \
+	(INSTR_TIME_TICKS_TO_NANOSEC((t).ticks))
 
 #define INSTR_TIME_GET_DOUBLE(t) \
 	((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S)
-- 
2.47.3


--vtqqtrpooseurzip--





^ permalink  raw  reply  [nested|flat] 265+ messages in thread

* [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source
@ 2025-07-27 15:48  Lukas Fittl <[email protected]>
  0 siblings, 0 replies; 265+ messages in thread

From: Lukas Fittl @ 2025-07-27 15:48 UTC (permalink / raw)

In passing also reduce the per-loop overhead caused by repeated divisions
in INSTR_TIME_GET_NANOSEC when the ticks variable has become very large,
instead diff first and then turn it into nanosecs.
---
 src/bin/pg_test_timing/pg_test_timing.c | 59 +++++++++++++++++++------
 src/include/portability/instr_time.h    | 30 ++++++++-----
 2 files changed, 65 insertions(+), 24 deletions(-)

diff --git a/src/bin/pg_test_timing/pg_test_timing.c b/src/bin/pg_test_timing/pg_test_timing.c
index a5621251afc..b77ef2063b6 100644
--- a/src/bin/pg_test_timing/pg_test_timing.c
+++ b/src/bin/pg_test_timing/pg_test_timing.c
@@ -16,6 +16,7 @@ static const char *progname;
 
 static unsigned int test_duration = 3;
 static double max_rprct = 99.99;
+static bool fast_timing = false;
 
 /* record duration in powers of 2 nanoseconds */
 static long long int histogram[32];
@@ -56,6 +57,7 @@ handle_args(int argc, char *argv[])
 	static struct option long_options[] = {
 		{"duration", required_argument, NULL, 'd'},
 		{"cutoff", required_argument, NULL, 'c'},
+		{"fast", no_argument, NULL, 'f'},
 		{NULL, 0, NULL, 0}
 	};
 
@@ -68,7 +70,7 @@ handle_args(int argc, char *argv[])
 	{
 		if (strcmp(argv[1], "--help") == 0 || strcmp(argv[1], "-?") == 0)
 		{
-			printf(_("Usage: %s [-d DURATION] [-c CUTOFF]\n"), progname);
+			printf(_("Usage: %s [-d DURATION] [-c CUTOFF] [--fast]\n"), progname);
 			exit(0);
 		}
 		if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0)
@@ -78,7 +80,7 @@ handle_args(int argc, char *argv[])
 		}
 	}
 
-	while ((option = getopt_long(argc, argv, "d:c:",
+	while ((option = getopt_long(argc, argv, "d:c:f:",
 								 long_options, &optindex)) != -1)
 	{
 		switch (option)
@@ -125,6 +127,10 @@ handle_args(int argc, char *argv[])
 				}
 				break;
 
+			case 'f':
+				fast_timing = true;
+				break;
+
 			default:
 				fprintf(stderr, _("Try \"%s --help\" for more information.\n"),
 						progname);
@@ -155,11 +161,31 @@ test_timing(unsigned int duration)
 	uint64		total_time;
 	int64		time_elapsed = 0;
 	uint64		loop_count = 0;
-	uint64		prev,
-				cur;
 	instr_time	start_time,
 				end_time,
-				temp;
+				prev,
+				cur;
+	char	   *time_source = NULL;
+	bool		fast_timing_used = false;
+
+	INSTR_TIME_INITIALIZE();
+
+#if !defined(WIN32) && defined(__x86_64__) && defined(__linux__)
+	if (fast_timing && has_rdtsc)
+	{
+		time_source = "RDTSC";
+		fast_timing_used = true;
+	}
+	else if (has_rdtscp)
+		time_source = "RDTSCP";
+	else
+		time_source = PG_INSTR_CLOCK_NAME;
+#else
+	time_source = PG_INSTR_CLOCK_NAME;
+#endif
+	if (fast_timing && !fast_timing_used)
+		printf(_("Warning: Fast timing requested, but not available - regular timing source will be used\n"));
+	printf(_("Time source: %s\n"), time_source);
 
 	/*
 	 * Pre-zero the statistics data structures.  They're already zero by
@@ -173,8 +199,11 @@ test_timing(unsigned int duration)
 
 	total_time = duration > 0 ? duration * INT64CONST(1000000000) : 0;
 
-	INSTR_TIME_SET_CURRENT(start_time);
-	cur = INSTR_TIME_GET_NANOSEC(start_time);
+	if (fast_timing)
+		INSTR_TIME_SET_CURRENT_FAST(start_time);
+	else
+		INSTR_TIME_SET_CURRENT(start_time);
+	cur = start_time;
 
 	while (time_elapsed < total_time)
 	{
@@ -182,9 +211,11 @@ test_timing(unsigned int duration)
 					bits;
 
 		prev = cur;
-		INSTR_TIME_SET_CURRENT(temp);
-		cur = INSTR_TIME_GET_NANOSEC(temp);
-		diff = cur - prev;
+		if (fast_timing)
+			INSTR_TIME_SET_CURRENT_FAST(cur);
+		else
+			INSTR_TIME_SET_CURRENT(cur);
+		diff = INSTR_TIME_DIFF_NANOSEC(cur, prev);
 
 		/* Did time go backwards? */
 		if (unlikely(diff < 0))
@@ -217,11 +248,13 @@ test_timing(unsigned int duration)
 			largest_diff_count++;
 
 		loop_count++;
-		INSTR_TIME_SUBTRACT(temp, start_time);
-		time_elapsed = INSTR_TIME_GET_NANOSEC(temp);
+		time_elapsed = INSTR_TIME_DIFF_NANOSEC(cur, start_time);
 	}
 
-	INSTR_TIME_SET_CURRENT(end_time);
+	if (fast_timing)
+		INSTR_TIME_SET_CURRENT_FAST(end_time);
+	else
+		INSTR_TIME_SET_CURRENT(end_time);
 
 	INSTR_TIME_SUBTRACT(end_time, start_time);
 
diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h
index e2e339a0c4f..f02296f1026 100644
--- a/src/include/portability/instr_time.h
+++ b/src/include/portability/instr_time.h
@@ -112,10 +112,13 @@ extern int64 max_ticks_no_overflow;
  */
 #if defined(__darwin__) && defined(CLOCK_MONOTONIC_RAW)
 #define PG_INSTR_CLOCK	CLOCK_MONOTONIC_RAW
+#define PG_INSTR_CLOCK_NAME	"clock_gettime (CLOCK_MONOTONIC_RAW)"
 #elif defined(CLOCK_MONOTONIC)
 #define PG_INSTR_CLOCK	CLOCK_MONOTONIC
+#define PG_INSTR_CLOCK_NAME	"clock_gettime (CLOCK_MONOTONIC)"
 #else
 #define PG_INSTR_CLOCK	CLOCK_REALTIME
+#define PG_INSTR_CLOCK_NAME	"clock_gettime (CLOCK_REALTIME)"
 #endif
 
 #if defined(__x86_64__) && defined(__linux__)
@@ -174,7 +177,7 @@ pg_get_ticks(void)
 }
 
 static inline int64_t
-pg_ticks_to_ns(instr_time t)
+pg_ticks_to_ns(int64 ticks)
 {
 	/*
 	 * Would multiplication overflow? If so perform computation in two parts.
@@ -183,7 +186,7 @@ pg_ticks_to_ns(instr_time t)
 	 */
 	int64		ns = 0;
 
-	if (unlikely(t.ticks > max_ticks_no_overflow))
+	if (unlikely(ticks > max_ticks_no_overflow))
 	{
 		/*
 		 * Compute how often the maximum number of ticks fits completely into
@@ -192,7 +195,7 @@ pg_ticks_to_ns(instr_time t)
 		 * value. In a 2nd step we adjust the number of elapsed ticks and
 		 * convert the remaining ticks.
 		 */
-		int64		count = t.ticks / max_ticks_no_overflow;
+		int64		count = ticks / max_ticks_no_overflow;
 		int64		max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION;
 
 		ns = max_ns * count;
@@ -201,11 +204,11 @@ pg_ticks_to_ns(instr_time t)
 		 * Subtract the ticks that we now already accounted for, so that they
 		 * don't get counted twice.
 		 */
-		t.ticks -= count * max_ticks_no_overflow;
-		Assert(t.ticks >= 0);
+		ticks -= count * max_ticks_no_overflow;
+		Assert(ticks >= 0);
 	}
 
-	ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION;
+	ns += ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION;
 	return ns;
 }
 
@@ -226,14 +229,14 @@ pg_initialize_get_ticks()
 #define INSTR_TIME_SET_CURRENT(t) \
 	((t) = pg_get_ticks())
 
-#define INSTR_TIME_GET_NANOSEC(t) \
-	pg_ticks_to_ns(t)
-
+#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \
+	(pg_ticks_to_ns(ticks))
 
 #else							/* WIN32 */
 
 
 /* Use QueryPerformanceCounter() */
+#define PG_INSTR_CLOCK_NAME	"QueryPerformanceCounter"
 
 /* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */
 static inline instr_time
@@ -265,8 +268,8 @@ GetTimerFrequency(void)
 #define INSTR_TIME_SET_CURRENT(t) \
 	((t) = pg_query_performance_counter())
 
-#define INSTR_TIME_GET_NANOSEC(t) \
-	((int64) ((t).ticks * ((double) NS_PER_S / GetTimerFrequency())))
+#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \
+	((int64) ((ticks) * ((double) NS_PER_S / GetTimerFrequency())))
 
 #endif							/* WIN32 */
 
@@ -285,9 +288,14 @@ GetTimerFrequency(void)
 #define INSTR_TIME_SUBTRACT(x,y) \
 	((x).ticks -= (y).ticks)
 
+#define INSTR_TIME_DIFF_NANOSEC(x,y) \
+	(INSTR_TIME_TICKS_TO_NANOSEC((x).ticks - (y).ticks))
+
 #define INSTR_TIME_ACCUM_DIFF(x,y,z) \
 	((x).ticks += (y).ticks - (z).ticks)
 
+#define INSTR_TIME_GET_NANOSEC(t) \
+	(INSTR_TIME_TICKS_TO_NANOSEC((t).ticks))
 
 #define INSTR_TIME_GET_DOUBLE(t) \
 	((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S)
-- 
2.47.3


--vtqqtrpooseurzip--





^ permalink  raw  reply  [nested|flat] 265+ messages in thread

* [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source
@ 2025-07-27 15:48  Lukas Fittl <[email protected]>
  0 siblings, 0 replies; 265+ messages in thread

From: Lukas Fittl @ 2025-07-27 15:48 UTC (permalink / raw)

In passing also reduce the per-loop overhead caused by repeated divisions
in INSTR_TIME_GET_NANOSEC when the ticks variable has become very large,
instead diff first and then turn it into nanosecs.
---
 src/bin/pg_test_timing/pg_test_timing.c | 59 +++++++++++++++++++------
 src/include/portability/instr_time.h    | 30 ++++++++-----
 2 files changed, 65 insertions(+), 24 deletions(-)

diff --git a/src/bin/pg_test_timing/pg_test_timing.c b/src/bin/pg_test_timing/pg_test_timing.c
index a5621251afc..b77ef2063b6 100644
--- a/src/bin/pg_test_timing/pg_test_timing.c
+++ b/src/bin/pg_test_timing/pg_test_timing.c
@@ -16,6 +16,7 @@ static const char *progname;
 
 static unsigned int test_duration = 3;
 static double max_rprct = 99.99;
+static bool fast_timing = false;
 
 /* record duration in powers of 2 nanoseconds */
 static long long int histogram[32];
@@ -56,6 +57,7 @@ handle_args(int argc, char *argv[])
 	static struct option long_options[] = {
 		{"duration", required_argument, NULL, 'd'},
 		{"cutoff", required_argument, NULL, 'c'},
+		{"fast", no_argument, NULL, 'f'},
 		{NULL, 0, NULL, 0}
 	};
 
@@ -68,7 +70,7 @@ handle_args(int argc, char *argv[])
 	{
 		if (strcmp(argv[1], "--help") == 0 || strcmp(argv[1], "-?") == 0)
 		{
-			printf(_("Usage: %s [-d DURATION] [-c CUTOFF]\n"), progname);
+			printf(_("Usage: %s [-d DURATION] [-c CUTOFF] [--fast]\n"), progname);
 			exit(0);
 		}
 		if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0)
@@ -78,7 +80,7 @@ handle_args(int argc, char *argv[])
 		}
 	}
 
-	while ((option = getopt_long(argc, argv, "d:c:",
+	while ((option = getopt_long(argc, argv, "d:c:f:",
 								 long_options, &optindex)) != -1)
 	{
 		switch (option)
@@ -125,6 +127,10 @@ handle_args(int argc, char *argv[])
 				}
 				break;
 
+			case 'f':
+				fast_timing = true;
+				break;
+
 			default:
 				fprintf(stderr, _("Try \"%s --help\" for more information.\n"),
 						progname);
@@ -155,11 +161,31 @@ test_timing(unsigned int duration)
 	uint64		total_time;
 	int64		time_elapsed = 0;
 	uint64		loop_count = 0;
-	uint64		prev,
-				cur;
 	instr_time	start_time,
 				end_time,
-				temp;
+				prev,
+				cur;
+	char	   *time_source = NULL;
+	bool		fast_timing_used = false;
+
+	INSTR_TIME_INITIALIZE();
+
+#if !defined(WIN32) && defined(__x86_64__) && defined(__linux__)
+	if (fast_timing && has_rdtsc)
+	{
+		time_source = "RDTSC";
+		fast_timing_used = true;
+	}
+	else if (has_rdtscp)
+		time_source = "RDTSCP";
+	else
+		time_source = PG_INSTR_CLOCK_NAME;
+#else
+	time_source = PG_INSTR_CLOCK_NAME;
+#endif
+	if (fast_timing && !fast_timing_used)
+		printf(_("Warning: Fast timing requested, but not available - regular timing source will be used\n"));
+	printf(_("Time source: %s\n"), time_source);
 
 	/*
 	 * Pre-zero the statistics data structures.  They're already zero by
@@ -173,8 +199,11 @@ test_timing(unsigned int duration)
 
 	total_time = duration > 0 ? duration * INT64CONST(1000000000) : 0;
 
-	INSTR_TIME_SET_CURRENT(start_time);
-	cur = INSTR_TIME_GET_NANOSEC(start_time);
+	if (fast_timing)
+		INSTR_TIME_SET_CURRENT_FAST(start_time);
+	else
+		INSTR_TIME_SET_CURRENT(start_time);
+	cur = start_time;
 
 	while (time_elapsed < total_time)
 	{
@@ -182,9 +211,11 @@ test_timing(unsigned int duration)
 					bits;
 
 		prev = cur;
-		INSTR_TIME_SET_CURRENT(temp);
-		cur = INSTR_TIME_GET_NANOSEC(temp);
-		diff = cur - prev;
+		if (fast_timing)
+			INSTR_TIME_SET_CURRENT_FAST(cur);
+		else
+			INSTR_TIME_SET_CURRENT(cur);
+		diff = INSTR_TIME_DIFF_NANOSEC(cur, prev);
 
 		/* Did time go backwards? */
 		if (unlikely(diff < 0))
@@ -217,11 +248,13 @@ test_timing(unsigned int duration)
 			largest_diff_count++;
 
 		loop_count++;
-		INSTR_TIME_SUBTRACT(temp, start_time);
-		time_elapsed = INSTR_TIME_GET_NANOSEC(temp);
+		time_elapsed = INSTR_TIME_DIFF_NANOSEC(cur, start_time);
 	}
 
-	INSTR_TIME_SET_CURRENT(end_time);
+	if (fast_timing)
+		INSTR_TIME_SET_CURRENT_FAST(end_time);
+	else
+		INSTR_TIME_SET_CURRENT(end_time);
 
 	INSTR_TIME_SUBTRACT(end_time, start_time);
 
diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h
index e2e339a0c4f..f02296f1026 100644
--- a/src/include/portability/instr_time.h
+++ b/src/include/portability/instr_time.h
@@ -112,10 +112,13 @@ extern int64 max_ticks_no_overflow;
  */
 #if defined(__darwin__) && defined(CLOCK_MONOTONIC_RAW)
 #define PG_INSTR_CLOCK	CLOCK_MONOTONIC_RAW
+#define PG_INSTR_CLOCK_NAME	"clock_gettime (CLOCK_MONOTONIC_RAW)"
 #elif defined(CLOCK_MONOTONIC)
 #define PG_INSTR_CLOCK	CLOCK_MONOTONIC
+#define PG_INSTR_CLOCK_NAME	"clock_gettime (CLOCK_MONOTONIC)"
 #else
 #define PG_INSTR_CLOCK	CLOCK_REALTIME
+#define PG_INSTR_CLOCK_NAME	"clock_gettime (CLOCK_REALTIME)"
 #endif
 
 #if defined(__x86_64__) && defined(__linux__)
@@ -174,7 +177,7 @@ pg_get_ticks(void)
 }
 
 static inline int64_t
-pg_ticks_to_ns(instr_time t)
+pg_ticks_to_ns(int64 ticks)
 {
 	/*
 	 * Would multiplication overflow? If so perform computation in two parts.
@@ -183,7 +186,7 @@ pg_ticks_to_ns(instr_time t)
 	 */
 	int64		ns = 0;
 
-	if (unlikely(t.ticks > max_ticks_no_overflow))
+	if (unlikely(ticks > max_ticks_no_overflow))
 	{
 		/*
 		 * Compute how often the maximum number of ticks fits completely into
@@ -192,7 +195,7 @@ pg_ticks_to_ns(instr_time t)
 		 * value. In a 2nd step we adjust the number of elapsed ticks and
 		 * convert the remaining ticks.
 		 */
-		int64		count = t.ticks / max_ticks_no_overflow;
+		int64		count = ticks / max_ticks_no_overflow;
 		int64		max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION;
 
 		ns = max_ns * count;
@@ -201,11 +204,11 @@ pg_ticks_to_ns(instr_time t)
 		 * Subtract the ticks that we now already accounted for, so that they
 		 * don't get counted twice.
 		 */
-		t.ticks -= count * max_ticks_no_overflow;
-		Assert(t.ticks >= 0);
+		ticks -= count * max_ticks_no_overflow;
+		Assert(ticks >= 0);
 	}
 
-	ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION;
+	ns += ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION;
 	return ns;
 }
 
@@ -226,14 +229,14 @@ pg_initialize_get_ticks()
 #define INSTR_TIME_SET_CURRENT(t) \
 	((t) = pg_get_ticks())
 
-#define INSTR_TIME_GET_NANOSEC(t) \
-	pg_ticks_to_ns(t)
-
+#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \
+	(pg_ticks_to_ns(ticks))
 
 #else							/* WIN32 */
 
 
 /* Use QueryPerformanceCounter() */
+#define PG_INSTR_CLOCK_NAME	"QueryPerformanceCounter"
 
 /* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */
 static inline instr_time
@@ -265,8 +268,8 @@ GetTimerFrequency(void)
 #define INSTR_TIME_SET_CURRENT(t) \
 	((t) = pg_query_performance_counter())
 
-#define INSTR_TIME_GET_NANOSEC(t) \
-	((int64) ((t).ticks * ((double) NS_PER_S / GetTimerFrequency())))
+#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \
+	((int64) ((ticks) * ((double) NS_PER_S / GetTimerFrequency())))
 
 #endif							/* WIN32 */
 
@@ -285,9 +288,14 @@ GetTimerFrequency(void)
 #define INSTR_TIME_SUBTRACT(x,y) \
 	((x).ticks -= (y).ticks)
 
+#define INSTR_TIME_DIFF_NANOSEC(x,y) \
+	(INSTR_TIME_TICKS_TO_NANOSEC((x).ticks - (y).ticks))
+
 #define INSTR_TIME_ACCUM_DIFF(x,y,z) \
 	((x).ticks += (y).ticks - (z).ticks)
 
+#define INSTR_TIME_GET_NANOSEC(t) \
+	(INSTR_TIME_TICKS_TO_NANOSEC((t).ticks))
 
 #define INSTR_TIME_GET_DOUBLE(t) \
 	((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S)
-- 
2.47.3


--vtqqtrpooseurzip--





^ permalink  raw  reply  [nested|flat] 265+ messages in thread

* [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source
@ 2025-07-27 15:48  Lukas Fittl <[email protected]>
  0 siblings, 0 replies; 265+ messages in thread

From: Lukas Fittl @ 2025-07-27 15:48 UTC (permalink / raw)

In passing also reduce the per-loop overhead caused by repeated divisions
in INSTR_TIME_GET_NANOSEC when the ticks variable has become very large,
instead diff first and then turn it into nanosecs.
---
 src/bin/pg_test_timing/pg_test_timing.c | 59 +++++++++++++++++++------
 src/include/portability/instr_time.h    | 30 ++++++++-----
 2 files changed, 65 insertions(+), 24 deletions(-)

diff --git a/src/bin/pg_test_timing/pg_test_timing.c b/src/bin/pg_test_timing/pg_test_timing.c
index a5621251afc..b77ef2063b6 100644
--- a/src/bin/pg_test_timing/pg_test_timing.c
+++ b/src/bin/pg_test_timing/pg_test_timing.c
@@ -16,6 +16,7 @@ static const char *progname;
 
 static unsigned int test_duration = 3;
 static double max_rprct = 99.99;
+static bool fast_timing = false;
 
 /* record duration in powers of 2 nanoseconds */
 static long long int histogram[32];
@@ -56,6 +57,7 @@ handle_args(int argc, char *argv[])
 	static struct option long_options[] = {
 		{"duration", required_argument, NULL, 'd'},
 		{"cutoff", required_argument, NULL, 'c'},
+		{"fast", no_argument, NULL, 'f'},
 		{NULL, 0, NULL, 0}
 	};
 
@@ -68,7 +70,7 @@ handle_args(int argc, char *argv[])
 	{
 		if (strcmp(argv[1], "--help") == 0 || strcmp(argv[1], "-?") == 0)
 		{
-			printf(_("Usage: %s [-d DURATION] [-c CUTOFF]\n"), progname);
+			printf(_("Usage: %s [-d DURATION] [-c CUTOFF] [--fast]\n"), progname);
 			exit(0);
 		}
 		if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0)
@@ -78,7 +80,7 @@ handle_args(int argc, char *argv[])
 		}
 	}
 
-	while ((option = getopt_long(argc, argv, "d:c:",
+	while ((option = getopt_long(argc, argv, "d:c:f:",
 								 long_options, &optindex)) != -1)
 	{
 		switch (option)
@@ -125,6 +127,10 @@ handle_args(int argc, char *argv[])
 				}
 				break;
 
+			case 'f':
+				fast_timing = true;
+				break;
+
 			default:
 				fprintf(stderr, _("Try \"%s --help\" for more information.\n"),
 						progname);
@@ -155,11 +161,31 @@ test_timing(unsigned int duration)
 	uint64		total_time;
 	int64		time_elapsed = 0;
 	uint64		loop_count = 0;
-	uint64		prev,
-				cur;
 	instr_time	start_time,
 				end_time,
-				temp;
+				prev,
+				cur;
+	char	   *time_source = NULL;
+	bool		fast_timing_used = false;
+
+	INSTR_TIME_INITIALIZE();
+
+#if !defined(WIN32) && defined(__x86_64__) && defined(__linux__)
+	if (fast_timing && has_rdtsc)
+	{
+		time_source = "RDTSC";
+		fast_timing_used = true;
+	}
+	else if (has_rdtscp)
+		time_source = "RDTSCP";
+	else
+		time_source = PG_INSTR_CLOCK_NAME;
+#else
+	time_source = PG_INSTR_CLOCK_NAME;
+#endif
+	if (fast_timing && !fast_timing_used)
+		printf(_("Warning: Fast timing requested, but not available - regular timing source will be used\n"));
+	printf(_("Time source: %s\n"), time_source);
 
 	/*
 	 * Pre-zero the statistics data structures.  They're already zero by
@@ -173,8 +199,11 @@ test_timing(unsigned int duration)
 
 	total_time = duration > 0 ? duration * INT64CONST(1000000000) : 0;
 
-	INSTR_TIME_SET_CURRENT(start_time);
-	cur = INSTR_TIME_GET_NANOSEC(start_time);
+	if (fast_timing)
+		INSTR_TIME_SET_CURRENT_FAST(start_time);
+	else
+		INSTR_TIME_SET_CURRENT(start_time);
+	cur = start_time;
 
 	while (time_elapsed < total_time)
 	{
@@ -182,9 +211,11 @@ test_timing(unsigned int duration)
 					bits;
 
 		prev = cur;
-		INSTR_TIME_SET_CURRENT(temp);
-		cur = INSTR_TIME_GET_NANOSEC(temp);
-		diff = cur - prev;
+		if (fast_timing)
+			INSTR_TIME_SET_CURRENT_FAST(cur);
+		else
+			INSTR_TIME_SET_CURRENT(cur);
+		diff = INSTR_TIME_DIFF_NANOSEC(cur, prev);
 
 		/* Did time go backwards? */
 		if (unlikely(diff < 0))
@@ -217,11 +248,13 @@ test_timing(unsigned int duration)
 			largest_diff_count++;
 
 		loop_count++;
-		INSTR_TIME_SUBTRACT(temp, start_time);
-		time_elapsed = INSTR_TIME_GET_NANOSEC(temp);
+		time_elapsed = INSTR_TIME_DIFF_NANOSEC(cur, start_time);
 	}
 
-	INSTR_TIME_SET_CURRENT(end_time);
+	if (fast_timing)
+		INSTR_TIME_SET_CURRENT_FAST(end_time);
+	else
+		INSTR_TIME_SET_CURRENT(end_time);
 
 	INSTR_TIME_SUBTRACT(end_time, start_time);
 
diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h
index e2e339a0c4f..f02296f1026 100644
--- a/src/include/portability/instr_time.h
+++ b/src/include/portability/instr_time.h
@@ -112,10 +112,13 @@ extern int64 max_ticks_no_overflow;
  */
 #if defined(__darwin__) && defined(CLOCK_MONOTONIC_RAW)
 #define PG_INSTR_CLOCK	CLOCK_MONOTONIC_RAW
+#define PG_INSTR_CLOCK_NAME	"clock_gettime (CLOCK_MONOTONIC_RAW)"
 #elif defined(CLOCK_MONOTONIC)
 #define PG_INSTR_CLOCK	CLOCK_MONOTONIC
+#define PG_INSTR_CLOCK_NAME	"clock_gettime (CLOCK_MONOTONIC)"
 #else
 #define PG_INSTR_CLOCK	CLOCK_REALTIME
+#define PG_INSTR_CLOCK_NAME	"clock_gettime (CLOCK_REALTIME)"
 #endif
 
 #if defined(__x86_64__) && defined(__linux__)
@@ -174,7 +177,7 @@ pg_get_ticks(void)
 }
 
 static inline int64_t
-pg_ticks_to_ns(instr_time t)
+pg_ticks_to_ns(int64 ticks)
 {
 	/*
 	 * Would multiplication overflow? If so perform computation in two parts.
@@ -183,7 +186,7 @@ pg_ticks_to_ns(instr_time t)
 	 */
 	int64		ns = 0;
 
-	if (unlikely(t.ticks > max_ticks_no_overflow))
+	if (unlikely(ticks > max_ticks_no_overflow))
 	{
 		/*
 		 * Compute how often the maximum number of ticks fits completely into
@@ -192,7 +195,7 @@ pg_ticks_to_ns(instr_time t)
 		 * value. In a 2nd step we adjust the number of elapsed ticks and
 		 * convert the remaining ticks.
 		 */
-		int64		count = t.ticks / max_ticks_no_overflow;
+		int64		count = ticks / max_ticks_no_overflow;
 		int64		max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION;
 
 		ns = max_ns * count;
@@ -201,11 +204,11 @@ pg_ticks_to_ns(instr_time t)
 		 * Subtract the ticks that we now already accounted for, so that they
 		 * don't get counted twice.
 		 */
-		t.ticks -= count * max_ticks_no_overflow;
-		Assert(t.ticks >= 0);
+		ticks -= count * max_ticks_no_overflow;
+		Assert(ticks >= 0);
 	}
 
-	ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION;
+	ns += ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION;
 	return ns;
 }
 
@@ -226,14 +229,14 @@ pg_initialize_get_ticks()
 #define INSTR_TIME_SET_CURRENT(t) \
 	((t) = pg_get_ticks())
 
-#define INSTR_TIME_GET_NANOSEC(t) \
-	pg_ticks_to_ns(t)
-
+#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \
+	(pg_ticks_to_ns(ticks))
 
 #else							/* WIN32 */
 
 
 /* Use QueryPerformanceCounter() */
+#define PG_INSTR_CLOCK_NAME	"QueryPerformanceCounter"
 
 /* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */
 static inline instr_time
@@ -265,8 +268,8 @@ GetTimerFrequency(void)
 #define INSTR_TIME_SET_CURRENT(t) \
 	((t) = pg_query_performance_counter())
 
-#define INSTR_TIME_GET_NANOSEC(t) \
-	((int64) ((t).ticks * ((double) NS_PER_S / GetTimerFrequency())))
+#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \
+	((int64) ((ticks) * ((double) NS_PER_S / GetTimerFrequency())))
 
 #endif							/* WIN32 */
 
@@ -285,9 +288,14 @@ GetTimerFrequency(void)
 #define INSTR_TIME_SUBTRACT(x,y) \
 	((x).ticks -= (y).ticks)
 
+#define INSTR_TIME_DIFF_NANOSEC(x,y) \
+	(INSTR_TIME_TICKS_TO_NANOSEC((x).ticks - (y).ticks))
+
 #define INSTR_TIME_ACCUM_DIFF(x,y,z) \
 	((x).ticks += (y).ticks - (z).ticks)
 
+#define INSTR_TIME_GET_NANOSEC(t) \
+	(INSTR_TIME_TICKS_TO_NANOSEC((t).ticks))
 
 #define INSTR_TIME_GET_DOUBLE(t) \
 	((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S)
-- 
2.47.3


--vtqqtrpooseurzip--





^ permalink  raw  reply  [nested|flat] 265+ messages in thread

* [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source
@ 2025-07-27 15:48  Lukas Fittl <[email protected]>
  0 siblings, 0 replies; 265+ messages in thread

From: Lukas Fittl @ 2025-07-27 15:48 UTC (permalink / raw)

In passing also reduce the per-loop overhead caused by repeated divisions
in INSTR_TIME_GET_NANOSEC when the ticks variable has become very large,
instead diff first and then turn it into nanosecs.
---
 src/bin/pg_test_timing/pg_test_timing.c | 59 +++++++++++++++++++------
 src/include/portability/instr_time.h    | 30 ++++++++-----
 2 files changed, 65 insertions(+), 24 deletions(-)

diff --git a/src/bin/pg_test_timing/pg_test_timing.c b/src/bin/pg_test_timing/pg_test_timing.c
index a5621251afc..b77ef2063b6 100644
--- a/src/bin/pg_test_timing/pg_test_timing.c
+++ b/src/bin/pg_test_timing/pg_test_timing.c
@@ -16,6 +16,7 @@ static const char *progname;
 
 static unsigned int test_duration = 3;
 static double max_rprct = 99.99;
+static bool fast_timing = false;
 
 /* record duration in powers of 2 nanoseconds */
 static long long int histogram[32];
@@ -56,6 +57,7 @@ handle_args(int argc, char *argv[])
 	static struct option long_options[] = {
 		{"duration", required_argument, NULL, 'd'},
 		{"cutoff", required_argument, NULL, 'c'},
+		{"fast", no_argument, NULL, 'f'},
 		{NULL, 0, NULL, 0}
 	};
 
@@ -68,7 +70,7 @@ handle_args(int argc, char *argv[])
 	{
 		if (strcmp(argv[1], "--help") == 0 || strcmp(argv[1], "-?") == 0)
 		{
-			printf(_("Usage: %s [-d DURATION] [-c CUTOFF]\n"), progname);
+			printf(_("Usage: %s [-d DURATION] [-c CUTOFF] [--fast]\n"), progname);
 			exit(0);
 		}
 		if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0)
@@ -78,7 +80,7 @@ handle_args(int argc, char *argv[])
 		}
 	}
 
-	while ((option = getopt_long(argc, argv, "d:c:",
+	while ((option = getopt_long(argc, argv, "d:c:f:",
 								 long_options, &optindex)) != -1)
 	{
 		switch (option)
@@ -125,6 +127,10 @@ handle_args(int argc, char *argv[])
 				}
 				break;
 
+			case 'f':
+				fast_timing = true;
+				break;
+
 			default:
 				fprintf(stderr, _("Try \"%s --help\" for more information.\n"),
 						progname);
@@ -155,11 +161,31 @@ test_timing(unsigned int duration)
 	uint64		total_time;
 	int64		time_elapsed = 0;
 	uint64		loop_count = 0;
-	uint64		prev,
-				cur;
 	instr_time	start_time,
 				end_time,
-				temp;
+				prev,
+				cur;
+	char	   *time_source = NULL;
+	bool		fast_timing_used = false;
+
+	INSTR_TIME_INITIALIZE();
+
+#if !defined(WIN32) && defined(__x86_64__) && defined(__linux__)
+	if (fast_timing && has_rdtsc)
+	{
+		time_source = "RDTSC";
+		fast_timing_used = true;
+	}
+	else if (has_rdtscp)
+		time_source = "RDTSCP";
+	else
+		time_source = PG_INSTR_CLOCK_NAME;
+#else
+	time_source = PG_INSTR_CLOCK_NAME;
+#endif
+	if (fast_timing && !fast_timing_used)
+		printf(_("Warning: Fast timing requested, but not available - regular timing source will be used\n"));
+	printf(_("Time source: %s\n"), time_source);
 
 	/*
 	 * Pre-zero the statistics data structures.  They're already zero by
@@ -173,8 +199,11 @@ test_timing(unsigned int duration)
 
 	total_time = duration > 0 ? duration * INT64CONST(1000000000) : 0;
 
-	INSTR_TIME_SET_CURRENT(start_time);
-	cur = INSTR_TIME_GET_NANOSEC(start_time);
+	if (fast_timing)
+		INSTR_TIME_SET_CURRENT_FAST(start_time);
+	else
+		INSTR_TIME_SET_CURRENT(start_time);
+	cur = start_time;
 
 	while (time_elapsed < total_time)
 	{
@@ -182,9 +211,11 @@ test_timing(unsigned int duration)
 					bits;
 
 		prev = cur;
-		INSTR_TIME_SET_CURRENT(temp);
-		cur = INSTR_TIME_GET_NANOSEC(temp);
-		diff = cur - prev;
+		if (fast_timing)
+			INSTR_TIME_SET_CURRENT_FAST(cur);
+		else
+			INSTR_TIME_SET_CURRENT(cur);
+		diff = INSTR_TIME_DIFF_NANOSEC(cur, prev);
 
 		/* Did time go backwards? */
 		if (unlikely(diff < 0))
@@ -217,11 +248,13 @@ test_timing(unsigned int duration)
 			largest_diff_count++;
 
 		loop_count++;
-		INSTR_TIME_SUBTRACT(temp, start_time);
-		time_elapsed = INSTR_TIME_GET_NANOSEC(temp);
+		time_elapsed = INSTR_TIME_DIFF_NANOSEC(cur, start_time);
 	}
 
-	INSTR_TIME_SET_CURRENT(end_time);
+	if (fast_timing)
+		INSTR_TIME_SET_CURRENT_FAST(end_time);
+	else
+		INSTR_TIME_SET_CURRENT(end_time);
 
 	INSTR_TIME_SUBTRACT(end_time, start_time);
 
diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h
index e2e339a0c4f..f02296f1026 100644
--- a/src/include/portability/instr_time.h
+++ b/src/include/portability/instr_time.h
@@ -112,10 +112,13 @@ extern int64 max_ticks_no_overflow;
  */
 #if defined(__darwin__) && defined(CLOCK_MONOTONIC_RAW)
 #define PG_INSTR_CLOCK	CLOCK_MONOTONIC_RAW
+#define PG_INSTR_CLOCK_NAME	"clock_gettime (CLOCK_MONOTONIC_RAW)"
 #elif defined(CLOCK_MONOTONIC)
 #define PG_INSTR_CLOCK	CLOCK_MONOTONIC
+#define PG_INSTR_CLOCK_NAME	"clock_gettime (CLOCK_MONOTONIC)"
 #else
 #define PG_INSTR_CLOCK	CLOCK_REALTIME
+#define PG_INSTR_CLOCK_NAME	"clock_gettime (CLOCK_REALTIME)"
 #endif
 
 #if defined(__x86_64__) && defined(__linux__)
@@ -174,7 +177,7 @@ pg_get_ticks(void)
 }
 
 static inline int64_t
-pg_ticks_to_ns(instr_time t)
+pg_ticks_to_ns(int64 ticks)
 {
 	/*
 	 * Would multiplication overflow? If so perform computation in two parts.
@@ -183,7 +186,7 @@ pg_ticks_to_ns(instr_time t)
 	 */
 	int64		ns = 0;
 
-	if (unlikely(t.ticks > max_ticks_no_overflow))
+	if (unlikely(ticks > max_ticks_no_overflow))
 	{
 		/*
 		 * Compute how often the maximum number of ticks fits completely into
@@ -192,7 +195,7 @@ pg_ticks_to_ns(instr_time t)
 		 * value. In a 2nd step we adjust the number of elapsed ticks and
 		 * convert the remaining ticks.
 		 */
-		int64		count = t.ticks / max_ticks_no_overflow;
+		int64		count = ticks / max_ticks_no_overflow;
 		int64		max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION;
 
 		ns = max_ns * count;
@@ -201,11 +204,11 @@ pg_ticks_to_ns(instr_time t)
 		 * Subtract the ticks that we now already accounted for, so that they
 		 * don't get counted twice.
 		 */
-		t.ticks -= count * max_ticks_no_overflow;
-		Assert(t.ticks >= 0);
+		ticks -= count * max_ticks_no_overflow;
+		Assert(ticks >= 0);
 	}
 
-	ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION;
+	ns += ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION;
 	return ns;
 }
 
@@ -226,14 +229,14 @@ pg_initialize_get_ticks()
 #define INSTR_TIME_SET_CURRENT(t) \
 	((t) = pg_get_ticks())
 
-#define INSTR_TIME_GET_NANOSEC(t) \
-	pg_ticks_to_ns(t)
-
+#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \
+	(pg_ticks_to_ns(ticks))
 
 #else							/* WIN32 */
 
 
 /* Use QueryPerformanceCounter() */
+#define PG_INSTR_CLOCK_NAME	"QueryPerformanceCounter"
 
 /* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */
 static inline instr_time
@@ -265,8 +268,8 @@ GetTimerFrequency(void)
 #define INSTR_TIME_SET_CURRENT(t) \
 	((t) = pg_query_performance_counter())
 
-#define INSTR_TIME_GET_NANOSEC(t) \
-	((int64) ((t).ticks * ((double) NS_PER_S / GetTimerFrequency())))
+#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \
+	((int64) ((ticks) * ((double) NS_PER_S / GetTimerFrequency())))
 
 #endif							/* WIN32 */
 
@@ -285,9 +288,14 @@ GetTimerFrequency(void)
 #define INSTR_TIME_SUBTRACT(x,y) \
 	((x).ticks -= (y).ticks)
 
+#define INSTR_TIME_DIFF_NANOSEC(x,y) \
+	(INSTR_TIME_TICKS_TO_NANOSEC((x).ticks - (y).ticks))
+
 #define INSTR_TIME_ACCUM_DIFF(x,y,z) \
 	((x).ticks += (y).ticks - (z).ticks)
 
+#define INSTR_TIME_GET_NANOSEC(t) \
+	(INSTR_TIME_TICKS_TO_NANOSEC((t).ticks))
 
 #define INSTR_TIME_GET_DOUBLE(t) \
 	((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S)
-- 
2.47.3


--vtqqtrpooseurzip--





^ permalink  raw  reply  [nested|flat] 265+ messages in thread

* [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source
@ 2025-07-27 15:48  Lukas Fittl <[email protected]>
  0 siblings, 0 replies; 265+ messages in thread

From: Lukas Fittl @ 2025-07-27 15:48 UTC (permalink / raw)

In passing also reduce the per-loop overhead caused by repeated divisions
in INSTR_TIME_GET_NANOSEC when the ticks variable has become very large,
instead diff first and then turn it into nanosecs.
---
 src/bin/pg_test_timing/pg_test_timing.c | 59 +++++++++++++++++++------
 src/include/portability/instr_time.h    | 30 ++++++++-----
 2 files changed, 65 insertions(+), 24 deletions(-)

diff --git a/src/bin/pg_test_timing/pg_test_timing.c b/src/bin/pg_test_timing/pg_test_timing.c
index a5621251afc..b77ef2063b6 100644
--- a/src/bin/pg_test_timing/pg_test_timing.c
+++ b/src/bin/pg_test_timing/pg_test_timing.c
@@ -16,6 +16,7 @@ static const char *progname;
 
 static unsigned int test_duration = 3;
 static double max_rprct = 99.99;
+static bool fast_timing = false;
 
 /* record duration in powers of 2 nanoseconds */
 static long long int histogram[32];
@@ -56,6 +57,7 @@ handle_args(int argc, char *argv[])
 	static struct option long_options[] = {
 		{"duration", required_argument, NULL, 'd'},
 		{"cutoff", required_argument, NULL, 'c'},
+		{"fast", no_argument, NULL, 'f'},
 		{NULL, 0, NULL, 0}
 	};
 
@@ -68,7 +70,7 @@ handle_args(int argc, char *argv[])
 	{
 		if (strcmp(argv[1], "--help") == 0 || strcmp(argv[1], "-?") == 0)
 		{
-			printf(_("Usage: %s [-d DURATION] [-c CUTOFF]\n"), progname);
+			printf(_("Usage: %s [-d DURATION] [-c CUTOFF] [--fast]\n"), progname);
 			exit(0);
 		}
 		if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0)
@@ -78,7 +80,7 @@ handle_args(int argc, char *argv[])
 		}
 	}
 
-	while ((option = getopt_long(argc, argv, "d:c:",
+	while ((option = getopt_long(argc, argv, "d:c:f:",
 								 long_options, &optindex)) != -1)
 	{
 		switch (option)
@@ -125,6 +127,10 @@ handle_args(int argc, char *argv[])
 				}
 				break;
 
+			case 'f':
+				fast_timing = true;
+				break;
+
 			default:
 				fprintf(stderr, _("Try \"%s --help\" for more information.\n"),
 						progname);
@@ -155,11 +161,31 @@ test_timing(unsigned int duration)
 	uint64		total_time;
 	int64		time_elapsed = 0;
 	uint64		loop_count = 0;
-	uint64		prev,
-				cur;
 	instr_time	start_time,
 				end_time,
-				temp;
+				prev,
+				cur;
+	char	   *time_source = NULL;
+	bool		fast_timing_used = false;
+
+	INSTR_TIME_INITIALIZE();
+
+#if !defined(WIN32) && defined(__x86_64__) && defined(__linux__)
+	if (fast_timing && has_rdtsc)
+	{
+		time_source = "RDTSC";
+		fast_timing_used = true;
+	}
+	else if (has_rdtscp)
+		time_source = "RDTSCP";
+	else
+		time_source = PG_INSTR_CLOCK_NAME;
+#else
+	time_source = PG_INSTR_CLOCK_NAME;
+#endif
+	if (fast_timing && !fast_timing_used)
+		printf(_("Warning: Fast timing requested, but not available - regular timing source will be used\n"));
+	printf(_("Time source: %s\n"), time_source);
 
 	/*
 	 * Pre-zero the statistics data structures.  They're already zero by
@@ -173,8 +199,11 @@ test_timing(unsigned int duration)
 
 	total_time = duration > 0 ? duration * INT64CONST(1000000000) : 0;
 
-	INSTR_TIME_SET_CURRENT(start_time);
-	cur = INSTR_TIME_GET_NANOSEC(start_time);
+	if (fast_timing)
+		INSTR_TIME_SET_CURRENT_FAST(start_time);
+	else
+		INSTR_TIME_SET_CURRENT(start_time);
+	cur = start_time;
 
 	while (time_elapsed < total_time)
 	{
@@ -182,9 +211,11 @@ test_timing(unsigned int duration)
 					bits;
 
 		prev = cur;
-		INSTR_TIME_SET_CURRENT(temp);
-		cur = INSTR_TIME_GET_NANOSEC(temp);
-		diff = cur - prev;
+		if (fast_timing)
+			INSTR_TIME_SET_CURRENT_FAST(cur);
+		else
+			INSTR_TIME_SET_CURRENT(cur);
+		diff = INSTR_TIME_DIFF_NANOSEC(cur, prev);
 
 		/* Did time go backwards? */
 		if (unlikely(diff < 0))
@@ -217,11 +248,13 @@ test_timing(unsigned int duration)
 			largest_diff_count++;
 
 		loop_count++;
-		INSTR_TIME_SUBTRACT(temp, start_time);
-		time_elapsed = INSTR_TIME_GET_NANOSEC(temp);
+		time_elapsed = INSTR_TIME_DIFF_NANOSEC(cur, start_time);
 	}
 
-	INSTR_TIME_SET_CURRENT(end_time);
+	if (fast_timing)
+		INSTR_TIME_SET_CURRENT_FAST(end_time);
+	else
+		INSTR_TIME_SET_CURRENT(end_time);
 
 	INSTR_TIME_SUBTRACT(end_time, start_time);
 
diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h
index e2e339a0c4f..f02296f1026 100644
--- a/src/include/portability/instr_time.h
+++ b/src/include/portability/instr_time.h
@@ -112,10 +112,13 @@ extern int64 max_ticks_no_overflow;
  */
 #if defined(__darwin__) && defined(CLOCK_MONOTONIC_RAW)
 #define PG_INSTR_CLOCK	CLOCK_MONOTONIC_RAW
+#define PG_INSTR_CLOCK_NAME	"clock_gettime (CLOCK_MONOTONIC_RAW)"
 #elif defined(CLOCK_MONOTONIC)
 #define PG_INSTR_CLOCK	CLOCK_MONOTONIC
+#define PG_INSTR_CLOCK_NAME	"clock_gettime (CLOCK_MONOTONIC)"
 #else
 #define PG_INSTR_CLOCK	CLOCK_REALTIME
+#define PG_INSTR_CLOCK_NAME	"clock_gettime (CLOCK_REALTIME)"
 #endif
 
 #if defined(__x86_64__) && defined(__linux__)
@@ -174,7 +177,7 @@ pg_get_ticks(void)
 }
 
 static inline int64_t
-pg_ticks_to_ns(instr_time t)
+pg_ticks_to_ns(int64 ticks)
 {
 	/*
 	 * Would multiplication overflow? If so perform computation in two parts.
@@ -183,7 +186,7 @@ pg_ticks_to_ns(instr_time t)
 	 */
 	int64		ns = 0;
 
-	if (unlikely(t.ticks > max_ticks_no_overflow))
+	if (unlikely(ticks > max_ticks_no_overflow))
 	{
 		/*
 		 * Compute how often the maximum number of ticks fits completely into
@@ -192,7 +195,7 @@ pg_ticks_to_ns(instr_time t)
 		 * value. In a 2nd step we adjust the number of elapsed ticks and
 		 * convert the remaining ticks.
 		 */
-		int64		count = t.ticks / max_ticks_no_overflow;
+		int64		count = ticks / max_ticks_no_overflow;
 		int64		max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION;
 
 		ns = max_ns * count;
@@ -201,11 +204,11 @@ pg_ticks_to_ns(instr_time t)
 		 * Subtract the ticks that we now already accounted for, so that they
 		 * don't get counted twice.
 		 */
-		t.ticks -= count * max_ticks_no_overflow;
-		Assert(t.ticks >= 0);
+		ticks -= count * max_ticks_no_overflow;
+		Assert(ticks >= 0);
 	}
 
-	ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION;
+	ns += ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION;
 	return ns;
 }
 
@@ -226,14 +229,14 @@ pg_initialize_get_ticks()
 #define INSTR_TIME_SET_CURRENT(t) \
 	((t) = pg_get_ticks())
 
-#define INSTR_TIME_GET_NANOSEC(t) \
-	pg_ticks_to_ns(t)
-
+#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \
+	(pg_ticks_to_ns(ticks))
 
 #else							/* WIN32 */
 
 
 /* Use QueryPerformanceCounter() */
+#define PG_INSTR_CLOCK_NAME	"QueryPerformanceCounter"
 
 /* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */
 static inline instr_time
@@ -265,8 +268,8 @@ GetTimerFrequency(void)
 #define INSTR_TIME_SET_CURRENT(t) \
 	((t) = pg_query_performance_counter())
 
-#define INSTR_TIME_GET_NANOSEC(t) \
-	((int64) ((t).ticks * ((double) NS_PER_S / GetTimerFrequency())))
+#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \
+	((int64) ((ticks) * ((double) NS_PER_S / GetTimerFrequency())))
 
 #endif							/* WIN32 */
 
@@ -285,9 +288,14 @@ GetTimerFrequency(void)
 #define INSTR_TIME_SUBTRACT(x,y) \
 	((x).ticks -= (y).ticks)
 
+#define INSTR_TIME_DIFF_NANOSEC(x,y) \
+	(INSTR_TIME_TICKS_TO_NANOSEC((x).ticks - (y).ticks))
+
 #define INSTR_TIME_ACCUM_DIFF(x,y,z) \
 	((x).ticks += (y).ticks - (z).ticks)
 
+#define INSTR_TIME_GET_NANOSEC(t) \
+	(INSTR_TIME_TICKS_TO_NANOSEC((t).ticks))
 
 #define INSTR_TIME_GET_DOUBLE(t) \
 	((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S)
-- 
2.47.3


--vtqqtrpooseurzip--





^ permalink  raw  reply  [nested|flat] 265+ messages in thread

* [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source
@ 2025-07-27 15:48  Lukas Fittl <[email protected]>
  0 siblings, 0 replies; 265+ messages in thread

From: Lukas Fittl @ 2025-07-27 15:48 UTC (permalink / raw)

In passing also reduce the per-loop overhead caused by repeated divisions
in INSTR_TIME_GET_NANOSEC when the ticks variable has become very large,
instead diff first and then turn it into nanosecs.
---
 src/bin/pg_test_timing/pg_test_timing.c | 59 +++++++++++++++++++------
 src/include/portability/instr_time.h    | 30 ++++++++-----
 2 files changed, 65 insertions(+), 24 deletions(-)

diff --git a/src/bin/pg_test_timing/pg_test_timing.c b/src/bin/pg_test_timing/pg_test_timing.c
index a5621251afc..b77ef2063b6 100644
--- a/src/bin/pg_test_timing/pg_test_timing.c
+++ b/src/bin/pg_test_timing/pg_test_timing.c
@@ -16,6 +16,7 @@ static const char *progname;
 
 static unsigned int test_duration = 3;
 static double max_rprct = 99.99;
+static bool fast_timing = false;
 
 /* record duration in powers of 2 nanoseconds */
 static long long int histogram[32];
@@ -56,6 +57,7 @@ handle_args(int argc, char *argv[])
 	static struct option long_options[] = {
 		{"duration", required_argument, NULL, 'd'},
 		{"cutoff", required_argument, NULL, 'c'},
+		{"fast", no_argument, NULL, 'f'},
 		{NULL, 0, NULL, 0}
 	};
 
@@ -68,7 +70,7 @@ handle_args(int argc, char *argv[])
 	{
 		if (strcmp(argv[1], "--help") == 0 || strcmp(argv[1], "-?") == 0)
 		{
-			printf(_("Usage: %s [-d DURATION] [-c CUTOFF]\n"), progname);
+			printf(_("Usage: %s [-d DURATION] [-c CUTOFF] [--fast]\n"), progname);
 			exit(0);
 		}
 		if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0)
@@ -78,7 +80,7 @@ handle_args(int argc, char *argv[])
 		}
 	}
 
-	while ((option = getopt_long(argc, argv, "d:c:",
+	while ((option = getopt_long(argc, argv, "d:c:f:",
 								 long_options, &optindex)) != -1)
 	{
 		switch (option)
@@ -125,6 +127,10 @@ handle_args(int argc, char *argv[])
 				}
 				break;
 
+			case 'f':
+				fast_timing = true;
+				break;
+
 			default:
 				fprintf(stderr, _("Try \"%s --help\" for more information.\n"),
 						progname);
@@ -155,11 +161,31 @@ test_timing(unsigned int duration)
 	uint64		total_time;
 	int64		time_elapsed = 0;
 	uint64		loop_count = 0;
-	uint64		prev,
-				cur;
 	instr_time	start_time,
 				end_time,
-				temp;
+				prev,
+				cur;
+	char	   *time_source = NULL;
+	bool		fast_timing_used = false;
+
+	INSTR_TIME_INITIALIZE();
+
+#if !defined(WIN32) && defined(__x86_64__) && defined(__linux__)
+	if (fast_timing && has_rdtsc)
+	{
+		time_source = "RDTSC";
+		fast_timing_used = true;
+	}
+	else if (has_rdtscp)
+		time_source = "RDTSCP";
+	else
+		time_source = PG_INSTR_CLOCK_NAME;
+#else
+	time_source = PG_INSTR_CLOCK_NAME;
+#endif
+	if (fast_timing && !fast_timing_used)
+		printf(_("Warning: Fast timing requested, but not available - regular timing source will be used\n"));
+	printf(_("Time source: %s\n"), time_source);
 
 	/*
 	 * Pre-zero the statistics data structures.  They're already zero by
@@ -173,8 +199,11 @@ test_timing(unsigned int duration)
 
 	total_time = duration > 0 ? duration * INT64CONST(1000000000) : 0;
 
-	INSTR_TIME_SET_CURRENT(start_time);
-	cur = INSTR_TIME_GET_NANOSEC(start_time);
+	if (fast_timing)
+		INSTR_TIME_SET_CURRENT_FAST(start_time);
+	else
+		INSTR_TIME_SET_CURRENT(start_time);
+	cur = start_time;
 
 	while (time_elapsed < total_time)
 	{
@@ -182,9 +211,11 @@ test_timing(unsigned int duration)
 					bits;
 
 		prev = cur;
-		INSTR_TIME_SET_CURRENT(temp);
-		cur = INSTR_TIME_GET_NANOSEC(temp);
-		diff = cur - prev;
+		if (fast_timing)
+			INSTR_TIME_SET_CURRENT_FAST(cur);
+		else
+			INSTR_TIME_SET_CURRENT(cur);
+		diff = INSTR_TIME_DIFF_NANOSEC(cur, prev);
 
 		/* Did time go backwards? */
 		if (unlikely(diff < 0))
@@ -217,11 +248,13 @@ test_timing(unsigned int duration)
 			largest_diff_count++;
 
 		loop_count++;
-		INSTR_TIME_SUBTRACT(temp, start_time);
-		time_elapsed = INSTR_TIME_GET_NANOSEC(temp);
+		time_elapsed = INSTR_TIME_DIFF_NANOSEC(cur, start_time);
 	}
 
-	INSTR_TIME_SET_CURRENT(end_time);
+	if (fast_timing)
+		INSTR_TIME_SET_CURRENT_FAST(end_time);
+	else
+		INSTR_TIME_SET_CURRENT(end_time);
 
 	INSTR_TIME_SUBTRACT(end_time, start_time);
 
diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h
index e2e339a0c4f..f02296f1026 100644
--- a/src/include/portability/instr_time.h
+++ b/src/include/portability/instr_time.h
@@ -112,10 +112,13 @@ extern int64 max_ticks_no_overflow;
  */
 #if defined(__darwin__) && defined(CLOCK_MONOTONIC_RAW)
 #define PG_INSTR_CLOCK	CLOCK_MONOTONIC_RAW
+#define PG_INSTR_CLOCK_NAME	"clock_gettime (CLOCK_MONOTONIC_RAW)"
 #elif defined(CLOCK_MONOTONIC)
 #define PG_INSTR_CLOCK	CLOCK_MONOTONIC
+#define PG_INSTR_CLOCK_NAME	"clock_gettime (CLOCK_MONOTONIC)"
 #else
 #define PG_INSTR_CLOCK	CLOCK_REALTIME
+#define PG_INSTR_CLOCK_NAME	"clock_gettime (CLOCK_REALTIME)"
 #endif
 
 #if defined(__x86_64__) && defined(__linux__)
@@ -174,7 +177,7 @@ pg_get_ticks(void)
 }
 
 static inline int64_t
-pg_ticks_to_ns(instr_time t)
+pg_ticks_to_ns(int64 ticks)
 {
 	/*
 	 * Would multiplication overflow? If so perform computation in two parts.
@@ -183,7 +186,7 @@ pg_ticks_to_ns(instr_time t)
 	 */
 	int64		ns = 0;
 
-	if (unlikely(t.ticks > max_ticks_no_overflow))
+	if (unlikely(ticks > max_ticks_no_overflow))
 	{
 		/*
 		 * Compute how often the maximum number of ticks fits completely into
@@ -192,7 +195,7 @@ pg_ticks_to_ns(instr_time t)
 		 * value. In a 2nd step we adjust the number of elapsed ticks and
 		 * convert the remaining ticks.
 		 */
-		int64		count = t.ticks / max_ticks_no_overflow;
+		int64		count = ticks / max_ticks_no_overflow;
 		int64		max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION;
 
 		ns = max_ns * count;
@@ -201,11 +204,11 @@ pg_ticks_to_ns(instr_time t)
 		 * Subtract the ticks that we now already accounted for, so that they
 		 * don't get counted twice.
 		 */
-		t.ticks -= count * max_ticks_no_overflow;
-		Assert(t.ticks >= 0);
+		ticks -= count * max_ticks_no_overflow;
+		Assert(ticks >= 0);
 	}
 
-	ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION;
+	ns += ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION;
 	return ns;
 }
 
@@ -226,14 +229,14 @@ pg_initialize_get_ticks()
 #define INSTR_TIME_SET_CURRENT(t) \
 	((t) = pg_get_ticks())
 
-#define INSTR_TIME_GET_NANOSEC(t) \
-	pg_ticks_to_ns(t)
-
+#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \
+	(pg_ticks_to_ns(ticks))
 
 #else							/* WIN32 */
 
 
 /* Use QueryPerformanceCounter() */
+#define PG_INSTR_CLOCK_NAME	"QueryPerformanceCounter"
 
 /* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */
 static inline instr_time
@@ -265,8 +268,8 @@ GetTimerFrequency(void)
 #define INSTR_TIME_SET_CURRENT(t) \
 	((t) = pg_query_performance_counter())
 
-#define INSTR_TIME_GET_NANOSEC(t) \
-	((int64) ((t).ticks * ((double) NS_PER_S / GetTimerFrequency())))
+#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \
+	((int64) ((ticks) * ((double) NS_PER_S / GetTimerFrequency())))
 
 #endif							/* WIN32 */
 
@@ -285,9 +288,14 @@ GetTimerFrequency(void)
 #define INSTR_TIME_SUBTRACT(x,y) \
 	((x).ticks -= (y).ticks)
 
+#define INSTR_TIME_DIFF_NANOSEC(x,y) \
+	(INSTR_TIME_TICKS_TO_NANOSEC((x).ticks - (y).ticks))
+
 #define INSTR_TIME_ACCUM_DIFF(x,y,z) \
 	((x).ticks += (y).ticks - (z).ticks)
 
+#define INSTR_TIME_GET_NANOSEC(t) \
+	(INSTR_TIME_TICKS_TO_NANOSEC((t).ticks))
 
 #define INSTR_TIME_GET_DOUBLE(t) \
 	((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S)
-- 
2.47.3


--vtqqtrpooseurzip--





^ permalink  raw  reply  [nested|flat] 265+ messages in thread

* [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source
@ 2025-07-27 15:48  Lukas Fittl <[email protected]>
  0 siblings, 0 replies; 265+ messages in thread

From: Lukas Fittl @ 2025-07-27 15:48 UTC (permalink / raw)

In passing also reduce the per-loop overhead caused by repeated divisions
in INSTR_TIME_GET_NANOSEC when the ticks variable has become very large,
instead diff first and then turn it into nanosecs.
---
 src/bin/pg_test_timing/pg_test_timing.c | 59 +++++++++++++++++++------
 src/include/portability/instr_time.h    | 30 ++++++++-----
 2 files changed, 65 insertions(+), 24 deletions(-)

diff --git a/src/bin/pg_test_timing/pg_test_timing.c b/src/bin/pg_test_timing/pg_test_timing.c
index a5621251afc..b77ef2063b6 100644
--- a/src/bin/pg_test_timing/pg_test_timing.c
+++ b/src/bin/pg_test_timing/pg_test_timing.c
@@ -16,6 +16,7 @@ static const char *progname;
 
 static unsigned int test_duration = 3;
 static double max_rprct = 99.99;
+static bool fast_timing = false;
 
 /* record duration in powers of 2 nanoseconds */
 static long long int histogram[32];
@@ -56,6 +57,7 @@ handle_args(int argc, char *argv[])
 	static struct option long_options[] = {
 		{"duration", required_argument, NULL, 'd'},
 		{"cutoff", required_argument, NULL, 'c'},
+		{"fast", no_argument, NULL, 'f'},
 		{NULL, 0, NULL, 0}
 	};
 
@@ -68,7 +70,7 @@ handle_args(int argc, char *argv[])
 	{
 		if (strcmp(argv[1], "--help") == 0 || strcmp(argv[1], "-?") == 0)
 		{
-			printf(_("Usage: %s [-d DURATION] [-c CUTOFF]\n"), progname);
+			printf(_("Usage: %s [-d DURATION] [-c CUTOFF] [--fast]\n"), progname);
 			exit(0);
 		}
 		if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0)
@@ -78,7 +80,7 @@ handle_args(int argc, char *argv[])
 		}
 	}
 
-	while ((option = getopt_long(argc, argv, "d:c:",
+	while ((option = getopt_long(argc, argv, "d:c:f:",
 								 long_options, &optindex)) != -1)
 	{
 		switch (option)
@@ -125,6 +127,10 @@ handle_args(int argc, char *argv[])
 				}
 				break;
 
+			case 'f':
+				fast_timing = true;
+				break;
+
 			default:
 				fprintf(stderr, _("Try \"%s --help\" for more information.\n"),
 						progname);
@@ -155,11 +161,31 @@ test_timing(unsigned int duration)
 	uint64		total_time;
 	int64		time_elapsed = 0;
 	uint64		loop_count = 0;
-	uint64		prev,
-				cur;
 	instr_time	start_time,
 				end_time,
-				temp;
+				prev,
+				cur;
+	char	   *time_source = NULL;
+	bool		fast_timing_used = false;
+
+	INSTR_TIME_INITIALIZE();
+
+#if !defined(WIN32) && defined(__x86_64__) && defined(__linux__)
+	if (fast_timing && has_rdtsc)
+	{
+		time_source = "RDTSC";
+		fast_timing_used = true;
+	}
+	else if (has_rdtscp)
+		time_source = "RDTSCP";
+	else
+		time_source = PG_INSTR_CLOCK_NAME;
+#else
+	time_source = PG_INSTR_CLOCK_NAME;
+#endif
+	if (fast_timing && !fast_timing_used)
+		printf(_("Warning: Fast timing requested, but not available - regular timing source will be used\n"));
+	printf(_("Time source: %s\n"), time_source);
 
 	/*
 	 * Pre-zero the statistics data structures.  They're already zero by
@@ -173,8 +199,11 @@ test_timing(unsigned int duration)
 
 	total_time = duration > 0 ? duration * INT64CONST(1000000000) : 0;
 
-	INSTR_TIME_SET_CURRENT(start_time);
-	cur = INSTR_TIME_GET_NANOSEC(start_time);
+	if (fast_timing)
+		INSTR_TIME_SET_CURRENT_FAST(start_time);
+	else
+		INSTR_TIME_SET_CURRENT(start_time);
+	cur = start_time;
 
 	while (time_elapsed < total_time)
 	{
@@ -182,9 +211,11 @@ test_timing(unsigned int duration)
 					bits;
 
 		prev = cur;
-		INSTR_TIME_SET_CURRENT(temp);
-		cur = INSTR_TIME_GET_NANOSEC(temp);
-		diff = cur - prev;
+		if (fast_timing)
+			INSTR_TIME_SET_CURRENT_FAST(cur);
+		else
+			INSTR_TIME_SET_CURRENT(cur);
+		diff = INSTR_TIME_DIFF_NANOSEC(cur, prev);
 
 		/* Did time go backwards? */
 		if (unlikely(diff < 0))
@@ -217,11 +248,13 @@ test_timing(unsigned int duration)
 			largest_diff_count++;
 
 		loop_count++;
-		INSTR_TIME_SUBTRACT(temp, start_time);
-		time_elapsed = INSTR_TIME_GET_NANOSEC(temp);
+		time_elapsed = INSTR_TIME_DIFF_NANOSEC(cur, start_time);
 	}
 
-	INSTR_TIME_SET_CURRENT(end_time);
+	if (fast_timing)
+		INSTR_TIME_SET_CURRENT_FAST(end_time);
+	else
+		INSTR_TIME_SET_CURRENT(end_time);
 
 	INSTR_TIME_SUBTRACT(end_time, start_time);
 
diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h
index e2e339a0c4f..f02296f1026 100644
--- a/src/include/portability/instr_time.h
+++ b/src/include/portability/instr_time.h
@@ -112,10 +112,13 @@ extern int64 max_ticks_no_overflow;
  */
 #if defined(__darwin__) && defined(CLOCK_MONOTONIC_RAW)
 #define PG_INSTR_CLOCK	CLOCK_MONOTONIC_RAW
+#define PG_INSTR_CLOCK_NAME	"clock_gettime (CLOCK_MONOTONIC_RAW)"
 #elif defined(CLOCK_MONOTONIC)
 #define PG_INSTR_CLOCK	CLOCK_MONOTONIC
+#define PG_INSTR_CLOCK_NAME	"clock_gettime (CLOCK_MONOTONIC)"
 #else
 #define PG_INSTR_CLOCK	CLOCK_REALTIME
+#define PG_INSTR_CLOCK_NAME	"clock_gettime (CLOCK_REALTIME)"
 #endif
 
 #if defined(__x86_64__) && defined(__linux__)
@@ -174,7 +177,7 @@ pg_get_ticks(void)
 }
 
 static inline int64_t
-pg_ticks_to_ns(instr_time t)
+pg_ticks_to_ns(int64 ticks)
 {
 	/*
 	 * Would multiplication overflow? If so perform computation in two parts.
@@ -183,7 +186,7 @@ pg_ticks_to_ns(instr_time t)
 	 */
 	int64		ns = 0;
 
-	if (unlikely(t.ticks > max_ticks_no_overflow))
+	if (unlikely(ticks > max_ticks_no_overflow))
 	{
 		/*
 		 * Compute how often the maximum number of ticks fits completely into
@@ -192,7 +195,7 @@ pg_ticks_to_ns(instr_time t)
 		 * value. In a 2nd step we adjust the number of elapsed ticks and
 		 * convert the remaining ticks.
 		 */
-		int64		count = t.ticks / max_ticks_no_overflow;
+		int64		count = ticks / max_ticks_no_overflow;
 		int64		max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION;
 
 		ns = max_ns * count;
@@ -201,11 +204,11 @@ pg_ticks_to_ns(instr_time t)
 		 * Subtract the ticks that we now already accounted for, so that they
 		 * don't get counted twice.
 		 */
-		t.ticks -= count * max_ticks_no_overflow;
-		Assert(t.ticks >= 0);
+		ticks -= count * max_ticks_no_overflow;
+		Assert(ticks >= 0);
 	}
 
-	ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION;
+	ns += ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION;
 	return ns;
 }
 
@@ -226,14 +229,14 @@ pg_initialize_get_ticks()
 #define INSTR_TIME_SET_CURRENT(t) \
 	((t) = pg_get_ticks())
 
-#define INSTR_TIME_GET_NANOSEC(t) \
-	pg_ticks_to_ns(t)
-
+#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \
+	(pg_ticks_to_ns(ticks))
 
 #else							/* WIN32 */
 
 
 /* Use QueryPerformanceCounter() */
+#define PG_INSTR_CLOCK_NAME	"QueryPerformanceCounter"
 
 /* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */
 static inline instr_time
@@ -265,8 +268,8 @@ GetTimerFrequency(void)
 #define INSTR_TIME_SET_CURRENT(t) \
 	((t) = pg_query_performance_counter())
 
-#define INSTR_TIME_GET_NANOSEC(t) \
-	((int64) ((t).ticks * ((double) NS_PER_S / GetTimerFrequency())))
+#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \
+	((int64) ((ticks) * ((double) NS_PER_S / GetTimerFrequency())))
 
 #endif							/* WIN32 */
 
@@ -285,9 +288,14 @@ GetTimerFrequency(void)
 #define INSTR_TIME_SUBTRACT(x,y) \
 	((x).ticks -= (y).ticks)
 
+#define INSTR_TIME_DIFF_NANOSEC(x,y) \
+	(INSTR_TIME_TICKS_TO_NANOSEC((x).ticks - (y).ticks))
+
 #define INSTR_TIME_ACCUM_DIFF(x,y,z) \
 	((x).ticks += (y).ticks - (z).ticks)
 
+#define INSTR_TIME_GET_NANOSEC(t) \
+	(INSTR_TIME_TICKS_TO_NANOSEC((t).ticks))
 
 #define INSTR_TIME_GET_DOUBLE(t) \
 	((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S)
-- 
2.47.3


--vtqqtrpooseurzip--





^ permalink  raw  reply  [nested|flat] 265+ messages in thread

* [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source
@ 2025-07-27 15:48  Lukas Fittl <[email protected]>
  0 siblings, 0 replies; 265+ messages in thread

From: Lukas Fittl @ 2025-07-27 15:48 UTC (permalink / raw)

In passing also reduce the per-loop overhead caused by repeated divisions
in INSTR_TIME_GET_NANOSEC when the ticks variable has become very large,
instead diff first and then turn it into nanosecs.
---
 src/bin/pg_test_timing/pg_test_timing.c | 59 +++++++++++++++++++------
 src/include/portability/instr_time.h    | 30 ++++++++-----
 2 files changed, 65 insertions(+), 24 deletions(-)

diff --git a/src/bin/pg_test_timing/pg_test_timing.c b/src/bin/pg_test_timing/pg_test_timing.c
index a5621251afc..b77ef2063b6 100644
--- a/src/bin/pg_test_timing/pg_test_timing.c
+++ b/src/bin/pg_test_timing/pg_test_timing.c
@@ -16,6 +16,7 @@ static const char *progname;
 
 static unsigned int test_duration = 3;
 static double max_rprct = 99.99;
+static bool fast_timing = false;
 
 /* record duration in powers of 2 nanoseconds */
 static long long int histogram[32];
@@ -56,6 +57,7 @@ handle_args(int argc, char *argv[])
 	static struct option long_options[] = {
 		{"duration", required_argument, NULL, 'd'},
 		{"cutoff", required_argument, NULL, 'c'},
+		{"fast", no_argument, NULL, 'f'},
 		{NULL, 0, NULL, 0}
 	};
 
@@ -68,7 +70,7 @@ handle_args(int argc, char *argv[])
 	{
 		if (strcmp(argv[1], "--help") == 0 || strcmp(argv[1], "-?") == 0)
 		{
-			printf(_("Usage: %s [-d DURATION] [-c CUTOFF]\n"), progname);
+			printf(_("Usage: %s [-d DURATION] [-c CUTOFF] [--fast]\n"), progname);
 			exit(0);
 		}
 		if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0)
@@ -78,7 +80,7 @@ handle_args(int argc, char *argv[])
 		}
 	}
 
-	while ((option = getopt_long(argc, argv, "d:c:",
+	while ((option = getopt_long(argc, argv, "d:c:f:",
 								 long_options, &optindex)) != -1)
 	{
 		switch (option)
@@ -125,6 +127,10 @@ handle_args(int argc, char *argv[])
 				}
 				break;
 
+			case 'f':
+				fast_timing = true;
+				break;
+
 			default:
 				fprintf(stderr, _("Try \"%s --help\" for more information.\n"),
 						progname);
@@ -155,11 +161,31 @@ test_timing(unsigned int duration)
 	uint64		total_time;
 	int64		time_elapsed = 0;
 	uint64		loop_count = 0;
-	uint64		prev,
-				cur;
 	instr_time	start_time,
 				end_time,
-				temp;
+				prev,
+				cur;
+	char	   *time_source = NULL;
+	bool		fast_timing_used = false;
+
+	INSTR_TIME_INITIALIZE();
+
+#if !defined(WIN32) && defined(__x86_64__) && defined(__linux__)
+	if (fast_timing && has_rdtsc)
+	{
+		time_source = "RDTSC";
+		fast_timing_used = true;
+	}
+	else if (has_rdtscp)
+		time_source = "RDTSCP";
+	else
+		time_source = PG_INSTR_CLOCK_NAME;
+#else
+	time_source = PG_INSTR_CLOCK_NAME;
+#endif
+	if (fast_timing && !fast_timing_used)
+		printf(_("Warning: Fast timing requested, but not available - regular timing source will be used\n"));
+	printf(_("Time source: %s\n"), time_source);
 
 	/*
 	 * Pre-zero the statistics data structures.  They're already zero by
@@ -173,8 +199,11 @@ test_timing(unsigned int duration)
 
 	total_time = duration > 0 ? duration * INT64CONST(1000000000) : 0;
 
-	INSTR_TIME_SET_CURRENT(start_time);
-	cur = INSTR_TIME_GET_NANOSEC(start_time);
+	if (fast_timing)
+		INSTR_TIME_SET_CURRENT_FAST(start_time);
+	else
+		INSTR_TIME_SET_CURRENT(start_time);
+	cur = start_time;
 
 	while (time_elapsed < total_time)
 	{
@@ -182,9 +211,11 @@ test_timing(unsigned int duration)
 					bits;
 
 		prev = cur;
-		INSTR_TIME_SET_CURRENT(temp);
-		cur = INSTR_TIME_GET_NANOSEC(temp);
-		diff = cur - prev;
+		if (fast_timing)
+			INSTR_TIME_SET_CURRENT_FAST(cur);
+		else
+			INSTR_TIME_SET_CURRENT(cur);
+		diff = INSTR_TIME_DIFF_NANOSEC(cur, prev);
 
 		/* Did time go backwards? */
 		if (unlikely(diff < 0))
@@ -217,11 +248,13 @@ test_timing(unsigned int duration)
 			largest_diff_count++;
 
 		loop_count++;
-		INSTR_TIME_SUBTRACT(temp, start_time);
-		time_elapsed = INSTR_TIME_GET_NANOSEC(temp);
+		time_elapsed = INSTR_TIME_DIFF_NANOSEC(cur, start_time);
 	}
 
-	INSTR_TIME_SET_CURRENT(end_time);
+	if (fast_timing)
+		INSTR_TIME_SET_CURRENT_FAST(end_time);
+	else
+		INSTR_TIME_SET_CURRENT(end_time);
 
 	INSTR_TIME_SUBTRACT(end_time, start_time);
 
diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h
index e2e339a0c4f..f02296f1026 100644
--- a/src/include/portability/instr_time.h
+++ b/src/include/portability/instr_time.h
@@ -112,10 +112,13 @@ extern int64 max_ticks_no_overflow;
  */
 #if defined(__darwin__) && defined(CLOCK_MONOTONIC_RAW)
 #define PG_INSTR_CLOCK	CLOCK_MONOTONIC_RAW
+#define PG_INSTR_CLOCK_NAME	"clock_gettime (CLOCK_MONOTONIC_RAW)"
 #elif defined(CLOCK_MONOTONIC)
 #define PG_INSTR_CLOCK	CLOCK_MONOTONIC
+#define PG_INSTR_CLOCK_NAME	"clock_gettime (CLOCK_MONOTONIC)"
 #else
 #define PG_INSTR_CLOCK	CLOCK_REALTIME
+#define PG_INSTR_CLOCK_NAME	"clock_gettime (CLOCK_REALTIME)"
 #endif
 
 #if defined(__x86_64__) && defined(__linux__)
@@ -174,7 +177,7 @@ pg_get_ticks(void)
 }
 
 static inline int64_t
-pg_ticks_to_ns(instr_time t)
+pg_ticks_to_ns(int64 ticks)
 {
 	/*
 	 * Would multiplication overflow? If so perform computation in two parts.
@@ -183,7 +186,7 @@ pg_ticks_to_ns(instr_time t)
 	 */
 	int64		ns = 0;
 
-	if (unlikely(t.ticks > max_ticks_no_overflow))
+	if (unlikely(ticks > max_ticks_no_overflow))
 	{
 		/*
 		 * Compute how often the maximum number of ticks fits completely into
@@ -192,7 +195,7 @@ pg_ticks_to_ns(instr_time t)
 		 * value. In a 2nd step we adjust the number of elapsed ticks and
 		 * convert the remaining ticks.
 		 */
-		int64		count = t.ticks / max_ticks_no_overflow;
+		int64		count = ticks / max_ticks_no_overflow;
 		int64		max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION;
 
 		ns = max_ns * count;
@@ -201,11 +204,11 @@ pg_ticks_to_ns(instr_time t)
 		 * Subtract the ticks that we now already accounted for, so that they
 		 * don't get counted twice.
 		 */
-		t.ticks -= count * max_ticks_no_overflow;
-		Assert(t.ticks >= 0);
+		ticks -= count * max_ticks_no_overflow;
+		Assert(ticks >= 0);
 	}
 
-	ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION;
+	ns += ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION;
 	return ns;
 }
 
@@ -226,14 +229,14 @@ pg_initialize_get_ticks()
 #define INSTR_TIME_SET_CURRENT(t) \
 	((t) = pg_get_ticks())
 
-#define INSTR_TIME_GET_NANOSEC(t) \
-	pg_ticks_to_ns(t)
-
+#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \
+	(pg_ticks_to_ns(ticks))
 
 #else							/* WIN32 */
 
 
 /* Use QueryPerformanceCounter() */
+#define PG_INSTR_CLOCK_NAME	"QueryPerformanceCounter"
 
 /* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */
 static inline instr_time
@@ -265,8 +268,8 @@ GetTimerFrequency(void)
 #define INSTR_TIME_SET_CURRENT(t) \
 	((t) = pg_query_performance_counter())
 
-#define INSTR_TIME_GET_NANOSEC(t) \
-	((int64) ((t).ticks * ((double) NS_PER_S / GetTimerFrequency())))
+#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \
+	((int64) ((ticks) * ((double) NS_PER_S / GetTimerFrequency())))
 
 #endif							/* WIN32 */
 
@@ -285,9 +288,14 @@ GetTimerFrequency(void)
 #define INSTR_TIME_SUBTRACT(x,y) \
 	((x).ticks -= (y).ticks)
 
+#define INSTR_TIME_DIFF_NANOSEC(x,y) \
+	(INSTR_TIME_TICKS_TO_NANOSEC((x).ticks - (y).ticks))
+
 #define INSTR_TIME_ACCUM_DIFF(x,y,z) \
 	((x).ticks += (y).ticks - (z).ticks)
 
+#define INSTR_TIME_GET_NANOSEC(t) \
+	(INSTR_TIME_TICKS_TO_NANOSEC((t).ticks))
 
 #define INSTR_TIME_GET_DOUBLE(t) \
 	((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S)
-- 
2.47.3


--vtqqtrpooseurzip--





^ permalink  raw  reply  [nested|flat] 265+ messages in thread

* [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source
@ 2025-07-27 15:48  Lukas Fittl <[email protected]>
  0 siblings, 0 replies; 265+ messages in thread

From: Lukas Fittl @ 2025-07-27 15:48 UTC (permalink / raw)

In passing also reduce the per-loop overhead caused by repeated divisions
in INSTR_TIME_GET_NANOSEC when the ticks variable has become very large,
instead diff first and then turn it into nanosecs.
---
 src/bin/pg_test_timing/pg_test_timing.c | 59 +++++++++++++++++++------
 src/include/portability/instr_time.h    | 30 ++++++++-----
 2 files changed, 65 insertions(+), 24 deletions(-)

diff --git a/src/bin/pg_test_timing/pg_test_timing.c b/src/bin/pg_test_timing/pg_test_timing.c
index a5621251afc..b77ef2063b6 100644
--- a/src/bin/pg_test_timing/pg_test_timing.c
+++ b/src/bin/pg_test_timing/pg_test_timing.c
@@ -16,6 +16,7 @@ static const char *progname;
 
 static unsigned int test_duration = 3;
 static double max_rprct = 99.99;
+static bool fast_timing = false;
 
 /* record duration in powers of 2 nanoseconds */
 static long long int histogram[32];
@@ -56,6 +57,7 @@ handle_args(int argc, char *argv[])
 	static struct option long_options[] = {
 		{"duration", required_argument, NULL, 'd'},
 		{"cutoff", required_argument, NULL, 'c'},
+		{"fast", no_argument, NULL, 'f'},
 		{NULL, 0, NULL, 0}
 	};
 
@@ -68,7 +70,7 @@ handle_args(int argc, char *argv[])
 	{
 		if (strcmp(argv[1], "--help") == 0 || strcmp(argv[1], "-?") == 0)
 		{
-			printf(_("Usage: %s [-d DURATION] [-c CUTOFF]\n"), progname);
+			printf(_("Usage: %s [-d DURATION] [-c CUTOFF] [--fast]\n"), progname);
 			exit(0);
 		}
 		if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0)
@@ -78,7 +80,7 @@ handle_args(int argc, char *argv[])
 		}
 	}
 
-	while ((option = getopt_long(argc, argv, "d:c:",
+	while ((option = getopt_long(argc, argv, "d:c:f:",
 								 long_options, &optindex)) != -1)
 	{
 		switch (option)
@@ -125,6 +127,10 @@ handle_args(int argc, char *argv[])
 				}
 				break;
 
+			case 'f':
+				fast_timing = true;
+				break;
+
 			default:
 				fprintf(stderr, _("Try \"%s --help\" for more information.\n"),
 						progname);
@@ -155,11 +161,31 @@ test_timing(unsigned int duration)
 	uint64		total_time;
 	int64		time_elapsed = 0;
 	uint64		loop_count = 0;
-	uint64		prev,
-				cur;
 	instr_time	start_time,
 				end_time,
-				temp;
+				prev,
+				cur;
+	char	   *time_source = NULL;
+	bool		fast_timing_used = false;
+
+	INSTR_TIME_INITIALIZE();
+
+#if !defined(WIN32) && defined(__x86_64__) && defined(__linux__)
+	if (fast_timing && has_rdtsc)
+	{
+		time_source = "RDTSC";
+		fast_timing_used = true;
+	}
+	else if (has_rdtscp)
+		time_source = "RDTSCP";
+	else
+		time_source = PG_INSTR_CLOCK_NAME;
+#else
+	time_source = PG_INSTR_CLOCK_NAME;
+#endif
+	if (fast_timing && !fast_timing_used)
+		printf(_("Warning: Fast timing requested, but not available - regular timing source will be used\n"));
+	printf(_("Time source: %s\n"), time_source);
 
 	/*
 	 * Pre-zero the statistics data structures.  They're already zero by
@@ -173,8 +199,11 @@ test_timing(unsigned int duration)
 
 	total_time = duration > 0 ? duration * INT64CONST(1000000000) : 0;
 
-	INSTR_TIME_SET_CURRENT(start_time);
-	cur = INSTR_TIME_GET_NANOSEC(start_time);
+	if (fast_timing)
+		INSTR_TIME_SET_CURRENT_FAST(start_time);
+	else
+		INSTR_TIME_SET_CURRENT(start_time);
+	cur = start_time;
 
 	while (time_elapsed < total_time)
 	{
@@ -182,9 +211,11 @@ test_timing(unsigned int duration)
 					bits;
 
 		prev = cur;
-		INSTR_TIME_SET_CURRENT(temp);
-		cur = INSTR_TIME_GET_NANOSEC(temp);
-		diff = cur - prev;
+		if (fast_timing)
+			INSTR_TIME_SET_CURRENT_FAST(cur);
+		else
+			INSTR_TIME_SET_CURRENT(cur);
+		diff = INSTR_TIME_DIFF_NANOSEC(cur, prev);
 
 		/* Did time go backwards? */
 		if (unlikely(diff < 0))
@@ -217,11 +248,13 @@ test_timing(unsigned int duration)
 			largest_diff_count++;
 
 		loop_count++;
-		INSTR_TIME_SUBTRACT(temp, start_time);
-		time_elapsed = INSTR_TIME_GET_NANOSEC(temp);
+		time_elapsed = INSTR_TIME_DIFF_NANOSEC(cur, start_time);
 	}
 
-	INSTR_TIME_SET_CURRENT(end_time);
+	if (fast_timing)
+		INSTR_TIME_SET_CURRENT_FAST(end_time);
+	else
+		INSTR_TIME_SET_CURRENT(end_time);
 
 	INSTR_TIME_SUBTRACT(end_time, start_time);
 
diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h
index e2e339a0c4f..f02296f1026 100644
--- a/src/include/portability/instr_time.h
+++ b/src/include/portability/instr_time.h
@@ -112,10 +112,13 @@ extern int64 max_ticks_no_overflow;
  */
 #if defined(__darwin__) && defined(CLOCK_MONOTONIC_RAW)
 #define PG_INSTR_CLOCK	CLOCK_MONOTONIC_RAW
+#define PG_INSTR_CLOCK_NAME	"clock_gettime (CLOCK_MONOTONIC_RAW)"
 #elif defined(CLOCK_MONOTONIC)
 #define PG_INSTR_CLOCK	CLOCK_MONOTONIC
+#define PG_INSTR_CLOCK_NAME	"clock_gettime (CLOCK_MONOTONIC)"
 #else
 #define PG_INSTR_CLOCK	CLOCK_REALTIME
+#define PG_INSTR_CLOCK_NAME	"clock_gettime (CLOCK_REALTIME)"
 #endif
 
 #if defined(__x86_64__) && defined(__linux__)
@@ -174,7 +177,7 @@ pg_get_ticks(void)
 }
 
 static inline int64_t
-pg_ticks_to_ns(instr_time t)
+pg_ticks_to_ns(int64 ticks)
 {
 	/*
 	 * Would multiplication overflow? If so perform computation in two parts.
@@ -183,7 +186,7 @@ pg_ticks_to_ns(instr_time t)
 	 */
 	int64		ns = 0;
 
-	if (unlikely(t.ticks > max_ticks_no_overflow))
+	if (unlikely(ticks > max_ticks_no_overflow))
 	{
 		/*
 		 * Compute how often the maximum number of ticks fits completely into
@@ -192,7 +195,7 @@ pg_ticks_to_ns(instr_time t)
 		 * value. In a 2nd step we adjust the number of elapsed ticks and
 		 * convert the remaining ticks.
 		 */
-		int64		count = t.ticks / max_ticks_no_overflow;
+		int64		count = ticks / max_ticks_no_overflow;
 		int64		max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION;
 
 		ns = max_ns * count;
@@ -201,11 +204,11 @@ pg_ticks_to_ns(instr_time t)
 		 * Subtract the ticks that we now already accounted for, so that they
 		 * don't get counted twice.
 		 */
-		t.ticks -= count * max_ticks_no_overflow;
-		Assert(t.ticks >= 0);
+		ticks -= count * max_ticks_no_overflow;
+		Assert(ticks >= 0);
 	}
 
-	ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION;
+	ns += ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION;
 	return ns;
 }
 
@@ -226,14 +229,14 @@ pg_initialize_get_ticks()
 #define INSTR_TIME_SET_CURRENT(t) \
 	((t) = pg_get_ticks())
 
-#define INSTR_TIME_GET_NANOSEC(t) \
-	pg_ticks_to_ns(t)
-
+#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \
+	(pg_ticks_to_ns(ticks))
 
 #else							/* WIN32 */
 
 
 /* Use QueryPerformanceCounter() */
+#define PG_INSTR_CLOCK_NAME	"QueryPerformanceCounter"
 
 /* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */
 static inline instr_time
@@ -265,8 +268,8 @@ GetTimerFrequency(void)
 #define INSTR_TIME_SET_CURRENT(t) \
 	((t) = pg_query_performance_counter())
 
-#define INSTR_TIME_GET_NANOSEC(t) \
-	((int64) ((t).ticks * ((double) NS_PER_S / GetTimerFrequency())))
+#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \
+	((int64) ((ticks) * ((double) NS_PER_S / GetTimerFrequency())))
 
 #endif							/* WIN32 */
 
@@ -285,9 +288,14 @@ GetTimerFrequency(void)
 #define INSTR_TIME_SUBTRACT(x,y) \
 	((x).ticks -= (y).ticks)
 
+#define INSTR_TIME_DIFF_NANOSEC(x,y) \
+	(INSTR_TIME_TICKS_TO_NANOSEC((x).ticks - (y).ticks))
+
 #define INSTR_TIME_ACCUM_DIFF(x,y,z) \
 	((x).ticks += (y).ticks - (z).ticks)
 
+#define INSTR_TIME_GET_NANOSEC(t) \
+	(INSTR_TIME_TICKS_TO_NANOSEC((t).ticks))
 
 #define INSTR_TIME_GET_DOUBLE(t) \
 	((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S)
-- 
2.47.3


--vtqqtrpooseurzip--





^ permalink  raw  reply  [nested|flat] 265+ messages in thread

* [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source
@ 2025-07-27 15:48  Lukas Fittl <[email protected]>
  0 siblings, 0 replies; 265+ messages in thread

From: Lukas Fittl @ 2025-07-27 15:48 UTC (permalink / raw)

In passing also reduce the per-loop overhead caused by repeated divisions
in INSTR_TIME_GET_NANOSEC when the ticks variable has become very large,
instead diff first and then turn it into nanosecs.
---
 src/bin/pg_test_timing/pg_test_timing.c | 59 +++++++++++++++++++------
 src/include/portability/instr_time.h    | 30 ++++++++-----
 2 files changed, 65 insertions(+), 24 deletions(-)

diff --git a/src/bin/pg_test_timing/pg_test_timing.c b/src/bin/pg_test_timing/pg_test_timing.c
index a5621251afc..b77ef2063b6 100644
--- a/src/bin/pg_test_timing/pg_test_timing.c
+++ b/src/bin/pg_test_timing/pg_test_timing.c
@@ -16,6 +16,7 @@ static const char *progname;
 
 static unsigned int test_duration = 3;
 static double max_rprct = 99.99;
+static bool fast_timing = false;
 
 /* record duration in powers of 2 nanoseconds */
 static long long int histogram[32];
@@ -56,6 +57,7 @@ handle_args(int argc, char *argv[])
 	static struct option long_options[] = {
 		{"duration", required_argument, NULL, 'd'},
 		{"cutoff", required_argument, NULL, 'c'},
+		{"fast", no_argument, NULL, 'f'},
 		{NULL, 0, NULL, 0}
 	};
 
@@ -68,7 +70,7 @@ handle_args(int argc, char *argv[])
 	{
 		if (strcmp(argv[1], "--help") == 0 || strcmp(argv[1], "-?") == 0)
 		{
-			printf(_("Usage: %s [-d DURATION] [-c CUTOFF]\n"), progname);
+			printf(_("Usage: %s [-d DURATION] [-c CUTOFF] [--fast]\n"), progname);
 			exit(0);
 		}
 		if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0)
@@ -78,7 +80,7 @@ handle_args(int argc, char *argv[])
 		}
 	}
 
-	while ((option = getopt_long(argc, argv, "d:c:",
+	while ((option = getopt_long(argc, argv, "d:c:f:",
 								 long_options, &optindex)) != -1)
 	{
 		switch (option)
@@ -125,6 +127,10 @@ handle_args(int argc, char *argv[])
 				}
 				break;
 
+			case 'f':
+				fast_timing = true;
+				break;
+
 			default:
 				fprintf(stderr, _("Try \"%s --help\" for more information.\n"),
 						progname);
@@ -155,11 +161,31 @@ test_timing(unsigned int duration)
 	uint64		total_time;
 	int64		time_elapsed = 0;
 	uint64		loop_count = 0;
-	uint64		prev,
-				cur;
 	instr_time	start_time,
 				end_time,
-				temp;
+				prev,
+				cur;
+	char	   *time_source = NULL;
+	bool		fast_timing_used = false;
+
+	INSTR_TIME_INITIALIZE();
+
+#if !defined(WIN32) && defined(__x86_64__) && defined(__linux__)
+	if (fast_timing && has_rdtsc)
+	{
+		time_source = "RDTSC";
+		fast_timing_used = true;
+	}
+	else if (has_rdtscp)
+		time_source = "RDTSCP";
+	else
+		time_source = PG_INSTR_CLOCK_NAME;
+#else
+	time_source = PG_INSTR_CLOCK_NAME;
+#endif
+	if (fast_timing && !fast_timing_used)
+		printf(_("Warning: Fast timing requested, but not available - regular timing source will be used\n"));
+	printf(_("Time source: %s\n"), time_source);
 
 	/*
 	 * Pre-zero the statistics data structures.  They're already zero by
@@ -173,8 +199,11 @@ test_timing(unsigned int duration)
 
 	total_time = duration > 0 ? duration * INT64CONST(1000000000) : 0;
 
-	INSTR_TIME_SET_CURRENT(start_time);
-	cur = INSTR_TIME_GET_NANOSEC(start_time);
+	if (fast_timing)
+		INSTR_TIME_SET_CURRENT_FAST(start_time);
+	else
+		INSTR_TIME_SET_CURRENT(start_time);
+	cur = start_time;
 
 	while (time_elapsed < total_time)
 	{
@@ -182,9 +211,11 @@ test_timing(unsigned int duration)
 					bits;
 
 		prev = cur;
-		INSTR_TIME_SET_CURRENT(temp);
-		cur = INSTR_TIME_GET_NANOSEC(temp);
-		diff = cur - prev;
+		if (fast_timing)
+			INSTR_TIME_SET_CURRENT_FAST(cur);
+		else
+			INSTR_TIME_SET_CURRENT(cur);
+		diff = INSTR_TIME_DIFF_NANOSEC(cur, prev);
 
 		/* Did time go backwards? */
 		if (unlikely(diff < 0))
@@ -217,11 +248,13 @@ test_timing(unsigned int duration)
 			largest_diff_count++;
 
 		loop_count++;
-		INSTR_TIME_SUBTRACT(temp, start_time);
-		time_elapsed = INSTR_TIME_GET_NANOSEC(temp);
+		time_elapsed = INSTR_TIME_DIFF_NANOSEC(cur, start_time);
 	}
 
-	INSTR_TIME_SET_CURRENT(end_time);
+	if (fast_timing)
+		INSTR_TIME_SET_CURRENT_FAST(end_time);
+	else
+		INSTR_TIME_SET_CURRENT(end_time);
 
 	INSTR_TIME_SUBTRACT(end_time, start_time);
 
diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h
index e2e339a0c4f..f02296f1026 100644
--- a/src/include/portability/instr_time.h
+++ b/src/include/portability/instr_time.h
@@ -112,10 +112,13 @@ extern int64 max_ticks_no_overflow;
  */
 #if defined(__darwin__) && defined(CLOCK_MONOTONIC_RAW)
 #define PG_INSTR_CLOCK	CLOCK_MONOTONIC_RAW
+#define PG_INSTR_CLOCK_NAME	"clock_gettime (CLOCK_MONOTONIC_RAW)"
 #elif defined(CLOCK_MONOTONIC)
 #define PG_INSTR_CLOCK	CLOCK_MONOTONIC
+#define PG_INSTR_CLOCK_NAME	"clock_gettime (CLOCK_MONOTONIC)"
 #else
 #define PG_INSTR_CLOCK	CLOCK_REALTIME
+#define PG_INSTR_CLOCK_NAME	"clock_gettime (CLOCK_REALTIME)"
 #endif
 
 #if defined(__x86_64__) && defined(__linux__)
@@ -174,7 +177,7 @@ pg_get_ticks(void)
 }
 
 static inline int64_t
-pg_ticks_to_ns(instr_time t)
+pg_ticks_to_ns(int64 ticks)
 {
 	/*
 	 * Would multiplication overflow? If so perform computation in two parts.
@@ -183,7 +186,7 @@ pg_ticks_to_ns(instr_time t)
 	 */
 	int64		ns = 0;
 
-	if (unlikely(t.ticks > max_ticks_no_overflow))
+	if (unlikely(ticks > max_ticks_no_overflow))
 	{
 		/*
 		 * Compute how often the maximum number of ticks fits completely into
@@ -192,7 +195,7 @@ pg_ticks_to_ns(instr_time t)
 		 * value. In a 2nd step we adjust the number of elapsed ticks and
 		 * convert the remaining ticks.
 		 */
-		int64		count = t.ticks / max_ticks_no_overflow;
+		int64		count = ticks / max_ticks_no_overflow;
 		int64		max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION;
 
 		ns = max_ns * count;
@@ -201,11 +204,11 @@ pg_ticks_to_ns(instr_time t)
 		 * Subtract the ticks that we now already accounted for, so that they
 		 * don't get counted twice.
 		 */
-		t.ticks -= count * max_ticks_no_overflow;
-		Assert(t.ticks >= 0);
+		ticks -= count * max_ticks_no_overflow;
+		Assert(ticks >= 0);
 	}
 
-	ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION;
+	ns += ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION;
 	return ns;
 }
 
@@ -226,14 +229,14 @@ pg_initialize_get_ticks()
 #define INSTR_TIME_SET_CURRENT(t) \
 	((t) = pg_get_ticks())
 
-#define INSTR_TIME_GET_NANOSEC(t) \
-	pg_ticks_to_ns(t)
-
+#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \
+	(pg_ticks_to_ns(ticks))
 
 #else							/* WIN32 */
 
 
 /* Use QueryPerformanceCounter() */
+#define PG_INSTR_CLOCK_NAME	"QueryPerformanceCounter"
 
 /* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */
 static inline instr_time
@@ -265,8 +268,8 @@ GetTimerFrequency(void)
 #define INSTR_TIME_SET_CURRENT(t) \
 	((t) = pg_query_performance_counter())
 
-#define INSTR_TIME_GET_NANOSEC(t) \
-	((int64) ((t).ticks * ((double) NS_PER_S / GetTimerFrequency())))
+#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \
+	((int64) ((ticks) * ((double) NS_PER_S / GetTimerFrequency())))
 
 #endif							/* WIN32 */
 
@@ -285,9 +288,14 @@ GetTimerFrequency(void)
 #define INSTR_TIME_SUBTRACT(x,y) \
 	((x).ticks -= (y).ticks)
 
+#define INSTR_TIME_DIFF_NANOSEC(x,y) \
+	(INSTR_TIME_TICKS_TO_NANOSEC((x).ticks - (y).ticks))
+
 #define INSTR_TIME_ACCUM_DIFF(x,y,z) \
 	((x).ticks += (y).ticks - (z).ticks)
 
+#define INSTR_TIME_GET_NANOSEC(t) \
+	(INSTR_TIME_TICKS_TO_NANOSEC((t).ticks))
 
 #define INSTR_TIME_GET_DOUBLE(t) \
 	((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S)
-- 
2.47.3


--vtqqtrpooseurzip--





^ permalink  raw  reply  [nested|flat] 265+ messages in thread

* [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source
@ 2025-07-27 15:48  Lukas Fittl <[email protected]>
  0 siblings, 0 replies; 265+ messages in thread

From: Lukas Fittl @ 2025-07-27 15:48 UTC (permalink / raw)

In passing also reduce the per-loop overhead caused by repeated divisions
in INSTR_TIME_GET_NANOSEC when the ticks variable has become very large,
instead diff first and then turn it into nanosecs.
---
 src/bin/pg_test_timing/pg_test_timing.c | 59 +++++++++++++++++++------
 src/include/portability/instr_time.h    | 30 ++++++++-----
 2 files changed, 65 insertions(+), 24 deletions(-)

diff --git a/src/bin/pg_test_timing/pg_test_timing.c b/src/bin/pg_test_timing/pg_test_timing.c
index a5621251afc..b77ef2063b6 100644
--- a/src/bin/pg_test_timing/pg_test_timing.c
+++ b/src/bin/pg_test_timing/pg_test_timing.c
@@ -16,6 +16,7 @@ static const char *progname;
 
 static unsigned int test_duration = 3;
 static double max_rprct = 99.99;
+static bool fast_timing = false;
 
 /* record duration in powers of 2 nanoseconds */
 static long long int histogram[32];
@@ -56,6 +57,7 @@ handle_args(int argc, char *argv[])
 	static struct option long_options[] = {
 		{"duration", required_argument, NULL, 'd'},
 		{"cutoff", required_argument, NULL, 'c'},
+		{"fast", no_argument, NULL, 'f'},
 		{NULL, 0, NULL, 0}
 	};
 
@@ -68,7 +70,7 @@ handle_args(int argc, char *argv[])
 	{
 		if (strcmp(argv[1], "--help") == 0 || strcmp(argv[1], "-?") == 0)
 		{
-			printf(_("Usage: %s [-d DURATION] [-c CUTOFF]\n"), progname);
+			printf(_("Usage: %s [-d DURATION] [-c CUTOFF] [--fast]\n"), progname);
 			exit(0);
 		}
 		if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0)
@@ -78,7 +80,7 @@ handle_args(int argc, char *argv[])
 		}
 	}
 
-	while ((option = getopt_long(argc, argv, "d:c:",
+	while ((option = getopt_long(argc, argv, "d:c:f:",
 								 long_options, &optindex)) != -1)
 	{
 		switch (option)
@@ -125,6 +127,10 @@ handle_args(int argc, char *argv[])
 				}
 				break;
 
+			case 'f':
+				fast_timing = true;
+				break;
+
 			default:
 				fprintf(stderr, _("Try \"%s --help\" for more information.\n"),
 						progname);
@@ -155,11 +161,31 @@ test_timing(unsigned int duration)
 	uint64		total_time;
 	int64		time_elapsed = 0;
 	uint64		loop_count = 0;
-	uint64		prev,
-				cur;
 	instr_time	start_time,
 				end_time,
-				temp;
+				prev,
+				cur;
+	char	   *time_source = NULL;
+	bool		fast_timing_used = false;
+
+	INSTR_TIME_INITIALIZE();
+
+#if !defined(WIN32) && defined(__x86_64__) && defined(__linux__)
+	if (fast_timing && has_rdtsc)
+	{
+		time_source = "RDTSC";
+		fast_timing_used = true;
+	}
+	else if (has_rdtscp)
+		time_source = "RDTSCP";
+	else
+		time_source = PG_INSTR_CLOCK_NAME;
+#else
+	time_source = PG_INSTR_CLOCK_NAME;
+#endif
+	if (fast_timing && !fast_timing_used)
+		printf(_("Warning: Fast timing requested, but not available - regular timing source will be used\n"));
+	printf(_("Time source: %s\n"), time_source);
 
 	/*
 	 * Pre-zero the statistics data structures.  They're already zero by
@@ -173,8 +199,11 @@ test_timing(unsigned int duration)
 
 	total_time = duration > 0 ? duration * INT64CONST(1000000000) : 0;
 
-	INSTR_TIME_SET_CURRENT(start_time);
-	cur = INSTR_TIME_GET_NANOSEC(start_time);
+	if (fast_timing)
+		INSTR_TIME_SET_CURRENT_FAST(start_time);
+	else
+		INSTR_TIME_SET_CURRENT(start_time);
+	cur = start_time;
 
 	while (time_elapsed < total_time)
 	{
@@ -182,9 +211,11 @@ test_timing(unsigned int duration)
 					bits;
 
 		prev = cur;
-		INSTR_TIME_SET_CURRENT(temp);
-		cur = INSTR_TIME_GET_NANOSEC(temp);
-		diff = cur - prev;
+		if (fast_timing)
+			INSTR_TIME_SET_CURRENT_FAST(cur);
+		else
+			INSTR_TIME_SET_CURRENT(cur);
+		diff = INSTR_TIME_DIFF_NANOSEC(cur, prev);
 
 		/* Did time go backwards? */
 		if (unlikely(diff < 0))
@@ -217,11 +248,13 @@ test_timing(unsigned int duration)
 			largest_diff_count++;
 
 		loop_count++;
-		INSTR_TIME_SUBTRACT(temp, start_time);
-		time_elapsed = INSTR_TIME_GET_NANOSEC(temp);
+		time_elapsed = INSTR_TIME_DIFF_NANOSEC(cur, start_time);
 	}
 
-	INSTR_TIME_SET_CURRENT(end_time);
+	if (fast_timing)
+		INSTR_TIME_SET_CURRENT_FAST(end_time);
+	else
+		INSTR_TIME_SET_CURRENT(end_time);
 
 	INSTR_TIME_SUBTRACT(end_time, start_time);
 
diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h
index e2e339a0c4f..f02296f1026 100644
--- a/src/include/portability/instr_time.h
+++ b/src/include/portability/instr_time.h
@@ -112,10 +112,13 @@ extern int64 max_ticks_no_overflow;
  */
 #if defined(__darwin__) && defined(CLOCK_MONOTONIC_RAW)
 #define PG_INSTR_CLOCK	CLOCK_MONOTONIC_RAW
+#define PG_INSTR_CLOCK_NAME	"clock_gettime (CLOCK_MONOTONIC_RAW)"
 #elif defined(CLOCK_MONOTONIC)
 #define PG_INSTR_CLOCK	CLOCK_MONOTONIC
+#define PG_INSTR_CLOCK_NAME	"clock_gettime (CLOCK_MONOTONIC)"
 #else
 #define PG_INSTR_CLOCK	CLOCK_REALTIME
+#define PG_INSTR_CLOCK_NAME	"clock_gettime (CLOCK_REALTIME)"
 #endif
 
 #if defined(__x86_64__) && defined(__linux__)
@@ -174,7 +177,7 @@ pg_get_ticks(void)
 }
 
 static inline int64_t
-pg_ticks_to_ns(instr_time t)
+pg_ticks_to_ns(int64 ticks)
 {
 	/*
 	 * Would multiplication overflow? If so perform computation in two parts.
@@ -183,7 +186,7 @@ pg_ticks_to_ns(instr_time t)
 	 */
 	int64		ns = 0;
 
-	if (unlikely(t.ticks > max_ticks_no_overflow))
+	if (unlikely(ticks > max_ticks_no_overflow))
 	{
 		/*
 		 * Compute how often the maximum number of ticks fits completely into
@@ -192,7 +195,7 @@ pg_ticks_to_ns(instr_time t)
 		 * value. In a 2nd step we adjust the number of elapsed ticks and
 		 * convert the remaining ticks.
 		 */
-		int64		count = t.ticks / max_ticks_no_overflow;
+		int64		count = ticks / max_ticks_no_overflow;
 		int64		max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION;
 
 		ns = max_ns * count;
@@ -201,11 +204,11 @@ pg_ticks_to_ns(instr_time t)
 		 * Subtract the ticks that we now already accounted for, so that they
 		 * don't get counted twice.
 		 */
-		t.ticks -= count * max_ticks_no_overflow;
-		Assert(t.ticks >= 0);
+		ticks -= count * max_ticks_no_overflow;
+		Assert(ticks >= 0);
 	}
 
-	ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION;
+	ns += ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION;
 	return ns;
 }
 
@@ -226,14 +229,14 @@ pg_initialize_get_ticks()
 #define INSTR_TIME_SET_CURRENT(t) \
 	((t) = pg_get_ticks())
 
-#define INSTR_TIME_GET_NANOSEC(t) \
-	pg_ticks_to_ns(t)
-
+#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \
+	(pg_ticks_to_ns(ticks))
 
 #else							/* WIN32 */
 
 
 /* Use QueryPerformanceCounter() */
+#define PG_INSTR_CLOCK_NAME	"QueryPerformanceCounter"
 
 /* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */
 static inline instr_time
@@ -265,8 +268,8 @@ GetTimerFrequency(void)
 #define INSTR_TIME_SET_CURRENT(t) \
 	((t) = pg_query_performance_counter())
 
-#define INSTR_TIME_GET_NANOSEC(t) \
-	((int64) ((t).ticks * ((double) NS_PER_S / GetTimerFrequency())))
+#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \
+	((int64) ((ticks) * ((double) NS_PER_S / GetTimerFrequency())))
 
 #endif							/* WIN32 */
 
@@ -285,9 +288,14 @@ GetTimerFrequency(void)
 #define INSTR_TIME_SUBTRACT(x,y) \
 	((x).ticks -= (y).ticks)
 
+#define INSTR_TIME_DIFF_NANOSEC(x,y) \
+	(INSTR_TIME_TICKS_TO_NANOSEC((x).ticks - (y).ticks))
+
 #define INSTR_TIME_ACCUM_DIFF(x,y,z) \
 	((x).ticks += (y).ticks - (z).ticks)
 
+#define INSTR_TIME_GET_NANOSEC(t) \
+	(INSTR_TIME_TICKS_TO_NANOSEC((t).ticks))
 
 #define INSTR_TIME_GET_DOUBLE(t) \
 	((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S)
-- 
2.47.3


--vtqqtrpooseurzip--





^ permalink  raw  reply  [nested|flat] 265+ messages in thread

* [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source
@ 2025-07-27 15:48  Lukas Fittl <[email protected]>
  0 siblings, 0 replies; 265+ messages in thread

From: Lukas Fittl @ 2025-07-27 15:48 UTC (permalink / raw)

In passing also reduce the per-loop overhead caused by repeated divisions
in INSTR_TIME_GET_NANOSEC when the ticks variable has become very large,
instead diff first and then turn it into nanosecs.
---
 src/bin/pg_test_timing/pg_test_timing.c | 59 +++++++++++++++++++------
 src/include/portability/instr_time.h    | 30 ++++++++-----
 2 files changed, 65 insertions(+), 24 deletions(-)

diff --git a/src/bin/pg_test_timing/pg_test_timing.c b/src/bin/pg_test_timing/pg_test_timing.c
index a5621251afc..b77ef2063b6 100644
--- a/src/bin/pg_test_timing/pg_test_timing.c
+++ b/src/bin/pg_test_timing/pg_test_timing.c
@@ -16,6 +16,7 @@ static const char *progname;
 
 static unsigned int test_duration = 3;
 static double max_rprct = 99.99;
+static bool fast_timing = false;
 
 /* record duration in powers of 2 nanoseconds */
 static long long int histogram[32];
@@ -56,6 +57,7 @@ handle_args(int argc, char *argv[])
 	static struct option long_options[] = {
 		{"duration", required_argument, NULL, 'd'},
 		{"cutoff", required_argument, NULL, 'c'},
+		{"fast", no_argument, NULL, 'f'},
 		{NULL, 0, NULL, 0}
 	};
 
@@ -68,7 +70,7 @@ handle_args(int argc, char *argv[])
 	{
 		if (strcmp(argv[1], "--help") == 0 || strcmp(argv[1], "-?") == 0)
 		{
-			printf(_("Usage: %s [-d DURATION] [-c CUTOFF]\n"), progname);
+			printf(_("Usage: %s [-d DURATION] [-c CUTOFF] [--fast]\n"), progname);
 			exit(0);
 		}
 		if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0)
@@ -78,7 +80,7 @@ handle_args(int argc, char *argv[])
 		}
 	}
 
-	while ((option = getopt_long(argc, argv, "d:c:",
+	while ((option = getopt_long(argc, argv, "d:c:f:",
 								 long_options, &optindex)) != -1)
 	{
 		switch (option)
@@ -125,6 +127,10 @@ handle_args(int argc, char *argv[])
 				}
 				break;
 
+			case 'f':
+				fast_timing = true;
+				break;
+
 			default:
 				fprintf(stderr, _("Try \"%s --help\" for more information.\n"),
 						progname);
@@ -155,11 +161,31 @@ test_timing(unsigned int duration)
 	uint64		total_time;
 	int64		time_elapsed = 0;
 	uint64		loop_count = 0;
-	uint64		prev,
-				cur;
 	instr_time	start_time,
 				end_time,
-				temp;
+				prev,
+				cur;
+	char	   *time_source = NULL;
+	bool		fast_timing_used = false;
+
+	INSTR_TIME_INITIALIZE();
+
+#if !defined(WIN32) && defined(__x86_64__) && defined(__linux__)
+	if (fast_timing && has_rdtsc)
+	{
+		time_source = "RDTSC";
+		fast_timing_used = true;
+	}
+	else if (has_rdtscp)
+		time_source = "RDTSCP";
+	else
+		time_source = PG_INSTR_CLOCK_NAME;
+#else
+	time_source = PG_INSTR_CLOCK_NAME;
+#endif
+	if (fast_timing && !fast_timing_used)
+		printf(_("Warning: Fast timing requested, but not available - regular timing source will be used\n"));
+	printf(_("Time source: %s\n"), time_source);
 
 	/*
 	 * Pre-zero the statistics data structures.  They're already zero by
@@ -173,8 +199,11 @@ test_timing(unsigned int duration)
 
 	total_time = duration > 0 ? duration * INT64CONST(1000000000) : 0;
 
-	INSTR_TIME_SET_CURRENT(start_time);
-	cur = INSTR_TIME_GET_NANOSEC(start_time);
+	if (fast_timing)
+		INSTR_TIME_SET_CURRENT_FAST(start_time);
+	else
+		INSTR_TIME_SET_CURRENT(start_time);
+	cur = start_time;
 
 	while (time_elapsed < total_time)
 	{
@@ -182,9 +211,11 @@ test_timing(unsigned int duration)
 					bits;
 
 		prev = cur;
-		INSTR_TIME_SET_CURRENT(temp);
-		cur = INSTR_TIME_GET_NANOSEC(temp);
-		diff = cur - prev;
+		if (fast_timing)
+			INSTR_TIME_SET_CURRENT_FAST(cur);
+		else
+			INSTR_TIME_SET_CURRENT(cur);
+		diff = INSTR_TIME_DIFF_NANOSEC(cur, prev);
 
 		/* Did time go backwards? */
 		if (unlikely(diff < 0))
@@ -217,11 +248,13 @@ test_timing(unsigned int duration)
 			largest_diff_count++;
 
 		loop_count++;
-		INSTR_TIME_SUBTRACT(temp, start_time);
-		time_elapsed = INSTR_TIME_GET_NANOSEC(temp);
+		time_elapsed = INSTR_TIME_DIFF_NANOSEC(cur, start_time);
 	}
 
-	INSTR_TIME_SET_CURRENT(end_time);
+	if (fast_timing)
+		INSTR_TIME_SET_CURRENT_FAST(end_time);
+	else
+		INSTR_TIME_SET_CURRENT(end_time);
 
 	INSTR_TIME_SUBTRACT(end_time, start_time);
 
diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h
index e2e339a0c4f..f02296f1026 100644
--- a/src/include/portability/instr_time.h
+++ b/src/include/portability/instr_time.h
@@ -112,10 +112,13 @@ extern int64 max_ticks_no_overflow;
  */
 #if defined(__darwin__) && defined(CLOCK_MONOTONIC_RAW)
 #define PG_INSTR_CLOCK	CLOCK_MONOTONIC_RAW
+#define PG_INSTR_CLOCK_NAME	"clock_gettime (CLOCK_MONOTONIC_RAW)"
 #elif defined(CLOCK_MONOTONIC)
 #define PG_INSTR_CLOCK	CLOCK_MONOTONIC
+#define PG_INSTR_CLOCK_NAME	"clock_gettime (CLOCK_MONOTONIC)"
 #else
 #define PG_INSTR_CLOCK	CLOCK_REALTIME
+#define PG_INSTR_CLOCK_NAME	"clock_gettime (CLOCK_REALTIME)"
 #endif
 
 #if defined(__x86_64__) && defined(__linux__)
@@ -174,7 +177,7 @@ pg_get_ticks(void)
 }
 
 static inline int64_t
-pg_ticks_to_ns(instr_time t)
+pg_ticks_to_ns(int64 ticks)
 {
 	/*
 	 * Would multiplication overflow? If so perform computation in two parts.
@@ -183,7 +186,7 @@ pg_ticks_to_ns(instr_time t)
 	 */
 	int64		ns = 0;
 
-	if (unlikely(t.ticks > max_ticks_no_overflow))
+	if (unlikely(ticks > max_ticks_no_overflow))
 	{
 		/*
 		 * Compute how often the maximum number of ticks fits completely into
@@ -192,7 +195,7 @@ pg_ticks_to_ns(instr_time t)
 		 * value. In a 2nd step we adjust the number of elapsed ticks and
 		 * convert the remaining ticks.
 		 */
-		int64		count = t.ticks / max_ticks_no_overflow;
+		int64		count = ticks / max_ticks_no_overflow;
 		int64		max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION;
 
 		ns = max_ns * count;
@@ -201,11 +204,11 @@ pg_ticks_to_ns(instr_time t)
 		 * Subtract the ticks that we now already accounted for, so that they
 		 * don't get counted twice.
 		 */
-		t.ticks -= count * max_ticks_no_overflow;
-		Assert(t.ticks >= 0);
+		ticks -= count * max_ticks_no_overflow;
+		Assert(ticks >= 0);
 	}
 
-	ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION;
+	ns += ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION;
 	return ns;
 }
 
@@ -226,14 +229,14 @@ pg_initialize_get_ticks()
 #define INSTR_TIME_SET_CURRENT(t) \
 	((t) = pg_get_ticks())
 
-#define INSTR_TIME_GET_NANOSEC(t) \
-	pg_ticks_to_ns(t)
-
+#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \
+	(pg_ticks_to_ns(ticks))
 
 #else							/* WIN32 */
 
 
 /* Use QueryPerformanceCounter() */
+#define PG_INSTR_CLOCK_NAME	"QueryPerformanceCounter"
 
 /* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */
 static inline instr_time
@@ -265,8 +268,8 @@ GetTimerFrequency(void)
 #define INSTR_TIME_SET_CURRENT(t) \
 	((t) = pg_query_performance_counter())
 
-#define INSTR_TIME_GET_NANOSEC(t) \
-	((int64) ((t).ticks * ((double) NS_PER_S / GetTimerFrequency())))
+#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \
+	((int64) ((ticks) * ((double) NS_PER_S / GetTimerFrequency())))
 
 #endif							/* WIN32 */
 
@@ -285,9 +288,14 @@ GetTimerFrequency(void)
 #define INSTR_TIME_SUBTRACT(x,y) \
 	((x).ticks -= (y).ticks)
 
+#define INSTR_TIME_DIFF_NANOSEC(x,y) \
+	(INSTR_TIME_TICKS_TO_NANOSEC((x).ticks - (y).ticks))
+
 #define INSTR_TIME_ACCUM_DIFF(x,y,z) \
 	((x).ticks += (y).ticks - (z).ticks)
 
+#define INSTR_TIME_GET_NANOSEC(t) \
+	(INSTR_TIME_TICKS_TO_NANOSEC((t).ticks))
 
 #define INSTR_TIME_GET_DOUBLE(t) \
 	((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S)
-- 
2.47.3


--vtqqtrpooseurzip--





^ permalink  raw  reply  [nested|flat] 265+ messages in thread

* [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source
@ 2025-07-27 15:48  Lukas Fittl <[email protected]>
  0 siblings, 0 replies; 265+ messages in thread

From: Lukas Fittl @ 2025-07-27 15:48 UTC (permalink / raw)

In passing also reduce the per-loop overhead caused by repeated divisions
in INSTR_TIME_GET_NANOSEC when the ticks variable has become very large,
instead diff first and then turn it into nanosecs.
---
 src/bin/pg_test_timing/pg_test_timing.c | 59 +++++++++++++++++++------
 src/include/portability/instr_time.h    | 30 ++++++++-----
 2 files changed, 65 insertions(+), 24 deletions(-)

diff --git a/src/bin/pg_test_timing/pg_test_timing.c b/src/bin/pg_test_timing/pg_test_timing.c
index a5621251afc..b77ef2063b6 100644
--- a/src/bin/pg_test_timing/pg_test_timing.c
+++ b/src/bin/pg_test_timing/pg_test_timing.c
@@ -16,6 +16,7 @@ static const char *progname;
 
 static unsigned int test_duration = 3;
 static double max_rprct = 99.99;
+static bool fast_timing = false;
 
 /* record duration in powers of 2 nanoseconds */
 static long long int histogram[32];
@@ -56,6 +57,7 @@ handle_args(int argc, char *argv[])
 	static struct option long_options[] = {
 		{"duration", required_argument, NULL, 'd'},
 		{"cutoff", required_argument, NULL, 'c'},
+		{"fast", no_argument, NULL, 'f'},
 		{NULL, 0, NULL, 0}
 	};
 
@@ -68,7 +70,7 @@ handle_args(int argc, char *argv[])
 	{
 		if (strcmp(argv[1], "--help") == 0 || strcmp(argv[1], "-?") == 0)
 		{
-			printf(_("Usage: %s [-d DURATION] [-c CUTOFF]\n"), progname);
+			printf(_("Usage: %s [-d DURATION] [-c CUTOFF] [--fast]\n"), progname);
 			exit(0);
 		}
 		if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0)
@@ -78,7 +80,7 @@ handle_args(int argc, char *argv[])
 		}
 	}
 
-	while ((option = getopt_long(argc, argv, "d:c:",
+	while ((option = getopt_long(argc, argv, "d:c:f:",
 								 long_options, &optindex)) != -1)
 	{
 		switch (option)
@@ -125,6 +127,10 @@ handle_args(int argc, char *argv[])
 				}
 				break;
 
+			case 'f':
+				fast_timing = true;
+				break;
+
 			default:
 				fprintf(stderr, _("Try \"%s --help\" for more information.\n"),
 						progname);
@@ -155,11 +161,31 @@ test_timing(unsigned int duration)
 	uint64		total_time;
 	int64		time_elapsed = 0;
 	uint64		loop_count = 0;
-	uint64		prev,
-				cur;
 	instr_time	start_time,
 				end_time,
-				temp;
+				prev,
+				cur;
+	char	   *time_source = NULL;
+	bool		fast_timing_used = false;
+
+	INSTR_TIME_INITIALIZE();
+
+#if !defined(WIN32) && defined(__x86_64__) && defined(__linux__)
+	if (fast_timing && has_rdtsc)
+	{
+		time_source = "RDTSC";
+		fast_timing_used = true;
+	}
+	else if (has_rdtscp)
+		time_source = "RDTSCP";
+	else
+		time_source = PG_INSTR_CLOCK_NAME;
+#else
+	time_source = PG_INSTR_CLOCK_NAME;
+#endif
+	if (fast_timing && !fast_timing_used)
+		printf(_("Warning: Fast timing requested, but not available - regular timing source will be used\n"));
+	printf(_("Time source: %s\n"), time_source);
 
 	/*
 	 * Pre-zero the statistics data structures.  They're already zero by
@@ -173,8 +199,11 @@ test_timing(unsigned int duration)
 
 	total_time = duration > 0 ? duration * INT64CONST(1000000000) : 0;
 
-	INSTR_TIME_SET_CURRENT(start_time);
-	cur = INSTR_TIME_GET_NANOSEC(start_time);
+	if (fast_timing)
+		INSTR_TIME_SET_CURRENT_FAST(start_time);
+	else
+		INSTR_TIME_SET_CURRENT(start_time);
+	cur = start_time;
 
 	while (time_elapsed < total_time)
 	{
@@ -182,9 +211,11 @@ test_timing(unsigned int duration)
 					bits;
 
 		prev = cur;
-		INSTR_TIME_SET_CURRENT(temp);
-		cur = INSTR_TIME_GET_NANOSEC(temp);
-		diff = cur - prev;
+		if (fast_timing)
+			INSTR_TIME_SET_CURRENT_FAST(cur);
+		else
+			INSTR_TIME_SET_CURRENT(cur);
+		diff = INSTR_TIME_DIFF_NANOSEC(cur, prev);
 
 		/* Did time go backwards? */
 		if (unlikely(diff < 0))
@@ -217,11 +248,13 @@ test_timing(unsigned int duration)
 			largest_diff_count++;
 
 		loop_count++;
-		INSTR_TIME_SUBTRACT(temp, start_time);
-		time_elapsed = INSTR_TIME_GET_NANOSEC(temp);
+		time_elapsed = INSTR_TIME_DIFF_NANOSEC(cur, start_time);
 	}
 
-	INSTR_TIME_SET_CURRENT(end_time);
+	if (fast_timing)
+		INSTR_TIME_SET_CURRENT_FAST(end_time);
+	else
+		INSTR_TIME_SET_CURRENT(end_time);
 
 	INSTR_TIME_SUBTRACT(end_time, start_time);
 
diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h
index e2e339a0c4f..f02296f1026 100644
--- a/src/include/portability/instr_time.h
+++ b/src/include/portability/instr_time.h
@@ -112,10 +112,13 @@ extern int64 max_ticks_no_overflow;
  */
 #if defined(__darwin__) && defined(CLOCK_MONOTONIC_RAW)
 #define PG_INSTR_CLOCK	CLOCK_MONOTONIC_RAW
+#define PG_INSTR_CLOCK_NAME	"clock_gettime (CLOCK_MONOTONIC_RAW)"
 #elif defined(CLOCK_MONOTONIC)
 #define PG_INSTR_CLOCK	CLOCK_MONOTONIC
+#define PG_INSTR_CLOCK_NAME	"clock_gettime (CLOCK_MONOTONIC)"
 #else
 #define PG_INSTR_CLOCK	CLOCK_REALTIME
+#define PG_INSTR_CLOCK_NAME	"clock_gettime (CLOCK_REALTIME)"
 #endif
 
 #if defined(__x86_64__) && defined(__linux__)
@@ -174,7 +177,7 @@ pg_get_ticks(void)
 }
 
 static inline int64_t
-pg_ticks_to_ns(instr_time t)
+pg_ticks_to_ns(int64 ticks)
 {
 	/*
 	 * Would multiplication overflow? If so perform computation in two parts.
@@ -183,7 +186,7 @@ pg_ticks_to_ns(instr_time t)
 	 */
 	int64		ns = 0;
 
-	if (unlikely(t.ticks > max_ticks_no_overflow))
+	if (unlikely(ticks > max_ticks_no_overflow))
 	{
 		/*
 		 * Compute how often the maximum number of ticks fits completely into
@@ -192,7 +195,7 @@ pg_ticks_to_ns(instr_time t)
 		 * value. In a 2nd step we adjust the number of elapsed ticks and
 		 * convert the remaining ticks.
 		 */
-		int64		count = t.ticks / max_ticks_no_overflow;
+		int64		count = ticks / max_ticks_no_overflow;
 		int64		max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION;
 
 		ns = max_ns * count;
@@ -201,11 +204,11 @@ pg_ticks_to_ns(instr_time t)
 		 * Subtract the ticks that we now already accounted for, so that they
 		 * don't get counted twice.
 		 */
-		t.ticks -= count * max_ticks_no_overflow;
-		Assert(t.ticks >= 0);
+		ticks -= count * max_ticks_no_overflow;
+		Assert(ticks >= 0);
 	}
 
-	ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION;
+	ns += ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION;
 	return ns;
 }
 
@@ -226,14 +229,14 @@ pg_initialize_get_ticks()
 #define INSTR_TIME_SET_CURRENT(t) \
 	((t) = pg_get_ticks())
 
-#define INSTR_TIME_GET_NANOSEC(t) \
-	pg_ticks_to_ns(t)
-
+#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \
+	(pg_ticks_to_ns(ticks))
 
 #else							/* WIN32 */
 
 
 /* Use QueryPerformanceCounter() */
+#define PG_INSTR_CLOCK_NAME	"QueryPerformanceCounter"
 
 /* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */
 static inline instr_time
@@ -265,8 +268,8 @@ GetTimerFrequency(void)
 #define INSTR_TIME_SET_CURRENT(t) \
 	((t) = pg_query_performance_counter())
 
-#define INSTR_TIME_GET_NANOSEC(t) \
-	((int64) ((t).ticks * ((double) NS_PER_S / GetTimerFrequency())))
+#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \
+	((int64) ((ticks) * ((double) NS_PER_S / GetTimerFrequency())))
 
 #endif							/* WIN32 */
 
@@ -285,9 +288,14 @@ GetTimerFrequency(void)
 #define INSTR_TIME_SUBTRACT(x,y) \
 	((x).ticks -= (y).ticks)
 
+#define INSTR_TIME_DIFF_NANOSEC(x,y) \
+	(INSTR_TIME_TICKS_TO_NANOSEC((x).ticks - (y).ticks))
+
 #define INSTR_TIME_ACCUM_DIFF(x,y,z) \
 	((x).ticks += (y).ticks - (z).ticks)
 
+#define INSTR_TIME_GET_NANOSEC(t) \
+	(INSTR_TIME_TICKS_TO_NANOSEC((t).ticks))
 
 #define INSTR_TIME_GET_DOUBLE(t) \
 	((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S)
-- 
2.47.3


--vtqqtrpooseurzip--





^ permalink  raw  reply  [nested|flat] 265+ messages in thread

* [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source
@ 2025-07-27 15:48  Lukas Fittl <[email protected]>
  0 siblings, 0 replies; 265+ messages in thread

From: Lukas Fittl @ 2025-07-27 15:48 UTC (permalink / raw)

In passing also reduce the per-loop overhead caused by repeated divisions
in INSTR_TIME_GET_NANOSEC when the ticks variable has become very large,
instead diff first and then turn it into nanosecs.
---
 src/bin/pg_test_timing/pg_test_timing.c | 59 +++++++++++++++++++------
 src/include/portability/instr_time.h    | 30 ++++++++-----
 2 files changed, 65 insertions(+), 24 deletions(-)

diff --git a/src/bin/pg_test_timing/pg_test_timing.c b/src/bin/pg_test_timing/pg_test_timing.c
index a5621251afc..b77ef2063b6 100644
--- a/src/bin/pg_test_timing/pg_test_timing.c
+++ b/src/bin/pg_test_timing/pg_test_timing.c
@@ -16,6 +16,7 @@ static const char *progname;
 
 static unsigned int test_duration = 3;
 static double max_rprct = 99.99;
+static bool fast_timing = false;
 
 /* record duration in powers of 2 nanoseconds */
 static long long int histogram[32];
@@ -56,6 +57,7 @@ handle_args(int argc, char *argv[])
 	static struct option long_options[] = {
 		{"duration", required_argument, NULL, 'd'},
 		{"cutoff", required_argument, NULL, 'c'},
+		{"fast", no_argument, NULL, 'f'},
 		{NULL, 0, NULL, 0}
 	};
 
@@ -68,7 +70,7 @@ handle_args(int argc, char *argv[])
 	{
 		if (strcmp(argv[1], "--help") == 0 || strcmp(argv[1], "-?") == 0)
 		{
-			printf(_("Usage: %s [-d DURATION] [-c CUTOFF]\n"), progname);
+			printf(_("Usage: %s [-d DURATION] [-c CUTOFF] [--fast]\n"), progname);
 			exit(0);
 		}
 		if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0)
@@ -78,7 +80,7 @@ handle_args(int argc, char *argv[])
 		}
 	}
 
-	while ((option = getopt_long(argc, argv, "d:c:",
+	while ((option = getopt_long(argc, argv, "d:c:f:",
 								 long_options, &optindex)) != -1)
 	{
 		switch (option)
@@ -125,6 +127,10 @@ handle_args(int argc, char *argv[])
 				}
 				break;
 
+			case 'f':
+				fast_timing = true;
+				break;
+
 			default:
 				fprintf(stderr, _("Try \"%s --help\" for more information.\n"),
 						progname);
@@ -155,11 +161,31 @@ test_timing(unsigned int duration)
 	uint64		total_time;
 	int64		time_elapsed = 0;
 	uint64		loop_count = 0;
-	uint64		prev,
-				cur;
 	instr_time	start_time,
 				end_time,
-				temp;
+				prev,
+				cur;
+	char	   *time_source = NULL;
+	bool		fast_timing_used = false;
+
+	INSTR_TIME_INITIALIZE();
+
+#if !defined(WIN32) && defined(__x86_64__) && defined(__linux__)
+	if (fast_timing && has_rdtsc)
+	{
+		time_source = "RDTSC";
+		fast_timing_used = true;
+	}
+	else if (has_rdtscp)
+		time_source = "RDTSCP";
+	else
+		time_source = PG_INSTR_CLOCK_NAME;
+#else
+	time_source = PG_INSTR_CLOCK_NAME;
+#endif
+	if (fast_timing && !fast_timing_used)
+		printf(_("Warning: Fast timing requested, but not available - regular timing source will be used\n"));
+	printf(_("Time source: %s\n"), time_source);
 
 	/*
 	 * Pre-zero the statistics data structures.  They're already zero by
@@ -173,8 +199,11 @@ test_timing(unsigned int duration)
 
 	total_time = duration > 0 ? duration * INT64CONST(1000000000) : 0;
 
-	INSTR_TIME_SET_CURRENT(start_time);
-	cur = INSTR_TIME_GET_NANOSEC(start_time);
+	if (fast_timing)
+		INSTR_TIME_SET_CURRENT_FAST(start_time);
+	else
+		INSTR_TIME_SET_CURRENT(start_time);
+	cur = start_time;
 
 	while (time_elapsed < total_time)
 	{
@@ -182,9 +211,11 @@ test_timing(unsigned int duration)
 					bits;
 
 		prev = cur;
-		INSTR_TIME_SET_CURRENT(temp);
-		cur = INSTR_TIME_GET_NANOSEC(temp);
-		diff = cur - prev;
+		if (fast_timing)
+			INSTR_TIME_SET_CURRENT_FAST(cur);
+		else
+			INSTR_TIME_SET_CURRENT(cur);
+		diff = INSTR_TIME_DIFF_NANOSEC(cur, prev);
 
 		/* Did time go backwards? */
 		if (unlikely(diff < 0))
@@ -217,11 +248,13 @@ test_timing(unsigned int duration)
 			largest_diff_count++;
 
 		loop_count++;
-		INSTR_TIME_SUBTRACT(temp, start_time);
-		time_elapsed = INSTR_TIME_GET_NANOSEC(temp);
+		time_elapsed = INSTR_TIME_DIFF_NANOSEC(cur, start_time);
 	}
 
-	INSTR_TIME_SET_CURRENT(end_time);
+	if (fast_timing)
+		INSTR_TIME_SET_CURRENT_FAST(end_time);
+	else
+		INSTR_TIME_SET_CURRENT(end_time);
 
 	INSTR_TIME_SUBTRACT(end_time, start_time);
 
diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h
index e2e339a0c4f..f02296f1026 100644
--- a/src/include/portability/instr_time.h
+++ b/src/include/portability/instr_time.h
@@ -112,10 +112,13 @@ extern int64 max_ticks_no_overflow;
  */
 #if defined(__darwin__) && defined(CLOCK_MONOTONIC_RAW)
 #define PG_INSTR_CLOCK	CLOCK_MONOTONIC_RAW
+#define PG_INSTR_CLOCK_NAME	"clock_gettime (CLOCK_MONOTONIC_RAW)"
 #elif defined(CLOCK_MONOTONIC)
 #define PG_INSTR_CLOCK	CLOCK_MONOTONIC
+#define PG_INSTR_CLOCK_NAME	"clock_gettime (CLOCK_MONOTONIC)"
 #else
 #define PG_INSTR_CLOCK	CLOCK_REALTIME
+#define PG_INSTR_CLOCK_NAME	"clock_gettime (CLOCK_REALTIME)"
 #endif
 
 #if defined(__x86_64__) && defined(__linux__)
@@ -174,7 +177,7 @@ pg_get_ticks(void)
 }
 
 static inline int64_t
-pg_ticks_to_ns(instr_time t)
+pg_ticks_to_ns(int64 ticks)
 {
 	/*
 	 * Would multiplication overflow? If so perform computation in two parts.
@@ -183,7 +186,7 @@ pg_ticks_to_ns(instr_time t)
 	 */
 	int64		ns = 0;
 
-	if (unlikely(t.ticks > max_ticks_no_overflow))
+	if (unlikely(ticks > max_ticks_no_overflow))
 	{
 		/*
 		 * Compute how often the maximum number of ticks fits completely into
@@ -192,7 +195,7 @@ pg_ticks_to_ns(instr_time t)
 		 * value. In a 2nd step we adjust the number of elapsed ticks and
 		 * convert the remaining ticks.
 		 */
-		int64		count = t.ticks / max_ticks_no_overflow;
+		int64		count = ticks / max_ticks_no_overflow;
 		int64		max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION;
 
 		ns = max_ns * count;
@@ -201,11 +204,11 @@ pg_ticks_to_ns(instr_time t)
 		 * Subtract the ticks that we now already accounted for, so that they
 		 * don't get counted twice.
 		 */
-		t.ticks -= count * max_ticks_no_overflow;
-		Assert(t.ticks >= 0);
+		ticks -= count * max_ticks_no_overflow;
+		Assert(ticks >= 0);
 	}
 
-	ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION;
+	ns += ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION;
 	return ns;
 }
 
@@ -226,14 +229,14 @@ pg_initialize_get_ticks()
 #define INSTR_TIME_SET_CURRENT(t) \
 	((t) = pg_get_ticks())
 
-#define INSTR_TIME_GET_NANOSEC(t) \
-	pg_ticks_to_ns(t)
-
+#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \
+	(pg_ticks_to_ns(ticks))
 
 #else							/* WIN32 */
 
 
 /* Use QueryPerformanceCounter() */
+#define PG_INSTR_CLOCK_NAME	"QueryPerformanceCounter"
 
 /* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */
 static inline instr_time
@@ -265,8 +268,8 @@ GetTimerFrequency(void)
 #define INSTR_TIME_SET_CURRENT(t) \
 	((t) = pg_query_performance_counter())
 
-#define INSTR_TIME_GET_NANOSEC(t) \
-	((int64) ((t).ticks * ((double) NS_PER_S / GetTimerFrequency())))
+#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \
+	((int64) ((ticks) * ((double) NS_PER_S / GetTimerFrequency())))
 
 #endif							/* WIN32 */
 
@@ -285,9 +288,14 @@ GetTimerFrequency(void)
 #define INSTR_TIME_SUBTRACT(x,y) \
 	((x).ticks -= (y).ticks)
 
+#define INSTR_TIME_DIFF_NANOSEC(x,y) \
+	(INSTR_TIME_TICKS_TO_NANOSEC((x).ticks - (y).ticks))
+
 #define INSTR_TIME_ACCUM_DIFF(x,y,z) \
 	((x).ticks += (y).ticks - (z).ticks)
 
+#define INSTR_TIME_GET_NANOSEC(t) \
+	(INSTR_TIME_TICKS_TO_NANOSEC((t).ticks))
 
 #define INSTR_TIME_GET_DOUBLE(t) \
 	((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S)
-- 
2.47.3


--vtqqtrpooseurzip--





^ permalink  raw  reply  [nested|flat] 265+ messages in thread

* [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source
@ 2025-07-27 15:48  Lukas Fittl <[email protected]>
  0 siblings, 0 replies; 265+ messages in thread

From: Lukas Fittl @ 2025-07-27 15:48 UTC (permalink / raw)

In passing also reduce the per-loop overhead caused by repeated divisions
in INSTR_TIME_GET_NANOSEC when the ticks variable has become very large,
instead diff first and then turn it into nanosecs.
---
 src/bin/pg_test_timing/pg_test_timing.c | 59 +++++++++++++++++++------
 src/include/portability/instr_time.h    | 30 ++++++++-----
 2 files changed, 65 insertions(+), 24 deletions(-)

diff --git a/src/bin/pg_test_timing/pg_test_timing.c b/src/bin/pg_test_timing/pg_test_timing.c
index a5621251afc..b77ef2063b6 100644
--- a/src/bin/pg_test_timing/pg_test_timing.c
+++ b/src/bin/pg_test_timing/pg_test_timing.c
@@ -16,6 +16,7 @@ static const char *progname;
 
 static unsigned int test_duration = 3;
 static double max_rprct = 99.99;
+static bool fast_timing = false;
 
 /* record duration in powers of 2 nanoseconds */
 static long long int histogram[32];
@@ -56,6 +57,7 @@ handle_args(int argc, char *argv[])
 	static struct option long_options[] = {
 		{"duration", required_argument, NULL, 'd'},
 		{"cutoff", required_argument, NULL, 'c'},
+		{"fast", no_argument, NULL, 'f'},
 		{NULL, 0, NULL, 0}
 	};
 
@@ -68,7 +70,7 @@ handle_args(int argc, char *argv[])
 	{
 		if (strcmp(argv[1], "--help") == 0 || strcmp(argv[1], "-?") == 0)
 		{
-			printf(_("Usage: %s [-d DURATION] [-c CUTOFF]\n"), progname);
+			printf(_("Usage: %s [-d DURATION] [-c CUTOFF] [--fast]\n"), progname);
 			exit(0);
 		}
 		if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0)
@@ -78,7 +80,7 @@ handle_args(int argc, char *argv[])
 		}
 	}
 
-	while ((option = getopt_long(argc, argv, "d:c:",
+	while ((option = getopt_long(argc, argv, "d:c:f:",
 								 long_options, &optindex)) != -1)
 	{
 		switch (option)
@@ -125,6 +127,10 @@ handle_args(int argc, char *argv[])
 				}
 				break;
 
+			case 'f':
+				fast_timing = true;
+				break;
+
 			default:
 				fprintf(stderr, _("Try \"%s --help\" for more information.\n"),
 						progname);
@@ -155,11 +161,31 @@ test_timing(unsigned int duration)
 	uint64		total_time;
 	int64		time_elapsed = 0;
 	uint64		loop_count = 0;
-	uint64		prev,
-				cur;
 	instr_time	start_time,
 				end_time,
-				temp;
+				prev,
+				cur;
+	char	   *time_source = NULL;
+	bool		fast_timing_used = false;
+
+	INSTR_TIME_INITIALIZE();
+
+#if !defined(WIN32) && defined(__x86_64__) && defined(__linux__)
+	if (fast_timing && has_rdtsc)
+	{
+		time_source = "RDTSC";
+		fast_timing_used = true;
+	}
+	else if (has_rdtscp)
+		time_source = "RDTSCP";
+	else
+		time_source = PG_INSTR_CLOCK_NAME;
+#else
+	time_source = PG_INSTR_CLOCK_NAME;
+#endif
+	if (fast_timing && !fast_timing_used)
+		printf(_("Warning: Fast timing requested, but not available - regular timing source will be used\n"));
+	printf(_("Time source: %s\n"), time_source);
 
 	/*
 	 * Pre-zero the statistics data structures.  They're already zero by
@@ -173,8 +199,11 @@ test_timing(unsigned int duration)
 
 	total_time = duration > 0 ? duration * INT64CONST(1000000000) : 0;
 
-	INSTR_TIME_SET_CURRENT(start_time);
-	cur = INSTR_TIME_GET_NANOSEC(start_time);
+	if (fast_timing)
+		INSTR_TIME_SET_CURRENT_FAST(start_time);
+	else
+		INSTR_TIME_SET_CURRENT(start_time);
+	cur = start_time;
 
 	while (time_elapsed < total_time)
 	{
@@ -182,9 +211,11 @@ test_timing(unsigned int duration)
 					bits;
 
 		prev = cur;
-		INSTR_TIME_SET_CURRENT(temp);
-		cur = INSTR_TIME_GET_NANOSEC(temp);
-		diff = cur - prev;
+		if (fast_timing)
+			INSTR_TIME_SET_CURRENT_FAST(cur);
+		else
+			INSTR_TIME_SET_CURRENT(cur);
+		diff = INSTR_TIME_DIFF_NANOSEC(cur, prev);
 
 		/* Did time go backwards? */
 		if (unlikely(diff < 0))
@@ -217,11 +248,13 @@ test_timing(unsigned int duration)
 			largest_diff_count++;
 
 		loop_count++;
-		INSTR_TIME_SUBTRACT(temp, start_time);
-		time_elapsed = INSTR_TIME_GET_NANOSEC(temp);
+		time_elapsed = INSTR_TIME_DIFF_NANOSEC(cur, start_time);
 	}
 
-	INSTR_TIME_SET_CURRENT(end_time);
+	if (fast_timing)
+		INSTR_TIME_SET_CURRENT_FAST(end_time);
+	else
+		INSTR_TIME_SET_CURRENT(end_time);
 
 	INSTR_TIME_SUBTRACT(end_time, start_time);
 
diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h
index e2e339a0c4f..f02296f1026 100644
--- a/src/include/portability/instr_time.h
+++ b/src/include/portability/instr_time.h
@@ -112,10 +112,13 @@ extern int64 max_ticks_no_overflow;
  */
 #if defined(__darwin__) && defined(CLOCK_MONOTONIC_RAW)
 #define PG_INSTR_CLOCK	CLOCK_MONOTONIC_RAW
+#define PG_INSTR_CLOCK_NAME	"clock_gettime (CLOCK_MONOTONIC_RAW)"
 #elif defined(CLOCK_MONOTONIC)
 #define PG_INSTR_CLOCK	CLOCK_MONOTONIC
+#define PG_INSTR_CLOCK_NAME	"clock_gettime (CLOCK_MONOTONIC)"
 #else
 #define PG_INSTR_CLOCK	CLOCK_REALTIME
+#define PG_INSTR_CLOCK_NAME	"clock_gettime (CLOCK_REALTIME)"
 #endif
 
 #if defined(__x86_64__) && defined(__linux__)
@@ -174,7 +177,7 @@ pg_get_ticks(void)
 }
 
 static inline int64_t
-pg_ticks_to_ns(instr_time t)
+pg_ticks_to_ns(int64 ticks)
 {
 	/*
 	 * Would multiplication overflow? If so perform computation in two parts.
@@ -183,7 +186,7 @@ pg_ticks_to_ns(instr_time t)
 	 */
 	int64		ns = 0;
 
-	if (unlikely(t.ticks > max_ticks_no_overflow))
+	if (unlikely(ticks > max_ticks_no_overflow))
 	{
 		/*
 		 * Compute how often the maximum number of ticks fits completely into
@@ -192,7 +195,7 @@ pg_ticks_to_ns(instr_time t)
 		 * value. In a 2nd step we adjust the number of elapsed ticks and
 		 * convert the remaining ticks.
 		 */
-		int64		count = t.ticks / max_ticks_no_overflow;
+		int64		count = ticks / max_ticks_no_overflow;
 		int64		max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION;
 
 		ns = max_ns * count;
@@ -201,11 +204,11 @@ pg_ticks_to_ns(instr_time t)
 		 * Subtract the ticks that we now already accounted for, so that they
 		 * don't get counted twice.
 		 */
-		t.ticks -= count * max_ticks_no_overflow;
-		Assert(t.ticks >= 0);
+		ticks -= count * max_ticks_no_overflow;
+		Assert(ticks >= 0);
 	}
 
-	ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION;
+	ns += ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION;
 	return ns;
 }
 
@@ -226,14 +229,14 @@ pg_initialize_get_ticks()
 #define INSTR_TIME_SET_CURRENT(t) \
 	((t) = pg_get_ticks())
 
-#define INSTR_TIME_GET_NANOSEC(t) \
-	pg_ticks_to_ns(t)
-
+#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \
+	(pg_ticks_to_ns(ticks))
 
 #else							/* WIN32 */
 
 
 /* Use QueryPerformanceCounter() */
+#define PG_INSTR_CLOCK_NAME	"QueryPerformanceCounter"
 
 /* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */
 static inline instr_time
@@ -265,8 +268,8 @@ GetTimerFrequency(void)
 #define INSTR_TIME_SET_CURRENT(t) \
 	((t) = pg_query_performance_counter())
 
-#define INSTR_TIME_GET_NANOSEC(t) \
-	((int64) ((t).ticks * ((double) NS_PER_S / GetTimerFrequency())))
+#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \
+	((int64) ((ticks) * ((double) NS_PER_S / GetTimerFrequency())))
 
 #endif							/* WIN32 */
 
@@ -285,9 +288,14 @@ GetTimerFrequency(void)
 #define INSTR_TIME_SUBTRACT(x,y) \
 	((x).ticks -= (y).ticks)
 
+#define INSTR_TIME_DIFF_NANOSEC(x,y) \
+	(INSTR_TIME_TICKS_TO_NANOSEC((x).ticks - (y).ticks))
+
 #define INSTR_TIME_ACCUM_DIFF(x,y,z) \
 	((x).ticks += (y).ticks - (z).ticks)
 
+#define INSTR_TIME_GET_NANOSEC(t) \
+	(INSTR_TIME_TICKS_TO_NANOSEC((t).ticks))
 
 #define INSTR_TIME_GET_DOUBLE(t) \
 	((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S)
-- 
2.47.3


--vtqqtrpooseurzip--





^ permalink  raw  reply  [nested|flat] 265+ messages in thread

* [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source
@ 2025-07-27 15:48  Lukas Fittl <[email protected]>
  0 siblings, 0 replies; 265+ messages in thread

From: Lukas Fittl @ 2025-07-27 15:48 UTC (permalink / raw)

In passing also reduce the per-loop overhead caused by repeated divisions
in INSTR_TIME_GET_NANOSEC when the ticks variable has become very large,
instead diff first and then turn it into nanosecs.
---
 src/bin/pg_test_timing/pg_test_timing.c | 59 +++++++++++++++++++------
 src/include/portability/instr_time.h    | 30 ++++++++-----
 2 files changed, 65 insertions(+), 24 deletions(-)

diff --git a/src/bin/pg_test_timing/pg_test_timing.c b/src/bin/pg_test_timing/pg_test_timing.c
index a5621251afc..b77ef2063b6 100644
--- a/src/bin/pg_test_timing/pg_test_timing.c
+++ b/src/bin/pg_test_timing/pg_test_timing.c
@@ -16,6 +16,7 @@ static const char *progname;
 
 static unsigned int test_duration = 3;
 static double max_rprct = 99.99;
+static bool fast_timing = false;
 
 /* record duration in powers of 2 nanoseconds */
 static long long int histogram[32];
@@ -56,6 +57,7 @@ handle_args(int argc, char *argv[])
 	static struct option long_options[] = {
 		{"duration", required_argument, NULL, 'd'},
 		{"cutoff", required_argument, NULL, 'c'},
+		{"fast", no_argument, NULL, 'f'},
 		{NULL, 0, NULL, 0}
 	};
 
@@ -68,7 +70,7 @@ handle_args(int argc, char *argv[])
 	{
 		if (strcmp(argv[1], "--help") == 0 || strcmp(argv[1], "-?") == 0)
 		{
-			printf(_("Usage: %s [-d DURATION] [-c CUTOFF]\n"), progname);
+			printf(_("Usage: %s [-d DURATION] [-c CUTOFF] [--fast]\n"), progname);
 			exit(0);
 		}
 		if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0)
@@ -78,7 +80,7 @@ handle_args(int argc, char *argv[])
 		}
 	}
 
-	while ((option = getopt_long(argc, argv, "d:c:",
+	while ((option = getopt_long(argc, argv, "d:c:f:",
 								 long_options, &optindex)) != -1)
 	{
 		switch (option)
@@ -125,6 +127,10 @@ handle_args(int argc, char *argv[])
 				}
 				break;
 
+			case 'f':
+				fast_timing = true;
+				break;
+
 			default:
 				fprintf(stderr, _("Try \"%s --help\" for more information.\n"),
 						progname);
@@ -155,11 +161,31 @@ test_timing(unsigned int duration)
 	uint64		total_time;
 	int64		time_elapsed = 0;
 	uint64		loop_count = 0;
-	uint64		prev,
-				cur;
 	instr_time	start_time,
 				end_time,
-				temp;
+				prev,
+				cur;
+	char	   *time_source = NULL;
+	bool		fast_timing_used = false;
+
+	INSTR_TIME_INITIALIZE();
+
+#if !defined(WIN32) && defined(__x86_64__) && defined(__linux__)
+	if (fast_timing && has_rdtsc)
+	{
+		time_source = "RDTSC";
+		fast_timing_used = true;
+	}
+	else if (has_rdtscp)
+		time_source = "RDTSCP";
+	else
+		time_source = PG_INSTR_CLOCK_NAME;
+#else
+	time_source = PG_INSTR_CLOCK_NAME;
+#endif
+	if (fast_timing && !fast_timing_used)
+		printf(_("Warning: Fast timing requested, but not available - regular timing source will be used\n"));
+	printf(_("Time source: %s\n"), time_source);
 
 	/*
 	 * Pre-zero the statistics data structures.  They're already zero by
@@ -173,8 +199,11 @@ test_timing(unsigned int duration)
 
 	total_time = duration > 0 ? duration * INT64CONST(1000000000) : 0;
 
-	INSTR_TIME_SET_CURRENT(start_time);
-	cur = INSTR_TIME_GET_NANOSEC(start_time);
+	if (fast_timing)
+		INSTR_TIME_SET_CURRENT_FAST(start_time);
+	else
+		INSTR_TIME_SET_CURRENT(start_time);
+	cur = start_time;
 
 	while (time_elapsed < total_time)
 	{
@@ -182,9 +211,11 @@ test_timing(unsigned int duration)
 					bits;
 
 		prev = cur;
-		INSTR_TIME_SET_CURRENT(temp);
-		cur = INSTR_TIME_GET_NANOSEC(temp);
-		diff = cur - prev;
+		if (fast_timing)
+			INSTR_TIME_SET_CURRENT_FAST(cur);
+		else
+			INSTR_TIME_SET_CURRENT(cur);
+		diff = INSTR_TIME_DIFF_NANOSEC(cur, prev);
 
 		/* Did time go backwards? */
 		if (unlikely(diff < 0))
@@ -217,11 +248,13 @@ test_timing(unsigned int duration)
 			largest_diff_count++;
 
 		loop_count++;
-		INSTR_TIME_SUBTRACT(temp, start_time);
-		time_elapsed = INSTR_TIME_GET_NANOSEC(temp);
+		time_elapsed = INSTR_TIME_DIFF_NANOSEC(cur, start_time);
 	}
 
-	INSTR_TIME_SET_CURRENT(end_time);
+	if (fast_timing)
+		INSTR_TIME_SET_CURRENT_FAST(end_time);
+	else
+		INSTR_TIME_SET_CURRENT(end_time);
 
 	INSTR_TIME_SUBTRACT(end_time, start_time);
 
diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h
index e2e339a0c4f..f02296f1026 100644
--- a/src/include/portability/instr_time.h
+++ b/src/include/portability/instr_time.h
@@ -112,10 +112,13 @@ extern int64 max_ticks_no_overflow;
  */
 #if defined(__darwin__) && defined(CLOCK_MONOTONIC_RAW)
 #define PG_INSTR_CLOCK	CLOCK_MONOTONIC_RAW
+#define PG_INSTR_CLOCK_NAME	"clock_gettime (CLOCK_MONOTONIC_RAW)"
 #elif defined(CLOCK_MONOTONIC)
 #define PG_INSTR_CLOCK	CLOCK_MONOTONIC
+#define PG_INSTR_CLOCK_NAME	"clock_gettime (CLOCK_MONOTONIC)"
 #else
 #define PG_INSTR_CLOCK	CLOCK_REALTIME
+#define PG_INSTR_CLOCK_NAME	"clock_gettime (CLOCK_REALTIME)"
 #endif
 
 #if defined(__x86_64__) && defined(__linux__)
@@ -174,7 +177,7 @@ pg_get_ticks(void)
 }
 
 static inline int64_t
-pg_ticks_to_ns(instr_time t)
+pg_ticks_to_ns(int64 ticks)
 {
 	/*
 	 * Would multiplication overflow? If so perform computation in two parts.
@@ -183,7 +186,7 @@ pg_ticks_to_ns(instr_time t)
 	 */
 	int64		ns = 0;
 
-	if (unlikely(t.ticks > max_ticks_no_overflow))
+	if (unlikely(ticks > max_ticks_no_overflow))
 	{
 		/*
 		 * Compute how often the maximum number of ticks fits completely into
@@ -192,7 +195,7 @@ pg_ticks_to_ns(instr_time t)
 		 * value. In a 2nd step we adjust the number of elapsed ticks and
 		 * convert the remaining ticks.
 		 */
-		int64		count = t.ticks / max_ticks_no_overflow;
+		int64		count = ticks / max_ticks_no_overflow;
 		int64		max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION;
 
 		ns = max_ns * count;
@@ -201,11 +204,11 @@ pg_ticks_to_ns(instr_time t)
 		 * Subtract the ticks that we now already accounted for, so that they
 		 * don't get counted twice.
 		 */
-		t.ticks -= count * max_ticks_no_overflow;
-		Assert(t.ticks >= 0);
+		ticks -= count * max_ticks_no_overflow;
+		Assert(ticks >= 0);
 	}
 
-	ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION;
+	ns += ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION;
 	return ns;
 }
 
@@ -226,14 +229,14 @@ pg_initialize_get_ticks()
 #define INSTR_TIME_SET_CURRENT(t) \
 	((t) = pg_get_ticks())
 
-#define INSTR_TIME_GET_NANOSEC(t) \
-	pg_ticks_to_ns(t)
-
+#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \
+	(pg_ticks_to_ns(ticks))
 
 #else							/* WIN32 */
 
 
 /* Use QueryPerformanceCounter() */
+#define PG_INSTR_CLOCK_NAME	"QueryPerformanceCounter"
 
 /* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */
 static inline instr_time
@@ -265,8 +268,8 @@ GetTimerFrequency(void)
 #define INSTR_TIME_SET_CURRENT(t) \
 	((t) = pg_query_performance_counter())
 
-#define INSTR_TIME_GET_NANOSEC(t) \
-	((int64) ((t).ticks * ((double) NS_PER_S / GetTimerFrequency())))
+#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \
+	((int64) ((ticks) * ((double) NS_PER_S / GetTimerFrequency())))
 
 #endif							/* WIN32 */
 
@@ -285,9 +288,14 @@ GetTimerFrequency(void)
 #define INSTR_TIME_SUBTRACT(x,y) \
 	((x).ticks -= (y).ticks)
 
+#define INSTR_TIME_DIFF_NANOSEC(x,y) \
+	(INSTR_TIME_TICKS_TO_NANOSEC((x).ticks - (y).ticks))
+
 #define INSTR_TIME_ACCUM_DIFF(x,y,z) \
 	((x).ticks += (y).ticks - (z).ticks)
 
+#define INSTR_TIME_GET_NANOSEC(t) \
+	(INSTR_TIME_TICKS_TO_NANOSEC((t).ticks))
 
 #define INSTR_TIME_GET_DOUBLE(t) \
 	((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S)
-- 
2.47.3


--vtqqtrpooseurzip--





^ permalink  raw  reply  [nested|flat] 265+ messages in thread

* [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source
@ 2025-07-27 15:48  Lukas Fittl <[email protected]>
  0 siblings, 0 replies; 265+ messages in thread

From: Lukas Fittl @ 2025-07-27 15:48 UTC (permalink / raw)

In passing also reduce the per-loop overhead caused by repeated divisions
in INSTR_TIME_GET_NANOSEC when the ticks variable has become very large,
instead diff first and then turn it into nanosecs.
---
 src/bin/pg_test_timing/pg_test_timing.c | 59 +++++++++++++++++++------
 src/include/portability/instr_time.h    | 30 ++++++++-----
 2 files changed, 65 insertions(+), 24 deletions(-)

diff --git a/src/bin/pg_test_timing/pg_test_timing.c b/src/bin/pg_test_timing/pg_test_timing.c
index a5621251afc..b77ef2063b6 100644
--- a/src/bin/pg_test_timing/pg_test_timing.c
+++ b/src/bin/pg_test_timing/pg_test_timing.c
@@ -16,6 +16,7 @@ static const char *progname;
 
 static unsigned int test_duration = 3;
 static double max_rprct = 99.99;
+static bool fast_timing = false;
 
 /* record duration in powers of 2 nanoseconds */
 static long long int histogram[32];
@@ -56,6 +57,7 @@ handle_args(int argc, char *argv[])
 	static struct option long_options[] = {
 		{"duration", required_argument, NULL, 'd'},
 		{"cutoff", required_argument, NULL, 'c'},
+		{"fast", no_argument, NULL, 'f'},
 		{NULL, 0, NULL, 0}
 	};
 
@@ -68,7 +70,7 @@ handle_args(int argc, char *argv[])
 	{
 		if (strcmp(argv[1], "--help") == 0 || strcmp(argv[1], "-?") == 0)
 		{
-			printf(_("Usage: %s [-d DURATION] [-c CUTOFF]\n"), progname);
+			printf(_("Usage: %s [-d DURATION] [-c CUTOFF] [--fast]\n"), progname);
 			exit(0);
 		}
 		if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0)
@@ -78,7 +80,7 @@ handle_args(int argc, char *argv[])
 		}
 	}
 
-	while ((option = getopt_long(argc, argv, "d:c:",
+	while ((option = getopt_long(argc, argv, "d:c:f:",
 								 long_options, &optindex)) != -1)
 	{
 		switch (option)
@@ -125,6 +127,10 @@ handle_args(int argc, char *argv[])
 				}
 				break;
 
+			case 'f':
+				fast_timing = true;
+				break;
+
 			default:
 				fprintf(stderr, _("Try \"%s --help\" for more information.\n"),
 						progname);
@@ -155,11 +161,31 @@ test_timing(unsigned int duration)
 	uint64		total_time;
 	int64		time_elapsed = 0;
 	uint64		loop_count = 0;
-	uint64		prev,
-				cur;
 	instr_time	start_time,
 				end_time,
-				temp;
+				prev,
+				cur;
+	char	   *time_source = NULL;
+	bool		fast_timing_used = false;
+
+	INSTR_TIME_INITIALIZE();
+
+#if !defined(WIN32) && defined(__x86_64__) && defined(__linux__)
+	if (fast_timing && has_rdtsc)
+	{
+		time_source = "RDTSC";
+		fast_timing_used = true;
+	}
+	else if (has_rdtscp)
+		time_source = "RDTSCP";
+	else
+		time_source = PG_INSTR_CLOCK_NAME;
+#else
+	time_source = PG_INSTR_CLOCK_NAME;
+#endif
+	if (fast_timing && !fast_timing_used)
+		printf(_("Warning: Fast timing requested, but not available - regular timing source will be used\n"));
+	printf(_("Time source: %s\n"), time_source);
 
 	/*
 	 * Pre-zero the statistics data structures.  They're already zero by
@@ -173,8 +199,11 @@ test_timing(unsigned int duration)
 
 	total_time = duration > 0 ? duration * INT64CONST(1000000000) : 0;
 
-	INSTR_TIME_SET_CURRENT(start_time);
-	cur = INSTR_TIME_GET_NANOSEC(start_time);
+	if (fast_timing)
+		INSTR_TIME_SET_CURRENT_FAST(start_time);
+	else
+		INSTR_TIME_SET_CURRENT(start_time);
+	cur = start_time;
 
 	while (time_elapsed < total_time)
 	{
@@ -182,9 +211,11 @@ test_timing(unsigned int duration)
 					bits;
 
 		prev = cur;
-		INSTR_TIME_SET_CURRENT(temp);
-		cur = INSTR_TIME_GET_NANOSEC(temp);
-		diff = cur - prev;
+		if (fast_timing)
+			INSTR_TIME_SET_CURRENT_FAST(cur);
+		else
+			INSTR_TIME_SET_CURRENT(cur);
+		diff = INSTR_TIME_DIFF_NANOSEC(cur, prev);
 
 		/* Did time go backwards? */
 		if (unlikely(diff < 0))
@@ -217,11 +248,13 @@ test_timing(unsigned int duration)
 			largest_diff_count++;
 
 		loop_count++;
-		INSTR_TIME_SUBTRACT(temp, start_time);
-		time_elapsed = INSTR_TIME_GET_NANOSEC(temp);
+		time_elapsed = INSTR_TIME_DIFF_NANOSEC(cur, start_time);
 	}
 
-	INSTR_TIME_SET_CURRENT(end_time);
+	if (fast_timing)
+		INSTR_TIME_SET_CURRENT_FAST(end_time);
+	else
+		INSTR_TIME_SET_CURRENT(end_time);
 
 	INSTR_TIME_SUBTRACT(end_time, start_time);
 
diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h
index e2e339a0c4f..f02296f1026 100644
--- a/src/include/portability/instr_time.h
+++ b/src/include/portability/instr_time.h
@@ -112,10 +112,13 @@ extern int64 max_ticks_no_overflow;
  */
 #if defined(__darwin__) && defined(CLOCK_MONOTONIC_RAW)
 #define PG_INSTR_CLOCK	CLOCK_MONOTONIC_RAW
+#define PG_INSTR_CLOCK_NAME	"clock_gettime (CLOCK_MONOTONIC_RAW)"
 #elif defined(CLOCK_MONOTONIC)
 #define PG_INSTR_CLOCK	CLOCK_MONOTONIC
+#define PG_INSTR_CLOCK_NAME	"clock_gettime (CLOCK_MONOTONIC)"
 #else
 #define PG_INSTR_CLOCK	CLOCK_REALTIME
+#define PG_INSTR_CLOCK_NAME	"clock_gettime (CLOCK_REALTIME)"
 #endif
 
 #if defined(__x86_64__) && defined(__linux__)
@@ -174,7 +177,7 @@ pg_get_ticks(void)
 }
 
 static inline int64_t
-pg_ticks_to_ns(instr_time t)
+pg_ticks_to_ns(int64 ticks)
 {
 	/*
 	 * Would multiplication overflow? If so perform computation in two parts.
@@ -183,7 +186,7 @@ pg_ticks_to_ns(instr_time t)
 	 */
 	int64		ns = 0;
 
-	if (unlikely(t.ticks > max_ticks_no_overflow))
+	if (unlikely(ticks > max_ticks_no_overflow))
 	{
 		/*
 		 * Compute how often the maximum number of ticks fits completely into
@@ -192,7 +195,7 @@ pg_ticks_to_ns(instr_time t)
 		 * value. In a 2nd step we adjust the number of elapsed ticks and
 		 * convert the remaining ticks.
 		 */
-		int64		count = t.ticks / max_ticks_no_overflow;
+		int64		count = ticks / max_ticks_no_overflow;
 		int64		max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION;
 
 		ns = max_ns * count;
@@ -201,11 +204,11 @@ pg_ticks_to_ns(instr_time t)
 		 * Subtract the ticks that we now already accounted for, so that they
 		 * don't get counted twice.
 		 */
-		t.ticks -= count * max_ticks_no_overflow;
-		Assert(t.ticks >= 0);
+		ticks -= count * max_ticks_no_overflow;
+		Assert(ticks >= 0);
 	}
 
-	ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION;
+	ns += ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION;
 	return ns;
 }
 
@@ -226,14 +229,14 @@ pg_initialize_get_ticks()
 #define INSTR_TIME_SET_CURRENT(t) \
 	((t) = pg_get_ticks())
 
-#define INSTR_TIME_GET_NANOSEC(t) \
-	pg_ticks_to_ns(t)
-
+#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \
+	(pg_ticks_to_ns(ticks))
 
 #else							/* WIN32 */
 
 
 /* Use QueryPerformanceCounter() */
+#define PG_INSTR_CLOCK_NAME	"QueryPerformanceCounter"
 
 /* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */
 static inline instr_time
@@ -265,8 +268,8 @@ GetTimerFrequency(void)
 #define INSTR_TIME_SET_CURRENT(t) \
 	((t) = pg_query_performance_counter())
 
-#define INSTR_TIME_GET_NANOSEC(t) \
-	((int64) ((t).ticks * ((double) NS_PER_S / GetTimerFrequency())))
+#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \
+	((int64) ((ticks) * ((double) NS_PER_S / GetTimerFrequency())))
 
 #endif							/* WIN32 */
 
@@ -285,9 +288,14 @@ GetTimerFrequency(void)
 #define INSTR_TIME_SUBTRACT(x,y) \
 	((x).ticks -= (y).ticks)
 
+#define INSTR_TIME_DIFF_NANOSEC(x,y) \
+	(INSTR_TIME_TICKS_TO_NANOSEC((x).ticks - (y).ticks))
+
 #define INSTR_TIME_ACCUM_DIFF(x,y,z) \
 	((x).ticks += (y).ticks - (z).ticks)
 
+#define INSTR_TIME_GET_NANOSEC(t) \
+	(INSTR_TIME_TICKS_TO_NANOSEC((t).ticks))
 
 #define INSTR_TIME_GET_DOUBLE(t) \
 	((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S)
-- 
2.47.3


--vtqqtrpooseurzip--





^ permalink  raw  reply  [nested|flat] 265+ messages in thread

* [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source
@ 2025-07-27 15:48  Lukas Fittl <[email protected]>
  0 siblings, 0 replies; 265+ messages in thread

From: Lukas Fittl @ 2025-07-27 15:48 UTC (permalink / raw)

In passing also reduce the per-loop overhead caused by repeated divisions
in INSTR_TIME_GET_NANOSEC when the ticks variable has become very large,
instead diff first and then turn it into nanosecs.
---
 src/bin/pg_test_timing/pg_test_timing.c | 59 +++++++++++++++++++------
 src/include/portability/instr_time.h    | 30 ++++++++-----
 2 files changed, 65 insertions(+), 24 deletions(-)

diff --git a/src/bin/pg_test_timing/pg_test_timing.c b/src/bin/pg_test_timing/pg_test_timing.c
index a5621251afc..b77ef2063b6 100644
--- a/src/bin/pg_test_timing/pg_test_timing.c
+++ b/src/bin/pg_test_timing/pg_test_timing.c
@@ -16,6 +16,7 @@ static const char *progname;
 
 static unsigned int test_duration = 3;
 static double max_rprct = 99.99;
+static bool fast_timing = false;
 
 /* record duration in powers of 2 nanoseconds */
 static long long int histogram[32];
@@ -56,6 +57,7 @@ handle_args(int argc, char *argv[])
 	static struct option long_options[] = {
 		{"duration", required_argument, NULL, 'd'},
 		{"cutoff", required_argument, NULL, 'c'},
+		{"fast", no_argument, NULL, 'f'},
 		{NULL, 0, NULL, 0}
 	};
 
@@ -68,7 +70,7 @@ handle_args(int argc, char *argv[])
 	{
 		if (strcmp(argv[1], "--help") == 0 || strcmp(argv[1], "-?") == 0)
 		{
-			printf(_("Usage: %s [-d DURATION] [-c CUTOFF]\n"), progname);
+			printf(_("Usage: %s [-d DURATION] [-c CUTOFF] [--fast]\n"), progname);
 			exit(0);
 		}
 		if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0)
@@ -78,7 +80,7 @@ handle_args(int argc, char *argv[])
 		}
 	}
 
-	while ((option = getopt_long(argc, argv, "d:c:",
+	while ((option = getopt_long(argc, argv, "d:c:f:",
 								 long_options, &optindex)) != -1)
 	{
 		switch (option)
@@ -125,6 +127,10 @@ handle_args(int argc, char *argv[])
 				}
 				break;
 
+			case 'f':
+				fast_timing = true;
+				break;
+
 			default:
 				fprintf(stderr, _("Try \"%s --help\" for more information.\n"),
 						progname);
@@ -155,11 +161,31 @@ test_timing(unsigned int duration)
 	uint64		total_time;
 	int64		time_elapsed = 0;
 	uint64		loop_count = 0;
-	uint64		prev,
-				cur;
 	instr_time	start_time,
 				end_time,
-				temp;
+				prev,
+				cur;
+	char	   *time_source = NULL;
+	bool		fast_timing_used = false;
+
+	INSTR_TIME_INITIALIZE();
+
+#if !defined(WIN32) && defined(__x86_64__) && defined(__linux__)
+	if (fast_timing && has_rdtsc)
+	{
+		time_source = "RDTSC";
+		fast_timing_used = true;
+	}
+	else if (has_rdtscp)
+		time_source = "RDTSCP";
+	else
+		time_source = PG_INSTR_CLOCK_NAME;
+#else
+	time_source = PG_INSTR_CLOCK_NAME;
+#endif
+	if (fast_timing && !fast_timing_used)
+		printf(_("Warning: Fast timing requested, but not available - regular timing source will be used\n"));
+	printf(_("Time source: %s\n"), time_source);
 
 	/*
 	 * Pre-zero the statistics data structures.  They're already zero by
@@ -173,8 +199,11 @@ test_timing(unsigned int duration)
 
 	total_time = duration > 0 ? duration * INT64CONST(1000000000) : 0;
 
-	INSTR_TIME_SET_CURRENT(start_time);
-	cur = INSTR_TIME_GET_NANOSEC(start_time);
+	if (fast_timing)
+		INSTR_TIME_SET_CURRENT_FAST(start_time);
+	else
+		INSTR_TIME_SET_CURRENT(start_time);
+	cur = start_time;
 
 	while (time_elapsed < total_time)
 	{
@@ -182,9 +211,11 @@ test_timing(unsigned int duration)
 					bits;
 
 		prev = cur;
-		INSTR_TIME_SET_CURRENT(temp);
-		cur = INSTR_TIME_GET_NANOSEC(temp);
-		diff = cur - prev;
+		if (fast_timing)
+			INSTR_TIME_SET_CURRENT_FAST(cur);
+		else
+			INSTR_TIME_SET_CURRENT(cur);
+		diff = INSTR_TIME_DIFF_NANOSEC(cur, prev);
 
 		/* Did time go backwards? */
 		if (unlikely(diff < 0))
@@ -217,11 +248,13 @@ test_timing(unsigned int duration)
 			largest_diff_count++;
 
 		loop_count++;
-		INSTR_TIME_SUBTRACT(temp, start_time);
-		time_elapsed = INSTR_TIME_GET_NANOSEC(temp);
+		time_elapsed = INSTR_TIME_DIFF_NANOSEC(cur, start_time);
 	}
 
-	INSTR_TIME_SET_CURRENT(end_time);
+	if (fast_timing)
+		INSTR_TIME_SET_CURRENT_FAST(end_time);
+	else
+		INSTR_TIME_SET_CURRENT(end_time);
 
 	INSTR_TIME_SUBTRACT(end_time, start_time);
 
diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h
index e2e339a0c4f..f02296f1026 100644
--- a/src/include/portability/instr_time.h
+++ b/src/include/portability/instr_time.h
@@ -112,10 +112,13 @@ extern int64 max_ticks_no_overflow;
  */
 #if defined(__darwin__) && defined(CLOCK_MONOTONIC_RAW)
 #define PG_INSTR_CLOCK	CLOCK_MONOTONIC_RAW
+#define PG_INSTR_CLOCK_NAME	"clock_gettime (CLOCK_MONOTONIC_RAW)"
 #elif defined(CLOCK_MONOTONIC)
 #define PG_INSTR_CLOCK	CLOCK_MONOTONIC
+#define PG_INSTR_CLOCK_NAME	"clock_gettime (CLOCK_MONOTONIC)"
 #else
 #define PG_INSTR_CLOCK	CLOCK_REALTIME
+#define PG_INSTR_CLOCK_NAME	"clock_gettime (CLOCK_REALTIME)"
 #endif
 
 #if defined(__x86_64__) && defined(__linux__)
@@ -174,7 +177,7 @@ pg_get_ticks(void)
 }
 
 static inline int64_t
-pg_ticks_to_ns(instr_time t)
+pg_ticks_to_ns(int64 ticks)
 {
 	/*
 	 * Would multiplication overflow? If so perform computation in two parts.
@@ -183,7 +186,7 @@ pg_ticks_to_ns(instr_time t)
 	 */
 	int64		ns = 0;
 
-	if (unlikely(t.ticks > max_ticks_no_overflow))
+	if (unlikely(ticks > max_ticks_no_overflow))
 	{
 		/*
 		 * Compute how often the maximum number of ticks fits completely into
@@ -192,7 +195,7 @@ pg_ticks_to_ns(instr_time t)
 		 * value. In a 2nd step we adjust the number of elapsed ticks and
 		 * convert the remaining ticks.
 		 */
-		int64		count = t.ticks / max_ticks_no_overflow;
+		int64		count = ticks / max_ticks_no_overflow;
 		int64		max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION;
 
 		ns = max_ns * count;
@@ -201,11 +204,11 @@ pg_ticks_to_ns(instr_time t)
 		 * Subtract the ticks that we now already accounted for, so that they
 		 * don't get counted twice.
 		 */
-		t.ticks -= count * max_ticks_no_overflow;
-		Assert(t.ticks >= 0);
+		ticks -= count * max_ticks_no_overflow;
+		Assert(ticks >= 0);
 	}
 
-	ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION;
+	ns += ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION;
 	return ns;
 }
 
@@ -226,14 +229,14 @@ pg_initialize_get_ticks()
 #define INSTR_TIME_SET_CURRENT(t) \
 	((t) = pg_get_ticks())
 
-#define INSTR_TIME_GET_NANOSEC(t) \
-	pg_ticks_to_ns(t)
-
+#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \
+	(pg_ticks_to_ns(ticks))
 
 #else							/* WIN32 */
 
 
 /* Use QueryPerformanceCounter() */
+#define PG_INSTR_CLOCK_NAME	"QueryPerformanceCounter"
 
 /* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */
 static inline instr_time
@@ -265,8 +268,8 @@ GetTimerFrequency(void)
 #define INSTR_TIME_SET_CURRENT(t) \
 	((t) = pg_query_performance_counter())
 
-#define INSTR_TIME_GET_NANOSEC(t) \
-	((int64) ((t).ticks * ((double) NS_PER_S / GetTimerFrequency())))
+#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \
+	((int64) ((ticks) * ((double) NS_PER_S / GetTimerFrequency())))
 
 #endif							/* WIN32 */
 
@@ -285,9 +288,14 @@ GetTimerFrequency(void)
 #define INSTR_TIME_SUBTRACT(x,y) \
 	((x).ticks -= (y).ticks)
 
+#define INSTR_TIME_DIFF_NANOSEC(x,y) \
+	(INSTR_TIME_TICKS_TO_NANOSEC((x).ticks - (y).ticks))
+
 #define INSTR_TIME_ACCUM_DIFF(x,y,z) \
 	((x).ticks += (y).ticks - (z).ticks)
 
+#define INSTR_TIME_GET_NANOSEC(t) \
+	(INSTR_TIME_TICKS_TO_NANOSEC((t).ticks))
 
 #define INSTR_TIME_GET_DOUBLE(t) \
 	((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S)
-- 
2.47.3


--vtqqtrpooseurzip--





^ permalink  raw  reply  [nested|flat] 265+ messages in thread

* [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source
@ 2025-07-27 15:48  Lukas Fittl <[email protected]>
  0 siblings, 0 replies; 265+ messages in thread

From: Lukas Fittl @ 2025-07-27 15:48 UTC (permalink / raw)

In passing also reduce the per-loop overhead caused by repeated divisions
in INSTR_TIME_GET_NANOSEC when the ticks variable has become very large,
instead diff first and then turn it into nanosecs.
---
 src/bin/pg_test_timing/pg_test_timing.c | 59 +++++++++++++++++++------
 src/include/portability/instr_time.h    | 30 ++++++++-----
 2 files changed, 65 insertions(+), 24 deletions(-)

diff --git a/src/bin/pg_test_timing/pg_test_timing.c b/src/bin/pg_test_timing/pg_test_timing.c
index a5621251afc..b77ef2063b6 100644
--- a/src/bin/pg_test_timing/pg_test_timing.c
+++ b/src/bin/pg_test_timing/pg_test_timing.c
@@ -16,6 +16,7 @@ static const char *progname;
 
 static unsigned int test_duration = 3;
 static double max_rprct = 99.99;
+static bool fast_timing = false;
 
 /* record duration in powers of 2 nanoseconds */
 static long long int histogram[32];
@@ -56,6 +57,7 @@ handle_args(int argc, char *argv[])
 	static struct option long_options[] = {
 		{"duration", required_argument, NULL, 'd'},
 		{"cutoff", required_argument, NULL, 'c'},
+		{"fast", no_argument, NULL, 'f'},
 		{NULL, 0, NULL, 0}
 	};
 
@@ -68,7 +70,7 @@ handle_args(int argc, char *argv[])
 	{
 		if (strcmp(argv[1], "--help") == 0 || strcmp(argv[1], "-?") == 0)
 		{
-			printf(_("Usage: %s [-d DURATION] [-c CUTOFF]\n"), progname);
+			printf(_("Usage: %s [-d DURATION] [-c CUTOFF] [--fast]\n"), progname);
 			exit(0);
 		}
 		if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0)
@@ -78,7 +80,7 @@ handle_args(int argc, char *argv[])
 		}
 	}
 
-	while ((option = getopt_long(argc, argv, "d:c:",
+	while ((option = getopt_long(argc, argv, "d:c:f:",
 								 long_options, &optindex)) != -1)
 	{
 		switch (option)
@@ -125,6 +127,10 @@ handle_args(int argc, char *argv[])
 				}
 				break;
 
+			case 'f':
+				fast_timing = true;
+				break;
+
 			default:
 				fprintf(stderr, _("Try \"%s --help\" for more information.\n"),
 						progname);
@@ -155,11 +161,31 @@ test_timing(unsigned int duration)
 	uint64		total_time;
 	int64		time_elapsed = 0;
 	uint64		loop_count = 0;
-	uint64		prev,
-				cur;
 	instr_time	start_time,
 				end_time,
-				temp;
+				prev,
+				cur;
+	char	   *time_source = NULL;
+	bool		fast_timing_used = false;
+
+	INSTR_TIME_INITIALIZE();
+
+#if !defined(WIN32) && defined(__x86_64__) && defined(__linux__)
+	if (fast_timing && has_rdtsc)
+	{
+		time_source = "RDTSC";
+		fast_timing_used = true;
+	}
+	else if (has_rdtscp)
+		time_source = "RDTSCP";
+	else
+		time_source = PG_INSTR_CLOCK_NAME;
+#else
+	time_source = PG_INSTR_CLOCK_NAME;
+#endif
+	if (fast_timing && !fast_timing_used)
+		printf(_("Warning: Fast timing requested, but not available - regular timing source will be used\n"));
+	printf(_("Time source: %s\n"), time_source);
 
 	/*
 	 * Pre-zero the statistics data structures.  They're already zero by
@@ -173,8 +199,11 @@ test_timing(unsigned int duration)
 
 	total_time = duration > 0 ? duration * INT64CONST(1000000000) : 0;
 
-	INSTR_TIME_SET_CURRENT(start_time);
-	cur = INSTR_TIME_GET_NANOSEC(start_time);
+	if (fast_timing)
+		INSTR_TIME_SET_CURRENT_FAST(start_time);
+	else
+		INSTR_TIME_SET_CURRENT(start_time);
+	cur = start_time;
 
 	while (time_elapsed < total_time)
 	{
@@ -182,9 +211,11 @@ test_timing(unsigned int duration)
 					bits;
 
 		prev = cur;
-		INSTR_TIME_SET_CURRENT(temp);
-		cur = INSTR_TIME_GET_NANOSEC(temp);
-		diff = cur - prev;
+		if (fast_timing)
+			INSTR_TIME_SET_CURRENT_FAST(cur);
+		else
+			INSTR_TIME_SET_CURRENT(cur);
+		diff = INSTR_TIME_DIFF_NANOSEC(cur, prev);
 
 		/* Did time go backwards? */
 		if (unlikely(diff < 0))
@@ -217,11 +248,13 @@ test_timing(unsigned int duration)
 			largest_diff_count++;
 
 		loop_count++;
-		INSTR_TIME_SUBTRACT(temp, start_time);
-		time_elapsed = INSTR_TIME_GET_NANOSEC(temp);
+		time_elapsed = INSTR_TIME_DIFF_NANOSEC(cur, start_time);
 	}
 
-	INSTR_TIME_SET_CURRENT(end_time);
+	if (fast_timing)
+		INSTR_TIME_SET_CURRENT_FAST(end_time);
+	else
+		INSTR_TIME_SET_CURRENT(end_time);
 
 	INSTR_TIME_SUBTRACT(end_time, start_time);
 
diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h
index e2e339a0c4f..f02296f1026 100644
--- a/src/include/portability/instr_time.h
+++ b/src/include/portability/instr_time.h
@@ -112,10 +112,13 @@ extern int64 max_ticks_no_overflow;
  */
 #if defined(__darwin__) && defined(CLOCK_MONOTONIC_RAW)
 #define PG_INSTR_CLOCK	CLOCK_MONOTONIC_RAW
+#define PG_INSTR_CLOCK_NAME	"clock_gettime (CLOCK_MONOTONIC_RAW)"
 #elif defined(CLOCK_MONOTONIC)
 #define PG_INSTR_CLOCK	CLOCK_MONOTONIC
+#define PG_INSTR_CLOCK_NAME	"clock_gettime (CLOCK_MONOTONIC)"
 #else
 #define PG_INSTR_CLOCK	CLOCK_REALTIME
+#define PG_INSTR_CLOCK_NAME	"clock_gettime (CLOCK_REALTIME)"
 #endif
 
 #if defined(__x86_64__) && defined(__linux__)
@@ -174,7 +177,7 @@ pg_get_ticks(void)
 }
 
 static inline int64_t
-pg_ticks_to_ns(instr_time t)
+pg_ticks_to_ns(int64 ticks)
 {
 	/*
 	 * Would multiplication overflow? If so perform computation in two parts.
@@ -183,7 +186,7 @@ pg_ticks_to_ns(instr_time t)
 	 */
 	int64		ns = 0;
 
-	if (unlikely(t.ticks > max_ticks_no_overflow))
+	if (unlikely(ticks > max_ticks_no_overflow))
 	{
 		/*
 		 * Compute how often the maximum number of ticks fits completely into
@@ -192,7 +195,7 @@ pg_ticks_to_ns(instr_time t)
 		 * value. In a 2nd step we adjust the number of elapsed ticks and
 		 * convert the remaining ticks.
 		 */
-		int64		count = t.ticks / max_ticks_no_overflow;
+		int64		count = ticks / max_ticks_no_overflow;
 		int64		max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION;
 
 		ns = max_ns * count;
@@ -201,11 +204,11 @@ pg_ticks_to_ns(instr_time t)
 		 * Subtract the ticks that we now already accounted for, so that they
 		 * don't get counted twice.
 		 */
-		t.ticks -= count * max_ticks_no_overflow;
-		Assert(t.ticks >= 0);
+		ticks -= count * max_ticks_no_overflow;
+		Assert(ticks >= 0);
 	}
 
-	ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION;
+	ns += ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION;
 	return ns;
 }
 
@@ -226,14 +229,14 @@ pg_initialize_get_ticks()
 #define INSTR_TIME_SET_CURRENT(t) \
 	((t) = pg_get_ticks())
 
-#define INSTR_TIME_GET_NANOSEC(t) \
-	pg_ticks_to_ns(t)
-
+#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \
+	(pg_ticks_to_ns(ticks))
 
 #else							/* WIN32 */
 
 
 /* Use QueryPerformanceCounter() */
+#define PG_INSTR_CLOCK_NAME	"QueryPerformanceCounter"
 
 /* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */
 static inline instr_time
@@ -265,8 +268,8 @@ GetTimerFrequency(void)
 #define INSTR_TIME_SET_CURRENT(t) \
 	((t) = pg_query_performance_counter())
 
-#define INSTR_TIME_GET_NANOSEC(t) \
-	((int64) ((t).ticks * ((double) NS_PER_S / GetTimerFrequency())))
+#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \
+	((int64) ((ticks) * ((double) NS_PER_S / GetTimerFrequency())))
 
 #endif							/* WIN32 */
 
@@ -285,9 +288,14 @@ GetTimerFrequency(void)
 #define INSTR_TIME_SUBTRACT(x,y) \
 	((x).ticks -= (y).ticks)
 
+#define INSTR_TIME_DIFF_NANOSEC(x,y) \
+	(INSTR_TIME_TICKS_TO_NANOSEC((x).ticks - (y).ticks))
+
 #define INSTR_TIME_ACCUM_DIFF(x,y,z) \
 	((x).ticks += (y).ticks - (z).ticks)
 
+#define INSTR_TIME_GET_NANOSEC(t) \
+	(INSTR_TIME_TICKS_TO_NANOSEC((t).ticks))
 
 #define INSTR_TIME_GET_DOUBLE(t) \
 	((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S)
-- 
2.47.3


--vtqqtrpooseurzip--





^ permalink  raw  reply  [nested|flat] 265+ messages in thread

* [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source
@ 2025-07-27 15:48  Lukas Fittl <[email protected]>
  0 siblings, 0 replies; 265+ messages in thread

From: Lukas Fittl @ 2025-07-27 15:48 UTC (permalink / raw)

In passing also reduce the per-loop overhead caused by repeated divisions
in INSTR_TIME_GET_NANOSEC when the ticks variable has become very large,
instead diff first and then turn it into nanosecs.
---
 src/bin/pg_test_timing/pg_test_timing.c | 59 +++++++++++++++++++------
 src/include/portability/instr_time.h    | 30 ++++++++-----
 2 files changed, 65 insertions(+), 24 deletions(-)

diff --git a/src/bin/pg_test_timing/pg_test_timing.c b/src/bin/pg_test_timing/pg_test_timing.c
index a5621251afc..b77ef2063b6 100644
--- a/src/bin/pg_test_timing/pg_test_timing.c
+++ b/src/bin/pg_test_timing/pg_test_timing.c
@@ -16,6 +16,7 @@ static const char *progname;
 
 static unsigned int test_duration = 3;
 static double max_rprct = 99.99;
+static bool fast_timing = false;
 
 /* record duration in powers of 2 nanoseconds */
 static long long int histogram[32];
@@ -56,6 +57,7 @@ handle_args(int argc, char *argv[])
 	static struct option long_options[] = {
 		{"duration", required_argument, NULL, 'd'},
 		{"cutoff", required_argument, NULL, 'c'},
+		{"fast", no_argument, NULL, 'f'},
 		{NULL, 0, NULL, 0}
 	};
 
@@ -68,7 +70,7 @@ handle_args(int argc, char *argv[])
 	{
 		if (strcmp(argv[1], "--help") == 0 || strcmp(argv[1], "-?") == 0)
 		{
-			printf(_("Usage: %s [-d DURATION] [-c CUTOFF]\n"), progname);
+			printf(_("Usage: %s [-d DURATION] [-c CUTOFF] [--fast]\n"), progname);
 			exit(0);
 		}
 		if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0)
@@ -78,7 +80,7 @@ handle_args(int argc, char *argv[])
 		}
 	}
 
-	while ((option = getopt_long(argc, argv, "d:c:",
+	while ((option = getopt_long(argc, argv, "d:c:f:",
 								 long_options, &optindex)) != -1)
 	{
 		switch (option)
@@ -125,6 +127,10 @@ handle_args(int argc, char *argv[])
 				}
 				break;
 
+			case 'f':
+				fast_timing = true;
+				break;
+
 			default:
 				fprintf(stderr, _("Try \"%s --help\" for more information.\n"),
 						progname);
@@ -155,11 +161,31 @@ test_timing(unsigned int duration)
 	uint64		total_time;
 	int64		time_elapsed = 0;
 	uint64		loop_count = 0;
-	uint64		prev,
-				cur;
 	instr_time	start_time,
 				end_time,
-				temp;
+				prev,
+				cur;
+	char	   *time_source = NULL;
+	bool		fast_timing_used = false;
+
+	INSTR_TIME_INITIALIZE();
+
+#if !defined(WIN32) && defined(__x86_64__) && defined(__linux__)
+	if (fast_timing && has_rdtsc)
+	{
+		time_source = "RDTSC";
+		fast_timing_used = true;
+	}
+	else if (has_rdtscp)
+		time_source = "RDTSCP";
+	else
+		time_source = PG_INSTR_CLOCK_NAME;
+#else
+	time_source = PG_INSTR_CLOCK_NAME;
+#endif
+	if (fast_timing && !fast_timing_used)
+		printf(_("Warning: Fast timing requested, but not available - regular timing source will be used\n"));
+	printf(_("Time source: %s\n"), time_source);
 
 	/*
 	 * Pre-zero the statistics data structures.  They're already zero by
@@ -173,8 +199,11 @@ test_timing(unsigned int duration)
 
 	total_time = duration > 0 ? duration * INT64CONST(1000000000) : 0;
 
-	INSTR_TIME_SET_CURRENT(start_time);
-	cur = INSTR_TIME_GET_NANOSEC(start_time);
+	if (fast_timing)
+		INSTR_TIME_SET_CURRENT_FAST(start_time);
+	else
+		INSTR_TIME_SET_CURRENT(start_time);
+	cur = start_time;
 
 	while (time_elapsed < total_time)
 	{
@@ -182,9 +211,11 @@ test_timing(unsigned int duration)
 					bits;
 
 		prev = cur;
-		INSTR_TIME_SET_CURRENT(temp);
-		cur = INSTR_TIME_GET_NANOSEC(temp);
-		diff = cur - prev;
+		if (fast_timing)
+			INSTR_TIME_SET_CURRENT_FAST(cur);
+		else
+			INSTR_TIME_SET_CURRENT(cur);
+		diff = INSTR_TIME_DIFF_NANOSEC(cur, prev);
 
 		/* Did time go backwards? */
 		if (unlikely(diff < 0))
@@ -217,11 +248,13 @@ test_timing(unsigned int duration)
 			largest_diff_count++;
 
 		loop_count++;
-		INSTR_TIME_SUBTRACT(temp, start_time);
-		time_elapsed = INSTR_TIME_GET_NANOSEC(temp);
+		time_elapsed = INSTR_TIME_DIFF_NANOSEC(cur, start_time);
 	}
 
-	INSTR_TIME_SET_CURRENT(end_time);
+	if (fast_timing)
+		INSTR_TIME_SET_CURRENT_FAST(end_time);
+	else
+		INSTR_TIME_SET_CURRENT(end_time);
 
 	INSTR_TIME_SUBTRACT(end_time, start_time);
 
diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h
index e2e339a0c4f..f02296f1026 100644
--- a/src/include/portability/instr_time.h
+++ b/src/include/portability/instr_time.h
@@ -112,10 +112,13 @@ extern int64 max_ticks_no_overflow;
  */
 #if defined(__darwin__) && defined(CLOCK_MONOTONIC_RAW)
 #define PG_INSTR_CLOCK	CLOCK_MONOTONIC_RAW
+#define PG_INSTR_CLOCK_NAME	"clock_gettime (CLOCK_MONOTONIC_RAW)"
 #elif defined(CLOCK_MONOTONIC)
 #define PG_INSTR_CLOCK	CLOCK_MONOTONIC
+#define PG_INSTR_CLOCK_NAME	"clock_gettime (CLOCK_MONOTONIC)"
 #else
 #define PG_INSTR_CLOCK	CLOCK_REALTIME
+#define PG_INSTR_CLOCK_NAME	"clock_gettime (CLOCK_REALTIME)"
 #endif
 
 #if defined(__x86_64__) && defined(__linux__)
@@ -174,7 +177,7 @@ pg_get_ticks(void)
 }
 
 static inline int64_t
-pg_ticks_to_ns(instr_time t)
+pg_ticks_to_ns(int64 ticks)
 {
 	/*
 	 * Would multiplication overflow? If so perform computation in two parts.
@@ -183,7 +186,7 @@ pg_ticks_to_ns(instr_time t)
 	 */
 	int64		ns = 0;
 
-	if (unlikely(t.ticks > max_ticks_no_overflow))
+	if (unlikely(ticks > max_ticks_no_overflow))
 	{
 		/*
 		 * Compute how often the maximum number of ticks fits completely into
@@ -192,7 +195,7 @@ pg_ticks_to_ns(instr_time t)
 		 * value. In a 2nd step we adjust the number of elapsed ticks and
 		 * convert the remaining ticks.
 		 */
-		int64		count = t.ticks / max_ticks_no_overflow;
+		int64		count = ticks / max_ticks_no_overflow;
 		int64		max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION;
 
 		ns = max_ns * count;
@@ -201,11 +204,11 @@ pg_ticks_to_ns(instr_time t)
 		 * Subtract the ticks that we now already accounted for, so that they
 		 * don't get counted twice.
 		 */
-		t.ticks -= count * max_ticks_no_overflow;
-		Assert(t.ticks >= 0);
+		ticks -= count * max_ticks_no_overflow;
+		Assert(ticks >= 0);
 	}
 
-	ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION;
+	ns += ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION;
 	return ns;
 }
 
@@ -226,14 +229,14 @@ pg_initialize_get_ticks()
 #define INSTR_TIME_SET_CURRENT(t) \
 	((t) = pg_get_ticks())
 
-#define INSTR_TIME_GET_NANOSEC(t) \
-	pg_ticks_to_ns(t)
-
+#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \
+	(pg_ticks_to_ns(ticks))
 
 #else							/* WIN32 */
 
 
 /* Use QueryPerformanceCounter() */
+#define PG_INSTR_CLOCK_NAME	"QueryPerformanceCounter"
 
 /* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */
 static inline instr_time
@@ -265,8 +268,8 @@ GetTimerFrequency(void)
 #define INSTR_TIME_SET_CURRENT(t) \
 	((t) = pg_query_performance_counter())
 
-#define INSTR_TIME_GET_NANOSEC(t) \
-	((int64) ((t).ticks * ((double) NS_PER_S / GetTimerFrequency())))
+#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \
+	((int64) ((ticks) * ((double) NS_PER_S / GetTimerFrequency())))
 
 #endif							/* WIN32 */
 
@@ -285,9 +288,14 @@ GetTimerFrequency(void)
 #define INSTR_TIME_SUBTRACT(x,y) \
 	((x).ticks -= (y).ticks)
 
+#define INSTR_TIME_DIFF_NANOSEC(x,y) \
+	(INSTR_TIME_TICKS_TO_NANOSEC((x).ticks - (y).ticks))
+
 #define INSTR_TIME_ACCUM_DIFF(x,y,z) \
 	((x).ticks += (y).ticks - (z).ticks)
 
+#define INSTR_TIME_GET_NANOSEC(t) \
+	(INSTR_TIME_TICKS_TO_NANOSEC((t).ticks))
 
 #define INSTR_TIME_GET_DOUBLE(t) \
 	((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S)
-- 
2.47.3


--vtqqtrpooseurzip--





^ permalink  raw  reply  [nested|flat] 265+ messages in thread

* [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source
@ 2025-07-27 15:48  Lukas Fittl <[email protected]>
  0 siblings, 0 replies; 265+ messages in thread

From: Lukas Fittl @ 2025-07-27 15:48 UTC (permalink / raw)

In passing also reduce the per-loop overhead caused by repeated divisions
in INSTR_TIME_GET_NANOSEC when the ticks variable has become very large,
instead diff first and then turn it into nanosecs.
---
 src/bin/pg_test_timing/pg_test_timing.c | 59 +++++++++++++++++++------
 src/include/portability/instr_time.h    | 30 ++++++++-----
 2 files changed, 65 insertions(+), 24 deletions(-)

diff --git a/src/bin/pg_test_timing/pg_test_timing.c b/src/bin/pg_test_timing/pg_test_timing.c
index a5621251afc..b77ef2063b6 100644
--- a/src/bin/pg_test_timing/pg_test_timing.c
+++ b/src/bin/pg_test_timing/pg_test_timing.c
@@ -16,6 +16,7 @@ static const char *progname;
 
 static unsigned int test_duration = 3;
 static double max_rprct = 99.99;
+static bool fast_timing = false;
 
 /* record duration in powers of 2 nanoseconds */
 static long long int histogram[32];
@@ -56,6 +57,7 @@ handle_args(int argc, char *argv[])
 	static struct option long_options[] = {
 		{"duration", required_argument, NULL, 'd'},
 		{"cutoff", required_argument, NULL, 'c'},
+		{"fast", no_argument, NULL, 'f'},
 		{NULL, 0, NULL, 0}
 	};
 
@@ -68,7 +70,7 @@ handle_args(int argc, char *argv[])
 	{
 		if (strcmp(argv[1], "--help") == 0 || strcmp(argv[1], "-?") == 0)
 		{
-			printf(_("Usage: %s [-d DURATION] [-c CUTOFF]\n"), progname);
+			printf(_("Usage: %s [-d DURATION] [-c CUTOFF] [--fast]\n"), progname);
 			exit(0);
 		}
 		if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0)
@@ -78,7 +80,7 @@ handle_args(int argc, char *argv[])
 		}
 	}
 
-	while ((option = getopt_long(argc, argv, "d:c:",
+	while ((option = getopt_long(argc, argv, "d:c:f:",
 								 long_options, &optindex)) != -1)
 	{
 		switch (option)
@@ -125,6 +127,10 @@ handle_args(int argc, char *argv[])
 				}
 				break;
 
+			case 'f':
+				fast_timing = true;
+				break;
+
 			default:
 				fprintf(stderr, _("Try \"%s --help\" for more information.\n"),
 						progname);
@@ -155,11 +161,31 @@ test_timing(unsigned int duration)
 	uint64		total_time;
 	int64		time_elapsed = 0;
 	uint64		loop_count = 0;
-	uint64		prev,
-				cur;
 	instr_time	start_time,
 				end_time,
-				temp;
+				prev,
+				cur;
+	char	   *time_source = NULL;
+	bool		fast_timing_used = false;
+
+	INSTR_TIME_INITIALIZE();
+
+#if !defined(WIN32) && defined(__x86_64__) && defined(__linux__)
+	if (fast_timing && has_rdtsc)
+	{
+		time_source = "RDTSC";
+		fast_timing_used = true;
+	}
+	else if (has_rdtscp)
+		time_source = "RDTSCP";
+	else
+		time_source = PG_INSTR_CLOCK_NAME;
+#else
+	time_source = PG_INSTR_CLOCK_NAME;
+#endif
+	if (fast_timing && !fast_timing_used)
+		printf(_("Warning: Fast timing requested, but not available - regular timing source will be used\n"));
+	printf(_("Time source: %s\n"), time_source);
 
 	/*
 	 * Pre-zero the statistics data structures.  They're already zero by
@@ -173,8 +199,11 @@ test_timing(unsigned int duration)
 
 	total_time = duration > 0 ? duration * INT64CONST(1000000000) : 0;
 
-	INSTR_TIME_SET_CURRENT(start_time);
-	cur = INSTR_TIME_GET_NANOSEC(start_time);
+	if (fast_timing)
+		INSTR_TIME_SET_CURRENT_FAST(start_time);
+	else
+		INSTR_TIME_SET_CURRENT(start_time);
+	cur = start_time;
 
 	while (time_elapsed < total_time)
 	{
@@ -182,9 +211,11 @@ test_timing(unsigned int duration)
 					bits;
 
 		prev = cur;
-		INSTR_TIME_SET_CURRENT(temp);
-		cur = INSTR_TIME_GET_NANOSEC(temp);
-		diff = cur - prev;
+		if (fast_timing)
+			INSTR_TIME_SET_CURRENT_FAST(cur);
+		else
+			INSTR_TIME_SET_CURRENT(cur);
+		diff = INSTR_TIME_DIFF_NANOSEC(cur, prev);
 
 		/* Did time go backwards? */
 		if (unlikely(diff < 0))
@@ -217,11 +248,13 @@ test_timing(unsigned int duration)
 			largest_diff_count++;
 
 		loop_count++;
-		INSTR_TIME_SUBTRACT(temp, start_time);
-		time_elapsed = INSTR_TIME_GET_NANOSEC(temp);
+		time_elapsed = INSTR_TIME_DIFF_NANOSEC(cur, start_time);
 	}
 
-	INSTR_TIME_SET_CURRENT(end_time);
+	if (fast_timing)
+		INSTR_TIME_SET_CURRENT_FAST(end_time);
+	else
+		INSTR_TIME_SET_CURRENT(end_time);
 
 	INSTR_TIME_SUBTRACT(end_time, start_time);
 
diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h
index e2e339a0c4f..f02296f1026 100644
--- a/src/include/portability/instr_time.h
+++ b/src/include/portability/instr_time.h
@@ -112,10 +112,13 @@ extern int64 max_ticks_no_overflow;
  */
 #if defined(__darwin__) && defined(CLOCK_MONOTONIC_RAW)
 #define PG_INSTR_CLOCK	CLOCK_MONOTONIC_RAW
+#define PG_INSTR_CLOCK_NAME	"clock_gettime (CLOCK_MONOTONIC_RAW)"
 #elif defined(CLOCK_MONOTONIC)
 #define PG_INSTR_CLOCK	CLOCK_MONOTONIC
+#define PG_INSTR_CLOCK_NAME	"clock_gettime (CLOCK_MONOTONIC)"
 #else
 #define PG_INSTR_CLOCK	CLOCK_REALTIME
+#define PG_INSTR_CLOCK_NAME	"clock_gettime (CLOCK_REALTIME)"
 #endif
 
 #if defined(__x86_64__) && defined(__linux__)
@@ -174,7 +177,7 @@ pg_get_ticks(void)
 }
 
 static inline int64_t
-pg_ticks_to_ns(instr_time t)
+pg_ticks_to_ns(int64 ticks)
 {
 	/*
 	 * Would multiplication overflow? If so perform computation in two parts.
@@ -183,7 +186,7 @@ pg_ticks_to_ns(instr_time t)
 	 */
 	int64		ns = 0;
 
-	if (unlikely(t.ticks > max_ticks_no_overflow))
+	if (unlikely(ticks > max_ticks_no_overflow))
 	{
 		/*
 		 * Compute how often the maximum number of ticks fits completely into
@@ -192,7 +195,7 @@ pg_ticks_to_ns(instr_time t)
 		 * value. In a 2nd step we adjust the number of elapsed ticks and
 		 * convert the remaining ticks.
 		 */
-		int64		count = t.ticks / max_ticks_no_overflow;
+		int64		count = ticks / max_ticks_no_overflow;
 		int64		max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION;
 
 		ns = max_ns * count;
@@ -201,11 +204,11 @@ pg_ticks_to_ns(instr_time t)
 		 * Subtract the ticks that we now already accounted for, so that they
 		 * don't get counted twice.
 		 */
-		t.ticks -= count * max_ticks_no_overflow;
-		Assert(t.ticks >= 0);
+		ticks -= count * max_ticks_no_overflow;
+		Assert(ticks >= 0);
 	}
 
-	ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION;
+	ns += ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION;
 	return ns;
 }
 
@@ -226,14 +229,14 @@ pg_initialize_get_ticks()
 #define INSTR_TIME_SET_CURRENT(t) \
 	((t) = pg_get_ticks())
 
-#define INSTR_TIME_GET_NANOSEC(t) \
-	pg_ticks_to_ns(t)
-
+#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \
+	(pg_ticks_to_ns(ticks))
 
 #else							/* WIN32 */
 
 
 /* Use QueryPerformanceCounter() */
+#define PG_INSTR_CLOCK_NAME	"QueryPerformanceCounter"
 
 /* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */
 static inline instr_time
@@ -265,8 +268,8 @@ GetTimerFrequency(void)
 #define INSTR_TIME_SET_CURRENT(t) \
 	((t) = pg_query_performance_counter())
 
-#define INSTR_TIME_GET_NANOSEC(t) \
-	((int64) ((t).ticks * ((double) NS_PER_S / GetTimerFrequency())))
+#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \
+	((int64) ((ticks) * ((double) NS_PER_S / GetTimerFrequency())))
 
 #endif							/* WIN32 */
 
@@ -285,9 +288,14 @@ GetTimerFrequency(void)
 #define INSTR_TIME_SUBTRACT(x,y) \
 	((x).ticks -= (y).ticks)
 
+#define INSTR_TIME_DIFF_NANOSEC(x,y) \
+	(INSTR_TIME_TICKS_TO_NANOSEC((x).ticks - (y).ticks))
+
 #define INSTR_TIME_ACCUM_DIFF(x,y,z) \
 	((x).ticks += (y).ticks - (z).ticks)
 
+#define INSTR_TIME_GET_NANOSEC(t) \
+	(INSTR_TIME_TICKS_TO_NANOSEC((t).ticks))
 
 #define INSTR_TIME_GET_DOUBLE(t) \
 	((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S)
-- 
2.47.3


--vtqqtrpooseurzip--





^ permalink  raw  reply  [nested|flat] 265+ messages in thread

* [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source
@ 2025-07-27 15:48  Lukas Fittl <[email protected]>
  0 siblings, 0 replies; 265+ messages in thread

From: Lukas Fittl @ 2025-07-27 15:48 UTC (permalink / raw)

In passing also reduce the per-loop overhead caused by repeated divisions
in INSTR_TIME_GET_NANOSEC when the ticks variable has become very large,
instead diff first and then turn it into nanosecs.
---
 src/bin/pg_test_timing/pg_test_timing.c | 59 +++++++++++++++++++------
 src/include/portability/instr_time.h    | 30 ++++++++-----
 2 files changed, 65 insertions(+), 24 deletions(-)

diff --git a/src/bin/pg_test_timing/pg_test_timing.c b/src/bin/pg_test_timing/pg_test_timing.c
index a5621251afc..b77ef2063b6 100644
--- a/src/bin/pg_test_timing/pg_test_timing.c
+++ b/src/bin/pg_test_timing/pg_test_timing.c
@@ -16,6 +16,7 @@ static const char *progname;
 
 static unsigned int test_duration = 3;
 static double max_rprct = 99.99;
+static bool fast_timing = false;
 
 /* record duration in powers of 2 nanoseconds */
 static long long int histogram[32];
@@ -56,6 +57,7 @@ handle_args(int argc, char *argv[])
 	static struct option long_options[] = {
 		{"duration", required_argument, NULL, 'd'},
 		{"cutoff", required_argument, NULL, 'c'},
+		{"fast", no_argument, NULL, 'f'},
 		{NULL, 0, NULL, 0}
 	};
 
@@ -68,7 +70,7 @@ handle_args(int argc, char *argv[])
 	{
 		if (strcmp(argv[1], "--help") == 0 || strcmp(argv[1], "-?") == 0)
 		{
-			printf(_("Usage: %s [-d DURATION] [-c CUTOFF]\n"), progname);
+			printf(_("Usage: %s [-d DURATION] [-c CUTOFF] [--fast]\n"), progname);
 			exit(0);
 		}
 		if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0)
@@ -78,7 +80,7 @@ handle_args(int argc, char *argv[])
 		}
 	}
 
-	while ((option = getopt_long(argc, argv, "d:c:",
+	while ((option = getopt_long(argc, argv, "d:c:f:",
 								 long_options, &optindex)) != -1)
 	{
 		switch (option)
@@ -125,6 +127,10 @@ handle_args(int argc, char *argv[])
 				}
 				break;
 
+			case 'f':
+				fast_timing = true;
+				break;
+
 			default:
 				fprintf(stderr, _("Try \"%s --help\" for more information.\n"),
 						progname);
@@ -155,11 +161,31 @@ test_timing(unsigned int duration)
 	uint64		total_time;
 	int64		time_elapsed = 0;
 	uint64		loop_count = 0;
-	uint64		prev,
-				cur;
 	instr_time	start_time,
 				end_time,
-				temp;
+				prev,
+				cur;
+	char	   *time_source = NULL;
+	bool		fast_timing_used = false;
+
+	INSTR_TIME_INITIALIZE();
+
+#if !defined(WIN32) && defined(__x86_64__) && defined(__linux__)
+	if (fast_timing && has_rdtsc)
+	{
+		time_source = "RDTSC";
+		fast_timing_used = true;
+	}
+	else if (has_rdtscp)
+		time_source = "RDTSCP";
+	else
+		time_source = PG_INSTR_CLOCK_NAME;
+#else
+	time_source = PG_INSTR_CLOCK_NAME;
+#endif
+	if (fast_timing && !fast_timing_used)
+		printf(_("Warning: Fast timing requested, but not available - regular timing source will be used\n"));
+	printf(_("Time source: %s\n"), time_source);
 
 	/*
 	 * Pre-zero the statistics data structures.  They're already zero by
@@ -173,8 +199,11 @@ test_timing(unsigned int duration)
 
 	total_time = duration > 0 ? duration * INT64CONST(1000000000) : 0;
 
-	INSTR_TIME_SET_CURRENT(start_time);
-	cur = INSTR_TIME_GET_NANOSEC(start_time);
+	if (fast_timing)
+		INSTR_TIME_SET_CURRENT_FAST(start_time);
+	else
+		INSTR_TIME_SET_CURRENT(start_time);
+	cur = start_time;
 
 	while (time_elapsed < total_time)
 	{
@@ -182,9 +211,11 @@ test_timing(unsigned int duration)
 					bits;
 
 		prev = cur;
-		INSTR_TIME_SET_CURRENT(temp);
-		cur = INSTR_TIME_GET_NANOSEC(temp);
-		diff = cur - prev;
+		if (fast_timing)
+			INSTR_TIME_SET_CURRENT_FAST(cur);
+		else
+			INSTR_TIME_SET_CURRENT(cur);
+		diff = INSTR_TIME_DIFF_NANOSEC(cur, prev);
 
 		/* Did time go backwards? */
 		if (unlikely(diff < 0))
@@ -217,11 +248,13 @@ test_timing(unsigned int duration)
 			largest_diff_count++;
 
 		loop_count++;
-		INSTR_TIME_SUBTRACT(temp, start_time);
-		time_elapsed = INSTR_TIME_GET_NANOSEC(temp);
+		time_elapsed = INSTR_TIME_DIFF_NANOSEC(cur, start_time);
 	}
 
-	INSTR_TIME_SET_CURRENT(end_time);
+	if (fast_timing)
+		INSTR_TIME_SET_CURRENT_FAST(end_time);
+	else
+		INSTR_TIME_SET_CURRENT(end_time);
 
 	INSTR_TIME_SUBTRACT(end_time, start_time);
 
diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h
index e2e339a0c4f..f02296f1026 100644
--- a/src/include/portability/instr_time.h
+++ b/src/include/portability/instr_time.h
@@ -112,10 +112,13 @@ extern int64 max_ticks_no_overflow;
  */
 #if defined(__darwin__) && defined(CLOCK_MONOTONIC_RAW)
 #define PG_INSTR_CLOCK	CLOCK_MONOTONIC_RAW
+#define PG_INSTR_CLOCK_NAME	"clock_gettime (CLOCK_MONOTONIC_RAW)"
 #elif defined(CLOCK_MONOTONIC)
 #define PG_INSTR_CLOCK	CLOCK_MONOTONIC
+#define PG_INSTR_CLOCK_NAME	"clock_gettime (CLOCK_MONOTONIC)"
 #else
 #define PG_INSTR_CLOCK	CLOCK_REALTIME
+#define PG_INSTR_CLOCK_NAME	"clock_gettime (CLOCK_REALTIME)"
 #endif
 
 #if defined(__x86_64__) && defined(__linux__)
@@ -174,7 +177,7 @@ pg_get_ticks(void)
 }
 
 static inline int64_t
-pg_ticks_to_ns(instr_time t)
+pg_ticks_to_ns(int64 ticks)
 {
 	/*
 	 * Would multiplication overflow? If so perform computation in two parts.
@@ -183,7 +186,7 @@ pg_ticks_to_ns(instr_time t)
 	 */
 	int64		ns = 0;
 
-	if (unlikely(t.ticks > max_ticks_no_overflow))
+	if (unlikely(ticks > max_ticks_no_overflow))
 	{
 		/*
 		 * Compute how often the maximum number of ticks fits completely into
@@ -192,7 +195,7 @@ pg_ticks_to_ns(instr_time t)
 		 * value. In a 2nd step we adjust the number of elapsed ticks and
 		 * convert the remaining ticks.
 		 */
-		int64		count = t.ticks / max_ticks_no_overflow;
+		int64		count = ticks / max_ticks_no_overflow;
 		int64		max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION;
 
 		ns = max_ns * count;
@@ -201,11 +204,11 @@ pg_ticks_to_ns(instr_time t)
 		 * Subtract the ticks that we now already accounted for, so that they
 		 * don't get counted twice.
 		 */
-		t.ticks -= count * max_ticks_no_overflow;
-		Assert(t.ticks >= 0);
+		ticks -= count * max_ticks_no_overflow;
+		Assert(ticks >= 0);
 	}
 
-	ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION;
+	ns += ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION;
 	return ns;
 }
 
@@ -226,14 +229,14 @@ pg_initialize_get_ticks()
 #define INSTR_TIME_SET_CURRENT(t) \
 	((t) = pg_get_ticks())
 
-#define INSTR_TIME_GET_NANOSEC(t) \
-	pg_ticks_to_ns(t)
-
+#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \
+	(pg_ticks_to_ns(ticks))
 
 #else							/* WIN32 */
 
 
 /* Use QueryPerformanceCounter() */
+#define PG_INSTR_CLOCK_NAME	"QueryPerformanceCounter"
 
 /* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */
 static inline instr_time
@@ -265,8 +268,8 @@ GetTimerFrequency(void)
 #define INSTR_TIME_SET_CURRENT(t) \
 	((t) = pg_query_performance_counter())
 
-#define INSTR_TIME_GET_NANOSEC(t) \
-	((int64) ((t).ticks * ((double) NS_PER_S / GetTimerFrequency())))
+#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \
+	((int64) ((ticks) * ((double) NS_PER_S / GetTimerFrequency())))
 
 #endif							/* WIN32 */
 
@@ -285,9 +288,14 @@ GetTimerFrequency(void)
 #define INSTR_TIME_SUBTRACT(x,y) \
 	((x).ticks -= (y).ticks)
 
+#define INSTR_TIME_DIFF_NANOSEC(x,y) \
+	(INSTR_TIME_TICKS_TO_NANOSEC((x).ticks - (y).ticks))
+
 #define INSTR_TIME_ACCUM_DIFF(x,y,z) \
 	((x).ticks += (y).ticks - (z).ticks)
 
+#define INSTR_TIME_GET_NANOSEC(t) \
+	(INSTR_TIME_TICKS_TO_NANOSEC((t).ticks))
 
 #define INSTR_TIME_GET_DOUBLE(t) \
 	((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S)
-- 
2.47.3


--vtqqtrpooseurzip--





^ permalink  raw  reply  [nested|flat] 265+ messages in thread

* [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source
@ 2025-07-27 15:48  Lukas Fittl <[email protected]>
  0 siblings, 0 replies; 265+ messages in thread

From: Lukas Fittl @ 2025-07-27 15:48 UTC (permalink / raw)

In passing also reduce the per-loop overhead caused by repeated divisions
in INSTR_TIME_GET_NANOSEC when the ticks variable has become very large,
instead diff first and then turn it into nanosecs.
---
 src/bin/pg_test_timing/pg_test_timing.c | 59 +++++++++++++++++++------
 src/include/portability/instr_time.h    | 30 ++++++++-----
 2 files changed, 65 insertions(+), 24 deletions(-)

diff --git a/src/bin/pg_test_timing/pg_test_timing.c b/src/bin/pg_test_timing/pg_test_timing.c
index a5621251afc..b77ef2063b6 100644
--- a/src/bin/pg_test_timing/pg_test_timing.c
+++ b/src/bin/pg_test_timing/pg_test_timing.c
@@ -16,6 +16,7 @@ static const char *progname;
 
 static unsigned int test_duration = 3;
 static double max_rprct = 99.99;
+static bool fast_timing = false;
 
 /* record duration in powers of 2 nanoseconds */
 static long long int histogram[32];
@@ -56,6 +57,7 @@ handle_args(int argc, char *argv[])
 	static struct option long_options[] = {
 		{"duration", required_argument, NULL, 'd'},
 		{"cutoff", required_argument, NULL, 'c'},
+		{"fast", no_argument, NULL, 'f'},
 		{NULL, 0, NULL, 0}
 	};
 
@@ -68,7 +70,7 @@ handle_args(int argc, char *argv[])
 	{
 		if (strcmp(argv[1], "--help") == 0 || strcmp(argv[1], "-?") == 0)
 		{
-			printf(_("Usage: %s [-d DURATION] [-c CUTOFF]\n"), progname);
+			printf(_("Usage: %s [-d DURATION] [-c CUTOFF] [--fast]\n"), progname);
 			exit(0);
 		}
 		if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0)
@@ -78,7 +80,7 @@ handle_args(int argc, char *argv[])
 		}
 	}
 
-	while ((option = getopt_long(argc, argv, "d:c:",
+	while ((option = getopt_long(argc, argv, "d:c:f:",
 								 long_options, &optindex)) != -1)
 	{
 		switch (option)
@@ -125,6 +127,10 @@ handle_args(int argc, char *argv[])
 				}
 				break;
 
+			case 'f':
+				fast_timing = true;
+				break;
+
 			default:
 				fprintf(stderr, _("Try \"%s --help\" for more information.\n"),
 						progname);
@@ -155,11 +161,31 @@ test_timing(unsigned int duration)
 	uint64		total_time;
 	int64		time_elapsed = 0;
 	uint64		loop_count = 0;
-	uint64		prev,
-				cur;
 	instr_time	start_time,
 				end_time,
-				temp;
+				prev,
+				cur;
+	char	   *time_source = NULL;
+	bool		fast_timing_used = false;
+
+	INSTR_TIME_INITIALIZE();
+
+#if !defined(WIN32) && defined(__x86_64__) && defined(__linux__)
+	if (fast_timing && has_rdtsc)
+	{
+		time_source = "RDTSC";
+		fast_timing_used = true;
+	}
+	else if (has_rdtscp)
+		time_source = "RDTSCP";
+	else
+		time_source = PG_INSTR_CLOCK_NAME;
+#else
+	time_source = PG_INSTR_CLOCK_NAME;
+#endif
+	if (fast_timing && !fast_timing_used)
+		printf(_("Warning: Fast timing requested, but not available - regular timing source will be used\n"));
+	printf(_("Time source: %s\n"), time_source);
 
 	/*
 	 * Pre-zero the statistics data structures.  They're already zero by
@@ -173,8 +199,11 @@ test_timing(unsigned int duration)
 
 	total_time = duration > 0 ? duration * INT64CONST(1000000000) : 0;
 
-	INSTR_TIME_SET_CURRENT(start_time);
-	cur = INSTR_TIME_GET_NANOSEC(start_time);
+	if (fast_timing)
+		INSTR_TIME_SET_CURRENT_FAST(start_time);
+	else
+		INSTR_TIME_SET_CURRENT(start_time);
+	cur = start_time;
 
 	while (time_elapsed < total_time)
 	{
@@ -182,9 +211,11 @@ test_timing(unsigned int duration)
 					bits;
 
 		prev = cur;
-		INSTR_TIME_SET_CURRENT(temp);
-		cur = INSTR_TIME_GET_NANOSEC(temp);
-		diff = cur - prev;
+		if (fast_timing)
+			INSTR_TIME_SET_CURRENT_FAST(cur);
+		else
+			INSTR_TIME_SET_CURRENT(cur);
+		diff = INSTR_TIME_DIFF_NANOSEC(cur, prev);
 
 		/* Did time go backwards? */
 		if (unlikely(diff < 0))
@@ -217,11 +248,13 @@ test_timing(unsigned int duration)
 			largest_diff_count++;
 
 		loop_count++;
-		INSTR_TIME_SUBTRACT(temp, start_time);
-		time_elapsed = INSTR_TIME_GET_NANOSEC(temp);
+		time_elapsed = INSTR_TIME_DIFF_NANOSEC(cur, start_time);
 	}
 
-	INSTR_TIME_SET_CURRENT(end_time);
+	if (fast_timing)
+		INSTR_TIME_SET_CURRENT_FAST(end_time);
+	else
+		INSTR_TIME_SET_CURRENT(end_time);
 
 	INSTR_TIME_SUBTRACT(end_time, start_time);
 
diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h
index e2e339a0c4f..f02296f1026 100644
--- a/src/include/portability/instr_time.h
+++ b/src/include/portability/instr_time.h
@@ -112,10 +112,13 @@ extern int64 max_ticks_no_overflow;
  */
 #if defined(__darwin__) && defined(CLOCK_MONOTONIC_RAW)
 #define PG_INSTR_CLOCK	CLOCK_MONOTONIC_RAW
+#define PG_INSTR_CLOCK_NAME	"clock_gettime (CLOCK_MONOTONIC_RAW)"
 #elif defined(CLOCK_MONOTONIC)
 #define PG_INSTR_CLOCK	CLOCK_MONOTONIC
+#define PG_INSTR_CLOCK_NAME	"clock_gettime (CLOCK_MONOTONIC)"
 #else
 #define PG_INSTR_CLOCK	CLOCK_REALTIME
+#define PG_INSTR_CLOCK_NAME	"clock_gettime (CLOCK_REALTIME)"
 #endif
 
 #if defined(__x86_64__) && defined(__linux__)
@@ -174,7 +177,7 @@ pg_get_ticks(void)
 }
 
 static inline int64_t
-pg_ticks_to_ns(instr_time t)
+pg_ticks_to_ns(int64 ticks)
 {
 	/*
 	 * Would multiplication overflow? If so perform computation in two parts.
@@ -183,7 +186,7 @@ pg_ticks_to_ns(instr_time t)
 	 */
 	int64		ns = 0;
 
-	if (unlikely(t.ticks > max_ticks_no_overflow))
+	if (unlikely(ticks > max_ticks_no_overflow))
 	{
 		/*
 		 * Compute how often the maximum number of ticks fits completely into
@@ -192,7 +195,7 @@ pg_ticks_to_ns(instr_time t)
 		 * value. In a 2nd step we adjust the number of elapsed ticks and
 		 * convert the remaining ticks.
 		 */
-		int64		count = t.ticks / max_ticks_no_overflow;
+		int64		count = ticks / max_ticks_no_overflow;
 		int64		max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION;
 
 		ns = max_ns * count;
@@ -201,11 +204,11 @@ pg_ticks_to_ns(instr_time t)
 		 * Subtract the ticks that we now already accounted for, so that they
 		 * don't get counted twice.
 		 */
-		t.ticks -= count * max_ticks_no_overflow;
-		Assert(t.ticks >= 0);
+		ticks -= count * max_ticks_no_overflow;
+		Assert(ticks >= 0);
 	}
 
-	ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION;
+	ns += ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION;
 	return ns;
 }
 
@@ -226,14 +229,14 @@ pg_initialize_get_ticks()
 #define INSTR_TIME_SET_CURRENT(t) \
 	((t) = pg_get_ticks())
 
-#define INSTR_TIME_GET_NANOSEC(t) \
-	pg_ticks_to_ns(t)
-
+#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \
+	(pg_ticks_to_ns(ticks))
 
 #else							/* WIN32 */
 
 
 /* Use QueryPerformanceCounter() */
+#define PG_INSTR_CLOCK_NAME	"QueryPerformanceCounter"
 
 /* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */
 static inline instr_time
@@ -265,8 +268,8 @@ GetTimerFrequency(void)
 #define INSTR_TIME_SET_CURRENT(t) \
 	((t) = pg_query_performance_counter())
 
-#define INSTR_TIME_GET_NANOSEC(t) \
-	((int64) ((t).ticks * ((double) NS_PER_S / GetTimerFrequency())))
+#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \
+	((int64) ((ticks) * ((double) NS_PER_S / GetTimerFrequency())))
 
 #endif							/* WIN32 */
 
@@ -285,9 +288,14 @@ GetTimerFrequency(void)
 #define INSTR_TIME_SUBTRACT(x,y) \
 	((x).ticks -= (y).ticks)
 
+#define INSTR_TIME_DIFF_NANOSEC(x,y) \
+	(INSTR_TIME_TICKS_TO_NANOSEC((x).ticks - (y).ticks))
+
 #define INSTR_TIME_ACCUM_DIFF(x,y,z) \
 	((x).ticks += (y).ticks - (z).ticks)
 
+#define INSTR_TIME_GET_NANOSEC(t) \
+	(INSTR_TIME_TICKS_TO_NANOSEC((t).ticks))
 
 #define INSTR_TIME_GET_DOUBLE(t) \
 	((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S)
-- 
2.47.3


--vtqqtrpooseurzip--





^ permalink  raw  reply  [nested|flat] 265+ messages in thread

* [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source
@ 2025-07-27 15:48  Lukas Fittl <[email protected]>
  0 siblings, 0 replies; 265+ messages in thread

From: Lukas Fittl @ 2025-07-27 15:48 UTC (permalink / raw)

In passing also reduce the per-loop overhead caused by repeated divisions
in INSTR_TIME_GET_NANOSEC when the ticks variable has become very large,
instead diff first and then turn it into nanosecs.
---
 src/bin/pg_test_timing/pg_test_timing.c | 59 +++++++++++++++++++------
 src/include/portability/instr_time.h    | 30 ++++++++-----
 2 files changed, 65 insertions(+), 24 deletions(-)

diff --git a/src/bin/pg_test_timing/pg_test_timing.c b/src/bin/pg_test_timing/pg_test_timing.c
index a5621251afc..b77ef2063b6 100644
--- a/src/bin/pg_test_timing/pg_test_timing.c
+++ b/src/bin/pg_test_timing/pg_test_timing.c
@@ -16,6 +16,7 @@ static const char *progname;
 
 static unsigned int test_duration = 3;
 static double max_rprct = 99.99;
+static bool fast_timing = false;
 
 /* record duration in powers of 2 nanoseconds */
 static long long int histogram[32];
@@ -56,6 +57,7 @@ handle_args(int argc, char *argv[])
 	static struct option long_options[] = {
 		{"duration", required_argument, NULL, 'd'},
 		{"cutoff", required_argument, NULL, 'c'},
+		{"fast", no_argument, NULL, 'f'},
 		{NULL, 0, NULL, 0}
 	};
 
@@ -68,7 +70,7 @@ handle_args(int argc, char *argv[])
 	{
 		if (strcmp(argv[1], "--help") == 0 || strcmp(argv[1], "-?") == 0)
 		{
-			printf(_("Usage: %s [-d DURATION] [-c CUTOFF]\n"), progname);
+			printf(_("Usage: %s [-d DURATION] [-c CUTOFF] [--fast]\n"), progname);
 			exit(0);
 		}
 		if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0)
@@ -78,7 +80,7 @@ handle_args(int argc, char *argv[])
 		}
 	}
 
-	while ((option = getopt_long(argc, argv, "d:c:",
+	while ((option = getopt_long(argc, argv, "d:c:f:",
 								 long_options, &optindex)) != -1)
 	{
 		switch (option)
@@ -125,6 +127,10 @@ handle_args(int argc, char *argv[])
 				}
 				break;
 
+			case 'f':
+				fast_timing = true;
+				break;
+
 			default:
 				fprintf(stderr, _("Try \"%s --help\" for more information.\n"),
 						progname);
@@ -155,11 +161,31 @@ test_timing(unsigned int duration)
 	uint64		total_time;
 	int64		time_elapsed = 0;
 	uint64		loop_count = 0;
-	uint64		prev,
-				cur;
 	instr_time	start_time,
 				end_time,
-				temp;
+				prev,
+				cur;
+	char	   *time_source = NULL;
+	bool		fast_timing_used = false;
+
+	INSTR_TIME_INITIALIZE();
+
+#if !defined(WIN32) && defined(__x86_64__) && defined(__linux__)
+	if (fast_timing && has_rdtsc)
+	{
+		time_source = "RDTSC";
+		fast_timing_used = true;
+	}
+	else if (has_rdtscp)
+		time_source = "RDTSCP";
+	else
+		time_source = PG_INSTR_CLOCK_NAME;
+#else
+	time_source = PG_INSTR_CLOCK_NAME;
+#endif
+	if (fast_timing && !fast_timing_used)
+		printf(_("Warning: Fast timing requested, but not available - regular timing source will be used\n"));
+	printf(_("Time source: %s\n"), time_source);
 
 	/*
 	 * Pre-zero the statistics data structures.  They're already zero by
@@ -173,8 +199,11 @@ test_timing(unsigned int duration)
 
 	total_time = duration > 0 ? duration * INT64CONST(1000000000) : 0;
 
-	INSTR_TIME_SET_CURRENT(start_time);
-	cur = INSTR_TIME_GET_NANOSEC(start_time);
+	if (fast_timing)
+		INSTR_TIME_SET_CURRENT_FAST(start_time);
+	else
+		INSTR_TIME_SET_CURRENT(start_time);
+	cur = start_time;
 
 	while (time_elapsed < total_time)
 	{
@@ -182,9 +211,11 @@ test_timing(unsigned int duration)
 					bits;
 
 		prev = cur;
-		INSTR_TIME_SET_CURRENT(temp);
-		cur = INSTR_TIME_GET_NANOSEC(temp);
-		diff = cur - prev;
+		if (fast_timing)
+			INSTR_TIME_SET_CURRENT_FAST(cur);
+		else
+			INSTR_TIME_SET_CURRENT(cur);
+		diff = INSTR_TIME_DIFF_NANOSEC(cur, prev);
 
 		/* Did time go backwards? */
 		if (unlikely(diff < 0))
@@ -217,11 +248,13 @@ test_timing(unsigned int duration)
 			largest_diff_count++;
 
 		loop_count++;
-		INSTR_TIME_SUBTRACT(temp, start_time);
-		time_elapsed = INSTR_TIME_GET_NANOSEC(temp);
+		time_elapsed = INSTR_TIME_DIFF_NANOSEC(cur, start_time);
 	}
 
-	INSTR_TIME_SET_CURRENT(end_time);
+	if (fast_timing)
+		INSTR_TIME_SET_CURRENT_FAST(end_time);
+	else
+		INSTR_TIME_SET_CURRENT(end_time);
 
 	INSTR_TIME_SUBTRACT(end_time, start_time);
 
diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h
index e2e339a0c4f..f02296f1026 100644
--- a/src/include/portability/instr_time.h
+++ b/src/include/portability/instr_time.h
@@ -112,10 +112,13 @@ extern int64 max_ticks_no_overflow;
  */
 #if defined(__darwin__) && defined(CLOCK_MONOTONIC_RAW)
 #define PG_INSTR_CLOCK	CLOCK_MONOTONIC_RAW
+#define PG_INSTR_CLOCK_NAME	"clock_gettime (CLOCK_MONOTONIC_RAW)"
 #elif defined(CLOCK_MONOTONIC)
 #define PG_INSTR_CLOCK	CLOCK_MONOTONIC
+#define PG_INSTR_CLOCK_NAME	"clock_gettime (CLOCK_MONOTONIC)"
 #else
 #define PG_INSTR_CLOCK	CLOCK_REALTIME
+#define PG_INSTR_CLOCK_NAME	"clock_gettime (CLOCK_REALTIME)"
 #endif
 
 #if defined(__x86_64__) && defined(__linux__)
@@ -174,7 +177,7 @@ pg_get_ticks(void)
 }
 
 static inline int64_t
-pg_ticks_to_ns(instr_time t)
+pg_ticks_to_ns(int64 ticks)
 {
 	/*
 	 * Would multiplication overflow? If so perform computation in two parts.
@@ -183,7 +186,7 @@ pg_ticks_to_ns(instr_time t)
 	 */
 	int64		ns = 0;
 
-	if (unlikely(t.ticks > max_ticks_no_overflow))
+	if (unlikely(ticks > max_ticks_no_overflow))
 	{
 		/*
 		 * Compute how often the maximum number of ticks fits completely into
@@ -192,7 +195,7 @@ pg_ticks_to_ns(instr_time t)
 		 * value. In a 2nd step we adjust the number of elapsed ticks and
 		 * convert the remaining ticks.
 		 */
-		int64		count = t.ticks / max_ticks_no_overflow;
+		int64		count = ticks / max_ticks_no_overflow;
 		int64		max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION;
 
 		ns = max_ns * count;
@@ -201,11 +204,11 @@ pg_ticks_to_ns(instr_time t)
 		 * Subtract the ticks that we now already accounted for, so that they
 		 * don't get counted twice.
 		 */
-		t.ticks -= count * max_ticks_no_overflow;
-		Assert(t.ticks >= 0);
+		ticks -= count * max_ticks_no_overflow;
+		Assert(ticks >= 0);
 	}
 
-	ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION;
+	ns += ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION;
 	return ns;
 }
 
@@ -226,14 +229,14 @@ pg_initialize_get_ticks()
 #define INSTR_TIME_SET_CURRENT(t) \
 	((t) = pg_get_ticks())
 
-#define INSTR_TIME_GET_NANOSEC(t) \
-	pg_ticks_to_ns(t)
-
+#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \
+	(pg_ticks_to_ns(ticks))
 
 #else							/* WIN32 */
 
 
 /* Use QueryPerformanceCounter() */
+#define PG_INSTR_CLOCK_NAME	"QueryPerformanceCounter"
 
 /* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */
 static inline instr_time
@@ -265,8 +268,8 @@ GetTimerFrequency(void)
 #define INSTR_TIME_SET_CURRENT(t) \
 	((t) = pg_query_performance_counter())
 
-#define INSTR_TIME_GET_NANOSEC(t) \
-	((int64) ((t).ticks * ((double) NS_PER_S / GetTimerFrequency())))
+#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \
+	((int64) ((ticks) * ((double) NS_PER_S / GetTimerFrequency())))
 
 #endif							/* WIN32 */
 
@@ -285,9 +288,14 @@ GetTimerFrequency(void)
 #define INSTR_TIME_SUBTRACT(x,y) \
 	((x).ticks -= (y).ticks)
 
+#define INSTR_TIME_DIFF_NANOSEC(x,y) \
+	(INSTR_TIME_TICKS_TO_NANOSEC((x).ticks - (y).ticks))
+
 #define INSTR_TIME_ACCUM_DIFF(x,y,z) \
 	((x).ticks += (y).ticks - (z).ticks)
 
+#define INSTR_TIME_GET_NANOSEC(t) \
+	(INSTR_TIME_TICKS_TO_NANOSEC((t).ticks))
 
 #define INSTR_TIME_GET_DOUBLE(t) \
 	((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S)
-- 
2.47.3


--vtqqtrpooseurzip--





^ permalink  raw  reply  [nested|flat] 265+ messages in thread

* [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source
@ 2025-07-27 15:48  Lukas Fittl <[email protected]>
  0 siblings, 0 replies; 265+ messages in thread

From: Lukas Fittl @ 2025-07-27 15:48 UTC (permalink / raw)

In passing also reduce the per-loop overhead caused by repeated divisions
in INSTR_TIME_GET_NANOSEC when the ticks variable has become very large,
instead diff first and then turn it into nanosecs.
---
 src/bin/pg_test_timing/pg_test_timing.c | 59 +++++++++++++++++++------
 src/include/portability/instr_time.h    | 30 ++++++++-----
 2 files changed, 65 insertions(+), 24 deletions(-)

diff --git a/src/bin/pg_test_timing/pg_test_timing.c b/src/bin/pg_test_timing/pg_test_timing.c
index a5621251afc..b77ef2063b6 100644
--- a/src/bin/pg_test_timing/pg_test_timing.c
+++ b/src/bin/pg_test_timing/pg_test_timing.c
@@ -16,6 +16,7 @@ static const char *progname;
 
 static unsigned int test_duration = 3;
 static double max_rprct = 99.99;
+static bool fast_timing = false;
 
 /* record duration in powers of 2 nanoseconds */
 static long long int histogram[32];
@@ -56,6 +57,7 @@ handle_args(int argc, char *argv[])
 	static struct option long_options[] = {
 		{"duration", required_argument, NULL, 'd'},
 		{"cutoff", required_argument, NULL, 'c'},
+		{"fast", no_argument, NULL, 'f'},
 		{NULL, 0, NULL, 0}
 	};
 
@@ -68,7 +70,7 @@ handle_args(int argc, char *argv[])
 	{
 		if (strcmp(argv[1], "--help") == 0 || strcmp(argv[1], "-?") == 0)
 		{
-			printf(_("Usage: %s [-d DURATION] [-c CUTOFF]\n"), progname);
+			printf(_("Usage: %s [-d DURATION] [-c CUTOFF] [--fast]\n"), progname);
 			exit(0);
 		}
 		if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0)
@@ -78,7 +80,7 @@ handle_args(int argc, char *argv[])
 		}
 	}
 
-	while ((option = getopt_long(argc, argv, "d:c:",
+	while ((option = getopt_long(argc, argv, "d:c:f:",
 								 long_options, &optindex)) != -1)
 	{
 		switch (option)
@@ -125,6 +127,10 @@ handle_args(int argc, char *argv[])
 				}
 				break;
 
+			case 'f':
+				fast_timing = true;
+				break;
+
 			default:
 				fprintf(stderr, _("Try \"%s --help\" for more information.\n"),
 						progname);
@@ -155,11 +161,31 @@ test_timing(unsigned int duration)
 	uint64		total_time;
 	int64		time_elapsed = 0;
 	uint64		loop_count = 0;
-	uint64		prev,
-				cur;
 	instr_time	start_time,
 				end_time,
-				temp;
+				prev,
+				cur;
+	char	   *time_source = NULL;
+	bool		fast_timing_used = false;
+
+	INSTR_TIME_INITIALIZE();
+
+#if !defined(WIN32) && defined(__x86_64__) && defined(__linux__)
+	if (fast_timing && has_rdtsc)
+	{
+		time_source = "RDTSC";
+		fast_timing_used = true;
+	}
+	else if (has_rdtscp)
+		time_source = "RDTSCP";
+	else
+		time_source = PG_INSTR_CLOCK_NAME;
+#else
+	time_source = PG_INSTR_CLOCK_NAME;
+#endif
+	if (fast_timing && !fast_timing_used)
+		printf(_("Warning: Fast timing requested, but not available - regular timing source will be used\n"));
+	printf(_("Time source: %s\n"), time_source);
 
 	/*
 	 * Pre-zero the statistics data structures.  They're already zero by
@@ -173,8 +199,11 @@ test_timing(unsigned int duration)
 
 	total_time = duration > 0 ? duration * INT64CONST(1000000000) : 0;
 
-	INSTR_TIME_SET_CURRENT(start_time);
-	cur = INSTR_TIME_GET_NANOSEC(start_time);
+	if (fast_timing)
+		INSTR_TIME_SET_CURRENT_FAST(start_time);
+	else
+		INSTR_TIME_SET_CURRENT(start_time);
+	cur = start_time;
 
 	while (time_elapsed < total_time)
 	{
@@ -182,9 +211,11 @@ test_timing(unsigned int duration)
 					bits;
 
 		prev = cur;
-		INSTR_TIME_SET_CURRENT(temp);
-		cur = INSTR_TIME_GET_NANOSEC(temp);
-		diff = cur - prev;
+		if (fast_timing)
+			INSTR_TIME_SET_CURRENT_FAST(cur);
+		else
+			INSTR_TIME_SET_CURRENT(cur);
+		diff = INSTR_TIME_DIFF_NANOSEC(cur, prev);
 
 		/* Did time go backwards? */
 		if (unlikely(diff < 0))
@@ -217,11 +248,13 @@ test_timing(unsigned int duration)
 			largest_diff_count++;
 
 		loop_count++;
-		INSTR_TIME_SUBTRACT(temp, start_time);
-		time_elapsed = INSTR_TIME_GET_NANOSEC(temp);
+		time_elapsed = INSTR_TIME_DIFF_NANOSEC(cur, start_time);
 	}
 
-	INSTR_TIME_SET_CURRENT(end_time);
+	if (fast_timing)
+		INSTR_TIME_SET_CURRENT_FAST(end_time);
+	else
+		INSTR_TIME_SET_CURRENT(end_time);
 
 	INSTR_TIME_SUBTRACT(end_time, start_time);
 
diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h
index e2e339a0c4f..f02296f1026 100644
--- a/src/include/portability/instr_time.h
+++ b/src/include/portability/instr_time.h
@@ -112,10 +112,13 @@ extern int64 max_ticks_no_overflow;
  */
 #if defined(__darwin__) && defined(CLOCK_MONOTONIC_RAW)
 #define PG_INSTR_CLOCK	CLOCK_MONOTONIC_RAW
+#define PG_INSTR_CLOCK_NAME	"clock_gettime (CLOCK_MONOTONIC_RAW)"
 #elif defined(CLOCK_MONOTONIC)
 #define PG_INSTR_CLOCK	CLOCK_MONOTONIC
+#define PG_INSTR_CLOCK_NAME	"clock_gettime (CLOCK_MONOTONIC)"
 #else
 #define PG_INSTR_CLOCK	CLOCK_REALTIME
+#define PG_INSTR_CLOCK_NAME	"clock_gettime (CLOCK_REALTIME)"
 #endif
 
 #if defined(__x86_64__) && defined(__linux__)
@@ -174,7 +177,7 @@ pg_get_ticks(void)
 }
 
 static inline int64_t
-pg_ticks_to_ns(instr_time t)
+pg_ticks_to_ns(int64 ticks)
 {
 	/*
 	 * Would multiplication overflow? If so perform computation in two parts.
@@ -183,7 +186,7 @@ pg_ticks_to_ns(instr_time t)
 	 */
 	int64		ns = 0;
 
-	if (unlikely(t.ticks > max_ticks_no_overflow))
+	if (unlikely(ticks > max_ticks_no_overflow))
 	{
 		/*
 		 * Compute how often the maximum number of ticks fits completely into
@@ -192,7 +195,7 @@ pg_ticks_to_ns(instr_time t)
 		 * value. In a 2nd step we adjust the number of elapsed ticks and
 		 * convert the remaining ticks.
 		 */
-		int64		count = t.ticks / max_ticks_no_overflow;
+		int64		count = ticks / max_ticks_no_overflow;
 		int64		max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION;
 
 		ns = max_ns * count;
@@ -201,11 +204,11 @@ pg_ticks_to_ns(instr_time t)
 		 * Subtract the ticks that we now already accounted for, so that they
 		 * don't get counted twice.
 		 */
-		t.ticks -= count * max_ticks_no_overflow;
-		Assert(t.ticks >= 0);
+		ticks -= count * max_ticks_no_overflow;
+		Assert(ticks >= 0);
 	}
 
-	ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION;
+	ns += ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION;
 	return ns;
 }
 
@@ -226,14 +229,14 @@ pg_initialize_get_ticks()
 #define INSTR_TIME_SET_CURRENT(t) \
 	((t) = pg_get_ticks())
 
-#define INSTR_TIME_GET_NANOSEC(t) \
-	pg_ticks_to_ns(t)
-
+#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \
+	(pg_ticks_to_ns(ticks))
 
 #else							/* WIN32 */
 
 
 /* Use QueryPerformanceCounter() */
+#define PG_INSTR_CLOCK_NAME	"QueryPerformanceCounter"
 
 /* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */
 static inline instr_time
@@ -265,8 +268,8 @@ GetTimerFrequency(void)
 #define INSTR_TIME_SET_CURRENT(t) \
 	((t) = pg_query_performance_counter())
 
-#define INSTR_TIME_GET_NANOSEC(t) \
-	((int64) ((t).ticks * ((double) NS_PER_S / GetTimerFrequency())))
+#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \
+	((int64) ((ticks) * ((double) NS_PER_S / GetTimerFrequency())))
 
 #endif							/* WIN32 */
 
@@ -285,9 +288,14 @@ GetTimerFrequency(void)
 #define INSTR_TIME_SUBTRACT(x,y) \
 	((x).ticks -= (y).ticks)
 
+#define INSTR_TIME_DIFF_NANOSEC(x,y) \
+	(INSTR_TIME_TICKS_TO_NANOSEC((x).ticks - (y).ticks))
+
 #define INSTR_TIME_ACCUM_DIFF(x,y,z) \
 	((x).ticks += (y).ticks - (z).ticks)
 
+#define INSTR_TIME_GET_NANOSEC(t) \
+	(INSTR_TIME_TICKS_TO_NANOSEC((t).ticks))
 
 #define INSTR_TIME_GET_DOUBLE(t) \
 	((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S)
-- 
2.47.3


--vtqqtrpooseurzip--





^ permalink  raw  reply  [nested|flat] 265+ messages in thread

* [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source
@ 2025-07-27 15:48  Lukas Fittl <[email protected]>
  0 siblings, 0 replies; 265+ messages in thread

From: Lukas Fittl @ 2025-07-27 15:48 UTC (permalink / raw)

In passing also reduce the per-loop overhead caused by repeated divisions
in INSTR_TIME_GET_NANOSEC when the ticks variable has become very large,
instead diff first and then turn it into nanosecs.
---
 src/bin/pg_test_timing/pg_test_timing.c | 59 +++++++++++++++++++------
 src/include/portability/instr_time.h    | 30 ++++++++-----
 2 files changed, 65 insertions(+), 24 deletions(-)

diff --git a/src/bin/pg_test_timing/pg_test_timing.c b/src/bin/pg_test_timing/pg_test_timing.c
index a5621251afc..b77ef2063b6 100644
--- a/src/bin/pg_test_timing/pg_test_timing.c
+++ b/src/bin/pg_test_timing/pg_test_timing.c
@@ -16,6 +16,7 @@ static const char *progname;
 
 static unsigned int test_duration = 3;
 static double max_rprct = 99.99;
+static bool fast_timing = false;
 
 /* record duration in powers of 2 nanoseconds */
 static long long int histogram[32];
@@ -56,6 +57,7 @@ handle_args(int argc, char *argv[])
 	static struct option long_options[] = {
 		{"duration", required_argument, NULL, 'd'},
 		{"cutoff", required_argument, NULL, 'c'},
+		{"fast", no_argument, NULL, 'f'},
 		{NULL, 0, NULL, 0}
 	};
 
@@ -68,7 +70,7 @@ handle_args(int argc, char *argv[])
 	{
 		if (strcmp(argv[1], "--help") == 0 || strcmp(argv[1], "-?") == 0)
 		{
-			printf(_("Usage: %s [-d DURATION] [-c CUTOFF]\n"), progname);
+			printf(_("Usage: %s [-d DURATION] [-c CUTOFF] [--fast]\n"), progname);
 			exit(0);
 		}
 		if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0)
@@ -78,7 +80,7 @@ handle_args(int argc, char *argv[])
 		}
 	}
 
-	while ((option = getopt_long(argc, argv, "d:c:",
+	while ((option = getopt_long(argc, argv, "d:c:f:",
 								 long_options, &optindex)) != -1)
 	{
 		switch (option)
@@ -125,6 +127,10 @@ handle_args(int argc, char *argv[])
 				}
 				break;
 
+			case 'f':
+				fast_timing = true;
+				break;
+
 			default:
 				fprintf(stderr, _("Try \"%s --help\" for more information.\n"),
 						progname);
@@ -155,11 +161,31 @@ test_timing(unsigned int duration)
 	uint64		total_time;
 	int64		time_elapsed = 0;
 	uint64		loop_count = 0;
-	uint64		prev,
-				cur;
 	instr_time	start_time,
 				end_time,
-				temp;
+				prev,
+				cur;
+	char	   *time_source = NULL;
+	bool		fast_timing_used = false;
+
+	INSTR_TIME_INITIALIZE();
+
+#if !defined(WIN32) && defined(__x86_64__) && defined(__linux__)
+	if (fast_timing && has_rdtsc)
+	{
+		time_source = "RDTSC";
+		fast_timing_used = true;
+	}
+	else if (has_rdtscp)
+		time_source = "RDTSCP";
+	else
+		time_source = PG_INSTR_CLOCK_NAME;
+#else
+	time_source = PG_INSTR_CLOCK_NAME;
+#endif
+	if (fast_timing && !fast_timing_used)
+		printf(_("Warning: Fast timing requested, but not available - regular timing source will be used\n"));
+	printf(_("Time source: %s\n"), time_source);
 
 	/*
 	 * Pre-zero the statistics data structures.  They're already zero by
@@ -173,8 +199,11 @@ test_timing(unsigned int duration)
 
 	total_time = duration > 0 ? duration * INT64CONST(1000000000) : 0;
 
-	INSTR_TIME_SET_CURRENT(start_time);
-	cur = INSTR_TIME_GET_NANOSEC(start_time);
+	if (fast_timing)
+		INSTR_TIME_SET_CURRENT_FAST(start_time);
+	else
+		INSTR_TIME_SET_CURRENT(start_time);
+	cur = start_time;
 
 	while (time_elapsed < total_time)
 	{
@@ -182,9 +211,11 @@ test_timing(unsigned int duration)
 					bits;
 
 		prev = cur;
-		INSTR_TIME_SET_CURRENT(temp);
-		cur = INSTR_TIME_GET_NANOSEC(temp);
-		diff = cur - prev;
+		if (fast_timing)
+			INSTR_TIME_SET_CURRENT_FAST(cur);
+		else
+			INSTR_TIME_SET_CURRENT(cur);
+		diff = INSTR_TIME_DIFF_NANOSEC(cur, prev);
 
 		/* Did time go backwards? */
 		if (unlikely(diff < 0))
@@ -217,11 +248,13 @@ test_timing(unsigned int duration)
 			largest_diff_count++;
 
 		loop_count++;
-		INSTR_TIME_SUBTRACT(temp, start_time);
-		time_elapsed = INSTR_TIME_GET_NANOSEC(temp);
+		time_elapsed = INSTR_TIME_DIFF_NANOSEC(cur, start_time);
 	}
 
-	INSTR_TIME_SET_CURRENT(end_time);
+	if (fast_timing)
+		INSTR_TIME_SET_CURRENT_FAST(end_time);
+	else
+		INSTR_TIME_SET_CURRENT(end_time);
 
 	INSTR_TIME_SUBTRACT(end_time, start_time);
 
diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h
index e2e339a0c4f..f02296f1026 100644
--- a/src/include/portability/instr_time.h
+++ b/src/include/portability/instr_time.h
@@ -112,10 +112,13 @@ extern int64 max_ticks_no_overflow;
  */
 #if defined(__darwin__) && defined(CLOCK_MONOTONIC_RAW)
 #define PG_INSTR_CLOCK	CLOCK_MONOTONIC_RAW
+#define PG_INSTR_CLOCK_NAME	"clock_gettime (CLOCK_MONOTONIC_RAW)"
 #elif defined(CLOCK_MONOTONIC)
 #define PG_INSTR_CLOCK	CLOCK_MONOTONIC
+#define PG_INSTR_CLOCK_NAME	"clock_gettime (CLOCK_MONOTONIC)"
 #else
 #define PG_INSTR_CLOCK	CLOCK_REALTIME
+#define PG_INSTR_CLOCK_NAME	"clock_gettime (CLOCK_REALTIME)"
 #endif
 
 #if defined(__x86_64__) && defined(__linux__)
@@ -174,7 +177,7 @@ pg_get_ticks(void)
 }
 
 static inline int64_t
-pg_ticks_to_ns(instr_time t)
+pg_ticks_to_ns(int64 ticks)
 {
 	/*
 	 * Would multiplication overflow? If so perform computation in two parts.
@@ -183,7 +186,7 @@ pg_ticks_to_ns(instr_time t)
 	 */
 	int64		ns = 0;
 
-	if (unlikely(t.ticks > max_ticks_no_overflow))
+	if (unlikely(ticks > max_ticks_no_overflow))
 	{
 		/*
 		 * Compute how often the maximum number of ticks fits completely into
@@ -192,7 +195,7 @@ pg_ticks_to_ns(instr_time t)
 		 * value. In a 2nd step we adjust the number of elapsed ticks and
 		 * convert the remaining ticks.
 		 */
-		int64		count = t.ticks / max_ticks_no_overflow;
+		int64		count = ticks / max_ticks_no_overflow;
 		int64		max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION;
 
 		ns = max_ns * count;
@@ -201,11 +204,11 @@ pg_ticks_to_ns(instr_time t)
 		 * Subtract the ticks that we now already accounted for, so that they
 		 * don't get counted twice.
 		 */
-		t.ticks -= count * max_ticks_no_overflow;
-		Assert(t.ticks >= 0);
+		ticks -= count * max_ticks_no_overflow;
+		Assert(ticks >= 0);
 	}
 
-	ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION;
+	ns += ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION;
 	return ns;
 }
 
@@ -226,14 +229,14 @@ pg_initialize_get_ticks()
 #define INSTR_TIME_SET_CURRENT(t) \
 	((t) = pg_get_ticks())
 
-#define INSTR_TIME_GET_NANOSEC(t) \
-	pg_ticks_to_ns(t)
-
+#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \
+	(pg_ticks_to_ns(ticks))
 
 #else							/* WIN32 */
 
 
 /* Use QueryPerformanceCounter() */
+#define PG_INSTR_CLOCK_NAME	"QueryPerformanceCounter"
 
 /* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */
 static inline instr_time
@@ -265,8 +268,8 @@ GetTimerFrequency(void)
 #define INSTR_TIME_SET_CURRENT(t) \
 	((t) = pg_query_performance_counter())
 
-#define INSTR_TIME_GET_NANOSEC(t) \
-	((int64) ((t).ticks * ((double) NS_PER_S / GetTimerFrequency())))
+#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \
+	((int64) ((ticks) * ((double) NS_PER_S / GetTimerFrequency())))
 
 #endif							/* WIN32 */
 
@@ -285,9 +288,14 @@ GetTimerFrequency(void)
 #define INSTR_TIME_SUBTRACT(x,y) \
 	((x).ticks -= (y).ticks)
 
+#define INSTR_TIME_DIFF_NANOSEC(x,y) \
+	(INSTR_TIME_TICKS_TO_NANOSEC((x).ticks - (y).ticks))
+
 #define INSTR_TIME_ACCUM_DIFF(x,y,z) \
 	((x).ticks += (y).ticks - (z).ticks)
 
+#define INSTR_TIME_GET_NANOSEC(t) \
+	(INSTR_TIME_TICKS_TO_NANOSEC((t).ticks))
 
 #define INSTR_TIME_GET_DOUBLE(t) \
 	((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S)
-- 
2.47.3


--vtqqtrpooseurzip--





^ permalink  raw  reply  [nested|flat] 265+ messages in thread

* [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source
@ 2025-07-27 15:48  Lukas Fittl <[email protected]>
  0 siblings, 0 replies; 265+ messages in thread

From: Lukas Fittl @ 2025-07-27 15:48 UTC (permalink / raw)

In passing also reduce the per-loop overhead caused by repeated divisions
in INSTR_TIME_GET_NANOSEC when the ticks variable has become very large,
instead diff first and then turn it into nanosecs.
---
 src/bin/pg_test_timing/pg_test_timing.c | 59 +++++++++++++++++++------
 src/include/portability/instr_time.h    | 30 ++++++++-----
 2 files changed, 65 insertions(+), 24 deletions(-)

diff --git a/src/bin/pg_test_timing/pg_test_timing.c b/src/bin/pg_test_timing/pg_test_timing.c
index a5621251afc..b77ef2063b6 100644
--- a/src/bin/pg_test_timing/pg_test_timing.c
+++ b/src/bin/pg_test_timing/pg_test_timing.c
@@ -16,6 +16,7 @@ static const char *progname;
 
 static unsigned int test_duration = 3;
 static double max_rprct = 99.99;
+static bool fast_timing = false;
 
 /* record duration in powers of 2 nanoseconds */
 static long long int histogram[32];
@@ -56,6 +57,7 @@ handle_args(int argc, char *argv[])
 	static struct option long_options[] = {
 		{"duration", required_argument, NULL, 'd'},
 		{"cutoff", required_argument, NULL, 'c'},
+		{"fast", no_argument, NULL, 'f'},
 		{NULL, 0, NULL, 0}
 	};
 
@@ -68,7 +70,7 @@ handle_args(int argc, char *argv[])
 	{
 		if (strcmp(argv[1], "--help") == 0 || strcmp(argv[1], "-?") == 0)
 		{
-			printf(_("Usage: %s [-d DURATION] [-c CUTOFF]\n"), progname);
+			printf(_("Usage: %s [-d DURATION] [-c CUTOFF] [--fast]\n"), progname);
 			exit(0);
 		}
 		if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0)
@@ -78,7 +80,7 @@ handle_args(int argc, char *argv[])
 		}
 	}
 
-	while ((option = getopt_long(argc, argv, "d:c:",
+	while ((option = getopt_long(argc, argv, "d:c:f:",
 								 long_options, &optindex)) != -1)
 	{
 		switch (option)
@@ -125,6 +127,10 @@ handle_args(int argc, char *argv[])
 				}
 				break;
 
+			case 'f':
+				fast_timing = true;
+				break;
+
 			default:
 				fprintf(stderr, _("Try \"%s --help\" for more information.\n"),
 						progname);
@@ -155,11 +161,31 @@ test_timing(unsigned int duration)
 	uint64		total_time;
 	int64		time_elapsed = 0;
 	uint64		loop_count = 0;
-	uint64		prev,
-				cur;
 	instr_time	start_time,
 				end_time,
-				temp;
+				prev,
+				cur;
+	char	   *time_source = NULL;
+	bool		fast_timing_used = false;
+
+	INSTR_TIME_INITIALIZE();
+
+#if !defined(WIN32) && defined(__x86_64__) && defined(__linux__)
+	if (fast_timing && has_rdtsc)
+	{
+		time_source = "RDTSC";
+		fast_timing_used = true;
+	}
+	else if (has_rdtscp)
+		time_source = "RDTSCP";
+	else
+		time_source = PG_INSTR_CLOCK_NAME;
+#else
+	time_source = PG_INSTR_CLOCK_NAME;
+#endif
+	if (fast_timing && !fast_timing_used)
+		printf(_("Warning: Fast timing requested, but not available - regular timing source will be used\n"));
+	printf(_("Time source: %s\n"), time_source);
 
 	/*
 	 * Pre-zero the statistics data structures.  They're already zero by
@@ -173,8 +199,11 @@ test_timing(unsigned int duration)
 
 	total_time = duration > 0 ? duration * INT64CONST(1000000000) : 0;
 
-	INSTR_TIME_SET_CURRENT(start_time);
-	cur = INSTR_TIME_GET_NANOSEC(start_time);
+	if (fast_timing)
+		INSTR_TIME_SET_CURRENT_FAST(start_time);
+	else
+		INSTR_TIME_SET_CURRENT(start_time);
+	cur = start_time;
 
 	while (time_elapsed < total_time)
 	{
@@ -182,9 +211,11 @@ test_timing(unsigned int duration)
 					bits;
 
 		prev = cur;
-		INSTR_TIME_SET_CURRENT(temp);
-		cur = INSTR_TIME_GET_NANOSEC(temp);
-		diff = cur - prev;
+		if (fast_timing)
+			INSTR_TIME_SET_CURRENT_FAST(cur);
+		else
+			INSTR_TIME_SET_CURRENT(cur);
+		diff = INSTR_TIME_DIFF_NANOSEC(cur, prev);
 
 		/* Did time go backwards? */
 		if (unlikely(diff < 0))
@@ -217,11 +248,13 @@ test_timing(unsigned int duration)
 			largest_diff_count++;
 
 		loop_count++;
-		INSTR_TIME_SUBTRACT(temp, start_time);
-		time_elapsed = INSTR_TIME_GET_NANOSEC(temp);
+		time_elapsed = INSTR_TIME_DIFF_NANOSEC(cur, start_time);
 	}
 
-	INSTR_TIME_SET_CURRENT(end_time);
+	if (fast_timing)
+		INSTR_TIME_SET_CURRENT_FAST(end_time);
+	else
+		INSTR_TIME_SET_CURRENT(end_time);
 
 	INSTR_TIME_SUBTRACT(end_time, start_time);
 
diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h
index e2e339a0c4f..f02296f1026 100644
--- a/src/include/portability/instr_time.h
+++ b/src/include/portability/instr_time.h
@@ -112,10 +112,13 @@ extern int64 max_ticks_no_overflow;
  */
 #if defined(__darwin__) && defined(CLOCK_MONOTONIC_RAW)
 #define PG_INSTR_CLOCK	CLOCK_MONOTONIC_RAW
+#define PG_INSTR_CLOCK_NAME	"clock_gettime (CLOCK_MONOTONIC_RAW)"
 #elif defined(CLOCK_MONOTONIC)
 #define PG_INSTR_CLOCK	CLOCK_MONOTONIC
+#define PG_INSTR_CLOCK_NAME	"clock_gettime (CLOCK_MONOTONIC)"
 #else
 #define PG_INSTR_CLOCK	CLOCK_REALTIME
+#define PG_INSTR_CLOCK_NAME	"clock_gettime (CLOCK_REALTIME)"
 #endif
 
 #if defined(__x86_64__) && defined(__linux__)
@@ -174,7 +177,7 @@ pg_get_ticks(void)
 }
 
 static inline int64_t
-pg_ticks_to_ns(instr_time t)
+pg_ticks_to_ns(int64 ticks)
 {
 	/*
 	 * Would multiplication overflow? If so perform computation in two parts.
@@ -183,7 +186,7 @@ pg_ticks_to_ns(instr_time t)
 	 */
 	int64		ns = 0;
 
-	if (unlikely(t.ticks > max_ticks_no_overflow))
+	if (unlikely(ticks > max_ticks_no_overflow))
 	{
 		/*
 		 * Compute how often the maximum number of ticks fits completely into
@@ -192,7 +195,7 @@ pg_ticks_to_ns(instr_time t)
 		 * value. In a 2nd step we adjust the number of elapsed ticks and
 		 * convert the remaining ticks.
 		 */
-		int64		count = t.ticks / max_ticks_no_overflow;
+		int64		count = ticks / max_ticks_no_overflow;
 		int64		max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION;
 
 		ns = max_ns * count;
@@ -201,11 +204,11 @@ pg_ticks_to_ns(instr_time t)
 		 * Subtract the ticks that we now already accounted for, so that they
 		 * don't get counted twice.
 		 */
-		t.ticks -= count * max_ticks_no_overflow;
-		Assert(t.ticks >= 0);
+		ticks -= count * max_ticks_no_overflow;
+		Assert(ticks >= 0);
 	}
 
-	ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION;
+	ns += ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION;
 	return ns;
 }
 
@@ -226,14 +229,14 @@ pg_initialize_get_ticks()
 #define INSTR_TIME_SET_CURRENT(t) \
 	((t) = pg_get_ticks())
 
-#define INSTR_TIME_GET_NANOSEC(t) \
-	pg_ticks_to_ns(t)
-
+#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \
+	(pg_ticks_to_ns(ticks))
 
 #else							/* WIN32 */
 
 
 /* Use QueryPerformanceCounter() */
+#define PG_INSTR_CLOCK_NAME	"QueryPerformanceCounter"
 
 /* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */
 static inline instr_time
@@ -265,8 +268,8 @@ GetTimerFrequency(void)
 #define INSTR_TIME_SET_CURRENT(t) \
 	((t) = pg_query_performance_counter())
 
-#define INSTR_TIME_GET_NANOSEC(t) \
-	((int64) ((t).ticks * ((double) NS_PER_S / GetTimerFrequency())))
+#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \
+	((int64) ((ticks) * ((double) NS_PER_S / GetTimerFrequency())))
 
 #endif							/* WIN32 */
 
@@ -285,9 +288,14 @@ GetTimerFrequency(void)
 #define INSTR_TIME_SUBTRACT(x,y) \
 	((x).ticks -= (y).ticks)
 
+#define INSTR_TIME_DIFF_NANOSEC(x,y) \
+	(INSTR_TIME_TICKS_TO_NANOSEC((x).ticks - (y).ticks))
+
 #define INSTR_TIME_ACCUM_DIFF(x,y,z) \
 	((x).ticks += (y).ticks - (z).ticks)
 
+#define INSTR_TIME_GET_NANOSEC(t) \
+	(INSTR_TIME_TICKS_TO_NANOSEC((t).ticks))
 
 #define INSTR_TIME_GET_DOUBLE(t) \
 	((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S)
-- 
2.47.3


--vtqqtrpooseurzip--





^ permalink  raw  reply  [nested|flat] 265+ messages in thread

* [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source
@ 2025-07-27 15:48  Lukas Fittl <[email protected]>
  0 siblings, 0 replies; 265+ messages in thread

From: Lukas Fittl @ 2025-07-27 15:48 UTC (permalink / raw)

In passing also reduce the per-loop overhead caused by repeated divisions
in INSTR_TIME_GET_NANOSEC when the ticks variable has become very large,
instead diff first and then turn it into nanosecs.
---
 src/bin/pg_test_timing/pg_test_timing.c | 59 +++++++++++++++++++------
 src/include/portability/instr_time.h    | 30 ++++++++-----
 2 files changed, 65 insertions(+), 24 deletions(-)

diff --git a/src/bin/pg_test_timing/pg_test_timing.c b/src/bin/pg_test_timing/pg_test_timing.c
index a5621251afc..b77ef2063b6 100644
--- a/src/bin/pg_test_timing/pg_test_timing.c
+++ b/src/bin/pg_test_timing/pg_test_timing.c
@@ -16,6 +16,7 @@ static const char *progname;
 
 static unsigned int test_duration = 3;
 static double max_rprct = 99.99;
+static bool fast_timing = false;
 
 /* record duration in powers of 2 nanoseconds */
 static long long int histogram[32];
@@ -56,6 +57,7 @@ handle_args(int argc, char *argv[])
 	static struct option long_options[] = {
 		{"duration", required_argument, NULL, 'd'},
 		{"cutoff", required_argument, NULL, 'c'},
+		{"fast", no_argument, NULL, 'f'},
 		{NULL, 0, NULL, 0}
 	};
 
@@ -68,7 +70,7 @@ handle_args(int argc, char *argv[])
 	{
 		if (strcmp(argv[1], "--help") == 0 || strcmp(argv[1], "-?") == 0)
 		{
-			printf(_("Usage: %s [-d DURATION] [-c CUTOFF]\n"), progname);
+			printf(_("Usage: %s [-d DURATION] [-c CUTOFF] [--fast]\n"), progname);
 			exit(0);
 		}
 		if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0)
@@ -78,7 +80,7 @@ handle_args(int argc, char *argv[])
 		}
 	}
 
-	while ((option = getopt_long(argc, argv, "d:c:",
+	while ((option = getopt_long(argc, argv, "d:c:f:",
 								 long_options, &optindex)) != -1)
 	{
 		switch (option)
@@ -125,6 +127,10 @@ handle_args(int argc, char *argv[])
 				}
 				break;
 
+			case 'f':
+				fast_timing = true;
+				break;
+
 			default:
 				fprintf(stderr, _("Try \"%s --help\" for more information.\n"),
 						progname);
@@ -155,11 +161,31 @@ test_timing(unsigned int duration)
 	uint64		total_time;
 	int64		time_elapsed = 0;
 	uint64		loop_count = 0;
-	uint64		prev,
-				cur;
 	instr_time	start_time,
 				end_time,
-				temp;
+				prev,
+				cur;
+	char	   *time_source = NULL;
+	bool		fast_timing_used = false;
+
+	INSTR_TIME_INITIALIZE();
+
+#if !defined(WIN32) && defined(__x86_64__) && defined(__linux__)
+	if (fast_timing && has_rdtsc)
+	{
+		time_source = "RDTSC";
+		fast_timing_used = true;
+	}
+	else if (has_rdtscp)
+		time_source = "RDTSCP";
+	else
+		time_source = PG_INSTR_CLOCK_NAME;
+#else
+	time_source = PG_INSTR_CLOCK_NAME;
+#endif
+	if (fast_timing && !fast_timing_used)
+		printf(_("Warning: Fast timing requested, but not available - regular timing source will be used\n"));
+	printf(_("Time source: %s\n"), time_source);
 
 	/*
 	 * Pre-zero the statistics data structures.  They're already zero by
@@ -173,8 +199,11 @@ test_timing(unsigned int duration)
 
 	total_time = duration > 0 ? duration * INT64CONST(1000000000) : 0;
 
-	INSTR_TIME_SET_CURRENT(start_time);
-	cur = INSTR_TIME_GET_NANOSEC(start_time);
+	if (fast_timing)
+		INSTR_TIME_SET_CURRENT_FAST(start_time);
+	else
+		INSTR_TIME_SET_CURRENT(start_time);
+	cur = start_time;
 
 	while (time_elapsed < total_time)
 	{
@@ -182,9 +211,11 @@ test_timing(unsigned int duration)
 					bits;
 
 		prev = cur;
-		INSTR_TIME_SET_CURRENT(temp);
-		cur = INSTR_TIME_GET_NANOSEC(temp);
-		diff = cur - prev;
+		if (fast_timing)
+			INSTR_TIME_SET_CURRENT_FAST(cur);
+		else
+			INSTR_TIME_SET_CURRENT(cur);
+		diff = INSTR_TIME_DIFF_NANOSEC(cur, prev);
 
 		/* Did time go backwards? */
 		if (unlikely(diff < 0))
@@ -217,11 +248,13 @@ test_timing(unsigned int duration)
 			largest_diff_count++;
 
 		loop_count++;
-		INSTR_TIME_SUBTRACT(temp, start_time);
-		time_elapsed = INSTR_TIME_GET_NANOSEC(temp);
+		time_elapsed = INSTR_TIME_DIFF_NANOSEC(cur, start_time);
 	}
 
-	INSTR_TIME_SET_CURRENT(end_time);
+	if (fast_timing)
+		INSTR_TIME_SET_CURRENT_FAST(end_time);
+	else
+		INSTR_TIME_SET_CURRENT(end_time);
 
 	INSTR_TIME_SUBTRACT(end_time, start_time);
 
diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h
index e2e339a0c4f..f02296f1026 100644
--- a/src/include/portability/instr_time.h
+++ b/src/include/portability/instr_time.h
@@ -112,10 +112,13 @@ extern int64 max_ticks_no_overflow;
  */
 #if defined(__darwin__) && defined(CLOCK_MONOTONIC_RAW)
 #define PG_INSTR_CLOCK	CLOCK_MONOTONIC_RAW
+#define PG_INSTR_CLOCK_NAME	"clock_gettime (CLOCK_MONOTONIC_RAW)"
 #elif defined(CLOCK_MONOTONIC)
 #define PG_INSTR_CLOCK	CLOCK_MONOTONIC
+#define PG_INSTR_CLOCK_NAME	"clock_gettime (CLOCK_MONOTONIC)"
 #else
 #define PG_INSTR_CLOCK	CLOCK_REALTIME
+#define PG_INSTR_CLOCK_NAME	"clock_gettime (CLOCK_REALTIME)"
 #endif
 
 #if defined(__x86_64__) && defined(__linux__)
@@ -174,7 +177,7 @@ pg_get_ticks(void)
 }
 
 static inline int64_t
-pg_ticks_to_ns(instr_time t)
+pg_ticks_to_ns(int64 ticks)
 {
 	/*
 	 * Would multiplication overflow? If so perform computation in two parts.
@@ -183,7 +186,7 @@ pg_ticks_to_ns(instr_time t)
 	 */
 	int64		ns = 0;
 
-	if (unlikely(t.ticks > max_ticks_no_overflow))
+	if (unlikely(ticks > max_ticks_no_overflow))
 	{
 		/*
 		 * Compute how often the maximum number of ticks fits completely into
@@ -192,7 +195,7 @@ pg_ticks_to_ns(instr_time t)
 		 * value. In a 2nd step we adjust the number of elapsed ticks and
 		 * convert the remaining ticks.
 		 */
-		int64		count = t.ticks / max_ticks_no_overflow;
+		int64		count = ticks / max_ticks_no_overflow;
 		int64		max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION;
 
 		ns = max_ns * count;
@@ -201,11 +204,11 @@ pg_ticks_to_ns(instr_time t)
 		 * Subtract the ticks that we now already accounted for, so that they
 		 * don't get counted twice.
 		 */
-		t.ticks -= count * max_ticks_no_overflow;
-		Assert(t.ticks >= 0);
+		ticks -= count * max_ticks_no_overflow;
+		Assert(ticks >= 0);
 	}
 
-	ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION;
+	ns += ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION;
 	return ns;
 }
 
@@ -226,14 +229,14 @@ pg_initialize_get_ticks()
 #define INSTR_TIME_SET_CURRENT(t) \
 	((t) = pg_get_ticks())
 
-#define INSTR_TIME_GET_NANOSEC(t) \
-	pg_ticks_to_ns(t)
-
+#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \
+	(pg_ticks_to_ns(ticks))
 
 #else							/* WIN32 */
 
 
 /* Use QueryPerformanceCounter() */
+#define PG_INSTR_CLOCK_NAME	"QueryPerformanceCounter"
 
 /* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */
 static inline instr_time
@@ -265,8 +268,8 @@ GetTimerFrequency(void)
 #define INSTR_TIME_SET_CURRENT(t) \
 	((t) = pg_query_performance_counter())
 
-#define INSTR_TIME_GET_NANOSEC(t) \
-	((int64) ((t).ticks * ((double) NS_PER_S / GetTimerFrequency())))
+#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \
+	((int64) ((ticks) * ((double) NS_PER_S / GetTimerFrequency())))
 
 #endif							/* WIN32 */
 
@@ -285,9 +288,14 @@ GetTimerFrequency(void)
 #define INSTR_TIME_SUBTRACT(x,y) \
 	((x).ticks -= (y).ticks)
 
+#define INSTR_TIME_DIFF_NANOSEC(x,y) \
+	(INSTR_TIME_TICKS_TO_NANOSEC((x).ticks - (y).ticks))
+
 #define INSTR_TIME_ACCUM_DIFF(x,y,z) \
 	((x).ticks += (y).ticks - (z).ticks)
 
+#define INSTR_TIME_GET_NANOSEC(t) \
+	(INSTR_TIME_TICKS_TO_NANOSEC((t).ticks))
 
 #define INSTR_TIME_GET_DOUBLE(t) \
 	((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S)
-- 
2.47.3


--vtqqtrpooseurzip--





^ permalink  raw  reply  [nested|flat] 265+ messages in thread

* [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source
@ 2025-07-27 15:48  Lukas Fittl <[email protected]>
  0 siblings, 0 replies; 265+ messages in thread

From: Lukas Fittl @ 2025-07-27 15:48 UTC (permalink / raw)

In passing also reduce the per-loop overhead caused by repeated divisions
in INSTR_TIME_GET_NANOSEC when the ticks variable has become very large,
instead diff first and then turn it into nanosecs.
---
 src/bin/pg_test_timing/pg_test_timing.c | 59 +++++++++++++++++++------
 src/include/portability/instr_time.h    | 30 ++++++++-----
 2 files changed, 65 insertions(+), 24 deletions(-)

diff --git a/src/bin/pg_test_timing/pg_test_timing.c b/src/bin/pg_test_timing/pg_test_timing.c
index a5621251afc..b77ef2063b6 100644
--- a/src/bin/pg_test_timing/pg_test_timing.c
+++ b/src/bin/pg_test_timing/pg_test_timing.c
@@ -16,6 +16,7 @@ static const char *progname;
 
 static unsigned int test_duration = 3;
 static double max_rprct = 99.99;
+static bool fast_timing = false;
 
 /* record duration in powers of 2 nanoseconds */
 static long long int histogram[32];
@@ -56,6 +57,7 @@ handle_args(int argc, char *argv[])
 	static struct option long_options[] = {
 		{"duration", required_argument, NULL, 'd'},
 		{"cutoff", required_argument, NULL, 'c'},
+		{"fast", no_argument, NULL, 'f'},
 		{NULL, 0, NULL, 0}
 	};
 
@@ -68,7 +70,7 @@ handle_args(int argc, char *argv[])
 	{
 		if (strcmp(argv[1], "--help") == 0 || strcmp(argv[1], "-?") == 0)
 		{
-			printf(_("Usage: %s [-d DURATION] [-c CUTOFF]\n"), progname);
+			printf(_("Usage: %s [-d DURATION] [-c CUTOFF] [--fast]\n"), progname);
 			exit(0);
 		}
 		if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0)
@@ -78,7 +80,7 @@ handle_args(int argc, char *argv[])
 		}
 	}
 
-	while ((option = getopt_long(argc, argv, "d:c:",
+	while ((option = getopt_long(argc, argv, "d:c:f:",
 								 long_options, &optindex)) != -1)
 	{
 		switch (option)
@@ -125,6 +127,10 @@ handle_args(int argc, char *argv[])
 				}
 				break;
 
+			case 'f':
+				fast_timing = true;
+				break;
+
 			default:
 				fprintf(stderr, _("Try \"%s --help\" for more information.\n"),
 						progname);
@@ -155,11 +161,31 @@ test_timing(unsigned int duration)
 	uint64		total_time;
 	int64		time_elapsed = 0;
 	uint64		loop_count = 0;
-	uint64		prev,
-				cur;
 	instr_time	start_time,
 				end_time,
-				temp;
+				prev,
+				cur;
+	char	   *time_source = NULL;
+	bool		fast_timing_used = false;
+
+	INSTR_TIME_INITIALIZE();
+
+#if !defined(WIN32) && defined(__x86_64__) && defined(__linux__)
+	if (fast_timing && has_rdtsc)
+	{
+		time_source = "RDTSC";
+		fast_timing_used = true;
+	}
+	else if (has_rdtscp)
+		time_source = "RDTSCP";
+	else
+		time_source = PG_INSTR_CLOCK_NAME;
+#else
+	time_source = PG_INSTR_CLOCK_NAME;
+#endif
+	if (fast_timing && !fast_timing_used)
+		printf(_("Warning: Fast timing requested, but not available - regular timing source will be used\n"));
+	printf(_("Time source: %s\n"), time_source);
 
 	/*
 	 * Pre-zero the statistics data structures.  They're already zero by
@@ -173,8 +199,11 @@ test_timing(unsigned int duration)
 
 	total_time = duration > 0 ? duration * INT64CONST(1000000000) : 0;
 
-	INSTR_TIME_SET_CURRENT(start_time);
-	cur = INSTR_TIME_GET_NANOSEC(start_time);
+	if (fast_timing)
+		INSTR_TIME_SET_CURRENT_FAST(start_time);
+	else
+		INSTR_TIME_SET_CURRENT(start_time);
+	cur = start_time;
 
 	while (time_elapsed < total_time)
 	{
@@ -182,9 +211,11 @@ test_timing(unsigned int duration)
 					bits;
 
 		prev = cur;
-		INSTR_TIME_SET_CURRENT(temp);
-		cur = INSTR_TIME_GET_NANOSEC(temp);
-		diff = cur - prev;
+		if (fast_timing)
+			INSTR_TIME_SET_CURRENT_FAST(cur);
+		else
+			INSTR_TIME_SET_CURRENT(cur);
+		diff = INSTR_TIME_DIFF_NANOSEC(cur, prev);
 
 		/* Did time go backwards? */
 		if (unlikely(diff < 0))
@@ -217,11 +248,13 @@ test_timing(unsigned int duration)
 			largest_diff_count++;
 
 		loop_count++;
-		INSTR_TIME_SUBTRACT(temp, start_time);
-		time_elapsed = INSTR_TIME_GET_NANOSEC(temp);
+		time_elapsed = INSTR_TIME_DIFF_NANOSEC(cur, start_time);
 	}
 
-	INSTR_TIME_SET_CURRENT(end_time);
+	if (fast_timing)
+		INSTR_TIME_SET_CURRENT_FAST(end_time);
+	else
+		INSTR_TIME_SET_CURRENT(end_time);
 
 	INSTR_TIME_SUBTRACT(end_time, start_time);
 
diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h
index e2e339a0c4f..f02296f1026 100644
--- a/src/include/portability/instr_time.h
+++ b/src/include/portability/instr_time.h
@@ -112,10 +112,13 @@ extern int64 max_ticks_no_overflow;
  */
 #if defined(__darwin__) && defined(CLOCK_MONOTONIC_RAW)
 #define PG_INSTR_CLOCK	CLOCK_MONOTONIC_RAW
+#define PG_INSTR_CLOCK_NAME	"clock_gettime (CLOCK_MONOTONIC_RAW)"
 #elif defined(CLOCK_MONOTONIC)
 #define PG_INSTR_CLOCK	CLOCK_MONOTONIC
+#define PG_INSTR_CLOCK_NAME	"clock_gettime (CLOCK_MONOTONIC)"
 #else
 #define PG_INSTR_CLOCK	CLOCK_REALTIME
+#define PG_INSTR_CLOCK_NAME	"clock_gettime (CLOCK_REALTIME)"
 #endif
 
 #if defined(__x86_64__) && defined(__linux__)
@@ -174,7 +177,7 @@ pg_get_ticks(void)
 }
 
 static inline int64_t
-pg_ticks_to_ns(instr_time t)
+pg_ticks_to_ns(int64 ticks)
 {
 	/*
 	 * Would multiplication overflow? If so perform computation in two parts.
@@ -183,7 +186,7 @@ pg_ticks_to_ns(instr_time t)
 	 */
 	int64		ns = 0;
 
-	if (unlikely(t.ticks > max_ticks_no_overflow))
+	if (unlikely(ticks > max_ticks_no_overflow))
 	{
 		/*
 		 * Compute how often the maximum number of ticks fits completely into
@@ -192,7 +195,7 @@ pg_ticks_to_ns(instr_time t)
 		 * value. In a 2nd step we adjust the number of elapsed ticks and
 		 * convert the remaining ticks.
 		 */
-		int64		count = t.ticks / max_ticks_no_overflow;
+		int64		count = ticks / max_ticks_no_overflow;
 		int64		max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION;
 
 		ns = max_ns * count;
@@ -201,11 +204,11 @@ pg_ticks_to_ns(instr_time t)
 		 * Subtract the ticks that we now already accounted for, so that they
 		 * don't get counted twice.
 		 */
-		t.ticks -= count * max_ticks_no_overflow;
-		Assert(t.ticks >= 0);
+		ticks -= count * max_ticks_no_overflow;
+		Assert(ticks >= 0);
 	}
 
-	ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION;
+	ns += ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION;
 	return ns;
 }
 
@@ -226,14 +229,14 @@ pg_initialize_get_ticks()
 #define INSTR_TIME_SET_CURRENT(t) \
 	((t) = pg_get_ticks())
 
-#define INSTR_TIME_GET_NANOSEC(t) \
-	pg_ticks_to_ns(t)
-
+#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \
+	(pg_ticks_to_ns(ticks))
 
 #else							/* WIN32 */
 
 
 /* Use QueryPerformanceCounter() */
+#define PG_INSTR_CLOCK_NAME	"QueryPerformanceCounter"
 
 /* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */
 static inline instr_time
@@ -265,8 +268,8 @@ GetTimerFrequency(void)
 #define INSTR_TIME_SET_CURRENT(t) \
 	((t) = pg_query_performance_counter())
 
-#define INSTR_TIME_GET_NANOSEC(t) \
-	((int64) ((t).ticks * ((double) NS_PER_S / GetTimerFrequency())))
+#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \
+	((int64) ((ticks) * ((double) NS_PER_S / GetTimerFrequency())))
 
 #endif							/* WIN32 */
 
@@ -285,9 +288,14 @@ GetTimerFrequency(void)
 #define INSTR_TIME_SUBTRACT(x,y) \
 	((x).ticks -= (y).ticks)
 
+#define INSTR_TIME_DIFF_NANOSEC(x,y) \
+	(INSTR_TIME_TICKS_TO_NANOSEC((x).ticks - (y).ticks))
+
 #define INSTR_TIME_ACCUM_DIFF(x,y,z) \
 	((x).ticks += (y).ticks - (z).ticks)
 
+#define INSTR_TIME_GET_NANOSEC(t) \
+	(INSTR_TIME_TICKS_TO_NANOSEC((t).ticks))
 
 #define INSTR_TIME_GET_DOUBLE(t) \
 	((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S)
-- 
2.47.3


--vtqqtrpooseurzip--





^ permalink  raw  reply  [nested|flat] 265+ messages in thread

* [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source
@ 2025-07-27 15:48  Lukas Fittl <[email protected]>
  0 siblings, 0 replies; 265+ messages in thread

From: Lukas Fittl @ 2025-07-27 15:48 UTC (permalink / raw)

In passing also reduce the per-loop overhead caused by repeated divisions
in INSTR_TIME_GET_NANOSEC when the ticks variable has become very large,
instead diff first and then turn it into nanosecs.
---
 src/bin/pg_test_timing/pg_test_timing.c | 59 +++++++++++++++++++------
 src/include/portability/instr_time.h    | 30 ++++++++-----
 2 files changed, 65 insertions(+), 24 deletions(-)

diff --git a/src/bin/pg_test_timing/pg_test_timing.c b/src/bin/pg_test_timing/pg_test_timing.c
index a5621251afc..b77ef2063b6 100644
--- a/src/bin/pg_test_timing/pg_test_timing.c
+++ b/src/bin/pg_test_timing/pg_test_timing.c
@@ -16,6 +16,7 @@ static const char *progname;
 
 static unsigned int test_duration = 3;
 static double max_rprct = 99.99;
+static bool fast_timing = false;
 
 /* record duration in powers of 2 nanoseconds */
 static long long int histogram[32];
@@ -56,6 +57,7 @@ handle_args(int argc, char *argv[])
 	static struct option long_options[] = {
 		{"duration", required_argument, NULL, 'd'},
 		{"cutoff", required_argument, NULL, 'c'},
+		{"fast", no_argument, NULL, 'f'},
 		{NULL, 0, NULL, 0}
 	};
 
@@ -68,7 +70,7 @@ handle_args(int argc, char *argv[])
 	{
 		if (strcmp(argv[1], "--help") == 0 || strcmp(argv[1], "-?") == 0)
 		{
-			printf(_("Usage: %s [-d DURATION] [-c CUTOFF]\n"), progname);
+			printf(_("Usage: %s [-d DURATION] [-c CUTOFF] [--fast]\n"), progname);
 			exit(0);
 		}
 		if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0)
@@ -78,7 +80,7 @@ handle_args(int argc, char *argv[])
 		}
 	}
 
-	while ((option = getopt_long(argc, argv, "d:c:",
+	while ((option = getopt_long(argc, argv, "d:c:f:",
 								 long_options, &optindex)) != -1)
 	{
 		switch (option)
@@ -125,6 +127,10 @@ handle_args(int argc, char *argv[])
 				}
 				break;
 
+			case 'f':
+				fast_timing = true;
+				break;
+
 			default:
 				fprintf(stderr, _("Try \"%s --help\" for more information.\n"),
 						progname);
@@ -155,11 +161,31 @@ test_timing(unsigned int duration)
 	uint64		total_time;
 	int64		time_elapsed = 0;
 	uint64		loop_count = 0;
-	uint64		prev,
-				cur;
 	instr_time	start_time,
 				end_time,
-				temp;
+				prev,
+				cur;
+	char	   *time_source = NULL;
+	bool		fast_timing_used = false;
+
+	INSTR_TIME_INITIALIZE();
+
+#if !defined(WIN32) && defined(__x86_64__) && defined(__linux__)
+	if (fast_timing && has_rdtsc)
+	{
+		time_source = "RDTSC";
+		fast_timing_used = true;
+	}
+	else if (has_rdtscp)
+		time_source = "RDTSCP";
+	else
+		time_source = PG_INSTR_CLOCK_NAME;
+#else
+	time_source = PG_INSTR_CLOCK_NAME;
+#endif
+	if (fast_timing && !fast_timing_used)
+		printf(_("Warning: Fast timing requested, but not available - regular timing source will be used\n"));
+	printf(_("Time source: %s\n"), time_source);
 
 	/*
 	 * Pre-zero the statistics data structures.  They're already zero by
@@ -173,8 +199,11 @@ test_timing(unsigned int duration)
 
 	total_time = duration > 0 ? duration * INT64CONST(1000000000) : 0;
 
-	INSTR_TIME_SET_CURRENT(start_time);
-	cur = INSTR_TIME_GET_NANOSEC(start_time);
+	if (fast_timing)
+		INSTR_TIME_SET_CURRENT_FAST(start_time);
+	else
+		INSTR_TIME_SET_CURRENT(start_time);
+	cur = start_time;
 
 	while (time_elapsed < total_time)
 	{
@@ -182,9 +211,11 @@ test_timing(unsigned int duration)
 					bits;
 
 		prev = cur;
-		INSTR_TIME_SET_CURRENT(temp);
-		cur = INSTR_TIME_GET_NANOSEC(temp);
-		diff = cur - prev;
+		if (fast_timing)
+			INSTR_TIME_SET_CURRENT_FAST(cur);
+		else
+			INSTR_TIME_SET_CURRENT(cur);
+		diff = INSTR_TIME_DIFF_NANOSEC(cur, prev);
 
 		/* Did time go backwards? */
 		if (unlikely(diff < 0))
@@ -217,11 +248,13 @@ test_timing(unsigned int duration)
 			largest_diff_count++;
 
 		loop_count++;
-		INSTR_TIME_SUBTRACT(temp, start_time);
-		time_elapsed = INSTR_TIME_GET_NANOSEC(temp);
+		time_elapsed = INSTR_TIME_DIFF_NANOSEC(cur, start_time);
 	}
 
-	INSTR_TIME_SET_CURRENT(end_time);
+	if (fast_timing)
+		INSTR_TIME_SET_CURRENT_FAST(end_time);
+	else
+		INSTR_TIME_SET_CURRENT(end_time);
 
 	INSTR_TIME_SUBTRACT(end_time, start_time);
 
diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h
index e2e339a0c4f..f02296f1026 100644
--- a/src/include/portability/instr_time.h
+++ b/src/include/portability/instr_time.h
@@ -112,10 +112,13 @@ extern int64 max_ticks_no_overflow;
  */
 #if defined(__darwin__) && defined(CLOCK_MONOTONIC_RAW)
 #define PG_INSTR_CLOCK	CLOCK_MONOTONIC_RAW
+#define PG_INSTR_CLOCK_NAME	"clock_gettime (CLOCK_MONOTONIC_RAW)"
 #elif defined(CLOCK_MONOTONIC)
 #define PG_INSTR_CLOCK	CLOCK_MONOTONIC
+#define PG_INSTR_CLOCK_NAME	"clock_gettime (CLOCK_MONOTONIC)"
 #else
 #define PG_INSTR_CLOCK	CLOCK_REALTIME
+#define PG_INSTR_CLOCK_NAME	"clock_gettime (CLOCK_REALTIME)"
 #endif
 
 #if defined(__x86_64__) && defined(__linux__)
@@ -174,7 +177,7 @@ pg_get_ticks(void)
 }
 
 static inline int64_t
-pg_ticks_to_ns(instr_time t)
+pg_ticks_to_ns(int64 ticks)
 {
 	/*
 	 * Would multiplication overflow? If so perform computation in two parts.
@@ -183,7 +186,7 @@ pg_ticks_to_ns(instr_time t)
 	 */
 	int64		ns = 0;
 
-	if (unlikely(t.ticks > max_ticks_no_overflow))
+	if (unlikely(ticks > max_ticks_no_overflow))
 	{
 		/*
 		 * Compute how often the maximum number of ticks fits completely into
@@ -192,7 +195,7 @@ pg_ticks_to_ns(instr_time t)
 		 * value. In a 2nd step we adjust the number of elapsed ticks and
 		 * convert the remaining ticks.
 		 */
-		int64		count = t.ticks / max_ticks_no_overflow;
+		int64		count = ticks / max_ticks_no_overflow;
 		int64		max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION;
 
 		ns = max_ns * count;
@@ -201,11 +204,11 @@ pg_ticks_to_ns(instr_time t)
 		 * Subtract the ticks that we now already accounted for, so that they
 		 * don't get counted twice.
 		 */
-		t.ticks -= count * max_ticks_no_overflow;
-		Assert(t.ticks >= 0);
+		ticks -= count * max_ticks_no_overflow;
+		Assert(ticks >= 0);
 	}
 
-	ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION;
+	ns += ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION;
 	return ns;
 }
 
@@ -226,14 +229,14 @@ pg_initialize_get_ticks()
 #define INSTR_TIME_SET_CURRENT(t) \
 	((t) = pg_get_ticks())
 
-#define INSTR_TIME_GET_NANOSEC(t) \
-	pg_ticks_to_ns(t)
-
+#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \
+	(pg_ticks_to_ns(ticks))
 
 #else							/* WIN32 */
 
 
 /* Use QueryPerformanceCounter() */
+#define PG_INSTR_CLOCK_NAME	"QueryPerformanceCounter"
 
 /* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */
 static inline instr_time
@@ -265,8 +268,8 @@ GetTimerFrequency(void)
 #define INSTR_TIME_SET_CURRENT(t) \
 	((t) = pg_query_performance_counter())
 
-#define INSTR_TIME_GET_NANOSEC(t) \
-	((int64) ((t).ticks * ((double) NS_PER_S / GetTimerFrequency())))
+#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \
+	((int64) ((ticks) * ((double) NS_PER_S / GetTimerFrequency())))
 
 #endif							/* WIN32 */
 
@@ -285,9 +288,14 @@ GetTimerFrequency(void)
 #define INSTR_TIME_SUBTRACT(x,y) \
 	((x).ticks -= (y).ticks)
 
+#define INSTR_TIME_DIFF_NANOSEC(x,y) \
+	(INSTR_TIME_TICKS_TO_NANOSEC((x).ticks - (y).ticks))
+
 #define INSTR_TIME_ACCUM_DIFF(x,y,z) \
 	((x).ticks += (y).ticks - (z).ticks)
 
+#define INSTR_TIME_GET_NANOSEC(t) \
+	(INSTR_TIME_TICKS_TO_NANOSEC((t).ticks))
 
 #define INSTR_TIME_GET_DOUBLE(t) \
 	((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S)
-- 
2.47.3


--vtqqtrpooseurzip--





^ permalink  raw  reply  [nested|flat] 265+ messages in thread

* [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source
@ 2025-07-27 15:48  Lukas Fittl <[email protected]>
  0 siblings, 0 replies; 265+ messages in thread

From: Lukas Fittl @ 2025-07-27 15:48 UTC (permalink / raw)

In passing also reduce the per-loop overhead caused by repeated divisions
in INSTR_TIME_GET_NANOSEC when the ticks variable has become very large,
instead diff first and then turn it into nanosecs.
---
 src/bin/pg_test_timing/pg_test_timing.c | 59 +++++++++++++++++++------
 src/include/portability/instr_time.h    | 30 ++++++++-----
 2 files changed, 65 insertions(+), 24 deletions(-)

diff --git a/src/bin/pg_test_timing/pg_test_timing.c b/src/bin/pg_test_timing/pg_test_timing.c
index a5621251afc..b77ef2063b6 100644
--- a/src/bin/pg_test_timing/pg_test_timing.c
+++ b/src/bin/pg_test_timing/pg_test_timing.c
@@ -16,6 +16,7 @@ static const char *progname;
 
 static unsigned int test_duration = 3;
 static double max_rprct = 99.99;
+static bool fast_timing = false;
 
 /* record duration in powers of 2 nanoseconds */
 static long long int histogram[32];
@@ -56,6 +57,7 @@ handle_args(int argc, char *argv[])
 	static struct option long_options[] = {
 		{"duration", required_argument, NULL, 'd'},
 		{"cutoff", required_argument, NULL, 'c'},
+		{"fast", no_argument, NULL, 'f'},
 		{NULL, 0, NULL, 0}
 	};
 
@@ -68,7 +70,7 @@ handle_args(int argc, char *argv[])
 	{
 		if (strcmp(argv[1], "--help") == 0 || strcmp(argv[1], "-?") == 0)
 		{
-			printf(_("Usage: %s [-d DURATION] [-c CUTOFF]\n"), progname);
+			printf(_("Usage: %s [-d DURATION] [-c CUTOFF] [--fast]\n"), progname);
 			exit(0);
 		}
 		if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0)
@@ -78,7 +80,7 @@ handle_args(int argc, char *argv[])
 		}
 	}
 
-	while ((option = getopt_long(argc, argv, "d:c:",
+	while ((option = getopt_long(argc, argv, "d:c:f:",
 								 long_options, &optindex)) != -1)
 	{
 		switch (option)
@@ -125,6 +127,10 @@ handle_args(int argc, char *argv[])
 				}
 				break;
 
+			case 'f':
+				fast_timing = true;
+				break;
+
 			default:
 				fprintf(stderr, _("Try \"%s --help\" for more information.\n"),
 						progname);
@@ -155,11 +161,31 @@ test_timing(unsigned int duration)
 	uint64		total_time;
 	int64		time_elapsed = 0;
 	uint64		loop_count = 0;
-	uint64		prev,
-				cur;
 	instr_time	start_time,
 				end_time,
-				temp;
+				prev,
+				cur;
+	char	   *time_source = NULL;
+	bool		fast_timing_used = false;
+
+	INSTR_TIME_INITIALIZE();
+
+#if !defined(WIN32) && defined(__x86_64__) && defined(__linux__)
+	if (fast_timing && has_rdtsc)
+	{
+		time_source = "RDTSC";
+		fast_timing_used = true;
+	}
+	else if (has_rdtscp)
+		time_source = "RDTSCP";
+	else
+		time_source = PG_INSTR_CLOCK_NAME;
+#else
+	time_source = PG_INSTR_CLOCK_NAME;
+#endif
+	if (fast_timing && !fast_timing_used)
+		printf(_("Warning: Fast timing requested, but not available - regular timing source will be used\n"));
+	printf(_("Time source: %s\n"), time_source);
 
 	/*
 	 * Pre-zero the statistics data structures.  They're already zero by
@@ -173,8 +199,11 @@ test_timing(unsigned int duration)
 
 	total_time = duration > 0 ? duration * INT64CONST(1000000000) : 0;
 
-	INSTR_TIME_SET_CURRENT(start_time);
-	cur = INSTR_TIME_GET_NANOSEC(start_time);
+	if (fast_timing)
+		INSTR_TIME_SET_CURRENT_FAST(start_time);
+	else
+		INSTR_TIME_SET_CURRENT(start_time);
+	cur = start_time;
 
 	while (time_elapsed < total_time)
 	{
@@ -182,9 +211,11 @@ test_timing(unsigned int duration)
 					bits;
 
 		prev = cur;
-		INSTR_TIME_SET_CURRENT(temp);
-		cur = INSTR_TIME_GET_NANOSEC(temp);
-		diff = cur - prev;
+		if (fast_timing)
+			INSTR_TIME_SET_CURRENT_FAST(cur);
+		else
+			INSTR_TIME_SET_CURRENT(cur);
+		diff = INSTR_TIME_DIFF_NANOSEC(cur, prev);
 
 		/* Did time go backwards? */
 		if (unlikely(diff < 0))
@@ -217,11 +248,13 @@ test_timing(unsigned int duration)
 			largest_diff_count++;
 
 		loop_count++;
-		INSTR_TIME_SUBTRACT(temp, start_time);
-		time_elapsed = INSTR_TIME_GET_NANOSEC(temp);
+		time_elapsed = INSTR_TIME_DIFF_NANOSEC(cur, start_time);
 	}
 
-	INSTR_TIME_SET_CURRENT(end_time);
+	if (fast_timing)
+		INSTR_TIME_SET_CURRENT_FAST(end_time);
+	else
+		INSTR_TIME_SET_CURRENT(end_time);
 
 	INSTR_TIME_SUBTRACT(end_time, start_time);
 
diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h
index e2e339a0c4f..f02296f1026 100644
--- a/src/include/portability/instr_time.h
+++ b/src/include/portability/instr_time.h
@@ -112,10 +112,13 @@ extern int64 max_ticks_no_overflow;
  */
 #if defined(__darwin__) && defined(CLOCK_MONOTONIC_RAW)
 #define PG_INSTR_CLOCK	CLOCK_MONOTONIC_RAW
+#define PG_INSTR_CLOCK_NAME	"clock_gettime (CLOCK_MONOTONIC_RAW)"
 #elif defined(CLOCK_MONOTONIC)
 #define PG_INSTR_CLOCK	CLOCK_MONOTONIC
+#define PG_INSTR_CLOCK_NAME	"clock_gettime (CLOCK_MONOTONIC)"
 #else
 #define PG_INSTR_CLOCK	CLOCK_REALTIME
+#define PG_INSTR_CLOCK_NAME	"clock_gettime (CLOCK_REALTIME)"
 #endif
 
 #if defined(__x86_64__) && defined(__linux__)
@@ -174,7 +177,7 @@ pg_get_ticks(void)
 }
 
 static inline int64_t
-pg_ticks_to_ns(instr_time t)
+pg_ticks_to_ns(int64 ticks)
 {
 	/*
 	 * Would multiplication overflow? If so perform computation in two parts.
@@ -183,7 +186,7 @@ pg_ticks_to_ns(instr_time t)
 	 */
 	int64		ns = 0;
 
-	if (unlikely(t.ticks > max_ticks_no_overflow))
+	if (unlikely(ticks > max_ticks_no_overflow))
 	{
 		/*
 		 * Compute how often the maximum number of ticks fits completely into
@@ -192,7 +195,7 @@ pg_ticks_to_ns(instr_time t)
 		 * value. In a 2nd step we adjust the number of elapsed ticks and
 		 * convert the remaining ticks.
 		 */
-		int64		count = t.ticks / max_ticks_no_overflow;
+		int64		count = ticks / max_ticks_no_overflow;
 		int64		max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION;
 
 		ns = max_ns * count;
@@ -201,11 +204,11 @@ pg_ticks_to_ns(instr_time t)
 		 * Subtract the ticks that we now already accounted for, so that they
 		 * don't get counted twice.
 		 */
-		t.ticks -= count * max_ticks_no_overflow;
-		Assert(t.ticks >= 0);
+		ticks -= count * max_ticks_no_overflow;
+		Assert(ticks >= 0);
 	}
 
-	ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION;
+	ns += ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION;
 	return ns;
 }
 
@@ -226,14 +229,14 @@ pg_initialize_get_ticks()
 #define INSTR_TIME_SET_CURRENT(t) \
 	((t) = pg_get_ticks())
 
-#define INSTR_TIME_GET_NANOSEC(t) \
-	pg_ticks_to_ns(t)
-
+#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \
+	(pg_ticks_to_ns(ticks))
 
 #else							/* WIN32 */
 
 
 /* Use QueryPerformanceCounter() */
+#define PG_INSTR_CLOCK_NAME	"QueryPerformanceCounter"
 
 /* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */
 static inline instr_time
@@ -265,8 +268,8 @@ GetTimerFrequency(void)
 #define INSTR_TIME_SET_CURRENT(t) \
 	((t) = pg_query_performance_counter())
 
-#define INSTR_TIME_GET_NANOSEC(t) \
-	((int64) ((t).ticks * ((double) NS_PER_S / GetTimerFrequency())))
+#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \
+	((int64) ((ticks) * ((double) NS_PER_S / GetTimerFrequency())))
 
 #endif							/* WIN32 */
 
@@ -285,9 +288,14 @@ GetTimerFrequency(void)
 #define INSTR_TIME_SUBTRACT(x,y) \
 	((x).ticks -= (y).ticks)
 
+#define INSTR_TIME_DIFF_NANOSEC(x,y) \
+	(INSTR_TIME_TICKS_TO_NANOSEC((x).ticks - (y).ticks))
+
 #define INSTR_TIME_ACCUM_DIFF(x,y,z) \
 	((x).ticks += (y).ticks - (z).ticks)
 
+#define INSTR_TIME_GET_NANOSEC(t) \
+	(INSTR_TIME_TICKS_TO_NANOSEC((t).ticks))
 
 #define INSTR_TIME_GET_DOUBLE(t) \
 	((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S)
-- 
2.47.3


--vtqqtrpooseurzip--





^ permalink  raw  reply  [nested|flat] 265+ messages in thread

* [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source
@ 2025-07-27 15:48  Lukas Fittl <[email protected]>
  0 siblings, 0 replies; 265+ messages in thread

From: Lukas Fittl @ 2025-07-27 15:48 UTC (permalink / raw)

In passing also reduce the per-loop overhead caused by repeated divisions
in INSTR_TIME_GET_NANOSEC when the ticks variable has become very large,
instead diff first and then turn it into nanosecs.
---
 src/bin/pg_test_timing/pg_test_timing.c | 59 +++++++++++++++++++------
 src/include/portability/instr_time.h    | 30 ++++++++-----
 2 files changed, 65 insertions(+), 24 deletions(-)

diff --git a/src/bin/pg_test_timing/pg_test_timing.c b/src/bin/pg_test_timing/pg_test_timing.c
index a5621251afc..b77ef2063b6 100644
--- a/src/bin/pg_test_timing/pg_test_timing.c
+++ b/src/bin/pg_test_timing/pg_test_timing.c
@@ -16,6 +16,7 @@ static const char *progname;
 
 static unsigned int test_duration = 3;
 static double max_rprct = 99.99;
+static bool fast_timing = false;
 
 /* record duration in powers of 2 nanoseconds */
 static long long int histogram[32];
@@ -56,6 +57,7 @@ handle_args(int argc, char *argv[])
 	static struct option long_options[] = {
 		{"duration", required_argument, NULL, 'd'},
 		{"cutoff", required_argument, NULL, 'c'},
+		{"fast", no_argument, NULL, 'f'},
 		{NULL, 0, NULL, 0}
 	};
 
@@ -68,7 +70,7 @@ handle_args(int argc, char *argv[])
 	{
 		if (strcmp(argv[1], "--help") == 0 || strcmp(argv[1], "-?") == 0)
 		{
-			printf(_("Usage: %s [-d DURATION] [-c CUTOFF]\n"), progname);
+			printf(_("Usage: %s [-d DURATION] [-c CUTOFF] [--fast]\n"), progname);
 			exit(0);
 		}
 		if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0)
@@ -78,7 +80,7 @@ handle_args(int argc, char *argv[])
 		}
 	}
 
-	while ((option = getopt_long(argc, argv, "d:c:",
+	while ((option = getopt_long(argc, argv, "d:c:f:",
 								 long_options, &optindex)) != -1)
 	{
 		switch (option)
@@ -125,6 +127,10 @@ handle_args(int argc, char *argv[])
 				}
 				break;
 
+			case 'f':
+				fast_timing = true;
+				break;
+
 			default:
 				fprintf(stderr, _("Try \"%s --help\" for more information.\n"),
 						progname);
@@ -155,11 +161,31 @@ test_timing(unsigned int duration)
 	uint64		total_time;
 	int64		time_elapsed = 0;
 	uint64		loop_count = 0;
-	uint64		prev,
-				cur;
 	instr_time	start_time,
 				end_time,
-				temp;
+				prev,
+				cur;
+	char	   *time_source = NULL;
+	bool		fast_timing_used = false;
+
+	INSTR_TIME_INITIALIZE();
+
+#if !defined(WIN32) && defined(__x86_64__) && defined(__linux__)
+	if (fast_timing && has_rdtsc)
+	{
+		time_source = "RDTSC";
+		fast_timing_used = true;
+	}
+	else if (has_rdtscp)
+		time_source = "RDTSCP";
+	else
+		time_source = PG_INSTR_CLOCK_NAME;
+#else
+	time_source = PG_INSTR_CLOCK_NAME;
+#endif
+	if (fast_timing && !fast_timing_used)
+		printf(_("Warning: Fast timing requested, but not available - regular timing source will be used\n"));
+	printf(_("Time source: %s\n"), time_source);
 
 	/*
 	 * Pre-zero the statistics data structures.  They're already zero by
@@ -173,8 +199,11 @@ test_timing(unsigned int duration)
 
 	total_time = duration > 0 ? duration * INT64CONST(1000000000) : 0;
 
-	INSTR_TIME_SET_CURRENT(start_time);
-	cur = INSTR_TIME_GET_NANOSEC(start_time);
+	if (fast_timing)
+		INSTR_TIME_SET_CURRENT_FAST(start_time);
+	else
+		INSTR_TIME_SET_CURRENT(start_time);
+	cur = start_time;
 
 	while (time_elapsed < total_time)
 	{
@@ -182,9 +211,11 @@ test_timing(unsigned int duration)
 					bits;
 
 		prev = cur;
-		INSTR_TIME_SET_CURRENT(temp);
-		cur = INSTR_TIME_GET_NANOSEC(temp);
-		diff = cur - prev;
+		if (fast_timing)
+			INSTR_TIME_SET_CURRENT_FAST(cur);
+		else
+			INSTR_TIME_SET_CURRENT(cur);
+		diff = INSTR_TIME_DIFF_NANOSEC(cur, prev);
 
 		/* Did time go backwards? */
 		if (unlikely(diff < 0))
@@ -217,11 +248,13 @@ test_timing(unsigned int duration)
 			largest_diff_count++;
 
 		loop_count++;
-		INSTR_TIME_SUBTRACT(temp, start_time);
-		time_elapsed = INSTR_TIME_GET_NANOSEC(temp);
+		time_elapsed = INSTR_TIME_DIFF_NANOSEC(cur, start_time);
 	}
 
-	INSTR_TIME_SET_CURRENT(end_time);
+	if (fast_timing)
+		INSTR_TIME_SET_CURRENT_FAST(end_time);
+	else
+		INSTR_TIME_SET_CURRENT(end_time);
 
 	INSTR_TIME_SUBTRACT(end_time, start_time);
 
diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h
index e2e339a0c4f..f02296f1026 100644
--- a/src/include/portability/instr_time.h
+++ b/src/include/portability/instr_time.h
@@ -112,10 +112,13 @@ extern int64 max_ticks_no_overflow;
  */
 #if defined(__darwin__) && defined(CLOCK_MONOTONIC_RAW)
 #define PG_INSTR_CLOCK	CLOCK_MONOTONIC_RAW
+#define PG_INSTR_CLOCK_NAME	"clock_gettime (CLOCK_MONOTONIC_RAW)"
 #elif defined(CLOCK_MONOTONIC)
 #define PG_INSTR_CLOCK	CLOCK_MONOTONIC
+#define PG_INSTR_CLOCK_NAME	"clock_gettime (CLOCK_MONOTONIC)"
 #else
 #define PG_INSTR_CLOCK	CLOCK_REALTIME
+#define PG_INSTR_CLOCK_NAME	"clock_gettime (CLOCK_REALTIME)"
 #endif
 
 #if defined(__x86_64__) && defined(__linux__)
@@ -174,7 +177,7 @@ pg_get_ticks(void)
 }
 
 static inline int64_t
-pg_ticks_to_ns(instr_time t)
+pg_ticks_to_ns(int64 ticks)
 {
 	/*
 	 * Would multiplication overflow? If so perform computation in two parts.
@@ -183,7 +186,7 @@ pg_ticks_to_ns(instr_time t)
 	 */
 	int64		ns = 0;
 
-	if (unlikely(t.ticks > max_ticks_no_overflow))
+	if (unlikely(ticks > max_ticks_no_overflow))
 	{
 		/*
 		 * Compute how often the maximum number of ticks fits completely into
@@ -192,7 +195,7 @@ pg_ticks_to_ns(instr_time t)
 		 * value. In a 2nd step we adjust the number of elapsed ticks and
 		 * convert the remaining ticks.
 		 */
-		int64		count = t.ticks / max_ticks_no_overflow;
+		int64		count = ticks / max_ticks_no_overflow;
 		int64		max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION;
 
 		ns = max_ns * count;
@@ -201,11 +204,11 @@ pg_ticks_to_ns(instr_time t)
 		 * Subtract the ticks that we now already accounted for, so that they
 		 * don't get counted twice.
 		 */
-		t.ticks -= count * max_ticks_no_overflow;
-		Assert(t.ticks >= 0);
+		ticks -= count * max_ticks_no_overflow;
+		Assert(ticks >= 0);
 	}
 
-	ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION;
+	ns += ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION;
 	return ns;
 }
 
@@ -226,14 +229,14 @@ pg_initialize_get_ticks()
 #define INSTR_TIME_SET_CURRENT(t) \
 	((t) = pg_get_ticks())
 
-#define INSTR_TIME_GET_NANOSEC(t) \
-	pg_ticks_to_ns(t)
-
+#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \
+	(pg_ticks_to_ns(ticks))
 
 #else							/* WIN32 */
 
 
 /* Use QueryPerformanceCounter() */
+#define PG_INSTR_CLOCK_NAME	"QueryPerformanceCounter"
 
 /* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */
 static inline instr_time
@@ -265,8 +268,8 @@ GetTimerFrequency(void)
 #define INSTR_TIME_SET_CURRENT(t) \
 	((t) = pg_query_performance_counter())
 
-#define INSTR_TIME_GET_NANOSEC(t) \
-	((int64) ((t).ticks * ((double) NS_PER_S / GetTimerFrequency())))
+#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \
+	((int64) ((ticks) * ((double) NS_PER_S / GetTimerFrequency())))
 
 #endif							/* WIN32 */
 
@@ -285,9 +288,14 @@ GetTimerFrequency(void)
 #define INSTR_TIME_SUBTRACT(x,y) \
 	((x).ticks -= (y).ticks)
 
+#define INSTR_TIME_DIFF_NANOSEC(x,y) \
+	(INSTR_TIME_TICKS_TO_NANOSEC((x).ticks - (y).ticks))
+
 #define INSTR_TIME_ACCUM_DIFF(x,y,z) \
 	((x).ticks += (y).ticks - (z).ticks)
 
+#define INSTR_TIME_GET_NANOSEC(t) \
+	(INSTR_TIME_TICKS_TO_NANOSEC((t).ticks))
 
 #define INSTR_TIME_GET_DOUBLE(t) \
 	((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S)
-- 
2.47.3


--vtqqtrpooseurzip--





^ permalink  raw  reply  [nested|flat] 265+ messages in thread

* [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source
@ 2025-07-27 15:48  Lukas Fittl <[email protected]>
  0 siblings, 0 replies; 265+ messages in thread

From: Lukas Fittl @ 2025-07-27 15:48 UTC (permalink / raw)

In passing also reduce the per-loop overhead caused by repeated divisions
in INSTR_TIME_GET_NANOSEC when the ticks variable has become very large,
instead diff first and then turn it into nanosecs.
---
 src/bin/pg_test_timing/pg_test_timing.c | 59 +++++++++++++++++++------
 src/include/portability/instr_time.h    | 30 ++++++++-----
 2 files changed, 65 insertions(+), 24 deletions(-)

diff --git a/src/bin/pg_test_timing/pg_test_timing.c b/src/bin/pg_test_timing/pg_test_timing.c
index a5621251afc..b77ef2063b6 100644
--- a/src/bin/pg_test_timing/pg_test_timing.c
+++ b/src/bin/pg_test_timing/pg_test_timing.c
@@ -16,6 +16,7 @@ static const char *progname;
 
 static unsigned int test_duration = 3;
 static double max_rprct = 99.99;
+static bool fast_timing = false;
 
 /* record duration in powers of 2 nanoseconds */
 static long long int histogram[32];
@@ -56,6 +57,7 @@ handle_args(int argc, char *argv[])
 	static struct option long_options[] = {
 		{"duration", required_argument, NULL, 'd'},
 		{"cutoff", required_argument, NULL, 'c'},
+		{"fast", no_argument, NULL, 'f'},
 		{NULL, 0, NULL, 0}
 	};
 
@@ -68,7 +70,7 @@ handle_args(int argc, char *argv[])
 	{
 		if (strcmp(argv[1], "--help") == 0 || strcmp(argv[1], "-?") == 0)
 		{
-			printf(_("Usage: %s [-d DURATION] [-c CUTOFF]\n"), progname);
+			printf(_("Usage: %s [-d DURATION] [-c CUTOFF] [--fast]\n"), progname);
 			exit(0);
 		}
 		if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0)
@@ -78,7 +80,7 @@ handle_args(int argc, char *argv[])
 		}
 	}
 
-	while ((option = getopt_long(argc, argv, "d:c:",
+	while ((option = getopt_long(argc, argv, "d:c:f:",
 								 long_options, &optindex)) != -1)
 	{
 		switch (option)
@@ -125,6 +127,10 @@ handle_args(int argc, char *argv[])
 				}
 				break;
 
+			case 'f':
+				fast_timing = true;
+				break;
+
 			default:
 				fprintf(stderr, _("Try \"%s --help\" for more information.\n"),
 						progname);
@@ -155,11 +161,31 @@ test_timing(unsigned int duration)
 	uint64		total_time;
 	int64		time_elapsed = 0;
 	uint64		loop_count = 0;
-	uint64		prev,
-				cur;
 	instr_time	start_time,
 				end_time,
-				temp;
+				prev,
+				cur;
+	char	   *time_source = NULL;
+	bool		fast_timing_used = false;
+
+	INSTR_TIME_INITIALIZE();
+
+#if !defined(WIN32) && defined(__x86_64__) && defined(__linux__)
+	if (fast_timing && has_rdtsc)
+	{
+		time_source = "RDTSC";
+		fast_timing_used = true;
+	}
+	else if (has_rdtscp)
+		time_source = "RDTSCP";
+	else
+		time_source = PG_INSTR_CLOCK_NAME;
+#else
+	time_source = PG_INSTR_CLOCK_NAME;
+#endif
+	if (fast_timing && !fast_timing_used)
+		printf(_("Warning: Fast timing requested, but not available - regular timing source will be used\n"));
+	printf(_("Time source: %s\n"), time_source);
 
 	/*
 	 * Pre-zero the statistics data structures.  They're already zero by
@@ -173,8 +199,11 @@ test_timing(unsigned int duration)
 
 	total_time = duration > 0 ? duration * INT64CONST(1000000000) : 0;
 
-	INSTR_TIME_SET_CURRENT(start_time);
-	cur = INSTR_TIME_GET_NANOSEC(start_time);
+	if (fast_timing)
+		INSTR_TIME_SET_CURRENT_FAST(start_time);
+	else
+		INSTR_TIME_SET_CURRENT(start_time);
+	cur = start_time;
 
 	while (time_elapsed < total_time)
 	{
@@ -182,9 +211,11 @@ test_timing(unsigned int duration)
 					bits;
 
 		prev = cur;
-		INSTR_TIME_SET_CURRENT(temp);
-		cur = INSTR_TIME_GET_NANOSEC(temp);
-		diff = cur - prev;
+		if (fast_timing)
+			INSTR_TIME_SET_CURRENT_FAST(cur);
+		else
+			INSTR_TIME_SET_CURRENT(cur);
+		diff = INSTR_TIME_DIFF_NANOSEC(cur, prev);
 
 		/* Did time go backwards? */
 		if (unlikely(diff < 0))
@@ -217,11 +248,13 @@ test_timing(unsigned int duration)
 			largest_diff_count++;
 
 		loop_count++;
-		INSTR_TIME_SUBTRACT(temp, start_time);
-		time_elapsed = INSTR_TIME_GET_NANOSEC(temp);
+		time_elapsed = INSTR_TIME_DIFF_NANOSEC(cur, start_time);
 	}
 
-	INSTR_TIME_SET_CURRENT(end_time);
+	if (fast_timing)
+		INSTR_TIME_SET_CURRENT_FAST(end_time);
+	else
+		INSTR_TIME_SET_CURRENT(end_time);
 
 	INSTR_TIME_SUBTRACT(end_time, start_time);
 
diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h
index e2e339a0c4f..f02296f1026 100644
--- a/src/include/portability/instr_time.h
+++ b/src/include/portability/instr_time.h
@@ -112,10 +112,13 @@ extern int64 max_ticks_no_overflow;
  */
 #if defined(__darwin__) && defined(CLOCK_MONOTONIC_RAW)
 #define PG_INSTR_CLOCK	CLOCK_MONOTONIC_RAW
+#define PG_INSTR_CLOCK_NAME	"clock_gettime (CLOCK_MONOTONIC_RAW)"
 #elif defined(CLOCK_MONOTONIC)
 #define PG_INSTR_CLOCK	CLOCK_MONOTONIC
+#define PG_INSTR_CLOCK_NAME	"clock_gettime (CLOCK_MONOTONIC)"
 #else
 #define PG_INSTR_CLOCK	CLOCK_REALTIME
+#define PG_INSTR_CLOCK_NAME	"clock_gettime (CLOCK_REALTIME)"
 #endif
 
 #if defined(__x86_64__) && defined(__linux__)
@@ -174,7 +177,7 @@ pg_get_ticks(void)
 }
 
 static inline int64_t
-pg_ticks_to_ns(instr_time t)
+pg_ticks_to_ns(int64 ticks)
 {
 	/*
 	 * Would multiplication overflow? If so perform computation in two parts.
@@ -183,7 +186,7 @@ pg_ticks_to_ns(instr_time t)
 	 */
 	int64		ns = 0;
 
-	if (unlikely(t.ticks > max_ticks_no_overflow))
+	if (unlikely(ticks > max_ticks_no_overflow))
 	{
 		/*
 		 * Compute how often the maximum number of ticks fits completely into
@@ -192,7 +195,7 @@ pg_ticks_to_ns(instr_time t)
 		 * value. In a 2nd step we adjust the number of elapsed ticks and
 		 * convert the remaining ticks.
 		 */
-		int64		count = t.ticks / max_ticks_no_overflow;
+		int64		count = ticks / max_ticks_no_overflow;
 		int64		max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION;
 
 		ns = max_ns * count;
@@ -201,11 +204,11 @@ pg_ticks_to_ns(instr_time t)
 		 * Subtract the ticks that we now already accounted for, so that they
 		 * don't get counted twice.
 		 */
-		t.ticks -= count * max_ticks_no_overflow;
-		Assert(t.ticks >= 0);
+		ticks -= count * max_ticks_no_overflow;
+		Assert(ticks >= 0);
 	}
 
-	ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION;
+	ns += ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION;
 	return ns;
 }
 
@@ -226,14 +229,14 @@ pg_initialize_get_ticks()
 #define INSTR_TIME_SET_CURRENT(t) \
 	((t) = pg_get_ticks())
 
-#define INSTR_TIME_GET_NANOSEC(t) \
-	pg_ticks_to_ns(t)
-
+#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \
+	(pg_ticks_to_ns(ticks))
 
 #else							/* WIN32 */
 
 
 /* Use QueryPerformanceCounter() */
+#define PG_INSTR_CLOCK_NAME	"QueryPerformanceCounter"
 
 /* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */
 static inline instr_time
@@ -265,8 +268,8 @@ GetTimerFrequency(void)
 #define INSTR_TIME_SET_CURRENT(t) \
 	((t) = pg_query_performance_counter())
 
-#define INSTR_TIME_GET_NANOSEC(t) \
-	((int64) ((t).ticks * ((double) NS_PER_S / GetTimerFrequency())))
+#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \
+	((int64) ((ticks) * ((double) NS_PER_S / GetTimerFrequency())))
 
 #endif							/* WIN32 */
 
@@ -285,9 +288,14 @@ GetTimerFrequency(void)
 #define INSTR_TIME_SUBTRACT(x,y) \
 	((x).ticks -= (y).ticks)
 
+#define INSTR_TIME_DIFF_NANOSEC(x,y) \
+	(INSTR_TIME_TICKS_TO_NANOSEC((x).ticks - (y).ticks))
+
 #define INSTR_TIME_ACCUM_DIFF(x,y,z) \
 	((x).ticks += (y).ticks - (z).ticks)
 
+#define INSTR_TIME_GET_NANOSEC(t) \
+	(INSTR_TIME_TICKS_TO_NANOSEC((t).ticks))
 
 #define INSTR_TIME_GET_DOUBLE(t) \
 	((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S)
-- 
2.47.3


--vtqqtrpooseurzip--





^ permalink  raw  reply  [nested|flat] 265+ messages in thread

* [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source
@ 2025-07-27 15:48  Lukas Fittl <[email protected]>
  0 siblings, 0 replies; 265+ messages in thread

From: Lukas Fittl @ 2025-07-27 15:48 UTC (permalink / raw)

In passing also reduce the per-loop overhead caused by repeated divisions
in INSTR_TIME_GET_NANOSEC when the ticks variable has become very large,
instead diff first and then turn it into nanosecs.
---
 src/bin/pg_test_timing/pg_test_timing.c | 59 +++++++++++++++++++------
 src/include/portability/instr_time.h    | 30 ++++++++-----
 2 files changed, 65 insertions(+), 24 deletions(-)

diff --git a/src/bin/pg_test_timing/pg_test_timing.c b/src/bin/pg_test_timing/pg_test_timing.c
index a5621251afc..b77ef2063b6 100644
--- a/src/bin/pg_test_timing/pg_test_timing.c
+++ b/src/bin/pg_test_timing/pg_test_timing.c
@@ -16,6 +16,7 @@ static const char *progname;
 
 static unsigned int test_duration = 3;
 static double max_rprct = 99.99;
+static bool fast_timing = false;
 
 /* record duration in powers of 2 nanoseconds */
 static long long int histogram[32];
@@ -56,6 +57,7 @@ handle_args(int argc, char *argv[])
 	static struct option long_options[] = {
 		{"duration", required_argument, NULL, 'd'},
 		{"cutoff", required_argument, NULL, 'c'},
+		{"fast", no_argument, NULL, 'f'},
 		{NULL, 0, NULL, 0}
 	};
 
@@ -68,7 +70,7 @@ handle_args(int argc, char *argv[])
 	{
 		if (strcmp(argv[1], "--help") == 0 || strcmp(argv[1], "-?") == 0)
 		{
-			printf(_("Usage: %s [-d DURATION] [-c CUTOFF]\n"), progname);
+			printf(_("Usage: %s [-d DURATION] [-c CUTOFF] [--fast]\n"), progname);
 			exit(0);
 		}
 		if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0)
@@ -78,7 +80,7 @@ handle_args(int argc, char *argv[])
 		}
 	}
 
-	while ((option = getopt_long(argc, argv, "d:c:",
+	while ((option = getopt_long(argc, argv, "d:c:f:",
 								 long_options, &optindex)) != -1)
 	{
 		switch (option)
@@ -125,6 +127,10 @@ handle_args(int argc, char *argv[])
 				}
 				break;
 
+			case 'f':
+				fast_timing = true;
+				break;
+
 			default:
 				fprintf(stderr, _("Try \"%s --help\" for more information.\n"),
 						progname);
@@ -155,11 +161,31 @@ test_timing(unsigned int duration)
 	uint64		total_time;
 	int64		time_elapsed = 0;
 	uint64		loop_count = 0;
-	uint64		prev,
-				cur;
 	instr_time	start_time,
 				end_time,
-				temp;
+				prev,
+				cur;
+	char	   *time_source = NULL;
+	bool		fast_timing_used = false;
+
+	INSTR_TIME_INITIALIZE();
+
+#if !defined(WIN32) && defined(__x86_64__) && defined(__linux__)
+	if (fast_timing && has_rdtsc)
+	{
+		time_source = "RDTSC";
+		fast_timing_used = true;
+	}
+	else if (has_rdtscp)
+		time_source = "RDTSCP";
+	else
+		time_source = PG_INSTR_CLOCK_NAME;
+#else
+	time_source = PG_INSTR_CLOCK_NAME;
+#endif
+	if (fast_timing && !fast_timing_used)
+		printf(_("Warning: Fast timing requested, but not available - regular timing source will be used\n"));
+	printf(_("Time source: %s\n"), time_source);
 
 	/*
 	 * Pre-zero the statistics data structures.  They're already zero by
@@ -173,8 +199,11 @@ test_timing(unsigned int duration)
 
 	total_time = duration > 0 ? duration * INT64CONST(1000000000) : 0;
 
-	INSTR_TIME_SET_CURRENT(start_time);
-	cur = INSTR_TIME_GET_NANOSEC(start_time);
+	if (fast_timing)
+		INSTR_TIME_SET_CURRENT_FAST(start_time);
+	else
+		INSTR_TIME_SET_CURRENT(start_time);
+	cur = start_time;
 
 	while (time_elapsed < total_time)
 	{
@@ -182,9 +211,11 @@ test_timing(unsigned int duration)
 					bits;
 
 		prev = cur;
-		INSTR_TIME_SET_CURRENT(temp);
-		cur = INSTR_TIME_GET_NANOSEC(temp);
-		diff = cur - prev;
+		if (fast_timing)
+			INSTR_TIME_SET_CURRENT_FAST(cur);
+		else
+			INSTR_TIME_SET_CURRENT(cur);
+		diff = INSTR_TIME_DIFF_NANOSEC(cur, prev);
 
 		/* Did time go backwards? */
 		if (unlikely(diff < 0))
@@ -217,11 +248,13 @@ test_timing(unsigned int duration)
 			largest_diff_count++;
 
 		loop_count++;
-		INSTR_TIME_SUBTRACT(temp, start_time);
-		time_elapsed = INSTR_TIME_GET_NANOSEC(temp);
+		time_elapsed = INSTR_TIME_DIFF_NANOSEC(cur, start_time);
 	}
 
-	INSTR_TIME_SET_CURRENT(end_time);
+	if (fast_timing)
+		INSTR_TIME_SET_CURRENT_FAST(end_time);
+	else
+		INSTR_TIME_SET_CURRENT(end_time);
 
 	INSTR_TIME_SUBTRACT(end_time, start_time);
 
diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h
index e2e339a0c4f..f02296f1026 100644
--- a/src/include/portability/instr_time.h
+++ b/src/include/portability/instr_time.h
@@ -112,10 +112,13 @@ extern int64 max_ticks_no_overflow;
  */
 #if defined(__darwin__) && defined(CLOCK_MONOTONIC_RAW)
 #define PG_INSTR_CLOCK	CLOCK_MONOTONIC_RAW
+#define PG_INSTR_CLOCK_NAME	"clock_gettime (CLOCK_MONOTONIC_RAW)"
 #elif defined(CLOCK_MONOTONIC)
 #define PG_INSTR_CLOCK	CLOCK_MONOTONIC
+#define PG_INSTR_CLOCK_NAME	"clock_gettime (CLOCK_MONOTONIC)"
 #else
 #define PG_INSTR_CLOCK	CLOCK_REALTIME
+#define PG_INSTR_CLOCK_NAME	"clock_gettime (CLOCK_REALTIME)"
 #endif
 
 #if defined(__x86_64__) && defined(__linux__)
@@ -174,7 +177,7 @@ pg_get_ticks(void)
 }
 
 static inline int64_t
-pg_ticks_to_ns(instr_time t)
+pg_ticks_to_ns(int64 ticks)
 {
 	/*
 	 * Would multiplication overflow? If so perform computation in two parts.
@@ -183,7 +186,7 @@ pg_ticks_to_ns(instr_time t)
 	 */
 	int64		ns = 0;
 
-	if (unlikely(t.ticks > max_ticks_no_overflow))
+	if (unlikely(ticks > max_ticks_no_overflow))
 	{
 		/*
 		 * Compute how often the maximum number of ticks fits completely into
@@ -192,7 +195,7 @@ pg_ticks_to_ns(instr_time t)
 		 * value. In a 2nd step we adjust the number of elapsed ticks and
 		 * convert the remaining ticks.
 		 */
-		int64		count = t.ticks / max_ticks_no_overflow;
+		int64		count = ticks / max_ticks_no_overflow;
 		int64		max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION;
 
 		ns = max_ns * count;
@@ -201,11 +204,11 @@ pg_ticks_to_ns(instr_time t)
 		 * Subtract the ticks that we now already accounted for, so that they
 		 * don't get counted twice.
 		 */
-		t.ticks -= count * max_ticks_no_overflow;
-		Assert(t.ticks >= 0);
+		ticks -= count * max_ticks_no_overflow;
+		Assert(ticks >= 0);
 	}
 
-	ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION;
+	ns += ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION;
 	return ns;
 }
 
@@ -226,14 +229,14 @@ pg_initialize_get_ticks()
 #define INSTR_TIME_SET_CURRENT(t) \
 	((t) = pg_get_ticks())
 
-#define INSTR_TIME_GET_NANOSEC(t) \
-	pg_ticks_to_ns(t)
-
+#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \
+	(pg_ticks_to_ns(ticks))
 
 #else							/* WIN32 */
 
 
 /* Use QueryPerformanceCounter() */
+#define PG_INSTR_CLOCK_NAME	"QueryPerformanceCounter"
 
 /* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */
 static inline instr_time
@@ -265,8 +268,8 @@ GetTimerFrequency(void)
 #define INSTR_TIME_SET_CURRENT(t) \
 	((t) = pg_query_performance_counter())
 
-#define INSTR_TIME_GET_NANOSEC(t) \
-	((int64) ((t).ticks * ((double) NS_PER_S / GetTimerFrequency())))
+#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \
+	((int64) ((ticks) * ((double) NS_PER_S / GetTimerFrequency())))
 
 #endif							/* WIN32 */
 
@@ -285,9 +288,14 @@ GetTimerFrequency(void)
 #define INSTR_TIME_SUBTRACT(x,y) \
 	((x).ticks -= (y).ticks)
 
+#define INSTR_TIME_DIFF_NANOSEC(x,y) \
+	(INSTR_TIME_TICKS_TO_NANOSEC((x).ticks - (y).ticks))
+
 #define INSTR_TIME_ACCUM_DIFF(x,y,z) \
 	((x).ticks += (y).ticks - (z).ticks)
 
+#define INSTR_TIME_GET_NANOSEC(t) \
+	(INSTR_TIME_TICKS_TO_NANOSEC((t).ticks))
 
 #define INSTR_TIME_GET_DOUBLE(t) \
 	((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S)
-- 
2.47.3


--vtqqtrpooseurzip--





^ permalink  raw  reply  [nested|flat] 265+ messages in thread

* [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source
@ 2025-07-27 15:48  Lukas Fittl <[email protected]>
  0 siblings, 0 replies; 265+ messages in thread

From: Lukas Fittl @ 2025-07-27 15:48 UTC (permalink / raw)

In passing also reduce the per-loop overhead caused by repeated divisions
in INSTR_TIME_GET_NANOSEC when the ticks variable has become very large,
instead diff first and then turn it into nanosecs.
---
 src/bin/pg_test_timing/pg_test_timing.c | 59 +++++++++++++++++++------
 src/include/portability/instr_time.h    | 30 ++++++++-----
 2 files changed, 65 insertions(+), 24 deletions(-)

diff --git a/src/bin/pg_test_timing/pg_test_timing.c b/src/bin/pg_test_timing/pg_test_timing.c
index a5621251afc..b77ef2063b6 100644
--- a/src/bin/pg_test_timing/pg_test_timing.c
+++ b/src/bin/pg_test_timing/pg_test_timing.c
@@ -16,6 +16,7 @@ static const char *progname;
 
 static unsigned int test_duration = 3;
 static double max_rprct = 99.99;
+static bool fast_timing = false;
 
 /* record duration in powers of 2 nanoseconds */
 static long long int histogram[32];
@@ -56,6 +57,7 @@ handle_args(int argc, char *argv[])
 	static struct option long_options[] = {
 		{"duration", required_argument, NULL, 'd'},
 		{"cutoff", required_argument, NULL, 'c'},
+		{"fast", no_argument, NULL, 'f'},
 		{NULL, 0, NULL, 0}
 	};
 
@@ -68,7 +70,7 @@ handle_args(int argc, char *argv[])
 	{
 		if (strcmp(argv[1], "--help") == 0 || strcmp(argv[1], "-?") == 0)
 		{
-			printf(_("Usage: %s [-d DURATION] [-c CUTOFF]\n"), progname);
+			printf(_("Usage: %s [-d DURATION] [-c CUTOFF] [--fast]\n"), progname);
 			exit(0);
 		}
 		if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0)
@@ -78,7 +80,7 @@ handle_args(int argc, char *argv[])
 		}
 	}
 
-	while ((option = getopt_long(argc, argv, "d:c:",
+	while ((option = getopt_long(argc, argv, "d:c:f:",
 								 long_options, &optindex)) != -1)
 	{
 		switch (option)
@@ -125,6 +127,10 @@ handle_args(int argc, char *argv[])
 				}
 				break;
 
+			case 'f':
+				fast_timing = true;
+				break;
+
 			default:
 				fprintf(stderr, _("Try \"%s --help\" for more information.\n"),
 						progname);
@@ -155,11 +161,31 @@ test_timing(unsigned int duration)
 	uint64		total_time;
 	int64		time_elapsed = 0;
 	uint64		loop_count = 0;
-	uint64		prev,
-				cur;
 	instr_time	start_time,
 				end_time,
-				temp;
+				prev,
+				cur;
+	char	   *time_source = NULL;
+	bool		fast_timing_used = false;
+
+	INSTR_TIME_INITIALIZE();
+
+#if !defined(WIN32) && defined(__x86_64__) && defined(__linux__)
+	if (fast_timing && has_rdtsc)
+	{
+		time_source = "RDTSC";
+		fast_timing_used = true;
+	}
+	else if (has_rdtscp)
+		time_source = "RDTSCP";
+	else
+		time_source = PG_INSTR_CLOCK_NAME;
+#else
+	time_source = PG_INSTR_CLOCK_NAME;
+#endif
+	if (fast_timing && !fast_timing_used)
+		printf(_("Warning: Fast timing requested, but not available - regular timing source will be used\n"));
+	printf(_("Time source: %s\n"), time_source);
 
 	/*
 	 * Pre-zero the statistics data structures.  They're already zero by
@@ -173,8 +199,11 @@ test_timing(unsigned int duration)
 
 	total_time = duration > 0 ? duration * INT64CONST(1000000000) : 0;
 
-	INSTR_TIME_SET_CURRENT(start_time);
-	cur = INSTR_TIME_GET_NANOSEC(start_time);
+	if (fast_timing)
+		INSTR_TIME_SET_CURRENT_FAST(start_time);
+	else
+		INSTR_TIME_SET_CURRENT(start_time);
+	cur = start_time;
 
 	while (time_elapsed < total_time)
 	{
@@ -182,9 +211,11 @@ test_timing(unsigned int duration)
 					bits;
 
 		prev = cur;
-		INSTR_TIME_SET_CURRENT(temp);
-		cur = INSTR_TIME_GET_NANOSEC(temp);
-		diff = cur - prev;
+		if (fast_timing)
+			INSTR_TIME_SET_CURRENT_FAST(cur);
+		else
+			INSTR_TIME_SET_CURRENT(cur);
+		diff = INSTR_TIME_DIFF_NANOSEC(cur, prev);
 
 		/* Did time go backwards? */
 		if (unlikely(diff < 0))
@@ -217,11 +248,13 @@ test_timing(unsigned int duration)
 			largest_diff_count++;
 
 		loop_count++;
-		INSTR_TIME_SUBTRACT(temp, start_time);
-		time_elapsed = INSTR_TIME_GET_NANOSEC(temp);
+		time_elapsed = INSTR_TIME_DIFF_NANOSEC(cur, start_time);
 	}
 
-	INSTR_TIME_SET_CURRENT(end_time);
+	if (fast_timing)
+		INSTR_TIME_SET_CURRENT_FAST(end_time);
+	else
+		INSTR_TIME_SET_CURRENT(end_time);
 
 	INSTR_TIME_SUBTRACT(end_time, start_time);
 
diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h
index e2e339a0c4f..f02296f1026 100644
--- a/src/include/portability/instr_time.h
+++ b/src/include/portability/instr_time.h
@@ -112,10 +112,13 @@ extern int64 max_ticks_no_overflow;
  */
 #if defined(__darwin__) && defined(CLOCK_MONOTONIC_RAW)
 #define PG_INSTR_CLOCK	CLOCK_MONOTONIC_RAW
+#define PG_INSTR_CLOCK_NAME	"clock_gettime (CLOCK_MONOTONIC_RAW)"
 #elif defined(CLOCK_MONOTONIC)
 #define PG_INSTR_CLOCK	CLOCK_MONOTONIC
+#define PG_INSTR_CLOCK_NAME	"clock_gettime (CLOCK_MONOTONIC)"
 #else
 #define PG_INSTR_CLOCK	CLOCK_REALTIME
+#define PG_INSTR_CLOCK_NAME	"clock_gettime (CLOCK_REALTIME)"
 #endif
 
 #if defined(__x86_64__) && defined(__linux__)
@@ -174,7 +177,7 @@ pg_get_ticks(void)
 }
 
 static inline int64_t
-pg_ticks_to_ns(instr_time t)
+pg_ticks_to_ns(int64 ticks)
 {
 	/*
 	 * Would multiplication overflow? If so perform computation in two parts.
@@ -183,7 +186,7 @@ pg_ticks_to_ns(instr_time t)
 	 */
 	int64		ns = 0;
 
-	if (unlikely(t.ticks > max_ticks_no_overflow))
+	if (unlikely(ticks > max_ticks_no_overflow))
 	{
 		/*
 		 * Compute how often the maximum number of ticks fits completely into
@@ -192,7 +195,7 @@ pg_ticks_to_ns(instr_time t)
 		 * value. In a 2nd step we adjust the number of elapsed ticks and
 		 * convert the remaining ticks.
 		 */
-		int64		count = t.ticks / max_ticks_no_overflow;
+		int64		count = ticks / max_ticks_no_overflow;
 		int64		max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION;
 
 		ns = max_ns * count;
@@ -201,11 +204,11 @@ pg_ticks_to_ns(instr_time t)
 		 * Subtract the ticks that we now already accounted for, so that they
 		 * don't get counted twice.
 		 */
-		t.ticks -= count * max_ticks_no_overflow;
-		Assert(t.ticks >= 0);
+		ticks -= count * max_ticks_no_overflow;
+		Assert(ticks >= 0);
 	}
 
-	ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION;
+	ns += ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION;
 	return ns;
 }
 
@@ -226,14 +229,14 @@ pg_initialize_get_ticks()
 #define INSTR_TIME_SET_CURRENT(t) \
 	((t) = pg_get_ticks())
 
-#define INSTR_TIME_GET_NANOSEC(t) \
-	pg_ticks_to_ns(t)
-
+#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \
+	(pg_ticks_to_ns(ticks))
 
 #else							/* WIN32 */
 
 
 /* Use QueryPerformanceCounter() */
+#define PG_INSTR_CLOCK_NAME	"QueryPerformanceCounter"
 
 /* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */
 static inline instr_time
@@ -265,8 +268,8 @@ GetTimerFrequency(void)
 #define INSTR_TIME_SET_CURRENT(t) \
 	((t) = pg_query_performance_counter())
 
-#define INSTR_TIME_GET_NANOSEC(t) \
-	((int64) ((t).ticks * ((double) NS_PER_S / GetTimerFrequency())))
+#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \
+	((int64) ((ticks) * ((double) NS_PER_S / GetTimerFrequency())))
 
 #endif							/* WIN32 */
 
@@ -285,9 +288,14 @@ GetTimerFrequency(void)
 #define INSTR_TIME_SUBTRACT(x,y) \
 	((x).ticks -= (y).ticks)
 
+#define INSTR_TIME_DIFF_NANOSEC(x,y) \
+	(INSTR_TIME_TICKS_TO_NANOSEC((x).ticks - (y).ticks))
+
 #define INSTR_TIME_ACCUM_DIFF(x,y,z) \
 	((x).ticks += (y).ticks - (z).ticks)
 
+#define INSTR_TIME_GET_NANOSEC(t) \
+	(INSTR_TIME_TICKS_TO_NANOSEC((t).ticks))
 
 #define INSTR_TIME_GET_DOUBLE(t) \
 	((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S)
-- 
2.47.3


--vtqqtrpooseurzip--





^ permalink  raw  reply  [nested|flat] 265+ messages in thread

* [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source
@ 2025-07-27 15:48  Lukas Fittl <[email protected]>
  0 siblings, 0 replies; 265+ messages in thread

From: Lukas Fittl @ 2025-07-27 15:48 UTC (permalink / raw)

In passing also reduce the per-loop overhead caused by repeated divisions
in INSTR_TIME_GET_NANOSEC when the ticks variable has become very large,
instead diff first and then turn it into nanosecs.
---
 src/bin/pg_test_timing/pg_test_timing.c | 59 +++++++++++++++++++------
 src/include/portability/instr_time.h    | 30 ++++++++-----
 2 files changed, 65 insertions(+), 24 deletions(-)

diff --git a/src/bin/pg_test_timing/pg_test_timing.c b/src/bin/pg_test_timing/pg_test_timing.c
index a5621251afc..b77ef2063b6 100644
--- a/src/bin/pg_test_timing/pg_test_timing.c
+++ b/src/bin/pg_test_timing/pg_test_timing.c
@@ -16,6 +16,7 @@ static const char *progname;
 
 static unsigned int test_duration = 3;
 static double max_rprct = 99.99;
+static bool fast_timing = false;
 
 /* record duration in powers of 2 nanoseconds */
 static long long int histogram[32];
@@ -56,6 +57,7 @@ handle_args(int argc, char *argv[])
 	static struct option long_options[] = {
 		{"duration", required_argument, NULL, 'd'},
 		{"cutoff", required_argument, NULL, 'c'},
+		{"fast", no_argument, NULL, 'f'},
 		{NULL, 0, NULL, 0}
 	};
 
@@ -68,7 +70,7 @@ handle_args(int argc, char *argv[])
 	{
 		if (strcmp(argv[1], "--help") == 0 || strcmp(argv[1], "-?") == 0)
 		{
-			printf(_("Usage: %s [-d DURATION] [-c CUTOFF]\n"), progname);
+			printf(_("Usage: %s [-d DURATION] [-c CUTOFF] [--fast]\n"), progname);
 			exit(0);
 		}
 		if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0)
@@ -78,7 +80,7 @@ handle_args(int argc, char *argv[])
 		}
 	}
 
-	while ((option = getopt_long(argc, argv, "d:c:",
+	while ((option = getopt_long(argc, argv, "d:c:f:",
 								 long_options, &optindex)) != -1)
 	{
 		switch (option)
@@ -125,6 +127,10 @@ handle_args(int argc, char *argv[])
 				}
 				break;
 
+			case 'f':
+				fast_timing = true;
+				break;
+
 			default:
 				fprintf(stderr, _("Try \"%s --help\" for more information.\n"),
 						progname);
@@ -155,11 +161,31 @@ test_timing(unsigned int duration)
 	uint64		total_time;
 	int64		time_elapsed = 0;
 	uint64		loop_count = 0;
-	uint64		prev,
-				cur;
 	instr_time	start_time,
 				end_time,
-				temp;
+				prev,
+				cur;
+	char	   *time_source = NULL;
+	bool		fast_timing_used = false;
+
+	INSTR_TIME_INITIALIZE();
+
+#if !defined(WIN32) && defined(__x86_64__) && defined(__linux__)
+	if (fast_timing && has_rdtsc)
+	{
+		time_source = "RDTSC";
+		fast_timing_used = true;
+	}
+	else if (has_rdtscp)
+		time_source = "RDTSCP";
+	else
+		time_source = PG_INSTR_CLOCK_NAME;
+#else
+	time_source = PG_INSTR_CLOCK_NAME;
+#endif
+	if (fast_timing && !fast_timing_used)
+		printf(_("Warning: Fast timing requested, but not available - regular timing source will be used\n"));
+	printf(_("Time source: %s\n"), time_source);
 
 	/*
 	 * Pre-zero the statistics data structures.  They're already zero by
@@ -173,8 +199,11 @@ test_timing(unsigned int duration)
 
 	total_time = duration > 0 ? duration * INT64CONST(1000000000) : 0;
 
-	INSTR_TIME_SET_CURRENT(start_time);
-	cur = INSTR_TIME_GET_NANOSEC(start_time);
+	if (fast_timing)
+		INSTR_TIME_SET_CURRENT_FAST(start_time);
+	else
+		INSTR_TIME_SET_CURRENT(start_time);
+	cur = start_time;
 
 	while (time_elapsed < total_time)
 	{
@@ -182,9 +211,11 @@ test_timing(unsigned int duration)
 					bits;
 
 		prev = cur;
-		INSTR_TIME_SET_CURRENT(temp);
-		cur = INSTR_TIME_GET_NANOSEC(temp);
-		diff = cur - prev;
+		if (fast_timing)
+			INSTR_TIME_SET_CURRENT_FAST(cur);
+		else
+			INSTR_TIME_SET_CURRENT(cur);
+		diff = INSTR_TIME_DIFF_NANOSEC(cur, prev);
 
 		/* Did time go backwards? */
 		if (unlikely(diff < 0))
@@ -217,11 +248,13 @@ test_timing(unsigned int duration)
 			largest_diff_count++;
 
 		loop_count++;
-		INSTR_TIME_SUBTRACT(temp, start_time);
-		time_elapsed = INSTR_TIME_GET_NANOSEC(temp);
+		time_elapsed = INSTR_TIME_DIFF_NANOSEC(cur, start_time);
 	}
 
-	INSTR_TIME_SET_CURRENT(end_time);
+	if (fast_timing)
+		INSTR_TIME_SET_CURRENT_FAST(end_time);
+	else
+		INSTR_TIME_SET_CURRENT(end_time);
 
 	INSTR_TIME_SUBTRACT(end_time, start_time);
 
diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h
index e2e339a0c4f..f02296f1026 100644
--- a/src/include/portability/instr_time.h
+++ b/src/include/portability/instr_time.h
@@ -112,10 +112,13 @@ extern int64 max_ticks_no_overflow;
  */
 #if defined(__darwin__) && defined(CLOCK_MONOTONIC_RAW)
 #define PG_INSTR_CLOCK	CLOCK_MONOTONIC_RAW
+#define PG_INSTR_CLOCK_NAME	"clock_gettime (CLOCK_MONOTONIC_RAW)"
 #elif defined(CLOCK_MONOTONIC)
 #define PG_INSTR_CLOCK	CLOCK_MONOTONIC
+#define PG_INSTR_CLOCK_NAME	"clock_gettime (CLOCK_MONOTONIC)"
 #else
 #define PG_INSTR_CLOCK	CLOCK_REALTIME
+#define PG_INSTR_CLOCK_NAME	"clock_gettime (CLOCK_REALTIME)"
 #endif
 
 #if defined(__x86_64__) && defined(__linux__)
@@ -174,7 +177,7 @@ pg_get_ticks(void)
 }
 
 static inline int64_t
-pg_ticks_to_ns(instr_time t)
+pg_ticks_to_ns(int64 ticks)
 {
 	/*
 	 * Would multiplication overflow? If so perform computation in two parts.
@@ -183,7 +186,7 @@ pg_ticks_to_ns(instr_time t)
 	 */
 	int64		ns = 0;
 
-	if (unlikely(t.ticks > max_ticks_no_overflow))
+	if (unlikely(ticks > max_ticks_no_overflow))
 	{
 		/*
 		 * Compute how often the maximum number of ticks fits completely into
@@ -192,7 +195,7 @@ pg_ticks_to_ns(instr_time t)
 		 * value. In a 2nd step we adjust the number of elapsed ticks and
 		 * convert the remaining ticks.
 		 */
-		int64		count = t.ticks / max_ticks_no_overflow;
+		int64		count = ticks / max_ticks_no_overflow;
 		int64		max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION;
 
 		ns = max_ns * count;
@@ -201,11 +204,11 @@ pg_ticks_to_ns(instr_time t)
 		 * Subtract the ticks that we now already accounted for, so that they
 		 * don't get counted twice.
 		 */
-		t.ticks -= count * max_ticks_no_overflow;
-		Assert(t.ticks >= 0);
+		ticks -= count * max_ticks_no_overflow;
+		Assert(ticks >= 0);
 	}
 
-	ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION;
+	ns += ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION;
 	return ns;
 }
 
@@ -226,14 +229,14 @@ pg_initialize_get_ticks()
 #define INSTR_TIME_SET_CURRENT(t) \
 	((t) = pg_get_ticks())
 
-#define INSTR_TIME_GET_NANOSEC(t) \
-	pg_ticks_to_ns(t)
-
+#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \
+	(pg_ticks_to_ns(ticks))
 
 #else							/* WIN32 */
 
 
 /* Use QueryPerformanceCounter() */
+#define PG_INSTR_CLOCK_NAME	"QueryPerformanceCounter"
 
 /* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */
 static inline instr_time
@@ -265,8 +268,8 @@ GetTimerFrequency(void)
 #define INSTR_TIME_SET_CURRENT(t) \
 	((t) = pg_query_performance_counter())
 
-#define INSTR_TIME_GET_NANOSEC(t) \
-	((int64) ((t).ticks * ((double) NS_PER_S / GetTimerFrequency())))
+#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \
+	((int64) ((ticks) * ((double) NS_PER_S / GetTimerFrequency())))
 
 #endif							/* WIN32 */
 
@@ -285,9 +288,14 @@ GetTimerFrequency(void)
 #define INSTR_TIME_SUBTRACT(x,y) \
 	((x).ticks -= (y).ticks)
 
+#define INSTR_TIME_DIFF_NANOSEC(x,y) \
+	(INSTR_TIME_TICKS_TO_NANOSEC((x).ticks - (y).ticks))
+
 #define INSTR_TIME_ACCUM_DIFF(x,y,z) \
 	((x).ticks += (y).ticks - (z).ticks)
 
+#define INSTR_TIME_GET_NANOSEC(t) \
+	(INSTR_TIME_TICKS_TO_NANOSEC((t).ticks))
 
 #define INSTR_TIME_GET_DOUBLE(t) \
 	((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S)
-- 
2.47.3


--vtqqtrpooseurzip--





^ permalink  raw  reply  [nested|flat] 265+ messages in thread

* [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source
@ 2025-07-27 15:48  Lukas Fittl <[email protected]>
  0 siblings, 0 replies; 265+ messages in thread

From: Lukas Fittl @ 2025-07-27 15:48 UTC (permalink / raw)

In passing also reduce the per-loop overhead caused by repeated divisions
in INSTR_TIME_GET_NANOSEC when the ticks variable has become very large,
instead diff first and then turn it into nanosecs.
---
 src/bin/pg_test_timing/pg_test_timing.c | 59 +++++++++++++++++++------
 src/include/portability/instr_time.h    | 30 ++++++++-----
 2 files changed, 65 insertions(+), 24 deletions(-)

diff --git a/src/bin/pg_test_timing/pg_test_timing.c b/src/bin/pg_test_timing/pg_test_timing.c
index a5621251afc..b77ef2063b6 100644
--- a/src/bin/pg_test_timing/pg_test_timing.c
+++ b/src/bin/pg_test_timing/pg_test_timing.c
@@ -16,6 +16,7 @@ static const char *progname;
 
 static unsigned int test_duration = 3;
 static double max_rprct = 99.99;
+static bool fast_timing = false;
 
 /* record duration in powers of 2 nanoseconds */
 static long long int histogram[32];
@@ -56,6 +57,7 @@ handle_args(int argc, char *argv[])
 	static struct option long_options[] = {
 		{"duration", required_argument, NULL, 'd'},
 		{"cutoff", required_argument, NULL, 'c'},
+		{"fast", no_argument, NULL, 'f'},
 		{NULL, 0, NULL, 0}
 	};
 
@@ -68,7 +70,7 @@ handle_args(int argc, char *argv[])
 	{
 		if (strcmp(argv[1], "--help") == 0 || strcmp(argv[1], "-?") == 0)
 		{
-			printf(_("Usage: %s [-d DURATION] [-c CUTOFF]\n"), progname);
+			printf(_("Usage: %s [-d DURATION] [-c CUTOFF] [--fast]\n"), progname);
 			exit(0);
 		}
 		if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0)
@@ -78,7 +80,7 @@ handle_args(int argc, char *argv[])
 		}
 	}
 
-	while ((option = getopt_long(argc, argv, "d:c:",
+	while ((option = getopt_long(argc, argv, "d:c:f:",
 								 long_options, &optindex)) != -1)
 	{
 		switch (option)
@@ -125,6 +127,10 @@ handle_args(int argc, char *argv[])
 				}
 				break;
 
+			case 'f':
+				fast_timing = true;
+				break;
+
 			default:
 				fprintf(stderr, _("Try \"%s --help\" for more information.\n"),
 						progname);
@@ -155,11 +161,31 @@ test_timing(unsigned int duration)
 	uint64		total_time;
 	int64		time_elapsed = 0;
 	uint64		loop_count = 0;
-	uint64		prev,
-				cur;
 	instr_time	start_time,
 				end_time,
-				temp;
+				prev,
+				cur;
+	char	   *time_source = NULL;
+	bool		fast_timing_used = false;
+
+	INSTR_TIME_INITIALIZE();
+
+#if !defined(WIN32) && defined(__x86_64__) && defined(__linux__)
+	if (fast_timing && has_rdtsc)
+	{
+		time_source = "RDTSC";
+		fast_timing_used = true;
+	}
+	else if (has_rdtscp)
+		time_source = "RDTSCP";
+	else
+		time_source = PG_INSTR_CLOCK_NAME;
+#else
+	time_source = PG_INSTR_CLOCK_NAME;
+#endif
+	if (fast_timing && !fast_timing_used)
+		printf(_("Warning: Fast timing requested, but not available - regular timing source will be used\n"));
+	printf(_("Time source: %s\n"), time_source);
 
 	/*
 	 * Pre-zero the statistics data structures.  They're already zero by
@@ -173,8 +199,11 @@ test_timing(unsigned int duration)
 
 	total_time = duration > 0 ? duration * INT64CONST(1000000000) : 0;
 
-	INSTR_TIME_SET_CURRENT(start_time);
-	cur = INSTR_TIME_GET_NANOSEC(start_time);
+	if (fast_timing)
+		INSTR_TIME_SET_CURRENT_FAST(start_time);
+	else
+		INSTR_TIME_SET_CURRENT(start_time);
+	cur = start_time;
 
 	while (time_elapsed < total_time)
 	{
@@ -182,9 +211,11 @@ test_timing(unsigned int duration)
 					bits;
 
 		prev = cur;
-		INSTR_TIME_SET_CURRENT(temp);
-		cur = INSTR_TIME_GET_NANOSEC(temp);
-		diff = cur - prev;
+		if (fast_timing)
+			INSTR_TIME_SET_CURRENT_FAST(cur);
+		else
+			INSTR_TIME_SET_CURRENT(cur);
+		diff = INSTR_TIME_DIFF_NANOSEC(cur, prev);
 
 		/* Did time go backwards? */
 		if (unlikely(diff < 0))
@@ -217,11 +248,13 @@ test_timing(unsigned int duration)
 			largest_diff_count++;
 
 		loop_count++;
-		INSTR_TIME_SUBTRACT(temp, start_time);
-		time_elapsed = INSTR_TIME_GET_NANOSEC(temp);
+		time_elapsed = INSTR_TIME_DIFF_NANOSEC(cur, start_time);
 	}
 
-	INSTR_TIME_SET_CURRENT(end_time);
+	if (fast_timing)
+		INSTR_TIME_SET_CURRENT_FAST(end_time);
+	else
+		INSTR_TIME_SET_CURRENT(end_time);
 
 	INSTR_TIME_SUBTRACT(end_time, start_time);
 
diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h
index e2e339a0c4f..f02296f1026 100644
--- a/src/include/portability/instr_time.h
+++ b/src/include/portability/instr_time.h
@@ -112,10 +112,13 @@ extern int64 max_ticks_no_overflow;
  */
 #if defined(__darwin__) && defined(CLOCK_MONOTONIC_RAW)
 #define PG_INSTR_CLOCK	CLOCK_MONOTONIC_RAW
+#define PG_INSTR_CLOCK_NAME	"clock_gettime (CLOCK_MONOTONIC_RAW)"
 #elif defined(CLOCK_MONOTONIC)
 #define PG_INSTR_CLOCK	CLOCK_MONOTONIC
+#define PG_INSTR_CLOCK_NAME	"clock_gettime (CLOCK_MONOTONIC)"
 #else
 #define PG_INSTR_CLOCK	CLOCK_REALTIME
+#define PG_INSTR_CLOCK_NAME	"clock_gettime (CLOCK_REALTIME)"
 #endif
 
 #if defined(__x86_64__) && defined(__linux__)
@@ -174,7 +177,7 @@ pg_get_ticks(void)
 }
 
 static inline int64_t
-pg_ticks_to_ns(instr_time t)
+pg_ticks_to_ns(int64 ticks)
 {
 	/*
 	 * Would multiplication overflow? If so perform computation in two parts.
@@ -183,7 +186,7 @@ pg_ticks_to_ns(instr_time t)
 	 */
 	int64		ns = 0;
 
-	if (unlikely(t.ticks > max_ticks_no_overflow))
+	if (unlikely(ticks > max_ticks_no_overflow))
 	{
 		/*
 		 * Compute how often the maximum number of ticks fits completely into
@@ -192,7 +195,7 @@ pg_ticks_to_ns(instr_time t)
 		 * value. In a 2nd step we adjust the number of elapsed ticks and
 		 * convert the remaining ticks.
 		 */
-		int64		count = t.ticks / max_ticks_no_overflow;
+		int64		count = ticks / max_ticks_no_overflow;
 		int64		max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION;
 
 		ns = max_ns * count;
@@ -201,11 +204,11 @@ pg_ticks_to_ns(instr_time t)
 		 * Subtract the ticks that we now already accounted for, so that they
 		 * don't get counted twice.
 		 */
-		t.ticks -= count * max_ticks_no_overflow;
-		Assert(t.ticks >= 0);
+		ticks -= count * max_ticks_no_overflow;
+		Assert(ticks >= 0);
 	}
 
-	ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION;
+	ns += ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION;
 	return ns;
 }
 
@@ -226,14 +229,14 @@ pg_initialize_get_ticks()
 #define INSTR_TIME_SET_CURRENT(t) \
 	((t) = pg_get_ticks())
 
-#define INSTR_TIME_GET_NANOSEC(t) \
-	pg_ticks_to_ns(t)
-
+#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \
+	(pg_ticks_to_ns(ticks))
 
 #else							/* WIN32 */
 
 
 /* Use QueryPerformanceCounter() */
+#define PG_INSTR_CLOCK_NAME	"QueryPerformanceCounter"
 
 /* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */
 static inline instr_time
@@ -265,8 +268,8 @@ GetTimerFrequency(void)
 #define INSTR_TIME_SET_CURRENT(t) \
 	((t) = pg_query_performance_counter())
 
-#define INSTR_TIME_GET_NANOSEC(t) \
-	((int64) ((t).ticks * ((double) NS_PER_S / GetTimerFrequency())))
+#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \
+	((int64) ((ticks) * ((double) NS_PER_S / GetTimerFrequency())))
 
 #endif							/* WIN32 */
 
@@ -285,9 +288,14 @@ GetTimerFrequency(void)
 #define INSTR_TIME_SUBTRACT(x,y) \
 	((x).ticks -= (y).ticks)
 
+#define INSTR_TIME_DIFF_NANOSEC(x,y) \
+	(INSTR_TIME_TICKS_TO_NANOSEC((x).ticks - (y).ticks))
+
 #define INSTR_TIME_ACCUM_DIFF(x,y,z) \
 	((x).ticks += (y).ticks - (z).ticks)
 
+#define INSTR_TIME_GET_NANOSEC(t) \
+	(INSTR_TIME_TICKS_TO_NANOSEC((t).ticks))
 
 #define INSTR_TIME_GET_DOUBLE(t) \
 	((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S)
-- 
2.47.3


--vtqqtrpooseurzip--





^ permalink  raw  reply  [nested|flat] 265+ messages in thread

* [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source
@ 2025-07-27 15:48  Lukas Fittl <[email protected]>
  0 siblings, 0 replies; 265+ messages in thread

From: Lukas Fittl @ 2025-07-27 15:48 UTC (permalink / raw)

In passing also reduce the per-loop overhead caused by repeated divisions
in INSTR_TIME_GET_NANOSEC when the ticks variable has become very large,
instead diff first and then turn it into nanosecs.
---
 src/bin/pg_test_timing/pg_test_timing.c | 59 +++++++++++++++++++------
 src/include/portability/instr_time.h    | 30 ++++++++-----
 2 files changed, 65 insertions(+), 24 deletions(-)

diff --git a/src/bin/pg_test_timing/pg_test_timing.c b/src/bin/pg_test_timing/pg_test_timing.c
index a5621251afc..b77ef2063b6 100644
--- a/src/bin/pg_test_timing/pg_test_timing.c
+++ b/src/bin/pg_test_timing/pg_test_timing.c
@@ -16,6 +16,7 @@ static const char *progname;
 
 static unsigned int test_duration = 3;
 static double max_rprct = 99.99;
+static bool fast_timing = false;
 
 /* record duration in powers of 2 nanoseconds */
 static long long int histogram[32];
@@ -56,6 +57,7 @@ handle_args(int argc, char *argv[])
 	static struct option long_options[] = {
 		{"duration", required_argument, NULL, 'd'},
 		{"cutoff", required_argument, NULL, 'c'},
+		{"fast", no_argument, NULL, 'f'},
 		{NULL, 0, NULL, 0}
 	};
 
@@ -68,7 +70,7 @@ handle_args(int argc, char *argv[])
 	{
 		if (strcmp(argv[1], "--help") == 0 || strcmp(argv[1], "-?") == 0)
 		{
-			printf(_("Usage: %s [-d DURATION] [-c CUTOFF]\n"), progname);
+			printf(_("Usage: %s [-d DURATION] [-c CUTOFF] [--fast]\n"), progname);
 			exit(0);
 		}
 		if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0)
@@ -78,7 +80,7 @@ handle_args(int argc, char *argv[])
 		}
 	}
 
-	while ((option = getopt_long(argc, argv, "d:c:",
+	while ((option = getopt_long(argc, argv, "d:c:f:",
 								 long_options, &optindex)) != -1)
 	{
 		switch (option)
@@ -125,6 +127,10 @@ handle_args(int argc, char *argv[])
 				}
 				break;
 
+			case 'f':
+				fast_timing = true;
+				break;
+
 			default:
 				fprintf(stderr, _("Try \"%s --help\" for more information.\n"),
 						progname);
@@ -155,11 +161,31 @@ test_timing(unsigned int duration)
 	uint64		total_time;
 	int64		time_elapsed = 0;
 	uint64		loop_count = 0;
-	uint64		prev,
-				cur;
 	instr_time	start_time,
 				end_time,
-				temp;
+				prev,
+				cur;
+	char	   *time_source = NULL;
+	bool		fast_timing_used = false;
+
+	INSTR_TIME_INITIALIZE();
+
+#if !defined(WIN32) && defined(__x86_64__) && defined(__linux__)
+	if (fast_timing && has_rdtsc)
+	{
+		time_source = "RDTSC";
+		fast_timing_used = true;
+	}
+	else if (has_rdtscp)
+		time_source = "RDTSCP";
+	else
+		time_source = PG_INSTR_CLOCK_NAME;
+#else
+	time_source = PG_INSTR_CLOCK_NAME;
+#endif
+	if (fast_timing && !fast_timing_used)
+		printf(_("Warning: Fast timing requested, but not available - regular timing source will be used\n"));
+	printf(_("Time source: %s\n"), time_source);
 
 	/*
 	 * Pre-zero the statistics data structures.  They're already zero by
@@ -173,8 +199,11 @@ test_timing(unsigned int duration)
 
 	total_time = duration > 0 ? duration * INT64CONST(1000000000) : 0;
 
-	INSTR_TIME_SET_CURRENT(start_time);
-	cur = INSTR_TIME_GET_NANOSEC(start_time);
+	if (fast_timing)
+		INSTR_TIME_SET_CURRENT_FAST(start_time);
+	else
+		INSTR_TIME_SET_CURRENT(start_time);
+	cur = start_time;
 
 	while (time_elapsed < total_time)
 	{
@@ -182,9 +211,11 @@ test_timing(unsigned int duration)
 					bits;
 
 		prev = cur;
-		INSTR_TIME_SET_CURRENT(temp);
-		cur = INSTR_TIME_GET_NANOSEC(temp);
-		diff = cur - prev;
+		if (fast_timing)
+			INSTR_TIME_SET_CURRENT_FAST(cur);
+		else
+			INSTR_TIME_SET_CURRENT(cur);
+		diff = INSTR_TIME_DIFF_NANOSEC(cur, prev);
 
 		/* Did time go backwards? */
 		if (unlikely(diff < 0))
@@ -217,11 +248,13 @@ test_timing(unsigned int duration)
 			largest_diff_count++;
 
 		loop_count++;
-		INSTR_TIME_SUBTRACT(temp, start_time);
-		time_elapsed = INSTR_TIME_GET_NANOSEC(temp);
+		time_elapsed = INSTR_TIME_DIFF_NANOSEC(cur, start_time);
 	}
 
-	INSTR_TIME_SET_CURRENT(end_time);
+	if (fast_timing)
+		INSTR_TIME_SET_CURRENT_FAST(end_time);
+	else
+		INSTR_TIME_SET_CURRENT(end_time);
 
 	INSTR_TIME_SUBTRACT(end_time, start_time);
 
diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h
index e2e339a0c4f..f02296f1026 100644
--- a/src/include/portability/instr_time.h
+++ b/src/include/portability/instr_time.h
@@ -112,10 +112,13 @@ extern int64 max_ticks_no_overflow;
  */
 #if defined(__darwin__) && defined(CLOCK_MONOTONIC_RAW)
 #define PG_INSTR_CLOCK	CLOCK_MONOTONIC_RAW
+#define PG_INSTR_CLOCK_NAME	"clock_gettime (CLOCK_MONOTONIC_RAW)"
 #elif defined(CLOCK_MONOTONIC)
 #define PG_INSTR_CLOCK	CLOCK_MONOTONIC
+#define PG_INSTR_CLOCK_NAME	"clock_gettime (CLOCK_MONOTONIC)"
 #else
 #define PG_INSTR_CLOCK	CLOCK_REALTIME
+#define PG_INSTR_CLOCK_NAME	"clock_gettime (CLOCK_REALTIME)"
 #endif
 
 #if defined(__x86_64__) && defined(__linux__)
@@ -174,7 +177,7 @@ pg_get_ticks(void)
 }
 
 static inline int64_t
-pg_ticks_to_ns(instr_time t)
+pg_ticks_to_ns(int64 ticks)
 {
 	/*
 	 * Would multiplication overflow? If so perform computation in two parts.
@@ -183,7 +186,7 @@ pg_ticks_to_ns(instr_time t)
 	 */
 	int64		ns = 0;
 
-	if (unlikely(t.ticks > max_ticks_no_overflow))
+	if (unlikely(ticks > max_ticks_no_overflow))
 	{
 		/*
 		 * Compute how often the maximum number of ticks fits completely into
@@ -192,7 +195,7 @@ pg_ticks_to_ns(instr_time t)
 		 * value. In a 2nd step we adjust the number of elapsed ticks and
 		 * convert the remaining ticks.
 		 */
-		int64		count = t.ticks / max_ticks_no_overflow;
+		int64		count = ticks / max_ticks_no_overflow;
 		int64		max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION;
 
 		ns = max_ns * count;
@@ -201,11 +204,11 @@ pg_ticks_to_ns(instr_time t)
 		 * Subtract the ticks that we now already accounted for, so that they
 		 * don't get counted twice.
 		 */
-		t.ticks -= count * max_ticks_no_overflow;
-		Assert(t.ticks >= 0);
+		ticks -= count * max_ticks_no_overflow;
+		Assert(ticks >= 0);
 	}
 
-	ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION;
+	ns += ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION;
 	return ns;
 }
 
@@ -226,14 +229,14 @@ pg_initialize_get_ticks()
 #define INSTR_TIME_SET_CURRENT(t) \
 	((t) = pg_get_ticks())
 
-#define INSTR_TIME_GET_NANOSEC(t) \
-	pg_ticks_to_ns(t)
-
+#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \
+	(pg_ticks_to_ns(ticks))
 
 #else							/* WIN32 */
 
 
 /* Use QueryPerformanceCounter() */
+#define PG_INSTR_CLOCK_NAME	"QueryPerformanceCounter"
 
 /* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */
 static inline instr_time
@@ -265,8 +268,8 @@ GetTimerFrequency(void)
 #define INSTR_TIME_SET_CURRENT(t) \
 	((t) = pg_query_performance_counter())
 
-#define INSTR_TIME_GET_NANOSEC(t) \
-	((int64) ((t).ticks * ((double) NS_PER_S / GetTimerFrequency())))
+#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \
+	((int64) ((ticks) * ((double) NS_PER_S / GetTimerFrequency())))
 
 #endif							/* WIN32 */
 
@@ -285,9 +288,14 @@ GetTimerFrequency(void)
 #define INSTR_TIME_SUBTRACT(x,y) \
 	((x).ticks -= (y).ticks)
 
+#define INSTR_TIME_DIFF_NANOSEC(x,y) \
+	(INSTR_TIME_TICKS_TO_NANOSEC((x).ticks - (y).ticks))
+
 #define INSTR_TIME_ACCUM_DIFF(x,y,z) \
 	((x).ticks += (y).ticks - (z).ticks)
 
+#define INSTR_TIME_GET_NANOSEC(t) \
+	(INSTR_TIME_TICKS_TO_NANOSEC((t).ticks))
 
 #define INSTR_TIME_GET_DOUBLE(t) \
 	((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S)
-- 
2.47.3


--vtqqtrpooseurzip--





^ permalink  raw  reply  [nested|flat] 265+ messages in thread

* [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source
@ 2025-07-27 15:48  Lukas Fittl <[email protected]>
  0 siblings, 0 replies; 265+ messages in thread

From: Lukas Fittl @ 2025-07-27 15:48 UTC (permalink / raw)

In passing also reduce the per-loop overhead caused by repeated divisions
in INSTR_TIME_GET_NANOSEC when the ticks variable has become very large,
instead diff first and then turn it into nanosecs.
---
 src/bin/pg_test_timing/pg_test_timing.c | 59 +++++++++++++++++++------
 src/include/portability/instr_time.h    | 30 ++++++++-----
 2 files changed, 65 insertions(+), 24 deletions(-)

diff --git a/src/bin/pg_test_timing/pg_test_timing.c b/src/bin/pg_test_timing/pg_test_timing.c
index a5621251afc..b77ef2063b6 100644
--- a/src/bin/pg_test_timing/pg_test_timing.c
+++ b/src/bin/pg_test_timing/pg_test_timing.c
@@ -16,6 +16,7 @@ static const char *progname;
 
 static unsigned int test_duration = 3;
 static double max_rprct = 99.99;
+static bool fast_timing = false;
 
 /* record duration in powers of 2 nanoseconds */
 static long long int histogram[32];
@@ -56,6 +57,7 @@ handle_args(int argc, char *argv[])
 	static struct option long_options[] = {
 		{"duration", required_argument, NULL, 'd'},
 		{"cutoff", required_argument, NULL, 'c'},
+		{"fast", no_argument, NULL, 'f'},
 		{NULL, 0, NULL, 0}
 	};
 
@@ -68,7 +70,7 @@ handle_args(int argc, char *argv[])
 	{
 		if (strcmp(argv[1], "--help") == 0 || strcmp(argv[1], "-?") == 0)
 		{
-			printf(_("Usage: %s [-d DURATION] [-c CUTOFF]\n"), progname);
+			printf(_("Usage: %s [-d DURATION] [-c CUTOFF] [--fast]\n"), progname);
 			exit(0);
 		}
 		if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0)
@@ -78,7 +80,7 @@ handle_args(int argc, char *argv[])
 		}
 	}
 
-	while ((option = getopt_long(argc, argv, "d:c:",
+	while ((option = getopt_long(argc, argv, "d:c:f:",
 								 long_options, &optindex)) != -1)
 	{
 		switch (option)
@@ -125,6 +127,10 @@ handle_args(int argc, char *argv[])
 				}
 				break;
 
+			case 'f':
+				fast_timing = true;
+				break;
+
 			default:
 				fprintf(stderr, _("Try \"%s --help\" for more information.\n"),
 						progname);
@@ -155,11 +161,31 @@ test_timing(unsigned int duration)
 	uint64		total_time;
 	int64		time_elapsed = 0;
 	uint64		loop_count = 0;
-	uint64		prev,
-				cur;
 	instr_time	start_time,
 				end_time,
-				temp;
+				prev,
+				cur;
+	char	   *time_source = NULL;
+	bool		fast_timing_used = false;
+
+	INSTR_TIME_INITIALIZE();
+
+#if !defined(WIN32) && defined(__x86_64__) && defined(__linux__)
+	if (fast_timing && has_rdtsc)
+	{
+		time_source = "RDTSC";
+		fast_timing_used = true;
+	}
+	else if (has_rdtscp)
+		time_source = "RDTSCP";
+	else
+		time_source = PG_INSTR_CLOCK_NAME;
+#else
+	time_source = PG_INSTR_CLOCK_NAME;
+#endif
+	if (fast_timing && !fast_timing_used)
+		printf(_("Warning: Fast timing requested, but not available - regular timing source will be used\n"));
+	printf(_("Time source: %s\n"), time_source);
 
 	/*
 	 * Pre-zero the statistics data structures.  They're already zero by
@@ -173,8 +199,11 @@ test_timing(unsigned int duration)
 
 	total_time = duration > 0 ? duration * INT64CONST(1000000000) : 0;
 
-	INSTR_TIME_SET_CURRENT(start_time);
-	cur = INSTR_TIME_GET_NANOSEC(start_time);
+	if (fast_timing)
+		INSTR_TIME_SET_CURRENT_FAST(start_time);
+	else
+		INSTR_TIME_SET_CURRENT(start_time);
+	cur = start_time;
 
 	while (time_elapsed < total_time)
 	{
@@ -182,9 +211,11 @@ test_timing(unsigned int duration)
 					bits;
 
 		prev = cur;
-		INSTR_TIME_SET_CURRENT(temp);
-		cur = INSTR_TIME_GET_NANOSEC(temp);
-		diff = cur - prev;
+		if (fast_timing)
+			INSTR_TIME_SET_CURRENT_FAST(cur);
+		else
+			INSTR_TIME_SET_CURRENT(cur);
+		diff = INSTR_TIME_DIFF_NANOSEC(cur, prev);
 
 		/* Did time go backwards? */
 		if (unlikely(diff < 0))
@@ -217,11 +248,13 @@ test_timing(unsigned int duration)
 			largest_diff_count++;
 
 		loop_count++;
-		INSTR_TIME_SUBTRACT(temp, start_time);
-		time_elapsed = INSTR_TIME_GET_NANOSEC(temp);
+		time_elapsed = INSTR_TIME_DIFF_NANOSEC(cur, start_time);
 	}
 
-	INSTR_TIME_SET_CURRENT(end_time);
+	if (fast_timing)
+		INSTR_TIME_SET_CURRENT_FAST(end_time);
+	else
+		INSTR_TIME_SET_CURRENT(end_time);
 
 	INSTR_TIME_SUBTRACT(end_time, start_time);
 
diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h
index e2e339a0c4f..f02296f1026 100644
--- a/src/include/portability/instr_time.h
+++ b/src/include/portability/instr_time.h
@@ -112,10 +112,13 @@ extern int64 max_ticks_no_overflow;
  */
 #if defined(__darwin__) && defined(CLOCK_MONOTONIC_RAW)
 #define PG_INSTR_CLOCK	CLOCK_MONOTONIC_RAW
+#define PG_INSTR_CLOCK_NAME	"clock_gettime (CLOCK_MONOTONIC_RAW)"
 #elif defined(CLOCK_MONOTONIC)
 #define PG_INSTR_CLOCK	CLOCK_MONOTONIC
+#define PG_INSTR_CLOCK_NAME	"clock_gettime (CLOCK_MONOTONIC)"
 #else
 #define PG_INSTR_CLOCK	CLOCK_REALTIME
+#define PG_INSTR_CLOCK_NAME	"clock_gettime (CLOCK_REALTIME)"
 #endif
 
 #if defined(__x86_64__) && defined(__linux__)
@@ -174,7 +177,7 @@ pg_get_ticks(void)
 }
 
 static inline int64_t
-pg_ticks_to_ns(instr_time t)
+pg_ticks_to_ns(int64 ticks)
 {
 	/*
 	 * Would multiplication overflow? If so perform computation in two parts.
@@ -183,7 +186,7 @@ pg_ticks_to_ns(instr_time t)
 	 */
 	int64		ns = 0;
 
-	if (unlikely(t.ticks > max_ticks_no_overflow))
+	if (unlikely(ticks > max_ticks_no_overflow))
 	{
 		/*
 		 * Compute how often the maximum number of ticks fits completely into
@@ -192,7 +195,7 @@ pg_ticks_to_ns(instr_time t)
 		 * value. In a 2nd step we adjust the number of elapsed ticks and
 		 * convert the remaining ticks.
 		 */
-		int64		count = t.ticks / max_ticks_no_overflow;
+		int64		count = ticks / max_ticks_no_overflow;
 		int64		max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION;
 
 		ns = max_ns * count;
@@ -201,11 +204,11 @@ pg_ticks_to_ns(instr_time t)
 		 * Subtract the ticks that we now already accounted for, so that they
 		 * don't get counted twice.
 		 */
-		t.ticks -= count * max_ticks_no_overflow;
-		Assert(t.ticks >= 0);
+		ticks -= count * max_ticks_no_overflow;
+		Assert(ticks >= 0);
 	}
 
-	ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION;
+	ns += ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION;
 	return ns;
 }
 
@@ -226,14 +229,14 @@ pg_initialize_get_ticks()
 #define INSTR_TIME_SET_CURRENT(t) \
 	((t) = pg_get_ticks())
 
-#define INSTR_TIME_GET_NANOSEC(t) \
-	pg_ticks_to_ns(t)
-
+#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \
+	(pg_ticks_to_ns(ticks))
 
 #else							/* WIN32 */
 
 
 /* Use QueryPerformanceCounter() */
+#define PG_INSTR_CLOCK_NAME	"QueryPerformanceCounter"
 
 /* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */
 static inline instr_time
@@ -265,8 +268,8 @@ GetTimerFrequency(void)
 #define INSTR_TIME_SET_CURRENT(t) \
 	((t) = pg_query_performance_counter())
 
-#define INSTR_TIME_GET_NANOSEC(t) \
-	((int64) ((t).ticks * ((double) NS_PER_S / GetTimerFrequency())))
+#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \
+	((int64) ((ticks) * ((double) NS_PER_S / GetTimerFrequency())))
 
 #endif							/* WIN32 */
 
@@ -285,9 +288,14 @@ GetTimerFrequency(void)
 #define INSTR_TIME_SUBTRACT(x,y) \
 	((x).ticks -= (y).ticks)
 
+#define INSTR_TIME_DIFF_NANOSEC(x,y) \
+	(INSTR_TIME_TICKS_TO_NANOSEC((x).ticks - (y).ticks))
+
 #define INSTR_TIME_ACCUM_DIFF(x,y,z) \
 	((x).ticks += (y).ticks - (z).ticks)
 
+#define INSTR_TIME_GET_NANOSEC(t) \
+	(INSTR_TIME_TICKS_TO_NANOSEC((t).ticks))
 
 #define INSTR_TIME_GET_DOUBLE(t) \
 	((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S)
-- 
2.47.3


--vtqqtrpooseurzip--





^ permalink  raw  reply  [nested|flat] 265+ messages in thread

* [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source
@ 2025-07-27 15:48  Lukas Fittl <[email protected]>
  0 siblings, 0 replies; 265+ messages in thread

From: Lukas Fittl @ 2025-07-27 15:48 UTC (permalink / raw)

In passing also reduce the per-loop overhead caused by repeated divisions
in INSTR_TIME_GET_NANOSEC when the ticks variable has become very large,
instead diff first and then turn it into nanosecs.
---
 src/bin/pg_test_timing/pg_test_timing.c | 59 +++++++++++++++++++------
 src/include/portability/instr_time.h    | 30 ++++++++-----
 2 files changed, 65 insertions(+), 24 deletions(-)

diff --git a/src/bin/pg_test_timing/pg_test_timing.c b/src/bin/pg_test_timing/pg_test_timing.c
index a5621251afc..b77ef2063b6 100644
--- a/src/bin/pg_test_timing/pg_test_timing.c
+++ b/src/bin/pg_test_timing/pg_test_timing.c
@@ -16,6 +16,7 @@ static const char *progname;
 
 static unsigned int test_duration = 3;
 static double max_rprct = 99.99;
+static bool fast_timing = false;
 
 /* record duration in powers of 2 nanoseconds */
 static long long int histogram[32];
@@ -56,6 +57,7 @@ handle_args(int argc, char *argv[])
 	static struct option long_options[] = {
 		{"duration", required_argument, NULL, 'd'},
 		{"cutoff", required_argument, NULL, 'c'},
+		{"fast", no_argument, NULL, 'f'},
 		{NULL, 0, NULL, 0}
 	};
 
@@ -68,7 +70,7 @@ handle_args(int argc, char *argv[])
 	{
 		if (strcmp(argv[1], "--help") == 0 || strcmp(argv[1], "-?") == 0)
 		{
-			printf(_("Usage: %s [-d DURATION] [-c CUTOFF]\n"), progname);
+			printf(_("Usage: %s [-d DURATION] [-c CUTOFF] [--fast]\n"), progname);
 			exit(0);
 		}
 		if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0)
@@ -78,7 +80,7 @@ handle_args(int argc, char *argv[])
 		}
 	}
 
-	while ((option = getopt_long(argc, argv, "d:c:",
+	while ((option = getopt_long(argc, argv, "d:c:f:",
 								 long_options, &optindex)) != -1)
 	{
 		switch (option)
@@ -125,6 +127,10 @@ handle_args(int argc, char *argv[])
 				}
 				break;
 
+			case 'f':
+				fast_timing = true;
+				break;
+
 			default:
 				fprintf(stderr, _("Try \"%s --help\" for more information.\n"),
 						progname);
@@ -155,11 +161,31 @@ test_timing(unsigned int duration)
 	uint64		total_time;
 	int64		time_elapsed = 0;
 	uint64		loop_count = 0;
-	uint64		prev,
-				cur;
 	instr_time	start_time,
 				end_time,
-				temp;
+				prev,
+				cur;
+	char	   *time_source = NULL;
+	bool		fast_timing_used = false;
+
+	INSTR_TIME_INITIALIZE();
+
+#if !defined(WIN32) && defined(__x86_64__) && defined(__linux__)
+	if (fast_timing && has_rdtsc)
+	{
+		time_source = "RDTSC";
+		fast_timing_used = true;
+	}
+	else if (has_rdtscp)
+		time_source = "RDTSCP";
+	else
+		time_source = PG_INSTR_CLOCK_NAME;
+#else
+	time_source = PG_INSTR_CLOCK_NAME;
+#endif
+	if (fast_timing && !fast_timing_used)
+		printf(_("Warning: Fast timing requested, but not available - regular timing source will be used\n"));
+	printf(_("Time source: %s\n"), time_source);
 
 	/*
 	 * Pre-zero the statistics data structures.  They're already zero by
@@ -173,8 +199,11 @@ test_timing(unsigned int duration)
 
 	total_time = duration > 0 ? duration * INT64CONST(1000000000) : 0;
 
-	INSTR_TIME_SET_CURRENT(start_time);
-	cur = INSTR_TIME_GET_NANOSEC(start_time);
+	if (fast_timing)
+		INSTR_TIME_SET_CURRENT_FAST(start_time);
+	else
+		INSTR_TIME_SET_CURRENT(start_time);
+	cur = start_time;
 
 	while (time_elapsed < total_time)
 	{
@@ -182,9 +211,11 @@ test_timing(unsigned int duration)
 					bits;
 
 		prev = cur;
-		INSTR_TIME_SET_CURRENT(temp);
-		cur = INSTR_TIME_GET_NANOSEC(temp);
-		diff = cur - prev;
+		if (fast_timing)
+			INSTR_TIME_SET_CURRENT_FAST(cur);
+		else
+			INSTR_TIME_SET_CURRENT(cur);
+		diff = INSTR_TIME_DIFF_NANOSEC(cur, prev);
 
 		/* Did time go backwards? */
 		if (unlikely(diff < 0))
@@ -217,11 +248,13 @@ test_timing(unsigned int duration)
 			largest_diff_count++;
 
 		loop_count++;
-		INSTR_TIME_SUBTRACT(temp, start_time);
-		time_elapsed = INSTR_TIME_GET_NANOSEC(temp);
+		time_elapsed = INSTR_TIME_DIFF_NANOSEC(cur, start_time);
 	}
 
-	INSTR_TIME_SET_CURRENT(end_time);
+	if (fast_timing)
+		INSTR_TIME_SET_CURRENT_FAST(end_time);
+	else
+		INSTR_TIME_SET_CURRENT(end_time);
 
 	INSTR_TIME_SUBTRACT(end_time, start_time);
 
diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h
index e2e339a0c4f..f02296f1026 100644
--- a/src/include/portability/instr_time.h
+++ b/src/include/portability/instr_time.h
@@ -112,10 +112,13 @@ extern int64 max_ticks_no_overflow;
  */
 #if defined(__darwin__) && defined(CLOCK_MONOTONIC_RAW)
 #define PG_INSTR_CLOCK	CLOCK_MONOTONIC_RAW
+#define PG_INSTR_CLOCK_NAME	"clock_gettime (CLOCK_MONOTONIC_RAW)"
 #elif defined(CLOCK_MONOTONIC)
 #define PG_INSTR_CLOCK	CLOCK_MONOTONIC
+#define PG_INSTR_CLOCK_NAME	"clock_gettime (CLOCK_MONOTONIC)"
 #else
 #define PG_INSTR_CLOCK	CLOCK_REALTIME
+#define PG_INSTR_CLOCK_NAME	"clock_gettime (CLOCK_REALTIME)"
 #endif
 
 #if defined(__x86_64__) && defined(__linux__)
@@ -174,7 +177,7 @@ pg_get_ticks(void)
 }
 
 static inline int64_t
-pg_ticks_to_ns(instr_time t)
+pg_ticks_to_ns(int64 ticks)
 {
 	/*
 	 * Would multiplication overflow? If so perform computation in two parts.
@@ -183,7 +186,7 @@ pg_ticks_to_ns(instr_time t)
 	 */
 	int64		ns = 0;
 
-	if (unlikely(t.ticks > max_ticks_no_overflow))
+	if (unlikely(ticks > max_ticks_no_overflow))
 	{
 		/*
 		 * Compute how often the maximum number of ticks fits completely into
@@ -192,7 +195,7 @@ pg_ticks_to_ns(instr_time t)
 		 * value. In a 2nd step we adjust the number of elapsed ticks and
 		 * convert the remaining ticks.
 		 */
-		int64		count = t.ticks / max_ticks_no_overflow;
+		int64		count = ticks / max_ticks_no_overflow;
 		int64		max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION;
 
 		ns = max_ns * count;
@@ -201,11 +204,11 @@ pg_ticks_to_ns(instr_time t)
 		 * Subtract the ticks that we now already accounted for, so that they
 		 * don't get counted twice.
 		 */
-		t.ticks -= count * max_ticks_no_overflow;
-		Assert(t.ticks >= 0);
+		ticks -= count * max_ticks_no_overflow;
+		Assert(ticks >= 0);
 	}
 
-	ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION;
+	ns += ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION;
 	return ns;
 }
 
@@ -226,14 +229,14 @@ pg_initialize_get_ticks()
 #define INSTR_TIME_SET_CURRENT(t) \
 	((t) = pg_get_ticks())
 
-#define INSTR_TIME_GET_NANOSEC(t) \
-	pg_ticks_to_ns(t)
-
+#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \
+	(pg_ticks_to_ns(ticks))
 
 #else							/* WIN32 */
 
 
 /* Use QueryPerformanceCounter() */
+#define PG_INSTR_CLOCK_NAME	"QueryPerformanceCounter"
 
 /* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */
 static inline instr_time
@@ -265,8 +268,8 @@ GetTimerFrequency(void)
 #define INSTR_TIME_SET_CURRENT(t) \
 	((t) = pg_query_performance_counter())
 
-#define INSTR_TIME_GET_NANOSEC(t) \
-	((int64) ((t).ticks * ((double) NS_PER_S / GetTimerFrequency())))
+#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \
+	((int64) ((ticks) * ((double) NS_PER_S / GetTimerFrequency())))
 
 #endif							/* WIN32 */
 
@@ -285,9 +288,14 @@ GetTimerFrequency(void)
 #define INSTR_TIME_SUBTRACT(x,y) \
 	((x).ticks -= (y).ticks)
 
+#define INSTR_TIME_DIFF_NANOSEC(x,y) \
+	(INSTR_TIME_TICKS_TO_NANOSEC((x).ticks - (y).ticks))
+
 #define INSTR_TIME_ACCUM_DIFF(x,y,z) \
 	((x).ticks += (y).ticks - (z).ticks)
 
+#define INSTR_TIME_GET_NANOSEC(t) \
+	(INSTR_TIME_TICKS_TO_NANOSEC((t).ticks))
 
 #define INSTR_TIME_GET_DOUBLE(t) \
 	((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S)
-- 
2.47.3


--vtqqtrpooseurzip--





^ permalink  raw  reply  [nested|flat] 265+ messages in thread

* [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source
@ 2025-07-27 15:48  Lukas Fittl <[email protected]>
  0 siblings, 0 replies; 265+ messages in thread

From: Lukas Fittl @ 2025-07-27 15:48 UTC (permalink / raw)

In passing also reduce the per-loop overhead caused by repeated divisions
in INSTR_TIME_GET_NANOSEC when the ticks variable has become very large,
instead diff first and then turn it into nanosecs.
---
 src/bin/pg_test_timing/pg_test_timing.c | 59 +++++++++++++++++++------
 src/include/portability/instr_time.h    | 30 ++++++++-----
 2 files changed, 65 insertions(+), 24 deletions(-)

diff --git a/src/bin/pg_test_timing/pg_test_timing.c b/src/bin/pg_test_timing/pg_test_timing.c
index a5621251afc..b77ef2063b6 100644
--- a/src/bin/pg_test_timing/pg_test_timing.c
+++ b/src/bin/pg_test_timing/pg_test_timing.c
@@ -16,6 +16,7 @@ static const char *progname;
 
 static unsigned int test_duration = 3;
 static double max_rprct = 99.99;
+static bool fast_timing = false;
 
 /* record duration in powers of 2 nanoseconds */
 static long long int histogram[32];
@@ -56,6 +57,7 @@ handle_args(int argc, char *argv[])
 	static struct option long_options[] = {
 		{"duration", required_argument, NULL, 'd'},
 		{"cutoff", required_argument, NULL, 'c'},
+		{"fast", no_argument, NULL, 'f'},
 		{NULL, 0, NULL, 0}
 	};
 
@@ -68,7 +70,7 @@ handle_args(int argc, char *argv[])
 	{
 		if (strcmp(argv[1], "--help") == 0 || strcmp(argv[1], "-?") == 0)
 		{
-			printf(_("Usage: %s [-d DURATION] [-c CUTOFF]\n"), progname);
+			printf(_("Usage: %s [-d DURATION] [-c CUTOFF] [--fast]\n"), progname);
 			exit(0);
 		}
 		if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0)
@@ -78,7 +80,7 @@ handle_args(int argc, char *argv[])
 		}
 	}
 
-	while ((option = getopt_long(argc, argv, "d:c:",
+	while ((option = getopt_long(argc, argv, "d:c:f:",
 								 long_options, &optindex)) != -1)
 	{
 		switch (option)
@@ -125,6 +127,10 @@ handle_args(int argc, char *argv[])
 				}
 				break;
 
+			case 'f':
+				fast_timing = true;
+				break;
+
 			default:
 				fprintf(stderr, _("Try \"%s --help\" for more information.\n"),
 						progname);
@@ -155,11 +161,31 @@ test_timing(unsigned int duration)
 	uint64		total_time;
 	int64		time_elapsed = 0;
 	uint64		loop_count = 0;
-	uint64		prev,
-				cur;
 	instr_time	start_time,
 				end_time,
-				temp;
+				prev,
+				cur;
+	char	   *time_source = NULL;
+	bool		fast_timing_used = false;
+
+	INSTR_TIME_INITIALIZE();
+
+#if !defined(WIN32) && defined(__x86_64__) && defined(__linux__)
+	if (fast_timing && has_rdtsc)
+	{
+		time_source = "RDTSC";
+		fast_timing_used = true;
+	}
+	else if (has_rdtscp)
+		time_source = "RDTSCP";
+	else
+		time_source = PG_INSTR_CLOCK_NAME;
+#else
+	time_source = PG_INSTR_CLOCK_NAME;
+#endif
+	if (fast_timing && !fast_timing_used)
+		printf(_("Warning: Fast timing requested, but not available - regular timing source will be used\n"));
+	printf(_("Time source: %s\n"), time_source);
 
 	/*
 	 * Pre-zero the statistics data structures.  They're already zero by
@@ -173,8 +199,11 @@ test_timing(unsigned int duration)
 
 	total_time = duration > 0 ? duration * INT64CONST(1000000000) : 0;
 
-	INSTR_TIME_SET_CURRENT(start_time);
-	cur = INSTR_TIME_GET_NANOSEC(start_time);
+	if (fast_timing)
+		INSTR_TIME_SET_CURRENT_FAST(start_time);
+	else
+		INSTR_TIME_SET_CURRENT(start_time);
+	cur = start_time;
 
 	while (time_elapsed < total_time)
 	{
@@ -182,9 +211,11 @@ test_timing(unsigned int duration)
 					bits;
 
 		prev = cur;
-		INSTR_TIME_SET_CURRENT(temp);
-		cur = INSTR_TIME_GET_NANOSEC(temp);
-		diff = cur - prev;
+		if (fast_timing)
+			INSTR_TIME_SET_CURRENT_FAST(cur);
+		else
+			INSTR_TIME_SET_CURRENT(cur);
+		diff = INSTR_TIME_DIFF_NANOSEC(cur, prev);
 
 		/* Did time go backwards? */
 		if (unlikely(diff < 0))
@@ -217,11 +248,13 @@ test_timing(unsigned int duration)
 			largest_diff_count++;
 
 		loop_count++;
-		INSTR_TIME_SUBTRACT(temp, start_time);
-		time_elapsed = INSTR_TIME_GET_NANOSEC(temp);
+		time_elapsed = INSTR_TIME_DIFF_NANOSEC(cur, start_time);
 	}
 
-	INSTR_TIME_SET_CURRENT(end_time);
+	if (fast_timing)
+		INSTR_TIME_SET_CURRENT_FAST(end_time);
+	else
+		INSTR_TIME_SET_CURRENT(end_time);
 
 	INSTR_TIME_SUBTRACT(end_time, start_time);
 
diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h
index e2e339a0c4f..f02296f1026 100644
--- a/src/include/portability/instr_time.h
+++ b/src/include/portability/instr_time.h
@@ -112,10 +112,13 @@ extern int64 max_ticks_no_overflow;
  */
 #if defined(__darwin__) && defined(CLOCK_MONOTONIC_RAW)
 #define PG_INSTR_CLOCK	CLOCK_MONOTONIC_RAW
+#define PG_INSTR_CLOCK_NAME	"clock_gettime (CLOCK_MONOTONIC_RAW)"
 #elif defined(CLOCK_MONOTONIC)
 #define PG_INSTR_CLOCK	CLOCK_MONOTONIC
+#define PG_INSTR_CLOCK_NAME	"clock_gettime (CLOCK_MONOTONIC)"
 #else
 #define PG_INSTR_CLOCK	CLOCK_REALTIME
+#define PG_INSTR_CLOCK_NAME	"clock_gettime (CLOCK_REALTIME)"
 #endif
 
 #if defined(__x86_64__) && defined(__linux__)
@@ -174,7 +177,7 @@ pg_get_ticks(void)
 }
 
 static inline int64_t
-pg_ticks_to_ns(instr_time t)
+pg_ticks_to_ns(int64 ticks)
 {
 	/*
 	 * Would multiplication overflow? If so perform computation in two parts.
@@ -183,7 +186,7 @@ pg_ticks_to_ns(instr_time t)
 	 */
 	int64		ns = 0;
 
-	if (unlikely(t.ticks > max_ticks_no_overflow))
+	if (unlikely(ticks > max_ticks_no_overflow))
 	{
 		/*
 		 * Compute how often the maximum number of ticks fits completely into
@@ -192,7 +195,7 @@ pg_ticks_to_ns(instr_time t)
 		 * value. In a 2nd step we adjust the number of elapsed ticks and
 		 * convert the remaining ticks.
 		 */
-		int64		count = t.ticks / max_ticks_no_overflow;
+		int64		count = ticks / max_ticks_no_overflow;
 		int64		max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION;
 
 		ns = max_ns * count;
@@ -201,11 +204,11 @@ pg_ticks_to_ns(instr_time t)
 		 * Subtract the ticks that we now already accounted for, so that they
 		 * don't get counted twice.
 		 */
-		t.ticks -= count * max_ticks_no_overflow;
-		Assert(t.ticks >= 0);
+		ticks -= count * max_ticks_no_overflow;
+		Assert(ticks >= 0);
 	}
 
-	ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION;
+	ns += ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION;
 	return ns;
 }
 
@@ -226,14 +229,14 @@ pg_initialize_get_ticks()
 #define INSTR_TIME_SET_CURRENT(t) \
 	((t) = pg_get_ticks())
 
-#define INSTR_TIME_GET_NANOSEC(t) \
-	pg_ticks_to_ns(t)
-
+#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \
+	(pg_ticks_to_ns(ticks))
 
 #else							/* WIN32 */
 
 
 /* Use QueryPerformanceCounter() */
+#define PG_INSTR_CLOCK_NAME	"QueryPerformanceCounter"
 
 /* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */
 static inline instr_time
@@ -265,8 +268,8 @@ GetTimerFrequency(void)
 #define INSTR_TIME_SET_CURRENT(t) \
 	((t) = pg_query_performance_counter())
 
-#define INSTR_TIME_GET_NANOSEC(t) \
-	((int64) ((t).ticks * ((double) NS_PER_S / GetTimerFrequency())))
+#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \
+	((int64) ((ticks) * ((double) NS_PER_S / GetTimerFrequency())))
 
 #endif							/* WIN32 */
 
@@ -285,9 +288,14 @@ GetTimerFrequency(void)
 #define INSTR_TIME_SUBTRACT(x,y) \
 	((x).ticks -= (y).ticks)
 
+#define INSTR_TIME_DIFF_NANOSEC(x,y) \
+	(INSTR_TIME_TICKS_TO_NANOSEC((x).ticks - (y).ticks))
+
 #define INSTR_TIME_ACCUM_DIFF(x,y,z) \
 	((x).ticks += (y).ticks - (z).ticks)
 
+#define INSTR_TIME_GET_NANOSEC(t) \
+	(INSTR_TIME_TICKS_TO_NANOSEC((t).ticks))
 
 #define INSTR_TIME_GET_DOUBLE(t) \
 	((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S)
-- 
2.47.3


--vtqqtrpooseurzip--





^ permalink  raw  reply  [nested|flat] 265+ messages in thread

* [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source
@ 2025-07-27 15:48  Lukas Fittl <[email protected]>
  0 siblings, 0 replies; 265+ messages in thread

From: Lukas Fittl @ 2025-07-27 15:48 UTC (permalink / raw)

In passing also reduce the per-loop overhead caused by repeated divisions
in INSTR_TIME_GET_NANOSEC when the ticks variable has become very large,
instead diff first and then turn it into nanosecs.
---
 src/bin/pg_test_timing/pg_test_timing.c | 59 +++++++++++++++++++------
 src/include/portability/instr_time.h    | 30 ++++++++-----
 2 files changed, 65 insertions(+), 24 deletions(-)

diff --git a/src/bin/pg_test_timing/pg_test_timing.c b/src/bin/pg_test_timing/pg_test_timing.c
index a5621251afc..b77ef2063b6 100644
--- a/src/bin/pg_test_timing/pg_test_timing.c
+++ b/src/bin/pg_test_timing/pg_test_timing.c
@@ -16,6 +16,7 @@ static const char *progname;
 
 static unsigned int test_duration = 3;
 static double max_rprct = 99.99;
+static bool fast_timing = false;
 
 /* record duration in powers of 2 nanoseconds */
 static long long int histogram[32];
@@ -56,6 +57,7 @@ handle_args(int argc, char *argv[])
 	static struct option long_options[] = {
 		{"duration", required_argument, NULL, 'd'},
 		{"cutoff", required_argument, NULL, 'c'},
+		{"fast", no_argument, NULL, 'f'},
 		{NULL, 0, NULL, 0}
 	};
 
@@ -68,7 +70,7 @@ handle_args(int argc, char *argv[])
 	{
 		if (strcmp(argv[1], "--help") == 0 || strcmp(argv[1], "-?") == 0)
 		{
-			printf(_("Usage: %s [-d DURATION] [-c CUTOFF]\n"), progname);
+			printf(_("Usage: %s [-d DURATION] [-c CUTOFF] [--fast]\n"), progname);
 			exit(0);
 		}
 		if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0)
@@ -78,7 +80,7 @@ handle_args(int argc, char *argv[])
 		}
 	}
 
-	while ((option = getopt_long(argc, argv, "d:c:",
+	while ((option = getopt_long(argc, argv, "d:c:f:",
 								 long_options, &optindex)) != -1)
 	{
 		switch (option)
@@ -125,6 +127,10 @@ handle_args(int argc, char *argv[])
 				}
 				break;
 
+			case 'f':
+				fast_timing = true;
+				break;
+
 			default:
 				fprintf(stderr, _("Try \"%s --help\" for more information.\n"),
 						progname);
@@ -155,11 +161,31 @@ test_timing(unsigned int duration)
 	uint64		total_time;
 	int64		time_elapsed = 0;
 	uint64		loop_count = 0;
-	uint64		prev,
-				cur;
 	instr_time	start_time,
 				end_time,
-				temp;
+				prev,
+				cur;
+	char	   *time_source = NULL;
+	bool		fast_timing_used = false;
+
+	INSTR_TIME_INITIALIZE();
+
+#if !defined(WIN32) && defined(__x86_64__) && defined(__linux__)
+	if (fast_timing && has_rdtsc)
+	{
+		time_source = "RDTSC";
+		fast_timing_used = true;
+	}
+	else if (has_rdtscp)
+		time_source = "RDTSCP";
+	else
+		time_source = PG_INSTR_CLOCK_NAME;
+#else
+	time_source = PG_INSTR_CLOCK_NAME;
+#endif
+	if (fast_timing && !fast_timing_used)
+		printf(_("Warning: Fast timing requested, but not available - regular timing source will be used\n"));
+	printf(_("Time source: %s\n"), time_source);
 
 	/*
 	 * Pre-zero the statistics data structures.  They're already zero by
@@ -173,8 +199,11 @@ test_timing(unsigned int duration)
 
 	total_time = duration > 0 ? duration * INT64CONST(1000000000) : 0;
 
-	INSTR_TIME_SET_CURRENT(start_time);
-	cur = INSTR_TIME_GET_NANOSEC(start_time);
+	if (fast_timing)
+		INSTR_TIME_SET_CURRENT_FAST(start_time);
+	else
+		INSTR_TIME_SET_CURRENT(start_time);
+	cur = start_time;
 
 	while (time_elapsed < total_time)
 	{
@@ -182,9 +211,11 @@ test_timing(unsigned int duration)
 					bits;
 
 		prev = cur;
-		INSTR_TIME_SET_CURRENT(temp);
-		cur = INSTR_TIME_GET_NANOSEC(temp);
-		diff = cur - prev;
+		if (fast_timing)
+			INSTR_TIME_SET_CURRENT_FAST(cur);
+		else
+			INSTR_TIME_SET_CURRENT(cur);
+		diff = INSTR_TIME_DIFF_NANOSEC(cur, prev);
 
 		/* Did time go backwards? */
 		if (unlikely(diff < 0))
@@ -217,11 +248,13 @@ test_timing(unsigned int duration)
 			largest_diff_count++;
 
 		loop_count++;
-		INSTR_TIME_SUBTRACT(temp, start_time);
-		time_elapsed = INSTR_TIME_GET_NANOSEC(temp);
+		time_elapsed = INSTR_TIME_DIFF_NANOSEC(cur, start_time);
 	}
 
-	INSTR_TIME_SET_CURRENT(end_time);
+	if (fast_timing)
+		INSTR_TIME_SET_CURRENT_FAST(end_time);
+	else
+		INSTR_TIME_SET_CURRENT(end_time);
 
 	INSTR_TIME_SUBTRACT(end_time, start_time);
 
diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h
index e2e339a0c4f..f02296f1026 100644
--- a/src/include/portability/instr_time.h
+++ b/src/include/portability/instr_time.h
@@ -112,10 +112,13 @@ extern int64 max_ticks_no_overflow;
  */
 #if defined(__darwin__) && defined(CLOCK_MONOTONIC_RAW)
 #define PG_INSTR_CLOCK	CLOCK_MONOTONIC_RAW
+#define PG_INSTR_CLOCK_NAME	"clock_gettime (CLOCK_MONOTONIC_RAW)"
 #elif defined(CLOCK_MONOTONIC)
 #define PG_INSTR_CLOCK	CLOCK_MONOTONIC
+#define PG_INSTR_CLOCK_NAME	"clock_gettime (CLOCK_MONOTONIC)"
 #else
 #define PG_INSTR_CLOCK	CLOCK_REALTIME
+#define PG_INSTR_CLOCK_NAME	"clock_gettime (CLOCK_REALTIME)"
 #endif
 
 #if defined(__x86_64__) && defined(__linux__)
@@ -174,7 +177,7 @@ pg_get_ticks(void)
 }
 
 static inline int64_t
-pg_ticks_to_ns(instr_time t)
+pg_ticks_to_ns(int64 ticks)
 {
 	/*
 	 * Would multiplication overflow? If so perform computation in two parts.
@@ -183,7 +186,7 @@ pg_ticks_to_ns(instr_time t)
 	 */
 	int64		ns = 0;
 
-	if (unlikely(t.ticks > max_ticks_no_overflow))
+	if (unlikely(ticks > max_ticks_no_overflow))
 	{
 		/*
 		 * Compute how often the maximum number of ticks fits completely into
@@ -192,7 +195,7 @@ pg_ticks_to_ns(instr_time t)
 		 * value. In a 2nd step we adjust the number of elapsed ticks and
 		 * convert the remaining ticks.
 		 */
-		int64		count = t.ticks / max_ticks_no_overflow;
+		int64		count = ticks / max_ticks_no_overflow;
 		int64		max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION;
 
 		ns = max_ns * count;
@@ -201,11 +204,11 @@ pg_ticks_to_ns(instr_time t)
 		 * Subtract the ticks that we now already accounted for, so that they
 		 * don't get counted twice.
 		 */
-		t.ticks -= count * max_ticks_no_overflow;
-		Assert(t.ticks >= 0);
+		ticks -= count * max_ticks_no_overflow;
+		Assert(ticks >= 0);
 	}
 
-	ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION;
+	ns += ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION;
 	return ns;
 }
 
@@ -226,14 +229,14 @@ pg_initialize_get_ticks()
 #define INSTR_TIME_SET_CURRENT(t) \
 	((t) = pg_get_ticks())
 
-#define INSTR_TIME_GET_NANOSEC(t) \
-	pg_ticks_to_ns(t)
-
+#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \
+	(pg_ticks_to_ns(ticks))
 
 #else							/* WIN32 */
 
 
 /* Use QueryPerformanceCounter() */
+#define PG_INSTR_CLOCK_NAME	"QueryPerformanceCounter"
 
 /* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */
 static inline instr_time
@@ -265,8 +268,8 @@ GetTimerFrequency(void)
 #define INSTR_TIME_SET_CURRENT(t) \
 	((t) = pg_query_performance_counter())
 
-#define INSTR_TIME_GET_NANOSEC(t) \
-	((int64) ((t).ticks * ((double) NS_PER_S / GetTimerFrequency())))
+#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \
+	((int64) ((ticks) * ((double) NS_PER_S / GetTimerFrequency())))
 
 #endif							/* WIN32 */
 
@@ -285,9 +288,14 @@ GetTimerFrequency(void)
 #define INSTR_TIME_SUBTRACT(x,y) \
 	((x).ticks -= (y).ticks)
 
+#define INSTR_TIME_DIFF_NANOSEC(x,y) \
+	(INSTR_TIME_TICKS_TO_NANOSEC((x).ticks - (y).ticks))
+
 #define INSTR_TIME_ACCUM_DIFF(x,y,z) \
 	((x).ticks += (y).ticks - (z).ticks)
 
+#define INSTR_TIME_GET_NANOSEC(t) \
+	(INSTR_TIME_TICKS_TO_NANOSEC((t).ticks))
 
 #define INSTR_TIME_GET_DOUBLE(t) \
 	((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S)
-- 
2.47.3


--vtqqtrpooseurzip--





^ permalink  raw  reply  [nested|flat] 265+ messages in thread

* [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source
@ 2025-07-27 15:48  Lukas Fittl <[email protected]>
  0 siblings, 0 replies; 265+ messages in thread

From: Lukas Fittl @ 2025-07-27 15:48 UTC (permalink / raw)

In passing also reduce the per-loop overhead caused by repeated divisions
in INSTR_TIME_GET_NANOSEC when the ticks variable has become very large,
instead diff first and then turn it into nanosecs.
---
 src/bin/pg_test_timing/pg_test_timing.c | 59 +++++++++++++++++++------
 src/include/portability/instr_time.h    | 30 ++++++++-----
 2 files changed, 65 insertions(+), 24 deletions(-)

diff --git a/src/bin/pg_test_timing/pg_test_timing.c b/src/bin/pg_test_timing/pg_test_timing.c
index a5621251afc..b77ef2063b6 100644
--- a/src/bin/pg_test_timing/pg_test_timing.c
+++ b/src/bin/pg_test_timing/pg_test_timing.c
@@ -16,6 +16,7 @@ static const char *progname;
 
 static unsigned int test_duration = 3;
 static double max_rprct = 99.99;
+static bool fast_timing = false;
 
 /* record duration in powers of 2 nanoseconds */
 static long long int histogram[32];
@@ -56,6 +57,7 @@ handle_args(int argc, char *argv[])
 	static struct option long_options[] = {
 		{"duration", required_argument, NULL, 'd'},
 		{"cutoff", required_argument, NULL, 'c'},
+		{"fast", no_argument, NULL, 'f'},
 		{NULL, 0, NULL, 0}
 	};
 
@@ -68,7 +70,7 @@ handle_args(int argc, char *argv[])
 	{
 		if (strcmp(argv[1], "--help") == 0 || strcmp(argv[1], "-?") == 0)
 		{
-			printf(_("Usage: %s [-d DURATION] [-c CUTOFF]\n"), progname);
+			printf(_("Usage: %s [-d DURATION] [-c CUTOFF] [--fast]\n"), progname);
 			exit(0);
 		}
 		if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0)
@@ -78,7 +80,7 @@ handle_args(int argc, char *argv[])
 		}
 	}
 
-	while ((option = getopt_long(argc, argv, "d:c:",
+	while ((option = getopt_long(argc, argv, "d:c:f:",
 								 long_options, &optindex)) != -1)
 	{
 		switch (option)
@@ -125,6 +127,10 @@ handle_args(int argc, char *argv[])
 				}
 				break;
 
+			case 'f':
+				fast_timing = true;
+				break;
+
 			default:
 				fprintf(stderr, _("Try \"%s --help\" for more information.\n"),
 						progname);
@@ -155,11 +161,31 @@ test_timing(unsigned int duration)
 	uint64		total_time;
 	int64		time_elapsed = 0;
 	uint64		loop_count = 0;
-	uint64		prev,
-				cur;
 	instr_time	start_time,
 				end_time,
-				temp;
+				prev,
+				cur;
+	char	   *time_source = NULL;
+	bool		fast_timing_used = false;
+
+	INSTR_TIME_INITIALIZE();
+
+#if !defined(WIN32) && defined(__x86_64__) && defined(__linux__)
+	if (fast_timing && has_rdtsc)
+	{
+		time_source = "RDTSC";
+		fast_timing_used = true;
+	}
+	else if (has_rdtscp)
+		time_source = "RDTSCP";
+	else
+		time_source = PG_INSTR_CLOCK_NAME;
+#else
+	time_source = PG_INSTR_CLOCK_NAME;
+#endif
+	if (fast_timing && !fast_timing_used)
+		printf(_("Warning: Fast timing requested, but not available - regular timing source will be used\n"));
+	printf(_("Time source: %s\n"), time_source);
 
 	/*
 	 * Pre-zero the statistics data structures.  They're already zero by
@@ -173,8 +199,11 @@ test_timing(unsigned int duration)
 
 	total_time = duration > 0 ? duration * INT64CONST(1000000000) : 0;
 
-	INSTR_TIME_SET_CURRENT(start_time);
-	cur = INSTR_TIME_GET_NANOSEC(start_time);
+	if (fast_timing)
+		INSTR_TIME_SET_CURRENT_FAST(start_time);
+	else
+		INSTR_TIME_SET_CURRENT(start_time);
+	cur = start_time;
 
 	while (time_elapsed < total_time)
 	{
@@ -182,9 +211,11 @@ test_timing(unsigned int duration)
 					bits;
 
 		prev = cur;
-		INSTR_TIME_SET_CURRENT(temp);
-		cur = INSTR_TIME_GET_NANOSEC(temp);
-		diff = cur - prev;
+		if (fast_timing)
+			INSTR_TIME_SET_CURRENT_FAST(cur);
+		else
+			INSTR_TIME_SET_CURRENT(cur);
+		diff = INSTR_TIME_DIFF_NANOSEC(cur, prev);
 
 		/* Did time go backwards? */
 		if (unlikely(diff < 0))
@@ -217,11 +248,13 @@ test_timing(unsigned int duration)
 			largest_diff_count++;
 
 		loop_count++;
-		INSTR_TIME_SUBTRACT(temp, start_time);
-		time_elapsed = INSTR_TIME_GET_NANOSEC(temp);
+		time_elapsed = INSTR_TIME_DIFF_NANOSEC(cur, start_time);
 	}
 
-	INSTR_TIME_SET_CURRENT(end_time);
+	if (fast_timing)
+		INSTR_TIME_SET_CURRENT_FAST(end_time);
+	else
+		INSTR_TIME_SET_CURRENT(end_time);
 
 	INSTR_TIME_SUBTRACT(end_time, start_time);
 
diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h
index e2e339a0c4f..f02296f1026 100644
--- a/src/include/portability/instr_time.h
+++ b/src/include/portability/instr_time.h
@@ -112,10 +112,13 @@ extern int64 max_ticks_no_overflow;
  */
 #if defined(__darwin__) && defined(CLOCK_MONOTONIC_RAW)
 #define PG_INSTR_CLOCK	CLOCK_MONOTONIC_RAW
+#define PG_INSTR_CLOCK_NAME	"clock_gettime (CLOCK_MONOTONIC_RAW)"
 #elif defined(CLOCK_MONOTONIC)
 #define PG_INSTR_CLOCK	CLOCK_MONOTONIC
+#define PG_INSTR_CLOCK_NAME	"clock_gettime (CLOCK_MONOTONIC)"
 #else
 #define PG_INSTR_CLOCK	CLOCK_REALTIME
+#define PG_INSTR_CLOCK_NAME	"clock_gettime (CLOCK_REALTIME)"
 #endif
 
 #if defined(__x86_64__) && defined(__linux__)
@@ -174,7 +177,7 @@ pg_get_ticks(void)
 }
 
 static inline int64_t
-pg_ticks_to_ns(instr_time t)
+pg_ticks_to_ns(int64 ticks)
 {
 	/*
 	 * Would multiplication overflow? If so perform computation in two parts.
@@ -183,7 +186,7 @@ pg_ticks_to_ns(instr_time t)
 	 */
 	int64		ns = 0;
 
-	if (unlikely(t.ticks > max_ticks_no_overflow))
+	if (unlikely(ticks > max_ticks_no_overflow))
 	{
 		/*
 		 * Compute how often the maximum number of ticks fits completely into
@@ -192,7 +195,7 @@ pg_ticks_to_ns(instr_time t)
 		 * value. In a 2nd step we adjust the number of elapsed ticks and
 		 * convert the remaining ticks.
 		 */
-		int64		count = t.ticks / max_ticks_no_overflow;
+		int64		count = ticks / max_ticks_no_overflow;
 		int64		max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION;
 
 		ns = max_ns * count;
@@ -201,11 +204,11 @@ pg_ticks_to_ns(instr_time t)
 		 * Subtract the ticks that we now already accounted for, so that they
 		 * don't get counted twice.
 		 */
-		t.ticks -= count * max_ticks_no_overflow;
-		Assert(t.ticks >= 0);
+		ticks -= count * max_ticks_no_overflow;
+		Assert(ticks >= 0);
 	}
 
-	ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION;
+	ns += ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION;
 	return ns;
 }
 
@@ -226,14 +229,14 @@ pg_initialize_get_ticks()
 #define INSTR_TIME_SET_CURRENT(t) \
 	((t) = pg_get_ticks())
 
-#define INSTR_TIME_GET_NANOSEC(t) \
-	pg_ticks_to_ns(t)
-
+#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \
+	(pg_ticks_to_ns(ticks))
 
 #else							/* WIN32 */
 
 
 /* Use QueryPerformanceCounter() */
+#define PG_INSTR_CLOCK_NAME	"QueryPerformanceCounter"
 
 /* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */
 static inline instr_time
@@ -265,8 +268,8 @@ GetTimerFrequency(void)
 #define INSTR_TIME_SET_CURRENT(t) \
 	((t) = pg_query_performance_counter())
 
-#define INSTR_TIME_GET_NANOSEC(t) \
-	((int64) ((t).ticks * ((double) NS_PER_S / GetTimerFrequency())))
+#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \
+	((int64) ((ticks) * ((double) NS_PER_S / GetTimerFrequency())))
 
 #endif							/* WIN32 */
 
@@ -285,9 +288,14 @@ GetTimerFrequency(void)
 #define INSTR_TIME_SUBTRACT(x,y) \
 	((x).ticks -= (y).ticks)
 
+#define INSTR_TIME_DIFF_NANOSEC(x,y) \
+	(INSTR_TIME_TICKS_TO_NANOSEC((x).ticks - (y).ticks))
+
 #define INSTR_TIME_ACCUM_DIFF(x,y,z) \
 	((x).ticks += (y).ticks - (z).ticks)
 
+#define INSTR_TIME_GET_NANOSEC(t) \
+	(INSTR_TIME_TICKS_TO_NANOSEC((t).ticks))
 
 #define INSTR_TIME_GET_DOUBLE(t) \
 	((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S)
-- 
2.47.3


--vtqqtrpooseurzip--





^ permalink  raw  reply  [nested|flat] 265+ messages in thread

* [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source
@ 2025-07-27 15:48  Lukas Fittl <[email protected]>
  0 siblings, 0 replies; 265+ messages in thread

From: Lukas Fittl @ 2025-07-27 15:48 UTC (permalink / raw)

In passing also reduce the per-loop overhead caused by repeated divisions
in INSTR_TIME_GET_NANOSEC when the ticks variable has become very large,
instead diff first and then turn it into nanosecs.
---
 src/bin/pg_test_timing/pg_test_timing.c | 59 +++++++++++++++++++------
 src/include/portability/instr_time.h    | 30 ++++++++-----
 2 files changed, 65 insertions(+), 24 deletions(-)

diff --git a/src/bin/pg_test_timing/pg_test_timing.c b/src/bin/pg_test_timing/pg_test_timing.c
index a5621251afc..b77ef2063b6 100644
--- a/src/bin/pg_test_timing/pg_test_timing.c
+++ b/src/bin/pg_test_timing/pg_test_timing.c
@@ -16,6 +16,7 @@ static const char *progname;
 
 static unsigned int test_duration = 3;
 static double max_rprct = 99.99;
+static bool fast_timing = false;
 
 /* record duration in powers of 2 nanoseconds */
 static long long int histogram[32];
@@ -56,6 +57,7 @@ handle_args(int argc, char *argv[])
 	static struct option long_options[] = {
 		{"duration", required_argument, NULL, 'd'},
 		{"cutoff", required_argument, NULL, 'c'},
+		{"fast", no_argument, NULL, 'f'},
 		{NULL, 0, NULL, 0}
 	};
 
@@ -68,7 +70,7 @@ handle_args(int argc, char *argv[])
 	{
 		if (strcmp(argv[1], "--help") == 0 || strcmp(argv[1], "-?") == 0)
 		{
-			printf(_("Usage: %s [-d DURATION] [-c CUTOFF]\n"), progname);
+			printf(_("Usage: %s [-d DURATION] [-c CUTOFF] [--fast]\n"), progname);
 			exit(0);
 		}
 		if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0)
@@ -78,7 +80,7 @@ handle_args(int argc, char *argv[])
 		}
 	}
 
-	while ((option = getopt_long(argc, argv, "d:c:",
+	while ((option = getopt_long(argc, argv, "d:c:f:",
 								 long_options, &optindex)) != -1)
 	{
 		switch (option)
@@ -125,6 +127,10 @@ handle_args(int argc, char *argv[])
 				}
 				break;
 
+			case 'f':
+				fast_timing = true;
+				break;
+
 			default:
 				fprintf(stderr, _("Try \"%s --help\" for more information.\n"),
 						progname);
@@ -155,11 +161,31 @@ test_timing(unsigned int duration)
 	uint64		total_time;
 	int64		time_elapsed = 0;
 	uint64		loop_count = 0;
-	uint64		prev,
-				cur;
 	instr_time	start_time,
 				end_time,
-				temp;
+				prev,
+				cur;
+	char	   *time_source = NULL;
+	bool		fast_timing_used = false;
+
+	INSTR_TIME_INITIALIZE();
+
+#if !defined(WIN32) && defined(__x86_64__) && defined(__linux__)
+	if (fast_timing && has_rdtsc)
+	{
+		time_source = "RDTSC";
+		fast_timing_used = true;
+	}
+	else if (has_rdtscp)
+		time_source = "RDTSCP";
+	else
+		time_source = PG_INSTR_CLOCK_NAME;
+#else
+	time_source = PG_INSTR_CLOCK_NAME;
+#endif
+	if (fast_timing && !fast_timing_used)
+		printf(_("Warning: Fast timing requested, but not available - regular timing source will be used\n"));
+	printf(_("Time source: %s\n"), time_source);
 
 	/*
 	 * Pre-zero the statistics data structures.  They're already zero by
@@ -173,8 +199,11 @@ test_timing(unsigned int duration)
 
 	total_time = duration > 0 ? duration * INT64CONST(1000000000) : 0;
 
-	INSTR_TIME_SET_CURRENT(start_time);
-	cur = INSTR_TIME_GET_NANOSEC(start_time);
+	if (fast_timing)
+		INSTR_TIME_SET_CURRENT_FAST(start_time);
+	else
+		INSTR_TIME_SET_CURRENT(start_time);
+	cur = start_time;
 
 	while (time_elapsed < total_time)
 	{
@@ -182,9 +211,11 @@ test_timing(unsigned int duration)
 					bits;
 
 		prev = cur;
-		INSTR_TIME_SET_CURRENT(temp);
-		cur = INSTR_TIME_GET_NANOSEC(temp);
-		diff = cur - prev;
+		if (fast_timing)
+			INSTR_TIME_SET_CURRENT_FAST(cur);
+		else
+			INSTR_TIME_SET_CURRENT(cur);
+		diff = INSTR_TIME_DIFF_NANOSEC(cur, prev);
 
 		/* Did time go backwards? */
 		if (unlikely(diff < 0))
@@ -217,11 +248,13 @@ test_timing(unsigned int duration)
 			largest_diff_count++;
 
 		loop_count++;
-		INSTR_TIME_SUBTRACT(temp, start_time);
-		time_elapsed = INSTR_TIME_GET_NANOSEC(temp);
+		time_elapsed = INSTR_TIME_DIFF_NANOSEC(cur, start_time);
 	}
 
-	INSTR_TIME_SET_CURRENT(end_time);
+	if (fast_timing)
+		INSTR_TIME_SET_CURRENT_FAST(end_time);
+	else
+		INSTR_TIME_SET_CURRENT(end_time);
 
 	INSTR_TIME_SUBTRACT(end_time, start_time);
 
diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h
index e2e339a0c4f..f02296f1026 100644
--- a/src/include/portability/instr_time.h
+++ b/src/include/portability/instr_time.h
@@ -112,10 +112,13 @@ extern int64 max_ticks_no_overflow;
  */
 #if defined(__darwin__) && defined(CLOCK_MONOTONIC_RAW)
 #define PG_INSTR_CLOCK	CLOCK_MONOTONIC_RAW
+#define PG_INSTR_CLOCK_NAME	"clock_gettime (CLOCK_MONOTONIC_RAW)"
 #elif defined(CLOCK_MONOTONIC)
 #define PG_INSTR_CLOCK	CLOCK_MONOTONIC
+#define PG_INSTR_CLOCK_NAME	"clock_gettime (CLOCK_MONOTONIC)"
 #else
 #define PG_INSTR_CLOCK	CLOCK_REALTIME
+#define PG_INSTR_CLOCK_NAME	"clock_gettime (CLOCK_REALTIME)"
 #endif
 
 #if defined(__x86_64__) && defined(__linux__)
@@ -174,7 +177,7 @@ pg_get_ticks(void)
 }
 
 static inline int64_t
-pg_ticks_to_ns(instr_time t)
+pg_ticks_to_ns(int64 ticks)
 {
 	/*
 	 * Would multiplication overflow? If so perform computation in two parts.
@@ -183,7 +186,7 @@ pg_ticks_to_ns(instr_time t)
 	 */
 	int64		ns = 0;
 
-	if (unlikely(t.ticks > max_ticks_no_overflow))
+	if (unlikely(ticks > max_ticks_no_overflow))
 	{
 		/*
 		 * Compute how often the maximum number of ticks fits completely into
@@ -192,7 +195,7 @@ pg_ticks_to_ns(instr_time t)
 		 * value. In a 2nd step we adjust the number of elapsed ticks and
 		 * convert the remaining ticks.
 		 */
-		int64		count = t.ticks / max_ticks_no_overflow;
+		int64		count = ticks / max_ticks_no_overflow;
 		int64		max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION;
 
 		ns = max_ns * count;
@@ -201,11 +204,11 @@ pg_ticks_to_ns(instr_time t)
 		 * Subtract the ticks that we now already accounted for, so that they
 		 * don't get counted twice.
 		 */
-		t.ticks -= count * max_ticks_no_overflow;
-		Assert(t.ticks >= 0);
+		ticks -= count * max_ticks_no_overflow;
+		Assert(ticks >= 0);
 	}
 
-	ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION;
+	ns += ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION;
 	return ns;
 }
 
@@ -226,14 +229,14 @@ pg_initialize_get_ticks()
 #define INSTR_TIME_SET_CURRENT(t) \
 	((t) = pg_get_ticks())
 
-#define INSTR_TIME_GET_NANOSEC(t) \
-	pg_ticks_to_ns(t)
-
+#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \
+	(pg_ticks_to_ns(ticks))
 
 #else							/* WIN32 */
 
 
 /* Use QueryPerformanceCounter() */
+#define PG_INSTR_CLOCK_NAME	"QueryPerformanceCounter"
 
 /* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */
 static inline instr_time
@@ -265,8 +268,8 @@ GetTimerFrequency(void)
 #define INSTR_TIME_SET_CURRENT(t) \
 	((t) = pg_query_performance_counter())
 
-#define INSTR_TIME_GET_NANOSEC(t) \
-	((int64) ((t).ticks * ((double) NS_PER_S / GetTimerFrequency())))
+#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \
+	((int64) ((ticks) * ((double) NS_PER_S / GetTimerFrequency())))
 
 #endif							/* WIN32 */
 
@@ -285,9 +288,14 @@ GetTimerFrequency(void)
 #define INSTR_TIME_SUBTRACT(x,y) \
 	((x).ticks -= (y).ticks)
 
+#define INSTR_TIME_DIFF_NANOSEC(x,y) \
+	(INSTR_TIME_TICKS_TO_NANOSEC((x).ticks - (y).ticks))
+
 #define INSTR_TIME_ACCUM_DIFF(x,y,z) \
 	((x).ticks += (y).ticks - (z).ticks)
 
+#define INSTR_TIME_GET_NANOSEC(t) \
+	(INSTR_TIME_TICKS_TO_NANOSEC((t).ticks))
 
 #define INSTR_TIME_GET_DOUBLE(t) \
 	((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S)
-- 
2.47.3


--vtqqtrpooseurzip--





^ permalink  raw  reply  [nested|flat] 265+ messages in thread

* [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source
@ 2025-07-27 15:48  Lukas Fittl <[email protected]>
  0 siblings, 0 replies; 265+ messages in thread

From: Lukas Fittl @ 2025-07-27 15:48 UTC (permalink / raw)

In passing also reduce the per-loop overhead caused by repeated divisions
in INSTR_TIME_GET_NANOSEC when the ticks variable has become very large,
instead diff first and then turn it into nanosecs.
---
 src/bin/pg_test_timing/pg_test_timing.c | 59 +++++++++++++++++++------
 src/include/portability/instr_time.h    | 30 ++++++++-----
 2 files changed, 65 insertions(+), 24 deletions(-)

diff --git a/src/bin/pg_test_timing/pg_test_timing.c b/src/bin/pg_test_timing/pg_test_timing.c
index a5621251afc..b77ef2063b6 100644
--- a/src/bin/pg_test_timing/pg_test_timing.c
+++ b/src/bin/pg_test_timing/pg_test_timing.c
@@ -16,6 +16,7 @@ static const char *progname;
 
 static unsigned int test_duration = 3;
 static double max_rprct = 99.99;
+static bool fast_timing = false;
 
 /* record duration in powers of 2 nanoseconds */
 static long long int histogram[32];
@@ -56,6 +57,7 @@ handle_args(int argc, char *argv[])
 	static struct option long_options[] = {
 		{"duration", required_argument, NULL, 'd'},
 		{"cutoff", required_argument, NULL, 'c'},
+		{"fast", no_argument, NULL, 'f'},
 		{NULL, 0, NULL, 0}
 	};
 
@@ -68,7 +70,7 @@ handle_args(int argc, char *argv[])
 	{
 		if (strcmp(argv[1], "--help") == 0 || strcmp(argv[1], "-?") == 0)
 		{
-			printf(_("Usage: %s [-d DURATION] [-c CUTOFF]\n"), progname);
+			printf(_("Usage: %s [-d DURATION] [-c CUTOFF] [--fast]\n"), progname);
 			exit(0);
 		}
 		if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0)
@@ -78,7 +80,7 @@ handle_args(int argc, char *argv[])
 		}
 	}
 
-	while ((option = getopt_long(argc, argv, "d:c:",
+	while ((option = getopt_long(argc, argv, "d:c:f:",
 								 long_options, &optindex)) != -1)
 	{
 		switch (option)
@@ -125,6 +127,10 @@ handle_args(int argc, char *argv[])
 				}
 				break;
 
+			case 'f':
+				fast_timing = true;
+				break;
+
 			default:
 				fprintf(stderr, _("Try \"%s --help\" for more information.\n"),
 						progname);
@@ -155,11 +161,31 @@ test_timing(unsigned int duration)
 	uint64		total_time;
 	int64		time_elapsed = 0;
 	uint64		loop_count = 0;
-	uint64		prev,
-				cur;
 	instr_time	start_time,
 				end_time,
-				temp;
+				prev,
+				cur;
+	char	   *time_source = NULL;
+	bool		fast_timing_used = false;
+
+	INSTR_TIME_INITIALIZE();
+
+#if !defined(WIN32) && defined(__x86_64__) && defined(__linux__)
+	if (fast_timing && has_rdtsc)
+	{
+		time_source = "RDTSC";
+		fast_timing_used = true;
+	}
+	else if (has_rdtscp)
+		time_source = "RDTSCP";
+	else
+		time_source = PG_INSTR_CLOCK_NAME;
+#else
+	time_source = PG_INSTR_CLOCK_NAME;
+#endif
+	if (fast_timing && !fast_timing_used)
+		printf(_("Warning: Fast timing requested, but not available - regular timing source will be used\n"));
+	printf(_("Time source: %s\n"), time_source);
 
 	/*
 	 * Pre-zero the statistics data structures.  They're already zero by
@@ -173,8 +199,11 @@ test_timing(unsigned int duration)
 
 	total_time = duration > 0 ? duration * INT64CONST(1000000000) : 0;
 
-	INSTR_TIME_SET_CURRENT(start_time);
-	cur = INSTR_TIME_GET_NANOSEC(start_time);
+	if (fast_timing)
+		INSTR_TIME_SET_CURRENT_FAST(start_time);
+	else
+		INSTR_TIME_SET_CURRENT(start_time);
+	cur = start_time;
 
 	while (time_elapsed < total_time)
 	{
@@ -182,9 +211,11 @@ test_timing(unsigned int duration)
 					bits;
 
 		prev = cur;
-		INSTR_TIME_SET_CURRENT(temp);
-		cur = INSTR_TIME_GET_NANOSEC(temp);
-		diff = cur - prev;
+		if (fast_timing)
+			INSTR_TIME_SET_CURRENT_FAST(cur);
+		else
+			INSTR_TIME_SET_CURRENT(cur);
+		diff = INSTR_TIME_DIFF_NANOSEC(cur, prev);
 
 		/* Did time go backwards? */
 		if (unlikely(diff < 0))
@@ -217,11 +248,13 @@ test_timing(unsigned int duration)
 			largest_diff_count++;
 
 		loop_count++;
-		INSTR_TIME_SUBTRACT(temp, start_time);
-		time_elapsed = INSTR_TIME_GET_NANOSEC(temp);
+		time_elapsed = INSTR_TIME_DIFF_NANOSEC(cur, start_time);
 	}
 
-	INSTR_TIME_SET_CURRENT(end_time);
+	if (fast_timing)
+		INSTR_TIME_SET_CURRENT_FAST(end_time);
+	else
+		INSTR_TIME_SET_CURRENT(end_time);
 
 	INSTR_TIME_SUBTRACT(end_time, start_time);
 
diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h
index e2e339a0c4f..f02296f1026 100644
--- a/src/include/portability/instr_time.h
+++ b/src/include/portability/instr_time.h
@@ -112,10 +112,13 @@ extern int64 max_ticks_no_overflow;
  */
 #if defined(__darwin__) && defined(CLOCK_MONOTONIC_RAW)
 #define PG_INSTR_CLOCK	CLOCK_MONOTONIC_RAW
+#define PG_INSTR_CLOCK_NAME	"clock_gettime (CLOCK_MONOTONIC_RAW)"
 #elif defined(CLOCK_MONOTONIC)
 #define PG_INSTR_CLOCK	CLOCK_MONOTONIC
+#define PG_INSTR_CLOCK_NAME	"clock_gettime (CLOCK_MONOTONIC)"
 #else
 #define PG_INSTR_CLOCK	CLOCK_REALTIME
+#define PG_INSTR_CLOCK_NAME	"clock_gettime (CLOCK_REALTIME)"
 #endif
 
 #if defined(__x86_64__) && defined(__linux__)
@@ -174,7 +177,7 @@ pg_get_ticks(void)
 }
 
 static inline int64_t
-pg_ticks_to_ns(instr_time t)
+pg_ticks_to_ns(int64 ticks)
 {
 	/*
 	 * Would multiplication overflow? If so perform computation in two parts.
@@ -183,7 +186,7 @@ pg_ticks_to_ns(instr_time t)
 	 */
 	int64		ns = 0;
 
-	if (unlikely(t.ticks > max_ticks_no_overflow))
+	if (unlikely(ticks > max_ticks_no_overflow))
 	{
 		/*
 		 * Compute how often the maximum number of ticks fits completely into
@@ -192,7 +195,7 @@ pg_ticks_to_ns(instr_time t)
 		 * value. In a 2nd step we adjust the number of elapsed ticks and
 		 * convert the remaining ticks.
 		 */
-		int64		count = t.ticks / max_ticks_no_overflow;
+		int64		count = ticks / max_ticks_no_overflow;
 		int64		max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION;
 
 		ns = max_ns * count;
@@ -201,11 +204,11 @@ pg_ticks_to_ns(instr_time t)
 		 * Subtract the ticks that we now already accounted for, so that they
 		 * don't get counted twice.
 		 */
-		t.ticks -= count * max_ticks_no_overflow;
-		Assert(t.ticks >= 0);
+		ticks -= count * max_ticks_no_overflow;
+		Assert(ticks >= 0);
 	}
 
-	ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION;
+	ns += ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION;
 	return ns;
 }
 
@@ -226,14 +229,14 @@ pg_initialize_get_ticks()
 #define INSTR_TIME_SET_CURRENT(t) \
 	((t) = pg_get_ticks())
 
-#define INSTR_TIME_GET_NANOSEC(t) \
-	pg_ticks_to_ns(t)
-
+#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \
+	(pg_ticks_to_ns(ticks))
 
 #else							/* WIN32 */
 
 
 /* Use QueryPerformanceCounter() */
+#define PG_INSTR_CLOCK_NAME	"QueryPerformanceCounter"
 
 /* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */
 static inline instr_time
@@ -265,8 +268,8 @@ GetTimerFrequency(void)
 #define INSTR_TIME_SET_CURRENT(t) \
 	((t) = pg_query_performance_counter())
 
-#define INSTR_TIME_GET_NANOSEC(t) \
-	((int64) ((t).ticks * ((double) NS_PER_S / GetTimerFrequency())))
+#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \
+	((int64) ((ticks) * ((double) NS_PER_S / GetTimerFrequency())))
 
 #endif							/* WIN32 */
 
@@ -285,9 +288,14 @@ GetTimerFrequency(void)
 #define INSTR_TIME_SUBTRACT(x,y) \
 	((x).ticks -= (y).ticks)
 
+#define INSTR_TIME_DIFF_NANOSEC(x,y) \
+	(INSTR_TIME_TICKS_TO_NANOSEC((x).ticks - (y).ticks))
+
 #define INSTR_TIME_ACCUM_DIFF(x,y,z) \
 	((x).ticks += (y).ticks - (z).ticks)
 
+#define INSTR_TIME_GET_NANOSEC(t) \
+	(INSTR_TIME_TICKS_TO_NANOSEC((t).ticks))
 
 #define INSTR_TIME_GET_DOUBLE(t) \
 	((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S)
-- 
2.47.3


--vtqqtrpooseurzip--





^ permalink  raw  reply  [nested|flat] 265+ messages in thread

* [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source
@ 2025-07-27 15:48  Lukas Fittl <[email protected]>
  0 siblings, 0 replies; 265+ messages in thread

From: Lukas Fittl @ 2025-07-27 15:48 UTC (permalink / raw)

In passing also reduce the per-loop overhead caused by repeated divisions
in INSTR_TIME_GET_NANOSEC when the ticks variable has become very large,
instead diff first and then turn it into nanosecs.
---
 src/bin/pg_test_timing/pg_test_timing.c | 59 +++++++++++++++++++------
 src/include/portability/instr_time.h    | 30 ++++++++-----
 2 files changed, 65 insertions(+), 24 deletions(-)

diff --git a/src/bin/pg_test_timing/pg_test_timing.c b/src/bin/pg_test_timing/pg_test_timing.c
index a5621251afc..b77ef2063b6 100644
--- a/src/bin/pg_test_timing/pg_test_timing.c
+++ b/src/bin/pg_test_timing/pg_test_timing.c
@@ -16,6 +16,7 @@ static const char *progname;
 
 static unsigned int test_duration = 3;
 static double max_rprct = 99.99;
+static bool fast_timing = false;
 
 /* record duration in powers of 2 nanoseconds */
 static long long int histogram[32];
@@ -56,6 +57,7 @@ handle_args(int argc, char *argv[])
 	static struct option long_options[] = {
 		{"duration", required_argument, NULL, 'd'},
 		{"cutoff", required_argument, NULL, 'c'},
+		{"fast", no_argument, NULL, 'f'},
 		{NULL, 0, NULL, 0}
 	};
 
@@ -68,7 +70,7 @@ handle_args(int argc, char *argv[])
 	{
 		if (strcmp(argv[1], "--help") == 0 || strcmp(argv[1], "-?") == 0)
 		{
-			printf(_("Usage: %s [-d DURATION] [-c CUTOFF]\n"), progname);
+			printf(_("Usage: %s [-d DURATION] [-c CUTOFF] [--fast]\n"), progname);
 			exit(0);
 		}
 		if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0)
@@ -78,7 +80,7 @@ handle_args(int argc, char *argv[])
 		}
 	}
 
-	while ((option = getopt_long(argc, argv, "d:c:",
+	while ((option = getopt_long(argc, argv, "d:c:f:",
 								 long_options, &optindex)) != -1)
 	{
 		switch (option)
@@ -125,6 +127,10 @@ handle_args(int argc, char *argv[])
 				}
 				break;
 
+			case 'f':
+				fast_timing = true;
+				break;
+
 			default:
 				fprintf(stderr, _("Try \"%s --help\" for more information.\n"),
 						progname);
@@ -155,11 +161,31 @@ test_timing(unsigned int duration)
 	uint64		total_time;
 	int64		time_elapsed = 0;
 	uint64		loop_count = 0;
-	uint64		prev,
-				cur;
 	instr_time	start_time,
 				end_time,
-				temp;
+				prev,
+				cur;
+	char	   *time_source = NULL;
+	bool		fast_timing_used = false;
+
+	INSTR_TIME_INITIALIZE();
+
+#if !defined(WIN32) && defined(__x86_64__) && defined(__linux__)
+	if (fast_timing && has_rdtsc)
+	{
+		time_source = "RDTSC";
+		fast_timing_used = true;
+	}
+	else if (has_rdtscp)
+		time_source = "RDTSCP";
+	else
+		time_source = PG_INSTR_CLOCK_NAME;
+#else
+	time_source = PG_INSTR_CLOCK_NAME;
+#endif
+	if (fast_timing && !fast_timing_used)
+		printf(_("Warning: Fast timing requested, but not available - regular timing source will be used\n"));
+	printf(_("Time source: %s\n"), time_source);
 
 	/*
 	 * Pre-zero the statistics data structures.  They're already zero by
@@ -173,8 +199,11 @@ test_timing(unsigned int duration)
 
 	total_time = duration > 0 ? duration * INT64CONST(1000000000) : 0;
 
-	INSTR_TIME_SET_CURRENT(start_time);
-	cur = INSTR_TIME_GET_NANOSEC(start_time);
+	if (fast_timing)
+		INSTR_TIME_SET_CURRENT_FAST(start_time);
+	else
+		INSTR_TIME_SET_CURRENT(start_time);
+	cur = start_time;
 
 	while (time_elapsed < total_time)
 	{
@@ -182,9 +211,11 @@ test_timing(unsigned int duration)
 					bits;
 
 		prev = cur;
-		INSTR_TIME_SET_CURRENT(temp);
-		cur = INSTR_TIME_GET_NANOSEC(temp);
-		diff = cur - prev;
+		if (fast_timing)
+			INSTR_TIME_SET_CURRENT_FAST(cur);
+		else
+			INSTR_TIME_SET_CURRENT(cur);
+		diff = INSTR_TIME_DIFF_NANOSEC(cur, prev);
 
 		/* Did time go backwards? */
 		if (unlikely(diff < 0))
@@ -217,11 +248,13 @@ test_timing(unsigned int duration)
 			largest_diff_count++;
 
 		loop_count++;
-		INSTR_TIME_SUBTRACT(temp, start_time);
-		time_elapsed = INSTR_TIME_GET_NANOSEC(temp);
+		time_elapsed = INSTR_TIME_DIFF_NANOSEC(cur, start_time);
 	}
 
-	INSTR_TIME_SET_CURRENT(end_time);
+	if (fast_timing)
+		INSTR_TIME_SET_CURRENT_FAST(end_time);
+	else
+		INSTR_TIME_SET_CURRENT(end_time);
 
 	INSTR_TIME_SUBTRACT(end_time, start_time);
 
diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h
index e2e339a0c4f..f02296f1026 100644
--- a/src/include/portability/instr_time.h
+++ b/src/include/portability/instr_time.h
@@ -112,10 +112,13 @@ extern int64 max_ticks_no_overflow;
  */
 #if defined(__darwin__) && defined(CLOCK_MONOTONIC_RAW)
 #define PG_INSTR_CLOCK	CLOCK_MONOTONIC_RAW
+#define PG_INSTR_CLOCK_NAME	"clock_gettime (CLOCK_MONOTONIC_RAW)"
 #elif defined(CLOCK_MONOTONIC)
 #define PG_INSTR_CLOCK	CLOCK_MONOTONIC
+#define PG_INSTR_CLOCK_NAME	"clock_gettime (CLOCK_MONOTONIC)"
 #else
 #define PG_INSTR_CLOCK	CLOCK_REALTIME
+#define PG_INSTR_CLOCK_NAME	"clock_gettime (CLOCK_REALTIME)"
 #endif
 
 #if defined(__x86_64__) && defined(__linux__)
@@ -174,7 +177,7 @@ pg_get_ticks(void)
 }
 
 static inline int64_t
-pg_ticks_to_ns(instr_time t)
+pg_ticks_to_ns(int64 ticks)
 {
 	/*
 	 * Would multiplication overflow? If so perform computation in two parts.
@@ -183,7 +186,7 @@ pg_ticks_to_ns(instr_time t)
 	 */
 	int64		ns = 0;
 
-	if (unlikely(t.ticks > max_ticks_no_overflow))
+	if (unlikely(ticks > max_ticks_no_overflow))
 	{
 		/*
 		 * Compute how often the maximum number of ticks fits completely into
@@ -192,7 +195,7 @@ pg_ticks_to_ns(instr_time t)
 		 * value. In a 2nd step we adjust the number of elapsed ticks and
 		 * convert the remaining ticks.
 		 */
-		int64		count = t.ticks / max_ticks_no_overflow;
+		int64		count = ticks / max_ticks_no_overflow;
 		int64		max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION;
 
 		ns = max_ns * count;
@@ -201,11 +204,11 @@ pg_ticks_to_ns(instr_time t)
 		 * Subtract the ticks that we now already accounted for, so that they
 		 * don't get counted twice.
 		 */
-		t.ticks -= count * max_ticks_no_overflow;
-		Assert(t.ticks >= 0);
+		ticks -= count * max_ticks_no_overflow;
+		Assert(ticks >= 0);
 	}
 
-	ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION;
+	ns += ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION;
 	return ns;
 }
 
@@ -226,14 +229,14 @@ pg_initialize_get_ticks()
 #define INSTR_TIME_SET_CURRENT(t) \
 	((t) = pg_get_ticks())
 
-#define INSTR_TIME_GET_NANOSEC(t) \
-	pg_ticks_to_ns(t)
-
+#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \
+	(pg_ticks_to_ns(ticks))
 
 #else							/* WIN32 */
 
 
 /* Use QueryPerformanceCounter() */
+#define PG_INSTR_CLOCK_NAME	"QueryPerformanceCounter"
 
 /* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */
 static inline instr_time
@@ -265,8 +268,8 @@ GetTimerFrequency(void)
 #define INSTR_TIME_SET_CURRENT(t) \
 	((t) = pg_query_performance_counter())
 
-#define INSTR_TIME_GET_NANOSEC(t) \
-	((int64) ((t).ticks * ((double) NS_PER_S / GetTimerFrequency())))
+#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \
+	((int64) ((ticks) * ((double) NS_PER_S / GetTimerFrequency())))
 
 #endif							/* WIN32 */
 
@@ -285,9 +288,14 @@ GetTimerFrequency(void)
 #define INSTR_TIME_SUBTRACT(x,y) \
 	((x).ticks -= (y).ticks)
 
+#define INSTR_TIME_DIFF_NANOSEC(x,y) \
+	(INSTR_TIME_TICKS_TO_NANOSEC((x).ticks - (y).ticks))
+
 #define INSTR_TIME_ACCUM_DIFF(x,y,z) \
 	((x).ticks += (y).ticks - (z).ticks)
 
+#define INSTR_TIME_GET_NANOSEC(t) \
+	(INSTR_TIME_TICKS_TO_NANOSEC((t).ticks))
 
 #define INSTR_TIME_GET_DOUBLE(t) \
 	((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S)
-- 
2.47.3


--vtqqtrpooseurzip--





^ permalink  raw  reply  [nested|flat] 265+ messages in thread

* [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source
@ 2025-07-27 15:48  Lukas Fittl <[email protected]>
  0 siblings, 0 replies; 265+ messages in thread

From: Lukas Fittl @ 2025-07-27 15:48 UTC (permalink / raw)

In passing also reduce the per-loop overhead caused by repeated divisions
in INSTR_TIME_GET_NANOSEC when the ticks variable has become very large,
instead diff first and then turn it into nanosecs.
---
 src/bin/pg_test_timing/pg_test_timing.c | 59 +++++++++++++++++++------
 src/include/portability/instr_time.h    | 30 ++++++++-----
 2 files changed, 65 insertions(+), 24 deletions(-)

diff --git a/src/bin/pg_test_timing/pg_test_timing.c b/src/bin/pg_test_timing/pg_test_timing.c
index a5621251afc..b77ef2063b6 100644
--- a/src/bin/pg_test_timing/pg_test_timing.c
+++ b/src/bin/pg_test_timing/pg_test_timing.c
@@ -16,6 +16,7 @@ static const char *progname;
 
 static unsigned int test_duration = 3;
 static double max_rprct = 99.99;
+static bool fast_timing = false;
 
 /* record duration in powers of 2 nanoseconds */
 static long long int histogram[32];
@@ -56,6 +57,7 @@ handle_args(int argc, char *argv[])
 	static struct option long_options[] = {
 		{"duration", required_argument, NULL, 'd'},
 		{"cutoff", required_argument, NULL, 'c'},
+		{"fast", no_argument, NULL, 'f'},
 		{NULL, 0, NULL, 0}
 	};
 
@@ -68,7 +70,7 @@ handle_args(int argc, char *argv[])
 	{
 		if (strcmp(argv[1], "--help") == 0 || strcmp(argv[1], "-?") == 0)
 		{
-			printf(_("Usage: %s [-d DURATION] [-c CUTOFF]\n"), progname);
+			printf(_("Usage: %s [-d DURATION] [-c CUTOFF] [--fast]\n"), progname);
 			exit(0);
 		}
 		if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0)
@@ -78,7 +80,7 @@ handle_args(int argc, char *argv[])
 		}
 	}
 
-	while ((option = getopt_long(argc, argv, "d:c:",
+	while ((option = getopt_long(argc, argv, "d:c:f:",
 								 long_options, &optindex)) != -1)
 	{
 		switch (option)
@@ -125,6 +127,10 @@ handle_args(int argc, char *argv[])
 				}
 				break;
 
+			case 'f':
+				fast_timing = true;
+				break;
+
 			default:
 				fprintf(stderr, _("Try \"%s --help\" for more information.\n"),
 						progname);
@@ -155,11 +161,31 @@ test_timing(unsigned int duration)
 	uint64		total_time;
 	int64		time_elapsed = 0;
 	uint64		loop_count = 0;
-	uint64		prev,
-				cur;
 	instr_time	start_time,
 				end_time,
-				temp;
+				prev,
+				cur;
+	char	   *time_source = NULL;
+	bool		fast_timing_used = false;
+
+	INSTR_TIME_INITIALIZE();
+
+#if !defined(WIN32) && defined(__x86_64__) && defined(__linux__)
+	if (fast_timing && has_rdtsc)
+	{
+		time_source = "RDTSC";
+		fast_timing_used = true;
+	}
+	else if (has_rdtscp)
+		time_source = "RDTSCP";
+	else
+		time_source = PG_INSTR_CLOCK_NAME;
+#else
+	time_source = PG_INSTR_CLOCK_NAME;
+#endif
+	if (fast_timing && !fast_timing_used)
+		printf(_("Warning: Fast timing requested, but not available - regular timing source will be used\n"));
+	printf(_("Time source: %s\n"), time_source);
 
 	/*
 	 * Pre-zero the statistics data structures.  They're already zero by
@@ -173,8 +199,11 @@ test_timing(unsigned int duration)
 
 	total_time = duration > 0 ? duration * INT64CONST(1000000000) : 0;
 
-	INSTR_TIME_SET_CURRENT(start_time);
-	cur = INSTR_TIME_GET_NANOSEC(start_time);
+	if (fast_timing)
+		INSTR_TIME_SET_CURRENT_FAST(start_time);
+	else
+		INSTR_TIME_SET_CURRENT(start_time);
+	cur = start_time;
 
 	while (time_elapsed < total_time)
 	{
@@ -182,9 +211,11 @@ test_timing(unsigned int duration)
 					bits;
 
 		prev = cur;
-		INSTR_TIME_SET_CURRENT(temp);
-		cur = INSTR_TIME_GET_NANOSEC(temp);
-		diff = cur - prev;
+		if (fast_timing)
+			INSTR_TIME_SET_CURRENT_FAST(cur);
+		else
+			INSTR_TIME_SET_CURRENT(cur);
+		diff = INSTR_TIME_DIFF_NANOSEC(cur, prev);
 
 		/* Did time go backwards? */
 		if (unlikely(diff < 0))
@@ -217,11 +248,13 @@ test_timing(unsigned int duration)
 			largest_diff_count++;
 
 		loop_count++;
-		INSTR_TIME_SUBTRACT(temp, start_time);
-		time_elapsed = INSTR_TIME_GET_NANOSEC(temp);
+		time_elapsed = INSTR_TIME_DIFF_NANOSEC(cur, start_time);
 	}
 
-	INSTR_TIME_SET_CURRENT(end_time);
+	if (fast_timing)
+		INSTR_TIME_SET_CURRENT_FAST(end_time);
+	else
+		INSTR_TIME_SET_CURRENT(end_time);
 
 	INSTR_TIME_SUBTRACT(end_time, start_time);
 
diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h
index e2e339a0c4f..f02296f1026 100644
--- a/src/include/portability/instr_time.h
+++ b/src/include/portability/instr_time.h
@@ -112,10 +112,13 @@ extern int64 max_ticks_no_overflow;
  */
 #if defined(__darwin__) && defined(CLOCK_MONOTONIC_RAW)
 #define PG_INSTR_CLOCK	CLOCK_MONOTONIC_RAW
+#define PG_INSTR_CLOCK_NAME	"clock_gettime (CLOCK_MONOTONIC_RAW)"
 #elif defined(CLOCK_MONOTONIC)
 #define PG_INSTR_CLOCK	CLOCK_MONOTONIC
+#define PG_INSTR_CLOCK_NAME	"clock_gettime (CLOCK_MONOTONIC)"
 #else
 #define PG_INSTR_CLOCK	CLOCK_REALTIME
+#define PG_INSTR_CLOCK_NAME	"clock_gettime (CLOCK_REALTIME)"
 #endif
 
 #if defined(__x86_64__) && defined(__linux__)
@@ -174,7 +177,7 @@ pg_get_ticks(void)
 }
 
 static inline int64_t
-pg_ticks_to_ns(instr_time t)
+pg_ticks_to_ns(int64 ticks)
 {
 	/*
 	 * Would multiplication overflow? If so perform computation in two parts.
@@ -183,7 +186,7 @@ pg_ticks_to_ns(instr_time t)
 	 */
 	int64		ns = 0;
 
-	if (unlikely(t.ticks > max_ticks_no_overflow))
+	if (unlikely(ticks > max_ticks_no_overflow))
 	{
 		/*
 		 * Compute how often the maximum number of ticks fits completely into
@@ -192,7 +195,7 @@ pg_ticks_to_ns(instr_time t)
 		 * value. In a 2nd step we adjust the number of elapsed ticks and
 		 * convert the remaining ticks.
 		 */
-		int64		count = t.ticks / max_ticks_no_overflow;
+		int64		count = ticks / max_ticks_no_overflow;
 		int64		max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION;
 
 		ns = max_ns * count;
@@ -201,11 +204,11 @@ pg_ticks_to_ns(instr_time t)
 		 * Subtract the ticks that we now already accounted for, so that they
 		 * don't get counted twice.
 		 */
-		t.ticks -= count * max_ticks_no_overflow;
-		Assert(t.ticks >= 0);
+		ticks -= count * max_ticks_no_overflow;
+		Assert(ticks >= 0);
 	}
 
-	ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION;
+	ns += ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION;
 	return ns;
 }
 
@@ -226,14 +229,14 @@ pg_initialize_get_ticks()
 #define INSTR_TIME_SET_CURRENT(t) \
 	((t) = pg_get_ticks())
 
-#define INSTR_TIME_GET_NANOSEC(t) \
-	pg_ticks_to_ns(t)
-
+#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \
+	(pg_ticks_to_ns(ticks))
 
 #else							/* WIN32 */
 
 
 /* Use QueryPerformanceCounter() */
+#define PG_INSTR_CLOCK_NAME	"QueryPerformanceCounter"
 
 /* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */
 static inline instr_time
@@ -265,8 +268,8 @@ GetTimerFrequency(void)
 #define INSTR_TIME_SET_CURRENT(t) \
 	((t) = pg_query_performance_counter())
 
-#define INSTR_TIME_GET_NANOSEC(t) \
-	((int64) ((t).ticks * ((double) NS_PER_S / GetTimerFrequency())))
+#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \
+	((int64) ((ticks) * ((double) NS_PER_S / GetTimerFrequency())))
 
 #endif							/* WIN32 */
 
@@ -285,9 +288,14 @@ GetTimerFrequency(void)
 #define INSTR_TIME_SUBTRACT(x,y) \
 	((x).ticks -= (y).ticks)
 
+#define INSTR_TIME_DIFF_NANOSEC(x,y) \
+	(INSTR_TIME_TICKS_TO_NANOSEC((x).ticks - (y).ticks))
+
 #define INSTR_TIME_ACCUM_DIFF(x,y,z) \
 	((x).ticks += (y).ticks - (z).ticks)
 
+#define INSTR_TIME_GET_NANOSEC(t) \
+	(INSTR_TIME_TICKS_TO_NANOSEC((t).ticks))
 
 #define INSTR_TIME_GET_DOUBLE(t) \
 	((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S)
-- 
2.47.3


--vtqqtrpooseurzip--





^ permalink  raw  reply  [nested|flat] 265+ messages in thread

* [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source
@ 2025-07-27 15:48  Lukas Fittl <[email protected]>
  0 siblings, 0 replies; 265+ messages in thread

From: Lukas Fittl @ 2025-07-27 15:48 UTC (permalink / raw)

In passing also reduce the per-loop overhead caused by repeated divisions
in INSTR_TIME_GET_NANOSEC when the ticks variable has become very large,
instead diff first and then turn it into nanosecs.
---
 src/bin/pg_test_timing/pg_test_timing.c | 59 +++++++++++++++++++------
 src/include/portability/instr_time.h    | 30 ++++++++-----
 2 files changed, 65 insertions(+), 24 deletions(-)

diff --git a/src/bin/pg_test_timing/pg_test_timing.c b/src/bin/pg_test_timing/pg_test_timing.c
index a5621251afc..b77ef2063b6 100644
--- a/src/bin/pg_test_timing/pg_test_timing.c
+++ b/src/bin/pg_test_timing/pg_test_timing.c
@@ -16,6 +16,7 @@ static const char *progname;
 
 static unsigned int test_duration = 3;
 static double max_rprct = 99.99;
+static bool fast_timing = false;
 
 /* record duration in powers of 2 nanoseconds */
 static long long int histogram[32];
@@ -56,6 +57,7 @@ handle_args(int argc, char *argv[])
 	static struct option long_options[] = {
 		{"duration", required_argument, NULL, 'd'},
 		{"cutoff", required_argument, NULL, 'c'},
+		{"fast", no_argument, NULL, 'f'},
 		{NULL, 0, NULL, 0}
 	};
 
@@ -68,7 +70,7 @@ handle_args(int argc, char *argv[])
 	{
 		if (strcmp(argv[1], "--help") == 0 || strcmp(argv[1], "-?") == 0)
 		{
-			printf(_("Usage: %s [-d DURATION] [-c CUTOFF]\n"), progname);
+			printf(_("Usage: %s [-d DURATION] [-c CUTOFF] [--fast]\n"), progname);
 			exit(0);
 		}
 		if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0)
@@ -78,7 +80,7 @@ handle_args(int argc, char *argv[])
 		}
 	}
 
-	while ((option = getopt_long(argc, argv, "d:c:",
+	while ((option = getopt_long(argc, argv, "d:c:f:",
 								 long_options, &optindex)) != -1)
 	{
 		switch (option)
@@ -125,6 +127,10 @@ handle_args(int argc, char *argv[])
 				}
 				break;
 
+			case 'f':
+				fast_timing = true;
+				break;
+
 			default:
 				fprintf(stderr, _("Try \"%s --help\" for more information.\n"),
 						progname);
@@ -155,11 +161,31 @@ test_timing(unsigned int duration)
 	uint64		total_time;
 	int64		time_elapsed = 0;
 	uint64		loop_count = 0;
-	uint64		prev,
-				cur;
 	instr_time	start_time,
 				end_time,
-				temp;
+				prev,
+				cur;
+	char	   *time_source = NULL;
+	bool		fast_timing_used = false;
+
+	INSTR_TIME_INITIALIZE();
+
+#if !defined(WIN32) && defined(__x86_64__) && defined(__linux__)
+	if (fast_timing && has_rdtsc)
+	{
+		time_source = "RDTSC";
+		fast_timing_used = true;
+	}
+	else if (has_rdtscp)
+		time_source = "RDTSCP";
+	else
+		time_source = PG_INSTR_CLOCK_NAME;
+#else
+	time_source = PG_INSTR_CLOCK_NAME;
+#endif
+	if (fast_timing && !fast_timing_used)
+		printf(_("Warning: Fast timing requested, but not available - regular timing source will be used\n"));
+	printf(_("Time source: %s\n"), time_source);
 
 	/*
 	 * Pre-zero the statistics data structures.  They're already zero by
@@ -173,8 +199,11 @@ test_timing(unsigned int duration)
 
 	total_time = duration > 0 ? duration * INT64CONST(1000000000) : 0;
 
-	INSTR_TIME_SET_CURRENT(start_time);
-	cur = INSTR_TIME_GET_NANOSEC(start_time);
+	if (fast_timing)
+		INSTR_TIME_SET_CURRENT_FAST(start_time);
+	else
+		INSTR_TIME_SET_CURRENT(start_time);
+	cur = start_time;
 
 	while (time_elapsed < total_time)
 	{
@@ -182,9 +211,11 @@ test_timing(unsigned int duration)
 					bits;
 
 		prev = cur;
-		INSTR_TIME_SET_CURRENT(temp);
-		cur = INSTR_TIME_GET_NANOSEC(temp);
-		diff = cur - prev;
+		if (fast_timing)
+			INSTR_TIME_SET_CURRENT_FAST(cur);
+		else
+			INSTR_TIME_SET_CURRENT(cur);
+		diff = INSTR_TIME_DIFF_NANOSEC(cur, prev);
 
 		/* Did time go backwards? */
 		if (unlikely(diff < 0))
@@ -217,11 +248,13 @@ test_timing(unsigned int duration)
 			largest_diff_count++;
 
 		loop_count++;
-		INSTR_TIME_SUBTRACT(temp, start_time);
-		time_elapsed = INSTR_TIME_GET_NANOSEC(temp);
+		time_elapsed = INSTR_TIME_DIFF_NANOSEC(cur, start_time);
 	}
 
-	INSTR_TIME_SET_CURRENT(end_time);
+	if (fast_timing)
+		INSTR_TIME_SET_CURRENT_FAST(end_time);
+	else
+		INSTR_TIME_SET_CURRENT(end_time);
 
 	INSTR_TIME_SUBTRACT(end_time, start_time);
 
diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h
index e2e339a0c4f..f02296f1026 100644
--- a/src/include/portability/instr_time.h
+++ b/src/include/portability/instr_time.h
@@ -112,10 +112,13 @@ extern int64 max_ticks_no_overflow;
  */
 #if defined(__darwin__) && defined(CLOCK_MONOTONIC_RAW)
 #define PG_INSTR_CLOCK	CLOCK_MONOTONIC_RAW
+#define PG_INSTR_CLOCK_NAME	"clock_gettime (CLOCK_MONOTONIC_RAW)"
 #elif defined(CLOCK_MONOTONIC)
 #define PG_INSTR_CLOCK	CLOCK_MONOTONIC
+#define PG_INSTR_CLOCK_NAME	"clock_gettime (CLOCK_MONOTONIC)"
 #else
 #define PG_INSTR_CLOCK	CLOCK_REALTIME
+#define PG_INSTR_CLOCK_NAME	"clock_gettime (CLOCK_REALTIME)"
 #endif
 
 #if defined(__x86_64__) && defined(__linux__)
@@ -174,7 +177,7 @@ pg_get_ticks(void)
 }
 
 static inline int64_t
-pg_ticks_to_ns(instr_time t)
+pg_ticks_to_ns(int64 ticks)
 {
 	/*
 	 * Would multiplication overflow? If so perform computation in two parts.
@@ -183,7 +186,7 @@ pg_ticks_to_ns(instr_time t)
 	 */
 	int64		ns = 0;
 
-	if (unlikely(t.ticks > max_ticks_no_overflow))
+	if (unlikely(ticks > max_ticks_no_overflow))
 	{
 		/*
 		 * Compute how often the maximum number of ticks fits completely into
@@ -192,7 +195,7 @@ pg_ticks_to_ns(instr_time t)
 		 * value. In a 2nd step we adjust the number of elapsed ticks and
 		 * convert the remaining ticks.
 		 */
-		int64		count = t.ticks / max_ticks_no_overflow;
+		int64		count = ticks / max_ticks_no_overflow;
 		int64		max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION;
 
 		ns = max_ns * count;
@@ -201,11 +204,11 @@ pg_ticks_to_ns(instr_time t)
 		 * Subtract the ticks that we now already accounted for, so that they
 		 * don't get counted twice.
 		 */
-		t.ticks -= count * max_ticks_no_overflow;
-		Assert(t.ticks >= 0);
+		ticks -= count * max_ticks_no_overflow;
+		Assert(ticks >= 0);
 	}
 
-	ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION;
+	ns += ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION;
 	return ns;
 }
 
@@ -226,14 +229,14 @@ pg_initialize_get_ticks()
 #define INSTR_TIME_SET_CURRENT(t) \
 	((t) = pg_get_ticks())
 
-#define INSTR_TIME_GET_NANOSEC(t) \
-	pg_ticks_to_ns(t)
-
+#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \
+	(pg_ticks_to_ns(ticks))
 
 #else							/* WIN32 */
 
 
 /* Use QueryPerformanceCounter() */
+#define PG_INSTR_CLOCK_NAME	"QueryPerformanceCounter"
 
 /* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */
 static inline instr_time
@@ -265,8 +268,8 @@ GetTimerFrequency(void)
 #define INSTR_TIME_SET_CURRENT(t) \
 	((t) = pg_query_performance_counter())
 
-#define INSTR_TIME_GET_NANOSEC(t) \
-	((int64) ((t).ticks * ((double) NS_PER_S / GetTimerFrequency())))
+#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \
+	((int64) ((ticks) * ((double) NS_PER_S / GetTimerFrequency())))
 
 #endif							/* WIN32 */
 
@@ -285,9 +288,14 @@ GetTimerFrequency(void)
 #define INSTR_TIME_SUBTRACT(x,y) \
 	((x).ticks -= (y).ticks)
 
+#define INSTR_TIME_DIFF_NANOSEC(x,y) \
+	(INSTR_TIME_TICKS_TO_NANOSEC((x).ticks - (y).ticks))
+
 #define INSTR_TIME_ACCUM_DIFF(x,y,z) \
 	((x).ticks += (y).ticks - (z).ticks)
 
+#define INSTR_TIME_GET_NANOSEC(t) \
+	(INSTR_TIME_TICKS_TO_NANOSEC((t).ticks))
 
 #define INSTR_TIME_GET_DOUBLE(t) \
 	((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S)
-- 
2.47.3


--vtqqtrpooseurzip--





^ permalink  raw  reply  [nested|flat] 265+ messages in thread

* [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source
@ 2025-07-27 15:48  Lukas Fittl <[email protected]>
  0 siblings, 0 replies; 265+ messages in thread

From: Lukas Fittl @ 2025-07-27 15:48 UTC (permalink / raw)

In passing also reduce the per-loop overhead caused by repeated divisions
in INSTR_TIME_GET_NANOSEC when the ticks variable has become very large,
instead diff first and then turn it into nanosecs.
---
 src/bin/pg_test_timing/pg_test_timing.c | 59 +++++++++++++++++++------
 src/include/portability/instr_time.h    | 30 ++++++++-----
 2 files changed, 65 insertions(+), 24 deletions(-)

diff --git a/src/bin/pg_test_timing/pg_test_timing.c b/src/bin/pg_test_timing/pg_test_timing.c
index a5621251afc..b77ef2063b6 100644
--- a/src/bin/pg_test_timing/pg_test_timing.c
+++ b/src/bin/pg_test_timing/pg_test_timing.c
@@ -16,6 +16,7 @@ static const char *progname;
 
 static unsigned int test_duration = 3;
 static double max_rprct = 99.99;
+static bool fast_timing = false;
 
 /* record duration in powers of 2 nanoseconds */
 static long long int histogram[32];
@@ -56,6 +57,7 @@ handle_args(int argc, char *argv[])
 	static struct option long_options[] = {
 		{"duration", required_argument, NULL, 'd'},
 		{"cutoff", required_argument, NULL, 'c'},
+		{"fast", no_argument, NULL, 'f'},
 		{NULL, 0, NULL, 0}
 	};
 
@@ -68,7 +70,7 @@ handle_args(int argc, char *argv[])
 	{
 		if (strcmp(argv[1], "--help") == 0 || strcmp(argv[1], "-?") == 0)
 		{
-			printf(_("Usage: %s [-d DURATION] [-c CUTOFF]\n"), progname);
+			printf(_("Usage: %s [-d DURATION] [-c CUTOFF] [--fast]\n"), progname);
 			exit(0);
 		}
 		if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0)
@@ -78,7 +80,7 @@ handle_args(int argc, char *argv[])
 		}
 	}
 
-	while ((option = getopt_long(argc, argv, "d:c:",
+	while ((option = getopt_long(argc, argv, "d:c:f:",
 								 long_options, &optindex)) != -1)
 	{
 		switch (option)
@@ -125,6 +127,10 @@ handle_args(int argc, char *argv[])
 				}
 				break;
 
+			case 'f':
+				fast_timing = true;
+				break;
+
 			default:
 				fprintf(stderr, _("Try \"%s --help\" for more information.\n"),
 						progname);
@@ -155,11 +161,31 @@ test_timing(unsigned int duration)
 	uint64		total_time;
 	int64		time_elapsed = 0;
 	uint64		loop_count = 0;
-	uint64		prev,
-				cur;
 	instr_time	start_time,
 				end_time,
-				temp;
+				prev,
+				cur;
+	char	   *time_source = NULL;
+	bool		fast_timing_used = false;
+
+	INSTR_TIME_INITIALIZE();
+
+#if !defined(WIN32) && defined(__x86_64__) && defined(__linux__)
+	if (fast_timing && has_rdtsc)
+	{
+		time_source = "RDTSC";
+		fast_timing_used = true;
+	}
+	else if (has_rdtscp)
+		time_source = "RDTSCP";
+	else
+		time_source = PG_INSTR_CLOCK_NAME;
+#else
+	time_source = PG_INSTR_CLOCK_NAME;
+#endif
+	if (fast_timing && !fast_timing_used)
+		printf(_("Warning: Fast timing requested, but not available - regular timing source will be used\n"));
+	printf(_("Time source: %s\n"), time_source);
 
 	/*
 	 * Pre-zero the statistics data structures.  They're already zero by
@@ -173,8 +199,11 @@ test_timing(unsigned int duration)
 
 	total_time = duration > 0 ? duration * INT64CONST(1000000000) : 0;
 
-	INSTR_TIME_SET_CURRENT(start_time);
-	cur = INSTR_TIME_GET_NANOSEC(start_time);
+	if (fast_timing)
+		INSTR_TIME_SET_CURRENT_FAST(start_time);
+	else
+		INSTR_TIME_SET_CURRENT(start_time);
+	cur = start_time;
 
 	while (time_elapsed < total_time)
 	{
@@ -182,9 +211,11 @@ test_timing(unsigned int duration)
 					bits;
 
 		prev = cur;
-		INSTR_TIME_SET_CURRENT(temp);
-		cur = INSTR_TIME_GET_NANOSEC(temp);
-		diff = cur - prev;
+		if (fast_timing)
+			INSTR_TIME_SET_CURRENT_FAST(cur);
+		else
+			INSTR_TIME_SET_CURRENT(cur);
+		diff = INSTR_TIME_DIFF_NANOSEC(cur, prev);
 
 		/* Did time go backwards? */
 		if (unlikely(diff < 0))
@@ -217,11 +248,13 @@ test_timing(unsigned int duration)
 			largest_diff_count++;
 
 		loop_count++;
-		INSTR_TIME_SUBTRACT(temp, start_time);
-		time_elapsed = INSTR_TIME_GET_NANOSEC(temp);
+		time_elapsed = INSTR_TIME_DIFF_NANOSEC(cur, start_time);
 	}
 
-	INSTR_TIME_SET_CURRENT(end_time);
+	if (fast_timing)
+		INSTR_TIME_SET_CURRENT_FAST(end_time);
+	else
+		INSTR_TIME_SET_CURRENT(end_time);
 
 	INSTR_TIME_SUBTRACT(end_time, start_time);
 
diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h
index e2e339a0c4f..f02296f1026 100644
--- a/src/include/portability/instr_time.h
+++ b/src/include/portability/instr_time.h
@@ -112,10 +112,13 @@ extern int64 max_ticks_no_overflow;
  */
 #if defined(__darwin__) && defined(CLOCK_MONOTONIC_RAW)
 #define PG_INSTR_CLOCK	CLOCK_MONOTONIC_RAW
+#define PG_INSTR_CLOCK_NAME	"clock_gettime (CLOCK_MONOTONIC_RAW)"
 #elif defined(CLOCK_MONOTONIC)
 #define PG_INSTR_CLOCK	CLOCK_MONOTONIC
+#define PG_INSTR_CLOCK_NAME	"clock_gettime (CLOCK_MONOTONIC)"
 #else
 #define PG_INSTR_CLOCK	CLOCK_REALTIME
+#define PG_INSTR_CLOCK_NAME	"clock_gettime (CLOCK_REALTIME)"
 #endif
 
 #if defined(__x86_64__) && defined(__linux__)
@@ -174,7 +177,7 @@ pg_get_ticks(void)
 }
 
 static inline int64_t
-pg_ticks_to_ns(instr_time t)
+pg_ticks_to_ns(int64 ticks)
 {
 	/*
 	 * Would multiplication overflow? If so perform computation in two parts.
@@ -183,7 +186,7 @@ pg_ticks_to_ns(instr_time t)
 	 */
 	int64		ns = 0;
 
-	if (unlikely(t.ticks > max_ticks_no_overflow))
+	if (unlikely(ticks > max_ticks_no_overflow))
 	{
 		/*
 		 * Compute how often the maximum number of ticks fits completely into
@@ -192,7 +195,7 @@ pg_ticks_to_ns(instr_time t)
 		 * value. In a 2nd step we adjust the number of elapsed ticks and
 		 * convert the remaining ticks.
 		 */
-		int64		count = t.ticks / max_ticks_no_overflow;
+		int64		count = ticks / max_ticks_no_overflow;
 		int64		max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION;
 
 		ns = max_ns * count;
@@ -201,11 +204,11 @@ pg_ticks_to_ns(instr_time t)
 		 * Subtract the ticks that we now already accounted for, so that they
 		 * don't get counted twice.
 		 */
-		t.ticks -= count * max_ticks_no_overflow;
-		Assert(t.ticks >= 0);
+		ticks -= count * max_ticks_no_overflow;
+		Assert(ticks >= 0);
 	}
 
-	ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION;
+	ns += ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION;
 	return ns;
 }
 
@@ -226,14 +229,14 @@ pg_initialize_get_ticks()
 #define INSTR_TIME_SET_CURRENT(t) \
 	((t) = pg_get_ticks())
 
-#define INSTR_TIME_GET_NANOSEC(t) \
-	pg_ticks_to_ns(t)
-
+#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \
+	(pg_ticks_to_ns(ticks))
 
 #else							/* WIN32 */
 
 
 /* Use QueryPerformanceCounter() */
+#define PG_INSTR_CLOCK_NAME	"QueryPerformanceCounter"
 
 /* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */
 static inline instr_time
@@ -265,8 +268,8 @@ GetTimerFrequency(void)
 #define INSTR_TIME_SET_CURRENT(t) \
 	((t) = pg_query_performance_counter())
 
-#define INSTR_TIME_GET_NANOSEC(t) \
-	((int64) ((t).ticks * ((double) NS_PER_S / GetTimerFrequency())))
+#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \
+	((int64) ((ticks) * ((double) NS_PER_S / GetTimerFrequency())))
 
 #endif							/* WIN32 */
 
@@ -285,9 +288,14 @@ GetTimerFrequency(void)
 #define INSTR_TIME_SUBTRACT(x,y) \
 	((x).ticks -= (y).ticks)
 
+#define INSTR_TIME_DIFF_NANOSEC(x,y) \
+	(INSTR_TIME_TICKS_TO_NANOSEC((x).ticks - (y).ticks))
+
 #define INSTR_TIME_ACCUM_DIFF(x,y,z) \
 	((x).ticks += (y).ticks - (z).ticks)
 
+#define INSTR_TIME_GET_NANOSEC(t) \
+	(INSTR_TIME_TICKS_TO_NANOSEC((t).ticks))
 
 #define INSTR_TIME_GET_DOUBLE(t) \
 	((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S)
-- 
2.47.3


--vtqqtrpooseurzip--





^ permalink  raw  reply  [nested|flat] 265+ messages in thread

* [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source
@ 2025-07-27 15:48  Lukas Fittl <[email protected]>
  0 siblings, 0 replies; 265+ messages in thread

From: Lukas Fittl @ 2025-07-27 15:48 UTC (permalink / raw)

In passing also reduce the per-loop overhead caused by repeated divisions
in INSTR_TIME_GET_NANOSEC when the ticks variable has become very large,
instead diff first and then turn it into nanosecs.
---
 src/bin/pg_test_timing/pg_test_timing.c | 59 +++++++++++++++++++------
 src/include/portability/instr_time.h    | 30 ++++++++-----
 2 files changed, 65 insertions(+), 24 deletions(-)

diff --git a/src/bin/pg_test_timing/pg_test_timing.c b/src/bin/pg_test_timing/pg_test_timing.c
index a5621251afc..b77ef2063b6 100644
--- a/src/bin/pg_test_timing/pg_test_timing.c
+++ b/src/bin/pg_test_timing/pg_test_timing.c
@@ -16,6 +16,7 @@ static const char *progname;
 
 static unsigned int test_duration = 3;
 static double max_rprct = 99.99;
+static bool fast_timing = false;
 
 /* record duration in powers of 2 nanoseconds */
 static long long int histogram[32];
@@ -56,6 +57,7 @@ handle_args(int argc, char *argv[])
 	static struct option long_options[] = {
 		{"duration", required_argument, NULL, 'd'},
 		{"cutoff", required_argument, NULL, 'c'},
+		{"fast", no_argument, NULL, 'f'},
 		{NULL, 0, NULL, 0}
 	};
 
@@ -68,7 +70,7 @@ handle_args(int argc, char *argv[])
 	{
 		if (strcmp(argv[1], "--help") == 0 || strcmp(argv[1], "-?") == 0)
 		{
-			printf(_("Usage: %s [-d DURATION] [-c CUTOFF]\n"), progname);
+			printf(_("Usage: %s [-d DURATION] [-c CUTOFF] [--fast]\n"), progname);
 			exit(0);
 		}
 		if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0)
@@ -78,7 +80,7 @@ handle_args(int argc, char *argv[])
 		}
 	}
 
-	while ((option = getopt_long(argc, argv, "d:c:",
+	while ((option = getopt_long(argc, argv, "d:c:f:",
 								 long_options, &optindex)) != -1)
 	{
 		switch (option)
@@ -125,6 +127,10 @@ handle_args(int argc, char *argv[])
 				}
 				break;
 
+			case 'f':
+				fast_timing = true;
+				break;
+
 			default:
 				fprintf(stderr, _("Try \"%s --help\" for more information.\n"),
 						progname);
@@ -155,11 +161,31 @@ test_timing(unsigned int duration)
 	uint64		total_time;
 	int64		time_elapsed = 0;
 	uint64		loop_count = 0;
-	uint64		prev,
-				cur;
 	instr_time	start_time,
 				end_time,
-				temp;
+				prev,
+				cur;
+	char	   *time_source = NULL;
+	bool		fast_timing_used = false;
+
+	INSTR_TIME_INITIALIZE();
+
+#if !defined(WIN32) && defined(__x86_64__) && defined(__linux__)
+	if (fast_timing && has_rdtsc)
+	{
+		time_source = "RDTSC";
+		fast_timing_used = true;
+	}
+	else if (has_rdtscp)
+		time_source = "RDTSCP";
+	else
+		time_source = PG_INSTR_CLOCK_NAME;
+#else
+	time_source = PG_INSTR_CLOCK_NAME;
+#endif
+	if (fast_timing && !fast_timing_used)
+		printf(_("Warning: Fast timing requested, but not available - regular timing source will be used\n"));
+	printf(_("Time source: %s\n"), time_source);
 
 	/*
 	 * Pre-zero the statistics data structures.  They're already zero by
@@ -173,8 +199,11 @@ test_timing(unsigned int duration)
 
 	total_time = duration > 0 ? duration * INT64CONST(1000000000) : 0;
 
-	INSTR_TIME_SET_CURRENT(start_time);
-	cur = INSTR_TIME_GET_NANOSEC(start_time);
+	if (fast_timing)
+		INSTR_TIME_SET_CURRENT_FAST(start_time);
+	else
+		INSTR_TIME_SET_CURRENT(start_time);
+	cur = start_time;
 
 	while (time_elapsed < total_time)
 	{
@@ -182,9 +211,11 @@ test_timing(unsigned int duration)
 					bits;
 
 		prev = cur;
-		INSTR_TIME_SET_CURRENT(temp);
-		cur = INSTR_TIME_GET_NANOSEC(temp);
-		diff = cur - prev;
+		if (fast_timing)
+			INSTR_TIME_SET_CURRENT_FAST(cur);
+		else
+			INSTR_TIME_SET_CURRENT(cur);
+		diff = INSTR_TIME_DIFF_NANOSEC(cur, prev);
 
 		/* Did time go backwards? */
 		if (unlikely(diff < 0))
@@ -217,11 +248,13 @@ test_timing(unsigned int duration)
 			largest_diff_count++;
 
 		loop_count++;
-		INSTR_TIME_SUBTRACT(temp, start_time);
-		time_elapsed = INSTR_TIME_GET_NANOSEC(temp);
+		time_elapsed = INSTR_TIME_DIFF_NANOSEC(cur, start_time);
 	}
 
-	INSTR_TIME_SET_CURRENT(end_time);
+	if (fast_timing)
+		INSTR_TIME_SET_CURRENT_FAST(end_time);
+	else
+		INSTR_TIME_SET_CURRENT(end_time);
 
 	INSTR_TIME_SUBTRACT(end_time, start_time);
 
diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h
index e2e339a0c4f..f02296f1026 100644
--- a/src/include/portability/instr_time.h
+++ b/src/include/portability/instr_time.h
@@ -112,10 +112,13 @@ extern int64 max_ticks_no_overflow;
  */
 #if defined(__darwin__) && defined(CLOCK_MONOTONIC_RAW)
 #define PG_INSTR_CLOCK	CLOCK_MONOTONIC_RAW
+#define PG_INSTR_CLOCK_NAME	"clock_gettime (CLOCK_MONOTONIC_RAW)"
 #elif defined(CLOCK_MONOTONIC)
 #define PG_INSTR_CLOCK	CLOCK_MONOTONIC
+#define PG_INSTR_CLOCK_NAME	"clock_gettime (CLOCK_MONOTONIC)"
 #else
 #define PG_INSTR_CLOCK	CLOCK_REALTIME
+#define PG_INSTR_CLOCK_NAME	"clock_gettime (CLOCK_REALTIME)"
 #endif
 
 #if defined(__x86_64__) && defined(__linux__)
@@ -174,7 +177,7 @@ pg_get_ticks(void)
 }
 
 static inline int64_t
-pg_ticks_to_ns(instr_time t)
+pg_ticks_to_ns(int64 ticks)
 {
 	/*
 	 * Would multiplication overflow? If so perform computation in two parts.
@@ -183,7 +186,7 @@ pg_ticks_to_ns(instr_time t)
 	 */
 	int64		ns = 0;
 
-	if (unlikely(t.ticks > max_ticks_no_overflow))
+	if (unlikely(ticks > max_ticks_no_overflow))
 	{
 		/*
 		 * Compute how often the maximum number of ticks fits completely into
@@ -192,7 +195,7 @@ pg_ticks_to_ns(instr_time t)
 		 * value. In a 2nd step we adjust the number of elapsed ticks and
 		 * convert the remaining ticks.
 		 */
-		int64		count = t.ticks / max_ticks_no_overflow;
+		int64		count = ticks / max_ticks_no_overflow;
 		int64		max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION;
 
 		ns = max_ns * count;
@@ -201,11 +204,11 @@ pg_ticks_to_ns(instr_time t)
 		 * Subtract the ticks that we now already accounted for, so that they
 		 * don't get counted twice.
 		 */
-		t.ticks -= count * max_ticks_no_overflow;
-		Assert(t.ticks >= 0);
+		ticks -= count * max_ticks_no_overflow;
+		Assert(ticks >= 0);
 	}
 
-	ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION;
+	ns += ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION;
 	return ns;
 }
 
@@ -226,14 +229,14 @@ pg_initialize_get_ticks()
 #define INSTR_TIME_SET_CURRENT(t) \
 	((t) = pg_get_ticks())
 
-#define INSTR_TIME_GET_NANOSEC(t) \
-	pg_ticks_to_ns(t)
-
+#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \
+	(pg_ticks_to_ns(ticks))
 
 #else							/* WIN32 */
 
 
 /* Use QueryPerformanceCounter() */
+#define PG_INSTR_CLOCK_NAME	"QueryPerformanceCounter"
 
 /* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */
 static inline instr_time
@@ -265,8 +268,8 @@ GetTimerFrequency(void)
 #define INSTR_TIME_SET_CURRENT(t) \
 	((t) = pg_query_performance_counter())
 
-#define INSTR_TIME_GET_NANOSEC(t) \
-	((int64) ((t).ticks * ((double) NS_PER_S / GetTimerFrequency())))
+#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \
+	((int64) ((ticks) * ((double) NS_PER_S / GetTimerFrequency())))
 
 #endif							/* WIN32 */
 
@@ -285,9 +288,14 @@ GetTimerFrequency(void)
 #define INSTR_TIME_SUBTRACT(x,y) \
 	((x).ticks -= (y).ticks)
 
+#define INSTR_TIME_DIFF_NANOSEC(x,y) \
+	(INSTR_TIME_TICKS_TO_NANOSEC((x).ticks - (y).ticks))
+
 #define INSTR_TIME_ACCUM_DIFF(x,y,z) \
 	((x).ticks += (y).ticks - (z).ticks)
 
+#define INSTR_TIME_GET_NANOSEC(t) \
+	(INSTR_TIME_TICKS_TO_NANOSEC((t).ticks))
 
 #define INSTR_TIME_GET_DOUBLE(t) \
 	((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S)
-- 
2.47.3


--vtqqtrpooseurzip--





^ permalink  raw  reply  [nested|flat] 265+ messages in thread

* [PATCH v12 3/3] pg_test_timing: Add --fast flag to test fast timing, report time source
@ 2025-07-27 15:48  Lukas Fittl <[email protected]>
  0 siblings, 0 replies; 265+ messages in thread

From: Lukas Fittl @ 2025-07-27 15:48 UTC (permalink / raw)

In passing also reduce the per-loop overhead caused by repeated divisions
in INSTR_TIME_GET_NANOSEC when the ticks variable has become very large,
instead diff first and then turn it into nanosecs.
---
 src/bin/pg_test_timing/pg_test_timing.c | 59 +++++++++++++++++++------
 src/include/portability/instr_time.h    | 30 ++++++++-----
 2 files changed, 65 insertions(+), 24 deletions(-)

diff --git a/src/bin/pg_test_timing/pg_test_timing.c b/src/bin/pg_test_timing/pg_test_timing.c
index a5621251afc..b77ef2063b6 100644
--- a/src/bin/pg_test_timing/pg_test_timing.c
+++ b/src/bin/pg_test_timing/pg_test_timing.c
@@ -16,6 +16,7 @@ static const char *progname;
 
 static unsigned int test_duration = 3;
 static double max_rprct = 99.99;
+static bool fast_timing = false;
 
 /* record duration in powers of 2 nanoseconds */
 static long long int histogram[32];
@@ -56,6 +57,7 @@ handle_args(int argc, char *argv[])
 	static struct option long_options[] = {
 		{"duration", required_argument, NULL, 'd'},
 		{"cutoff", required_argument, NULL, 'c'},
+		{"fast", no_argument, NULL, 'f'},
 		{NULL, 0, NULL, 0}
 	};
 
@@ -68,7 +70,7 @@ handle_args(int argc, char *argv[])
 	{
 		if (strcmp(argv[1], "--help") == 0 || strcmp(argv[1], "-?") == 0)
 		{
-			printf(_("Usage: %s [-d DURATION] [-c CUTOFF]\n"), progname);
+			printf(_("Usage: %s [-d DURATION] [-c CUTOFF] [--fast]\n"), progname);
 			exit(0);
 		}
 		if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0)
@@ -78,7 +80,7 @@ handle_args(int argc, char *argv[])
 		}
 	}
 
-	while ((option = getopt_long(argc, argv, "d:c:",
+	while ((option = getopt_long(argc, argv, "d:c:f:",
 								 long_options, &optindex)) != -1)
 	{
 		switch (option)
@@ -125,6 +127,10 @@ handle_args(int argc, char *argv[])
 				}
 				break;
 
+			case 'f':
+				fast_timing = true;
+				break;
+
 			default:
 				fprintf(stderr, _("Try \"%s --help\" for more information.\n"),
 						progname);
@@ -155,11 +161,31 @@ test_timing(unsigned int duration)
 	uint64		total_time;
 	int64		time_elapsed = 0;
 	uint64		loop_count = 0;
-	uint64		prev,
-				cur;
 	instr_time	start_time,
 				end_time,
-				temp;
+				prev,
+				cur;
+	char	   *time_source = NULL;
+	bool		fast_timing_used = false;
+
+	INSTR_TIME_INITIALIZE();
+
+#if !defined(WIN32) && defined(__x86_64__) && defined(__linux__)
+	if (fast_timing && has_rdtsc)
+	{
+		time_source = "RDTSC";
+		fast_timing_used = true;
+	}
+	else if (has_rdtscp)
+		time_source = "RDTSCP";
+	else
+		time_source = PG_INSTR_CLOCK_NAME;
+#else
+	time_source = PG_INSTR_CLOCK_NAME;
+#endif
+	if (fast_timing && !fast_timing_used)
+		printf(_("Warning: Fast timing requested, but not available - regular timing source will be used\n"));
+	printf(_("Time source: %s\n"), time_source);
 
 	/*
 	 * Pre-zero the statistics data structures.  They're already zero by
@@ -173,8 +199,11 @@ test_timing(unsigned int duration)
 
 	total_time = duration > 0 ? duration * INT64CONST(1000000000) : 0;
 
-	INSTR_TIME_SET_CURRENT(start_time);
-	cur = INSTR_TIME_GET_NANOSEC(start_time);
+	if (fast_timing)
+		INSTR_TIME_SET_CURRENT_FAST(start_time);
+	else
+		INSTR_TIME_SET_CURRENT(start_time);
+	cur = start_time;
 
 	while (time_elapsed < total_time)
 	{
@@ -182,9 +211,11 @@ test_timing(unsigned int duration)
 					bits;
 
 		prev = cur;
-		INSTR_TIME_SET_CURRENT(temp);
-		cur = INSTR_TIME_GET_NANOSEC(temp);
-		diff = cur - prev;
+		if (fast_timing)
+			INSTR_TIME_SET_CURRENT_FAST(cur);
+		else
+			INSTR_TIME_SET_CURRENT(cur);
+		diff = INSTR_TIME_DIFF_NANOSEC(cur, prev);
 
 		/* Did time go backwards? */
 		if (unlikely(diff < 0))
@@ -217,11 +248,13 @@ test_timing(unsigned int duration)
 			largest_diff_count++;
 
 		loop_count++;
-		INSTR_TIME_SUBTRACT(temp, start_time);
-		time_elapsed = INSTR_TIME_GET_NANOSEC(temp);
+		time_elapsed = INSTR_TIME_DIFF_NANOSEC(cur, start_time);
 	}
 
-	INSTR_TIME_SET_CURRENT(end_time);
+	if (fast_timing)
+		INSTR_TIME_SET_CURRENT_FAST(end_time);
+	else
+		INSTR_TIME_SET_CURRENT(end_time);
 
 	INSTR_TIME_SUBTRACT(end_time, start_time);
 
diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h
index e2e339a0c4f..f02296f1026 100644
--- a/src/include/portability/instr_time.h
+++ b/src/include/portability/instr_time.h
@@ -112,10 +112,13 @@ extern int64 max_ticks_no_overflow;
  */
 #if defined(__darwin__) && defined(CLOCK_MONOTONIC_RAW)
 #define PG_INSTR_CLOCK	CLOCK_MONOTONIC_RAW
+#define PG_INSTR_CLOCK_NAME	"clock_gettime (CLOCK_MONOTONIC_RAW)"
 #elif defined(CLOCK_MONOTONIC)
 #define PG_INSTR_CLOCK	CLOCK_MONOTONIC
+#define PG_INSTR_CLOCK_NAME	"clock_gettime (CLOCK_MONOTONIC)"
 #else
 #define PG_INSTR_CLOCK	CLOCK_REALTIME
+#define PG_INSTR_CLOCK_NAME	"clock_gettime (CLOCK_REALTIME)"
 #endif
 
 #if defined(__x86_64__) && defined(__linux__)
@@ -174,7 +177,7 @@ pg_get_ticks(void)
 }
 
 static inline int64_t
-pg_ticks_to_ns(instr_time t)
+pg_ticks_to_ns(int64 ticks)
 {
 	/*
 	 * Would multiplication overflow? If so perform computation in two parts.
@@ -183,7 +186,7 @@ pg_ticks_to_ns(instr_time t)
 	 */
 	int64		ns = 0;
 
-	if (unlikely(t.ticks > max_ticks_no_overflow))
+	if (unlikely(ticks > max_ticks_no_overflow))
 	{
 		/*
 		 * Compute how often the maximum number of ticks fits completely into
@@ -192,7 +195,7 @@ pg_ticks_to_ns(instr_time t)
 		 * value. In a 2nd step we adjust the number of elapsed ticks and
 		 * convert the remaining ticks.
 		 */
-		int64		count = t.ticks / max_ticks_no_overflow;
+		int64		count = ticks / max_ticks_no_overflow;
 		int64		max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION;
 
 		ns = max_ns * count;
@@ -201,11 +204,11 @@ pg_ticks_to_ns(instr_time t)
 		 * Subtract the ticks that we now already accounted for, so that they
 		 * don't get counted twice.
 		 */
-		t.ticks -= count * max_ticks_no_overflow;
-		Assert(t.ticks >= 0);
+		ticks -= count * max_ticks_no_overflow;
+		Assert(ticks >= 0);
 	}
 
-	ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION;
+	ns += ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION;
 	return ns;
 }
 
@@ -226,14 +229,14 @@ pg_initialize_get_ticks()
 #define INSTR_TIME_SET_CURRENT(t) \
 	((t) = pg_get_ticks())
 
-#define INSTR_TIME_GET_NANOSEC(t) \
-	pg_ticks_to_ns(t)
-
+#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \
+	(pg_ticks_to_ns(ticks))
 
 #else							/* WIN32 */
 
 
 /* Use QueryPerformanceCounter() */
+#define PG_INSTR_CLOCK_NAME	"QueryPerformanceCounter"
 
 /* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */
 static inline instr_time
@@ -265,8 +268,8 @@ GetTimerFrequency(void)
 #define INSTR_TIME_SET_CURRENT(t) \
 	((t) = pg_query_performance_counter())
 
-#define INSTR_TIME_GET_NANOSEC(t) \
-	((int64) ((t).ticks * ((double) NS_PER_S / GetTimerFrequency())))
+#define INSTR_TIME_TICKS_TO_NANOSEC(ticks) \
+	((int64) ((ticks) * ((double) NS_PER_S / GetTimerFrequency())))
 
 #endif							/* WIN32 */
 
@@ -285,9 +288,14 @@ GetTimerFrequency(void)
 #define INSTR_TIME_SUBTRACT(x,y) \
 	((x).ticks -= (y).ticks)
 
+#define INSTR_TIME_DIFF_NANOSEC(x,y) \
+	(INSTR_TIME_TICKS_TO_NANOSEC((x).ticks - (y).ticks))
+
 #define INSTR_TIME_ACCUM_DIFF(x,y,z) \
 	((x).ticks += (y).ticks - (z).ticks)
 
+#define INSTR_TIME_GET_NANOSEC(t) \
+	(INSTR_TIME_TICKS_TO_NANOSEC((t).ticks))
 
 #define INSTR_TIME_GET_DOUBLE(t) \
 	((double) INSTR_TIME_GET_NANOSEC(t) / NS_PER_S)
-- 
2.47.3


--vtqqtrpooseurzip--





^ permalink  raw  reply  [nested|flat] 265+ messages in thread