agora inbox for [email protected]  

help / color / mirror / Atom feed

[PATCH 3/4] Add autoconf test for computed goto support.
265+ messages / 2 participants
[nested] [flat]

* [PATCH 3/4] Add autoconf test for computed goto support.
@ 2017-02-07 22:16 Andres Freund <[email protected]>
  0 siblings, 0 replies; 265+ messages in thread

From: Andres Freund @ 2017-02-07 22:16 UTC (permalink / raw)

Author: Andres Freund
---
 config/c-compiler.m4          | 24 ++++++++++++++++++++++++
 configure                     | 34 ++++++++++++++++++++++++++++++++++
 configure.in                  |  1 +
 src/include/pg_config.h.in    |  3 +++
 src/include/pg_config.h.win32 |  3 +++
 5 files changed, 65 insertions(+)

diff --git a/config/c-compiler.m4 b/config/c-compiler.m4
index 7d901e1f1a..f56d8852f0 100644
--- a/config/c-compiler.m4
+++ b/config/c-compiler.m4
@@ -491,3 +491,27 @@ if test x"$Ac_cachevar" = x"yes"; then
 fi
 undefine([Ac_cachevar])dnl
 ])# PGAC_SSE42_CRC32_INTRINSICS
+
+
+
+# PGAC_C_COMPUTED_GOTO
+# -----------------------
+# Check if the C compiler knows computed gotos (gcc extension, also
+# available in at least clang).  If so define HAVE_COMPUTED_GOTO
+#
+# Checking whether computed gotos are supported syntax-wise ought to
+# be enough, as the syntax is otherwise illegal.
+AC_DEFUN([PGAC_C_COMPUTED_GOTO],
+[AC_CACHE_CHECK(for computed goto support, pgac_cv__computed_goto,
+[AC_COMPILE_IFELSE([AC_LANG_PROGRAM([],
+[[void *labeladdrs[] = {&&my_label};
+  goto *labeladdrs[0];
+  my_label:
+  return 1;
+]])],
+[pgac_cv__computed_goto=yes],
+[pgac_cv__computed_goto=no])])
+if test x"$pgac_cv__computed_goto" = xyes ; then
+AC_DEFINE(HAVE__COMPUTED_GOTO, 1,
+  [Define to 1 if your compiler handles computed gotos.])
+fi])# PGAC_C_COMPUTED_GOTO
diff --git a/configure b/configure
index b5cdebb510..fafef4638e 100755
--- a/configure
+++ b/configure
@@ -11564,6 +11564,40 @@ if test x"$pgac_cv__va_args" = xyes ; then
 $as_echo "#define HAVE__VA_ARGS 1" >>confdefs.h
 
 fi
+{ $as_echo "$as_me:${as_lineno-$LINENO}: checking for computed goto support" >&5
+$as_echo_n "checking for computed goto support... " >&6; }
+if ${pgac_cv__computed_goto+:} false; then :
+  $as_echo_n "(cached) " >&6
+else
+  cat confdefs.h - <<_ACEOF >conftest.$ac_ext
+/* end confdefs.h.  */
+
+int
+main ()
+{
+void *labeladdrs[] = {&&my_label};
+  goto *labeladdrs[0];
+  my_label:
+  return 1;
+
+  ;
+  return 0;
+}
+_ACEOF
+if ac_fn_c_try_compile "$LINENO"; then :
+  pgac_cv__computed_goto=yes
+else
+  pgac_cv__computed_goto=no
+fi
+rm -f core conftest.err conftest.$ac_objext conftest.$ac_ext
+fi
+{ $as_echo "$as_me:${as_lineno-$LINENO}: result: $pgac_cv__computed_goto" >&5
+$as_echo "$pgac_cv__computed_goto" >&6; }
+if test x"$pgac_cv__computed_goto" = xyes ; then
+
+$as_echo "#define HAVE__COMPUTED_GOTO 1" >>confdefs.h
+
+fi
 { $as_echo "$as_me:${as_lineno-$LINENO}: checking whether struct tm is in sys/time.h or time.h" >&5
 $as_echo_n "checking whether struct tm is in sys/time.h or time.h... " >&6; }
 if ${ac_cv_struct_tm+:} false; then :
diff --git a/configure.in b/configure.in
index 1d99cda1d8..9aa9203c40 100644
--- a/configure.in
+++ b/configure.in
@@ -1323,6 +1323,7 @@ PGAC_C_BUILTIN_BSWAP64
 PGAC_C_BUILTIN_CONSTANT_P
 PGAC_C_BUILTIN_UNREACHABLE
 PGAC_C_VA_ARGS
+PGAC_C_COMPUTED_GOTO
 PGAC_STRUCT_TIMEZONE
 PGAC_UNION_SEMUN
 PGAC_STRUCT_SOCKADDR_UN
diff --git a/src/include/pg_config.h.in b/src/include/pg_config.h.in
index 5bcd8a1160..94de1a75a2 100644
--- a/src/include/pg_config.h.in
+++ b/src/include/pg_config.h.in
@@ -687,6 +687,9 @@
 /* Define to 1 if your compiler understands __builtin_unreachable. */
 #undef HAVE__BUILTIN_UNREACHABLE
 
+/* Define to 1 if your compiler handles computed gotos. */
+#undef HAVE__COMPUTED_GOTO
+
 /* Define to 1 if you have __cpuid. */
 #undef HAVE__CPUID
 
diff --git a/src/include/pg_config.h.win32 b/src/include/pg_config.h.win32
index 3e4132cd82..c5441855bd 100644
--- a/src/include/pg_config.h.win32
+++ b/src/include/pg_config.h.win32
@@ -514,6 +514,9 @@
 /* Define to 1 if your compiler understands __builtin_unreachable. */
 /* #undef HAVE__BUILTIN_UNREACHABLE */
 
+/* Define to 1 if your compiler handles computed gotos. */
+#undef HAVE__COMPUTED_GOTO
+
 /* Define to 1 if you have __cpuid. */
 #define HAVE__CPUID 1
 
-- 
2.11.0.22.g8d7a455.dirty


--y7hr4yk6lkjgumip
Content-Type: text/x-patch; charset=us-ascii
Content-Disposition: attachment;
 filename="0004-WIP-Faster-expression-evaluation-and-targetlist-proj.patch"



^ 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