agora inbox for [email protected]  

help / color / mirror / Atom feed

Call for alpha testing: planner statistics revisions
271+ messages / 4 participants
[nested] [flat]

* Call for alpha testing: planner statistics revisions
@ 2001-06-17 20:47 Tom Lane <[email protected]>
  2001-06-21 11:38 ` Re: Call for alpha testing: planner statistics revisions Einar Karttunen <[email protected]>
  2001-06-21 19:05 ` Re: [GENERAL] Call for alpha testing: planner statistics revisions Ed Loehr <[email protected]>
  0 siblings, 2 replies; 271+ messages in thread

From: Tom Lane @ 2001-06-17 20:47 UTC (permalink / raw)
  To: pgsql-hackers; [email protected]

I have finished a first pass at the planner statistics and cost
estimation changes that I want to do for 7.2.  It's now time to see
how well the new code does in the real world.  Accordingly, if you've
had problems in the past with silly choices of plans, I'd like to ask
you to load your data into a test installation of current sources and
see if the planner is any brighter than before.

I realize that loading a bunch of data into a temporary installation is
a pain in the neck, but it'd be really great to get some feedback about
performance of the new code now, while we're still early enough in the
7.2 development cycle to do something about any problems that turn up.

If you're willing to help out, you can get current sources from the
CVS server, or from the nightly snapshot tarball (see the dev/
directory on your favorite Postgres FTP mirror).

Some highlights of the new code include:

* ANALYZE is now available as a separate command; you can run it without
also doing a VACUUM.  (Of course, VACUUM ANALYZE still works.)

* On large tables, ANALYZE uses a random sample of rows rather than
examining every row, so that it should take a reasonably short time
even on very large tables.  Possible downside: inaccurate stats.
We need to find out if the sample size is large enough.

* Statistics now include the "top ten" most common values, not just
the single most common value, plus an estimate of the total number of
distinct values in a column.  This should mean that selectivity
estimates for "column = something" estimates are a lot better than
before, especially for highly skewed data distributions.

* Statistics also include (for scalar datatypes) a histogram that
gives the boundary values dividing the data into ten
roughly-equal-population bins.  This should allow much better estimation
for inequality and range queries, again especially for skewed data
distributions.  (Note that "range queries" include such things as
anchored LIKE and regexp searches, plus now inet subnet searches thanks
to Alex Pilosov.)

* The magic number "ten" mentioned above is controllable via
ALTER TABLE tab ALTER COLUMN col SET STATISTICS statstarget.
Adjusting it gives a tradeoff between estimation accuracy and
time/space taken by ANALYZE.  We need to find out if ten is a good
default or not ... it might be too high or too low.

* There's also a physical-order-correlation statistic that should help
the planner deal with clustered indices better.  Whether it's good
enough, and whether the costs are correctly interpolated using it,
remain to be seen.

For more info see my original proposal at
http://fts.postgresql.org/db/mw/msg.html?mid=112714
and followup discussion.

			regards, tom lane



^ permalink  raw  reply  [nested|flat] 271+ messages in thread

* Re: Call for alpha testing: planner statistics revisions
  2001-06-17 20:47 Call for alpha testing: planner statistics revisions Tom Lane <[email protected]>
@ 2001-06-21 11:38 ` Einar Karttunen <[email protected]>
  1 sibling, 0 replies; 271+ messages in thread

From: Einar Karttunen @ 2001-06-21 11:38 UTC (permalink / raw)
  To: Tom Lane <[email protected]>; +Cc: pgsql-hackers; [email protected]

On Sun, 17 Jun 2001, Tom Lane wrote:
> * On large tables, ANALYZE uses a random sample of rows rather than
> examining every row, so that it should take a reasonably short time
> even on very large tables.  Possible downside: inaccurate stats.
> We need to find out if the sample size is large enough.
How about letting the user specify how much of the table should be
examined? So if you know the data is homogenous you can just specify a
smaller sample than normal and if you have time you can have the whole
table scanned.

- Einar Karttunen




^ permalink  raw  reply  [nested|flat] 271+ messages in thread

* Re: [GENERAL] Call for alpha testing: planner statistics revisions
  2001-06-17 20:47 Call for alpha testing: planner statistics revisions Tom Lane <[email protected]>
@ 2001-06-21 19:05 ` Ed Loehr <[email protected]>
  2001-06-21 20:02   ` Re: [GENERAL] Call for alpha testing: planner statistics revisions Tom Lane <[email protected]>
  1 sibling, 1 reply; 271+ messages in thread

From: Ed Loehr @ 2001-06-21 19:05 UTC (permalink / raw)
  To: Tom Lane <[email protected]>; +Cc: pgsql-hackers

Tom Lane wrote:
> 
> I have finished a first pass at the planner statistics and cost
> estimation changes that I want to do for 7.2.  It's now time to see
> how well the new code does in the real world...
> 
> Some highlights of the new code include:
> 
> * ANALYZE is now available as a separate command; you can run it without
> also doing a VACUUM.  (Of course, VACUUM ANALYZE still works.)

What is the impact of this newly isolated ANALYZE command on the need
and/or frequency for VACUUMs?  

I'd like to reduce the frequency of VACUUMs given my understanding has
been that updates/inserts/deletes are a no-no during VACUUMs (that was
6.5.x era hearsay), and we lock people out during VACUUMs (VACUUM
ANALYZE, that is).  

Regards,
Ed Loehr



^ permalink  raw  reply  [nested|flat] 271+ messages in thread

* Re: [GENERAL] Call for alpha testing: planner statistics revisions
  2001-06-17 20:47 Call for alpha testing: planner statistics revisions Tom Lane <[email protected]>
  2001-06-21 19:05 ` Re: [GENERAL] Call for alpha testing: planner statistics revisions Ed Loehr <[email protected]>
@ 2001-06-21 20:02   ` Tom Lane <[email protected]>
  0 siblings, 0 replies; 271+ messages in thread

From: Tom Lane @ 2001-06-21 20:02 UTC (permalink / raw)
  To: Ed Loehr <[email protected]>; +Cc: pgsql-hackers

Ed Loehr <[email protected]> writes:
> Tom Lane wrote:
>> * ANALYZE is now available as a separate command; you can run it without
>> also doing a VACUUM.  (Of course, VACUUM ANALYZE still works.)

> What is the impact of this newly isolated ANALYZE command on the need
> and/or frequency for VACUUMs?  

None really.  By the time 7.2 is out, I expect we will also have a
more lightweight form of VACUUM, and so running VACUUM ANALYZE as a
reasonably frequent background operation will still be the norm.

			regards, tom lane



^ permalink  raw  reply  [nested|flat] 271+ messages in thread

* [PATCH v12 2/3] Use time stamp counter to measure time on Linux/x86
@ 2025-07-26 00:57 Lukas Fittl <[email protected]>
  0 siblings, 0 replies; 271+ messages in thread

From: Lukas Fittl @ 2025-07-26 00:57 UTC (permalink / raw)

We switch to using the time stamp counter (TSC) instead of clock_gettime()
to reduce overhead of EXPLAIN (ANALYZE, TIME ON). Tests showed that runtime
is reduced by around 10% for queries moving lots of rows through the plan.

For now this is only enabled on Linux/x86, in case the system clocksource is
reported as TSC. Relying on the Linux kernel simplifies the logic to detect
if the present TSC is usable (frequency invariant, synchronized between
sockets, etc.). In all other cases we fallback to clock_gettime().

Note, that we intentionally use RDTSC in the fast paths, rather than RDTSCP.
RDTSCP waits for outstanding instructions to retire on out-of-order CPUs.
This adds noticably for little benefit in the typical InstrStartNode() /
InstrStopNode() use case. The macro to be used in such cases is called
INSTR_TIME_SET_CURRENT_FAST(). The original macro INSTR_TIME_SET_CURRENT()
uses RDTSCP and is supposed to be used when precision is more important
than performance.

Author: David Geier <[email protected]>
Author: Andres Freund <[email protected]>
Author: Lukas Fittl <[email protected]>
Reviewed-by:
Discussion: https://www.postgresql.org/message-id/flat/20200612232810.f46nbqkdhbutzqdg%40alap3.anarazel.de
---
 src/backend/access/heap/vacuumlazy.c |   4 +-
 src/backend/executor/instrument.c    |  12 +-
 src/backend/utils/init/postinit.c    |   3 +
 src/bin/pgbench/pgbench.c            |   3 +
 src/bin/psql/startup.c               |   4 +
 src/common/Makefile                  |   1 +
 src/common/instr_time.c              | 206 +++++++++++++++++++++++++++
 src/common/meson.build               |   1 +
 src/include/portability/instr_time.h | 136 +++++++++++++++---
 9 files changed, 348 insertions(+), 22 deletions(-)
 create mode 100644 src/common/instr_time.c

diff --git a/src/backend/access/heap/vacuumlazy.c b/src/backend/access/heap/vacuumlazy.c
index d2b031fdd06..5027048cac4 100644
--- a/src/backend/access/heap/vacuumlazy.c
+++ b/src/backend/access/heap/vacuumlazy.c
@@ -3409,8 +3409,8 @@ count_nondeletable_pages(LVRelState *vacrel, bool *lock_waiter_detected)
 			INSTR_TIME_SET_CURRENT(currenttime);
 			elapsed = currenttime;
 			INSTR_TIME_SUBTRACT(elapsed, starttime);
-			if ((INSTR_TIME_GET_MICROSEC(elapsed) / 1000)
-				>= VACUUM_TRUNCATE_LOCK_CHECK_INTERVAL)
+			if (INSTR_TIME_GET_MILLISEC(elapsed) >=
+				VACUUM_TRUNCATE_LOCK_CHECK_INTERVAL)
 			{
 				if (LockHasWaitersRelation(vacrel->rel, AccessExclusiveLock))
 				{
diff --git a/src/backend/executor/instrument.c b/src/backend/executor/instrument.c
index 56e635f4700..01f67c5d972 100644
--- a/src/backend/executor/instrument.c
+++ b/src/backend/executor/instrument.c
@@ -67,9 +67,13 @@ InstrInit(Instrumentation *instr, int instrument_options)
 void
 InstrStartNode(Instrumentation *instr)
 {
-	if (instr->need_timer &&
-		!INSTR_TIME_SET_CURRENT_LAZY(instr->starttime))
-		elog(ERROR, "InstrStartNode called twice in a row");
+	if (instr->need_timer)
+	{
+		if (!INSTR_TIME_IS_ZERO(instr->starttime))
+			elog(ERROR, "InstrStartNode called twice in a row");
+		else
+			INSTR_TIME_SET_CURRENT_FAST(instr->starttime);
+	}
 
 	/* save buffer usage totals at node entry, if needed */
 	if (instr->need_bufusage)
@@ -95,7 +99,7 @@ InstrStopNode(Instrumentation *instr, double nTuples)
 		if (INSTR_TIME_IS_ZERO(instr->starttime))
 			elog(ERROR, "InstrStopNode called without start");
 
-		INSTR_TIME_SET_CURRENT(endtime);
+		INSTR_TIME_SET_CURRENT_FAST(endtime);
 		INSTR_TIME_ACCUM_DIFF(instr->counter, endtime, instr->starttime);
 
 		INSTR_TIME_SET_ZERO(instr->starttime);
diff --git a/src/backend/utils/init/postinit.c b/src/backend/utils/init/postinit.c
index 641e535a73c..d573409903b 100644
--- a/src/backend/utils/init/postinit.c
+++ b/src/backend/utils/init/postinit.c
@@ -810,6 +810,9 @@ InitPostgres(const char *in_dbname, Oid dboid,
 	/* Initialize portal manager */
 	EnablePortalManager();
 
+	/* initialize high-precision interval timing */
+	INSTR_TIME_INITIALIZE();
+
 	/*
 	 * Load relcache entries for the shared system catalogs.  This must create
 	 * at least entries for pg_database and catalogs used for authentication.
diff --git a/src/bin/pgbench/pgbench.c b/src/bin/pgbench/pgbench.c
index 1515ed405ba..79bef2d2aec 100644
--- a/src/bin/pgbench/pgbench.c
+++ b/src/bin/pgbench/pgbench.c
@@ -7290,6 +7290,9 @@ main(int argc, char **argv)
 		initRandomState(&state[i].cs_func_rs);
 	}
 
+	/* initialize high-precision interval timing */
+	INSTR_TIME_INITIALIZE();
+
 	/* opening connection... */
 	con = doConnect();
 	if (con == NULL)
diff --git a/src/bin/psql/startup.c b/src/bin/psql/startup.c
index 249b6aa5169..d615df593c7 100644
--- a/src/bin/psql/startup.c
+++ b/src/bin/psql/startup.c
@@ -24,6 +24,7 @@
 #include "help.h"
 #include "input.h"
 #include "mainloop.h"
+#include "portability/instr_time.h"
 #include "settings.h"
 
 /*
@@ -327,6 +328,9 @@ main(int argc, char *argv[])
 
 	PQsetNoticeProcessor(pset.db, NoticeProcessor, NULL);
 
+	/* initialize high-precision interval timing */
+	INSTR_TIME_INITIALIZE();
+
 	SyncVariables();
 
 	if (options.list_dbs)
diff --git a/src/common/Makefile b/src/common/Makefile
index 2c720caa509..1a2fbbe887f 100644
--- a/src/common/Makefile
+++ b/src/common/Makefile
@@ -59,6 +59,7 @@ OBJS_COMMON = \
 	file_perm.o \
 	file_utils.o \
 	hashfn.o \
+	instr_time.o \
 	ip.o \
 	jsonapi.o \
 	keywords.o \
diff --git a/src/common/instr_time.c b/src/common/instr_time.c
new file mode 100644
index 00000000000..fdf47699f20
--- /dev/null
+++ b/src/common/instr_time.c
@@ -0,0 +1,206 @@
+/*-------------------------------------------------------------------------
+ *
+ * instr_time.c
+ *	   Non-inline parts of the portable high-precision interval timing
+ *	 implementation
+ *
+ * Portions Copyright (c) 2025, PostgreSQL Global Development Group
+ *
+ *
+ * IDENTIFICATION
+ *	  src/backend/port/instr_time.c
+ *
+ *-------------------------------------------------------------------------
+ */
+#include "postgres.h"
+
+#if defined(HAVE__GET_CPUID) || (defined(HAVE__CPUIDEX) && !defined(_MSC_VER))
+#include <cpuid.h>
+#endif
+
+#if defined(HAVE__CPUID) || (defined(HAVE__CPUIDEX) && defined(_MSC_VER))
+#include <intrin.h>
+#endif
+
+#include "portability/instr_time.h"
+
+#ifndef WIN32
+/*
+ * Stores what the number of cycles needs to be multiplied with to end up
+ * with nanoseconds using integer math. See comment in pg_initialize_rdtsc()
+ * for more details.
+ *
+ * By default assume we are using clock_gettime() as a fallback which uses
+ * nanoseconds as ticks. Hence, we set the multiplier to the precision scalar
+ * so that the division in INSTR_TIME_GET_NANOSEC() won't change the nanoseconds.
+ *
+ * When using the RDTSC instruction directly this is filled in during initialization
+ * based on the relevant CPUID fields.
+ */
+int64		ticks_per_ns_scaled = TICKS_TO_NS_PRECISION;
+int64		ticks_per_sec = NS_PER_S;
+int64		max_ticks_no_overflow = PG_INT64_MAX / TICKS_TO_NS_PRECISION;
+
+#if defined(__x86_64__) && defined(__linux__)
+/*
+ * Indicates if RDTSC can be used (Linux/x86 only, when OS uses TSC clocksource)
+ */
+bool		has_rdtsc = false;
+
+/*
+ * Indicates if RDTSCP can be used. True if RDTSC can be used and RDTSCP is available.
+ */
+bool		has_rdtscp = false;
+
+#define CPUID_HYPERVISOR_VMWARE(words) (words[1] == 0x61774d56 && words[2] == 0x4d566572 && words[3] == 0x65726177) /* VMwareVMware */
+#define CPUID_HYPERVISOR_KVM(words) (words[1] == 0x4b4d564b && words[2] == 0x564b4d56 && words[3] == 0x0000004d)	/* KVMKVMKVM */
+
+static bool
+get_tsc_frequency_khz(uint32 *tsc_freq)
+{
+	uint32		r[4] = {0, 0, 0, 0};
+
+#if defined(HAVE__GET_CPUID)
+	__get_cpuid(0x15, &r[0] /* denominator */ , &r[1] /* numerator */ , &r[2] /* hz */ , &r[3]);
+#elif defined(HAVE__CPUID)
+	__cpuid(r, 0x15);
+#else
+#error cpuid instruction not available
+#endif
+
+	if (r[2] > 0)
+	{
+		if (r[0] == 0 || r[1] == 0)
+			return false;
+
+		*tsc_freq = r[2] / 1000 * r[1] / r[0];
+		return true;
+	}
+
+	/* Some CPUs only report frequency in 16H */
+
+#if defined(HAVE__GET_CPUID)
+	__get_cpuid(0x16, &r[0] /* base_mhz */ , &r[1], &r[2], &r[3]);
+#elif defined(HAVE__CPUID)
+	__cpuid(r, 0x16);
+#else
+#error cpuid instruction not available
+#endif
+
+	if (r[0] > 0)
+	{
+		*tsc_freq = r[0] * 1000;
+		return true;
+	}
+
+	/*
+	 * Check if we have a KVM or VMware Hypervisor passing down TSC frequency
+	 * to us in a guest VM
+	 *
+	 * Note that accessing the 0x40000000 leaf for Hypervisor info requires
+	 * use of __cpuidex to set ECX to 0. The similar __get_cpuid_count
+	 * function does not work as expected since it contains a check for
+	 * __get_cpuid_max, which has been observed to be lower than the special
+	 * Hypervisor leaf.
+	 */
+#if defined(HAVE__CPUIDEX)
+	__cpuidex((int32 *) r, 0x40000000, 0);
+	if (r[0] >= 0x40000010 && (CPUID_HYPERVISOR_VMWARE(r) || CPUID_HYPERVISOR_KVM(r)))
+	{
+		__cpuidex((int32 *) r, 0x40000010, 0);
+		if (r[0] > 0)
+		{
+			*tsc_freq = r[0];
+			return true;
+		}
+	}
+#endif
+
+	return false;
+}
+
+static bool
+is_rdtscp_available()
+{
+	uint32		r[4] = {0, 0, 0, 0};
+
+#if defined(HAVE__GET_CPUID)
+	if (!__get_cpuid(0x80000001, &r[0], &r[1], &r[2], &r[3]))
+		return false;
+#elif defined(HAVE__CPUID)
+	__cpuid(r, 0x80000001);
+#else
+#error cpuid instruction not available
+#endif
+
+	return (r[3] & (1 << 27)) != 0;
+}
+
+/*
+ * Decide whether we use the RDTSC instruction at runtime, for Linux/x86,
+ * instead of incurring the overhead of a full clock_gettime() call.
+ *
+ * This can't be reliably determined at compile time, since the
+ * availability of an "invariant" TSC (that is not affected by CPU
+ * frequency changes) is dependent on the CPU architecture. Additionally,
+ * there are cases where TSC availability is impacted by virtualization,
+ * where a simple cpuid feature check would not be enough.
+ *
+ * Since Linux already does a significant amount of work to determine
+ * whether TSC is a viable clock source, decide based on that.
+ */
+void
+pg_initialize_rdtsc(void)
+{
+	FILE	   *fp = fopen("/sys/devices/system/clocksource/clocksource0/current_clocksource", "r");
+
+	if (fp)
+	{
+		char		buf[128];
+
+		if (fgets(buf, sizeof(buf), fp) != NULL && strcmp(buf, "tsc\n") == 0)
+		{
+			/*
+			 * Compute baseline CPU peformance, determines speed at which
+			 * RDTSC advances.
+			 */
+			uint32		tsc_freq;
+
+			if (get_tsc_frequency_khz(&tsc_freq))
+			{
+				/*
+				 * Ticks to nanoseconds conversion requires floating point
+				 * math because because:
+				 *
+				 * sec = ticks / frequency_hz ns  = ticks / frequency_hz *
+				 * 1,000,000,000 ns  = ticks * (1,000,000,000 / frequency_hz)
+				 * ns  = ticks * (1,000,000 / frequency_khz) <-- now in
+				 * kilohertz
+				 *
+				 * Here, 'ns' is usually a floating number. For example for a
+				 * 2.5 GHz CPU the scaling factor becomes 1,000,000 /
+				 * 2,500,000 = 1.2.
+				 *
+				 * To be able to use integer math we work around the lack of
+				 * precision. We first scale the integer up and after the
+				 * multiplication by the number of ticks in
+				 * INSTR_TIME_GET_NANOSEC() we divide again by the same value.
+				 * We picked the scaler such that it provides enough precision
+				 * and is a power-of-two which allows for shifting instead of
+				 * doing an integer division.
+				 */
+				ticks_per_ns_scaled = INT64CONST(1000000) * TICKS_TO_NS_PRECISION / tsc_freq;
+				ticks_per_sec = tsc_freq * 1000;	/* KHz->Hz */
+				max_ticks_no_overflow = PG_INT64_MAX / ticks_per_ns_scaled;
+
+				has_rdtsc = true;
+				has_rdtscp = is_rdtscp_available();
+			}
+		}
+
+		fclose(fp);
+	}
+}
+#endif							/* defined(__x86_64__) && defined(__linux__) */
+
+#endif							/* WIN32 */
diff --git a/src/common/meson.build b/src/common/meson.build
index 1540ba67cca..62b90b3e609 100644
--- a/src/common/meson.build
+++ b/src/common/meson.build
@@ -13,6 +13,7 @@ common_sources = files(
   'file_perm.c',
   'file_utils.c',
   'hashfn.c',
+  'instr_time.c',
   'ip.c',
   'jsonapi.c',
   'keywords.c',
diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h
index f71a851b18d..e2e339a0c4f 100644
--- a/src/include/portability/instr_time.h
+++ b/src/include/portability/instr_time.h
@@ -4,9 +4,11 @@
  *	  portable high-precision interval timing
  *
  * This file provides an abstraction layer to hide portability issues in
- * interval timing.  On Unix we use clock_gettime(), and on Windows we use
- * QueryPerformanceCounter().  These macros also give some breathing room to
- * use other high-precision-timing APIs.
+ * interval timing. On Linux/x86 we use the rdtsc instruction when a TSC
+ * clocksource is also used on the host OS.  Otherwise, and on other
+ * Unix-like systems we use clock_gettime() and on Windows we use
+ * QueryPerformanceCounter(). These macros also give some breathing
+ * room to use other high-precision-timing APIs.
  *
  * The basic data type is instr_time, which all callers should treat as an
  * opaque typedef.  instr_time can store either an absolute time (of
@@ -17,10 +19,11 @@
  *
  * INSTR_TIME_SET_ZERO(t)			set t to zero (memset is acceptable too)
  *
- * INSTR_TIME_SET_CURRENT(t)		set t to current time
+ * INSTR_TIME_SET_CURRENT_FAST(t)	set t to current time without waiting
+ * 									for instructions in out-of-order window
  *
- * INSTR_TIME_SET_CURRENT_LAZY(t)	set t to current time if t is zero,
- *									evaluates to whether t changed
+ * INSTR_TIME_SET_CURRENT(t)		set t to current time while waiting for
+ * 									instructions in OOO to retire
  *
  * INSTR_TIME_ADD(x, y)				x += y
  *
@@ -81,6 +84,15 @@ typedef struct instr_time
 
 #ifndef WIN32
 
+/*
+ * Make sure this is a power-of-two, so that the compiler can turn the
+ * multiplications and divisions into shifts.
+ */
+#define TICKS_TO_NS_PRECISION (1<<14)
+
+extern int64 ticks_per_ns_scaled;
+extern int64 ticks_per_sec;
+extern int64 max_ticks_no_overflow;
 
 /* Use clock_gettime() */
 
@@ -106,9 +118,18 @@ typedef struct instr_time
 #define PG_INSTR_CLOCK	CLOCK_REALTIME
 #endif
 
-/* helper for INSTR_TIME_SET_CURRENT */
+#if defined(__x86_64__) && defined(__linux__)
+#include <x86intrin.h>
+#include <cpuid.h>
+
+extern bool has_rdtsc;
+extern bool has_rdtscp;
+
+extern void pg_initialize_rdtsc(void);
+#endif
+
 static inline instr_time
-pg_clock_gettime_ns(void)
+pg_clock_gettime(void)
 {
 	instr_time	now;
 	struct timespec tmp;
@@ -119,11 +140,94 @@ pg_clock_gettime_ns(void)
 	return now;
 }
 
+static inline instr_time
+pg_get_ticks_fast(void)
+{
+#if defined(__x86_64__) && defined(__linux__)
+	if (has_rdtsc)
+	{
+		instr_time	now;
+
+		now.ticks = __rdtsc();
+		return now;
+	}
+#endif
+
+	return pg_clock_gettime();
+}
+
+static inline instr_time
+pg_get_ticks(void)
+{
+#if defined(__x86_64__) && defined(__linux__)
+	if (has_rdtscp)
+	{
+		instr_time	now;
+		uint32		unused;
+
+		now.ticks = __rdtscp(&unused);
+		return now;
+	}
+#endif
+
+	return pg_clock_gettime();
+}
+
+static inline int64_t
+pg_ticks_to_ns(instr_time t)
+{
+	/*
+	 * Would multiplication overflow? If so perform computation in two parts.
+	 * Check overflow without actually overflowing via: a * b > max <=> a >
+	 * max / b
+	 */
+	int64		ns = 0;
+
+	if (unlikely(t.ticks > max_ticks_no_overflow))
+	{
+		/*
+		 * Compute how often the maximum number of ticks fits completely into
+		 * the number of elapsed ticks and convert that number into
+		 * nanoseconds. Then multiply by the count to arrive at the final
+		 * 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		max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION;
+
+		ns = max_ns * count;
+
+		/*
+		 * 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);
+	}
+
+	ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION;
+	return ns;
+}
+
+static inline void
+pg_initialize_get_ticks()
+{
+#if defined(__x86_64__) && defined(__linux__)
+	pg_initialize_rdtsc();
+#endif
+}
+
+#define INSTR_TIME_INITIALIZE() \
+	pg_initialize_get_ticks()
+
+#define INSTR_TIME_SET_CURRENT_FAST(t) \
+	((t) = pg_get_ticks_fast())
+
 #define INSTR_TIME_SET_CURRENT(t) \
-	((t) = pg_clock_gettime_ns())
+	((t) = pg_get_ticks())
 
 #define INSTR_TIME_GET_NANOSEC(t) \
-	((int64) (t).ticks)
+	pg_ticks_to_ns(t)
 
 
 #else							/* WIN32 */
@@ -131,7 +235,7 @@ pg_clock_gettime_ns(void)
 
 /* Use QueryPerformanceCounter() */
 
-/* helper for INSTR_TIME_SET_CURRENT */
+/* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */
 static inline instr_time
 pg_query_performance_counter(void)
 {
@@ -153,6 +257,11 @@ GetTimerFrequency(void)
 	return (double) f.QuadPart;
 }
 
+#define INSTR_TIME_INITIALIZE()
+
+#define INSTR_TIME_SET_CURRENT_FAST(t) \
+	((t) = pg_query_performance_counter())
+
 #define INSTR_TIME_SET_CURRENT(t) \
 	((t) = pg_query_performance_counter())
 
@@ -168,13 +277,8 @@ GetTimerFrequency(void)
 
 #define INSTR_TIME_IS_ZERO(t)	((t).ticks == 0)
 
-
 #define INSTR_TIME_SET_ZERO(t)	((t).ticks = 0)
 
-#define INSTR_TIME_SET_CURRENT_LAZY(t) \
-	(INSTR_TIME_IS_ZERO(t) ? INSTR_TIME_SET_CURRENT(t), true : false)
-
-
 #define INSTR_TIME_ADD(x,y) \
 	((x).ticks += (y).ticks)
 
-- 
2.47.3


--vtqqtrpooseurzip
Content-Type: text/x-diff; charset=utf-8
Content-Disposition: attachment;
	filename="v12-0003-pg_test_timing-Add-fast-flag-to-test-fast-timing.patch"



^ permalink  raw  reply  [nested|flat] 271+ messages in thread

* [PATCH v12 2/3] Use time stamp counter to measure time on Linux/x86
@ 2025-07-26 00:57 Lukas Fittl <[email protected]>
  0 siblings, 0 replies; 271+ messages in thread

From: Lukas Fittl @ 2025-07-26 00:57 UTC (permalink / raw)

We switch to using the time stamp counter (TSC) instead of clock_gettime()
to reduce overhead of EXPLAIN (ANALYZE, TIME ON). Tests showed that runtime
is reduced by around 10% for queries moving lots of rows through the plan.

For now this is only enabled on Linux/x86, in case the system clocksource is
reported as TSC. Relying on the Linux kernel simplifies the logic to detect
if the present TSC is usable (frequency invariant, synchronized between
sockets, etc.). In all other cases we fallback to clock_gettime().

Note, that we intentionally use RDTSC in the fast paths, rather than RDTSCP.
RDTSCP waits for outstanding instructions to retire on out-of-order CPUs.
This adds noticably for little benefit in the typical InstrStartNode() /
InstrStopNode() use case. The macro to be used in such cases is called
INSTR_TIME_SET_CURRENT_FAST(). The original macro INSTR_TIME_SET_CURRENT()
uses RDTSCP and is supposed to be used when precision is more important
than performance.

Author: David Geier <[email protected]>
Author: Andres Freund <[email protected]>
Author: Lukas Fittl <[email protected]>
Reviewed-by:
Discussion: https://www.postgresql.org/message-id/flat/20200612232810.f46nbqkdhbutzqdg%40alap3.anarazel.de
---
 src/backend/access/heap/vacuumlazy.c |   4 +-
 src/backend/executor/instrument.c    |  12 +-
 src/backend/utils/init/postinit.c    |   3 +
 src/bin/pgbench/pgbench.c            |   3 +
 src/bin/psql/startup.c               |   4 +
 src/common/Makefile                  |   1 +
 src/common/instr_time.c              | 206 +++++++++++++++++++++++++++
 src/common/meson.build               |   1 +
 src/include/portability/instr_time.h | 136 +++++++++++++++---
 9 files changed, 348 insertions(+), 22 deletions(-)
 create mode 100644 src/common/instr_time.c

diff --git a/src/backend/access/heap/vacuumlazy.c b/src/backend/access/heap/vacuumlazy.c
index d2b031fdd06..5027048cac4 100644
--- a/src/backend/access/heap/vacuumlazy.c
+++ b/src/backend/access/heap/vacuumlazy.c
@@ -3409,8 +3409,8 @@ count_nondeletable_pages(LVRelState *vacrel, bool *lock_waiter_detected)
 			INSTR_TIME_SET_CURRENT(currenttime);
 			elapsed = currenttime;
 			INSTR_TIME_SUBTRACT(elapsed, starttime);
-			if ((INSTR_TIME_GET_MICROSEC(elapsed) / 1000)
-				>= VACUUM_TRUNCATE_LOCK_CHECK_INTERVAL)
+			if (INSTR_TIME_GET_MILLISEC(elapsed) >=
+				VACUUM_TRUNCATE_LOCK_CHECK_INTERVAL)
 			{
 				if (LockHasWaitersRelation(vacrel->rel, AccessExclusiveLock))
 				{
diff --git a/src/backend/executor/instrument.c b/src/backend/executor/instrument.c
index 56e635f4700..01f67c5d972 100644
--- a/src/backend/executor/instrument.c
+++ b/src/backend/executor/instrument.c
@@ -67,9 +67,13 @@ InstrInit(Instrumentation *instr, int instrument_options)
 void
 InstrStartNode(Instrumentation *instr)
 {
-	if (instr->need_timer &&
-		!INSTR_TIME_SET_CURRENT_LAZY(instr->starttime))
-		elog(ERROR, "InstrStartNode called twice in a row");
+	if (instr->need_timer)
+	{
+		if (!INSTR_TIME_IS_ZERO(instr->starttime))
+			elog(ERROR, "InstrStartNode called twice in a row");
+		else
+			INSTR_TIME_SET_CURRENT_FAST(instr->starttime);
+	}
 
 	/* save buffer usage totals at node entry, if needed */
 	if (instr->need_bufusage)
@@ -95,7 +99,7 @@ InstrStopNode(Instrumentation *instr, double nTuples)
 		if (INSTR_TIME_IS_ZERO(instr->starttime))
 			elog(ERROR, "InstrStopNode called without start");
 
-		INSTR_TIME_SET_CURRENT(endtime);
+		INSTR_TIME_SET_CURRENT_FAST(endtime);
 		INSTR_TIME_ACCUM_DIFF(instr->counter, endtime, instr->starttime);
 
 		INSTR_TIME_SET_ZERO(instr->starttime);
diff --git a/src/backend/utils/init/postinit.c b/src/backend/utils/init/postinit.c
index 641e535a73c..d573409903b 100644
--- a/src/backend/utils/init/postinit.c
+++ b/src/backend/utils/init/postinit.c
@@ -810,6 +810,9 @@ InitPostgres(const char *in_dbname, Oid dboid,
 	/* Initialize portal manager */
 	EnablePortalManager();
 
+	/* initialize high-precision interval timing */
+	INSTR_TIME_INITIALIZE();
+
 	/*
 	 * Load relcache entries for the shared system catalogs.  This must create
 	 * at least entries for pg_database and catalogs used for authentication.
diff --git a/src/bin/pgbench/pgbench.c b/src/bin/pgbench/pgbench.c
index 1515ed405ba..79bef2d2aec 100644
--- a/src/bin/pgbench/pgbench.c
+++ b/src/bin/pgbench/pgbench.c
@@ -7290,6 +7290,9 @@ main(int argc, char **argv)
 		initRandomState(&state[i].cs_func_rs);
 	}
 
+	/* initialize high-precision interval timing */
+	INSTR_TIME_INITIALIZE();
+
 	/* opening connection... */
 	con = doConnect();
 	if (con == NULL)
diff --git a/src/bin/psql/startup.c b/src/bin/psql/startup.c
index 249b6aa5169..d615df593c7 100644
--- a/src/bin/psql/startup.c
+++ b/src/bin/psql/startup.c
@@ -24,6 +24,7 @@
 #include "help.h"
 #include "input.h"
 #include "mainloop.h"
+#include "portability/instr_time.h"
 #include "settings.h"
 
 /*
@@ -327,6 +328,9 @@ main(int argc, char *argv[])
 
 	PQsetNoticeProcessor(pset.db, NoticeProcessor, NULL);
 
+	/* initialize high-precision interval timing */
+	INSTR_TIME_INITIALIZE();
+
 	SyncVariables();
 
 	if (options.list_dbs)
diff --git a/src/common/Makefile b/src/common/Makefile
index 2c720caa509..1a2fbbe887f 100644
--- a/src/common/Makefile
+++ b/src/common/Makefile
@@ -59,6 +59,7 @@ OBJS_COMMON = \
 	file_perm.o \
 	file_utils.o \
 	hashfn.o \
+	instr_time.o \
 	ip.o \
 	jsonapi.o \
 	keywords.o \
diff --git a/src/common/instr_time.c b/src/common/instr_time.c
new file mode 100644
index 00000000000..fdf47699f20
--- /dev/null
+++ b/src/common/instr_time.c
@@ -0,0 +1,206 @@
+/*-------------------------------------------------------------------------
+ *
+ * instr_time.c
+ *	   Non-inline parts of the portable high-precision interval timing
+ *	 implementation
+ *
+ * Portions Copyright (c) 2025, PostgreSQL Global Development Group
+ *
+ *
+ * IDENTIFICATION
+ *	  src/backend/port/instr_time.c
+ *
+ *-------------------------------------------------------------------------
+ */
+#include "postgres.h"
+
+#if defined(HAVE__GET_CPUID) || (defined(HAVE__CPUIDEX) && !defined(_MSC_VER))
+#include <cpuid.h>
+#endif
+
+#if defined(HAVE__CPUID) || (defined(HAVE__CPUIDEX) && defined(_MSC_VER))
+#include <intrin.h>
+#endif
+
+#include "portability/instr_time.h"
+
+#ifndef WIN32
+/*
+ * Stores what the number of cycles needs to be multiplied with to end up
+ * with nanoseconds using integer math. See comment in pg_initialize_rdtsc()
+ * for more details.
+ *
+ * By default assume we are using clock_gettime() as a fallback which uses
+ * nanoseconds as ticks. Hence, we set the multiplier to the precision scalar
+ * so that the division in INSTR_TIME_GET_NANOSEC() won't change the nanoseconds.
+ *
+ * When using the RDTSC instruction directly this is filled in during initialization
+ * based on the relevant CPUID fields.
+ */
+int64		ticks_per_ns_scaled = TICKS_TO_NS_PRECISION;
+int64		ticks_per_sec = NS_PER_S;
+int64		max_ticks_no_overflow = PG_INT64_MAX / TICKS_TO_NS_PRECISION;
+
+#if defined(__x86_64__) && defined(__linux__)
+/*
+ * Indicates if RDTSC can be used (Linux/x86 only, when OS uses TSC clocksource)
+ */
+bool		has_rdtsc = false;
+
+/*
+ * Indicates if RDTSCP can be used. True if RDTSC can be used and RDTSCP is available.
+ */
+bool		has_rdtscp = false;
+
+#define CPUID_HYPERVISOR_VMWARE(words) (words[1] == 0x61774d56 && words[2] == 0x4d566572 && words[3] == 0x65726177) /* VMwareVMware */
+#define CPUID_HYPERVISOR_KVM(words) (words[1] == 0x4b4d564b && words[2] == 0x564b4d56 && words[3] == 0x0000004d)	/* KVMKVMKVM */
+
+static bool
+get_tsc_frequency_khz(uint32 *tsc_freq)
+{
+	uint32		r[4] = {0, 0, 0, 0};
+
+#if defined(HAVE__GET_CPUID)
+	__get_cpuid(0x15, &r[0] /* denominator */ , &r[1] /* numerator */ , &r[2] /* hz */ , &r[3]);
+#elif defined(HAVE__CPUID)
+	__cpuid(r, 0x15);
+#else
+#error cpuid instruction not available
+#endif
+
+	if (r[2] > 0)
+	{
+		if (r[0] == 0 || r[1] == 0)
+			return false;
+
+		*tsc_freq = r[2] / 1000 * r[1] / r[0];
+		return true;
+	}
+
+	/* Some CPUs only report frequency in 16H */
+
+#if defined(HAVE__GET_CPUID)
+	__get_cpuid(0x16, &r[0] /* base_mhz */ , &r[1], &r[2], &r[3]);
+#elif defined(HAVE__CPUID)
+	__cpuid(r, 0x16);
+#else
+#error cpuid instruction not available
+#endif
+
+	if (r[0] > 0)
+	{
+		*tsc_freq = r[0] * 1000;
+		return true;
+	}
+
+	/*
+	 * Check if we have a KVM or VMware Hypervisor passing down TSC frequency
+	 * to us in a guest VM
+	 *
+	 * Note that accessing the 0x40000000 leaf for Hypervisor info requires
+	 * use of __cpuidex to set ECX to 0. The similar __get_cpuid_count
+	 * function does not work as expected since it contains a check for
+	 * __get_cpuid_max, which has been observed to be lower than the special
+	 * Hypervisor leaf.
+	 */
+#if defined(HAVE__CPUIDEX)
+	__cpuidex((int32 *) r, 0x40000000, 0);
+	if (r[0] >= 0x40000010 && (CPUID_HYPERVISOR_VMWARE(r) || CPUID_HYPERVISOR_KVM(r)))
+	{
+		__cpuidex((int32 *) r, 0x40000010, 0);
+		if (r[0] > 0)
+		{
+			*tsc_freq = r[0];
+			return true;
+		}
+	}
+#endif
+
+	return false;
+}
+
+static bool
+is_rdtscp_available()
+{
+	uint32		r[4] = {0, 0, 0, 0};
+
+#if defined(HAVE__GET_CPUID)
+	if (!__get_cpuid(0x80000001, &r[0], &r[1], &r[2], &r[3]))
+		return false;
+#elif defined(HAVE__CPUID)
+	__cpuid(r, 0x80000001);
+#else
+#error cpuid instruction not available
+#endif
+
+	return (r[3] & (1 << 27)) != 0;
+}
+
+/*
+ * Decide whether we use the RDTSC instruction at runtime, for Linux/x86,
+ * instead of incurring the overhead of a full clock_gettime() call.
+ *
+ * This can't be reliably determined at compile time, since the
+ * availability of an "invariant" TSC (that is not affected by CPU
+ * frequency changes) is dependent on the CPU architecture. Additionally,
+ * there are cases where TSC availability is impacted by virtualization,
+ * where a simple cpuid feature check would not be enough.
+ *
+ * Since Linux already does a significant amount of work to determine
+ * whether TSC is a viable clock source, decide based on that.
+ */
+void
+pg_initialize_rdtsc(void)
+{
+	FILE	   *fp = fopen("/sys/devices/system/clocksource/clocksource0/current_clocksource", "r");
+
+	if (fp)
+	{
+		char		buf[128];
+
+		if (fgets(buf, sizeof(buf), fp) != NULL && strcmp(buf, "tsc\n") == 0)
+		{
+			/*
+			 * Compute baseline CPU peformance, determines speed at which
+			 * RDTSC advances.
+			 */
+			uint32		tsc_freq;
+
+			if (get_tsc_frequency_khz(&tsc_freq))
+			{
+				/*
+				 * Ticks to nanoseconds conversion requires floating point
+				 * math because because:
+				 *
+				 * sec = ticks / frequency_hz ns  = ticks / frequency_hz *
+				 * 1,000,000,000 ns  = ticks * (1,000,000,000 / frequency_hz)
+				 * ns  = ticks * (1,000,000 / frequency_khz) <-- now in
+				 * kilohertz
+				 *
+				 * Here, 'ns' is usually a floating number. For example for a
+				 * 2.5 GHz CPU the scaling factor becomes 1,000,000 /
+				 * 2,500,000 = 1.2.
+				 *
+				 * To be able to use integer math we work around the lack of
+				 * precision. We first scale the integer up and after the
+				 * multiplication by the number of ticks in
+				 * INSTR_TIME_GET_NANOSEC() we divide again by the same value.
+				 * We picked the scaler such that it provides enough precision
+				 * and is a power-of-two which allows for shifting instead of
+				 * doing an integer division.
+				 */
+				ticks_per_ns_scaled = INT64CONST(1000000) * TICKS_TO_NS_PRECISION / tsc_freq;
+				ticks_per_sec = tsc_freq * 1000;	/* KHz->Hz */
+				max_ticks_no_overflow = PG_INT64_MAX / ticks_per_ns_scaled;
+
+				has_rdtsc = true;
+				has_rdtscp = is_rdtscp_available();
+			}
+		}
+
+		fclose(fp);
+	}
+}
+#endif							/* defined(__x86_64__) && defined(__linux__) */
+
+#endif							/* WIN32 */
diff --git a/src/common/meson.build b/src/common/meson.build
index 1540ba67cca..62b90b3e609 100644
--- a/src/common/meson.build
+++ b/src/common/meson.build
@@ -13,6 +13,7 @@ common_sources = files(
   'file_perm.c',
   'file_utils.c',
   'hashfn.c',
+  'instr_time.c',
   'ip.c',
   'jsonapi.c',
   'keywords.c',
diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h
index f71a851b18d..e2e339a0c4f 100644
--- a/src/include/portability/instr_time.h
+++ b/src/include/portability/instr_time.h
@@ -4,9 +4,11 @@
  *	  portable high-precision interval timing
  *
  * This file provides an abstraction layer to hide portability issues in
- * interval timing.  On Unix we use clock_gettime(), and on Windows we use
- * QueryPerformanceCounter().  These macros also give some breathing room to
- * use other high-precision-timing APIs.
+ * interval timing. On Linux/x86 we use the rdtsc instruction when a TSC
+ * clocksource is also used on the host OS.  Otherwise, and on other
+ * Unix-like systems we use clock_gettime() and on Windows we use
+ * QueryPerformanceCounter(). These macros also give some breathing
+ * room to use other high-precision-timing APIs.
  *
  * The basic data type is instr_time, which all callers should treat as an
  * opaque typedef.  instr_time can store either an absolute time (of
@@ -17,10 +19,11 @@
  *
  * INSTR_TIME_SET_ZERO(t)			set t to zero (memset is acceptable too)
  *
- * INSTR_TIME_SET_CURRENT(t)		set t to current time
+ * INSTR_TIME_SET_CURRENT_FAST(t)	set t to current time without waiting
+ * 									for instructions in out-of-order window
  *
- * INSTR_TIME_SET_CURRENT_LAZY(t)	set t to current time if t is zero,
- *									evaluates to whether t changed
+ * INSTR_TIME_SET_CURRENT(t)		set t to current time while waiting for
+ * 									instructions in OOO to retire
  *
  * INSTR_TIME_ADD(x, y)				x += y
  *
@@ -81,6 +84,15 @@ typedef struct instr_time
 
 #ifndef WIN32
 
+/*
+ * Make sure this is a power-of-two, so that the compiler can turn the
+ * multiplications and divisions into shifts.
+ */
+#define TICKS_TO_NS_PRECISION (1<<14)
+
+extern int64 ticks_per_ns_scaled;
+extern int64 ticks_per_sec;
+extern int64 max_ticks_no_overflow;
 
 /* Use clock_gettime() */
 
@@ -106,9 +118,18 @@ typedef struct instr_time
 #define PG_INSTR_CLOCK	CLOCK_REALTIME
 #endif
 
-/* helper for INSTR_TIME_SET_CURRENT */
+#if defined(__x86_64__) && defined(__linux__)
+#include <x86intrin.h>
+#include <cpuid.h>
+
+extern bool has_rdtsc;
+extern bool has_rdtscp;
+
+extern void pg_initialize_rdtsc(void);
+#endif
+
 static inline instr_time
-pg_clock_gettime_ns(void)
+pg_clock_gettime(void)
 {
 	instr_time	now;
 	struct timespec tmp;
@@ -119,11 +140,94 @@ pg_clock_gettime_ns(void)
 	return now;
 }
 
+static inline instr_time
+pg_get_ticks_fast(void)
+{
+#if defined(__x86_64__) && defined(__linux__)
+	if (has_rdtsc)
+	{
+		instr_time	now;
+
+		now.ticks = __rdtsc();
+		return now;
+	}
+#endif
+
+	return pg_clock_gettime();
+}
+
+static inline instr_time
+pg_get_ticks(void)
+{
+#if defined(__x86_64__) && defined(__linux__)
+	if (has_rdtscp)
+	{
+		instr_time	now;
+		uint32		unused;
+
+		now.ticks = __rdtscp(&unused);
+		return now;
+	}
+#endif
+
+	return pg_clock_gettime();
+}
+
+static inline int64_t
+pg_ticks_to_ns(instr_time t)
+{
+	/*
+	 * Would multiplication overflow? If so perform computation in two parts.
+	 * Check overflow without actually overflowing via: a * b > max <=> a >
+	 * max / b
+	 */
+	int64		ns = 0;
+
+	if (unlikely(t.ticks > max_ticks_no_overflow))
+	{
+		/*
+		 * Compute how often the maximum number of ticks fits completely into
+		 * the number of elapsed ticks and convert that number into
+		 * nanoseconds. Then multiply by the count to arrive at the final
+		 * 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		max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION;
+
+		ns = max_ns * count;
+
+		/*
+		 * 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);
+	}
+
+	ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION;
+	return ns;
+}
+
+static inline void
+pg_initialize_get_ticks()
+{
+#if defined(__x86_64__) && defined(__linux__)
+	pg_initialize_rdtsc();
+#endif
+}
+
+#define INSTR_TIME_INITIALIZE() \
+	pg_initialize_get_ticks()
+
+#define INSTR_TIME_SET_CURRENT_FAST(t) \
+	((t) = pg_get_ticks_fast())
+
 #define INSTR_TIME_SET_CURRENT(t) \
-	((t) = pg_clock_gettime_ns())
+	((t) = pg_get_ticks())
 
 #define INSTR_TIME_GET_NANOSEC(t) \
-	((int64) (t).ticks)
+	pg_ticks_to_ns(t)
 
 
 #else							/* WIN32 */
@@ -131,7 +235,7 @@ pg_clock_gettime_ns(void)
 
 /* Use QueryPerformanceCounter() */
 
-/* helper for INSTR_TIME_SET_CURRENT */
+/* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */
 static inline instr_time
 pg_query_performance_counter(void)
 {
@@ -153,6 +257,11 @@ GetTimerFrequency(void)
 	return (double) f.QuadPart;
 }
 
+#define INSTR_TIME_INITIALIZE()
+
+#define INSTR_TIME_SET_CURRENT_FAST(t) \
+	((t) = pg_query_performance_counter())
+
 #define INSTR_TIME_SET_CURRENT(t) \
 	((t) = pg_query_performance_counter())
 
@@ -168,13 +277,8 @@ GetTimerFrequency(void)
 
 #define INSTR_TIME_IS_ZERO(t)	((t).ticks == 0)
 
-
 #define INSTR_TIME_SET_ZERO(t)	((t).ticks = 0)
 
-#define INSTR_TIME_SET_CURRENT_LAZY(t) \
-	(INSTR_TIME_IS_ZERO(t) ? INSTR_TIME_SET_CURRENT(t), true : false)
-
-
 #define INSTR_TIME_ADD(x,y) \
 	((x).ticks += (y).ticks)
 
-- 
2.47.3


--vtqqtrpooseurzip
Content-Type: text/x-diff; charset=utf-8
Content-Disposition: attachment;
	filename="v12-0003-pg_test_timing-Add-fast-flag-to-test-fast-timing.patch"



^ permalink  raw  reply  [nested|flat] 271+ messages in thread

* [PATCH v12 2/3] Use time stamp counter to measure time on Linux/x86
@ 2025-07-26 00:57 Lukas Fittl <[email protected]>
  0 siblings, 0 replies; 271+ messages in thread

From: Lukas Fittl @ 2025-07-26 00:57 UTC (permalink / raw)

We switch to using the time stamp counter (TSC) instead of clock_gettime()
to reduce overhead of EXPLAIN (ANALYZE, TIME ON). Tests showed that runtime
is reduced by around 10% for queries moving lots of rows through the plan.

For now this is only enabled on Linux/x86, in case the system clocksource is
reported as TSC. Relying on the Linux kernel simplifies the logic to detect
if the present TSC is usable (frequency invariant, synchronized between
sockets, etc.). In all other cases we fallback to clock_gettime().

Note, that we intentionally use RDTSC in the fast paths, rather than RDTSCP.
RDTSCP waits for outstanding instructions to retire on out-of-order CPUs.
This adds noticably for little benefit in the typical InstrStartNode() /
InstrStopNode() use case. The macro to be used in such cases is called
INSTR_TIME_SET_CURRENT_FAST(). The original macro INSTR_TIME_SET_CURRENT()
uses RDTSCP and is supposed to be used when precision is more important
than performance.

Author: David Geier <[email protected]>
Author: Andres Freund <[email protected]>
Author: Lukas Fittl <[email protected]>
Reviewed-by:
Discussion: https://www.postgresql.org/message-id/flat/20200612232810.f46nbqkdhbutzqdg%40alap3.anarazel.de
---
 src/backend/access/heap/vacuumlazy.c |   4 +-
 src/backend/executor/instrument.c    |  12 +-
 src/backend/utils/init/postinit.c    |   3 +
 src/bin/pgbench/pgbench.c            |   3 +
 src/bin/psql/startup.c               |   4 +
 src/common/Makefile                  |   1 +
 src/common/instr_time.c              | 206 +++++++++++++++++++++++++++
 src/common/meson.build               |   1 +
 src/include/portability/instr_time.h | 136 +++++++++++++++---
 9 files changed, 348 insertions(+), 22 deletions(-)
 create mode 100644 src/common/instr_time.c

diff --git a/src/backend/access/heap/vacuumlazy.c b/src/backend/access/heap/vacuumlazy.c
index d2b031fdd06..5027048cac4 100644
--- a/src/backend/access/heap/vacuumlazy.c
+++ b/src/backend/access/heap/vacuumlazy.c
@@ -3409,8 +3409,8 @@ count_nondeletable_pages(LVRelState *vacrel, bool *lock_waiter_detected)
 			INSTR_TIME_SET_CURRENT(currenttime);
 			elapsed = currenttime;
 			INSTR_TIME_SUBTRACT(elapsed, starttime);
-			if ((INSTR_TIME_GET_MICROSEC(elapsed) / 1000)
-				>= VACUUM_TRUNCATE_LOCK_CHECK_INTERVAL)
+			if (INSTR_TIME_GET_MILLISEC(elapsed) >=
+				VACUUM_TRUNCATE_LOCK_CHECK_INTERVAL)
 			{
 				if (LockHasWaitersRelation(vacrel->rel, AccessExclusiveLock))
 				{
diff --git a/src/backend/executor/instrument.c b/src/backend/executor/instrument.c
index 56e635f4700..01f67c5d972 100644
--- a/src/backend/executor/instrument.c
+++ b/src/backend/executor/instrument.c
@@ -67,9 +67,13 @@ InstrInit(Instrumentation *instr, int instrument_options)
 void
 InstrStartNode(Instrumentation *instr)
 {
-	if (instr->need_timer &&
-		!INSTR_TIME_SET_CURRENT_LAZY(instr->starttime))
-		elog(ERROR, "InstrStartNode called twice in a row");
+	if (instr->need_timer)
+	{
+		if (!INSTR_TIME_IS_ZERO(instr->starttime))
+			elog(ERROR, "InstrStartNode called twice in a row");
+		else
+			INSTR_TIME_SET_CURRENT_FAST(instr->starttime);
+	}
 
 	/* save buffer usage totals at node entry, if needed */
 	if (instr->need_bufusage)
@@ -95,7 +99,7 @@ InstrStopNode(Instrumentation *instr, double nTuples)
 		if (INSTR_TIME_IS_ZERO(instr->starttime))
 			elog(ERROR, "InstrStopNode called without start");
 
-		INSTR_TIME_SET_CURRENT(endtime);
+		INSTR_TIME_SET_CURRENT_FAST(endtime);
 		INSTR_TIME_ACCUM_DIFF(instr->counter, endtime, instr->starttime);
 
 		INSTR_TIME_SET_ZERO(instr->starttime);
diff --git a/src/backend/utils/init/postinit.c b/src/backend/utils/init/postinit.c
index 641e535a73c..d573409903b 100644
--- a/src/backend/utils/init/postinit.c
+++ b/src/backend/utils/init/postinit.c
@@ -810,6 +810,9 @@ InitPostgres(const char *in_dbname, Oid dboid,
 	/* Initialize portal manager */
 	EnablePortalManager();
 
+	/* initialize high-precision interval timing */
+	INSTR_TIME_INITIALIZE();
+
 	/*
 	 * Load relcache entries for the shared system catalogs.  This must create
 	 * at least entries for pg_database and catalogs used for authentication.
diff --git a/src/bin/pgbench/pgbench.c b/src/bin/pgbench/pgbench.c
index 1515ed405ba..79bef2d2aec 100644
--- a/src/bin/pgbench/pgbench.c
+++ b/src/bin/pgbench/pgbench.c
@@ -7290,6 +7290,9 @@ main(int argc, char **argv)
 		initRandomState(&state[i].cs_func_rs);
 	}
 
+	/* initialize high-precision interval timing */
+	INSTR_TIME_INITIALIZE();
+
 	/* opening connection... */
 	con = doConnect();
 	if (con == NULL)
diff --git a/src/bin/psql/startup.c b/src/bin/psql/startup.c
index 249b6aa5169..d615df593c7 100644
--- a/src/bin/psql/startup.c
+++ b/src/bin/psql/startup.c
@@ -24,6 +24,7 @@
 #include "help.h"
 #include "input.h"
 #include "mainloop.h"
+#include "portability/instr_time.h"
 #include "settings.h"
 
 /*
@@ -327,6 +328,9 @@ main(int argc, char *argv[])
 
 	PQsetNoticeProcessor(pset.db, NoticeProcessor, NULL);
 
+	/* initialize high-precision interval timing */
+	INSTR_TIME_INITIALIZE();
+
 	SyncVariables();
 
 	if (options.list_dbs)
diff --git a/src/common/Makefile b/src/common/Makefile
index 2c720caa509..1a2fbbe887f 100644
--- a/src/common/Makefile
+++ b/src/common/Makefile
@@ -59,6 +59,7 @@ OBJS_COMMON = \
 	file_perm.o \
 	file_utils.o \
 	hashfn.o \
+	instr_time.o \
 	ip.o \
 	jsonapi.o \
 	keywords.o \
diff --git a/src/common/instr_time.c b/src/common/instr_time.c
new file mode 100644
index 00000000000..fdf47699f20
--- /dev/null
+++ b/src/common/instr_time.c
@@ -0,0 +1,206 @@
+/*-------------------------------------------------------------------------
+ *
+ * instr_time.c
+ *	   Non-inline parts of the portable high-precision interval timing
+ *	 implementation
+ *
+ * Portions Copyright (c) 2025, PostgreSQL Global Development Group
+ *
+ *
+ * IDENTIFICATION
+ *	  src/backend/port/instr_time.c
+ *
+ *-------------------------------------------------------------------------
+ */
+#include "postgres.h"
+
+#if defined(HAVE__GET_CPUID) || (defined(HAVE__CPUIDEX) && !defined(_MSC_VER))
+#include <cpuid.h>
+#endif
+
+#if defined(HAVE__CPUID) || (defined(HAVE__CPUIDEX) && defined(_MSC_VER))
+#include <intrin.h>
+#endif
+
+#include "portability/instr_time.h"
+
+#ifndef WIN32
+/*
+ * Stores what the number of cycles needs to be multiplied with to end up
+ * with nanoseconds using integer math. See comment in pg_initialize_rdtsc()
+ * for more details.
+ *
+ * By default assume we are using clock_gettime() as a fallback which uses
+ * nanoseconds as ticks. Hence, we set the multiplier to the precision scalar
+ * so that the division in INSTR_TIME_GET_NANOSEC() won't change the nanoseconds.
+ *
+ * When using the RDTSC instruction directly this is filled in during initialization
+ * based on the relevant CPUID fields.
+ */
+int64		ticks_per_ns_scaled = TICKS_TO_NS_PRECISION;
+int64		ticks_per_sec = NS_PER_S;
+int64		max_ticks_no_overflow = PG_INT64_MAX / TICKS_TO_NS_PRECISION;
+
+#if defined(__x86_64__) && defined(__linux__)
+/*
+ * Indicates if RDTSC can be used (Linux/x86 only, when OS uses TSC clocksource)
+ */
+bool		has_rdtsc = false;
+
+/*
+ * Indicates if RDTSCP can be used. True if RDTSC can be used and RDTSCP is available.
+ */
+bool		has_rdtscp = false;
+
+#define CPUID_HYPERVISOR_VMWARE(words) (words[1] == 0x61774d56 && words[2] == 0x4d566572 && words[3] == 0x65726177) /* VMwareVMware */
+#define CPUID_HYPERVISOR_KVM(words) (words[1] == 0x4b4d564b && words[2] == 0x564b4d56 && words[3] == 0x0000004d)	/* KVMKVMKVM */
+
+static bool
+get_tsc_frequency_khz(uint32 *tsc_freq)
+{
+	uint32		r[4] = {0, 0, 0, 0};
+
+#if defined(HAVE__GET_CPUID)
+	__get_cpuid(0x15, &r[0] /* denominator */ , &r[1] /* numerator */ , &r[2] /* hz */ , &r[3]);
+#elif defined(HAVE__CPUID)
+	__cpuid(r, 0x15);
+#else
+#error cpuid instruction not available
+#endif
+
+	if (r[2] > 0)
+	{
+		if (r[0] == 0 || r[1] == 0)
+			return false;
+
+		*tsc_freq = r[2] / 1000 * r[1] / r[0];
+		return true;
+	}
+
+	/* Some CPUs only report frequency in 16H */
+
+#if defined(HAVE__GET_CPUID)
+	__get_cpuid(0x16, &r[0] /* base_mhz */ , &r[1], &r[2], &r[3]);
+#elif defined(HAVE__CPUID)
+	__cpuid(r, 0x16);
+#else
+#error cpuid instruction not available
+#endif
+
+	if (r[0] > 0)
+	{
+		*tsc_freq = r[0] * 1000;
+		return true;
+	}
+
+	/*
+	 * Check if we have a KVM or VMware Hypervisor passing down TSC frequency
+	 * to us in a guest VM
+	 *
+	 * Note that accessing the 0x40000000 leaf for Hypervisor info requires
+	 * use of __cpuidex to set ECX to 0. The similar __get_cpuid_count
+	 * function does not work as expected since it contains a check for
+	 * __get_cpuid_max, which has been observed to be lower than the special
+	 * Hypervisor leaf.
+	 */
+#if defined(HAVE__CPUIDEX)
+	__cpuidex((int32 *) r, 0x40000000, 0);
+	if (r[0] >= 0x40000010 && (CPUID_HYPERVISOR_VMWARE(r) || CPUID_HYPERVISOR_KVM(r)))
+	{
+		__cpuidex((int32 *) r, 0x40000010, 0);
+		if (r[0] > 0)
+		{
+			*tsc_freq = r[0];
+			return true;
+		}
+	}
+#endif
+
+	return false;
+}
+
+static bool
+is_rdtscp_available()
+{
+	uint32		r[4] = {0, 0, 0, 0};
+
+#if defined(HAVE__GET_CPUID)
+	if (!__get_cpuid(0x80000001, &r[0], &r[1], &r[2], &r[3]))
+		return false;
+#elif defined(HAVE__CPUID)
+	__cpuid(r, 0x80000001);
+#else
+#error cpuid instruction not available
+#endif
+
+	return (r[3] & (1 << 27)) != 0;
+}
+
+/*
+ * Decide whether we use the RDTSC instruction at runtime, for Linux/x86,
+ * instead of incurring the overhead of a full clock_gettime() call.
+ *
+ * This can't be reliably determined at compile time, since the
+ * availability of an "invariant" TSC (that is not affected by CPU
+ * frequency changes) is dependent on the CPU architecture. Additionally,
+ * there are cases where TSC availability is impacted by virtualization,
+ * where a simple cpuid feature check would not be enough.
+ *
+ * Since Linux already does a significant amount of work to determine
+ * whether TSC is a viable clock source, decide based on that.
+ */
+void
+pg_initialize_rdtsc(void)
+{
+	FILE	   *fp = fopen("/sys/devices/system/clocksource/clocksource0/current_clocksource", "r");
+
+	if (fp)
+	{
+		char		buf[128];
+
+		if (fgets(buf, sizeof(buf), fp) != NULL && strcmp(buf, "tsc\n") == 0)
+		{
+			/*
+			 * Compute baseline CPU peformance, determines speed at which
+			 * RDTSC advances.
+			 */
+			uint32		tsc_freq;
+
+			if (get_tsc_frequency_khz(&tsc_freq))
+			{
+				/*
+				 * Ticks to nanoseconds conversion requires floating point
+				 * math because because:
+				 *
+				 * sec = ticks / frequency_hz ns  = ticks / frequency_hz *
+				 * 1,000,000,000 ns  = ticks * (1,000,000,000 / frequency_hz)
+				 * ns  = ticks * (1,000,000 / frequency_khz) <-- now in
+				 * kilohertz
+				 *
+				 * Here, 'ns' is usually a floating number. For example for a
+				 * 2.5 GHz CPU the scaling factor becomes 1,000,000 /
+				 * 2,500,000 = 1.2.
+				 *
+				 * To be able to use integer math we work around the lack of
+				 * precision. We first scale the integer up and after the
+				 * multiplication by the number of ticks in
+				 * INSTR_TIME_GET_NANOSEC() we divide again by the same value.
+				 * We picked the scaler such that it provides enough precision
+				 * and is a power-of-two which allows for shifting instead of
+				 * doing an integer division.
+				 */
+				ticks_per_ns_scaled = INT64CONST(1000000) * TICKS_TO_NS_PRECISION / tsc_freq;
+				ticks_per_sec = tsc_freq * 1000;	/* KHz->Hz */
+				max_ticks_no_overflow = PG_INT64_MAX / ticks_per_ns_scaled;
+
+				has_rdtsc = true;
+				has_rdtscp = is_rdtscp_available();
+			}
+		}
+
+		fclose(fp);
+	}
+}
+#endif							/* defined(__x86_64__) && defined(__linux__) */
+
+#endif							/* WIN32 */
diff --git a/src/common/meson.build b/src/common/meson.build
index 1540ba67cca..62b90b3e609 100644
--- a/src/common/meson.build
+++ b/src/common/meson.build
@@ -13,6 +13,7 @@ common_sources = files(
   'file_perm.c',
   'file_utils.c',
   'hashfn.c',
+  'instr_time.c',
   'ip.c',
   'jsonapi.c',
   'keywords.c',
diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h
index f71a851b18d..e2e339a0c4f 100644
--- a/src/include/portability/instr_time.h
+++ b/src/include/portability/instr_time.h
@@ -4,9 +4,11 @@
  *	  portable high-precision interval timing
  *
  * This file provides an abstraction layer to hide portability issues in
- * interval timing.  On Unix we use clock_gettime(), and on Windows we use
- * QueryPerformanceCounter().  These macros also give some breathing room to
- * use other high-precision-timing APIs.
+ * interval timing. On Linux/x86 we use the rdtsc instruction when a TSC
+ * clocksource is also used on the host OS.  Otherwise, and on other
+ * Unix-like systems we use clock_gettime() and on Windows we use
+ * QueryPerformanceCounter(). These macros also give some breathing
+ * room to use other high-precision-timing APIs.
  *
  * The basic data type is instr_time, which all callers should treat as an
  * opaque typedef.  instr_time can store either an absolute time (of
@@ -17,10 +19,11 @@
  *
  * INSTR_TIME_SET_ZERO(t)			set t to zero (memset is acceptable too)
  *
- * INSTR_TIME_SET_CURRENT(t)		set t to current time
+ * INSTR_TIME_SET_CURRENT_FAST(t)	set t to current time without waiting
+ * 									for instructions in out-of-order window
  *
- * INSTR_TIME_SET_CURRENT_LAZY(t)	set t to current time if t is zero,
- *									evaluates to whether t changed
+ * INSTR_TIME_SET_CURRENT(t)		set t to current time while waiting for
+ * 									instructions in OOO to retire
  *
  * INSTR_TIME_ADD(x, y)				x += y
  *
@@ -81,6 +84,15 @@ typedef struct instr_time
 
 #ifndef WIN32
 
+/*
+ * Make sure this is a power-of-two, so that the compiler can turn the
+ * multiplications and divisions into shifts.
+ */
+#define TICKS_TO_NS_PRECISION (1<<14)
+
+extern int64 ticks_per_ns_scaled;
+extern int64 ticks_per_sec;
+extern int64 max_ticks_no_overflow;
 
 /* Use clock_gettime() */
 
@@ -106,9 +118,18 @@ typedef struct instr_time
 #define PG_INSTR_CLOCK	CLOCK_REALTIME
 #endif
 
-/* helper for INSTR_TIME_SET_CURRENT */
+#if defined(__x86_64__) && defined(__linux__)
+#include <x86intrin.h>
+#include <cpuid.h>
+
+extern bool has_rdtsc;
+extern bool has_rdtscp;
+
+extern void pg_initialize_rdtsc(void);
+#endif
+
 static inline instr_time
-pg_clock_gettime_ns(void)
+pg_clock_gettime(void)
 {
 	instr_time	now;
 	struct timespec tmp;
@@ -119,11 +140,94 @@ pg_clock_gettime_ns(void)
 	return now;
 }
 
+static inline instr_time
+pg_get_ticks_fast(void)
+{
+#if defined(__x86_64__) && defined(__linux__)
+	if (has_rdtsc)
+	{
+		instr_time	now;
+
+		now.ticks = __rdtsc();
+		return now;
+	}
+#endif
+
+	return pg_clock_gettime();
+}
+
+static inline instr_time
+pg_get_ticks(void)
+{
+#if defined(__x86_64__) && defined(__linux__)
+	if (has_rdtscp)
+	{
+		instr_time	now;
+		uint32		unused;
+
+		now.ticks = __rdtscp(&unused);
+		return now;
+	}
+#endif
+
+	return pg_clock_gettime();
+}
+
+static inline int64_t
+pg_ticks_to_ns(instr_time t)
+{
+	/*
+	 * Would multiplication overflow? If so perform computation in two parts.
+	 * Check overflow without actually overflowing via: a * b > max <=> a >
+	 * max / b
+	 */
+	int64		ns = 0;
+
+	if (unlikely(t.ticks > max_ticks_no_overflow))
+	{
+		/*
+		 * Compute how often the maximum number of ticks fits completely into
+		 * the number of elapsed ticks and convert that number into
+		 * nanoseconds. Then multiply by the count to arrive at the final
+		 * 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		max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION;
+
+		ns = max_ns * count;
+
+		/*
+		 * 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);
+	}
+
+	ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION;
+	return ns;
+}
+
+static inline void
+pg_initialize_get_ticks()
+{
+#if defined(__x86_64__) && defined(__linux__)
+	pg_initialize_rdtsc();
+#endif
+}
+
+#define INSTR_TIME_INITIALIZE() \
+	pg_initialize_get_ticks()
+
+#define INSTR_TIME_SET_CURRENT_FAST(t) \
+	((t) = pg_get_ticks_fast())
+
 #define INSTR_TIME_SET_CURRENT(t) \
-	((t) = pg_clock_gettime_ns())
+	((t) = pg_get_ticks())
 
 #define INSTR_TIME_GET_NANOSEC(t) \
-	((int64) (t).ticks)
+	pg_ticks_to_ns(t)
 
 
 #else							/* WIN32 */
@@ -131,7 +235,7 @@ pg_clock_gettime_ns(void)
 
 /* Use QueryPerformanceCounter() */
 
-/* helper for INSTR_TIME_SET_CURRENT */
+/* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */
 static inline instr_time
 pg_query_performance_counter(void)
 {
@@ -153,6 +257,11 @@ GetTimerFrequency(void)
 	return (double) f.QuadPart;
 }
 
+#define INSTR_TIME_INITIALIZE()
+
+#define INSTR_TIME_SET_CURRENT_FAST(t) \
+	((t) = pg_query_performance_counter())
+
 #define INSTR_TIME_SET_CURRENT(t) \
 	((t) = pg_query_performance_counter())
 
@@ -168,13 +277,8 @@ GetTimerFrequency(void)
 
 #define INSTR_TIME_IS_ZERO(t)	((t).ticks == 0)
 
-
 #define INSTR_TIME_SET_ZERO(t)	((t).ticks = 0)
 
-#define INSTR_TIME_SET_CURRENT_LAZY(t) \
-	(INSTR_TIME_IS_ZERO(t) ? INSTR_TIME_SET_CURRENT(t), true : false)
-
-
 #define INSTR_TIME_ADD(x,y) \
 	((x).ticks += (y).ticks)
 
-- 
2.47.3


--vtqqtrpooseurzip
Content-Type: text/x-diff; charset=utf-8
Content-Disposition: attachment;
	filename="v12-0003-pg_test_timing-Add-fast-flag-to-test-fast-timing.patch"



^ permalink  raw  reply  [nested|flat] 271+ messages in thread

* [PATCH v12 2/3] Use time stamp counter to measure time on Linux/x86
@ 2025-07-26 00:57 Lukas Fittl <[email protected]>
  0 siblings, 0 replies; 271+ messages in thread

From: Lukas Fittl @ 2025-07-26 00:57 UTC (permalink / raw)

We switch to using the time stamp counter (TSC) instead of clock_gettime()
to reduce overhead of EXPLAIN (ANALYZE, TIME ON). Tests showed that runtime
is reduced by around 10% for queries moving lots of rows through the plan.

For now this is only enabled on Linux/x86, in case the system clocksource is
reported as TSC. Relying on the Linux kernel simplifies the logic to detect
if the present TSC is usable (frequency invariant, synchronized between
sockets, etc.). In all other cases we fallback to clock_gettime().

Note, that we intentionally use RDTSC in the fast paths, rather than RDTSCP.
RDTSCP waits for outstanding instructions to retire on out-of-order CPUs.
This adds noticably for little benefit in the typical InstrStartNode() /
InstrStopNode() use case. The macro to be used in such cases is called
INSTR_TIME_SET_CURRENT_FAST(). The original macro INSTR_TIME_SET_CURRENT()
uses RDTSCP and is supposed to be used when precision is more important
than performance.

Author: David Geier <[email protected]>
Author: Andres Freund <[email protected]>
Author: Lukas Fittl <[email protected]>
Reviewed-by:
Discussion: https://www.postgresql.org/message-id/flat/20200612232810.f46nbqkdhbutzqdg%40alap3.anarazel.de
---
 src/backend/access/heap/vacuumlazy.c |   4 +-
 src/backend/executor/instrument.c    |  12 +-
 src/backend/utils/init/postinit.c    |   3 +
 src/bin/pgbench/pgbench.c            |   3 +
 src/bin/psql/startup.c               |   4 +
 src/common/Makefile                  |   1 +
 src/common/instr_time.c              | 206 +++++++++++++++++++++++++++
 src/common/meson.build               |   1 +
 src/include/portability/instr_time.h | 136 +++++++++++++++---
 9 files changed, 348 insertions(+), 22 deletions(-)
 create mode 100644 src/common/instr_time.c

diff --git a/src/backend/access/heap/vacuumlazy.c b/src/backend/access/heap/vacuumlazy.c
index d2b031fdd06..5027048cac4 100644
--- a/src/backend/access/heap/vacuumlazy.c
+++ b/src/backend/access/heap/vacuumlazy.c
@@ -3409,8 +3409,8 @@ count_nondeletable_pages(LVRelState *vacrel, bool *lock_waiter_detected)
 			INSTR_TIME_SET_CURRENT(currenttime);
 			elapsed = currenttime;
 			INSTR_TIME_SUBTRACT(elapsed, starttime);
-			if ((INSTR_TIME_GET_MICROSEC(elapsed) / 1000)
-				>= VACUUM_TRUNCATE_LOCK_CHECK_INTERVAL)
+			if (INSTR_TIME_GET_MILLISEC(elapsed) >=
+				VACUUM_TRUNCATE_LOCK_CHECK_INTERVAL)
 			{
 				if (LockHasWaitersRelation(vacrel->rel, AccessExclusiveLock))
 				{
diff --git a/src/backend/executor/instrument.c b/src/backend/executor/instrument.c
index 56e635f4700..01f67c5d972 100644
--- a/src/backend/executor/instrument.c
+++ b/src/backend/executor/instrument.c
@@ -67,9 +67,13 @@ InstrInit(Instrumentation *instr, int instrument_options)
 void
 InstrStartNode(Instrumentation *instr)
 {
-	if (instr->need_timer &&
-		!INSTR_TIME_SET_CURRENT_LAZY(instr->starttime))
-		elog(ERROR, "InstrStartNode called twice in a row");
+	if (instr->need_timer)
+	{
+		if (!INSTR_TIME_IS_ZERO(instr->starttime))
+			elog(ERROR, "InstrStartNode called twice in a row");
+		else
+			INSTR_TIME_SET_CURRENT_FAST(instr->starttime);
+	}
 
 	/* save buffer usage totals at node entry, if needed */
 	if (instr->need_bufusage)
@@ -95,7 +99,7 @@ InstrStopNode(Instrumentation *instr, double nTuples)
 		if (INSTR_TIME_IS_ZERO(instr->starttime))
 			elog(ERROR, "InstrStopNode called without start");
 
-		INSTR_TIME_SET_CURRENT(endtime);
+		INSTR_TIME_SET_CURRENT_FAST(endtime);
 		INSTR_TIME_ACCUM_DIFF(instr->counter, endtime, instr->starttime);
 
 		INSTR_TIME_SET_ZERO(instr->starttime);
diff --git a/src/backend/utils/init/postinit.c b/src/backend/utils/init/postinit.c
index 641e535a73c..d573409903b 100644
--- a/src/backend/utils/init/postinit.c
+++ b/src/backend/utils/init/postinit.c
@@ -810,6 +810,9 @@ InitPostgres(const char *in_dbname, Oid dboid,
 	/* Initialize portal manager */
 	EnablePortalManager();
 
+	/* initialize high-precision interval timing */
+	INSTR_TIME_INITIALIZE();
+
 	/*
 	 * Load relcache entries for the shared system catalogs.  This must create
 	 * at least entries for pg_database and catalogs used for authentication.
diff --git a/src/bin/pgbench/pgbench.c b/src/bin/pgbench/pgbench.c
index 1515ed405ba..79bef2d2aec 100644
--- a/src/bin/pgbench/pgbench.c
+++ b/src/bin/pgbench/pgbench.c
@@ -7290,6 +7290,9 @@ main(int argc, char **argv)
 		initRandomState(&state[i].cs_func_rs);
 	}
 
+	/* initialize high-precision interval timing */
+	INSTR_TIME_INITIALIZE();
+
 	/* opening connection... */
 	con = doConnect();
 	if (con == NULL)
diff --git a/src/bin/psql/startup.c b/src/bin/psql/startup.c
index 249b6aa5169..d615df593c7 100644
--- a/src/bin/psql/startup.c
+++ b/src/bin/psql/startup.c
@@ -24,6 +24,7 @@
 #include "help.h"
 #include "input.h"
 #include "mainloop.h"
+#include "portability/instr_time.h"
 #include "settings.h"
 
 /*
@@ -327,6 +328,9 @@ main(int argc, char *argv[])
 
 	PQsetNoticeProcessor(pset.db, NoticeProcessor, NULL);
 
+	/* initialize high-precision interval timing */
+	INSTR_TIME_INITIALIZE();
+
 	SyncVariables();
 
 	if (options.list_dbs)
diff --git a/src/common/Makefile b/src/common/Makefile
index 2c720caa509..1a2fbbe887f 100644
--- a/src/common/Makefile
+++ b/src/common/Makefile
@@ -59,6 +59,7 @@ OBJS_COMMON = \
 	file_perm.o \
 	file_utils.o \
 	hashfn.o \
+	instr_time.o \
 	ip.o \
 	jsonapi.o \
 	keywords.o \
diff --git a/src/common/instr_time.c b/src/common/instr_time.c
new file mode 100644
index 00000000000..fdf47699f20
--- /dev/null
+++ b/src/common/instr_time.c
@@ -0,0 +1,206 @@
+/*-------------------------------------------------------------------------
+ *
+ * instr_time.c
+ *	   Non-inline parts of the portable high-precision interval timing
+ *	 implementation
+ *
+ * Portions Copyright (c) 2025, PostgreSQL Global Development Group
+ *
+ *
+ * IDENTIFICATION
+ *	  src/backend/port/instr_time.c
+ *
+ *-------------------------------------------------------------------------
+ */
+#include "postgres.h"
+
+#if defined(HAVE__GET_CPUID) || (defined(HAVE__CPUIDEX) && !defined(_MSC_VER))
+#include <cpuid.h>
+#endif
+
+#if defined(HAVE__CPUID) || (defined(HAVE__CPUIDEX) && defined(_MSC_VER))
+#include <intrin.h>
+#endif
+
+#include "portability/instr_time.h"
+
+#ifndef WIN32
+/*
+ * Stores what the number of cycles needs to be multiplied with to end up
+ * with nanoseconds using integer math. See comment in pg_initialize_rdtsc()
+ * for more details.
+ *
+ * By default assume we are using clock_gettime() as a fallback which uses
+ * nanoseconds as ticks. Hence, we set the multiplier to the precision scalar
+ * so that the division in INSTR_TIME_GET_NANOSEC() won't change the nanoseconds.
+ *
+ * When using the RDTSC instruction directly this is filled in during initialization
+ * based on the relevant CPUID fields.
+ */
+int64		ticks_per_ns_scaled = TICKS_TO_NS_PRECISION;
+int64		ticks_per_sec = NS_PER_S;
+int64		max_ticks_no_overflow = PG_INT64_MAX / TICKS_TO_NS_PRECISION;
+
+#if defined(__x86_64__) && defined(__linux__)
+/*
+ * Indicates if RDTSC can be used (Linux/x86 only, when OS uses TSC clocksource)
+ */
+bool		has_rdtsc = false;
+
+/*
+ * Indicates if RDTSCP can be used. True if RDTSC can be used and RDTSCP is available.
+ */
+bool		has_rdtscp = false;
+
+#define CPUID_HYPERVISOR_VMWARE(words) (words[1] == 0x61774d56 && words[2] == 0x4d566572 && words[3] == 0x65726177) /* VMwareVMware */
+#define CPUID_HYPERVISOR_KVM(words) (words[1] == 0x4b4d564b && words[2] == 0x564b4d56 && words[3] == 0x0000004d)	/* KVMKVMKVM */
+
+static bool
+get_tsc_frequency_khz(uint32 *tsc_freq)
+{
+	uint32		r[4] = {0, 0, 0, 0};
+
+#if defined(HAVE__GET_CPUID)
+	__get_cpuid(0x15, &r[0] /* denominator */ , &r[1] /* numerator */ , &r[2] /* hz */ , &r[3]);
+#elif defined(HAVE__CPUID)
+	__cpuid(r, 0x15);
+#else
+#error cpuid instruction not available
+#endif
+
+	if (r[2] > 0)
+	{
+		if (r[0] == 0 || r[1] == 0)
+			return false;
+
+		*tsc_freq = r[2] / 1000 * r[1] / r[0];
+		return true;
+	}
+
+	/* Some CPUs only report frequency in 16H */
+
+#if defined(HAVE__GET_CPUID)
+	__get_cpuid(0x16, &r[0] /* base_mhz */ , &r[1], &r[2], &r[3]);
+#elif defined(HAVE__CPUID)
+	__cpuid(r, 0x16);
+#else
+#error cpuid instruction not available
+#endif
+
+	if (r[0] > 0)
+	{
+		*tsc_freq = r[0] * 1000;
+		return true;
+	}
+
+	/*
+	 * Check if we have a KVM or VMware Hypervisor passing down TSC frequency
+	 * to us in a guest VM
+	 *
+	 * Note that accessing the 0x40000000 leaf for Hypervisor info requires
+	 * use of __cpuidex to set ECX to 0. The similar __get_cpuid_count
+	 * function does not work as expected since it contains a check for
+	 * __get_cpuid_max, which has been observed to be lower than the special
+	 * Hypervisor leaf.
+	 */
+#if defined(HAVE__CPUIDEX)
+	__cpuidex((int32 *) r, 0x40000000, 0);
+	if (r[0] >= 0x40000010 && (CPUID_HYPERVISOR_VMWARE(r) || CPUID_HYPERVISOR_KVM(r)))
+	{
+		__cpuidex((int32 *) r, 0x40000010, 0);
+		if (r[0] > 0)
+		{
+			*tsc_freq = r[0];
+			return true;
+		}
+	}
+#endif
+
+	return false;
+}
+
+static bool
+is_rdtscp_available()
+{
+	uint32		r[4] = {0, 0, 0, 0};
+
+#if defined(HAVE__GET_CPUID)
+	if (!__get_cpuid(0x80000001, &r[0], &r[1], &r[2], &r[3]))
+		return false;
+#elif defined(HAVE__CPUID)
+	__cpuid(r, 0x80000001);
+#else
+#error cpuid instruction not available
+#endif
+
+	return (r[3] & (1 << 27)) != 0;
+}
+
+/*
+ * Decide whether we use the RDTSC instruction at runtime, for Linux/x86,
+ * instead of incurring the overhead of a full clock_gettime() call.
+ *
+ * This can't be reliably determined at compile time, since the
+ * availability of an "invariant" TSC (that is not affected by CPU
+ * frequency changes) is dependent on the CPU architecture. Additionally,
+ * there are cases where TSC availability is impacted by virtualization,
+ * where a simple cpuid feature check would not be enough.
+ *
+ * Since Linux already does a significant amount of work to determine
+ * whether TSC is a viable clock source, decide based on that.
+ */
+void
+pg_initialize_rdtsc(void)
+{
+	FILE	   *fp = fopen("/sys/devices/system/clocksource/clocksource0/current_clocksource", "r");
+
+	if (fp)
+	{
+		char		buf[128];
+
+		if (fgets(buf, sizeof(buf), fp) != NULL && strcmp(buf, "tsc\n") == 0)
+		{
+			/*
+			 * Compute baseline CPU peformance, determines speed at which
+			 * RDTSC advances.
+			 */
+			uint32		tsc_freq;
+
+			if (get_tsc_frequency_khz(&tsc_freq))
+			{
+				/*
+				 * Ticks to nanoseconds conversion requires floating point
+				 * math because because:
+				 *
+				 * sec = ticks / frequency_hz ns  = ticks / frequency_hz *
+				 * 1,000,000,000 ns  = ticks * (1,000,000,000 / frequency_hz)
+				 * ns  = ticks * (1,000,000 / frequency_khz) <-- now in
+				 * kilohertz
+				 *
+				 * Here, 'ns' is usually a floating number. For example for a
+				 * 2.5 GHz CPU the scaling factor becomes 1,000,000 /
+				 * 2,500,000 = 1.2.
+				 *
+				 * To be able to use integer math we work around the lack of
+				 * precision. We first scale the integer up and after the
+				 * multiplication by the number of ticks in
+				 * INSTR_TIME_GET_NANOSEC() we divide again by the same value.
+				 * We picked the scaler such that it provides enough precision
+				 * and is a power-of-two which allows for shifting instead of
+				 * doing an integer division.
+				 */
+				ticks_per_ns_scaled = INT64CONST(1000000) * TICKS_TO_NS_PRECISION / tsc_freq;
+				ticks_per_sec = tsc_freq * 1000;	/* KHz->Hz */
+				max_ticks_no_overflow = PG_INT64_MAX / ticks_per_ns_scaled;
+
+				has_rdtsc = true;
+				has_rdtscp = is_rdtscp_available();
+			}
+		}
+
+		fclose(fp);
+	}
+}
+#endif							/* defined(__x86_64__) && defined(__linux__) */
+
+#endif							/* WIN32 */
diff --git a/src/common/meson.build b/src/common/meson.build
index 1540ba67cca..62b90b3e609 100644
--- a/src/common/meson.build
+++ b/src/common/meson.build
@@ -13,6 +13,7 @@ common_sources = files(
   'file_perm.c',
   'file_utils.c',
   'hashfn.c',
+  'instr_time.c',
   'ip.c',
   'jsonapi.c',
   'keywords.c',
diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h
index f71a851b18d..e2e339a0c4f 100644
--- a/src/include/portability/instr_time.h
+++ b/src/include/portability/instr_time.h
@@ -4,9 +4,11 @@
  *	  portable high-precision interval timing
  *
  * This file provides an abstraction layer to hide portability issues in
- * interval timing.  On Unix we use clock_gettime(), and on Windows we use
- * QueryPerformanceCounter().  These macros also give some breathing room to
- * use other high-precision-timing APIs.
+ * interval timing. On Linux/x86 we use the rdtsc instruction when a TSC
+ * clocksource is also used on the host OS.  Otherwise, and on other
+ * Unix-like systems we use clock_gettime() and on Windows we use
+ * QueryPerformanceCounter(). These macros also give some breathing
+ * room to use other high-precision-timing APIs.
  *
  * The basic data type is instr_time, which all callers should treat as an
  * opaque typedef.  instr_time can store either an absolute time (of
@@ -17,10 +19,11 @@
  *
  * INSTR_TIME_SET_ZERO(t)			set t to zero (memset is acceptable too)
  *
- * INSTR_TIME_SET_CURRENT(t)		set t to current time
+ * INSTR_TIME_SET_CURRENT_FAST(t)	set t to current time without waiting
+ * 									for instructions in out-of-order window
  *
- * INSTR_TIME_SET_CURRENT_LAZY(t)	set t to current time if t is zero,
- *									evaluates to whether t changed
+ * INSTR_TIME_SET_CURRENT(t)		set t to current time while waiting for
+ * 									instructions in OOO to retire
  *
  * INSTR_TIME_ADD(x, y)				x += y
  *
@@ -81,6 +84,15 @@ typedef struct instr_time
 
 #ifndef WIN32
 
+/*
+ * Make sure this is a power-of-two, so that the compiler can turn the
+ * multiplications and divisions into shifts.
+ */
+#define TICKS_TO_NS_PRECISION (1<<14)
+
+extern int64 ticks_per_ns_scaled;
+extern int64 ticks_per_sec;
+extern int64 max_ticks_no_overflow;
 
 /* Use clock_gettime() */
 
@@ -106,9 +118,18 @@ typedef struct instr_time
 #define PG_INSTR_CLOCK	CLOCK_REALTIME
 #endif
 
-/* helper for INSTR_TIME_SET_CURRENT */
+#if defined(__x86_64__) && defined(__linux__)
+#include <x86intrin.h>
+#include <cpuid.h>
+
+extern bool has_rdtsc;
+extern bool has_rdtscp;
+
+extern void pg_initialize_rdtsc(void);
+#endif
+
 static inline instr_time
-pg_clock_gettime_ns(void)
+pg_clock_gettime(void)
 {
 	instr_time	now;
 	struct timespec tmp;
@@ -119,11 +140,94 @@ pg_clock_gettime_ns(void)
 	return now;
 }
 
+static inline instr_time
+pg_get_ticks_fast(void)
+{
+#if defined(__x86_64__) && defined(__linux__)
+	if (has_rdtsc)
+	{
+		instr_time	now;
+
+		now.ticks = __rdtsc();
+		return now;
+	}
+#endif
+
+	return pg_clock_gettime();
+}
+
+static inline instr_time
+pg_get_ticks(void)
+{
+#if defined(__x86_64__) && defined(__linux__)
+	if (has_rdtscp)
+	{
+		instr_time	now;
+		uint32		unused;
+
+		now.ticks = __rdtscp(&unused);
+		return now;
+	}
+#endif
+
+	return pg_clock_gettime();
+}
+
+static inline int64_t
+pg_ticks_to_ns(instr_time t)
+{
+	/*
+	 * Would multiplication overflow? If so perform computation in two parts.
+	 * Check overflow without actually overflowing via: a * b > max <=> a >
+	 * max / b
+	 */
+	int64		ns = 0;
+
+	if (unlikely(t.ticks > max_ticks_no_overflow))
+	{
+		/*
+		 * Compute how often the maximum number of ticks fits completely into
+		 * the number of elapsed ticks and convert that number into
+		 * nanoseconds. Then multiply by the count to arrive at the final
+		 * 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		max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION;
+
+		ns = max_ns * count;
+
+		/*
+		 * 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);
+	}
+
+	ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION;
+	return ns;
+}
+
+static inline void
+pg_initialize_get_ticks()
+{
+#if defined(__x86_64__) && defined(__linux__)
+	pg_initialize_rdtsc();
+#endif
+}
+
+#define INSTR_TIME_INITIALIZE() \
+	pg_initialize_get_ticks()
+
+#define INSTR_TIME_SET_CURRENT_FAST(t) \
+	((t) = pg_get_ticks_fast())
+
 #define INSTR_TIME_SET_CURRENT(t) \
-	((t) = pg_clock_gettime_ns())
+	((t) = pg_get_ticks())
 
 #define INSTR_TIME_GET_NANOSEC(t) \
-	((int64) (t).ticks)
+	pg_ticks_to_ns(t)
 
 
 #else							/* WIN32 */
@@ -131,7 +235,7 @@ pg_clock_gettime_ns(void)
 
 /* Use QueryPerformanceCounter() */
 
-/* helper for INSTR_TIME_SET_CURRENT */
+/* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */
 static inline instr_time
 pg_query_performance_counter(void)
 {
@@ -153,6 +257,11 @@ GetTimerFrequency(void)
 	return (double) f.QuadPart;
 }
 
+#define INSTR_TIME_INITIALIZE()
+
+#define INSTR_TIME_SET_CURRENT_FAST(t) \
+	((t) = pg_query_performance_counter())
+
 #define INSTR_TIME_SET_CURRENT(t) \
 	((t) = pg_query_performance_counter())
 
@@ -168,13 +277,8 @@ GetTimerFrequency(void)
 
 #define INSTR_TIME_IS_ZERO(t)	((t).ticks == 0)
 
-
 #define INSTR_TIME_SET_ZERO(t)	((t).ticks = 0)
 
-#define INSTR_TIME_SET_CURRENT_LAZY(t) \
-	(INSTR_TIME_IS_ZERO(t) ? INSTR_TIME_SET_CURRENT(t), true : false)
-
-
 #define INSTR_TIME_ADD(x,y) \
 	((x).ticks += (y).ticks)
 
-- 
2.47.3


--vtqqtrpooseurzip
Content-Type: text/x-diff; charset=utf-8
Content-Disposition: attachment;
	filename="v12-0003-pg_test_timing-Add-fast-flag-to-test-fast-timing.patch"



^ permalink  raw  reply  [nested|flat] 271+ messages in thread

* [PATCH v12 2/3] Use time stamp counter to measure time on Linux/x86
@ 2025-07-26 00:57 Lukas Fittl <[email protected]>
  0 siblings, 0 replies; 271+ messages in thread

From: Lukas Fittl @ 2025-07-26 00:57 UTC (permalink / raw)

We switch to using the time stamp counter (TSC) instead of clock_gettime()
to reduce overhead of EXPLAIN (ANALYZE, TIME ON). Tests showed that runtime
is reduced by around 10% for queries moving lots of rows through the plan.

For now this is only enabled on Linux/x86, in case the system clocksource is
reported as TSC. Relying on the Linux kernel simplifies the logic to detect
if the present TSC is usable (frequency invariant, synchronized between
sockets, etc.). In all other cases we fallback to clock_gettime().

Note, that we intentionally use RDTSC in the fast paths, rather than RDTSCP.
RDTSCP waits for outstanding instructions to retire on out-of-order CPUs.
This adds noticably for little benefit in the typical InstrStartNode() /
InstrStopNode() use case. The macro to be used in such cases is called
INSTR_TIME_SET_CURRENT_FAST(). The original macro INSTR_TIME_SET_CURRENT()
uses RDTSCP and is supposed to be used when precision is more important
than performance.

Author: David Geier <[email protected]>
Author: Andres Freund <[email protected]>
Author: Lukas Fittl <[email protected]>
Reviewed-by:
Discussion: https://www.postgresql.org/message-id/flat/20200612232810.f46nbqkdhbutzqdg%40alap3.anarazel.de
---
 src/backend/access/heap/vacuumlazy.c |   4 +-
 src/backend/executor/instrument.c    |  12 +-
 src/backend/utils/init/postinit.c    |   3 +
 src/bin/pgbench/pgbench.c            |   3 +
 src/bin/psql/startup.c               |   4 +
 src/common/Makefile                  |   1 +
 src/common/instr_time.c              | 206 +++++++++++++++++++++++++++
 src/common/meson.build               |   1 +
 src/include/portability/instr_time.h | 136 +++++++++++++++---
 9 files changed, 348 insertions(+), 22 deletions(-)
 create mode 100644 src/common/instr_time.c

diff --git a/src/backend/access/heap/vacuumlazy.c b/src/backend/access/heap/vacuumlazy.c
index d2b031fdd06..5027048cac4 100644
--- a/src/backend/access/heap/vacuumlazy.c
+++ b/src/backend/access/heap/vacuumlazy.c
@@ -3409,8 +3409,8 @@ count_nondeletable_pages(LVRelState *vacrel, bool *lock_waiter_detected)
 			INSTR_TIME_SET_CURRENT(currenttime);
 			elapsed = currenttime;
 			INSTR_TIME_SUBTRACT(elapsed, starttime);
-			if ((INSTR_TIME_GET_MICROSEC(elapsed) / 1000)
-				>= VACUUM_TRUNCATE_LOCK_CHECK_INTERVAL)
+			if (INSTR_TIME_GET_MILLISEC(elapsed) >=
+				VACUUM_TRUNCATE_LOCK_CHECK_INTERVAL)
 			{
 				if (LockHasWaitersRelation(vacrel->rel, AccessExclusiveLock))
 				{
diff --git a/src/backend/executor/instrument.c b/src/backend/executor/instrument.c
index 56e635f4700..01f67c5d972 100644
--- a/src/backend/executor/instrument.c
+++ b/src/backend/executor/instrument.c
@@ -67,9 +67,13 @@ InstrInit(Instrumentation *instr, int instrument_options)
 void
 InstrStartNode(Instrumentation *instr)
 {
-	if (instr->need_timer &&
-		!INSTR_TIME_SET_CURRENT_LAZY(instr->starttime))
-		elog(ERROR, "InstrStartNode called twice in a row");
+	if (instr->need_timer)
+	{
+		if (!INSTR_TIME_IS_ZERO(instr->starttime))
+			elog(ERROR, "InstrStartNode called twice in a row");
+		else
+			INSTR_TIME_SET_CURRENT_FAST(instr->starttime);
+	}
 
 	/* save buffer usage totals at node entry, if needed */
 	if (instr->need_bufusage)
@@ -95,7 +99,7 @@ InstrStopNode(Instrumentation *instr, double nTuples)
 		if (INSTR_TIME_IS_ZERO(instr->starttime))
 			elog(ERROR, "InstrStopNode called without start");
 
-		INSTR_TIME_SET_CURRENT(endtime);
+		INSTR_TIME_SET_CURRENT_FAST(endtime);
 		INSTR_TIME_ACCUM_DIFF(instr->counter, endtime, instr->starttime);
 
 		INSTR_TIME_SET_ZERO(instr->starttime);
diff --git a/src/backend/utils/init/postinit.c b/src/backend/utils/init/postinit.c
index 641e535a73c..d573409903b 100644
--- a/src/backend/utils/init/postinit.c
+++ b/src/backend/utils/init/postinit.c
@@ -810,6 +810,9 @@ InitPostgres(const char *in_dbname, Oid dboid,
 	/* Initialize portal manager */
 	EnablePortalManager();
 
+	/* initialize high-precision interval timing */
+	INSTR_TIME_INITIALIZE();
+
 	/*
 	 * Load relcache entries for the shared system catalogs.  This must create
 	 * at least entries for pg_database and catalogs used for authentication.
diff --git a/src/bin/pgbench/pgbench.c b/src/bin/pgbench/pgbench.c
index 1515ed405ba..79bef2d2aec 100644
--- a/src/bin/pgbench/pgbench.c
+++ b/src/bin/pgbench/pgbench.c
@@ -7290,6 +7290,9 @@ main(int argc, char **argv)
 		initRandomState(&state[i].cs_func_rs);
 	}
 
+	/* initialize high-precision interval timing */
+	INSTR_TIME_INITIALIZE();
+
 	/* opening connection... */
 	con = doConnect();
 	if (con == NULL)
diff --git a/src/bin/psql/startup.c b/src/bin/psql/startup.c
index 249b6aa5169..d615df593c7 100644
--- a/src/bin/psql/startup.c
+++ b/src/bin/psql/startup.c
@@ -24,6 +24,7 @@
 #include "help.h"
 #include "input.h"
 #include "mainloop.h"
+#include "portability/instr_time.h"
 #include "settings.h"
 
 /*
@@ -327,6 +328,9 @@ main(int argc, char *argv[])
 
 	PQsetNoticeProcessor(pset.db, NoticeProcessor, NULL);
 
+	/* initialize high-precision interval timing */
+	INSTR_TIME_INITIALIZE();
+
 	SyncVariables();
 
 	if (options.list_dbs)
diff --git a/src/common/Makefile b/src/common/Makefile
index 2c720caa509..1a2fbbe887f 100644
--- a/src/common/Makefile
+++ b/src/common/Makefile
@@ -59,6 +59,7 @@ OBJS_COMMON = \
 	file_perm.o \
 	file_utils.o \
 	hashfn.o \
+	instr_time.o \
 	ip.o \
 	jsonapi.o \
 	keywords.o \
diff --git a/src/common/instr_time.c b/src/common/instr_time.c
new file mode 100644
index 00000000000..fdf47699f20
--- /dev/null
+++ b/src/common/instr_time.c
@@ -0,0 +1,206 @@
+/*-------------------------------------------------------------------------
+ *
+ * instr_time.c
+ *	   Non-inline parts of the portable high-precision interval timing
+ *	 implementation
+ *
+ * Portions Copyright (c) 2025, PostgreSQL Global Development Group
+ *
+ *
+ * IDENTIFICATION
+ *	  src/backend/port/instr_time.c
+ *
+ *-------------------------------------------------------------------------
+ */
+#include "postgres.h"
+
+#if defined(HAVE__GET_CPUID) || (defined(HAVE__CPUIDEX) && !defined(_MSC_VER))
+#include <cpuid.h>
+#endif
+
+#if defined(HAVE__CPUID) || (defined(HAVE__CPUIDEX) && defined(_MSC_VER))
+#include <intrin.h>
+#endif
+
+#include "portability/instr_time.h"
+
+#ifndef WIN32
+/*
+ * Stores what the number of cycles needs to be multiplied with to end up
+ * with nanoseconds using integer math. See comment in pg_initialize_rdtsc()
+ * for more details.
+ *
+ * By default assume we are using clock_gettime() as a fallback which uses
+ * nanoseconds as ticks. Hence, we set the multiplier to the precision scalar
+ * so that the division in INSTR_TIME_GET_NANOSEC() won't change the nanoseconds.
+ *
+ * When using the RDTSC instruction directly this is filled in during initialization
+ * based on the relevant CPUID fields.
+ */
+int64		ticks_per_ns_scaled = TICKS_TO_NS_PRECISION;
+int64		ticks_per_sec = NS_PER_S;
+int64		max_ticks_no_overflow = PG_INT64_MAX / TICKS_TO_NS_PRECISION;
+
+#if defined(__x86_64__) && defined(__linux__)
+/*
+ * Indicates if RDTSC can be used (Linux/x86 only, when OS uses TSC clocksource)
+ */
+bool		has_rdtsc = false;
+
+/*
+ * Indicates if RDTSCP can be used. True if RDTSC can be used and RDTSCP is available.
+ */
+bool		has_rdtscp = false;
+
+#define CPUID_HYPERVISOR_VMWARE(words) (words[1] == 0x61774d56 && words[2] == 0x4d566572 && words[3] == 0x65726177) /* VMwareVMware */
+#define CPUID_HYPERVISOR_KVM(words) (words[1] == 0x4b4d564b && words[2] == 0x564b4d56 && words[3] == 0x0000004d)	/* KVMKVMKVM */
+
+static bool
+get_tsc_frequency_khz(uint32 *tsc_freq)
+{
+	uint32		r[4] = {0, 0, 0, 0};
+
+#if defined(HAVE__GET_CPUID)
+	__get_cpuid(0x15, &r[0] /* denominator */ , &r[1] /* numerator */ , &r[2] /* hz */ , &r[3]);
+#elif defined(HAVE__CPUID)
+	__cpuid(r, 0x15);
+#else
+#error cpuid instruction not available
+#endif
+
+	if (r[2] > 0)
+	{
+		if (r[0] == 0 || r[1] == 0)
+			return false;
+
+		*tsc_freq = r[2] / 1000 * r[1] / r[0];
+		return true;
+	}
+
+	/* Some CPUs only report frequency in 16H */
+
+#if defined(HAVE__GET_CPUID)
+	__get_cpuid(0x16, &r[0] /* base_mhz */ , &r[1], &r[2], &r[3]);
+#elif defined(HAVE__CPUID)
+	__cpuid(r, 0x16);
+#else
+#error cpuid instruction not available
+#endif
+
+	if (r[0] > 0)
+	{
+		*tsc_freq = r[0] * 1000;
+		return true;
+	}
+
+	/*
+	 * Check if we have a KVM or VMware Hypervisor passing down TSC frequency
+	 * to us in a guest VM
+	 *
+	 * Note that accessing the 0x40000000 leaf for Hypervisor info requires
+	 * use of __cpuidex to set ECX to 0. The similar __get_cpuid_count
+	 * function does not work as expected since it contains a check for
+	 * __get_cpuid_max, which has been observed to be lower than the special
+	 * Hypervisor leaf.
+	 */
+#if defined(HAVE__CPUIDEX)
+	__cpuidex((int32 *) r, 0x40000000, 0);
+	if (r[0] >= 0x40000010 && (CPUID_HYPERVISOR_VMWARE(r) || CPUID_HYPERVISOR_KVM(r)))
+	{
+		__cpuidex((int32 *) r, 0x40000010, 0);
+		if (r[0] > 0)
+		{
+			*tsc_freq = r[0];
+			return true;
+		}
+	}
+#endif
+
+	return false;
+}
+
+static bool
+is_rdtscp_available()
+{
+	uint32		r[4] = {0, 0, 0, 0};
+
+#if defined(HAVE__GET_CPUID)
+	if (!__get_cpuid(0x80000001, &r[0], &r[1], &r[2], &r[3]))
+		return false;
+#elif defined(HAVE__CPUID)
+	__cpuid(r, 0x80000001);
+#else
+#error cpuid instruction not available
+#endif
+
+	return (r[3] & (1 << 27)) != 0;
+}
+
+/*
+ * Decide whether we use the RDTSC instruction at runtime, for Linux/x86,
+ * instead of incurring the overhead of a full clock_gettime() call.
+ *
+ * This can't be reliably determined at compile time, since the
+ * availability of an "invariant" TSC (that is not affected by CPU
+ * frequency changes) is dependent on the CPU architecture. Additionally,
+ * there are cases where TSC availability is impacted by virtualization,
+ * where a simple cpuid feature check would not be enough.
+ *
+ * Since Linux already does a significant amount of work to determine
+ * whether TSC is a viable clock source, decide based on that.
+ */
+void
+pg_initialize_rdtsc(void)
+{
+	FILE	   *fp = fopen("/sys/devices/system/clocksource/clocksource0/current_clocksource", "r");
+
+	if (fp)
+	{
+		char		buf[128];
+
+		if (fgets(buf, sizeof(buf), fp) != NULL && strcmp(buf, "tsc\n") == 0)
+		{
+			/*
+			 * Compute baseline CPU peformance, determines speed at which
+			 * RDTSC advances.
+			 */
+			uint32		tsc_freq;
+
+			if (get_tsc_frequency_khz(&tsc_freq))
+			{
+				/*
+				 * Ticks to nanoseconds conversion requires floating point
+				 * math because because:
+				 *
+				 * sec = ticks / frequency_hz ns  = ticks / frequency_hz *
+				 * 1,000,000,000 ns  = ticks * (1,000,000,000 / frequency_hz)
+				 * ns  = ticks * (1,000,000 / frequency_khz) <-- now in
+				 * kilohertz
+				 *
+				 * Here, 'ns' is usually a floating number. For example for a
+				 * 2.5 GHz CPU the scaling factor becomes 1,000,000 /
+				 * 2,500,000 = 1.2.
+				 *
+				 * To be able to use integer math we work around the lack of
+				 * precision. We first scale the integer up and after the
+				 * multiplication by the number of ticks in
+				 * INSTR_TIME_GET_NANOSEC() we divide again by the same value.
+				 * We picked the scaler such that it provides enough precision
+				 * and is a power-of-two which allows for shifting instead of
+				 * doing an integer division.
+				 */
+				ticks_per_ns_scaled = INT64CONST(1000000) * TICKS_TO_NS_PRECISION / tsc_freq;
+				ticks_per_sec = tsc_freq * 1000;	/* KHz->Hz */
+				max_ticks_no_overflow = PG_INT64_MAX / ticks_per_ns_scaled;
+
+				has_rdtsc = true;
+				has_rdtscp = is_rdtscp_available();
+			}
+		}
+
+		fclose(fp);
+	}
+}
+#endif							/* defined(__x86_64__) && defined(__linux__) */
+
+#endif							/* WIN32 */
diff --git a/src/common/meson.build b/src/common/meson.build
index 1540ba67cca..62b90b3e609 100644
--- a/src/common/meson.build
+++ b/src/common/meson.build
@@ -13,6 +13,7 @@ common_sources = files(
   'file_perm.c',
   'file_utils.c',
   'hashfn.c',
+  'instr_time.c',
   'ip.c',
   'jsonapi.c',
   'keywords.c',
diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h
index f71a851b18d..e2e339a0c4f 100644
--- a/src/include/portability/instr_time.h
+++ b/src/include/portability/instr_time.h
@@ -4,9 +4,11 @@
  *	  portable high-precision interval timing
  *
  * This file provides an abstraction layer to hide portability issues in
- * interval timing.  On Unix we use clock_gettime(), and on Windows we use
- * QueryPerformanceCounter().  These macros also give some breathing room to
- * use other high-precision-timing APIs.
+ * interval timing. On Linux/x86 we use the rdtsc instruction when a TSC
+ * clocksource is also used on the host OS.  Otherwise, and on other
+ * Unix-like systems we use clock_gettime() and on Windows we use
+ * QueryPerformanceCounter(). These macros also give some breathing
+ * room to use other high-precision-timing APIs.
  *
  * The basic data type is instr_time, which all callers should treat as an
  * opaque typedef.  instr_time can store either an absolute time (of
@@ -17,10 +19,11 @@
  *
  * INSTR_TIME_SET_ZERO(t)			set t to zero (memset is acceptable too)
  *
- * INSTR_TIME_SET_CURRENT(t)		set t to current time
+ * INSTR_TIME_SET_CURRENT_FAST(t)	set t to current time without waiting
+ * 									for instructions in out-of-order window
  *
- * INSTR_TIME_SET_CURRENT_LAZY(t)	set t to current time if t is zero,
- *									evaluates to whether t changed
+ * INSTR_TIME_SET_CURRENT(t)		set t to current time while waiting for
+ * 									instructions in OOO to retire
  *
  * INSTR_TIME_ADD(x, y)				x += y
  *
@@ -81,6 +84,15 @@ typedef struct instr_time
 
 #ifndef WIN32
 
+/*
+ * Make sure this is a power-of-two, so that the compiler can turn the
+ * multiplications and divisions into shifts.
+ */
+#define TICKS_TO_NS_PRECISION (1<<14)
+
+extern int64 ticks_per_ns_scaled;
+extern int64 ticks_per_sec;
+extern int64 max_ticks_no_overflow;
 
 /* Use clock_gettime() */
 
@@ -106,9 +118,18 @@ typedef struct instr_time
 #define PG_INSTR_CLOCK	CLOCK_REALTIME
 #endif
 
-/* helper for INSTR_TIME_SET_CURRENT */
+#if defined(__x86_64__) && defined(__linux__)
+#include <x86intrin.h>
+#include <cpuid.h>
+
+extern bool has_rdtsc;
+extern bool has_rdtscp;
+
+extern void pg_initialize_rdtsc(void);
+#endif
+
 static inline instr_time
-pg_clock_gettime_ns(void)
+pg_clock_gettime(void)
 {
 	instr_time	now;
 	struct timespec tmp;
@@ -119,11 +140,94 @@ pg_clock_gettime_ns(void)
 	return now;
 }
 
+static inline instr_time
+pg_get_ticks_fast(void)
+{
+#if defined(__x86_64__) && defined(__linux__)
+	if (has_rdtsc)
+	{
+		instr_time	now;
+
+		now.ticks = __rdtsc();
+		return now;
+	}
+#endif
+
+	return pg_clock_gettime();
+}
+
+static inline instr_time
+pg_get_ticks(void)
+{
+#if defined(__x86_64__) && defined(__linux__)
+	if (has_rdtscp)
+	{
+		instr_time	now;
+		uint32		unused;
+
+		now.ticks = __rdtscp(&unused);
+		return now;
+	}
+#endif
+
+	return pg_clock_gettime();
+}
+
+static inline int64_t
+pg_ticks_to_ns(instr_time t)
+{
+	/*
+	 * Would multiplication overflow? If so perform computation in two parts.
+	 * Check overflow without actually overflowing via: a * b > max <=> a >
+	 * max / b
+	 */
+	int64		ns = 0;
+
+	if (unlikely(t.ticks > max_ticks_no_overflow))
+	{
+		/*
+		 * Compute how often the maximum number of ticks fits completely into
+		 * the number of elapsed ticks and convert that number into
+		 * nanoseconds. Then multiply by the count to arrive at the final
+		 * 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		max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION;
+
+		ns = max_ns * count;
+
+		/*
+		 * 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);
+	}
+
+	ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION;
+	return ns;
+}
+
+static inline void
+pg_initialize_get_ticks()
+{
+#if defined(__x86_64__) && defined(__linux__)
+	pg_initialize_rdtsc();
+#endif
+}
+
+#define INSTR_TIME_INITIALIZE() \
+	pg_initialize_get_ticks()
+
+#define INSTR_TIME_SET_CURRENT_FAST(t) \
+	((t) = pg_get_ticks_fast())
+
 #define INSTR_TIME_SET_CURRENT(t) \
-	((t) = pg_clock_gettime_ns())
+	((t) = pg_get_ticks())
 
 #define INSTR_TIME_GET_NANOSEC(t) \
-	((int64) (t).ticks)
+	pg_ticks_to_ns(t)
 
 
 #else							/* WIN32 */
@@ -131,7 +235,7 @@ pg_clock_gettime_ns(void)
 
 /* Use QueryPerformanceCounter() */
 
-/* helper for INSTR_TIME_SET_CURRENT */
+/* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */
 static inline instr_time
 pg_query_performance_counter(void)
 {
@@ -153,6 +257,11 @@ GetTimerFrequency(void)
 	return (double) f.QuadPart;
 }
 
+#define INSTR_TIME_INITIALIZE()
+
+#define INSTR_TIME_SET_CURRENT_FAST(t) \
+	((t) = pg_query_performance_counter())
+
 #define INSTR_TIME_SET_CURRENT(t) \
 	((t) = pg_query_performance_counter())
 
@@ -168,13 +277,8 @@ GetTimerFrequency(void)
 
 #define INSTR_TIME_IS_ZERO(t)	((t).ticks == 0)
 
-
 #define INSTR_TIME_SET_ZERO(t)	((t).ticks = 0)
 
-#define INSTR_TIME_SET_CURRENT_LAZY(t) \
-	(INSTR_TIME_IS_ZERO(t) ? INSTR_TIME_SET_CURRENT(t), true : false)
-
-
 #define INSTR_TIME_ADD(x,y) \
 	((x).ticks += (y).ticks)
 
-- 
2.47.3


--vtqqtrpooseurzip
Content-Type: text/x-diff; charset=utf-8
Content-Disposition: attachment;
	filename="v12-0003-pg_test_timing-Add-fast-flag-to-test-fast-timing.patch"



^ permalink  raw  reply  [nested|flat] 271+ messages in thread

* [PATCH v12 2/3] Use time stamp counter to measure time on Linux/x86
@ 2025-07-26 00:57 Lukas Fittl <[email protected]>
  0 siblings, 0 replies; 271+ messages in thread

From: Lukas Fittl @ 2025-07-26 00:57 UTC (permalink / raw)

We switch to using the time stamp counter (TSC) instead of clock_gettime()
to reduce overhead of EXPLAIN (ANALYZE, TIME ON). Tests showed that runtime
is reduced by around 10% for queries moving lots of rows through the plan.

For now this is only enabled on Linux/x86, in case the system clocksource is
reported as TSC. Relying on the Linux kernel simplifies the logic to detect
if the present TSC is usable (frequency invariant, synchronized between
sockets, etc.). In all other cases we fallback to clock_gettime().

Note, that we intentionally use RDTSC in the fast paths, rather than RDTSCP.
RDTSCP waits for outstanding instructions to retire on out-of-order CPUs.
This adds noticably for little benefit in the typical InstrStartNode() /
InstrStopNode() use case. The macro to be used in such cases is called
INSTR_TIME_SET_CURRENT_FAST(). The original macro INSTR_TIME_SET_CURRENT()
uses RDTSCP and is supposed to be used when precision is more important
than performance.

Author: David Geier <[email protected]>
Author: Andres Freund <[email protected]>
Author: Lukas Fittl <[email protected]>
Reviewed-by:
Discussion: https://www.postgresql.org/message-id/flat/20200612232810.f46nbqkdhbutzqdg%40alap3.anarazel.de
---
 src/backend/access/heap/vacuumlazy.c |   4 +-
 src/backend/executor/instrument.c    |  12 +-
 src/backend/utils/init/postinit.c    |   3 +
 src/bin/pgbench/pgbench.c            |   3 +
 src/bin/psql/startup.c               |   4 +
 src/common/Makefile                  |   1 +
 src/common/instr_time.c              | 206 +++++++++++++++++++++++++++
 src/common/meson.build               |   1 +
 src/include/portability/instr_time.h | 136 +++++++++++++++---
 9 files changed, 348 insertions(+), 22 deletions(-)
 create mode 100644 src/common/instr_time.c

diff --git a/src/backend/access/heap/vacuumlazy.c b/src/backend/access/heap/vacuumlazy.c
index d2b031fdd06..5027048cac4 100644
--- a/src/backend/access/heap/vacuumlazy.c
+++ b/src/backend/access/heap/vacuumlazy.c
@@ -3409,8 +3409,8 @@ count_nondeletable_pages(LVRelState *vacrel, bool *lock_waiter_detected)
 			INSTR_TIME_SET_CURRENT(currenttime);
 			elapsed = currenttime;
 			INSTR_TIME_SUBTRACT(elapsed, starttime);
-			if ((INSTR_TIME_GET_MICROSEC(elapsed) / 1000)
-				>= VACUUM_TRUNCATE_LOCK_CHECK_INTERVAL)
+			if (INSTR_TIME_GET_MILLISEC(elapsed) >=
+				VACUUM_TRUNCATE_LOCK_CHECK_INTERVAL)
 			{
 				if (LockHasWaitersRelation(vacrel->rel, AccessExclusiveLock))
 				{
diff --git a/src/backend/executor/instrument.c b/src/backend/executor/instrument.c
index 56e635f4700..01f67c5d972 100644
--- a/src/backend/executor/instrument.c
+++ b/src/backend/executor/instrument.c
@@ -67,9 +67,13 @@ InstrInit(Instrumentation *instr, int instrument_options)
 void
 InstrStartNode(Instrumentation *instr)
 {
-	if (instr->need_timer &&
-		!INSTR_TIME_SET_CURRENT_LAZY(instr->starttime))
-		elog(ERROR, "InstrStartNode called twice in a row");
+	if (instr->need_timer)
+	{
+		if (!INSTR_TIME_IS_ZERO(instr->starttime))
+			elog(ERROR, "InstrStartNode called twice in a row");
+		else
+			INSTR_TIME_SET_CURRENT_FAST(instr->starttime);
+	}
 
 	/* save buffer usage totals at node entry, if needed */
 	if (instr->need_bufusage)
@@ -95,7 +99,7 @@ InstrStopNode(Instrumentation *instr, double nTuples)
 		if (INSTR_TIME_IS_ZERO(instr->starttime))
 			elog(ERROR, "InstrStopNode called without start");
 
-		INSTR_TIME_SET_CURRENT(endtime);
+		INSTR_TIME_SET_CURRENT_FAST(endtime);
 		INSTR_TIME_ACCUM_DIFF(instr->counter, endtime, instr->starttime);
 
 		INSTR_TIME_SET_ZERO(instr->starttime);
diff --git a/src/backend/utils/init/postinit.c b/src/backend/utils/init/postinit.c
index 641e535a73c..d573409903b 100644
--- a/src/backend/utils/init/postinit.c
+++ b/src/backend/utils/init/postinit.c
@@ -810,6 +810,9 @@ InitPostgres(const char *in_dbname, Oid dboid,
 	/* Initialize portal manager */
 	EnablePortalManager();
 
+	/* initialize high-precision interval timing */
+	INSTR_TIME_INITIALIZE();
+
 	/*
 	 * Load relcache entries for the shared system catalogs.  This must create
 	 * at least entries for pg_database and catalogs used for authentication.
diff --git a/src/bin/pgbench/pgbench.c b/src/bin/pgbench/pgbench.c
index 1515ed405ba..79bef2d2aec 100644
--- a/src/bin/pgbench/pgbench.c
+++ b/src/bin/pgbench/pgbench.c
@@ -7290,6 +7290,9 @@ main(int argc, char **argv)
 		initRandomState(&state[i].cs_func_rs);
 	}
 
+	/* initialize high-precision interval timing */
+	INSTR_TIME_INITIALIZE();
+
 	/* opening connection... */
 	con = doConnect();
 	if (con == NULL)
diff --git a/src/bin/psql/startup.c b/src/bin/psql/startup.c
index 249b6aa5169..d615df593c7 100644
--- a/src/bin/psql/startup.c
+++ b/src/bin/psql/startup.c
@@ -24,6 +24,7 @@
 #include "help.h"
 #include "input.h"
 #include "mainloop.h"
+#include "portability/instr_time.h"
 #include "settings.h"
 
 /*
@@ -327,6 +328,9 @@ main(int argc, char *argv[])
 
 	PQsetNoticeProcessor(pset.db, NoticeProcessor, NULL);
 
+	/* initialize high-precision interval timing */
+	INSTR_TIME_INITIALIZE();
+
 	SyncVariables();
 
 	if (options.list_dbs)
diff --git a/src/common/Makefile b/src/common/Makefile
index 2c720caa509..1a2fbbe887f 100644
--- a/src/common/Makefile
+++ b/src/common/Makefile
@@ -59,6 +59,7 @@ OBJS_COMMON = \
 	file_perm.o \
 	file_utils.o \
 	hashfn.o \
+	instr_time.o \
 	ip.o \
 	jsonapi.o \
 	keywords.o \
diff --git a/src/common/instr_time.c b/src/common/instr_time.c
new file mode 100644
index 00000000000..fdf47699f20
--- /dev/null
+++ b/src/common/instr_time.c
@@ -0,0 +1,206 @@
+/*-------------------------------------------------------------------------
+ *
+ * instr_time.c
+ *	   Non-inline parts of the portable high-precision interval timing
+ *	 implementation
+ *
+ * Portions Copyright (c) 2025, PostgreSQL Global Development Group
+ *
+ *
+ * IDENTIFICATION
+ *	  src/backend/port/instr_time.c
+ *
+ *-------------------------------------------------------------------------
+ */
+#include "postgres.h"
+
+#if defined(HAVE__GET_CPUID) || (defined(HAVE__CPUIDEX) && !defined(_MSC_VER))
+#include <cpuid.h>
+#endif
+
+#if defined(HAVE__CPUID) || (defined(HAVE__CPUIDEX) && defined(_MSC_VER))
+#include <intrin.h>
+#endif
+
+#include "portability/instr_time.h"
+
+#ifndef WIN32
+/*
+ * Stores what the number of cycles needs to be multiplied with to end up
+ * with nanoseconds using integer math. See comment in pg_initialize_rdtsc()
+ * for more details.
+ *
+ * By default assume we are using clock_gettime() as a fallback which uses
+ * nanoseconds as ticks. Hence, we set the multiplier to the precision scalar
+ * so that the division in INSTR_TIME_GET_NANOSEC() won't change the nanoseconds.
+ *
+ * When using the RDTSC instruction directly this is filled in during initialization
+ * based on the relevant CPUID fields.
+ */
+int64		ticks_per_ns_scaled = TICKS_TO_NS_PRECISION;
+int64		ticks_per_sec = NS_PER_S;
+int64		max_ticks_no_overflow = PG_INT64_MAX / TICKS_TO_NS_PRECISION;
+
+#if defined(__x86_64__) && defined(__linux__)
+/*
+ * Indicates if RDTSC can be used (Linux/x86 only, when OS uses TSC clocksource)
+ */
+bool		has_rdtsc = false;
+
+/*
+ * Indicates if RDTSCP can be used. True if RDTSC can be used and RDTSCP is available.
+ */
+bool		has_rdtscp = false;
+
+#define CPUID_HYPERVISOR_VMWARE(words) (words[1] == 0x61774d56 && words[2] == 0x4d566572 && words[3] == 0x65726177) /* VMwareVMware */
+#define CPUID_HYPERVISOR_KVM(words) (words[1] == 0x4b4d564b && words[2] == 0x564b4d56 && words[3] == 0x0000004d)	/* KVMKVMKVM */
+
+static bool
+get_tsc_frequency_khz(uint32 *tsc_freq)
+{
+	uint32		r[4] = {0, 0, 0, 0};
+
+#if defined(HAVE__GET_CPUID)
+	__get_cpuid(0x15, &r[0] /* denominator */ , &r[1] /* numerator */ , &r[2] /* hz */ , &r[3]);
+#elif defined(HAVE__CPUID)
+	__cpuid(r, 0x15);
+#else
+#error cpuid instruction not available
+#endif
+
+	if (r[2] > 0)
+	{
+		if (r[0] == 0 || r[1] == 0)
+			return false;
+
+		*tsc_freq = r[2] / 1000 * r[1] / r[0];
+		return true;
+	}
+
+	/* Some CPUs only report frequency in 16H */
+
+#if defined(HAVE__GET_CPUID)
+	__get_cpuid(0x16, &r[0] /* base_mhz */ , &r[1], &r[2], &r[3]);
+#elif defined(HAVE__CPUID)
+	__cpuid(r, 0x16);
+#else
+#error cpuid instruction not available
+#endif
+
+	if (r[0] > 0)
+	{
+		*tsc_freq = r[0] * 1000;
+		return true;
+	}
+
+	/*
+	 * Check if we have a KVM or VMware Hypervisor passing down TSC frequency
+	 * to us in a guest VM
+	 *
+	 * Note that accessing the 0x40000000 leaf for Hypervisor info requires
+	 * use of __cpuidex to set ECX to 0. The similar __get_cpuid_count
+	 * function does not work as expected since it contains a check for
+	 * __get_cpuid_max, which has been observed to be lower than the special
+	 * Hypervisor leaf.
+	 */
+#if defined(HAVE__CPUIDEX)
+	__cpuidex((int32 *) r, 0x40000000, 0);
+	if (r[0] >= 0x40000010 && (CPUID_HYPERVISOR_VMWARE(r) || CPUID_HYPERVISOR_KVM(r)))
+	{
+		__cpuidex((int32 *) r, 0x40000010, 0);
+		if (r[0] > 0)
+		{
+			*tsc_freq = r[0];
+			return true;
+		}
+	}
+#endif
+
+	return false;
+}
+
+static bool
+is_rdtscp_available()
+{
+	uint32		r[4] = {0, 0, 0, 0};
+
+#if defined(HAVE__GET_CPUID)
+	if (!__get_cpuid(0x80000001, &r[0], &r[1], &r[2], &r[3]))
+		return false;
+#elif defined(HAVE__CPUID)
+	__cpuid(r, 0x80000001);
+#else
+#error cpuid instruction not available
+#endif
+
+	return (r[3] & (1 << 27)) != 0;
+}
+
+/*
+ * Decide whether we use the RDTSC instruction at runtime, for Linux/x86,
+ * instead of incurring the overhead of a full clock_gettime() call.
+ *
+ * This can't be reliably determined at compile time, since the
+ * availability of an "invariant" TSC (that is not affected by CPU
+ * frequency changes) is dependent on the CPU architecture. Additionally,
+ * there are cases where TSC availability is impacted by virtualization,
+ * where a simple cpuid feature check would not be enough.
+ *
+ * Since Linux already does a significant amount of work to determine
+ * whether TSC is a viable clock source, decide based on that.
+ */
+void
+pg_initialize_rdtsc(void)
+{
+	FILE	   *fp = fopen("/sys/devices/system/clocksource/clocksource0/current_clocksource", "r");
+
+	if (fp)
+	{
+		char		buf[128];
+
+		if (fgets(buf, sizeof(buf), fp) != NULL && strcmp(buf, "tsc\n") == 0)
+		{
+			/*
+			 * Compute baseline CPU peformance, determines speed at which
+			 * RDTSC advances.
+			 */
+			uint32		tsc_freq;
+
+			if (get_tsc_frequency_khz(&tsc_freq))
+			{
+				/*
+				 * Ticks to nanoseconds conversion requires floating point
+				 * math because because:
+				 *
+				 * sec = ticks / frequency_hz ns  = ticks / frequency_hz *
+				 * 1,000,000,000 ns  = ticks * (1,000,000,000 / frequency_hz)
+				 * ns  = ticks * (1,000,000 / frequency_khz) <-- now in
+				 * kilohertz
+				 *
+				 * Here, 'ns' is usually a floating number. For example for a
+				 * 2.5 GHz CPU the scaling factor becomes 1,000,000 /
+				 * 2,500,000 = 1.2.
+				 *
+				 * To be able to use integer math we work around the lack of
+				 * precision. We first scale the integer up and after the
+				 * multiplication by the number of ticks in
+				 * INSTR_TIME_GET_NANOSEC() we divide again by the same value.
+				 * We picked the scaler such that it provides enough precision
+				 * and is a power-of-two which allows for shifting instead of
+				 * doing an integer division.
+				 */
+				ticks_per_ns_scaled = INT64CONST(1000000) * TICKS_TO_NS_PRECISION / tsc_freq;
+				ticks_per_sec = tsc_freq * 1000;	/* KHz->Hz */
+				max_ticks_no_overflow = PG_INT64_MAX / ticks_per_ns_scaled;
+
+				has_rdtsc = true;
+				has_rdtscp = is_rdtscp_available();
+			}
+		}
+
+		fclose(fp);
+	}
+}
+#endif							/* defined(__x86_64__) && defined(__linux__) */
+
+#endif							/* WIN32 */
diff --git a/src/common/meson.build b/src/common/meson.build
index 1540ba67cca..62b90b3e609 100644
--- a/src/common/meson.build
+++ b/src/common/meson.build
@@ -13,6 +13,7 @@ common_sources = files(
   'file_perm.c',
   'file_utils.c',
   'hashfn.c',
+  'instr_time.c',
   'ip.c',
   'jsonapi.c',
   'keywords.c',
diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h
index f71a851b18d..e2e339a0c4f 100644
--- a/src/include/portability/instr_time.h
+++ b/src/include/portability/instr_time.h
@@ -4,9 +4,11 @@
  *	  portable high-precision interval timing
  *
  * This file provides an abstraction layer to hide portability issues in
- * interval timing.  On Unix we use clock_gettime(), and on Windows we use
- * QueryPerformanceCounter().  These macros also give some breathing room to
- * use other high-precision-timing APIs.
+ * interval timing. On Linux/x86 we use the rdtsc instruction when a TSC
+ * clocksource is also used on the host OS.  Otherwise, and on other
+ * Unix-like systems we use clock_gettime() and on Windows we use
+ * QueryPerformanceCounter(). These macros also give some breathing
+ * room to use other high-precision-timing APIs.
  *
  * The basic data type is instr_time, which all callers should treat as an
  * opaque typedef.  instr_time can store either an absolute time (of
@@ -17,10 +19,11 @@
  *
  * INSTR_TIME_SET_ZERO(t)			set t to zero (memset is acceptable too)
  *
- * INSTR_TIME_SET_CURRENT(t)		set t to current time
+ * INSTR_TIME_SET_CURRENT_FAST(t)	set t to current time without waiting
+ * 									for instructions in out-of-order window
  *
- * INSTR_TIME_SET_CURRENT_LAZY(t)	set t to current time if t is zero,
- *									evaluates to whether t changed
+ * INSTR_TIME_SET_CURRENT(t)		set t to current time while waiting for
+ * 									instructions in OOO to retire
  *
  * INSTR_TIME_ADD(x, y)				x += y
  *
@@ -81,6 +84,15 @@ typedef struct instr_time
 
 #ifndef WIN32
 
+/*
+ * Make sure this is a power-of-two, so that the compiler can turn the
+ * multiplications and divisions into shifts.
+ */
+#define TICKS_TO_NS_PRECISION (1<<14)
+
+extern int64 ticks_per_ns_scaled;
+extern int64 ticks_per_sec;
+extern int64 max_ticks_no_overflow;
 
 /* Use clock_gettime() */
 
@@ -106,9 +118,18 @@ typedef struct instr_time
 #define PG_INSTR_CLOCK	CLOCK_REALTIME
 #endif
 
-/* helper for INSTR_TIME_SET_CURRENT */
+#if defined(__x86_64__) && defined(__linux__)
+#include <x86intrin.h>
+#include <cpuid.h>
+
+extern bool has_rdtsc;
+extern bool has_rdtscp;
+
+extern void pg_initialize_rdtsc(void);
+#endif
+
 static inline instr_time
-pg_clock_gettime_ns(void)
+pg_clock_gettime(void)
 {
 	instr_time	now;
 	struct timespec tmp;
@@ -119,11 +140,94 @@ pg_clock_gettime_ns(void)
 	return now;
 }
 
+static inline instr_time
+pg_get_ticks_fast(void)
+{
+#if defined(__x86_64__) && defined(__linux__)
+	if (has_rdtsc)
+	{
+		instr_time	now;
+
+		now.ticks = __rdtsc();
+		return now;
+	}
+#endif
+
+	return pg_clock_gettime();
+}
+
+static inline instr_time
+pg_get_ticks(void)
+{
+#if defined(__x86_64__) && defined(__linux__)
+	if (has_rdtscp)
+	{
+		instr_time	now;
+		uint32		unused;
+
+		now.ticks = __rdtscp(&unused);
+		return now;
+	}
+#endif
+
+	return pg_clock_gettime();
+}
+
+static inline int64_t
+pg_ticks_to_ns(instr_time t)
+{
+	/*
+	 * Would multiplication overflow? If so perform computation in two parts.
+	 * Check overflow without actually overflowing via: a * b > max <=> a >
+	 * max / b
+	 */
+	int64		ns = 0;
+
+	if (unlikely(t.ticks > max_ticks_no_overflow))
+	{
+		/*
+		 * Compute how often the maximum number of ticks fits completely into
+		 * the number of elapsed ticks and convert that number into
+		 * nanoseconds. Then multiply by the count to arrive at the final
+		 * 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		max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION;
+
+		ns = max_ns * count;
+
+		/*
+		 * 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);
+	}
+
+	ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION;
+	return ns;
+}
+
+static inline void
+pg_initialize_get_ticks()
+{
+#if defined(__x86_64__) && defined(__linux__)
+	pg_initialize_rdtsc();
+#endif
+}
+
+#define INSTR_TIME_INITIALIZE() \
+	pg_initialize_get_ticks()
+
+#define INSTR_TIME_SET_CURRENT_FAST(t) \
+	((t) = pg_get_ticks_fast())
+
 #define INSTR_TIME_SET_CURRENT(t) \
-	((t) = pg_clock_gettime_ns())
+	((t) = pg_get_ticks())
 
 #define INSTR_TIME_GET_NANOSEC(t) \
-	((int64) (t).ticks)
+	pg_ticks_to_ns(t)
 
 
 #else							/* WIN32 */
@@ -131,7 +235,7 @@ pg_clock_gettime_ns(void)
 
 /* Use QueryPerformanceCounter() */
 
-/* helper for INSTR_TIME_SET_CURRENT */
+/* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */
 static inline instr_time
 pg_query_performance_counter(void)
 {
@@ -153,6 +257,11 @@ GetTimerFrequency(void)
 	return (double) f.QuadPart;
 }
 
+#define INSTR_TIME_INITIALIZE()
+
+#define INSTR_TIME_SET_CURRENT_FAST(t) \
+	((t) = pg_query_performance_counter())
+
 #define INSTR_TIME_SET_CURRENT(t) \
 	((t) = pg_query_performance_counter())
 
@@ -168,13 +277,8 @@ GetTimerFrequency(void)
 
 #define INSTR_TIME_IS_ZERO(t)	((t).ticks == 0)
 
-
 #define INSTR_TIME_SET_ZERO(t)	((t).ticks = 0)
 
-#define INSTR_TIME_SET_CURRENT_LAZY(t) \
-	(INSTR_TIME_IS_ZERO(t) ? INSTR_TIME_SET_CURRENT(t), true : false)
-
-
 #define INSTR_TIME_ADD(x,y) \
 	((x).ticks += (y).ticks)
 
-- 
2.47.3


--vtqqtrpooseurzip
Content-Type: text/x-diff; charset=utf-8
Content-Disposition: attachment;
	filename="v12-0003-pg_test_timing-Add-fast-flag-to-test-fast-timing.patch"



^ permalink  raw  reply  [nested|flat] 271+ messages in thread

* [PATCH v12 2/3] Use time stamp counter to measure time on Linux/x86
@ 2025-07-26 00:57 Lukas Fittl <[email protected]>
  0 siblings, 0 replies; 271+ messages in thread

From: Lukas Fittl @ 2025-07-26 00:57 UTC (permalink / raw)

We switch to using the time stamp counter (TSC) instead of clock_gettime()
to reduce overhead of EXPLAIN (ANALYZE, TIME ON). Tests showed that runtime
is reduced by around 10% for queries moving lots of rows through the plan.

For now this is only enabled on Linux/x86, in case the system clocksource is
reported as TSC. Relying on the Linux kernel simplifies the logic to detect
if the present TSC is usable (frequency invariant, synchronized between
sockets, etc.). In all other cases we fallback to clock_gettime().

Note, that we intentionally use RDTSC in the fast paths, rather than RDTSCP.
RDTSCP waits for outstanding instructions to retire on out-of-order CPUs.
This adds noticably for little benefit in the typical InstrStartNode() /
InstrStopNode() use case. The macro to be used in such cases is called
INSTR_TIME_SET_CURRENT_FAST(). The original macro INSTR_TIME_SET_CURRENT()
uses RDTSCP and is supposed to be used when precision is more important
than performance.

Author: David Geier <[email protected]>
Author: Andres Freund <[email protected]>
Author: Lukas Fittl <[email protected]>
Reviewed-by:
Discussion: https://www.postgresql.org/message-id/flat/20200612232810.f46nbqkdhbutzqdg%40alap3.anarazel.de
---
 src/backend/access/heap/vacuumlazy.c |   4 +-
 src/backend/executor/instrument.c    |  12 +-
 src/backend/utils/init/postinit.c    |   3 +
 src/bin/pgbench/pgbench.c            |   3 +
 src/bin/psql/startup.c               |   4 +
 src/common/Makefile                  |   1 +
 src/common/instr_time.c              | 206 +++++++++++++++++++++++++++
 src/common/meson.build               |   1 +
 src/include/portability/instr_time.h | 136 +++++++++++++++---
 9 files changed, 348 insertions(+), 22 deletions(-)
 create mode 100644 src/common/instr_time.c

diff --git a/src/backend/access/heap/vacuumlazy.c b/src/backend/access/heap/vacuumlazy.c
index d2b031fdd06..5027048cac4 100644
--- a/src/backend/access/heap/vacuumlazy.c
+++ b/src/backend/access/heap/vacuumlazy.c
@@ -3409,8 +3409,8 @@ count_nondeletable_pages(LVRelState *vacrel, bool *lock_waiter_detected)
 			INSTR_TIME_SET_CURRENT(currenttime);
 			elapsed = currenttime;
 			INSTR_TIME_SUBTRACT(elapsed, starttime);
-			if ((INSTR_TIME_GET_MICROSEC(elapsed) / 1000)
-				>= VACUUM_TRUNCATE_LOCK_CHECK_INTERVAL)
+			if (INSTR_TIME_GET_MILLISEC(elapsed) >=
+				VACUUM_TRUNCATE_LOCK_CHECK_INTERVAL)
 			{
 				if (LockHasWaitersRelation(vacrel->rel, AccessExclusiveLock))
 				{
diff --git a/src/backend/executor/instrument.c b/src/backend/executor/instrument.c
index 56e635f4700..01f67c5d972 100644
--- a/src/backend/executor/instrument.c
+++ b/src/backend/executor/instrument.c
@@ -67,9 +67,13 @@ InstrInit(Instrumentation *instr, int instrument_options)
 void
 InstrStartNode(Instrumentation *instr)
 {
-	if (instr->need_timer &&
-		!INSTR_TIME_SET_CURRENT_LAZY(instr->starttime))
-		elog(ERROR, "InstrStartNode called twice in a row");
+	if (instr->need_timer)
+	{
+		if (!INSTR_TIME_IS_ZERO(instr->starttime))
+			elog(ERROR, "InstrStartNode called twice in a row");
+		else
+			INSTR_TIME_SET_CURRENT_FAST(instr->starttime);
+	}
 
 	/* save buffer usage totals at node entry, if needed */
 	if (instr->need_bufusage)
@@ -95,7 +99,7 @@ InstrStopNode(Instrumentation *instr, double nTuples)
 		if (INSTR_TIME_IS_ZERO(instr->starttime))
 			elog(ERROR, "InstrStopNode called without start");
 
-		INSTR_TIME_SET_CURRENT(endtime);
+		INSTR_TIME_SET_CURRENT_FAST(endtime);
 		INSTR_TIME_ACCUM_DIFF(instr->counter, endtime, instr->starttime);
 
 		INSTR_TIME_SET_ZERO(instr->starttime);
diff --git a/src/backend/utils/init/postinit.c b/src/backend/utils/init/postinit.c
index 641e535a73c..d573409903b 100644
--- a/src/backend/utils/init/postinit.c
+++ b/src/backend/utils/init/postinit.c
@@ -810,6 +810,9 @@ InitPostgres(const char *in_dbname, Oid dboid,
 	/* Initialize portal manager */
 	EnablePortalManager();
 
+	/* initialize high-precision interval timing */
+	INSTR_TIME_INITIALIZE();
+
 	/*
 	 * Load relcache entries for the shared system catalogs.  This must create
 	 * at least entries for pg_database and catalogs used for authentication.
diff --git a/src/bin/pgbench/pgbench.c b/src/bin/pgbench/pgbench.c
index 1515ed405ba..79bef2d2aec 100644
--- a/src/bin/pgbench/pgbench.c
+++ b/src/bin/pgbench/pgbench.c
@@ -7290,6 +7290,9 @@ main(int argc, char **argv)
 		initRandomState(&state[i].cs_func_rs);
 	}
 
+	/* initialize high-precision interval timing */
+	INSTR_TIME_INITIALIZE();
+
 	/* opening connection... */
 	con = doConnect();
 	if (con == NULL)
diff --git a/src/bin/psql/startup.c b/src/bin/psql/startup.c
index 249b6aa5169..d615df593c7 100644
--- a/src/bin/psql/startup.c
+++ b/src/bin/psql/startup.c
@@ -24,6 +24,7 @@
 #include "help.h"
 #include "input.h"
 #include "mainloop.h"
+#include "portability/instr_time.h"
 #include "settings.h"
 
 /*
@@ -327,6 +328,9 @@ main(int argc, char *argv[])
 
 	PQsetNoticeProcessor(pset.db, NoticeProcessor, NULL);
 
+	/* initialize high-precision interval timing */
+	INSTR_TIME_INITIALIZE();
+
 	SyncVariables();
 
 	if (options.list_dbs)
diff --git a/src/common/Makefile b/src/common/Makefile
index 2c720caa509..1a2fbbe887f 100644
--- a/src/common/Makefile
+++ b/src/common/Makefile
@@ -59,6 +59,7 @@ OBJS_COMMON = \
 	file_perm.o \
 	file_utils.o \
 	hashfn.o \
+	instr_time.o \
 	ip.o \
 	jsonapi.o \
 	keywords.o \
diff --git a/src/common/instr_time.c b/src/common/instr_time.c
new file mode 100644
index 00000000000..fdf47699f20
--- /dev/null
+++ b/src/common/instr_time.c
@@ -0,0 +1,206 @@
+/*-------------------------------------------------------------------------
+ *
+ * instr_time.c
+ *	   Non-inline parts of the portable high-precision interval timing
+ *	 implementation
+ *
+ * Portions Copyright (c) 2025, PostgreSQL Global Development Group
+ *
+ *
+ * IDENTIFICATION
+ *	  src/backend/port/instr_time.c
+ *
+ *-------------------------------------------------------------------------
+ */
+#include "postgres.h"
+
+#if defined(HAVE__GET_CPUID) || (defined(HAVE__CPUIDEX) && !defined(_MSC_VER))
+#include <cpuid.h>
+#endif
+
+#if defined(HAVE__CPUID) || (defined(HAVE__CPUIDEX) && defined(_MSC_VER))
+#include <intrin.h>
+#endif
+
+#include "portability/instr_time.h"
+
+#ifndef WIN32
+/*
+ * Stores what the number of cycles needs to be multiplied with to end up
+ * with nanoseconds using integer math. See comment in pg_initialize_rdtsc()
+ * for more details.
+ *
+ * By default assume we are using clock_gettime() as a fallback which uses
+ * nanoseconds as ticks. Hence, we set the multiplier to the precision scalar
+ * so that the division in INSTR_TIME_GET_NANOSEC() won't change the nanoseconds.
+ *
+ * When using the RDTSC instruction directly this is filled in during initialization
+ * based on the relevant CPUID fields.
+ */
+int64		ticks_per_ns_scaled = TICKS_TO_NS_PRECISION;
+int64		ticks_per_sec = NS_PER_S;
+int64		max_ticks_no_overflow = PG_INT64_MAX / TICKS_TO_NS_PRECISION;
+
+#if defined(__x86_64__) && defined(__linux__)
+/*
+ * Indicates if RDTSC can be used (Linux/x86 only, when OS uses TSC clocksource)
+ */
+bool		has_rdtsc = false;
+
+/*
+ * Indicates if RDTSCP can be used. True if RDTSC can be used and RDTSCP is available.
+ */
+bool		has_rdtscp = false;
+
+#define CPUID_HYPERVISOR_VMWARE(words) (words[1] == 0x61774d56 && words[2] == 0x4d566572 && words[3] == 0x65726177) /* VMwareVMware */
+#define CPUID_HYPERVISOR_KVM(words) (words[1] == 0x4b4d564b && words[2] == 0x564b4d56 && words[3] == 0x0000004d)	/* KVMKVMKVM */
+
+static bool
+get_tsc_frequency_khz(uint32 *tsc_freq)
+{
+	uint32		r[4] = {0, 0, 0, 0};
+
+#if defined(HAVE__GET_CPUID)
+	__get_cpuid(0x15, &r[0] /* denominator */ , &r[1] /* numerator */ , &r[2] /* hz */ , &r[3]);
+#elif defined(HAVE__CPUID)
+	__cpuid(r, 0x15);
+#else
+#error cpuid instruction not available
+#endif
+
+	if (r[2] > 0)
+	{
+		if (r[0] == 0 || r[1] == 0)
+			return false;
+
+		*tsc_freq = r[2] / 1000 * r[1] / r[0];
+		return true;
+	}
+
+	/* Some CPUs only report frequency in 16H */
+
+#if defined(HAVE__GET_CPUID)
+	__get_cpuid(0x16, &r[0] /* base_mhz */ , &r[1], &r[2], &r[3]);
+#elif defined(HAVE__CPUID)
+	__cpuid(r, 0x16);
+#else
+#error cpuid instruction not available
+#endif
+
+	if (r[0] > 0)
+	{
+		*tsc_freq = r[0] * 1000;
+		return true;
+	}
+
+	/*
+	 * Check if we have a KVM or VMware Hypervisor passing down TSC frequency
+	 * to us in a guest VM
+	 *
+	 * Note that accessing the 0x40000000 leaf for Hypervisor info requires
+	 * use of __cpuidex to set ECX to 0. The similar __get_cpuid_count
+	 * function does not work as expected since it contains a check for
+	 * __get_cpuid_max, which has been observed to be lower than the special
+	 * Hypervisor leaf.
+	 */
+#if defined(HAVE__CPUIDEX)
+	__cpuidex((int32 *) r, 0x40000000, 0);
+	if (r[0] >= 0x40000010 && (CPUID_HYPERVISOR_VMWARE(r) || CPUID_HYPERVISOR_KVM(r)))
+	{
+		__cpuidex((int32 *) r, 0x40000010, 0);
+		if (r[0] > 0)
+		{
+			*tsc_freq = r[0];
+			return true;
+		}
+	}
+#endif
+
+	return false;
+}
+
+static bool
+is_rdtscp_available()
+{
+	uint32		r[4] = {0, 0, 0, 0};
+
+#if defined(HAVE__GET_CPUID)
+	if (!__get_cpuid(0x80000001, &r[0], &r[1], &r[2], &r[3]))
+		return false;
+#elif defined(HAVE__CPUID)
+	__cpuid(r, 0x80000001);
+#else
+#error cpuid instruction not available
+#endif
+
+	return (r[3] & (1 << 27)) != 0;
+}
+
+/*
+ * Decide whether we use the RDTSC instruction at runtime, for Linux/x86,
+ * instead of incurring the overhead of a full clock_gettime() call.
+ *
+ * This can't be reliably determined at compile time, since the
+ * availability of an "invariant" TSC (that is not affected by CPU
+ * frequency changes) is dependent on the CPU architecture. Additionally,
+ * there are cases where TSC availability is impacted by virtualization,
+ * where a simple cpuid feature check would not be enough.
+ *
+ * Since Linux already does a significant amount of work to determine
+ * whether TSC is a viable clock source, decide based on that.
+ */
+void
+pg_initialize_rdtsc(void)
+{
+	FILE	   *fp = fopen("/sys/devices/system/clocksource/clocksource0/current_clocksource", "r");
+
+	if (fp)
+	{
+		char		buf[128];
+
+		if (fgets(buf, sizeof(buf), fp) != NULL && strcmp(buf, "tsc\n") == 0)
+		{
+			/*
+			 * Compute baseline CPU peformance, determines speed at which
+			 * RDTSC advances.
+			 */
+			uint32		tsc_freq;
+
+			if (get_tsc_frequency_khz(&tsc_freq))
+			{
+				/*
+				 * Ticks to nanoseconds conversion requires floating point
+				 * math because because:
+				 *
+				 * sec = ticks / frequency_hz ns  = ticks / frequency_hz *
+				 * 1,000,000,000 ns  = ticks * (1,000,000,000 / frequency_hz)
+				 * ns  = ticks * (1,000,000 / frequency_khz) <-- now in
+				 * kilohertz
+				 *
+				 * Here, 'ns' is usually a floating number. For example for a
+				 * 2.5 GHz CPU the scaling factor becomes 1,000,000 /
+				 * 2,500,000 = 1.2.
+				 *
+				 * To be able to use integer math we work around the lack of
+				 * precision. We first scale the integer up and after the
+				 * multiplication by the number of ticks in
+				 * INSTR_TIME_GET_NANOSEC() we divide again by the same value.
+				 * We picked the scaler such that it provides enough precision
+				 * and is a power-of-two which allows for shifting instead of
+				 * doing an integer division.
+				 */
+				ticks_per_ns_scaled = INT64CONST(1000000) * TICKS_TO_NS_PRECISION / tsc_freq;
+				ticks_per_sec = tsc_freq * 1000;	/* KHz->Hz */
+				max_ticks_no_overflow = PG_INT64_MAX / ticks_per_ns_scaled;
+
+				has_rdtsc = true;
+				has_rdtscp = is_rdtscp_available();
+			}
+		}
+
+		fclose(fp);
+	}
+}
+#endif							/* defined(__x86_64__) && defined(__linux__) */
+
+#endif							/* WIN32 */
diff --git a/src/common/meson.build b/src/common/meson.build
index 1540ba67cca..62b90b3e609 100644
--- a/src/common/meson.build
+++ b/src/common/meson.build
@@ -13,6 +13,7 @@ common_sources = files(
   'file_perm.c',
   'file_utils.c',
   'hashfn.c',
+  'instr_time.c',
   'ip.c',
   'jsonapi.c',
   'keywords.c',
diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h
index f71a851b18d..e2e339a0c4f 100644
--- a/src/include/portability/instr_time.h
+++ b/src/include/portability/instr_time.h
@@ -4,9 +4,11 @@
  *	  portable high-precision interval timing
  *
  * This file provides an abstraction layer to hide portability issues in
- * interval timing.  On Unix we use clock_gettime(), and on Windows we use
- * QueryPerformanceCounter().  These macros also give some breathing room to
- * use other high-precision-timing APIs.
+ * interval timing. On Linux/x86 we use the rdtsc instruction when a TSC
+ * clocksource is also used on the host OS.  Otherwise, and on other
+ * Unix-like systems we use clock_gettime() and on Windows we use
+ * QueryPerformanceCounter(). These macros also give some breathing
+ * room to use other high-precision-timing APIs.
  *
  * The basic data type is instr_time, which all callers should treat as an
  * opaque typedef.  instr_time can store either an absolute time (of
@@ -17,10 +19,11 @@
  *
  * INSTR_TIME_SET_ZERO(t)			set t to zero (memset is acceptable too)
  *
- * INSTR_TIME_SET_CURRENT(t)		set t to current time
+ * INSTR_TIME_SET_CURRENT_FAST(t)	set t to current time without waiting
+ * 									for instructions in out-of-order window
  *
- * INSTR_TIME_SET_CURRENT_LAZY(t)	set t to current time if t is zero,
- *									evaluates to whether t changed
+ * INSTR_TIME_SET_CURRENT(t)		set t to current time while waiting for
+ * 									instructions in OOO to retire
  *
  * INSTR_TIME_ADD(x, y)				x += y
  *
@@ -81,6 +84,15 @@ typedef struct instr_time
 
 #ifndef WIN32
 
+/*
+ * Make sure this is a power-of-two, so that the compiler can turn the
+ * multiplications and divisions into shifts.
+ */
+#define TICKS_TO_NS_PRECISION (1<<14)
+
+extern int64 ticks_per_ns_scaled;
+extern int64 ticks_per_sec;
+extern int64 max_ticks_no_overflow;
 
 /* Use clock_gettime() */
 
@@ -106,9 +118,18 @@ typedef struct instr_time
 #define PG_INSTR_CLOCK	CLOCK_REALTIME
 #endif
 
-/* helper for INSTR_TIME_SET_CURRENT */
+#if defined(__x86_64__) && defined(__linux__)
+#include <x86intrin.h>
+#include <cpuid.h>
+
+extern bool has_rdtsc;
+extern bool has_rdtscp;
+
+extern void pg_initialize_rdtsc(void);
+#endif
+
 static inline instr_time
-pg_clock_gettime_ns(void)
+pg_clock_gettime(void)
 {
 	instr_time	now;
 	struct timespec tmp;
@@ -119,11 +140,94 @@ pg_clock_gettime_ns(void)
 	return now;
 }
 
+static inline instr_time
+pg_get_ticks_fast(void)
+{
+#if defined(__x86_64__) && defined(__linux__)
+	if (has_rdtsc)
+	{
+		instr_time	now;
+
+		now.ticks = __rdtsc();
+		return now;
+	}
+#endif
+
+	return pg_clock_gettime();
+}
+
+static inline instr_time
+pg_get_ticks(void)
+{
+#if defined(__x86_64__) && defined(__linux__)
+	if (has_rdtscp)
+	{
+		instr_time	now;
+		uint32		unused;
+
+		now.ticks = __rdtscp(&unused);
+		return now;
+	}
+#endif
+
+	return pg_clock_gettime();
+}
+
+static inline int64_t
+pg_ticks_to_ns(instr_time t)
+{
+	/*
+	 * Would multiplication overflow? If so perform computation in two parts.
+	 * Check overflow without actually overflowing via: a * b > max <=> a >
+	 * max / b
+	 */
+	int64		ns = 0;
+
+	if (unlikely(t.ticks > max_ticks_no_overflow))
+	{
+		/*
+		 * Compute how often the maximum number of ticks fits completely into
+		 * the number of elapsed ticks and convert that number into
+		 * nanoseconds. Then multiply by the count to arrive at the final
+		 * 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		max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION;
+
+		ns = max_ns * count;
+
+		/*
+		 * 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);
+	}
+
+	ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION;
+	return ns;
+}
+
+static inline void
+pg_initialize_get_ticks()
+{
+#if defined(__x86_64__) && defined(__linux__)
+	pg_initialize_rdtsc();
+#endif
+}
+
+#define INSTR_TIME_INITIALIZE() \
+	pg_initialize_get_ticks()
+
+#define INSTR_TIME_SET_CURRENT_FAST(t) \
+	((t) = pg_get_ticks_fast())
+
 #define INSTR_TIME_SET_CURRENT(t) \
-	((t) = pg_clock_gettime_ns())
+	((t) = pg_get_ticks())
 
 #define INSTR_TIME_GET_NANOSEC(t) \
-	((int64) (t).ticks)
+	pg_ticks_to_ns(t)
 
 
 #else							/* WIN32 */
@@ -131,7 +235,7 @@ pg_clock_gettime_ns(void)
 
 /* Use QueryPerformanceCounter() */
 
-/* helper for INSTR_TIME_SET_CURRENT */
+/* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */
 static inline instr_time
 pg_query_performance_counter(void)
 {
@@ -153,6 +257,11 @@ GetTimerFrequency(void)
 	return (double) f.QuadPart;
 }
 
+#define INSTR_TIME_INITIALIZE()
+
+#define INSTR_TIME_SET_CURRENT_FAST(t) \
+	((t) = pg_query_performance_counter())
+
 #define INSTR_TIME_SET_CURRENT(t) \
 	((t) = pg_query_performance_counter())
 
@@ -168,13 +277,8 @@ GetTimerFrequency(void)
 
 #define INSTR_TIME_IS_ZERO(t)	((t).ticks == 0)
 
-
 #define INSTR_TIME_SET_ZERO(t)	((t).ticks = 0)
 
-#define INSTR_TIME_SET_CURRENT_LAZY(t) \
-	(INSTR_TIME_IS_ZERO(t) ? INSTR_TIME_SET_CURRENT(t), true : false)
-
-
 #define INSTR_TIME_ADD(x,y) \
 	((x).ticks += (y).ticks)
 
-- 
2.47.3


--vtqqtrpooseurzip
Content-Type: text/x-diff; charset=utf-8
Content-Disposition: attachment;
	filename="v12-0003-pg_test_timing-Add-fast-flag-to-test-fast-timing.patch"



^ permalink  raw  reply  [nested|flat] 271+ messages in thread

* [PATCH v12 2/3] Use time stamp counter to measure time on Linux/x86
@ 2025-07-26 00:57 Lukas Fittl <[email protected]>
  0 siblings, 0 replies; 271+ messages in thread

From: Lukas Fittl @ 2025-07-26 00:57 UTC (permalink / raw)

We switch to using the time stamp counter (TSC) instead of clock_gettime()
to reduce overhead of EXPLAIN (ANALYZE, TIME ON). Tests showed that runtime
is reduced by around 10% for queries moving lots of rows through the plan.

For now this is only enabled on Linux/x86, in case the system clocksource is
reported as TSC. Relying on the Linux kernel simplifies the logic to detect
if the present TSC is usable (frequency invariant, synchronized between
sockets, etc.). In all other cases we fallback to clock_gettime().

Note, that we intentionally use RDTSC in the fast paths, rather than RDTSCP.
RDTSCP waits for outstanding instructions to retire on out-of-order CPUs.
This adds noticably for little benefit in the typical InstrStartNode() /
InstrStopNode() use case. The macro to be used in such cases is called
INSTR_TIME_SET_CURRENT_FAST(). The original macro INSTR_TIME_SET_CURRENT()
uses RDTSCP and is supposed to be used when precision is more important
than performance.

Author: David Geier <[email protected]>
Author: Andres Freund <[email protected]>
Author: Lukas Fittl <[email protected]>
Reviewed-by:
Discussion: https://www.postgresql.org/message-id/flat/20200612232810.f46nbqkdhbutzqdg%40alap3.anarazel.de
---
 src/backend/access/heap/vacuumlazy.c |   4 +-
 src/backend/executor/instrument.c    |  12 +-
 src/backend/utils/init/postinit.c    |   3 +
 src/bin/pgbench/pgbench.c            |   3 +
 src/bin/psql/startup.c               |   4 +
 src/common/Makefile                  |   1 +
 src/common/instr_time.c              | 206 +++++++++++++++++++++++++++
 src/common/meson.build               |   1 +
 src/include/portability/instr_time.h | 136 +++++++++++++++---
 9 files changed, 348 insertions(+), 22 deletions(-)
 create mode 100644 src/common/instr_time.c

diff --git a/src/backend/access/heap/vacuumlazy.c b/src/backend/access/heap/vacuumlazy.c
index d2b031fdd06..5027048cac4 100644
--- a/src/backend/access/heap/vacuumlazy.c
+++ b/src/backend/access/heap/vacuumlazy.c
@@ -3409,8 +3409,8 @@ count_nondeletable_pages(LVRelState *vacrel, bool *lock_waiter_detected)
 			INSTR_TIME_SET_CURRENT(currenttime);
 			elapsed = currenttime;
 			INSTR_TIME_SUBTRACT(elapsed, starttime);
-			if ((INSTR_TIME_GET_MICROSEC(elapsed) / 1000)
-				>= VACUUM_TRUNCATE_LOCK_CHECK_INTERVAL)
+			if (INSTR_TIME_GET_MILLISEC(elapsed) >=
+				VACUUM_TRUNCATE_LOCK_CHECK_INTERVAL)
 			{
 				if (LockHasWaitersRelation(vacrel->rel, AccessExclusiveLock))
 				{
diff --git a/src/backend/executor/instrument.c b/src/backend/executor/instrument.c
index 56e635f4700..01f67c5d972 100644
--- a/src/backend/executor/instrument.c
+++ b/src/backend/executor/instrument.c
@@ -67,9 +67,13 @@ InstrInit(Instrumentation *instr, int instrument_options)
 void
 InstrStartNode(Instrumentation *instr)
 {
-	if (instr->need_timer &&
-		!INSTR_TIME_SET_CURRENT_LAZY(instr->starttime))
-		elog(ERROR, "InstrStartNode called twice in a row");
+	if (instr->need_timer)
+	{
+		if (!INSTR_TIME_IS_ZERO(instr->starttime))
+			elog(ERROR, "InstrStartNode called twice in a row");
+		else
+			INSTR_TIME_SET_CURRENT_FAST(instr->starttime);
+	}
 
 	/* save buffer usage totals at node entry, if needed */
 	if (instr->need_bufusage)
@@ -95,7 +99,7 @@ InstrStopNode(Instrumentation *instr, double nTuples)
 		if (INSTR_TIME_IS_ZERO(instr->starttime))
 			elog(ERROR, "InstrStopNode called without start");
 
-		INSTR_TIME_SET_CURRENT(endtime);
+		INSTR_TIME_SET_CURRENT_FAST(endtime);
 		INSTR_TIME_ACCUM_DIFF(instr->counter, endtime, instr->starttime);
 
 		INSTR_TIME_SET_ZERO(instr->starttime);
diff --git a/src/backend/utils/init/postinit.c b/src/backend/utils/init/postinit.c
index 641e535a73c..d573409903b 100644
--- a/src/backend/utils/init/postinit.c
+++ b/src/backend/utils/init/postinit.c
@@ -810,6 +810,9 @@ InitPostgres(const char *in_dbname, Oid dboid,
 	/* Initialize portal manager */
 	EnablePortalManager();
 
+	/* initialize high-precision interval timing */
+	INSTR_TIME_INITIALIZE();
+
 	/*
 	 * Load relcache entries for the shared system catalogs.  This must create
 	 * at least entries for pg_database and catalogs used for authentication.
diff --git a/src/bin/pgbench/pgbench.c b/src/bin/pgbench/pgbench.c
index 1515ed405ba..79bef2d2aec 100644
--- a/src/bin/pgbench/pgbench.c
+++ b/src/bin/pgbench/pgbench.c
@@ -7290,6 +7290,9 @@ main(int argc, char **argv)
 		initRandomState(&state[i].cs_func_rs);
 	}
 
+	/* initialize high-precision interval timing */
+	INSTR_TIME_INITIALIZE();
+
 	/* opening connection... */
 	con = doConnect();
 	if (con == NULL)
diff --git a/src/bin/psql/startup.c b/src/bin/psql/startup.c
index 249b6aa5169..d615df593c7 100644
--- a/src/bin/psql/startup.c
+++ b/src/bin/psql/startup.c
@@ -24,6 +24,7 @@
 #include "help.h"
 #include "input.h"
 #include "mainloop.h"
+#include "portability/instr_time.h"
 #include "settings.h"
 
 /*
@@ -327,6 +328,9 @@ main(int argc, char *argv[])
 
 	PQsetNoticeProcessor(pset.db, NoticeProcessor, NULL);
 
+	/* initialize high-precision interval timing */
+	INSTR_TIME_INITIALIZE();
+
 	SyncVariables();
 
 	if (options.list_dbs)
diff --git a/src/common/Makefile b/src/common/Makefile
index 2c720caa509..1a2fbbe887f 100644
--- a/src/common/Makefile
+++ b/src/common/Makefile
@@ -59,6 +59,7 @@ OBJS_COMMON = \
 	file_perm.o \
 	file_utils.o \
 	hashfn.o \
+	instr_time.o \
 	ip.o \
 	jsonapi.o \
 	keywords.o \
diff --git a/src/common/instr_time.c b/src/common/instr_time.c
new file mode 100644
index 00000000000..fdf47699f20
--- /dev/null
+++ b/src/common/instr_time.c
@@ -0,0 +1,206 @@
+/*-------------------------------------------------------------------------
+ *
+ * instr_time.c
+ *	   Non-inline parts of the portable high-precision interval timing
+ *	 implementation
+ *
+ * Portions Copyright (c) 2025, PostgreSQL Global Development Group
+ *
+ *
+ * IDENTIFICATION
+ *	  src/backend/port/instr_time.c
+ *
+ *-------------------------------------------------------------------------
+ */
+#include "postgres.h"
+
+#if defined(HAVE__GET_CPUID) || (defined(HAVE__CPUIDEX) && !defined(_MSC_VER))
+#include <cpuid.h>
+#endif
+
+#if defined(HAVE__CPUID) || (defined(HAVE__CPUIDEX) && defined(_MSC_VER))
+#include <intrin.h>
+#endif
+
+#include "portability/instr_time.h"
+
+#ifndef WIN32
+/*
+ * Stores what the number of cycles needs to be multiplied with to end up
+ * with nanoseconds using integer math. See comment in pg_initialize_rdtsc()
+ * for more details.
+ *
+ * By default assume we are using clock_gettime() as a fallback which uses
+ * nanoseconds as ticks. Hence, we set the multiplier to the precision scalar
+ * so that the division in INSTR_TIME_GET_NANOSEC() won't change the nanoseconds.
+ *
+ * When using the RDTSC instruction directly this is filled in during initialization
+ * based on the relevant CPUID fields.
+ */
+int64		ticks_per_ns_scaled = TICKS_TO_NS_PRECISION;
+int64		ticks_per_sec = NS_PER_S;
+int64		max_ticks_no_overflow = PG_INT64_MAX / TICKS_TO_NS_PRECISION;
+
+#if defined(__x86_64__) && defined(__linux__)
+/*
+ * Indicates if RDTSC can be used (Linux/x86 only, when OS uses TSC clocksource)
+ */
+bool		has_rdtsc = false;
+
+/*
+ * Indicates if RDTSCP can be used. True if RDTSC can be used and RDTSCP is available.
+ */
+bool		has_rdtscp = false;
+
+#define CPUID_HYPERVISOR_VMWARE(words) (words[1] == 0x61774d56 && words[2] == 0x4d566572 && words[3] == 0x65726177) /* VMwareVMware */
+#define CPUID_HYPERVISOR_KVM(words) (words[1] == 0x4b4d564b && words[2] == 0x564b4d56 && words[3] == 0x0000004d)	/* KVMKVMKVM */
+
+static bool
+get_tsc_frequency_khz(uint32 *tsc_freq)
+{
+	uint32		r[4] = {0, 0, 0, 0};
+
+#if defined(HAVE__GET_CPUID)
+	__get_cpuid(0x15, &r[0] /* denominator */ , &r[1] /* numerator */ , &r[2] /* hz */ , &r[3]);
+#elif defined(HAVE__CPUID)
+	__cpuid(r, 0x15);
+#else
+#error cpuid instruction not available
+#endif
+
+	if (r[2] > 0)
+	{
+		if (r[0] == 0 || r[1] == 0)
+			return false;
+
+		*tsc_freq = r[2] / 1000 * r[1] / r[0];
+		return true;
+	}
+
+	/* Some CPUs only report frequency in 16H */
+
+#if defined(HAVE__GET_CPUID)
+	__get_cpuid(0x16, &r[0] /* base_mhz */ , &r[1], &r[2], &r[3]);
+#elif defined(HAVE__CPUID)
+	__cpuid(r, 0x16);
+#else
+#error cpuid instruction not available
+#endif
+
+	if (r[0] > 0)
+	{
+		*tsc_freq = r[0] * 1000;
+		return true;
+	}
+
+	/*
+	 * Check if we have a KVM or VMware Hypervisor passing down TSC frequency
+	 * to us in a guest VM
+	 *
+	 * Note that accessing the 0x40000000 leaf for Hypervisor info requires
+	 * use of __cpuidex to set ECX to 0. The similar __get_cpuid_count
+	 * function does not work as expected since it contains a check for
+	 * __get_cpuid_max, which has been observed to be lower than the special
+	 * Hypervisor leaf.
+	 */
+#if defined(HAVE__CPUIDEX)
+	__cpuidex((int32 *) r, 0x40000000, 0);
+	if (r[0] >= 0x40000010 && (CPUID_HYPERVISOR_VMWARE(r) || CPUID_HYPERVISOR_KVM(r)))
+	{
+		__cpuidex((int32 *) r, 0x40000010, 0);
+		if (r[0] > 0)
+		{
+			*tsc_freq = r[0];
+			return true;
+		}
+	}
+#endif
+
+	return false;
+}
+
+static bool
+is_rdtscp_available()
+{
+	uint32		r[4] = {0, 0, 0, 0};
+
+#if defined(HAVE__GET_CPUID)
+	if (!__get_cpuid(0x80000001, &r[0], &r[1], &r[2], &r[3]))
+		return false;
+#elif defined(HAVE__CPUID)
+	__cpuid(r, 0x80000001);
+#else
+#error cpuid instruction not available
+#endif
+
+	return (r[3] & (1 << 27)) != 0;
+}
+
+/*
+ * Decide whether we use the RDTSC instruction at runtime, for Linux/x86,
+ * instead of incurring the overhead of a full clock_gettime() call.
+ *
+ * This can't be reliably determined at compile time, since the
+ * availability of an "invariant" TSC (that is not affected by CPU
+ * frequency changes) is dependent on the CPU architecture. Additionally,
+ * there are cases where TSC availability is impacted by virtualization,
+ * where a simple cpuid feature check would not be enough.
+ *
+ * Since Linux already does a significant amount of work to determine
+ * whether TSC is a viable clock source, decide based on that.
+ */
+void
+pg_initialize_rdtsc(void)
+{
+	FILE	   *fp = fopen("/sys/devices/system/clocksource/clocksource0/current_clocksource", "r");
+
+	if (fp)
+	{
+		char		buf[128];
+
+		if (fgets(buf, sizeof(buf), fp) != NULL && strcmp(buf, "tsc\n") == 0)
+		{
+			/*
+			 * Compute baseline CPU peformance, determines speed at which
+			 * RDTSC advances.
+			 */
+			uint32		tsc_freq;
+
+			if (get_tsc_frequency_khz(&tsc_freq))
+			{
+				/*
+				 * Ticks to nanoseconds conversion requires floating point
+				 * math because because:
+				 *
+				 * sec = ticks / frequency_hz ns  = ticks / frequency_hz *
+				 * 1,000,000,000 ns  = ticks * (1,000,000,000 / frequency_hz)
+				 * ns  = ticks * (1,000,000 / frequency_khz) <-- now in
+				 * kilohertz
+				 *
+				 * Here, 'ns' is usually a floating number. For example for a
+				 * 2.5 GHz CPU the scaling factor becomes 1,000,000 /
+				 * 2,500,000 = 1.2.
+				 *
+				 * To be able to use integer math we work around the lack of
+				 * precision. We first scale the integer up and after the
+				 * multiplication by the number of ticks in
+				 * INSTR_TIME_GET_NANOSEC() we divide again by the same value.
+				 * We picked the scaler such that it provides enough precision
+				 * and is a power-of-two which allows for shifting instead of
+				 * doing an integer division.
+				 */
+				ticks_per_ns_scaled = INT64CONST(1000000) * TICKS_TO_NS_PRECISION / tsc_freq;
+				ticks_per_sec = tsc_freq * 1000;	/* KHz->Hz */
+				max_ticks_no_overflow = PG_INT64_MAX / ticks_per_ns_scaled;
+
+				has_rdtsc = true;
+				has_rdtscp = is_rdtscp_available();
+			}
+		}
+
+		fclose(fp);
+	}
+}
+#endif							/* defined(__x86_64__) && defined(__linux__) */
+
+#endif							/* WIN32 */
diff --git a/src/common/meson.build b/src/common/meson.build
index 1540ba67cca..62b90b3e609 100644
--- a/src/common/meson.build
+++ b/src/common/meson.build
@@ -13,6 +13,7 @@ common_sources = files(
   'file_perm.c',
   'file_utils.c',
   'hashfn.c',
+  'instr_time.c',
   'ip.c',
   'jsonapi.c',
   'keywords.c',
diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h
index f71a851b18d..e2e339a0c4f 100644
--- a/src/include/portability/instr_time.h
+++ b/src/include/portability/instr_time.h
@@ -4,9 +4,11 @@
  *	  portable high-precision interval timing
  *
  * This file provides an abstraction layer to hide portability issues in
- * interval timing.  On Unix we use clock_gettime(), and on Windows we use
- * QueryPerformanceCounter().  These macros also give some breathing room to
- * use other high-precision-timing APIs.
+ * interval timing. On Linux/x86 we use the rdtsc instruction when a TSC
+ * clocksource is also used on the host OS.  Otherwise, and on other
+ * Unix-like systems we use clock_gettime() and on Windows we use
+ * QueryPerformanceCounter(). These macros also give some breathing
+ * room to use other high-precision-timing APIs.
  *
  * The basic data type is instr_time, which all callers should treat as an
  * opaque typedef.  instr_time can store either an absolute time (of
@@ -17,10 +19,11 @@
  *
  * INSTR_TIME_SET_ZERO(t)			set t to zero (memset is acceptable too)
  *
- * INSTR_TIME_SET_CURRENT(t)		set t to current time
+ * INSTR_TIME_SET_CURRENT_FAST(t)	set t to current time without waiting
+ * 									for instructions in out-of-order window
  *
- * INSTR_TIME_SET_CURRENT_LAZY(t)	set t to current time if t is zero,
- *									evaluates to whether t changed
+ * INSTR_TIME_SET_CURRENT(t)		set t to current time while waiting for
+ * 									instructions in OOO to retire
  *
  * INSTR_TIME_ADD(x, y)				x += y
  *
@@ -81,6 +84,15 @@ typedef struct instr_time
 
 #ifndef WIN32
 
+/*
+ * Make sure this is a power-of-two, so that the compiler can turn the
+ * multiplications and divisions into shifts.
+ */
+#define TICKS_TO_NS_PRECISION (1<<14)
+
+extern int64 ticks_per_ns_scaled;
+extern int64 ticks_per_sec;
+extern int64 max_ticks_no_overflow;
 
 /* Use clock_gettime() */
 
@@ -106,9 +118,18 @@ typedef struct instr_time
 #define PG_INSTR_CLOCK	CLOCK_REALTIME
 #endif
 
-/* helper for INSTR_TIME_SET_CURRENT */
+#if defined(__x86_64__) && defined(__linux__)
+#include <x86intrin.h>
+#include <cpuid.h>
+
+extern bool has_rdtsc;
+extern bool has_rdtscp;
+
+extern void pg_initialize_rdtsc(void);
+#endif
+
 static inline instr_time
-pg_clock_gettime_ns(void)
+pg_clock_gettime(void)
 {
 	instr_time	now;
 	struct timespec tmp;
@@ -119,11 +140,94 @@ pg_clock_gettime_ns(void)
 	return now;
 }
 
+static inline instr_time
+pg_get_ticks_fast(void)
+{
+#if defined(__x86_64__) && defined(__linux__)
+	if (has_rdtsc)
+	{
+		instr_time	now;
+
+		now.ticks = __rdtsc();
+		return now;
+	}
+#endif
+
+	return pg_clock_gettime();
+}
+
+static inline instr_time
+pg_get_ticks(void)
+{
+#if defined(__x86_64__) && defined(__linux__)
+	if (has_rdtscp)
+	{
+		instr_time	now;
+		uint32		unused;
+
+		now.ticks = __rdtscp(&unused);
+		return now;
+	}
+#endif
+
+	return pg_clock_gettime();
+}
+
+static inline int64_t
+pg_ticks_to_ns(instr_time t)
+{
+	/*
+	 * Would multiplication overflow? If so perform computation in two parts.
+	 * Check overflow without actually overflowing via: a * b > max <=> a >
+	 * max / b
+	 */
+	int64		ns = 0;
+
+	if (unlikely(t.ticks > max_ticks_no_overflow))
+	{
+		/*
+		 * Compute how often the maximum number of ticks fits completely into
+		 * the number of elapsed ticks and convert that number into
+		 * nanoseconds. Then multiply by the count to arrive at the final
+		 * 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		max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION;
+
+		ns = max_ns * count;
+
+		/*
+		 * 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);
+	}
+
+	ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION;
+	return ns;
+}
+
+static inline void
+pg_initialize_get_ticks()
+{
+#if defined(__x86_64__) && defined(__linux__)
+	pg_initialize_rdtsc();
+#endif
+}
+
+#define INSTR_TIME_INITIALIZE() \
+	pg_initialize_get_ticks()
+
+#define INSTR_TIME_SET_CURRENT_FAST(t) \
+	((t) = pg_get_ticks_fast())
+
 #define INSTR_TIME_SET_CURRENT(t) \
-	((t) = pg_clock_gettime_ns())
+	((t) = pg_get_ticks())
 
 #define INSTR_TIME_GET_NANOSEC(t) \
-	((int64) (t).ticks)
+	pg_ticks_to_ns(t)
 
 
 #else							/* WIN32 */
@@ -131,7 +235,7 @@ pg_clock_gettime_ns(void)
 
 /* Use QueryPerformanceCounter() */
 
-/* helper for INSTR_TIME_SET_CURRENT */
+/* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */
 static inline instr_time
 pg_query_performance_counter(void)
 {
@@ -153,6 +257,11 @@ GetTimerFrequency(void)
 	return (double) f.QuadPart;
 }
 
+#define INSTR_TIME_INITIALIZE()
+
+#define INSTR_TIME_SET_CURRENT_FAST(t) \
+	((t) = pg_query_performance_counter())
+
 #define INSTR_TIME_SET_CURRENT(t) \
 	((t) = pg_query_performance_counter())
 
@@ -168,13 +277,8 @@ GetTimerFrequency(void)
 
 #define INSTR_TIME_IS_ZERO(t)	((t).ticks == 0)
 
-
 #define INSTR_TIME_SET_ZERO(t)	((t).ticks = 0)
 
-#define INSTR_TIME_SET_CURRENT_LAZY(t) \
-	(INSTR_TIME_IS_ZERO(t) ? INSTR_TIME_SET_CURRENT(t), true : false)
-
-
 #define INSTR_TIME_ADD(x,y) \
 	((x).ticks += (y).ticks)
 
-- 
2.47.3


--vtqqtrpooseurzip
Content-Type: text/x-diff; charset=utf-8
Content-Disposition: attachment;
	filename="v12-0003-pg_test_timing-Add-fast-flag-to-test-fast-timing.patch"



^ permalink  raw  reply  [nested|flat] 271+ messages in thread

* [PATCH v12 2/3] Use time stamp counter to measure time on Linux/x86
@ 2025-07-26 00:57 Lukas Fittl <[email protected]>
  0 siblings, 0 replies; 271+ messages in thread

From: Lukas Fittl @ 2025-07-26 00:57 UTC (permalink / raw)

We switch to using the time stamp counter (TSC) instead of clock_gettime()
to reduce overhead of EXPLAIN (ANALYZE, TIME ON). Tests showed that runtime
is reduced by around 10% for queries moving lots of rows through the plan.

For now this is only enabled on Linux/x86, in case the system clocksource is
reported as TSC. Relying on the Linux kernel simplifies the logic to detect
if the present TSC is usable (frequency invariant, synchronized between
sockets, etc.). In all other cases we fallback to clock_gettime().

Note, that we intentionally use RDTSC in the fast paths, rather than RDTSCP.
RDTSCP waits for outstanding instructions to retire on out-of-order CPUs.
This adds noticably for little benefit in the typical InstrStartNode() /
InstrStopNode() use case. The macro to be used in such cases is called
INSTR_TIME_SET_CURRENT_FAST(). The original macro INSTR_TIME_SET_CURRENT()
uses RDTSCP and is supposed to be used when precision is more important
than performance.

Author: David Geier <[email protected]>
Author: Andres Freund <[email protected]>
Author: Lukas Fittl <[email protected]>
Reviewed-by:
Discussion: https://www.postgresql.org/message-id/flat/20200612232810.f46nbqkdhbutzqdg%40alap3.anarazel.de
---
 src/backend/access/heap/vacuumlazy.c |   4 +-
 src/backend/executor/instrument.c    |  12 +-
 src/backend/utils/init/postinit.c    |   3 +
 src/bin/pgbench/pgbench.c            |   3 +
 src/bin/psql/startup.c               |   4 +
 src/common/Makefile                  |   1 +
 src/common/instr_time.c              | 206 +++++++++++++++++++++++++++
 src/common/meson.build               |   1 +
 src/include/portability/instr_time.h | 136 +++++++++++++++---
 9 files changed, 348 insertions(+), 22 deletions(-)
 create mode 100644 src/common/instr_time.c

diff --git a/src/backend/access/heap/vacuumlazy.c b/src/backend/access/heap/vacuumlazy.c
index d2b031fdd06..5027048cac4 100644
--- a/src/backend/access/heap/vacuumlazy.c
+++ b/src/backend/access/heap/vacuumlazy.c
@@ -3409,8 +3409,8 @@ count_nondeletable_pages(LVRelState *vacrel, bool *lock_waiter_detected)
 			INSTR_TIME_SET_CURRENT(currenttime);
 			elapsed = currenttime;
 			INSTR_TIME_SUBTRACT(elapsed, starttime);
-			if ((INSTR_TIME_GET_MICROSEC(elapsed) / 1000)
-				>= VACUUM_TRUNCATE_LOCK_CHECK_INTERVAL)
+			if (INSTR_TIME_GET_MILLISEC(elapsed) >=
+				VACUUM_TRUNCATE_LOCK_CHECK_INTERVAL)
 			{
 				if (LockHasWaitersRelation(vacrel->rel, AccessExclusiveLock))
 				{
diff --git a/src/backend/executor/instrument.c b/src/backend/executor/instrument.c
index 56e635f4700..01f67c5d972 100644
--- a/src/backend/executor/instrument.c
+++ b/src/backend/executor/instrument.c
@@ -67,9 +67,13 @@ InstrInit(Instrumentation *instr, int instrument_options)
 void
 InstrStartNode(Instrumentation *instr)
 {
-	if (instr->need_timer &&
-		!INSTR_TIME_SET_CURRENT_LAZY(instr->starttime))
-		elog(ERROR, "InstrStartNode called twice in a row");
+	if (instr->need_timer)
+	{
+		if (!INSTR_TIME_IS_ZERO(instr->starttime))
+			elog(ERROR, "InstrStartNode called twice in a row");
+		else
+			INSTR_TIME_SET_CURRENT_FAST(instr->starttime);
+	}
 
 	/* save buffer usage totals at node entry, if needed */
 	if (instr->need_bufusage)
@@ -95,7 +99,7 @@ InstrStopNode(Instrumentation *instr, double nTuples)
 		if (INSTR_TIME_IS_ZERO(instr->starttime))
 			elog(ERROR, "InstrStopNode called without start");
 
-		INSTR_TIME_SET_CURRENT(endtime);
+		INSTR_TIME_SET_CURRENT_FAST(endtime);
 		INSTR_TIME_ACCUM_DIFF(instr->counter, endtime, instr->starttime);
 
 		INSTR_TIME_SET_ZERO(instr->starttime);
diff --git a/src/backend/utils/init/postinit.c b/src/backend/utils/init/postinit.c
index 641e535a73c..d573409903b 100644
--- a/src/backend/utils/init/postinit.c
+++ b/src/backend/utils/init/postinit.c
@@ -810,6 +810,9 @@ InitPostgres(const char *in_dbname, Oid dboid,
 	/* Initialize portal manager */
 	EnablePortalManager();
 
+	/* initialize high-precision interval timing */
+	INSTR_TIME_INITIALIZE();
+
 	/*
 	 * Load relcache entries for the shared system catalogs.  This must create
 	 * at least entries for pg_database and catalogs used for authentication.
diff --git a/src/bin/pgbench/pgbench.c b/src/bin/pgbench/pgbench.c
index 1515ed405ba..79bef2d2aec 100644
--- a/src/bin/pgbench/pgbench.c
+++ b/src/bin/pgbench/pgbench.c
@@ -7290,6 +7290,9 @@ main(int argc, char **argv)
 		initRandomState(&state[i].cs_func_rs);
 	}
 
+	/* initialize high-precision interval timing */
+	INSTR_TIME_INITIALIZE();
+
 	/* opening connection... */
 	con = doConnect();
 	if (con == NULL)
diff --git a/src/bin/psql/startup.c b/src/bin/psql/startup.c
index 249b6aa5169..d615df593c7 100644
--- a/src/bin/psql/startup.c
+++ b/src/bin/psql/startup.c
@@ -24,6 +24,7 @@
 #include "help.h"
 #include "input.h"
 #include "mainloop.h"
+#include "portability/instr_time.h"
 #include "settings.h"
 
 /*
@@ -327,6 +328,9 @@ main(int argc, char *argv[])
 
 	PQsetNoticeProcessor(pset.db, NoticeProcessor, NULL);
 
+	/* initialize high-precision interval timing */
+	INSTR_TIME_INITIALIZE();
+
 	SyncVariables();
 
 	if (options.list_dbs)
diff --git a/src/common/Makefile b/src/common/Makefile
index 2c720caa509..1a2fbbe887f 100644
--- a/src/common/Makefile
+++ b/src/common/Makefile
@@ -59,6 +59,7 @@ OBJS_COMMON = \
 	file_perm.o \
 	file_utils.o \
 	hashfn.o \
+	instr_time.o \
 	ip.o \
 	jsonapi.o \
 	keywords.o \
diff --git a/src/common/instr_time.c b/src/common/instr_time.c
new file mode 100644
index 00000000000..fdf47699f20
--- /dev/null
+++ b/src/common/instr_time.c
@@ -0,0 +1,206 @@
+/*-------------------------------------------------------------------------
+ *
+ * instr_time.c
+ *	   Non-inline parts of the portable high-precision interval timing
+ *	 implementation
+ *
+ * Portions Copyright (c) 2025, PostgreSQL Global Development Group
+ *
+ *
+ * IDENTIFICATION
+ *	  src/backend/port/instr_time.c
+ *
+ *-------------------------------------------------------------------------
+ */
+#include "postgres.h"
+
+#if defined(HAVE__GET_CPUID) || (defined(HAVE__CPUIDEX) && !defined(_MSC_VER))
+#include <cpuid.h>
+#endif
+
+#if defined(HAVE__CPUID) || (defined(HAVE__CPUIDEX) && defined(_MSC_VER))
+#include <intrin.h>
+#endif
+
+#include "portability/instr_time.h"
+
+#ifndef WIN32
+/*
+ * Stores what the number of cycles needs to be multiplied with to end up
+ * with nanoseconds using integer math. See comment in pg_initialize_rdtsc()
+ * for more details.
+ *
+ * By default assume we are using clock_gettime() as a fallback which uses
+ * nanoseconds as ticks. Hence, we set the multiplier to the precision scalar
+ * so that the division in INSTR_TIME_GET_NANOSEC() won't change the nanoseconds.
+ *
+ * When using the RDTSC instruction directly this is filled in during initialization
+ * based on the relevant CPUID fields.
+ */
+int64		ticks_per_ns_scaled = TICKS_TO_NS_PRECISION;
+int64		ticks_per_sec = NS_PER_S;
+int64		max_ticks_no_overflow = PG_INT64_MAX / TICKS_TO_NS_PRECISION;
+
+#if defined(__x86_64__) && defined(__linux__)
+/*
+ * Indicates if RDTSC can be used (Linux/x86 only, when OS uses TSC clocksource)
+ */
+bool		has_rdtsc = false;
+
+/*
+ * Indicates if RDTSCP can be used. True if RDTSC can be used and RDTSCP is available.
+ */
+bool		has_rdtscp = false;
+
+#define CPUID_HYPERVISOR_VMWARE(words) (words[1] == 0x61774d56 && words[2] == 0x4d566572 && words[3] == 0x65726177) /* VMwareVMware */
+#define CPUID_HYPERVISOR_KVM(words) (words[1] == 0x4b4d564b && words[2] == 0x564b4d56 && words[3] == 0x0000004d)	/* KVMKVMKVM */
+
+static bool
+get_tsc_frequency_khz(uint32 *tsc_freq)
+{
+	uint32		r[4] = {0, 0, 0, 0};
+
+#if defined(HAVE__GET_CPUID)
+	__get_cpuid(0x15, &r[0] /* denominator */ , &r[1] /* numerator */ , &r[2] /* hz */ , &r[3]);
+#elif defined(HAVE__CPUID)
+	__cpuid(r, 0x15);
+#else
+#error cpuid instruction not available
+#endif
+
+	if (r[2] > 0)
+	{
+		if (r[0] == 0 || r[1] == 0)
+			return false;
+
+		*tsc_freq = r[2] / 1000 * r[1] / r[0];
+		return true;
+	}
+
+	/* Some CPUs only report frequency in 16H */
+
+#if defined(HAVE__GET_CPUID)
+	__get_cpuid(0x16, &r[0] /* base_mhz */ , &r[1], &r[2], &r[3]);
+#elif defined(HAVE__CPUID)
+	__cpuid(r, 0x16);
+#else
+#error cpuid instruction not available
+#endif
+
+	if (r[0] > 0)
+	{
+		*tsc_freq = r[0] * 1000;
+		return true;
+	}
+
+	/*
+	 * Check if we have a KVM or VMware Hypervisor passing down TSC frequency
+	 * to us in a guest VM
+	 *
+	 * Note that accessing the 0x40000000 leaf for Hypervisor info requires
+	 * use of __cpuidex to set ECX to 0. The similar __get_cpuid_count
+	 * function does not work as expected since it contains a check for
+	 * __get_cpuid_max, which has been observed to be lower than the special
+	 * Hypervisor leaf.
+	 */
+#if defined(HAVE__CPUIDEX)
+	__cpuidex((int32 *) r, 0x40000000, 0);
+	if (r[0] >= 0x40000010 && (CPUID_HYPERVISOR_VMWARE(r) || CPUID_HYPERVISOR_KVM(r)))
+	{
+		__cpuidex((int32 *) r, 0x40000010, 0);
+		if (r[0] > 0)
+		{
+			*tsc_freq = r[0];
+			return true;
+		}
+	}
+#endif
+
+	return false;
+}
+
+static bool
+is_rdtscp_available()
+{
+	uint32		r[4] = {0, 0, 0, 0};
+
+#if defined(HAVE__GET_CPUID)
+	if (!__get_cpuid(0x80000001, &r[0], &r[1], &r[2], &r[3]))
+		return false;
+#elif defined(HAVE__CPUID)
+	__cpuid(r, 0x80000001);
+#else
+#error cpuid instruction not available
+#endif
+
+	return (r[3] & (1 << 27)) != 0;
+}
+
+/*
+ * Decide whether we use the RDTSC instruction at runtime, for Linux/x86,
+ * instead of incurring the overhead of a full clock_gettime() call.
+ *
+ * This can't be reliably determined at compile time, since the
+ * availability of an "invariant" TSC (that is not affected by CPU
+ * frequency changes) is dependent on the CPU architecture. Additionally,
+ * there are cases where TSC availability is impacted by virtualization,
+ * where a simple cpuid feature check would not be enough.
+ *
+ * Since Linux already does a significant amount of work to determine
+ * whether TSC is a viable clock source, decide based on that.
+ */
+void
+pg_initialize_rdtsc(void)
+{
+	FILE	   *fp = fopen("/sys/devices/system/clocksource/clocksource0/current_clocksource", "r");
+
+	if (fp)
+	{
+		char		buf[128];
+
+		if (fgets(buf, sizeof(buf), fp) != NULL && strcmp(buf, "tsc\n") == 0)
+		{
+			/*
+			 * Compute baseline CPU peformance, determines speed at which
+			 * RDTSC advances.
+			 */
+			uint32		tsc_freq;
+
+			if (get_tsc_frequency_khz(&tsc_freq))
+			{
+				/*
+				 * Ticks to nanoseconds conversion requires floating point
+				 * math because because:
+				 *
+				 * sec = ticks / frequency_hz ns  = ticks / frequency_hz *
+				 * 1,000,000,000 ns  = ticks * (1,000,000,000 / frequency_hz)
+				 * ns  = ticks * (1,000,000 / frequency_khz) <-- now in
+				 * kilohertz
+				 *
+				 * Here, 'ns' is usually a floating number. For example for a
+				 * 2.5 GHz CPU the scaling factor becomes 1,000,000 /
+				 * 2,500,000 = 1.2.
+				 *
+				 * To be able to use integer math we work around the lack of
+				 * precision. We first scale the integer up and after the
+				 * multiplication by the number of ticks in
+				 * INSTR_TIME_GET_NANOSEC() we divide again by the same value.
+				 * We picked the scaler such that it provides enough precision
+				 * and is a power-of-two which allows for shifting instead of
+				 * doing an integer division.
+				 */
+				ticks_per_ns_scaled = INT64CONST(1000000) * TICKS_TO_NS_PRECISION / tsc_freq;
+				ticks_per_sec = tsc_freq * 1000;	/* KHz->Hz */
+				max_ticks_no_overflow = PG_INT64_MAX / ticks_per_ns_scaled;
+
+				has_rdtsc = true;
+				has_rdtscp = is_rdtscp_available();
+			}
+		}
+
+		fclose(fp);
+	}
+}
+#endif							/* defined(__x86_64__) && defined(__linux__) */
+
+#endif							/* WIN32 */
diff --git a/src/common/meson.build b/src/common/meson.build
index 1540ba67cca..62b90b3e609 100644
--- a/src/common/meson.build
+++ b/src/common/meson.build
@@ -13,6 +13,7 @@ common_sources = files(
   'file_perm.c',
   'file_utils.c',
   'hashfn.c',
+  'instr_time.c',
   'ip.c',
   'jsonapi.c',
   'keywords.c',
diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h
index f71a851b18d..e2e339a0c4f 100644
--- a/src/include/portability/instr_time.h
+++ b/src/include/portability/instr_time.h
@@ -4,9 +4,11 @@
  *	  portable high-precision interval timing
  *
  * This file provides an abstraction layer to hide portability issues in
- * interval timing.  On Unix we use clock_gettime(), and on Windows we use
- * QueryPerformanceCounter().  These macros also give some breathing room to
- * use other high-precision-timing APIs.
+ * interval timing. On Linux/x86 we use the rdtsc instruction when a TSC
+ * clocksource is also used on the host OS.  Otherwise, and on other
+ * Unix-like systems we use clock_gettime() and on Windows we use
+ * QueryPerformanceCounter(). These macros also give some breathing
+ * room to use other high-precision-timing APIs.
  *
  * The basic data type is instr_time, which all callers should treat as an
  * opaque typedef.  instr_time can store either an absolute time (of
@@ -17,10 +19,11 @@
  *
  * INSTR_TIME_SET_ZERO(t)			set t to zero (memset is acceptable too)
  *
- * INSTR_TIME_SET_CURRENT(t)		set t to current time
+ * INSTR_TIME_SET_CURRENT_FAST(t)	set t to current time without waiting
+ * 									for instructions in out-of-order window
  *
- * INSTR_TIME_SET_CURRENT_LAZY(t)	set t to current time if t is zero,
- *									evaluates to whether t changed
+ * INSTR_TIME_SET_CURRENT(t)		set t to current time while waiting for
+ * 									instructions in OOO to retire
  *
  * INSTR_TIME_ADD(x, y)				x += y
  *
@@ -81,6 +84,15 @@ typedef struct instr_time
 
 #ifndef WIN32
 
+/*
+ * Make sure this is a power-of-two, so that the compiler can turn the
+ * multiplications and divisions into shifts.
+ */
+#define TICKS_TO_NS_PRECISION (1<<14)
+
+extern int64 ticks_per_ns_scaled;
+extern int64 ticks_per_sec;
+extern int64 max_ticks_no_overflow;
 
 /* Use clock_gettime() */
 
@@ -106,9 +118,18 @@ typedef struct instr_time
 #define PG_INSTR_CLOCK	CLOCK_REALTIME
 #endif
 
-/* helper for INSTR_TIME_SET_CURRENT */
+#if defined(__x86_64__) && defined(__linux__)
+#include <x86intrin.h>
+#include <cpuid.h>
+
+extern bool has_rdtsc;
+extern bool has_rdtscp;
+
+extern void pg_initialize_rdtsc(void);
+#endif
+
 static inline instr_time
-pg_clock_gettime_ns(void)
+pg_clock_gettime(void)
 {
 	instr_time	now;
 	struct timespec tmp;
@@ -119,11 +140,94 @@ pg_clock_gettime_ns(void)
 	return now;
 }
 
+static inline instr_time
+pg_get_ticks_fast(void)
+{
+#if defined(__x86_64__) && defined(__linux__)
+	if (has_rdtsc)
+	{
+		instr_time	now;
+
+		now.ticks = __rdtsc();
+		return now;
+	}
+#endif
+
+	return pg_clock_gettime();
+}
+
+static inline instr_time
+pg_get_ticks(void)
+{
+#if defined(__x86_64__) && defined(__linux__)
+	if (has_rdtscp)
+	{
+		instr_time	now;
+		uint32		unused;
+
+		now.ticks = __rdtscp(&unused);
+		return now;
+	}
+#endif
+
+	return pg_clock_gettime();
+}
+
+static inline int64_t
+pg_ticks_to_ns(instr_time t)
+{
+	/*
+	 * Would multiplication overflow? If so perform computation in two parts.
+	 * Check overflow without actually overflowing via: a * b > max <=> a >
+	 * max / b
+	 */
+	int64		ns = 0;
+
+	if (unlikely(t.ticks > max_ticks_no_overflow))
+	{
+		/*
+		 * Compute how often the maximum number of ticks fits completely into
+		 * the number of elapsed ticks and convert that number into
+		 * nanoseconds. Then multiply by the count to arrive at the final
+		 * 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		max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION;
+
+		ns = max_ns * count;
+
+		/*
+		 * 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);
+	}
+
+	ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION;
+	return ns;
+}
+
+static inline void
+pg_initialize_get_ticks()
+{
+#if defined(__x86_64__) && defined(__linux__)
+	pg_initialize_rdtsc();
+#endif
+}
+
+#define INSTR_TIME_INITIALIZE() \
+	pg_initialize_get_ticks()
+
+#define INSTR_TIME_SET_CURRENT_FAST(t) \
+	((t) = pg_get_ticks_fast())
+
 #define INSTR_TIME_SET_CURRENT(t) \
-	((t) = pg_clock_gettime_ns())
+	((t) = pg_get_ticks())
 
 #define INSTR_TIME_GET_NANOSEC(t) \
-	((int64) (t).ticks)
+	pg_ticks_to_ns(t)
 
 
 #else							/* WIN32 */
@@ -131,7 +235,7 @@ pg_clock_gettime_ns(void)
 
 /* Use QueryPerformanceCounter() */
 
-/* helper for INSTR_TIME_SET_CURRENT */
+/* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */
 static inline instr_time
 pg_query_performance_counter(void)
 {
@@ -153,6 +257,11 @@ GetTimerFrequency(void)
 	return (double) f.QuadPart;
 }
 
+#define INSTR_TIME_INITIALIZE()
+
+#define INSTR_TIME_SET_CURRENT_FAST(t) \
+	((t) = pg_query_performance_counter())
+
 #define INSTR_TIME_SET_CURRENT(t) \
 	((t) = pg_query_performance_counter())
 
@@ -168,13 +277,8 @@ GetTimerFrequency(void)
 
 #define INSTR_TIME_IS_ZERO(t)	((t).ticks == 0)
 
-
 #define INSTR_TIME_SET_ZERO(t)	((t).ticks = 0)
 
-#define INSTR_TIME_SET_CURRENT_LAZY(t) \
-	(INSTR_TIME_IS_ZERO(t) ? INSTR_TIME_SET_CURRENT(t), true : false)
-
-
 #define INSTR_TIME_ADD(x,y) \
 	((x).ticks += (y).ticks)
 
-- 
2.47.3


--vtqqtrpooseurzip
Content-Type: text/x-diff; charset=utf-8
Content-Disposition: attachment;
	filename="v12-0003-pg_test_timing-Add-fast-flag-to-test-fast-timing.patch"



^ permalink  raw  reply  [nested|flat] 271+ messages in thread

* [PATCH v12 2/3] Use time stamp counter to measure time on Linux/x86
@ 2025-07-26 00:57 Lukas Fittl <[email protected]>
  0 siblings, 0 replies; 271+ messages in thread

From: Lukas Fittl @ 2025-07-26 00:57 UTC (permalink / raw)

We switch to using the time stamp counter (TSC) instead of clock_gettime()
to reduce overhead of EXPLAIN (ANALYZE, TIME ON). Tests showed that runtime
is reduced by around 10% for queries moving lots of rows through the plan.

For now this is only enabled on Linux/x86, in case the system clocksource is
reported as TSC. Relying on the Linux kernel simplifies the logic to detect
if the present TSC is usable (frequency invariant, synchronized between
sockets, etc.). In all other cases we fallback to clock_gettime().

Note, that we intentionally use RDTSC in the fast paths, rather than RDTSCP.
RDTSCP waits for outstanding instructions to retire on out-of-order CPUs.
This adds noticably for little benefit in the typical InstrStartNode() /
InstrStopNode() use case. The macro to be used in such cases is called
INSTR_TIME_SET_CURRENT_FAST(). The original macro INSTR_TIME_SET_CURRENT()
uses RDTSCP and is supposed to be used when precision is more important
than performance.

Author: David Geier <[email protected]>
Author: Andres Freund <[email protected]>
Author: Lukas Fittl <[email protected]>
Reviewed-by:
Discussion: https://www.postgresql.org/message-id/flat/20200612232810.f46nbqkdhbutzqdg%40alap3.anarazel.de
---
 src/backend/access/heap/vacuumlazy.c |   4 +-
 src/backend/executor/instrument.c    |  12 +-
 src/backend/utils/init/postinit.c    |   3 +
 src/bin/pgbench/pgbench.c            |   3 +
 src/bin/psql/startup.c               |   4 +
 src/common/Makefile                  |   1 +
 src/common/instr_time.c              | 206 +++++++++++++++++++++++++++
 src/common/meson.build               |   1 +
 src/include/portability/instr_time.h | 136 +++++++++++++++---
 9 files changed, 348 insertions(+), 22 deletions(-)
 create mode 100644 src/common/instr_time.c

diff --git a/src/backend/access/heap/vacuumlazy.c b/src/backend/access/heap/vacuumlazy.c
index d2b031fdd06..5027048cac4 100644
--- a/src/backend/access/heap/vacuumlazy.c
+++ b/src/backend/access/heap/vacuumlazy.c
@@ -3409,8 +3409,8 @@ count_nondeletable_pages(LVRelState *vacrel, bool *lock_waiter_detected)
 			INSTR_TIME_SET_CURRENT(currenttime);
 			elapsed = currenttime;
 			INSTR_TIME_SUBTRACT(elapsed, starttime);
-			if ((INSTR_TIME_GET_MICROSEC(elapsed) / 1000)
-				>= VACUUM_TRUNCATE_LOCK_CHECK_INTERVAL)
+			if (INSTR_TIME_GET_MILLISEC(elapsed) >=
+				VACUUM_TRUNCATE_LOCK_CHECK_INTERVAL)
 			{
 				if (LockHasWaitersRelation(vacrel->rel, AccessExclusiveLock))
 				{
diff --git a/src/backend/executor/instrument.c b/src/backend/executor/instrument.c
index 56e635f4700..01f67c5d972 100644
--- a/src/backend/executor/instrument.c
+++ b/src/backend/executor/instrument.c
@@ -67,9 +67,13 @@ InstrInit(Instrumentation *instr, int instrument_options)
 void
 InstrStartNode(Instrumentation *instr)
 {
-	if (instr->need_timer &&
-		!INSTR_TIME_SET_CURRENT_LAZY(instr->starttime))
-		elog(ERROR, "InstrStartNode called twice in a row");
+	if (instr->need_timer)
+	{
+		if (!INSTR_TIME_IS_ZERO(instr->starttime))
+			elog(ERROR, "InstrStartNode called twice in a row");
+		else
+			INSTR_TIME_SET_CURRENT_FAST(instr->starttime);
+	}
 
 	/* save buffer usage totals at node entry, if needed */
 	if (instr->need_bufusage)
@@ -95,7 +99,7 @@ InstrStopNode(Instrumentation *instr, double nTuples)
 		if (INSTR_TIME_IS_ZERO(instr->starttime))
 			elog(ERROR, "InstrStopNode called without start");
 
-		INSTR_TIME_SET_CURRENT(endtime);
+		INSTR_TIME_SET_CURRENT_FAST(endtime);
 		INSTR_TIME_ACCUM_DIFF(instr->counter, endtime, instr->starttime);
 
 		INSTR_TIME_SET_ZERO(instr->starttime);
diff --git a/src/backend/utils/init/postinit.c b/src/backend/utils/init/postinit.c
index 641e535a73c..d573409903b 100644
--- a/src/backend/utils/init/postinit.c
+++ b/src/backend/utils/init/postinit.c
@@ -810,6 +810,9 @@ InitPostgres(const char *in_dbname, Oid dboid,
 	/* Initialize portal manager */
 	EnablePortalManager();
 
+	/* initialize high-precision interval timing */
+	INSTR_TIME_INITIALIZE();
+
 	/*
 	 * Load relcache entries for the shared system catalogs.  This must create
 	 * at least entries for pg_database and catalogs used for authentication.
diff --git a/src/bin/pgbench/pgbench.c b/src/bin/pgbench/pgbench.c
index 1515ed405ba..79bef2d2aec 100644
--- a/src/bin/pgbench/pgbench.c
+++ b/src/bin/pgbench/pgbench.c
@@ -7290,6 +7290,9 @@ main(int argc, char **argv)
 		initRandomState(&state[i].cs_func_rs);
 	}
 
+	/* initialize high-precision interval timing */
+	INSTR_TIME_INITIALIZE();
+
 	/* opening connection... */
 	con = doConnect();
 	if (con == NULL)
diff --git a/src/bin/psql/startup.c b/src/bin/psql/startup.c
index 249b6aa5169..d615df593c7 100644
--- a/src/bin/psql/startup.c
+++ b/src/bin/psql/startup.c
@@ -24,6 +24,7 @@
 #include "help.h"
 #include "input.h"
 #include "mainloop.h"
+#include "portability/instr_time.h"
 #include "settings.h"
 
 /*
@@ -327,6 +328,9 @@ main(int argc, char *argv[])
 
 	PQsetNoticeProcessor(pset.db, NoticeProcessor, NULL);
 
+	/* initialize high-precision interval timing */
+	INSTR_TIME_INITIALIZE();
+
 	SyncVariables();
 
 	if (options.list_dbs)
diff --git a/src/common/Makefile b/src/common/Makefile
index 2c720caa509..1a2fbbe887f 100644
--- a/src/common/Makefile
+++ b/src/common/Makefile
@@ -59,6 +59,7 @@ OBJS_COMMON = \
 	file_perm.o \
 	file_utils.o \
 	hashfn.o \
+	instr_time.o \
 	ip.o \
 	jsonapi.o \
 	keywords.o \
diff --git a/src/common/instr_time.c b/src/common/instr_time.c
new file mode 100644
index 00000000000..fdf47699f20
--- /dev/null
+++ b/src/common/instr_time.c
@@ -0,0 +1,206 @@
+/*-------------------------------------------------------------------------
+ *
+ * instr_time.c
+ *	   Non-inline parts of the portable high-precision interval timing
+ *	 implementation
+ *
+ * Portions Copyright (c) 2025, PostgreSQL Global Development Group
+ *
+ *
+ * IDENTIFICATION
+ *	  src/backend/port/instr_time.c
+ *
+ *-------------------------------------------------------------------------
+ */
+#include "postgres.h"
+
+#if defined(HAVE__GET_CPUID) || (defined(HAVE__CPUIDEX) && !defined(_MSC_VER))
+#include <cpuid.h>
+#endif
+
+#if defined(HAVE__CPUID) || (defined(HAVE__CPUIDEX) && defined(_MSC_VER))
+#include <intrin.h>
+#endif
+
+#include "portability/instr_time.h"
+
+#ifndef WIN32
+/*
+ * Stores what the number of cycles needs to be multiplied with to end up
+ * with nanoseconds using integer math. See comment in pg_initialize_rdtsc()
+ * for more details.
+ *
+ * By default assume we are using clock_gettime() as a fallback which uses
+ * nanoseconds as ticks. Hence, we set the multiplier to the precision scalar
+ * so that the division in INSTR_TIME_GET_NANOSEC() won't change the nanoseconds.
+ *
+ * When using the RDTSC instruction directly this is filled in during initialization
+ * based on the relevant CPUID fields.
+ */
+int64		ticks_per_ns_scaled = TICKS_TO_NS_PRECISION;
+int64		ticks_per_sec = NS_PER_S;
+int64		max_ticks_no_overflow = PG_INT64_MAX / TICKS_TO_NS_PRECISION;
+
+#if defined(__x86_64__) && defined(__linux__)
+/*
+ * Indicates if RDTSC can be used (Linux/x86 only, when OS uses TSC clocksource)
+ */
+bool		has_rdtsc = false;
+
+/*
+ * Indicates if RDTSCP can be used. True if RDTSC can be used and RDTSCP is available.
+ */
+bool		has_rdtscp = false;
+
+#define CPUID_HYPERVISOR_VMWARE(words) (words[1] == 0x61774d56 && words[2] == 0x4d566572 && words[3] == 0x65726177) /* VMwareVMware */
+#define CPUID_HYPERVISOR_KVM(words) (words[1] == 0x4b4d564b && words[2] == 0x564b4d56 && words[3] == 0x0000004d)	/* KVMKVMKVM */
+
+static bool
+get_tsc_frequency_khz(uint32 *tsc_freq)
+{
+	uint32		r[4] = {0, 0, 0, 0};
+
+#if defined(HAVE__GET_CPUID)
+	__get_cpuid(0x15, &r[0] /* denominator */ , &r[1] /* numerator */ , &r[2] /* hz */ , &r[3]);
+#elif defined(HAVE__CPUID)
+	__cpuid(r, 0x15);
+#else
+#error cpuid instruction not available
+#endif
+
+	if (r[2] > 0)
+	{
+		if (r[0] == 0 || r[1] == 0)
+			return false;
+
+		*tsc_freq = r[2] / 1000 * r[1] / r[0];
+		return true;
+	}
+
+	/* Some CPUs only report frequency in 16H */
+
+#if defined(HAVE__GET_CPUID)
+	__get_cpuid(0x16, &r[0] /* base_mhz */ , &r[1], &r[2], &r[3]);
+#elif defined(HAVE__CPUID)
+	__cpuid(r, 0x16);
+#else
+#error cpuid instruction not available
+#endif
+
+	if (r[0] > 0)
+	{
+		*tsc_freq = r[0] * 1000;
+		return true;
+	}
+
+	/*
+	 * Check if we have a KVM or VMware Hypervisor passing down TSC frequency
+	 * to us in a guest VM
+	 *
+	 * Note that accessing the 0x40000000 leaf for Hypervisor info requires
+	 * use of __cpuidex to set ECX to 0. The similar __get_cpuid_count
+	 * function does not work as expected since it contains a check for
+	 * __get_cpuid_max, which has been observed to be lower than the special
+	 * Hypervisor leaf.
+	 */
+#if defined(HAVE__CPUIDEX)
+	__cpuidex((int32 *) r, 0x40000000, 0);
+	if (r[0] >= 0x40000010 && (CPUID_HYPERVISOR_VMWARE(r) || CPUID_HYPERVISOR_KVM(r)))
+	{
+		__cpuidex((int32 *) r, 0x40000010, 0);
+		if (r[0] > 0)
+		{
+			*tsc_freq = r[0];
+			return true;
+		}
+	}
+#endif
+
+	return false;
+}
+
+static bool
+is_rdtscp_available()
+{
+	uint32		r[4] = {0, 0, 0, 0};
+
+#if defined(HAVE__GET_CPUID)
+	if (!__get_cpuid(0x80000001, &r[0], &r[1], &r[2], &r[3]))
+		return false;
+#elif defined(HAVE__CPUID)
+	__cpuid(r, 0x80000001);
+#else
+#error cpuid instruction not available
+#endif
+
+	return (r[3] & (1 << 27)) != 0;
+}
+
+/*
+ * Decide whether we use the RDTSC instruction at runtime, for Linux/x86,
+ * instead of incurring the overhead of a full clock_gettime() call.
+ *
+ * This can't be reliably determined at compile time, since the
+ * availability of an "invariant" TSC (that is not affected by CPU
+ * frequency changes) is dependent on the CPU architecture. Additionally,
+ * there are cases where TSC availability is impacted by virtualization,
+ * where a simple cpuid feature check would not be enough.
+ *
+ * Since Linux already does a significant amount of work to determine
+ * whether TSC is a viable clock source, decide based on that.
+ */
+void
+pg_initialize_rdtsc(void)
+{
+	FILE	   *fp = fopen("/sys/devices/system/clocksource/clocksource0/current_clocksource", "r");
+
+	if (fp)
+	{
+		char		buf[128];
+
+		if (fgets(buf, sizeof(buf), fp) != NULL && strcmp(buf, "tsc\n") == 0)
+		{
+			/*
+			 * Compute baseline CPU peformance, determines speed at which
+			 * RDTSC advances.
+			 */
+			uint32		tsc_freq;
+
+			if (get_tsc_frequency_khz(&tsc_freq))
+			{
+				/*
+				 * Ticks to nanoseconds conversion requires floating point
+				 * math because because:
+				 *
+				 * sec = ticks / frequency_hz ns  = ticks / frequency_hz *
+				 * 1,000,000,000 ns  = ticks * (1,000,000,000 / frequency_hz)
+				 * ns  = ticks * (1,000,000 / frequency_khz) <-- now in
+				 * kilohertz
+				 *
+				 * Here, 'ns' is usually a floating number. For example for a
+				 * 2.5 GHz CPU the scaling factor becomes 1,000,000 /
+				 * 2,500,000 = 1.2.
+				 *
+				 * To be able to use integer math we work around the lack of
+				 * precision. We first scale the integer up and after the
+				 * multiplication by the number of ticks in
+				 * INSTR_TIME_GET_NANOSEC() we divide again by the same value.
+				 * We picked the scaler such that it provides enough precision
+				 * and is a power-of-two which allows for shifting instead of
+				 * doing an integer division.
+				 */
+				ticks_per_ns_scaled = INT64CONST(1000000) * TICKS_TO_NS_PRECISION / tsc_freq;
+				ticks_per_sec = tsc_freq * 1000;	/* KHz->Hz */
+				max_ticks_no_overflow = PG_INT64_MAX / ticks_per_ns_scaled;
+
+				has_rdtsc = true;
+				has_rdtscp = is_rdtscp_available();
+			}
+		}
+
+		fclose(fp);
+	}
+}
+#endif							/* defined(__x86_64__) && defined(__linux__) */
+
+#endif							/* WIN32 */
diff --git a/src/common/meson.build b/src/common/meson.build
index 1540ba67cca..62b90b3e609 100644
--- a/src/common/meson.build
+++ b/src/common/meson.build
@@ -13,6 +13,7 @@ common_sources = files(
   'file_perm.c',
   'file_utils.c',
   'hashfn.c',
+  'instr_time.c',
   'ip.c',
   'jsonapi.c',
   'keywords.c',
diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h
index f71a851b18d..e2e339a0c4f 100644
--- a/src/include/portability/instr_time.h
+++ b/src/include/portability/instr_time.h
@@ -4,9 +4,11 @@
  *	  portable high-precision interval timing
  *
  * This file provides an abstraction layer to hide portability issues in
- * interval timing.  On Unix we use clock_gettime(), and on Windows we use
- * QueryPerformanceCounter().  These macros also give some breathing room to
- * use other high-precision-timing APIs.
+ * interval timing. On Linux/x86 we use the rdtsc instruction when a TSC
+ * clocksource is also used on the host OS.  Otherwise, and on other
+ * Unix-like systems we use clock_gettime() and on Windows we use
+ * QueryPerformanceCounter(). These macros also give some breathing
+ * room to use other high-precision-timing APIs.
  *
  * The basic data type is instr_time, which all callers should treat as an
  * opaque typedef.  instr_time can store either an absolute time (of
@@ -17,10 +19,11 @@
  *
  * INSTR_TIME_SET_ZERO(t)			set t to zero (memset is acceptable too)
  *
- * INSTR_TIME_SET_CURRENT(t)		set t to current time
+ * INSTR_TIME_SET_CURRENT_FAST(t)	set t to current time without waiting
+ * 									for instructions in out-of-order window
  *
- * INSTR_TIME_SET_CURRENT_LAZY(t)	set t to current time if t is zero,
- *									evaluates to whether t changed
+ * INSTR_TIME_SET_CURRENT(t)		set t to current time while waiting for
+ * 									instructions in OOO to retire
  *
  * INSTR_TIME_ADD(x, y)				x += y
  *
@@ -81,6 +84,15 @@ typedef struct instr_time
 
 #ifndef WIN32
 
+/*
+ * Make sure this is a power-of-two, so that the compiler can turn the
+ * multiplications and divisions into shifts.
+ */
+#define TICKS_TO_NS_PRECISION (1<<14)
+
+extern int64 ticks_per_ns_scaled;
+extern int64 ticks_per_sec;
+extern int64 max_ticks_no_overflow;
 
 /* Use clock_gettime() */
 
@@ -106,9 +118,18 @@ typedef struct instr_time
 #define PG_INSTR_CLOCK	CLOCK_REALTIME
 #endif
 
-/* helper for INSTR_TIME_SET_CURRENT */
+#if defined(__x86_64__) && defined(__linux__)
+#include <x86intrin.h>
+#include <cpuid.h>
+
+extern bool has_rdtsc;
+extern bool has_rdtscp;
+
+extern void pg_initialize_rdtsc(void);
+#endif
+
 static inline instr_time
-pg_clock_gettime_ns(void)
+pg_clock_gettime(void)
 {
 	instr_time	now;
 	struct timespec tmp;
@@ -119,11 +140,94 @@ pg_clock_gettime_ns(void)
 	return now;
 }
 
+static inline instr_time
+pg_get_ticks_fast(void)
+{
+#if defined(__x86_64__) && defined(__linux__)
+	if (has_rdtsc)
+	{
+		instr_time	now;
+
+		now.ticks = __rdtsc();
+		return now;
+	}
+#endif
+
+	return pg_clock_gettime();
+}
+
+static inline instr_time
+pg_get_ticks(void)
+{
+#if defined(__x86_64__) && defined(__linux__)
+	if (has_rdtscp)
+	{
+		instr_time	now;
+		uint32		unused;
+
+		now.ticks = __rdtscp(&unused);
+		return now;
+	}
+#endif
+
+	return pg_clock_gettime();
+}
+
+static inline int64_t
+pg_ticks_to_ns(instr_time t)
+{
+	/*
+	 * Would multiplication overflow? If so perform computation in two parts.
+	 * Check overflow without actually overflowing via: a * b > max <=> a >
+	 * max / b
+	 */
+	int64		ns = 0;
+
+	if (unlikely(t.ticks > max_ticks_no_overflow))
+	{
+		/*
+		 * Compute how often the maximum number of ticks fits completely into
+		 * the number of elapsed ticks and convert that number into
+		 * nanoseconds. Then multiply by the count to arrive at the final
+		 * 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		max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION;
+
+		ns = max_ns * count;
+
+		/*
+		 * 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);
+	}
+
+	ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION;
+	return ns;
+}
+
+static inline void
+pg_initialize_get_ticks()
+{
+#if defined(__x86_64__) && defined(__linux__)
+	pg_initialize_rdtsc();
+#endif
+}
+
+#define INSTR_TIME_INITIALIZE() \
+	pg_initialize_get_ticks()
+
+#define INSTR_TIME_SET_CURRENT_FAST(t) \
+	((t) = pg_get_ticks_fast())
+
 #define INSTR_TIME_SET_CURRENT(t) \
-	((t) = pg_clock_gettime_ns())
+	((t) = pg_get_ticks())
 
 #define INSTR_TIME_GET_NANOSEC(t) \
-	((int64) (t).ticks)
+	pg_ticks_to_ns(t)
 
 
 #else							/* WIN32 */
@@ -131,7 +235,7 @@ pg_clock_gettime_ns(void)
 
 /* Use QueryPerformanceCounter() */
 
-/* helper for INSTR_TIME_SET_CURRENT */
+/* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */
 static inline instr_time
 pg_query_performance_counter(void)
 {
@@ -153,6 +257,11 @@ GetTimerFrequency(void)
 	return (double) f.QuadPart;
 }
 
+#define INSTR_TIME_INITIALIZE()
+
+#define INSTR_TIME_SET_CURRENT_FAST(t) \
+	((t) = pg_query_performance_counter())
+
 #define INSTR_TIME_SET_CURRENT(t) \
 	((t) = pg_query_performance_counter())
 
@@ -168,13 +277,8 @@ GetTimerFrequency(void)
 
 #define INSTR_TIME_IS_ZERO(t)	((t).ticks == 0)
 
-
 #define INSTR_TIME_SET_ZERO(t)	((t).ticks = 0)
 
-#define INSTR_TIME_SET_CURRENT_LAZY(t) \
-	(INSTR_TIME_IS_ZERO(t) ? INSTR_TIME_SET_CURRENT(t), true : false)
-
-
 #define INSTR_TIME_ADD(x,y) \
 	((x).ticks += (y).ticks)
 
-- 
2.47.3


--vtqqtrpooseurzip
Content-Type: text/x-diff; charset=utf-8
Content-Disposition: attachment;
	filename="v12-0003-pg_test_timing-Add-fast-flag-to-test-fast-timing.patch"



^ permalink  raw  reply  [nested|flat] 271+ messages in thread

* [PATCH v12 2/3] Use time stamp counter to measure time on Linux/x86
@ 2025-07-26 00:57 Lukas Fittl <[email protected]>
  0 siblings, 0 replies; 271+ messages in thread

From: Lukas Fittl @ 2025-07-26 00:57 UTC (permalink / raw)

We switch to using the time stamp counter (TSC) instead of clock_gettime()
to reduce overhead of EXPLAIN (ANALYZE, TIME ON). Tests showed that runtime
is reduced by around 10% for queries moving lots of rows through the plan.

For now this is only enabled on Linux/x86, in case the system clocksource is
reported as TSC. Relying on the Linux kernel simplifies the logic to detect
if the present TSC is usable (frequency invariant, synchronized between
sockets, etc.). In all other cases we fallback to clock_gettime().

Note, that we intentionally use RDTSC in the fast paths, rather than RDTSCP.
RDTSCP waits for outstanding instructions to retire on out-of-order CPUs.
This adds noticably for little benefit in the typical InstrStartNode() /
InstrStopNode() use case. The macro to be used in such cases is called
INSTR_TIME_SET_CURRENT_FAST(). The original macro INSTR_TIME_SET_CURRENT()
uses RDTSCP and is supposed to be used when precision is more important
than performance.

Author: David Geier <[email protected]>
Author: Andres Freund <[email protected]>
Author: Lukas Fittl <[email protected]>
Reviewed-by:
Discussion: https://www.postgresql.org/message-id/flat/20200612232810.f46nbqkdhbutzqdg%40alap3.anarazel.de
---
 src/backend/access/heap/vacuumlazy.c |   4 +-
 src/backend/executor/instrument.c    |  12 +-
 src/backend/utils/init/postinit.c    |   3 +
 src/bin/pgbench/pgbench.c            |   3 +
 src/bin/psql/startup.c               |   4 +
 src/common/Makefile                  |   1 +
 src/common/instr_time.c              | 206 +++++++++++++++++++++++++++
 src/common/meson.build               |   1 +
 src/include/portability/instr_time.h | 136 +++++++++++++++---
 9 files changed, 348 insertions(+), 22 deletions(-)
 create mode 100644 src/common/instr_time.c

diff --git a/src/backend/access/heap/vacuumlazy.c b/src/backend/access/heap/vacuumlazy.c
index d2b031fdd06..5027048cac4 100644
--- a/src/backend/access/heap/vacuumlazy.c
+++ b/src/backend/access/heap/vacuumlazy.c
@@ -3409,8 +3409,8 @@ count_nondeletable_pages(LVRelState *vacrel, bool *lock_waiter_detected)
 			INSTR_TIME_SET_CURRENT(currenttime);
 			elapsed = currenttime;
 			INSTR_TIME_SUBTRACT(elapsed, starttime);
-			if ((INSTR_TIME_GET_MICROSEC(elapsed) / 1000)
-				>= VACUUM_TRUNCATE_LOCK_CHECK_INTERVAL)
+			if (INSTR_TIME_GET_MILLISEC(elapsed) >=
+				VACUUM_TRUNCATE_LOCK_CHECK_INTERVAL)
 			{
 				if (LockHasWaitersRelation(vacrel->rel, AccessExclusiveLock))
 				{
diff --git a/src/backend/executor/instrument.c b/src/backend/executor/instrument.c
index 56e635f4700..01f67c5d972 100644
--- a/src/backend/executor/instrument.c
+++ b/src/backend/executor/instrument.c
@@ -67,9 +67,13 @@ InstrInit(Instrumentation *instr, int instrument_options)
 void
 InstrStartNode(Instrumentation *instr)
 {
-	if (instr->need_timer &&
-		!INSTR_TIME_SET_CURRENT_LAZY(instr->starttime))
-		elog(ERROR, "InstrStartNode called twice in a row");
+	if (instr->need_timer)
+	{
+		if (!INSTR_TIME_IS_ZERO(instr->starttime))
+			elog(ERROR, "InstrStartNode called twice in a row");
+		else
+			INSTR_TIME_SET_CURRENT_FAST(instr->starttime);
+	}
 
 	/* save buffer usage totals at node entry, if needed */
 	if (instr->need_bufusage)
@@ -95,7 +99,7 @@ InstrStopNode(Instrumentation *instr, double nTuples)
 		if (INSTR_TIME_IS_ZERO(instr->starttime))
 			elog(ERROR, "InstrStopNode called without start");
 
-		INSTR_TIME_SET_CURRENT(endtime);
+		INSTR_TIME_SET_CURRENT_FAST(endtime);
 		INSTR_TIME_ACCUM_DIFF(instr->counter, endtime, instr->starttime);
 
 		INSTR_TIME_SET_ZERO(instr->starttime);
diff --git a/src/backend/utils/init/postinit.c b/src/backend/utils/init/postinit.c
index 641e535a73c..d573409903b 100644
--- a/src/backend/utils/init/postinit.c
+++ b/src/backend/utils/init/postinit.c
@@ -810,6 +810,9 @@ InitPostgres(const char *in_dbname, Oid dboid,
 	/* Initialize portal manager */
 	EnablePortalManager();
 
+	/* initialize high-precision interval timing */
+	INSTR_TIME_INITIALIZE();
+
 	/*
 	 * Load relcache entries for the shared system catalogs.  This must create
 	 * at least entries for pg_database and catalogs used for authentication.
diff --git a/src/bin/pgbench/pgbench.c b/src/bin/pgbench/pgbench.c
index 1515ed405ba..79bef2d2aec 100644
--- a/src/bin/pgbench/pgbench.c
+++ b/src/bin/pgbench/pgbench.c
@@ -7290,6 +7290,9 @@ main(int argc, char **argv)
 		initRandomState(&state[i].cs_func_rs);
 	}
 
+	/* initialize high-precision interval timing */
+	INSTR_TIME_INITIALIZE();
+
 	/* opening connection... */
 	con = doConnect();
 	if (con == NULL)
diff --git a/src/bin/psql/startup.c b/src/bin/psql/startup.c
index 249b6aa5169..d615df593c7 100644
--- a/src/bin/psql/startup.c
+++ b/src/bin/psql/startup.c
@@ -24,6 +24,7 @@
 #include "help.h"
 #include "input.h"
 #include "mainloop.h"
+#include "portability/instr_time.h"
 #include "settings.h"
 
 /*
@@ -327,6 +328,9 @@ main(int argc, char *argv[])
 
 	PQsetNoticeProcessor(pset.db, NoticeProcessor, NULL);
 
+	/* initialize high-precision interval timing */
+	INSTR_TIME_INITIALIZE();
+
 	SyncVariables();
 
 	if (options.list_dbs)
diff --git a/src/common/Makefile b/src/common/Makefile
index 2c720caa509..1a2fbbe887f 100644
--- a/src/common/Makefile
+++ b/src/common/Makefile
@@ -59,6 +59,7 @@ OBJS_COMMON = \
 	file_perm.o \
 	file_utils.o \
 	hashfn.o \
+	instr_time.o \
 	ip.o \
 	jsonapi.o \
 	keywords.o \
diff --git a/src/common/instr_time.c b/src/common/instr_time.c
new file mode 100644
index 00000000000..fdf47699f20
--- /dev/null
+++ b/src/common/instr_time.c
@@ -0,0 +1,206 @@
+/*-------------------------------------------------------------------------
+ *
+ * instr_time.c
+ *	   Non-inline parts of the portable high-precision interval timing
+ *	 implementation
+ *
+ * Portions Copyright (c) 2025, PostgreSQL Global Development Group
+ *
+ *
+ * IDENTIFICATION
+ *	  src/backend/port/instr_time.c
+ *
+ *-------------------------------------------------------------------------
+ */
+#include "postgres.h"
+
+#if defined(HAVE__GET_CPUID) || (defined(HAVE__CPUIDEX) && !defined(_MSC_VER))
+#include <cpuid.h>
+#endif
+
+#if defined(HAVE__CPUID) || (defined(HAVE__CPUIDEX) && defined(_MSC_VER))
+#include <intrin.h>
+#endif
+
+#include "portability/instr_time.h"
+
+#ifndef WIN32
+/*
+ * Stores what the number of cycles needs to be multiplied with to end up
+ * with nanoseconds using integer math. See comment in pg_initialize_rdtsc()
+ * for more details.
+ *
+ * By default assume we are using clock_gettime() as a fallback which uses
+ * nanoseconds as ticks. Hence, we set the multiplier to the precision scalar
+ * so that the division in INSTR_TIME_GET_NANOSEC() won't change the nanoseconds.
+ *
+ * When using the RDTSC instruction directly this is filled in during initialization
+ * based on the relevant CPUID fields.
+ */
+int64		ticks_per_ns_scaled = TICKS_TO_NS_PRECISION;
+int64		ticks_per_sec = NS_PER_S;
+int64		max_ticks_no_overflow = PG_INT64_MAX / TICKS_TO_NS_PRECISION;
+
+#if defined(__x86_64__) && defined(__linux__)
+/*
+ * Indicates if RDTSC can be used (Linux/x86 only, when OS uses TSC clocksource)
+ */
+bool		has_rdtsc = false;
+
+/*
+ * Indicates if RDTSCP can be used. True if RDTSC can be used and RDTSCP is available.
+ */
+bool		has_rdtscp = false;
+
+#define CPUID_HYPERVISOR_VMWARE(words) (words[1] == 0x61774d56 && words[2] == 0x4d566572 && words[3] == 0x65726177) /* VMwareVMware */
+#define CPUID_HYPERVISOR_KVM(words) (words[1] == 0x4b4d564b && words[2] == 0x564b4d56 && words[3] == 0x0000004d)	/* KVMKVMKVM */
+
+static bool
+get_tsc_frequency_khz(uint32 *tsc_freq)
+{
+	uint32		r[4] = {0, 0, 0, 0};
+
+#if defined(HAVE__GET_CPUID)
+	__get_cpuid(0x15, &r[0] /* denominator */ , &r[1] /* numerator */ , &r[2] /* hz */ , &r[3]);
+#elif defined(HAVE__CPUID)
+	__cpuid(r, 0x15);
+#else
+#error cpuid instruction not available
+#endif
+
+	if (r[2] > 0)
+	{
+		if (r[0] == 0 || r[1] == 0)
+			return false;
+
+		*tsc_freq = r[2] / 1000 * r[1] / r[0];
+		return true;
+	}
+
+	/* Some CPUs only report frequency in 16H */
+
+#if defined(HAVE__GET_CPUID)
+	__get_cpuid(0x16, &r[0] /* base_mhz */ , &r[1], &r[2], &r[3]);
+#elif defined(HAVE__CPUID)
+	__cpuid(r, 0x16);
+#else
+#error cpuid instruction not available
+#endif
+
+	if (r[0] > 0)
+	{
+		*tsc_freq = r[0] * 1000;
+		return true;
+	}
+
+	/*
+	 * Check if we have a KVM or VMware Hypervisor passing down TSC frequency
+	 * to us in a guest VM
+	 *
+	 * Note that accessing the 0x40000000 leaf for Hypervisor info requires
+	 * use of __cpuidex to set ECX to 0. The similar __get_cpuid_count
+	 * function does not work as expected since it contains a check for
+	 * __get_cpuid_max, which has been observed to be lower than the special
+	 * Hypervisor leaf.
+	 */
+#if defined(HAVE__CPUIDEX)
+	__cpuidex((int32 *) r, 0x40000000, 0);
+	if (r[0] >= 0x40000010 && (CPUID_HYPERVISOR_VMWARE(r) || CPUID_HYPERVISOR_KVM(r)))
+	{
+		__cpuidex((int32 *) r, 0x40000010, 0);
+		if (r[0] > 0)
+		{
+			*tsc_freq = r[0];
+			return true;
+		}
+	}
+#endif
+
+	return false;
+}
+
+static bool
+is_rdtscp_available()
+{
+	uint32		r[4] = {0, 0, 0, 0};
+
+#if defined(HAVE__GET_CPUID)
+	if (!__get_cpuid(0x80000001, &r[0], &r[1], &r[2], &r[3]))
+		return false;
+#elif defined(HAVE__CPUID)
+	__cpuid(r, 0x80000001);
+#else
+#error cpuid instruction not available
+#endif
+
+	return (r[3] & (1 << 27)) != 0;
+}
+
+/*
+ * Decide whether we use the RDTSC instruction at runtime, for Linux/x86,
+ * instead of incurring the overhead of a full clock_gettime() call.
+ *
+ * This can't be reliably determined at compile time, since the
+ * availability of an "invariant" TSC (that is not affected by CPU
+ * frequency changes) is dependent on the CPU architecture. Additionally,
+ * there are cases where TSC availability is impacted by virtualization,
+ * where a simple cpuid feature check would not be enough.
+ *
+ * Since Linux already does a significant amount of work to determine
+ * whether TSC is a viable clock source, decide based on that.
+ */
+void
+pg_initialize_rdtsc(void)
+{
+	FILE	   *fp = fopen("/sys/devices/system/clocksource/clocksource0/current_clocksource", "r");
+
+	if (fp)
+	{
+		char		buf[128];
+
+		if (fgets(buf, sizeof(buf), fp) != NULL && strcmp(buf, "tsc\n") == 0)
+		{
+			/*
+			 * Compute baseline CPU peformance, determines speed at which
+			 * RDTSC advances.
+			 */
+			uint32		tsc_freq;
+
+			if (get_tsc_frequency_khz(&tsc_freq))
+			{
+				/*
+				 * Ticks to nanoseconds conversion requires floating point
+				 * math because because:
+				 *
+				 * sec = ticks / frequency_hz ns  = ticks / frequency_hz *
+				 * 1,000,000,000 ns  = ticks * (1,000,000,000 / frequency_hz)
+				 * ns  = ticks * (1,000,000 / frequency_khz) <-- now in
+				 * kilohertz
+				 *
+				 * Here, 'ns' is usually a floating number. For example for a
+				 * 2.5 GHz CPU the scaling factor becomes 1,000,000 /
+				 * 2,500,000 = 1.2.
+				 *
+				 * To be able to use integer math we work around the lack of
+				 * precision. We first scale the integer up and after the
+				 * multiplication by the number of ticks in
+				 * INSTR_TIME_GET_NANOSEC() we divide again by the same value.
+				 * We picked the scaler such that it provides enough precision
+				 * and is a power-of-two which allows for shifting instead of
+				 * doing an integer division.
+				 */
+				ticks_per_ns_scaled = INT64CONST(1000000) * TICKS_TO_NS_PRECISION / tsc_freq;
+				ticks_per_sec = tsc_freq * 1000;	/* KHz->Hz */
+				max_ticks_no_overflow = PG_INT64_MAX / ticks_per_ns_scaled;
+
+				has_rdtsc = true;
+				has_rdtscp = is_rdtscp_available();
+			}
+		}
+
+		fclose(fp);
+	}
+}
+#endif							/* defined(__x86_64__) && defined(__linux__) */
+
+#endif							/* WIN32 */
diff --git a/src/common/meson.build b/src/common/meson.build
index 1540ba67cca..62b90b3e609 100644
--- a/src/common/meson.build
+++ b/src/common/meson.build
@@ -13,6 +13,7 @@ common_sources = files(
   'file_perm.c',
   'file_utils.c',
   'hashfn.c',
+  'instr_time.c',
   'ip.c',
   'jsonapi.c',
   'keywords.c',
diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h
index f71a851b18d..e2e339a0c4f 100644
--- a/src/include/portability/instr_time.h
+++ b/src/include/portability/instr_time.h
@@ -4,9 +4,11 @@
  *	  portable high-precision interval timing
  *
  * This file provides an abstraction layer to hide portability issues in
- * interval timing.  On Unix we use clock_gettime(), and on Windows we use
- * QueryPerformanceCounter().  These macros also give some breathing room to
- * use other high-precision-timing APIs.
+ * interval timing. On Linux/x86 we use the rdtsc instruction when a TSC
+ * clocksource is also used on the host OS.  Otherwise, and on other
+ * Unix-like systems we use clock_gettime() and on Windows we use
+ * QueryPerformanceCounter(). These macros also give some breathing
+ * room to use other high-precision-timing APIs.
  *
  * The basic data type is instr_time, which all callers should treat as an
  * opaque typedef.  instr_time can store either an absolute time (of
@@ -17,10 +19,11 @@
  *
  * INSTR_TIME_SET_ZERO(t)			set t to zero (memset is acceptable too)
  *
- * INSTR_TIME_SET_CURRENT(t)		set t to current time
+ * INSTR_TIME_SET_CURRENT_FAST(t)	set t to current time without waiting
+ * 									for instructions in out-of-order window
  *
- * INSTR_TIME_SET_CURRENT_LAZY(t)	set t to current time if t is zero,
- *									evaluates to whether t changed
+ * INSTR_TIME_SET_CURRENT(t)		set t to current time while waiting for
+ * 									instructions in OOO to retire
  *
  * INSTR_TIME_ADD(x, y)				x += y
  *
@@ -81,6 +84,15 @@ typedef struct instr_time
 
 #ifndef WIN32
 
+/*
+ * Make sure this is a power-of-two, so that the compiler can turn the
+ * multiplications and divisions into shifts.
+ */
+#define TICKS_TO_NS_PRECISION (1<<14)
+
+extern int64 ticks_per_ns_scaled;
+extern int64 ticks_per_sec;
+extern int64 max_ticks_no_overflow;
 
 /* Use clock_gettime() */
 
@@ -106,9 +118,18 @@ typedef struct instr_time
 #define PG_INSTR_CLOCK	CLOCK_REALTIME
 #endif
 
-/* helper for INSTR_TIME_SET_CURRENT */
+#if defined(__x86_64__) && defined(__linux__)
+#include <x86intrin.h>
+#include <cpuid.h>
+
+extern bool has_rdtsc;
+extern bool has_rdtscp;
+
+extern void pg_initialize_rdtsc(void);
+#endif
+
 static inline instr_time
-pg_clock_gettime_ns(void)
+pg_clock_gettime(void)
 {
 	instr_time	now;
 	struct timespec tmp;
@@ -119,11 +140,94 @@ pg_clock_gettime_ns(void)
 	return now;
 }
 
+static inline instr_time
+pg_get_ticks_fast(void)
+{
+#if defined(__x86_64__) && defined(__linux__)
+	if (has_rdtsc)
+	{
+		instr_time	now;
+
+		now.ticks = __rdtsc();
+		return now;
+	}
+#endif
+
+	return pg_clock_gettime();
+}
+
+static inline instr_time
+pg_get_ticks(void)
+{
+#if defined(__x86_64__) && defined(__linux__)
+	if (has_rdtscp)
+	{
+		instr_time	now;
+		uint32		unused;
+
+		now.ticks = __rdtscp(&unused);
+		return now;
+	}
+#endif
+
+	return pg_clock_gettime();
+}
+
+static inline int64_t
+pg_ticks_to_ns(instr_time t)
+{
+	/*
+	 * Would multiplication overflow? If so perform computation in two parts.
+	 * Check overflow without actually overflowing via: a * b > max <=> a >
+	 * max / b
+	 */
+	int64		ns = 0;
+
+	if (unlikely(t.ticks > max_ticks_no_overflow))
+	{
+		/*
+		 * Compute how often the maximum number of ticks fits completely into
+		 * the number of elapsed ticks and convert that number into
+		 * nanoseconds. Then multiply by the count to arrive at the final
+		 * 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		max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION;
+
+		ns = max_ns * count;
+
+		/*
+		 * 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);
+	}
+
+	ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION;
+	return ns;
+}
+
+static inline void
+pg_initialize_get_ticks()
+{
+#if defined(__x86_64__) && defined(__linux__)
+	pg_initialize_rdtsc();
+#endif
+}
+
+#define INSTR_TIME_INITIALIZE() \
+	pg_initialize_get_ticks()
+
+#define INSTR_TIME_SET_CURRENT_FAST(t) \
+	((t) = pg_get_ticks_fast())
+
 #define INSTR_TIME_SET_CURRENT(t) \
-	((t) = pg_clock_gettime_ns())
+	((t) = pg_get_ticks())
 
 #define INSTR_TIME_GET_NANOSEC(t) \
-	((int64) (t).ticks)
+	pg_ticks_to_ns(t)
 
 
 #else							/* WIN32 */
@@ -131,7 +235,7 @@ pg_clock_gettime_ns(void)
 
 /* Use QueryPerformanceCounter() */
 
-/* helper for INSTR_TIME_SET_CURRENT */
+/* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */
 static inline instr_time
 pg_query_performance_counter(void)
 {
@@ -153,6 +257,11 @@ GetTimerFrequency(void)
 	return (double) f.QuadPart;
 }
 
+#define INSTR_TIME_INITIALIZE()
+
+#define INSTR_TIME_SET_CURRENT_FAST(t) \
+	((t) = pg_query_performance_counter())
+
 #define INSTR_TIME_SET_CURRENT(t) \
 	((t) = pg_query_performance_counter())
 
@@ -168,13 +277,8 @@ GetTimerFrequency(void)
 
 #define INSTR_TIME_IS_ZERO(t)	((t).ticks == 0)
 
-
 #define INSTR_TIME_SET_ZERO(t)	((t).ticks = 0)
 
-#define INSTR_TIME_SET_CURRENT_LAZY(t) \
-	(INSTR_TIME_IS_ZERO(t) ? INSTR_TIME_SET_CURRENT(t), true : false)
-
-
 #define INSTR_TIME_ADD(x,y) \
 	((x).ticks += (y).ticks)
 
-- 
2.47.3


--vtqqtrpooseurzip
Content-Type: text/x-diff; charset=utf-8
Content-Disposition: attachment;
	filename="v12-0003-pg_test_timing-Add-fast-flag-to-test-fast-timing.patch"



^ permalink  raw  reply  [nested|flat] 271+ messages in thread

* [PATCH v12 2/3] Use time stamp counter to measure time on Linux/x86
@ 2025-07-26 00:57 Lukas Fittl <[email protected]>
  0 siblings, 0 replies; 271+ messages in thread

From: Lukas Fittl @ 2025-07-26 00:57 UTC (permalink / raw)

We switch to using the time stamp counter (TSC) instead of clock_gettime()
to reduce overhead of EXPLAIN (ANALYZE, TIME ON). Tests showed that runtime
is reduced by around 10% for queries moving lots of rows through the plan.

For now this is only enabled on Linux/x86, in case the system clocksource is
reported as TSC. Relying on the Linux kernel simplifies the logic to detect
if the present TSC is usable (frequency invariant, synchronized between
sockets, etc.). In all other cases we fallback to clock_gettime().

Note, that we intentionally use RDTSC in the fast paths, rather than RDTSCP.
RDTSCP waits for outstanding instructions to retire on out-of-order CPUs.
This adds noticably for little benefit in the typical InstrStartNode() /
InstrStopNode() use case. The macro to be used in such cases is called
INSTR_TIME_SET_CURRENT_FAST(). The original macro INSTR_TIME_SET_CURRENT()
uses RDTSCP and is supposed to be used when precision is more important
than performance.

Author: David Geier <[email protected]>
Author: Andres Freund <[email protected]>
Author: Lukas Fittl <[email protected]>
Reviewed-by:
Discussion: https://www.postgresql.org/message-id/flat/20200612232810.f46nbqkdhbutzqdg%40alap3.anarazel.de
---
 src/backend/access/heap/vacuumlazy.c |   4 +-
 src/backend/executor/instrument.c    |  12 +-
 src/backend/utils/init/postinit.c    |   3 +
 src/bin/pgbench/pgbench.c            |   3 +
 src/bin/psql/startup.c               |   4 +
 src/common/Makefile                  |   1 +
 src/common/instr_time.c              | 206 +++++++++++++++++++++++++++
 src/common/meson.build               |   1 +
 src/include/portability/instr_time.h | 136 +++++++++++++++---
 9 files changed, 348 insertions(+), 22 deletions(-)
 create mode 100644 src/common/instr_time.c

diff --git a/src/backend/access/heap/vacuumlazy.c b/src/backend/access/heap/vacuumlazy.c
index d2b031fdd06..5027048cac4 100644
--- a/src/backend/access/heap/vacuumlazy.c
+++ b/src/backend/access/heap/vacuumlazy.c
@@ -3409,8 +3409,8 @@ count_nondeletable_pages(LVRelState *vacrel, bool *lock_waiter_detected)
 			INSTR_TIME_SET_CURRENT(currenttime);
 			elapsed = currenttime;
 			INSTR_TIME_SUBTRACT(elapsed, starttime);
-			if ((INSTR_TIME_GET_MICROSEC(elapsed) / 1000)
-				>= VACUUM_TRUNCATE_LOCK_CHECK_INTERVAL)
+			if (INSTR_TIME_GET_MILLISEC(elapsed) >=
+				VACUUM_TRUNCATE_LOCK_CHECK_INTERVAL)
 			{
 				if (LockHasWaitersRelation(vacrel->rel, AccessExclusiveLock))
 				{
diff --git a/src/backend/executor/instrument.c b/src/backend/executor/instrument.c
index 56e635f4700..01f67c5d972 100644
--- a/src/backend/executor/instrument.c
+++ b/src/backend/executor/instrument.c
@@ -67,9 +67,13 @@ InstrInit(Instrumentation *instr, int instrument_options)
 void
 InstrStartNode(Instrumentation *instr)
 {
-	if (instr->need_timer &&
-		!INSTR_TIME_SET_CURRENT_LAZY(instr->starttime))
-		elog(ERROR, "InstrStartNode called twice in a row");
+	if (instr->need_timer)
+	{
+		if (!INSTR_TIME_IS_ZERO(instr->starttime))
+			elog(ERROR, "InstrStartNode called twice in a row");
+		else
+			INSTR_TIME_SET_CURRENT_FAST(instr->starttime);
+	}
 
 	/* save buffer usage totals at node entry, if needed */
 	if (instr->need_bufusage)
@@ -95,7 +99,7 @@ InstrStopNode(Instrumentation *instr, double nTuples)
 		if (INSTR_TIME_IS_ZERO(instr->starttime))
 			elog(ERROR, "InstrStopNode called without start");
 
-		INSTR_TIME_SET_CURRENT(endtime);
+		INSTR_TIME_SET_CURRENT_FAST(endtime);
 		INSTR_TIME_ACCUM_DIFF(instr->counter, endtime, instr->starttime);
 
 		INSTR_TIME_SET_ZERO(instr->starttime);
diff --git a/src/backend/utils/init/postinit.c b/src/backend/utils/init/postinit.c
index 641e535a73c..d573409903b 100644
--- a/src/backend/utils/init/postinit.c
+++ b/src/backend/utils/init/postinit.c
@@ -810,6 +810,9 @@ InitPostgres(const char *in_dbname, Oid dboid,
 	/* Initialize portal manager */
 	EnablePortalManager();
 
+	/* initialize high-precision interval timing */
+	INSTR_TIME_INITIALIZE();
+
 	/*
 	 * Load relcache entries for the shared system catalogs.  This must create
 	 * at least entries for pg_database and catalogs used for authentication.
diff --git a/src/bin/pgbench/pgbench.c b/src/bin/pgbench/pgbench.c
index 1515ed405ba..79bef2d2aec 100644
--- a/src/bin/pgbench/pgbench.c
+++ b/src/bin/pgbench/pgbench.c
@@ -7290,6 +7290,9 @@ main(int argc, char **argv)
 		initRandomState(&state[i].cs_func_rs);
 	}
 
+	/* initialize high-precision interval timing */
+	INSTR_TIME_INITIALIZE();
+
 	/* opening connection... */
 	con = doConnect();
 	if (con == NULL)
diff --git a/src/bin/psql/startup.c b/src/bin/psql/startup.c
index 249b6aa5169..d615df593c7 100644
--- a/src/bin/psql/startup.c
+++ b/src/bin/psql/startup.c
@@ -24,6 +24,7 @@
 #include "help.h"
 #include "input.h"
 #include "mainloop.h"
+#include "portability/instr_time.h"
 #include "settings.h"
 
 /*
@@ -327,6 +328,9 @@ main(int argc, char *argv[])
 
 	PQsetNoticeProcessor(pset.db, NoticeProcessor, NULL);
 
+	/* initialize high-precision interval timing */
+	INSTR_TIME_INITIALIZE();
+
 	SyncVariables();
 
 	if (options.list_dbs)
diff --git a/src/common/Makefile b/src/common/Makefile
index 2c720caa509..1a2fbbe887f 100644
--- a/src/common/Makefile
+++ b/src/common/Makefile
@@ -59,6 +59,7 @@ OBJS_COMMON = \
 	file_perm.o \
 	file_utils.o \
 	hashfn.o \
+	instr_time.o \
 	ip.o \
 	jsonapi.o \
 	keywords.o \
diff --git a/src/common/instr_time.c b/src/common/instr_time.c
new file mode 100644
index 00000000000..fdf47699f20
--- /dev/null
+++ b/src/common/instr_time.c
@@ -0,0 +1,206 @@
+/*-------------------------------------------------------------------------
+ *
+ * instr_time.c
+ *	   Non-inline parts of the portable high-precision interval timing
+ *	 implementation
+ *
+ * Portions Copyright (c) 2025, PostgreSQL Global Development Group
+ *
+ *
+ * IDENTIFICATION
+ *	  src/backend/port/instr_time.c
+ *
+ *-------------------------------------------------------------------------
+ */
+#include "postgres.h"
+
+#if defined(HAVE__GET_CPUID) || (defined(HAVE__CPUIDEX) && !defined(_MSC_VER))
+#include <cpuid.h>
+#endif
+
+#if defined(HAVE__CPUID) || (defined(HAVE__CPUIDEX) && defined(_MSC_VER))
+#include <intrin.h>
+#endif
+
+#include "portability/instr_time.h"
+
+#ifndef WIN32
+/*
+ * Stores what the number of cycles needs to be multiplied with to end up
+ * with nanoseconds using integer math. See comment in pg_initialize_rdtsc()
+ * for more details.
+ *
+ * By default assume we are using clock_gettime() as a fallback which uses
+ * nanoseconds as ticks. Hence, we set the multiplier to the precision scalar
+ * so that the division in INSTR_TIME_GET_NANOSEC() won't change the nanoseconds.
+ *
+ * When using the RDTSC instruction directly this is filled in during initialization
+ * based on the relevant CPUID fields.
+ */
+int64		ticks_per_ns_scaled = TICKS_TO_NS_PRECISION;
+int64		ticks_per_sec = NS_PER_S;
+int64		max_ticks_no_overflow = PG_INT64_MAX / TICKS_TO_NS_PRECISION;
+
+#if defined(__x86_64__) && defined(__linux__)
+/*
+ * Indicates if RDTSC can be used (Linux/x86 only, when OS uses TSC clocksource)
+ */
+bool		has_rdtsc = false;
+
+/*
+ * Indicates if RDTSCP can be used. True if RDTSC can be used and RDTSCP is available.
+ */
+bool		has_rdtscp = false;
+
+#define CPUID_HYPERVISOR_VMWARE(words) (words[1] == 0x61774d56 && words[2] == 0x4d566572 && words[3] == 0x65726177) /* VMwareVMware */
+#define CPUID_HYPERVISOR_KVM(words) (words[1] == 0x4b4d564b && words[2] == 0x564b4d56 && words[3] == 0x0000004d)	/* KVMKVMKVM */
+
+static bool
+get_tsc_frequency_khz(uint32 *tsc_freq)
+{
+	uint32		r[4] = {0, 0, 0, 0};
+
+#if defined(HAVE__GET_CPUID)
+	__get_cpuid(0x15, &r[0] /* denominator */ , &r[1] /* numerator */ , &r[2] /* hz */ , &r[3]);
+#elif defined(HAVE__CPUID)
+	__cpuid(r, 0x15);
+#else
+#error cpuid instruction not available
+#endif
+
+	if (r[2] > 0)
+	{
+		if (r[0] == 0 || r[1] == 0)
+			return false;
+
+		*tsc_freq = r[2] / 1000 * r[1] / r[0];
+		return true;
+	}
+
+	/* Some CPUs only report frequency in 16H */
+
+#if defined(HAVE__GET_CPUID)
+	__get_cpuid(0x16, &r[0] /* base_mhz */ , &r[1], &r[2], &r[3]);
+#elif defined(HAVE__CPUID)
+	__cpuid(r, 0x16);
+#else
+#error cpuid instruction not available
+#endif
+
+	if (r[0] > 0)
+	{
+		*tsc_freq = r[0] * 1000;
+		return true;
+	}
+
+	/*
+	 * Check if we have a KVM or VMware Hypervisor passing down TSC frequency
+	 * to us in a guest VM
+	 *
+	 * Note that accessing the 0x40000000 leaf for Hypervisor info requires
+	 * use of __cpuidex to set ECX to 0. The similar __get_cpuid_count
+	 * function does not work as expected since it contains a check for
+	 * __get_cpuid_max, which has been observed to be lower than the special
+	 * Hypervisor leaf.
+	 */
+#if defined(HAVE__CPUIDEX)
+	__cpuidex((int32 *) r, 0x40000000, 0);
+	if (r[0] >= 0x40000010 && (CPUID_HYPERVISOR_VMWARE(r) || CPUID_HYPERVISOR_KVM(r)))
+	{
+		__cpuidex((int32 *) r, 0x40000010, 0);
+		if (r[0] > 0)
+		{
+			*tsc_freq = r[0];
+			return true;
+		}
+	}
+#endif
+
+	return false;
+}
+
+static bool
+is_rdtscp_available()
+{
+	uint32		r[4] = {0, 0, 0, 0};
+
+#if defined(HAVE__GET_CPUID)
+	if (!__get_cpuid(0x80000001, &r[0], &r[1], &r[2], &r[3]))
+		return false;
+#elif defined(HAVE__CPUID)
+	__cpuid(r, 0x80000001);
+#else
+#error cpuid instruction not available
+#endif
+
+	return (r[3] & (1 << 27)) != 0;
+}
+
+/*
+ * Decide whether we use the RDTSC instruction at runtime, for Linux/x86,
+ * instead of incurring the overhead of a full clock_gettime() call.
+ *
+ * This can't be reliably determined at compile time, since the
+ * availability of an "invariant" TSC (that is not affected by CPU
+ * frequency changes) is dependent on the CPU architecture. Additionally,
+ * there are cases where TSC availability is impacted by virtualization,
+ * where a simple cpuid feature check would not be enough.
+ *
+ * Since Linux already does a significant amount of work to determine
+ * whether TSC is a viable clock source, decide based on that.
+ */
+void
+pg_initialize_rdtsc(void)
+{
+	FILE	   *fp = fopen("/sys/devices/system/clocksource/clocksource0/current_clocksource", "r");
+
+	if (fp)
+	{
+		char		buf[128];
+
+		if (fgets(buf, sizeof(buf), fp) != NULL && strcmp(buf, "tsc\n") == 0)
+		{
+			/*
+			 * Compute baseline CPU peformance, determines speed at which
+			 * RDTSC advances.
+			 */
+			uint32		tsc_freq;
+
+			if (get_tsc_frequency_khz(&tsc_freq))
+			{
+				/*
+				 * Ticks to nanoseconds conversion requires floating point
+				 * math because because:
+				 *
+				 * sec = ticks / frequency_hz ns  = ticks / frequency_hz *
+				 * 1,000,000,000 ns  = ticks * (1,000,000,000 / frequency_hz)
+				 * ns  = ticks * (1,000,000 / frequency_khz) <-- now in
+				 * kilohertz
+				 *
+				 * Here, 'ns' is usually a floating number. For example for a
+				 * 2.5 GHz CPU the scaling factor becomes 1,000,000 /
+				 * 2,500,000 = 1.2.
+				 *
+				 * To be able to use integer math we work around the lack of
+				 * precision. We first scale the integer up and after the
+				 * multiplication by the number of ticks in
+				 * INSTR_TIME_GET_NANOSEC() we divide again by the same value.
+				 * We picked the scaler such that it provides enough precision
+				 * and is a power-of-two which allows for shifting instead of
+				 * doing an integer division.
+				 */
+				ticks_per_ns_scaled = INT64CONST(1000000) * TICKS_TO_NS_PRECISION / tsc_freq;
+				ticks_per_sec = tsc_freq * 1000;	/* KHz->Hz */
+				max_ticks_no_overflow = PG_INT64_MAX / ticks_per_ns_scaled;
+
+				has_rdtsc = true;
+				has_rdtscp = is_rdtscp_available();
+			}
+		}
+
+		fclose(fp);
+	}
+}
+#endif							/* defined(__x86_64__) && defined(__linux__) */
+
+#endif							/* WIN32 */
diff --git a/src/common/meson.build b/src/common/meson.build
index 1540ba67cca..62b90b3e609 100644
--- a/src/common/meson.build
+++ b/src/common/meson.build
@@ -13,6 +13,7 @@ common_sources = files(
   'file_perm.c',
   'file_utils.c',
   'hashfn.c',
+  'instr_time.c',
   'ip.c',
   'jsonapi.c',
   'keywords.c',
diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h
index f71a851b18d..e2e339a0c4f 100644
--- a/src/include/portability/instr_time.h
+++ b/src/include/portability/instr_time.h
@@ -4,9 +4,11 @@
  *	  portable high-precision interval timing
  *
  * This file provides an abstraction layer to hide portability issues in
- * interval timing.  On Unix we use clock_gettime(), and on Windows we use
- * QueryPerformanceCounter().  These macros also give some breathing room to
- * use other high-precision-timing APIs.
+ * interval timing. On Linux/x86 we use the rdtsc instruction when a TSC
+ * clocksource is also used on the host OS.  Otherwise, and on other
+ * Unix-like systems we use clock_gettime() and on Windows we use
+ * QueryPerformanceCounter(). These macros also give some breathing
+ * room to use other high-precision-timing APIs.
  *
  * The basic data type is instr_time, which all callers should treat as an
  * opaque typedef.  instr_time can store either an absolute time (of
@@ -17,10 +19,11 @@
  *
  * INSTR_TIME_SET_ZERO(t)			set t to zero (memset is acceptable too)
  *
- * INSTR_TIME_SET_CURRENT(t)		set t to current time
+ * INSTR_TIME_SET_CURRENT_FAST(t)	set t to current time without waiting
+ * 									for instructions in out-of-order window
  *
- * INSTR_TIME_SET_CURRENT_LAZY(t)	set t to current time if t is zero,
- *									evaluates to whether t changed
+ * INSTR_TIME_SET_CURRENT(t)		set t to current time while waiting for
+ * 									instructions in OOO to retire
  *
  * INSTR_TIME_ADD(x, y)				x += y
  *
@@ -81,6 +84,15 @@ typedef struct instr_time
 
 #ifndef WIN32
 
+/*
+ * Make sure this is a power-of-two, so that the compiler can turn the
+ * multiplications and divisions into shifts.
+ */
+#define TICKS_TO_NS_PRECISION (1<<14)
+
+extern int64 ticks_per_ns_scaled;
+extern int64 ticks_per_sec;
+extern int64 max_ticks_no_overflow;
 
 /* Use clock_gettime() */
 
@@ -106,9 +118,18 @@ typedef struct instr_time
 #define PG_INSTR_CLOCK	CLOCK_REALTIME
 #endif
 
-/* helper for INSTR_TIME_SET_CURRENT */
+#if defined(__x86_64__) && defined(__linux__)
+#include <x86intrin.h>
+#include <cpuid.h>
+
+extern bool has_rdtsc;
+extern bool has_rdtscp;
+
+extern void pg_initialize_rdtsc(void);
+#endif
+
 static inline instr_time
-pg_clock_gettime_ns(void)
+pg_clock_gettime(void)
 {
 	instr_time	now;
 	struct timespec tmp;
@@ -119,11 +140,94 @@ pg_clock_gettime_ns(void)
 	return now;
 }
 
+static inline instr_time
+pg_get_ticks_fast(void)
+{
+#if defined(__x86_64__) && defined(__linux__)
+	if (has_rdtsc)
+	{
+		instr_time	now;
+
+		now.ticks = __rdtsc();
+		return now;
+	}
+#endif
+
+	return pg_clock_gettime();
+}
+
+static inline instr_time
+pg_get_ticks(void)
+{
+#if defined(__x86_64__) && defined(__linux__)
+	if (has_rdtscp)
+	{
+		instr_time	now;
+		uint32		unused;
+
+		now.ticks = __rdtscp(&unused);
+		return now;
+	}
+#endif
+
+	return pg_clock_gettime();
+}
+
+static inline int64_t
+pg_ticks_to_ns(instr_time t)
+{
+	/*
+	 * Would multiplication overflow? If so perform computation in two parts.
+	 * Check overflow without actually overflowing via: a * b > max <=> a >
+	 * max / b
+	 */
+	int64		ns = 0;
+
+	if (unlikely(t.ticks > max_ticks_no_overflow))
+	{
+		/*
+		 * Compute how often the maximum number of ticks fits completely into
+		 * the number of elapsed ticks and convert that number into
+		 * nanoseconds. Then multiply by the count to arrive at the final
+		 * 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		max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION;
+
+		ns = max_ns * count;
+
+		/*
+		 * 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);
+	}
+
+	ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION;
+	return ns;
+}
+
+static inline void
+pg_initialize_get_ticks()
+{
+#if defined(__x86_64__) && defined(__linux__)
+	pg_initialize_rdtsc();
+#endif
+}
+
+#define INSTR_TIME_INITIALIZE() \
+	pg_initialize_get_ticks()
+
+#define INSTR_TIME_SET_CURRENT_FAST(t) \
+	((t) = pg_get_ticks_fast())
+
 #define INSTR_TIME_SET_CURRENT(t) \
-	((t) = pg_clock_gettime_ns())
+	((t) = pg_get_ticks())
 
 #define INSTR_TIME_GET_NANOSEC(t) \
-	((int64) (t).ticks)
+	pg_ticks_to_ns(t)
 
 
 #else							/* WIN32 */
@@ -131,7 +235,7 @@ pg_clock_gettime_ns(void)
 
 /* Use QueryPerformanceCounter() */
 
-/* helper for INSTR_TIME_SET_CURRENT */
+/* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */
 static inline instr_time
 pg_query_performance_counter(void)
 {
@@ -153,6 +257,11 @@ GetTimerFrequency(void)
 	return (double) f.QuadPart;
 }
 
+#define INSTR_TIME_INITIALIZE()
+
+#define INSTR_TIME_SET_CURRENT_FAST(t) \
+	((t) = pg_query_performance_counter())
+
 #define INSTR_TIME_SET_CURRENT(t) \
 	((t) = pg_query_performance_counter())
 
@@ -168,13 +277,8 @@ GetTimerFrequency(void)
 
 #define INSTR_TIME_IS_ZERO(t)	((t).ticks == 0)
 
-
 #define INSTR_TIME_SET_ZERO(t)	((t).ticks = 0)
 
-#define INSTR_TIME_SET_CURRENT_LAZY(t) \
-	(INSTR_TIME_IS_ZERO(t) ? INSTR_TIME_SET_CURRENT(t), true : false)
-
-
 #define INSTR_TIME_ADD(x,y) \
 	((x).ticks += (y).ticks)
 
-- 
2.47.3


--vtqqtrpooseurzip
Content-Type: text/x-diff; charset=utf-8
Content-Disposition: attachment;
	filename="v12-0003-pg_test_timing-Add-fast-flag-to-test-fast-timing.patch"



^ permalink  raw  reply  [nested|flat] 271+ messages in thread

* [PATCH v12 2/3] Use time stamp counter to measure time on Linux/x86
@ 2025-07-26 00:57 Lukas Fittl <[email protected]>
  0 siblings, 0 replies; 271+ messages in thread

From: Lukas Fittl @ 2025-07-26 00:57 UTC (permalink / raw)

We switch to using the time stamp counter (TSC) instead of clock_gettime()
to reduce overhead of EXPLAIN (ANALYZE, TIME ON). Tests showed that runtime
is reduced by around 10% for queries moving lots of rows through the plan.

For now this is only enabled on Linux/x86, in case the system clocksource is
reported as TSC. Relying on the Linux kernel simplifies the logic to detect
if the present TSC is usable (frequency invariant, synchronized between
sockets, etc.). In all other cases we fallback to clock_gettime().

Note, that we intentionally use RDTSC in the fast paths, rather than RDTSCP.
RDTSCP waits for outstanding instructions to retire on out-of-order CPUs.
This adds noticably for little benefit in the typical InstrStartNode() /
InstrStopNode() use case. The macro to be used in such cases is called
INSTR_TIME_SET_CURRENT_FAST(). The original macro INSTR_TIME_SET_CURRENT()
uses RDTSCP and is supposed to be used when precision is more important
than performance.

Author: David Geier <[email protected]>
Author: Andres Freund <[email protected]>
Author: Lukas Fittl <[email protected]>
Reviewed-by:
Discussion: https://www.postgresql.org/message-id/flat/20200612232810.f46nbqkdhbutzqdg%40alap3.anarazel.de
---
 src/backend/access/heap/vacuumlazy.c |   4 +-
 src/backend/executor/instrument.c    |  12 +-
 src/backend/utils/init/postinit.c    |   3 +
 src/bin/pgbench/pgbench.c            |   3 +
 src/bin/psql/startup.c               |   4 +
 src/common/Makefile                  |   1 +
 src/common/instr_time.c              | 206 +++++++++++++++++++++++++++
 src/common/meson.build               |   1 +
 src/include/portability/instr_time.h | 136 +++++++++++++++---
 9 files changed, 348 insertions(+), 22 deletions(-)
 create mode 100644 src/common/instr_time.c

diff --git a/src/backend/access/heap/vacuumlazy.c b/src/backend/access/heap/vacuumlazy.c
index d2b031fdd06..5027048cac4 100644
--- a/src/backend/access/heap/vacuumlazy.c
+++ b/src/backend/access/heap/vacuumlazy.c
@@ -3409,8 +3409,8 @@ count_nondeletable_pages(LVRelState *vacrel, bool *lock_waiter_detected)
 			INSTR_TIME_SET_CURRENT(currenttime);
 			elapsed = currenttime;
 			INSTR_TIME_SUBTRACT(elapsed, starttime);
-			if ((INSTR_TIME_GET_MICROSEC(elapsed) / 1000)
-				>= VACUUM_TRUNCATE_LOCK_CHECK_INTERVAL)
+			if (INSTR_TIME_GET_MILLISEC(elapsed) >=
+				VACUUM_TRUNCATE_LOCK_CHECK_INTERVAL)
 			{
 				if (LockHasWaitersRelation(vacrel->rel, AccessExclusiveLock))
 				{
diff --git a/src/backend/executor/instrument.c b/src/backend/executor/instrument.c
index 56e635f4700..01f67c5d972 100644
--- a/src/backend/executor/instrument.c
+++ b/src/backend/executor/instrument.c
@@ -67,9 +67,13 @@ InstrInit(Instrumentation *instr, int instrument_options)
 void
 InstrStartNode(Instrumentation *instr)
 {
-	if (instr->need_timer &&
-		!INSTR_TIME_SET_CURRENT_LAZY(instr->starttime))
-		elog(ERROR, "InstrStartNode called twice in a row");
+	if (instr->need_timer)
+	{
+		if (!INSTR_TIME_IS_ZERO(instr->starttime))
+			elog(ERROR, "InstrStartNode called twice in a row");
+		else
+			INSTR_TIME_SET_CURRENT_FAST(instr->starttime);
+	}
 
 	/* save buffer usage totals at node entry, if needed */
 	if (instr->need_bufusage)
@@ -95,7 +99,7 @@ InstrStopNode(Instrumentation *instr, double nTuples)
 		if (INSTR_TIME_IS_ZERO(instr->starttime))
 			elog(ERROR, "InstrStopNode called without start");
 
-		INSTR_TIME_SET_CURRENT(endtime);
+		INSTR_TIME_SET_CURRENT_FAST(endtime);
 		INSTR_TIME_ACCUM_DIFF(instr->counter, endtime, instr->starttime);
 
 		INSTR_TIME_SET_ZERO(instr->starttime);
diff --git a/src/backend/utils/init/postinit.c b/src/backend/utils/init/postinit.c
index 641e535a73c..d573409903b 100644
--- a/src/backend/utils/init/postinit.c
+++ b/src/backend/utils/init/postinit.c
@@ -810,6 +810,9 @@ InitPostgres(const char *in_dbname, Oid dboid,
 	/* Initialize portal manager */
 	EnablePortalManager();
 
+	/* initialize high-precision interval timing */
+	INSTR_TIME_INITIALIZE();
+
 	/*
 	 * Load relcache entries for the shared system catalogs.  This must create
 	 * at least entries for pg_database and catalogs used for authentication.
diff --git a/src/bin/pgbench/pgbench.c b/src/bin/pgbench/pgbench.c
index 1515ed405ba..79bef2d2aec 100644
--- a/src/bin/pgbench/pgbench.c
+++ b/src/bin/pgbench/pgbench.c
@@ -7290,6 +7290,9 @@ main(int argc, char **argv)
 		initRandomState(&state[i].cs_func_rs);
 	}
 
+	/* initialize high-precision interval timing */
+	INSTR_TIME_INITIALIZE();
+
 	/* opening connection... */
 	con = doConnect();
 	if (con == NULL)
diff --git a/src/bin/psql/startup.c b/src/bin/psql/startup.c
index 249b6aa5169..d615df593c7 100644
--- a/src/bin/psql/startup.c
+++ b/src/bin/psql/startup.c
@@ -24,6 +24,7 @@
 #include "help.h"
 #include "input.h"
 #include "mainloop.h"
+#include "portability/instr_time.h"
 #include "settings.h"
 
 /*
@@ -327,6 +328,9 @@ main(int argc, char *argv[])
 
 	PQsetNoticeProcessor(pset.db, NoticeProcessor, NULL);
 
+	/* initialize high-precision interval timing */
+	INSTR_TIME_INITIALIZE();
+
 	SyncVariables();
 
 	if (options.list_dbs)
diff --git a/src/common/Makefile b/src/common/Makefile
index 2c720caa509..1a2fbbe887f 100644
--- a/src/common/Makefile
+++ b/src/common/Makefile
@@ -59,6 +59,7 @@ OBJS_COMMON = \
 	file_perm.o \
 	file_utils.o \
 	hashfn.o \
+	instr_time.o \
 	ip.o \
 	jsonapi.o \
 	keywords.o \
diff --git a/src/common/instr_time.c b/src/common/instr_time.c
new file mode 100644
index 00000000000..fdf47699f20
--- /dev/null
+++ b/src/common/instr_time.c
@@ -0,0 +1,206 @@
+/*-------------------------------------------------------------------------
+ *
+ * instr_time.c
+ *	   Non-inline parts of the portable high-precision interval timing
+ *	 implementation
+ *
+ * Portions Copyright (c) 2025, PostgreSQL Global Development Group
+ *
+ *
+ * IDENTIFICATION
+ *	  src/backend/port/instr_time.c
+ *
+ *-------------------------------------------------------------------------
+ */
+#include "postgres.h"
+
+#if defined(HAVE__GET_CPUID) || (defined(HAVE__CPUIDEX) && !defined(_MSC_VER))
+#include <cpuid.h>
+#endif
+
+#if defined(HAVE__CPUID) || (defined(HAVE__CPUIDEX) && defined(_MSC_VER))
+#include <intrin.h>
+#endif
+
+#include "portability/instr_time.h"
+
+#ifndef WIN32
+/*
+ * Stores what the number of cycles needs to be multiplied with to end up
+ * with nanoseconds using integer math. See comment in pg_initialize_rdtsc()
+ * for more details.
+ *
+ * By default assume we are using clock_gettime() as a fallback which uses
+ * nanoseconds as ticks. Hence, we set the multiplier to the precision scalar
+ * so that the division in INSTR_TIME_GET_NANOSEC() won't change the nanoseconds.
+ *
+ * When using the RDTSC instruction directly this is filled in during initialization
+ * based on the relevant CPUID fields.
+ */
+int64		ticks_per_ns_scaled = TICKS_TO_NS_PRECISION;
+int64		ticks_per_sec = NS_PER_S;
+int64		max_ticks_no_overflow = PG_INT64_MAX / TICKS_TO_NS_PRECISION;
+
+#if defined(__x86_64__) && defined(__linux__)
+/*
+ * Indicates if RDTSC can be used (Linux/x86 only, when OS uses TSC clocksource)
+ */
+bool		has_rdtsc = false;
+
+/*
+ * Indicates if RDTSCP can be used. True if RDTSC can be used and RDTSCP is available.
+ */
+bool		has_rdtscp = false;
+
+#define CPUID_HYPERVISOR_VMWARE(words) (words[1] == 0x61774d56 && words[2] == 0x4d566572 && words[3] == 0x65726177) /* VMwareVMware */
+#define CPUID_HYPERVISOR_KVM(words) (words[1] == 0x4b4d564b && words[2] == 0x564b4d56 && words[3] == 0x0000004d)	/* KVMKVMKVM */
+
+static bool
+get_tsc_frequency_khz(uint32 *tsc_freq)
+{
+	uint32		r[4] = {0, 0, 0, 0};
+
+#if defined(HAVE__GET_CPUID)
+	__get_cpuid(0x15, &r[0] /* denominator */ , &r[1] /* numerator */ , &r[2] /* hz */ , &r[3]);
+#elif defined(HAVE__CPUID)
+	__cpuid(r, 0x15);
+#else
+#error cpuid instruction not available
+#endif
+
+	if (r[2] > 0)
+	{
+		if (r[0] == 0 || r[1] == 0)
+			return false;
+
+		*tsc_freq = r[2] / 1000 * r[1] / r[0];
+		return true;
+	}
+
+	/* Some CPUs only report frequency in 16H */
+
+#if defined(HAVE__GET_CPUID)
+	__get_cpuid(0x16, &r[0] /* base_mhz */ , &r[1], &r[2], &r[3]);
+#elif defined(HAVE__CPUID)
+	__cpuid(r, 0x16);
+#else
+#error cpuid instruction not available
+#endif
+
+	if (r[0] > 0)
+	{
+		*tsc_freq = r[0] * 1000;
+		return true;
+	}
+
+	/*
+	 * Check if we have a KVM or VMware Hypervisor passing down TSC frequency
+	 * to us in a guest VM
+	 *
+	 * Note that accessing the 0x40000000 leaf for Hypervisor info requires
+	 * use of __cpuidex to set ECX to 0. The similar __get_cpuid_count
+	 * function does not work as expected since it contains a check for
+	 * __get_cpuid_max, which has been observed to be lower than the special
+	 * Hypervisor leaf.
+	 */
+#if defined(HAVE__CPUIDEX)
+	__cpuidex((int32 *) r, 0x40000000, 0);
+	if (r[0] >= 0x40000010 && (CPUID_HYPERVISOR_VMWARE(r) || CPUID_HYPERVISOR_KVM(r)))
+	{
+		__cpuidex((int32 *) r, 0x40000010, 0);
+		if (r[0] > 0)
+		{
+			*tsc_freq = r[0];
+			return true;
+		}
+	}
+#endif
+
+	return false;
+}
+
+static bool
+is_rdtscp_available()
+{
+	uint32		r[4] = {0, 0, 0, 0};
+
+#if defined(HAVE__GET_CPUID)
+	if (!__get_cpuid(0x80000001, &r[0], &r[1], &r[2], &r[3]))
+		return false;
+#elif defined(HAVE__CPUID)
+	__cpuid(r, 0x80000001);
+#else
+#error cpuid instruction not available
+#endif
+
+	return (r[3] & (1 << 27)) != 0;
+}
+
+/*
+ * Decide whether we use the RDTSC instruction at runtime, for Linux/x86,
+ * instead of incurring the overhead of a full clock_gettime() call.
+ *
+ * This can't be reliably determined at compile time, since the
+ * availability of an "invariant" TSC (that is not affected by CPU
+ * frequency changes) is dependent on the CPU architecture. Additionally,
+ * there are cases where TSC availability is impacted by virtualization,
+ * where a simple cpuid feature check would not be enough.
+ *
+ * Since Linux already does a significant amount of work to determine
+ * whether TSC is a viable clock source, decide based on that.
+ */
+void
+pg_initialize_rdtsc(void)
+{
+	FILE	   *fp = fopen("/sys/devices/system/clocksource/clocksource0/current_clocksource", "r");
+
+	if (fp)
+	{
+		char		buf[128];
+
+		if (fgets(buf, sizeof(buf), fp) != NULL && strcmp(buf, "tsc\n") == 0)
+		{
+			/*
+			 * Compute baseline CPU peformance, determines speed at which
+			 * RDTSC advances.
+			 */
+			uint32		tsc_freq;
+
+			if (get_tsc_frequency_khz(&tsc_freq))
+			{
+				/*
+				 * Ticks to nanoseconds conversion requires floating point
+				 * math because because:
+				 *
+				 * sec = ticks / frequency_hz ns  = ticks / frequency_hz *
+				 * 1,000,000,000 ns  = ticks * (1,000,000,000 / frequency_hz)
+				 * ns  = ticks * (1,000,000 / frequency_khz) <-- now in
+				 * kilohertz
+				 *
+				 * Here, 'ns' is usually a floating number. For example for a
+				 * 2.5 GHz CPU the scaling factor becomes 1,000,000 /
+				 * 2,500,000 = 1.2.
+				 *
+				 * To be able to use integer math we work around the lack of
+				 * precision. We first scale the integer up and after the
+				 * multiplication by the number of ticks in
+				 * INSTR_TIME_GET_NANOSEC() we divide again by the same value.
+				 * We picked the scaler such that it provides enough precision
+				 * and is a power-of-two which allows for shifting instead of
+				 * doing an integer division.
+				 */
+				ticks_per_ns_scaled = INT64CONST(1000000) * TICKS_TO_NS_PRECISION / tsc_freq;
+				ticks_per_sec = tsc_freq * 1000;	/* KHz->Hz */
+				max_ticks_no_overflow = PG_INT64_MAX / ticks_per_ns_scaled;
+
+				has_rdtsc = true;
+				has_rdtscp = is_rdtscp_available();
+			}
+		}
+
+		fclose(fp);
+	}
+}
+#endif							/* defined(__x86_64__) && defined(__linux__) */
+
+#endif							/* WIN32 */
diff --git a/src/common/meson.build b/src/common/meson.build
index 1540ba67cca..62b90b3e609 100644
--- a/src/common/meson.build
+++ b/src/common/meson.build
@@ -13,6 +13,7 @@ common_sources = files(
   'file_perm.c',
   'file_utils.c',
   'hashfn.c',
+  'instr_time.c',
   'ip.c',
   'jsonapi.c',
   'keywords.c',
diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h
index f71a851b18d..e2e339a0c4f 100644
--- a/src/include/portability/instr_time.h
+++ b/src/include/portability/instr_time.h
@@ -4,9 +4,11 @@
  *	  portable high-precision interval timing
  *
  * This file provides an abstraction layer to hide portability issues in
- * interval timing.  On Unix we use clock_gettime(), and on Windows we use
- * QueryPerformanceCounter().  These macros also give some breathing room to
- * use other high-precision-timing APIs.
+ * interval timing. On Linux/x86 we use the rdtsc instruction when a TSC
+ * clocksource is also used on the host OS.  Otherwise, and on other
+ * Unix-like systems we use clock_gettime() and on Windows we use
+ * QueryPerformanceCounter(). These macros also give some breathing
+ * room to use other high-precision-timing APIs.
  *
  * The basic data type is instr_time, which all callers should treat as an
  * opaque typedef.  instr_time can store either an absolute time (of
@@ -17,10 +19,11 @@
  *
  * INSTR_TIME_SET_ZERO(t)			set t to zero (memset is acceptable too)
  *
- * INSTR_TIME_SET_CURRENT(t)		set t to current time
+ * INSTR_TIME_SET_CURRENT_FAST(t)	set t to current time without waiting
+ * 									for instructions in out-of-order window
  *
- * INSTR_TIME_SET_CURRENT_LAZY(t)	set t to current time if t is zero,
- *									evaluates to whether t changed
+ * INSTR_TIME_SET_CURRENT(t)		set t to current time while waiting for
+ * 									instructions in OOO to retire
  *
  * INSTR_TIME_ADD(x, y)				x += y
  *
@@ -81,6 +84,15 @@ typedef struct instr_time
 
 #ifndef WIN32
 
+/*
+ * Make sure this is a power-of-two, so that the compiler can turn the
+ * multiplications and divisions into shifts.
+ */
+#define TICKS_TO_NS_PRECISION (1<<14)
+
+extern int64 ticks_per_ns_scaled;
+extern int64 ticks_per_sec;
+extern int64 max_ticks_no_overflow;
 
 /* Use clock_gettime() */
 
@@ -106,9 +118,18 @@ typedef struct instr_time
 #define PG_INSTR_CLOCK	CLOCK_REALTIME
 #endif
 
-/* helper for INSTR_TIME_SET_CURRENT */
+#if defined(__x86_64__) && defined(__linux__)
+#include <x86intrin.h>
+#include <cpuid.h>
+
+extern bool has_rdtsc;
+extern bool has_rdtscp;
+
+extern void pg_initialize_rdtsc(void);
+#endif
+
 static inline instr_time
-pg_clock_gettime_ns(void)
+pg_clock_gettime(void)
 {
 	instr_time	now;
 	struct timespec tmp;
@@ -119,11 +140,94 @@ pg_clock_gettime_ns(void)
 	return now;
 }
 
+static inline instr_time
+pg_get_ticks_fast(void)
+{
+#if defined(__x86_64__) && defined(__linux__)
+	if (has_rdtsc)
+	{
+		instr_time	now;
+
+		now.ticks = __rdtsc();
+		return now;
+	}
+#endif
+
+	return pg_clock_gettime();
+}
+
+static inline instr_time
+pg_get_ticks(void)
+{
+#if defined(__x86_64__) && defined(__linux__)
+	if (has_rdtscp)
+	{
+		instr_time	now;
+		uint32		unused;
+
+		now.ticks = __rdtscp(&unused);
+		return now;
+	}
+#endif
+
+	return pg_clock_gettime();
+}
+
+static inline int64_t
+pg_ticks_to_ns(instr_time t)
+{
+	/*
+	 * Would multiplication overflow? If so perform computation in two parts.
+	 * Check overflow without actually overflowing via: a * b > max <=> a >
+	 * max / b
+	 */
+	int64		ns = 0;
+
+	if (unlikely(t.ticks > max_ticks_no_overflow))
+	{
+		/*
+		 * Compute how often the maximum number of ticks fits completely into
+		 * the number of elapsed ticks and convert that number into
+		 * nanoseconds. Then multiply by the count to arrive at the final
+		 * 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		max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION;
+
+		ns = max_ns * count;
+
+		/*
+		 * 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);
+	}
+
+	ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION;
+	return ns;
+}
+
+static inline void
+pg_initialize_get_ticks()
+{
+#if defined(__x86_64__) && defined(__linux__)
+	pg_initialize_rdtsc();
+#endif
+}
+
+#define INSTR_TIME_INITIALIZE() \
+	pg_initialize_get_ticks()
+
+#define INSTR_TIME_SET_CURRENT_FAST(t) \
+	((t) = pg_get_ticks_fast())
+
 #define INSTR_TIME_SET_CURRENT(t) \
-	((t) = pg_clock_gettime_ns())
+	((t) = pg_get_ticks())
 
 #define INSTR_TIME_GET_NANOSEC(t) \
-	((int64) (t).ticks)
+	pg_ticks_to_ns(t)
 
 
 #else							/* WIN32 */
@@ -131,7 +235,7 @@ pg_clock_gettime_ns(void)
 
 /* Use QueryPerformanceCounter() */
 
-/* helper for INSTR_TIME_SET_CURRENT */
+/* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */
 static inline instr_time
 pg_query_performance_counter(void)
 {
@@ -153,6 +257,11 @@ GetTimerFrequency(void)
 	return (double) f.QuadPart;
 }
 
+#define INSTR_TIME_INITIALIZE()
+
+#define INSTR_TIME_SET_CURRENT_FAST(t) \
+	((t) = pg_query_performance_counter())
+
 #define INSTR_TIME_SET_CURRENT(t) \
 	((t) = pg_query_performance_counter())
 
@@ -168,13 +277,8 @@ GetTimerFrequency(void)
 
 #define INSTR_TIME_IS_ZERO(t)	((t).ticks == 0)
 
-
 #define INSTR_TIME_SET_ZERO(t)	((t).ticks = 0)
 
-#define INSTR_TIME_SET_CURRENT_LAZY(t) \
-	(INSTR_TIME_IS_ZERO(t) ? INSTR_TIME_SET_CURRENT(t), true : false)
-
-
 #define INSTR_TIME_ADD(x,y) \
 	((x).ticks += (y).ticks)
 
-- 
2.47.3


--vtqqtrpooseurzip
Content-Type: text/x-diff; charset=utf-8
Content-Disposition: attachment;
	filename="v12-0003-pg_test_timing-Add-fast-flag-to-test-fast-timing.patch"



^ permalink  raw  reply  [nested|flat] 271+ messages in thread

* [PATCH v12 2/3] Use time stamp counter to measure time on Linux/x86
@ 2025-07-26 00:57 Lukas Fittl <[email protected]>
  0 siblings, 0 replies; 271+ messages in thread

From: Lukas Fittl @ 2025-07-26 00:57 UTC (permalink / raw)

We switch to using the time stamp counter (TSC) instead of clock_gettime()
to reduce overhead of EXPLAIN (ANALYZE, TIME ON). Tests showed that runtime
is reduced by around 10% for queries moving lots of rows through the plan.

For now this is only enabled on Linux/x86, in case the system clocksource is
reported as TSC. Relying on the Linux kernel simplifies the logic to detect
if the present TSC is usable (frequency invariant, synchronized between
sockets, etc.). In all other cases we fallback to clock_gettime().

Note, that we intentionally use RDTSC in the fast paths, rather than RDTSCP.
RDTSCP waits for outstanding instructions to retire on out-of-order CPUs.
This adds noticably for little benefit in the typical InstrStartNode() /
InstrStopNode() use case. The macro to be used in such cases is called
INSTR_TIME_SET_CURRENT_FAST(). The original macro INSTR_TIME_SET_CURRENT()
uses RDTSCP and is supposed to be used when precision is more important
than performance.

Author: David Geier <[email protected]>
Author: Andres Freund <[email protected]>
Author: Lukas Fittl <[email protected]>
Reviewed-by:
Discussion: https://www.postgresql.org/message-id/flat/20200612232810.f46nbqkdhbutzqdg%40alap3.anarazel.de
---
 src/backend/access/heap/vacuumlazy.c |   4 +-
 src/backend/executor/instrument.c    |  12 +-
 src/backend/utils/init/postinit.c    |   3 +
 src/bin/pgbench/pgbench.c            |   3 +
 src/bin/psql/startup.c               |   4 +
 src/common/Makefile                  |   1 +
 src/common/instr_time.c              | 206 +++++++++++++++++++++++++++
 src/common/meson.build               |   1 +
 src/include/portability/instr_time.h | 136 +++++++++++++++---
 9 files changed, 348 insertions(+), 22 deletions(-)
 create mode 100644 src/common/instr_time.c

diff --git a/src/backend/access/heap/vacuumlazy.c b/src/backend/access/heap/vacuumlazy.c
index d2b031fdd06..5027048cac4 100644
--- a/src/backend/access/heap/vacuumlazy.c
+++ b/src/backend/access/heap/vacuumlazy.c
@@ -3409,8 +3409,8 @@ count_nondeletable_pages(LVRelState *vacrel, bool *lock_waiter_detected)
 			INSTR_TIME_SET_CURRENT(currenttime);
 			elapsed = currenttime;
 			INSTR_TIME_SUBTRACT(elapsed, starttime);
-			if ((INSTR_TIME_GET_MICROSEC(elapsed) / 1000)
-				>= VACUUM_TRUNCATE_LOCK_CHECK_INTERVAL)
+			if (INSTR_TIME_GET_MILLISEC(elapsed) >=
+				VACUUM_TRUNCATE_LOCK_CHECK_INTERVAL)
 			{
 				if (LockHasWaitersRelation(vacrel->rel, AccessExclusiveLock))
 				{
diff --git a/src/backend/executor/instrument.c b/src/backend/executor/instrument.c
index 56e635f4700..01f67c5d972 100644
--- a/src/backend/executor/instrument.c
+++ b/src/backend/executor/instrument.c
@@ -67,9 +67,13 @@ InstrInit(Instrumentation *instr, int instrument_options)
 void
 InstrStartNode(Instrumentation *instr)
 {
-	if (instr->need_timer &&
-		!INSTR_TIME_SET_CURRENT_LAZY(instr->starttime))
-		elog(ERROR, "InstrStartNode called twice in a row");
+	if (instr->need_timer)
+	{
+		if (!INSTR_TIME_IS_ZERO(instr->starttime))
+			elog(ERROR, "InstrStartNode called twice in a row");
+		else
+			INSTR_TIME_SET_CURRENT_FAST(instr->starttime);
+	}
 
 	/* save buffer usage totals at node entry, if needed */
 	if (instr->need_bufusage)
@@ -95,7 +99,7 @@ InstrStopNode(Instrumentation *instr, double nTuples)
 		if (INSTR_TIME_IS_ZERO(instr->starttime))
 			elog(ERROR, "InstrStopNode called without start");
 
-		INSTR_TIME_SET_CURRENT(endtime);
+		INSTR_TIME_SET_CURRENT_FAST(endtime);
 		INSTR_TIME_ACCUM_DIFF(instr->counter, endtime, instr->starttime);
 
 		INSTR_TIME_SET_ZERO(instr->starttime);
diff --git a/src/backend/utils/init/postinit.c b/src/backend/utils/init/postinit.c
index 641e535a73c..d573409903b 100644
--- a/src/backend/utils/init/postinit.c
+++ b/src/backend/utils/init/postinit.c
@@ -810,6 +810,9 @@ InitPostgres(const char *in_dbname, Oid dboid,
 	/* Initialize portal manager */
 	EnablePortalManager();
 
+	/* initialize high-precision interval timing */
+	INSTR_TIME_INITIALIZE();
+
 	/*
 	 * Load relcache entries for the shared system catalogs.  This must create
 	 * at least entries for pg_database and catalogs used for authentication.
diff --git a/src/bin/pgbench/pgbench.c b/src/bin/pgbench/pgbench.c
index 1515ed405ba..79bef2d2aec 100644
--- a/src/bin/pgbench/pgbench.c
+++ b/src/bin/pgbench/pgbench.c
@@ -7290,6 +7290,9 @@ main(int argc, char **argv)
 		initRandomState(&state[i].cs_func_rs);
 	}
 
+	/* initialize high-precision interval timing */
+	INSTR_TIME_INITIALIZE();
+
 	/* opening connection... */
 	con = doConnect();
 	if (con == NULL)
diff --git a/src/bin/psql/startup.c b/src/bin/psql/startup.c
index 249b6aa5169..d615df593c7 100644
--- a/src/bin/psql/startup.c
+++ b/src/bin/psql/startup.c
@@ -24,6 +24,7 @@
 #include "help.h"
 #include "input.h"
 #include "mainloop.h"
+#include "portability/instr_time.h"
 #include "settings.h"
 
 /*
@@ -327,6 +328,9 @@ main(int argc, char *argv[])
 
 	PQsetNoticeProcessor(pset.db, NoticeProcessor, NULL);
 
+	/* initialize high-precision interval timing */
+	INSTR_TIME_INITIALIZE();
+
 	SyncVariables();
 
 	if (options.list_dbs)
diff --git a/src/common/Makefile b/src/common/Makefile
index 2c720caa509..1a2fbbe887f 100644
--- a/src/common/Makefile
+++ b/src/common/Makefile
@@ -59,6 +59,7 @@ OBJS_COMMON = \
 	file_perm.o \
 	file_utils.o \
 	hashfn.o \
+	instr_time.o \
 	ip.o \
 	jsonapi.o \
 	keywords.o \
diff --git a/src/common/instr_time.c b/src/common/instr_time.c
new file mode 100644
index 00000000000..fdf47699f20
--- /dev/null
+++ b/src/common/instr_time.c
@@ -0,0 +1,206 @@
+/*-------------------------------------------------------------------------
+ *
+ * instr_time.c
+ *	   Non-inline parts of the portable high-precision interval timing
+ *	 implementation
+ *
+ * Portions Copyright (c) 2025, PostgreSQL Global Development Group
+ *
+ *
+ * IDENTIFICATION
+ *	  src/backend/port/instr_time.c
+ *
+ *-------------------------------------------------------------------------
+ */
+#include "postgres.h"
+
+#if defined(HAVE__GET_CPUID) || (defined(HAVE__CPUIDEX) && !defined(_MSC_VER))
+#include <cpuid.h>
+#endif
+
+#if defined(HAVE__CPUID) || (defined(HAVE__CPUIDEX) && defined(_MSC_VER))
+#include <intrin.h>
+#endif
+
+#include "portability/instr_time.h"
+
+#ifndef WIN32
+/*
+ * Stores what the number of cycles needs to be multiplied with to end up
+ * with nanoseconds using integer math. See comment in pg_initialize_rdtsc()
+ * for more details.
+ *
+ * By default assume we are using clock_gettime() as a fallback which uses
+ * nanoseconds as ticks. Hence, we set the multiplier to the precision scalar
+ * so that the division in INSTR_TIME_GET_NANOSEC() won't change the nanoseconds.
+ *
+ * When using the RDTSC instruction directly this is filled in during initialization
+ * based on the relevant CPUID fields.
+ */
+int64		ticks_per_ns_scaled = TICKS_TO_NS_PRECISION;
+int64		ticks_per_sec = NS_PER_S;
+int64		max_ticks_no_overflow = PG_INT64_MAX / TICKS_TO_NS_PRECISION;
+
+#if defined(__x86_64__) && defined(__linux__)
+/*
+ * Indicates if RDTSC can be used (Linux/x86 only, when OS uses TSC clocksource)
+ */
+bool		has_rdtsc = false;
+
+/*
+ * Indicates if RDTSCP can be used. True if RDTSC can be used and RDTSCP is available.
+ */
+bool		has_rdtscp = false;
+
+#define CPUID_HYPERVISOR_VMWARE(words) (words[1] == 0x61774d56 && words[2] == 0x4d566572 && words[3] == 0x65726177) /* VMwareVMware */
+#define CPUID_HYPERVISOR_KVM(words) (words[1] == 0x4b4d564b && words[2] == 0x564b4d56 && words[3] == 0x0000004d)	/* KVMKVMKVM */
+
+static bool
+get_tsc_frequency_khz(uint32 *tsc_freq)
+{
+	uint32		r[4] = {0, 0, 0, 0};
+
+#if defined(HAVE__GET_CPUID)
+	__get_cpuid(0x15, &r[0] /* denominator */ , &r[1] /* numerator */ , &r[2] /* hz */ , &r[3]);
+#elif defined(HAVE__CPUID)
+	__cpuid(r, 0x15);
+#else
+#error cpuid instruction not available
+#endif
+
+	if (r[2] > 0)
+	{
+		if (r[0] == 0 || r[1] == 0)
+			return false;
+
+		*tsc_freq = r[2] / 1000 * r[1] / r[0];
+		return true;
+	}
+
+	/* Some CPUs only report frequency in 16H */
+
+#if defined(HAVE__GET_CPUID)
+	__get_cpuid(0x16, &r[0] /* base_mhz */ , &r[1], &r[2], &r[3]);
+#elif defined(HAVE__CPUID)
+	__cpuid(r, 0x16);
+#else
+#error cpuid instruction not available
+#endif
+
+	if (r[0] > 0)
+	{
+		*tsc_freq = r[0] * 1000;
+		return true;
+	}
+
+	/*
+	 * Check if we have a KVM or VMware Hypervisor passing down TSC frequency
+	 * to us in a guest VM
+	 *
+	 * Note that accessing the 0x40000000 leaf for Hypervisor info requires
+	 * use of __cpuidex to set ECX to 0. The similar __get_cpuid_count
+	 * function does not work as expected since it contains a check for
+	 * __get_cpuid_max, which has been observed to be lower than the special
+	 * Hypervisor leaf.
+	 */
+#if defined(HAVE__CPUIDEX)
+	__cpuidex((int32 *) r, 0x40000000, 0);
+	if (r[0] >= 0x40000010 && (CPUID_HYPERVISOR_VMWARE(r) || CPUID_HYPERVISOR_KVM(r)))
+	{
+		__cpuidex((int32 *) r, 0x40000010, 0);
+		if (r[0] > 0)
+		{
+			*tsc_freq = r[0];
+			return true;
+		}
+	}
+#endif
+
+	return false;
+}
+
+static bool
+is_rdtscp_available()
+{
+	uint32		r[4] = {0, 0, 0, 0};
+
+#if defined(HAVE__GET_CPUID)
+	if (!__get_cpuid(0x80000001, &r[0], &r[1], &r[2], &r[3]))
+		return false;
+#elif defined(HAVE__CPUID)
+	__cpuid(r, 0x80000001);
+#else
+#error cpuid instruction not available
+#endif
+
+	return (r[3] & (1 << 27)) != 0;
+}
+
+/*
+ * Decide whether we use the RDTSC instruction at runtime, for Linux/x86,
+ * instead of incurring the overhead of a full clock_gettime() call.
+ *
+ * This can't be reliably determined at compile time, since the
+ * availability of an "invariant" TSC (that is not affected by CPU
+ * frequency changes) is dependent on the CPU architecture. Additionally,
+ * there are cases where TSC availability is impacted by virtualization,
+ * where a simple cpuid feature check would not be enough.
+ *
+ * Since Linux already does a significant amount of work to determine
+ * whether TSC is a viable clock source, decide based on that.
+ */
+void
+pg_initialize_rdtsc(void)
+{
+	FILE	   *fp = fopen("/sys/devices/system/clocksource/clocksource0/current_clocksource", "r");
+
+	if (fp)
+	{
+		char		buf[128];
+
+		if (fgets(buf, sizeof(buf), fp) != NULL && strcmp(buf, "tsc\n") == 0)
+		{
+			/*
+			 * Compute baseline CPU peformance, determines speed at which
+			 * RDTSC advances.
+			 */
+			uint32		tsc_freq;
+
+			if (get_tsc_frequency_khz(&tsc_freq))
+			{
+				/*
+				 * Ticks to nanoseconds conversion requires floating point
+				 * math because because:
+				 *
+				 * sec = ticks / frequency_hz ns  = ticks / frequency_hz *
+				 * 1,000,000,000 ns  = ticks * (1,000,000,000 / frequency_hz)
+				 * ns  = ticks * (1,000,000 / frequency_khz) <-- now in
+				 * kilohertz
+				 *
+				 * Here, 'ns' is usually a floating number. For example for a
+				 * 2.5 GHz CPU the scaling factor becomes 1,000,000 /
+				 * 2,500,000 = 1.2.
+				 *
+				 * To be able to use integer math we work around the lack of
+				 * precision. We first scale the integer up and after the
+				 * multiplication by the number of ticks in
+				 * INSTR_TIME_GET_NANOSEC() we divide again by the same value.
+				 * We picked the scaler such that it provides enough precision
+				 * and is a power-of-two which allows for shifting instead of
+				 * doing an integer division.
+				 */
+				ticks_per_ns_scaled = INT64CONST(1000000) * TICKS_TO_NS_PRECISION / tsc_freq;
+				ticks_per_sec = tsc_freq * 1000;	/* KHz->Hz */
+				max_ticks_no_overflow = PG_INT64_MAX / ticks_per_ns_scaled;
+
+				has_rdtsc = true;
+				has_rdtscp = is_rdtscp_available();
+			}
+		}
+
+		fclose(fp);
+	}
+}
+#endif							/* defined(__x86_64__) && defined(__linux__) */
+
+#endif							/* WIN32 */
diff --git a/src/common/meson.build b/src/common/meson.build
index 1540ba67cca..62b90b3e609 100644
--- a/src/common/meson.build
+++ b/src/common/meson.build
@@ -13,6 +13,7 @@ common_sources = files(
   'file_perm.c',
   'file_utils.c',
   'hashfn.c',
+  'instr_time.c',
   'ip.c',
   'jsonapi.c',
   'keywords.c',
diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h
index f71a851b18d..e2e339a0c4f 100644
--- a/src/include/portability/instr_time.h
+++ b/src/include/portability/instr_time.h
@@ -4,9 +4,11 @@
  *	  portable high-precision interval timing
  *
  * This file provides an abstraction layer to hide portability issues in
- * interval timing.  On Unix we use clock_gettime(), and on Windows we use
- * QueryPerformanceCounter().  These macros also give some breathing room to
- * use other high-precision-timing APIs.
+ * interval timing. On Linux/x86 we use the rdtsc instruction when a TSC
+ * clocksource is also used on the host OS.  Otherwise, and on other
+ * Unix-like systems we use clock_gettime() and on Windows we use
+ * QueryPerformanceCounter(). These macros also give some breathing
+ * room to use other high-precision-timing APIs.
  *
  * The basic data type is instr_time, which all callers should treat as an
  * opaque typedef.  instr_time can store either an absolute time (of
@@ -17,10 +19,11 @@
  *
  * INSTR_TIME_SET_ZERO(t)			set t to zero (memset is acceptable too)
  *
- * INSTR_TIME_SET_CURRENT(t)		set t to current time
+ * INSTR_TIME_SET_CURRENT_FAST(t)	set t to current time without waiting
+ * 									for instructions in out-of-order window
  *
- * INSTR_TIME_SET_CURRENT_LAZY(t)	set t to current time if t is zero,
- *									evaluates to whether t changed
+ * INSTR_TIME_SET_CURRENT(t)		set t to current time while waiting for
+ * 									instructions in OOO to retire
  *
  * INSTR_TIME_ADD(x, y)				x += y
  *
@@ -81,6 +84,15 @@ typedef struct instr_time
 
 #ifndef WIN32
 
+/*
+ * Make sure this is a power-of-two, so that the compiler can turn the
+ * multiplications and divisions into shifts.
+ */
+#define TICKS_TO_NS_PRECISION (1<<14)
+
+extern int64 ticks_per_ns_scaled;
+extern int64 ticks_per_sec;
+extern int64 max_ticks_no_overflow;
 
 /* Use clock_gettime() */
 
@@ -106,9 +118,18 @@ typedef struct instr_time
 #define PG_INSTR_CLOCK	CLOCK_REALTIME
 #endif
 
-/* helper for INSTR_TIME_SET_CURRENT */
+#if defined(__x86_64__) && defined(__linux__)
+#include <x86intrin.h>
+#include <cpuid.h>
+
+extern bool has_rdtsc;
+extern bool has_rdtscp;
+
+extern void pg_initialize_rdtsc(void);
+#endif
+
 static inline instr_time
-pg_clock_gettime_ns(void)
+pg_clock_gettime(void)
 {
 	instr_time	now;
 	struct timespec tmp;
@@ -119,11 +140,94 @@ pg_clock_gettime_ns(void)
 	return now;
 }
 
+static inline instr_time
+pg_get_ticks_fast(void)
+{
+#if defined(__x86_64__) && defined(__linux__)
+	if (has_rdtsc)
+	{
+		instr_time	now;
+
+		now.ticks = __rdtsc();
+		return now;
+	}
+#endif
+
+	return pg_clock_gettime();
+}
+
+static inline instr_time
+pg_get_ticks(void)
+{
+#if defined(__x86_64__) && defined(__linux__)
+	if (has_rdtscp)
+	{
+		instr_time	now;
+		uint32		unused;
+
+		now.ticks = __rdtscp(&unused);
+		return now;
+	}
+#endif
+
+	return pg_clock_gettime();
+}
+
+static inline int64_t
+pg_ticks_to_ns(instr_time t)
+{
+	/*
+	 * Would multiplication overflow? If so perform computation in two parts.
+	 * Check overflow without actually overflowing via: a * b > max <=> a >
+	 * max / b
+	 */
+	int64		ns = 0;
+
+	if (unlikely(t.ticks > max_ticks_no_overflow))
+	{
+		/*
+		 * Compute how often the maximum number of ticks fits completely into
+		 * the number of elapsed ticks and convert that number into
+		 * nanoseconds. Then multiply by the count to arrive at the final
+		 * 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		max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION;
+
+		ns = max_ns * count;
+
+		/*
+		 * 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);
+	}
+
+	ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION;
+	return ns;
+}
+
+static inline void
+pg_initialize_get_ticks()
+{
+#if defined(__x86_64__) && defined(__linux__)
+	pg_initialize_rdtsc();
+#endif
+}
+
+#define INSTR_TIME_INITIALIZE() \
+	pg_initialize_get_ticks()
+
+#define INSTR_TIME_SET_CURRENT_FAST(t) \
+	((t) = pg_get_ticks_fast())
+
 #define INSTR_TIME_SET_CURRENT(t) \
-	((t) = pg_clock_gettime_ns())
+	((t) = pg_get_ticks())
 
 #define INSTR_TIME_GET_NANOSEC(t) \
-	((int64) (t).ticks)
+	pg_ticks_to_ns(t)
 
 
 #else							/* WIN32 */
@@ -131,7 +235,7 @@ pg_clock_gettime_ns(void)
 
 /* Use QueryPerformanceCounter() */
 
-/* helper for INSTR_TIME_SET_CURRENT */
+/* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */
 static inline instr_time
 pg_query_performance_counter(void)
 {
@@ -153,6 +257,11 @@ GetTimerFrequency(void)
 	return (double) f.QuadPart;
 }
 
+#define INSTR_TIME_INITIALIZE()
+
+#define INSTR_TIME_SET_CURRENT_FAST(t) \
+	((t) = pg_query_performance_counter())
+
 #define INSTR_TIME_SET_CURRENT(t) \
 	((t) = pg_query_performance_counter())
 
@@ -168,13 +277,8 @@ GetTimerFrequency(void)
 
 #define INSTR_TIME_IS_ZERO(t)	((t).ticks == 0)
 
-
 #define INSTR_TIME_SET_ZERO(t)	((t).ticks = 0)
 
-#define INSTR_TIME_SET_CURRENT_LAZY(t) \
-	(INSTR_TIME_IS_ZERO(t) ? INSTR_TIME_SET_CURRENT(t), true : false)
-
-
 #define INSTR_TIME_ADD(x,y) \
 	((x).ticks += (y).ticks)
 
-- 
2.47.3


--vtqqtrpooseurzip
Content-Type: text/x-diff; charset=utf-8
Content-Disposition: attachment;
	filename="v12-0003-pg_test_timing-Add-fast-flag-to-test-fast-timing.patch"



^ permalink  raw  reply  [nested|flat] 271+ messages in thread

* [PATCH v12 2/3] Use time stamp counter to measure time on Linux/x86
@ 2025-07-26 00:57 Lukas Fittl <[email protected]>
  0 siblings, 0 replies; 271+ messages in thread

From: Lukas Fittl @ 2025-07-26 00:57 UTC (permalink / raw)

We switch to using the time stamp counter (TSC) instead of clock_gettime()
to reduce overhead of EXPLAIN (ANALYZE, TIME ON). Tests showed that runtime
is reduced by around 10% for queries moving lots of rows through the plan.

For now this is only enabled on Linux/x86, in case the system clocksource is
reported as TSC. Relying on the Linux kernel simplifies the logic to detect
if the present TSC is usable (frequency invariant, synchronized between
sockets, etc.). In all other cases we fallback to clock_gettime().

Note, that we intentionally use RDTSC in the fast paths, rather than RDTSCP.
RDTSCP waits for outstanding instructions to retire on out-of-order CPUs.
This adds noticably for little benefit in the typical InstrStartNode() /
InstrStopNode() use case. The macro to be used in such cases is called
INSTR_TIME_SET_CURRENT_FAST(). The original macro INSTR_TIME_SET_CURRENT()
uses RDTSCP and is supposed to be used when precision is more important
than performance.

Author: David Geier <[email protected]>
Author: Andres Freund <[email protected]>
Author: Lukas Fittl <[email protected]>
Reviewed-by:
Discussion: https://www.postgresql.org/message-id/flat/20200612232810.f46nbqkdhbutzqdg%40alap3.anarazel.de
---
 src/backend/access/heap/vacuumlazy.c |   4 +-
 src/backend/executor/instrument.c    |  12 +-
 src/backend/utils/init/postinit.c    |   3 +
 src/bin/pgbench/pgbench.c            |   3 +
 src/bin/psql/startup.c               |   4 +
 src/common/Makefile                  |   1 +
 src/common/instr_time.c              | 206 +++++++++++++++++++++++++++
 src/common/meson.build               |   1 +
 src/include/portability/instr_time.h | 136 +++++++++++++++---
 9 files changed, 348 insertions(+), 22 deletions(-)
 create mode 100644 src/common/instr_time.c

diff --git a/src/backend/access/heap/vacuumlazy.c b/src/backend/access/heap/vacuumlazy.c
index d2b031fdd06..5027048cac4 100644
--- a/src/backend/access/heap/vacuumlazy.c
+++ b/src/backend/access/heap/vacuumlazy.c
@@ -3409,8 +3409,8 @@ count_nondeletable_pages(LVRelState *vacrel, bool *lock_waiter_detected)
 			INSTR_TIME_SET_CURRENT(currenttime);
 			elapsed = currenttime;
 			INSTR_TIME_SUBTRACT(elapsed, starttime);
-			if ((INSTR_TIME_GET_MICROSEC(elapsed) / 1000)
-				>= VACUUM_TRUNCATE_LOCK_CHECK_INTERVAL)
+			if (INSTR_TIME_GET_MILLISEC(elapsed) >=
+				VACUUM_TRUNCATE_LOCK_CHECK_INTERVAL)
 			{
 				if (LockHasWaitersRelation(vacrel->rel, AccessExclusiveLock))
 				{
diff --git a/src/backend/executor/instrument.c b/src/backend/executor/instrument.c
index 56e635f4700..01f67c5d972 100644
--- a/src/backend/executor/instrument.c
+++ b/src/backend/executor/instrument.c
@@ -67,9 +67,13 @@ InstrInit(Instrumentation *instr, int instrument_options)
 void
 InstrStartNode(Instrumentation *instr)
 {
-	if (instr->need_timer &&
-		!INSTR_TIME_SET_CURRENT_LAZY(instr->starttime))
-		elog(ERROR, "InstrStartNode called twice in a row");
+	if (instr->need_timer)
+	{
+		if (!INSTR_TIME_IS_ZERO(instr->starttime))
+			elog(ERROR, "InstrStartNode called twice in a row");
+		else
+			INSTR_TIME_SET_CURRENT_FAST(instr->starttime);
+	}
 
 	/* save buffer usage totals at node entry, if needed */
 	if (instr->need_bufusage)
@@ -95,7 +99,7 @@ InstrStopNode(Instrumentation *instr, double nTuples)
 		if (INSTR_TIME_IS_ZERO(instr->starttime))
 			elog(ERROR, "InstrStopNode called without start");
 
-		INSTR_TIME_SET_CURRENT(endtime);
+		INSTR_TIME_SET_CURRENT_FAST(endtime);
 		INSTR_TIME_ACCUM_DIFF(instr->counter, endtime, instr->starttime);
 
 		INSTR_TIME_SET_ZERO(instr->starttime);
diff --git a/src/backend/utils/init/postinit.c b/src/backend/utils/init/postinit.c
index 641e535a73c..d573409903b 100644
--- a/src/backend/utils/init/postinit.c
+++ b/src/backend/utils/init/postinit.c
@@ -810,6 +810,9 @@ InitPostgres(const char *in_dbname, Oid dboid,
 	/* Initialize portal manager */
 	EnablePortalManager();
 
+	/* initialize high-precision interval timing */
+	INSTR_TIME_INITIALIZE();
+
 	/*
 	 * Load relcache entries for the shared system catalogs.  This must create
 	 * at least entries for pg_database and catalogs used for authentication.
diff --git a/src/bin/pgbench/pgbench.c b/src/bin/pgbench/pgbench.c
index 1515ed405ba..79bef2d2aec 100644
--- a/src/bin/pgbench/pgbench.c
+++ b/src/bin/pgbench/pgbench.c
@@ -7290,6 +7290,9 @@ main(int argc, char **argv)
 		initRandomState(&state[i].cs_func_rs);
 	}
 
+	/* initialize high-precision interval timing */
+	INSTR_TIME_INITIALIZE();
+
 	/* opening connection... */
 	con = doConnect();
 	if (con == NULL)
diff --git a/src/bin/psql/startup.c b/src/bin/psql/startup.c
index 249b6aa5169..d615df593c7 100644
--- a/src/bin/psql/startup.c
+++ b/src/bin/psql/startup.c
@@ -24,6 +24,7 @@
 #include "help.h"
 #include "input.h"
 #include "mainloop.h"
+#include "portability/instr_time.h"
 #include "settings.h"
 
 /*
@@ -327,6 +328,9 @@ main(int argc, char *argv[])
 
 	PQsetNoticeProcessor(pset.db, NoticeProcessor, NULL);
 
+	/* initialize high-precision interval timing */
+	INSTR_TIME_INITIALIZE();
+
 	SyncVariables();
 
 	if (options.list_dbs)
diff --git a/src/common/Makefile b/src/common/Makefile
index 2c720caa509..1a2fbbe887f 100644
--- a/src/common/Makefile
+++ b/src/common/Makefile
@@ -59,6 +59,7 @@ OBJS_COMMON = \
 	file_perm.o \
 	file_utils.o \
 	hashfn.o \
+	instr_time.o \
 	ip.o \
 	jsonapi.o \
 	keywords.o \
diff --git a/src/common/instr_time.c b/src/common/instr_time.c
new file mode 100644
index 00000000000..fdf47699f20
--- /dev/null
+++ b/src/common/instr_time.c
@@ -0,0 +1,206 @@
+/*-------------------------------------------------------------------------
+ *
+ * instr_time.c
+ *	   Non-inline parts of the portable high-precision interval timing
+ *	 implementation
+ *
+ * Portions Copyright (c) 2025, PostgreSQL Global Development Group
+ *
+ *
+ * IDENTIFICATION
+ *	  src/backend/port/instr_time.c
+ *
+ *-------------------------------------------------------------------------
+ */
+#include "postgres.h"
+
+#if defined(HAVE__GET_CPUID) || (defined(HAVE__CPUIDEX) && !defined(_MSC_VER))
+#include <cpuid.h>
+#endif
+
+#if defined(HAVE__CPUID) || (defined(HAVE__CPUIDEX) && defined(_MSC_VER))
+#include <intrin.h>
+#endif
+
+#include "portability/instr_time.h"
+
+#ifndef WIN32
+/*
+ * Stores what the number of cycles needs to be multiplied with to end up
+ * with nanoseconds using integer math. See comment in pg_initialize_rdtsc()
+ * for more details.
+ *
+ * By default assume we are using clock_gettime() as a fallback which uses
+ * nanoseconds as ticks. Hence, we set the multiplier to the precision scalar
+ * so that the division in INSTR_TIME_GET_NANOSEC() won't change the nanoseconds.
+ *
+ * When using the RDTSC instruction directly this is filled in during initialization
+ * based on the relevant CPUID fields.
+ */
+int64		ticks_per_ns_scaled = TICKS_TO_NS_PRECISION;
+int64		ticks_per_sec = NS_PER_S;
+int64		max_ticks_no_overflow = PG_INT64_MAX / TICKS_TO_NS_PRECISION;
+
+#if defined(__x86_64__) && defined(__linux__)
+/*
+ * Indicates if RDTSC can be used (Linux/x86 only, when OS uses TSC clocksource)
+ */
+bool		has_rdtsc = false;
+
+/*
+ * Indicates if RDTSCP can be used. True if RDTSC can be used and RDTSCP is available.
+ */
+bool		has_rdtscp = false;
+
+#define CPUID_HYPERVISOR_VMWARE(words) (words[1] == 0x61774d56 && words[2] == 0x4d566572 && words[3] == 0x65726177) /* VMwareVMware */
+#define CPUID_HYPERVISOR_KVM(words) (words[1] == 0x4b4d564b && words[2] == 0x564b4d56 && words[3] == 0x0000004d)	/* KVMKVMKVM */
+
+static bool
+get_tsc_frequency_khz(uint32 *tsc_freq)
+{
+	uint32		r[4] = {0, 0, 0, 0};
+
+#if defined(HAVE__GET_CPUID)
+	__get_cpuid(0x15, &r[0] /* denominator */ , &r[1] /* numerator */ , &r[2] /* hz */ , &r[3]);
+#elif defined(HAVE__CPUID)
+	__cpuid(r, 0x15);
+#else
+#error cpuid instruction not available
+#endif
+
+	if (r[2] > 0)
+	{
+		if (r[0] == 0 || r[1] == 0)
+			return false;
+
+		*tsc_freq = r[2] / 1000 * r[1] / r[0];
+		return true;
+	}
+
+	/* Some CPUs only report frequency in 16H */
+
+#if defined(HAVE__GET_CPUID)
+	__get_cpuid(0x16, &r[0] /* base_mhz */ , &r[1], &r[2], &r[3]);
+#elif defined(HAVE__CPUID)
+	__cpuid(r, 0x16);
+#else
+#error cpuid instruction not available
+#endif
+
+	if (r[0] > 0)
+	{
+		*tsc_freq = r[0] * 1000;
+		return true;
+	}
+
+	/*
+	 * Check if we have a KVM or VMware Hypervisor passing down TSC frequency
+	 * to us in a guest VM
+	 *
+	 * Note that accessing the 0x40000000 leaf for Hypervisor info requires
+	 * use of __cpuidex to set ECX to 0. The similar __get_cpuid_count
+	 * function does not work as expected since it contains a check for
+	 * __get_cpuid_max, which has been observed to be lower than the special
+	 * Hypervisor leaf.
+	 */
+#if defined(HAVE__CPUIDEX)
+	__cpuidex((int32 *) r, 0x40000000, 0);
+	if (r[0] >= 0x40000010 && (CPUID_HYPERVISOR_VMWARE(r) || CPUID_HYPERVISOR_KVM(r)))
+	{
+		__cpuidex((int32 *) r, 0x40000010, 0);
+		if (r[0] > 0)
+		{
+			*tsc_freq = r[0];
+			return true;
+		}
+	}
+#endif
+
+	return false;
+}
+
+static bool
+is_rdtscp_available()
+{
+	uint32		r[4] = {0, 0, 0, 0};
+
+#if defined(HAVE__GET_CPUID)
+	if (!__get_cpuid(0x80000001, &r[0], &r[1], &r[2], &r[3]))
+		return false;
+#elif defined(HAVE__CPUID)
+	__cpuid(r, 0x80000001);
+#else
+#error cpuid instruction not available
+#endif
+
+	return (r[3] & (1 << 27)) != 0;
+}
+
+/*
+ * Decide whether we use the RDTSC instruction at runtime, for Linux/x86,
+ * instead of incurring the overhead of a full clock_gettime() call.
+ *
+ * This can't be reliably determined at compile time, since the
+ * availability of an "invariant" TSC (that is not affected by CPU
+ * frequency changes) is dependent on the CPU architecture. Additionally,
+ * there are cases where TSC availability is impacted by virtualization,
+ * where a simple cpuid feature check would not be enough.
+ *
+ * Since Linux already does a significant amount of work to determine
+ * whether TSC is a viable clock source, decide based on that.
+ */
+void
+pg_initialize_rdtsc(void)
+{
+	FILE	   *fp = fopen("/sys/devices/system/clocksource/clocksource0/current_clocksource", "r");
+
+	if (fp)
+	{
+		char		buf[128];
+
+		if (fgets(buf, sizeof(buf), fp) != NULL && strcmp(buf, "tsc\n") == 0)
+		{
+			/*
+			 * Compute baseline CPU peformance, determines speed at which
+			 * RDTSC advances.
+			 */
+			uint32		tsc_freq;
+
+			if (get_tsc_frequency_khz(&tsc_freq))
+			{
+				/*
+				 * Ticks to nanoseconds conversion requires floating point
+				 * math because because:
+				 *
+				 * sec = ticks / frequency_hz ns  = ticks / frequency_hz *
+				 * 1,000,000,000 ns  = ticks * (1,000,000,000 / frequency_hz)
+				 * ns  = ticks * (1,000,000 / frequency_khz) <-- now in
+				 * kilohertz
+				 *
+				 * Here, 'ns' is usually a floating number. For example for a
+				 * 2.5 GHz CPU the scaling factor becomes 1,000,000 /
+				 * 2,500,000 = 1.2.
+				 *
+				 * To be able to use integer math we work around the lack of
+				 * precision. We first scale the integer up and after the
+				 * multiplication by the number of ticks in
+				 * INSTR_TIME_GET_NANOSEC() we divide again by the same value.
+				 * We picked the scaler such that it provides enough precision
+				 * and is a power-of-two which allows for shifting instead of
+				 * doing an integer division.
+				 */
+				ticks_per_ns_scaled = INT64CONST(1000000) * TICKS_TO_NS_PRECISION / tsc_freq;
+				ticks_per_sec = tsc_freq * 1000;	/* KHz->Hz */
+				max_ticks_no_overflow = PG_INT64_MAX / ticks_per_ns_scaled;
+
+				has_rdtsc = true;
+				has_rdtscp = is_rdtscp_available();
+			}
+		}
+
+		fclose(fp);
+	}
+}
+#endif							/* defined(__x86_64__) && defined(__linux__) */
+
+#endif							/* WIN32 */
diff --git a/src/common/meson.build b/src/common/meson.build
index 1540ba67cca..62b90b3e609 100644
--- a/src/common/meson.build
+++ b/src/common/meson.build
@@ -13,6 +13,7 @@ common_sources = files(
   'file_perm.c',
   'file_utils.c',
   'hashfn.c',
+  'instr_time.c',
   'ip.c',
   'jsonapi.c',
   'keywords.c',
diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h
index f71a851b18d..e2e339a0c4f 100644
--- a/src/include/portability/instr_time.h
+++ b/src/include/portability/instr_time.h
@@ -4,9 +4,11 @@
  *	  portable high-precision interval timing
  *
  * This file provides an abstraction layer to hide portability issues in
- * interval timing.  On Unix we use clock_gettime(), and on Windows we use
- * QueryPerformanceCounter().  These macros also give some breathing room to
- * use other high-precision-timing APIs.
+ * interval timing. On Linux/x86 we use the rdtsc instruction when a TSC
+ * clocksource is also used on the host OS.  Otherwise, and on other
+ * Unix-like systems we use clock_gettime() and on Windows we use
+ * QueryPerformanceCounter(). These macros also give some breathing
+ * room to use other high-precision-timing APIs.
  *
  * The basic data type is instr_time, which all callers should treat as an
  * opaque typedef.  instr_time can store either an absolute time (of
@@ -17,10 +19,11 @@
  *
  * INSTR_TIME_SET_ZERO(t)			set t to zero (memset is acceptable too)
  *
- * INSTR_TIME_SET_CURRENT(t)		set t to current time
+ * INSTR_TIME_SET_CURRENT_FAST(t)	set t to current time without waiting
+ * 									for instructions in out-of-order window
  *
- * INSTR_TIME_SET_CURRENT_LAZY(t)	set t to current time if t is zero,
- *									evaluates to whether t changed
+ * INSTR_TIME_SET_CURRENT(t)		set t to current time while waiting for
+ * 									instructions in OOO to retire
  *
  * INSTR_TIME_ADD(x, y)				x += y
  *
@@ -81,6 +84,15 @@ typedef struct instr_time
 
 #ifndef WIN32
 
+/*
+ * Make sure this is a power-of-two, so that the compiler can turn the
+ * multiplications and divisions into shifts.
+ */
+#define TICKS_TO_NS_PRECISION (1<<14)
+
+extern int64 ticks_per_ns_scaled;
+extern int64 ticks_per_sec;
+extern int64 max_ticks_no_overflow;
 
 /* Use clock_gettime() */
 
@@ -106,9 +118,18 @@ typedef struct instr_time
 #define PG_INSTR_CLOCK	CLOCK_REALTIME
 #endif
 
-/* helper for INSTR_TIME_SET_CURRENT */
+#if defined(__x86_64__) && defined(__linux__)
+#include <x86intrin.h>
+#include <cpuid.h>
+
+extern bool has_rdtsc;
+extern bool has_rdtscp;
+
+extern void pg_initialize_rdtsc(void);
+#endif
+
 static inline instr_time
-pg_clock_gettime_ns(void)
+pg_clock_gettime(void)
 {
 	instr_time	now;
 	struct timespec tmp;
@@ -119,11 +140,94 @@ pg_clock_gettime_ns(void)
 	return now;
 }
 
+static inline instr_time
+pg_get_ticks_fast(void)
+{
+#if defined(__x86_64__) && defined(__linux__)
+	if (has_rdtsc)
+	{
+		instr_time	now;
+
+		now.ticks = __rdtsc();
+		return now;
+	}
+#endif
+
+	return pg_clock_gettime();
+}
+
+static inline instr_time
+pg_get_ticks(void)
+{
+#if defined(__x86_64__) && defined(__linux__)
+	if (has_rdtscp)
+	{
+		instr_time	now;
+		uint32		unused;
+
+		now.ticks = __rdtscp(&unused);
+		return now;
+	}
+#endif
+
+	return pg_clock_gettime();
+}
+
+static inline int64_t
+pg_ticks_to_ns(instr_time t)
+{
+	/*
+	 * Would multiplication overflow? If so perform computation in two parts.
+	 * Check overflow without actually overflowing via: a * b > max <=> a >
+	 * max / b
+	 */
+	int64		ns = 0;
+
+	if (unlikely(t.ticks > max_ticks_no_overflow))
+	{
+		/*
+		 * Compute how often the maximum number of ticks fits completely into
+		 * the number of elapsed ticks and convert that number into
+		 * nanoseconds. Then multiply by the count to arrive at the final
+		 * 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		max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION;
+
+		ns = max_ns * count;
+
+		/*
+		 * 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);
+	}
+
+	ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION;
+	return ns;
+}
+
+static inline void
+pg_initialize_get_ticks()
+{
+#if defined(__x86_64__) && defined(__linux__)
+	pg_initialize_rdtsc();
+#endif
+}
+
+#define INSTR_TIME_INITIALIZE() \
+	pg_initialize_get_ticks()
+
+#define INSTR_TIME_SET_CURRENT_FAST(t) \
+	((t) = pg_get_ticks_fast())
+
 #define INSTR_TIME_SET_CURRENT(t) \
-	((t) = pg_clock_gettime_ns())
+	((t) = pg_get_ticks())
 
 #define INSTR_TIME_GET_NANOSEC(t) \
-	((int64) (t).ticks)
+	pg_ticks_to_ns(t)
 
 
 #else							/* WIN32 */
@@ -131,7 +235,7 @@ pg_clock_gettime_ns(void)
 
 /* Use QueryPerformanceCounter() */
 
-/* helper for INSTR_TIME_SET_CURRENT */
+/* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */
 static inline instr_time
 pg_query_performance_counter(void)
 {
@@ -153,6 +257,11 @@ GetTimerFrequency(void)
 	return (double) f.QuadPart;
 }
 
+#define INSTR_TIME_INITIALIZE()
+
+#define INSTR_TIME_SET_CURRENT_FAST(t) \
+	((t) = pg_query_performance_counter())
+
 #define INSTR_TIME_SET_CURRENT(t) \
 	((t) = pg_query_performance_counter())
 
@@ -168,13 +277,8 @@ GetTimerFrequency(void)
 
 #define INSTR_TIME_IS_ZERO(t)	((t).ticks == 0)
 
-
 #define INSTR_TIME_SET_ZERO(t)	((t).ticks = 0)
 
-#define INSTR_TIME_SET_CURRENT_LAZY(t) \
-	(INSTR_TIME_IS_ZERO(t) ? INSTR_TIME_SET_CURRENT(t), true : false)
-
-
 #define INSTR_TIME_ADD(x,y) \
 	((x).ticks += (y).ticks)
 
-- 
2.47.3


--vtqqtrpooseurzip
Content-Type: text/x-diff; charset=utf-8
Content-Disposition: attachment;
	filename="v12-0003-pg_test_timing-Add-fast-flag-to-test-fast-timing.patch"



^ permalink  raw  reply  [nested|flat] 271+ messages in thread

* [PATCH v12 2/3] Use time stamp counter to measure time on Linux/x86
@ 2025-07-26 00:57 Lukas Fittl <[email protected]>
  0 siblings, 0 replies; 271+ messages in thread

From: Lukas Fittl @ 2025-07-26 00:57 UTC (permalink / raw)

We switch to using the time stamp counter (TSC) instead of clock_gettime()
to reduce overhead of EXPLAIN (ANALYZE, TIME ON). Tests showed that runtime
is reduced by around 10% for queries moving lots of rows through the plan.

For now this is only enabled on Linux/x86, in case the system clocksource is
reported as TSC. Relying on the Linux kernel simplifies the logic to detect
if the present TSC is usable (frequency invariant, synchronized between
sockets, etc.). In all other cases we fallback to clock_gettime().

Note, that we intentionally use RDTSC in the fast paths, rather than RDTSCP.
RDTSCP waits for outstanding instructions to retire on out-of-order CPUs.
This adds noticably for little benefit in the typical InstrStartNode() /
InstrStopNode() use case. The macro to be used in such cases is called
INSTR_TIME_SET_CURRENT_FAST(). The original macro INSTR_TIME_SET_CURRENT()
uses RDTSCP and is supposed to be used when precision is more important
than performance.

Author: David Geier <[email protected]>
Author: Andres Freund <[email protected]>
Author: Lukas Fittl <[email protected]>
Reviewed-by:
Discussion: https://www.postgresql.org/message-id/flat/20200612232810.f46nbqkdhbutzqdg%40alap3.anarazel.de
---
 src/backend/access/heap/vacuumlazy.c |   4 +-
 src/backend/executor/instrument.c    |  12 +-
 src/backend/utils/init/postinit.c    |   3 +
 src/bin/pgbench/pgbench.c            |   3 +
 src/bin/psql/startup.c               |   4 +
 src/common/Makefile                  |   1 +
 src/common/instr_time.c              | 206 +++++++++++++++++++++++++++
 src/common/meson.build               |   1 +
 src/include/portability/instr_time.h | 136 +++++++++++++++---
 9 files changed, 348 insertions(+), 22 deletions(-)
 create mode 100644 src/common/instr_time.c

diff --git a/src/backend/access/heap/vacuumlazy.c b/src/backend/access/heap/vacuumlazy.c
index d2b031fdd06..5027048cac4 100644
--- a/src/backend/access/heap/vacuumlazy.c
+++ b/src/backend/access/heap/vacuumlazy.c
@@ -3409,8 +3409,8 @@ count_nondeletable_pages(LVRelState *vacrel, bool *lock_waiter_detected)
 			INSTR_TIME_SET_CURRENT(currenttime);
 			elapsed = currenttime;
 			INSTR_TIME_SUBTRACT(elapsed, starttime);
-			if ((INSTR_TIME_GET_MICROSEC(elapsed) / 1000)
-				>= VACUUM_TRUNCATE_LOCK_CHECK_INTERVAL)
+			if (INSTR_TIME_GET_MILLISEC(elapsed) >=
+				VACUUM_TRUNCATE_LOCK_CHECK_INTERVAL)
 			{
 				if (LockHasWaitersRelation(vacrel->rel, AccessExclusiveLock))
 				{
diff --git a/src/backend/executor/instrument.c b/src/backend/executor/instrument.c
index 56e635f4700..01f67c5d972 100644
--- a/src/backend/executor/instrument.c
+++ b/src/backend/executor/instrument.c
@@ -67,9 +67,13 @@ InstrInit(Instrumentation *instr, int instrument_options)
 void
 InstrStartNode(Instrumentation *instr)
 {
-	if (instr->need_timer &&
-		!INSTR_TIME_SET_CURRENT_LAZY(instr->starttime))
-		elog(ERROR, "InstrStartNode called twice in a row");
+	if (instr->need_timer)
+	{
+		if (!INSTR_TIME_IS_ZERO(instr->starttime))
+			elog(ERROR, "InstrStartNode called twice in a row");
+		else
+			INSTR_TIME_SET_CURRENT_FAST(instr->starttime);
+	}
 
 	/* save buffer usage totals at node entry, if needed */
 	if (instr->need_bufusage)
@@ -95,7 +99,7 @@ InstrStopNode(Instrumentation *instr, double nTuples)
 		if (INSTR_TIME_IS_ZERO(instr->starttime))
 			elog(ERROR, "InstrStopNode called without start");
 
-		INSTR_TIME_SET_CURRENT(endtime);
+		INSTR_TIME_SET_CURRENT_FAST(endtime);
 		INSTR_TIME_ACCUM_DIFF(instr->counter, endtime, instr->starttime);
 
 		INSTR_TIME_SET_ZERO(instr->starttime);
diff --git a/src/backend/utils/init/postinit.c b/src/backend/utils/init/postinit.c
index 641e535a73c..d573409903b 100644
--- a/src/backend/utils/init/postinit.c
+++ b/src/backend/utils/init/postinit.c
@@ -810,6 +810,9 @@ InitPostgres(const char *in_dbname, Oid dboid,
 	/* Initialize portal manager */
 	EnablePortalManager();
 
+	/* initialize high-precision interval timing */
+	INSTR_TIME_INITIALIZE();
+
 	/*
 	 * Load relcache entries for the shared system catalogs.  This must create
 	 * at least entries for pg_database and catalogs used for authentication.
diff --git a/src/bin/pgbench/pgbench.c b/src/bin/pgbench/pgbench.c
index 1515ed405ba..79bef2d2aec 100644
--- a/src/bin/pgbench/pgbench.c
+++ b/src/bin/pgbench/pgbench.c
@@ -7290,6 +7290,9 @@ main(int argc, char **argv)
 		initRandomState(&state[i].cs_func_rs);
 	}
 
+	/* initialize high-precision interval timing */
+	INSTR_TIME_INITIALIZE();
+
 	/* opening connection... */
 	con = doConnect();
 	if (con == NULL)
diff --git a/src/bin/psql/startup.c b/src/bin/psql/startup.c
index 249b6aa5169..d615df593c7 100644
--- a/src/bin/psql/startup.c
+++ b/src/bin/psql/startup.c
@@ -24,6 +24,7 @@
 #include "help.h"
 #include "input.h"
 #include "mainloop.h"
+#include "portability/instr_time.h"
 #include "settings.h"
 
 /*
@@ -327,6 +328,9 @@ main(int argc, char *argv[])
 
 	PQsetNoticeProcessor(pset.db, NoticeProcessor, NULL);
 
+	/* initialize high-precision interval timing */
+	INSTR_TIME_INITIALIZE();
+
 	SyncVariables();
 
 	if (options.list_dbs)
diff --git a/src/common/Makefile b/src/common/Makefile
index 2c720caa509..1a2fbbe887f 100644
--- a/src/common/Makefile
+++ b/src/common/Makefile
@@ -59,6 +59,7 @@ OBJS_COMMON = \
 	file_perm.o \
 	file_utils.o \
 	hashfn.o \
+	instr_time.o \
 	ip.o \
 	jsonapi.o \
 	keywords.o \
diff --git a/src/common/instr_time.c b/src/common/instr_time.c
new file mode 100644
index 00000000000..fdf47699f20
--- /dev/null
+++ b/src/common/instr_time.c
@@ -0,0 +1,206 @@
+/*-------------------------------------------------------------------------
+ *
+ * instr_time.c
+ *	   Non-inline parts of the portable high-precision interval timing
+ *	 implementation
+ *
+ * Portions Copyright (c) 2025, PostgreSQL Global Development Group
+ *
+ *
+ * IDENTIFICATION
+ *	  src/backend/port/instr_time.c
+ *
+ *-------------------------------------------------------------------------
+ */
+#include "postgres.h"
+
+#if defined(HAVE__GET_CPUID) || (defined(HAVE__CPUIDEX) && !defined(_MSC_VER))
+#include <cpuid.h>
+#endif
+
+#if defined(HAVE__CPUID) || (defined(HAVE__CPUIDEX) && defined(_MSC_VER))
+#include <intrin.h>
+#endif
+
+#include "portability/instr_time.h"
+
+#ifndef WIN32
+/*
+ * Stores what the number of cycles needs to be multiplied with to end up
+ * with nanoseconds using integer math. See comment in pg_initialize_rdtsc()
+ * for more details.
+ *
+ * By default assume we are using clock_gettime() as a fallback which uses
+ * nanoseconds as ticks. Hence, we set the multiplier to the precision scalar
+ * so that the division in INSTR_TIME_GET_NANOSEC() won't change the nanoseconds.
+ *
+ * When using the RDTSC instruction directly this is filled in during initialization
+ * based on the relevant CPUID fields.
+ */
+int64		ticks_per_ns_scaled = TICKS_TO_NS_PRECISION;
+int64		ticks_per_sec = NS_PER_S;
+int64		max_ticks_no_overflow = PG_INT64_MAX / TICKS_TO_NS_PRECISION;
+
+#if defined(__x86_64__) && defined(__linux__)
+/*
+ * Indicates if RDTSC can be used (Linux/x86 only, when OS uses TSC clocksource)
+ */
+bool		has_rdtsc = false;
+
+/*
+ * Indicates if RDTSCP can be used. True if RDTSC can be used and RDTSCP is available.
+ */
+bool		has_rdtscp = false;
+
+#define CPUID_HYPERVISOR_VMWARE(words) (words[1] == 0x61774d56 && words[2] == 0x4d566572 && words[3] == 0x65726177) /* VMwareVMware */
+#define CPUID_HYPERVISOR_KVM(words) (words[1] == 0x4b4d564b && words[2] == 0x564b4d56 && words[3] == 0x0000004d)	/* KVMKVMKVM */
+
+static bool
+get_tsc_frequency_khz(uint32 *tsc_freq)
+{
+	uint32		r[4] = {0, 0, 0, 0};
+
+#if defined(HAVE__GET_CPUID)
+	__get_cpuid(0x15, &r[0] /* denominator */ , &r[1] /* numerator */ , &r[2] /* hz */ , &r[3]);
+#elif defined(HAVE__CPUID)
+	__cpuid(r, 0x15);
+#else
+#error cpuid instruction not available
+#endif
+
+	if (r[2] > 0)
+	{
+		if (r[0] == 0 || r[1] == 0)
+			return false;
+
+		*tsc_freq = r[2] / 1000 * r[1] / r[0];
+		return true;
+	}
+
+	/* Some CPUs only report frequency in 16H */
+
+#if defined(HAVE__GET_CPUID)
+	__get_cpuid(0x16, &r[0] /* base_mhz */ , &r[1], &r[2], &r[3]);
+#elif defined(HAVE__CPUID)
+	__cpuid(r, 0x16);
+#else
+#error cpuid instruction not available
+#endif
+
+	if (r[0] > 0)
+	{
+		*tsc_freq = r[0] * 1000;
+		return true;
+	}
+
+	/*
+	 * Check if we have a KVM or VMware Hypervisor passing down TSC frequency
+	 * to us in a guest VM
+	 *
+	 * Note that accessing the 0x40000000 leaf for Hypervisor info requires
+	 * use of __cpuidex to set ECX to 0. The similar __get_cpuid_count
+	 * function does not work as expected since it contains a check for
+	 * __get_cpuid_max, which has been observed to be lower than the special
+	 * Hypervisor leaf.
+	 */
+#if defined(HAVE__CPUIDEX)
+	__cpuidex((int32 *) r, 0x40000000, 0);
+	if (r[0] >= 0x40000010 && (CPUID_HYPERVISOR_VMWARE(r) || CPUID_HYPERVISOR_KVM(r)))
+	{
+		__cpuidex((int32 *) r, 0x40000010, 0);
+		if (r[0] > 0)
+		{
+			*tsc_freq = r[0];
+			return true;
+		}
+	}
+#endif
+
+	return false;
+}
+
+static bool
+is_rdtscp_available()
+{
+	uint32		r[4] = {0, 0, 0, 0};
+
+#if defined(HAVE__GET_CPUID)
+	if (!__get_cpuid(0x80000001, &r[0], &r[1], &r[2], &r[3]))
+		return false;
+#elif defined(HAVE__CPUID)
+	__cpuid(r, 0x80000001);
+#else
+#error cpuid instruction not available
+#endif
+
+	return (r[3] & (1 << 27)) != 0;
+}
+
+/*
+ * Decide whether we use the RDTSC instruction at runtime, for Linux/x86,
+ * instead of incurring the overhead of a full clock_gettime() call.
+ *
+ * This can't be reliably determined at compile time, since the
+ * availability of an "invariant" TSC (that is not affected by CPU
+ * frequency changes) is dependent on the CPU architecture. Additionally,
+ * there are cases where TSC availability is impacted by virtualization,
+ * where a simple cpuid feature check would not be enough.
+ *
+ * Since Linux already does a significant amount of work to determine
+ * whether TSC is a viable clock source, decide based on that.
+ */
+void
+pg_initialize_rdtsc(void)
+{
+	FILE	   *fp = fopen("/sys/devices/system/clocksource/clocksource0/current_clocksource", "r");
+
+	if (fp)
+	{
+		char		buf[128];
+
+		if (fgets(buf, sizeof(buf), fp) != NULL && strcmp(buf, "tsc\n") == 0)
+		{
+			/*
+			 * Compute baseline CPU peformance, determines speed at which
+			 * RDTSC advances.
+			 */
+			uint32		tsc_freq;
+
+			if (get_tsc_frequency_khz(&tsc_freq))
+			{
+				/*
+				 * Ticks to nanoseconds conversion requires floating point
+				 * math because because:
+				 *
+				 * sec = ticks / frequency_hz ns  = ticks / frequency_hz *
+				 * 1,000,000,000 ns  = ticks * (1,000,000,000 / frequency_hz)
+				 * ns  = ticks * (1,000,000 / frequency_khz) <-- now in
+				 * kilohertz
+				 *
+				 * Here, 'ns' is usually a floating number. For example for a
+				 * 2.5 GHz CPU the scaling factor becomes 1,000,000 /
+				 * 2,500,000 = 1.2.
+				 *
+				 * To be able to use integer math we work around the lack of
+				 * precision. We first scale the integer up and after the
+				 * multiplication by the number of ticks in
+				 * INSTR_TIME_GET_NANOSEC() we divide again by the same value.
+				 * We picked the scaler such that it provides enough precision
+				 * and is a power-of-two which allows for shifting instead of
+				 * doing an integer division.
+				 */
+				ticks_per_ns_scaled = INT64CONST(1000000) * TICKS_TO_NS_PRECISION / tsc_freq;
+				ticks_per_sec = tsc_freq * 1000;	/* KHz->Hz */
+				max_ticks_no_overflow = PG_INT64_MAX / ticks_per_ns_scaled;
+
+				has_rdtsc = true;
+				has_rdtscp = is_rdtscp_available();
+			}
+		}
+
+		fclose(fp);
+	}
+}
+#endif							/* defined(__x86_64__) && defined(__linux__) */
+
+#endif							/* WIN32 */
diff --git a/src/common/meson.build b/src/common/meson.build
index 1540ba67cca..62b90b3e609 100644
--- a/src/common/meson.build
+++ b/src/common/meson.build
@@ -13,6 +13,7 @@ common_sources = files(
   'file_perm.c',
   'file_utils.c',
   'hashfn.c',
+  'instr_time.c',
   'ip.c',
   'jsonapi.c',
   'keywords.c',
diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h
index f71a851b18d..e2e339a0c4f 100644
--- a/src/include/portability/instr_time.h
+++ b/src/include/portability/instr_time.h
@@ -4,9 +4,11 @@
  *	  portable high-precision interval timing
  *
  * This file provides an abstraction layer to hide portability issues in
- * interval timing.  On Unix we use clock_gettime(), and on Windows we use
- * QueryPerformanceCounter().  These macros also give some breathing room to
- * use other high-precision-timing APIs.
+ * interval timing. On Linux/x86 we use the rdtsc instruction when a TSC
+ * clocksource is also used on the host OS.  Otherwise, and on other
+ * Unix-like systems we use clock_gettime() and on Windows we use
+ * QueryPerformanceCounter(). These macros also give some breathing
+ * room to use other high-precision-timing APIs.
  *
  * The basic data type is instr_time, which all callers should treat as an
  * opaque typedef.  instr_time can store either an absolute time (of
@@ -17,10 +19,11 @@
  *
  * INSTR_TIME_SET_ZERO(t)			set t to zero (memset is acceptable too)
  *
- * INSTR_TIME_SET_CURRENT(t)		set t to current time
+ * INSTR_TIME_SET_CURRENT_FAST(t)	set t to current time without waiting
+ * 									for instructions in out-of-order window
  *
- * INSTR_TIME_SET_CURRENT_LAZY(t)	set t to current time if t is zero,
- *									evaluates to whether t changed
+ * INSTR_TIME_SET_CURRENT(t)		set t to current time while waiting for
+ * 									instructions in OOO to retire
  *
  * INSTR_TIME_ADD(x, y)				x += y
  *
@@ -81,6 +84,15 @@ typedef struct instr_time
 
 #ifndef WIN32
 
+/*
+ * Make sure this is a power-of-two, so that the compiler can turn the
+ * multiplications and divisions into shifts.
+ */
+#define TICKS_TO_NS_PRECISION (1<<14)
+
+extern int64 ticks_per_ns_scaled;
+extern int64 ticks_per_sec;
+extern int64 max_ticks_no_overflow;
 
 /* Use clock_gettime() */
 
@@ -106,9 +118,18 @@ typedef struct instr_time
 #define PG_INSTR_CLOCK	CLOCK_REALTIME
 #endif
 
-/* helper for INSTR_TIME_SET_CURRENT */
+#if defined(__x86_64__) && defined(__linux__)
+#include <x86intrin.h>
+#include <cpuid.h>
+
+extern bool has_rdtsc;
+extern bool has_rdtscp;
+
+extern void pg_initialize_rdtsc(void);
+#endif
+
 static inline instr_time
-pg_clock_gettime_ns(void)
+pg_clock_gettime(void)
 {
 	instr_time	now;
 	struct timespec tmp;
@@ -119,11 +140,94 @@ pg_clock_gettime_ns(void)
 	return now;
 }
 
+static inline instr_time
+pg_get_ticks_fast(void)
+{
+#if defined(__x86_64__) && defined(__linux__)
+	if (has_rdtsc)
+	{
+		instr_time	now;
+
+		now.ticks = __rdtsc();
+		return now;
+	}
+#endif
+
+	return pg_clock_gettime();
+}
+
+static inline instr_time
+pg_get_ticks(void)
+{
+#if defined(__x86_64__) && defined(__linux__)
+	if (has_rdtscp)
+	{
+		instr_time	now;
+		uint32		unused;
+
+		now.ticks = __rdtscp(&unused);
+		return now;
+	}
+#endif
+
+	return pg_clock_gettime();
+}
+
+static inline int64_t
+pg_ticks_to_ns(instr_time t)
+{
+	/*
+	 * Would multiplication overflow? If so perform computation in two parts.
+	 * Check overflow without actually overflowing via: a * b > max <=> a >
+	 * max / b
+	 */
+	int64		ns = 0;
+
+	if (unlikely(t.ticks > max_ticks_no_overflow))
+	{
+		/*
+		 * Compute how often the maximum number of ticks fits completely into
+		 * the number of elapsed ticks and convert that number into
+		 * nanoseconds. Then multiply by the count to arrive at the final
+		 * 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		max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION;
+
+		ns = max_ns * count;
+
+		/*
+		 * 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);
+	}
+
+	ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION;
+	return ns;
+}
+
+static inline void
+pg_initialize_get_ticks()
+{
+#if defined(__x86_64__) && defined(__linux__)
+	pg_initialize_rdtsc();
+#endif
+}
+
+#define INSTR_TIME_INITIALIZE() \
+	pg_initialize_get_ticks()
+
+#define INSTR_TIME_SET_CURRENT_FAST(t) \
+	((t) = pg_get_ticks_fast())
+
 #define INSTR_TIME_SET_CURRENT(t) \
-	((t) = pg_clock_gettime_ns())
+	((t) = pg_get_ticks())
 
 #define INSTR_TIME_GET_NANOSEC(t) \
-	((int64) (t).ticks)
+	pg_ticks_to_ns(t)
 
 
 #else							/* WIN32 */
@@ -131,7 +235,7 @@ pg_clock_gettime_ns(void)
 
 /* Use QueryPerformanceCounter() */
 
-/* helper for INSTR_TIME_SET_CURRENT */
+/* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */
 static inline instr_time
 pg_query_performance_counter(void)
 {
@@ -153,6 +257,11 @@ GetTimerFrequency(void)
 	return (double) f.QuadPart;
 }
 
+#define INSTR_TIME_INITIALIZE()
+
+#define INSTR_TIME_SET_CURRENT_FAST(t) \
+	((t) = pg_query_performance_counter())
+
 #define INSTR_TIME_SET_CURRENT(t) \
 	((t) = pg_query_performance_counter())
 
@@ -168,13 +277,8 @@ GetTimerFrequency(void)
 
 #define INSTR_TIME_IS_ZERO(t)	((t).ticks == 0)
 
-
 #define INSTR_TIME_SET_ZERO(t)	((t).ticks = 0)
 
-#define INSTR_TIME_SET_CURRENT_LAZY(t) \
-	(INSTR_TIME_IS_ZERO(t) ? INSTR_TIME_SET_CURRENT(t), true : false)
-
-
 #define INSTR_TIME_ADD(x,y) \
 	((x).ticks += (y).ticks)
 
-- 
2.47.3


--vtqqtrpooseurzip
Content-Type: text/x-diff; charset=utf-8
Content-Disposition: attachment;
	filename="v12-0003-pg_test_timing-Add-fast-flag-to-test-fast-timing.patch"



^ permalink  raw  reply  [nested|flat] 271+ messages in thread

* [PATCH v12 2/3] Use time stamp counter to measure time on Linux/x86
@ 2025-07-26 00:57 Lukas Fittl <[email protected]>
  0 siblings, 0 replies; 271+ messages in thread

From: Lukas Fittl @ 2025-07-26 00:57 UTC (permalink / raw)

We switch to using the time stamp counter (TSC) instead of clock_gettime()
to reduce overhead of EXPLAIN (ANALYZE, TIME ON). Tests showed that runtime
is reduced by around 10% for queries moving lots of rows through the plan.

For now this is only enabled on Linux/x86, in case the system clocksource is
reported as TSC. Relying on the Linux kernel simplifies the logic to detect
if the present TSC is usable (frequency invariant, synchronized between
sockets, etc.). In all other cases we fallback to clock_gettime().

Note, that we intentionally use RDTSC in the fast paths, rather than RDTSCP.
RDTSCP waits for outstanding instructions to retire on out-of-order CPUs.
This adds noticably for little benefit in the typical InstrStartNode() /
InstrStopNode() use case. The macro to be used in such cases is called
INSTR_TIME_SET_CURRENT_FAST(). The original macro INSTR_TIME_SET_CURRENT()
uses RDTSCP and is supposed to be used when precision is more important
than performance.

Author: David Geier <[email protected]>
Author: Andres Freund <[email protected]>
Author: Lukas Fittl <[email protected]>
Reviewed-by:
Discussion: https://www.postgresql.org/message-id/flat/20200612232810.f46nbqkdhbutzqdg%40alap3.anarazel.de
---
 src/backend/access/heap/vacuumlazy.c |   4 +-
 src/backend/executor/instrument.c    |  12 +-
 src/backend/utils/init/postinit.c    |   3 +
 src/bin/pgbench/pgbench.c            |   3 +
 src/bin/psql/startup.c               |   4 +
 src/common/Makefile                  |   1 +
 src/common/instr_time.c              | 206 +++++++++++++++++++++++++++
 src/common/meson.build               |   1 +
 src/include/portability/instr_time.h | 136 +++++++++++++++---
 9 files changed, 348 insertions(+), 22 deletions(-)
 create mode 100644 src/common/instr_time.c

diff --git a/src/backend/access/heap/vacuumlazy.c b/src/backend/access/heap/vacuumlazy.c
index d2b031fdd06..5027048cac4 100644
--- a/src/backend/access/heap/vacuumlazy.c
+++ b/src/backend/access/heap/vacuumlazy.c
@@ -3409,8 +3409,8 @@ count_nondeletable_pages(LVRelState *vacrel, bool *lock_waiter_detected)
 			INSTR_TIME_SET_CURRENT(currenttime);
 			elapsed = currenttime;
 			INSTR_TIME_SUBTRACT(elapsed, starttime);
-			if ((INSTR_TIME_GET_MICROSEC(elapsed) / 1000)
-				>= VACUUM_TRUNCATE_LOCK_CHECK_INTERVAL)
+			if (INSTR_TIME_GET_MILLISEC(elapsed) >=
+				VACUUM_TRUNCATE_LOCK_CHECK_INTERVAL)
 			{
 				if (LockHasWaitersRelation(vacrel->rel, AccessExclusiveLock))
 				{
diff --git a/src/backend/executor/instrument.c b/src/backend/executor/instrument.c
index 56e635f4700..01f67c5d972 100644
--- a/src/backend/executor/instrument.c
+++ b/src/backend/executor/instrument.c
@@ -67,9 +67,13 @@ InstrInit(Instrumentation *instr, int instrument_options)
 void
 InstrStartNode(Instrumentation *instr)
 {
-	if (instr->need_timer &&
-		!INSTR_TIME_SET_CURRENT_LAZY(instr->starttime))
-		elog(ERROR, "InstrStartNode called twice in a row");
+	if (instr->need_timer)
+	{
+		if (!INSTR_TIME_IS_ZERO(instr->starttime))
+			elog(ERROR, "InstrStartNode called twice in a row");
+		else
+			INSTR_TIME_SET_CURRENT_FAST(instr->starttime);
+	}
 
 	/* save buffer usage totals at node entry, if needed */
 	if (instr->need_bufusage)
@@ -95,7 +99,7 @@ InstrStopNode(Instrumentation *instr, double nTuples)
 		if (INSTR_TIME_IS_ZERO(instr->starttime))
 			elog(ERROR, "InstrStopNode called without start");
 
-		INSTR_TIME_SET_CURRENT(endtime);
+		INSTR_TIME_SET_CURRENT_FAST(endtime);
 		INSTR_TIME_ACCUM_DIFF(instr->counter, endtime, instr->starttime);
 
 		INSTR_TIME_SET_ZERO(instr->starttime);
diff --git a/src/backend/utils/init/postinit.c b/src/backend/utils/init/postinit.c
index 641e535a73c..d573409903b 100644
--- a/src/backend/utils/init/postinit.c
+++ b/src/backend/utils/init/postinit.c
@@ -810,6 +810,9 @@ InitPostgres(const char *in_dbname, Oid dboid,
 	/* Initialize portal manager */
 	EnablePortalManager();
 
+	/* initialize high-precision interval timing */
+	INSTR_TIME_INITIALIZE();
+
 	/*
 	 * Load relcache entries for the shared system catalogs.  This must create
 	 * at least entries for pg_database and catalogs used for authentication.
diff --git a/src/bin/pgbench/pgbench.c b/src/bin/pgbench/pgbench.c
index 1515ed405ba..79bef2d2aec 100644
--- a/src/bin/pgbench/pgbench.c
+++ b/src/bin/pgbench/pgbench.c
@@ -7290,6 +7290,9 @@ main(int argc, char **argv)
 		initRandomState(&state[i].cs_func_rs);
 	}
 
+	/* initialize high-precision interval timing */
+	INSTR_TIME_INITIALIZE();
+
 	/* opening connection... */
 	con = doConnect();
 	if (con == NULL)
diff --git a/src/bin/psql/startup.c b/src/bin/psql/startup.c
index 249b6aa5169..d615df593c7 100644
--- a/src/bin/psql/startup.c
+++ b/src/bin/psql/startup.c
@@ -24,6 +24,7 @@
 #include "help.h"
 #include "input.h"
 #include "mainloop.h"
+#include "portability/instr_time.h"
 #include "settings.h"
 
 /*
@@ -327,6 +328,9 @@ main(int argc, char *argv[])
 
 	PQsetNoticeProcessor(pset.db, NoticeProcessor, NULL);
 
+	/* initialize high-precision interval timing */
+	INSTR_TIME_INITIALIZE();
+
 	SyncVariables();
 
 	if (options.list_dbs)
diff --git a/src/common/Makefile b/src/common/Makefile
index 2c720caa509..1a2fbbe887f 100644
--- a/src/common/Makefile
+++ b/src/common/Makefile
@@ -59,6 +59,7 @@ OBJS_COMMON = \
 	file_perm.o \
 	file_utils.o \
 	hashfn.o \
+	instr_time.o \
 	ip.o \
 	jsonapi.o \
 	keywords.o \
diff --git a/src/common/instr_time.c b/src/common/instr_time.c
new file mode 100644
index 00000000000..fdf47699f20
--- /dev/null
+++ b/src/common/instr_time.c
@@ -0,0 +1,206 @@
+/*-------------------------------------------------------------------------
+ *
+ * instr_time.c
+ *	   Non-inline parts of the portable high-precision interval timing
+ *	 implementation
+ *
+ * Portions Copyright (c) 2025, PostgreSQL Global Development Group
+ *
+ *
+ * IDENTIFICATION
+ *	  src/backend/port/instr_time.c
+ *
+ *-------------------------------------------------------------------------
+ */
+#include "postgres.h"
+
+#if defined(HAVE__GET_CPUID) || (defined(HAVE__CPUIDEX) && !defined(_MSC_VER))
+#include <cpuid.h>
+#endif
+
+#if defined(HAVE__CPUID) || (defined(HAVE__CPUIDEX) && defined(_MSC_VER))
+#include <intrin.h>
+#endif
+
+#include "portability/instr_time.h"
+
+#ifndef WIN32
+/*
+ * Stores what the number of cycles needs to be multiplied with to end up
+ * with nanoseconds using integer math. See comment in pg_initialize_rdtsc()
+ * for more details.
+ *
+ * By default assume we are using clock_gettime() as a fallback which uses
+ * nanoseconds as ticks. Hence, we set the multiplier to the precision scalar
+ * so that the division in INSTR_TIME_GET_NANOSEC() won't change the nanoseconds.
+ *
+ * When using the RDTSC instruction directly this is filled in during initialization
+ * based on the relevant CPUID fields.
+ */
+int64		ticks_per_ns_scaled = TICKS_TO_NS_PRECISION;
+int64		ticks_per_sec = NS_PER_S;
+int64		max_ticks_no_overflow = PG_INT64_MAX / TICKS_TO_NS_PRECISION;
+
+#if defined(__x86_64__) && defined(__linux__)
+/*
+ * Indicates if RDTSC can be used (Linux/x86 only, when OS uses TSC clocksource)
+ */
+bool		has_rdtsc = false;
+
+/*
+ * Indicates if RDTSCP can be used. True if RDTSC can be used and RDTSCP is available.
+ */
+bool		has_rdtscp = false;
+
+#define CPUID_HYPERVISOR_VMWARE(words) (words[1] == 0x61774d56 && words[2] == 0x4d566572 && words[3] == 0x65726177) /* VMwareVMware */
+#define CPUID_HYPERVISOR_KVM(words) (words[1] == 0x4b4d564b && words[2] == 0x564b4d56 && words[3] == 0x0000004d)	/* KVMKVMKVM */
+
+static bool
+get_tsc_frequency_khz(uint32 *tsc_freq)
+{
+	uint32		r[4] = {0, 0, 0, 0};
+
+#if defined(HAVE__GET_CPUID)
+	__get_cpuid(0x15, &r[0] /* denominator */ , &r[1] /* numerator */ , &r[2] /* hz */ , &r[3]);
+#elif defined(HAVE__CPUID)
+	__cpuid(r, 0x15);
+#else
+#error cpuid instruction not available
+#endif
+
+	if (r[2] > 0)
+	{
+		if (r[0] == 0 || r[1] == 0)
+			return false;
+
+		*tsc_freq = r[2] / 1000 * r[1] / r[0];
+		return true;
+	}
+
+	/* Some CPUs only report frequency in 16H */
+
+#if defined(HAVE__GET_CPUID)
+	__get_cpuid(0x16, &r[0] /* base_mhz */ , &r[1], &r[2], &r[3]);
+#elif defined(HAVE__CPUID)
+	__cpuid(r, 0x16);
+#else
+#error cpuid instruction not available
+#endif
+
+	if (r[0] > 0)
+	{
+		*tsc_freq = r[0] * 1000;
+		return true;
+	}
+
+	/*
+	 * Check if we have a KVM or VMware Hypervisor passing down TSC frequency
+	 * to us in a guest VM
+	 *
+	 * Note that accessing the 0x40000000 leaf for Hypervisor info requires
+	 * use of __cpuidex to set ECX to 0. The similar __get_cpuid_count
+	 * function does not work as expected since it contains a check for
+	 * __get_cpuid_max, which has been observed to be lower than the special
+	 * Hypervisor leaf.
+	 */
+#if defined(HAVE__CPUIDEX)
+	__cpuidex((int32 *) r, 0x40000000, 0);
+	if (r[0] >= 0x40000010 && (CPUID_HYPERVISOR_VMWARE(r) || CPUID_HYPERVISOR_KVM(r)))
+	{
+		__cpuidex((int32 *) r, 0x40000010, 0);
+		if (r[0] > 0)
+		{
+			*tsc_freq = r[0];
+			return true;
+		}
+	}
+#endif
+
+	return false;
+}
+
+static bool
+is_rdtscp_available()
+{
+	uint32		r[4] = {0, 0, 0, 0};
+
+#if defined(HAVE__GET_CPUID)
+	if (!__get_cpuid(0x80000001, &r[0], &r[1], &r[2], &r[3]))
+		return false;
+#elif defined(HAVE__CPUID)
+	__cpuid(r, 0x80000001);
+#else
+#error cpuid instruction not available
+#endif
+
+	return (r[3] & (1 << 27)) != 0;
+}
+
+/*
+ * Decide whether we use the RDTSC instruction at runtime, for Linux/x86,
+ * instead of incurring the overhead of a full clock_gettime() call.
+ *
+ * This can't be reliably determined at compile time, since the
+ * availability of an "invariant" TSC (that is not affected by CPU
+ * frequency changes) is dependent on the CPU architecture. Additionally,
+ * there are cases where TSC availability is impacted by virtualization,
+ * where a simple cpuid feature check would not be enough.
+ *
+ * Since Linux already does a significant amount of work to determine
+ * whether TSC is a viable clock source, decide based on that.
+ */
+void
+pg_initialize_rdtsc(void)
+{
+	FILE	   *fp = fopen("/sys/devices/system/clocksource/clocksource0/current_clocksource", "r");
+
+	if (fp)
+	{
+		char		buf[128];
+
+		if (fgets(buf, sizeof(buf), fp) != NULL && strcmp(buf, "tsc\n") == 0)
+		{
+			/*
+			 * Compute baseline CPU peformance, determines speed at which
+			 * RDTSC advances.
+			 */
+			uint32		tsc_freq;
+
+			if (get_tsc_frequency_khz(&tsc_freq))
+			{
+				/*
+				 * Ticks to nanoseconds conversion requires floating point
+				 * math because because:
+				 *
+				 * sec = ticks / frequency_hz ns  = ticks / frequency_hz *
+				 * 1,000,000,000 ns  = ticks * (1,000,000,000 / frequency_hz)
+				 * ns  = ticks * (1,000,000 / frequency_khz) <-- now in
+				 * kilohertz
+				 *
+				 * Here, 'ns' is usually a floating number. For example for a
+				 * 2.5 GHz CPU the scaling factor becomes 1,000,000 /
+				 * 2,500,000 = 1.2.
+				 *
+				 * To be able to use integer math we work around the lack of
+				 * precision. We first scale the integer up and after the
+				 * multiplication by the number of ticks in
+				 * INSTR_TIME_GET_NANOSEC() we divide again by the same value.
+				 * We picked the scaler such that it provides enough precision
+				 * and is a power-of-two which allows for shifting instead of
+				 * doing an integer division.
+				 */
+				ticks_per_ns_scaled = INT64CONST(1000000) * TICKS_TO_NS_PRECISION / tsc_freq;
+				ticks_per_sec = tsc_freq * 1000;	/* KHz->Hz */
+				max_ticks_no_overflow = PG_INT64_MAX / ticks_per_ns_scaled;
+
+				has_rdtsc = true;
+				has_rdtscp = is_rdtscp_available();
+			}
+		}
+
+		fclose(fp);
+	}
+}
+#endif							/* defined(__x86_64__) && defined(__linux__) */
+
+#endif							/* WIN32 */
diff --git a/src/common/meson.build b/src/common/meson.build
index 1540ba67cca..62b90b3e609 100644
--- a/src/common/meson.build
+++ b/src/common/meson.build
@@ -13,6 +13,7 @@ common_sources = files(
   'file_perm.c',
   'file_utils.c',
   'hashfn.c',
+  'instr_time.c',
   'ip.c',
   'jsonapi.c',
   'keywords.c',
diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h
index f71a851b18d..e2e339a0c4f 100644
--- a/src/include/portability/instr_time.h
+++ b/src/include/portability/instr_time.h
@@ -4,9 +4,11 @@
  *	  portable high-precision interval timing
  *
  * This file provides an abstraction layer to hide portability issues in
- * interval timing.  On Unix we use clock_gettime(), and on Windows we use
- * QueryPerformanceCounter().  These macros also give some breathing room to
- * use other high-precision-timing APIs.
+ * interval timing. On Linux/x86 we use the rdtsc instruction when a TSC
+ * clocksource is also used on the host OS.  Otherwise, and on other
+ * Unix-like systems we use clock_gettime() and on Windows we use
+ * QueryPerformanceCounter(). These macros also give some breathing
+ * room to use other high-precision-timing APIs.
  *
  * The basic data type is instr_time, which all callers should treat as an
  * opaque typedef.  instr_time can store either an absolute time (of
@@ -17,10 +19,11 @@
  *
  * INSTR_TIME_SET_ZERO(t)			set t to zero (memset is acceptable too)
  *
- * INSTR_TIME_SET_CURRENT(t)		set t to current time
+ * INSTR_TIME_SET_CURRENT_FAST(t)	set t to current time without waiting
+ * 									for instructions in out-of-order window
  *
- * INSTR_TIME_SET_CURRENT_LAZY(t)	set t to current time if t is zero,
- *									evaluates to whether t changed
+ * INSTR_TIME_SET_CURRENT(t)		set t to current time while waiting for
+ * 									instructions in OOO to retire
  *
  * INSTR_TIME_ADD(x, y)				x += y
  *
@@ -81,6 +84,15 @@ typedef struct instr_time
 
 #ifndef WIN32
 
+/*
+ * Make sure this is a power-of-two, so that the compiler can turn the
+ * multiplications and divisions into shifts.
+ */
+#define TICKS_TO_NS_PRECISION (1<<14)
+
+extern int64 ticks_per_ns_scaled;
+extern int64 ticks_per_sec;
+extern int64 max_ticks_no_overflow;
 
 /* Use clock_gettime() */
 
@@ -106,9 +118,18 @@ typedef struct instr_time
 #define PG_INSTR_CLOCK	CLOCK_REALTIME
 #endif
 
-/* helper for INSTR_TIME_SET_CURRENT */
+#if defined(__x86_64__) && defined(__linux__)
+#include <x86intrin.h>
+#include <cpuid.h>
+
+extern bool has_rdtsc;
+extern bool has_rdtscp;
+
+extern void pg_initialize_rdtsc(void);
+#endif
+
 static inline instr_time
-pg_clock_gettime_ns(void)
+pg_clock_gettime(void)
 {
 	instr_time	now;
 	struct timespec tmp;
@@ -119,11 +140,94 @@ pg_clock_gettime_ns(void)
 	return now;
 }
 
+static inline instr_time
+pg_get_ticks_fast(void)
+{
+#if defined(__x86_64__) && defined(__linux__)
+	if (has_rdtsc)
+	{
+		instr_time	now;
+
+		now.ticks = __rdtsc();
+		return now;
+	}
+#endif
+
+	return pg_clock_gettime();
+}
+
+static inline instr_time
+pg_get_ticks(void)
+{
+#if defined(__x86_64__) && defined(__linux__)
+	if (has_rdtscp)
+	{
+		instr_time	now;
+		uint32		unused;
+
+		now.ticks = __rdtscp(&unused);
+		return now;
+	}
+#endif
+
+	return pg_clock_gettime();
+}
+
+static inline int64_t
+pg_ticks_to_ns(instr_time t)
+{
+	/*
+	 * Would multiplication overflow? If so perform computation in two parts.
+	 * Check overflow without actually overflowing via: a * b > max <=> a >
+	 * max / b
+	 */
+	int64		ns = 0;
+
+	if (unlikely(t.ticks > max_ticks_no_overflow))
+	{
+		/*
+		 * Compute how often the maximum number of ticks fits completely into
+		 * the number of elapsed ticks and convert that number into
+		 * nanoseconds. Then multiply by the count to arrive at the final
+		 * 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		max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION;
+
+		ns = max_ns * count;
+
+		/*
+		 * 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);
+	}
+
+	ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION;
+	return ns;
+}
+
+static inline void
+pg_initialize_get_ticks()
+{
+#if defined(__x86_64__) && defined(__linux__)
+	pg_initialize_rdtsc();
+#endif
+}
+
+#define INSTR_TIME_INITIALIZE() \
+	pg_initialize_get_ticks()
+
+#define INSTR_TIME_SET_CURRENT_FAST(t) \
+	((t) = pg_get_ticks_fast())
+
 #define INSTR_TIME_SET_CURRENT(t) \
-	((t) = pg_clock_gettime_ns())
+	((t) = pg_get_ticks())
 
 #define INSTR_TIME_GET_NANOSEC(t) \
-	((int64) (t).ticks)
+	pg_ticks_to_ns(t)
 
 
 #else							/* WIN32 */
@@ -131,7 +235,7 @@ pg_clock_gettime_ns(void)
 
 /* Use QueryPerformanceCounter() */
 
-/* helper for INSTR_TIME_SET_CURRENT */
+/* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */
 static inline instr_time
 pg_query_performance_counter(void)
 {
@@ -153,6 +257,11 @@ GetTimerFrequency(void)
 	return (double) f.QuadPart;
 }
 
+#define INSTR_TIME_INITIALIZE()
+
+#define INSTR_TIME_SET_CURRENT_FAST(t) \
+	((t) = pg_query_performance_counter())
+
 #define INSTR_TIME_SET_CURRENT(t) \
 	((t) = pg_query_performance_counter())
 
@@ -168,13 +277,8 @@ GetTimerFrequency(void)
 
 #define INSTR_TIME_IS_ZERO(t)	((t).ticks == 0)
 
-
 #define INSTR_TIME_SET_ZERO(t)	((t).ticks = 0)
 
-#define INSTR_TIME_SET_CURRENT_LAZY(t) \
-	(INSTR_TIME_IS_ZERO(t) ? INSTR_TIME_SET_CURRENT(t), true : false)
-
-
 #define INSTR_TIME_ADD(x,y) \
 	((x).ticks += (y).ticks)
 
-- 
2.47.3


--vtqqtrpooseurzip
Content-Type: text/x-diff; charset=utf-8
Content-Disposition: attachment;
	filename="v12-0003-pg_test_timing-Add-fast-flag-to-test-fast-timing.patch"



^ permalink  raw  reply  [nested|flat] 271+ messages in thread

* [PATCH v12 2/3] Use time stamp counter to measure time on Linux/x86
@ 2025-07-26 00:57 Lukas Fittl <[email protected]>
  0 siblings, 0 replies; 271+ messages in thread

From: Lukas Fittl @ 2025-07-26 00:57 UTC (permalink / raw)

We switch to using the time stamp counter (TSC) instead of clock_gettime()
to reduce overhead of EXPLAIN (ANALYZE, TIME ON). Tests showed that runtime
is reduced by around 10% for queries moving lots of rows through the plan.

For now this is only enabled on Linux/x86, in case the system clocksource is
reported as TSC. Relying on the Linux kernel simplifies the logic to detect
if the present TSC is usable (frequency invariant, synchronized between
sockets, etc.). In all other cases we fallback to clock_gettime().

Note, that we intentionally use RDTSC in the fast paths, rather than RDTSCP.
RDTSCP waits for outstanding instructions to retire on out-of-order CPUs.
This adds noticably for little benefit in the typical InstrStartNode() /
InstrStopNode() use case. The macro to be used in such cases is called
INSTR_TIME_SET_CURRENT_FAST(). The original macro INSTR_TIME_SET_CURRENT()
uses RDTSCP and is supposed to be used when precision is more important
than performance.

Author: David Geier <[email protected]>
Author: Andres Freund <[email protected]>
Author: Lukas Fittl <[email protected]>
Reviewed-by:
Discussion: https://www.postgresql.org/message-id/flat/20200612232810.f46nbqkdhbutzqdg%40alap3.anarazel.de
---
 src/backend/access/heap/vacuumlazy.c |   4 +-
 src/backend/executor/instrument.c    |  12 +-
 src/backend/utils/init/postinit.c    |   3 +
 src/bin/pgbench/pgbench.c            |   3 +
 src/bin/psql/startup.c               |   4 +
 src/common/Makefile                  |   1 +
 src/common/instr_time.c              | 206 +++++++++++++++++++++++++++
 src/common/meson.build               |   1 +
 src/include/portability/instr_time.h | 136 +++++++++++++++---
 9 files changed, 348 insertions(+), 22 deletions(-)
 create mode 100644 src/common/instr_time.c

diff --git a/src/backend/access/heap/vacuumlazy.c b/src/backend/access/heap/vacuumlazy.c
index d2b031fdd06..5027048cac4 100644
--- a/src/backend/access/heap/vacuumlazy.c
+++ b/src/backend/access/heap/vacuumlazy.c
@@ -3409,8 +3409,8 @@ count_nondeletable_pages(LVRelState *vacrel, bool *lock_waiter_detected)
 			INSTR_TIME_SET_CURRENT(currenttime);
 			elapsed = currenttime;
 			INSTR_TIME_SUBTRACT(elapsed, starttime);
-			if ((INSTR_TIME_GET_MICROSEC(elapsed) / 1000)
-				>= VACUUM_TRUNCATE_LOCK_CHECK_INTERVAL)
+			if (INSTR_TIME_GET_MILLISEC(elapsed) >=
+				VACUUM_TRUNCATE_LOCK_CHECK_INTERVAL)
 			{
 				if (LockHasWaitersRelation(vacrel->rel, AccessExclusiveLock))
 				{
diff --git a/src/backend/executor/instrument.c b/src/backend/executor/instrument.c
index 56e635f4700..01f67c5d972 100644
--- a/src/backend/executor/instrument.c
+++ b/src/backend/executor/instrument.c
@@ -67,9 +67,13 @@ InstrInit(Instrumentation *instr, int instrument_options)
 void
 InstrStartNode(Instrumentation *instr)
 {
-	if (instr->need_timer &&
-		!INSTR_TIME_SET_CURRENT_LAZY(instr->starttime))
-		elog(ERROR, "InstrStartNode called twice in a row");
+	if (instr->need_timer)
+	{
+		if (!INSTR_TIME_IS_ZERO(instr->starttime))
+			elog(ERROR, "InstrStartNode called twice in a row");
+		else
+			INSTR_TIME_SET_CURRENT_FAST(instr->starttime);
+	}
 
 	/* save buffer usage totals at node entry, if needed */
 	if (instr->need_bufusage)
@@ -95,7 +99,7 @@ InstrStopNode(Instrumentation *instr, double nTuples)
 		if (INSTR_TIME_IS_ZERO(instr->starttime))
 			elog(ERROR, "InstrStopNode called without start");
 
-		INSTR_TIME_SET_CURRENT(endtime);
+		INSTR_TIME_SET_CURRENT_FAST(endtime);
 		INSTR_TIME_ACCUM_DIFF(instr->counter, endtime, instr->starttime);
 
 		INSTR_TIME_SET_ZERO(instr->starttime);
diff --git a/src/backend/utils/init/postinit.c b/src/backend/utils/init/postinit.c
index 641e535a73c..d573409903b 100644
--- a/src/backend/utils/init/postinit.c
+++ b/src/backend/utils/init/postinit.c
@@ -810,6 +810,9 @@ InitPostgres(const char *in_dbname, Oid dboid,
 	/* Initialize portal manager */
 	EnablePortalManager();
 
+	/* initialize high-precision interval timing */
+	INSTR_TIME_INITIALIZE();
+
 	/*
 	 * Load relcache entries for the shared system catalogs.  This must create
 	 * at least entries for pg_database and catalogs used for authentication.
diff --git a/src/bin/pgbench/pgbench.c b/src/bin/pgbench/pgbench.c
index 1515ed405ba..79bef2d2aec 100644
--- a/src/bin/pgbench/pgbench.c
+++ b/src/bin/pgbench/pgbench.c
@@ -7290,6 +7290,9 @@ main(int argc, char **argv)
 		initRandomState(&state[i].cs_func_rs);
 	}
 
+	/* initialize high-precision interval timing */
+	INSTR_TIME_INITIALIZE();
+
 	/* opening connection... */
 	con = doConnect();
 	if (con == NULL)
diff --git a/src/bin/psql/startup.c b/src/bin/psql/startup.c
index 249b6aa5169..d615df593c7 100644
--- a/src/bin/psql/startup.c
+++ b/src/bin/psql/startup.c
@@ -24,6 +24,7 @@
 #include "help.h"
 #include "input.h"
 #include "mainloop.h"
+#include "portability/instr_time.h"
 #include "settings.h"
 
 /*
@@ -327,6 +328,9 @@ main(int argc, char *argv[])
 
 	PQsetNoticeProcessor(pset.db, NoticeProcessor, NULL);
 
+	/* initialize high-precision interval timing */
+	INSTR_TIME_INITIALIZE();
+
 	SyncVariables();
 
 	if (options.list_dbs)
diff --git a/src/common/Makefile b/src/common/Makefile
index 2c720caa509..1a2fbbe887f 100644
--- a/src/common/Makefile
+++ b/src/common/Makefile
@@ -59,6 +59,7 @@ OBJS_COMMON = \
 	file_perm.o \
 	file_utils.o \
 	hashfn.o \
+	instr_time.o \
 	ip.o \
 	jsonapi.o \
 	keywords.o \
diff --git a/src/common/instr_time.c b/src/common/instr_time.c
new file mode 100644
index 00000000000..fdf47699f20
--- /dev/null
+++ b/src/common/instr_time.c
@@ -0,0 +1,206 @@
+/*-------------------------------------------------------------------------
+ *
+ * instr_time.c
+ *	   Non-inline parts of the portable high-precision interval timing
+ *	 implementation
+ *
+ * Portions Copyright (c) 2025, PostgreSQL Global Development Group
+ *
+ *
+ * IDENTIFICATION
+ *	  src/backend/port/instr_time.c
+ *
+ *-------------------------------------------------------------------------
+ */
+#include "postgres.h"
+
+#if defined(HAVE__GET_CPUID) || (defined(HAVE__CPUIDEX) && !defined(_MSC_VER))
+#include <cpuid.h>
+#endif
+
+#if defined(HAVE__CPUID) || (defined(HAVE__CPUIDEX) && defined(_MSC_VER))
+#include <intrin.h>
+#endif
+
+#include "portability/instr_time.h"
+
+#ifndef WIN32
+/*
+ * Stores what the number of cycles needs to be multiplied with to end up
+ * with nanoseconds using integer math. See comment in pg_initialize_rdtsc()
+ * for more details.
+ *
+ * By default assume we are using clock_gettime() as a fallback which uses
+ * nanoseconds as ticks. Hence, we set the multiplier to the precision scalar
+ * so that the division in INSTR_TIME_GET_NANOSEC() won't change the nanoseconds.
+ *
+ * When using the RDTSC instruction directly this is filled in during initialization
+ * based on the relevant CPUID fields.
+ */
+int64		ticks_per_ns_scaled = TICKS_TO_NS_PRECISION;
+int64		ticks_per_sec = NS_PER_S;
+int64		max_ticks_no_overflow = PG_INT64_MAX / TICKS_TO_NS_PRECISION;
+
+#if defined(__x86_64__) && defined(__linux__)
+/*
+ * Indicates if RDTSC can be used (Linux/x86 only, when OS uses TSC clocksource)
+ */
+bool		has_rdtsc = false;
+
+/*
+ * Indicates if RDTSCP can be used. True if RDTSC can be used and RDTSCP is available.
+ */
+bool		has_rdtscp = false;
+
+#define CPUID_HYPERVISOR_VMWARE(words) (words[1] == 0x61774d56 && words[2] == 0x4d566572 && words[3] == 0x65726177) /* VMwareVMware */
+#define CPUID_HYPERVISOR_KVM(words) (words[1] == 0x4b4d564b && words[2] == 0x564b4d56 && words[3] == 0x0000004d)	/* KVMKVMKVM */
+
+static bool
+get_tsc_frequency_khz(uint32 *tsc_freq)
+{
+	uint32		r[4] = {0, 0, 0, 0};
+
+#if defined(HAVE__GET_CPUID)
+	__get_cpuid(0x15, &r[0] /* denominator */ , &r[1] /* numerator */ , &r[2] /* hz */ , &r[3]);
+#elif defined(HAVE__CPUID)
+	__cpuid(r, 0x15);
+#else
+#error cpuid instruction not available
+#endif
+
+	if (r[2] > 0)
+	{
+		if (r[0] == 0 || r[1] == 0)
+			return false;
+
+		*tsc_freq = r[2] / 1000 * r[1] / r[0];
+		return true;
+	}
+
+	/* Some CPUs only report frequency in 16H */
+
+#if defined(HAVE__GET_CPUID)
+	__get_cpuid(0x16, &r[0] /* base_mhz */ , &r[1], &r[2], &r[3]);
+#elif defined(HAVE__CPUID)
+	__cpuid(r, 0x16);
+#else
+#error cpuid instruction not available
+#endif
+
+	if (r[0] > 0)
+	{
+		*tsc_freq = r[0] * 1000;
+		return true;
+	}
+
+	/*
+	 * Check if we have a KVM or VMware Hypervisor passing down TSC frequency
+	 * to us in a guest VM
+	 *
+	 * Note that accessing the 0x40000000 leaf for Hypervisor info requires
+	 * use of __cpuidex to set ECX to 0. The similar __get_cpuid_count
+	 * function does not work as expected since it contains a check for
+	 * __get_cpuid_max, which has been observed to be lower than the special
+	 * Hypervisor leaf.
+	 */
+#if defined(HAVE__CPUIDEX)
+	__cpuidex((int32 *) r, 0x40000000, 0);
+	if (r[0] >= 0x40000010 && (CPUID_HYPERVISOR_VMWARE(r) || CPUID_HYPERVISOR_KVM(r)))
+	{
+		__cpuidex((int32 *) r, 0x40000010, 0);
+		if (r[0] > 0)
+		{
+			*tsc_freq = r[0];
+			return true;
+		}
+	}
+#endif
+
+	return false;
+}
+
+static bool
+is_rdtscp_available()
+{
+	uint32		r[4] = {0, 0, 0, 0};
+
+#if defined(HAVE__GET_CPUID)
+	if (!__get_cpuid(0x80000001, &r[0], &r[1], &r[2], &r[3]))
+		return false;
+#elif defined(HAVE__CPUID)
+	__cpuid(r, 0x80000001);
+#else
+#error cpuid instruction not available
+#endif
+
+	return (r[3] & (1 << 27)) != 0;
+}
+
+/*
+ * Decide whether we use the RDTSC instruction at runtime, for Linux/x86,
+ * instead of incurring the overhead of a full clock_gettime() call.
+ *
+ * This can't be reliably determined at compile time, since the
+ * availability of an "invariant" TSC (that is not affected by CPU
+ * frequency changes) is dependent on the CPU architecture. Additionally,
+ * there are cases where TSC availability is impacted by virtualization,
+ * where a simple cpuid feature check would not be enough.
+ *
+ * Since Linux already does a significant amount of work to determine
+ * whether TSC is a viable clock source, decide based on that.
+ */
+void
+pg_initialize_rdtsc(void)
+{
+	FILE	   *fp = fopen("/sys/devices/system/clocksource/clocksource0/current_clocksource", "r");
+
+	if (fp)
+	{
+		char		buf[128];
+
+		if (fgets(buf, sizeof(buf), fp) != NULL && strcmp(buf, "tsc\n") == 0)
+		{
+			/*
+			 * Compute baseline CPU peformance, determines speed at which
+			 * RDTSC advances.
+			 */
+			uint32		tsc_freq;
+
+			if (get_tsc_frequency_khz(&tsc_freq))
+			{
+				/*
+				 * Ticks to nanoseconds conversion requires floating point
+				 * math because because:
+				 *
+				 * sec = ticks / frequency_hz ns  = ticks / frequency_hz *
+				 * 1,000,000,000 ns  = ticks * (1,000,000,000 / frequency_hz)
+				 * ns  = ticks * (1,000,000 / frequency_khz) <-- now in
+				 * kilohertz
+				 *
+				 * Here, 'ns' is usually a floating number. For example for a
+				 * 2.5 GHz CPU the scaling factor becomes 1,000,000 /
+				 * 2,500,000 = 1.2.
+				 *
+				 * To be able to use integer math we work around the lack of
+				 * precision. We first scale the integer up and after the
+				 * multiplication by the number of ticks in
+				 * INSTR_TIME_GET_NANOSEC() we divide again by the same value.
+				 * We picked the scaler such that it provides enough precision
+				 * and is a power-of-two which allows for shifting instead of
+				 * doing an integer division.
+				 */
+				ticks_per_ns_scaled = INT64CONST(1000000) * TICKS_TO_NS_PRECISION / tsc_freq;
+				ticks_per_sec = tsc_freq * 1000;	/* KHz->Hz */
+				max_ticks_no_overflow = PG_INT64_MAX / ticks_per_ns_scaled;
+
+				has_rdtsc = true;
+				has_rdtscp = is_rdtscp_available();
+			}
+		}
+
+		fclose(fp);
+	}
+}
+#endif							/* defined(__x86_64__) && defined(__linux__) */
+
+#endif							/* WIN32 */
diff --git a/src/common/meson.build b/src/common/meson.build
index 1540ba67cca..62b90b3e609 100644
--- a/src/common/meson.build
+++ b/src/common/meson.build
@@ -13,6 +13,7 @@ common_sources = files(
   'file_perm.c',
   'file_utils.c',
   'hashfn.c',
+  'instr_time.c',
   'ip.c',
   'jsonapi.c',
   'keywords.c',
diff --git a/src/include/portability/instr_time.h b/src/include/portability/instr_time.h
index f71a851b18d..e2e339a0c4f 100644
--- a/src/include/portability/instr_time.h
+++ b/src/include/portability/instr_time.h
@@ -4,9 +4,11 @@
  *	  portable high-precision interval timing
  *
  * This file provides an abstraction layer to hide portability issues in
- * interval timing.  On Unix we use clock_gettime(), and on Windows we use
- * QueryPerformanceCounter().  These macros also give some breathing room to
- * use other high-precision-timing APIs.
+ * interval timing. On Linux/x86 we use the rdtsc instruction when a TSC
+ * clocksource is also used on the host OS.  Otherwise, and on other
+ * Unix-like systems we use clock_gettime() and on Windows we use
+ * QueryPerformanceCounter(). These macros also give some breathing
+ * room to use other high-precision-timing APIs.
  *
  * The basic data type is instr_time, which all callers should treat as an
  * opaque typedef.  instr_time can store either an absolute time (of
@@ -17,10 +19,11 @@
  *
  * INSTR_TIME_SET_ZERO(t)			set t to zero (memset is acceptable too)
  *
- * INSTR_TIME_SET_CURRENT(t)		set t to current time
+ * INSTR_TIME_SET_CURRENT_FAST(t)	set t to current time without waiting
+ * 									for instructions in out-of-order window
  *
- * INSTR_TIME_SET_CURRENT_LAZY(t)	set t to current time if t is zero,
- *									evaluates to whether t changed
+ * INSTR_TIME_SET_CURRENT(t)		set t to current time while waiting for
+ * 									instructions in OOO to retire
  *
  * INSTR_TIME_ADD(x, y)				x += y
  *
@@ -81,6 +84,15 @@ typedef struct instr_time
 
 #ifndef WIN32
 
+/*
+ * Make sure this is a power-of-two, so that the compiler can turn the
+ * multiplications and divisions into shifts.
+ */
+#define TICKS_TO_NS_PRECISION (1<<14)
+
+extern int64 ticks_per_ns_scaled;
+extern int64 ticks_per_sec;
+extern int64 max_ticks_no_overflow;
 
 /* Use clock_gettime() */
 
@@ -106,9 +118,18 @@ typedef struct instr_time
 #define PG_INSTR_CLOCK	CLOCK_REALTIME
 #endif
 
-/* helper for INSTR_TIME_SET_CURRENT */
+#if defined(__x86_64__) && defined(__linux__)
+#include <x86intrin.h>
+#include <cpuid.h>
+
+extern bool has_rdtsc;
+extern bool has_rdtscp;
+
+extern void pg_initialize_rdtsc(void);
+#endif
+
 static inline instr_time
-pg_clock_gettime_ns(void)
+pg_clock_gettime(void)
 {
 	instr_time	now;
 	struct timespec tmp;
@@ -119,11 +140,94 @@ pg_clock_gettime_ns(void)
 	return now;
 }
 
+static inline instr_time
+pg_get_ticks_fast(void)
+{
+#if defined(__x86_64__) && defined(__linux__)
+	if (has_rdtsc)
+	{
+		instr_time	now;
+
+		now.ticks = __rdtsc();
+		return now;
+	}
+#endif
+
+	return pg_clock_gettime();
+}
+
+static inline instr_time
+pg_get_ticks(void)
+{
+#if defined(__x86_64__) && defined(__linux__)
+	if (has_rdtscp)
+	{
+		instr_time	now;
+		uint32		unused;
+
+		now.ticks = __rdtscp(&unused);
+		return now;
+	}
+#endif
+
+	return pg_clock_gettime();
+}
+
+static inline int64_t
+pg_ticks_to_ns(instr_time t)
+{
+	/*
+	 * Would multiplication overflow? If so perform computation in two parts.
+	 * Check overflow without actually overflowing via: a * b > max <=> a >
+	 * max / b
+	 */
+	int64		ns = 0;
+
+	if (unlikely(t.ticks > max_ticks_no_overflow))
+	{
+		/*
+		 * Compute how often the maximum number of ticks fits completely into
+		 * the number of elapsed ticks and convert that number into
+		 * nanoseconds. Then multiply by the count to arrive at the final
+		 * 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		max_ns = max_ticks_no_overflow * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION;
+
+		ns = max_ns * count;
+
+		/*
+		 * 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);
+	}
+
+	ns += t.ticks * ticks_per_ns_scaled / TICKS_TO_NS_PRECISION;
+	return ns;
+}
+
+static inline void
+pg_initialize_get_ticks()
+{
+#if defined(__x86_64__) && defined(__linux__)
+	pg_initialize_rdtsc();
+#endif
+}
+
+#define INSTR_TIME_INITIALIZE() \
+	pg_initialize_get_ticks()
+
+#define INSTR_TIME_SET_CURRENT_FAST(t) \
+	((t) = pg_get_ticks_fast())
+
 #define INSTR_TIME_SET_CURRENT(t) \
-	((t) = pg_clock_gettime_ns())
+	((t) = pg_get_ticks())
 
 #define INSTR_TIME_GET_NANOSEC(t) \
-	((int64) (t).ticks)
+	pg_ticks_to_ns(t)
 
 
 #else							/* WIN32 */
@@ -131,7 +235,7 @@ pg_clock_gettime_ns(void)
 
 /* Use QueryPerformanceCounter() */
 
-/* helper for INSTR_TIME_SET_CURRENT */
+/* helper for INSTR_TIME_SET_CURRENT / INSTR_TIME_SET_CURRENT_FAST */
 static inline instr_time
 pg_query_performance_counter(void)
 {
@@ -153,6 +257,11 @@ GetTimerFrequency(void)
 	return (double) f.QuadPart;
 }
 
+#define INSTR_TIME_INITIALIZE()
+
+#define INSTR_TIME_SET_CURRENT_FAST(t) \
+	((t) = pg_query_performance_counter())
+
 #define INSTR_TIME_SET_CURRENT(t) \
 	((t) = pg_query_performance_counter())
 
@@ -168,13 +277,8 @@ GetTimerFrequency(void)
 
 #define INSTR_TIME_IS_ZERO(t)	((t).ticks == 0)
 
-
 #define INSTR_TIME_SET_ZERO(t)	((t).ticks = 0)
 
-#define INSTR_TIME_SET_CURRENT_LAZY(t) \
-	(INSTR_TIME_IS_ZERO(t) ? INSTR_TIME_SET_CURRENT(t), true : false)
-
-
 #define INSTR_TIME_ADD(x,y) \
 	((x).ticks += (y).ticks)
 
-- 
2.47.3


--vtqqtrpooseurzip
Content-Type: text/x-diff; charset=utf-8
Content-Disposition: attachment;
	filename="v12-0003-pg_test_timing-Add-fast-flag-to-test-fast-timing.patch"



^ permalink  raw  reply  [nested|flat] 271+ messages in thread